diff options
1541 files changed, 26878 insertions, 16887 deletions
@@ -28,6 +28,7 @@ modules.builtin *.gz *.bz2 *.lzma +*.xz *.lzo *.patch *.gcno diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl index 2861055..c279158 100644 --- a/Documentation/DocBook/drm.tmpl +++ b/Documentation/DocBook/drm.tmpl @@ -73,8 +73,8 @@ services. </para> <para> - The core of every DRM driver is struct drm_device. Drivers - will typically statically initialize a drm_device structure, + The core of every DRM driver is struct drm_driver. Drivers + will typically statically initialize a drm_driver structure, then pass it to drm_init() at load time. </para> @@ -84,7 +84,7 @@ <title>Driver initialization</title> <para> Before calling the DRM initialization routines, the driver must - first create and fill out a struct drm_device structure. + first create and fill out a struct drm_driver structure. </para> <programlisting> static struct drm_driver driver = { diff --git a/Documentation/DocBook/filesystems.tmpl b/Documentation/DocBook/filesystems.tmpl index 5e87ad5..f51f285 100644 --- a/Documentation/DocBook/filesystems.tmpl +++ b/Documentation/DocBook/filesystems.tmpl @@ -82,6 +82,11 @@ </sect1> </chapter> + <chapter id="fs_events"> + <title>Events based on file descriptors</title> +!Efs/eventfd.c + </chapter> + <chapter id="sysfs"> <title>The Filesystem for Exporting Kernel Objects</title> !Efs/sysfs/file.c diff --git a/Documentation/powerpc/dts-bindings/fsl/sata.txt b/Documentation/devicetree/bindings/ata/fsl-sata.txt index b46bcf4..b46bcf4 100644 --- a/Documentation/powerpc/dts-bindings/fsl/sata.txt +++ b/Documentation/devicetree/bindings/ata/fsl-sata.txt diff --git a/Documentation/powerpc/dts-bindings/eeprom.txt b/Documentation/devicetree/bindings/eeprom.txt index 4342c10..4342c10 100644 --- a/Documentation/powerpc/dts-bindings/eeprom.txt +++ b/Documentation/devicetree/bindings/eeprom.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt b/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt index b0019eb..b0019eb 100644 --- a/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt +++ b/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt diff --git a/Documentation/powerpc/dts-bindings/gpio/gpio.txt b/Documentation/devicetree/bindings/gpio/gpio.txt index edaa84d..edaa84d 100644 --- a/Documentation/powerpc/dts-bindings/gpio/gpio.txt +++ b/Documentation/devicetree/bindings/gpio/gpio.txt diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/devicetree/bindings/gpio/led.txt index 064db92..064db92 100644 --- a/Documentation/powerpc/dts-bindings/gpio/led.txt +++ b/Documentation/devicetree/bindings/gpio/led.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/devicetree/bindings/i2c/fsl-i2c.txt index 1eacd6b..1eacd6b 100644 --- a/Documentation/powerpc/dts-bindings/fsl/i2c.txt +++ b/Documentation/devicetree/bindings/i2c/fsl-i2c.txt diff --git a/Documentation/powerpc/dts-bindings/marvell.txt b/Documentation/devicetree/bindings/marvell.txt index f1533d9..f1533d9 100644 --- a/Documentation/powerpc/dts-bindings/marvell.txt +++ b/Documentation/devicetree/bindings/marvell.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt index 64bcb8b..64bcb8b 100644 --- a/Documentation/powerpc/dts-bindings/fsl/esdhc.txt +++ b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt diff --git a/Documentation/powerpc/dts-bindings/mmc-spi-slot.txt b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt index c39ac28..c39ac28 100644 --- a/Documentation/powerpc/dts-bindings/mmc-spi-slot.txt +++ b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt b/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt index a48b2ca..a48b2ca 100644 --- a/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt +++ b/Documentation/devicetree/bindings/mtd/fsl-upm-nand.txt diff --git a/Documentation/powerpc/dts-bindings/mtd-physmap.txt b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt index 80152cb..80152cb 100644 --- a/Documentation/powerpc/dts-bindings/mtd-physmap.txt +++ b/Documentation/devicetree/bindings/mtd/mtd-physmap.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/can.txt b/Documentation/devicetree/bindings/net/can/mpc5xxx-mscan.txt index 2fa4fcd..2fa4fcd 100644 --- a/Documentation/powerpc/dts-bindings/fsl/can.txt +++ b/Documentation/devicetree/bindings/net/can/mpc5xxx-mscan.txt diff --git a/Documentation/powerpc/dts-bindings/can/sja1000.txt b/Documentation/devicetree/bindings/net/can/sja1000.txt index d6d209d..d6d209d 100644 --- a/Documentation/powerpc/dts-bindings/can/sja1000.txt +++ b/Documentation/devicetree/bindings/net/can/sja1000.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/tsec.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index edb7ae1..edb7ae1 100644 --- a/Documentation/powerpc/dts-bindings/fsl/tsec.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt diff --git a/Documentation/powerpc/dts-bindings/gpio/mdio.txt b/Documentation/devicetree/bindings/net/mdio-gpio.txt index bc954952..bc954952 100644 --- a/Documentation/powerpc/dts-bindings/gpio/mdio.txt +++ b/Documentation/devicetree/bindings/net/mdio-gpio.txt diff --git a/Documentation/powerpc/dts-bindings/phy.txt b/Documentation/devicetree/bindings/net/phy.txt index bb8c742..bb8c742 100644 --- a/Documentation/powerpc/dts-bindings/phy.txt +++ b/Documentation/devicetree/bindings/net/phy.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/83xx-512x-pci.txt b/Documentation/devicetree/bindings/pci/83xx-512x-pci.txt index 35a4653..35a4653 100644 --- a/Documentation/powerpc/dts-bindings/fsl/83xx-512x-pci.txt +++ b/Documentation/devicetree/bindings/pci/83xx-512x-pci.txt diff --git a/Documentation/powerpc/dts-bindings/4xx/cpm.txt b/Documentation/devicetree/bindings/powerpc/4xx/cpm.txt index ee45980..ee45980 100644 --- a/Documentation/powerpc/dts-bindings/4xx/cpm.txt +++ b/Documentation/devicetree/bindings/powerpc/4xx/cpm.txt diff --git a/Documentation/powerpc/dts-bindings/4xx/emac.txt b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt index 2161334a..2161334a 100644 --- a/Documentation/powerpc/dts-bindings/4xx/emac.txt +++ b/Documentation/devicetree/bindings/powerpc/4xx/emac.txt diff --git a/Documentation/powerpc/dts-bindings/4xx/ndfc.txt b/Documentation/devicetree/bindings/powerpc/4xx/ndfc.txt index 869f0b5..869f0b5 100644 --- a/Documentation/powerpc/dts-bindings/4xx/ndfc.txt +++ b/Documentation/devicetree/bindings/powerpc/4xx/ndfc.txt diff --git a/Documentation/powerpc/dts-bindings/4xx/ppc440spe-adma.txt b/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt index 515ebcf..515ebcf 100644 --- a/Documentation/powerpc/dts-bindings/4xx/ppc440spe-adma.txt +++ b/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt diff --git a/Documentation/powerpc/dts-bindings/4xx/reboot.txt b/Documentation/devicetree/bindings/powerpc/4xx/reboot.txt index d721726..d721726 100644 --- a/Documentation/powerpc/dts-bindings/4xx/reboot.txt +++ b/Documentation/devicetree/bindings/powerpc/4xx/reboot.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/devicetree/bindings/powerpc/fsl/board.txt index 39e9415..39e9415 100644 --- a/Documentation/powerpc/dts-bindings/fsl/board.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/board.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm.txt index 160c752..160c752 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/brg.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/brg.txt index 4c7d45e..4c7d45e 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/brg.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/brg.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/i2c.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/i2c.txt index 87bc604..87bc604 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/i2c.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/i2c.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/pic.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/pic.txt index 8e3ee16..8e3ee16 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/pic.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/pic.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/usb.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/usb.txt index 74bfda4..74bfda4 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/cpm/usb.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/cpm/usb.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/gpio.txt index 349f79f..349f79f 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/gpio.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/network.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/network.txt index 0e42694..0e42694 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/network.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/network.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe.txt index 4f89302..4f89302 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/firmware.txt index 249db3a..249db3a 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/firmware.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/par_io.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/par_io.txt index 6098426..6098426 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/par_io.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/par_io.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/pincfg.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/pincfg.txt index c5b4306..c5b4306 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/pincfg.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/pincfg.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/ucc.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/ucc.txt index e47734b..e47734b 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/ucc.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/ucc.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/usb.txt index 9ccd5f3..9ccd5f3 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/qe/usb.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/serial.txt index 2ea76d9..2ea76d9 100644 --- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/cpm_qe/serial.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/diu.txt b/Documentation/devicetree/bindings/powerpc/fsl/diu.txt index b66cb6d..b66cb6d 100644 --- a/Documentation/powerpc/dts-bindings/fsl/diu.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/diu.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt index 2a4b4bc..2a4b4bc 100644 --- a/Documentation/powerpc/dts-bindings/fsl/dma.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt diff --git a/Documentation/powerpc/dts-bindings/ecm.txt b/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt index f514f29..f514f29 100644 --- a/Documentation/powerpc/dts-bindings/ecm.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/gtm.txt b/Documentation/devicetree/bindings/powerpc/fsl/gtm.txt index 9a33efd..9a33efd 100644 --- a/Documentation/powerpc/dts-bindings/fsl/gtm.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/gtm.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/guts.txt b/Documentation/devicetree/bindings/powerpc/fsl/guts.txt index 9e7a241..9e7a241 100644 --- a/Documentation/powerpc/dts-bindings/fsl/guts.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/guts.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/lbc.txt b/Documentation/devicetree/bindings/powerpc/fsl/lbc.txt index 3300fec..3300fec 100644 --- a/Documentation/powerpc/dts-bindings/fsl/lbc.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/lbc.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/mcm.txt b/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt index 4ceda9b..4ceda9b 100644 --- a/Documentation/powerpc/dts-bindings/fsl/mcm.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt b/Documentation/devicetree/bindings/powerpc/fsl/mcu-mpc8349emitx.txt index 0f76633..0f76633 100644 --- a/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/mcu-mpc8349emitx.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt index 8832e87..8832e87 100644 --- a/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt index 4ccb2cd..4ccb2cd 100644 --- a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5200.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/mpic.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpic.txt index 71e39cf..71e39cf 100644 --- a/Documentation/powerpc/dts-bindings/fsl/mpic.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/mpic.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt index bcc30ba..bcc30ba 100644 --- a/Documentation/powerpc/dts-bindings/fsl/msi-pic.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/pmc.txt b/Documentation/devicetree/bindings/powerpc/fsl/pmc.txt index 07256b7..07256b7 100644 --- a/Documentation/powerpc/dts-bindings/fsl/pmc.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/pmc.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/sec.txt b/Documentation/devicetree/bindings/powerpc/fsl/sec.txt index 2b6f2d4..2b6f2d4 100644 --- a/Documentation/powerpc/dts-bindings/fsl/sec.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/sec.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/ssi.txt b/Documentation/devicetree/bindings/powerpc/fsl/ssi.txt index 5ff76c9..5ff76c9 100644 --- a/Documentation/powerpc/dts-bindings/fsl/ssi.txt +++ b/Documentation/devicetree/bindings/powerpc/fsl/ssi.txt diff --git a/Documentation/powerpc/dts-bindings/nintendo/gamecube.txt b/Documentation/devicetree/bindings/powerpc/nintendo/gamecube.txt index b558585..b558585 100644 --- a/Documentation/powerpc/dts-bindings/nintendo/gamecube.txt +++ b/Documentation/devicetree/bindings/powerpc/nintendo/gamecube.txt diff --git a/Documentation/powerpc/dts-bindings/nintendo/wii.txt b/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt index a7e155a..a7e155a 100644 --- a/Documentation/powerpc/dts-bindings/nintendo/wii.txt +++ b/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/devicetree/bindings/spi/fsl-spi.txt index 777abd7..777abd7 100644 --- a/Documentation/powerpc/dts-bindings/fsl/spi.txt +++ b/Documentation/devicetree/bindings/spi/fsl-spi.txt diff --git a/Documentation/powerpc/dts-bindings/spi-bus.txt b/Documentation/devicetree/bindings/spi/spi-bus.txt index e782add..e782add 100644 --- a/Documentation/powerpc/dts-bindings/spi-bus.txt +++ b/Documentation/devicetree/bindings/spi/spi-bus.txt diff --git a/Documentation/powerpc/dts-bindings/fsl/usb.txt b/Documentation/devicetree/bindings/usb/fsl-usb.txt index bd5723f..bd5723f 100644 --- a/Documentation/powerpc/dts-bindings/fsl/usb.txt +++ b/Documentation/devicetree/bindings/usb/fsl-usb.txt diff --git a/Documentation/powerpc/dts-bindings/usb-ehci.txt b/Documentation/devicetree/bindings/usb/usb-ehci.txt index fa18612..fa18612 100644 --- a/Documentation/powerpc/dts-bindings/usb-ehci.txt +++ b/Documentation/devicetree/bindings/usb/usb-ehci.txt diff --git a/Documentation/powerpc/dts-bindings/xilinx.txt b/Documentation/devicetree/bindings/xilinx.txt index 299d0923..299d0923 100644 --- a/Documentation/powerpc/dts-bindings/xilinx.txt +++ b/Documentation/devicetree/bindings/xilinx.txt diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/devicetree/booting-without-of.txt index 7400d75..28b1c9d 100644 --- a/Documentation/powerpc/booting-without-of.txt +++ b/Documentation/devicetree/booting-without-of.txt @@ -13,7 +13,6 @@ Table of Contents I - Introduction 1) Entry point for arch/powerpc - 2) Board support II - The DT block format 1) Header @@ -41,13 +40,6 @@ Table of Contents VI - System-on-a-chip devices and nodes 1) Defining child nodes of an SOC 2) Representing devices without a current OF specification - a) PHY nodes - b) Interrupt controllers - c) 4xx/Axon EMAC ethernet nodes - d) Xilinx IP cores - e) USB EHCI controllers - f) MDIO on GPIOs - g) SPI busses VII - Specifying interrupt information for devices 1) interrupts property @@ -123,7 +115,7 @@ Revision Information I - Introduction ================ -During the recent development of the Linux/ppc64 kernel, and more +During the development of the Linux/ppc64 kernel, and more specifically, the addition of new platform types outside of the old IBM pSeries/iSeries pair, it was decided to enforce some strict rules regarding the kernel entry and bootloader <-> kernel interfaces, in @@ -146,7 +138,7 @@ section III, but, for example, the kernel does not require you to create a node for every PCI device in the system. It is a requirement to have a node for PCI host bridges in order to provide interrupt routing informations and memory/IO ranges, among others. It is also -recommended to define nodes for on chip devices and other busses that +recommended to define nodes for on chip devices and other buses that don't specifically fit in an existing OF specification. This creates a great flexibility in the way the kernel can then probe those and match drivers to device, without having to hard code all sorts of tables. It @@ -158,7 +150,7 @@ it with special cases. 1) Entry point for arch/powerpc ------------------------------- - There is one and one single entry point to the kernel, at the start + There is one single entry point to the kernel, at the start of the kernel image. That entry point supports two calling conventions: @@ -210,12 +202,6 @@ it with special cases. with all CPUs. The way to do that with method b) will be described in a later revision of this document. - -2) Board support ----------------- - -64-bit kernels: - Board supports (platforms) are not exclusive config options. An arbitrary set of board supports can be built in a single kernel image. The kernel will "know" what set of functions to use for a @@ -234,48 +220,11 @@ it with special cases. containing the various callbacks that the generic code will use to get to your platform specific code - c) Add a reference to your "ppc_md" structure in the - "machines" table in arch/powerpc/kernel/setup_64.c if you are - a 64-bit platform. - - d) request and get assigned a platform number (see PLATFORM_* - constants in arch/powerpc/include/asm/processor.h - -32-bit embedded kernels: - - Currently, board support is essentially an exclusive config option. - The kernel is configured for a single platform. Part of the reason - for this is to keep kernels on embedded systems small and efficient; - part of this is due to the fact the code is already that way. In the - future, a kernel may support multiple platforms, but only if the + A kernel image may support multiple platforms, but only if the platforms feature the same core architecture. A single kernel build cannot support both configurations with Book E and configurations with classic Powerpc architectures. - 32-bit embedded platforms that are moved into arch/powerpc using a - flattened device tree should adopt the merged tree practice of - setting ppc_md up dynamically, even though the kernel is currently - built with support for only a single platform at a time. This allows - unification of the setup code, and will make it easier to go to a - multiple-platform-support model in the future. - -NOTE: I believe the above will be true once Ben's done with the merge -of the boot sequences.... someone speak up if this is wrong! - - To add a 32-bit embedded platform support, follow the instructions - for 64-bit platforms above, with the exception that the Kconfig - option should be set up such that the kernel builds exclusively for - the platform selected. The processor type for the platform should - enable another config option to select the specific board - supported. - -NOTE: If Ben doesn't merge the setup files, may need to change this to -point to setup_32.c - - - I will describe later the boot process and various callbacks that - your platform should implement. - II - The DT block format ======================== @@ -300,8 +249,8 @@ the block to RAM before passing it to the kernel. 1) Header --------- - The kernel is entered with r3 pointing to an area of memory that is - roughly described in arch/powerpc/include/asm/prom.h by the structure + The kernel is passed the physical address pointing to an area of memory + that is roughly described in include/linux/of_fdt.h by the structure boot_param_header: struct boot_param_header { @@ -339,7 +288,7 @@ struct boot_param_header { All values in this header are in big endian format, the various fields in this header are defined more precisely below. All "offset" values are in bytes from the start of the header; that is - from the value of r3. + from the physical base address of the device tree block. - magic @@ -437,7 +386,7 @@ struct boot_param_header { ------------------------------ - r3 -> | struct boot_param_header | + base -> | struct boot_param_header | ------------------------------ | (alignment gap) (*) | ------------------------------ @@ -457,7 +406,7 @@ struct boot_param_header { -----> ------------------------------ | | - --- (r3 + totalsize) + --- (base + totalsize) (*) The alignment gaps are not necessarily present; their presence and size are dependent on the various alignment requirements of @@ -500,7 +449,7 @@ the device-tree structure. It is typically used to represent "path" in the device-tree. More details about the actual format of these will be below. -The kernel powerpc generic code does not make any formal use of the +The kernel generic code does not make any formal use of the unit address (though some board support code may do) so the only real requirement here for the unit address is to ensure uniqueness of the node unit name at a given level of the tree. Nodes with no notion @@ -518,20 +467,21 @@ path to the root node is "/". Every node which actually represents an actual device (that is, a node which isn't only a virtual "container" for more nodes, like "/cpus" -is) is also required to have a "device_type" property indicating the -type of node . +is) is also required to have a "compatible" property indicating the +specific hardware and an optional list of devices it is fully +backwards compatible with. Finally, every node that can be referenced from a property in another -node is required to have a "linux,phandle" property. Real open -firmware implementations provide a unique "phandle" value for every -node that the "prom_init()" trampoline code turns into -"linux,phandle" properties. However, this is made optional if the -flattened device tree is used directly. An example of a node +node is required to have either a "phandle" or a "linux,phandle" +property. Real Open Firmware implementations provide a unique +"phandle" value for every node that the "prom_init()" trampoline code +turns into "linux,phandle" properties. However, this is made optional +if the flattened device tree is used directly. An example of a node referencing another node via "phandle" is when laying out the interrupt tree which will be described in a further version of this document. -This "linux, phandle" property is a 32-bit value that uniquely +The "phandle" property is a 32-bit value that uniquely identifies a node. You are free to use whatever values or system of values, internal pointers, or whatever to generate these, the only requirement is that every node for which you provide that property has @@ -694,7 +644,7 @@ made of 3 cells, the bottom two containing the actual address itself while the top cell contains address space indication, flags, and pci bus & device numbers. -For busses that support dynamic allocation, it's the accepted practice +For buses that support dynamic allocation, it's the accepted practice to then not provide the address in "reg" (keep it 0) though while providing a flag indicating the address is dynamically allocated, and then, to provide a separate "assigned-addresses" property that @@ -711,7 +661,7 @@ prom_parse.c file of the recent kernels for your bus type. The "reg" property only defines addresses and sizes (if #size-cells is non-0) within a given bus. In order to translate addresses upward (that is into parent bus addresses, and possibly into CPU physical -addresses), all busses must contain a "ranges" property. If the +addresses), all buses must contain a "ranges" property. If the "ranges" property is missing at a given level, it's assumed that translation isn't possible, i.e., the registers are not visible on the parent bus. The format of the "ranges" property for a bus is a list @@ -727,9 +677,9 @@ example, for a PCI host controller, that would be a CPU address. For a PCI<->ISA bridge, that would be a PCI address. It defines the base address in the parent bus where the beginning of that range is mapped. -For a new 64-bit powerpc board, I recommend either the 2/2 format or +For new 64-bit board support, I recommend either the 2/2 format or Apple's 2/1 format which is slightly more compact since sizes usually -fit in a single 32-bit word. New 32-bit powerpc boards should use a +fit in a single 32-bit word. New 32-bit board support should use a 1/1 format, unless the processor supports physical addresses greater than 32-bits, in which case a 2/1 format is recommended. @@ -754,7 +704,7 @@ of their actual names. While earlier users of Open Firmware like OldWorld macintoshes tended to use the actual device name for the "name" property, it's nowadays considered a good practice to use a name that is closer to the device -class (often equal to device_type). For example, nowadays, ethernet +class (often equal to device_type). For example, nowadays, Ethernet controllers are named "ethernet", an additional "model" property defining precisely the chip type/model, and "compatible" property defining the family in case a single driver can driver more than one @@ -772,7 +722,7 @@ is present). 4) Note about node and property names and character set ------------------------------------------------------- -While open firmware provides more flexible usage of 8859-1, this +While Open Firmware provides more flexible usage of 8859-1, this specification enforces more strict rules. Nodes and properties should be comprised only of ASCII characters 'a' to 'z', '0' to '9', ',', '.', '_', '+', '#', '?', and '-'. Node names additionally @@ -792,7 +742,7 @@ address which can extend beyond that limit. -------------------------------- These are all that are currently required. However, it is strongly recommended that you expose PCI host bridges as documented in the - PCI binding to open firmware, and your interrupt tree as documented + PCI binding to Open Firmware, and your interrupt tree as documented in OF interrupt tree specification. a) The root node @@ -802,20 +752,12 @@ address which can extend beyond that limit. - model : this is your board name/model - #address-cells : address representation for "root" devices - #size-cells: the size representation for "root" devices - - device_type : This property shouldn't be necessary. However, if - you decide to create a device_type for your root node, make sure it - is _not_ "chrp" unless your platform is a pSeries or PAPR compliant - one for 64-bit, or a CHRP-type machine for 32-bit as this will - matched by the kernel this way. - - Additionally, some recommended properties are: - - compatible : the board "family" generally finds its way here, for example, if you have 2 board models with a similar layout, that typically get driven by the same platform code in the - kernel, you would use a different "model" property but put a - value in "compatible". The kernel doesn't directly use that - value but it is generally useful. + kernel, you would specify the exact board model in the + compatible property followed by an entry that represents the SoC + model. The root node is also generally where you add additional properties specific to your board like the serial number if any, that sort of @@ -841,8 +783,11 @@ address which can extend beyond that limit. So under /cpus, you are supposed to create a node for every CPU on the machine. There is no specific restriction on the name of the - CPU, though It's common practice to call it PowerPC,<name>. For + CPU, though it's common to call it <architecture>,<core>. For example, Apple uses PowerPC,G5 while IBM uses PowerPC,970FX. + However, the Generic Names convention suggests that it would be + better to simply use 'cpu' for each cpu node and use the compatible + property to identify the specific cpu core. Required properties: @@ -923,7 +868,7 @@ compatibility. e) The /chosen node - This node is a bit "special". Normally, that's where open firmware + This node is a bit "special". Normally, that's where Open Firmware puts some variable environment information, like the arguments, or the default input/output devices. @@ -940,11 +885,7 @@ compatibility. console device if any. Typically, if you have serial devices on your board, you may want to put the full path to the one set as the default console in the firmware here, for the kernel to pick - it up as its own default console. If you look at the function - set_preferred_console() in arch/ppc64/kernel/setup.c, you'll see - that the kernel tries to find out the default console and has - knowledge of various types like 8250 serial ports. You may want - to extend this function to add your own. + it up as its own default console. Note that u-boot creates and fills in the chosen node for platforms that use it. @@ -955,23 +896,23 @@ compatibility. f) the /soc<SOCname> node - This node is used to represent a system-on-a-chip (SOC) and must be - present if the processor is a SOC. The top-level soc node contains - information that is global to all devices on the SOC. The node name - should contain a unit address for the SOC, which is the base address - of the memory-mapped register set for the SOC. The name of an soc + This node is used to represent a system-on-a-chip (SoC) and must be + present if the processor is a SoC. The top-level soc node contains + information that is global to all devices on the SoC. The node name + should contain a unit address for the SoC, which is the base address + of the memory-mapped register set for the SoC. The name of an SoC node should start with "soc", and the remainder of the name should represent the part number for the soc. For example, the MPC8540's soc node would be called "soc8540". Required properties: - - device_type : Should be "soc" - ranges : Should be defined as specified in 1) to describe the - translation of SOC addresses for memory mapped SOC registers. - - bus-frequency: Contains the bus frequency for the SOC node. + translation of SoC addresses for memory mapped SoC registers. + - bus-frequency: Contains the bus frequency for the SoC node. Typically, the value of this field is filled in by the boot loader. + - compatible : Exact model of the SoC Recommended properties: @@ -1155,12 +1096,13 @@ while all this has been defined and implemented. - An example of code for iterating nodes & retrieving properties directly from the flattened tree format can be found in the kernel - file arch/ppc64/kernel/prom.c, look at scan_flat_dt() function, + file drivers/of/fdt.c. Look at the of_scan_flat_dt() function, its usage in early_init_devtree(), and the corresponding various early_init_dt_scan_*() callbacks. That code can be re-used in a GPL bootloader, and as the author of that code, I would be happy to discuss possible free licensing to any vendor who wishes to integrate all or part of this code into a non-GPL bootloader. + (reference needed; who is 'I' here? ---gcl Jan 31, 2011) @@ -1203,18 +1145,19 @@ MPC8540. 2) Representing devices without a current OF specification ---------------------------------------------------------- -Currently, there are many devices on SOCs that do not have a standard -representation pre-defined as part of the open firmware -specifications, mainly because the boards that contain these SOCs are -not currently booted using open firmware. This section contains -descriptions for the SOC devices for which new nodes have been -defined; this list will expand as more and more SOC-containing -platforms are moved over to use the flattened-device-tree model. +Currently, there are many devices on SoCs that do not have a standard +representation defined as part of the Open Firmware specifications, +mainly because the boards that contain these SoCs are not currently +booted using Open Firmware. Binding documentation for new devices +should be added to the Documentation/devicetree/bindings directory. +That directory will expand as device tree support is added to more and +more SoCs. + VII - Specifying interrupt information for devices =================================================== -The device tree represents the busses and devices of a hardware +The device tree represents the buses and devices of a hardware system in a form similar to the physical bus topology of the hardware. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index b959659..b3f35e5 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -603,3 +603,19 @@ Why: The adm9240, w83792d and w83793 hardware monitoring drivers have Who: Jean Delvare <khali@linux-fr.org> ---------------------------- + +What: noswapaccount kernel command line parameter +When: 2.6.40 +Why: The original implementation of memsw feature enabled by + CONFIG_CGROUP_MEM_RES_CTLR_SWAP could be disabled by the noswapaccount + kernel parameter (introduced in 2.6.29-rc1). Later on, this decision + turned out to be not ideal because we cannot have the feature compiled + in and disabled by default and let only interested to enable it + (e.g. general distribution kernels might need it). Therefore we have + added swapaccount[=0|1] parameter (introduced in 2.6.37) which provides + the both possibilities. If we remove noswapaccount we will have + less command line parameters with the same functionality and we + can also cleanup the parameter handling a bit (). +Who: Michal Hocko <mhocko@suse.cz> + +---------------------------- diff --git a/Documentation/hwmon/jc42 b/Documentation/hwmon/jc42 index 0e76ef1..a22ecf4 100644 --- a/Documentation/hwmon/jc42 +++ b/Documentation/hwmon/jc42 @@ -51,7 +51,8 @@ Supported chips: * JEDEC JC 42.4 compliant temperature sensor chips Prefix: 'jc42' Addresses scanned: I2C 0x18 - 0x1f - Datasheet: - + Datasheet: + http://www.jedec.org/sites/default/files/docs/4_01_04R19.pdf Author: Guenter Roeck <guenter.roeck@ericsson.com> @@ -60,7 +61,11 @@ Author: Description ----------- -This driver implements support for JEDEC JC 42.4 compliant temperature sensors. +This driver implements support for JEDEC JC 42.4 compliant temperature sensors, +which are used on many DDR3 memory modules for mobile devices and servers. Some +systems use the sensor to prevent memory overheating by automatically throttling +the memory controller. + The driver auto-detects the chips listed above, but can be manually instantiated to support other JC 42.4 compliant chips. @@ -81,15 +86,19 @@ limits. The chip supports only a single register to configure the hysteresis, which applies to all limits. This register can be written by writing into temp1_crit_hyst. Other hysteresis attributes are read-only. +If the BIOS has configured the sensor for automatic temperature management, it +is likely that it has locked the registers, i.e., that the temperature limits +cannot be changed. + Sysfs entries ------------- temp1_input Temperature (RO) -temp1_min Minimum temperature (RW) -temp1_max Maximum temperature (RW) -temp1_crit Critical high temperature (RW) +temp1_min Minimum temperature (RO or RW) +temp1_max Maximum temperature (RO or RW) +temp1_crit Critical high temperature (RO or RW) -temp1_crit_hyst Critical hysteresis temperature (RW) +temp1_crit_hyst Critical hysteresis temperature (RO or RW) temp1_max_hyst Maximum hysteresis temperature (RO) temp1_min_alarm Temperature low alarm diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp index 6526eee..d2b56a4 100644 --- a/Documentation/hwmon/k10temp +++ b/Documentation/hwmon/k10temp @@ -9,6 +9,8 @@ Supported chips: Socket S1G3: Athlon II, Sempron, Turion II * AMD Family 11h processors: Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra) +* AMD Family 12h processors: "Llano" +* AMD Family 14h processors: "Brazos" (C/E/G-Series) Prefix: 'k10temp' Addresses scanned: PCI space @@ -17,10 +19,14 @@ Supported chips: http://support.amd.com/us/Processor_TechDocs/31116.pdf BIOS and Kernel Developer's Guide (BKDG) for AMD Family 11h Processors: http://support.amd.com/us/Processor_TechDocs/41256.pdf + BIOS and Kernel Developer's Guide (BKDG) for AMD Family 14h Models 00h-0Fh Processors: + http://support.amd.com/us/Processor_TechDocs/43170.pdf Revision Guide for AMD Family 10h Processors: http://support.amd.com/us/Processor_TechDocs/41322.pdf Revision Guide for AMD Family 11h Processors: http://support.amd.com/us/Processor_TechDocs/41788.pdf + Revision Guide for AMD Family 14h Models 00h-0Fh Processors: + http://support.amd.com/us/Processor_TechDocs/47534.pdf AMD Family 11h Processor Power and Thermal Data Sheet for Notebooks: http://support.amd.com/us/Processor_TechDocs/43373.pdf AMD Family 10h Server and Workstation Processor Power and Thermal Data Sheet: @@ -34,7 +40,7 @@ Description ----------- This driver permits reading of the internal temperature sensor of AMD -Family 10h and 11h processors. +Family 10h/11h/12h/14h processors. All these processors have a sensor, but on those for Socket F or AM2+, the sensor may return inconsistent values (erratum 319). The driver diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 89835a4..f4a04c0 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -144,6 +144,11 @@ a fixed number of characters. This limit depends on the architecture and is between 256 and 4096 characters. It is defined in the file ./include/asm/setup.h as COMMAND_LINE_SIZE. +Finally, the [KMG] suffix is commonly described after a number of kernel +parameter values. These 'K', 'M', and 'G' letters represent the _binary_ +multipliers 'Kilo', 'Mega', and 'Giga', equalling 2^10, 2^20, and 2^30 +bytes respectively. Such letter suffixes can also be entirely omitted. + acpi= [HW,ACPI,X86] Advanced Configuration and Power Interface @@ -545,16 +550,20 @@ and is between 256 and 4096 characters. It is defined in the file Format: <first_slot>,<last_slot>,<port>,<enum_bit>[,<debug>] - crashkernel=nn[KMG]@ss[KMG] - [KNL] Reserve a chunk of physical memory to - hold a kernel to switch to with kexec on panic. + crashkernel=size[KMG][@offset[KMG]] + [KNL] Using kexec, Linux can switch to a 'crash kernel' + upon panic. This parameter reserves the physical + memory region [offset, offset + size] for that kernel + image. If '@offset' is omitted, then a suitable offset + is selected automatically. Check + Documentation/kdump/kdump.txt for further details. crashkernel=range1:size1[,range2:size2,...][@offset] [KNL] Same as above, but depends on the memory in the running system. The syntax of range is start-[end] where start and end are both a memory unit (amount[KMG]). See also - Documentation/kdump/kdump.txt for a example. + Documentation/kdump/kdump.txt for an example. cs89x0_dma= [HW,NET] Format: <dma> @@ -1262,10 +1271,9 @@ and is between 256 and 4096 characters. It is defined in the file 6 (KERN_INFO) informational 7 (KERN_DEBUG) debug-level messages - log_buf_len=n Sets the size of the printk ring buffer, in bytes. - Format: { n | nk | nM } - n must be a power of two. The default size - is set in the kernel config file. + log_buf_len=n[KMG] Sets the size of the printk ring buffer, + in bytes. n must be a power of two. The default + size is set in the kernel config file. logo.nologo [FB] Disables display of the built-in Linux logo. This may be used to provide more screen space for diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index fe5c099..4edd78d 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -40,8 +40,6 @@ decnet.txt - info on using the DECnet networking layer in Linux. depca.txt - the Digital DEPCA/EtherWORKS DE1?? and DE2?? LANCE Ethernet driver -dgrs.txt - - the Digi International RightSwitch SE-X Ethernet driver dmfe.txt - info on the Davicom DM9102(A)/DM9132/DM9801 fast ethernet driver. e100.txt @@ -50,8 +48,6 @@ e1000.txt - info on Intel's E1000 line of gigabit ethernet boards eql.txt - serial IP load balancing -ethertap.txt - - the Ethertap user space packet reception and transmission driver ewrk3.txt - the Digital EtherWORKS 3 DE203/4/5 Ethernet driver filter.txt @@ -104,8 +100,6 @@ tuntap.txt - TUN/TAP device driver, allowing user space Rx/Tx of packets. vortex.txt - info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards. -wavelan.txt - - AT&T GIS (nee NCR) WaveLAN card: An Ethernet-like radio transceiver x25.txt - general info on X.25 development. x25-iface.txt diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile index 5aba7a3..24c308d 100644 --- a/Documentation/networking/Makefile +++ b/Documentation/networking/Makefile @@ -4,6 +4,8 @@ obj- := dummy.o # List of programs to build hostprogs-y := ifenslave +HOSTCFLAGS_ifenslave.o += -I$(objtree)/usr/include + # Tell kbuild to always build the programs always := $(hostprogs-y) diff --git a/Documentation/networking/dns_resolver.txt b/Documentation/networking/dns_resolver.txt index aefd1e6..04ca0632 100644 --- a/Documentation/networking/dns_resolver.txt +++ b/Documentation/networking/dns_resolver.txt @@ -61,7 +61,6 @@ before the more general line given above as the first match is the one taken. create dns_resolver foo:* * /usr/sbin/dns.foo %k - ===== USAGE ===== @@ -104,6 +103,14 @@ implemented in the module can be called after doing: returned also. +=============================== +READING DNS KEYS FROM USERSPACE +=============================== + +Keys of dns_resolver type can be read from userspace using keyctl_read() or +"keyctl read/print/pipe". + + ========= MECHANISM ========= diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index d99940d..ac3b4a7 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -187,7 +187,7 @@ tcp_cookie_size - INTEGER tcp_dsack - BOOLEAN Allows TCP to send "duplicate" SACKs. -tcp_ecn - BOOLEAN +tcp_ecn - INTEGER Enable Explicit Congestion Notification (ECN) in TCP. ECN is only used when both ends of the TCP flow support it. It is useful to avoid losses due to congestion (when the bottleneck router supports diff --git a/Documentation/scheduler/sched-stats.txt b/Documentation/scheduler/sched-stats.txt index 01e6940..1cd5d51 100644 --- a/Documentation/scheduler/sched-stats.txt +++ b/Documentation/scheduler/sched-stats.txt @@ -1,3 +1,7 @@ +Version 15 of schedstats dropped counters for some sched_yield: +yld_exp_empty, yld_act_empty and yld_both_empty. Otherwise, it is +identical to version 14. + Version 14 of schedstats includes support for sched_domains, which hit the mainline kernel in 2.6.20 although it is identical to the stats from version 12 which was in the kernel from 2.6.13-2.6.19 (version 13 never saw a kernel @@ -28,32 +32,25 @@ to write their own scripts, the fields are described here. CPU statistics -------------- -cpu<N> 1 2 3 4 5 6 7 8 9 10 11 12 - -NOTE: In the sched_yield() statistics, the active queue is considered empty - if it has only one process in it, since obviously the process calling - sched_yield() is that process. +cpu<N> 1 2 3 4 5 6 7 8 9 -First four fields are sched_yield() statistics: - 1) # of times both the active and the expired queue were empty - 2) # of times just the active queue was empty - 3) # of times just the expired queue was empty - 4) # of times sched_yield() was called +First field is a sched_yield() statistic: + 1) # of times sched_yield() was called Next three are schedule() statistics: - 5) # of times we switched to the expired queue and reused it - 6) # of times schedule() was called - 7) # of times schedule() left the processor idle + 2) # of times we switched to the expired queue and reused it + 3) # of times schedule() was called + 4) # of times schedule() left the processor idle Next two are try_to_wake_up() statistics: - 8) # of times try_to_wake_up() was called - 9) # of times try_to_wake_up() was called to wake up the local cpu + 5) # of times try_to_wake_up() was called + 6) # of times try_to_wake_up() was called to wake up the local cpu Next three are statistics describing scheduling latency: - 10) sum of all time spent running by tasks on this processor (in jiffies) - 11) sum of all time spent waiting to run by tasks on this processor (in + 7) sum of all time spent running by tasks on this processor (in jiffies) + 8) sum of all time spent waiting to run by tasks on this processor (in jiffies) - 12) # of timeslices run on this cpu + 9) # of timeslices run on this cpu Domain statistics diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt index 16ae430..0caf77e 100644 --- a/Documentation/sound/alsa/HD-Audio-Models.txt +++ b/Documentation/sound/alsa/HD-Audio-Models.txt @@ -296,6 +296,7 @@ Conexant 5066 ============= laptop Basic Laptop config (default) hp-laptop HP laptops, e g G60 + asus Asus K52JU, Lenovo G560 dell-laptop Dell laptops dell-vostro Dell Vostro olpc-xo-1_5 OLPC XO 1.5 diff --git a/Documentation/spinlocks.txt b/Documentation/spinlocks.txt index 178c831..2e3c64b 100644 --- a/Documentation/spinlocks.txt +++ b/Documentation/spinlocks.txt @@ -86,7 +86,7 @@ to change the variables it has to get an exclusive write lock. The routines look the same as above: - rwlock_t xxx_lock = RW_LOCK_UNLOCKED; + rwlock_t xxx_lock = __RW_LOCK_UNLOCKED(xxx_lock); unsigned long flags; @@ -196,25 +196,3 @@ appropriate: For static initialization, use DEFINE_SPINLOCK() / DEFINE_RWLOCK() or __SPIN_LOCK_UNLOCKED() / __RW_LOCK_UNLOCKED() as appropriate. - -SPIN_LOCK_UNLOCKED and RW_LOCK_UNLOCKED are deprecated. These interfere -with lockdep state tracking. - -Most of the time, you can simply turn: - static spinlock_t xxx_lock = SPIN_LOCK_UNLOCKED; -into: - static DEFINE_SPINLOCK(xxx_lock); - -Static structure member variables go from: - - struct foo bar { - .lock = SPIN_LOCK_UNLOCKED; - }; - -to: - - struct foo bar { - .lock = __SPIN_LOCK_UNLOCKED(bar.lock); - }; - -Declaration of static rw_locks undergo a similar transformation. diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt index dc52bd4..79fcafc 100644 --- a/Documentation/trace/ftrace-design.txt +++ b/Documentation/trace/ftrace-design.txt @@ -247,6 +247,13 @@ You need very few things to get the syscalls tracing in an arch. - Support the TIF_SYSCALL_TRACEPOINT thread flags. - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace in the ptrace syscalls tracing path. +- If the system call table on this arch is more complicated than a simple array + of addresses of the system calls, implement an arch_syscall_addr to return + the address of a given system call. +- If the symbol names of the system calls do not match the function names on + this arch, define ARCH_HAS_SYSCALL_MATCH_SYM_NAME in asm/ftrace.h and + implement arch_syscall_match_sym_name with the appropriate logic to return + true if the function name corresponds with the symbol name. - Tag this arch as HAVE_SYSCALL_TRACEPOINTS. diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 557c1ed..1ebc24c 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -80,11 +80,11 @@ of ftrace. Here is a list of some of the key files: tracers listed here can be configured by echoing their name into current_tracer. - tracing_enabled: + tracing_on: - This sets or displays whether the current_tracer - is activated and tracing or not. Echo 0 into this - file to disable the tracer or 1 to enable it. + This sets or displays whether writing to the trace + ring buffer is enabled. Echo 0 into this file to disable + the tracer or 1 to enable it. trace: @@ -202,10 +202,6 @@ Here is the list of current tracers that may be configured. to draw a graph of function calls similar to C code source. - "sched_switch" - - Traces the context switches and wakeups between tasks. - "irqsoff" Traces the areas that disable interrupts and saves @@ -273,39 +269,6 @@ format, the function name that was traced "path_put" and the parent function that called this function "path_walk". The timestamp is the time at which the function was entered. -The sched_switch tracer also includes tracing of task wakeups -and context switches. - - ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 2916:115:S - ksoftirqd/1-7 [01] 1453.070013: 7:115:R + 10:115:S - ksoftirqd/1-7 [01] 1453.070013: 7:115:R ==> 10:115:R - events/1-10 [01] 1453.070013: 10:115:S ==> 2916:115:R - kondemand/1-2916 [01] 1453.070013: 2916:115:S ==> 7:115:R - ksoftirqd/1-7 [01] 1453.070013: 7:115:S ==> 0:140:R - -Wake ups are represented by a "+" and the context switches are -shown as "==>". The format is: - - Context switches: - - Previous task Next Task - - <pid>:<prio>:<state> ==> <pid>:<prio>:<state> - - Wake ups: - - Current task Task waking up - - <pid>:<prio>:<state> + <pid>:<prio>:<state> - -The prio is the internal kernel priority, which is the inverse -of the priority that is usually displayed by user-space tools. -Zero represents the highest priority (99). Prio 100 starts the -"nice" priorities with 100 being equal to nice -20 and 139 being -nice 19. The prio "140" is reserved for the idle task which is -the lowest priority thread (pid 0). - - Latency trace format -------------------- @@ -491,78 +454,10 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6] latencies, as described in "Latency trace format". -sched_switch ------------- - -This tracer simply records schedule switches. Here is an example -of how to use it. - - # echo sched_switch > current_tracer - # echo 1 > tracing_enabled - # sleep 1 - # echo 0 > tracing_enabled - # cat trace - -# tracer: sched_switch -# -# TASK-PID CPU# TIMESTAMP FUNCTION -# | | | | | - bash-3997 [01] 240.132281: 3997:120:R + 4055:120:R - bash-3997 [01] 240.132284: 3997:120:R ==> 4055:120:R - sleep-4055 [01] 240.132371: 4055:120:S ==> 3997:120:R - bash-3997 [01] 240.132454: 3997:120:R + 4055:120:S - bash-3997 [01] 240.132457: 3997:120:R ==> 4055:120:R - sleep-4055 [01] 240.132460: 4055:120:D ==> 3997:120:R - bash-3997 [01] 240.132463: 3997:120:R + 4055:120:D - bash-3997 [01] 240.132465: 3997:120:R ==> 4055:120:R - <idle>-0 [00] 240.132589: 0:140:R + 4:115:S - <idle>-0 [00] 240.132591: 0:140:R ==> 4:115:R - ksoftirqd/0-4 [00] 240.132595: 4:115:S ==> 0:140:R - <idle>-0 [00] 240.132598: 0:140:R + 4:115:S - <idle>-0 [00] 240.132599: 0:140:R ==> 4:115:R - ksoftirqd/0-4 [00] 240.132603: 4:115:S ==> 0:140:R - sleep-4055 [01] 240.133058: 4055:120:S ==> 3997:120:R - [...] - - -As we have discussed previously about this format, the header -shows the name of the trace and points to the options. The -"FUNCTION" is a misnomer since here it represents the wake ups -and context switches. - -The sched_switch file only lists the wake ups (represented with -'+') and context switches ('==>') with the previous task or -current task first followed by the next task or task waking up. -The format for both of these is PID:KERNEL-PRIO:TASK-STATE. -Remember that the KERNEL-PRIO is the inverse of the actual -priority with zero (0) being the highest priority and the nice -values starting at 100 (nice -20). Below is a quick chart to map -the kernel priority to user land priorities. - - Kernel Space User Space - =============================================================== - 0(high) to 98(low) user RT priority 99(high) to 1(low) - with SCHED_RR or SCHED_FIFO - --------------------------------------------------------------- - 99 sched_priority is not used in scheduling - decisions(it must be specified as 0) - --------------------------------------------------------------- - 100(high) to 139(low) user nice -20(high) to 19(low) - --------------------------------------------------------------- - 140 idle task priority - --------------------------------------------------------------- - -The task states are: - - R - running : wants to run, may not actually be running - S - sleep : process is waiting to be woken up (handles signals) - D - disk sleep (uninterruptible sleep) : process must be woken up - (ignores signals) - T - stopped : process suspended - t - traced : process is being traced (with something like gdb) - Z - zombie : process waiting to be cleaned up - X - unknown - + overwrite - This controls what happens when the trace buffer is + full. If "1" (default), the oldest events are + discarded and overwritten. If "0", then the newest + events are discarded. ftrace_enabled -------------- @@ -607,10 +502,10 @@ an example: # echo irqsoff > current_tracer # echo latency-format > trace_options # echo 0 > tracing_max_latency - # echo 1 > tracing_enabled + # echo 1 > tracing_on # ls -ltr [...] - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: irqsoff # @@ -715,10 +610,10 @@ is much like the irqsoff tracer. # echo preemptoff > current_tracer # echo latency-format > trace_options # echo 0 > tracing_max_latency - # echo 1 > tracing_enabled + # echo 1 > tracing_on # ls -ltr [...] - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: preemptoff # @@ -863,10 +758,10 @@ tracers. # echo preemptirqsoff > current_tracer # echo latency-format > trace_options # echo 0 > tracing_max_latency - # echo 1 > tracing_enabled + # echo 1 > tracing_on # ls -ltr [...] - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: preemptirqsoff # @@ -1026,9 +921,9 @@ Instead of performing an 'ls', we will run 'sleep 1' under # echo wakeup > current_tracer # echo latency-format > trace_options # echo 0 > tracing_max_latency - # echo 1 > tracing_enabled + # echo 1 > tracing_on # chrt -f 5 sleep 1 - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: wakeup # @@ -1140,9 +1035,9 @@ ftrace_enabled is set; otherwise this tracer is a nop. # sysctl kernel.ftrace_enabled=1 # echo function > current_tracer - # echo 1 > tracing_enabled + # echo 1 > tracing_on # usleep 1 - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: function # @@ -1180,7 +1075,7 @@ int trace_fd; [...] int main(int argc, char *argv[]) { [...] - trace_fd = open(tracing_file("tracing_enabled"), O_WRONLY); + trace_fd = open(tracing_file("tracing_on"), O_WRONLY); [...] if (condition_hit()) { write(trace_fd, "0", 1); @@ -1631,9 +1526,9 @@ If I am only interested in sys_nanosleep and hrtimer_interrupt: # echo sys_nanosleep hrtimer_interrupt \ > set_ftrace_filter # echo function > current_tracer - # echo 1 > tracing_enabled + # echo 1 > tracing_on # usleep 1 - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: ftrace # @@ -1879,9 +1774,9 @@ different. The trace is live. # echo function > current_tracer # cat trace_pipe > /tmp/trace.out & [1] 4153 - # echo 1 > tracing_enabled + # echo 1 > tracing_on # usleep 1 - # echo 0 > tracing_enabled + # echo 0 > tracing_on # cat trace # tracer: function # diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt index 5f77d94..6d27ab8 100644 --- a/Documentation/trace/kprobetrace.txt +++ b/Documentation/trace/kprobetrace.txt @@ -42,11 +42,25 @@ Synopsis of kprobe_events +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**) NAME=FETCHARG : Set NAME as the argument name of FETCHARG. FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types - (u8/u16/u32/u64/s8/s16/s32/s64) and string are supported. + (u8/u16/u32/u64/s8/s16/s32/s64), "string" and bitfield + are supported. (*) only for return probe. (**) this is useful for fetching a field of data structures. +Types +----- +Several types are supported for fetch-args. Kprobe tracer will access memory +by given type. Prefix 's' and 'u' means those types are signed and unsigned +respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). +String type is a special type, which fetches a "null-terminated" string from +kernel space. This means it will fail and store NULL if the string container +has been paged out. +Bitfield is another special type, which takes 3 parameters, bit-width, bit- +offset, and container-size (usually 32). The syntax is; + + b<bit-width>@<bit-offset>/<container-size> + Per-Probe Event Filtering ------------------------- diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt index 996a27d..01c513f 100644 --- a/Documentation/workqueue.txt +++ b/Documentation/workqueue.txt @@ -190,9 +190,9 @@ resources, scheduled and executed. * Long running CPU intensive workloads which can be better managed by the system scheduler. - WQ_FREEZEABLE + WQ_FREEZABLE - A freezeable wq participates in the freeze phase of the system + A freezable wq participates in the freeze phase of the system suspend operations. Work items on the wq are drained and no new work item starts execution until thawed. diff --git a/MAINTAINERS b/MAINTAINERS index 9d12977..f1bc3dc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -885,7 +885,7 @@ S: Supported ARM/QUALCOMM MSM MACHINE SUPPORT M: David Brown <davidb@codeaurora.org> -M: Daniel Walker <dwalker@codeaurora.org> +M: Daniel Walker <dwalker@fifo99.com> M: Bryan Huntsman <bryanh@codeaurora.org> L: linux-arm-msm@vger.kernel.org F: arch/arm/mach-msm/ @@ -978,6 +978,8 @@ S: Maintained F: arch/arm/plat-samsung/ F: arch/arm/plat-s3c24xx/ F: arch/arm/plat-s5p/ +F: drivers/*/*s3c2410* +F: drivers/*/*/*s3c2410* ARM/S3C2410 ARM ARCHITECTURE M: Ben Dooks <ben-linux@fluff.org> @@ -1008,6 +1010,15 @@ L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-s5p*/ +ARM/SAMSUNG MOBILE MACHINE SUPPORT +M: Kyungmin Park <kyungmin.park@samsung.com> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/mach-s5pv210/mach-aquila.c +F: arch/arm/mach-s5pv210/mach-goni.c +F: arch/arm/mach-exynos4/mach-universal_c210.c +F: arch/arm/mach-exynos4/mach-nuri.c + ARM/SAMSUNG S5P SERIES FIMC SUPPORT M: Kyungmin Park <kyungmin.park@samsung.com> M: Sylwester Nawrocki <s.nawrocki@samsung.com> @@ -1465,6 +1476,7 @@ F: include/net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <fubar@us.ibm.com> +M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org W: http://sourceforge.net/projects/bonding/ S: Supported @@ -1690,6 +1702,13 @@ M: Andy Whitcroft <apw@canonical.com> S: Supported F: scripts/checkpatch.pl +CHINESE DOCUMENTATION +M: Harry Wei <harryxiyou@gmail.com> +L: xiyoulinuxkernelgroup@googlegroups.com +L: linux-kernel@zh-kernel.org (moderated for non-subscribers) +S: Maintained +F: Documentation/zh_CN/ + CISCO VIC ETHERNET NIC DRIVER M: Vasanthy Kolluri <vkolluri@cisco.com> M: Roopa Prabhu <roprabhu@cisco.com> @@ -2024,7 +2043,7 @@ F: Documentation/scsi/dc395x.txt F: drivers/scsi/dc395x.* DCCP PROTOCOL -M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> +M: Gerrit Renker <gerrit@erg.abdn.ac.uk> L: dccp@vger.kernel.org W: http://www.linuxfoundation.org/collaborate/workgroups/networking/dccp S: Maintained @@ -2124,6 +2143,7 @@ S: Supported F: fs/dlm/ DMA GENERIC OFFLOAD ENGINE SUBSYSTEM +M: Vinod Koul <vinod.koul@intel.com> M: Dan Williams <dan.j.williams@intel.com> S: Supported F: drivers/dma/ @@ -2772,6 +2792,15 @@ F: Documentation/isdn/README.gigaset F: drivers/isdn/gigaset/ F: include/linux/gigaset_dev.h +GPIO SUBSYSTEM +M: Grant Likely <grant.likely@secretlab.ca> +L: linux-kernel@vger.kernel.org +S: Maintained +T: git git://git.secretlab.ca/git/linux-2.6.git +F: Documentation/gpio/gpio.txt +F: drivers/gpio/ +F: include/linux/gpio* + GRETH 10/100/1G Ethernet MAC device driver M: Kristoffer Glembo <kristoffer@gaisler.com> L: netdev@vger.kernel.org @@ -2861,7 +2890,6 @@ M: Guenter Roeck <guenter.roeck@ericsson.com> L: lm-sensors@lm-sensors.org W: http://www.lm-sensors.org/ T: quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/ -T: quilt kernel.org/pub/linux/kernel/people/groeck/linux-staging/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git S: Maintained F: Documentation/hwmon/ @@ -3139,6 +3167,12 @@ S: Maintained F: net/ieee802154/ F: drivers/ieee802154/ +IKANOS/ADI EAGLE ADSL USB DRIVER +M: Matthieu Castet <castet.matthieu@free.fr> +M: Stanislaw Gruszka <stf_xl@wp.pl> +S: Maintained +F: drivers/usb/atm/ueagle-atm.c + INTEGRITY MEASUREMENT ARCHITECTURE (IMA) M: Mimi Zohar <zohar@us.ibm.com> S: Supported @@ -3495,7 +3529,7 @@ F: drivers/hwmon/jc42.c F: Documentation/hwmon/jc42 JFS FILESYSTEM -M: Dave Kleikamp <shaggy@linux.vnet.ibm.com> +M: Dave Kleikamp <shaggy@kernel.org> L: jfs-discussion@lists.sourceforge.net W: http://jfs.sourceforge.net/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/shaggy/jfs-2.6.git @@ -4258,10 +4292,7 @@ S: Maintained F: net/sched/sch_netem.c NETERION 10GbE DRIVERS (s2io/vxge) -M: Ramkrishna Vepa <ramkrishna.vepa@exar.com> -M: Sivakumar Subramani <sivakumar.subramani@exar.com> -M: Sreenivasa Honnur <sreenivasa.honnur@exar.com> -M: Jon Mason <jon.mason@exar.com> +M: Jon Mason <jdmason@kudzu.us> L: netdev@vger.kernel.org W: http://trac.neterion.com/cgi-bin/trac.cgi/wiki/Linux?Anonymous W: http://trac.neterion.com/cgi-bin/trac.cgi/wiki/X3100Linux?Anonymous @@ -4583,7 +4614,7 @@ F: drivers/i2c/busses/i2c-ocores.c OPEN FIRMWARE AND FLATTENED DEVICE TREE M: Grant Likely <grant.likely@secretlab.ca> -L: devicetree-discuss@lists.ozlabs.org +L: devicetree-discuss@lists.ozlabs.org (moderated for non-subscribers) W: http://fdt.secretlab.ca T: git git://git.secretlab.ca/git/linux-2.6.git S: Maintained @@ -5147,6 +5178,7 @@ F: drivers/char/random.c RAPIDIO SUBSYSTEM M: Matt Porter <mporter@kernel.crashing.org> +M: Alexandre Bounine <alexandre.bounine@idt.com> S: Maintained F: drivers/rapidio/ @@ -5249,7 +5281,7 @@ S: Maintained F: drivers/net/wireless/rtl818x/rtl8180/ RTL8187 WIRELESS DRIVER -M: Herton Ronaldo Krzesinski <herton@mandriva.com.br> +M: Herton Ronaldo Krzesinski <herton@canonical.com> M: Hin-Tak Leung <htl10@users.sourceforge.net> M: Larry Finger <Larry.Finger@lwfinger.net> L: linux-wireless@vger.kernel.org @@ -5543,12 +5575,11 @@ S: Supported F: drivers/scsi/be2iscsi/ SERVER ENGINES 10Gbps NIC - BladeEngine 2 DRIVER -M: Sathya Perla <sathyap@serverengines.com> -M: Subbu Seetharaman <subbus@serverengines.com> -M: Sarveshwar Bandi <sarveshwarb@serverengines.com> -M: Ajit Khaparde <ajitk@serverengines.com> +M: Sathya Perla <sathya.perla@emulex.com> +M: Subbu Seetharaman <subbu.seetharaman@emulex.com> +M: Ajit Khaparde <ajit.khaparde@emulex.com> L: netdev@vger.kernel.org -W: http://www.serverengines.com +W: http://www.emulex.com S: Supported F: drivers/net/benet/ @@ -5608,18 +5639,20 @@ F: include/linux/sfi*.h SIMTEC EB110ATX (Chalice CATS) P: Ben Dooks -M: Vincent Sanders <support@simtec.co.uk> +P: Vincent Sanders <vince@simtec.co.uk> +M: Simtec Linux Team <linux@simtec.co.uk> W: http://www.simtec.co.uk/products/EB110ATX/ S: Supported SIMTEC EB2410ITX (BAST) P: Ben Dooks -M: Vincent Sanders <support@simtec.co.uk> +P: Vincent Sanders <vince@simtec.co.uk> +M: Simtec Linux Team <linux@simtec.co.uk> W: http://www.simtec.co.uk/products/EB2410ITX/ S: Supported -F: arch/arm/mach-s3c2410/ -F: drivers/*/*s3c2410* -F: drivers/*/*/*s3c2410* +F: arch/arm/mach-s3c2410/mach-bast.c +F: arch/arm/mach-s3c2410/bast-ide.c +F: arch/arm/mach-s3c2410/bast-irq.c TI DAVINCI MACHINE SUPPORT M: Kevin Hilman <khilman@deeprootsystems.com> @@ -6086,7 +6119,7 @@ S: Maintained F: security/tomoyo/ TOPSTAR LAPTOP EXTRAS DRIVER -M: Herton Ronaldo Krzesinski <herton@mandriva.com.br> +M: Herton Ronaldo Krzesinski <herton@canonical.com> L: platform-driver-x86@vger.kernel.org S: Maintained F: drivers/platform/x86/topstar-laptop.c @@ -6594,6 +6627,16 @@ S: Maintained F: drivers/char/virtio_console.c F: include/linux/virtio_console.h +VIRTIO CORE, NET AND BLOCK DRIVERS +M: Rusty Russell <rusty@rustcorp.com.au> +M: "Michael S. Tsirkin" <mst@redhat.com> +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/virtio/ +F: drivers/net/virtio_net.c +F: drivers/block/virtio_blk.c +F: include/linux/virtio_*.h + VIRTIO HOST (VHOST) M: "Michael S. Tsirkin" <mst@redhat.com> L: kvm@vger.kernel.org @@ -6767,12 +6810,12 @@ S: Maintained F: drivers/net/wireless/wl1251/* WL1271 WIRELESS DRIVER -M: Luciano Coelho <luciano.coelho@nokia.com> +M: Luciano Coelho <coelho@ti.com> L: linux-wireless@vger.kernel.org -W: http://wireless.kernel.org +W: http://wireless.kernel.org/en/users/Drivers/wl12xx T: git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git S: Maintained -F: drivers/net/wireless/wl12xx/wl1271* +F: drivers/net/wireless/wl12xx/ F: include/linux/wl12xx.h WL3501 WIRELESS PCMCIA CARD DRIVER @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 38 -EXTRAVERSION = -rc2 +EXTRAVERSION = NAME = Flesh-Eating Bats with Fangs # *DOCUMENTATION* diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 47f63d4..cc31bec 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -11,6 +11,7 @@ config ALPHA select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_PROBE select AUTO_IRQ_AFFINITY if SMP + select GENERIC_HARDIRQS_NO_DEPRECATED help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h index 945de22..e8a761a 100644 --- a/arch/alpha/include/asm/futex.h +++ b/arch/alpha/include/asm/futex.h @@ -29,7 +29,7 @@ : "r" (uaddr), "r"(oparg) \ : "memory") -static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -39,7 +39,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -81,21 +81,23 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - int prev, cmp; + int ret = 0, cmp; + u32 prev; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; __asm__ __volatile__ ( __ASM_SMP_MB - "1: ldl_l %0,0(%2)\n" - " cmpeq %0,%3,%1\n" - " beq %1,3f\n" - " mov %4,%1\n" - "2: stl_c %1,0(%2)\n" - " beq %1,4f\n" + "1: ldl_l %1,0(%3)\n" + " cmpeq %1,%4,%2\n" + " beq %2,3f\n" + " mov %5,%2\n" + "2: stl_c %2,0(%3)\n" + " beq %2,4f\n" "3: .subsection 2\n" "4: br 1b\n" " .previous\n" @@ -105,11 +107,12 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) " .long 2b-.\n" " lda $31,3b-2b(%0)\n" " .previous\n" - : "=&r"(prev), "=&r"(cmp) + : "+r"(ret), "=&r"(prev), "=&r"(cmp) : "r"(uaddr), "r"((long)oldval), "r"(newval) : "memory"); - return prev; + *uval = prev; + return ret; } #endif /* __KERNEL__ */ diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h index 1570c0b..a83bbea6 100644 --- a/arch/alpha/include/asm/rwsem.h +++ b/arch/alpha/include/asm/rwsem.h @@ -13,44 +13,13 @@ #ifdef __KERNEL__ #include <linux/compiler.h> -#include <linux/list.h> -#include <linux/spinlock.h> -struct rwsem_waiter; - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -/* - * the semaphore definition - */ -struct rw_semaphore { - long count; #define RWSEM_UNLOCKED_VALUE 0x0000000000000000L #define RWSEM_ACTIVE_BIAS 0x0000000000000001L #define RWSEM_ACTIVE_MASK 0x00000000ffffffffL #define RWSEM_WAITING_BIAS (-0x0000000100000000L) #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - spinlock_t wait_lock; - struct list_head wait_list; -}; - -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \ - LIST_HEAD_INIT((name).wait_list) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -static inline void init_rwsem(struct rw_semaphore *sem) -{ - sem->count = RWSEM_UNLOCKED_VALUE; - spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} static inline void __down_read(struct rw_semaphore *sem) { @@ -250,10 +219,5 @@ static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem) #endif } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* __KERNEL__ */ #endif /* _ALPHA_RWSEM_H */ diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c index 9ab234f..a19d600 100644 --- a/arch/alpha/kernel/irq.c +++ b/arch/alpha/kernel/irq.c @@ -44,11 +44,16 @@ static char irq_user_affinity[NR_IRQS]; int irq_select_affinity(unsigned int irq) { - struct irq_desc *desc = irq_to_desc[irq]; + struct irq_data *data = irq_get_irq_data(irq); + struct irq_chip *chip; static int last_cpu; int cpu = last_cpu + 1; - if (!desc || !get_irq_desc_chip(desc)->set_affinity || irq_user_affinity[irq]) + if (!data) + return 1; + chip = irq_data_get_irq_chip(data); + + if (!chip->irq_set_affinity || irq_user_affinity[irq]) return 1; while (!cpu_possible(cpu) || @@ -56,8 +61,8 @@ int irq_select_affinity(unsigned int irq) cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0); last_cpu = cpu; - cpumask_copy(desc->affinity, cpumask_of(cpu)); - get_irq_desc_chip(desc)->set_affinity(irq, cpumask_of(cpu)); + cpumask_copy(data->affinity, cpumask_of(cpu)); + chip->irq_set_affinity(data, cpumask_of(cpu), false); return 0; } #endif /* CONFIG_SMP */ diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c index 2d0679b..411ca11 100644 --- a/arch/alpha/kernel/irq_alpha.c +++ b/arch/alpha/kernel/irq_alpha.c @@ -228,14 +228,9 @@ struct irqaction timer_irqaction = { void __init init_rtc_irq(void) { - struct irq_desc *desc = irq_to_desc(RTC_IRQ); - - if (desc) { - desc->status |= IRQ_DISABLED; - set_irq_chip_and_handler_name(RTC_IRQ, &no_irq_chip, - handle_simple_irq, "RTC"); - setup_irq(RTC_IRQ, &timer_irqaction); - } + set_irq_chip_and_handler_name(RTC_IRQ, &no_irq_chip, + handle_simple_irq, "RTC"); + setup_irq(RTC_IRQ, &timer_irqaction); } /* Dummy irqactions. */ diff --git a/arch/alpha/kernel/irq_i8259.c b/arch/alpha/kernel/irq_i8259.c index 956ea0e..c7cc981 100644 --- a/arch/alpha/kernel/irq_i8259.c +++ b/arch/alpha/kernel/irq_i8259.c @@ -33,10 +33,10 @@ i8259_update_irq_hw(unsigned int irq, unsigned long mask) } inline void -i8259a_enable_irq(unsigned int irq) +i8259a_enable_irq(struct irq_data *d) { spin_lock(&i8259_irq_lock); - i8259_update_irq_hw(irq, cached_irq_mask &= ~(1 << irq)); + i8259_update_irq_hw(d->irq, cached_irq_mask &= ~(1 << d->irq)); spin_unlock(&i8259_irq_lock); } @@ -47,16 +47,18 @@ __i8259a_disable_irq(unsigned int irq) } void -i8259a_disable_irq(unsigned int irq) +i8259a_disable_irq(struct irq_data *d) { spin_lock(&i8259_irq_lock); - __i8259a_disable_irq(irq); + __i8259a_disable_irq(d->irq); spin_unlock(&i8259_irq_lock); } void -i8259a_mask_and_ack_irq(unsigned int irq) +i8259a_mask_and_ack_irq(struct irq_data *d) { + unsigned int irq = d->irq; + spin_lock(&i8259_irq_lock); __i8259a_disable_irq(irq); @@ -71,9 +73,9 @@ i8259a_mask_and_ack_irq(unsigned int irq) struct irq_chip i8259a_irq_type = { .name = "XT-PIC", - .unmask = i8259a_enable_irq, - .mask = i8259a_disable_irq, - .mask_ack = i8259a_mask_and_ack_irq, + .irq_unmask = i8259a_enable_irq, + .irq_mask = i8259a_disable_irq, + .irq_mask_ack = i8259a_mask_and_ack_irq, }; void __init diff --git a/arch/alpha/kernel/irq_impl.h b/arch/alpha/kernel/irq_impl.h index b63ccd7..d507a23 100644 --- a/arch/alpha/kernel/irq_impl.h +++ b/arch/alpha/kernel/irq_impl.h @@ -31,11 +31,9 @@ extern void init_rtc_irq(void); extern void common_init_isa_dma(void); -extern void i8259a_enable_irq(unsigned int); -extern void i8259a_disable_irq(unsigned int); -extern void i8259a_mask_and_ack_irq(unsigned int); -extern unsigned int i8259a_startup_irq(unsigned int); -extern void i8259a_end_irq(unsigned int); +extern void i8259a_enable_irq(struct irq_data *d); +extern void i8259a_disable_irq(struct irq_data *d); +extern void i8259a_mask_and_ack_irq(struct irq_data *d); extern struct irq_chip i8259a_irq_type; extern void init_i8259a_irqs(void); diff --git a/arch/alpha/kernel/irq_pyxis.c b/arch/alpha/kernel/irq_pyxis.c index 2863458..b30227f 100644 --- a/arch/alpha/kernel/irq_pyxis.c +++ b/arch/alpha/kernel/irq_pyxis.c @@ -29,21 +29,21 @@ pyxis_update_irq_hw(unsigned long mask) } static inline void -pyxis_enable_irq(unsigned int irq) +pyxis_enable_irq(struct irq_data *d) { - pyxis_update_irq_hw(cached_irq_mask |= 1UL << (irq - 16)); + pyxis_update_irq_hw(cached_irq_mask |= 1UL << (d->irq - 16)); } static void -pyxis_disable_irq(unsigned int irq) +pyxis_disable_irq(struct irq_data *d) { - pyxis_update_irq_hw(cached_irq_mask &= ~(1UL << (irq - 16))); + pyxis_update_irq_hw(cached_irq_mask &= ~(1UL << (d->irq - 16))); } static void -pyxis_mask_and_ack_irq(unsigned int irq) +pyxis_mask_and_ack_irq(struct irq_data *d) { - unsigned long bit = 1UL << (irq - 16); + unsigned long bit = 1UL << (d->irq - 16); unsigned long mask = cached_irq_mask &= ~bit; /* Disable the interrupt. */ @@ -58,9 +58,9 @@ pyxis_mask_and_ack_irq(unsigned int irq) static struct irq_chip pyxis_irq_type = { .name = "PYXIS", - .mask_ack = pyxis_mask_and_ack_irq, - .mask = pyxis_disable_irq, - .unmask = pyxis_enable_irq, + .irq_mask_ack = pyxis_mask_and_ack_irq, + .irq_mask = pyxis_disable_irq, + .irq_unmask = pyxis_enable_irq, }; void @@ -103,7 +103,7 @@ init_pyxis_irqs(unsigned long ignore_mask) if ((ignore_mask >> i) & 1) continue; set_irq_chip_and_handler(i, &pyxis_irq_type, handle_level_irq); - irq_to_desc(i)->status |= IRQ_LEVEL; + irq_set_status_flags(i, IRQ_LEVEL); } setup_irq(16+7, &isa_cascade_irqaction); diff --git a/arch/alpha/kernel/irq_srm.c b/arch/alpha/kernel/irq_srm.c index 0e57e82..82a47bb 100644 --- a/arch/alpha/kernel/irq_srm.c +++ b/arch/alpha/kernel/irq_srm.c @@ -18,27 +18,27 @@ DEFINE_SPINLOCK(srm_irq_lock); static inline void -srm_enable_irq(unsigned int irq) +srm_enable_irq(struct irq_data *d) { spin_lock(&srm_irq_lock); - cserve_ena(irq - 16); + cserve_ena(d->irq - 16); spin_unlock(&srm_irq_lock); } static void -srm_disable_irq(unsigned int irq) +srm_disable_irq(struct irq_data *d) { spin_lock(&srm_irq_lock); - cserve_dis(irq - 16); + cserve_dis(d->irq - 16); spin_unlock(&srm_irq_lock); } /* Handle interrupts from the SRM, assuming no additional weirdness. */ static struct irq_chip srm_irq_type = { .name = "SRM", - .unmask = srm_enable_irq, - .mask = srm_disable_irq, - .mask_ack = srm_disable_irq, + .irq_unmask = srm_enable_irq, + .irq_mask = srm_disable_irq, + .irq_mask_ack = srm_disable_irq, }; void __init @@ -52,7 +52,7 @@ init_srm_irqs(long max, unsigned long ignore_mask) if (i < 64 && ((ignore_mask >> i) & 1)) continue; set_irq_chip_and_handler(i, &srm_irq_type, handle_level_irq); - irq_to_desc(i)->status |= IRQ_LEVEL; + irq_set_status_flags(i, IRQ_LEVEL); } } diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index fe698b5..376f221 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -230,44 +230,24 @@ linux_to_osf_statfs(struct kstatfs *linux_stat, struct osf_statfs __user *osf_st return copy_to_user(osf_stat, &tmp_stat, bufsiz) ? -EFAULT : 0; } -static int -do_osf_statfs(struct path *path, struct osf_statfs __user *buffer, - unsigned long bufsiz) +SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname, + struct osf_statfs __user *, buffer, unsigned long, bufsiz) { struct kstatfs linux_stat; - int error = vfs_statfs(path, &linux_stat); + int error = user_statfs(pathname, &linux_stat); if (!error) error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz); return error; } -SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname, - struct osf_statfs __user *, buffer, unsigned long, bufsiz) -{ - struct path path; - int retval; - - retval = user_path(pathname, &path); - if (!retval) { - retval = do_osf_statfs(&path, buffer, bufsiz); - path_put(&path); - } - return retval; -} - SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd, struct osf_statfs __user *, buffer, unsigned long, bufsiz) { - struct file *file; - int retval; - - retval = -EBADF; - file = fget(fd); - if (file) { - retval = do_osf_statfs(&file->f_path, buffer, bufsiz); - fput(file); - } - return retval; + struct kstatfs linux_stat; + int error = fd_statfs(fd, &linux_stat); + if (!error) + error = linux_to_osf_statfs(&linux_stat, buffer, bufsiz); + return error; } /* diff --git a/arch/alpha/kernel/sys_alcor.c b/arch/alpha/kernel/sys_alcor.c index 7bef617..88d95e8 100644 --- a/arch/alpha/kernel/sys_alcor.c +++ b/arch/alpha/kernel/sys_alcor.c @@ -44,31 +44,31 @@ alcor_update_irq_hw(unsigned long mask) } static inline void -alcor_enable_irq(unsigned int irq) +alcor_enable_irq(struct irq_data *d) { - alcor_update_irq_hw(cached_irq_mask |= 1UL << (irq - 16)); + alcor_update_irq_hw(cached_irq_mask |= 1UL << (d->irq - 16)); } static void -alcor_disable_irq(unsigned int irq) +alcor_disable_irq(struct irq_data *d) { - alcor_update_irq_hw(cached_irq_mask &= ~(1UL << (irq - 16))); + alcor_update_irq_hw(cached_irq_mask &= ~(1UL << (d->irq - 16))); } static void -alcor_mask_and_ack_irq(unsigned int irq) +alcor_mask_and_ack_irq(struct irq_data *d) { - alcor_disable_irq(irq); + alcor_disable_irq(d); /* On ALCOR/XLT, need to dismiss interrupt via GRU. */ - *(vuip)GRU_INT_CLEAR = 1 << (irq - 16); mb(); + *(vuip)GRU_INT_CLEAR = 1 << (d->irq - 16); mb(); *(vuip)GRU_INT_CLEAR = 0; mb(); } static void -alcor_isa_mask_and_ack_irq(unsigned int irq) +alcor_isa_mask_and_ack_irq(struct irq_data *d) { - i8259a_mask_and_ack_irq(irq); + i8259a_mask_and_ack_irq(d); /* On ALCOR/XLT, need to dismiss interrupt via GRU. */ *(vuip)GRU_INT_CLEAR = 0x80000000; mb(); @@ -77,9 +77,9 @@ alcor_isa_mask_and_ack_irq(unsigned int irq) static struct irq_chip alcor_irq_type = { .name = "ALCOR", - .unmask = alcor_enable_irq, - .mask = alcor_disable_irq, - .mask_ack = alcor_mask_and_ack_irq, + .irq_unmask = alcor_enable_irq, + .irq_mask = alcor_disable_irq, + .irq_mask_ack = alcor_mask_and_ack_irq, }; static void @@ -126,9 +126,9 @@ alcor_init_irq(void) if (i >= 16+20 && i <= 16+30) continue; set_irq_chip_and_handler(i, &alcor_irq_type, handle_level_irq); - irq_to_desc(i)->status |= IRQ_LEVEL; + irq_set_status_flags(i, IRQ_LEVEL); } - i8259a_irq_type.ack = alcor_isa_mask_and_ack_irq; + i8259a_irq_type.irq_ack = alcor_isa_mask_and_ack_irq; init_i8259a_irqs(); common_init_isa_dma(); diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index b0c9164..57eb630 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -46,22 +46,22 @@ cabriolet_update_irq_hw(unsigned int irq, unsigned long mask) } static inline void -cabriolet_enable_irq(unsigned int irq) +cabriolet_enable_irq(struct irq_data *d) { - cabriolet_update_irq_hw(irq, cached_irq_mask &= ~(1UL << irq)); + cabriolet_update_irq_hw(d->irq, cached_irq_mask &= ~(1UL << d->irq)); } static void -cabriolet_disable_irq(unsigned int irq) +cabriolet_disable_irq(struct irq_data *d) { - cabriolet_update_irq_hw(irq, cached_irq_mask |= 1UL << irq); + cabriolet_update_irq_hw(d->irq, cached_irq_mask |= 1UL << d->irq); } static struct irq_chip cabriolet_irq_type = { .name = "CABRIOLET", - .unmask = cabriolet_enable_irq, - .mask = cabriolet_disable_irq, - .mask_ack = cabriolet_disable_irq, + .irq_unmask = cabriolet_enable_irq, + .irq_mask = cabriolet_disable_irq, + .irq_mask_ack = cabriolet_disable_irq, }; static void @@ -107,7 +107,7 @@ common_init_irq(void (*srm_dev_int)(unsigned long v)) for (i = 16; i < 35; ++i) { set_irq_chip_and_handler(i, &cabriolet_irq_type, handle_level_irq); - irq_to_desc(i)->status |= IRQ_LEVEL; + irq_set_status_flags(i, IRQ_LEVEL); } } diff --git a/arch/alpha/kernel/sys_dp264.c b/arch/alpha/kernel/sys_dp264.c index edad5f7..481df4e 100644 --- a/arch/alpha/kernel/sys_dp264.c +++ b/arch/alpha/kernel/sys_dp264.c @@ -98,37 +98,37 @@ tsunami_update_irq_hw(unsigned long mask) } static void -dp264_enable_irq(unsigned int irq) +dp264_enable_irq(struct irq_data *d) { spin_lock(&dp264_irq_lock); - cached_irq_mask |= 1UL << irq; + cached_irq_mask |= 1UL << d->irq; tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); } static void -dp264_disable_irq(unsigned int irq) +dp264_disable_irq(struct irq_data *d) { spin_lock(&dp264_irq_lock); - cached_irq_mask &= ~(1UL << irq); + cached_irq_mask &= ~(1UL << d->irq); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); } static void -clipper_enable_irq(unsigned int irq) +clipper_enable_irq(struct irq_data *d) { spin_lock(&dp264_irq_lock); - cached_irq_mask |= 1UL << (irq - 16); + cached_irq_mask |= 1UL << (d->irq - 16); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); } static void -clipper_disable_irq(unsigned int irq) +clipper_disable_irq(struct irq_data *d) { spin_lock(&dp264_irq_lock); - cached_irq_mask &= ~(1UL << (irq - 16)); + cached_irq_mask &= ~(1UL << (d->irq - 16)); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); } @@ -149,10 +149,11 @@ cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } static int -dp264_set_affinity(unsigned int irq, const struct cpumask *affinity) -{ +dp264_set_affinity(struct irq_data *d, const struct cpumask *affinity, + bool force) +{ spin_lock(&dp264_irq_lock); - cpu_set_irq_affinity(irq, *affinity); + cpu_set_irq_affinity(d->irq, *affinity); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); @@ -160,10 +161,11 @@ dp264_set_affinity(unsigned int irq, const struct cpumask *affinity) } static int -clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) -{ +clipper_set_affinity(struct irq_data *d, const struct cpumask *affinity, + bool force) +{ spin_lock(&dp264_irq_lock); - cpu_set_irq_affinity(irq - 16, *affinity); + cpu_set_irq_affinity(d->irq - 16, *affinity); tsunami_update_irq_hw(cached_irq_mask); spin_unlock(&dp264_irq_lock); @@ -171,19 +173,19 @@ clipper_set_affinity(unsigned int irq, const struct cpumask *affinity) } static struct irq_chip dp264_irq_type = { - .name = "DP264", - .unmask = dp264_enable_irq, - .mask = dp264_disable_irq, - .mask_ack = dp264_disable_irq, - .set_affinity = dp264_set_affinity, + .name = "DP264", + .irq_unmask = dp264_enable_irq, + .irq_mask = dp264_disable_irq, + .irq_mask_ack = dp264_disable_irq, + .irq_set_affinity = dp264_set_affinity, }; static struct irq_chip clipper_irq_type = { - .name = "CLIPPER", - .unmask = clipper_enable_irq, - .mask = clipper_disable_irq, - .mask_ack = clipper_disable_irq, - .set_affinity = clipper_set_affinity, + .name = "CLIPPER", + .irq_unmask = clipper_enable_irq, + .irq_mask = clipper_disable_irq, + .irq_mask_ack = clipper_disable_irq, + .irq_set_affinity = clipper_set_affinity, }; static void @@ -268,8 +270,8 @@ init_tsunami_irqs(struct irq_chip * ops, int imin, int imax) { long i; for (i = imin; i <= imax; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, ops, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } } diff --git a/arch/alpha/kernel/sys_eb64p.c b/arch/alpha/kernel/sys_eb64p.c index ae5f29d..402e908 100644 --- a/arch/alpha/kernel/sys_eb64p.c +++ b/arch/alpha/kernel/sys_eb64p.c @@ -44,22 +44,22 @@ eb64p_update_irq_hw(unsigned int irq, unsigned long mask) } static inline void -eb64p_enable_irq(unsigned int irq) +eb64p_enable_irq(struct irq_data *d) { - eb64p_update_irq_hw(irq, cached_irq_mask &= ~(1 << irq)); + eb64p_update_irq_hw(d->irq, cached_irq_mask &= ~(1 << d->irq)); } static void -eb64p_disable_irq(unsigned int irq) +eb64p_disable_irq(struct irq_data *d) { - eb64p_update_irq_hw(irq, cached_irq_mask |= 1 << irq); + eb64p_update_irq_hw(d->irq, cached_irq_mask |= 1 << d->irq); } static struct irq_chip eb64p_irq_type = { .name = "EB64P", - .unmask = eb64p_enable_irq, - .mask = eb64p_disable_irq, - .mask_ack = eb64p_disable_irq, + .irq_unmask = eb64p_enable_irq, + .irq_mask = eb64p_disable_irq, + .irq_mask_ack = eb64p_disable_irq, }; static void @@ -118,9 +118,9 @@ eb64p_init_irq(void) init_i8259a_irqs(); for (i = 16; i < 32; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &eb64p_irq_type, handle_level_irq); - } + irq_set_status_flags(i, IRQ_LEVEL); + } common_init_isa_dma(); setup_irq(16+5, &isa_cascade_irqaction); diff --git a/arch/alpha/kernel/sys_eiger.c b/arch/alpha/kernel/sys_eiger.c index 1121bc5..0b44a54 100644 --- a/arch/alpha/kernel/sys_eiger.c +++ b/arch/alpha/kernel/sys_eiger.c @@ -51,16 +51,18 @@ eiger_update_irq_hw(unsigned long irq, unsigned long mask) } static inline void -eiger_enable_irq(unsigned int irq) +eiger_enable_irq(struct irq_data *d) { + unsigned int irq = d->irq; unsigned long mask; mask = (cached_irq_mask[irq >= 64] &= ~(1UL << (irq & 63))); eiger_update_irq_hw(irq, mask); } static void -eiger_disable_irq(unsigned int irq) +eiger_disable_irq(struct irq_data *d) { + unsigned int irq = d->irq; unsigned long mask; mask = (cached_irq_mask[irq >= 64] |= 1UL << (irq & 63)); eiger_update_irq_hw(irq, mask); @@ -68,9 +70,9 @@ eiger_disable_irq(unsigned int irq) static struct irq_chip eiger_irq_type = { .name = "EIGER", - .unmask = eiger_enable_irq, - .mask = eiger_disable_irq, - .mask_ack = eiger_disable_irq, + .irq_unmask = eiger_enable_irq, + .irq_mask = eiger_disable_irq, + .irq_mask_ack = eiger_disable_irq, }; static void @@ -136,8 +138,8 @@ eiger_init_irq(void) init_i8259a_irqs(); for (i = 16; i < 128; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &eiger_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } } diff --git a/arch/alpha/kernel/sys_jensen.c b/arch/alpha/kernel/sys_jensen.c index 34f55e0..00341b7 100644 --- a/arch/alpha/kernel/sys_jensen.c +++ b/arch/alpha/kernel/sys_jensen.c @@ -63,34 +63,34 @@ */ static void -jensen_local_enable(unsigned int irq) +jensen_local_enable(struct irq_data *d) { /* the parport is really hw IRQ 1, silly Jensen. */ - if (irq == 7) - i8259a_enable_irq(1); + if (d->irq == 7) + i8259a_enable_irq(d); } static void -jensen_local_disable(unsigned int irq) +jensen_local_disable(struct irq_data *d) { /* the parport is really hw IRQ 1, silly Jensen. */ - if (irq == 7) - i8259a_disable_irq(1); + if (d->irq == 7) + i8259a_disable_irq(d); } static void -jensen_local_mask_ack(unsigned int irq) +jensen_local_mask_ack(struct irq_data *d) { /* the parport is really hw IRQ 1, silly Jensen. */ - if (irq == 7) - i8259a_mask_and_ack_irq(1); + if (d->irq == 7) + i8259a_mask_and_ack_irq(d); } static struct irq_chip jensen_local_irq_type = { .name = "LOCAL", - .unmask = jensen_local_enable, - .mask = jensen_local_disable, - .mask_ack = jensen_local_mask_ack, + .irq_unmask = jensen_local_enable, + .irq_mask = jensen_local_disable, + .irq_mask_ack = jensen_local_mask_ack, }; static void diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index 2bfc9f1..e619107 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -104,9 +104,10 @@ io7_get_irq_ctl(unsigned int irq, struct io7 **pio7) } static void -io7_enable_irq(unsigned int irq) +io7_enable_irq(struct irq_data *d) { volatile unsigned long *ctl; + unsigned int irq = d->irq; struct io7 *io7; ctl = io7_get_irq_ctl(irq, &io7); @@ -115,7 +116,7 @@ io7_enable_irq(unsigned int irq) __func__, irq); return; } - + spin_lock(&io7->irq_lock); *ctl |= 1UL << 24; mb(); @@ -124,9 +125,10 @@ io7_enable_irq(unsigned int irq) } static void -io7_disable_irq(unsigned int irq) +io7_disable_irq(struct irq_data *d) { volatile unsigned long *ctl; + unsigned int irq = d->irq; struct io7 *io7; ctl = io7_get_irq_ctl(irq, &io7); @@ -135,7 +137,7 @@ io7_disable_irq(unsigned int irq) __func__, irq); return; } - + spin_lock(&io7->irq_lock); *ctl &= ~(1UL << 24); mb(); @@ -144,35 +146,29 @@ io7_disable_irq(unsigned int irq) } static void -marvel_irq_noop(unsigned int irq) -{ - return; -} - -static unsigned int -marvel_irq_noop_return(unsigned int irq) -{ - return 0; +marvel_irq_noop(struct irq_data *d) +{ + return; } static struct irq_chip marvel_legacy_irq_type = { .name = "LEGACY", - .mask = marvel_irq_noop, - .unmask = marvel_irq_noop, + .irq_mask = marvel_irq_noop, + .irq_unmask = marvel_irq_noop, }; static struct irq_chip io7_lsi_irq_type = { .name = "LSI", - .unmask = io7_enable_irq, - .mask = io7_disable_irq, - .mask_ack = io7_disable_irq, + .irq_unmask = io7_enable_irq, + .irq_mask = io7_disable_irq, + .irq_mask_ack = io7_disable_irq, }; static struct irq_chip io7_msi_irq_type = { .name = "MSI", - .unmask = io7_enable_irq, - .mask = io7_disable_irq, - .ack = marvel_irq_noop, + .irq_unmask = io7_enable_irq, + .irq_mask = io7_disable_irq, + .irq_ack = marvel_irq_noop, }; static void @@ -280,8 +276,8 @@ init_io7_irqs(struct io7 *io7, /* Set up the lsi irqs. */ for (i = 0; i < 128; ++i) { - irq_to_desc(base + i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(base + i, lsi_ops, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } /* Disable the implemented irqs in hardware. */ @@ -294,8 +290,8 @@ init_io7_irqs(struct io7 *io7, /* Set up the msi irqs. */ for (i = 128; i < (128 + 512); ++i) { - irq_to_desc(base + i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(base + i, msi_ops, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } for (i = 0; i < 16; ++i) diff --git a/arch/alpha/kernel/sys_mikasa.c b/arch/alpha/kernel/sys_mikasa.c index bcc1639..cf7f43d 100644 --- a/arch/alpha/kernel/sys_mikasa.c +++ b/arch/alpha/kernel/sys_mikasa.c @@ -43,22 +43,22 @@ mikasa_update_irq_hw(int mask) } static inline void -mikasa_enable_irq(unsigned int irq) +mikasa_enable_irq(struct irq_data *d) { - mikasa_update_irq_hw(cached_irq_mask |= 1 << (irq - 16)); + mikasa_update_irq_hw(cached_irq_mask |= 1 << (d->irq - 16)); } static void -mikasa_disable_irq(unsigned int irq) +mikasa_disable_irq(struct irq_data *d) { - mikasa_update_irq_hw(cached_irq_mask &= ~(1 << (irq - 16))); + mikasa_update_irq_hw(cached_irq_mask &= ~(1 << (d->irq - 16))); } static struct irq_chip mikasa_irq_type = { .name = "MIKASA", - .unmask = mikasa_enable_irq, - .mask = mikasa_disable_irq, - .mask_ack = mikasa_disable_irq, + .irq_unmask = mikasa_enable_irq, + .irq_mask = mikasa_disable_irq, + .irq_mask_ack = mikasa_disable_irq, }; static void @@ -98,8 +98,8 @@ mikasa_init_irq(void) mikasa_update_irq_hw(0); for (i = 16; i < 32; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &mikasa_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } init_i8259a_irqs(); diff --git a/arch/alpha/kernel/sys_noritake.c b/arch/alpha/kernel/sys_noritake.c index e88f4ae..92bc188 100644 --- a/arch/alpha/kernel/sys_noritake.c +++ b/arch/alpha/kernel/sys_noritake.c @@ -48,22 +48,22 @@ noritake_update_irq_hw(int irq, int mask) } static void -noritake_enable_irq(unsigned int irq) +noritake_enable_irq(struct irq_data *d) { - noritake_update_irq_hw(irq, cached_irq_mask |= 1 << (irq - 16)); + noritake_update_irq_hw(d->irq, cached_irq_mask |= 1 << (d->irq - 16)); } static void -noritake_disable_irq(unsigned int irq) +noritake_disable_irq(struct irq_data *d) { - noritake_update_irq_hw(irq, cached_irq_mask &= ~(1 << (irq - 16))); + noritake_update_irq_hw(d->irq, cached_irq_mask &= ~(1 << (d->irq - 16))); } static struct irq_chip noritake_irq_type = { .name = "NORITAKE", - .unmask = noritake_enable_irq, - .mask = noritake_disable_irq, - .mask_ack = noritake_disable_irq, + .irq_unmask = noritake_enable_irq, + .irq_mask = noritake_disable_irq, + .irq_mask_ack = noritake_disable_irq, }; static void @@ -127,8 +127,8 @@ noritake_init_irq(void) outw(0, 0x54c); for (i = 16; i < 48; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &noritake_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } init_i8259a_irqs(); diff --git a/arch/alpha/kernel/sys_rawhide.c b/arch/alpha/kernel/sys_rawhide.c index 6a51364..936d414 100644 --- a/arch/alpha/kernel/sys_rawhide.c +++ b/arch/alpha/kernel/sys_rawhide.c @@ -56,9 +56,10 @@ rawhide_update_irq_hw(int hose, int mask) (((h) < MCPCIA_MAX_HOSES) && (cached_irq_masks[(h)] != 0)) static inline void -rawhide_enable_irq(unsigned int irq) +rawhide_enable_irq(struct irq_data *d) { unsigned int mask, hose; + unsigned int irq = d->irq; irq -= 16; hose = irq / 24; @@ -76,9 +77,10 @@ rawhide_enable_irq(unsigned int irq) } static void -rawhide_disable_irq(unsigned int irq) +rawhide_disable_irq(struct irq_data *d) { unsigned int mask, hose; + unsigned int irq = d->irq; irq -= 16; hose = irq / 24; @@ -96,9 +98,10 @@ rawhide_disable_irq(unsigned int irq) } static void -rawhide_mask_and_ack_irq(unsigned int irq) +rawhide_mask_and_ack_irq(struct irq_data *d) { unsigned int mask, mask1, hose; + unsigned int irq = d->irq; irq -= 16; hose = irq / 24; @@ -123,9 +126,9 @@ rawhide_mask_and_ack_irq(unsigned int irq) static struct irq_chip rawhide_irq_type = { .name = "RAWHIDE", - .unmask = rawhide_enable_irq, - .mask = rawhide_disable_irq, - .mask_ack = rawhide_mask_and_ack_irq, + .irq_unmask = rawhide_enable_irq, + .irq_mask = rawhide_disable_irq, + .irq_mask_ack = rawhide_mask_and_ack_irq, }; static void @@ -177,8 +180,8 @@ rawhide_init_irq(void) } for (i = 16; i < 128; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &rawhide_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } init_i8259a_irqs(); diff --git a/arch/alpha/kernel/sys_rx164.c b/arch/alpha/kernel/sys_rx164.c index 89e7e37e..cea22a6 100644 --- a/arch/alpha/kernel/sys_rx164.c +++ b/arch/alpha/kernel/sys_rx164.c @@ -47,22 +47,22 @@ rx164_update_irq_hw(unsigned long mask) } static inline void -rx164_enable_irq(unsigned int irq) +rx164_enable_irq(struct irq_data *d) { - rx164_update_irq_hw(cached_irq_mask |= 1UL << (irq - 16)); + rx164_update_irq_hw(cached_irq_mask |= 1UL << (d->irq - 16)); } static void -rx164_disable_irq(unsigned int irq) +rx164_disable_irq(struct irq_data *d) { - rx164_update_irq_hw(cached_irq_mask &= ~(1UL << (irq - 16))); + rx164_update_irq_hw(cached_irq_mask &= ~(1UL << (d->irq - 16))); } static struct irq_chip rx164_irq_type = { .name = "RX164", - .unmask = rx164_enable_irq, - .mask = rx164_disable_irq, - .mask_ack = rx164_disable_irq, + .irq_unmask = rx164_enable_irq, + .irq_mask = rx164_disable_irq, + .irq_mask_ack = rx164_disable_irq, }; static void @@ -99,8 +99,8 @@ rx164_init_irq(void) rx164_update_irq_hw(0); for (i = 16; i < 40; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &rx164_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } init_i8259a_irqs(); diff --git a/arch/alpha/kernel/sys_sable.c b/arch/alpha/kernel/sys_sable.c index 5c4423d..a349538 100644 --- a/arch/alpha/kernel/sys_sable.c +++ b/arch/alpha/kernel/sys_sable.c @@ -443,11 +443,11 @@ lynx_swizzle(struct pci_dev *dev, u8 *pinp) /* GENERIC irq routines */ static inline void -sable_lynx_enable_irq(unsigned int irq) +sable_lynx_enable_irq(struct irq_data *d) { unsigned long bit, mask; - bit = sable_lynx_irq_swizzle->irq_to_mask[irq]; + bit = sable_lynx_irq_swizzle->irq_to_mask[d->irq]; spin_lock(&sable_lynx_irq_lock); mask = sable_lynx_irq_swizzle->shadow_mask &= ~(1UL << bit); sable_lynx_irq_swizzle->update_irq_hw(bit, mask); @@ -459,11 +459,11 @@ sable_lynx_enable_irq(unsigned int irq) } static void -sable_lynx_disable_irq(unsigned int irq) +sable_lynx_disable_irq(struct irq_data *d) { unsigned long bit, mask; - bit = sable_lynx_irq_swizzle->irq_to_mask[irq]; + bit = sable_lynx_irq_swizzle->irq_to_mask[d->irq]; spin_lock(&sable_lynx_irq_lock); mask = sable_lynx_irq_swizzle->shadow_mask |= 1UL << bit; sable_lynx_irq_swizzle->update_irq_hw(bit, mask); @@ -475,11 +475,11 @@ sable_lynx_disable_irq(unsigned int irq) } static void -sable_lynx_mask_and_ack_irq(unsigned int irq) +sable_lynx_mask_and_ack_irq(struct irq_data *d) { unsigned long bit, mask; - bit = sable_lynx_irq_swizzle->irq_to_mask[irq]; + bit = sable_lynx_irq_swizzle->irq_to_mask[d->irq]; spin_lock(&sable_lynx_irq_lock); mask = sable_lynx_irq_swizzle->shadow_mask |= 1UL << bit; sable_lynx_irq_swizzle->update_irq_hw(bit, mask); @@ -489,9 +489,9 @@ sable_lynx_mask_and_ack_irq(unsigned int irq) static struct irq_chip sable_lynx_irq_type = { .name = "SABLE/LYNX", - .unmask = sable_lynx_enable_irq, - .mask = sable_lynx_disable_irq, - .mask_ack = sable_lynx_mask_and_ack_irq, + .irq_unmask = sable_lynx_enable_irq, + .irq_mask = sable_lynx_disable_irq, + .irq_mask_ack = sable_lynx_mask_and_ack_irq, }; static void @@ -518,9 +518,9 @@ sable_lynx_init_irq(int nr_of_irqs) long i; for (i = 0; i < nr_of_irqs; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &sable_lynx_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } common_init_isa_dma(); diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index f8a1e8a..42a5331 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -45,16 +45,18 @@ takara_update_irq_hw(unsigned long irq, unsigned long mask) } static inline void -takara_enable_irq(unsigned int irq) +takara_enable_irq(struct irq_data *d) { + unsigned int irq = d->irq; unsigned long mask; mask = (cached_irq_mask[irq >= 64] &= ~(1UL << (irq & 63))); takara_update_irq_hw(irq, mask); } static void -takara_disable_irq(unsigned int irq) +takara_disable_irq(struct irq_data *d) { + unsigned int irq = d->irq; unsigned long mask; mask = (cached_irq_mask[irq >= 64] |= 1UL << (irq & 63)); takara_update_irq_hw(irq, mask); @@ -62,9 +64,9 @@ takara_disable_irq(unsigned int irq) static struct irq_chip takara_irq_type = { .name = "TAKARA", - .unmask = takara_enable_irq, - .mask = takara_disable_irq, - .mask_ack = takara_disable_irq, + .irq_unmask = takara_enable_irq, + .irq_mask = takara_disable_irq, + .irq_mask_ack = takara_disable_irq, }; static void @@ -136,8 +138,8 @@ takara_init_irq(void) takara_update_irq_hw(i, -1); for (i = 16; i < 128; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, &takara_irq_type, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } common_init_isa_dma(); diff --git a/arch/alpha/kernel/sys_titan.c b/arch/alpha/kernel/sys_titan.c index e02494b..8c13a0c 100644 --- a/arch/alpha/kernel/sys_titan.c +++ b/arch/alpha/kernel/sys_titan.c @@ -112,8 +112,9 @@ titan_update_irq_hw(unsigned long mask) } static inline void -titan_enable_irq(unsigned int irq) +titan_enable_irq(struct irq_data *d) { + unsigned int irq = d->irq; spin_lock(&titan_irq_lock); titan_cached_irq_mask |= 1UL << (irq - 16); titan_update_irq_hw(titan_cached_irq_mask); @@ -121,8 +122,9 @@ titan_enable_irq(unsigned int irq) } static inline void -titan_disable_irq(unsigned int irq) +titan_disable_irq(struct irq_data *d) { + unsigned int irq = d->irq; spin_lock(&titan_irq_lock); titan_cached_irq_mask &= ~(1UL << (irq - 16)); titan_update_irq_hw(titan_cached_irq_mask); @@ -144,8 +146,10 @@ titan_cpu_set_irq_affinity(unsigned int irq, cpumask_t affinity) } static int -titan_set_irq_affinity(unsigned int irq, const struct cpumask *affinity) +titan_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity, + bool force) { + unsigned int irq = d->irq; spin_lock(&titan_irq_lock); titan_cpu_set_irq_affinity(irq - 16, *affinity); titan_update_irq_hw(titan_cached_irq_mask); @@ -175,17 +179,17 @@ init_titan_irqs(struct irq_chip * ops, int imin, int imax) { long i; for (i = imin; i <= imax; ++i) { - irq_to_desc(i)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i, ops, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); } } static struct irq_chip titan_irq_type = { - .name = "TITAN", - .unmask = titan_enable_irq, - .mask = titan_disable_irq, - .mask_ack = titan_disable_irq, - .set_affinity = titan_set_irq_affinity, + .name = "TITAN", + .irq_unmask = titan_enable_irq, + .irq_mask = titan_disable_irq, + .irq_mask_ack = titan_disable_irq, + .irq_set_affinity = titan_set_irq_affinity, }; static irqreturn_t diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index eec5259..ca60a38 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -104,10 +104,12 @@ wildfire_init_irq_hw(void) } static void -wildfire_enable_irq(unsigned int irq) +wildfire_enable_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < 16) - i8259a_enable_irq(irq); + i8259a_enable_irq(d); spin_lock(&wildfire_irq_lock); set_bit(irq, &cached_irq_mask); @@ -116,10 +118,12 @@ wildfire_enable_irq(unsigned int irq) } static void -wildfire_disable_irq(unsigned int irq) +wildfire_disable_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < 16) - i8259a_disable_irq(irq); + i8259a_disable_irq(d); spin_lock(&wildfire_irq_lock); clear_bit(irq, &cached_irq_mask); @@ -128,10 +132,12 @@ wildfire_disable_irq(unsigned int irq) } static void -wildfire_mask_and_ack_irq(unsigned int irq) +wildfire_mask_and_ack_irq(struct irq_data *d) { + unsigned int irq = d->irq; + if (irq < 16) - i8259a_mask_and_ack_irq(irq); + i8259a_mask_and_ack_irq(d); spin_lock(&wildfire_irq_lock); clear_bit(irq, &cached_irq_mask); @@ -141,9 +147,9 @@ wildfire_mask_and_ack_irq(unsigned int irq) static struct irq_chip wildfire_irq_type = { .name = "WILDFIRE", - .unmask = wildfire_enable_irq, - .mask = wildfire_disable_irq, - .mask_ack = wildfire_mask_and_ack_irq, + .irq_unmask = wildfire_enable_irq, + .irq_mask = wildfire_disable_irq, + .irq_mask_ack = wildfire_mask_and_ack_irq, }; static void __init @@ -177,21 +183,21 @@ wildfire_init_irq_per_pca(int qbbno, int pcano) for (i = 0; i < 16; ++i) { if (i == 2) continue; - irq_to_desc(i+irq_bias)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i+irq_bias, &wildfire_irq_type, handle_level_irq); + irq_set_status_flags(i + irq_bias, IRQ_LEVEL); } - irq_to_desc(36+irq_bias)->status |= IRQ_LEVEL; set_irq_chip_and_handler(36+irq_bias, &wildfire_irq_type, handle_level_irq); + irq_set_status_flags(36 + irq_bias, IRQ_LEVEL); for (i = 40; i < 64; ++i) { - irq_to_desc(i+irq_bias)->status |= IRQ_LEVEL; set_irq_chip_and_handler(i+irq_bias, &wildfire_irq_type, handle_level_irq); + irq_set_status_flags(i + irq_bias, IRQ_LEVEL); } - setup_irq(32+irq_bias, &isa_enable); + setup_irq(32+irq_bias, &isa_enable); } static void __init diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5cff165..166efa2 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1177,6 +1177,31 @@ config ARM_ERRATA_743622 visible impact on the overall performance or power consumption of the processor. +config ARM_ERRATA_751472 + bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation" + depends on CPU_V7 && SMP + help + This option enables the workaround for the 751472 Cortex-A9 (prior + to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the + completion of a following broadcasted operation if the second + operation is received by a CPU before the ICIALLUIS has completed, + potentially leading to corrupted entries in the cache or TLB. + +config ARM_ERRATA_753970 + bool "ARM errata: cache sync operation may be faulty" + depends on CACHE_PL310 + help + This option enables the workaround for the 753970 PL310 (r3p0) erratum. + + Under some condition the effect of cache sync operation on + the store buffer still remains when the operation completes. + This means that the store buffer is always asked to drain and + this prevents it from merging any further writes. The workaround + is to replace the normal offset of cache sync operation (0x730) + by another offset targeting an unmapped PL310 register 0x740. + This has the same effect as the cache sync operation: store buffer + drain and waiting for all buffers empty. + endmenu source "arch/arm/common/Kconfig" @@ -1391,7 +1416,7 @@ config AEABI config OABI_COMPAT bool "Allow old ABI binaries to run with this kernel (EXPERIMENTAL)" - depends on AEABI && EXPERIMENTAL + depends on AEABI && EXPERIMENTAL && !THUMB2_KERNEL default y help This option preserves the old syscall interface along with the diff --git a/arch/arm/Makefile b/arch/arm/Makefile index c22c1ad..6f7b292 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -15,7 +15,7 @@ ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 endif -OBJCOPYFLAGS :=-O binary -R .note -R .note.gnu.build-id -R .comment -S +OBJCOPYFLAGS :=-O binary -R .comment -S GZFLAGS :=-9 #KBUILD_CFLAGS +=-pipe # Explicitly specifiy 32-bit ARM ISA since toolchain default can be -mthumb: diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore index ab204db..c602896 100644 --- a/arch/arm/boot/compressed/.gitignore +++ b/arch/arm/boot/compressed/.gitignore @@ -1,3 +1,7 @@ font.c -piggy.gz +lib1funcs.S +piggy.gzip +piggy.lzo +piggy.lzma +vmlinux vmlinux.lds diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig index 778655f..ea5ee4d 100644 --- a/arch/arm/common/Kconfig +++ b/arch/arm/common/Kconfig @@ -6,6 +6,8 @@ config ARM_VIC config ARM_VIC_NR int + default 4 if ARCH_S5PV210 + default 3 if ARCH_S5P6442 || ARCH_S5PC100 default 2 depends on ARM_VIC help diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index b33fe70..199a6b6 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -35,7 +35,7 @@ : "cc", "memory") static inline int -futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -46,7 +46,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); /* implies preempt_disable() */ @@ -88,36 +88,35 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - int val; + int ret = 0; + u32 val; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ - __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" - "1: " T(ldr) " %0, [%3]\n" - " teq %0, %1\n" + "1: " T(ldr) " %1, [%4]\n" + " teq %1, %2\n" " it eq @ explicit IT needed for the 2b label\n" - "2: " T(streq) " %2, [%3]\n" + "2: " T(streq) " %3, [%4]\n" "3:\n" " .pushsection __ex_table,\"a\"\n" " .align 3\n" " .long 1b, 4f, 2b, 4f\n" " .popsection\n" " .pushsection .fixup,\"ax\"\n" - "4: mov %0, %4\n" + "4: mov %0, %5\n" " b 3b\n" " .popsection" - : "=&r" (val) + : "+r" (ret), "=&r" (val) : "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT) : "cc", "memory"); - pagefault_enable(); /* subsumes preempt_enable() */ - - return val; + *uval = val; + return ret; } #endif /* !SMP */ diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h index 5aeec1e..16bd480 100644 --- a/arch/arm/include/asm/hardware/cache-l2x0.h +++ b/arch/arm/include/asm/hardware/cache-l2x0.h @@ -36,6 +36,7 @@ #define L2X0_RAW_INTR_STAT 0x21C #define L2X0_INTR_CLEAR 0x220 #define L2X0_CACHE_SYNC 0x730 +#define L2X0_DUMMY_REG 0x740 #define L2X0_INV_LINE_PA 0x770 #define L2X0_INV_WAY 0x77C #define L2X0_CLEAN_LINE_PA 0x7B0 diff --git a/arch/arm/include/asm/hardware/sp810.h b/arch/arm/include/asm/hardware/sp810.h index 721847d..e0d1c0c 100644 --- a/arch/arm/include/asm/hardware/sp810.h +++ b/arch/arm/include/asm/hardware/sp810.h @@ -58,6 +58,9 @@ static inline void sysctl_soft_reset(void __iomem *base) { + /* switch to slow mode */ + writel(0x2, base + SCCTRL); + /* writing any value to SCSYSSTAT reg will reset system */ writel(0, base + SCSYSSTAT); } diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index 20e0f7c..d66605de 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -95,6 +95,15 @@ static inline void __iomem *__typesafe_io(unsigned long addr) return (void __iomem *)addr; } +/* IO barriers */ +#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + /* * Now, pick up the machine-defined IO definitions */ @@ -125,17 +134,17 @@ static inline void __iomem *__typesafe_io(unsigned long addr) * The {in,out}[bwl] macros are for emulating x86-style PCI/ISA IO space. */ #ifdef __io -#define outb(v,p) __raw_writeb(v,__io(p)) -#define outw(v,p) __raw_writew((__force __u16) \ - cpu_to_le16(v),__io(p)) -#define outl(v,p) __raw_writel((__force __u32) \ - cpu_to_le32(v),__io(p)) +#define outb(v,p) ({ __iowmb(); __raw_writeb(v,__io(p)); }) +#define outw(v,p) ({ __iowmb(); __raw_writew((__force __u16) \ + cpu_to_le16(v),__io(p)); }) +#define outl(v,p) ({ __iowmb(); __raw_writel((__force __u32) \ + cpu_to_le32(v),__io(p)); }) -#define inb(p) ({ __u8 __v = __raw_readb(__io(p)); __v; }) +#define inb(p) ({ __u8 __v = __raw_readb(__io(p)); __iormb(); __v; }) #define inw(p) ({ __u16 __v = le16_to_cpu((__force __le16) \ - __raw_readw(__io(p))); __v; }) + __raw_readw(__io(p))); __iormb(); __v; }) #define inl(p) ({ __u32 __v = le32_to_cpu((__force __le32) \ - __raw_readl(__io(p))); __v; }) + __raw_readl(__io(p))); __iormb(); __v; }) #define outsb(p,d,l) __raw_writesb(__io(p),d,l) #define outsw(p,d,l) __raw_writesw(__io(p),d,l) @@ -192,14 +201,6 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define writel_relaxed(v,c) ((void)__raw_writel((__force u32) \ cpu_to_le32(v),__mem_pci(c))) -#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE -#define __iormb() rmb() -#define __iowmb() wmb() -#else -#define __iormb() do { } while (0) -#define __iowmb() do { } while (0) -#endif - #define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(); __v; }) #define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(); __v; }) #define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(); __v; }) diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 3a0893a..bf13b81 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -15,10 +15,6 @@ struct meminfo; struct sys_timer; struct machine_desc { - /* - * Note! The first two elements are used - * by assembler code in head.S, head-common.S - */ unsigned int nr; /* architecture number */ const char *name; /* architecture name */ unsigned long boot_params; /* tagged list */ diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 9763be0..22de005 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -10,6 +10,8 @@ #ifndef _ASMARM_PGALLOC_H #define _ASMARM_PGALLOC_H +#include <linux/pagemap.h> + #include <asm/domain.h> #include <asm/pgtable-hwdef.h> #include <asm/processor.h> diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index f41a6f5..82dfe5d 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -18,16 +18,34 @@ #define __ASMARM_TLB_H #include <asm/cacheflush.h> -#include <asm/tlbflush.h> #ifndef CONFIG_MMU #include <linux/pagemap.h> + +#define tlb_flush(tlb) ((void) tlb) + #include <asm-generic/tlb.h> #else /* !CONFIG_MMU */ +#include <linux/swap.h> #include <asm/pgalloc.h> +#include <asm/tlbflush.h> + +/* + * We need to delay page freeing for SMP as other CPUs can access pages + * which have been removed but not yet had their TLB entries invalidated. + * Also, as ARMv7 speculative prefetch can drag new entries into the TLB, + * we need to apply this same delaying tactic to ensure correct operation. + */ +#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7) +#define tlb_fast_mode(tlb) 0 +#define FREE_PTE_NR 500 +#else +#define tlb_fast_mode(tlb) 1 +#define FREE_PTE_NR 0 +#endif /* * TLB handling. This allows us to remove pages from the page @@ -36,12 +54,58 @@ struct mmu_gather { struct mm_struct *mm; unsigned int fullmm; + struct vm_area_struct *vma; unsigned long range_start; unsigned long range_end; + unsigned int nr; + struct page *pages[FREE_PTE_NR]; }; DECLARE_PER_CPU(struct mmu_gather, mmu_gathers); +/* + * This is unnecessarily complex. There's three ways the TLB shootdown + * code is used: + * 1. Unmapping a range of vmas. See zap_page_range(), unmap_region(). + * tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called. + * tlb->vma will be non-NULL. + * 2. Unmapping all vmas. See exit_mmap(). + * tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called. + * tlb->vma will be non-NULL. Additionally, page tables will be freed. + * 3. Unmapping argument pages. See shift_arg_pages(). + * tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called. + * tlb->vma will be NULL. + */ +static inline void tlb_flush(struct mmu_gather *tlb) +{ + if (tlb->fullmm || !tlb->vma) + flush_tlb_mm(tlb->mm); + else if (tlb->range_end > 0) { + flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end); + tlb->range_start = TASK_SIZE; + tlb->range_end = 0; + } +} + +static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr) +{ + if (!tlb->fullmm) { + if (addr < tlb->range_start) + tlb->range_start = addr; + if (addr + PAGE_SIZE > tlb->range_end) + tlb->range_end = addr + PAGE_SIZE; + } +} + +static inline void tlb_flush_mmu(struct mmu_gather *tlb) +{ + tlb_flush(tlb); + if (!tlb_fast_mode(tlb)) { + free_pages_and_swap_cache(tlb->pages, tlb->nr); + tlb->nr = 0; + } +} + static inline struct mmu_gather * tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) { @@ -49,6 +113,8 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) tlb->mm = mm; tlb->fullmm = full_mm_flush; + tlb->vma = NULL; + tlb->nr = 0; return tlb; } @@ -56,8 +122,7 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush) static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - if (tlb->fullmm) - flush_tlb_mm(tlb->mm); + tlb_flush_mmu(tlb); /* keep the page table cache within bounds */ check_pgt_cache(); @@ -71,12 +136,7 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) static inline void tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr) { - if (!tlb->fullmm) { - if (addr < tlb->range_start) - tlb->range_start = addr; - if (addr + PAGE_SIZE > tlb->range_end) - tlb->range_end = addr + PAGE_SIZE; - } + tlb_add_flush(tlb, addr); } /* @@ -89,6 +149,7 @@ tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (!tlb->fullmm) { flush_cache_range(vma, vma->vm_start, vma->vm_end); + tlb->vma = vma; tlb->range_start = TASK_SIZE; tlb->range_end = 0; } @@ -97,12 +158,30 @@ tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { - if (!tlb->fullmm && tlb->range_end > 0) - flush_tlb_range(vma, tlb->range_start, tlb->range_end); + if (!tlb->fullmm) + tlb_flush(tlb); +} + +static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) +{ + if (tlb_fast_mode(tlb)) { + free_page_and_swap_cache(page); + } else { + tlb->pages[tlb->nr++] = page; + if (tlb->nr >= FREE_PTE_NR) + tlb_flush_mmu(tlb); + } +} + +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, + unsigned long addr) +{ + pgtable_page_dtor(pte); + tlb_add_flush(tlb, addr); + tlb_remove_page(tlb, pte); } -#define tlb_remove_page(tlb,page) free_page_and_swap_cache(page) -#define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep) +#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr) #define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp) #define tlb_migrate_finish(mm) do { } while (0) diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index ce7378ea..d2005de 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -10,12 +10,7 @@ #ifndef _ASMARM_TLBFLUSH_H #define _ASMARM_TLBFLUSH_H - -#ifndef CONFIG_MMU - -#define tlb_flush(tlb) ((void) tlb) - -#else /* CONFIG_MMU */ +#ifdef CONFIG_MMU #include <asm/glue.h> diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index f17d9a0..f06ff9f 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -391,25 +391,24 @@ ENDPROC(__turn_mmu_on) #ifdef CONFIG_SMP_ON_UP + __INIT __fixup_smp: - mov r4, #0x00070000 - orr r3, r4, #0xff000000 @ mask 0xff070000 - orr r4, r4, #0x41000000 @ val 0x41070000 - and r0, r9, r3 - teq r0, r4 @ ARM CPU and ARMv6/v7? + and r3, r9, #0x000f0000 @ architecture version + teq r3, #0x000f0000 @ CPU ID supported? bne __fixup_smp_on_up @ no, assume UP - orr r3, r3, #0x0000ff00 - orr r3, r3, #0x000000f0 @ mask 0xff07fff0 + bic r3, r9, #0x00ff0000 + bic r3, r3, #0x0000000f @ mask 0xff00fff0 + mov r4, #0x41000000 orr r4, r4, #0x0000b000 - orr r4, r4, #0x00000020 @ val 0x4107b020 - and r0, r9, r3 - teq r0, r4 @ ARM 11MPCore? + orr r4, r4, #0x00000020 @ val 0x4100b020 + teq r3, r4 @ ARM 11MPCore? moveq pc, lr @ yes, assume SMP mrc p15, 0, r0, c0, c0, 5 @ read MPIDR - tst r0, #1 << 31 - movne pc, lr @ bit 31 => SMP + and r0, r0, #0xc0000000 @ multiprocessing extensions and + teq r0, #0x80000000 @ not part of a uniprocessor system? + moveq pc, lr @ yes, assume SMP __fixup_smp_on_up: adr r0, 1f @@ -417,18 +416,7 @@ __fixup_smp_on_up: sub r3, r0, r3 add r4, r4, r3 add r5, r5, r3 -2: cmp r4, r5 - movhs pc, lr - ldmia r4!, {r0, r6} - ARM( str r6, [r0, r3] ) - THUMB( add r0, r0, r3 ) -#ifdef __ARMEB__ - THUMB( mov r6, r6, ror #16 ) @ Convert word order for big-endian. -#endif - THUMB( strh r6, [r0], #2 ) @ For Thumb-2, store as two halfwords - THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r3. - THUMB( strh r6, [r0] ) - b 2b + b __do_fixup_smp_on_up ENDPROC(__fixup_smp) .align @@ -442,7 +430,31 @@ smp_on_up: ALT_SMP(.long 1) ALT_UP(.long 0) .popsection +#endif + .text +__do_fixup_smp_on_up: + cmp r4, r5 + movhs pc, lr + ldmia r4!, {r0, r6} + ARM( str r6, [r0, r3] ) + THUMB( add r0, r0, r3 ) +#ifdef __ARMEB__ + THUMB( mov r6, r6, ror #16 ) @ Convert word order for big-endian. #endif + THUMB( strh r6, [r0], #2 ) @ For Thumb-2, store as two halfwords + THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r3. + THUMB( strh r6, [r0] ) + b __do_fixup_smp_on_up +ENDPROC(__do_fixup_smp_on_up) + +ENTRY(fixup_smp) + stmfd sp!, {r4 - r6, lr} + mov r4, r0 + add r5, r0, r1 + mov r3, #0 + bl __do_fixup_smp_on_up + ldmfd sp!, {r4 - r6, pc} +ENDPROC(fixup_smp) #include "head-common.S" diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index c9f3f04..44b84fe 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -137,11 +137,10 @@ static u8 get_debug_arch(void) u32 didr; /* Do we implement the extended CPUID interface? */ - if (((read_cpuid_id() >> 16) & 0xf) != 0xf) { - pr_warning("CPUID feature registers not supported. " - "Assuming v6 debug is present.\n"); + if (WARN_ONCE((((read_cpuid_id() >> 16) & 0xf) != 0xf), + "CPUID feature registers not supported. " + "Assuming v6 debug is present.\n")) return ARM_DEBUG_ARCH_V6; - } ARM_DBG_READ(c0, 0, didr); return (didr >> 16) & 0xf; @@ -152,6 +151,12 @@ u8 arch_get_debug_arch(void) return debug_arch; } +static int debug_arch_supported(void) +{ + u8 arch = get_debug_arch(); + return arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14; +} + /* Determine number of BRP register available. */ static int get_num_brp_resources(void) { @@ -268,6 +273,9 @@ out: int hw_breakpoint_slots(int type) { + if (!debug_arch_supported()) + return 0; + /* * We can be called early, so don't rely on * our static variables being initialised. @@ -828,20 +836,33 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, /* * One-time initialisation. */ -static void reset_ctrl_regs(void *unused) +static void reset_ctrl_regs(void *info) { - int i; + int i, cpu = smp_processor_id(); + u32 dbg_power; + cpumask_t *cpumask = info; /* * v7 debug contains save and restore registers so that debug state - * can be maintained across low-power modes without leaving - * the debug logic powered up. It is IMPLEMENTATION DEFINED whether - * we can write to the debug registers out of reset, so we must - * unlock the OS Lock Access Register to avoid taking undefined - * instruction exceptions later on. + * can be maintained across low-power modes without leaving the debug + * logic powered up. It is IMPLEMENTATION DEFINED whether we can access + * the debug registers out of reset, so we must unlock the OS Lock + * Access Register to avoid taking undefined instruction exceptions + * later on. */ if (debug_arch >= ARM_DEBUG_ARCH_V7_ECP14) { /* + * Ensure sticky power-down is clear (i.e. debug logic is + * powered up). + */ + asm volatile("mrc p14, 0, %0, c1, c5, 4" : "=r" (dbg_power)); + if ((dbg_power & 0x1) == 0) { + pr_warning("CPU %d debug is powered down!\n", cpu); + cpumask_or(cpumask, cpumask, cpumask_of(cpu)); + return; + } + + /* * Unconditionally clear the lock by writing a value * other than 0xC5ACCE55 to the access register. */ @@ -879,10 +900,11 @@ static struct notifier_block __cpuinitdata dbg_reset_nb = { static int __init arch_hw_breakpoint_init(void) { u32 dscr; + cpumask_t cpumask = { CPU_BITS_NONE }; debug_arch = get_debug_arch(); - if (debug_arch > ARM_DEBUG_ARCH_V7_ECP14) { + if (!debug_arch_supported()) { pr_info("debug architecture 0x%x unsupported.\n", debug_arch); return 0; } @@ -899,18 +921,24 @@ static int __init arch_hw_breakpoint_init(void) pr_info("%d breakpoint(s) reserved for watchpoint " "single-step.\n", core_num_reserved_brps); + /* + * Reset the breakpoint resources. We assume that a halting + * debugger will leave the world in a nice state for us. + */ + on_each_cpu(reset_ctrl_regs, &cpumask, 1); + if (!cpumask_empty(&cpumask)) { + core_num_brps = 0; + core_num_reserved_brps = 0; + core_num_wrps = 0; + return 0; + } + ARM_DBG_READ(c1, 0, dscr); if (dscr & ARM_DSCR_HDBGEN) { + max_watchpoint_len = 4; pr_warning("halting debug mode enabled. Assuming maximum " - "watchpoint size of 4 bytes."); + "watchpoint size of %u bytes.", max_watchpoint_len); } else { - /* - * Reset the breakpoint resources. We assume that a halting - * debugger will leave the world in a nice state for us. - */ - smp_call_function(reset_ctrl_regs, NULL, 1); - reset_ctrl_regs(NULL); - /* Work out the maximum supported watchpoint length. */ max_watchpoint_len = get_max_wp_len(); pr_info("maximum watchpoint size is %u bytes.\n", diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c index 2c1f005..8f6ed43 100644 --- a/arch/arm/kernel/kprobes-decode.c +++ b/arch/arm/kernel/kprobes-decode.c @@ -1437,7 +1437,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) return space_cccc_1100_010x(insn, asi); - } else if ((insn & 0x0e000000) == 0x0c400000) { + } else if ((insn & 0x0e000000) == 0x0c000000) { return space_cccc_110x(insn, asi); diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 2cfe816..6d4105e 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -22,6 +22,7 @@ #include <asm/pgtable.h> #include <asm/sections.h> +#include <asm/smp_plat.h> #include <asm/unwind.h> #ifdef CONFIG_XIP_KERNEL @@ -268,12 +269,28 @@ struct mod_unwind_map { const Elf_Shdr *txt_sec; }; +static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr, + const Elf_Shdr *sechdrs, const char *name) +{ + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; + + return NULL; +} + +extern void fixup_smp(const void *, unsigned long); + int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { + const Elf_Shdr * __maybe_unused s = NULL; #ifdef CONFIG_ARM_UNWIND const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - const Elf_Shdr *s, *sechdrs_end = sechdrs + hdr->e_shnum; + const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum; struct mod_unwind_map maps[ARM_SEC_MAX]; int i; @@ -315,6 +332,9 @@ int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, maps[i].txt_sec->sh_addr, maps[i].txt_sec->sh_size); #endif + s = find_mod_section(hdr, sechdrs, ".alt.smp.init"); + if (s && !is_smp()) + fixup_smp((void *)s->sh_addr, s->sh_size); return 0; } diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 5efa264..d150ad1 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -700,7 +700,7 @@ user_backtrace(struct frame_tail __user *tail, * Frame pointers should strictly progress back up the stack * (towards higher addresses). */ - if (tail >= buftail.fp) + if (tail + 1 >= buftail.fp) return NULL; return buftail.fp - 1; diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index b8af96e..2c79eec 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -97,28 +97,34 @@ set_irq_affinity(int irq, irq, cpu); return err; #else - return 0; + return -EINVAL; #endif } static int init_cpu_pmu(void) { - int i, err = 0; + int i, irqs, err = 0; struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU]; - if (!pdev) { - err = -ENODEV; - goto out; - } + if (!pdev) + return -ENODEV; + + irqs = pdev->num_resources; + + /* + * If we have a single PMU interrupt that we can't shift, assume that + * we're running on a uniprocessor machine and continue. + */ + if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0))) + return 0; - for (i = 0; i < pdev->num_resources; ++i) { + for (i = 0; i < irqs; ++i) { err = set_irq_affinity(platform_get_irq(pdev, i), i); if (err) break; } -out: return err; } diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index 19c6816..b13e70f 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -996,10 +996,10 @@ static int ptrace_gethbpregs(struct task_struct *tsk, long num, while (!(arch_ctrl.len & 0x1)) arch_ctrl.len >>= 1; - if (idx & 0x1) - reg = encode_ctrl_reg(arch_ctrl); - else + if (num & 0x1) reg = bp->attr.bp_addr; + else + reg = encode_ctrl_reg(arch_ctrl); } put: diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 420b8d6..5ea4fb71 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -226,8 +226,8 @@ int cpu_architecture(void) * Register 0 and check for VMSAv7 or PMSAv7 */ asm("mrc p15, 0, %0, c0, c1, 4" : "=r" (mmfr0)); - if ((mmfr0 & 0x0000000f) == 0x00000003 || - (mmfr0 & 0x000000f0) == 0x00000030) + if ((mmfr0 & 0x0000000f) >= 0x00000003 || + (mmfr0 & 0x000000f0) >= 0x00000030) cpu_arch = CPU_ARCH_ARMv7; else if ((mmfr0 & 0x0000000f) == 0x00000002 || (mmfr0 & 0x000000f0) == 0x00000020) diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 907d5a6..abaf844 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -474,7 +474,9 @@ setup_return(struct pt_regs *regs, struct k_sigaction *ka, unsigned long handler = (unsigned long)ka->sa.sa_handler; unsigned long retcode; int thumb = 0; - unsigned long cpsr = regs->ARM_cpsr & ~PSR_f; + unsigned long cpsr = regs->ARM_cpsr & ~(PSR_f | PSR_E_BIT); + + cpsr |= PSR_ENDSTATE; /* * Maybe we need to deliver a 32-bit signal to a 26-bit task. diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 86b66f3..6146279 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -21,6 +21,12 @@ #define ARM_CPU_KEEP(x) #endif +#if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK) +#define ARM_EXIT_KEEP(x) x +#else +#define ARM_EXIT_KEEP(x) +#endif + OUTPUT_ARCH(arm) ENTRY(stext) @@ -43,6 +49,7 @@ SECTIONS _sinittext = .; HEAD_TEXT INIT_TEXT + ARM_EXIT_KEEP(EXIT_TEXT) _einittext = .; ARM_CPU_DISCARD(PROC_INFO) __arch_info_begin = .; @@ -67,6 +74,7 @@ SECTIONS #ifndef CONFIG_XIP_KERNEL __init_begin = _stext; INIT_DATA + ARM_EXIT_KEEP(EXIT_DATA) #endif } @@ -162,6 +170,7 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_begin = .; INIT_DATA + ARM_EXIT_KEEP(EXIT_DATA) . = ALIGN(PAGE_SIZE); __init_end = .; #endif @@ -247,6 +256,8 @@ SECTIONS } #endif + NOTES + BSS_SECTION(0, 0, 0) _end = .; diff --git a/arch/arm/mach-davinci/cpufreq.c b/arch/arm/mach-davinci/cpufreq.c index 343de73..4a68c2b 100644 --- a/arch/arm/mach-davinci/cpufreq.c +++ b/arch/arm/mach-davinci/cpufreq.c @@ -132,7 +132,7 @@ out: return ret; } -static int __init davinci_cpu_init(struct cpufreq_policy *policy) +static int davinci_cpu_init(struct cpufreq_policy *policy) { int result = 0; struct davinci_cpufreq_config *pdata = cpufreq.dev->platform_data; diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c index 9eec630..beda8a4 100644 --- a/arch/arm/mach-davinci/devices-da8xx.c +++ b/arch/arm/mach-davinci/devices-da8xx.c @@ -480,8 +480,15 @@ static struct platform_device da850_mcasp_device = { .resource = da850_mcasp_resources, }; +struct platform_device davinci_pcm_device = { + .name = "davinci-pcm-audio", + .id = -1, +}; + void __init da8xx_register_mcasp(int id, struct snd_platform_data *pdata) { + platform_device_register(&davinci_pcm_device); + /* DA830/OMAP-L137 has 3 instances of McASP */ if (cpu_is_davinci_da830() && id == 1) { da830_mcasp1_device.dev.platform_data = pdata; diff --git a/arch/arm/mach-davinci/gpio-tnetv107x.c b/arch/arm/mach-davinci/gpio-tnetv107x.c index d102986..3fa3e28 100644 --- a/arch/arm/mach-davinci/gpio-tnetv107x.c +++ b/arch/arm/mach-davinci/gpio-tnetv107x.c @@ -58,7 +58,7 @@ static int tnetv107x_gpio_request(struct gpio_chip *chip, unsigned offset) spin_lock_irqsave(&ctlr->lock, flags); - gpio_reg_set_bit(®s->enable, gpio); + gpio_reg_set_bit(regs->enable, gpio); spin_unlock_irqrestore(&ctlr->lock, flags); @@ -74,7 +74,7 @@ static void tnetv107x_gpio_free(struct gpio_chip *chip, unsigned offset) spin_lock_irqsave(&ctlr->lock, flags); - gpio_reg_clear_bit(®s->enable, gpio); + gpio_reg_clear_bit(regs->enable, gpio); spin_unlock_irqrestore(&ctlr->lock, flags); } @@ -88,7 +88,7 @@ static int tnetv107x_gpio_dir_in(struct gpio_chip *chip, unsigned offset) spin_lock_irqsave(&ctlr->lock, flags); - gpio_reg_set_bit(®s->direction, gpio); + gpio_reg_set_bit(regs->direction, gpio); spin_unlock_irqrestore(&ctlr->lock, flags); @@ -106,11 +106,11 @@ static int tnetv107x_gpio_dir_out(struct gpio_chip *chip, spin_lock_irqsave(&ctlr->lock, flags); if (value) - gpio_reg_set_bit(®s->data_out, gpio); + gpio_reg_set_bit(regs->data_out, gpio); else - gpio_reg_clear_bit(®s->data_out, gpio); + gpio_reg_clear_bit(regs->data_out, gpio); - gpio_reg_clear_bit(®s->direction, gpio); + gpio_reg_clear_bit(regs->direction, gpio); spin_unlock_irqrestore(&ctlr->lock, flags); @@ -124,7 +124,7 @@ static int tnetv107x_gpio_get(struct gpio_chip *chip, unsigned offset) unsigned gpio = chip->base + offset; int ret; - ret = gpio_reg_get_bit(®s->data_in, gpio); + ret = gpio_reg_get_bit(regs->data_in, gpio); return ret ? 1 : 0; } @@ -140,9 +140,9 @@ static void tnetv107x_gpio_set(struct gpio_chip *chip, spin_lock_irqsave(&ctlr->lock, flags); if (value) - gpio_reg_set_bit(®s->data_out, gpio); + gpio_reg_set_bit(regs->data_out, gpio); else - gpio_reg_clear_bit(®s->data_out, gpio); + gpio_reg_clear_bit(regs->data_out, gpio); spin_unlock_irqrestore(&ctlr->lock, flags); } diff --git a/arch/arm/mach-davinci/include/mach/clkdev.h b/arch/arm/mach-davinci/include/mach/clkdev.h index 730c49d..14a5048 100644 --- a/arch/arm/mach-davinci/include/mach/clkdev.h +++ b/arch/arm/mach-davinci/include/mach/clkdev.h @@ -1,6 +1,8 @@ #ifndef __MACH_CLKDEV_H #define __MACH_CLKDEV_H +struct clk; + static inline int __clk_get(struct clk *clk) { return 1; diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index ffdf87b..8207954 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -838,7 +838,7 @@ EXPORT_SYMBOL(ep93xx_i2s_release); static struct resource ep93xx_ac97_resources[] = { { .start = EP93XX_AAC_PHYS_BASE, - .end = EP93XX_AAC_PHYS_BASE + 0xb0 - 1, + .end = EP93XX_AAC_PHYS_BASE + 0xac - 1, .flags = IORESOURCE_MEM, }, { diff --git a/arch/arm/mach-footbridge/include/mach/debug-macro.S b/arch/arm/mach-footbridge/include/mach/debug-macro.S index 3c9e0c4..30b971d 100644 --- a/arch/arm/mach-footbridge/include/mach/debug-macro.S +++ b/arch/arm/mach-footbridge/include/mach/debug-macro.S @@ -17,8 +17,8 @@ /* For NetWinder debugging */ .macro addruart, rp, rv mov \rp, #0x000003f8 - orr \rv, \rp, #0x7c000000 @ physical - orr \rp, \rp, #0xff000000 @ virtual + orr \rv, \rp, #0xff000000 @ virtual + orr \rp, \rp, #0x7c000000 @ physical .endm #define UART_SHIFT 0 diff --git a/arch/arm/mach-imx/mach-mx25_3ds.c b/arch/arm/mach-imx/mach-mx25_3ds.c index aa76cfd..8382e79 100644 --- a/arch/arm/mach-imx/mach-mx25_3ds.c +++ b/arch/arm/mach-imx/mach-mx25_3ds.c @@ -180,7 +180,7 @@ static const uint32_t mx25pdk_keymap[] = { KEY(3, 3, KEY_POWER), }; -static const struct matrix_keymap_data mx25pdk_keymap_data __initdata = { +static const struct matrix_keymap_data mx25pdk_keymap_data __initconst = { .keymap = mx25pdk_keymap, .keymap_size = ARRAY_SIZE(mx25pdk_keymap), }; diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c index 4dc68d6..9fd8942 100644 --- a/arch/arm/mach-ixp4xx/common.c +++ b/arch/arm/mach-ixp4xx/common.c @@ -432,7 +432,7 @@ static struct clocksource clocksource_ixp4xx = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -unsigned long ixp4xx_timer_freq = FREQ; +unsigned long ixp4xx_timer_freq = IXP4XX_TIMER_FREQ; EXPORT_SYMBOL(ixp4xx_timer_freq); static void __init ixp4xx_clocksource_init(void) { @@ -496,7 +496,7 @@ static struct clock_event_device clockevent_ixp4xx = { static void __init ixp4xx_clockevent_init(void) { - clockevent_ixp4xx.mult = div_sc(FREQ, NSEC_PER_SEC, + clockevent_ixp4xx.mult = div_sc(IXP4XX_TIMER_FREQ, NSEC_PER_SEC, clockevent_ixp4xx.shift); clockevent_ixp4xx.max_delta_ns = clockevent_delta2ns(0xfffffffe, &clockevent_ixp4xx); diff --git a/arch/arm/mach-ixp4xx/include/mach/timex.h b/arch/arm/mach-ixp4xx/include/mach/timex.h index 2c3f93c..c9e930f 100644 --- a/arch/arm/mach-ixp4xx/include/mach/timex.h +++ b/arch/arm/mach-ixp4xx/include/mach/timex.h @@ -10,6 +10,7 @@ * 66.66... MHz. We do a convulted calculation of CLOCK_TICK_RATE b/c the * timer register ignores the bottom 2 bits of the LATCH value. */ -#define FREQ 66666000 -#define CLOCK_TICK_RATE (((FREQ / HZ & ~IXP4XX_OST_RELOAD_MASK) + 1) * HZ) +#define IXP4XX_TIMER_FREQ 66666000 +#define CLOCK_TICK_RATE \ + (((IXP4XX_TIMER_FREQ / HZ & ~IXP4XX_OST_RELOAD_MASK) + 1) * HZ) diff --git a/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c index bfdbe4b..852f7c9 100644 --- a/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c +++ b/arch/arm/mach-ixp4xx/ixp4xx_qmgr.c @@ -265,6 +265,11 @@ void qmgr_release_queue(unsigned int queue) qmgr_queue_descs[queue], queue); qmgr_queue_descs[queue][0] = '\x0'; #endif + + while ((addr = qmgr_get_entry(queue))) + printk(KERN_ERR "qmgr: released queue %i not empty: 0x%08X\n", + queue, addr); + __raw_writel(0, &qmgr_regs->sram[queue]); used_sram_bitmap[0] &= ~mask[0]; @@ -275,10 +280,6 @@ void qmgr_release_queue(unsigned int queue) spin_unlock_irq(&qmgr_lock); module_put(THIS_MODULE); - - while ((addr = qmgr_get_entry(queue))) - printk(KERN_ERR "qmgr: released queue %i not empty: 0x%08X\n", - queue, addr); } static int qmgr_init(void) diff --git a/arch/arm/mach-mxs/clock-mx23.c b/arch/arm/mach-mxs/clock-mx23.c index b1a362e..ca72a05 100644 --- a/arch/arm/mach-mxs/clock-mx23.c +++ b/arch/arm/mach-mxs/clock-mx23.c @@ -304,7 +304,7 @@ static int name##_set_rate(struct clk *clk, unsigned long rate) \ reg = __raw_readl(CLKCTRL_BASE_ADDR + HW_CLKCTRL_##dr); \ reg &= ~BM_CLKCTRL_##dr##_DIV; \ reg |= div << BP_CLKCTRL_##dr##_DIV; \ - if (reg | (1 << clk->enable_shift)) { \ + if (reg & (1 << clk->enable_shift)) { \ pr_err("%s: clock is gated\n", __func__); \ return -EINVAL; \ } \ @@ -347,7 +347,7 @@ static int name##_set_parent(struct clk *clk, struct clk *parent) \ { \ if (parent != clk->parent) { \ __raw_writel(BM_CLKCTRL_CLKSEQ_BYPASS_##bit, \ - HW_CLKCTRL_CLKSEQ_TOG); \ + CLKCTRL_BASE_ADDR + HW_CLKCTRL_CLKSEQ_TOG); \ clk->parent = parent; \ } \ \ diff --git a/arch/arm/mach-mxs/clock-mx28.c b/arch/arm/mach-mxs/clock-mx28.c index 56312c0..fd1c4c5 100644 --- a/arch/arm/mach-mxs/clock-mx28.c +++ b/arch/arm/mach-mxs/clock-mx28.c @@ -355,12 +355,12 @@ static int name##_set_rate(struct clk *clk, unsigned long rate) \ } else { \ reg &= ~BM_CLKCTRL_##dr##_DIV; \ reg |= div << BP_CLKCTRL_##dr##_DIV; \ - if (reg | (1 << clk->enable_shift)) { \ + if (reg & (1 << clk->enable_shift)) { \ pr_err("%s: clock is gated\n", __func__); \ return -EINVAL; \ } \ } \ - __raw_writel(reg, CLKCTRL_BASE_ADDR + HW_CLKCTRL_CPU); \ + __raw_writel(reg, CLKCTRL_BASE_ADDR + HW_CLKCTRL_##dr); \ \ for (i = 10000; i; i--) \ if (!(__raw_readl(CLKCTRL_BASE_ADDR + \ @@ -483,7 +483,7 @@ static int name##_set_parent(struct clk *clk, struct clk *parent) \ { \ if (parent != clk->parent) { \ __raw_writel(BM_CLKCTRL_CLKSEQ_BYPASS_##bit, \ - HW_CLKCTRL_CLKSEQ_TOG); \ + CLKCTRL_BASE_ADDR + HW_CLKCTRL_CLKSEQ_TOG); \ clk->parent = parent; \ } \ \ @@ -609,7 +609,6 @@ static struct clk_lookup lookups[] = { _REGISTER_CLOCK("duart", NULL, uart_clk) _REGISTER_CLOCK("imx28-fec.0", NULL, fec_clk) _REGISTER_CLOCK("imx28-fec.1", NULL, fec_clk) - _REGISTER_CLOCK("fec.0", NULL, fec_clk) _REGISTER_CLOCK("rtc", NULL, rtc_clk) _REGISTER_CLOCK("pll2", NULL, pll2_clk) _REGISTER_CLOCK(NULL, "hclk", hbus_clk) diff --git a/arch/arm/mach-mxs/clock.c b/arch/arm/mach-mxs/clock.c index e7d2269..a7093c8 100644 --- a/arch/arm/mach-mxs/clock.c +++ b/arch/arm/mach-mxs/clock.c @@ -57,7 +57,6 @@ static void __clk_disable(struct clk *clk) if (clk->disable) clk->disable(clk); __clk_disable(clk->parent); - __clk_disable(clk->secondary); } } @@ -68,7 +67,6 @@ static int __clk_enable(struct clk *clk) if (clk->usecount++ == 0) { __clk_enable(clk->parent); - __clk_enable(clk->secondary); if (clk->enable) clk->enable(clk); diff --git a/arch/arm/mach-mxs/gpio.c b/arch/arm/mach-mxs/gpio.c index d7ad7a6..cb0c0e8 100644 --- a/arch/arm/mach-mxs/gpio.c +++ b/arch/arm/mach-mxs/gpio.c @@ -139,6 +139,8 @@ static void mxs_gpio_irq_handler(u32 irq, struct irq_desc *desc) struct mxs_gpio_port *port = (struct mxs_gpio_port *)get_irq_data(irq); u32 gpio_irq_no_base = port->virtual_irq_start; + desc->irq_data.chip->irq_ack(&desc->irq_data); + irq_stat = __raw_readl(port->base + PINCTRL_IRQSTAT(port->id)) & __raw_readl(port->base + PINCTRL_IRQEN(port->id)); diff --git a/arch/arm/mach-mxs/include/mach/clock.h b/arch/arm/mach-mxs/include/mach/clock.h index 041e276..592c9ab 100644 --- a/arch/arm/mach-mxs/include/mach/clock.h +++ b/arch/arm/mach-mxs/include/mach/clock.h @@ -29,8 +29,6 @@ struct clk { int id; /* Source clock this clk depends on */ struct clk *parent; - /* Secondary clock to enable/disable with this clock */ - struct clk *secondary; /* Reference count of clock enable/disable */ __s8 usecount; /* Register bit position for clock's enable/disable control. */ diff --git a/arch/arm/mach-omap1/include/mach/entry-macro.S b/arch/arm/mach-omap1/include/mach/entry-macro.S index c9be6d4..bfb4fb1 100644 --- a/arch/arm/mach-omap1/include/mach/entry-macro.S +++ b/arch/arm/mach-omap1/include/mach/entry-macro.S @@ -14,19 +14,6 @@ #include <mach/irqs.h> #include <asm/hardware/gic.h> -/* - * We use __glue to avoid errors with multiple definitions of - * .globl omap_irq_flags as it's included from entry-armv.S but not - * from entry-common.S. - */ -#ifdef __glue - .pushsection .data - .globl omap_irq_flags -omap_irq_flags: - .word 0 - .popsection -#endif - .macro disable_fiq .endm diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c index 4770158..731dd33 100644 --- a/arch/arm/mach-omap1/irq.c +++ b/arch/arm/mach-omap1/irq.c @@ -57,6 +57,7 @@ struct omap_irq_bank { unsigned long wake_enable; }; +u32 omap_irq_flags; static unsigned int irq_bank_count; static struct omap_irq_bank *irq_banks; @@ -176,7 +177,6 @@ static struct irq_chip omap_irq_chip = { void __init omap_init_irq(void) { - extern unsigned int omap_irq_flags; int i, j; #if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) diff --git a/arch/arm/mach-omap1/lcd_dma.c b/arch/arm/mach-omap1/lcd_dma.c index c9088d8..4538093 100644 --- a/arch/arm/mach-omap1/lcd_dma.c +++ b/arch/arm/mach-omap1/lcd_dma.c @@ -37,7 +37,7 @@ int omap_lcd_dma_running(void) * On OMAP1510, internal LCD controller will start the transfer * when it gets enabled, so assume DMA running if LCD enabled. */ - if (cpu_is_omap1510()) + if (cpu_is_omap15xx()) if (omap_readw(OMAP_LCDC_CONTROL) & OMAP_LCDC_CTRL_LCD_EN) return 1; @@ -95,7 +95,7 @@ EXPORT_SYMBOL(omap_set_lcd_dma_single_transfer); void omap_set_lcd_dma_b1_rotation(int rotate) { - if (cpu_is_omap1510()) { + if (cpu_is_omap15xx()) { printk(KERN_ERR "DMA rotation is not supported in 1510 mode\n"); BUG(); return; @@ -106,7 +106,7 @@ EXPORT_SYMBOL(omap_set_lcd_dma_b1_rotation); void omap_set_lcd_dma_b1_mirror(int mirror) { - if (cpu_is_omap1510()) { + if (cpu_is_omap15xx()) { printk(KERN_ERR "DMA mirror is not supported in 1510 mode\n"); BUG(); } @@ -116,7 +116,7 @@ EXPORT_SYMBOL(omap_set_lcd_dma_b1_mirror); void omap_set_lcd_dma_b1_vxres(unsigned long vxres) { - if (cpu_is_omap1510()) { + if (cpu_is_omap15xx()) { printk(KERN_ERR "DMA virtual resulotion is not supported " "in 1510 mode\n"); BUG(); @@ -127,7 +127,7 @@ EXPORT_SYMBOL(omap_set_lcd_dma_b1_vxres); void omap_set_lcd_dma_b1_scale(unsigned int xscale, unsigned int yscale) { - if (cpu_is_omap1510()) { + if (cpu_is_omap15xx()) { printk(KERN_ERR "DMA scale is not supported in 1510 mode\n"); BUG(); } @@ -177,7 +177,7 @@ static void set_b1_regs(void) bottom = PIXADDR(lcd_dma.xres - 1, lcd_dma.yres - 1); /* 1510 DMA requires the bottom address to be 2 more * than the actual last memory access location. */ - if (cpu_is_omap1510() && + if (cpu_is_omap15xx() && lcd_dma.data_type == OMAP_DMA_DATA_TYPE_S32) bottom += 2; ei = PIXSTEP(0, 0, 1, 0); @@ -241,7 +241,7 @@ static void set_b1_regs(void) return; /* Suppress warning about uninitialized vars */ } - if (cpu_is_omap1510()) { + if (cpu_is_omap15xx()) { omap_writew(top >> 16, OMAP1510_DMA_LCD_TOP_F1_U); omap_writew(top, OMAP1510_DMA_LCD_TOP_F1_L); omap_writew(bottom >> 16, OMAP1510_DMA_LCD_BOT_F1_U); @@ -343,7 +343,7 @@ void omap_free_lcd_dma(void) BUG(); return; } - if (!cpu_is_omap1510()) + if (!cpu_is_omap15xx()) omap_writew(omap_readw(OMAP1610_DMA_LCD_CCR) & ~1, OMAP1610_DMA_LCD_CCR); lcd_dma.reserved = 0; @@ -360,7 +360,7 @@ void omap_enable_lcd_dma(void) * connected. Otherwise the OMAP internal controller will * start the transfer when it gets enabled. */ - if (cpu_is_omap1510() || !lcd_dma.ext_ctrl) + if (cpu_is_omap15xx() || !lcd_dma.ext_ctrl) return; w = omap_readw(OMAP1610_DMA_LCD_CTRL); @@ -378,14 +378,14 @@ EXPORT_SYMBOL(omap_enable_lcd_dma); void omap_setup_lcd_dma(void) { BUG_ON(lcd_dma.active); - if (!cpu_is_omap1510()) { + if (!cpu_is_omap15xx()) { /* Set some reasonable defaults */ omap_writew(0x5440, OMAP1610_DMA_LCD_CCR); omap_writew(0x9102, OMAP1610_DMA_LCD_CSDP); omap_writew(0x0004, OMAP1610_DMA_LCD_LCH_CTRL); } set_b1_regs(); - if (!cpu_is_omap1510()) { + if (!cpu_is_omap15xx()) { u16 w; w = omap_readw(OMAP1610_DMA_LCD_CCR); @@ -407,7 +407,7 @@ void omap_stop_lcd_dma(void) u16 w; lcd_dma.active = 0; - if (cpu_is_omap1510() || !lcd_dma.ext_ctrl) + if (cpu_is_omap15xx() || !lcd_dma.ext_ctrl) return; w = omap_readw(OMAP1610_DMA_LCD_CCR); diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c index f83fc33..6885d2f 100644 --- a/arch/arm/mach-omap1/time.c +++ b/arch/arm/mach-omap1/time.c @@ -44,7 +44,6 @@ #include <linux/clocksource.h> #include <linux/clockchips.h> #include <linux/io.h> -#include <linux/sched.h> #include <asm/system.h> #include <mach/hardware.h> diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c index e906e05..9a2a31e 100644 --- a/arch/arm/mach-omap2/board-devkit8000.c +++ b/arch/arm/mach-omap2/board-devkit8000.c @@ -115,9 +115,6 @@ static struct omap2_hsmmc_info mmc[] = { static int devkit8000_panel_enable_lcd(struct omap_dss_device *dssdev) { - twl_i2c_write_u8(TWL4030_MODULE_GPIO, 0x80, REG_GPIODATADIR1); - twl_i2c_write_u8(TWL4030_MODULE_LED, 0x0, 0x0); - if (gpio_is_valid(dssdev->reset_gpio)) gpio_set_value_cansleep(dssdev->reset_gpio, 1); return 0; @@ -247,6 +244,8 @@ static struct gpio_led gpio_leds[]; static int devkit8000_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio) { + int ret; + omap_mux_init_gpio(29, OMAP_PIN_INPUT); /* gpio + 0 is "mmc0_cd" (input/IRQ) */ mmc[0].gpio_cd = gpio + 0; @@ -255,17 +254,23 @@ static int devkit8000_twl_gpio_setup(struct device *dev, /* TWL4030_GPIO_MAX + 1 == ledB, PMU_STAT (out, active low LED) */ gpio_leds[2].gpio = gpio + TWL4030_GPIO_MAX + 1; - /* gpio + 1 is "LCD_PWREN" (out, active high) */ - devkit8000_lcd_device.reset_gpio = gpio + 1; - gpio_request(devkit8000_lcd_device.reset_gpio, "LCD_PWREN"); - /* Disable until needed */ - gpio_direction_output(devkit8000_lcd_device.reset_gpio, 0); + /* TWL4030_GPIO_MAX + 0 is "LCD_PWREN" (out, active high) */ + devkit8000_lcd_device.reset_gpio = gpio + TWL4030_GPIO_MAX + 0; + ret = gpio_request_one(devkit8000_lcd_device.reset_gpio, + GPIOF_DIR_OUT | GPIOF_INIT_LOW, "LCD_PWREN"); + if (ret < 0) { + devkit8000_lcd_device.reset_gpio = -EINVAL; + printk(KERN_ERR "Failed to request GPIO for LCD_PWRN\n"); + } /* gpio + 7 is "DVI_PD" (out, active low) */ devkit8000_dvi_device.reset_gpio = gpio + 7; - gpio_request(devkit8000_dvi_device.reset_gpio, "DVI PowerDown"); - /* Disable until needed */ - gpio_direction_output(devkit8000_dvi_device.reset_gpio, 0); + ret = gpio_request_one(devkit8000_dvi_device.reset_gpio, + GPIOF_DIR_OUT | GPIOF_INIT_LOW, "DVI PowerDown"); + if (ret < 0) { + devkit8000_dvi_device.reset_gpio = -EINVAL; + printk(KERN_ERR "Failed to request GPIO for DVI PowerDown\n"); + } return 0; } diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c index e001a04..e944025 100644 --- a/arch/arm/mach-omap2/board-omap4panda.c +++ b/arch/arm/mach-omap2/board-omap4panda.c @@ -409,8 +409,6 @@ static void __init omap4_panda_init(void) platform_add_devices(panda_devices, ARRAY_SIZE(panda_devices)); omap_serial_init(); omap4_twl6030_hsmmc_init(mmc); - /* OMAP4 Panda uses internal transceiver so register nop transceiver */ - usb_nop_xceiv_register(); omap4_ehci_init(); usb_musb_init(&musb_board_data); } diff --git a/arch/arm/mach-omap2/board-rm680.c b/arch/arm/mach-omap2/board-rm680.c index cb77be7..39a71bb 100644 --- a/arch/arm/mach-omap2/board-rm680.c +++ b/arch/arm/mach-omap2/board-rm680.c @@ -40,9 +40,6 @@ static struct regulator_consumer_supply rm680_vemmc_consumers[] = { static struct regulator_init_data rm680_vemmc = { .constraints = { .name = "rm680_vemmc", - .min_uV = 2900000, - .max_uV = 2900000, - .apply_uV = 1, .valid_modes_mask = REGULATOR_MODE_NORMAL | REGULATOR_MODE_STANDBY, .valid_ops_mask = REGULATOR_CHANGE_STATUS diff --git a/arch/arm/mach-omap2/clkt_dpll.c b/arch/arm/mach-omap2/clkt_dpll.c index 337392c..acb7ae5 100644 --- a/arch/arm/mach-omap2/clkt_dpll.c +++ b/arch/arm/mach-omap2/clkt_dpll.c @@ -77,7 +77,7 @@ static int _dpll_test_fint(struct clk *clk, u8 n) dd = clk->dpll_data; /* DPLL divider must result in a valid jitter correction val */ - fint = clk->parent->rate / (n + 1); + fint = clk->parent->rate / n; if (fint < DPLL_FINT_BAND1_MIN) { pr_debug("rejecting n=%d due to Fint failure, " diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c index d2f15f5..34922b2 100644 --- a/arch/arm/mach-omap2/dma.c +++ b/arch/arm/mach-omap2/dma.c @@ -264,7 +264,7 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused) if (IS_ERR(od)) { pr_err("%s: Cant build omap_device for %s:%s.\n", __func__, name, oh->name); - return IS_ERR(od); + return PTR_ERR(od); } mem = platform_get_resource(&od->pdev, IORESOURCE_MEM, 0); diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S index befa321..81985a6 100644 --- a/arch/arm/mach-omap2/include/mach/entry-macro.S +++ b/arch/arm/mach-omap2/include/mach/entry-macro.S @@ -38,20 +38,6 @@ */ #ifdef MULTI_OMAP2 - -/* - * We use __glue to avoid errors with multiple definitions of - * .globl omap_irq_base as it's included from entry-armv.S but not - * from entry-common.S. - */ -#ifdef __glue - .pushsection .data - .globl omap_irq_base -omap_irq_base: - .word 0 - .popsection -#endif - /* * Configure the interrupt base on the first interrupt. * See also omap_irq_base_init for setting omap_irq_base. diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index e66687b..c203204 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -314,14 +314,13 @@ static int _set_hwmod_postsetup_state(struct omap_hwmod *oh, void *data) return omap_hwmod_set_postsetup_state(oh, *(u8 *)data); } +void __iomem *omap_irq_base; + /* * Initialize asm_irq_base for entry-macro.S */ static inline void omap_irq_base_init(void) { - extern void __iomem *omap_irq_base; - -#ifdef MULTI_OMAP2 if (cpu_is_omap24xx()) omap_irq_base = OMAP2_L4_IO_ADDRESS(OMAP24XX_IC_BASE); else if (cpu_is_omap34xx()) @@ -330,7 +329,6 @@ static inline void omap_irq_base_init(void) omap_irq_base = OMAP2_L4_IO_ADDRESS(OMAP44XX_GIC_CPU_BASE); else pr_err("Could not initialize omap_irq_base\n"); -#endif } void __init omap2_init_common_infrastructure(void) diff --git a/arch/arm/mach-omap2/mailbox.c b/arch/arm/mach-omap2/mailbox.c index 394413d..24b8850 100644 --- a/arch/arm/mach-omap2/mailbox.c +++ b/arch/arm/mach-omap2/mailbox.c @@ -193,10 +193,12 @@ static void omap2_mbox_disable_irq(struct omap_mbox *mbox, omap_mbox_type_t irq) { struct omap_mbox2_priv *p = mbox->priv; - u32 l, bit = (irq == IRQ_TX) ? p->notfull_bit : p->newmsg_bit; - l = mbox_read_reg(p->irqdisable); - l &= ~bit; - mbox_write_reg(l, p->irqdisable); + u32 bit = (irq == IRQ_TX) ? p->notfull_bit : p->newmsg_bit; + + if (!cpu_is_omap44xx()) + bit = mbox_read_reg(p->irqdisable) & ~bit; + + mbox_write_reg(bit, p->irqdisable); } static void omap2_mbox_ack_irq(struct omap_mbox *mbox, @@ -334,7 +336,7 @@ static struct omap_mbox mbox_iva_info = { .priv = &omap2_mbox_iva_priv, }; -struct omap_mbox *omap2_mboxes[] = { &mbox_iva_info, &mbox_dsp_info, NULL }; +struct omap_mbox *omap2_mboxes[] = { &mbox_dsp_info, &mbox_iva_info, NULL }; #endif #if defined(CONFIG_ARCH_OMAP4) diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c index df8d2f2..6c84659 100644 --- a/arch/arm/mach-omap2/mux.c +++ b/arch/arm/mach-omap2/mux.c @@ -160,7 +160,7 @@ static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition, struct omap_mux *mux = NULL; struct omap_mux_entry *e; const char *mode_name; - int found = 0, found_mode, mode0_len = 0; + int found = 0, found_mode = 0, mode0_len = 0; struct list_head *muxmodes = &partition->muxmodes; mode_name = strchr(muxname, '.'); @@ -605,7 +605,7 @@ static void __init omap_mux_dbg_create_entry( list_for_each_entry(e, &partition->muxmodes, node) { struct omap_mux *m = &e->mux; - (void)debugfs_create_file(m->muxnames[0], S_IWUGO, mux_dbg_dir, + (void)debugfs_create_file(m->muxnames[0], S_IWUSR, mux_dbg_dir, m, &omap_mux_dbg_signal_fops); } } @@ -1000,6 +1000,7 @@ int __init omap_mux_init(const char *name, u32 flags, if (!partition->base) { pr_err("%s: Could not ioremap mux partition at 0x%08x\n", __func__, partition->phys); + kfree(partition); return -ENODEV; } diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c index 125f565..a5a83b3 100644 --- a/arch/arm/mach-omap2/pm-debug.c +++ b/arch/arm/mach-omap2/pm-debug.c @@ -637,14 +637,14 @@ static int __init pm_dbg_init(void) } - (void) debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUGO, d, + (void) debugfs_create_file("enable_off_mode", S_IRUGO | S_IWUSR, d, &enable_off_mode, &pm_dbg_option_fops); - (void) debugfs_create_file("sleep_while_idle", S_IRUGO | S_IWUGO, d, + (void) debugfs_create_file("sleep_while_idle", S_IRUGO | S_IWUSR, d, &sleep_while_idle, &pm_dbg_option_fops); - (void) debugfs_create_file("wakeup_timer_seconds", S_IRUGO | S_IWUGO, d, + (void) debugfs_create_file("wakeup_timer_seconds", S_IRUGO | S_IWUSR, d, &wakeup_timer_seconds, &pm_dbg_option_fops); (void) debugfs_create_file("wakeup_timer_milliseconds", - S_IRUGO | S_IWUGO, d, &wakeup_timer_milliseconds, + S_IRUGO | S_IWUSR, d, &wakeup_timer_milliseconds, &pm_dbg_option_fops); pm_dbg_init_done = 1; diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index a4aa192..2f864e4 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -168,9 +168,10 @@ static void omap3_core_restore_context(void) * once during boot sequence, but this works as we are not using secure * services. */ -static void omap3_save_secure_ram_context(u32 target_mpu_state) +static void omap3_save_secure_ram_context(void) { u32 ret; + int mpu_next_state = pwrdm_read_next_pwrst(mpu_pwrdm); if (omap_type() != OMAP2_DEVICE_TYPE_GP) { /* @@ -181,7 +182,7 @@ static void omap3_save_secure_ram_context(u32 target_mpu_state) pwrdm_set_next_pwrst(mpu_pwrdm, PWRDM_POWER_ON); ret = _omap_save_secure_sram((u32 *) __pa(omap3_secure_ram_storage)); - pwrdm_set_next_pwrst(mpu_pwrdm, target_mpu_state); + pwrdm_set_next_pwrst(mpu_pwrdm, mpu_next_state); /* Following is for error tracking, it should not happen */ if (ret) { printk(KERN_ERR "save_secure_sram() returns %08x\n", @@ -1094,7 +1095,7 @@ static int __init omap3_pm_init(void) local_fiq_disable(); omap_dma_global_context_save(); - omap3_save_secure_ram_context(PWRDM_POWER_ON); + omap3_save_secure_ram_context(); omap_dma_global_context_restore(); local_irq_enable(); diff --git a/arch/arm/mach-omap2/prcm_mpu44xx.h b/arch/arm/mach-omap2/prcm_mpu44xx.h index 729a644..3300ff6 100644 --- a/arch/arm/mach-omap2/prcm_mpu44xx.h +++ b/arch/arm/mach-omap2/prcm_mpu44xx.h @@ -38,8 +38,8 @@ #define OMAP4430_PRCM_MPU_CPU1_INST 0x0800 /* PRCM_MPU clockdomain register offsets (from instance start) */ -#define OMAP4430_PRCM_MPU_CPU0_MPU_CDOFFS 0x0000 -#define OMAP4430_PRCM_MPU_CPU1_MPU_CDOFFS 0x0000 +#define OMAP4430_PRCM_MPU_CPU0_MPU_CDOFFS 0x0018 +#define OMAP4430_PRCM_MPU_CPU1_MPU_CDOFFS 0x0018 /* diff --git a/arch/arm/mach-omap2/smartreflex.c b/arch/arm/mach-omap2/smartreflex.c index 77ecebf..1a777e3 100644 --- a/arch/arm/mach-omap2/smartreflex.c +++ b/arch/arm/mach-omap2/smartreflex.c @@ -282,6 +282,7 @@ error: dev_err(&sr_info->pdev->dev, "%s: ERROR in registering" "interrupt handler. Smartreflex will" "not function as desired\n", __func__); + kfree(name); kfree(sr_info); return ret; } @@ -780,8 +781,7 @@ static int omap_sr_autocomp_show(void *data, u64 *val) struct omap_sr *sr_info = (struct omap_sr *) data; if (!sr_info) { - pr_warning("%s: omap_sr struct for sr_%s not found\n", - __func__, sr_info->voltdm->name); + pr_warning("%s: omap_sr struct not found\n", __func__); return -EINVAL; } @@ -795,8 +795,7 @@ static int omap_sr_autocomp_store(void *data, u64 val) struct omap_sr *sr_info = (struct omap_sr *) data; if (!sr_info) { - pr_warning("%s: omap_sr struct for sr_%s not found\n", - __func__, sr_info->voltdm->name); + pr_warning("%s: omap_sr struct not found\n", __func__); return -EINVAL; } @@ -834,7 +833,8 @@ static int __init omap_sr_probe(struct platform_device *pdev) if (!pdata) { dev_err(&pdev->dev, "%s: platform data missing\n", __func__); - return -EINVAL; + ret = -EINVAL; + goto err_free_devinfo; } mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -880,7 +880,7 @@ static int __init omap_sr_probe(struct platform_device *pdev) ret = sr_late_init(sr_info); if (ret) { pr_warning("%s: Error in SR late init\n", __func__); - return ret; + goto err_release_region; } } @@ -891,17 +891,20 @@ static int __init omap_sr_probe(struct platform_device *pdev) * not try to create rest of the debugfs entries. */ vdd_dbg_dir = omap_voltage_get_dbgdir(sr_info->voltdm); - if (!vdd_dbg_dir) - return -EINVAL; + if (!vdd_dbg_dir) { + ret = -EINVAL; + goto err_release_region; + } dbg_dir = debugfs_create_dir("smartreflex", vdd_dbg_dir); if (IS_ERR(dbg_dir)) { dev_err(&pdev->dev, "%s: Unable to create debugfs directory\n", __func__); - return PTR_ERR(dbg_dir); + ret = PTR_ERR(dbg_dir); + goto err_release_region; } - (void) debugfs_create_file("autocomp", S_IRUGO | S_IWUGO, dbg_dir, + (void) debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, dbg_dir, (void *)sr_info, &pm_sr_fops); (void) debugfs_create_x32("errweight", S_IRUGO, dbg_dir, &sr_info->err_weight); @@ -914,7 +917,8 @@ static int __init omap_sr_probe(struct platform_device *pdev) if (IS_ERR(nvalue_dir)) { dev_err(&pdev->dev, "%s: Unable to create debugfs directory" "for n-values\n", __func__); - return PTR_ERR(nvalue_dir); + ret = PTR_ERR(nvalue_dir); + goto err_release_region; } omap_voltage_get_volttable(sr_info->voltdm, &volt_data); @@ -923,24 +927,16 @@ static int __init omap_sr_probe(struct platform_device *pdev) " corresponding vdd vdd_%s. Cannot create debugfs" "entries for n-values\n", __func__, sr_info->voltdm->name); - return -ENODATA; + ret = -ENODATA; + goto err_release_region; } for (i = 0; i < sr_info->nvalue_count; i++) { - char *name; - char volt_name[32]; - - name = kzalloc(NVALUE_NAME_LEN + 1, GFP_KERNEL); - if (!name) { - dev_err(&pdev->dev, "%s: Unable to allocate memory" - " for n-value directory name\n", __func__); - return -ENOMEM; - } + char name[NVALUE_NAME_LEN + 1]; - strcpy(name, "volt_"); - sprintf(volt_name, "%d", volt_data[i].volt_nominal); - strcat(name, volt_name); - (void) debugfs_create_x32(name, S_IRUGO | S_IWUGO, nvalue_dir, + snprintf(name, sizeof(name), "volt_%d", + volt_data[i].volt_nominal); + (void) debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, &(sr_info->nvalue_table[i].nvalue)); } @@ -966,7 +962,7 @@ static int __devexit omap_sr_remove(struct platform_device *pdev) } sr_info = _sr_lookup(pdata->voltdm); - if (!sr_info) { + if (IS_ERR(sr_info)) { dev_warn(&pdev->dev, "%s: omap_sr struct not found\n", __func__); return -EINVAL; diff --git a/arch/arm/mach-omap2/timer-gp.c b/arch/arm/mach-omap2/timer-gp.c index 7b7c268..0fc550e 100644 --- a/arch/arm/mach-omap2/timer-gp.c +++ b/arch/arm/mach-omap2/timer-gp.c @@ -39,6 +39,7 @@ #include <asm/mach/time.h> #include <plat/dmtimer.h> #include <asm/localtimer.h> +#include <asm/sched_clock.h> #include "timer-gp.h" @@ -190,6 +191,7 @@ static void __init omap2_gp_clocksource_init(void) /* * clocksource */ +static DEFINE_CLOCK_DATA(cd); static struct omap_dm_timer *gpt_clocksource; static cycle_t clocksource_read_cycles(struct clocksource *cs) { @@ -204,6 +206,15 @@ static struct clocksource clocksource_gpt = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +static void notrace dmtimer_update_sched_clock(void) +{ + u32 cyc; + + cyc = omap_dm_timer_read_counter(gpt_clocksource); + + update_sched_clock(&cd, cyc, (u32)~0); +} + /* Setup free-running counter for clocksource */ static void __init omap2_gp_clocksource_init(void) { @@ -224,6 +235,8 @@ static void __init omap2_gp_clocksource_init(void) omap_dm_timer_set_load_start(gpt, 1, 0); + init_sched_clock(&cd, dmtimer_update_sched_clock, 32, tick_rate); + if (clocksource_register_hz(&clocksource_gpt, tick_rate)) printk(err2, clocksource_gpt.name); } diff --git a/arch/arm/mach-omap2/voltage.c b/arch/arm/mach-omap2/voltage.c index ed6079c9..12be525 100644 --- a/arch/arm/mach-omap2/voltage.c +++ b/arch/arm/mach-omap2/voltage.c @@ -471,6 +471,7 @@ static void __init vdd_debugfs_init(struct omap_vdd_info *vdd) strcat(name, vdd->voltdm.name); vdd->debug_dir = debugfs_create_dir(name, voltage_dir); + kfree(name); if (IS_ERR(vdd->debug_dir)) { pr_warning("%s: Unable to create debugfs directory for" " vdd_%s\n", __func__, vdd->voltdm.name); diff --git a/arch/arm/mach-pxa/colibri-evalboard.c b/arch/arm/mach-pxa/colibri-evalboard.c index 6b2c800..28f667e 100644 --- a/arch/arm/mach-pxa/colibri-evalboard.c +++ b/arch/arm/mach-pxa/colibri-evalboard.c @@ -50,7 +50,7 @@ static void __init colibri_mmc_init(void) GPIO0_COLIBRI_PXA270_SD_DETECT; if (machine_is_colibri300()) /* PXA300 Colibri */ colibri_mci_platform_data.gpio_card_detect = - GPIO39_COLIBRI_PXA300_SD_DETECT; + GPIO13_COLIBRI_PXA300_SD_DETECT; else /* PXA320 Colibri */ colibri_mci_platform_data.gpio_card_detect = GPIO28_COLIBRI_PXA320_SD_DETECT; diff --git a/arch/arm/mach-pxa/colibri-pxa300.c b/arch/arm/mach-pxa/colibri-pxa300.c index fddb16d..66dd81c 100644 --- a/arch/arm/mach-pxa/colibri-pxa300.c +++ b/arch/arm/mach-pxa/colibri-pxa300.c @@ -41,7 +41,7 @@ static mfp_cfg_t colibri_pxa300_evalboard_pin_config[] __initdata = { GPIO4_MMC1_DAT1, GPIO5_MMC1_DAT2, GPIO6_MMC1_DAT3, - GPIO39_GPIO, /* SD detect */ + GPIO13_GPIO, /* GPIO13_COLIBRI_PXA300_SD_DETECT */ /* UHC */ GPIO0_2_USBH_PEN, diff --git a/arch/arm/mach-pxa/include/mach/colibri.h b/arch/arm/mach-pxa/include/mach/colibri.h index 388a96f..cb4236e 100644 --- a/arch/arm/mach-pxa/include/mach/colibri.h +++ b/arch/arm/mach-pxa/include/mach/colibri.h @@ -60,7 +60,7 @@ static inline void colibri_pxa3xx_init_nand(void) {} #define GPIO113_COLIBRI_PXA270_TS_IRQ 113 /* GPIO definitions for Colibri PXA300/310 */ -#define GPIO39_COLIBRI_PXA300_SD_DETECT 39 +#define GPIO13_COLIBRI_PXA300_SD_DETECT 13 /* GPIO definitions for Colibri PXA320 */ #define GPIO28_COLIBRI_PXA320_SD_DETECT 28 diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c index 405b92a..35572c4 100644 --- a/arch/arm/mach-pxa/palm27x.c +++ b/arch/arm/mach-pxa/palm27x.c @@ -323,7 +323,7 @@ static struct platform_pwm_backlight_data palm27x_backlight_data = { .pwm_id = 0, .max_brightness = 0xfe, .dft_brightness = 0x7e, - .pwm_period_ns = 3500, + .pwm_period_ns = 3500 * 1024, .init = palm27x_backlight_init, .notify = palm27x_backlight_notify, .exit = palm27x_backlight_exit, diff --git a/arch/arm/mach-pxa/pm.c b/arch/arm/mach-pxa/pm.c index 978e1b2..1807c9a 100644 --- a/arch/arm/mach-pxa/pm.c +++ b/arch/arm/mach-pxa/pm.c @@ -33,7 +33,7 @@ int pxa_pm_enter(suspend_state_t state) #endif /* skip registers saving for standby */ - if (state != PM_SUSPEND_STANDBY) { + if (state != PM_SUSPEND_STANDBY && pxa_cpu_pm_fns->save) { pxa_cpu_pm_fns->save(sleep_save); /* before sleeping, calculate and save a checksum */ for (i = 0; i < pxa_cpu_pm_fns->save_count - 1; i++) @@ -44,7 +44,7 @@ int pxa_pm_enter(suspend_state_t state) pxa_cpu_pm_fns->enter(state); cpu_init(); - if (state != PM_SUSPEND_STANDBY) { + if (state != PM_SUSPEND_STANDBY && pxa_cpu_pm_fns->restore) { /* after sleeping, validate the checksum */ for (i = 0; i < pxa_cpu_pm_fns->save_count - 1; i++) checksum += sleep_save[i]; diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c index fbc5b77..b166b1d 100644 --- a/arch/arm/mach-pxa/pxa25x.c +++ b/arch/arm/mach-pxa/pxa25x.c @@ -347,6 +347,7 @@ static struct platform_device *pxa25x_devices[] __initdata = { &pxa25x_device_assp, &pxa25x_device_pwm0, &pxa25x_device_pwm1, + &pxa_device_asoc_platform, }; static struct sys_device pxa25x_sysdev[] = { diff --git a/arch/arm/mach-pxa/tosa-bt.c b/arch/arm/mach-pxa/tosa-bt.c index c31e601..b9b1e5c 100644 --- a/arch/arm/mach-pxa/tosa-bt.c +++ b/arch/arm/mach-pxa/tosa-bt.c @@ -81,8 +81,6 @@ static int tosa_bt_probe(struct platform_device *dev) goto err_rfk_alloc; } - rfkill_set_led_trigger_name(rfk, "tosa-bt"); - rc = rfkill_register(rfk); if (rc) goto err_rfkill; diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c index af152e7..f2582ec 100644 --- a/arch/arm/mach-pxa/tosa.c +++ b/arch/arm/mach-pxa/tosa.c @@ -875,6 +875,11 @@ static struct platform_device sharpsl_rom_device = { .dev.platform_data = &sharpsl_rom_data, }; +static struct platform_device wm9712_device = { + .name = "wm9712-codec", + .id = -1, +}; + static struct platform_device *devices[] __initdata = { &tosascoop_device, &tosascoop_jc_device, @@ -885,6 +890,7 @@ static struct platform_device *devices[] __initdata = { &tosaled_device, &tosa_bt_device, &sharpsl_rom_device, + &wm9712_device, }; static void tosa_poweroff(void) diff --git a/arch/arm/mach-s3c2440/Kconfig b/arch/arm/mach-s3c2440/Kconfig index a0cb258..50825a3 100644 --- a/arch/arm/mach-s3c2440/Kconfig +++ b/arch/arm/mach-s3c2440/Kconfig @@ -99,6 +99,7 @@ config MACH_NEO1973_GTA02 select POWER_SUPPLY select MACH_NEO1973 select S3C2410_PWM + select S3C_DEV_USB_HOST help Say Y here if you are using the Openmoko GTA02 / Freerunner GSM Phone diff --git a/arch/arm/mach-s3c2440/include/mach/gta02.h b/arch/arm/mach-s3c2440/include/mach/gta02.h index 953331d..3a56a22 100644 --- a/arch/arm/mach-s3c2440/include/mach/gta02.h +++ b/arch/arm/mach-s3c2440/include/mach/gta02.h @@ -44,19 +44,19 @@ #define GTA02v3_GPIO_nUSB_FLT S3C2410_GPG(10) /* v3 + v4 only */ #define GTA02v3_GPIO_nGSM_OC S3C2410_GPG(11) /* v3 + v4 only */ -#define GTA02_GPIO_AMP_SHUT S3C2440_GPJ1 /* v2 + v3 + v4 only */ -#define GTA02v1_GPIO_WLAN_GPIO10 S3C2440_GPJ2 -#define GTA02_GPIO_HP_IN S3C2440_GPJ2 /* v2 + v3 + v4 only */ -#define GTA02_GPIO_INT0 S3C2440_GPJ3 /* v2 + v3 + v4 only */ -#define GTA02_GPIO_nGSM_EN S3C2440_GPJ4 -#define GTA02_GPIO_3D_RESET S3C2440_GPJ5 -#define GTA02_GPIO_nDL_GSM S3C2440_GPJ6 /* v4 + v5 only */ -#define GTA02_GPIO_WLAN_GPIO0 S3C2440_GPJ7 -#define GTA02v1_GPIO_BAT_ID S3C2440_GPJ8 -#define GTA02_GPIO_KEEPACT S3C2440_GPJ8 -#define GTA02v1_GPIO_HP_IN S3C2440_GPJ10 -#define GTA02_CHIP_PWD S3C2440_GPJ11 /* v2 + v3 + v4 only */ -#define GTA02_GPIO_nWLAN_RESET S3C2440_GPJ12 /* v2 + v3 + v4 only */ +#define GTA02_GPIO_AMP_SHUT S3C2410_GPJ(1) /* v2 + v3 + v4 only */ +#define GTA02v1_GPIO_WLAN_GPIO10 S3C2410_GPJ(2) +#define GTA02_GPIO_HP_IN S3C2410_GPJ(2) /* v2 + v3 + v4 only */ +#define GTA02_GPIO_INT0 S3C2410_GPJ(3) /* v2 + v3 + v4 only */ +#define GTA02_GPIO_nGSM_EN S3C2410_GPJ(4) +#define GTA02_GPIO_3D_RESET S3C2410_GPJ(5) +#define GTA02_GPIO_nDL_GSM S3C2410_GPJ(6) /* v4 + v5 only */ +#define GTA02_GPIO_WLAN_GPIO0 S3C2410_GPJ(7) +#define GTA02v1_GPIO_BAT_ID S3C2410_GPJ(8) +#define GTA02_GPIO_KEEPACT S3C2410_GPJ(8) +#define GTA02v1_GPIO_HP_IN S3C2410_GPJ(10) +#define GTA02_CHIP_PWD S3C2410_GPJ(11) /* v2 + v3 + v4 only */ +#define GTA02_GPIO_nWLAN_RESET S3C2410_GPJ(12) /* v2 + v3 + v4 only */ #define GTA02_IRQ_GSENSOR_1 IRQ_EINT0 #define GTA02_IRQ_MODEM IRQ_EINT1 diff --git a/arch/arm/mach-s3c64xx/clock.c b/arch/arm/mach-s3c64xx/clock.c index dd37820..fdfc4d5 100644 --- a/arch/arm/mach-s3c64xx/clock.c +++ b/arch/arm/mach-s3c64xx/clock.c @@ -151,6 +151,12 @@ static struct clk init_clocks_off[] = { .enable = s3c64xx_pclk_ctrl, .ctrlbit = S3C_CLKCON_PCLK_IIC, }, { + .name = "i2c", + .id = 1, + .parent = &clk_p, + .enable = s3c64xx_pclk_ctrl, + .ctrlbit = S3C6410_CLKCON_PCLK_I2C1, + }, { .name = "iis", .id = 0, .parent = &clk_p, diff --git a/arch/arm/mach-s3c64xx/dma.c b/arch/arm/mach-s3c64xx/dma.c index 135db1b..c35585c 100644 --- a/arch/arm/mach-s3c64xx/dma.c +++ b/arch/arm/mach-s3c64xx/dma.c @@ -690,12 +690,12 @@ static int s3c64xx_dma_init1(int chno, enum dma_ch chbase, regptr = regs + PL080_Cx_BASE(0); - for (ch = 0; ch < 8; ch++, chno++, chptr++) { - printk(KERN_INFO "%s: registering DMA %d (%p)\n", - __func__, chno, regptr); + for (ch = 0; ch < 8; ch++, chptr++) { + pr_debug("%s: registering DMA %d (%p)\n", + __func__, chno + ch, regptr); chptr->bit = 1 << ch; - chptr->number = chno; + chptr->number = chno + ch; chptr->dmac = dmac; chptr->regs = regptr; regptr += PL080_Cx_STRIDE; @@ -704,7 +704,8 @@ static int s3c64xx_dma_init1(int chno, enum dma_ch chbase, /* for the moment, permanently enable the controller */ writel(PL080_CONFIG_ENABLE, regs + PL080_CONFIG); - printk(KERN_INFO "PL080: IRQ %d, at %p\n", irq, regs); + printk(KERN_INFO "PL080: IRQ %d, at %p, channels %d..%d\n", + irq, regs, chno, chno+8); return 0; diff --git a/arch/arm/mach-s3c64xx/gpiolib.c b/arch/arm/mach-s3c64xx/gpiolib.c index fd99a82..92b0908 100644 --- a/arch/arm/mach-s3c64xx/gpiolib.c +++ b/arch/arm/mach-s3c64xx/gpiolib.c @@ -72,7 +72,7 @@ static struct s3c_gpio_cfg gpio_4bit_cfg_eint0011 = { .get_pull = s3c_gpio_getpull_updown, }; -int s3c64xx_gpio2int_gpm(struct gpio_chip *chip, unsigned pin) +static int s3c64xx_gpio2int_gpm(struct gpio_chip *chip, unsigned pin) { return pin < 5 ? IRQ_EINT(23) + pin : -ENXIO; } @@ -138,7 +138,7 @@ static struct s3c_gpio_chip gpio_4bit[] = { }, }; -int s3c64xx_gpio2int_gpl(struct gpio_chip *chip, unsigned pin) +static int s3c64xx_gpio2int_gpl(struct gpio_chip *chip, unsigned pin) { return pin >= 8 ? IRQ_EINT(16) + pin - 8 : -ENXIO; } diff --git a/arch/arm/mach-s3c64xx/mach-smdk6410.c b/arch/arm/mach-s3c64xx/mach-smdk6410.c index e85192a..a80a316 100644 --- a/arch/arm/mach-s3c64xx/mach-smdk6410.c +++ b/arch/arm/mach-s3c64xx/mach-smdk6410.c @@ -28,6 +28,7 @@ #include <linux/delay.h> #include <linux/smsc911x.h> #include <linux/regulator/fixed.h> +#include <linux/regulator/machine.h> #ifdef CONFIG_SMDK6410_WM1190_EV1 #include <linux/mfd/wm8350/core.h> @@ -351,7 +352,7 @@ static struct regulator_init_data smdk6410_vddpll = { /* VDD_UH_MMC, LDO5 on J5 */ static struct regulator_init_data smdk6410_vdduh_mmc = { .constraints = { - .name = "PVDD_UH/PVDD_MMC", + .name = "PVDD_UH+PVDD_MMC", .always_on = 1, }, }; @@ -417,7 +418,7 @@ static struct regulator_init_data smdk6410_vddaudio = { /* S3C64xx internal logic & PLL */ static struct regulator_init_data wm8350_dcdc1_data = { .constraints = { - .name = "PVDD_INT/PVDD_PLL", + .name = "PVDD_INT+PVDD_PLL", .min_uV = 1200000, .max_uV = 1200000, .always_on = 1, @@ -452,7 +453,7 @@ static struct regulator_consumer_supply wm8350_dcdc4_consumers[] = { static struct regulator_init_data wm8350_dcdc4_data = { .constraints = { - .name = "PVDD_HI/PVDD_EXT/PVDD_SYS/PVCCM2MTV", + .name = "PVDD_HI+PVDD_EXT+PVDD_SYS+PVCCM2MTV", .min_uV = 3000000, .max_uV = 3000000, .always_on = 1, @@ -464,7 +465,7 @@ static struct regulator_init_data wm8350_dcdc4_data = { /* OTGi/1190-EV1 HPVDD & AVDD */ static struct regulator_init_data wm8350_ldo4_data = { .constraints = { - .name = "PVDD_OTGI/HPVDD/AVDD", + .name = "PVDD_OTGI+HPVDD+AVDD", .min_uV = 1200000, .max_uV = 1200000, .apply_uV = 1, @@ -552,7 +553,7 @@ static struct wm831x_backlight_pdata wm1192_backlight_pdata = { static struct regulator_init_data wm1192_dcdc3 = { .constraints = { - .name = "PVDD_MEM/PVDD_GPS", + .name = "PVDD_MEM+PVDD_GPS", .always_on = 1, }, }; @@ -563,7 +564,7 @@ static struct regulator_consumer_supply wm1192_ldo1_consumers[] = { static struct regulator_init_data wm1192_ldo1 = { .constraints = { - .name = "PVDD_LCD/PVDD_EXT", + .name = "PVDD_LCD+PVDD_EXT", .always_on = 1, }, .consumer_supplies = wm1192_ldo1_consumers, diff --git a/arch/arm/mach-s3c64xx/setup-keypad.c b/arch/arm/mach-s3c64xx/setup-keypad.c index f8ed0d2..1d4d0ee 100644 --- a/arch/arm/mach-s3c64xx/setup-keypad.c +++ b/arch/arm/mach-s3c64xx/setup-keypad.c @@ -17,7 +17,7 @@ void samsung_keypad_cfg_gpio(unsigned int rows, unsigned int cols) { /* Set all the necessary GPK pins to special-function 3: KP_ROW[x] */ - s3c_gpio_cfgrange_nopull(S3C64XX_GPK(8), 8 + rows, S3C_GPIO_SFN(3)); + s3c_gpio_cfgrange_nopull(S3C64XX_GPK(8), rows, S3C_GPIO_SFN(3)); /* Set all the necessary GPL pins to special-function 3: KP_COL[x] */ s3c_gpio_cfgrange_nopull(S3C64XX_GPL(0), cols, S3C_GPIO_SFN(3)); diff --git a/arch/arm/mach-s3c64xx/setup-sdhci.c b/arch/arm/mach-s3c64xx/setup-sdhci.c index 1a94203..f344a22 100644 --- a/arch/arm/mach-s3c64xx/setup-sdhci.c +++ b/arch/arm/mach-s3c64xx/setup-sdhci.c @@ -56,7 +56,7 @@ void s3c6400_setup_sdhci_cfg_card(struct platform_device *dev, else ctrl3 = (S3C_SDHCI_CTRL3_FCSEL1 | S3C_SDHCI_CTRL3_FCSEL0); - printk(KERN_INFO "%s: CTRL 2=%08x, 3=%08x\n", __func__, ctrl2, ctrl3); + pr_debug("%s: CTRL 2=%08x, 3=%08x\n", __func__, ctrl2, ctrl3); writel(ctrl2, r + S3C_SDHCI_CONTROL2); writel(ctrl3, r + S3C_SDHCI_CONTROL3); } diff --git a/arch/arm/mach-s5p6442/include/mach/map.h b/arch/arm/mach-s5p6442/include/mach/map.h index 203dd5a..058dab4 100644 --- a/arch/arm/mach-s5p6442/include/mach/map.h +++ b/arch/arm/mach-s5p6442/include/mach/map.h @@ -1,6 +1,6 @@ /* linux/arch/arm/mach-s5p6442/include/mach/map.h * - * Copyright (c) 2010 Samsung Electronics Co., Ltd. + * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * S5P6442 - Memory map definitions @@ -16,56 +16,61 @@ #include <plat/map-base.h> #include <plat/map-s5p.h> -#define S5P6442_PA_CHIPID (0xE0000000) -#define S5P_PA_CHIPID S5P6442_PA_CHIPID +#define S5P6442_PA_SDRAM 0x20000000 -#define S5P6442_PA_SYSCON (0xE0100000) -#define S5P_PA_SYSCON S5P6442_PA_SYSCON +#define S5P6442_PA_I2S0 0xC0B00000 +#define S5P6442_PA_I2S1 0xF2200000 -#define S5P6442_PA_GPIO (0xE0200000) +#define S5P6442_PA_CHIPID 0xE0000000 -#define S5P6442_PA_VIC0 (0xE4000000) -#define S5P6442_PA_VIC1 (0xE4100000) -#define S5P6442_PA_VIC2 (0xE4200000) +#define S5P6442_PA_SYSCON 0xE0100000 -#define S5P6442_PA_SROMC (0xE7000000) -#define S5P_PA_SROMC S5P6442_PA_SROMC +#define S5P6442_PA_GPIO 0xE0200000 -#define S5P6442_PA_MDMA 0xE8000000 -#define S5P6442_PA_PDMA 0xE9000000 +#define S5P6442_PA_VIC0 0xE4000000 +#define S5P6442_PA_VIC1 0xE4100000 +#define S5P6442_PA_VIC2 0xE4200000 -#define S5P6442_PA_TIMER (0xEA000000) -#define S5P_PA_TIMER S5P6442_PA_TIMER +#define S5P6442_PA_SROMC 0xE7000000 -#define S5P6442_PA_SYSTIMER (0xEA100000) +#define S5P6442_PA_MDMA 0xE8000000 +#define S5P6442_PA_PDMA 0xE9000000 -#define S5P6442_PA_WATCHDOG (0xEA200000) +#define S5P6442_PA_TIMER 0xEA000000 -#define S5P6442_PA_UART (0xEC000000) +#define S5P6442_PA_SYSTIMER 0xEA100000 -#define S5P_PA_UART0 (S5P6442_PA_UART + 0x0) -#define S5P_PA_UART1 (S5P6442_PA_UART + 0x400) -#define S5P_PA_UART2 (S5P6442_PA_UART + 0x800) -#define S5P_SZ_UART SZ_256 +#define S5P6442_PA_WATCHDOG 0xEA200000 -#define S5P6442_PA_IIC0 (0xEC100000) +#define S5P6442_PA_UART 0xEC000000 -#define S5P6442_PA_SDRAM (0x20000000) -#define S5P_PA_SDRAM S5P6442_PA_SDRAM +#define S5P6442_PA_IIC0 0xEC100000 #define S5P6442_PA_SPI 0xEC300000 -/* I2S */ -#define S5P6442_PA_I2S0 0xC0B00000 -#define S5P6442_PA_I2S1 0xF2200000 - -/* PCM */ #define S5P6442_PA_PCM0 0xF2400000 #define S5P6442_PA_PCM1 0xF2500000 -/* compatibiltiy defines. */ +/* Compatibiltiy Defines */ + +#define S3C_PA_IIC S5P6442_PA_IIC0 #define S3C_PA_WDT S5P6442_PA_WATCHDOG + +#define S5P_PA_CHIPID S5P6442_PA_CHIPID +#define S5P_PA_SDRAM S5P6442_PA_SDRAM +#define S5P_PA_SROMC S5P6442_PA_SROMC +#define S5P_PA_SYSCON S5P6442_PA_SYSCON +#define S5P_PA_TIMER S5P6442_PA_TIMER + +/* UART */ + #define S3C_PA_UART S5P6442_PA_UART -#define S3C_PA_IIC S5P6442_PA_IIC0 + +#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET)) +#define S5P_PA_UART0 S5P_PA_UART(0) +#define S5P_PA_UART1 S5P_PA_UART(1) +#define S5P_PA_UART2 S5P_PA_UART(2) + +#define S5P_SZ_UART SZ_256 #endif /* __ASM_ARCH_MAP_H */ diff --git a/arch/arm/mach-s5p64x0/include/mach/gpio.h b/arch/arm/mach-s5p64x0/include/mach/gpio.h index 5486c8f..adb5f29 100644 --- a/arch/arm/mach-s5p64x0/include/mach/gpio.h +++ b/arch/arm/mach-s5p64x0/include/mach/gpio.h @@ -23,7 +23,7 @@ #define S5P6440_GPIO_A_NR (6) #define S5P6440_GPIO_B_NR (7) #define S5P6440_GPIO_C_NR (8) -#define S5P6440_GPIO_F_NR (2) +#define S5P6440_GPIO_F_NR (16) #define S5P6440_GPIO_G_NR (7) #define S5P6440_GPIO_H_NR (10) #define S5P6440_GPIO_I_NR (16) @@ -36,7 +36,7 @@ #define S5P6450_GPIO_B_NR (7) #define S5P6450_GPIO_C_NR (8) #define S5P6450_GPIO_D_NR (8) -#define S5P6450_GPIO_F_NR (2) +#define S5P6450_GPIO_F_NR (16) #define S5P6450_GPIO_G_NR (14) #define S5P6450_GPIO_H_NR (10) #define S5P6450_GPIO_I_NR (16) diff --git a/arch/arm/mach-s5p64x0/include/mach/map.h b/arch/arm/mach-s5p64x0/include/mach/map.h index a9365e5..95c9125 100644 --- a/arch/arm/mach-s5p64x0/include/mach/map.h +++ b/arch/arm/mach-s5p64x0/include/mach/map.h @@ -1,6 +1,6 @@ /* linux/arch/arm/mach-s5p64x0/include/mach/map.h * - * Copyright (c) 2009-2010 Samsung Electronics Co., Ltd. + * Copyright (c) 2009-2011 Samsung Electronics Co., Ltd. * http://www.samsung.com * * S5P64X0 - Memory map definitions @@ -16,64 +16,46 @@ #include <plat/map-base.h> #include <plat/map-s5p.h> -#define S5P64X0_PA_SDRAM (0x20000000) +#define S5P64X0_PA_SDRAM 0x20000000 -#define S5P64X0_PA_CHIPID (0xE0000000) -#define S5P_PA_CHIPID S5P64X0_PA_CHIPID - -#define S5P64X0_PA_SYSCON (0xE0100000) -#define S5P_PA_SYSCON S5P64X0_PA_SYSCON - -#define S5P64X0_PA_GPIO (0xE0308000) - -#define S5P64X0_PA_VIC0 (0xE4000000) -#define S5P64X0_PA_VIC1 (0xE4100000) +#define S5P64X0_PA_CHIPID 0xE0000000 -#define S5P64X0_PA_SROMC (0xE7000000) -#define S5P_PA_SROMC S5P64X0_PA_SROMC - -#define S5P64X0_PA_PDMA (0xE9000000) - -#define S5P64X0_PA_TIMER (0xEA000000) -#define S5P_PA_TIMER S5P64X0_PA_TIMER +#define S5P64X0_PA_SYSCON 0xE0100000 -#define S5P64X0_PA_RTC (0xEA100000) +#define S5P64X0_PA_GPIO 0xE0308000 -#define S5P64X0_PA_WDT (0xEA200000) +#define S5P64X0_PA_VIC0 0xE4000000 +#define S5P64X0_PA_VIC1 0xE4100000 -#define S5P6440_PA_UART(x) (0xEC000000 + ((x) * S3C_UART_OFFSET)) -#define S5P6450_PA_UART(x) ((x < 5) ? (0xEC800000 + ((x) * S3C_UART_OFFSET)) : (0xEC000000)) +#define S5P64X0_PA_SROMC 0xE7000000 -#define S5P_PA_UART0 S5P6450_PA_UART(0) -#define S5P_PA_UART1 S5P6450_PA_UART(1) -#define S5P_PA_UART2 S5P6450_PA_UART(2) -#define S5P_PA_UART3 S5P6450_PA_UART(3) -#define S5P_PA_UART4 S5P6450_PA_UART(4) -#define S5P_PA_UART5 S5P6450_PA_UART(5) +#define S5P64X0_PA_PDMA 0xE9000000 -#define S5P_SZ_UART SZ_256 +#define S5P64X0_PA_TIMER 0xEA000000 +#define S5P64X0_PA_RTC 0xEA100000 +#define S5P64X0_PA_WDT 0xEA200000 -#define S5P6440_PA_IIC0 (0xEC104000) -#define S5P6440_PA_IIC1 (0xEC20F000) -#define S5P6450_PA_IIC0 (0xEC100000) -#define S5P6450_PA_IIC1 (0xEC200000) +#define S5P6440_PA_IIC0 0xEC104000 +#define S5P6440_PA_IIC1 0xEC20F000 +#define S5P6450_PA_IIC0 0xEC100000 +#define S5P6450_PA_IIC1 0xEC200000 -#define S5P64X0_PA_SPI0 (0xEC400000) -#define S5P64X0_PA_SPI1 (0xEC500000) +#define S5P64X0_PA_SPI0 0xEC400000 +#define S5P64X0_PA_SPI1 0xEC500000 -#define S5P64X0_PA_HSOTG (0xED100000) +#define S5P64X0_PA_HSOTG 0xED100000 #define S5P64X0_PA_HSMMC(x) (0xED800000 + ((x) * 0x100000)) -#define S5P64X0_PA_I2S (0xF2000000) +#define S5P64X0_PA_I2S 0xF2000000 #define S5P6450_PA_I2S1 0xF2800000 #define S5P6450_PA_I2S2 0xF2900000 -#define S5P64X0_PA_PCM (0xF2100000) +#define S5P64X0_PA_PCM 0xF2100000 -#define S5P64X0_PA_ADC (0xF3000000) +#define S5P64X0_PA_ADC 0xF3000000 -/* compatibiltiy defines. */ +/* Compatibiltiy Defines */ #define S3C_PA_HSMMC0 S5P64X0_PA_HSMMC(0) #define S3C_PA_HSMMC1 S5P64X0_PA_HSMMC(1) @@ -83,6 +65,25 @@ #define S3C_PA_RTC S5P64X0_PA_RTC #define S3C_PA_WDT S5P64X0_PA_WDT +#define S5P_PA_CHIPID S5P64X0_PA_CHIPID +#define S5P_PA_SROMC S5P64X0_PA_SROMC +#define S5P_PA_SYSCON S5P64X0_PA_SYSCON +#define S5P_PA_TIMER S5P64X0_PA_TIMER + #define SAMSUNG_PA_ADC S5P64X0_PA_ADC +/* UART */ + +#define S5P6440_PA_UART(x) (0xEC000000 + ((x) * S3C_UART_OFFSET)) +#define S5P6450_PA_UART(x) ((x < 5) ? (0xEC800000 + ((x) * S3C_UART_OFFSET)) : (0xEC000000)) + +#define S5P_PA_UART0 S5P6450_PA_UART(0) +#define S5P_PA_UART1 S5P6450_PA_UART(1) +#define S5P_PA_UART2 S5P6450_PA_UART(2) +#define S5P_PA_UART3 S5P6450_PA_UART(3) +#define S5P_PA_UART4 S5P6450_PA_UART(4) +#define S5P_PA_UART5 S5P6450_PA_UART(5) + +#define S5P_SZ_UART SZ_256 + #endif /* __ASM_ARCH_MAP_H */ diff --git a/arch/arm/mach-s5pc100/include/mach/map.h b/arch/arm/mach-s5pc100/include/mach/map.h index 328467b..ccbe6b7 100644 --- a/arch/arm/mach-s5pc100/include/mach/map.h +++ b/arch/arm/mach-s5pc100/include/mach/map.h @@ -1,5 +1,8 @@ /* linux/arch/arm/mach-s5pc100/include/mach/map.h * + * Copyright (c) 2011 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * * Copyright 2009 Samsung Electronics Co. * Byungho Min <bhmin@samsung.com> * @@ -16,145 +19,115 @@ #include <plat/map-base.h> #include <plat/map-s5p.h> -/* - * map-base.h has already defined virtual memory address - * S3C_VA_IRQ S3C_ADDR(0x00000000) irq controller(s) - * S3C_VA_SYS S3C_ADDR(0x00100000) system control - * S3C_VA_MEM S3C_ADDR(0x00200000) system control (not used) - * S3C_VA_TIMER S3C_ADDR(0x00300000) timer block - * S3C_VA_WATCHDOG S3C_ADDR(0x00400000) watchdog - * S3C_VA_UART S3C_ADDR(0x01000000) UART - * - * S5PC100 specific virtual memory address can be defined here - * S5PC1XX_VA_GPIO S3C_ADDR(0x00500000) GPIO - * - */ +#define S5PC100_PA_SDRAM 0x20000000 + +#define S5PC100_PA_ONENAND 0xE7100000 +#define S5PC100_PA_ONENAND_BUF 0xB0000000 + +#define S5PC100_PA_CHIPID 0xE0000000 -#define S5PC100_PA_ONENAND_BUF (0xB0000000) -#define S5PC100_SZ_ONENAND_BUF (SZ_256M - SZ_32M) +#define S5PC100_PA_SYSCON 0xE0100000 -/* Chip ID */ +#define S5PC100_PA_OTHERS 0xE0200000 -#define S5PC100_PA_CHIPID (0xE0000000) -#define S5P_PA_CHIPID S5PC100_PA_CHIPID +#define S5PC100_PA_GPIO 0xE0300000 -#define S5PC100_PA_SYSCON (0xE0100000) -#define S5P_PA_SYSCON S5PC100_PA_SYSCON +#define S5PC100_PA_VIC0 0xE4000000 +#define S5PC100_PA_VIC1 0xE4100000 +#define S5PC100_PA_VIC2 0xE4200000 -#define S5PC100_PA_OTHERS (0xE0200000) -#define S5PC100_VA_OTHERS (S3C_VA_SYS + 0x10000) +#define S5PC100_PA_SROMC 0xE7000000 -#define S5PC100_PA_GPIO (0xE0300000) -#define S5PC1XX_VA_GPIO S3C_ADDR(0x00500000) +#define S5PC100_PA_CFCON 0xE7800000 -/* Interrupt */ -#define S5PC100_PA_VIC0 (0xE4000000) -#define S5PC100_PA_VIC1 (0xE4100000) -#define S5PC100_PA_VIC2 (0xE4200000) -#define S5PC100_VA_VIC S3C_VA_IRQ -#define S5PC100_VA_VIC_OFFSET 0x10000 -#define S5PC1XX_VA_VIC(x) (S5PC100_VA_VIC + ((x) * S5PC100_VA_VIC_OFFSET)) +#define S5PC100_PA_MDMA 0xE8100000 +#define S5PC100_PA_PDMA0 0xE9000000 +#define S5PC100_PA_PDMA1 0xE9200000 -#define S5PC100_PA_SROMC (0xE7000000) -#define S5P_PA_SROMC S5PC100_PA_SROMC +#define S5PC100_PA_TIMER 0xEA000000 +#define S5PC100_PA_SYSTIMER 0xEA100000 +#define S5PC100_PA_WATCHDOG 0xEA200000 +#define S5PC100_PA_RTC 0xEA300000 -#define S5PC100_PA_ONENAND (0xE7100000) +#define S5PC100_PA_UART 0xEC000000 -#define S5PC100_PA_CFCON (0xE7800000) +#define S5PC100_PA_IIC0 0xEC100000 +#define S5PC100_PA_IIC1 0xEC200000 -/* DMA */ -#define S5PC100_PA_MDMA (0xE8100000) -#define S5PC100_PA_PDMA0 (0xE9000000) -#define S5PC100_PA_PDMA1 (0xE9200000) +#define S5PC100_PA_SPI0 0xEC300000 +#define S5PC100_PA_SPI1 0xEC400000 +#define S5PC100_PA_SPI2 0xEC500000 -/* Timer */ -#define S5PC100_PA_TIMER (0xEA000000) -#define S5P_PA_TIMER S5PC100_PA_TIMER +#define S5PC100_PA_USB_HSOTG 0xED200000 +#define S5PC100_PA_USB_HSPHY 0xED300000 -#define S5PC100_PA_SYSTIMER (0xEA100000) +#define S5PC100_PA_HSMMC(x) (0xED800000 + ((x) * 0x100000)) -#define S5PC100_PA_WATCHDOG (0xEA200000) -#define S5PC100_PA_RTC (0xEA300000) +#define S5PC100_PA_FB 0xEE000000 -#define S5PC100_PA_UART (0xEC000000) +#define S5PC100_PA_FIMC0 0xEE200000 +#define S5PC100_PA_FIMC1 0xEE300000 +#define S5PC100_PA_FIMC2 0xEE400000 -#define S5P_PA_UART0 (S5PC100_PA_UART + 0x0) -#define S5P_PA_UART1 (S5PC100_PA_UART + 0x400) -#define S5P_PA_UART2 (S5PC100_PA_UART + 0x800) -#define S5P_PA_UART3 (S5PC100_PA_UART + 0xC00) -#define S5P_SZ_UART SZ_256 +#define S5PC100_PA_I2S0 0xF2000000 +#define S5PC100_PA_I2S1 0xF2100000 +#define S5PC100_PA_I2S2 0xF2200000 -#define S5PC100_PA_IIC0 (0xEC100000) -#define S5PC100_PA_IIC1 (0xEC200000) +#define S5PC100_PA_AC97 0xF2300000 -/* SPI */ -#define S5PC100_PA_SPI0 0xEC300000 -#define S5PC100_PA_SPI1 0xEC400000 -#define S5PC100_PA_SPI2 0xEC500000 +#define S5PC100_PA_PCM0 0xF2400000 +#define S5PC100_PA_PCM1 0xF2500000 -/* USB HS OTG */ -#define S5PC100_PA_USB_HSOTG (0xED200000) -#define S5PC100_PA_USB_HSPHY (0xED300000) +#define S5PC100_PA_SPDIF 0xF2600000 -#define S5PC100_PA_FB (0xEE000000) +#define S5PC100_PA_TSADC 0xF3000000 -#define S5PC100_PA_FIMC0 (0xEE200000) -#define S5PC100_PA_FIMC1 (0xEE300000) -#define S5PC100_PA_FIMC2 (0xEE400000) +#define S5PC100_PA_KEYPAD 0xF3100000 -#define S5PC100_PA_I2S0 (0xF2000000) -#define S5PC100_PA_I2S1 (0xF2100000) -#define S5PC100_PA_I2S2 (0xF2200000) +/* Compatibiltiy Defines */ -#define S5PC100_PA_AC97 0xF2300000 +#define S3C_PA_FB S5PC100_PA_FB +#define S3C_PA_HSMMC0 S5PC100_PA_HSMMC(0) +#define S3C_PA_HSMMC1 S5PC100_PA_HSMMC(1) +#define S3C_PA_HSMMC2 S5PC100_PA_HSMMC(2) +#define S3C_PA_IIC S5PC100_PA_IIC0 +#define S3C_PA_IIC1 S5PC100_PA_IIC1 +#define S3C_PA_KEYPAD S5PC100_PA_KEYPAD +#define S3C_PA_ONENAND S5PC100_PA_ONENAND +#define S3C_PA_ONENAND_BUF S5PC100_PA_ONENAND_BUF +#define S3C_PA_RTC S5PC100_PA_RTC +#define S3C_PA_TSADC S5PC100_PA_TSADC +#define S3C_PA_USB_HSOTG S5PC100_PA_USB_HSOTG +#define S3C_PA_USB_HSPHY S5PC100_PA_USB_HSPHY +#define S3C_PA_WDT S5PC100_PA_WATCHDOG -/* PCM */ -#define S5PC100_PA_PCM0 0xF2400000 -#define S5PC100_PA_PCM1 0xF2500000 +#define S5P_PA_CHIPID S5PC100_PA_CHIPID +#define S5P_PA_FIMC0 S5PC100_PA_FIMC0 +#define S5P_PA_FIMC1 S5PC100_PA_FIMC1 +#define S5P_PA_FIMC2 S5PC100_PA_FIMC2 +#define S5P_PA_SDRAM S5PC100_PA_SDRAM +#define S5P_PA_SROMC S5PC100_PA_SROMC +#define S5P_PA_SYSCON S5PC100_PA_SYSCON +#define S5P_PA_TIMER S5PC100_PA_TIMER -#define S5PC100_PA_SPDIF 0xF2600000 +#define SAMSUNG_PA_ADC S5PC100_PA_TSADC +#define SAMSUNG_PA_CFCON S5PC100_PA_CFCON +#define SAMSUNG_PA_KEYPAD S5PC100_PA_KEYPAD -#define S5PC100_PA_TSADC (0xF3000000) +#define S5PC100_VA_OTHERS (S3C_VA_SYS + 0x10000) -/* KEYPAD */ -#define S5PC100_PA_KEYPAD (0xF3100000) +#define S3C_SZ_ONENAND_BUF (SZ_256M - SZ_32M) -#define S5PC100_PA_HSMMC(x) (0xED800000 + ((x) * 0x100000)) +/* UART */ -#define S5PC100_PA_SDRAM (0x20000000) -#define S5P_PA_SDRAM S5PC100_PA_SDRAM +#define S3C_PA_UART S5PC100_PA_UART -/* compatibiltiy defines. */ -#define S3C_PA_UART S5PC100_PA_UART -#define S3C_PA_IIC S5PC100_PA_IIC0 -#define S3C_PA_IIC1 S5PC100_PA_IIC1 -#define S3C_PA_FB S5PC100_PA_FB -#define S3C_PA_G2D S5PC100_PA_G2D -#define S3C_PA_G3D S5PC100_PA_G3D -#define S3C_PA_JPEG S5PC100_PA_JPEG -#define S3C_PA_ROTATOR S5PC100_PA_ROTATOR -#define S5P_VA_VIC0 S5PC1XX_VA_VIC(0) -#define S5P_VA_VIC1 S5PC1XX_VA_VIC(1) -#define S5P_VA_VIC2 S5PC1XX_VA_VIC(2) -#define S3C_PA_USB_HSOTG S5PC100_PA_USB_HSOTG -#define S3C_PA_USB_HSPHY S5PC100_PA_USB_HSPHY -#define S3C_PA_HSMMC0 S5PC100_PA_HSMMC(0) -#define S3C_PA_HSMMC1 S5PC100_PA_HSMMC(1) -#define S3C_PA_HSMMC2 S5PC100_PA_HSMMC(2) -#define S3C_PA_KEYPAD S5PC100_PA_KEYPAD -#define S3C_PA_WDT S5PC100_PA_WATCHDOG -#define S3C_PA_TSADC S5PC100_PA_TSADC -#define S3C_PA_ONENAND S5PC100_PA_ONENAND -#define S3C_PA_ONENAND_BUF S5PC100_PA_ONENAND_BUF -#define S3C_SZ_ONENAND_BUF S5PC100_SZ_ONENAND_BUF -#define S3C_PA_RTC S5PC100_PA_RTC - -#define SAMSUNG_PA_ADC S5PC100_PA_TSADC -#define SAMSUNG_PA_CFCON S5PC100_PA_CFCON -#define SAMSUNG_PA_KEYPAD S5PC100_PA_KEYPAD +#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET)) +#define S5P_PA_UART0 S5P_PA_UART(0) +#define S5P_PA_UART1 S5P_PA_UART(1) +#define S5P_PA_UART2 S5P_PA_UART(2) +#define S5P_PA_UART3 S5P_PA_UART(3) -#define S5P_PA_FIMC0 S5PC100_PA_FIMC0 -#define S5P_PA_FIMC1 S5PC100_PA_FIMC1 -#define S5P_PA_FIMC2 S5PC100_PA_FIMC2 +#define S5P_SZ_UART SZ_256 -#endif /* __ASM_ARCH_C100_MAP_H */ +#endif /* __ASM_ARCH_MAP_H */ diff --git a/arch/arm/mach-s5pv210/include/mach/map.h b/arch/arm/mach-s5pv210/include/mach/map.h index 3611492..1dd5883 100644 --- a/arch/arm/mach-s5pv210/include/mach/map.h +++ b/arch/arm/mach-s5pv210/include/mach/map.h @@ -1,6 +1,6 @@ /* linux/arch/arm/mach-s5pv210/include/mach/map.h * - * Copyright (c) 2010 Samsung Electronics Co., Ltd. + * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * S5PV210 - Memory map definitions @@ -16,122 +16,120 @@ #include <plat/map-base.h> #include <plat/map-s5p.h> -#define S5PV210_PA_SROM_BANK5 (0xA8000000) +#define S5PV210_PA_SDRAM 0x20000000 -#define S5PC110_PA_ONENAND (0xB0000000) -#define S5P_PA_ONENAND S5PC110_PA_ONENAND +#define S5PV210_PA_SROM_BANK5 0xA8000000 -#define S5PC110_PA_ONENAND_DMA (0xB0600000) -#define S5P_PA_ONENAND_DMA S5PC110_PA_ONENAND_DMA +#define S5PC110_PA_ONENAND 0xB0000000 +#define S5PC110_PA_ONENAND_DMA 0xB0600000 -#define S5PV210_PA_CHIPID (0xE0000000) -#define S5P_PA_CHIPID S5PV210_PA_CHIPID +#define S5PV210_PA_CHIPID 0xE0000000 -#define S5PV210_PA_SYSCON (0xE0100000) -#define S5P_PA_SYSCON S5PV210_PA_SYSCON +#define S5PV210_PA_SYSCON 0xE0100000 -#define S5PV210_PA_GPIO (0xE0200000) +#define S5PV210_PA_GPIO 0xE0200000 -/* SPI */ -#define S5PV210_PA_SPI0 0xE1300000 -#define S5PV210_PA_SPI1 0xE1400000 +#define S5PV210_PA_SPDIF 0xE1100000 -#define S5PV210_PA_KEYPAD (0xE1600000) +#define S5PV210_PA_SPI0 0xE1300000 +#define S5PV210_PA_SPI1 0xE1400000 -#define S5PV210_PA_IIC0 (0xE1800000) -#define S5PV210_PA_IIC1 (0xFAB00000) -#define S5PV210_PA_IIC2 (0xE1A00000) +#define S5PV210_PA_KEYPAD 0xE1600000 -#define S5PV210_PA_TIMER (0xE2500000) -#define S5P_PA_TIMER S5PV210_PA_TIMER +#define S5PV210_PA_ADC 0xE1700000 -#define S5PV210_PA_SYSTIMER (0xE2600000) +#define S5PV210_PA_IIC0 0xE1800000 +#define S5PV210_PA_IIC1 0xFAB00000 +#define S5PV210_PA_IIC2 0xE1A00000 -#define S5PV210_PA_WATCHDOG (0xE2700000) +#define S5PV210_PA_AC97 0xE2200000 -#define S5PV210_PA_RTC (0xE2800000) -#define S5PV210_PA_UART (0xE2900000) +#define S5PV210_PA_PCM0 0xE2300000 +#define S5PV210_PA_PCM1 0xE1200000 +#define S5PV210_PA_PCM2 0xE2B00000 -#define S5P_PA_UART0 (S5PV210_PA_UART + 0x0) -#define S5P_PA_UART1 (S5PV210_PA_UART + 0x400) -#define S5P_PA_UART2 (S5PV210_PA_UART + 0x800) -#define S5P_PA_UART3 (S5PV210_PA_UART + 0xC00) +#define S5PV210_PA_TIMER 0xE2500000 +#define S5PV210_PA_SYSTIMER 0xE2600000 +#define S5PV210_PA_WATCHDOG 0xE2700000 +#define S5PV210_PA_RTC 0xE2800000 -#define S5P_SZ_UART SZ_256 +#define S5PV210_PA_UART 0xE2900000 -#define S3C_VA_UARTx(x) (S3C_VA_UART + ((x) * S3C_UART_OFFSET)) +#define S5PV210_PA_SROMC 0xE8000000 -#define S5PV210_PA_SROMC (0xE8000000) -#define S5P_PA_SROMC S5PV210_PA_SROMC +#define S5PV210_PA_CFCON 0xE8200000 -#define S5PV210_PA_CFCON (0xE8200000) +#define S5PV210_PA_HSMMC(x) (0xEB000000 + ((x) * 0x100000)) -#define S5PV210_PA_MDMA 0xFA200000 -#define S5PV210_PA_PDMA0 0xE0900000 -#define S5PV210_PA_PDMA1 0xE0A00000 +#define S5PV210_PA_HSOTG 0xEC000000 +#define S5PV210_PA_HSPHY 0xEC100000 -#define S5PV210_PA_FB (0xF8000000) +#define S5PV210_PA_IIS0 0xEEE30000 +#define S5PV210_PA_IIS1 0xE2100000 +#define S5PV210_PA_IIS2 0xE2A00000 -#define S5PV210_PA_FIMC0 (0xFB200000) -#define S5PV210_PA_FIMC1 (0xFB300000) -#define S5PV210_PA_FIMC2 (0xFB400000) +#define S5PV210_PA_DMC0 0xF0000000 +#define S5PV210_PA_DMC1 0xF1400000 -#define S5PV210_PA_HSMMC(x) (0xEB000000 + ((x) * 0x100000)) +#define S5PV210_PA_VIC0 0xF2000000 +#define S5PV210_PA_VIC1 0xF2100000 +#define S5PV210_PA_VIC2 0xF2200000 +#define S5PV210_PA_VIC3 0xF2300000 -#define S5PV210_PA_HSOTG (0xEC000000) -#define S5PV210_PA_HSPHY (0xEC100000) +#define S5PV210_PA_FB 0xF8000000 -#define S5PV210_PA_VIC0 (0xF2000000) -#define S5PV210_PA_VIC1 (0xF2100000) -#define S5PV210_PA_VIC2 (0xF2200000) -#define S5PV210_PA_VIC3 (0xF2300000) +#define S5PV210_PA_MDMA 0xFA200000 +#define S5PV210_PA_PDMA0 0xE0900000 +#define S5PV210_PA_PDMA1 0xE0A00000 -#define S5PV210_PA_SDRAM (0x20000000) -#define S5P_PA_SDRAM S5PV210_PA_SDRAM +#define S5PV210_PA_MIPI_CSIS 0xFA600000 -/* S/PDIF */ -#define S5PV210_PA_SPDIF 0xE1100000 +#define S5PV210_PA_FIMC0 0xFB200000 +#define S5PV210_PA_FIMC1 0xFB300000 +#define S5PV210_PA_FIMC2 0xFB400000 -/* I2S */ -#define S5PV210_PA_IIS0 0xEEE30000 -#define S5PV210_PA_IIS1 0xE2100000 -#define S5PV210_PA_IIS2 0xE2A00000 +/* Compatibiltiy Defines */ -/* PCM */ -#define S5PV210_PA_PCM0 0xE2300000 -#define S5PV210_PA_PCM1 0xE1200000 -#define S5PV210_PA_PCM2 0xE2B00000 +#define S3C_PA_FB S5PV210_PA_FB +#define S3C_PA_HSMMC0 S5PV210_PA_HSMMC(0) +#define S3C_PA_HSMMC1 S5PV210_PA_HSMMC(1) +#define S3C_PA_HSMMC2 S5PV210_PA_HSMMC(2) +#define S3C_PA_HSMMC3 S5PV210_PA_HSMMC(3) +#define S3C_PA_IIC S5PV210_PA_IIC0 +#define S3C_PA_IIC1 S5PV210_PA_IIC1 +#define S3C_PA_IIC2 S5PV210_PA_IIC2 +#define S3C_PA_RTC S5PV210_PA_RTC +#define S3C_PA_USB_HSOTG S5PV210_PA_HSOTG +#define S3C_PA_WDT S5PV210_PA_WATCHDOG -/* AC97 */ -#define S5PV210_PA_AC97 0xE2200000 +#define S5P_PA_CHIPID S5PV210_PA_CHIPID +#define S5P_PA_FIMC0 S5PV210_PA_FIMC0 +#define S5P_PA_FIMC1 S5PV210_PA_FIMC1 +#define S5P_PA_FIMC2 S5PV210_PA_FIMC2 +#define S5P_PA_MIPI_CSIS0 S5PV210_PA_MIPI_CSIS +#define S5P_PA_ONENAND S5PC110_PA_ONENAND +#define S5P_PA_ONENAND_DMA S5PC110_PA_ONENAND_DMA +#define S5P_PA_SDRAM S5PV210_PA_SDRAM +#define S5P_PA_SROMC S5PV210_PA_SROMC +#define S5P_PA_SYSCON S5PV210_PA_SYSCON +#define S5P_PA_TIMER S5PV210_PA_TIMER -#define S5PV210_PA_ADC (0xE1700000) +#define SAMSUNG_PA_ADC S5PV210_PA_ADC +#define SAMSUNG_PA_CFCON S5PV210_PA_CFCON +#define SAMSUNG_PA_KEYPAD S5PV210_PA_KEYPAD -#define S5PV210_PA_DMC0 (0xF0000000) -#define S5PV210_PA_DMC1 (0xF1400000) +/* UART */ -#define S5PV210_PA_MIPI_CSIS 0xFA600000 +#define S3C_VA_UARTx(x) (S3C_VA_UART + ((x) * S3C_UART_OFFSET)) -/* compatibiltiy defines. */ -#define S3C_PA_UART S5PV210_PA_UART -#define S3C_PA_HSMMC0 S5PV210_PA_HSMMC(0) -#define S3C_PA_HSMMC1 S5PV210_PA_HSMMC(1) -#define S3C_PA_HSMMC2 S5PV210_PA_HSMMC(2) -#define S3C_PA_HSMMC3 S5PV210_PA_HSMMC(3) -#define S3C_PA_IIC S5PV210_PA_IIC0 -#define S3C_PA_IIC1 S5PV210_PA_IIC1 -#define S3C_PA_IIC2 S5PV210_PA_IIC2 -#define S3C_PA_FB S5PV210_PA_FB -#define S3C_PA_RTC S5PV210_PA_RTC -#define S3C_PA_WDT S5PV210_PA_WATCHDOG -#define S3C_PA_USB_HSOTG S5PV210_PA_HSOTG -#define S5P_PA_FIMC0 S5PV210_PA_FIMC0 -#define S5P_PA_FIMC1 S5PV210_PA_FIMC1 -#define S5P_PA_FIMC2 S5PV210_PA_FIMC2 -#define S5P_PA_MIPI_CSIS0 S5PV210_PA_MIPI_CSIS +#define S3C_PA_UART S5PV210_PA_UART -#define SAMSUNG_PA_ADC S5PV210_PA_ADC -#define SAMSUNG_PA_CFCON S5PV210_PA_CFCON -#define SAMSUNG_PA_KEYPAD S5PV210_PA_KEYPAD +#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET)) +#define S5P_PA_UART0 S5P_PA_UART(0) +#define S5P_PA_UART1 S5P_PA_UART(1) +#define S5P_PA_UART2 S5P_PA_UART(2) +#define S5P_PA_UART3 S5P_PA_UART(3) + +#define S5P_SZ_UART SZ_256 #endif /* __ASM_ARCH_MAP_H */ diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c index 461aa035..557add4 100644 --- a/arch/arm/mach-s5pv210/mach-aquila.c +++ b/arch/arm/mach-s5pv210/mach-aquila.c @@ -149,7 +149,7 @@ static struct regulator_init_data aquila_ldo2_data = { static struct regulator_init_data aquila_ldo3_data = { .constraints = { - .name = "VUSB/MIPI_1.1V", + .name = "VUSB+MIPI_1.1V", .min_uV = 1100000, .max_uV = 1100000, .apply_uV = 1, @@ -197,7 +197,7 @@ static struct regulator_init_data aquila_ldo7_data = { static struct regulator_init_data aquila_ldo8_data = { .constraints = { - .name = "VUSB/VADC_3.3V", + .name = "VUSB+VADC_3.3V", .min_uV = 3300000, .max_uV = 3300000, .apply_uV = 1, @@ -207,7 +207,7 @@ static struct regulator_init_data aquila_ldo8_data = { static struct regulator_init_data aquila_ldo9_data = { .constraints = { - .name = "VCC/VCAM_2.8V", + .name = "VCC+VCAM_2.8V", .min_uV = 2800000, .max_uV = 2800000, .apply_uV = 1, @@ -381,9 +381,12 @@ static struct max8998_platform_data aquila_max8998_pdata = { .buck1_set1 = S5PV210_GPH0(3), .buck1_set2 = S5PV210_GPH0(4), .buck2_set3 = S5PV210_GPH0(5), - .buck1_max_voltage1 = 1200000, - .buck1_max_voltage2 = 1200000, - .buck2_max_voltage = 1200000, + .buck1_voltage1 = 1200000, + .buck1_voltage2 = 1200000, + .buck1_voltage3 = 1200000, + .buck1_voltage4 = 1200000, + .buck2_voltage1 = 1200000, + .buck2_voltage2 = 1200000, }; #endif diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c index e22d511..056f5c7 100644 --- a/arch/arm/mach-s5pv210/mach-goni.c +++ b/arch/arm/mach-s5pv210/mach-goni.c @@ -288,7 +288,7 @@ static struct regulator_init_data goni_ldo2_data = { static struct regulator_init_data goni_ldo3_data = { .constraints = { - .name = "VUSB/MIPI_1.1V", + .name = "VUSB+MIPI_1.1V", .min_uV = 1100000, .max_uV = 1100000, .apply_uV = 1, @@ -337,7 +337,7 @@ static struct regulator_init_data goni_ldo7_data = { static struct regulator_init_data goni_ldo8_data = { .constraints = { - .name = "VUSB/VADC_3.3V", + .name = "VUSB+VADC_3.3V", .min_uV = 3300000, .max_uV = 3300000, .apply_uV = 1, @@ -347,7 +347,7 @@ static struct regulator_init_data goni_ldo8_data = { static struct regulator_init_data goni_ldo9_data = { .constraints = { - .name = "VCC/VCAM_2.8V", + .name = "VCC+VCAM_2.8V", .min_uV = 2800000, .max_uV = 2800000, .apply_uV = 1, @@ -521,9 +521,12 @@ static struct max8998_platform_data goni_max8998_pdata = { .buck1_set1 = S5PV210_GPH0(3), .buck1_set2 = S5PV210_GPH0(4), .buck2_set3 = S5PV210_GPH0(5), - .buck1_max_voltage1 = 1200000, - .buck1_max_voltage2 = 1200000, - .buck2_max_voltage = 1200000, + .buck1_voltage1 = 1200000, + .buck1_voltage2 = 1200000, + .buck1_voltage3 = 1200000, + .buck1_voltage4 = 1200000, + .buck2_voltage1 = 1200000, + .buck2_voltage2 = 1200000, }; #endif diff --git a/arch/arm/mach-s5pv310/Kconfig b/arch/arm/mach-s5pv310/Kconfig index 09c4c21..b2a9acc 100644 --- a/arch/arm/mach-s5pv310/Kconfig +++ b/arch/arm/mach-s5pv310/Kconfig @@ -122,6 +122,7 @@ config MACH_SMDKV310 select S3C_DEV_HSMMC2 select S3C_DEV_HSMMC3 select S5PV310_DEV_PD + select S5PV310_DEV_SYSMMU select S5PV310_SETUP_I2C1 select S5PV310_SETUP_SDHCI help diff --git a/arch/arm/mach-s5pv310/include/mach/map.h b/arch/arm/mach-s5pv310/include/mach/map.h index 74d4006..901657f 100644 --- a/arch/arm/mach-s5pv310/include/mach/map.h +++ b/arch/arm/mach-s5pv310/include/mach/map.h @@ -1,6 +1,6 @@ /* linux/arch/arm/mach-s5pv310/include/mach/map.h * - * Copyright (c) 2010 Samsung Electronics Co., Ltd. + * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * S5PV310 - Memory map definitions @@ -23,90 +23,43 @@ #include <plat/map-s5p.h> -#define S5PV310_PA_SYSRAM (0x02025000) +#define S5PV310_PA_SYSRAM 0x02025000 -#define S5PV310_PA_SROM_BANK(x) (0x04000000 + ((x) * 0x01000000)) - -#define S5PC210_PA_ONENAND (0x0C000000) -#define S5P_PA_ONENAND S5PC210_PA_ONENAND - -#define S5PC210_PA_ONENAND_DMA (0x0C600000) -#define S5P_PA_ONENAND_DMA S5PC210_PA_ONENAND_DMA - -#define S5PV310_PA_CHIPID (0x10000000) -#define S5P_PA_CHIPID S5PV310_PA_CHIPID - -#define S5PV310_PA_SYSCON (0x10010000) -#define S5P_PA_SYSCON S5PV310_PA_SYSCON +#define S5PV310_PA_I2S0 0x03830000 +#define S5PV310_PA_I2S1 0xE3100000 +#define S5PV310_PA_I2S2 0xE2A00000 -#define S5PV310_PA_PMU (0x10020000) +#define S5PV310_PA_PCM0 0x03840000 +#define S5PV310_PA_PCM1 0x13980000 +#define S5PV310_PA_PCM2 0x13990000 -#define S5PV310_PA_CMU (0x10030000) - -#define S5PV310_PA_WATCHDOG (0x10060000) -#define S5PV310_PA_RTC (0x10070000) - -#define S5PV310_PA_DMC0 (0x10400000) - -#define S5PV310_PA_COMBINER (0x10448000) - -#define S5PV310_PA_COREPERI (0x10500000) -#define S5PV310_PA_GIC_CPU (0x10500100) -#define S5PV310_PA_TWD (0x10500600) -#define S5PV310_PA_GIC_DIST (0x10501000) -#define S5PV310_PA_L2CC (0x10502000) - -/* DMA */ -#define S5PV310_PA_MDMA 0x10810000 -#define S5PV310_PA_PDMA0 0x12680000 -#define S5PV310_PA_PDMA1 0x12690000 - -#define S5PV310_PA_GPIO1 (0x11400000) -#define S5PV310_PA_GPIO2 (0x11000000) -#define S5PV310_PA_GPIO3 (0x03860000) - -#define S5PV310_PA_MIPI_CSIS0 0x11880000 -#define S5PV310_PA_MIPI_CSIS1 0x11890000 +#define S5PV310_PA_SROM_BANK(x) (0x04000000 + ((x) * 0x01000000)) -#define S5PV310_PA_HSMMC(x) (0x12510000 + ((x) * 0x10000)) +#define S5PC210_PA_ONENAND 0x0C000000 +#define S5PC210_PA_ONENAND_DMA 0x0C600000 -#define S5PV310_PA_SROMC (0x12570000) -#define S5P_PA_SROMC S5PV310_PA_SROMC +#define S5PV310_PA_CHIPID 0x10000000 -/* S/PDIF */ -#define S5PV310_PA_SPDIF 0xE1100000 +#define S5PV310_PA_SYSCON 0x10010000 +#define S5PV310_PA_PMU 0x10020000 +#define S5PV310_PA_CMU 0x10030000 -/* I2S */ -#define S5PV310_PA_I2S0 0x03830000 -#define S5PV310_PA_I2S1 0xE3100000 -#define S5PV310_PA_I2S2 0xE2A00000 +#define S5PV310_PA_WATCHDOG 0x10060000 +#define S5PV310_PA_RTC 0x10070000 -/* PCM */ -#define S5PV310_PA_PCM0 0x03840000 -#define S5PV310_PA_PCM1 0x13980000 -#define S5PV310_PA_PCM2 0x13990000 +#define S5PV310_PA_DMC0 0x10400000 -/* AC97 */ -#define S5PV310_PA_AC97 0x139A0000 +#define S5PV310_PA_COMBINER 0x10448000 -#define S5PV310_PA_UART (0x13800000) +#define S5PV310_PA_COREPERI 0x10500000 +#define S5PV310_PA_GIC_CPU 0x10500100 +#define S5PV310_PA_TWD 0x10500600 +#define S5PV310_PA_GIC_DIST 0x10501000 +#define S5PV310_PA_L2CC 0x10502000 -#define S5P_PA_UART(x) (S5PV310_PA_UART + ((x) * S3C_UART_OFFSET)) -#define S5P_PA_UART0 S5P_PA_UART(0) -#define S5P_PA_UART1 S5P_PA_UART(1) -#define S5P_PA_UART2 S5P_PA_UART(2) -#define S5P_PA_UART3 S5P_PA_UART(3) -#define S5P_PA_UART4 S5P_PA_UART(4) - -#define S5P_SZ_UART SZ_256 - -#define S5PV310_PA_IIC(x) (0x13860000 + ((x) * 0x10000)) - -#define S5PV310_PA_TIMER (0x139D0000) -#define S5P_PA_TIMER S5PV310_PA_TIMER - -#define S5PV310_PA_SDRAM (0x40000000) -#define S5P_PA_SDRAM S5PV310_PA_SDRAM +#define S5PV310_PA_MDMA 0x10810000 +#define S5PV310_PA_PDMA0 0x12680000 +#define S5PV310_PA_PDMA1 0x12690000 #define S5PV310_PA_SYSMMU_MDMA 0x10A40000 #define S5PV310_PA_SYSMMU_SSS 0x10A50000 @@ -124,11 +77,32 @@ #define S5PV310_PA_SYSMMU_TV 0x12E20000 #define S5PV310_PA_SYSMMU_MFC_L 0x13620000 #define S5PV310_PA_SYSMMU_MFC_R 0x13630000 -#define S5PV310_SYSMMU_TOTAL_IPNUM 16 -#define S5P_SYSMMU_TOTAL_IPNUM S5PV310_SYSMMU_TOTAL_IPNUM -/* compatibiltiy defines. */ -#define S3C_PA_UART S5PV310_PA_UART +#define S5PV310_PA_GPIO1 0x11400000 +#define S5PV310_PA_GPIO2 0x11000000 +#define S5PV310_PA_GPIO3 0x03860000 + +#define S5PV310_PA_MIPI_CSIS0 0x11880000 +#define S5PV310_PA_MIPI_CSIS1 0x11890000 + +#define S5PV310_PA_HSMMC(x) (0x12510000 + ((x) * 0x10000)) + +#define S5PV310_PA_SROMC 0x12570000 + +#define S5PV310_PA_UART 0x13800000 + +#define S5PV310_PA_IIC(x) (0x13860000 + ((x) * 0x10000)) + +#define S5PV310_PA_AC97 0x139A0000 + +#define S5PV310_PA_TIMER 0x139D0000 + +#define S5PV310_PA_SDRAM 0x40000000 + +#define S5PV310_PA_SPDIF 0xE1100000 + +/* Compatibiltiy Defines */ + #define S3C_PA_HSMMC0 S5PV310_PA_HSMMC(0) #define S3C_PA_HSMMC1 S5PV310_PA_HSMMC(1) #define S3C_PA_HSMMC2 S5PV310_PA_HSMMC(2) @@ -143,7 +117,28 @@ #define S3C_PA_IIC7 S5PV310_PA_IIC(7) #define S3C_PA_RTC S5PV310_PA_RTC #define S3C_PA_WDT S5PV310_PA_WATCHDOG + +#define S5P_PA_CHIPID S5PV310_PA_CHIPID #define S5P_PA_MIPI_CSIS0 S5PV310_PA_MIPI_CSIS0 #define S5P_PA_MIPI_CSIS1 S5PV310_PA_MIPI_CSIS1 +#define S5P_PA_ONENAND S5PC210_PA_ONENAND +#define S5P_PA_ONENAND_DMA S5PC210_PA_ONENAND_DMA +#define S5P_PA_SDRAM S5PV310_PA_SDRAM +#define S5P_PA_SROMC S5PV310_PA_SROMC +#define S5P_PA_SYSCON S5PV310_PA_SYSCON +#define S5P_PA_TIMER S5PV310_PA_TIMER + +/* UART */ + +#define S3C_PA_UART S5PV310_PA_UART + +#define S5P_PA_UART(x) (S3C_PA_UART + ((x) * S3C_UART_OFFSET)) +#define S5P_PA_UART0 S5P_PA_UART(0) +#define S5P_PA_UART1 S5P_PA_UART(1) +#define S5P_PA_UART2 S5P_PA_UART(2) +#define S5P_PA_UART3 S5P_PA_UART(3) +#define S5P_PA_UART4 S5P_PA_UART(4) + +#define S5P_SZ_UART SZ_256 #endif /* __ASM_ARCH_MAP_H */ diff --git a/arch/arm/mach-s5pv310/include/mach/sysmmu.h b/arch/arm/mach-s5pv310/include/mach/sysmmu.h index 662fe85f..598fc5c 100644 --- a/arch/arm/mach-s5pv310/include/mach/sysmmu.h +++ b/arch/arm/mach-s5pv310/include/mach/sysmmu.h @@ -13,6 +13,9 @@ #ifndef __ASM_ARM_ARCH_SYSMMU_H #define __ASM_ARM_ARCH_SYSMMU_H __FILE__ +#define S5PV310_SYSMMU_TOTAL_IPNUM 16 +#define S5P_SYSMMU_TOTAL_IPNUM S5PV310_SYSMMU_TOTAL_IPNUM + enum s5pv310_sysmmu_ips { SYSMMU_MDMA, SYSMMU_SSS, @@ -32,7 +35,7 @@ enum s5pv310_sysmmu_ips { SYSMMU_MFC_R, }; -static char *sysmmu_ips_name[S5P_SYSMMU_TOTAL_IPNUM] = { +static char *sysmmu_ips_name[S5PV310_SYSMMU_TOTAL_IPNUM] = { "SYSMMU_MDMA" , "SYSMMU_SSS" , "SYSMMU_FIMC0" , diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c index d43c5ef..bd3e1bf 100644 --- a/arch/arm/mach-sa1100/collie.c +++ b/arch/arm/mach-sa1100/collie.c @@ -241,6 +241,9 @@ static struct locomo_platform_data locomo_info = { struct platform_device collie_locomo_device = { .name = "locomo", .id = 0, + .dev = { + .platform_data = &locomo_info, + }, .num_resources = ARRAY_SIZE(locomo_resources), .resource = locomo_resources, }; diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c index 2123b96..4303a86 100644 --- a/arch/arm/mach-shmobile/board-ag5evm.c +++ b/arch/arm/mach-shmobile/board-ag5evm.c @@ -454,6 +454,7 @@ static void __init ag5evm_init(void) gpio_direction_output(GPIO_PORT217, 0); mdelay(1); gpio_set_value(GPIO_PORT217, 1); + mdelay(100); /* LCD backlight controller */ gpio_request(GPIO_PORT235, NULL); /* RESET */ diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index 3cf0951..81d6536 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -1303,7 +1303,7 @@ static void __init ap4evb_init(void) lcdc_info.clock_source = LCDC_CLK_BUS; lcdc_info.ch[0].interface_type = RGB18; - lcdc_info.ch[0].clock_divider = 2; + lcdc_info.ch[0].clock_divider = 3; lcdc_info.ch[0].flags = 0; lcdc_info.ch[0].lcd_size_cfg.width = 152; lcdc_info.ch[0].lcd_size_cfg.height = 91; diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index fb4213a..1657eac 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -303,7 +303,7 @@ static struct sh_mobile_lcdc_info lcdc_info = { .lcd_cfg = mackerel_lcdc_modes, .num_cfg = ARRAY_SIZE(mackerel_lcdc_modes), .interface_type = RGB24, - .clock_divider = 2, + .clock_divider = 3, .flags = 0, .lcd_size_cfg.width = 152, .lcd_size_cfg.height = 91, diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c index ddd4a1b..7e58904 100644 --- a/arch/arm/mach-shmobile/clock-sh73a0.c +++ b/arch/arm/mach-shmobile/clock-sh73a0.c @@ -263,7 +263,7 @@ static struct clk div6_clks[DIV6_NR] = { }; enum { MSTP001, - MSTP125, MSTP118, MSTP116, MSTP100, + MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP100, MSTP219, MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200, MSTP331, MSTP329, MSTP325, MSTP323, MSTP312, @@ -275,6 +275,10 @@ enum { MSTP001, static struct clk mstp_clks[MSTP_NR] = { [MSTP001] = MSTP(&div4_clks[DIV4_HP], SMSTPCR0, 1, 0), /* IIC2 */ + [MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* CEU1 */ + [MSTP128] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 28, 0), /* CSI2-RX1 */ + [MSTP127] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 27, 0), /* CEU0 */ + [MSTP126] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 26, 0), /* CSI2-RX0 */ [MSTP125] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 25, 0), /* TMU0 */ [MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX0 */ [MSTP116] = MSTP(&div4_clks[DIV4_HP], SMSTPCR1, 16, 0), /* IIC0 */ @@ -306,6 +310,9 @@ static struct clk_lookup lookups[] = { CLKDEV_CON_ID("r_clk", &r_clk), /* DIV6 clocks */ + CLKDEV_CON_ID("vck1_clk", &div6_clks[DIV6_VCK1]), + CLKDEV_CON_ID("vck2_clk", &div6_clks[DIV6_VCK2]), + CLKDEV_CON_ID("vck3_clk", &div6_clks[DIV6_VCK3]), CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSIT]), CLKDEV_ICK_ID("dsit_clk", "sh-mipi-dsi.1", &div6_clks[DIV6_DSIT]), CLKDEV_ICK_ID("dsi0p_clk", "sh-mipi-dsi.0", &div6_clks[DIV6_DSI0P]), @@ -313,11 +320,15 @@ static struct clk_lookup lookups[] = { /* MSTP32 clocks */ CLKDEV_DEV_ID("i2c-sh_mobile.2", &mstp_clks[MSTP001]), /* I2C2 */ - CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */ + CLKDEV_DEV_ID("sh_mobile_ceu.1", &mstp_clks[MSTP129]), /* CEU1 */ + CLKDEV_DEV_ID("sh-mobile-csi2.1", &mstp_clks[MSTP128]), /* CSI2-RX1 */ + CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[MSTP127]), /* CEU0 */ + CLKDEV_DEV_ID("sh-mobile-csi2.0", &mstp_clks[MSTP126]), /* CSI2-RX0 */ CLKDEV_DEV_ID("sh_tmu.0", &mstp_clks[MSTP125]), /* TMU00 */ CLKDEV_DEV_ID("sh_tmu.1", &mstp_clks[MSTP125]), /* TMU01 */ - CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* I2C0 */ CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX */ + CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* I2C0 */ + CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */ CLKDEV_DEV_ID("sh-sci.7", &mstp_clks[MSTP219]), /* SCIFA7 */ CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */ CLKDEV_DEV_ID("sh-sci.8", &mstp_clks[MSTP206]), /* SCIFB */ diff --git a/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt b/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt index efd3687..3029aba 100644 --- a/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt +++ b/arch/arm/mach-shmobile/include/mach/head-ap4evb.txt @@ -6,13 +6,10 @@ LIST "RWT Setting" EW 0xE6020004, 0xA500 EW 0xE6030004, 0xA500 -DD 0x01001000, 0x01001000 - LIST "GPIO Setting" EB 0xE6051013, 0xA2 LIST "CPG" -ED 0xE6150080, 0x00000180 ED 0xE61500C0, 0x00000002 WAIT 1, 0xFE40009C @@ -37,6 +34,9 @@ ED 0xE615002C, 0x93000040 WAIT 1, 0xFE40009C +LIST "SUB/USBClk" +ED 0xE6150080, 0x00000180 + LIST "BSC" ED 0xFEC10000, 0x00E0001B @@ -53,7 +53,7 @@ ED 0xFE400048, 0x20C18505 ED 0xFE40004C, 0x00110209 ED 0xFE400010, 0x00000087 -WAIT 10, 0xFE40009C +WAIT 30, 0xFE40009C ED 0xFE400084, 0x0000003F EB 0xFE500000, 0x00 @@ -84,7 +84,7 @@ ED 0xE6150004, 0x80331050 WAIT 1, 0xFE40009C -ED 0xE6150354, 0x00000002 +ED 0xFE400354, 0x01AD8002 LIST "SCIF0 - Serial port for earlyprintk" EB 0xE6053098, 0x11 diff --git a/arch/arm/mach-shmobile/include/mach/head-mackerel.txt b/arch/arm/mach-shmobile/include/mach/head-mackerel.txt index efd3687..3029aba 100644 --- a/arch/arm/mach-shmobile/include/mach/head-mackerel.txt +++ b/arch/arm/mach-shmobile/include/mach/head-mackerel.txt @@ -6,13 +6,10 @@ LIST "RWT Setting" EW 0xE6020004, 0xA500 EW 0xE6030004, 0xA500 -DD 0x01001000, 0x01001000 - LIST "GPIO Setting" EB 0xE6051013, 0xA2 LIST "CPG" -ED 0xE6150080, 0x00000180 ED 0xE61500C0, 0x00000002 WAIT 1, 0xFE40009C @@ -37,6 +34,9 @@ ED 0xE615002C, 0x93000040 WAIT 1, 0xFE40009C +LIST "SUB/USBClk" +ED 0xE6150080, 0x00000180 + LIST "BSC" ED 0xFEC10000, 0x00E0001B @@ -53,7 +53,7 @@ ED 0xFE400048, 0x20C18505 ED 0xFE40004C, 0x00110209 ED 0xFE400010, 0x00000087 -WAIT 10, 0xFE40009C +WAIT 30, 0xFE40009C ED 0xFE400084, 0x0000003F EB 0xFE500000, 0x00 @@ -84,7 +84,7 @@ ED 0xE6150004, 0x80331050 WAIT 1, 0xFE40009C -ED 0xE6150354, 0x00000002 +ED 0xFE400354, 0x01AD8002 LIST "SCIF0 - Serial port for earlyprintk" EB 0xE6053098, 0x11 diff --git a/arch/arm/mach-spear3xx/include/mach/spear320.h b/arch/arm/mach-spear3xx/include/mach/spear320.h index cacf17a..53677e4 100644 --- a/arch/arm/mach-spear3xx/include/mach/spear320.h +++ b/arch/arm/mach-spear3xx/include/mach/spear320.h @@ -62,7 +62,7 @@ #define SPEAR320_SMII1_BASE 0xAB000000 #define SPEAR320_SMII1_SIZE 0x01000000 -#define SPEAR320_SOC_CONFIG_BASE 0xB4000000 +#define SPEAR320_SOC_CONFIG_BASE 0xB3000000 #define SPEAR320_SOC_CONFIG_SIZE 0x00000070 /* Interrupt registers offsets and masks */ #define INT_STS_MASK_REG 0x04 diff --git a/arch/arm/mach-tegra/include/mach/kbc.h b/arch/arm/mach-tegra/include/mach/kbc.h index 66ad276..04c7798 100644 --- a/arch/arm/mach-tegra/include/mach/kbc.h +++ b/arch/arm/mach-tegra/include/mach/kbc.h @@ -57,5 +57,6 @@ struct tegra_kbc_platform_data { const struct matrix_keymap_data *keymap_data; bool wakeup; + bool use_fn_map; }; #endif diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 9d30c6f..e4509ba 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -405,7 +405,7 @@ config CPU_V6 config CPU_32v6K bool "Support ARM V6K processor extensions" if !SMP depends on CPU_V6 || CPU_V7 - default y if SMP && !(ARCH_MX3 || ARCH_OMAP2) + default y if SMP help Say Y here if your ARMv6 processor supports the 'K' extension. This enables the kernel to use some instructions not present @@ -416,7 +416,7 @@ config CPU_32v6K # ARMv7 config CPU_V7 bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX - select CPU_32v6K if !ARCH_OMAP2 + select CPU_32v6K select CPU_32v7 select CPU_ABRT_EV7 select CPU_PABRT_V7 @@ -644,7 +644,7 @@ config ARM_THUMBEE config SWP_EMULATE bool "Emulate SWP/SWPB instructions" - depends on CPU_V7 && !CPU_V6 + depends on !CPU_USE_DOMAINS && CPU_V7 && !CPU_V6 select HAVE_PROC_CPU if PROC_FS default y if SMP help diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 170c9bb..f2ce38e 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -49,7 +49,13 @@ static inline void cache_wait(void __iomem *reg, unsigned long mask) static inline void cache_sync(void) { void __iomem *base = l2x0_base; + +#ifdef CONFIG_ARM_ERRATA_753970 + /* write to an unmmapped register */ + writel_relaxed(0, base + L2X0_DUMMY_REG); +#else writel_relaxed(0, base + L2X0_CACHE_SYNC); +#endif cache_wait(base + L2X0_CACHE_SYNC, 1); } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 5164069..cddd684 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -297,6 +297,12 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) memblock_reserve(__pa(_stext), _end - _stext); #endif #ifdef CONFIG_BLK_DEV_INITRD + if (phys_initrd_size && + memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) { + pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n", + phys_initrd_start, phys_initrd_size); + phys_initrd_start = phys_initrd_size = 0; + } if (phys_initrd_size) { memblock_reserve(phys_initrd_start, phys_initrd_size); diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 0c1172b..8e33562 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -264,6 +264,12 @@ __v7_setup: orreq r10, r10, #1 << 6 @ set bit #6 mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register #endif +#ifdef CONFIG_ARM_ERRATA_751472 + cmp r6, #0x30 @ present prior to r3p0 + mrclt p15, 0, r10, c15, c0, 1 @ read diagnostic register + orrlt r10, r10, #1 << 11 @ set bit #11 + mcrlt p15, 0, r10, c15, c0, 1 @ write diagnostic register +#endif 3: mov r10, #0 #ifdef HARVARD_CACHE diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 8aa9744..c074e66 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -10,8 +10,6 @@ */ #include <linux/cpumask.h> -#include <linux/err.h> -#include <linux/errno.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/oprofile.h> @@ -46,6 +44,7 @@ char *op_name_from_perf_id(void) return NULL; } } +#endif static int report_trace(struct stackframe *frame, void *d) { @@ -85,7 +84,7 @@ static struct frame_tail* user_backtrace(struct frame_tail *tail) /* frame pointers should strictly progress back up the stack * (towards higher addresses) */ - if (tail >= buftail[0].fp) + if (tail + 1 >= buftail[0].fp) return NULL; return buftail[0].fp-1; @@ -111,6 +110,7 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth) int __init oprofile_arch_init(struct oprofile_operations *ops) { + /* provide backtrace support also in timer mode: */ ops->backtrace = arm_backtrace; return oprofile_perf_init(ops); @@ -120,11 +120,3 @@ void __exit oprofile_arch_exit(void) { oprofile_perf_exit(); } -#else -int __init oprofile_arch_init(struct oprofile_operations *ops) -{ - pr_info("oprofile: hardware counters not available\n"); - return -ENODEV; -} -void __exit oprofile_arch_exit(void) {} -#endif /* CONFIG_HW_PERF_EVENTS */ diff --git a/arch/arm/plat-mxc/include/mach/uncompress.h b/arch/arm/plat-mxc/include/mach/uncompress.h index 3a70ebf..ff469c4 100644 --- a/arch/arm/plat-mxc/include/mach/uncompress.h +++ b/arch/arm/plat-mxc/include/mach/uncompress.h @@ -95,6 +95,7 @@ static __inline__ void __arch_decomp_setup(unsigned long arch_id) case MACH_TYPE_MX35_3DS: case MACH_TYPE_PCM043: case MACH_TYPE_LILLY1131: + case MACH_TYPE_VPR200: uart_base = MX3X_UART1_BASE_ADDR; break; case MACH_TYPE_MAGX_ZN5: @@ -102,6 +103,7 @@ static __inline__ void __arch_decomp_setup(unsigned long arch_id) break; case MACH_TYPE_MX51_BABBAGE: case MACH_TYPE_EUKREA_CPUIMX51SD: + case MACH_TYPE_MX51_3DS: uart_base = MX51_UART1_BASE_ADDR; break; case MACH_TYPE_MX50_RDP: diff --git a/arch/arm/plat-omap/mailbox.c b/arch/arm/plat-omap/mailbox.c index 459b319..49d3208 100644 --- a/arch/arm/plat-omap/mailbox.c +++ b/arch/arm/plat-omap/mailbox.c @@ -322,15 +322,18 @@ static void omap_mbox_fini(struct omap_mbox *mbox) struct omap_mbox *omap_mbox_get(const char *name, struct notifier_block *nb) { - struct omap_mbox *mbox; - int ret; + struct omap_mbox *_mbox, *mbox = NULL; + int i, ret; if (!mboxes) return ERR_PTR(-EINVAL); - for (mbox = *mboxes; mbox; mbox++) - if (!strcmp(mbox->name, name)) + for (i = 0; (_mbox = mboxes[i]); i++) { + if (!strcmp(_mbox->name, name)) { + mbox = _mbox; break; + } + } if (!mbox) return ERR_PTR(-ENOENT); diff --git a/arch/arm/plat-pxa/mfp.c b/arch/arm/plat-pxa/mfp.c index b77e018..a9aa5ad 100644 --- a/arch/arm/plat-pxa/mfp.c +++ b/arch/arm/plat-pxa/mfp.c @@ -139,10 +139,11 @@ static const unsigned long mfpr_edge[] = { #define mfp_configured(p) ((p)->config != -1) /* - * perform a read-back of any MFPR register to make sure the + * perform a read-back of any valid MFPR register to make sure the * previous writings are finished */ -#define mfpr_sync() (void)__raw_readl(mfpr_mmio_base + 0) +static unsigned long mfpr_off_readback; +#define mfpr_sync() (void)__raw_readl(mfpr_mmio_base + mfpr_off_readback) static inline void __mfp_config_run(struct mfp_pin *p) { @@ -248,6 +249,9 @@ void __init mfp_init_addr(struct mfp_addr_map *map) spin_lock_irqsave(&mfp_spin_lock, flags); + /* mfp offset for readback */ + mfpr_off_readback = map[0].offset; + for (p = map; p->start != MFP_PIN_INVALID; p++) { offset = p->offset; i = p->start; diff --git a/arch/arm/plat-s5p/Kconfig b/arch/arm/plat-s5p/Kconfig index deb3995..557f8c5 100644 --- a/arch/arm/plat-s5p/Kconfig +++ b/arch/arm/plat-s5p/Kconfig @@ -37,6 +37,14 @@ config S5P_GPIO_INT help Common code for the GPIO interrupts (other than external interrupts.) +comment "System MMU" + +config S5P_SYSTEM_MMU + bool "S5P SYSTEM MMU" + depends on ARCH_S5PV310 + help + Say Y here if you want to enable System MMU + config S5P_DEV_FIMC0 bool help @@ -66,19 +74,3 @@ config S5P_DEV_CSIS1 bool help Compile in platform device definitions for MIPI-CSIS channel 1 - -menuconfig S5P_SYSMMU - bool "SYSMMU support" - depends on ARCH_S5PV310 - help - This is a System MMU driver for Samsung ARM based Soc. - -if S5P_SYSMMU - -config S5P_SYSMMU_DEBUG - bool "Enables debug messages" - depends on S5P_SYSMMU - help - This enables SYSMMU driver debug massages. - -endif diff --git a/arch/arm/plat-s5p/Makefile b/arch/arm/plat-s5p/Makefile index 92efe1a..4bd5cf9 100644 --- a/arch/arm/plat-s5p/Makefile +++ b/arch/arm/plat-s5p/Makefile @@ -19,6 +19,7 @@ obj-y += clock.o obj-y += irq.o obj-$(CONFIG_S5P_EXT_INT) += irq-eint.o obj-$(CONFIG_S5P_GPIO_INT) += irq-gpioint.o +obj-$(CONFIG_S5P_SYSTEM_MMU) += sysmmu.o obj-$(CONFIG_PM) += pm.o obj-$(CONFIG_PM) += irq-pm.o @@ -30,4 +31,3 @@ obj-$(CONFIG_S5P_DEV_FIMC2) += dev-fimc2.o obj-$(CONFIG_S5P_DEV_ONENAND) += dev-onenand.o obj-$(CONFIG_S5P_DEV_CSIS0) += dev-csis0.o obj-$(CONFIG_S5P_DEV_CSIS1) += dev-csis1.o -obj-$(CONFIG_S5P_SYSMMU) += sysmmu.o diff --git a/arch/arm/plat-s5p/dev-uart.c b/arch/arm/plat-s5p/dev-uart.c index 6a73428..afaf87f 100644 --- a/arch/arm/plat-s5p/dev-uart.c +++ b/arch/arm/plat-s5p/dev-uart.c @@ -28,7 +28,7 @@ static struct resource s5p_uart0_resource[] = { [0] = { .start = S5P_PA_UART0, - .end = S5P_PA_UART0 + S5P_SZ_UART, + .end = S5P_PA_UART0 + S5P_SZ_UART - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -51,7 +51,7 @@ static struct resource s5p_uart0_resource[] = { static struct resource s5p_uart1_resource[] = { [0] = { .start = S5P_PA_UART1, - .end = S5P_PA_UART1 + S5P_SZ_UART, + .end = S5P_PA_UART1 + S5P_SZ_UART - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -74,7 +74,7 @@ static struct resource s5p_uart1_resource[] = { static struct resource s5p_uart2_resource[] = { [0] = { .start = S5P_PA_UART2, - .end = S5P_PA_UART2 + S5P_SZ_UART, + .end = S5P_PA_UART2 + S5P_SZ_UART - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -98,7 +98,7 @@ static struct resource s5p_uart3_resource[] = { #if CONFIG_SERIAL_SAMSUNG_UARTS > 3 [0] = { .start = S5P_PA_UART3, - .end = S5P_PA_UART3 + S5P_SZ_UART, + .end = S5P_PA_UART3 + S5P_SZ_UART - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -123,7 +123,7 @@ static struct resource s5p_uart4_resource[] = { #if CONFIG_SERIAL_SAMSUNG_UARTS > 4 [0] = { .start = S5P_PA_UART4, - .end = S5P_PA_UART4 + S5P_SZ_UART, + .end = S5P_PA_UART4 + S5P_SZ_UART - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -148,7 +148,7 @@ static struct resource s5p_uart5_resource[] = { #if CONFIG_SERIAL_SAMSUNG_UARTS > 5 [0] = { .start = S5P_PA_UART5, - .end = S5P_PA_UART5 + S5P_SZ_UART, + .end = S5P_PA_UART5 + S5P_SZ_UART - 1, .flags = IORESOURCE_MEM, }, [1] = { diff --git a/arch/arm/plat-s5p/include/plat/sysmmu.h b/arch/arm/plat-s5p/include/plat/sysmmu.h deleted file mode 100644 index db298fc..0000000 --- a/arch/arm/plat-s5p/include/plat/sysmmu.h +++ /dev/null @@ -1,23 +0,0 @@ -/* linux/arch/arm/plat-s5p/include/plat/sysmmu.h - * - * Copyright (c) 2010 Samsung Electronics Co., Ltd. - * http://www.samsung.com/ - * - * Samsung sysmmu driver - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. -*/ - -#ifndef __ASM_PLAT_S5P_SYSMMU_H -#define __ASM_PLAT_S5P_SYSMMU_H __FILE__ - -/* debug macro */ -#ifdef CONFIG_S5P_SYSMMU_DEBUG -#define sysmmu_debug(fmt, arg...) printk(KERN_INFO "[%s] " fmt, __func__, ## arg) -#else -#define sysmmu_debug(fmt, arg...) do { } while (0) -#endif - -#endif /* __ASM_PLAT_S5P_SYSMMU_H */ diff --git a/arch/arm/plat-s5p/sysmmu.c b/arch/arm/plat-s5p/sysmmu.c index d804914..ffe8a48 100644 --- a/arch/arm/plat-s5p/sysmmu.c +++ b/arch/arm/plat-s5p/sysmmu.c @@ -16,8 +16,6 @@ #include <mach/regs-sysmmu.h> #include <mach/sysmmu.h> -#include <plat/sysmmu.h> - struct sysmmu_controller s5p_sysmmu_cntlrs[S5P_SYSMMU_TOTAL_IPNUM]; void s5p_sysmmu_register(struct sysmmu_controller *sysmmuconp) @@ -123,7 +121,7 @@ static int s5p_sysmmu_set_tablebase(sysmmu_ips ips) : "=r" (pg) : : "cc"); \ pg &= ~0x3fff; - sysmmu_debug("CP15 TTBR0 : 0x%x\n", pg); + printk(KERN_INFO "%s: CP15 TTBR0 : 0x%x\n", __func__, pg); /* Set sysmmu page table base address */ __raw_writel(pg, sysmmuconp->regs + S5P_PT_BASE_ADDR); diff --git a/arch/arm/plat-samsung/dev-ts.c b/arch/arm/plat-samsung/dev-ts.c index 236ef84..3e4bd81 100644 --- a/arch/arm/plat-samsung/dev-ts.c +++ b/arch/arm/plat-samsung/dev-ts.c @@ -58,4 +58,3 @@ void __init s3c24xx_ts_set_platdata(struct s3c2410_ts_mach_info *pd) s3c_device_ts.dev.platform_data = npd; } -EXPORT_SYMBOL(s3c24xx_ts_set_platdata); diff --git a/arch/arm/plat-samsung/dev-uart.c b/arch/arm/plat-samsung/dev-uart.c index 3776cd9..5928105 100644 --- a/arch/arm/plat-samsung/dev-uart.c +++ b/arch/arm/plat-samsung/dev-uart.c @@ -15,6 +15,8 @@ #include <linux/kernel.h> #include <linux/platform_device.h> +#include <plat/devs.h> + /* uart devices */ static struct platform_device s3c24xx_uart_device0 = { diff --git a/arch/arm/plat-samsung/include/plat/pm.h b/arch/arm/plat-samsung/include/plat/pm.h index d9025e3..30518cc 100644 --- a/arch/arm/plat-samsung/include/plat/pm.h +++ b/arch/arm/plat-samsung/include/plat/pm.h @@ -17,6 +17,8 @@ #include <linux/irq.h> +struct sys_device; + #ifdef CONFIG_PM extern __init int s3c_pm_init(void); diff --git a/arch/arm/plat-spear/include/plat/uncompress.h b/arch/arm/plat-spear/include/plat/uncompress.h index 99ba678..6dd455b 100644 --- a/arch/arm/plat-spear/include/plat/uncompress.h +++ b/arch/arm/plat-spear/include/plat/uncompress.h @@ -24,10 +24,10 @@ static inline void putc(int c) { void __iomem *base = (void __iomem *)SPEAR_DBG_UART_BASE; - while (readl(base + UART01x_FR) & UART01x_FR_TXFF) + while (readl_relaxed(base + UART01x_FR) & UART01x_FR_TXFF) barrier(); - writel(c, base + UART01x_DR); + writel_relaxed(c, base + UART01x_DR); } static inline void flush(void) diff --git a/arch/arm/plat-spear/include/plat/vmalloc.h b/arch/arm/plat-spear/include/plat/vmalloc.h index 09e9372..8c8b24d 100644 --- a/arch/arm/plat-spear/include/plat/vmalloc.h +++ b/arch/arm/plat-spear/include/plat/vmalloc.h @@ -14,6 +14,6 @@ #ifndef __PLAT_VMALLOC_H #define __PLAT_VMALLOC_H -#define VMALLOC_END 0xF0000000 +#define VMALLOC_END 0xF0000000UL #endif /* __PLAT_VMALLOC_H */ diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 2fea897..9d6feaa 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Sun Dec 12 23:24:27 2010 +# Last update: Mon Feb 7 08:59:27 2011 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -2240,7 +2240,7 @@ arm_ultimator2 MACH_ARM_ULTIMATOR2 ARM_ULTIMATOR2 2250 vs_v210 MACH_VS_V210 VS_V210 2252 vs_v212 MACH_VS_V212 VS_V212 2253 hmt MACH_HMT HMT 2254 -suen3 MACH_SUEN3 SUEN3 2255 +km_kirkwood MACH_KM_KIRKWOOD KM_KIRKWOOD 2255 vesper MACH_VESPER VESPER 2256 str9 MACH_STR9 STR9 2257 omap3_wl_ff MACH_OMAP3_WL_FF OMAP3_WL_FF 2258 @@ -2987,7 +2987,7 @@ pxwnas_500_1000 MACH_PXWNAS_500_1000 PXWNAS_500_1000 3001 ea20 MACH_EA20 EA20 3002 awm2 MACH_AWM2 AWM2 3003 ti8148evm MACH_TI8148EVM TI8148EVM 3004 -tegra_seaboard MACH_TEGRA_SEABOARD TEGRA_SEABOARD 3005 +seaboard MACH_SEABOARD SEABOARD 3005 linkstation_chlv2 MACH_LINKSTATION_CHLV2 LINKSTATION_CHLV2 3006 tera_pro2_rack MACH_TERA_PRO2_RACK TERA_PRO2_RACK 3007 rubys MACH_RUBYS RUBYS 3008 @@ -3190,7 +3190,7 @@ synergy MACH_SYNERGY SYNERGY 3205 ics_if_voip MACH_ICS_IF_VOIP ICS_IF_VOIP 3206 wlf_cragg_6410 MACH_WLF_CRAGG_6410 WLF_CRAGG_6410 3207 punica MACH_PUNICA PUNICA 3208 -sbc_nt250 MACH_SBC_NT250 SBC_NT250 3209 +trimslice MACH_TRIMSLICE TRIMSLICE 3209 mx27_wmultra MACH_MX27_WMULTRA MX27_WMULTRA 3210 mackerel MACH_MACKEREL MACKEREL 3211 fa9x27 MACH_FA9X27 FA9X27 3213 @@ -3219,3 +3219,100 @@ pivicc MACH_PIVICC PIVICC 3235 pcm048 MACH_PCM048 PCM048 3236 dds MACH_DDS DDS 3237 chalten_xa1 MACH_CHALTEN_XA1 CHALTEN_XA1 3238 +ts48xx MACH_TS48XX TS48XX 3239 +tonga2_tfttimer MACH_TONGA2_TFTTIMER TONGA2_TFTTIMER 3240 +whistler MACH_WHISTLER WHISTLER 3241 +asl_phoenix MACH_ASL_PHOENIX ASL_PHOENIX 3242 +at91sam9263otlite MACH_AT91SAM9263OTLITE AT91SAM9263OTLITE 3243 +ddplug MACH_DDPLUG DDPLUG 3244 +d2plug MACH_D2PLUG D2PLUG 3245 +kzm9d MACH_KZM9D KZM9D 3246 +verdi_lte MACH_VERDI_LTE VERDI_LTE 3247 +nanozoom MACH_NANOZOOM NANOZOOM 3248 +dm3730_som_lv MACH_DM3730_SOM_LV DM3730_SOM_LV 3249 +dm3730_torpedo MACH_DM3730_TORPEDO DM3730_TORPEDO 3250 +anchovy MACH_ANCHOVY ANCHOVY 3251 +re2rev20 MACH_RE2REV20 RE2REV20 3253 +re2rev21 MACH_RE2REV21 RE2REV21 3254 +cns21xx MACH_CNS21XX CNS21XX 3255 +rider MACH_RIDER RIDER 3257 +nsk330 MACH_NSK330 NSK330 3258 +cns2133evb MACH_CNS2133EVB CNS2133EVB 3259 +z3_816x_mod MACH_Z3_816X_MOD Z3_816X_MOD 3260 +z3_814x_mod MACH_Z3_814X_MOD Z3_814X_MOD 3261 +beect MACH_BEECT BEECT 3262 +dma_thunderbug MACH_DMA_THUNDERBUG DMA_THUNDERBUG 3263 +omn_at91sam9g20 MACH_OMN_AT91SAM9G20 OMN_AT91SAM9G20 3264 +mx25_e2s_uc MACH_MX25_E2S_UC MX25_E2S_UC 3265 +mione MACH_MIONE MIONE 3266 +top9000_tcu MACH_TOP9000_TCU TOP9000_TCU 3267 +top9000_bsl MACH_TOP9000_BSL TOP9000_BSL 3268 +kingdom MACH_KINGDOM KINGDOM 3269 +armadillo460 MACH_ARMADILLO460 ARMADILLO460 3270 +lq2 MACH_LQ2 LQ2 3271 +sweda_tms2 MACH_SWEDA_TMS2 SWEDA_TMS2 3272 +mx53_loco MACH_MX53_LOCO MX53_LOCO 3273 +acer_a8 MACH_ACER_A8 ACER_A8 3275 +acer_gauguin MACH_ACER_GAUGUIN ACER_GAUGUIN 3276 +guppy MACH_GUPPY GUPPY 3277 +mx61_ard MACH_MX61_ARD MX61_ARD 3278 +tx53 MACH_TX53 TX53 3279 +omapl138_case_a3 MACH_OMAPL138_CASE_A3 OMAPL138_CASE_A3 3280 +uemd MACH_UEMD UEMD 3281 +ccwmx51mut MACH_CCWMX51MUT CCWMX51MUT 3282 +rockhopper MACH_ROCKHOPPER ROCKHOPPER 3283 +nookcolor MACH_NOOKCOLOR NOOKCOLOR 3284 +hkdkc100 MACH_HKDKC100 HKDKC100 3285 +ts42xx MACH_TS42XX TS42XX 3286 +aebl MACH_AEBL AEBL 3287 +wario MACH_WARIO WARIO 3288 +gfs_spm MACH_GFS_SPM GFS_SPM 3289 +cm_t3730 MACH_CM_T3730 CM_T3730 3290 +isc3 MACH_ISC3 ISC3 3291 +rascal MACH_RASCAL RASCAL 3292 +hrefv60 MACH_HREFV60 HREFV60 3293 +tpt_2_0 MACH_TPT_2_0 TPT_2_0 3294 +pyramid_td MACH_PYRAMID_TD PYRAMID_TD 3295 +splendor MACH_SPLENDOR SPLENDOR 3296 +guf_planet MACH_GUF_PLANET GUF_PLANET 3297 +msm8x60_qt MACH_MSM8X60_QT MSM8X60_QT 3298 +htc_hd_mini MACH_HTC_HD_MINI HTC_HD_MINI 3299 +athene MACH_ATHENE ATHENE 3300 +deep_r_ek_1 MACH_DEEP_R_EK_1 DEEP_R_EK_1 3301 +vivow_ct MACH_VIVOW_CT VIVOW_CT 3302 +nery_1000 MACH_NERY_1000 NERY_1000 3303 +rfl109145_ssrv MACH_RFL109145_SSRV RFL109145_SSRV 3304 +nmh MACH_NMH NMH 3305 +wn802t MACH_WN802T WN802T 3306 +dragonet MACH_DRAGONET DRAGONET 3307 +geneva_b MACH_GENEVA_B GENEVA_B 3308 +at91sam9263desk16l MACH_AT91SAM9263DESK16L AT91SAM9263DESK16L 3309 +bcmhana_sv MACH_BCMHANA_SV BCMHANA_SV 3310 +bcmhana_tablet MACH_BCMHANA_TABLET BCMHANA_TABLET 3311 +koi MACH_KOI KOI 3312 +ts4800 MACH_TS4800 TS4800 3313 +tqma9263 MACH_TQMA9263 TQMA9263 3314 +holiday MACH_HOLIDAY HOLIDAY 3315 +dma_6410 MACH_DMA6410 DMA6410 3316 +pcats_overlay MACH_PCATS_OVERLAY PCATS_OVERLAY 3317 +hwgw6410 MACH_HWGW6410 HWGW6410 3318 +shenzhou MACH_SHENZHOU SHENZHOU 3319 +cwme9210 MACH_CWME9210 CWME9210 3320 +cwme9210js MACH_CWME9210JS CWME9210JS 3321 +pgs_v1 MACH_PGS_SITARA PGS_SITARA 3322 +colibri_tegra2 MACH_COLIBRI_TEGRA2 COLIBRI_TEGRA2 3323 +w21 MACH_W21 W21 3324 +polysat1 MACH_POLYSAT1 POLYSAT1 3325 +dataway MACH_DATAWAY DATAWAY 3326 +cobral138 MACH_COBRAL138 COBRAL138 3327 +roverpcs8 MACH_ROVERPCS8 ROVERPCS8 3328 +marvelc MACH_MARVELC MARVELC 3329 +navefihid MACH_NAVEFIHID NAVEFIHID 3330 +dm365_cv100 MACH_DM365_CV100 DM365_CV100 3331 +able MACH_ABLE ABLE 3332 +legacy MACH_LEGACY LEGACY 3333 +icong MACH_ICONG ICONG 3334 +rover_g8 MACH_ROVER_G8 ROVER_G8 3335 +t5388p MACH_T5388P T5388P 3336 +dingo MACH_DINGO DINGO 3337 +goflexhome MACH_GOFLEXHOME GOFLEXHOME 3338 diff --git a/arch/blackfin/include/asm/bfin_serial.h b/arch/blackfin/include/asm/bfin_serial.h index 1ff9f14..7dbc664 100644 --- a/arch/blackfin/include/asm/bfin_serial.h +++ b/arch/blackfin/include/asm/bfin_serial.h @@ -10,6 +10,7 @@ #define __BFIN_ASM_SERIAL_H__ #include <linux/serial_core.h> +#include <linux/spinlock.h> #include <mach/anomaly.h> #include <mach/bfin_serial.h> @@ -41,6 +42,7 @@ struct bfin_serial_port { struct circ_buf rx_dma_buf; struct timer_list rx_dma_timer; int rx_dma_nrows; + spinlock_t rx_lock; unsigned int tx_dma_channel; unsigned int rx_dma_channel; struct work_struct tx_dma_workqueue; diff --git a/arch/blackfin/lib/outs.S b/arch/blackfin/lib/outs.S index 250f4d4..06a5e67 100644 --- a/arch/blackfin/lib/outs.S +++ b/arch/blackfin/lib/outs.S @@ -13,6 +13,8 @@ .align 2 ENTRY(_outsl) + CC = R2 == 0; + IF CC JUMP 1f; P0 = R0; /* P0 = port */ P1 = R1; /* P1 = address */ P2 = R2; /* P2 = count */ @@ -20,10 +22,12 @@ ENTRY(_outsl) LSETUP( .Llong_loop_s, .Llong_loop_e) LC0 = P2; .Llong_loop_s: R0 = [P1++]; .Llong_loop_e: [P0] = R0; - RTS; +1: RTS; ENDPROC(_outsl) ENTRY(_outsw) + CC = R2 == 0; + IF CC JUMP 1f; P0 = R0; /* P0 = port */ P1 = R1; /* P1 = address */ P2 = R2; /* P2 = count */ @@ -31,10 +35,12 @@ ENTRY(_outsw) LSETUP( .Lword_loop_s, .Lword_loop_e) LC0 = P2; .Lword_loop_s: R0 = W[P1++]; .Lword_loop_e: W[P0] = R0; - RTS; +1: RTS; ENDPROC(_outsw) ENTRY(_outsb) + CC = R2 == 0; + IF CC JUMP 1f; P0 = R0; /* P0 = port */ P1 = R1; /* P1 = address */ P2 = R2; /* P2 = count */ @@ -42,10 +48,12 @@ ENTRY(_outsb) LSETUP( .Lbyte_loop_s, .Lbyte_loop_e) LC0 = P2; .Lbyte_loop_s: R0 = B[P1++]; .Lbyte_loop_e: B[P0] = R0; - RTS; +1: RTS; ENDPROC(_outsb) ENTRY(_outsw_8) + CC = R2 == 0; + IF CC JUMP 1f; P0 = R0; /* P0 = port */ P1 = R1; /* P1 = address */ P2 = R2; /* P2 = count */ @@ -56,5 +64,5 @@ ENTRY(_outsw_8) R0 = R0 << 8; R0 = R0 + R1; .Lword8_loop_e: W[P0] = R0; - RTS; +1: RTS; ENDPROC(_outsw_8) diff --git a/arch/blackfin/mach-common/cache.S b/arch/blackfin/mach-common/cache.S index 790c767..ab4a925 100644 --- a/arch/blackfin/mach-common/cache.S +++ b/arch/blackfin/mach-common/cache.S @@ -58,6 +58,8 @@ 1: .ifeqs "\flushins", BROK_FLUSH_INST \flushins [P0++]; + nop; + nop; 2: nop; .else 2: \flushins [P0++]; diff --git a/arch/cris/arch-v32/kernel/smp.c b/arch/cris/arch-v32/kernel/smp.c index 84fed3b..4c9e3e1 100644 --- a/arch/cris/arch-v32/kernel/smp.c +++ b/arch/cris/arch-v32/kernel/smp.c @@ -26,7 +26,9 @@ #define FLUSH_ALL (void*)0xffffffff /* Vector of locks used for various atomic operations */ -spinlock_t cris_atomic_locks[] = { [0 ... LOCK_COUNT - 1] = SPIN_LOCK_UNLOCKED}; +spinlock_t cris_atomic_locks[] = { + [0 ... LOCK_COUNT - 1] = __SPIN_LOCK_UNLOCKED(cris_atomic_locks) +}; /* CPU masks */ cpumask_t phys_cpu_present_map = CPU_MASK_NONE; diff --git a/arch/cris/kernel/vmlinux.lds.S b/arch/cris/kernel/vmlinux.lds.S index 4422189..c49be84 100644 --- a/arch/cris/kernel/vmlinux.lds.S +++ b/arch/cris/kernel/vmlinux.lds.S @@ -72,11 +72,6 @@ SECTIONS INIT_TEXT_SECTION(PAGE_SIZE) .init.data : { INIT_DATA } .init.setup : { INIT_SETUP(16) } -#ifdef CONFIG_ETRAX_ARCH_V32 - __start___param = .; - __param : { *(__param) } - __stop___param = .; -#endif .initcall.init : { INIT_CALLS } diff --git a/arch/frv/include/asm/futex.h b/arch/frv/include/asm/futex.h index 08b3d1d..4bea27f 100644 --- a/arch/frv/include/asm/futex.h +++ b/arch/frv/include/asm/futex.h @@ -7,10 +7,11 @@ #include <asm/errno.h> #include <asm/uaccess.h> -extern int futex_atomic_op_inuser(int encoded_op, int __user *uaddr); +extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr); static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { return -ENOSYS; } diff --git a/arch/frv/kernel/futex.c b/arch/frv/kernel/futex.c index 14f64b0..d155ca9 100644 --- a/arch/frv/kernel/futex.c +++ b/arch/frv/kernel/futex.c @@ -18,7 +18,7 @@ * the various futex operations; MMU fault checking is ignored under no-MMU * conditions */ -static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_oldval) +static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr, int *_oldval) { int oldval, ret; @@ -50,7 +50,7 @@ static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, int *_o return ret; } -static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_oldval) +static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr, int *_oldval) { int oldval, ret; @@ -83,7 +83,7 @@ static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, int *_o return ret; } -static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_oldval) +static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr, int *_oldval) { int oldval, ret; @@ -116,7 +116,7 @@ static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, int *_ol return ret; } -static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_oldval) +static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr, int *_oldval) { int oldval, ret; @@ -149,7 +149,7 @@ static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, int *_o return ret; } -static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_oldval) +static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, int *_oldval) { int oldval, ret; @@ -186,7 +186,7 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, int *_o /* * do the futex operations */ -int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -197,7 +197,7 @@ int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h index c7f0f06..8428525 100644 --- a/arch/ia64/include/asm/futex.h +++ b/arch/ia64/include/asm/futex.h @@ -46,7 +46,7 @@ do { \ } while (0) static inline int -futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -56,7 +56,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -100,23 +100,26 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; { - register unsigned long r8 __asm ("r8"); + register unsigned long r8 __asm ("r8") = 0; + unsigned long prev; __asm__ __volatile__( " mf;; \n" " mov ar.ccv=%3;; \n" "[1:] cmpxchg4.acq %0=[%1],%2,ar.ccv \n" " .xdata4 \"__ex_table\", 1b-., 2f-. \n" "[2:]" - : "=r" (r8) + : "=r" (prev) : "r" (uaddr), "r" (newval), "rO" ((long) (unsigned) oldval) : "memory"); + *uval = prev; return r8; } } diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h index 215d545..3027e75 100644 --- a/arch/ia64/include/asm/rwsem.h +++ b/arch/ia64/include/asm/rwsem.h @@ -25,20 +25,8 @@ #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead." #endif -#include <linux/list.h> -#include <linux/spinlock.h> - #include <asm/intrinsics.h> -/* - * the semaphore definition - */ -struct rw_semaphore { - signed long count; - spinlock_t wait_lock; - struct list_head wait_list; -}; - #define RWSEM_UNLOCKED_VALUE __IA64_UL_CONST(0x0000000000000000) #define RWSEM_ACTIVE_BIAS (1L) #define RWSEM_ACTIVE_MASK (0xffffffffL) @@ -46,26 +34,6 @@ struct rw_semaphore { #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -static inline void -init_rwsem (struct rw_semaphore *sem) -{ - sem->count = RWSEM_UNLOCKED_VALUE; - spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} - /* * lock for reading */ @@ -174,9 +142,4 @@ __downgrade_write (struct rw_semaphore *sem) #define rwsem_atomic_add(delta, sem) atomic64_add(delta, (atomic64_t *)(&(sem)->count)) #define rwsem_atomic_update(delta, sem) atomic64_add_return(delta, (atomic64_t *)(&(sem)->count)) -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* _ASM_IA64_RWSEM_H */ diff --git a/arch/ia64/include/asm/xen/hypercall.h b/arch/ia64/include/asm/xen/hypercall.h index 96fc623..ed28bcd 100644 --- a/arch/ia64/include/asm/xen/hypercall.h +++ b/arch/ia64/include/asm/xen/hypercall.h @@ -107,7 +107,7 @@ extern unsigned long __hypercall(unsigned long a1, unsigned long a2, static inline int xencomm_arch_hypercall_sched_op(int cmd, struct xencomm_handle *arg) { - return _hypercall2(int, sched_op_new, cmd, arg); + return _hypercall2(int, sched_op, cmd, arg); } static inline long diff --git a/arch/ia64/xen/suspend.c b/arch/ia64/xen/suspend.c index fd66b04..419c862 100644 --- a/arch/ia64/xen/suspend.c +++ b/arch/ia64/xen/suspend.c @@ -37,19 +37,14 @@ xen_mm_unpin_all(void) /* nothing */ } -void xen_pre_device_suspend(void) -{ - /* nothing */ -} - void -xen_pre_suspend() +xen_arch_pre_suspend() { /* nothing */ } void -xen_post_suspend(int suspend_cancelled) +xen_arch_post_suspend(int suspend_cancelled) { if (suspend_cancelled) return; diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c index f745c12..76eaf38 100644 --- a/arch/m32r/kernel/irq.c +++ b/arch/m32r/kernel/irq.c @@ -80,7 +80,7 @@ asmlinkage unsigned int do_IRQ(int irq, struct pt_regs *regs) #ifdef CONFIG_DEBUG_STACKOVERFLOW /* FIXME M32R */ #endif - __do_IRQ(irq); + generic_handle_irq(irq); irq_exit(); set_irq_regs(old_regs); diff --git a/arch/m68k/include/asm/string.h b/arch/m68k/include/asm/string.h index 65b1312..3219845 100644 --- a/arch/m68k/include/asm/string.h +++ b/arch/m68k/include/asm/string.h @@ -99,14 +99,12 @@ static inline int strcmp(const char *cs, const char *ct) : "+a" (cs), "+a" (ct), "=d" (res)); return res; } +#endif /* CONFIG_COLDFIRE */ #define __HAVE_ARCH_MEMMOVE extern void *memmove(void *, const void *, __kernel_size_t); -#define __HAVE_ARCH_MEMCMP -extern int memcmp(const void *, const void *, __kernel_size_t); #define memcmp(d, s, n) __builtin_memcmp(d, s, n) -#endif /* CONFIG_COLDFIRE */ #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, __kernel_size_t); diff --git a/arch/m68k/lib/string.c b/arch/m68k/lib/string.c index 4253f87..d399c5f 100644 --- a/arch/m68k/lib/string.c +++ b/arch/m68k/lib/string.c @@ -243,14 +243,3 @@ void *memmove(void *dest, const void *src, size_t n) return xdest; } EXPORT_SYMBOL(memmove); - -int memcmp(const void *cs, const void *ct, size_t count) -{ - const unsigned char *su1, *su2; - - for (su1 = cs, su2 = ct; count > 0; ++su1, ++su2, count--) - if (*su1 != *su2) - return *su1 < *su2 ? -1 : +1; - return 0; -} -EXPORT_SYMBOL(memcmp); diff --git a/arch/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S index ef33213..47e15eb 100644 --- a/arch/m68knommu/kernel/vmlinux.lds.S +++ b/arch/m68knommu/kernel/vmlinux.lds.S @@ -141,6 +141,12 @@ SECTIONS { *(__param) __stop___param = .; + /* Built-in module versions */ + . = ALIGN(4) ; + __start___modver = .; + *(__modver) + __stop___modver = .; + . = ALIGN(4) ; _etext = . ; } > TEXT diff --git a/arch/m68knommu/lib/Makefile b/arch/m68knommu/lib/Makefile index d94d709..32d852e 100644 --- a/arch/m68knommu/lib/Makefile +++ b/arch/m68knommu/lib/Makefile @@ -4,4 +4,4 @@ lib-y := ashldi3.o ashrdi3.o lshrdi3.o \ muldi3.o mulsi3.o divsi3.o udivsi3.o modsi3.o umodsi3.o \ - checksum.o memcpy.o memset.o delay.o + checksum.o memcpy.o memmove.o memset.o delay.o diff --git a/arch/m68knommu/lib/memmove.c b/arch/m68knommu/lib/memmove.c new file mode 100644 index 0000000..b3dcfe9 --- /dev/null +++ b/arch/m68knommu/lib/memmove.c @@ -0,0 +1,105 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#define __IN_STRING_C + +#include <linux/module.h> +#include <linux/string.h> + +void *memmove(void *dest, const void *src, size_t n) +{ + void *xdest = dest; + size_t temp; + + if (!n) + return xdest; + + if (dest < src) { + if ((long)dest & 1) { + char *cdest = dest; + const char *csrc = src; + *cdest++ = *csrc++; + dest = cdest; + src = csrc; + n--; + } + if (n > 2 && (long)dest & 2) { + short *sdest = dest; + const short *ssrc = src; + *sdest++ = *ssrc++; + dest = sdest; + src = ssrc; + n -= 2; + } + temp = n >> 2; + if (temp) { + long *ldest = dest; + const long *lsrc = src; + temp--; + do + *ldest++ = *lsrc++; + while (temp--); + dest = ldest; + src = lsrc; + } + if (n & 2) { + short *sdest = dest; + const short *ssrc = src; + *sdest++ = *ssrc++; + dest = sdest; + src = ssrc; + } + if (n & 1) { + char *cdest = dest; + const char *csrc = src; + *cdest = *csrc; + } + } else { + dest = (char *)dest + n; + src = (const char *)src + n; + if ((long)dest & 1) { + char *cdest = dest; + const char *csrc = src; + *--cdest = *--csrc; + dest = cdest; + src = csrc; + n--; + } + if (n > 2 && (long)dest & 2) { + short *sdest = dest; + const short *ssrc = src; + *--sdest = *--ssrc; + dest = sdest; + src = ssrc; + n -= 2; + } + temp = n >> 2; + if (temp) { + long *ldest = dest; + const long *lsrc = src; + temp--; + do + *--ldest = *--lsrc; + while (temp--); + dest = ldest; + src = lsrc; + } + if (n & 2) { + short *sdest = dest; + const short *ssrc = src; + *--sdest = *--ssrc; + dest = sdest; + src = ssrc; + } + if (n & 1) { + char *cdest = dest; + const char *csrc = src; + *--cdest = *--csrc; + } + } + return xdest; +} +EXPORT_SYMBOL(memmove); diff --git a/arch/m68knommu/platform/5249/intc2.c b/arch/m68knommu/platform/5249/intc2.c index d09d9da..c5151f8 100644 --- a/arch/m68knommu/platform/5249/intc2.c +++ b/arch/m68knommu/platform/5249/intc2.c @@ -50,8 +50,10 @@ static int __init mcf_intc2_init(void) int irq; /* GPIO interrupt sources */ - for (irq = MCFINTC2_GPIOIRQ0; (irq <= MCFINTC2_GPIOIRQ7); irq++) + for (irq = MCFINTC2_GPIOIRQ0; (irq <= MCFINTC2_GPIOIRQ7); irq++) { irq_desc[irq].chip = &intc2_irq_gpio_chip; + set_irq_handler(irq, handle_edge_irq); + } return 0; } diff --git a/arch/m68knommu/platform/68328/entry.S b/arch/m68knommu/platform/68328/entry.S index 240a7a6..676960c 100644 --- a/arch/m68knommu/platform/68328/entry.S +++ b/arch/m68knommu/platform/68328/entry.S @@ -108,7 +108,6 @@ Luser_return: movel %d1,%a2 1: move %a2@(TI_FLAGS),%d1 /* thread_info->flags */ - andl #_TIF_WORK_MASK,%d1 jne Lwork_to_do RESTORE_ALL diff --git a/arch/m68knommu/platform/68360/commproc.c b/arch/m68knommu/platform/68360/commproc.c index f27e688..8e4e10c 100644 --- a/arch/m68knommu/platform/68360/commproc.c +++ b/arch/m68knommu/platform/68360/commproc.c @@ -210,7 +210,7 @@ void cpm_install_handler(int vec, void (*handler)(), void *dev_id) { - request_irq(vec, handler, IRQ_FLG_LOCK, "timer", dev_id); + request_irq(vec, handler, 0, "timer", dev_id); /* if (cpm_vecs[vec].handler != 0) */ /* printk(KERN_INFO "CPM interrupt %x replacing %x\n", */ diff --git a/arch/m68knommu/platform/68360/config.c b/arch/m68knommu/platform/68360/config.c index ac629fa3..9dd5bca 100644 --- a/arch/m68knommu/platform/68360/config.c +++ b/arch/m68knommu/platform/68360/config.c @@ -75,7 +75,7 @@ void hw_timer_init(void) /* Set compare register 32Khz / 32 / 10 = 100 */ TCMP = 10; - request_irq(IRQ_MACHSPEC | 1, timer_routine, IRQ_FLG_LOCK, "timer", NULL); + request_irq(IRQ_MACHSPEC | 1, timer_routine, 0, "timer", NULL); #endif /* General purpose quicc timers: MC68360UM p7-20 */ diff --git a/arch/m68knommu/platform/68360/entry.S b/arch/m68knommu/platform/68360/entry.S index 8a28788..46c1b18 100644 --- a/arch/m68knommu/platform/68360/entry.S +++ b/arch/m68knommu/platform/68360/entry.S @@ -104,7 +104,6 @@ Luser_return: movel %d1,%a2 1: move %a2@(TI_FLAGS),%d1 /* thread_info->flags */ - andl #_TIF_WORK_MASK,%d1 jne Lwork_to_do RESTORE_ALL diff --git a/arch/m68knommu/platform/68360/ints.c b/arch/m68knommu/platform/68360/ints.c index ad96ab1..a29041c 100644 --- a/arch/m68knommu/platform/68360/ints.c +++ b/arch/m68knommu/platform/68360/ints.c @@ -132,8 +132,8 @@ void init_IRQ(void) pquicc->intr_cimr = 0x00000000; for (i = 0; (i < NR_IRQS); i++) { - set_irq_chip(irq, &intc_irq_chip); - set_irq_handler(irq, handle_level_irq); + set_irq_chip(i, &intc_irq_chip); + set_irq_handler(i, handle_level_irq); } } diff --git a/arch/m68knommu/platform/coldfire/entry.S b/arch/m68knommu/platform/coldfire/entry.S index 4ddfc3da..5837cf0 100644 --- a/arch/m68knommu/platform/coldfire/entry.S +++ b/arch/m68knommu/platform/coldfire/entry.S @@ -138,7 +138,6 @@ Luser_return: andl #-THREAD_SIZE,%d1 /* at base of kernel stack */ movel %d1,%a0 movel %a0@(TI_FLAGS),%d1 /* get thread_info->flags */ - andl #0xefff,%d1 jne Lwork_to_do /* still work to do */ Lreturn: diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h index ad3fd61..b0526d2 100644 --- a/arch/microblaze/include/asm/futex.h +++ b/arch/microblaze/include/asm/futex.h @@ -29,7 +29,7 @@ }) static inline int -futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -39,7 +39,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -94,31 +94,34 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - int prev, cmp; + int ret = 0, cmp; + u32 prev; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - __asm__ __volatile__ ("1: lwx %0, %2, r0; \ - cmp %1, %0, %3; \ - beqi %1, 3f; \ - 2: swx %4, %2, r0; \ - addic %1, r0, 0; \ - bnei %1, 1b; \ + __asm__ __volatile__ ("1: lwx %1, %3, r0; \ + cmp %2, %1, %4; \ + beqi %2, 3f; \ + 2: swx %5, %3, r0; \ + addic %2, r0, 0; \ + bnei %2, 1b; \ 3: \ .section .fixup,\"ax\"; \ 4: brid 3b; \ - addik %0, r0, %5; \ + addik %0, r0, %6; \ .previous; \ .section __ex_table,\"a\"; \ .word 1b,4b,2b,4b; \ .previous;" \ - : "=&r" (prev), "=&r"(cmp) \ + : "+r" (ret), "=&r" (prev), "=&r"(cmp) \ : "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT)); - return prev; + *uval = prev; + return ret; } #endif /* __KERNEL__ */ diff --git a/arch/microblaze/include/asm/irqflags.h b/arch/microblaze/include/asm/irqflags.h index 5fd3190..c4532f0 100644 --- a/arch/microblaze/include/asm/irqflags.h +++ b/arch/microblaze/include/asm/irqflags.h @@ -12,7 +12,7 @@ #include <linux/types.h> #include <asm/registers.h> -#ifdef CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR +#if CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR static inline unsigned long arch_local_irq_save(void) { diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index b23f680..885574a 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -411,20 +411,19 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) static inline unsigned long pte_update(pte_t *p, unsigned long clr, unsigned long set) { - unsigned long old, tmp, msr; - - __asm__ __volatile__("\ - msrclr %2, 0x2\n\ - nop\n\ - lw %0, %4, r0\n\ - andn %1, %0, %5\n\ - or %1, %1, %6\n\ - sw %1, %4, r0\n\ - mts rmsr, %2\n\ - nop" - : "=&r" (old), "=&r" (tmp), "=&r" (msr), "=m" (*p) - : "r" ((unsigned long)(p + 1) - 4), "r" (clr), "r" (set), "m" (*p) - : "cc"); + unsigned long flags, old, tmp; + + raw_local_irq_save(flags); + + __asm__ __volatile__( "lw %0, %2, r0 \n" + "andn %1, %0, %3 \n" + "or %1, %1, %4 \n" + "sw %1, %2, r0 \n" + : "=&r" (old), "=&r" (tmp) + : "r" ((unsigned long)(p + 1) - 4), "r" (clr), "r" (set) + : "cc"); + + raw_local_irq_restore(flags); return old; } diff --git a/arch/microblaze/kernel/cpu/pvr.c b/arch/microblaze/kernel/cpu/pvr.c index e01afa6..488c1ed 100644 --- a/arch/microblaze/kernel/cpu/pvr.c +++ b/arch/microblaze/kernel/cpu/pvr.c @@ -27,7 +27,7 @@ register unsigned tmp __asm__("r3"); \ tmp = 0x0; /* Prevent warning about unused */ \ __asm__ __volatile__ ( \ - "mfs %0, rpvr" #pvrid ";" \ + "mfs %0, rpvr" #pvrid ";" \ : "=r" (tmp) : : "memory"); \ val = tmp; \ } @@ -54,7 +54,7 @@ int cpu_has_pvr(void) if (!(flags & PVR_MSR_BIT)) return 0; - get_single_pvr(0x00, pvr0); + get_single_pvr(0, pvr0); pr_debug("%s: pvr0 is 0x%08x\n", __func__, pvr0); if (pvr0 & PVR0_PVR_FULL_MASK) diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index 4243400..778a5ce 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -62,23 +62,32 @@ real_start: andi r1, r1, ~2 mts rmsr, r1 /* - * Here is checking mechanism which check if Microblaze has msr instructions - * We load msr and compare it with previous r1 value - if is the same, - * msr instructions works if not - cpu don't have them. + * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc' + * if the msrclr instruction is not enabled. We use this to detect + * if the opcode is available, by issuing msrclr and then testing the result. + * r8 == 0 - msr instructions are implemented + * r8 != 0 - msr instructions are not implemented */ - /* r8=0 - I have msr instr, 1 - I don't have them */ - rsubi r0, r0, 1 /* set the carry bit */ - msrclr r0, 0x4 /* try to clear it */ - /* read the carry bit, r8 will be '0' if msrclr exists */ - addik r8, r0, 0 + msrclr r8, 0 /* clear nothing - just read msr for test */ + cmpu r8, r8, r1 /* r1 must contain msr reg content */ /* r7 may point to an FDT, or there may be one linked in. if it's in r7, we've got to save it away ASAP. We ensure r7 points to a valid FDT, just in case the bootloader is broken or non-existent */ beqi r7, no_fdt_arg /* NULL pointer? don't copy */ - lw r11, r0, r7 /* Does r7 point to a */ - rsubi r11, r11, OF_DT_HEADER /* valid FDT? */ +/* Does r7 point to a valid FDT? Load HEADER magic number */ + /* Run time Big/Little endian platform */ + /* Save 1 as word and load byte - 0 - BIG, 1 - LITTLE */ + addik r11, r0, 0x1 /* BIG/LITTLE checking value */ + /* __bss_start will be zeroed later - it is just temp location */ + swi r11, r0, TOPHYS(__bss_start) + lbui r11, r0, TOPHYS(__bss_start) + beqid r11, big_endian /* DO NOT break delay stop dependency */ + lw r11, r0, r7 /* Big endian load in delay slot */ + lwr r11, r0, r7 /* Little endian load */ +big_endian: + rsubi r11, r11, OF_DT_HEADER /* Check FDT header */ beqi r11, _prepare_copy_fdt or r7, r0, r0 /* clear R7 when not valid DTB */ bnei r11, no_fdt_arg /* No - get out of here */ diff --git a/arch/microblaze/kernel/hw_exception_handler.S b/arch/microblaze/kernel/hw_exception_handler.S index 25f6e07..782680d 100644 --- a/arch/microblaze/kernel/hw_exception_handler.S +++ b/arch/microblaze/kernel/hw_exception_handler.S @@ -147,10 +147,6 @@ #if CONFIG_XILINX_MICROBLAZE0_USE_BARREL > 0 #define BSRLI(rD, rA, imm) \ bsrli rD, rA, imm - #elif CONFIG_XILINX_MICROBLAZE0_USE_DIV > 0 - #define BSRLI(rD, rA, imm) \ - ori rD, r0, (1 << imm); \ - idivu rD, rD, rA #else #define BSRLI(rD, rA, imm) BSRLI ## imm (rD, rA) /* Only the used shift constants defined here - add more if needed */ diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index bb1558e..9312fbb 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -161,11 +161,11 @@ void __init machine_early_init(const char *cmdline, unsigned int ram, #if CONFIG_XILINX_MICROBLAZE0_USE_MSR_INSTR if (msr) eprintk("!!!Your kernel has setup MSR instruction but " - "CPU don't have it %d\n", msr); + "CPU don't have it %x\n", msr); #else if (!msr) eprintk("!!!Your kernel not setup MSR instruction but " - "CPU have it %d\n", msr); + "CPU have it %x\n", msr); #endif for (src = __ivt_start; src < __ivt_end; src++, dst++) diff --git a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S index fdc48bb..62021d7 100644 --- a/arch/microblaze/lib/fastcopy.S +++ b/arch/microblaze/lib/fastcopy.S @@ -29,6 +29,10 @@ * between mem locations with size of xfer spec'd in bytes */ +#ifdef __MICROBLAZEEL__ +#error Microblaze LE not support ASM optimized lib func. Disable OPT_LIB_ASM. +#endif + #include <linux/linkage.h> .text .globl memcpy diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index f5ecc05..d889835 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -4,6 +4,7 @@ config MIPS select HAVE_GENERIC_DMA_COHERENT select HAVE_IDE select HAVE_OPROFILE + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC select HAVE_ARCH_KGDB @@ -208,6 +209,7 @@ config MACH_JZ4740 select ARCH_REQUIRE_GPIOLIB select SYS_HAS_EARLY_PRINTK select HAVE_PWM + select HAVE_CLK config LASAT bool "LASAT Networks platforms" @@ -333,6 +335,8 @@ config PNX8550_STB810 config PMC_MSP bool "PMC-Sierra MSP chipsets" depends on EXPERIMENTAL + select CEVT_R4K + select CSRC_R4K select DMA_NONCOHERENT select SWAP_IO_SPACE select NO_EXCEPT_FILL diff --git a/arch/mips/alchemy/mtx-1/board_setup.c b/arch/mips/alchemy/mtx-1/board_setup.c index 6398fa9..40b84b9 100644 --- a/arch/mips/alchemy/mtx-1/board_setup.c +++ b/arch/mips/alchemy/mtx-1/board_setup.c @@ -54,8 +54,8 @@ int mtx1_pci_idsel(unsigned int devsel, int assert); static void mtx1_reset(char *c) { - /* Hit BCSR.SYSTEM_CONTROL[SW_RST] */ - au_writel(0x00000000, 0xAE00001C); + /* Jump to the reset vector */ + __asm__ __volatile__("jr\t%0"::"r"(0xbfc00000)); } static void mtx1_power_off(void) diff --git a/arch/mips/alchemy/mtx-1/platform.c b/arch/mips/alchemy/mtx-1/platform.c index e30e42a..956f946 100644 --- a/arch/mips/alchemy/mtx-1/platform.c +++ b/arch/mips/alchemy/mtx-1/platform.c @@ -28,6 +28,8 @@ #include <linux/mtd/physmap.h> #include <mtd/mtd-abi.h> +#include <asm/mach-au1x00/au1xxx_eth.h> + static struct gpio_keys_button mtx1_gpio_button[] = { { .gpio = 207, @@ -140,10 +142,17 @@ static struct __initdata platform_device * mtx1_devs[] = { &mtx1_mtd, }; +static struct au1000_eth_platform_data mtx1_au1000_eth0_pdata = { + .phy_search_highest_addr = 1, + .phy1_search_mac0 = 1, +}; + static int __init mtx1_register_devices(void) { int rc; + au1xxx_override_eth_cfg(0, &mtx1_au1000_eth0_pdata); + rc = gpio_request(mtx1_gpio_button[0].gpio, mtx1_gpio_button[0].desc); if (rc < 0) { diff --git a/arch/mips/alchemy/xxs1500/board_setup.c b/arch/mips/alchemy/xxs1500/board_setup.c index b43c918..80c521e 100644 --- a/arch/mips/alchemy/xxs1500/board_setup.c +++ b/arch/mips/alchemy/xxs1500/board_setup.c @@ -36,8 +36,8 @@ static void xxs1500_reset(char *c) { - /* Hit BCSR.SYSTEM_CONTROL[SW_RST] */ - au_writel(0x00000000, 0xAE00001C); + /* Jump to the reset vector */ + __asm__ __volatile__("jr\t%0"::"r"(0xbfc00000)); } static void xxs1500_power_off(void) diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index b9cce90..6ebf173 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -75,7 +75,7 @@ } static inline int -futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -85,7 +85,7 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -132,11 +132,13 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - int retval; + int ret = 0; + u32 val; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; if (cpu_has_llsc && R10000_LLSC_WAR) { @@ -145,25 +147,25 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) " .set push \n" " .set noat \n" " .set mips3 \n" - "1: ll %0, %2 \n" - " bne %0, %z3, 3f \n" + "1: ll %1, %3 \n" + " bne %1, %z4, 3f \n" " .set mips0 \n" - " move $1, %z4 \n" + " move $1, %z5 \n" " .set mips3 \n" - "2: sc $1, %1 \n" + "2: sc $1, %2 \n" " beqzl $1, 1b \n" __WEAK_LLSC_MB "3: \n" " .set pop \n" " .section .fixup,\"ax\" \n" - "4: li %0, %5 \n" + "4: li %0, %6 \n" " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" " "__UA_ADDR "\t1b, 4b \n" " "__UA_ADDR "\t2b, 4b \n" " .previous \n" - : "=&r" (retval), "=R" (*uaddr) + : "+r" (ret), "=&r" (val), "=R" (*uaddr) : "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { @@ -172,31 +174,32 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) " .set push \n" " .set noat \n" " .set mips3 \n" - "1: ll %0, %2 \n" - " bne %0, %z3, 3f \n" + "1: ll %1, %3 \n" + " bne %1, %z4, 3f \n" " .set mips0 \n" - " move $1, %z4 \n" + " move $1, %z5 \n" " .set mips3 \n" - "2: sc $1, %1 \n" + "2: sc $1, %2 \n" " beqz $1, 1b \n" __WEAK_LLSC_MB "3: \n" " .set pop \n" " .section .fixup,\"ax\" \n" - "4: li %0, %5 \n" + "4: li %0, %6 \n" " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" " "__UA_ADDR "\t1b, 4b \n" " "__UA_ADDR "\t2b, 4b \n" " .previous \n" - : "=&r" (retval), "=R" (*uaddr) + : "+r" (ret), "=&r" (val), "=R" (*uaddr) : "R" (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); } else return -ENOSYS; - return retval; + *uval = val; + return ret; } #endif diff --git a/arch/mips/include/asm/perf_event.h b/arch/mips/include/asm/perf_event.h index e00007c..d0c7749 100644 --- a/arch/mips/include/asm/perf_event.h +++ b/arch/mips/include/asm/perf_event.h @@ -11,15 +11,5 @@ #ifndef __MIPS_PERF_EVENT_H__ #define __MIPS_PERF_EVENT_H__ - -/* - * MIPS performance counters do not raise NMI upon overflow, a regular - * interrupt will be signaled. Hence we can do the pending perf event - * work at the tail of the irq handler. - */ -static inline void -set_perf_event_pending(void) -{ -} - +/* Leave it empty here. The file is required by linux/perf_event.h */ #endif /* __MIPS_PERF_EVENT_H__ */ diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 5a84a1f..94ca2b0 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -17,29 +17,13 @@ #include <asm/cacheflush.h> #include <asm/uasm.h> -/* - * If the Instruction Pointer is in module space (0xc0000000), return true; - * otherwise, it is in kernel space (0x80000000), return false. - * - * FIXME: This will not work when the kernel space and module space are the - * same. If they are the same, we need to modify scripts/recordmcount.pl, - * ftrace_make_nop/call() and the other related parts to ensure the - * enabling/disabling of the calling site to _mcount is right for both kernel - * and module. - */ - -static inline int in_module(unsigned long ip) -{ - return ip & 0x40000000; -} +#include <asm-generic/sections.h> #ifdef CONFIG_DYNAMIC_FTRACE #define JAL 0x0c000000 /* jump & link: ip --> ra, jump to target */ #define ADDR_MASK 0x03ffffff /* op_code|addr : 31...26|25 ....0 */ -#define INSN_B_1F_4 0x10000004 /* b 1f; offset = 4 */ -#define INSN_B_1F_5 0x10000005 /* b 1f; offset = 5 */ #define INSN_NOP 0x00000000 /* nop */ #define INSN_JAL(addr) \ ((unsigned int)(JAL | (((addr) >> 2) & ADDR_MASK))) @@ -69,6 +53,20 @@ static inline void ftrace_dyn_arch_init_insns(void) #endif } +/* + * Check if the address is in kernel space + * + * Clone core_kernel_text() from kernel/extable.c, but doesn't call + * init_kernel_text() for Ftrace doesn't trace functions in init sections. + */ +static inline int in_kernel_space(unsigned long ip) +{ + if (ip >= (unsigned long)_stext && + ip <= (unsigned long)_etext) + return 1; + return 0; +} + static int ftrace_modify_code(unsigned long ip, unsigned int new_code) { int faulted; @@ -84,6 +82,42 @@ static int ftrace_modify_code(unsigned long ip, unsigned int new_code) return 0; } +/* + * The details about the calling site of mcount on MIPS + * + * 1. For kernel: + * + * move at, ra + * jal _mcount --> nop + * + * 2. For modules: + * + * 2.1 For KBUILD_MCOUNT_RA_ADDRESS and CONFIG_32BIT + * + * lui v1, hi_16bit_of_mcount --> b 1f (0x10000005) + * addiu v1, v1, low_16bit_of_mcount + * move at, ra + * move $12, ra_address + * jalr v1 + * sub sp, sp, 8 + * 1: offset = 5 instructions + * 2.2 For the Other situations + * + * lui v1, hi_16bit_of_mcount --> b 1f (0x10000004) + * addiu v1, v1, low_16bit_of_mcount + * move at, ra + * jalr v1 + * nop | move $12, ra_address | sub sp, sp, 8 + * 1: offset = 4 instructions + */ + +#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT) +#define MCOUNT_OFFSET_INSNS 5 +#else +#define MCOUNT_OFFSET_INSNS 4 +#endif +#define INSN_B_1F (0x10000000 | MCOUNT_OFFSET_INSNS) + int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { @@ -91,39 +125,11 @@ int ftrace_make_nop(struct module *mod, unsigned long ip = rec->ip; /* - * We have compiled module with -mlong-calls, but compiled the kernel - * without it, we need to cope with them respectively. + * If ip is in kernel space, no long call, otherwise, long call is + * needed. */ - if (in_module(ip)) { -#if defined(KBUILD_MCOUNT_RA_ADDRESS) && defined(CONFIG_32BIT) - /* - * lui v1, hi_16bit_of_mcount --> b 1f (0x10000005) - * addiu v1, v1, low_16bit_of_mcount - * move at, ra - * move $12, ra_address - * jalr v1 - * sub sp, sp, 8 - * 1: offset = 5 instructions - */ - new = INSN_B_1F_5; -#else - /* - * lui v1, hi_16bit_of_mcount --> b 1f (0x10000004) - * addiu v1, v1, low_16bit_of_mcount - * move at, ra - * jalr v1 - * nop | move $12, ra_address | sub sp, sp, 8 - * 1: offset = 4 instructions - */ - new = INSN_B_1F_4; -#endif - } else { - /* - * move at, ra - * jal _mcount --> nop - */ - new = INSN_NOP; - } + new = in_kernel_space(ip) ? INSN_NOP : INSN_B_1F; + return ftrace_modify_code(ip, new); } @@ -132,8 +138,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) unsigned int new; unsigned long ip = rec->ip; - /* ip, module: 0xc0000000, kernel: 0x80000000 */ - new = in_module(ip) ? insn_lui_v1_hi16_mcount : insn_jal_ftrace_caller; + new = in_kernel_space(ip) ? insn_jal_ftrace_caller : + insn_lui_v1_hi16_mcount; return ftrace_modify_code(ip, new); } @@ -190,29 +196,25 @@ int ftrace_disable_ftrace_graph_caller(void) #define S_R_SP (0xafb0 << 16) /* s{d,w} R, offset(sp) */ #define OFFSET_MASK 0xffff /* stack offset range: 0 ~ PT_SIZE */ -unsigned long ftrace_get_parent_addr(unsigned long self_addr, - unsigned long parent, - unsigned long parent_addr, - unsigned long fp) +unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long + old_parent_ra, unsigned long parent_ra_addr, unsigned long fp) { - unsigned long sp, ip, ra; + unsigned long sp, ip, tmp; unsigned int code; int faulted; /* - * For module, move the ip from calling site of mcount to the - * instruction "lui v1, hi_16bit_of_mcount"(offset is 20), but for - * kernel, move to the instruction "move ra, at"(offset is 12) + * For module, move the ip from the return address after the + * instruction "lui v1, hi_16bit_of_mcount"(offset is 24), but for + * kernel, move after the instruction "move ra, at"(offset is 16) */ - ip = self_addr - (in_module(self_addr) ? 20 : 12); + ip = self_ra - (in_kernel_space(self_ra) ? 16 : 24); /* * search the text until finding the non-store instruction or "s{d,w} * ra, offset(sp)" instruction */ do { - ip -= 4; - /* get the code at "ip": code = *(unsigned int *)ip; */ safe_load_code(code, ip, faulted); @@ -224,18 +226,20 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr, * store the ra on the stack */ if ((code & S_R_SP) != S_R_SP) - return parent_addr; + return parent_ra_addr; - } while (((code & S_RA_SP) != S_RA_SP)); + /* Move to the next instruction */ + ip -= 4; + } while ((code & S_RA_SP) != S_RA_SP); sp = fp + (code & OFFSET_MASK); - /* ra = *(unsigned long *)sp; */ - safe_load_stack(ra, sp, faulted); + /* tmp = *(unsigned long *)sp; */ + safe_load_stack(tmp, sp, faulted); if (unlikely(faulted)) return 0; - if (ra == parent) + if (tmp == old_parent_ra) return sp; return 0; } @@ -246,21 +250,21 @@ unsigned long ftrace_get_parent_addr(unsigned long self_addr, * Hook the return address and push it in the stack of return addrs * in current thread info. */ -void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, +void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, unsigned long fp) { - unsigned long old; + unsigned long old_parent_ra; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; - int faulted; + int faulted, insns; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; /* - * "parent" is the stack address saved the return address of the caller - * of _mcount. + * "parent_ra_addr" is the stack address saved the return address of + * the caller of _mcount. * * if the gcc < 4.5, a leaf function does not save the return address * in the stack address, so, we "emulate" one in _mcount's stack space, @@ -275,37 +279,44 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, * do it in ftrace_graph_caller of mcount.S. */ - /* old = *parent; */ - safe_load_stack(old, parent, faulted); + /* old_parent_ra = *parent_ra_addr; */ + safe_load_stack(old_parent_ra, parent_ra_addr, faulted); if (unlikely(faulted)) goto out; #ifndef KBUILD_MCOUNT_RA_ADDRESS - parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old, - (unsigned long)parent, fp); + parent_ra_addr = (unsigned long *)ftrace_get_parent_ra_addr(self_ra, + old_parent_ra, (unsigned long)parent_ra_addr, fp); /* * If fails when getting the stack address of the non-leaf function's * ra, stop function graph tracer and return */ - if (parent == 0) + if (parent_ra_addr == 0) goto out; #endif - /* *parent = return_hooker; */ - safe_store_stack(return_hooker, parent, faulted); + /* *parent_ra_addr = return_hooker; */ + safe_store_stack(return_hooker, parent_ra_addr, faulted); if (unlikely(faulted)) goto out; - if (ftrace_push_return_trace(old, self_addr, &trace.depth, fp) == - -EBUSY) { - *parent = old; + if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp) + == -EBUSY) { + *parent_ra_addr = old_parent_ra; return; } - trace.func = self_addr; + /* + * Get the recorded ip of the current mcount calling site in the + * __mcount_loc section, which will be used to filter the function + * entries configured through the tracing/set_graph_function interface. + */ + + insns = in_kernel_space(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; + trace.func = self_ra - (MCOUNT_INSN_SIZE * insns); /* Only trace if the calling function expects to */ if (!ftrace_graph_entry(&trace)) { current->curr_ret_stack--; - *parent = old; + *parent_ra_addr = old_parent_ra; } return; out: diff --git a/arch/mips/kernel/perf_event.c b/arch/mips/kernel/perf_event.c index 2b7f3f7..a824485 100644 --- a/arch/mips/kernel/perf_event.c +++ b/arch/mips/kernel/perf_event.c @@ -161,41 +161,6 @@ mipspmu_event_set_period(struct perf_event *event, return ret; } -static int mipspmu_enable(struct perf_event *event) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; - int idx; - int err = 0; - - /* To look for a free counter for this event. */ - idx = mipspmu->alloc_counter(cpuc, hwc); - if (idx < 0) { - err = idx; - goto out; - } - - /* - * If there is an event in the counter we are going to use then - * make sure it is disabled. - */ - event->hw.idx = idx; - mipspmu->disable_event(idx); - cpuc->events[idx] = event; - - /* Set the period for the event. */ - mipspmu_event_set_period(event, hwc, idx); - - /* Enable the event. */ - mipspmu->enable_event(hwc, idx); - - /* Propagate our changes to the userspace mapping. */ - perf_event_update_userpage(event); - -out: - return err; -} - static void mipspmu_event_update(struct perf_event *event, struct hw_perf_event *hwc, int idx) @@ -204,7 +169,7 @@ static void mipspmu_event_update(struct perf_event *event, unsigned long flags; int shift = 64 - TOTAL_BITS; s64 prev_raw_count, new_raw_count; - s64 delta; + u64 delta; again: prev_raw_count = local64_read(&hwc->prev_count); @@ -231,32 +196,90 @@ again: return; } -static void mipspmu_disable(struct perf_event *event) +static void mipspmu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!mipspmu) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + + hwc->state = 0; + + /* Set the period for the event. */ + mipspmu_event_set_period(event, hwc, hwc->idx); + + /* Enable the event. */ + mipspmu->enable_event(hwc, hwc->idx); +} + +static void mipspmu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!mipspmu) + return; + + if (!(hwc->state & PERF_HES_STOPPED)) { + /* We are working on a local event. */ + mipspmu->disable_event(hwc->idx); + barrier(); + mipspmu_event_update(event, hwc, hwc->idx); + hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + } +} + +static int mipspmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; + int idx; + int err = 0; + perf_pmu_disable(event->pmu); - WARN_ON(idx < 0 || idx >= mipspmu->num_counters); + /* To look for a free counter for this event. */ + idx = mipspmu->alloc_counter(cpuc, hwc); + if (idx < 0) { + err = idx; + goto out; + } - /* We are working on a local event. */ + /* + * If there is an event in the counter we are going to use then + * make sure it is disabled. + */ + event->hw.idx = idx; mipspmu->disable_event(idx); + cpuc->events[idx] = event; - barrier(); - - mipspmu_event_update(event, hwc, idx); - cpuc->events[idx] = NULL; - clear_bit(idx, cpuc->used_mask); + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + if (flags & PERF_EF_START) + mipspmu_start(event, PERF_EF_RELOAD); + /* Propagate our changes to the userspace mapping. */ perf_event_update_userpage(event); + +out: + perf_pmu_enable(event->pmu); + return err; } -static void mipspmu_unthrottle(struct perf_event *event) +static void mipspmu_del(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; - mipspmu->enable_event(hwc, hwc->idx); + WARN_ON(idx < 0 || idx >= mipspmu->num_counters); + + mipspmu_stop(event, PERF_EF_UPDATE); + cpuc->events[idx] = NULL; + clear_bit(idx, cpuc->used_mask); + + perf_event_update_userpage(event); } static void mipspmu_read(struct perf_event *event) @@ -270,12 +293,17 @@ static void mipspmu_read(struct perf_event *event) mipspmu_event_update(event, hwc, hwc->idx); } -static struct pmu pmu = { - .enable = mipspmu_enable, - .disable = mipspmu_disable, - .unthrottle = mipspmu_unthrottle, - .read = mipspmu_read, -}; +static void mipspmu_enable(struct pmu *pmu) +{ + if (mipspmu) + mipspmu->start(); +} + +static void mipspmu_disable(struct pmu *pmu) +{ + if (mipspmu) + mipspmu->stop(); +} static atomic_t active_events = ATOMIC_INIT(0); static DEFINE_MUTEX(pmu_reserve_mutex); @@ -318,6 +346,82 @@ static void mipspmu_free_irq(void) perf_irq = save_perf_irq; } +/* + * mipsxx/rm9000/loongson2 have different performance counters, they have + * specific low-level init routines. + */ +static void reset_counters(void *arg); +static int __hw_perf_event_init(struct perf_event *event); + +static void hw_perf_event_destroy(struct perf_event *event) +{ + if (atomic_dec_and_mutex_lock(&active_events, + &pmu_reserve_mutex)) { + /* + * We must not call the destroy function with interrupts + * disabled. + */ + on_each_cpu(reset_counters, + (void *)(long)mipspmu->num_counters, 1); + mipspmu_free_irq(); + mutex_unlock(&pmu_reserve_mutex); + } +} + +static int mipspmu_event_init(struct perf_event *event) +{ + int err = 0; + + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + break; + + default: + return -ENOENT; + } + + if (!mipspmu || event->cpu >= nr_cpumask_bits || + (event->cpu >= 0 && !cpu_online(event->cpu))) + return -ENODEV; + + if (!atomic_inc_not_zero(&active_events)) { + if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) { + atomic_dec(&active_events); + return -ENOSPC; + } + + mutex_lock(&pmu_reserve_mutex); + if (atomic_read(&active_events) == 0) + err = mipspmu_get_irq(); + + if (!err) + atomic_inc(&active_events); + mutex_unlock(&pmu_reserve_mutex); + } + + if (err) + return err; + + err = __hw_perf_event_init(event); + if (err) + hw_perf_event_destroy(event); + + return err; +} + +static struct pmu pmu = { + .pmu_enable = mipspmu_enable, + .pmu_disable = mipspmu_disable, + .event_init = mipspmu_event_init, + .add = mipspmu_add, + .del = mipspmu_del, + .start = mipspmu_start, + .stop = mipspmu_stop, + .read = mipspmu_read, +}; + static inline unsigned int mipspmu_perf_event_encode(const struct mips_perf_event *pev) { @@ -382,8 +486,9 @@ static int validate_event(struct cpu_hw_events *cpuc, { struct hw_perf_event fake_hwc = event->hw; - if (event->pmu && event->pmu != &pmu) - return 0; + /* Allow mixed event group. So return 1 to pass validation. */ + if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF) + return 1; return mipspmu->alloc_counter(cpuc, &fake_hwc) >= 0; } @@ -409,73 +514,6 @@ static int validate_group(struct perf_event *event) return 0; } -/* - * mipsxx/rm9000/loongson2 have different performance counters, they have - * specific low-level init routines. - */ -static void reset_counters(void *arg); -static int __hw_perf_event_init(struct perf_event *event); - -static void hw_perf_event_destroy(struct perf_event *event) -{ - if (atomic_dec_and_mutex_lock(&active_events, - &pmu_reserve_mutex)) { - /* - * We must not call the destroy function with interrupts - * disabled. - */ - on_each_cpu(reset_counters, - (void *)(long)mipspmu->num_counters, 1); - mipspmu_free_irq(); - mutex_unlock(&pmu_reserve_mutex); - } -} - -const struct pmu *hw_perf_event_init(struct perf_event *event) -{ - int err = 0; - - if (!mipspmu || event->cpu >= nr_cpumask_bits || - (event->cpu >= 0 && !cpu_online(event->cpu))) - return ERR_PTR(-ENODEV); - - if (!atomic_inc_not_zero(&active_events)) { - if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) { - atomic_dec(&active_events); - return ERR_PTR(-ENOSPC); - } - - mutex_lock(&pmu_reserve_mutex); - if (atomic_read(&active_events) == 0) - err = mipspmu_get_irq(); - - if (!err) - atomic_inc(&active_events); - mutex_unlock(&pmu_reserve_mutex); - } - - if (err) - return ERR_PTR(err); - - err = __hw_perf_event_init(event); - if (err) - hw_perf_event_destroy(event); - - return err ? ERR_PTR(err) : &pmu; -} - -void hw_perf_enable(void) -{ - if (mipspmu) - mipspmu->start(); -} - -void hw_perf_disable(void) -{ - if (mipspmu) - mipspmu->stop(); -} - /* This is needed by specific irq handlers in perf_event_*.c */ static void handle_associated_event(struct cpu_hw_events *cpuc, @@ -496,21 +534,13 @@ handle_associated_event(struct cpu_hw_events *cpuc, #include "perf_event_mipsxx.c" /* Callchain handling code. */ -static inline void -callchain_store(struct perf_callchain_entry *entry, - u64 ip) -{ - if (entry->nr < PERF_MAX_STACK_DEPTH) - entry->ip[entry->nr++] = ip; -} /* * Leave userspace callchain empty for now. When we find a way to trace * the user stack callchains, we add here. */ -static void -perf_callchain_user(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void perf_callchain_user(struct perf_callchain_entry *entry, + struct pt_regs *regs) { } @@ -523,23 +553,21 @@ static void save_raw_perf_callchain(struct perf_callchain_entry *entry, while (!kstack_end(sp)) { addr = *sp++; if (__kernel_text_address(addr)) { - callchain_store(entry, addr); + perf_callchain_store(entry, addr); if (entry->nr >= PERF_MAX_STACK_DEPTH) break; } } } -static void -perf_callchain_kernel(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned long sp = regs->regs[29]; #ifdef CONFIG_KALLSYMS unsigned long ra = regs->regs[31]; unsigned long pc = regs->cp0_epc; - callchain_store(entry, PERF_CONTEXT_KERNEL); if (raw_show_trace || !__kernel_text_address(pc)) { unsigned long stack_page = (unsigned long)task_stack_page(current); @@ -549,53 +577,12 @@ perf_callchain_kernel(struct pt_regs *regs, return; } do { - callchain_store(entry, pc); + perf_callchain_store(entry, pc); if (entry->nr >= PERF_MAX_STACK_DEPTH) break; pc = unwind_stack(current, &sp, pc, &ra); } while (pc); #else - callchain_store(entry, PERF_CONTEXT_KERNEL); save_raw_perf_callchain(entry, sp); #endif } - -static void -perf_do_callchain(struct pt_regs *regs, - struct perf_callchain_entry *entry) -{ - int is_user; - - if (!regs) - return; - - is_user = user_mode(regs); - - if (!current || !current->pid) - return; - - if (is_user && current->state != TASK_RUNNING) - return; - - if (!is_user) { - perf_callchain_kernel(regs, entry); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; - } - if (regs) - perf_callchain_user(regs, entry); -} - -static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); - -struct perf_callchain_entry * -perf_callchain(struct pt_regs *regs) -{ - struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry); - - entry->nr = 0; - perf_do_callchain(regs, entry); - return entry; -} diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 183e0d2..d9a7db7 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -696,7 +696,7 @@ static int mipsxx_pmu_handle_shared_irq(void) * interrupt, not NMI. */ if (handled == IRQ_HANDLED) - perf_event_do_pending(); + irq_work_run(); #ifdef CONFIG_MIPS_MT_SMP read_unlock(&pmuint_rwlock); @@ -1045,6 +1045,8 @@ init_hw_perf_events(void) "CPU, irq %d%s\n", mipspmu->name, counters, irq, irq < 0 ? " (share with timer interrupt)" : ""); + perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW); + return 0; } early_initcall(init_hw_perf_events); diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 5922342..dbbe0ce 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -84,7 +84,7 @@ static int protected_save_fp_context(struct sigcontext __user *sc) static int protected_restore_fp_context(struct sigcontext __user *sc) { - int err, tmp; + int err, tmp __maybe_unused; while (1) { lock_fpu_owner(); own_fpu_inatomic(0); diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c index a0ed0e0..aae9866 100644 --- a/arch/mips/kernel/signal32.c +++ b/arch/mips/kernel/signal32.c @@ -115,7 +115,7 @@ static int protected_save_fp_context32(struct sigcontext32 __user *sc) static int protected_restore_fp_context32(struct sigcontext32 __user *sc) { - int err, tmp; + int err, tmp __maybe_unused; while (1) { lock_fpu_owner(); own_fpu_inatomic(0); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 383aeb9..32a2561 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -193,6 +193,22 @@ void __devinit smp_prepare_boot_cpu(void) */ static struct task_struct *cpu_idle_thread[NR_CPUS]; +struct create_idle { + struct work_struct work; + struct task_struct *idle; + struct completion done; + int cpu; +}; + +static void __cpuinit do_fork_idle(struct work_struct *work) +{ + struct create_idle *c_idle = + container_of(work, struct create_idle, work); + + c_idle->idle = fork_idle(c_idle->cpu); + complete(&c_idle->done); +} + int __cpuinit __cpu_up(unsigned int cpu) { struct task_struct *idle; @@ -203,8 +219,19 @@ int __cpuinit __cpu_up(unsigned int cpu) * Linux can schedule processes on this slave. */ if (!cpu_idle_thread[cpu]) { - idle = fork_idle(cpu); - cpu_idle_thread[cpu] = idle; + /* + * Schedule work item to avoid forking user task + * Ported from arch/x86/kernel/smpboot.c + */ + struct create_idle c_idle = { + .cpu = cpu, + .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done), + }; + + INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle); + schedule_work(&c_idle.work); + wait_for_completion(&c_idle.done); + idle = cpu_idle_thread[cpu] = c_idle.idle; if (IS_ERR(idle)) panic(KERN_ERR "Fork failed for CPU %d", cpu); diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 1dc6edf..58beabf 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -383,12 +383,11 @@ save_static_function(sys_sysmips); static int __used noinline _sys_sysmips(nabi_no_regargs struct pt_regs regs) { - long cmd, arg1, arg2, arg3; + long cmd, arg1, arg2; cmd = regs.regs[4]; arg1 = regs.regs[5]; arg2 = regs.regs[6]; - arg3 = regs.regs[7]; switch (cmd) { case MIPS_ATOMIC_SET: @@ -405,7 +404,7 @@ _sys_sysmips(nabi_no_regargs struct pt_regs regs) if (arg1 & 2) set_thread_flag(TIF_LOGADE); else - clear_thread_flag(TIF_FIXADE); + clear_thread_flag(TIF_LOGADE); return 0; diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 6a1fdfe..ab52b7c 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -148,9 +148,9 @@ struct { spinlock_t tc_list_lock; struct list_head tc_list; /* Thread contexts */ } vpecontrol = { - .vpe_list_lock = SPIN_LOCK_UNLOCKED, + .vpe_list_lock = __SPIN_LOCK_UNLOCKED(vpe_list_lock), .vpe_list = LIST_HEAD_INIT(vpecontrol.vpe_list), - .tc_list_lock = SPIN_LOCK_UNLOCKED, + .tc_list_lock = __SPIN_LOCK_UNLOCKED(tc_list_lock), .tc_list = LIST_HEAD_INIT(vpecontrol.tc_list) }; diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig index 6e1b77f..aca93ee 100644 --- a/arch/mips/loongson/Kconfig +++ b/arch/mips/loongson/Kconfig @@ -1,6 +1,7 @@ +if MACH_LOONGSON + choice prompt "Machine Type" - depends on MACH_LOONGSON config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" @@ -87,3 +88,5 @@ config LOONGSON_UART_BASE config LOONGSON_MC146818 bool default n + +endif # MACH_LOONGSON diff --git a/arch/mips/loongson/common/cmdline.c b/arch/mips/loongson/common/cmdline.c index 1a06def..353e1d2 100644 --- a/arch/mips/loongson/common/cmdline.c +++ b/arch/mips/loongson/common/cmdline.c @@ -44,10 +44,5 @@ void __init prom_init_cmdline(void) strcat(arcs_cmdline, " "); } - if ((strstr(arcs_cmdline, "console=")) == NULL) - strcat(arcs_cmdline, " console=ttyS0,115200"); - if ((strstr(arcs_cmdline, "root=")) == NULL) - strcat(arcs_cmdline, " root=/dev/hda1"); - prom_init_machtype(); } diff --git a/arch/mips/loongson/common/machtype.c b/arch/mips/loongson/common/machtype.c index 81fbe6b..2efd5d9 100644 --- a/arch/mips/loongson/common/machtype.c +++ b/arch/mips/loongson/common/machtype.c @@ -41,7 +41,7 @@ void __weak __init mach_prom_init_machtype(void) void __init prom_init_machtype(void) { - char *p, str[MACHTYPE_LEN]; + char *p, str[MACHTYPE_LEN + 1]; int machtype = MACH_LEMOTE_FL2E; mips_machtype = LOONGSON_MACHTYPE; @@ -53,6 +53,7 @@ void __init prom_init_machtype(void) } p += strlen("machtype="); strncpy(str, p, MACHTYPE_LEN); + str[MACHTYPE_LEN] = '\0'; p = strstr(str, " "); if (p) *p = '\0'; diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h index 2701d95..2a7d43f 100644 --- a/arch/mips/math-emu/ieee754int.h +++ b/arch/mips/math-emu/ieee754int.h @@ -70,7 +70,7 @@ #define COMPXSP \ - unsigned xm; int xe; int xs; int xc + unsigned xm; int xe; int xs __maybe_unused; int xc #define COMPYSP \ unsigned ym; int ye; int ys; int yc @@ -104,7 +104,7 @@ #define COMPXDP \ -u64 xm; int xe; int xs; int xc +u64 xm; int xe; int xs __maybe_unused; int xc #define COMPYDP \ u64 ym; int ye; int ys; int yc diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 2efcbd2..279599e 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -324,7 +324,7 @@ int page_is_ram(unsigned long pagenr) void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; - unsigned long lastpfn; + unsigned long lastpfn __maybe_unused; pagetable_init(); diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 083d341..04f9e17 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -109,6 +109,8 @@ static bool scratchpad_available(void) static int scratchpad_offset(int i) { BUG(); + /* Really unreachable, but evidently some GCC want this. */ + return 0; } #endif /* diff --git a/arch/mips/pci/ops-pmcmsp.c b/arch/mips/pci/ops-pmcmsp.c index b7c03d8..68798f8 100644 --- a/arch/mips/pci/ops-pmcmsp.c +++ b/arch/mips/pci/ops-pmcmsp.c @@ -308,7 +308,7 @@ static struct resource pci_mem_resource = { * RETURNS: PCIBIOS_SUCCESSFUL - success * ****************************************************************************/ -static int bpci_interrupt(int irq, void *dev_id) +static irqreturn_t bpci_interrupt(int irq, void *dev_id) { struct msp_pci_regs *preg = (void *)PCI_BASE_REG; unsigned int stat = preg->if_status; @@ -326,7 +326,7 @@ static int bpci_interrupt(int irq, void *dev_id) /* write to clear all asserted interrupts */ preg->if_status = stat; - return PCIBIOS_SUCCESSFUL; + return IRQ_HANDLED; } /***************************************************************************** diff --git a/arch/mips/pmc-sierra/Kconfig b/arch/mips/pmc-sierra/Kconfig index c139988..8d79849 100644 --- a/arch/mips/pmc-sierra/Kconfig +++ b/arch/mips/pmc-sierra/Kconfig @@ -4,15 +4,11 @@ choice config PMC_MSP4200_EVAL bool "PMC-Sierra MSP4200 Eval Board" - select CEVT_R4K - select CSRC_R4K select IRQ_MSP_SLP select HW_HAS_PCI config PMC_MSP4200_GW bool "PMC-Sierra MSP4200 VoIP Gateway" - select CEVT_R4K - select CSRC_R4K select IRQ_MSP_SLP select HW_HAS_PCI diff --git a/arch/mips/pmc-sierra/msp71xx/msp_time.c b/arch/mips/pmc-sierra/msp71xx/msp_time.c index cca64e1..01df84c 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_time.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_time.c @@ -81,7 +81,7 @@ void __init plat_time_init(void) mips_hpt_frequency = cpu_rate/2; } -unsigned int __init get_c0_compare_int(void) +unsigned int __cpuinit get_c0_compare_int(void) { return MSP_INT_VPE0_TIMER; } diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h index 92d2f92..9d773a6 100644 --- a/arch/mn10300/include/asm/atomic.h +++ b/arch/mn10300/include/asm/atomic.h @@ -139,7 +139,7 @@ static inline unsigned long __cmpxchg(volatile unsigned long *m, * Atomically reads the value of @v. Note that the guaranteed * useful range of an atomic_t is only 24 bits. */ -#define atomic_read(v) ((v)->counter) +#define atomic_read(v) (ACCESS_ONCE((v)->counter)) /** * atomic_set - set atomic variable diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h index 679dee0..3d6e60d 100644 --- a/arch/mn10300/include/asm/uaccess.h +++ b/arch/mn10300/include/asm/uaccess.h @@ -160,9 +160,10 @@ struct __large_struct { unsigned long buf[100]; }; #define __get_user_check(x, ptr, size) \ ({ \ + const __typeof__(ptr) __guc_ptr = (ptr); \ int _e; \ - if (likely(__access_ok((unsigned long) (ptr), (size)))) \ - _e = __get_user_nocheck((x), (ptr), (size)); \ + if (likely(__access_ok((unsigned long) __guc_ptr, (size)))) \ + _e = __get_user_nocheck((x), __guc_ptr, (size)); \ else { \ _e = -EFAULT; \ (x) = (__typeof__(x))0; \ diff --git a/arch/mn10300/mm/cache-inv-icache.c b/arch/mn10300/mm/cache-inv-icache.c index a8933a6..a6b63dd 100644 --- a/arch/mn10300/mm/cache-inv-icache.c +++ b/arch/mn10300/mm/cache-inv-icache.c @@ -69,7 +69,7 @@ static void flush_icache_page_range(unsigned long start, unsigned long end) /* invalidate the icache coverage on that region */ mn10300_local_icache_inv_range2(addr + off, size); - smp_cache_call(SMP_ICACHE_INV_FLUSH_RANGE, start, end); + smp_cache_call(SMP_ICACHE_INV_RANGE, start, end); } /** @@ -101,7 +101,7 @@ void flush_icache_range(unsigned long start, unsigned long end) * directly */ start_page = (start >= 0x80000000UL) ? start : 0x80000000UL; mn10300_icache_inv_range(start_page, end); - smp_cache_call(SMP_ICACHE_INV_FLUSH_RANGE, start, end); + smp_cache_call(SMP_ICACHE_INV_RANGE, start, end); if (start_page == start) goto done; end = start_page; diff --git a/arch/parisc/hpux/sys_hpux.c b/arch/parisc/hpux/sys_hpux.c index 3039408..6ab9580 100644 --- a/arch/parisc/hpux/sys_hpux.c +++ b/arch/parisc/hpux/sys_hpux.c @@ -185,26 +185,21 @@ struct hpux_statfs { int16_t f_pad; }; -static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf) +static int do_statfs_hpux(struct kstatfs *st, struct hpux_statfs __user *p) { - struct kstatfs st; - int retval; - - retval = vfs_statfs(path, &st); - if (retval) - return retval; - - memset(buf, 0, sizeof(*buf)); - buf->f_type = st.f_type; - buf->f_bsize = st.f_bsize; - buf->f_blocks = st.f_blocks; - buf->f_bfree = st.f_bfree; - buf->f_bavail = st.f_bavail; - buf->f_files = st.f_files; - buf->f_ffree = st.f_ffree; - buf->f_fsid[0] = st.f_fsid.val[0]; - buf->f_fsid[1] = st.f_fsid.val[1]; - + struct hpux_statfs buf; + memset(&buf, 0, sizeof(buf)); + buf.f_type = st->f_type; + buf.f_bsize = st->f_bsize; + buf.f_blocks = st->f_blocks; + buf.f_bfree = st->f_bfree; + buf.f_bavail = st->f_bavail; + buf.f_files = st->f_files; + buf.f_ffree = st->f_ffree; + buf.f_fsid[0] = st->f_fsid.val[0]; + buf.f_fsid[1] = st->f_fsid.val[1]; + if (copy_to_user(p, &buf, sizeof(buf))) + return -EFAULT; return 0; } @@ -212,35 +207,19 @@ static int do_statfs_hpux(struct path *path, struct hpux_statfs *buf) asmlinkage long hpux_statfs(const char __user *pathname, struct hpux_statfs __user *buf) { - struct path path; - int error; - - error = user_path(pathname, &path); - if (!error) { - struct hpux_statfs tmp; - error = do_statfs_hpux(&path, &tmp); - if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) - error = -EFAULT; - path_put(&path); - } + struct kstatfs st; + int error = user_statfs(pathname, &st); + if (!error) + error = do_statfs_hpux(&st, buf); return error; } asmlinkage long hpux_fstatfs(unsigned int fd, struct hpux_statfs __user * buf) { - struct file *file; - struct hpux_statfs tmp; - int error; - - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = do_statfs_hpux(&file->f_path, &tmp); - if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) - error = -EFAULT; - fput(file); - out: + struct kstatfs st; + int error = fd_statfs(fd, &st); + if (!error) + error = do_statfs_hpux(&st, buf); return error; } diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h index 0c705c3..67a33cc 100644 --- a/arch/parisc/include/asm/futex.h +++ b/arch/parisc/include/asm/futex.h @@ -8,7 +8,7 @@ #include <asm/errno.h> static inline int -futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -18,7 +18,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -51,10 +51,10 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) /* Non-atomic version */ static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - int err = 0; - int uval; + u32 val; /* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is * our gateway page, and causes no end of trouble... @@ -62,15 +62,15 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) if (segment_eq(KERNEL_DS, get_fs()) && !uaddr) return -EFAULT; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - err = get_user(uval, uaddr); - if (err) return -EFAULT; - if (uval == oldval) - err = put_user(newval, uaddr); - if (err) return -EFAULT; - return uval; + if (get_user(val, uaddr)) + return -EFAULT; + if (val == oldval && put_user(newval, uaddr)) + return -EFAULT; + *uval = val; + return 0; } #endif /*__KERNEL__*/ diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index 7c589ef..c94e4a3 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -30,7 +30,7 @@ : "b" (uaddr), "i" (-EFAULT), "r" (oparg) \ : "cr0", "memory") -static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -40,7 +40,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -82,35 +82,38 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - int prev; + int ret = 0; + u32 prev; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; __asm__ __volatile__ ( PPC_RELEASE_BARRIER -"1: lwarx %0,0,%2 # futex_atomic_cmpxchg_inatomic\n\ - cmpw 0,%0,%3\n\ +"1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\ + cmpw 0,%1,%4\n\ bne- 3f\n" - PPC405_ERR77(0,%2) -"2: stwcx. %4,0,%2\n\ + PPC405_ERR77(0,%3) +"2: stwcx. %5,0,%3\n\ bne- 1b\n" PPC_ACQUIRE_BARRIER "3: .section .fixup,\"ax\"\n\ -4: li %0,%5\n\ +4: li %0,%6\n\ b 3b\n\ .previous\n\ .section __ex_table,\"a\"\n\ .align 3\n\ " PPC_LONG "1b,4b,2b,4b\n\ .previous" \ - : "=&r" (prev), "+m" (*uaddr) + : "+r" (ret), "=&r" (prev), "+m" (*uaddr) : "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT) : "cc", "memory"); - return prev; + *uval = prev; + return ret; } #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 380d48b..26b8c80 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -33,9 +33,25 @@ // //---------------------------------------------------------------------------- #include <linux/cache.h> +#include <linux/threads.h> #include <asm/types.h> #include <asm/mmu.h> +/* + * We only have to have statically allocated lppaca structs on + * legacy iSeries, which supports at most 64 cpus. + */ +#ifdef CONFIG_PPC_ISERIES +#if NR_CPUS < 64 +#define NR_LPPACAS NR_CPUS +#else +#define NR_LPPACAS 64 +#endif +#else /* not iSeries */ +#define NR_LPPACAS 1 +#endif + + /* The Hypervisor barfs if the lppaca crosses a page boundary. A 1k * alignment is sufficient to prevent this */ struct lppaca { diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 991d599..fe56a23 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -240,6 +240,12 @@ struct machdep_calls { * claims to support kexec. */ int (*machine_kexec_prepare)(struct kimage *image); + + /* Called to perform the _real_ kexec. + * Do NOT allocate memory or fail here. We are past the point of + * no return. + */ + void (*machine_kexec)(struct kimage *image); #endif /* CONFIG_KEXEC */ #ifdef CONFIG_SUSPEND diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h index 8eaed81..17194fc 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/mmu-book3e.h @@ -40,8 +40,8 @@ /* MAS registers bit definitions */ -#define MAS0_TLBSEL(x) ((x << 28) & 0x30000000) -#define MAS0_ESEL(x) ((x << 16) & 0x0FFF0000) +#define MAS0_TLBSEL(x) (((x) << 28) & 0x30000000) +#define MAS0_ESEL(x) (((x) << 16) & 0x0FFF0000) #define MAS0_NV(x) ((x) & 0x00000FFF) #define MAS0_HES 0x00004000 #define MAS0_WQ_ALLWAYS 0x00000000 @@ -50,12 +50,12 @@ #define MAS1_VALID 0x80000000 #define MAS1_IPROT 0x40000000 -#define MAS1_TID(x) ((x << 16) & 0x3FFF0000) +#define MAS1_TID(x) (((x) << 16) & 0x3FFF0000) #define MAS1_IND 0x00002000 #define MAS1_TS 0x00001000 #define MAS1_TSIZE_MASK 0x00000f80 #define MAS1_TSIZE_SHIFT 7 -#define MAS1_TSIZE(x) ((x << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK) +#define MAS1_TSIZE(x) (((x) << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK) #define MAS2_EPN 0xFFFFF000 #define MAS2_X0 0x00000040 diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 53b64be..da4b200 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -101,7 +101,7 @@ extern phys_addr_t kernstart_addr; #ifdef CONFIG_FLATMEM #define ARCH_PFN_OFFSET (MEMORY_START >> PAGE_SHIFT) -#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr)) +#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < max_mapnr) #endif #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h index 8447d89..bb1e2cd 100644 --- a/arch/powerpc/include/asm/rwsem.h +++ b/arch/powerpc/include/asm/rwsem.h @@ -13,11 +13,6 @@ * by Paul Mackerras <paulus@samba.org>. */ -#include <linux/list.h> -#include <linux/spinlock.h> -#include <asm/atomic.h> -#include <asm/system.h> - /* * the semaphore definition */ @@ -33,47 +28,6 @@ #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) -struct rw_semaphore { - long count; - spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - -#define __RWSEM_INITIALIZER(name) \ -{ \ - RWSEM_UNLOCKED_VALUE, \ - __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) \ - __RWSEM_DEP_MAP_INIT(name) \ -} - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ - do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ - } while (0) - /* * lock for reading */ @@ -174,10 +128,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) return atomic_long_add_return(delta, (atomic_long_t *)&sem->count); } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return sem->count != 0; -} - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_RWSEM_H */ diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index 55cba4a..f8cd9fb 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -18,7 +18,7 @@ #include <asm/mmu.h> _GLOBAL(__setup_cpu_603) - mflr r4 + mflr r5 BEGIN_MMU_FTR_SECTION li r10,0 mtspr SPRN_SPRG_603_LRU,r10 /* init SW LRU tracking */ @@ -27,60 +27,60 @@ BEGIN_FTR_SECTION bl __init_fpu_registers END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE) bl setup_common_caches - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_604) - mflr r4 + mflr r5 bl setup_common_caches bl setup_604_hid0 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_750) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_common_caches bl setup_750_7400_hid0 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_750cx) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_common_caches bl setup_750_7400_hid0 bl setup_750cx - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_750fx) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_common_caches bl setup_750_7400_hid0 bl setup_750fx - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_7400) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_7400_workarounds bl setup_common_caches bl setup_750_7400_hid0 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_7410) - mflr r4 + mflr r5 bl __init_fpu_registers bl setup_7410_workarounds bl setup_common_caches bl setup_750_7400_hid0 li r3,0 mtspr SPRN_L2CR2,r3 - mtlr r4 + mtlr r5 blr _GLOBAL(__setup_cpu_745x) - mflr r4 + mflr r5 bl setup_common_caches bl setup_745x_specifics - mtlr r4 + mtlr r5 blr /* Enable caches for 603's, 604, 750 & 7400 */ @@ -194,10 +194,10 @@ setup_750cx: cror 4*cr0+eq,4*cr0+eq,4*cr1+eq cror 4*cr0+eq,4*cr0+eq,4*cr2+eq bnelr - lwz r6,CPU_SPEC_FEATURES(r5) + lwz r6,CPU_SPEC_FEATURES(r4) li r7,CPU_FTR_CAN_NAP andc r6,r6,r7 - stw r6,CPU_SPEC_FEATURES(r5) + stw r6,CPU_SPEC_FEATURES(r4) blr /* 750fx specific @@ -225,12 +225,12 @@ BEGIN_FTR_SECTION andis. r11,r11,L3CR_L3E@h beq 1f END_FTR_SECTION_IFSET(CPU_FTR_L3CR) - lwz r6,CPU_SPEC_FEATURES(r5) + lwz r6,CPU_SPEC_FEATURES(r4) andi. r0,r6,CPU_FTR_L3_DISABLE_NAP beq 1f li r7,CPU_FTR_CAN_NAP andc r6,r6,r7 - stw r6,CPU_SPEC_FEATURES(r5) + stw r6,CPU_SPEC_FEATURES(r4) 1: mfspr r11,SPRN_HID0 diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 8d74a24..e8e915c 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -2076,8 +2076,8 @@ static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s) * pointer on ppc64 and booke as we are running at 0 in real mode * on ppc64 and reloc_offset is always 0 on booke. */ - if (s->cpu_setup) { - s->cpu_setup(offset, s); + if (t->cpu_setup) { + t->cpu_setup(offset, t); } #endif /* CONFIG_PPC64 || CONFIG_BOOKE */ } diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 49a170a..a5f8672 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -87,7 +87,10 @@ void machine_kexec(struct kimage *image) save_ftrace_enabled = __ftrace_enabled_save(); - default_machine_kexec(image); + if (ppc_md.machine_kexec) + ppc_md.machine_kexec(image); + else + default_machine_kexec(image); __ftrace_enabled_restore(save_ftrace_enabled); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index ebf9846..f4adf89 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -27,20 +27,6 @@ extern unsigned long __toc_start; #ifdef CONFIG_PPC_BOOK3S /* - * We only have to have statically allocated lppaca structs on - * legacy iSeries, which supports at most 64 cpus. - */ -#ifdef CONFIG_PPC_ISERIES -#if NR_CPUS < 64 -#define NR_LPPACAS NR_CPUS -#else -#define NR_LPPACAS 64 -#endif -#else /* not iSeries */ -#define NR_LPPACAS 1 -#endif - -/* * The structure which the hypervisor knows about - this structure * should not cross a page boundary. The vpa_init/register_vpa call * is now known to fail if the lppaca structure crosses a page diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7a1d5cb..8303a6c 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -353,6 +353,7 @@ static void switch_booke_debug_regs(struct thread_struct *new_thread) prime_debug_regs(new_thread); } #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ +#ifndef CONFIG_HAVE_HW_BREAKPOINT static void set_debug_reg_defaults(struct thread_struct *thread) { if (thread->dabr) { @@ -360,6 +361,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread) set_dabr(0); } } +#endif /* !CONFIG_HAVE_HW_BREAKPOINT */ #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ int set_dabr(unsigned long dabr) @@ -670,11 +672,11 @@ void flush_thread(void) { discard_lazy_cpu_state(); -#ifdef CONFIG_HAVE_HW_BREAKPOINTS +#ifdef CONFIG_HAVE_HW_BREAKPOINT flush_ptrace_hw_breakpoint(current); -#else /* CONFIG_HAVE_HW_BREAKPOINTS */ +#else /* CONFIG_HAVE_HW_BREAKPOINT */ set_debug_reg_defaults(¤t->thread); -#endif /* CONFIG_HAVE_HW_BREAKPOINTS */ +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ } void diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index bf5cb91..0dc95c0 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -186,7 +186,7 @@ static void unmap_cpu_from_node(unsigned long cpu) dbg("removing cpu %lu from node %d\n", cpu, node); if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) { - cpumask_set_cpu(cpu, node_to_cpumask_map[node]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[node]); } else { printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n", cpu, node); @@ -1289,10 +1289,9 @@ u64 memory_hotplug_max(void) } #endif /* CONFIG_MEMORY_HOTPLUG */ -/* Vrtual Processor Home Node (VPHN) support */ +/* Virtual Processor Home Node (VPHN) support */ #ifdef CONFIG_PPC_SPLPAR -#define VPHN_NR_CHANGE_CTRS (8) -static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS]; +static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS]; static cpumask_t cpu_associativity_changes_mask; static int vphn_enabled; static void set_topology_timer(void); @@ -1303,16 +1302,18 @@ static void set_topology_timer(void); */ static void setup_cpu_associativity_change_counters(void) { - int cpu = 0; + int cpu; + + /* The VPHN feature supports a maximum of 8 reference points */ + BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8); for_each_possible_cpu(cpu) { - int i = 0; + int i; u8 *counts = vphn_cpu_change_counts[cpu]; volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts; - for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) { + for (i = 0; i < distance_ref_points_depth; i++) counts[i] = hypervisor_counts[i]; - } } } @@ -1329,7 +1330,7 @@ static void setup_cpu_associativity_change_counters(void) */ static int update_cpu_associativity_changes_mask(void) { - int cpu = 0, nr_cpus = 0; + int cpu, nr_cpus = 0; cpumask_t *changes = &cpu_associativity_changes_mask; cpumask_clear(changes); @@ -1339,8 +1340,8 @@ static int update_cpu_associativity_changes_mask(void) u8 *counts = vphn_cpu_change_counts[cpu]; volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts; - for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) { - if (hypervisor_counts[i] > counts[i]) { + for (i = 0; i < distance_ref_points_depth; i++) { + if (hypervisor_counts[i] != counts[i]) { counts[i] = hypervisor_counts[i]; changed = 1; } @@ -1354,8 +1355,11 @@ static int update_cpu_associativity_changes_mask(void) return nr_cpus; } -/* 6 64-bit registers unpacked into 12 32-bit associativity values */ -#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32)) +/* + * 6 64-bit registers unpacked into 12 32-bit associativity values. To form + * the complete property we have to add the length in the first cell. + */ +#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32) + 1) /* * Convert the associativity domain numbers returned from the hypervisor @@ -1363,15 +1367,14 @@ static int update_cpu_associativity_changes_mask(void) */ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked) { - int i = 0; - int nr_assoc_doms = 0; + int i, nr_assoc_doms = 0; const u16 *field = (const u16*) packed; #define VPHN_FIELD_UNUSED (0xffff) #define VPHN_FIELD_MSB (0x8000) #define VPHN_FIELD_MASK (~VPHN_FIELD_MSB) - for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) { + for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) { if (*field == VPHN_FIELD_UNUSED) { /* All significant fields processed, and remaining * fields contain the reserved value of all 1's. @@ -1379,14 +1382,12 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked) */ unpacked[i] = *((u32*)field); field += 2; - } - else if (*field & VPHN_FIELD_MSB) { + } else if (*field & VPHN_FIELD_MSB) { /* Data is in the lower 15 bits of this field */ unpacked[i] = *field & VPHN_FIELD_MASK; field++; nr_assoc_doms++; - } - else { + } else { /* Data is in the lower 15 bits of this field * concatenated with the next 16 bit field */ @@ -1396,6 +1397,9 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked) } } + /* The first cell contains the length of the property */ + unpacked[0] = nr_assoc_doms; + return nr_assoc_doms; } @@ -1405,7 +1409,7 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked) */ static long hcall_vphn(unsigned long cpu, unsigned int *associativity) { - long rc = 0; + long rc; long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; u64 flags = 1; int hwcpu = get_hard_smp_processor_id(cpu); @@ -1419,7 +1423,7 @@ static long hcall_vphn(unsigned long cpu, unsigned int *associativity) static long vphn_get_associativity(unsigned long cpu, unsigned int *associativity) { - long rc = 0; + long rc; rc = hcall_vphn(cpu, associativity); @@ -1445,9 +1449,9 @@ static long vphn_get_associativity(unsigned long cpu, */ int arch_update_cpu_topology(void) { - int cpu = 0, nid = 0, old_nid = 0; + int cpu, nid, old_nid; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; - struct sys_device *sysdev = NULL; + struct sys_device *sysdev; for_each_cpu_mask(cpu, cpu_associativity_changes_mask) { vphn_get_associativity(cpu, associativity); @@ -1512,7 +1516,9 @@ int start_topology_update(void) { int rc = 0; - if (firmware_has_feature(FW_FEATURE_VPHN)) { + /* Disabled until races with load balancing are fixed */ + if (0 && firmware_has_feature(FW_FEATURE_VPHN) && + get_lppaca()->shared_proc) { vphn_enabled = 1; setup_cpu_associativity_change_counters(); init_timer_deferrable(&topology_timer); diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 1ec0657..c14d09f 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -38,13 +38,11 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); * neesd to be flushed. This function will either perform the flush * immediately or will batch it up if the current CPU has an active * batch on it. - * - * Must be called from within some kind of spinlock/non-preempt region... */ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pte, int huge) { - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch); unsigned long vsid, vaddr; unsigned int psize; int ssize; @@ -99,6 +97,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, */ if (!batch->active) { flush_hash_page(vaddr, rpte, psize, ssize, 0); + put_cpu_var(ppc64_tlb_batch); return; } @@ -127,6 +126,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, batch->index = ++i; if (i >= PPC64_TLB_BATCH_NR) __flush_tlb_pending(batch); + put_cpu_var(ppc64_tlb_batch); } /* diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c index 187a7d3..a3d2ce5 100644 --- a/arch/powerpc/platforms/cell/spufs/syscalls.c +++ b/arch/powerpc/platforms/cell/spufs/syscalls.c @@ -70,7 +70,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags, if (!IS_ERR(tmp)) { struct nameidata nd; - ret = path_lookup(tmp, LOOKUP_PARENT, &nd); + ret = kern_path_parent(tmp, &nd); if (!ret) { nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE; ret = spufs_create(&nd, flags, mode, neighbor); diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c index fdb7384..f0491cc 100644 --- a/arch/powerpc/platforms/iseries/dt.c +++ b/arch/powerpc/platforms/iseries/dt.c @@ -242,8 +242,8 @@ static void __init dt_cpus(struct iseries_flat_dt *dt) pft_size[0] = 0; /* NUMA CEC cookie, 0 for non NUMA */ pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE); - for (i = 0; i < NR_CPUS; i++) { - if (lppaca_of(i).dyn_proc_status >= 2) + for (i = 0; i < NR_LPPACAS; i++) { + if (lppaca[i].dyn_proc_status >= 2) continue; snprintf(p, 32 - (p - buf), "@%d", i); @@ -251,7 +251,7 @@ static void __init dt_cpus(struct iseries_flat_dt *dt) dt_prop_str(dt, "device_type", device_type_cpu); - index = lppaca_of(i).dyn_hv_phys_proc_index; + index = lppaca[i].dyn_hv_phys_proc_index; d = &xIoHriProcessorVpd[index]; dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024); diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index b086341..2946ae1 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -680,6 +680,7 @@ void * __init iSeries_early_setup(void) * on but calling this function multiple times is fine. */ identify_cpu(0, mfspr(SPRN_PVR)); + initialise_paca(&boot_paca, 0); powerpc_firmware_features |= FW_FEATURE_ISERIES; powerpc_firmware_features |= FW_FEATURE_LPAR; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 5d3ea9f..ca5d589 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -713,6 +713,13 @@ EXPORT_SYMBOL(arch_free_page); /* NB: reg/unreg are called while guarded with the tracepoints_mutex */ extern long hcall_tracepoint_refcount; +/* + * Since the tracing code might execute hcalls we need to guard against + * recursion. One example of this are spinlocks calling H_YIELD on + * shared processor partitions. + */ +static DEFINE_PER_CPU(unsigned int, hcall_trace_depth); + void hcall_tracepoint_regfunc(void) { hcall_tracepoint_refcount++; @@ -725,12 +732,42 @@ void hcall_tracepoint_unregfunc(void) void __trace_hcall_entry(unsigned long opcode, unsigned long *args) { + unsigned long flags; + unsigned int *depth; + + local_irq_save(flags); + + depth = &__get_cpu_var(hcall_trace_depth); + + if (*depth) + goto out; + + (*depth)++; trace_hcall_entry(opcode, args); + (*depth)--; + +out: + local_irq_restore(flags); } void __trace_hcall_exit(long opcode, unsigned long retval, unsigned long *retbuf) { + unsigned long flags; + unsigned int *depth; + + local_irq_save(flags); + + depth = &__get_cpu_var(hcall_trace_depth); + + if (*depth) + goto out; + + (*depth)++; trace_hcall_exit(opcode, retval, retbuf); + (*depth)--; + +out: + local_irq_restore(flags); } #endif diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ff19efd..636bcb8 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -406,7 +406,7 @@ config QDIO If unsure, say Y. config CHSC_SCH - def_tristate y + def_tristate m prompt "Support for CHSC subchannels" help This driver allows usage of CHSC subchannels. A CHSC subchannel diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c index 0851eb1..2751b3a 100644 --- a/arch/s390/boot/compressed/misc.c +++ b/arch/s390/boot/compressed/misc.c @@ -133,11 +133,12 @@ unsigned long decompress_kernel(void) unsigned long output_addr; unsigned char *output; - check_ipl_parmblock((void *) 0, (unsigned long) output + SZ__bss_start); + output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL; + check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start); memset(&_bss, 0, &_ebss - &_bss); free_mem_ptr = (unsigned long)&_end; free_mem_end_ptr = free_mem_ptr + HEAP_SIZE; - output = (unsigned char *) ((free_mem_end_ptr + 4095UL) & -4096UL); + output = (unsigned char *) output_addr; #ifdef CONFIG_BLK_DEV_INITRD /* diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index f42dbab..48884f8 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -38,6 +38,7 @@ int s390_sha_update(struct shash_desc *desc, const u8 *data, unsigned int len) BUG_ON(ret != bsize); data += bsize - index; len -= bsize - index; + index = 0; } /* process as many blocks as possible */ diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 76daea1..5c5ba10 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -36,14 +36,19 @@ static inline int atomic_read(const atomic_t *v) { - barrier(); - return v->counter; + int c; + + asm volatile( + " l %0,%1\n" + : "=d" (c) : "Q" (v->counter)); + return c; } static inline void atomic_set(atomic_t *v, int i) { - v->counter = i; - barrier(); + asm volatile( + " st %1,%0\n" + : "=Q" (v->counter) : "d" (i)); } static inline int atomic_add_return(int i, atomic_t *v) @@ -128,14 +133,19 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) static inline long long atomic64_read(const atomic64_t *v) { - barrier(); - return v->counter; + long long c; + + asm volatile( + " lg %0,%1\n" + : "=d" (c) : "Q" (v->counter)); + return c; } static inline void atomic64_set(atomic64_t *v, long long i) { - v->counter = i; - barrier(); + asm volatile( + " stg %1,%0\n" + : "=Q" (v->counter) : "d" (i)); } static inline long long atomic64_add_return(long long i, atomic64_t *v) diff --git a/arch/s390/include/asm/cache.h b/arch/s390/include/asm/cache.h index 24aafa6..2a30d5a 100644 --- a/arch/s390/include/asm/cache.h +++ b/arch/s390/include/asm/cache.h @@ -13,6 +13,7 @@ #define L1_CACHE_BYTES 256 #define L1_CACHE_SHIFT 8 +#define NET_SKB_PAD 32 #define __read_mostly __attribute__((__section__(".data..read_mostly"))) diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h index 405cc97..7e1f776 100644 --- a/arch/s390/include/asm/cacheflush.h +++ b/arch/s390/include/asm/cacheflush.h @@ -1,29 +1,8 @@ #ifndef _S390_CACHEFLUSH_H #define _S390_CACHEFLUSH_H -/* Keep includes the same across arches. */ -#include <linux/mm.h> - /* Caches aren't brain-dead on the s390. */ -#define flush_cache_all() do { } while (0) -#define flush_cache_mm(mm) do { } while (0) -#define flush_cache_dup_mm(mm) do { } while (0) -#define flush_cache_range(vma, start, end) do { } while (0) -#define flush_cache_page(vma, vmaddr, pfn) do { } while (0) -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define flush_dcache_page(page) do { } while (0) -#define flush_dcache_mmap_lock(mapping) do { } while (0) -#define flush_dcache_mmap_unlock(mapping) do { } while (0) -#define flush_icache_range(start, end) do { } while (0) -#define flush_icache_page(vma,pg) do { } while (0) -#define flush_icache_user_range(vma,pg,adr,len) do { } while (0) -#define flush_cache_vmap(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) do { } while (0) - -#define copy_to_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) +#include <asm-generic/cacheflush.h> #ifdef CONFIG_DEBUG_PAGEALLOC void kernel_map_pages(struct page *page, int numpages, int enable); diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index 5c5d02d..81cf36b 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -7,7 +7,7 @@ #include <linux/uaccess.h> #include <asm/errno.h> -static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -18,7 +18,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -39,13 +39,13 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr) return ret; } -static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, - int oldval, int newval) +static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - return uaccess.futex_atomic_cmpxchg(uaddr, oldval, newval); + return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval); } #endif /* __KERNEL__ */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index bf3de04..2c79b64 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -148,11 +148,6 @@ extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); */ extern unsigned long thread_saved_pc(struct task_struct *t); -/* - * Print register of task into buffer. Used in fs/proc/array.c. - */ -extern void task_show_regs(struct seq_file *m, struct task_struct *task); - extern void show_code(struct pt_regs *regs); unsigned long get_wchan(struct task_struct *p); diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h index 423fdda..d0eb465 100644 --- a/arch/s390/include/asm/rwsem.h +++ b/arch/s390/include/asm/rwsem.h @@ -43,29 +43,6 @@ #ifdef __KERNEL__ -#include <linux/list.h> -#include <linux/spinlock.h> - -struct rwsem_waiter; - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_downgrade_write(struct rw_semaphore *); - -/* - * the semaphore definition - */ -struct rw_semaphore { - signed long count; - spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - #ifndef __s390x__ #define RWSEM_UNLOCKED_VALUE 0x00000000 #define RWSEM_ACTIVE_BIAS 0x00000001 @@ -81,41 +58,6 @@ struct rw_semaphore { #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) /* - * initialisation - */ - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait.lock), \ - LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -static inline void init_rwsem(struct rw_semaphore *sem) -{ - sem->count = RWSEM_UNLOCKED_VALUE; - spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ -do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ -} while (0) - - -/* * lock for reading */ static inline void __down_read(struct rw_semaphore *sem) @@ -377,10 +319,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) return new; } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* __KERNEL__ */ #endif /* _S390_RWSEM_H */ diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index f1f644f..9074a54 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -22,6 +22,7 @@ */ #include <linux/mm.h> +#include <linux/pagemap.h> #include <linux/swap.h> #include <asm/processor.h> #include <asm/pgalloc.h> diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index d6b1ed0..2d9ea11f 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -83,8 +83,8 @@ struct uaccess_ops { size_t (*clear_user)(size_t, void __user *); size_t (*strnlen_user)(size_t, const char __user *); size_t (*strncpy_from_user)(size_t, const char __user *, char *); - int (*futex_atomic_op)(int op, int __user *, int oparg, int *old); - int (*futex_atomic_cmpxchg)(int __user *, int old, int new); + int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old); + int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new); }; extern struct uaccess_ops uaccess; diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 5eb78dd..b5a4a73 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -237,43 +237,6 @@ void show_regs(struct pt_regs *regs) show_last_breaking_event(regs); } -/* This is called from fs/proc/array.c */ -void task_show_regs(struct seq_file *m, struct task_struct *task) -{ - struct pt_regs *regs; - - regs = task_pt_regs(task); - seq_printf(m, "task: %p, ksp: %p\n", - task, (void *)task->thread.ksp); - seq_printf(m, "User PSW : %p %p\n", - (void *) regs->psw.mask, (void *)regs->psw.addr); - - seq_printf(m, "User GPRS: " FOURLONG, - regs->gprs[0], regs->gprs[1], - regs->gprs[2], regs->gprs[3]); - seq_printf(m, " " FOURLONG, - regs->gprs[4], regs->gprs[5], - regs->gprs[6], regs->gprs[7]); - seq_printf(m, " " FOURLONG, - regs->gprs[8], regs->gprs[9], - regs->gprs[10], regs->gprs[11]); - seq_printf(m, " " FOURLONG, - regs->gprs[12], regs->gprs[13], - regs->gprs[14], regs->gprs[15]); - seq_printf(m, "User ACRS: %08x %08x %08x %08x\n", - task->thread.acrs[0], task->thread.acrs[1], - task->thread.acrs[2], task->thread.acrs[3]); - seq_printf(m, " %08x %08x %08x %08x\n", - task->thread.acrs[4], task->thread.acrs[5], - task->thread.acrs[6], task->thread.acrs[7]); - seq_printf(m, " %08x %08x %08x %08x\n", - task->thread.acrs[8], task->thread.acrs[9], - task->thread.acrs[10], task->thread.acrs[11]); - seq_printf(m, " %08x %08x %08x %08x\n", - task->thread.acrs[12], task->thread.acrs[13], - task->thread.acrs[14], task->thread.acrs[15]); -} - static DEFINE_SPINLOCK(die_lock); void die(const char * str, struct pt_regs * regs, long err) diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h index 126011d..1d2536c 100644 --- a/arch/s390/lib/uaccess.h +++ b/arch/s390/lib/uaccess.h @@ -12,12 +12,12 @@ extern size_t copy_from_user_std(size_t, const void __user *, void *); extern size_t copy_to_user_std(size_t, void __user *, const void *); extern size_t strnlen_user_std(size_t, const char __user *); extern size_t strncpy_from_user_std(size_t, const char __user *, char *); -extern int futex_atomic_cmpxchg_std(int __user *, int, int); -extern int futex_atomic_op_std(int, int __user *, int, int *); +extern int futex_atomic_cmpxchg_std(u32 *, u32 __user *, u32, u32); +extern int futex_atomic_op_std(int, u32 __user *, int, int *); extern size_t copy_from_user_pt(size_t, const void __user *, void *); extern size_t copy_to_user_pt(size_t, void __user *, const void *); -extern int futex_atomic_op_pt(int, int __user *, int, int *); -extern int futex_atomic_cmpxchg_pt(int __user *, int, int); +extern int futex_atomic_op_pt(int, u32 __user *, int, int *); +extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32); #endif /* __ARCH_S390_LIB_UACCESS_H */ diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 404f2de..7483383 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -302,7 +302,7 @@ fault: : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ "m" (*uaddr) : "cc" ); -static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) +static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) { int oldval = 0, newval, ret; @@ -335,7 +335,7 @@ static int __futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) return ret; } -int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) +int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old) { int ret; @@ -354,26 +354,29 @@ int futex_atomic_op_pt(int op, int __user *uaddr, int oparg, int *old) return ret; } -static int __futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) +static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { int ret; asm volatile("0: cs %1,%4,0(%5)\n" - "1: lr %0,%1\n" + "1: la %0,0\n" "2:\n" EX_TABLE(0b,2b) EX_TABLE(1b,2b) : "=d" (ret), "+d" (oldval), "=m" (*uaddr) : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr) : "cc", "memory" ); + *uval = oldval; return ret; } -int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) +int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { int ret; if (segment_eq(get_fs(), KERNEL_DS)) - return __futex_atomic_cmpxchg_pt(uaddr, oldval, newval); + return __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval); spin_lock(¤t->mm->page_table_lock); uaddr = (int __user *) __dat_user_addr((unsigned long) uaddr); if (!uaddr) { @@ -382,7 +385,7 @@ int futex_atomic_cmpxchg_pt(int __user *uaddr, int oldval, int newval) } get_page(virt_to_page(uaddr)); spin_unlock(¤t->mm->page_table_lock); - ret = __futex_atomic_cmpxchg_pt(uaddr, oldval, newval); + ret = __futex_atomic_cmpxchg_pt(uval, uaddr, oldval, newval); put_page(virt_to_page(uaddr)); return ret; } diff --git a/arch/s390/lib/uaccess_std.c b/arch/s390/lib/uaccess_std.c index 07deaee..bb1a7ee 100644 --- a/arch/s390/lib/uaccess_std.c +++ b/arch/s390/lib/uaccess_std.c @@ -125,9 +125,9 @@ static size_t copy_in_user_std(size_t size, void __user *to, unsigned long tmp1; asm volatile( + " sacf 256\n" " "AHI" %0,-1\n" " jo 5f\n" - " sacf 256\n" " bras %3,3f\n" "0:"AHI" %0,257\n" "1: mvc 0(1,%1),0(%2)\n" @@ -142,9 +142,8 @@ static size_t copy_in_user_std(size_t size, void __user *to, "3:"AHI" %0,-256\n" " jnm 2b\n" "4: ex %0,1b-0b(%3)\n" - " sacf 0\n" "5: "SLR" %0,%0\n" - "6:\n" + "6: sacf 0\n" EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b) : "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1) : : "cc", "memory"); @@ -156,9 +155,9 @@ static size_t clear_user_std(size_t size, void __user *to) unsigned long tmp1, tmp2; asm volatile( + " sacf 256\n" " "AHI" %0,-1\n" " jo 5f\n" - " sacf 256\n" " bras %3,3f\n" " xc 0(1,%1),0(%1)\n" "0:"AHI" %0,257\n" @@ -178,9 +177,8 @@ static size_t clear_user_std(size_t size, void __user *to) "3:"AHI" %0,-256\n" " jnm 2b\n" "4: ex %0,0(%3)\n" - " sacf 0\n" "5: "SLR" %0,%0\n" - "6:\n" + "6: sacf 0\n" EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b) : "+a" (size), "+a" (to), "=a" (tmp1), "=a" (tmp2) : : "cc", "memory"); @@ -257,7 +255,7 @@ size_t strncpy_from_user_std(size_t size, const char __user *src, char *dst) : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ "m" (*uaddr) : "cc"); -int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old) +int futex_atomic_op_std(int op, u32 __user *uaddr, int oparg, int *old) { int oldval = 0, newval, ret; @@ -289,19 +287,21 @@ int futex_atomic_op_std(int op, int __user *uaddr, int oparg, int *old) return ret; } -int futex_atomic_cmpxchg_std(int __user *uaddr, int oldval, int newval) +int futex_atomic_cmpxchg_std(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { int ret; asm volatile( " sacf 256\n" "0: cs %1,%4,0(%5)\n" - "1: lr %0,%1\n" + "1: la %0,0\n" "2: sacf 0\n" EX_TABLE(0b,2b) EX_TABLE(1b,2b) : "=d" (ret), "+d" (oldval), "=m" (*uaddr) : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr) : "cc", "memory" ); + *uval = oldval; return ret; } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 0c719c6..e1850c2 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -336,7 +336,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) page->flags ^= bits; if (page->flags & FRAG_MASK) { /* Page now has some free pgtable fragments. */ - list_move(&page->lru, &mm->context.pgtable_list); + if (!list_empty(&page->lru)) + list_move(&page->lru, &mm->context.pgtable_list); page = NULL; } else /* All fragments of the 4K page have been freed. */ diff --git a/arch/sh/include/asm/futex-irq.h b/arch/sh/include/asm/futex-irq.h index a9f16a7..6cb9f19 100644 --- a/arch/sh/include/asm/futex-irq.h +++ b/arch/sh/include/asm/futex-irq.h @@ -3,7 +3,7 @@ #include <asm/system.h> -static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, +static inline int atomic_futex_op_xchg_set(int oparg, u32 __user *uaddr, int *oldval) { unsigned long flags; @@ -20,7 +20,7 @@ static inline int atomic_futex_op_xchg_set(int oparg, int __user *uaddr, return ret; } -static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, +static inline int atomic_futex_op_xchg_add(int oparg, u32 __user *uaddr, int *oldval) { unsigned long flags; @@ -37,7 +37,7 @@ static inline int atomic_futex_op_xchg_add(int oparg, int __user *uaddr, return ret; } -static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, +static inline int atomic_futex_op_xchg_or(int oparg, u32 __user *uaddr, int *oldval) { unsigned long flags; @@ -54,7 +54,7 @@ static inline int atomic_futex_op_xchg_or(int oparg, int __user *uaddr, return ret; } -static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, +static inline int atomic_futex_op_xchg_and(int oparg, u32 __user *uaddr, int *oldval) { unsigned long flags; @@ -71,7 +71,7 @@ static inline int atomic_futex_op_xchg_and(int oparg, int __user *uaddr, return ret; } -static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, +static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, int *oldval) { unsigned long flags; @@ -88,11 +88,13 @@ static inline int atomic_futex_op_xchg_xor(int oparg, int __user *uaddr, return ret; } -static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr, - int oldval, int newval) +static inline int atomic_futex_op_cmpxchg_inatomic(u32 *uval, + u32 __user *uaddr, + u32 oldval, u32 newval) { unsigned long flags; - int ret, prev = 0; + int ret; + u32 prev = 0; local_irq_save(flags); @@ -102,10 +104,8 @@ static inline int atomic_futex_op_cmpxchg_inatomic(int __user *uaddr, local_irq_restore(flags); - if (ret) - return ret; - - return prev; + *uval = prev; + return ret; } #endif /* __ASM_SH_FUTEX_IRQ_H */ diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h index 68256ec..7be39a6 100644 --- a/arch/sh/include/asm/futex.h +++ b/arch/sh/include/asm/futex.h @@ -10,7 +10,7 @@ /* XXX: UP variants, fix for SH-4A and SMP.. */ #include <asm/futex-irq.h> -static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -21,7 +21,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -65,12 +65,13 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - return atomic_futex_op_cmpxchg_inatomic(uaddr, oldval, newval); + return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval); } #endif /* __KERNEL__ */ diff --git a/arch/sh/include/asm/rwsem.h b/arch/sh/include/asm/rwsem.h index 06e2251..edab572 100644 --- a/arch/sh/include/asm/rwsem.h +++ b/arch/sh/include/asm/rwsem.h @@ -11,64 +11,13 @@ #endif #ifdef __KERNEL__ -#include <linux/list.h> -#include <linux/spinlock.h> -#include <asm/atomic.h> -#include <asm/system.h> -/* - * the semaphore definition - */ -struct rw_semaphore { - long count; #define RWSEM_UNLOCKED_VALUE 0x00000000 #define RWSEM_ACTIVE_BIAS 0x00000001 #define RWSEM_ACTIVE_MASK 0x0000ffff #define RWSEM_WAITING_BIAS (-0x00010000) #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) \ - __RWSEM_DEP_MAP_INIT(name) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ -do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ -} while (0) - -static inline void init_rwsem(struct rw_semaphore *sem) -{ - sem->count = RWSEM_UNLOCKED_VALUE; - spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} /* * lock for reading @@ -179,10 +128,5 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) return atomic_add_return(delta, (atomic_t *)(&sem->count)); } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* __KERNEL__ */ #endif /* _ASM_SH_RWSEM_H */ diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h index a78701d..4a53500 100644 --- a/arch/sh/include/asm/sections.h +++ b/arch/sh/include/asm/sections.h @@ -3,7 +3,7 @@ #include <asm-generic/sections.h> -extern void __nosave_begin, __nosave_end; +extern long __nosave_begin, __nosave_end; extern long __machvec_start, __machvec_end; extern char __uncached_start, __uncached_end; extern char _ebss[]; diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c index 672944f..e53b4b3 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c @@ -14,7 +14,7 @@ #include <linux/io.h> #include <linux/sh_timer.h> #include <linux/serial_sci.h> -#include <asm/machtypes.h> +#include <generated/machtypes.h> static struct resource rtc_resources[] = { [0] = { @@ -255,12 +255,17 @@ static struct platform_device *sh7750_early_devices[] __initdata = { void __init plat_early_device_setup(void) { + struct platform_device *dev[1]; + if (mach_is_rts7751r2d()) { scif_platform_data.scscr |= SCSCR_CKE1; - early_platform_add_devices(&scif_device, 1); + dev[0] = &scif_device; + early_platform_add_devices(dev, 1); } else { - early_platform_add_devices(&sci_device, 1); - early_platform_add_devices(&scif_device, 1); + dev[0] = &sci_device; + early_platform_add_devices(dev, 1); + dev[0] = &scif_device; + early_platform_add_devices(dev, 1); } early_platform_add_devices(sh7750_early_devices, diff --git a/arch/sh/lib/delay.c b/arch/sh/lib/delay.c index faa8f86..0901b2f 100644 --- a/arch/sh/lib/delay.c +++ b/arch/sh/lib/delay.c @@ -10,6 +10,16 @@ void __delay(unsigned long loops) { __asm__ __volatile__( + /* + * ST40-300 appears to have an issue with this code, + * normally taking two cycles each loop, as with all + * other SH variants. If however the branch and the + * delay slot straddle an 8 byte boundary, this increases + * to 3 cycles. + * This align directive ensures this doesn't occur. + */ + ".balign 8\n\t" + "tst %0, %0\n\t" "1:\t" "bf/s 1b\n\t" diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index 88d3dc3..5a580ea 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -108,7 +108,8 @@ void copy_user_highpage(struct page *to, struct page *from, kunmap_atomic(vfrom, KM_USER0); } - if (pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK)) + if (pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK) || + (vma->vm_flags & VM_EXEC)) __flush_purge_region(vto, PAGE_SIZE); kunmap_atomic(vto, KM_USER1); diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h index 47f9583..444e7be 100644 --- a/arch/sparc/include/asm/futex_64.h +++ b/arch/sparc/include/asm/futex_64.h @@ -30,7 +30,7 @@ : "r" (uaddr), "r" (oparg), "i" (-EFAULT) \ : "memory") -static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -38,7 +38,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret, tem; - if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))) + if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) return -EFAULT; if (unlikely((((unsigned long) uaddr) & 0x3UL))) return -EINVAL; @@ -85,26 +85,30 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { + int ret = 0; + __asm__ __volatile__( - "\n1: casa [%3] %%asi, %2, %0\n" + "\n1: casa [%4] %%asi, %3, %1\n" "2:\n" " .section .fixup,#alloc,#execinstr\n" " .align 4\n" "3: sethi %%hi(2b), %0\n" " jmpl %0 + %%lo(2b), %%g0\n" - " mov %4, %0\n" + " mov %5, %0\n" " .previous\n" " .section __ex_table,\"a\"\n" " .align 4\n" " .word 1b, 3b\n" " .previous\n" - : "=r" (newval) - : "0" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT) + : "+r" (ret), "=r" (newval) + : "1" (newval), "r" (oldval), "r" (uaddr), "i" (-EFAULT) : "memory"); - return newval; + *uval = newval; + return ret; } #endif /* !(_SPARC64_FUTEX_H) */ diff --git a/arch/sparc/include/asm/pcr.h b/arch/sparc/include/asm/pcr.h index a2f5c61..843e4fa 100644 --- a/arch/sparc/include/asm/pcr.h +++ b/arch/sparc/include/asm/pcr.h @@ -43,4 +43,6 @@ static inline u64 picl_value(unsigned int nmi_hz) extern u64 pcr_enable; +extern int pcr_arch_init(void); + #endif /* __PCR_H */ diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h index a2b4302..069bf4d 100644 --- a/arch/sparc/include/asm/rwsem.h +++ b/arch/sparc/include/asm/rwsem.h @@ -13,53 +13,12 @@ #ifdef __KERNEL__ -#include <linux/list.h> -#include <linux/spinlock.h> - -struct rwsem_waiter; - -struct rw_semaphore { - signed long count; #define RWSEM_UNLOCKED_VALUE 0x00000000L #define RWSEM_ACTIVE_BIAS 0x00000001L #define RWSEM_ACTIVE_MASK 0xffffffffL #define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - -#define __RWSEM_INITIALIZER(name) \ -{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ -do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ -} while (0) /* * lock for reading @@ -160,11 +119,6 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) return atomic64_add_return(delta, (atomic64_t *)(&sem->count)); } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* __KERNEL__ */ #endif /* _SPARC64_RWSEM_H */ diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 47977a7..72509d0 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -255,10 +255,9 @@ static inline iopte_t *alloc_npages(struct device *dev, struct iommu *iommu, static int iommu_alloc_ctx(struct iommu *iommu) { int lowest = iommu->ctx_lowest_free; - int sz = IOMMU_NUM_CTXS - lowest; - int n = find_next_zero_bit(iommu->ctx_bitmap, sz, lowest); + int n = find_next_zero_bit(iommu->ctx_bitmap, IOMMU_NUM_CTXS, lowest); - if (unlikely(n == sz)) { + if (unlikely(n == IOMMU_NUM_CTXS)) { n = find_next_zero_bit(iommu->ctx_bitmap, lowest, 1); if (unlikely(n == lowest)) { printk(KERN_WARNING "IOMMU: Ran out of contexts.\n"); diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index ae96cf5..7c2ced6 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -167,5 +167,3 @@ out_unregister: unregister_perf_hsvc(); return err; } - -early_initcall(pcr_arch_init); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b6a2b8f..555a76d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -49,6 +49,7 @@ #include <asm/mdesc.h> #include <asm/ldc.h> #include <asm/hypervisor.h> +#include <asm/pcr.h> #include "cpumap.h" @@ -1358,6 +1359,7 @@ void __cpu_die(unsigned int cpu) void __init smp_cpus_done(unsigned int max_cpus) { + pcr_arch_init(); } void smp_send_reschedule(int cpu) diff --git a/arch/sparc/kernel/una_asm_32.S b/arch/sparc/kernel/una_asm_32.S index 8cc0345..8f096e8 100644 --- a/arch/sparc/kernel/una_asm_32.S +++ b/arch/sparc/kernel/una_asm_32.S @@ -24,9 +24,9 @@ retl_efault: .globl __do_int_store __do_int_store: ld [%o2], %g1 - cmp %1, 2 + cmp %o1, 2 be 2f - cmp %1, 4 + cmp %o1, 4 be 1f srl %g1, 24, %g2 srl %g1, 16, %g7 diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index cbddeb3..d3c7a12 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -16,7 +16,7 @@ #define ATOMIC_HASH(a) (&__atomic_hash[(((unsigned long)a)>>8) & (ATOMIC_HASH_SIZE-1)]) spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] = { - [0 ... (ATOMIC_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED + [0 ... (ATOMIC_HASH_SIZE-1)] = __SPIN_LOCK_UNLOCKED(__atomic_hash) }; #else /* SMP */ diff --git a/arch/sparc/lib/bitext.c b/arch/sparc/lib/bitext.c index 764b3eb..48d00e7 100644 --- a/arch/sparc/lib/bitext.c +++ b/arch/sparc/lib/bitext.c @@ -10,7 +10,7 @@ */ #include <linux/string.h> -#include <linux/bitops.h> +#include <linux/bitmap.h> #include <asm/bitext.h> @@ -80,8 +80,7 @@ int bit_map_string_get(struct bit_map *t, int len, int align) while (test_bit(offset + i, t->map) == 0) { i++; if (i == len) { - for (i = 0; i < len; i++) - __set_bit(offset + i, t->map); + bitmap_set(t->map, offset, len); if (offset == t->first_free) t->first_free = find_next_zero_bit (t->map, t->size, diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h index fe0d10d..d03ec12 100644 --- a/arch/tile/include/asm/futex.h +++ b/arch/tile/include/asm/futex.h @@ -29,16 +29,16 @@ #include <linux/uaccess.h> #include <linux/errno.h> -extern struct __get_user futex_set(int __user *v, int i); -extern struct __get_user futex_add(int __user *v, int n); -extern struct __get_user futex_or(int __user *v, int n); -extern struct __get_user futex_andn(int __user *v, int n); -extern struct __get_user futex_cmpxchg(int __user *v, int o, int n); +extern struct __get_user futex_set(u32 __user *v, int i); +extern struct __get_user futex_add(u32 __user *v, int n); +extern struct __get_user futex_or(u32 __user *v, int n); +extern struct __get_user futex_andn(u32 __user *v, int n); +extern struct __get_user futex_cmpxchg(u32 __user *v, int o, int n); #ifndef __tilegx__ -extern struct __get_user futex_xor(int __user *v, int n); +extern struct __get_user futex_xor(u32 __user *v, int n); #else -static inline struct __get_user futex_xor(int __user *uaddr, int n) +static inline struct __get_user futex_xor(u32 __user *uaddr, int n) { struct __get_user asm_ret = __get_user_4(uaddr); if (!asm_ret.err) { @@ -53,7 +53,7 @@ static inline struct __get_user futex_xor(int __user *uaddr, int n) } #endif -static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -65,7 +65,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -119,16 +119,17 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) return ret; } -static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, - int newval) +static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { struct __get_user asm_ret; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; asm_ret = futex_cmpxchg(uaddr, oldval, newval); - return asm_ret.err ? asm_ret.err : asm_ret.val; + *uval = asm_ret.val; + return asm_ret.err; } #ifndef __tilegx__ diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 975613b..c70e047 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -124,35 +124,18 @@ void mconsole_log(struct mc_request *req) #if 0 void mconsole_proc(struct mc_request *req) { - struct nameidata nd; struct vfsmount *mnt = current->nsproxy->pid_ns->proc_mnt; struct file *file; - int n, err; + int n; char *ptr = req->request.data, *buf; mm_segment_t old_fs = get_fs(); ptr += strlen("proc"); ptr = skip_spaces(ptr); - err = vfs_path_lookup(mnt->mnt_root, mnt, ptr, LOOKUP_FOLLOW, &nd); - if (err) { - mconsole_reply(req, "Failed to look up file", 1, 0); - goto out; - } - - err = may_open(&nd.path, MAY_READ, O_RDONLY); - if (result) { - mconsole_reply(req, "Failed to open file", 1, 0); - path_put(&nd.path); - goto out; - } - - file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY, - current_cred()); - err = PTR_ERR(file); + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); - path_put(&nd.path); goto out; } diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index ba4a98b..620f5b7 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -185,7 +185,7 @@ struct ubd { .no_cow = 0, \ .shared = 0, \ .cow = DEFAULT_COW, \ - .lock = SPIN_LOCK_UNLOCKED, \ + .lock = __SPIN_LOCK_UNLOCKED(ubd_devs.lock), \ .request = NULL, \ .start_sg = 0, \ .end_sg = 0, \ diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index 646aa78..46a8238 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -62,7 +62,12 @@ int main(int argc, char *argv[]) if (fseek(f, -4L, SEEK_END)) { perror(argv[1]); } - fread(&olen, sizeof olen, 1, f); + + if (fread(&olen, sizeof(olen), 1, f) != 1) { + perror(argv[1]); + return 1; + } + ilen = ftell(f); olen = getle32(&olen); fclose(f); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 0ed7896..2f0d7b4 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -25,6 +25,8 @@ #define sysretl_audit ia32_ret_from_sys_call #endif + .section .entry.text, "ax" + #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) .macro IA32_ARG_FIXUP noebp=0 @@ -851,5 +853,7 @@ ia32_sys_call_table: .quad sys_fanotify_init .quad sys32_fanotify_mark .quad sys_prlimit64 /* 340 */ + .quad sys_name_to_handle_at + .quad compat_sys_open_by_handle_at .quad compat_sys_clock_adjtime ia32_syscall_end: diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 211ca3f..4ea15ca 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -88,6 +88,7 @@ extern int acpi_disabled; extern int acpi_pci_disabled; extern int acpi_skip_timer_override; extern int acpi_use_timer_override; +extern int acpi_fix_pin2_polarity; extern u8 acpi_sci_flags; extern int acpi_sci_override_gsi; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 5e3969c3..3c89694 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -233,6 +233,7 @@ extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void setup_local_APIC(void); extern void end_local_APIC_setup(void); +extern void bsp_end_local_APIC_setup(void); extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h new file mode 100644 index 0000000..e656ad8 --- /dev/null +++ b/arch/x86/include/asm/ce4100.h @@ -0,0 +1,6 @@ +#ifndef _ASM_CE4100_H_ +#define _ASM_CE4100_H_ + +int ce4100_pci_init(void); + +#endif diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 6e6e755..4564c8e 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -32,6 +32,6 @@ extern void arch_unregister_cpu(int); DECLARE_PER_CPU(int, cpu_state); -int __cpuinit mwait_usable(const struct cpuinfo_x86 *); +int mwait_usable(const struct cpuinfo_x86 *); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 220e2ea..91f3e087 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -160,6 +160,7 @@ #define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */ #define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */ #define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -279,6 +280,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) #define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) +#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index 1f11ce4..d09bb03 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -37,7 +37,7 @@ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)) -static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) +static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -48,7 +48,7 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP) @@ -109,9 +109,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr) return ret; } -static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, - int newval) +static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { + int ret = 0; #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP) /* Real i386 machines have no cmpxchg instruction */ @@ -119,21 +120,22 @@ static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, return -ENOSYS; #endif - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int))) + if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n" + asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" "2:\t.section .fixup, \"ax\"\n" - "3:\tmov %2, %0\n" + "3:\tmov %3, %0\n" "\tjmp 2b\n" "\t.previous\n" _ASM_EXTABLE(1b, 3b) - : "=a" (oldval), "+m" (*uaddr) - : "i" (-EFAULT), "r" (newval), "0" (oldval) + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) + : "i" (-EFAULT), "r" (newval), "1" (oldval) : "memory" ); - return oldval; + *uval = oldval; + return ret; } #endif diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index ca242d3..518bbbb 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -13,7 +13,6 @@ enum die_val { DIE_PANIC, DIE_NMI, DIE_DIE, - DIE_NMIWATCHDOG, DIE_KERNELDEBUG, DIE_TRAP, DIE_GPF, diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 4a2d4e0..8b5393e 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -36,8 +36,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, unsigned cpu = smp_processor_id(); if (likely(prev != next)) { - /* stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); #ifdef CONFIG_SMP percpu_write(cpu_tlbstate.state, TLBSTATE_OK); percpu_write(cpu_tlbstate.active_mm, next); @@ -47,6 +45,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); + /* stop flush ipis for the previous mm */ + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + /* * load the LDT, if the LDT is different: */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 4d0dfa0..823d482 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,6 +36,11 @@ #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd +#define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 +#define NHM_C3_AUTO_DEMOTE (1UL << 25) +#define NHM_C1_AUTO_DEMOTE (1UL << 26) +#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25) + #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 @@ -47,6 +52,9 @@ #define MSR_IA32_MCG_STATUS 0x0000017a #define MSR_IA32_MCG_CTL 0x0000017b +#define MSR_OFFCORE_RSP_0 0x000001a6 +#define MSR_OFFCORE_RSP_1 0x000001a7 + #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index c76f5b9..07f4601 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -7,7 +7,6 @@ #ifdef CONFIG_X86_LOCAL_APIC -extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index e2f6a99..cc29086 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -22,6 +22,7 @@ #define ARCH_P4_CNTRVAL_BITS (40) #define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1) +#define ARCH_P4_UNFLAGGED_BIT ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1)) #define P4_ESCR_EVENT_MASK 0x7e000000U #define P4_ESCR_EVENT_SHIFT 25 diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index d1e41b0..df4cd32 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -37,26 +37,9 @@ #endif #ifdef __KERNEL__ - -#include <linux/list.h> -#include <linux/spinlock.h> -#include <linux/lockdep.h> #include <asm/asm.h> -struct rwsem_waiter; - -extern asmregparm struct rw_semaphore * - rwsem_down_read_failed(struct rw_semaphore *sem); -extern asmregparm struct rw_semaphore * - rwsem_down_write_failed(struct rw_semaphore *sem); -extern asmregparm struct rw_semaphore * - rwsem_wake(struct rw_semaphore *); -extern asmregparm struct rw_semaphore * - rwsem_downgrade_wake(struct rw_semaphore *sem); - /* - * the semaphore definition - * * The bias values and the counter type limits the number of * potential readers/writers to 32767 for 32 bits and 2147483647 * for 64 bits. @@ -74,43 +57,6 @@ extern asmregparm struct rw_semaphore * #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) -typedef signed long rwsem_count_t; - -struct rw_semaphore { - rwsem_count_t count; - spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - - -#define __RWSEM_INITIALIZER(name) \ -{ \ - RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \ -} - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ -do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ -} while (0) - /* * lock for reading */ @@ -133,7 +79,7 @@ static inline void __down_read(struct rw_semaphore *sem) */ static inline int __down_read_trylock(struct rw_semaphore *sem) { - rwsem_count_t result, tmp; + long result, tmp; asm volatile("# beginning __down_read_trylock\n\t" " mov %0,%1\n\t" "1:\n\t" @@ -155,7 +101,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) */ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { - rwsem_count_t tmp; + long tmp; asm volatile("# beginning down_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* adds 0xffff0001, returns the old value */ @@ -180,9 +126,8 @@ static inline void __down_write(struct rw_semaphore *sem) */ static inline int __down_write_trylock(struct rw_semaphore *sem) { - rwsem_count_t ret = cmpxchg(&sem->count, - RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); + long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); if (ret == RWSEM_UNLOCKED_VALUE) return 1; return 0; @@ -193,7 +138,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - rwsem_count_t tmp; + long tmp; asm volatile("# beginning __up_read\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 1, returns the old value */ @@ -211,7 +156,7 @@ static inline void __up_read(struct rw_semaphore *sem) */ static inline void __up_write(struct rw_semaphore *sem) { - rwsem_count_t tmp; + long tmp; asm volatile("# beginning __up_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 0xffff0001, returns the old value */ @@ -247,8 +192,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem) /* * implement atomic add functionality */ -static inline void rwsem_atomic_add(rwsem_count_t delta, - struct rw_semaphore *sem) +static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) { asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0" : "+m" (sem->count) @@ -258,10 +202,9 @@ static inline void rwsem_atomic_add(rwsem_count_t delta, /* * implement exchange and add functionality */ -static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta, - struct rw_semaphore *sem) +static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) { - rwsem_count_t tmp = delta; + long tmp = delta; asm volatile(LOCK_PREFIX "xadd %0,%1" : "+r" (tmp), "+m" (sem->count) @@ -270,10 +213,5 @@ static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta, return tmp + delta; } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* __KERNEL__ */ #endif /* _ASM_X86_RWSEM_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4c2f63c..c1bbfa8 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -17,10 +17,20 @@ #endif #include <asm/thread_info.h> #include <asm/cpumask.h> +#include <asm/cpufeature.h> extern int smp_num_siblings; extern unsigned int num_processors; +static inline bool cpu_has_ht_siblings(void) +{ + bool has_siblings = false; +#ifdef CONFIG_SMP + has_siblings = cpu_has_ht && smp_num_siblings > 1; +#endif + return has_siblings; +} + DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU(u16, cpu_llc_id); @@ -40,10 +50,7 @@ DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid); /* Static state in head.S used to set up a CPU */ -extern struct { - void *sp; - unsigned short ss; -} stack_start; +extern unsigned long stack_start; /* Initial stack pointer address */ struct smp_ops { void (*smp_prepare_boot_cpu)(void); diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h index 6c22bf3..725b778 100644 --- a/arch/x86/include/asm/smpboot_hooks.h +++ b/arch/x86/include/asm/smpboot_hooks.h @@ -34,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void) */ CMOS_WRITE(0, 0xf); - *((volatile long *)phys_to_virt(apic->trampoline_phys_low)) = 0; + *((volatile u32 *)phys_to_virt(apic->trampoline_phys_low)) = 0; } static inline void __init smpboot_setup_io_apic(void) diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index b6f73f1..ffaf183 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -346,11 +346,13 @@ #define __NR_fanotify_init 338 #define __NR_fanotify_mark 339 #define __NR_prlimit64 340 -#define __NR_clock_adjtime 341 +#define __NR_name_to_handle_at 341 +#define __NR_open_by_handle_at 342 +#define __NR_clock_adjtime 343 #ifdef __KERNEL__ -#define NR_syscalls 342 +#define NR_syscalls 344 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 5ee3085..5466bea 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -669,7 +669,11 @@ __SYSCALL(__NR_fanotify_init, sys_fanotify_init) __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) #define __NR_prlimit64 302 __SYSCALL(__NR_prlimit64, sys_prlimit64) -#define __NR_clock_adjtime 303 +#define __NR_name_to_handle_at 303 +__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) +#define __NR_open_by_handle_at 304 +__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) +#define __NR_clock_adjtime 305 __SYSCALL(__NR_clock_adjtime, sys_clock_adjtime) #ifndef __NO_STUBS diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index ce1d54c..3e094af 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -176,7 +176,7 @@ struct bau_msg_payload { struct bau_msg_header { unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ - unsigned int base_dest_nodeid:15; /* nasid (pnode<<1) of */ + unsigned int base_dest_nodeid:15; /* nasid of the */ /* bits 20:6 */ /* first bit in uvhub map */ unsigned int command:8; /* message type */ /* bits 28:21 */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a3c28ae..8508bfe 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -287,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set) static inline int HYPERVISOR_sched_op(int cmd, void *arg) { - return _hypercall2(int, sched_op_new, cmd, arg); + return _hypercall2(int, sched_op, cmd, arg); } static inline long @@ -422,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value) #endif static inline int -HYPERVISOR_suspend(unsigned long srec) +HYPERVISOR_suspend(unsigned long start_info_mfn) { - return _hypercall3(int, sched_op, SCHEDOP_shutdown, - SHUTDOWN_suspend, srec); + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; + + /* + * For a PV guest the tools require that the start_info mfn be + * present in rdx/edx when the hypercall is made. Per the + * hypercall calling convention this is the third hypercall + * argument, which is start_info_mfn here. + */ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn); } static inline int diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index f25bdf2..c61934f 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -29,8 +29,10 @@ typedef struct xpaddr { /**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ #define INVALID_P2M_ENTRY (~0UL) -#define FOREIGN_FRAME_BIT (1UL<<31) +#define FOREIGN_FRAME_BIT (1UL<<(BITS_PER_LONG-1)) +#define IDENTITY_FRAME_BIT (1UL<<(BITS_PER_LONG-2)) #define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) +#define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT) /* Maximum amount of memory we can handle in a domain in pages */ #define MAX_DOMAIN_PAGES \ @@ -41,12 +43,18 @@ extern unsigned int machine_to_phys_order; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern unsigned long set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e); extern int m2p_add_override(unsigned long mfn, struct page *page); extern int m2p_remove_override(struct page *page); extern struct page *m2p_find_override(unsigned long mfn); extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn); +#ifdef CONFIG_XEN_DEBUG_FS +extern int p2m_dump_show(struct seq_file *m, void *v); +#endif static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; @@ -57,7 +65,7 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn) mfn = get_phys_to_machine(pfn); if (mfn != INVALID_P2M_ENTRY) - mfn &= ~FOREIGN_FRAME_BIT; + mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT); return mfn; } @@ -73,25 +81,44 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn) static inline unsigned long mfn_to_pfn(unsigned long mfn) { unsigned long pfn; + int ret = 0; if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; + if (unlikely((mfn >> machine_to_phys_order) != 0)) { + pfn = ~0; + goto try_override; + } pfn = 0; /* * The array access can fail (e.g., device space beyond end of RAM). * In such cases it doesn't matter what we return (we return garbage), * but we must handle the fault without crashing! */ - __get_user(pfn, &machine_to_phys_mapping[mfn]); - - /* - * If this appears to be a foreign mfn (because the pfn - * doesn't map back to the mfn), then check the local override - * table to see if there's a better pfn to use. + ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); +try_override: + /* ret might be < 0 if there are no entries in the m2p for mfn */ + if (ret < 0) + pfn = ~0; + else if (get_phys_to_machine(pfn) != mfn) + /* + * If this appears to be a foreign mfn (because the pfn + * doesn't map back to the mfn), then check the local override + * table to see if there's a better pfn to use. + * + * m2p_find_override_pfn returns ~0 if it doesn't find anything. + */ + pfn = m2p_find_override_pfn(mfn, ~0); + + /* + * pfn is ~0 if there are no entries in the m2p for mfn or if the + * entry doesn't map back to the mfn and m2p_override doesn't have a + * valid entry for it. */ - if (get_phys_to_machine(pfn) != mfn) - pfn = m2p_find_override_pfn(mfn, pfn); + if (pfn == ~0 && + get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn)) + pfn = mfn; return pfn; } diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 2329b3e..aa86209 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -27,16 +27,16 @@ static inline void __init xen_setup_pirqs(void) * its own functions. */ struct xen_pci_frontend_ops { - int (*enable_msi)(struct pci_dev *dev, int **vectors); + int (*enable_msi)(struct pci_dev *dev, int vectors[]); void (*disable_msi)(struct pci_dev *dev); - int (*enable_msix)(struct pci_dev *dev, int **vectors, int nvec); + int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec); void (*disable_msix)(struct pci_dev *dev); }; extern struct xen_pci_frontend_ops *xen_pci_frontend; static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, - int **vectors) + int vectors[]) { if (xen_pci_frontend && xen_pci_frontend->enable_msi) return xen_pci_frontend->enable_msi(dev, vectors); @@ -48,7 +48,7 @@ static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) xen_pci_frontend->disable_msi(dev); } static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, - int **vectors, int nvec) + int vectors[], int nvec) { if (xen_pci_frontend && xen_pci_frontend->enable_msix) return xen_pci_frontend->enable_msix(dev, vectors, nvec); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b3a7113..3e6e2d6 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -72,6 +72,7 @@ u8 acpi_sci_flags __initdata; int acpi_sci_override_gsi __initdata; int acpi_skip_timer_override __initdata; int acpi_use_timer_override __initdata; +int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; @@ -415,10 +416,15 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header, return 0; } - if (acpi_skip_timer_override && - intsrc->source_irq == 0 && intsrc->global_irq == 2) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); - return 0; + if (intsrc->source_irq == 0 && intsrc->global_irq == 2) { + if (acpi_skip_timer_override) { + printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + return 0; + } + if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { + intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; + printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); + } } mp_override_legacy_irq(intsrc->source_irq, diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 69fd72a..68d1537 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -12,10 +12,8 @@ #include <linux/cpumask.h> #include <asm/segment.h> #include <asm/desc.h> - -#ifdef CONFIG_X86_32 #include <asm/pgtable.h> -#endif +#include <asm/cacheflush.h> #include "realmode/wakeup.h" #include "sleep.h" @@ -100,7 +98,7 @@ int acpi_save_state_mem(void) #else /* CONFIG_64BIT */ header->trampoline_segment = setup_trampoline() >> 4; #ifdef CONFIG_SMP - stack_start.sp = temp_stack + sizeof(temp_stack); + stack_start = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); @@ -149,6 +147,15 @@ void __init acpi_reserve_wakeup_memory(void) memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); } +int __init acpi_configure_wakeup_memory(void) +{ + if (acpi_realmode) + set_memory_x(acpi_realmode, WAKEUP_SIZE >> PAGE_SHIFT); + + return 0; +} +arch_initcall(acpi_configure_wakeup_memory); + static int __init acpi_sleep_setup(char *str) { diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1236085..7038b95 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -671,7 +671,7 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) atomic_set(&stop_machine_first, 1); wrote_text = 0; - stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); + __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); } #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 51ef31a..51d4e16 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -284,7 +284,7 @@ static int __init apbt_clockevent_register(void) memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device)); if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) { - apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100; + adev->evt.rating = APBT_CLOCKEVENT_RATING - 100; global_clock_event = &adev->evt; printk(KERN_DEBUG "%s clockevent registered as global\n", global_clock_event->name); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 06c196d..76b96d7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1381,12 +1381,17 @@ void __cpuinit end_local_APIC_setup(void) #endif apic_pm_activate(); +} + +void __init bsp_end_local_APIC_setup(void) +{ + end_local_APIC_setup(); /* * Now that local APIC setup is completed for BP, configure the fault * handling for interrupt remapping. */ - if (!smp_processor_id() && intr_remapping_enabled) + if (intr_remapping_enabled) enable_drhd_fault_handling(); } @@ -1756,7 +1761,7 @@ int __init APIC_init_uniprocessor(void) enable_IO_APIC(); #endif - end_local_APIC_setup(); + bsp_end_local_APIC_setup(); #ifdef CONFIG_X86_IO_APIC if (smp_found_config && !skip_ioapic_setup && nr_ioapics) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 697dc34..ca9e2a35 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -4002,6 +4002,9 @@ int mp_find_ioapic(u32 gsi) { int i = 0; + if (nr_ioapics == 0) + return -1; + /* Find the IOAPIC that manages this GSI. */ for (i = 0; i < nr_ioapics; i++) { if ((gsi >= mp_gsi_routing[i].gsi_base) diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 13a3891..452932d 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -106,8 +106,8 @@ void __init setup_bios_corruption_check(void) addr += size; } - printk(KERN_INFO "Scanning %d areas for low memory corruption\n", - num_scan_areas); + if (num_scan_areas) + printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas); } @@ -143,12 +143,12 @@ static void check_corruption(struct work_struct *dummy) { check_for_bios_corruption(); schedule_delayed_work(&bios_check_work, - round_jiffies_relative(corruption_check_period*HZ)); + round_jiffies_relative(corruption_check_period*HZ)); } static int start_periodic_check_for_corruption(void) { - if (!memory_corruption_check || corruption_check_period == 0) + if (!num_scan_areas || !memory_corruption_check || corruption_check_period == 0) return 0; printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n", diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index bd1cac7..52c9364 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -158,9 +158,9 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { if (c->x86 == 0x06) { if (cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Warning: EST-capable CPU " - "detected. The acpi-cpufreq module offers " - "voltage scaling in addition of frequency " + printk_once(KERN_WARNING PFX "Warning: EST-capable " + "CPU detected. The acpi-cpufreq module offers " + "voltage scaling in addition to frequency " "scaling. You should use that instead of " "p4-clockmod, if possible.\n"); switch (c->x86_model) { diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c index 4f6f679..4a5a42b 100644 --- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c @@ -195,7 +195,7 @@ static unsigned int pcc_get_freq(unsigned int cpu) cmd_incomplete: iowrite16(0, &pcch_hdr->status); spin_unlock(&pcc_lock); - return -EINVAL; + return 0; } static int pcc_cpufreq_target(struct cpufreq_policy *policy, diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 35c7e65..c567dec 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1537,6 +1537,7 @@ static struct notifier_block cpb_nb = { static int __cpuinit powernowk8_init(void) { unsigned int i, supported_cpus = 0, cpu; + int rv; for_each_online_cpu(i) { int rc; @@ -1555,14 +1556,14 @@ static int __cpuinit powernowk8_init(void) cpb_capable = true; - register_cpu_notifier(&cpb_nb); - msrs = msrs_alloc(); if (!msrs) { printk(KERN_ERR "%s: Error allocating msrs!\n", __func__); return -ENOMEM; } + register_cpu_notifier(&cpb_nb); + rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs); for_each_cpu(cpu, cpu_online_mask) { @@ -1574,7 +1575,13 @@ static int __cpuinit powernowk8_init(void) (cpb_enabled ? "on" : "off")); } - return cpufreq_register_driver(&cpufreq_amd64_driver); + rv = cpufreq_register_driver(&cpufreq_amd64_driver); + if (rv < 0 && boot_cpu_has(X86_FEATURE_CPB)) { + unregister_cpu_notifier(&cpb_nb); + msrs_free(msrs); + msrs = NULL; + } + return rv; } /* driver entry point for term */ diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 01c0f3e..bebabec 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -793,13 +793,21 @@ void set_mtrr_aps_delayed_init(void) } /* - * MTRR initialization for all AP's + * Delayed MTRR initialization for all AP's */ void mtrr_aps_init(void) { if (!use_intel()) return; + /* + * Check if someone has requested the delay of AP MTRR initialization, + * by doing set_mtrr_aps_delayed_init(), prior to this point. If not, + * then we are done. + */ + if (!mtrr_aps_delayed_init) + return; + set_mtrr(~0U, 0, 0, 0); mtrr_aps_delayed_init = false; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9d977a2..2660418 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -30,6 +30,7 @@ #include <asm/stacktrace.h> #include <asm/nmi.h> #include <asm/compat.h> +#include <asm/smp.h> #if 0 #undef wrmsrl @@ -93,6 +94,8 @@ struct amd_nb { struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; +struct intel_percore; + #define MAX_LBR_ENTRIES 16 struct cpu_hw_events { @@ -128,6 +131,13 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; /* + * Intel percore register state. + * Coordinate shared resources between HT threads. + */ + int percore_used; /* Used by this CPU? */ + struct intel_percore *per_core; + + /* * AMD specific bits */ struct amd_nb *amd_nb; @@ -166,8 +176,10 @@ struct cpu_hw_events { /* * Constraint on the Event code + UMask */ -#define PEBS_EVENT_CONSTRAINT(c, n) \ +#define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +#define PEBS_EVENT_CONSTRAINT(c, n) \ + INTEL_UEVENT_CONSTRAINT(c, n) #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -175,6 +187,28 @@ struct cpu_hw_events { #define for_each_event_constraint(e, c) \ for ((e) = (c); (e)->weight; (e)++) +/* + * Extra registers for specific events. + * Some events need large masks and require external MSRs. + * Define a mapping to these extra registers. + */ +struct extra_reg { + unsigned int event; + unsigned int msr; + u64 config_mask; + u64 valid_mask; +}; + +#define EVENT_EXTRA_REG(e, ms, m, vm) { \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + } +#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm) +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0) + union perf_capabilities { struct { u64 lbr_format : 6; @@ -219,6 +253,7 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; + struct event_constraint *percore_constraints; void (*quirks)(void); int perfctr_second_write; @@ -247,6 +282,11 @@ struct x86_pmu { */ unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */ int lbr_nr; /* hardware stack size */ + + /* + * Extra registers for events + */ + struct extra_reg *extra_regs; }; static struct x86_pmu x86_pmu __read_mostly; @@ -271,6 +311,10 @@ static u64 __read_mostly hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; +static u64 __read_mostly hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX]; /* * Propagate event elapsed time into the generic event. @@ -298,7 +342,7 @@ x86_perf_event_update(struct perf_event *event) */ again: prev_raw_count = local64_read(&hwc->prev_count); - rdmsrl(hwc->event_base + idx, new_raw_count); + rdmsrl(hwc->event_base, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) @@ -321,6 +365,49 @@ again: return new_raw_count; } +/* using X86_FEATURE_PERFCTR_CORE to later implement ALTERNATIVE() here */ +static inline int x86_pmu_addr_offset(int index) +{ + if (boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + return index << 1; + return index; +} + +static inline unsigned int x86_pmu_config_addr(int index) +{ + return x86_pmu.eventsel + x86_pmu_addr_offset(index); +} + +static inline unsigned int x86_pmu_event_addr(int index) +{ + return x86_pmu.perfctr + x86_pmu_addr_offset(index); +} + +/* + * Find and validate any extra registers to set up. + */ +static int x86_pmu_extra_regs(u64 config, struct perf_event *event) +{ + struct extra_reg *er; + + event->hw.extra_reg = 0; + event->hw.extra_config = 0; + + if (!x86_pmu.extra_regs) + return 0; + + for (er = x86_pmu.extra_regs; er->msr; er++) { + if (er->event != (config & er->config_mask)) + continue; + if (event->attr.config1 & ~er->valid_mask) + return -EINVAL; + event->hw.extra_reg = er->msr; + event->hw.extra_config = event->attr.config1; + break; + } + return 0; +} + static atomic_t active_events; static DEFINE_MUTEX(pmc_reserve_mutex); @@ -331,12 +418,12 @@ static bool reserve_pmc_hardware(void) int i; for (i = 0; i < x86_pmu.num_counters; i++) { - if (!reserve_perfctr_nmi(x86_pmu.perfctr + i)) + if (!reserve_perfctr_nmi(x86_pmu_event_addr(i))) goto perfctr_fail; } for (i = 0; i < x86_pmu.num_counters; i++) { - if (!reserve_evntsel_nmi(x86_pmu.eventsel + i)) + if (!reserve_evntsel_nmi(x86_pmu_config_addr(i))) goto eventsel_fail; } @@ -344,13 +431,13 @@ static bool reserve_pmc_hardware(void) eventsel_fail: for (i--; i >= 0; i--) - release_evntsel_nmi(x86_pmu.eventsel + i); + release_evntsel_nmi(x86_pmu_config_addr(i)); i = x86_pmu.num_counters; perfctr_fail: for (i--; i >= 0; i--) - release_perfctr_nmi(x86_pmu.perfctr + i); + release_perfctr_nmi(x86_pmu_event_addr(i)); return false; } @@ -360,8 +447,8 @@ static void release_pmc_hardware(void) int i; for (i = 0; i < x86_pmu.num_counters; i++) { - release_perfctr_nmi(x86_pmu.perfctr + i); - release_evntsel_nmi(x86_pmu.eventsel + i); + release_perfctr_nmi(x86_pmu_event_addr(i)); + release_evntsel_nmi(x86_pmu_config_addr(i)); } } @@ -382,7 +469,7 @@ static bool check_hw_exists(void) * complain and bail. */ for (i = 0; i < x86_pmu.num_counters; i++) { - reg = x86_pmu.eventsel + i; + reg = x86_pmu_config_addr(i); ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; @@ -407,8 +494,8 @@ static bool check_hw_exists(void) * that don't trap on the MSR access and always return 0s. */ val = 0xabcdUL; - ret = checking_wrmsrl(x86_pmu.perfctr, val); - ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new); + ret = checking_wrmsrl(x86_pmu_event_addr(0), val); + ret |= rdmsrl_safe(x86_pmu_event_addr(0), &val_new); if (ret || val != val_new) goto msr_fail; @@ -442,8 +529,9 @@ static inline int x86_pmu_initialized(void) } static inline int -set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) +set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) { + struct perf_event_attr *attr = &event->attr; unsigned int cache_type, cache_op, cache_result; u64 config, val; @@ -470,8 +558,8 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr) return -EINVAL; hwc->config |= val; - - return 0; + attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result]; + return x86_pmu_extra_regs(val, event); } static int x86_setup_perfctr(struct perf_event *event) @@ -496,10 +584,10 @@ static int x86_setup_perfctr(struct perf_event *event) } if (attr->type == PERF_TYPE_RAW) - return 0; + return x86_pmu_extra_regs(event->attr.config, event); if (attr->type == PERF_TYPE_HW_CACHE) - return set_ext_hw_attr(hwc, attr); + return set_ext_hw_attr(hwc, event); if (attr->config >= x86_pmu.max_events) return -EINVAL; @@ -617,11 +705,11 @@ static void x86_pmu_disable_all(void) if (!test_bit(idx, cpuc->active_mask)) continue; - rdmsrl(x86_pmu.eventsel + idx, val); + rdmsrl(x86_pmu_config_addr(idx), val); if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE)) continue; val &= ~ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(x86_pmu.eventsel + idx, val); + wrmsrl(x86_pmu_config_addr(idx), val); } } @@ -642,21 +730,26 @@ static void x86_pmu_disable(struct pmu *pmu) x86_pmu.disable_all(); } +static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, + u64 enable_mask) +{ + if (hwc->extra_reg) + wrmsrl(hwc->extra_reg, hwc->extra_config); + wrmsrl(hwc->config_base, hwc->config | enable_mask); +} + static void x86_pmu_enable_all(int added) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { - struct perf_event *event = cpuc->events[idx]; - u64 val; + struct hw_perf_event *hwc = &cpuc->events[idx]->hw; if (!test_bit(idx, cpuc->active_mask)) continue; - val = event->hw.config; - val |= ARCH_PERFMON_EVENTSEL_ENABLE; - wrmsrl(x86_pmu.eventsel + idx, val); + __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); } } @@ -821,15 +914,10 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->event_base = 0; } else if (hwc->idx >= X86_PMC_IDX_FIXED) { hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL; - /* - * We set it so that event_base + idx in wrmsr/rdmsr maps to - * MSR_ARCH_PERFMON_FIXED_CTR0 ... CTR2: - */ - hwc->event_base = - MSR_ARCH_PERFMON_FIXED_CTR0 - X86_PMC_IDX_FIXED; + hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0; } else { - hwc->config_base = x86_pmu.eventsel; - hwc->event_base = x86_pmu.perfctr; + hwc->config_base = x86_pmu_config_addr(hwc->idx); + hwc->event_base = x86_pmu_event_addr(hwc->idx); } } @@ -915,17 +1003,11 @@ static void x86_pmu_enable(struct pmu *pmu) x86_pmu.enable_all(added); } -static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, - u64 enable_mask) -{ - wrmsrl(hwc->config_base + hwc->idx, hwc->config | enable_mask); -} - static inline void x86_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - wrmsrl(hwc->config_base + hwc->idx, hwc->config); + wrmsrl(hwc->config_base, hwc->config); } static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left); @@ -978,7 +1060,7 @@ x86_perf_event_set_period(struct perf_event *event) */ local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base + idx, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); /* * Due to erratum on certan cpu we need @@ -986,7 +1068,7 @@ x86_perf_event_set_period(struct perf_event *event) * is updated properly */ if (x86_pmu.perfctr_second_write) { - wrmsrl(hwc->event_base + idx, + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); } @@ -1113,8 +1195,8 @@ void perf_event_print_debug(void) pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - rdmsrl(x86_pmu.eventsel + idx, pmc_ctrl); - rdmsrl(x86_pmu.perfctr + idx, pmc_count); + rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl); + rdmsrl(x86_pmu_event_addr(idx), pmc_count); prev_left = per_cpu(pmc_prev_left[idx], cpu); @@ -1389,7 +1471,7 @@ static void __init pmu_check_apic(void) pr_info("no hardware sampling interrupt available.\n"); } -int __init init_hw_perf_events(void) +static int __init init_hw_perf_events(void) { struct event_constraint *c; int err; @@ -1608,7 +1690,7 @@ out: return ret; } -int x86_pmu_event_init(struct perf_event *event) +static int x86_pmu_event_init(struct perf_event *event) { struct pmu *tmp; int err; diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 67e2202..461f62b 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -127,6 +127,11 @@ static int amd_pmu_hw_config(struct perf_event *event) /* * AMD64 events are detected based on their event codes. */ +static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) +{ + return ((hwc->config >> 24) & 0x0f00) | (hwc->config & 0x00ff); +} + static inline int amd_is_nb_event(struct hw_perf_event *hwc) { return (hwc->config & 0xe0) == 0xe0; @@ -385,13 +390,181 @@ static __initconst const struct x86_pmu amd_pmu = { .cpu_dead = amd_pmu_cpu_dead, }; +/* AMD Family 15h */ + +#define AMD_EVENT_TYPE_MASK 0x000000F0ULL + +#define AMD_EVENT_FP 0x00000000ULL ... 0x00000010ULL +#define AMD_EVENT_LS 0x00000020ULL ... 0x00000030ULL +#define AMD_EVENT_DC 0x00000040ULL ... 0x00000050ULL +#define AMD_EVENT_CU 0x00000060ULL ... 0x00000070ULL +#define AMD_EVENT_IC_DE 0x00000080ULL ... 0x00000090ULL +#define AMD_EVENT_EX_LS 0x000000C0ULL +#define AMD_EVENT_DE 0x000000D0ULL +#define AMD_EVENT_NB 0x000000E0ULL ... 0x000000F0ULL + +/* + * AMD family 15h event code/PMC mappings: + * + * type = event_code & 0x0F0: + * + * 0x000 FP PERF_CTL[5:3] + * 0x010 FP PERF_CTL[5:3] + * 0x020 LS PERF_CTL[5:0] + * 0x030 LS PERF_CTL[5:0] + * 0x040 DC PERF_CTL[5:0] + * 0x050 DC PERF_CTL[5:0] + * 0x060 CU PERF_CTL[2:0] + * 0x070 CU PERF_CTL[2:0] + * 0x080 IC/DE PERF_CTL[2:0] + * 0x090 IC/DE PERF_CTL[2:0] + * 0x0A0 --- + * 0x0B0 --- + * 0x0C0 EX/LS PERF_CTL[5:0] + * 0x0D0 DE PERF_CTL[2:0] + * 0x0E0 NB NB_PERF_CTL[3:0] + * 0x0F0 NB NB_PERF_CTL[3:0] + * + * Exceptions: + * + * 0x003 FP PERF_CTL[3] + * 0x00B FP PERF_CTL[3] + * 0x00D FP PERF_CTL[3] + * 0x023 DE PERF_CTL[2:0] + * 0x02D LS PERF_CTL[3] + * 0x02E LS PERF_CTL[3,0] + * 0x043 CU PERF_CTL[2:0] + * 0x045 CU PERF_CTL[2:0] + * 0x046 CU PERF_CTL[2:0] + * 0x054 CU PERF_CTL[2:0] + * 0x055 CU PERF_CTL[2:0] + * 0x08F IC PERF_CTL[0] + * 0x187 DE PERF_CTL[0] + * 0x188 DE PERF_CTL[0] + * 0x0DB EX PERF_CTL[5:0] + * 0x0DC LS PERF_CTL[5:0] + * 0x0DD LS PERF_CTL[5:0] + * 0x0DE LS PERF_CTL[5:0] + * 0x0DF LS PERF_CTL[5:0] + * 0x1D6 EX PERF_CTL[5:0] + * 0x1D8 EX PERF_CTL[5:0] + */ + +static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0); +static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0); +static struct event_constraint amd_f15_PMC3 = EVENT_CONSTRAINT(0, 0x08, 0); +static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0); +static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); +static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); + +static struct event_constraint * +amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + unsigned int event_code = amd_get_event_code(&event->hw); + + switch (event_code & AMD_EVENT_TYPE_MASK) { + case AMD_EVENT_FP: + switch (event_code) { + case 0x003: + case 0x00B: + case 0x00D: + return &amd_f15_PMC3; + default: + return &amd_f15_PMC53; + } + case AMD_EVENT_LS: + case AMD_EVENT_DC: + case AMD_EVENT_EX_LS: + switch (event_code) { + case 0x023: + case 0x043: + case 0x045: + case 0x046: + case 0x054: + case 0x055: + return &amd_f15_PMC20; + case 0x02D: + return &amd_f15_PMC3; + case 0x02E: + return &amd_f15_PMC30; + default: + return &amd_f15_PMC50; + } + case AMD_EVENT_CU: + case AMD_EVENT_IC_DE: + case AMD_EVENT_DE: + switch (event_code) { + case 0x08F: + case 0x187: + case 0x188: + return &amd_f15_PMC0; + case 0x0DB ... 0x0DF: + case 0x1D6: + case 0x1D8: + return &amd_f15_PMC50; + default: + return &amd_f15_PMC20; + } + case AMD_EVENT_NB: + /* not yet implemented */ + return &emptyconstraint; + default: + return &emptyconstraint; + } +} + +static __initconst const struct x86_pmu amd_pmu_f15h = { + .name = "AMD Family 15h", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = x86_pmu_enable_all, + .enable = x86_pmu_enable_event, + .disable = x86_pmu_disable_event, + .hw_config = amd_pmu_hw_config, + .schedule_events = x86_schedule_events, + .eventsel = MSR_F15H_PERF_CTL, + .perfctr = MSR_F15H_PERF_CTR, + .event_map = amd_pmu_event_map, + .max_events = ARRAY_SIZE(amd_perfmon_event_map), + .num_counters = 6, + .cntval_bits = 48, + .cntval_mask = (1ULL << 48) - 1, + .apic = 1, + /* use highest bit to detect overflow */ + .max_period = (1ULL << 47) - 1, + .get_event_constraints = amd_get_event_constraints_f15h, + /* nortbridge counters not yet implemented: */ +#if 0 + .put_event_constraints = amd_put_event_constraints, + + .cpu_prepare = amd_pmu_cpu_prepare, + .cpu_starting = amd_pmu_cpu_starting, + .cpu_dead = amd_pmu_cpu_dead, +#endif +}; + static __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) return -ENODEV; - x86_pmu = amd_pmu; + /* + * If core performance counter extensions exists, it must be + * family 15h, otherwise fail. See x86_pmu_addr_offset(). + */ + switch (boot_cpu_data.x86) { + case 0x15: + if (!cpu_has_perfctr_core) + return -ENODEV; + x86_pmu = amd_pmu_f15h; + break; + default: + if (cpu_has_perfctr_core) + return -ENODEV; + x86_pmu = amd_pmu; + break; + } /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 008835c..8fc2b2c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,5 +1,27 @@ #ifdef CONFIG_CPU_SUP_INTEL +#define MAX_EXTRA_REGS 2 + +/* + * Per register state. + */ +struct er_account { + int ref; /* reference count */ + unsigned int extra_reg; /* extra MSR number */ + u64 extra_config; /* extra MSR config */ +}; + +/* + * Per core state + * This used to coordinate shared registers for HT threads. + */ +struct intel_percore { + raw_spinlock_t lock; /* protect structure */ + struct er_account regs[MAX_EXTRA_REGS]; + int refcnt; /* number of threads */ + unsigned core_id; +}; + /* * Intel PerfMon, used on Core and later. */ @@ -64,6 +86,18 @@ static struct event_constraint intel_nehalem_event_constraints[] = EVENT_CONSTRAINT_END }; +static struct extra_reg intel_nehalem_extra_regs[] = +{ + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), + EVENT_EXTRA_END +}; + +static struct event_constraint intel_nehalem_percore_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0xb7, 0), + EVENT_CONSTRAINT_END +}; + static struct event_constraint intel_westmere_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ @@ -76,6 +110,33 @@ static struct event_constraint intel_westmere_event_constraints[] = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_snb_event_constraints[] = +{ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ + INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */ + INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */ + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + EVENT_CONSTRAINT_END +}; + +static struct extra_reg intel_westmere_extra_regs[] = +{ + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff), + EVENT_EXTRA_END +}; + +static struct event_constraint intel_westmere_percore_constraints[] = +{ + INTEL_EVENT_CONSTRAINT(0xb7, 0), + INTEL_EVENT_CONSTRAINT(0xbb, 0), + EVENT_CONSTRAINT_END +}; + static struct event_constraint intel_gen_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ @@ -89,6 +150,106 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +static __initconst const u64 snb_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xf1d0, /* MEM_UOP_RETIRED.LOADS */ + [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0xf2d0, /* MEM_UOP_RETIRED.STORES */ + [ C(RESULT_MISS) ] = 0x0851, /* L1D.ALL_M_REPLACEMENT */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x024e, /* HW_PRE_REQ.DL1_MISS */ + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0280, /* ICACHE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + /* + * TBD: Need Off-core Response Performance Monitoring support + */ + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01bb, + }, + [ C(OP_WRITE) ] = { + /* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01bb, + }, + [ C(OP_PREFETCH) ] = { + /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01bb, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOP_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOP_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -124,16 +285,26 @@ static __initconst const u64 westmere_hw_cache_event_ids }, [ C(LL ) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ - [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01bb, }, + /* + * Use RFO, not WRITEBACK, because a write miss would typically occur + * on RFO. + */ [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ - [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + /* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01bb, + /* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ - [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01bb, }, }, [ C(DTLB) ] = { @@ -180,6 +351,39 @@ static __initconst const u64 westmere_hw_cache_event_ids }, }; +/* + * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3 + */ + +#define DMND_DATA_RD (1 << 0) +#define DMND_RFO (1 << 1) +#define DMND_WB (1 << 3) +#define PF_DATA_RD (1 << 4) +#define PF_DATA_RFO (1 << 5) +#define RESP_UNCORE_HIT (1 << 8) +#define RESP_MISS (0xf600) /* non uncore hit */ + +static __initconst const u64 nehalem_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT, + [ C(RESULT_MISS) ] = DMND_DATA_RD|RESP_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT, + [ C(RESULT_MISS) ] = DMND_RFO|DMND_WB|RESP_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT, + [ C(RESULT_MISS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS, + }, + } +}; + static __initconst const u64 nehalem_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -215,16 +419,26 @@ static __initconst const u64 nehalem_hw_cache_event_ids }, [ C(LL ) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */ - [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */ + /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, + /* + * Use RFO, not WRITEBACK, because a write miss would typically occur + * on RFO. + */ [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */ - [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */ + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, [ C(OP_PREFETCH) ] = { - [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */ - [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */ + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, }, }, [ C(DTLB) ] = { @@ -691,8 +905,8 @@ static void intel_pmu_reset(void) printk("clearing PMU state on CPU#%d\n", smp_processor_id()); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - checking_wrmsrl(x86_pmu.eventsel + idx, 0ull); - checking_wrmsrl(x86_pmu.perfctr + idx, 0ull); + checking_wrmsrl(x86_pmu_config_addr(idx), 0ull); + checking_wrmsrl(x86_pmu_event_addr(idx), 0ull); } for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull); @@ -794,6 +1008,67 @@ intel_bts_constraints(struct perf_event *event) } static struct event_constraint * +intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT; + struct event_constraint *c; + struct intel_percore *pc; + struct er_account *era; + int i; + int free_slot; + int found; + + if (!x86_pmu.percore_constraints || hwc->extra_alloc) + return NULL; + + for (c = x86_pmu.percore_constraints; c->cmask; c++) { + if (e != c->code) + continue; + + /* + * Allocate resource per core. + */ + pc = cpuc->per_core; + if (!pc) + break; + c = &emptyconstraint; + raw_spin_lock(&pc->lock); + free_slot = -1; + found = 0; + for (i = 0; i < MAX_EXTRA_REGS; i++) { + era = &pc->regs[i]; + if (era->ref > 0 && hwc->extra_reg == era->extra_reg) { + /* Allow sharing same config */ + if (hwc->extra_config == era->extra_config) { + era->ref++; + cpuc->percore_used = 1; + hwc->extra_alloc = 1; + c = NULL; + } + /* else conflict */ + found = 1; + break; + } else if (era->ref == 0 && free_slot == -1) + free_slot = i; + } + if (!found && free_slot != -1) { + era = &pc->regs[free_slot]; + era->ref = 1; + era->extra_reg = hwc->extra_reg; + era->extra_config = hwc->extra_config; + cpuc->percore_used = 1; + hwc->extra_alloc = 1; + c = NULL; + } + raw_spin_unlock(&pc->lock); + return c; + } + + return NULL; +} + +static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { struct event_constraint *c; @@ -806,9 +1081,51 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event if (c) return c; + c = intel_percore_constraints(cpuc, event); + if (c) + return c; + return x86_get_event_constraints(cpuc, event); } +static void intel_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct extra_reg *er; + struct intel_percore *pc; + struct er_account *era; + struct hw_perf_event *hwc = &event->hw; + int i, allref; + + if (!cpuc->percore_used) + return; + + for (er = x86_pmu.extra_regs; er->msr; er++) { + if (er->event != (hwc->config & er->config_mask)) + continue; + + pc = cpuc->per_core; + raw_spin_lock(&pc->lock); + for (i = 0; i < MAX_EXTRA_REGS; i++) { + era = &pc->regs[i]; + if (era->ref > 0 && + era->extra_config == hwc->extra_config && + era->extra_reg == er->msr) { + era->ref--; + hwc->extra_alloc = 0; + break; + } + } + allref = 0; + for (i = 0; i < MAX_EXTRA_REGS; i++) + allref += pc->regs[i].ref; + if (allref == 0) + cpuc->percore_used = 0; + raw_spin_unlock(&pc->lock); + break; + } +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -880,20 +1197,67 @@ static __initconst const struct x86_pmu core_pmu = { */ .max_period = (1ULL << 31) - 1, .get_event_constraints = intel_get_event_constraints, + .put_event_constraints = intel_put_event_constraints, .event_constraints = intel_core_event_constraints, }; +static int intel_pmu_cpu_prepare(int cpu) +{ + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + + if (!cpu_has_ht_siblings()) + return NOTIFY_OK; + + cpuc->per_core = kzalloc_node(sizeof(struct intel_percore), + GFP_KERNEL, cpu_to_node(cpu)); + if (!cpuc->per_core) + return NOTIFY_BAD; + + raw_spin_lock_init(&cpuc->per_core->lock); + cpuc->per_core->core_id = -1; + return NOTIFY_OK; +} + static void intel_pmu_cpu_starting(int cpu) { + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + int core_id = topology_core_id(cpu); + int i; + init_debug_store_on_cpu(cpu); /* * Deal with CPUs that don't clear their LBRs on power-up. */ intel_pmu_lbr_reset(); + + if (!cpu_has_ht_siblings()) + return; + + for_each_cpu(i, topology_thread_cpumask(cpu)) { + struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core; + + if (pc && pc->core_id == core_id) { + kfree(cpuc->per_core); + cpuc->per_core = pc; + break; + } + } + + cpuc->per_core->core_id = core_id; + cpuc->per_core->refcnt++; } static void intel_pmu_cpu_dying(int cpu) { + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + struct intel_percore *pc = cpuc->per_core; + + if (pc) { + if (pc->core_id == -1 || --pc->refcnt == 0) + kfree(pc); + cpuc->per_core = NULL; + } + fini_debug_store_on_cpu(cpu); } @@ -918,7 +1282,9 @@ static __initconst const struct x86_pmu intel_pmu = { */ .max_period = (1ULL << 31) - 1, .get_event_constraints = intel_get_event_constraints, + .put_event_constraints = intel_put_event_constraints, + .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, }; @@ -1024,6 +1390,7 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_core(); x86_pmu.event_constraints = intel_core2_event_constraints; + x86_pmu.pebs_constraints = intel_core2_pebs_event_constraints; pr_cont("Core2 events, "); break; @@ -1032,11 +1399,16 @@ static __init int intel_pmu_init(void) case 46: /* 45 nm nehalem-ex, "Beckton" */ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_nehalem_event_constraints; + x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints; + x86_pmu.percore_constraints = intel_nehalem_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; + x86_pmu.extra_regs = intel_nehalem_extra_regs; pr_cont("Nehalem events, "); break; @@ -1047,6 +1419,7 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_atom(); x86_pmu.event_constraints = intel_gen_event_constraints; + x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; pr_cont("Atom events, "); break; @@ -1054,14 +1427,30 @@ static __init int intel_pmu_init(void) case 44: /* 32 nm nehalem, "Gulftown" */ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_westmere_event_constraints; + x86_pmu.percore_constraints = intel_westmere_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; + x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints; + x86_pmu.extra_regs = intel_westmere_extra_regs; pr_cont("Westmere events, "); break; + case 42: /* SandyBridge */ + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + + intel_pmu_lbr_init_nhm(); + + x86_pmu.event_constraints = intel_snb_event_constraints; + x86_pmu.pebs_constraints = intel_snb_pebs_events; + pr_cont("SandyBridge events, "); + break; + default: /* * default constraints for v2 and up diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index b7dcd9f..b95c66a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -361,30 +361,88 @@ static int intel_pmu_drain_bts_buffer(void) /* * PEBS */ - -static struct event_constraint intel_core_pebs_events[] = { - PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */ +static struct event_constraint intel_core2_pebs_event_constraints[] = { + PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */ PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ - PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */ - PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */ - PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */ + INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_atom_pebs_event_constraints[] = { + PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ + PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ + INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ EVENT_CONSTRAINT_END }; -static struct event_constraint intel_nehalem_pebs_events[] = { - PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */ - PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */ - PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */ - PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */ - PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */ - PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */ - PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */ - PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */ +static struct event_constraint intel_nehalem_pebs_event_constraints[] = { + INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ + INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ + INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_westmere_pebs_event_constraints[] = { + INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ + PEBS_EVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ + INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */ + + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */ + PEBS_EVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ + INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + EVENT_CONSTRAINT_END +}; + +static struct event_constraint intel_snb_pebs_events[] = { + PEBS_EVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + PEBS_EVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + PEBS_EVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + PEBS_EVENT_CONSTRAINT(0x01c4, 0xf), /* BR_INST_RETIRED.CONDITIONAL */ + PEBS_EVENT_CONSTRAINT(0x02c4, 0xf), /* BR_INST_RETIRED.NEAR_CALL */ + PEBS_EVENT_CONSTRAINT(0x04c4, 0xf), /* BR_INST_RETIRED.ALL_BRANCHES */ + PEBS_EVENT_CONSTRAINT(0x08c4, 0xf), /* BR_INST_RETIRED.NEAR_RETURN */ + PEBS_EVENT_CONSTRAINT(0x10c4, 0xf), /* BR_INST_RETIRED.NOT_TAKEN */ + PEBS_EVENT_CONSTRAINT(0x20c4, 0xf), /* BR_INST_RETIRED.NEAR_TAKEN */ + PEBS_EVENT_CONSTRAINT(0x40c4, 0xf), /* BR_INST_RETIRED.FAR_BRANCH */ + PEBS_EVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */ + PEBS_EVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */ + PEBS_EVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */ + PEBS_EVENT_CONSTRAINT(0x10c5, 0xf), /* BR_MISP_RETIRED.NOT_TAKEN */ + PEBS_EVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.TAKEN */ + PEBS_EVENT_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + PEBS_EVENT_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORE */ + PEBS_EVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */ + PEBS_EVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */ + PEBS_EVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */ + PEBS_EVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */ + PEBS_EVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */ + PEBS_EVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */ + PEBS_EVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */ + PEBS_EVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */ + PEBS_EVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */ + PEBS_EVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */ + PEBS_EVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.LLC_HIT */ + PEBS_EVENT_CONSTRAINT(0x40d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */ + PEBS_EVENT_CONSTRAINT(0x01d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */ + PEBS_EVENT_CONSTRAINT(0x02d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */ + PEBS_EVENT_CONSTRAINT(0x04d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM */ + PEBS_EVENT_CONSTRAINT(0x08d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE */ + PEBS_EVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ EVENT_CONSTRAINT_END }; @@ -695,20 +753,17 @@ static void intel_ds_init(void) printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; - x86_pmu.pebs_constraints = intel_core_pebs_events; break; case 1: printk(KERN_CONT "PEBS fmt1%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; - x86_pmu.pebs_constraints = intel_nehalem_pebs_events; break; default: printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; - break; } } } diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index e56b9bf..3769ac82 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -682,7 +682,7 @@ static int p4_validate_raw_event(struct perf_event *event) * if an event is shared accross the logical threads * the user needs special permissions to be able to use it */ - if (p4_event_bind_map[v].shared) { + if (p4_ht_active() && p4_event_bind_map[v].shared) { if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return -EACCES; } @@ -727,7 +727,8 @@ static int p4_hw_config(struct perf_event *event) event->hw.config = p4_set_ht_bit(event->hw.config); if (event->attr.type == PERF_TYPE_RAW) { - + struct p4_event_bind *bind; + unsigned int esel; /* * Clear bits we reserve to be managed by kernel itself * and never allowed from a user space @@ -743,6 +744,13 @@ static int p4_hw_config(struct perf_event *event) * bits since we keep additional info here (for cache events and etc) */ event->hw.config |= event->attr.config; + bind = p4_config_get_bind(event->attr.config); + if (!bind) { + rc = -EINVAL; + goto out; + } + esel = P4_OPCODE_ESEL(bind->opcode); + event->hw.config |= p4_config_pack_cccr(P4_CCCR_ESEL(esel)); } rc = x86_setup_perfctr(event); @@ -756,15 +764,20 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc) u64 v; /* an official way for overflow indication */ - rdmsrl(hwc->config_base + hwc->idx, v); + rdmsrl(hwc->config_base, v); if (v & P4_CCCR_OVF) { - wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF); + wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF); return 1; } - /* it might be unflagged overflow */ - rdmsrl(hwc->event_base + hwc->idx, v); - if (!(v & ARCH_P4_CNTRVAL_MASK)) + /* + * In some circumstances the overflow might issue an NMI but did + * not set P4_CCCR_OVF bit. Because a counter holds a negative value + * we simply check for high bit being set, if it's cleared it means + * the counter has reached zero value and continued counting before + * real NMI signal was received: + */ + if (!(v & ARCH_P4_UNFLAGGED_BIT)) return 1; return 0; @@ -802,7 +815,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) * state we need to clear P4_CCCR_OVF, otherwise interrupt get * asserted again and again */ - (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (void)checking_wrmsrl(hwc->config_base, (u64)(p4_config_unpack_cccr(hwc->config)) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); } @@ -872,7 +885,7 @@ static void p4_pmu_enable_event(struct perf_event *event) p4_pmu_enable_pebs(hwc->config); (void)checking_wrmsrl(escr_addr, escr_conf); - (void)checking_wrmsrl(hwc->config_base + hwc->idx, + (void)checking_wrmsrl(hwc->config_base, (cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE); } diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 34ba07b..20c097e 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -68,7 +68,7 @@ p6_pmu_disable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); + (void)checking_wrmsrl(hwc->config_base, val); } static void p6_pmu_enable_event(struct perf_event *event) @@ -81,7 +81,7 @@ static void p6_pmu_enable_event(struct perf_event *event) if (cpuc->enabled) val |= ARCH_PERFMON_EVENTSEL_ENABLE; - (void)checking_wrmsrl(hwc->config_base + hwc->idx, val); + (void)checking_wrmsrl(hwc->config_base, val); } static __initconst const struct x86_pmu p6_pmu = { diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index d5a2366..966512b 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -46,6 +46,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) /* returns the bit offset of the performance counter register */ switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: + if (msr >= MSR_F15H_PERF_CTR) + return (msr - MSR_F15H_PERF_CTR) >> 1; return msr - MSR_K7_PERFCTR0; case X86_VENDOR_INTEL: if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) @@ -70,6 +72,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) /* returns the bit offset of the event selection register */ switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: + if (msr >= MSR_F15H_PERF_CTL) + return (msr - MSR_F15H_PERF_CTL) >> 1; return msr - MSR_K7_EVNTSEL0; case X86_VENDOR_INTEL: if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index df20723..220a1c1 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -320,31 +320,6 @@ void die(const char *str, struct pt_regs *regs, long err) oops_end(flags, regs, sig); } -void notrace __kprobes -die_nmi(char *str, struct pt_regs *regs, int do_panic) -{ - unsigned long flags; - - if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP) - return; - - /* - * We are in trouble anyway, lets at least try - * to get a message out. - */ - flags = oops_begin(); - printk(KERN_EMERG "%s", str); - printk(" on CPU%d, ip %08lx, registers:\n", - smp_processor_id(), regs->ip); - show_registers(regs); - oops_end(flags, regs, 0); - if (do_panic || panic_on_oops) - panic("Non maskable interrupt"); - nmi_exit(); - local_irq_enable(); - do_exit(SIGBUS); -} - static int __init oops_setup(char *s) { if (!s) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 76b8cd9..9efbdcc 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -143,15 +143,10 @@ static void __init ati_bugs(int num, int slot, int func) static u32 __init ati_sbx00_rev(int num, int slot, int func) { - u32 old, d; + u32 d; - d = read_pci_config(num, slot, func, 0x70); - old = d; - d &= ~(1<<8); - write_pci_config(num, slot, func, 0x70, d); d = read_pci_config(num, slot, func, 0x8); d &= 0xff; - write_pci_config(num, slot, func, 0x70, old); return d; } @@ -160,13 +155,16 @@ static void __init ati_bugs_contd(int num, int slot, int func) { u32 d, rev; - if (acpi_use_timer_override) - return; - rev = ati_sbx00_rev(num, slot, func); + if (rev >= 0x40) + acpi_fix_pin2_polarity = 1; + if (rev > 0x13) return; + if (acpi_use_timer_override) + return; + /* check for IRQ0 interrupt swap */ d = read_pci_config(num, slot, func, 0x64); if (!(d & (1<<14))) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index c8b4efa..f5accf8 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -65,6 +65,8 @@ #define sysexit_audit syscall_exit_work #endif + .section .entry.text, "ax" + /* * We use macros for low-level operations which need to be overridden * for paravirtualization. The following will never clobber any registers: @@ -788,7 +790,7 @@ ENDPROC(ptregs_clone) */ .section .init.rodata,"a" ENTRY(interrupt) -.text +.section .entry.text, "ax" .p2align 5 .p2align CONFIG_X86_L1_CACHE_SHIFT ENTRY(irq_entries_start) @@ -807,7 +809,7 @@ vector=FIRST_EXTERNAL_VECTOR .endif .previous .long 1b - .text + .section .entry.text, "ax" vector=vector+1 .endif .endr diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index aed1ffb..0a0ed79 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -61,6 +61,8 @@ #define __AUDIT_ARCH_LE 0x40000000 .code64 + .section .entry.text, "ax" + #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE ENTRY(mcount) @@ -744,7 +746,7 @@ END(stub_rt_sigreturn) */ .section .init.rodata,"a" ENTRY(interrupt) - .text + .section .entry.text .p2align 5 .p2align CONFIG_X86_L1_CACHE_SHIFT ENTRY(irq_entries_start) @@ -763,7 +765,7 @@ vector=FIRST_EXTERNAL_VECTOR .endif .previous .quad 1b - .text + .section .entry.text vector=vector+1 .endif .endr diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 382eb29..a93742a 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -437,18 +437,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, return; } - if (ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer) == -EBUSY) { - *parent = old; - return; - } - trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; *parent = old; + return; + } + + if (ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer) == -EBUSY) { + *parent = old; + return; } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index fc293dc..767d6c4 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -85,6 +85,8 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) */ __HEAD ENTRY(startup_32) + movl pa(stack_start),%ecx + /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ testb $(1<<6), BP_loadflags(%esi) @@ -99,7 +101,9 @@ ENTRY(startup_32) movl %eax,%es movl %eax,%fs movl %eax,%gs + movl %eax,%ss 2: + leal -__PAGE_OFFSET(%ecx),%esp /* * Clear BSS first so that there are no surprises... @@ -145,8 +149,6 @@ ENTRY(startup_32) * _brk_end is set up to point to the first "safe" location. * Mappings are created both at virtual address 0 (identity mapping) * and PAGE_OFFSET for up to _end. - * - * Note that the stack is not yet set up! */ #ifdef CONFIG_X86_PAE @@ -282,6 +284,9 @@ ENTRY(startup_32_smp) movl %eax,%es movl %eax,%fs movl %eax,%gs + movl pa(stack_start),%ecx + movl %eax,%ss + leal -__PAGE_OFFSET(%ecx),%esp #endif /* CONFIG_SMP */ default_entry: @@ -347,8 +352,8 @@ default_entry: movl %eax,%cr0 /* ..and set paging (PG) bit */ ljmp $__BOOT_CS,$1f /* Clear prefetch and normalize %eip */ 1: - /* Set up the stack pointer */ - lss stack_start,%esp + /* Shift the stack pointer to a virtual address */ + addl $__PAGE_OFFSET, %esp /* * Initialize eflags. Some BIOS's leave bits like NT set. This would @@ -360,9 +365,7 @@ default_entry: #ifdef CONFIG_SMP cmpb $0, ready - jz 1f /* Initial CPU cleans BSS */ - jmp checkCPUtype -1: + jnz checkCPUtype #endif /* CONFIG_SMP */ /* @@ -470,14 +473,7 @@ is386: movl $2,%ecx # set MP cld # gcc2 wants the direction flag cleared at all times pushl $0 # fake return address for unwinder -#ifdef CONFIG_SMP - movb ready, %cl movb $1, ready - cmpb $0,%cl # the first CPU calls start_kernel - je 1f - movl (stack_start), %esp -1: -#endif /* CONFIG_SMP */ jmp *(initial_code) /* @@ -670,15 +666,15 @@ ENTRY(initial_page_table) #endif .data +.balign 4 ENTRY(stack_start) .long init_thread_union+THREAD_SIZE - .long __BOOT_DS - -ready: .byte 0 early_recursion_flag: .long 0 +ready: .byte 0 + int_msg: .asciz "Unknown interrupt or fault at: %p %p %p\n" diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 52945da..387b6a0 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -367,7 +367,8 @@ void fixup_irqs(void) if (irr & (1 << (vector % 32))) { irq = __this_cpu_read(vector_irq[vector]); - data = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + data = &desc->irq_data; raw_spin_lock(&desc->lock); if (data->chip->irq_retrigger) data->chip->irq_retrigger(data); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index a413000..7c64c42 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -533,15 +533,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) } return NOTIFY_DONE; - case DIE_NMIWATCHDOG: - if (atomic_read(&kgdb_active) != -1) { - /* KGDB CPU roundup: */ - kgdb_nmicallback(raw_smp_processor_id(), regs); - return NOTIFY_STOP; - } - /* Enter debugger: */ - break; - case DIE_DEBUG: if (atomic_read(&kgdb_cpu_doing_single_step) != -1) { if (user_mode(regs)) diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index d91c477..c969fd9 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -1276,6 +1276,14 @@ static int __kprobes can_optimize(unsigned long paddr) if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) return 0; + /* + * Do not optimize in the entry code due to the unstable + * stack handling. + */ + if ((paddr >= (unsigned long )__entry_text_start) && + (paddr < (unsigned long )__entry_text_end)) + return 0; + /* Check there is enough space for a relative jump. */ if (size - offset < RELATIVEJUMP_SIZE) return 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e764fc0..ff45541 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -92,21 +92,31 @@ void show_regs(struct pt_regs *regs) void show_regs_common(void) { - const char *board, *product; + const char *vendor, *product, *board; - board = dmi_get_system_info(DMI_BOARD_NAME); - if (!board) - board = ""; + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + if (!vendor) + vendor = ""; product = dmi_get_system_info(DMI_PRODUCT_NAME); if (!product) product = ""; + /* Board Name is optional */ + board = dmi_get_system_info(DMI_BOARD_NAME); + printk(KERN_CONT "\n"); - printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n", + printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s", current->pid, current->comm, print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), - init_utsname()->version, board, product); + init_utsname()->version); + printk(KERN_CONT " "); + printk(KERN_CONT "%s %s", vendor, product); + if (board) { + printk(KERN_CONT "/"); + printk(KERN_CONT "%s", board); + } + printk(KERN_CONT "\n"); } void flush_thread(void) @@ -506,7 +516,7 @@ static void poll_idle(void) #define MWAIT_ECX_EXTENDED_INFO 0x01 #define MWAIT_EDX_C1 0xf0 -int __cpuinit mwait_usable(const struct cpuinfo_x86 *c) +int mwait_usable(const struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index fc7aae1..715037c 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -285,6 +285,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "P4S800"), }, }, + { /* Handle problems with rebooting on VersaLogic Menlow boards */ + .callback = set_bios_reboot, + .ident = "VersaLogic Menlow based board", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"), + }, + }, { } }; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0cbe8c0..08776a9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -638,7 +638,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) * target processor state. */ startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - (unsigned long)stack_start.sp); + stack_start); /* * Run STARTUP IPI loop. @@ -785,7 +785,7 @@ do_rest: #endif early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; - stack_start.sp = (void *) c_idle.idle->thread.sp; + stack_start = c_idle.idle->thread.sp; /* start_ip had better be page-aligned! */ start_ip = setup_trampoline(); @@ -1060,7 +1060,7 @@ static int __init smp_sanity_check(unsigned max_cpus) connect_bsp_APIC(); setup_local_APIC(); - end_local_APIC_setup(); + bsp_end_local_APIC_setup(); return -1; } @@ -1137,7 +1137,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) if (!skip_ioapic_setup && nr_ioapics) enable_IO_APIC(); - end_local_APIC_setup(); + bsp_end_local_APIC_setup(); map_cpu_to_logical_apicid(); diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 68c7b9a..5f18174 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -340,4 +340,6 @@ ENTRY(sys_call_table) .long sys_fanotify_init .long sys_fanotify_mark .long sys_prlimit64 /* 340 */ + .long sys_name_to_handle_at + .long sys_open_by_handle_at .long sys_clock_adjtime diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bf47007..6d4341d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -105,6 +105,7 @@ SECTIONS SCHED_TEXT LOCK_TEXT KPROBES_TEXT + ENTRY_TEXT IRQENTRY_TEXT *(.fixup) *(.gnu.warning) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 25bd1bc..63fec15 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1150,8 +1150,8 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) kvm_load_ldt(svm->host.ldt); #ifdef CONFIG_X86_64 loadsegment(fs, svm->host.fs); - load_gs_index(svm->host.gs); wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); + load_gs_index(svm->host.gs); #else loadsegment(gs, svm->host.gs); #endif @@ -2777,6 +2777,8 @@ static int dr_interception(struct vcpu_svm *svm) kvm_register_write(&svm->vcpu, reg, val); } + skip_emulated_instruction(&svm->vcpu); + return 1; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 1357d7c..db93276 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -62,21 +62,21 @@ TRACE_EVENT(kvm_hv_hypercall, TP_ARGS(code, fast, rep_cnt, rep_idx, ingpa, outgpa), TP_STRUCT__entry( - __field( __u16, code ) - __field( bool, fast ) __field( __u16, rep_cnt ) __field( __u16, rep_idx ) __field( __u64, ingpa ) __field( __u64, outgpa ) + __field( __u16, code ) + __field( bool, fast ) ), TP_fast_assign( - __entry->code = code; - __entry->fast = fast; __entry->rep_cnt = rep_cnt; __entry->rep_idx = rep_idx; __entry->ingpa = ingpa; __entry->outgpa = outgpa; + __entry->code = code; + __entry->fast = fast; ), TP_printk("code 0x%x %s cnt 0x%x idx 0x%x in 0x%llx out 0x%llx", diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7d90ceb..20e3f87 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -229,15 +229,14 @@ void vmalloc_sync_all(void) for (address = VMALLOC_START & PMD_MASK; address >= TASK_SIZE && address < FIXADDR_TOP; address += PMD_SIZE) { - - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; pmd_t *ret; + /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); @@ -247,7 +246,7 @@ void vmalloc_sync_all(void) if (!ret) break; } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } } @@ -828,6 +827,13 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { if (fault & VM_FAULT_OOM) { + /* Kernel mode? Handle exceptions or die: */ + if (!(error_code & PF_USER)) { + up_read(¤t->mm->mmap_sem); + no_context(regs, error_code, address); + return; + } + out_of_memory(regs, error_code, address); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 71a5929..c14a542 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -105,18 +105,18 @@ void sync_global_pgds(unsigned long start, unsigned long end) for (address = start; address <= end; address += PGDIR_SIZE) { const pgd_t *pgd_ref = pgd_offset_k(address); - unsigned long flags; struct page *page; if (pgd_none(*pgd_ref)) continue; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { pgd_t *pgd; spinlock_t *pgt_lock; pgd = (pgd_t *)page_address(page) + pgd_index(address); + /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); @@ -128,7 +128,7 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(pgt_lock); } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } } diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 95ea155..1337c51 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -780,11 +780,7 @@ void __cpuinit numa_add_cpu(int cpu) int physnid; int nid = NUMA_NO_NODE; - apicid = early_per_cpu(x86_cpu_to_apicid, cpu); - if (apicid != BAD_APICID) - nid = apicid_to_node[apicid]; - if (nid == NUMA_NO_NODE) - nid = early_cpu_to_node(cpu); + nid = early_cpu_to_node(cpu); BUG_ON(nid == NUMA_NO_NODE || !node_online(nid)); /* diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 8b830ca..90825f2 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -57,12 +57,10 @@ static unsigned long direct_pages_count[PG_LEVEL_NUM]; void update_page_count(int level, unsigned long pages) { - unsigned long flags; - /* Protect against CPA */ - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); direct_pages_count[level] += pages; - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } static void split_page_count(int level) @@ -256,7 +254,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, unsigned long pfn) { pgprot_t forbidden = __pgprot(0); - pgprot_t required = __pgprot(0); /* * The BIOS area between 640k and 1Mb needs to be executable for @@ -282,12 +279,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT, __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; - /* - * .data and .bss should always be writable. - */ - if (within(address, (unsigned long)_sdata, (unsigned long)_edata) || - within(address, (unsigned long)__bss_start, (unsigned long)__bss_stop)) - pgprot_val(required) |= _PAGE_RW; #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) /* @@ -327,7 +318,6 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, #endif prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); - prot = __pgprot(pgprot_val(prot) | pgprot_val(required)); return prot; } @@ -402,7 +392,7 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { - unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn; + unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn; pte_t new_pte, old_pte, *tmp; pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; @@ -411,7 +401,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, if (cpa->force_split) return 1; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); /* * Check for races, another CPU might have split this page * up already: @@ -506,14 +496,14 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, } out_unlock: - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return do_split; } static int split_large_page(pte_t *kpte, unsigned long address) { - unsigned long flags, pfn, pfninc = 1; + unsigned long pfn, pfninc = 1; unsigned int i, level; pte_t *pbase, *tmp; pgprot_t ref_prot; @@ -527,7 +517,7 @@ static int split_large_page(pte_t *kpte, unsigned long address) if (!base) return -ENOMEM; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); /* * Check for races, another CPU might have split this page * up for us already: @@ -599,7 +589,7 @@ out_unlock: */ if (base) __free_page(base); - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return 0; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 500242d..0113d19 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -121,14 +121,12 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) static void pgd_dtor(pgd_t *pgd) { - unsigned long flags; /* can be called from interrupt context */ - if (SHARED_KERNEL_PMD) return; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); pgd_list_del(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } /* @@ -260,7 +258,6 @@ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *pmds[PREALLOCATED_PMDS]; - unsigned long flags; pgd = (pgd_t *)__get_free_page(PGALLOC_GFP); @@ -280,12 +277,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm) * respect to anything walking the pgd_list, so that they * never see a partially populated pgd. */ - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); pgd_ctor(mm, pgd); pgd_prepopulate_pmd(mm, pgd, pmds); - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); return pgd; diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c index 85b68ef..9260b3e 100644 --- a/arch/x86/pci/ce4100.c +++ b/arch/x86/pci/ce4100.c @@ -34,6 +34,7 @@ #include <linux/pci.h> #include <linux/init.h> +#include <asm/ce4100.h> #include <asm/pci_x86.h> struct sim_reg { @@ -306,10 +307,10 @@ struct pci_raw_ops ce4100_pci_conf = { .write = ce4100_conf_write, }; -static int __init ce4100_pci_init(void) +int __init ce4100_pci_init(void) { init_sim_regs(); raw_pci_ops = &ce4100_pci_conf; - return 0; + /* Indicate caller that it should invoke pci_legacy_init() */ + return 1; } -subsys_initcall(ce4100_pci_init); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 25cd4a0..8c4085a 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -20,7 +20,8 @@ #include <asm/xen/pci.h> #ifdef CONFIG_ACPI -static int xen_hvm_register_pirq(u32 gsi, int triggering) +static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, + int trigger, int polarity) { int rc, irq; struct physdev_map_pirq map_irq; @@ -41,7 +42,7 @@ static int xen_hvm_register_pirq(u32 gsi, int triggering) return -1; } - if (triggering == ACPI_EDGE_SENSITIVE) { + if (trigger == ACPI_EDGE_SENSITIVE) { shareable = 0; name = "ioapic-edge"; } else { @@ -55,12 +56,6 @@ static int xen_hvm_register_pirq(u32 gsi, int triggering) return irq; } - -static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, - int trigger, int polarity) -{ - return xen_hvm_register_pirq(gsi, trigger); -} #endif #if defined(CONFIG_PCI_MSI) @@ -91,7 +86,7 @@ static void xen_msi_compose_msg(struct pci_dev *pdev, unsigned int pirq, static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - int irq, pirq, ret = 0; + int irq, pirq; struct msi_desc *msidesc; struct msi_msg msg; @@ -99,39 +94,32 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) __read_msi_msg(msidesc, &msg); pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); - if (xen_irq_from_pirq(pirq) >= 0 && msg.data == XEN_PIRQ_MSI_DATA) { - xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", &irq, &pirq, XEN_ALLOC_IRQ); - if (irq < 0) + if (msg.data != XEN_PIRQ_MSI_DATA || + xen_irq_from_pirq(pirq) < 0) { + pirq = xen_allocate_pirq_msi(dev, msidesc); + if (pirq < 0) goto error; - ret = set_irq_msi(irq, msidesc); - if (ret < 0) - goto error_while; - printk(KERN_DEBUG "xen: msi already setup: msi --> irq=%d" - " pirq=%d\n", irq, pirq); - return 0; + xen_msi_compose_msg(dev, pirq, &msg); + __write_msi_msg(msidesc, &msg); + dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); + } else { + dev_dbg(&dev->dev, + "xen: msi already bound to pirq=%d\n", pirq); } - xen_allocate_pirq_msi((type == PCI_CAP_ID_MSIX) ? - "msi-x" : "msi", &irq, &pirq, (XEN_ALLOC_IRQ | XEN_ALLOC_PIRQ)); - if (irq < 0 || pirq < 0) + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq, 0, + (type == PCI_CAP_ID_MSIX) ? + "msi-x" : "msi"); + if (irq < 0) goto error; - printk(KERN_DEBUG "xen: msi --> irq=%d, pirq=%d\n", irq, pirq); - xen_msi_compose_msg(dev, pirq, &msg); - ret = set_irq_msi(irq, msidesc); - if (ret < 0) - goto error_while; - write_msi_msg(irq, &msg); + dev_dbg(&dev->dev, + "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq); } return 0; -error_while: - unbind_from_irqhandler(irq, NULL); error: - if (ret == -ENODEV) - dev_err(&dev->dev, "Xen PCI frontend has not registered" \ - " MSI/MSI-X support!\n"); - - return ret; + dev_err(&dev->dev, + "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + return -ENODEV; } /* @@ -150,35 +138,26 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return -ENOMEM; if (type == PCI_CAP_ID_MSIX) - ret = xen_pci_frontend_enable_msix(dev, &v, nvec); + ret = xen_pci_frontend_enable_msix(dev, v, nvec); else - ret = xen_pci_frontend_enable_msi(dev, &v); + ret = xen_pci_frontend_enable_msi(dev, v); if (ret) goto error; i = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_allocate_pirq(v[i], 0, /* not sharable */ - (type == PCI_CAP_ID_MSIX) ? - "pcifront-msi-x" : "pcifront-msi"); - if (irq < 0) { - ret = -1; + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, + (type == PCI_CAP_ID_MSIX) ? + "pcifront-msi-x" : + "pcifront-msi"); + if (irq < 0) goto free; - } - - ret = set_irq_msi(irq, msidesc); - if (ret) - goto error_while; i++; } kfree(v); return 0; -error_while: - unbind_from_irqhandler(irq, NULL); error: - if (ret == -ENODEV) - dev_err(&dev->dev, "Xen PCI frontend has not registered" \ - " MSI/MSI-X support!\n"); + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); free: kfree(v); return ret; @@ -193,6 +172,9 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) xen_pci_frontend_disable_msix(dev); else xen_pci_frontend_disable_msi(dev); + + /* Free the IRQ's and the msidesc using the generic code. */ + default_teardown_msi_irqs(dev); } static void xen_teardown_msi_irq(unsigned int irq) @@ -200,47 +182,82 @@ static void xen_teardown_msi_irq(unsigned int irq) xen_destroy_irq(irq); } +#ifdef CONFIG_XEN_DOM0 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - int irq, ret; + int ret = 0; struct msi_desc *msidesc; list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_create_msi_irq(dev, msidesc, type); - if (irq < 0) - return -1; + struct physdev_map_pirq map_irq; - ret = set_irq_msi(irq, msidesc); - if (ret) - goto error; - } - return 0; + memset(&map_irq, 0, sizeof(map_irq)); + map_irq.domid = DOMID_SELF; + map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.index = -1; + map_irq.pirq = -1; + map_irq.bus = dev->bus->number; + map_irq.devfn = dev->devfn; -error: - xen_destroy_irq(irq); + if (type == PCI_CAP_ID_MSIX) { + int pos; + u32 table_offset, bir; + + pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); + + pci_read_config_dword(dev, pos + PCI_MSIX_TABLE, + &table_offset); + bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); + + map_irq.table_base = pci_resource_start(dev, bir); + map_irq.entry_nr = msidesc->msi_attrib.entry_nr; + } + + ret = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); + if (ret) { + dev_warn(&dev->dev, "xen map irq failed %d\n", ret); + goto out; + } + + ret = xen_bind_pirq_msi_to_irq(dev, msidesc, + map_irq.pirq, map_irq.index, + (type == PCI_CAP_ID_MSIX) ? + "msi-x" : "msi"); + if (ret < 0) + goto out; + } + ret = 0; +out: return ret; } #endif +#endif static int xen_pcifront_enable_irq(struct pci_dev *dev) { int rc; int share = 1; + u8 gsi; - dev_info(&dev->dev, "Xen PCI enabling IRQ: %d\n", dev->irq); - - if (dev->irq < 0) - return -EINVAL; + rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", + rc); + return rc; + } - if (dev->irq < NR_IRQS_LEGACY) + if (gsi < NR_IRQS_LEGACY) share = 0; - rc = xen_allocate_pirq(dev->irq, share, "pcifront"); + rc = xen_allocate_pirq(gsi, share, "pcifront"); if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI IRQ: %d, failed to register:%d\n", - dev->irq, rc); + dev_warn(&dev->dev, "Xen PCI: failed to register GSI%d: %d\n", + gsi, rc); return rc; } + + dev->irq = rc; + dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq); return 0; } diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index d2c0d51..cd6f184 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -15,6 +15,7 @@ #include <linux/serial_reg.h> #include <linux/serial_8250.h> +#include <asm/ce4100.h> #include <asm/setup.h> #include <asm/io.h> @@ -129,4 +130,5 @@ void __init x86_ce4100_early_setup(void) x86_init.resources.probe_roms = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; x86_init.mpparse.find_smp_config = sdv_find_smp_config; + x86_init.pci.init = ce4100_pci_init; } diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index dab8746..044bda5 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -140,8 +140,7 @@ void * __init prom_early_alloc(unsigned long size) * wasted bootmem) and hand off chunks of it to callers. */ res = alloc_bootmem(chunk_size); - if (!res) - return NULL; + BUG_ON(!res); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); free_mem = chunk_size; diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index df58e9c..a7b38d3 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -1364,11 +1364,11 @@ uv_activation_descriptor_init(int node, int pnode) memset(bd2, 0, sizeof(struct bau_desc)); bd2->header.sw_ack_flag = 1; /* - * base_dest_nodeid is the nasid (pnode<<1) of the first uvhub + * base_dest_nodeid is the nasid of the first uvhub * in the partition. The bit map will indicate uvhub numbers, * which are 0-N in a partition. Pnodes are unique system-wide. */ - bd2->header.base_dest_nodeid = uv_partition_base_pnode << 1; + bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode); bd2->header.dest_subnodeid = 0x10; /* the LB */ bd2->header.command = UV_NET_ENDPOINT_INTD; bd2->header.int_both = 1; diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 5b54892..e4343fe 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -48,3 +48,11 @@ config XEN_DEBUG_FS help Enable statistics output and various tuning options in debugfs. Enabling this option may incur a significant performance overhead. + +config XEN_DEBUG + bool "Enable Xen debug checks" + depends on XEN + default n + help + Enable various WARN_ON checks in the Xen MMU code. + Enabling this option WILL incur a significant performance overhead. diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 50542ef..49dbd78 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1284,15 +1284,14 @@ static int init_hvm_pv_info(int *major, int *minor) xen_setup_features(); - pv_info = xen_info; - pv_info.kernel_rpl = 0; + pv_info.name = "Xen HVM"; xen_domain_type = XEN_HVM_DOMAIN; return 0; } -void xen_hvm_init_shared_info(void) +void __ref xen_hvm_init_shared_info(void) { int cpu; struct xen_add_to_physmap xatp; @@ -1331,6 +1330,8 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self, switch (action) { case CPU_UP_PREPARE: per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; + if (xen_have_vector_callback) + xen_init_lock_cpu(cpu); break; default: break; @@ -1355,6 +1356,7 @@ static void __init xen_hvm_guest_init(void) if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; + xen_hvm_smp_init(); register_cpu_notifier(&xen_hvm_cpu_notifier); xen_unplug_emulated_devices(); have_vcpu_info_placement = 0; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5e92b61..832765c 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -46,6 +46,7 @@ #include <linux/module.h> #include <linux/gfp.h> #include <linux/memblock.h> +#include <linux/seq_file.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -416,8 +417,12 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) if (val & _PAGE_PRESENT) { unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; pteval_t flags = val & PTE_FLAGS_MASK; - unsigned long mfn = pfn_to_mfn(pfn); + unsigned long mfn; + if (!xen_feature(XENFEAT_auto_translated_physmap)) + mfn = get_phys_to_machine(pfn); + else + mfn = pfn; /* * If there's no mfn for the pfn, then just create an * empty non-present pte. Unfortunately this loses @@ -427,8 +432,18 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) if (unlikely(mfn == INVALID_P2M_ENTRY)) { mfn = 0; flags = 0; + } else { + /* + * Paramount to do this test _after_ the + * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY & + * IDENTITY_FRAME_BIT resolves to true. + */ + mfn &= ~FOREIGN_FRAME_BIT; + if (mfn & IDENTITY_FRAME_BIT) { + mfn &= ~IDENTITY_FRAME_BIT; + flags |= _PAGE_IOMAP; + } } - val = ((pteval_t)mfn << PAGE_SHIFT) | flags; } @@ -532,6 +547,41 @@ pte_t xen_make_pte(pteval_t pte) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte); +#ifdef CONFIG_XEN_DEBUG +pte_t xen_make_pte_debug(pteval_t pte) +{ + phys_addr_t addr = (pte & PTE_PFN_MASK); + phys_addr_t other_addr; + bool io_page = false; + pte_t _pte; + + if (pte & _PAGE_IOMAP) + io_page = true; + + _pte = xen_make_pte(pte); + + if (!addr) + return _pte; + + if (io_page && + (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { + other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT; + WARN(addr != other_addr, + "0x%lx is using VM_IO, but it is 0x%lx!\n", + (unsigned long)addr, (unsigned long)other_addr); + } else { + pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP; + other_addr = (_pte.pte & PTE_PFN_MASK); + WARN((addr == other_addr) && (!io_page) && (!iomap_set), + "0x%lx is missing VM_IO (and wasn't fixed)!\n", + (unsigned long)addr); + } + + return _pte; +} +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug); +#endif + pgd_t xen_make_pgd(pgdval_t pgd) { pgd = pte_pfn_to_mfn(pgd); @@ -986,10 +1036,9 @@ static void xen_pgd_pin(struct mm_struct *mm) */ void xen_mm_pin_all(void) { - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { if (!PagePinned(page)) { @@ -998,7 +1047,7 @@ void xen_mm_pin_all(void) } } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } /* @@ -1099,10 +1148,9 @@ static void xen_pgd_unpin(struct mm_struct *mm) */ void xen_mm_unpin_all(void) { - unsigned long flags; struct page *page; - spin_lock_irqsave(&pgd_lock, flags); + spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { if (PageSavePinned(page)) { @@ -1112,7 +1160,7 @@ void xen_mm_unpin_all(void) } } - spin_unlock_irqrestore(&pgd_lock, flags); + spin_unlock(&pgd_lock); } void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next) @@ -1942,6 +1990,9 @@ __init void xen_ident_map_ISA(void) static __init void xen_post_allocator_init(void) { +#ifdef CONFIG_XEN_DEBUG + pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug); +#endif pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2074,7 +2125,7 @@ static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, in_frames[i] = virt_to_mfn(vaddr); MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0); - set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY); + __set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY); if (out_frames) out_frames[i] = virt_to_pfn(vaddr); @@ -2353,6 +2404,18 @@ EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); #ifdef CONFIG_XEN_DEBUG_FS +static int p2m_dump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, p2m_dump_show, NULL); +} + +static const struct file_operations p2m_dump_fops = { + .open = p2m_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static struct dentry *d_mmu_debug; static int __init xen_mmu_debugfs(void) @@ -2408,6 +2471,7 @@ static int __init xen_mmu_debugfs(void) debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug, &mmu_stats.prot_commit_batched); + debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops); return 0; } fs_initcall(xen_mmu_debugfs); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index fd12d7c..215a3ce 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -23,6 +23,129 @@ * P2M_PER_PAGE depends on the architecture, as a mfn is always * unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to * 512 and 1024 entries respectively. + * + * In short, these structures contain the Machine Frame Number (MFN) of the PFN. + * + * However not all entries are filled with MFNs. Specifically for all other + * leaf entries, or for the top root, or middle one, for which there is a void + * entry, we assume it is "missing". So (for example) + * pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY. + * + * We also have the possibility of setting 1-1 mappings on certain regions, so + * that: + * pfn_to_mfn(0xc0000)=0xc0000 + * + * The benefit of this is, that we can assume for non-RAM regions (think + * PCI BARs, or ACPI spaces), we can create mappings easily b/c we + * get the PFN value to match the MFN. + * + * For this to work efficiently we have one new page p2m_identity and + * allocate (via reserved_brk) any other pages we need to cover the sides + * (1GB or 4MB boundary violations). All entries in p2m_identity are set to + * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs, + * no other fancy value). + * + * On lookup we spot that the entry points to p2m_identity and return the + * identity value instead of dereferencing and returning INVALID_P2M_ENTRY. + * If the entry points to an allocated page, we just proceed as before and + * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in + * appropriate functions (pfn_to_mfn). + * + * The reason for having the IDENTITY_FRAME_BIT instead of just returning the + * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a + * non-identity pfn. To protect ourselves against we elect to set (and get) the + * IDENTITY_FRAME_BIT on all identity mapped PFNs. + * + * This simplistic diagram is used to explain the more subtle piece of code. + * There is also a digram of the P2M at the end that can help. + * Imagine your E820 looking as so: + * + * 1GB 2GB + * /-------------------+---------\/----\ /----------\ /---+-----\ + * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | + * \-------------------+---------/\----/ \----------/ \---+-----/ + * ^- 1029MB ^- 2001MB + * + * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100), + * 2048MB = 524288 (0x80000)] + * + * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB + * is actually not present (would have to kick the balloon driver to put it in). + * + * When we are told to set the PFNs for identity mapping (see patch: "xen/setup: + * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start + * of the PFN and the end PFN (263424 and 512256 respectively). The first step + * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page + * covers 512^2 of page estate (1GB) and in case the start or end PFN is not + * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn + * to end pfn. We reserve_brk top leaf pages if they are missing (means they + * point to p2m_mid_missing). + * + * With the E820 example above, 263424 is not 1GB aligned so we allocate a + * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. + * Each entry in the allocate page is "missing" (points to p2m_missing). + * + * Next stage is to determine if we need to do a more granular boundary check + * on the 4MB (or 2MB depending on architecture) off the start and end pfn's. + * We check if the start pfn and end pfn violate that boundary check, and if + * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer + * granularity of setting which PFNs are missing and which ones are identity. + * In our example 263424 and 512256 both fail the check so we reserve_brk two + * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" + * values) and assign them to p2m[1][2] and p2m[1][488] respectively. + * + * At this point we would at minimum reserve_brk one page, but could be up to + * three. Each call to set_phys_range_identity has at maximum a three page + * cost. If we were to query the P2M at this stage, all those entries from + * start PFN through end PFN (so 1029MB -> 2001MB) would return + * INVALID_P2M_ENTRY ("missing"). + * + * The next step is to walk from the start pfn to the end pfn setting + * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity. + * If we find that the middle leaf is pointing to p2m_missing we can swap it + * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this + * point we do not need to worry about boundary aligment (so no need to + * reserve_brk a middle page, figure out which PFNs are "missing" and which + * ones are identity), as that has been done earlier. If we find that the + * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference + * that page (which covers 512 PFNs) and set the appropriate PFN with + * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we + * set from p2m[1][2][256->511] and p2m[1][488][0->256] with + * IDENTITY_FRAME_BIT set. + * + * All other regions that are void (or not filled) either point to p2m_missing + * (considered missing) or have the default value of INVALID_P2M_ENTRY (also + * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] + * contain the INVALID_P2M_ENTRY value and are considered "missing." + * + * This is what the p2m ends up looking (for the E820 above) with this + * fabulous drawing: + * + * p2m /--------------\ + * /-----\ | &mfn_list[0],| /-----------------\ + * | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. | + * |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] | + * | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] | + * |-----| \ | [p2m_identity]+\\ | .... | + * | 2 |--\ \-------------------->| ... | \\ \----------------/ + * |-----| \ \---------------/ \\ + * | 3 |\ \ \\ p2m_identity + * |-----| \ \-------------------->/---------------\ /-----------------\ + * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | + * \-----/ / | [p2m_identity]+-->| ..., ~0 | + * / /---------------\ | .... | \-----------------/ + * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | + * / | IDENTITY[@256]|<----/ \---------------/ + * / | ~0, ~0, .... | + * | \---------------/ + * | + * p2m_missing p2m_missing + * /------------------\ /------------\ + * | [p2m_mid_missing]+---->| ~0, ~0, ~0 | + * | [p2m_mid_missing]+---->| ..., ~0 | + * \------------------/ \------------/ + * + * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) */ #include <linux/init.h> @@ -30,6 +153,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/sched.h> +#include <linux/seq_file.h> #include <asm/cache.h> #include <asm/setup.h> @@ -59,9 +183,15 @@ static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE); + RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); +/* We might hit two boundary violations at the start and end, at max each + * boundary violation will require three middle nodes. */ +RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -136,7 +266,7 @@ static void p2m_init(unsigned long *p2m) * - After resume we're called from within stop_machine, but the mfn * tree should alreay be completely allocated. */ -void xen_build_mfn_list_list(void) +void __ref xen_build_mfn_list_list(void) { unsigned long pfn; @@ -221,6 +351,9 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_top_init(p2m_top); + p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_init(p2m_identity); + /* * The domain builder gives us a pre-constructed p2m array in * mfn_list for all the pages initially given to us, so we just @@ -266,6 +399,14 @@ unsigned long get_phys_to_machine(unsigned long pfn) mididx = p2m_mid_index(pfn); idx = p2m_index(pfn); + /* + * The INVALID_P2M_ENTRY is filled in both p2m_*identity + * and in p2m_*missing, so returning the INVALID_P2M_ENTRY + * would be wrong. + */ + if (p2m_top[topidx][mididx] == p2m_identity) + return IDENTITY_FRAME(pfn); + return p2m_top[topidx][mididx][idx]; } EXPORT_SYMBOL_GPL(get_phys_to_machine); @@ -335,9 +476,11 @@ static bool alloc_p2m(unsigned long pfn) p2m_top_mfn_p[topidx] = mid_mfn; } - if (p2m_top[topidx][mididx] == p2m_missing) { + if (p2m_top[topidx][mididx] == p2m_identity || + p2m_top[topidx][mididx] == p2m_missing) { /* p2m leaf page is missing */ unsigned long *p2m; + unsigned long *p2m_orig = p2m_top[topidx][mididx]; p2m = alloc_p2m_page(); if (!p2m) @@ -345,7 +488,7 @@ static bool alloc_p2m(unsigned long pfn) p2m_init(p2m); - if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing) + if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig) free_p2m_page(p2m); else mid_mfn[mididx] = virt_to_mfn(p2m); @@ -354,11 +497,91 @@ static bool alloc_p2m(unsigned long pfn) return true; } +bool __early_alloc_p2m(unsigned long pfn) +{ + unsigned topidx, mididx, idx; + + topidx = p2m_top_index(pfn); + mididx = p2m_mid_index(pfn); + idx = p2m_index(pfn); + + /* Pfff.. No boundary cross-over, lets get out. */ + if (!idx) + return false; + + WARN(p2m_top[topidx][mididx] == p2m_identity, + "P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n", + topidx, mididx); + + /* + * Could be done by xen_build_dynamic_phys_to_machine.. + */ + if (p2m_top[topidx][mididx] != p2m_missing) + return false; + + /* Boundary cross-over for the edges: */ + if (idx) { + unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE); + + p2m_init(p2m); + + p2m_top[topidx][mididx] = p2m; + + } + return idx != 0; +} +unsigned long set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e) +{ + unsigned long pfn; + + if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN)) + return 0; + + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) + return pfn_e - pfn_s; + + if (pfn_s > pfn_e) + return 0; + + for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1)); + pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE)); + pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE) + { + unsigned topidx = p2m_top_index(pfn); + if (p2m_top[topidx] == p2m_mid_missing) { + unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE); + + p2m_mid_init(mid); + + p2m_top[topidx] = mid; + } + } + + __early_alloc_p2m(pfn_s); + __early_alloc_p2m(pfn_e); + + for (pfn = pfn_s; pfn < pfn_e; pfn++) + if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn))) + break; + + if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s), + "Identity mapping failed. We are %ld short of 1-1 mappings!\n", + (pfn_e - pfn_s) - (pfn - pfn_s))) + printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn); + + return pfn - pfn_s; +} + /* Try to install p2m mapping; fail if intermediate bits missing */ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) { unsigned topidx, mididx, idx; + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return true; + } if (unlikely(pfn >= MAX_P2M_PFN)) { BUG_ON(mfn != INVALID_P2M_ENTRY); return true; @@ -368,6 +591,21 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) mididx = p2m_mid_index(pfn); idx = p2m_index(pfn); + /* For sparse holes were the p2m leaf has real PFN along with + * PCI holes, stick in the PFN as the MFN value. + */ + if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) { + if (p2m_top[topidx][mididx] == p2m_identity) + return true; + + /* Swap over from MISSING to IDENTITY if needed. */ + if (p2m_top[topidx][mididx] == p2m_missing) { + WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing, + p2m_identity) != p2m_missing); + return true; + } + } + if (p2m_top[topidx][mididx] == p2m_missing) return mfn == INVALID_P2M_ENTRY; @@ -378,11 +616,6 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return true; - } - if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!alloc_p2m(pfn)) return false; @@ -421,7 +654,7 @@ int m2p_add_override(unsigned long mfn, struct page *page) { unsigned long flags; unsigned long pfn; - unsigned long address; + unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; @@ -455,7 +688,7 @@ int m2p_remove_override(struct page *page) unsigned long flags; unsigned long mfn; unsigned long pfn; - unsigned long address; + unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; @@ -520,3 +753,80 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn) return ret; } EXPORT_SYMBOL_GPL(m2p_find_override_pfn); + +#ifdef CONFIG_XEN_DEBUG_FS + +int p2m_dump_show(struct seq_file *m, void *v) +{ + static const char * const level_name[] = { "top", "middle", + "entry", "abnormal" }; + static const char * const type_name[] = { "identity", "missing", + "pfn", "abnormal"}; +#define TYPE_IDENTITY 0 +#define TYPE_MISSING 1 +#define TYPE_PFN 2 +#define TYPE_UNKNOWN 3 + unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0; + unsigned int uninitialized_var(prev_level); + unsigned int uninitialized_var(prev_type); + + if (!p2m_top) + return 0; + + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx = p2m_mid_index(pfn); + unsigned idx = p2m_index(pfn); + unsigned lvl, type; + + lvl = 4; + type = TYPE_UNKNOWN; + if (p2m_top[topidx] == p2m_mid_missing) { + lvl = 0; type = TYPE_MISSING; + } else if (p2m_top[topidx] == NULL) { + lvl = 0; type = TYPE_UNKNOWN; + } else if (p2m_top[topidx][mididx] == NULL) { + lvl = 1; type = TYPE_UNKNOWN; + } else if (p2m_top[topidx][mididx] == p2m_identity) { + lvl = 1; type = TYPE_IDENTITY; + } else if (p2m_top[topidx][mididx] == p2m_missing) { + lvl = 1; type = TYPE_MISSING; + } else if (p2m_top[topidx][mididx][idx] == 0) { + lvl = 2; type = TYPE_UNKNOWN; + } else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) { + lvl = 2; type = TYPE_IDENTITY; + } else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) { + lvl = 2; type = TYPE_MISSING; + } else if (p2m_top[topidx][mididx][idx] == pfn) { + lvl = 2; type = TYPE_PFN; + } else if (p2m_top[topidx][mididx][idx] != pfn) { + lvl = 2; type = TYPE_PFN; + } + if (pfn == 0) { + prev_level = lvl; + prev_type = type; + } + if (pfn == MAX_DOMAIN_PAGES-1) { + lvl = 3; + type = TYPE_UNKNOWN; + } + if (prev_type != type) { + seq_printf(m, " [0x%lx->0x%lx] %s\n", + prev_pfn_type, pfn, type_name[prev_type]); + prev_pfn_type = pfn; + prev_type = type; + } + if (prev_level != lvl) { + seq_printf(m, " [0x%lx->0x%lx] level %s\n", + prev_pfn_level, pfn, level_name[prev_level]); + prev_pfn_level = pfn; + prev_level = lvl; + } + } + return 0; +#undef TYPE_IDENTITY +#undef TYPE_MISSING +#undef TYPE_PFN +#undef TYPE_UNKNOWN +} +#endif diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a8a66a5..fa0269a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -52,6 +52,8 @@ phys_addr_t xen_extra_mem_start, xen_extra_mem_size; static __init void xen_add_extra_mem(unsigned long pages) { + unsigned long pfn; + u64 size = (u64)pages * PAGE_SIZE; u64 extra_start = xen_extra_mem_start + xen_extra_mem_size; @@ -66,6 +68,9 @@ static __init void xen_add_extra_mem(unsigned long pages) xen_extra_mem_size += size; xen_max_p2m_pfn = PFN_DOWN(extra_start + size); + + for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++) + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } static unsigned long __init xen_release_chunk(phys_addr_t start_addr, @@ -104,7 +109,7 @@ static unsigned long __init xen_release_chunk(phys_addr_t start_addr, WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n", start, end, ret); if (ret == 1) { - set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); len++; } } @@ -138,12 +143,55 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn, return released; } +static unsigned long __init xen_set_identity(const struct e820entry *list, + ssize_t map_size) +{ + phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS; + phys_addr_t start_pci = last; + const struct e820entry *entry; + unsigned long identity = 0; + int i; + + for (i = 0, entry = list; i < map_size; i++, entry++) { + phys_addr_t start = entry->addr; + phys_addr_t end = start + entry->size; + + if (start < last) + start = last; + + if (end <= start) + continue; + + /* Skip over the 1MB region. */ + if (last > end) + continue; + + if (entry->type == E820_RAM) { + if (start > start_pci) + identity += set_phys_range_identity( + PFN_UP(start_pci), PFN_DOWN(start)); + + /* Without saving 'last' we would gooble RAM too + * at the end of the loop. */ + last = end; + start_pci = end; + continue; + } + start_pci = min(start, start_pci); + last = end; + } + if (last > start_pci) + identity += set_phys_range_identity( + PFN_UP(start_pci), PFN_DOWN(last)); + return identity; +} /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { static struct e820entry map[E820MAX] __initdata; + static struct e820entry map_raw[E820MAX] __initdata; unsigned long max_pfn = xen_start_info->nr_pages; unsigned long long mem_end; @@ -151,6 +199,7 @@ char * __init xen_memory_setup(void) struct xen_memory_map memmap; unsigned long extra_pages = 0; unsigned long extra_limit; + unsigned long identity_pages = 0; int i; int op; @@ -176,6 +225,7 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); + memcpy(map_raw, map, sizeof(map)); e820.nr_map = 0; xen_extra_mem_start = mem_end; for (i = 0; i < memmap.nr_entries; i++) { @@ -194,6 +244,15 @@ char * __init xen_memory_setup(void) end -= delta; extra_pages += PFN_DOWN(delta); + /* + * Set RAM below 4GB that is not for us to be unusable. + * This prevents "System RAM" address space from being + * used as potential resource for I/O address (happens + * when 'allocate_resource' is called). + */ + if (delta && + (xen_initial_domain() && end < 0x100000000ULL)) + e820_add_region(end, delta, E820_UNUSABLE); } if (map[i].size > 0 && end > xen_extra_mem_start) @@ -251,6 +310,13 @@ char * __init xen_memory_setup(void) xen_add_extra_mem(extra_pages); + /* + * Set P2M for all non-RAM pages and E820 gaps to be identity + * type PFNs. We supply it with the non-sanitized version + * of the E820. + */ + identity_pages = xen_set_identity(map_raw, memmap.nr_entries); + printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages); return "Xen"; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 72a4c79..3061244 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -509,3 +509,41 @@ void __init xen_smp_init(void) xen_fill_possible_map(); xen_init_spinlocks(); } + +static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) +{ + native_smp_prepare_cpus(max_cpus); + WARN_ON(xen_smp_intr_init(0)); + + if (!xen_have_vector_callback) + return; + xen_init_lock_cpu(0); + xen_init_spinlocks(); +} + +static int __cpuinit xen_hvm_cpu_up(unsigned int cpu) +{ + int rc; + rc = native_cpu_up(cpu); + WARN_ON (xen_smp_intr_init(cpu)); + return rc; +} + +static void xen_hvm_cpu_die(unsigned int cpu) +{ + unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL); + native_cpu_die(cpu); +} + +void __init xen_hvm_smp_init(void) +{ + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_send_reschedule = xen_smp_send_reschedule; + smp_ops.cpu_up = xen_hvm_cpu_up; + smp_ops.cpu_die = xen_hvm_cpu_die; + smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; + smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; +} diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 9bbd63a..45329c8 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -12,7 +12,7 @@ #include "xen-ops.h" #include "mmu.h" -void xen_pre_suspend(void) +void xen_arch_pre_suspend(void) { xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); xen_start_info->console.domU.mfn = @@ -26,8 +26,9 @@ void xen_pre_suspend(void) BUG(); } -void xen_hvm_post_suspend(int suspend_cancelled) +void xen_arch_hvm_post_suspend(int suspend_cancelled) { +#ifdef CONFIG_XEN_PVHVM int cpu; xen_hvm_init_shared_info(); xen_callback_vector(); @@ -37,9 +38,10 @@ void xen_hvm_post_suspend(int suspend_cancelled) xen_setup_runstate_info(cpu); } } +#endif } -void xen_post_suspend(int suspend_cancelled) +void xen_arch_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 067759e..2e2d370 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -397,7 +397,9 @@ void xen_setup_timer(int cpu) name = "<timer kasprintf failed>"; irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, - IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER, + IRQF_DISABLED|IRQF_PERCPU| + IRQF_NOBALANCING|IRQF_TIMER| + IRQF_FORCE_RESUME, name, NULL); evt = &per_cpu(xen_clock_events, cpu); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9d41bf9..3112f55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -64,10 +64,12 @@ void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP void xen_smp_init(void); +void __init xen_hvm_smp_init(void); extern cpumask_var_t xen_cpu_initialized_map; #else static inline void xen_smp_init(void) {} +static inline void xen_hvm_smp_init(void) {} #endif #ifdef CONFIG_PARAVIRT_SPINLOCKS diff --git a/arch/xtensa/include/asm/rwsem.h b/arch/xtensa/include/asm/rwsem.h index e39edf5..249619e 100644 --- a/arch/xtensa/include/asm/rwsem.h +++ b/arch/xtensa/include/asm/rwsem.h @@ -17,44 +17,12 @@ #error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead." #endif -#include <linux/list.h> -#include <linux/spinlock.h> -#include <asm/atomic.h> -#include <asm/system.h> - -/* - * the semaphore definition - */ -struct rw_semaphore { - signed long count; #define RWSEM_UNLOCKED_VALUE 0x00000000 #define RWSEM_ACTIVE_BIAS 0x00000001 #define RWSEM_ACTIVE_MASK 0x0000ffff #define RWSEM_WAITING_BIAS (-0x00010000) #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - spinlock_t wait_lock; - struct list_head wait_list; -}; - -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \ - LIST_HEAD_INIT((name).wait_list) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -static inline void init_rwsem(struct rw_semaphore *sem) -{ - sem->count = RWSEM_UNLOCKED_VALUE; - spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} /* * lock for reading @@ -160,9 +128,4 @@ static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) return atomic_add_return(delta, (atomic_t *)(&sem->count)); } -static inline int rwsem_is_locked(struct rw_semaphore *sem) -{ - return (sem->count != 0); -} - #endif /* _XTENSA_RWSEM_H */ diff --git a/block/blk-core.c b/block/blk-core.c index 2f4002f..518dd42 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -352,7 +352,7 @@ void blk_start_queue(struct request_queue *q) WARN_ON(!irqs_disabled()); queue_flag_clear(QUEUE_FLAG_STOPPED, q); - __blk_run_queue(q); + __blk_run_queue(q, false); } EXPORT_SYMBOL(blk_start_queue); @@ -403,13 +403,14 @@ EXPORT_SYMBOL(blk_sync_queue); /** * __blk_run_queue - run a single device queue * @q: The queue to run + * @force_kblockd: Don't run @q->request_fn directly. Use kblockd. * * Description: * See @blk_run_queue. This variant must be called with the queue lock * held and interrupts disabled. * */ -void __blk_run_queue(struct request_queue *q) +void __blk_run_queue(struct request_queue *q, bool force_kblockd) { blk_remove_plug(q); @@ -423,7 +424,7 @@ void __blk_run_queue(struct request_queue *q) * Only recurse once to avoid overrunning the stack, let the unplug * handling reinvoke the handler shortly if we already got there. */ - if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { + if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) { q->request_fn(q); queue_flag_clear(QUEUE_FLAG_REENTER, q); } else { @@ -446,7 +447,7 @@ void blk_run_queue(struct request_queue *q) unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - __blk_run_queue(q); + __blk_run_queue(q, false); spin_unlock_irqrestore(q->queue_lock, flags); } EXPORT_SYMBOL(blk_run_queue); @@ -1053,7 +1054,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq, drive_stat_acct(rq, 1); __elv_add_request(q, rq, where, 0); - __blk_run_queue(q); + __blk_run_queue(q, false); spin_unlock_irqrestore(q->queue_lock, flags); } EXPORT_SYMBOL(blk_insert_request); @@ -2610,13 +2611,6 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *dwork, unsigned long delay) -{ - return queue_delayed_work(kblockd_workqueue, dwork, delay); -} -EXPORT_SYMBOL(kblockd_schedule_delayed_work); - int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/blk-flush.c b/block/blk-flush.c index 54b123d..b27d020 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -66,10 +66,12 @@ static void blk_flush_complete_seq_end_io(struct request_queue *q, /* * Moving a request silently to empty queue_head may stall the - * queue. Kick the queue in those cases. + * queue. Kick the queue in those cases. This function is called + * from request completion path and calling directly into + * request_fn may confuse the driver. Always use kblockd. */ if (was_empty && next_rq) - __blk_run_queue(q); + __blk_run_queue(q, true); } static void pre_flush_end_io(struct request *rq, int error) @@ -130,7 +132,7 @@ static struct request *queue_next_fseq(struct request_queue *q) BUG(); } - elv_insert(q, rq, ELEVATOR_INSERT_FRONT); + elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE); return rq; } diff --git a/block/blk-lib.c b/block/blk-lib.c index 1a320d2..bd3e8df 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -109,7 +109,6 @@ struct bio_batch atomic_t done; unsigned long flags; struct completion *wait; - bio_end_io_t *end_io; }; static void bio_batch_end_io(struct bio *bio, int err) @@ -122,17 +121,14 @@ static void bio_batch_end_io(struct bio *bio, int err) else clear_bit(BIO_UPTODATE, &bb->flags); } - if (bb) { - if (bb->end_io) - bb->end_io(bio, err); - atomic_inc(&bb->done); - complete(bb->wait); - } + if (bb) + if (atomic_dec_and_test(&bb->done)) + complete(bb->wait); bio_put(bio); } /** - * blkdev_issue_zeroout generate number of zero filed write bios + * blkdev_issue_zeroout - generate number of zero filed write bios * @bdev: blockdev to issue * @sector: start sector * @nr_sects: number of sectors to write @@ -150,13 +146,12 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, int ret; struct bio *bio; struct bio_batch bb; - unsigned int sz, issued = 0; + unsigned int sz; DECLARE_COMPLETION_ONSTACK(wait); - atomic_set(&bb.done, 0); + atomic_set(&bb.done, 1); bb.flags = 1 << BIO_UPTODATE; bb.wait = &wait; - bb.end_io = NULL; submit: ret = 0; @@ -185,12 +180,12 @@ submit: break; } ret = 0; - issued++; + atomic_inc(&bb.done); submit_bio(WRITE, bio); } /* Wait for bios in-flight */ - while (issued != atomic_read(&bb.done)) + if (!atomic_dec_and_test(&bb.done)) wait_for_completion(&wait); if (!test_bit(BIO_UPTODATE, &bb.flags)) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 381b09b..e36cc10 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -20,6 +20,11 @@ static int throtl_quantum = 32; /* Throttling is performed over 100ms slice and after that slice is renewed */ static unsigned long throtl_slice = HZ/10; /* 100 ms */ +/* A workqueue to queue throttle related work */ +static struct workqueue_struct *kthrotld_workqueue; +static void throtl_schedule_delayed_work(struct throtl_data *td, + unsigned long delay); + struct throtl_rb_root { struct rb_root rb; struct rb_node *left; @@ -168,7 +173,15 @@ static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td, * tree of blkg (instead of traversing through hash list all * the time. */ - tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key)); + + /* + * This is the common case when there are no blkio cgroups. + * Avoid lookup in this case + */ + if (blkcg == &blkio_root_cgroup) + tg = &td->root_tg; + else + tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key)); /* Fill in device details for root group */ if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) { @@ -337,10 +350,9 @@ static void throtl_schedule_next_dispatch(struct throtl_data *td) update_min_dispatch_time(st); if (time_before_eq(st->min_disptime, jiffies)) - throtl_schedule_delayed_work(td->queue, 0); + throtl_schedule_delayed_work(td, 0); else - throtl_schedule_delayed_work(td->queue, - (st->min_disptime - jiffies)); + throtl_schedule_delayed_work(td, (st->min_disptime - jiffies)); } static inline void @@ -807,10 +819,10 @@ void blk_throtl_work(struct work_struct *work) } /* Call with queue lock held */ -void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) +static void +throtl_schedule_delayed_work(struct throtl_data *td, unsigned long delay) { - struct throtl_data *td = q->td; struct delayed_work *dwork = &td->throtl_work; if (total_nr_queued(td) > 0) { @@ -819,12 +831,11 @@ void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) * Cancel that and schedule a new one. */ __cancel_delayed_work(dwork); - kblockd_schedule_delayed_work(q, dwork, delay); + queue_delayed_work(kthrotld_workqueue, dwork, delay); throtl_log(td, "schedule work. delay=%lu jiffies=%lu", delay, jiffies); } } -EXPORT_SYMBOL(throtl_schedule_delayed_work); static void throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg) @@ -912,7 +923,7 @@ static void throtl_update_blkio_group_read_bps(void *key, smp_mb__after_atomic_inc(); /* Schedule a work now to process the limit change */ - throtl_schedule_delayed_work(td->queue, 0); + throtl_schedule_delayed_work(td, 0); } static void throtl_update_blkio_group_write_bps(void *key, @@ -926,7 +937,7 @@ static void throtl_update_blkio_group_write_bps(void *key, smp_mb__before_atomic_inc(); atomic_inc(&td->limits_changed); smp_mb__after_atomic_inc(); - throtl_schedule_delayed_work(td->queue, 0); + throtl_schedule_delayed_work(td, 0); } static void throtl_update_blkio_group_read_iops(void *key, @@ -940,7 +951,7 @@ static void throtl_update_blkio_group_read_iops(void *key, smp_mb__before_atomic_inc(); atomic_inc(&td->limits_changed); smp_mb__after_atomic_inc(); - throtl_schedule_delayed_work(td->queue, 0); + throtl_schedule_delayed_work(td, 0); } static void throtl_update_blkio_group_write_iops(void *key, @@ -954,7 +965,7 @@ static void throtl_update_blkio_group_write_iops(void *key, smp_mb__before_atomic_inc(); atomic_inc(&td->limits_changed); smp_mb__after_atomic_inc(); - throtl_schedule_delayed_work(td->queue, 0); + throtl_schedule_delayed_work(td, 0); } void throtl_shutdown_timer_wq(struct request_queue *q) @@ -1127,6 +1138,10 @@ void blk_throtl_exit(struct request_queue *q) static int __init throtl_init(void) { + kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0); + if (!kthrotld_workqueue) + panic("Failed to create kthrotld\n"); + blkio_policy_register(&blkio_policy_throtl); return 0; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 501ffdf..ea83a4f 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -599,7 +599,7 @@ cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg) } static inline unsigned -cfq_scaled_group_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) +cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) { unsigned slice = cfq_prio_to_slice(cfqd, cfqq); if (cfqd->cfq_latency) { @@ -631,7 +631,7 @@ cfq_scaled_group_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) static inline void cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) { - unsigned slice = cfq_scaled_group_slice(cfqd, cfqq); + unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq); cfqq->slice_start = jiffies; cfqq->slice_end = jiffies + slice; @@ -1671,7 +1671,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, */ if (timed_out) { if (cfq_cfqq_slice_new(cfqq)) - cfqq->slice_resid = cfq_scaled_group_slice(cfqd, cfqq); + cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq); else cfqq->slice_resid = cfqq->slice_end - jiffies; cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid); @@ -3355,7 +3355,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqd->busy_queues > 1) { cfq_del_timer(cfqd, cfqq); cfq_clear_cfqq_wait_request(cfqq); - __blk_run_queue(cfqd->queue); + __blk_run_queue(cfqd->queue, false); } else { cfq_blkiocg_update_idle_time_stats( &cfqq->cfqg->blkg); @@ -3370,7 +3370,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, * this new queue is RT and the current one is BE */ cfq_preempt_queue(cfqd, cfqq); - __blk_run_queue(cfqd->queue); + __blk_run_queue(cfqd->queue, false); } } @@ -3432,6 +3432,10 @@ static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq) { struct cfq_io_context *cic = cfqd->active_cic; + /* If the queue already has requests, don't wait */ + if (!RB_EMPTY_ROOT(&cfqq->sort_list)) + return false; + /* If there are other queues in the group, don't wait */ if (cfqq->cfqg->nr_cfqq > 1) return false; @@ -3727,7 +3731,7 @@ static void cfq_kick_queue(struct work_struct *work) struct request_queue *q = cfqd->queue; spin_lock_irq(q->queue_lock); - __blk_run_queue(cfqd->queue); + __blk_run_queue(cfqd->queue, false); spin_unlock_irq(q->queue_lock); } diff --git a/block/elevator.c b/block/elevator.c index 2569512..236e93c 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -602,7 +602,7 @@ void elv_quiesce_start(struct request_queue *q) */ elv_drain_elevator(q); while (q->rq.elvpriv) { - __blk_run_queue(q); + __blk_run_queue(q, false); spin_unlock_irq(q->queue_lock); msleep(10); spin_lock_irq(q->queue_lock); @@ -651,7 +651,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where) * with anything. There's no point in delaying queue * processing. */ - __blk_run_queue(q); + __blk_run_queue(q, false); break; case ELEVATOR_INSERT_SORT: diff --git a/block/genhd.c b/block/genhd.c index 6a5b772..cbf1112 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1355,7 +1355,7 @@ int invalidate_partition(struct gendisk *disk, int partno) struct block_device *bdev = bdget_disk(disk, partno); if (bdev) { fsync_bdev(bdev); - res = __invalidate_device(bdev); + res = __invalidate_device(bdev, true); bdput(bdev); } return res; diff --git a/block/ioctl.c b/block/ioctl.c index 9049d46..1124cd2 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -294,9 +294,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return -EINVAL; if (get_user(n, (int __user *) arg)) return -EFAULT; - if (!(mode & FMODE_EXCL) && - blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0) - return -EBUSY; + if (!(mode & FMODE_EXCL)) { + bdgrab(bdev); + if (blkdev_get(bdev, mode | FMODE_EXCL, &bdev) < 0) + return -EBUSY; + } ret = set_blocksize(bdev, n); if (!(mode & FMODE_EXCL)) blkdev_put(bdev, mode | FMODE_EXCL); diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index 54784bb..edc2586 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -416,10 +416,15 @@ struct acpi_gpe_handler_info { u8 originally_enabled; /* True if GPE was originally enabled */ }; +struct acpi_gpe_notify_object { + struct acpi_namespace_node *node; + struct acpi_gpe_notify_object *next; +}; + union acpi_gpe_dispatch_info { struct acpi_namespace_node *method_node; /* Method node for this GPE level */ struct acpi_gpe_handler_info *handler; /* Installed GPE handler */ - struct acpi_namespace_node *device_node; /* Parent _PRW device for implicit notify */ + struct acpi_gpe_notify_object device; /* List of _PRW devices for implicit notify */ }; /* diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c index 14988a8..f472521 100644 --- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -457,6 +457,7 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context) acpi_status status; struct acpi_gpe_event_info *local_gpe_event_info; struct acpi_evaluate_info *info; + struct acpi_gpe_notify_object *notify_object; ACPI_FUNCTION_TRACE(ev_asynch_execute_gpe_method); @@ -508,10 +509,18 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context) * from this thread -- because handlers may in turn run other * control methods. */ - status = - acpi_ev_queue_notify_request(local_gpe_event_info->dispatch. - device_node, - ACPI_NOTIFY_DEVICE_WAKE); + status = acpi_ev_queue_notify_request( + local_gpe_event_info->dispatch.device.node, + ACPI_NOTIFY_DEVICE_WAKE); + + notify_object = local_gpe_event_info->dispatch.device.next; + while (ACPI_SUCCESS(status) && notify_object) { + status = acpi_ev_queue_notify_request( + notify_object->node, + ACPI_NOTIFY_DEVICE_WAKE); + notify_object = notify_object->next; + } + break; case ACPI_GPE_DISPATCH_METHOD: diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index e9562a7..52aaff3 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -198,7 +198,9 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device, acpi_status status = AE_BAD_PARAMETER; struct acpi_gpe_event_info *gpe_event_info; struct acpi_namespace_node *device_node; + struct acpi_gpe_notify_object *notify_object; acpi_cpu_flags flags; + u8 gpe_dispatch_mask; ACPI_FUNCTION_TRACE(acpi_setup_gpe_for_wake); @@ -212,37 +214,62 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device, return_ACPI_STATUS(AE_BAD_PARAMETER); } + flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock); + + /* Ensure that we have a valid GPE number */ + + gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number); + if (!gpe_event_info) { + goto unlock_and_exit; + } + + if (wake_device == ACPI_ROOT_OBJECT) { + goto out; + } + + /* + * If there is no method or handler for this GPE, then the + * wake_device will be notified whenever this GPE fires (aka + * "implicit notify") Note: The GPE is assumed to be + * level-triggered (for windows compatibility). + */ + gpe_dispatch_mask = gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK; + if (gpe_dispatch_mask != ACPI_GPE_DISPATCH_NONE + && gpe_dispatch_mask != ACPI_GPE_DISPATCH_NOTIFY) { + goto out; + } + /* Validate wake_device is of type Device */ device_node = ACPI_CAST_PTR(struct acpi_namespace_node, wake_device); if (device_node->type != ACPI_TYPE_DEVICE) { - return_ACPI_STATUS(AE_BAD_PARAMETER); + goto unlock_and_exit; } - flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock); + if (gpe_dispatch_mask == ACPI_GPE_DISPATCH_NONE) { + gpe_event_info->flags = (ACPI_GPE_DISPATCH_NOTIFY | + ACPI_GPE_LEVEL_TRIGGERED); + gpe_event_info->dispatch.device.node = device_node; + gpe_event_info->dispatch.device.next = NULL; + } else { + /* There are multiple devices to notify implicitly. */ - /* Ensure that we have a valid GPE number */ - - gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number); - if (gpe_event_info) { - /* - * If there is no method or handler for this GPE, then the - * wake_device will be notified whenever this GPE fires (aka - * "implicit notify") Note: The GPE is assumed to be - * level-triggered (for windows compatibility). - */ - if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) == - ACPI_GPE_DISPATCH_NONE) { - gpe_event_info->flags = - (ACPI_GPE_DISPATCH_NOTIFY | - ACPI_GPE_LEVEL_TRIGGERED); - gpe_event_info->dispatch.device_node = device_node; + notify_object = ACPI_ALLOCATE_ZEROED(sizeof(*notify_object)); + if (!notify_object) { + status = AE_NO_MEMORY; + goto unlock_and_exit; } - gpe_event_info->flags |= ACPI_GPE_CAN_WAKE; - status = AE_OK; + notify_object->node = device_node; + notify_object->next = gpe_event_info->dispatch.device.next; + gpe_event_info->dispatch.device.next = notify_object; } + out: + gpe_event_info->flags |= ACPI_GPE_CAN_WAKE; + status = AE_OK; + + unlock_and_exit: acpi_os_release_lock(acpi_gbl_gpe_lock, flags); return_ACPI_STATUS(status); } diff --git a/drivers/acpi/debugfs.c b/drivers/acpi/debugfs.c index 5df67f1..384f7ab 100644 --- a/drivers/acpi/debugfs.c +++ b/drivers/acpi/debugfs.c @@ -26,7 +26,9 @@ static ssize_t cm_write(struct file *file, const char __user * user_buf, size_t count, loff_t *ppos) { static char *buf; - static int uncopied_bytes; + static u32 max_size; + static u32 uncopied_bytes; + struct acpi_table_header table; acpi_status status; @@ -37,19 +39,24 @@ static ssize_t cm_write(struct file *file, const char __user * user_buf, if (copy_from_user(&table, user_buf, sizeof(struct acpi_table_header))) return -EFAULT; - uncopied_bytes = table.length; - buf = kzalloc(uncopied_bytes, GFP_KERNEL); + uncopied_bytes = max_size = table.length; + buf = kzalloc(max_size, GFP_KERNEL); if (!buf) return -ENOMEM; } - if (uncopied_bytes < count) { - kfree(buf); + if (buf == NULL) + return -EINVAL; + + if ((*ppos > max_size) || + (*ppos + count > max_size) || + (*ppos + count < count) || + (count > uncopied_bytes)) return -EINVAL; - } if (copy_from_user(buf + (*ppos), user_buf, count)) { kfree(buf); + buf = NULL; return -EFAULT; } @@ -59,6 +66,7 @@ static ssize_t cm_write(struct file *file, const char __user * user_buf, if (!uncopied_bytes) { status = acpi_install_method(buf); kfree(buf); + buf = NULL; if (ACPI_FAILURE(status)) return -EINVAL; add_taint(TAINT_OVERRIDDEN_ACPI_TABLE); diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index b093181..c90c76a 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -636,17 +636,21 @@ EXPORT_SYMBOL(acpi_os_write_port); acpi_status acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width) { - u32 dummy; void __iomem *virt_addr; - int size = width / 8, unmap = 0; + unsigned int size = width / 8; + bool unmap = false; + u32 dummy; rcu_read_lock(); virt_addr = acpi_map_vaddr_lookup(phys_addr, size); - rcu_read_unlock(); if (!virt_addr) { + rcu_read_unlock(); virt_addr = acpi_os_ioremap(phys_addr, size); - unmap = 1; + if (!virt_addr) + return AE_BAD_ADDRESS; + unmap = true; } + if (!value) value = &dummy; @@ -666,6 +670,8 @@ acpi_os_read_memory(acpi_physical_address phys_addr, u32 * value, u32 width) if (unmap) iounmap(virt_addr); + else + rcu_read_unlock(); return AE_OK; } @@ -674,14 +680,17 @@ acpi_status acpi_os_write_memory(acpi_physical_address phys_addr, u32 value, u32 width) { void __iomem *virt_addr; - int size = width / 8, unmap = 0; + unsigned int size = width / 8; + bool unmap = false; rcu_read_lock(); virt_addr = acpi_map_vaddr_lookup(phys_addr, size); - rcu_read_unlock(); if (!virt_addr) { + rcu_read_unlock(); virt_addr = acpi_os_ioremap(phys_addr, size); - unmap = 1; + if (!virt_addr) + return AE_BAD_ADDRESS; + unmap = true; } switch (width) { @@ -700,6 +709,8 @@ acpi_os_write_memory(acpi_physical_address phys_addr, u32 value, u32 width) if (unmap) iounmap(virt_addr); + else + rcu_read_unlock(); return AE_OK; } diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 42d3d72..5af3479 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -82,6 +82,11 @@ long acpi_is_video_device(struct acpi_device *device) if (!device) return 0; + /* Is this device able to support video switching ? */ + if (ACPI_SUCCESS(acpi_get_handle(device->handle, "_DOD", &h_dummy)) || + ACPI_SUCCESS(acpi_get_handle(device->handle, "_DOS", &h_dummy))) + video_caps |= ACPI_VIDEO_OUTPUT_SWITCHING; + /* Is this device able to retrieve a video ROM ? */ if (ACPI_SUCCESS(acpi_get_handle(device->handle, "_ROM", &h_dummy))) video_caps |= ACPI_VIDEO_ROM_AVAILABLE; diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c index ed65014..7bfbe40 100644 --- a/drivers/acpi/wakeup.c +++ b/drivers/acpi/wakeup.c @@ -86,8 +86,12 @@ int __init acpi_wakeup_device_init(void) struct acpi_device *dev = container_of(node, struct acpi_device, wakeup_list); - if (device_can_wakeup(&dev->dev)) + if (device_can_wakeup(&dev->dev)) { + /* Button GPEs are supposed to be always enabled. */ + acpi_enable_gpe(dev->wakeup.gpe_device, + dev->wakeup.gpe_number); device_set_wakeup_enable(&dev->dev, true); + } } mutex_unlock(&acpi_device_lock); return 0; diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 73fb1c4..25ef1a4 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -866,8 +866,9 @@ static int popen(struct atm_vcc *vcc) } skb = alloc_skb(sizeof(*header), GFP_ATOMIC); - if (!skb && net_ratelimit()) { - dev_warn(&card->dev->dev, "Failed to allocate sk_buff in popen()\n"); + if (!skb) { + if (net_ratelimit()) + dev_warn(&card->dev->dev, "Failed to allocate sk_buff in popen()\n"); return -ENOMEM; } header = (void *)skb_put(skb, sizeof(*header)); diff --git a/drivers/block/Makefile b/drivers/block/Makefile index d7f463d..40528ba 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -39,4 +39,4 @@ obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o obj-$(CONFIG_BLK_DEV_DRBD) += drbd/ obj-$(CONFIG_BLK_DEV_RBD) += rbd.o -swim_mod-objs := swim.o swim_asm.o +swim_mod-y := swim.o swim_asm.o diff --git a/drivers/block/aoe/Makefile b/drivers/block/aoe/Makefile index e76d997..06ea82c 100644 --- a/drivers/block/aoe/Makefile +++ b/drivers/block/aoe/Makefile @@ -3,4 +3,4 @@ # obj-$(CONFIG_ATA_OVER_ETH) += aoe.o -aoe-objs := aoeblk.o aoechr.o aoecmd.o aoedev.o aoemain.o aoenet.o +aoe-y := aoeblk.o aoechr.o aoecmd.o aoedev.o aoemain.o aoenet.o diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index 516d5bb..9279272 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -2833,7 +2833,7 @@ static int cciss_revalidate(struct gendisk *disk) sector_t total_size; InquiryData_struct *inq_buff = NULL; - for (logvol = 0; logvol < CISS_MAX_LUN; logvol++) { + for (logvol = 0; logvol <= h->highest_lun; logvol++) { if (!h->drv[logvol]) continue; if (memcmp(h->drv[logvol]->LunID, drv->LunID, diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b9ba04f..77fc76f 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3281,7 +3281,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, struct block_device *bdev = opened_bdev[cnt]; if (!bdev || ITYPE(drive_state[cnt].fd_device) != type) continue; - __invalidate_device(bdev); + __invalidate_device(bdev, true); } mutex_unlock(&open_lock); } else { diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 44e18c0..dbf31ec 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -78,7 +78,6 @@ #include <asm/uaccess.h> -static DEFINE_MUTEX(loop_mutex); static LIST_HEAD(loop_devices); static DEFINE_MUTEX(loop_devices_mutex); @@ -1501,11 +1500,9 @@ static int lo_open(struct block_device *bdev, fmode_t mode) { struct loop_device *lo = bdev->bd_disk->private_data; - mutex_lock(&loop_mutex); mutex_lock(&lo->lo_ctl_mutex); lo->lo_refcnt++; mutex_unlock(&lo->lo_ctl_mutex); - mutex_unlock(&loop_mutex); return 0; } @@ -1515,7 +1512,6 @@ static int lo_release(struct gendisk *disk, fmode_t mode) struct loop_device *lo = disk->private_data; int err; - mutex_lock(&loop_mutex); mutex_lock(&lo->lo_ctl_mutex); if (--lo->lo_refcnt) @@ -1540,7 +1536,6 @@ static int lo_release(struct gendisk *disk, fmode_t mode) out: mutex_unlock(&lo->lo_ctl_mutex); out_unlocked: - mutex_unlock(&loop_mutex); return 0; } @@ -1641,6 +1636,9 @@ out: static void loop_free(struct loop_device *lo) { + if (!lo->lo_queue->queue_lock) + lo->lo_queue->queue_lock = &lo->lo_queue->__queue_lock; + blk_cleanup_queue(lo->lo_queue); put_disk(lo->lo_disk); list_del(&lo->lo_list); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index a32fb41..e6fc716 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -53,7 +53,6 @@ #define DBG_BLKDEV 0x0100 #define DBG_RX 0x0200 #define DBG_TX 0x0400 -static DEFINE_MUTEX(nbd_mutex); static unsigned int debugflags; #endif /* NDEBUG */ @@ -718,11 +717,9 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode, dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n", lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg); - mutex_lock(&nbd_mutex); mutex_lock(&lo->tx_lock); error = __nbd_ioctl(bdev, lo, cmd, arg); mutex_unlock(&lo->tx_lock); - mutex_unlock(&nbd_mutex); return error; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index d7aa39e..9cb8668 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -120,6 +120,10 @@ static DEFINE_SPINLOCK(minor_lock); #define EXTENDED (1<<EXT_SHIFT) #define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED)) #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED)) +#define EMULATED_HD_DISK_MINOR_OFFSET (0) +#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256) +#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16)) +#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4) #define DEV_NAME "xvd" /* name in /dev */ @@ -281,7 +285,7 @@ static int blkif_queue_request(struct request *req) info->shadow[id].request = req; ring_req->id = id; - ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req); + ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req); ring_req->handle = info->handle; ring_req->operation = rq_data_dir(req) ? @@ -317,7 +321,7 @@ static int blkif_queue_request(struct request *req) rq_data_dir(req) ); info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn); - ring_req->seg[i] = + ring_req->u.rw.seg[i] = (struct blkif_request_segment) { .gref = ref, .first_sect = fsect, @@ -434,6 +438,65 @@ static void xlvbd_flush(struct blkfront_info *info) info->feature_flush ? "enabled" : "disabled"); } +static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset) +{ + int major; + major = BLKIF_MAJOR(vdevice); + *minor = BLKIF_MINOR(vdevice); + switch (major) { + case XEN_IDE0_MAJOR: + *offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET; + *minor = ((*minor / 64) * PARTS_PER_DISK) + + EMULATED_HD_DISK_MINOR_OFFSET; + break; + case XEN_IDE1_MAJOR: + *offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET; + *minor = (((*minor / 64) + 2) * PARTS_PER_DISK) + + EMULATED_HD_DISK_MINOR_OFFSET; + break; + case XEN_SCSI_DISK0_MAJOR: + *offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET; + *minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET; + break; + case XEN_SCSI_DISK1_MAJOR: + case XEN_SCSI_DISK2_MAJOR: + case XEN_SCSI_DISK3_MAJOR: + case XEN_SCSI_DISK4_MAJOR: + case XEN_SCSI_DISK5_MAJOR: + case XEN_SCSI_DISK6_MAJOR: + case XEN_SCSI_DISK7_MAJOR: + *offset = (*minor / PARTS_PER_DISK) + + ((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) + + EMULATED_SD_DISK_NAME_OFFSET; + *minor = *minor + + ((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) + + EMULATED_SD_DISK_MINOR_OFFSET; + break; + case XEN_SCSI_DISK8_MAJOR: + case XEN_SCSI_DISK9_MAJOR: + case XEN_SCSI_DISK10_MAJOR: + case XEN_SCSI_DISK11_MAJOR: + case XEN_SCSI_DISK12_MAJOR: + case XEN_SCSI_DISK13_MAJOR: + case XEN_SCSI_DISK14_MAJOR: + case XEN_SCSI_DISK15_MAJOR: + *offset = (*minor / PARTS_PER_DISK) + + ((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) + + EMULATED_SD_DISK_NAME_OFFSET; + *minor = *minor + + ((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) + + EMULATED_SD_DISK_MINOR_OFFSET; + break; + case XENVBD_MAJOR: + *offset = *minor / PARTS_PER_DISK; + break; + default: + printk(KERN_WARNING "blkfront: your disk configuration is " + "incorrect, please use an xvd device instead\n"); + return -ENODEV; + } + return 0; +} static int xlvbd_alloc_gendisk(blkif_sector_t capacity, struct blkfront_info *info, @@ -441,7 +504,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, { struct gendisk *gd; int nr_minors = 1; - int err = -ENODEV; + int err; unsigned int offset; int minor; int nr_parts; @@ -456,12 +519,20 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, } if (!VDEV_IS_EXTENDED(info->vdevice)) { - minor = BLKIF_MINOR(info->vdevice); - nr_parts = PARTS_PER_DISK; + err = xen_translate_vdev(info->vdevice, &minor, &offset); + if (err) + return err; + nr_parts = PARTS_PER_DISK; } else { minor = BLKIF_MINOR_EXT(info->vdevice); nr_parts = PARTS_PER_EXT_DISK; + offset = minor / nr_parts; + if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4) + printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with " + "emulated IDE disks,\n\t choose an xvd device name" + "from xvde on\n", info->vdevice); } + err = -ENODEV; if ((minor % nr_parts) == 0) nr_minors = nr_parts; @@ -475,8 +546,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, if (gd == NULL) goto release; - offset = minor / nr_parts; - if (nr_minors > 1) { if (offset < 26) sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset); @@ -615,7 +684,7 @@ static void blkif_completion(struct blk_shadow *s) { int i; for (i = 0; i < s->req.nr_segments; i++) - gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL); + gnttab_end_foreign_access(s->req.u.rw.seg[i].gref, 0, 0UL); } static irqreturn_t blkif_interrupt(int irq, void *dev_id) @@ -932,7 +1001,7 @@ static int blkif_recover(struct blkfront_info *info) /* Rewrite any grant references invalidated by susp/resume. */ for (j = 0; j < req->nr_segments; j++) gnttab_grant_foreign_access_ref( - req->seg[j].gref, + req->u.rw.seg[j].gref, info->xbdev->otherend_id, pfn_to_mfn(info->shadow[req->id].frame[j]), rq_data_dir(info->shadow[req->id].request)); diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index a126e61..6dcd55a 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -39,6 +39,11 @@ static struct usb_device_id ath3k_table[] = { /* Atheros AR3011 with sflash firmware*/ { USB_DEVICE(0x0CF3, 0x3002) }, + /* Atheros AR9285 Malbec with sflash firmware */ + { USB_DEVICE(0x03F0, 0x311D) }, + + /* Atheros AR5BBU12 with sflash firmware */ + { USB_DEVICE(0x0489, 0xE02C) }, { } /* Terminating entry */ }; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 1da773f8..700a384 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -102,6 +102,12 @@ static struct usb_device_id blacklist_table[] = { /* Atheros 3011 with sflash firmware */ { USB_DEVICE(0x0cf3, 0x3002), .driver_info = BTUSB_IGNORE }, + /* Atheros AR9285 Malbec with sflash firmware */ + { USB_DEVICE(0x03f0, 0x311d), .driver_info = BTUSB_IGNORE }, + + /* Atheros AR5BBU12 with sflash firmware */ + { USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE }, + /* Broadcom BCM2035 */ { USB_DEVICE(0x0a5c, 0x2035), .driver_info = BTUSB_WRONG_SCO_MTU }, { USB_DEVICE(0x0a5c, 0x200a), .driver_info = BTUSB_WRONG_SCO_MTU }, @@ -826,7 +832,7 @@ static void btusb_work(struct work_struct *work) if (hdev->conn_hash.sco_num > 0) { if (!test_bit(BTUSB_DID_ISO_RESUME, &data->flags)) { - err = usb_autopm_get_interface(data->isoc); + err = usb_autopm_get_interface(data->isoc ? data->isoc : data->intf); if (err < 0) { clear_bit(BTUSB_ISOC_RUNNING, &data->flags); usb_kill_anchored_urbs(&data->isoc_anchor); @@ -855,7 +861,7 @@ static void btusb_work(struct work_struct *work) __set_isoc_interface(hdev, 0); if (test_and_clear_bit(BTUSB_DID_ISO_RESUME, &data->flags)) - usb_autopm_put_interface(data->isoc); + usb_autopm_put_interface(data->isoc ? data->isoc : data->intf); } } @@ -1038,8 +1044,6 @@ static int btusb_probe(struct usb_interface *intf, usb_set_intfdata(intf, data); - usb_enable_autosuspend(interface_to_usbdev(intf)); - return 0; } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 14033a36..e2c48a7 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -409,7 +409,8 @@ int register_cdrom(struct cdrom_device_info *cdi) } ENSURE(drive_status, CDC_DRIVE_STATUS ); - ENSURE(media_changed, CDC_MEDIA_CHANGED); + if (cdo->check_events == NULL && cdo->media_changed == NULL) + *change_capability = ~(CDC_MEDIA_CHANGED | CDC_SELECT_DISC); ENSURE(tray_move, CDC_CLOSE_TRAY | CDC_OPEN_TRAY); ENSURE(lock_door, CDC_LOCK); ENSURE(select_speed, CDC_SELECT_SPEED); diff --git a/drivers/char/Makefile b/drivers/char/Makefile index 5bc765d..8238f89 100644 --- a/drivers/char/Makefile +++ b/drivers/char/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_SYNCLINK_GT) += synclink_gt.o obj-$(CONFIG_AMIGA_BUILTIN_SERIAL) += amiserial.o obj-$(CONFIG_SX) += sx.o generic_serial.o obj-$(CONFIG_RIO) += rio/ generic_serial.o +obj-$(CONFIG_VIRTIO_CONSOLE) += virtio_console.o obj-$(CONFIG_RAW_DRIVER) += raw.o obj-$(CONFIG_SGI_SNSC) += snsc.o snsc_event.o obj-$(CONFIG_MSPEC) += mspec.o diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig index fcd867d..d8b1b57 100644 --- a/drivers/char/agp/Kconfig +++ b/drivers/char/agp/Kconfig @@ -50,7 +50,7 @@ config AGP_ATI config AGP_AMD tristate "AMD Irongate, 761, and 762 chipset support" - depends on AGP && (X86_32 || ALPHA) + depends on AGP && X86_32 help This option gives you AGP support for the GLX component of X on AMD Irongate, 761, and 762 chipsets. diff --git a/drivers/char/agp/amd-k7-agp.c b/drivers/char/agp/amd-k7-agp.c index b1b4362..45681c0 100644 --- a/drivers/char/agp/amd-k7-agp.c +++ b/drivers/char/agp/amd-k7-agp.c @@ -41,22 +41,8 @@ static int amd_create_page_map(struct amd_page_map *page_map) if (page_map->real == NULL) return -ENOMEM; -#ifndef CONFIG_X86 - SetPageReserved(virt_to_page(page_map->real)); - global_cache_flush(); - page_map->remapped = ioremap_nocache(virt_to_phys(page_map->real), - PAGE_SIZE); - if (page_map->remapped == NULL) { - ClearPageReserved(virt_to_page(page_map->real)); - free_page((unsigned long) page_map->real); - page_map->real = NULL; - return -ENOMEM; - } - global_cache_flush(); -#else set_memory_uc((unsigned long)page_map->real, 1); page_map->remapped = page_map->real; -#endif for (i = 0; i < PAGE_SIZE / sizeof(unsigned long); i++) { writel(agp_bridge->scratch_page, page_map->remapped+i); @@ -68,12 +54,7 @@ static int amd_create_page_map(struct amd_page_map *page_map) static void amd_free_page_map(struct amd_page_map *page_map) { -#ifndef CONFIG_X86 - iounmap(page_map->remapped); - ClearPageReserved(virt_to_page(page_map->real)); -#else set_memory_wb((unsigned long)page_map->real, 1); -#endif free_page((unsigned long) page_map->real); } diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index 9252e85..780498d 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -773,18 +773,23 @@ int __init agp_amd64_init(void) #else printk(KERN_INFO PFX "You can boot with agp=try_unsupported\n"); #endif + pci_unregister_driver(&agp_amd64_pci_driver); return -ENODEV; } /* First check that we have at least one AMD64 NB */ - if (!pci_dev_present(amd_nb_misc_ids)) + if (!pci_dev_present(amd_nb_misc_ids)) { + pci_unregister_driver(&agp_amd64_pci_driver); return -ENODEV; + } /* Look for any AGP bridge */ agp_amd64_pci_driver.id_table = agp_amd64_pci_promisc_table; err = driver_attach(&agp_amd64_pci_driver.driver); - if (err == 0 && agp_bridges_found == 0) + if (err == 0 && agp_bridges_found == 0) { + pci_unregister_driver(&agp_amd64_pci_driver); err = -ENODEV; + } } return err; } diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 857df10..b0a0dcc 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -774,20 +774,14 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, dev_info(&pdev->dev, "Intel %s Chipset\n", intel_agp_chipsets[i].name); /* - * If the device has not been properly setup, the following will catch - * the problem and should stop the system from crashing. - * 20030610 - hamish@zot.org - */ - if (pci_enable_device(pdev)) { - dev_err(&pdev->dev, "can't enable PCI device\n"); - agp_put_bridge(bridge); - return -ENODEV; - } - - /* * The following fixes the case where the BIOS has "forgotten" to * provide an address range for the GART. * 20030610 - hamish@zot.org + * This happens before pci_enable_device() intentionally; + * calling pci_enable_device() before assigning the resource + * will result in the GART being disabled on machines with such + * BIOSs (the GART ends up with a BAR starting at 0, which + * conflicts a lot of other devices). */ r = &pdev->resource[0]; if (!r->start && r->end) { @@ -798,6 +792,17 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, } } + /* + * If the device has not been properly setup, the following will catch + * the problem and should stop the system from crashing. + * 20030610 - hamish@zot.org + */ + if (pci_enable_device(pdev)) { + dev_err(&pdev->dev, "can't enable PCI device\n"); + agp_put_bridge(bridge); + return -ENODEV; + } + /* Fill in the mode register */ if (cap_ptr) { pci_read_config_dword(pdev, diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h index c195bfe..5feebe2 100644 --- a/drivers/char/agp/intel-agp.h +++ b/drivers/char/agp/intel-agp.h @@ -130,6 +130,7 @@ #define INTEL_GMCH_GMS_STOLEN_352M (0xd << 4) #define I915_IFPADDR 0x60 +#define I830_HIC 0x70 /* Intel 965G registers */ #define I965_MSAC 0x62 diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index fab3d32..0d09b53 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -21,6 +21,7 @@ #include <linux/kernel.h> #include <linux/pagemap.h> #include <linux/agp_backend.h> +#include <linux/delay.h> #include <asm/smp.h> #include "agp.h" #include "intel-agp.h" @@ -70,12 +71,8 @@ static struct _intel_private { u32 __iomem *gtt; /* I915G */ bool clear_fake_agp; /* on first access via agp, fill with scratch */ int num_dcache_entries; - union { - void __iomem *i9xx_flush_page; - void *i8xx_flush_page; - }; + void __iomem *i9xx_flush_page; char *i81x_gtt_table; - struct page *i8xx_page; struct resource ifp_resource; int resource_valid; struct page *scratch_page; @@ -722,28 +719,6 @@ static int intel_fake_agp_fetch_size(void) static void i830_cleanup(void) { - if (intel_private.i8xx_flush_page) { - kunmap(intel_private.i8xx_flush_page); - intel_private.i8xx_flush_page = NULL; - } - - __free_page(intel_private.i8xx_page); - intel_private.i8xx_page = NULL; -} - -static void intel_i830_setup_flush(void) -{ - /* return if we've already set the flush mechanism up */ - if (intel_private.i8xx_page) - return; - - intel_private.i8xx_page = alloc_page(GFP_KERNEL); - if (!intel_private.i8xx_page) - return; - - intel_private.i8xx_flush_page = kmap(intel_private.i8xx_page); - if (!intel_private.i8xx_flush_page) - i830_cleanup(); } /* The chipset_flush interface needs to get data that has already been @@ -758,14 +733,27 @@ static void intel_i830_setup_flush(void) */ static void i830_chipset_flush(void) { - unsigned int *pg = intel_private.i8xx_flush_page; + unsigned long timeout = jiffies + msecs_to_jiffies(1000); + + /* Forcibly evict everything from the CPU write buffers. + * clflush appears to be insufficient. + */ + wbinvd_on_all_cpus(); + + /* Now we've only seen documents for this magic bit on 855GM, + * we hope it exists for the other gen2 chipsets... + * + * Also works as advertised on my 845G. + */ + writel(readl(intel_private.registers+I830_HIC) | (1<<31), + intel_private.registers+I830_HIC); - memset(pg, 0, 1024); + while (readl(intel_private.registers+I830_HIC) & (1<<31)) { + if (time_after(jiffies, timeout)) + break; - if (cpu_has_clflush) - clflush_cache_range(pg, 1024); - else if (wbinvd_on_all_cpus() != 0) - printk(KERN_ERR "Timed out waiting for cache flush.\n"); + udelay(50); + } } static void i830_write_entry(dma_addr_t addr, unsigned int entry, @@ -849,8 +837,6 @@ static int i830_setup(void) intel_private.gtt_bus_addr = reg_addr + I810_PTE_BASE; - intel_i830_setup_flush(); - return 0; } diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index b6ae6e9..62787e3 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -320,6 +320,7 @@ static int unload_when_empty = 1; static int add_smi(struct smi_info *smi); static int try_smi_init(struct smi_info *smi); static void cleanup_one_si(struct smi_info *to_clean); +static void cleanup_ipmi_si(void); static ATOMIC_NOTIFIER_HEAD(xaction_notifier_list); static int register_xaction_notifier(struct notifier_block *nb) @@ -899,6 +900,14 @@ static void sender(void *send_info, printk("**Enqueue: %d.%9.9d\n", t.tv_sec, t.tv_usec); #endif + /* + * last_timeout_jiffies is updated here to avoid + * smi_timeout() handler passing very large time_diff + * value to smi_event_handler() that causes + * the send command to abort. + */ + smi_info->last_timeout_jiffies = jiffies; + mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES); if (smi_info->thread) @@ -3450,16 +3459,7 @@ static int __devinit init_ipmi_si(void) mutex_lock(&smi_infos_lock); if (unload_when_empty && list_empty(&smi_infos)) { mutex_unlock(&smi_infos_lock); -#ifdef CONFIG_PCI - if (pci_registered) - pci_unregister_driver(&ipmi_pci_driver); -#endif - -#ifdef CONFIG_PPC_OF - if (of_registered) - of_unregister_platform_driver(&ipmi_of_platform_driver); -#endif - driver_unregister(&ipmi_driver.driver); + cleanup_ipmi_si(); printk(KERN_WARNING PFX "Unable to find any System Interface(s)\n"); return -ENODEV; diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c index 777181a..bcbbc71 100644 --- a/drivers/char/pcmcia/cm4000_cs.c +++ b/drivers/char/pcmcia/cm4000_cs.c @@ -830,8 +830,7 @@ static void monitor_card(unsigned long p) test_bit(IS_ANY_T1, &dev->flags))) { DEBUGP(4, dev, "Perform AUTOPPS\n"); set_bit(IS_AUTOPPS_ACT, &dev->flags); - ptsreq.protocol = ptsreq.protocol = - (0x01 << dev->proto); + ptsreq.protocol = (0x01 << dev->proto); ptsreq.flags = 0x01; ptsreq.pts1 = 0x00; ptsreq.pts2 = 0x00; diff --git a/drivers/char/pcmcia/ipwireless/main.c b/drivers/char/pcmcia/ipwireless/main.c index 94b8eb4..444155a 100644 --- a/drivers/char/pcmcia/ipwireless/main.c +++ b/drivers/char/pcmcia/ipwireless/main.c @@ -78,7 +78,6 @@ static void signalled_reboot_callback(void *callback_data) static int ipwireless_probe(struct pcmcia_device *p_dev, void *priv_data) { struct ipw_dev *ipw = priv_data; - struct resource *io_resource; int ret; p_dev->resource[0]->flags &= ~IO_DATA_PATH_WIDTH; @@ -92,9 +91,12 @@ static int ipwireless_probe(struct pcmcia_device *p_dev, void *priv_data) if (ret) return ret; - io_resource = request_region(p_dev->resource[0]->start, - resource_size(p_dev->resource[0]), - IPWIRELESS_PCCARD_NAME); + if (!request_region(p_dev->resource[0]->start, + resource_size(p_dev->resource[0]), + IPWIRELESS_PCCARD_NAME)) { + ret = -EBUSY; + goto exit; + } p_dev->resource[2]->flags |= WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_CM | WIN_ENABLE; @@ -105,22 +107,25 @@ static int ipwireless_probe(struct pcmcia_device *p_dev, void *priv_data) ret = pcmcia_map_mem_page(p_dev, p_dev->resource[2], p_dev->card_addr); if (ret != 0) - goto exit2; + goto exit1; ipw->is_v2_card = resource_size(p_dev->resource[2]) == 0x100; - ipw->attr_memory = ioremap(p_dev->resource[2]->start, + ipw->common_memory = ioremap(p_dev->resource[2]->start, resource_size(p_dev->resource[2])); - request_mem_region(p_dev->resource[2]->start, - resource_size(p_dev->resource[2]), - IPWIRELESS_PCCARD_NAME); + if (!request_mem_region(p_dev->resource[2]->start, + resource_size(p_dev->resource[2]), + IPWIRELESS_PCCARD_NAME)) { + ret = -EBUSY; + goto exit2; + } p_dev->resource[3]->flags |= WIN_DATA_WIDTH_16 | WIN_MEMORY_TYPE_AM | WIN_ENABLE; p_dev->resource[3]->end = 0; /* this used to be 0x1000 */ ret = pcmcia_request_window(p_dev, p_dev->resource[3], 0); if (ret != 0) - goto exit2; + goto exit3; ret = pcmcia_map_mem_page(p_dev, p_dev->resource[3], 0); if (ret != 0) @@ -128,23 +133,28 @@ static int ipwireless_probe(struct pcmcia_device *p_dev, void *priv_data) ipw->attr_memory = ioremap(p_dev->resource[3]->start, resource_size(p_dev->resource[3])); - request_mem_region(p_dev->resource[3]->start, - resource_size(p_dev->resource[3]), - IPWIRELESS_PCCARD_NAME); + if (!request_mem_region(p_dev->resource[3]->start, + resource_size(p_dev->resource[3]), + IPWIRELESS_PCCARD_NAME)) { + ret = -EBUSY; + goto exit4; + } return 0; +exit4: + iounmap(ipw->attr_memory); exit3: + release_mem_region(p_dev->resource[2]->start, + resource_size(p_dev->resource[2])); exit2: - if (ipw->common_memory) { - release_mem_region(p_dev->resource[2]->start, - resource_size(p_dev->resource[2])); - iounmap(ipw->common_memory); - } + iounmap(ipw->common_memory); exit1: - release_resource(io_resource); + release_region(p_dev->resource[0]->start, + resource_size(p_dev->resource[0])); +exit: pcmcia_disable_device(p_dev); - return -1; + return ret; } static int config_ipwireless(struct ipw_dev *ipw) @@ -219,6 +229,8 @@ exit: static void release_ipwireless(struct ipw_dev *ipw) { + release_region(ipw->link->resource[0]->start, + resource_size(ipw->link->resource[0])); if (ipw->common_memory) { release_mem_region(ipw->link->resource[2]->start, resource_size(ipw->link->resource[2])); diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index 36e0fa1..1f46f1c 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -364,14 +364,12 @@ unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, tpm_protected_ordinal_duration[ordinal & TPM_PROTECTED_ORDINAL_MASK]; - if (duration_idx != TPM_UNDEFINED) { + if (duration_idx != TPM_UNDEFINED) duration = chip->vendor.duration[duration_idx]; - /* if duration is 0, it's because chip->vendor.duration wasn't */ - /* filled yet, so we set the lowest timeout just to give enough */ - /* time for tpm_get_timeouts() to succeed */ - return (duration <= 0 ? HZ : duration); - } else + if (duration <= 0) return 2 * 60 * HZ; + else + return duration; } EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration); diff --git a/drivers/tty/hvc/virtio_console.c b/drivers/char/virtio_console.c index 896a2ce..84b164d 100644 --- a/drivers/tty/hvc/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1,6 +1,7 @@ /* * Copyright (C) 2006, 2007, 2009 Rusty Russell, IBM Corporation - * Copyright (C) 2009, 2010 Red Hat, Inc. + * Copyright (C) 2009, 2010, 2011 Red Hat, Inc. + * Copyright (C) 2009, 2010, 2011 Amit Shah <amit.shah@redhat.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -31,7 +32,7 @@ #include <linux/virtio_console.h> #include <linux/wait.h> #include <linux/workqueue.h> -#include "hvc_console.h" +#include "../tty/hvc/hvc_console.h" /* * This is a global struct for storing common data for all the devices @@ -387,6 +388,10 @@ static void discard_port_data(struct port *port) unsigned int len; int ret; + if (!port->portdev) { + /* Device has been unplugged. vqs are already gone. */ + return; + } vq = port->in_vq; if (port->inbuf) buf = port->inbuf; @@ -469,6 +474,10 @@ static void reclaim_consumed_buffers(struct port *port) void *buf; unsigned int len; + if (!port->portdev) { + /* Device has been unplugged. vqs are already gone. */ + return; + } while ((buf = virtqueue_get_buf(port->out_vq, &len))) { kfree(buf); port->outvq_full = false; @@ -1462,6 +1471,17 @@ static void control_work_handler(struct work_struct *work) spin_unlock(&portdev->cvq_lock); } +static void out_intr(struct virtqueue *vq) +{ + struct port *port; + + port = find_port_by_vq(vq->vdev->priv, vq); + if (!port) + return; + + wake_up_interruptible(&port->waitqueue); +} + static void in_intr(struct virtqueue *vq) { struct port *port; @@ -1566,7 +1586,7 @@ static int init_vqs(struct ports_device *portdev) */ j = 0; io_callbacks[j] = in_intr; - io_callbacks[j + 1] = NULL; + io_callbacks[j + 1] = out_intr; io_names[j] = "input"; io_names[j + 1] = "output"; j += 2; @@ -1580,7 +1600,7 @@ static int init_vqs(struct ports_device *portdev) for (i = 1; i < nr_ports; i++) { j += 2; io_callbacks[j] = in_intr; - io_callbacks[j + 1] = NULL; + io_callbacks[j + 1] = out_intr; io_names[j] = "input"; io_names[j + 1] = "output"; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 1109f68..5cb4d09 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1919,8 +1919,10 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) ret = sysdev_driver_register(&cpu_sysdev_class, &cpufreq_sysdev_driver); + if (ret) + goto err_null_driver; - if ((!ret) && !(cpufreq_driver->flags & CPUFREQ_STICKY)) { + if (!(cpufreq_driver->flags & CPUFREQ_STICKY)) { int i; ret = -ENODEV; @@ -1935,21 +1937,22 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) if (ret) { dprintk("no CPU initialized for driver %s\n", driver_data->name); - sysdev_driver_unregister(&cpu_sysdev_class, - &cpufreq_sysdev_driver); - - spin_lock_irqsave(&cpufreq_driver_lock, flags); - cpufreq_driver = NULL; - spin_unlock_irqrestore(&cpufreq_driver_lock, flags); + goto err_sysdev_unreg; } } - if (!ret) { - register_hotcpu_notifier(&cpufreq_cpu_notifier); - dprintk("driver %s up and running\n", driver_data->name); - cpufreq_debug_enable_ratelimit(); - } + register_hotcpu_notifier(&cpufreq_cpu_notifier); + dprintk("driver %s up and running\n", driver_data->name); + cpufreq_debug_enable_ratelimit(); + return 0; +err_sysdev_unreg: + sysdev_driver_unregister(&cpu_sysdev_class, + &cpufreq_sysdev_driver); +err_null_driver: + spin_lock_irqsave(&cpufreq_driver_lock, flags); + cpufreq_driver = NULL; + spin_unlock_irqrestore(&cpufreq_driver_lock, flags); return ret; } EXPORT_SYMBOL_GPL(cpufreq_register_driver); diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index 297f48b..07bca49 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -79,6 +79,7 @@ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/slab.h> +#include <linux/delay.h> #include <linux/dmapool.h> #include <linux/dmaengine.h> #include <linux/amba/bus.h> @@ -235,16 +236,19 @@ static void pl08x_start_txd(struct pl08x_dma_chan *plchan, } /* - * Overall DMAC remains enabled always. + * Pause the channel by setting the HALT bit. * - * Disabling individual channels could lose data. + * For M->P transfers, pause the DMAC first and then stop the peripheral - + * the FIFO can only drain if the peripheral is still requesting data. + * (note: this can still timeout if the DMAC FIFO never drains of data.) * - * Disable the peripheral DMA after disabling the DMAC in order to allow - * the DMAC FIFO to drain, and hence allow the channel to show inactive + * For P->M transfers, disable the peripheral first to stop it filling + * the DMAC FIFO, and then pause the DMAC. */ static void pl08x_pause_phy_chan(struct pl08x_phy_chan *ch) { u32 val; + int timeout; /* Set the HALT bit and wait for the FIFO to drain */ val = readl(ch->base + PL080_CH_CONFIG); @@ -252,8 +256,13 @@ static void pl08x_pause_phy_chan(struct pl08x_phy_chan *ch) writel(val, ch->base + PL080_CH_CONFIG); /* Wait for channel inactive */ - while (pl08x_phy_channel_busy(ch)) - cpu_relax(); + for (timeout = 1000; timeout; timeout--) { + if (!pl08x_phy_channel_busy(ch)) + break; + udelay(1); + } + if (pl08x_phy_channel_busy(ch)) + pr_err("pl08x: channel%u timeout waiting for pause\n", ch->id); } static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch) @@ -267,19 +276,24 @@ static void pl08x_resume_phy_chan(struct pl08x_phy_chan *ch) } -/* Stops the channel */ -static void pl08x_stop_phy_chan(struct pl08x_phy_chan *ch) +/* + * pl08x_terminate_phy_chan() stops the channel, clears the FIFO and + * clears any pending interrupt status. This should not be used for + * an on-going transfer, but as a method of shutting down a channel + * (eg, when it's no longer used) or terminating a transfer. + */ +static void pl08x_terminate_phy_chan(struct pl08x_driver_data *pl08x, + struct pl08x_phy_chan *ch) { - u32 val; + u32 val = readl(ch->base + PL080_CH_CONFIG); - pl08x_pause_phy_chan(ch); + val &= ~(PL080_CONFIG_ENABLE | PL080_CONFIG_ERR_IRQ_MASK | + PL080_CONFIG_TC_IRQ_MASK); - /* Disable channel */ - val = readl(ch->base + PL080_CH_CONFIG); - val &= ~PL080_CONFIG_ENABLE; - val &= ~PL080_CONFIG_ERR_IRQ_MASK; - val &= ~PL080_CONFIG_TC_IRQ_MASK; writel(val, ch->base + PL080_CH_CONFIG); + + writel(1 << ch->id, pl08x->base + PL080_ERR_CLEAR); + writel(1 << ch->id, pl08x->base + PL080_TC_CLEAR); } static inline u32 get_bytes_in_cctl(u32 cctl) @@ -404,13 +418,12 @@ static inline void pl08x_put_phy_channel(struct pl08x_driver_data *pl08x, { unsigned long flags; + spin_lock_irqsave(&ch->lock, flags); + /* Stop the channel and clear its interrupts */ - pl08x_stop_phy_chan(ch); - writel((1 << ch->id), pl08x->base + PL080_ERR_CLEAR); - writel((1 << ch->id), pl08x->base + PL080_TC_CLEAR); + pl08x_terminate_phy_chan(pl08x, ch); /* Mark it as free */ - spin_lock_irqsave(&ch->lock, flags); ch->serving = NULL; spin_unlock_irqrestore(&ch->lock, flags); } @@ -1449,7 +1462,7 @@ static int pl08x_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, plchan->state = PL08X_CHAN_IDLE; if (plchan->phychan) { - pl08x_stop_phy_chan(plchan->phychan); + pl08x_terminate_phy_chan(pl08x, plchan->phychan); /* * Mark physical channel as free and free any slave diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index e53d438..e18eaab 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -49,6 +49,7 @@ struct imxdma_channel { struct imxdma_engine { struct device *dev; + struct device_dma_parameters dma_parms; struct dma_device dma_device; struct imxdma_channel channel[MAX_DMA_CHANNELS]; }; @@ -242,6 +243,21 @@ static struct dma_async_tx_descriptor *imxdma_prep_slave_sg( else dmamode = DMA_MODE_WRITE; + switch (imxdmac->word_size) { + case DMA_SLAVE_BUSWIDTH_4_BYTES: + if (sgl->length & 3 || sgl->dma_address & 3) + return NULL; + break; + case DMA_SLAVE_BUSWIDTH_2_BYTES: + if (sgl->length & 1 || sgl->dma_address & 1) + return NULL; + break; + case DMA_SLAVE_BUSWIDTH_1_BYTE: + break; + default: + return NULL; + } + ret = imx_dma_setup_sg(imxdmac->imxdma_channel, sgl, sg_len, dma_length, imxdmac->per_address, dmamode); if (ret) @@ -329,6 +345,9 @@ static int __init imxdma_probe(struct platform_device *pdev) INIT_LIST_HEAD(&imxdma->dma_device.channels); + dma_cap_set(DMA_SLAVE, imxdma->dma_device.cap_mask); + dma_cap_set(DMA_CYCLIC, imxdma->dma_device.cap_mask); + /* Initialize channel parameters */ for (i = 0; i < MAX_DMA_CHANNELS; i++) { struct imxdma_channel *imxdmac = &imxdma->channel[i]; @@ -346,11 +365,7 @@ static int __init imxdma_probe(struct platform_device *pdev) imxdmac->imxdma = imxdma; spin_lock_init(&imxdmac->lock); - dma_cap_set(DMA_SLAVE, imxdma->dma_device.cap_mask); - dma_cap_set(DMA_CYCLIC, imxdma->dma_device.cap_mask); - imxdmac->chan.device = &imxdma->dma_device; - imxdmac->chan.chan_id = i; imxdmac->channel = i; /* Add the channel to the DMAC list */ @@ -370,6 +385,9 @@ static int __init imxdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, imxdma); + imxdma->dma_device.dev->dma_parms = &imxdma->dma_parms; + dma_set_max_seg_size(imxdma->dma_device.dev, 0xffffff); + ret = dma_async_device_register(&imxdma->dma_device); if (ret) { dev_err(&pdev->dev, "unable to register\n"); diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index d5a5d4d..b6d1455 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -230,7 +230,7 @@ struct sdma_engine; * struct sdma_channel - housekeeping for a SDMA channel * * @sdma pointer to the SDMA engine for this channel - * @channel the channel number, matches dmaengine chan_id + * @channel the channel number, matches dmaengine chan_id + 1 * @direction transfer type. Needed for setting SDMA script * @peripheral_type Peripheral type. Needed for setting SDMA script * @event_id0 aka dma request line @@ -301,6 +301,7 @@ struct sdma_firmware_header { struct sdma_engine { struct device *dev; + struct device_dma_parameters dma_parms; struct sdma_channel channel[MAX_DMA_CHANNELS]; struct sdma_channel_control *channel_control; void __iomem *regs; @@ -449,7 +450,7 @@ static void sdma_handle_channel_loop(struct sdma_channel *sdmac) if (bd->mode.status & BD_RROR) sdmac->status = DMA_ERROR; else - sdmac->status = DMA_SUCCESS; + sdmac->status = DMA_IN_PROGRESS; bd->mode.status |= BD_DONE; sdmac->buf_tail++; @@ -770,15 +771,15 @@ static void sdma_enable_channel(struct sdma_engine *sdma, int channel) __raw_writel(1 << channel, sdma->regs + SDMA_H_START); } -static dma_cookie_t sdma_assign_cookie(struct sdma_channel *sdma) +static dma_cookie_t sdma_assign_cookie(struct sdma_channel *sdmac) { - dma_cookie_t cookie = sdma->chan.cookie; + dma_cookie_t cookie = sdmac->chan.cookie; if (++cookie < 0) cookie = 1; - sdma->chan.cookie = cookie; - sdma->desc.cookie = cookie; + sdmac->chan.cookie = cookie; + sdmac->desc.cookie = cookie; return cookie; } @@ -798,7 +799,7 @@ static dma_cookie_t sdma_tx_submit(struct dma_async_tx_descriptor *tx) cookie = sdma_assign_cookie(sdmac); - sdma_enable_channel(sdma, tx->chan->chan_id); + sdma_enable_channel(sdma, sdmac->channel); spin_unlock_irq(&sdmac->lock); @@ -811,10 +812,6 @@ static int sdma_alloc_chan_resources(struct dma_chan *chan) struct imx_dma_data *data = chan->private; int prio, ret; - /* No need to execute this for internal channel 0 */ - if (chan->chan_id == 0) - return 0; - if (!data) return -EINVAL; @@ -879,7 +876,7 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg( struct sdma_channel *sdmac = to_sdma_chan(chan); struct sdma_engine *sdma = sdmac->sdma; int ret, i, count; - int channel = chan->chan_id; + int channel = sdmac->channel; struct scatterlist *sg; if (sdmac->status == DMA_IN_PROGRESS) @@ -924,22 +921,33 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg( ret = -EINVAL; goto err_out; } - if (sdmac->word_size == DMA_SLAVE_BUSWIDTH_4_BYTES) + + switch (sdmac->word_size) { + case DMA_SLAVE_BUSWIDTH_4_BYTES: bd->mode.command = 0; - else - bd->mode.command = sdmac->word_size; + if (count & 3 || sg->dma_address & 3) + return NULL; + break; + case DMA_SLAVE_BUSWIDTH_2_BYTES: + bd->mode.command = 2; + if (count & 1 || sg->dma_address & 1) + return NULL; + break; + case DMA_SLAVE_BUSWIDTH_1_BYTE: + bd->mode.command = 1; + break; + default: + return NULL; + } param = BD_DONE | BD_EXTD | BD_CONT; - if (sdmac->flags & IMX_DMA_SG_LOOP) { + if (i + 1 == sg_len) { param |= BD_INTR; - if (i + 1 == sg_len) - param |= BD_WRAP; + param |= BD_LAST; + param &= ~BD_CONT; } - if (i + 1 == sg_len) - param |= BD_INTR; - dev_dbg(sdma->dev, "entry %d: count: %d dma: 0x%08x %s%s\n", i, count, sg->dma_address, param & BD_WRAP ? "wrap" : "", @@ -953,6 +961,7 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg( return &sdmac->desc; err_out: + sdmac->status = DMA_ERROR; return NULL; } @@ -963,7 +972,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic( struct sdma_channel *sdmac = to_sdma_chan(chan); struct sdma_engine *sdma = sdmac->sdma; int num_periods = buf_len / period_len; - int channel = chan->chan_id; + int channel = sdmac->channel; int ret, i = 0, buf = 0; dev_dbg(sdma->dev, "%s channel: %d\n", __func__, channel); @@ -1066,14 +1075,12 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan, { struct sdma_channel *sdmac = to_sdma_chan(chan); dma_cookie_t last_used; - enum dma_status ret; last_used = chan->cookie; - ret = dma_async_is_complete(cookie, sdmac->last_completed, last_used); dma_set_tx_state(txstate, sdmac->last_completed, last_used, 0); - return ret; + return sdmac->status; } static void sdma_issue_pending(struct dma_chan *chan) @@ -1135,7 +1142,7 @@ static int __init sdma_get_firmware(struct sdma_engine *sdma, /* download the RAM image for SDMA */ sdma_load_script(sdma, ram_code, header->ram_code_size, - sdma->script_addrs->ram_code_start_addr); + addr->ram_code_start_addr); clk_disable(sdma->clk); sdma_add_scripts(sdma, addr); @@ -1237,7 +1244,6 @@ static int __init sdma_probe(struct platform_device *pdev) struct resource *iores; struct sdma_platform_data *pdata = pdev->dev.platform_data; int i; - dma_cap_mask_t mask; struct sdma_engine *sdma; sdma = kzalloc(sizeof(*sdma), GFP_KERNEL); @@ -1280,6 +1286,9 @@ static int __init sdma_probe(struct platform_device *pdev) sdma->version = pdata->sdma_version; + dma_cap_set(DMA_SLAVE, sdma->dma_device.cap_mask); + dma_cap_set(DMA_CYCLIC, sdma->dma_device.cap_mask); + INIT_LIST_HEAD(&sdma->dma_device.channels); /* Initialize channel parameters */ for (i = 0; i < MAX_DMA_CHANNELS; i++) { @@ -1288,15 +1297,17 @@ static int __init sdma_probe(struct platform_device *pdev) sdmac->sdma = sdma; spin_lock_init(&sdmac->lock); - dma_cap_set(DMA_SLAVE, sdma->dma_device.cap_mask); - dma_cap_set(DMA_CYCLIC, sdma->dma_device.cap_mask); - sdmac->chan.device = &sdma->dma_device; - sdmac->chan.chan_id = i; sdmac->channel = i; - /* Add the channel to the DMAC list */ - list_add_tail(&sdmac->chan.device_node, &sdma->dma_device.channels); + /* + * Add the channel to the DMAC list. Do not add channel 0 though + * because we need it internally in the SDMA driver. This also means + * that channel 0 in dmaengine counting matches sdma channel 1. + */ + if (i) + list_add_tail(&sdmac->chan.device_node, + &sdma->dma_device.channels); } ret = sdma_init(sdma); @@ -1317,6 +1328,8 @@ static int __init sdma_probe(struct platform_device *pdev) sdma->dma_device.device_prep_dma_cyclic = sdma_prep_dma_cyclic; sdma->dma_device.device_control = sdma_control; sdma->dma_device.device_issue_pending = sdma_issue_pending; + sdma->dma_device.dev->dma_parms = &sdma->dma_parms; + dma_set_max_seg_size(sdma->dma_device.dev, 65535); ret = dma_async_device_register(&sdma->dma_device); if (ret) { @@ -1324,13 +1337,6 @@ static int __init sdma_probe(struct platform_device *pdev) goto err_init; } - /* request channel 0. This is an internal control channel - * to the SDMA engine and not available to clients. - */ - dma_cap_zero(mask); - dma_cap_set(DMA_SLAVE, mask); - dma_request_channel(mask, NULL, NULL); - dev_info(sdma->dev, "initialized\n"); return 0; @@ -1348,7 +1354,7 @@ err_clk: err_request_region: err_irq: kfree(sdma); - return 0; + return ret; } static int __exit sdma_remove(struct platform_device *pdev) diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index cb26ee9..c1a125e7 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -1145,29 +1145,6 @@ static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan, reg = idmac_read_icreg(ipu, IDMAC_CHA_EN); idmac_write_icreg(ipu, reg & ~chan_mask, IDMAC_CHA_EN); - /* - * Problem (observed with channel DMAIC_7): after enabling the channel - * and initialising buffers, there comes an interrupt with current still - * pointing at buffer 0, whereas it should use buffer 0 first and only - * generate an interrupt when it is done, then current should already - * point to buffer 1. This spurious interrupt also comes on channel - * DMASDC_0. With DMAIC_7 normally, is we just leave the ISR after the - * first interrupt, there comes the second with current correctly - * pointing to buffer 1 this time. But sometimes this second interrupt - * doesn't come and the channel hangs. Clearing BUFx_RDY when disabling - * the channel seems to prevent the channel from hanging, but it doesn't - * prevent the spurious interrupt. This might also be unsafe. Think - * about the IDMAC controller trying to switch to a buffer, when we - * clear the ready bit, and re-enable it a moment later. - */ - reg = idmac_read_ipureg(ipu, IPU_CHA_BUF0_RDY); - idmac_write_ipureg(ipu, 0, IPU_CHA_BUF0_RDY); - idmac_write_ipureg(ipu, reg & ~(1UL << channel), IPU_CHA_BUF0_RDY); - - reg = idmac_read_ipureg(ipu, IPU_CHA_BUF1_RDY); - idmac_write_ipureg(ipu, 0, IPU_CHA_BUF1_RDY); - idmac_write_ipureg(ipu, reg & ~(1UL << channel), IPU_CHA_BUF1_RDY); - spin_unlock_irqrestore(&ipu->lock, flags); return 0; @@ -1246,33 +1223,6 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id) /* Other interrupts do not interfere with this channel */ spin_lock(&ichan->lock); - if (unlikely(chan_id != IDMAC_SDC_0 && chan_id != IDMAC_SDC_1 && - ((curbuf >> chan_id) & 1) == ichan->active_buffer && - !list_is_last(ichan->queue.next, &ichan->queue))) { - int i = 100; - - /* This doesn't help. See comment in ipu_disable_channel() */ - while (--i) { - curbuf = idmac_read_ipureg(&ipu_data, IPU_CHA_CUR_BUF); - if (((curbuf >> chan_id) & 1) != ichan->active_buffer) - break; - cpu_relax(); - } - - if (!i) { - spin_unlock(&ichan->lock); - dev_dbg(dev, - "IRQ on active buffer on channel %x, active " - "%d, ready %x, %x, current %x!\n", chan_id, - ichan->active_buffer, ready0, ready1, curbuf); - return IRQ_NONE; - } else - dev_dbg(dev, - "Buffer deactivated on channel %x, active " - "%d, ready %x, %x, current %x, rest %d!\n", chan_id, - ichan->active_buffer, ready0, ready1, curbuf, i); - } - if (unlikely((ichan->active_buffer && (ready1 >> chan_id) & 1) || (!ichan->active_buffer && (ready0 >> chan_id) & 1) )) { diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 4a5ecc5..23e0355 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -826,8 +826,6 @@ static void amd64_dump_dramcfg_low(u32 dclr, int chan) /* Display and decode various NB registers for debug purposes. */ static void amd64_dump_misc_regs(struct amd64_pvt *pvt) { - int ganged; - debugf1("F3xE8 (NB Cap): 0x%08x\n", pvt->nbcap); debugf1(" NB two channel DRAM capable: %s\n", @@ -851,28 +849,19 @@ static void amd64_dump_misc_regs(struct amd64_pvt *pvt) debugf1(" DramHoleValid: %s\n", (pvt->dhar & DHAR_VALID) ? "yes" : "no"); + amd64_debug_display_dimm_sizes(0, pvt); + /* everything below this point is Fam10h and above */ - if (boot_cpu_data.x86 == 0xf) { - amd64_debug_display_dimm_sizes(0, pvt); + if (boot_cpu_data.x86 == 0xf) return; - } + + amd64_debug_display_dimm_sizes(1, pvt); amd64_info("using %s syndromes.\n", ((pvt->syn_type == 8) ? "x8" : "x4")); /* Only if NOT ganged does dclr1 have valid info */ if (!dct_ganging_enabled(pvt)) amd64_dump_dramcfg_low(pvt->dclr1, 1); - - /* - * Determine if ganged and then dump memory sizes for first controller, - * and if NOT ganged dump info for 2nd controller. - */ - ganged = dct_ganging_enabled(pvt); - - amd64_debug_display_dimm_sizes(0, pvt); - - if (!ganged) - amd64_debug_display_dimm_sizes(1, pvt); } /* Read in both of DBAM registers */ @@ -1644,11 +1633,10 @@ static void amd64_debug_display_dimm_sizes(int ctrl, struct amd64_pvt *pvt) WARN_ON(ctrl != 0); } - debugf1("F2x%d80 (DRAM Bank Address Mapping): 0x%08x\n", - ctrl, ctrl ? pvt->dbam1 : pvt->dbam0); + dbam = (ctrl && !dct_ganging_enabled(pvt)) ? pvt->dbam1 : pvt->dbam0; + dcsb = (ctrl && !dct_ganging_enabled(pvt)) ? pvt->dcsb1 : pvt->dcsb0; - dbam = ctrl ? pvt->dbam1 : pvt->dbam0; - dcsb = ctrl ? pvt->dcsb1 : pvt->dcsb0; + debugf1("F2x%d80 (DRAM Bank Address Mapping): 0x%08x\n", ctrl, dbam); edac_printk(KERN_DEBUG, EDAC_MC, "DCT%d chip selects:\n", ctrl); diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index e28e41668..bcb1126 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -378,10 +378,17 @@ static void __init print_filtered(const char *info) static void __init dmi_dump_ids(void) { + const char *board; /* Board Name is optional */ + printk(KERN_DEBUG "DMI: "); - print_filtered(dmi_get_system_info(DMI_BOARD_NAME)); - printk(KERN_CONT "/"); + print_filtered(dmi_get_system_info(DMI_SYS_VENDOR)); + printk(KERN_CONT " "); print_filtered(dmi_get_system_info(DMI_PRODUCT_NAME)); + board = dmi_get_system_info(DMI_BOARD_NAME); + if (board) { + printk(KERN_CONT "/"); + print_filtered(board); + } printk(KERN_CONT ", BIOS "); print_filtered(dmi_get_system_info(DMI_BIOS_VERSION)); printk(KERN_CONT " "); diff --git a/drivers/gpio/ml_ioh_gpio.c b/drivers/gpio/ml_ioh_gpio.c index cead8e6..7f6f01a 100644 --- a/drivers/gpio/ml_ioh_gpio.c +++ b/drivers/gpio/ml_ioh_gpio.c @@ -326,6 +326,7 @@ static DEFINE_PCI_DEVICE_TABLE(ioh_gpio_pcidev_id) = { { PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x802E) }, { 0, } }; +MODULE_DEVICE_TABLE(pci, ioh_gpio_pcidev_id); static struct pci_driver ioh_gpio_driver = { .name = "ml_ioh_gpio", diff --git a/drivers/gpio/pca953x.c b/drivers/gpio/pca953x.c index a261972..b473429e 100644 --- a/drivers/gpio/pca953x.c +++ b/drivers/gpio/pca953x.c @@ -60,6 +60,7 @@ struct pca953x_chip { unsigned gpio_start; uint16_t reg_output; uint16_t reg_direction; + struct mutex i2c_lock; #ifdef CONFIG_GPIO_PCA953X_IRQ struct mutex irq_lock; @@ -119,13 +120,17 @@ static int pca953x_gpio_direction_input(struct gpio_chip *gc, unsigned off) chip = container_of(gc, struct pca953x_chip, gpio_chip); + mutex_lock(&chip->i2c_lock); reg_val = chip->reg_direction | (1u << off); ret = pca953x_write_reg(chip, PCA953X_DIRECTION, reg_val); if (ret) - return ret; + goto exit; chip->reg_direction = reg_val; - return 0; + ret = 0; +exit: + mutex_unlock(&chip->i2c_lock); + return ret; } static int pca953x_gpio_direction_output(struct gpio_chip *gc, @@ -137,6 +142,7 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc, chip = container_of(gc, struct pca953x_chip, gpio_chip); + mutex_lock(&chip->i2c_lock); /* set output level */ if (val) reg_val = chip->reg_output | (1u << off); @@ -145,7 +151,7 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc, ret = pca953x_write_reg(chip, PCA953X_OUTPUT, reg_val); if (ret) - return ret; + goto exit; chip->reg_output = reg_val; @@ -153,10 +159,13 @@ static int pca953x_gpio_direction_output(struct gpio_chip *gc, reg_val = chip->reg_direction & ~(1u << off); ret = pca953x_write_reg(chip, PCA953X_DIRECTION, reg_val); if (ret) - return ret; + goto exit; chip->reg_direction = reg_val; - return 0; + ret = 0; +exit: + mutex_unlock(&chip->i2c_lock); + return ret; } static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off) @@ -167,7 +176,9 @@ static int pca953x_gpio_get_value(struct gpio_chip *gc, unsigned off) chip = container_of(gc, struct pca953x_chip, gpio_chip); + mutex_lock(&chip->i2c_lock); ret = pca953x_read_reg(chip, PCA953X_INPUT, ®_val); + mutex_unlock(&chip->i2c_lock); if (ret < 0) { /* NOTE: diagnostic already emitted; that's all we should * do unless gpio_*_value_cansleep() calls become different @@ -187,6 +198,7 @@ static void pca953x_gpio_set_value(struct gpio_chip *gc, unsigned off, int val) chip = container_of(gc, struct pca953x_chip, gpio_chip); + mutex_lock(&chip->i2c_lock); if (val) reg_val = chip->reg_output | (1u << off); else @@ -194,9 +206,11 @@ static void pca953x_gpio_set_value(struct gpio_chip *gc, unsigned off, int val) ret = pca953x_write_reg(chip, PCA953X_OUTPUT, reg_val); if (ret) - return; + goto exit; chip->reg_output = reg_val; +exit: + mutex_unlock(&chip->i2c_lock); } static void pca953x_setup_gpio(struct pca953x_chip *chip, int gpios) @@ -517,6 +531,8 @@ static int __devinit pca953x_probe(struct i2c_client *client, chip->names = pdata->names; + mutex_init(&chip->i2c_lock); + /* initialize cached registers from their original values. * we can't share this chip with another i2c master. */ diff --git a/drivers/gpio/pch_gpio.c b/drivers/gpio/pch_gpio.c index 0eba0a7..2c6af87 100644 --- a/drivers/gpio/pch_gpio.c +++ b/drivers/gpio/pch_gpio.c @@ -286,6 +286,7 @@ static DEFINE_PCI_DEVICE_TABLE(pch_gpio_pcidev_id) = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8803) }, { 0, } }; +MODULE_DEVICE_TABLE(pci, pch_gpio_pcidev_id); static struct pci_driver pch_gpio_driver = { .name = "pch_gpio", diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 2baa670..654faa8 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2674,3 +2674,23 @@ out: mutex_unlock(&dev->mode_config.mutex); return ret; } + +void drm_mode_config_reset(struct drm_device *dev) +{ + struct drm_crtc *crtc; + struct drm_encoder *encoder; + struct drm_connector *connector; + + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + if (crtc->funcs->reset) + crtc->funcs->reset(crtc); + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) + if (encoder->funcs->reset) + encoder->funcs->reset(encoder); + + list_for_each_entry(connector, &dev->mode_config.connector_list, head) + if (connector->funcs->reset) + connector->funcs->reset(connector); +} +EXPORT_SYMBOL(drm_mode_config_reset); diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index 952b3d4..9236965 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -343,13 +343,12 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, struct drm_encoder *encoder; bool ret = true; - adjusted_mode = drm_mode_duplicate(dev, mode); - crtc->enabled = drm_helper_crtc_in_use(crtc); - if (!crtc->enabled) return true; + adjusted_mode = drm_mode_duplicate(dev, mode); + saved_hwmode = crtc->hwmode; saved_mode = crtc->mode; saved_x = crtc->x; @@ -437,10 +436,9 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, */ drm_calc_timestamping_constants(crtc); - /* XXX free adjustedmode */ - drm_mode_destroy(dev, adjusted_mode); /* FIXME: add subpixel order */ done: + drm_mode_destroy(dev, adjusted_mode); if (!ret) { crtc->hwmode = saved_hwmode; crtc->mode = saved_mode; @@ -497,14 +495,17 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) crtc_funcs = set->crtc->helper_private; + if (!set->mode) + set->fb = NULL; + if (set->fb) { DRM_DEBUG_KMS("[CRTC:%d] [FB:%d] #connectors=%d (x y) (%i %i)\n", set->crtc->base.id, set->fb->base.id, (int)set->num_connectors, set->x, set->y); } else { - DRM_DEBUG_KMS("[CRTC:%d] [NOFB] #connectors=%d (x y) (%i %i)\n", - set->crtc->base.id, (int)set->num_connectors, - set->x, set->y); + DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id); + set->mode = NULL; + set->num_connectors = 0; } dev = set->crtc->dev; @@ -649,8 +650,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) mode_changed = true; if (mode_changed) { - set->crtc->enabled = (set->mode != NULL); - if (set->mode != NULL) { + set->crtc->enabled = drm_helper_crtc_in_use(set->crtc); + if (set->crtc->enabled) { DRM_DEBUG_KMS("attempting to set mode from" " userspace\n"); drm_mode_debug_printmodeline(set->mode); @@ -665,6 +666,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) ret = -EINVAL; goto fail; } + DRM_DEBUG_KMS("Setting connector DPMS state to on\n"); + for (i = 0; i < set->num_connectors; i++) { + DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id, + drm_get_connector_name(set->connectors[i])); + set->connectors[i]->dpms = DRM_MODE_DPMS_ON; + } } drm_helper_disable_unused_functions(dev); } else if (fb_changed) { @@ -681,12 +688,6 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) goto fail; } } - DRM_DEBUG_KMS("Setting connector DPMS state to on\n"); - for (i = 0; i < set->num_connectors; i++) { - DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id, - drm_get_connector_name(set->connectors[i])); - set->connectors[i]->dpms = DRM_MODE_DPMS_ON; - } kfree(save_connectors); kfree(save_encoders); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 6977a1c..f73ef43 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -672,7 +672,7 @@ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info) struct drm_crtc_helper_funcs *crtc_funcs; u16 *red, *green, *blue, *transp; struct drm_crtc *crtc; - int i, rc = 0; + int i, j, rc = 0; int start; for (i = 0; i < fb_helper->crtc_count; i++) { @@ -685,7 +685,7 @@ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info) transp = cmap->transp; start = cmap->start; - for (i = 0; i < cmap->len; i++) { + for (j = 0; j < cmap->len; j++) { u16 hred, hgreen, hblue, htransp = 0xffff; hred = *red++; diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c index 3cdbaf3..be9a9c0 100644 --- a/drivers/gpu/drm/drm_info.c +++ b/drivers/gpu/drm/drm_info.c @@ -283,17 +283,18 @@ int drm_vma_info(struct seq_file *m, void *data) #endif mutex_lock(&dev->struct_mutex); - seq_printf(m, "vma use count: %d, high_memory = %p, 0x%08llx\n", + seq_printf(m, "vma use count: %d, high_memory = %pK, 0x%pK\n", atomic_read(&dev->vma_count), - high_memory, (u64)virt_to_phys(high_memory)); + high_memory, (void *)virt_to_phys(high_memory)); list_for_each_entry(pt, &dev->vmalist, head) { vma = pt->vma; if (!vma) continue; seq_printf(m, - "\n%5d 0x%08lx-0x%08lx %c%c%c%c%c%c 0x%08lx000", - pt->pid, vma->vm_start, vma->vm_end, + "\n%5d 0x%pK-0x%pK %c%c%c%c%c%c 0x%08lx000", + pt->pid, + (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_flags & VM_READ ? 'r' : '-', vma->vm_flags & VM_WRITE ? 'w' : '-', vma->vm_flags & VM_EXEC ? 'x' : '-', diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 0054e95..28d1d3c 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -164,8 +164,10 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc) * available. In that case we can't account for this and just * hope for the best. */ - if ((vblrc > 0) && (abs(diff_ns) > 1000000)) + if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) { atomic_inc(&dev->_vblank_count[crtc]); + smp_mb__after_atomic_inc(); + } /* Invalidate all timestamps while vblank irq's are off. */ clear_vblank_timestamps(dev, crtc); @@ -491,6 +493,12 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc) /* Dot clock in Hz: */ dotclock = (u64) crtc->hwmode.clock * 1000; + /* Fields of interlaced scanout modes are only halve a frame duration. + * Double the dotclock to get halve the frame-/line-/pixelduration. + */ + if (crtc->hwmode.flags & DRM_MODE_FLAG_INTERLACE) + dotclock *= 2; + /* Valid dotclock? */ if (dotclock > 0) { /* Convert scanline length in pixels and video dot clock to @@ -603,14 +611,6 @@ int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, int crtc, return -EAGAIN; } - /* Don't know yet how to handle interlaced or - * double scan modes. Just no-op for now. - */ - if (mode->flags & (DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLSCAN)) { - DRM_DEBUG("crtc %d: Noop due to unsupported mode.\n", crtc); - return -ENOTSUPP; - } - /* Get current scanout position with system timestamp. * Repeat query up to DRM_TIMESTAMP_MAXRETRIES times * if single query takes longer than max_error nanoseconds. @@ -858,10 +858,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc) if (rc) { tslot = atomic_read(&dev->_vblank_count[crtc]) + diff; vblanktimestamp(dev, crtc, tslot) = t_vblank; - smp_wmb(); } + smp_mb__before_atomic_inc(); atomic_add(diff, &dev->_vblank_count[crtc]); + smp_mb__after_atomic_inc(); } /** @@ -1011,7 +1012,8 @@ int drm_modeset_ctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_modeset_ctl *modeset = data; - int crtc, ret = 0; + int ret = 0; + unsigned int crtc; /* If drm_vblank_init() hasn't been called yet, just no-op */ if (!dev->num_crtcs) @@ -1250,7 +1252,7 @@ void drm_handle_vblank_events(struct drm_device *dev, int crtc) * Drivers should call this routine in their vblank interrupt handlers to * update the vblank counter and send any signals that may be pending. */ -void drm_handle_vblank(struct drm_device *dev, int crtc) +bool drm_handle_vblank(struct drm_device *dev, int crtc) { u32 vblcount; s64 diff_ns; @@ -1258,7 +1260,7 @@ void drm_handle_vblank(struct drm_device *dev, int crtc) unsigned long irqflags; if (!dev->num_crtcs) - return; + return false; /* Need timestamp lock to prevent concurrent execution with * vblank enable/disable, as this would cause inconsistent @@ -1269,7 +1271,7 @@ void drm_handle_vblank(struct drm_device *dev, int crtc) /* Vblank irq handling disabled. Nothing to do. */ if (!dev->vblank_enabled[crtc]) { spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags); - return; + return false; } /* Fetch corresponding timestamp for this vblank interval from @@ -1293,15 +1295,16 @@ void drm_handle_vblank(struct drm_device *dev, int crtc) * e.g., due to spurious vblank interrupts. We need to * ignore those for accounting. */ - if (abs(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) { + if (abs64(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) { /* Store new timestamp in ringbuffer. */ vblanktimestamp(dev, crtc, vblcount + 1) = tvblank; - smp_wmb(); /* Increment cooked vblank count. This also atomically commits * the timestamp computed above. */ + smp_mb__before_atomic_inc(); atomic_inc(&dev->_vblank_count[crtc]); + smp_mb__after_atomic_inc(); } else { DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n", crtc, (int) diff_ns); @@ -1311,5 +1314,6 @@ void drm_handle_vblank(struct drm_device *dev, int crtc) drm_handle_vblank_events(dev, crtc); spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags); + return true; } EXPORT_SYMBOL(drm_handle_vblank); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 3601466..4ff9b6c 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -865,7 +865,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) int max_freq; /* RPSTAT1 is in the GT power well */ - __gen6_force_wake_get(dev_priv); + __gen6_gt_force_wake_get(dev_priv); seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status); seq_printf(m, "RPSTAT1: 0x%08x\n", I915_READ(GEN6_RPSTAT1)); @@ -888,7 +888,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n", max_freq * 100); - __gen6_force_wake_put(dev_priv); + __gen6_gt_force_wake_put(dev_priv); } else { seq_printf(m, "no P-state info available\n"); } diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 17bd766..e33d9be 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1895,6 +1895,17 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (IS_GEN2(dev)) dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30)); + /* 965GM sometimes incorrectly writes to hardware status page (HWS) + * using 32bit addressing, overwriting memory if HWS is located + * above 4GB. + * + * The documentation also mentions an issue with undefined + * behaviour if any general state is accessed within a page above 4GB, + * which also needs to be handled carefully. + */ + if (IS_BROADWATER(dev) || IS_CRESTLINE(dev)) + dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(32)); + mmio_bar = IS_GEN2(dev) ? 1 : 0; dev_priv->regs = pci_iomap(dev->pdev, mmio_bar, 0); if (!dev_priv->regs) { diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 66796bb..22ec066 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -46,6 +46,12 @@ module_param_named(fbpercrtc, i915_fbpercrtc, int, 0400); unsigned int i915_powersave = 1; module_param_named(powersave, i915_powersave, int, 0600); +unsigned int i915_semaphores = 0; +module_param_named(semaphores, i915_semaphores, int, 0600); + +unsigned int i915_enable_rc6 = 0; +module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600); + unsigned int i915_lvds_downclock = 0; module_param_named(lvds_downclock, i915_lvds_downclock, int, 0400); @@ -251,7 +257,7 @@ void intel_detect_pch (struct drm_device *dev) } } -void __gen6_force_wake_get(struct drm_i915_private *dev_priv) +void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv) { int count; @@ -267,12 +273,22 @@ void __gen6_force_wake_get(struct drm_i915_private *dev_priv) udelay(10); } -void __gen6_force_wake_put(struct drm_i915_private *dev_priv) +void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv) { I915_WRITE_NOTRACE(FORCEWAKE, 0); POSTING_READ(FORCEWAKE); } +void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) +{ + int loop = 500; + u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES); + while (fifo < 20 && loop--) { + udelay(10); + fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES); + } +} + static int i915_drm_freeze(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -354,12 +370,13 @@ static int i915_drm_thaw(struct drm_device *dev) error = i915_gem_init_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); + drm_mode_config_reset(dev); drm_irq_install(dev); /* Resume the modeset for every activated CRTC */ drm_helper_resume_force_mode(dev); - if (dev_priv->renderctx && dev_priv->pwrctx) + if (IS_IRONLAKE_M(dev)) ironlake_enable_rc6(dev); } @@ -542,6 +559,7 @@ int i915_reset(struct drm_device *dev, u8 flags) mutex_unlock(&dev->struct_mutex); drm_irq_uninstall(dev); + drm_mode_config_reset(dev); drm_irq_install(dev); mutex_lock(&dev->struct_mutex); } @@ -566,6 +584,14 @@ int i915_reset(struct drm_device *dev, u8 flags) static int __devinit i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { + /* Only bind to function 0 of the device. Early generations + * used function 1 as a placeholder for multi-head. This causes + * us confusion instead, especially on the systems where both + * functions have the same PCI-ID! + */ + if (PCI_FUNC(pdev->devfn)) + return -ENODEV; + return drm_get_pci_dev(pdev, ent, &driver); } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index a0149c6..456f404 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -956,8 +956,10 @@ extern struct drm_ioctl_desc i915_ioctls[]; extern int i915_max_ioctl; extern unsigned int i915_fbpercrtc; extern unsigned int i915_powersave; +extern unsigned int i915_semaphores; extern unsigned int i915_lvds_downclock; extern unsigned int i915_panel_use_ssc; +extern unsigned int i915_enable_rc6; extern int i915_suspend(struct drm_device *dev, pm_message_t state); extern int i915_resume(struct drm_device *dev); @@ -1176,6 +1178,9 @@ void i915_gem_detach_phys_object(struct drm_device *dev, void i915_gem_free_all_phys_object(struct drm_device *dev); void i915_gem_release(struct drm_device *dev, struct drm_file *file); +uint32_t +i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj); + /* i915_gem_gtt.c */ void i915_gem_restore_gtt_mappings(struct drm_device *dev); int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj); @@ -1352,22 +1357,32 @@ __i915_write(64, q) * must be set to prevent GT core from power down and stale values being * returned. */ -void __gen6_force_wake_get(struct drm_i915_private *dev_priv); -void __gen6_force_wake_put (struct drm_i915_private *dev_priv); -static inline u32 i915_safe_read(struct drm_i915_private *dev_priv, u32 reg) +void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv); +void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv); +void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv); + +static inline u32 i915_gt_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val; if (dev_priv->info->gen >= 6) { - __gen6_force_wake_get(dev_priv); + __gen6_gt_force_wake_get(dev_priv); val = I915_READ(reg); - __gen6_force_wake_put(dev_priv); + __gen6_gt_force_wake_put(dev_priv); } else val = I915_READ(reg); return val; } +static inline void i915_gt_write(struct drm_i915_private *dev_priv, + u32 reg, u32 val) +{ + if (dev_priv->info->gen >= 6) + __gen6_gt_wait_for_fifo(dev_priv); + I915_WRITE(reg, val); +} + static inline void i915_write(struct drm_i915_private *dev_priv, u32 reg, u64 val, int len) { diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index cf4f74c..36e66cc 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1398,7 +1398,7 @@ i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj) * Return the required GTT alignment for an object, only taking into account * unfenced tiled surface requirements. */ -static uint32_t +uint32_t i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj) { struct drm_device *dev = obj->base.dev; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index d2f445e..50ab161 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -772,8 +772,8 @@ i915_gem_execbuffer_sync_rings(struct drm_i915_gem_object *obj, if (from == NULL || to == from) return 0; - /* XXX gpu semaphores are currently causing hard hangs on SNB mobile */ - if (INTEL_INFO(obj->base.dev)->gen < 6 || IS_MOBILE(obj->base.dev)) + /* XXX gpu semaphores are implicated in various hard hangs on SNB */ + if (INTEL_INFO(obj->base.dev)->gen < 6 || !i915_semaphores) return i915_gem_object_wait_rendering(obj, true); idx = intel_ring_sync_index(from, to); diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 22a32b9..d64843e 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -349,14 +349,27 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, (obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end && i915_gem_object_fence_ok(obj, args->tiling_mode)); - obj->tiling_changed = true; - obj->tiling_mode = args->tiling_mode; - obj->stride = args->stride; + /* Rebind if we need a change of alignment */ + if (!obj->map_and_fenceable) { + u32 unfenced_alignment = + i915_gem_get_unfenced_gtt_alignment(obj); + if (obj->gtt_offset & (unfenced_alignment - 1)) + ret = i915_gem_object_unbind(obj); + } + + if (ret == 0) { + obj->tiling_changed = true; + obj->tiling_mode = args->tiling_mode; + obj->stride = args->stride; + } } + /* we have to maintain this existing ABI... */ + args->stride = obj->stride; + args->tiling_mode = obj->tiling_mode; drm_gem_object_unreference(&obj->base); mutex_unlock(&dev->struct_mutex); - return 0; + return ret; } /** diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 062f353..8a9e08b 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -316,6 +316,8 @@ static void i915_hotplug_work_func(struct work_struct *work) struct drm_mode_config *mode_config = &dev->mode_config; struct intel_encoder *encoder; + DRM_DEBUG_KMS("running encoder hotplug functions\n"); + list_for_each_entry(encoder, &mode_config->encoder_list, base.head) if (encoder->hot_plug) encoder->hot_plug(encoder); @@ -1196,18 +1198,18 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) intel_finish_page_flip_plane(dev, 1); } - if (pipea_stats & vblank_status) { + if (pipea_stats & vblank_status && + drm_handle_vblank(dev, 0)) { vblank++; - drm_handle_vblank(dev, 0); if (!dev_priv->flip_pending_is_done) { i915_pageflip_stall_check(dev, 0); intel_finish_page_flip(dev, 0); } } - if (pipeb_stats & vblank_status) { + if (pipeb_stats & vblank_status && + drm_handle_vblank(dev, 1)) { vblank++; - drm_handle_vblank(dev, 1); if (!dev_priv->flip_pending_is_done) { i915_pageflip_stall_check(dev, 1); intel_finish_page_flip(dev, 1); @@ -1649,9 +1651,7 @@ static int ironlake_irq_postinstall(struct drm_device *dev) } else { hotplug_mask = SDE_CRT_HOTPLUG | SDE_PORTB_HOTPLUG | SDE_PORTC_HOTPLUG | SDE_PORTD_HOTPLUG; - hotplug_mask |= SDE_AUX_MASK | SDE_FDI_MASK | SDE_TRANS_MASK; - I915_WRITE(FDI_RXA_IMR, 0); - I915_WRITE(FDI_RXB_IMR, 0); + hotplug_mask |= SDE_AUX_MASK; } dev_priv->pch_irq_mask = ~hotplug_mask; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 5cfc689..2abe240 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -174,7 +174,9 @@ * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! */ #define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*x-1) -#define MI_FLUSH_DW MI_INSTR(0x26, 2) /* for GEN6 */ +#define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */ +#define MI_INVALIDATE_TLB (1<<18) +#define MI_INVALIDATE_BSD (1<<7) #define MI_BATCH_BUFFER MI_INSTR(0x30, 1) #define MI_BATCH_NON_SECURE (1) #define MI_BATCH_NON_SECURE_I965 (1<<8) @@ -3269,6 +3271,8 @@ #define FORCEWAKE 0xA18C #define FORCEWAKE_ACK 0x130090 +#define GT_FIFO_FREE_ENTRIES 0x120008 + #define GEN6_RPNSWREQ 0xA008 #define GEN6_TURBO_DISABLE (1<<31) #define GEN6_FREQUENCY(x) ((x)<<25) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 17035b8..8a77ff4 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -535,6 +535,15 @@ static int intel_crt_set_property(struct drm_connector *connector, return 0; } +static void intel_crt_reset(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + struct intel_crt *crt = intel_attached_crt(connector); + + if (HAS_PCH_SPLIT(dev)) + crt->force_hotplug_required = 1; +} + /* * Routines for controlling stuff on the analog port */ @@ -548,6 +557,7 @@ static const struct drm_encoder_helper_funcs intel_crt_helper_funcs = { }; static const struct drm_connector_funcs intel_crt_connector_funcs = { + .reset = intel_crt_reset, .dpms = drm_helper_connector_dpms, .detect = intel_crt_detect, .fill_modes = drm_helper_probe_single_connector_modes, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index d7f237d..49fb54f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1219,7 +1219,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev) u32 blt_ecoskpd; /* Make sure blitter notifies FBC of writes */ - __gen6_force_wake_get(dev_priv); + __gen6_gt_force_wake_get(dev_priv); blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD); blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY << GEN6_BLITTER_LOCK_SHIFT; @@ -1230,7 +1230,7 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev) GEN6_BLITTER_LOCK_SHIFT); I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd); POSTING_READ(GEN6_BLITTER_ECOSKPD); - __gen6_force_wake_put(dev_priv); + __gen6_gt_force_wake_put(dev_priv); } static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval) @@ -1630,19 +1630,19 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, struct drm_i915_gem_object *obj = to_intel_framebuffer(old_fb)->obj; wait_event(dev_priv->pending_flip_queue, + atomic_read(&dev_priv->mm.wedged) || atomic_read(&obj->pending_flip) == 0); /* Big Hammer, we also need to ensure that any pending * MI_WAIT_FOR_EVENT inside a user batch buffer on the * current scanout is retired before unpinning the old * framebuffer. + * + * This should only fail upon a hung GPU, in which case we + * can safely continue. */ ret = i915_gem_object_flush_gpu(obj, false); - if (ret) { - i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj); - mutex_unlock(&dev->struct_mutex); - return ret; - } + (void) ret; } ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y, @@ -2045,6 +2045,31 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) atomic_read(&obj->pending_flip) == 0); } +static bool intel_crtc_driving_pch(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_mode_config *mode_config = &dev->mode_config; + struct intel_encoder *encoder; + + /* + * If there's a non-PCH eDP on this crtc, it must be DP_A, and that + * must be driven by its own crtc; no sharing is possible. + */ + list_for_each_entry(encoder, &mode_config->encoder_list, base.head) { + if (encoder->base.crtc != crtc) + continue; + + switch (encoder->type) { + case INTEL_OUTPUT_EDP: + if (!intel_encoder_is_pch_edp(&encoder->base)) + return false; + continue; + } + } + + return true; +} + static void ironlake_crtc_enable(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; @@ -2053,6 +2078,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) int pipe = intel_crtc->pipe; int plane = intel_crtc->plane; u32 reg, temp; + bool is_pch_port = false; if (intel_crtc->active) return; @@ -2066,7 +2092,56 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) I915_WRITE(PCH_LVDS, temp | LVDS_PORT_EN); } - ironlake_fdi_enable(crtc); + is_pch_port = intel_crtc_driving_pch(crtc); + + if (is_pch_port) + ironlake_fdi_enable(crtc); + else { + /* disable CPU FDI tx and PCH FDI rx */ + reg = FDI_TX_CTL(pipe); + temp = I915_READ(reg); + I915_WRITE(reg, temp & ~FDI_TX_ENABLE); + POSTING_READ(reg); + + reg = FDI_RX_CTL(pipe); + temp = I915_READ(reg); + temp &= ~(0x7 << 16); + temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11; + I915_WRITE(reg, temp & ~FDI_RX_ENABLE); + + POSTING_READ(reg); + udelay(100); + + /* Ironlake workaround, disable clock pointer after downing FDI */ + if (HAS_PCH_IBX(dev)) + I915_WRITE(FDI_RX_CHICKEN(pipe), + I915_READ(FDI_RX_CHICKEN(pipe) & + ~FDI_RX_PHASE_SYNC_POINTER_ENABLE)); + + /* still set train pattern 1 */ + reg = FDI_TX_CTL(pipe); + temp = I915_READ(reg); + temp &= ~FDI_LINK_TRAIN_NONE; + temp |= FDI_LINK_TRAIN_PATTERN_1; + I915_WRITE(reg, temp); + + reg = FDI_RX_CTL(pipe); + temp = I915_READ(reg); + if (HAS_PCH_CPT(dev)) { + temp &= ~FDI_LINK_TRAIN_PATTERN_MASK_CPT; + temp |= FDI_LINK_TRAIN_PATTERN_1_CPT; + } else { + temp &= ~FDI_LINK_TRAIN_NONE; + temp |= FDI_LINK_TRAIN_PATTERN_1; + } + /* BPC in FDI rx is consistent with that in PIPECONF */ + temp &= ~(0x07 << 16); + temp |= (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) << 11; + I915_WRITE(reg, temp); + + POSTING_READ(reg); + udelay(100); + } /* Enable panel fitting for LVDS */ if (dev_priv->pch_pf_size && @@ -2100,6 +2175,10 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) intel_flush_display_plane(dev, plane); } + /* Skip the PCH stuff if possible */ + if (!is_pch_port) + goto done; + /* For PCH output, training FDI link */ if (IS_GEN6(dev)) gen6_fdi_link_train(crtc); @@ -2184,7 +2263,7 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) I915_WRITE(reg, temp | TRANS_ENABLE); if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100)) DRM_ERROR("failed to enable transcoder %d\n", pipe); - +done: intel_crtc_load_lut(crtc); intel_update_fbc(dev); intel_crtc_update_cursor(crtc, true); @@ -5551,6 +5630,16 @@ cleanup_work: return ret; } +static void intel_crtc_reset(struct drm_crtc *crtc) +{ + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + + /* Reset flags back to the 'unknown' status so that they + * will be correctly set on the initial modeset. + */ + intel_crtc->dpms_mode = -1; +} + static struct drm_crtc_helper_funcs intel_helper_funcs = { .dpms = intel_crtc_dpms, .mode_fixup = intel_crtc_mode_fixup, @@ -5562,6 +5651,7 @@ static struct drm_crtc_helper_funcs intel_helper_funcs = { }; static const struct drm_crtc_funcs intel_crtc_funcs = { + .reset = intel_crtc_reset, .cursor_set = intel_crtc_cursor_set, .cursor_move = intel_crtc_cursor_move, .gamma_set = intel_crtc_gamma_set, @@ -5652,8 +5742,7 @@ static void intel_crtc_init(struct drm_device *dev, int pipe) dev_priv->plane_to_crtc_mapping[intel_crtc->plane] = &intel_crtc->base; dev_priv->pipe_to_crtc_mapping[intel_crtc->pipe] = &intel_crtc->base; - intel_crtc->cursor_addr = 0; - intel_crtc->dpms_mode = -1; + intel_crtc_reset(&intel_crtc->base); intel_crtc->active = true; /* force the pipe off on setup_init_config */ if (HAS_PCH_SPLIT(dev)) { @@ -6193,7 +6282,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) * userspace... */ I915_WRITE(GEN6_RC_STATE, 0); - __gen6_force_wake_get(dev_priv); + __gen6_gt_force_wake_get(dev_priv); /* disable the counters and set deterministic thresholds */ I915_WRITE(GEN6_RC_CONTROL, 0); @@ -6291,7 +6380,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) /* enable all PM interrupts */ I915_WRITE(GEN6_PMINTRMSK, 0); - __gen6_force_wake_put(dev_priv); + __gen6_gt_force_wake_put(dev_priv); } void intel_enable_clock_gating(struct drm_device *dev) @@ -6452,52 +6541,60 @@ void intel_enable_clock_gating(struct drm_device *dev) } } -void intel_disable_clock_gating(struct drm_device *dev) +static void ironlake_teardown_rc6(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; if (dev_priv->renderctx) { - struct drm_i915_gem_object *obj = dev_priv->renderctx; - - I915_WRITE(CCID, 0); - POSTING_READ(CCID); - - i915_gem_object_unpin(obj); - drm_gem_object_unreference(&obj->base); + i915_gem_object_unpin(dev_priv->renderctx); + drm_gem_object_unreference(&dev_priv->renderctx->base); dev_priv->renderctx = NULL; } if (dev_priv->pwrctx) { - struct drm_i915_gem_object *obj = dev_priv->pwrctx; + i915_gem_object_unpin(dev_priv->pwrctx); + drm_gem_object_unreference(&dev_priv->pwrctx->base); + dev_priv->pwrctx = NULL; + } +} + +static void ironlake_disable_rc6(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (I915_READ(PWRCTXA)) { + /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */ + I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT); + wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON), + 50); I915_WRITE(PWRCTXA, 0); POSTING_READ(PWRCTXA); - i915_gem_object_unpin(obj); - drm_gem_object_unreference(&obj->base); - dev_priv->pwrctx = NULL; + I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); + POSTING_READ(RSTDBYCTL); } + + ironlake_teardown_rc6(dev); } -static void ironlake_disable_rc6(struct drm_device *dev) +static int ironlake_setup_rc6(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - /* Wake the GPU, prevent RC6, then restore RSTDBYCTL */ - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) | RCX_SW_EXIT); - wait_for(((I915_READ(RSTDBYCTL) & RSX_STATUS_MASK) == RSX_STATUS_ON), - 10); - POSTING_READ(CCID); - I915_WRITE(PWRCTXA, 0); - POSTING_READ(PWRCTXA); - I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); - POSTING_READ(RSTDBYCTL); - i915_gem_object_unpin(dev_priv->renderctx); - drm_gem_object_unreference(&dev_priv->renderctx->base); - dev_priv->renderctx = NULL; - i915_gem_object_unpin(dev_priv->pwrctx); - drm_gem_object_unreference(&dev_priv->pwrctx->base); - dev_priv->pwrctx = NULL; + if (dev_priv->renderctx == NULL) + dev_priv->renderctx = intel_alloc_context_page(dev); + if (!dev_priv->renderctx) + return -ENOMEM; + + if (dev_priv->pwrctx == NULL) + dev_priv->pwrctx = intel_alloc_context_page(dev); + if (!dev_priv->pwrctx) { + ironlake_teardown_rc6(dev); + return -ENOMEM; + } + + return 0; } void ironlake_enable_rc6(struct drm_device *dev) @@ -6505,15 +6602,26 @@ void ironlake_enable_rc6(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; int ret; + /* rc6 disabled by default due to repeated reports of hanging during + * boot and resume. + */ + if (!i915_enable_rc6) + return; + + ret = ironlake_setup_rc6(dev); + if (ret) + return; + /* * GPU can automatically power down the render unit if given a page * to save state. */ ret = BEGIN_LP_RING(6); if (ret) { - ironlake_disable_rc6(dev); + ironlake_teardown_rc6(dev); return; } + OUT_RING(MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN); OUT_RING(MI_SET_CONTEXT); OUT_RING(dev_priv->renderctx->gtt_offset | @@ -6530,6 +6638,7 @@ void ironlake_enable_rc6(struct drm_device *dev) I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT); } + /* Set up chip specific display functions */ static void intel_init_display(struct drm_device *dev) { @@ -6772,21 +6881,9 @@ void intel_modeset_init(struct drm_device *dev) if (IS_GEN6(dev)) gen6_enable_rps(dev_priv); - if (IS_IRONLAKE_M(dev)) { - dev_priv->renderctx = intel_alloc_context_page(dev); - if (!dev_priv->renderctx) - goto skip_rc6; - dev_priv->pwrctx = intel_alloc_context_page(dev); - if (!dev_priv->pwrctx) { - i915_gem_object_unpin(dev_priv->renderctx); - drm_gem_object_unreference(&dev_priv->renderctx->base); - dev_priv->renderctx = NULL; - goto skip_rc6; - } + if (IS_IRONLAKE_M(dev)) ironlake_enable_rc6(dev); - } -skip_rc6: INIT_WORK(&dev_priv->idle_work, intel_idle_update); setup_timer(&dev_priv->idle_timer, intel_gpu_idle_timer, (unsigned long)dev); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 1f4242b..51cb4e3 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1639,6 +1639,24 @@ static int intel_dp_get_modes(struct drm_connector *connector) return 0; } +static bool +intel_dp_detect_audio(struct drm_connector *connector) +{ + struct intel_dp *intel_dp = intel_attached_dp(connector); + struct edid *edid; + bool has_audio = false; + + edid = drm_get_edid(connector, &intel_dp->adapter); + if (edid) { + has_audio = drm_detect_monitor_audio(edid); + + connector->display_info.raw_edid = NULL; + kfree(edid); + } + + return has_audio; +} + static int intel_dp_set_property(struct drm_connector *connector, struct drm_property *property, @@ -1652,17 +1670,23 @@ intel_dp_set_property(struct drm_connector *connector, return ret; if (property == intel_dp->force_audio_property) { - if (val == intel_dp->force_audio) + int i = val; + bool has_audio; + + if (i == intel_dp->force_audio) return 0; - intel_dp->force_audio = val; + intel_dp->force_audio = i; - if (val > 0 && intel_dp->has_audio) - return 0; - if (val < 0 && !intel_dp->has_audio) + if (i == 0) + has_audio = intel_dp_detect_audio(connector); + else + has_audio = i > 0; + + if (has_audio == intel_dp->has_audio) return 0; - intel_dp->has_audio = val > 0; + intel_dp->has_audio = has_audio; goto done; } diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 74db255..2c43104 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -298,7 +298,6 @@ extern void intel_crtc_fb_gamma_set(struct drm_crtc *crtc, u16 red, u16 green, extern void intel_crtc_fb_gamma_get(struct drm_crtc *crtc, u16 *red, u16 *green, u16 *blue, int regno); extern void intel_enable_clock_gating(struct drm_device *dev); -extern void intel_disable_clock_gating(struct drm_device *dev); extern void ironlake_enable_drps(struct drm_device *dev); extern void ironlake_disable_drps(struct drm_device *dev); extern void gen6_enable_rps(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 0d0273e..c635c9e 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -251,6 +251,27 @@ static int intel_hdmi_get_modes(struct drm_connector *connector) &dev_priv->gmbus[intel_hdmi->ddc_bus].adapter); } +static bool +intel_hdmi_detect_audio(struct drm_connector *connector) +{ + struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); + struct drm_i915_private *dev_priv = connector->dev->dev_private; + struct edid *edid; + bool has_audio = false; + + edid = drm_get_edid(connector, + &dev_priv->gmbus[intel_hdmi->ddc_bus].adapter); + if (edid) { + if (edid->input & DRM_EDID_INPUT_DIGITAL) + has_audio = drm_detect_monitor_audio(edid); + + connector->display_info.raw_edid = NULL; + kfree(edid); + } + + return has_audio; +} + static int intel_hdmi_set_property(struct drm_connector *connector, struct drm_property *property, @@ -264,17 +285,23 @@ intel_hdmi_set_property(struct drm_connector *connector, return ret; if (property == intel_hdmi->force_audio_property) { - if (val == intel_hdmi->force_audio) + int i = val; + bool has_audio; + + if (i == intel_hdmi->force_audio) return 0; - intel_hdmi->force_audio = val; + intel_hdmi->force_audio = i; - if (val > 0 && intel_hdmi->has_audio) - return 0; - if (val < 0 && !intel_hdmi->has_audio) + if (i == 0) + has_audio = intel_hdmi_detect_audio(connector); + else + has_audio = i > 0; + + if (has_audio == intel_hdmi->has_audio) return 0; - intel_hdmi->has_audio = val > 0; + intel_hdmi->has_audio = has_audio; goto done; } diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index ace8d5d..bcdba7b 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -261,12 +261,6 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, return true; } - /* Make sure pre-965s set dither correctly */ - if (INTEL_INFO(dev)->gen < 4) { - if (dev_priv->lvds_dither) - pfit_control |= PANEL_8TO6_DITHER_ENABLE; - } - /* Native modes don't need fitting */ if (adjusted_mode->hdisplay == mode->hdisplay && adjusted_mode->vdisplay == mode->vdisplay) @@ -374,10 +368,16 @@ static bool intel_lvds_mode_fixup(struct drm_encoder *encoder, } out: + /* If not enabling scaling, be consistent and always use 0. */ if ((pfit_control & PFIT_ENABLE) == 0) { pfit_control = 0; pfit_pgm_ratios = 0; } + + /* Make sure pre-965 set dither correctly */ + if (INTEL_INFO(dev)->gen < 4 && dev_priv->lvds_dither) + pfit_control |= PANEL_8TO6_DITHER_ENABLE; + if (pfit_control != intel_lvds->pfit_control || pfit_pgm_ratios != intel_lvds->pfit_pgm_ratios) { intel_lvds->pfit_control = pfit_control; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index c65992d..f8f86e5 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -208,7 +208,6 @@ u32 intel_panel_get_backlight(struct drm_device *dev) val &= ~1; pci_read_config_byte(dev->pdev, PCI_LBPC, &lbpc); val *= lbpc; - val >>= 1; } } @@ -235,11 +234,11 @@ void intel_panel_set_backlight(struct drm_device *dev, u32 level) if (is_backlight_combination_mode(dev)){ u32 max = intel_panel_get_max_backlight(dev); - u8 lpbc; + u8 lbpc; - lpbc = level * 0xfe / max + 1; - level /= lpbc; - pci_write_config_byte(dev->pdev, PCI_LBPC, lpbc); + lbpc = level * 0xfe / max + 1; + level /= lbpc; + pci_write_config_byte(dev->pdev, PCI_LBPC, lbpc); } tmp = I915_READ(BLC_PWM_CTL); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 6218fa9..445f27e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1059,22 +1059,25 @@ static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring, } static int gen6_ring_flush(struct intel_ring_buffer *ring, - u32 invalidate_domains, - u32 flush_domains) + u32 invalidate, u32 flush) { + uint32_t cmd; int ret; - if ((flush_domains & I915_GEM_DOMAIN_RENDER) == 0) + if (((invalidate | flush) & I915_GEM_GPU_DOMAINS) == 0) return 0; ret = intel_ring_begin(ring, 4); if (ret) return ret; - intel_ring_emit(ring, MI_FLUSH_DW); - intel_ring_emit(ring, 0); + cmd = MI_FLUSH_DW; + if (invalidate & I915_GEM_GPU_DOMAINS) + cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD; + intel_ring_emit(ring, cmd); intel_ring_emit(ring, 0); intel_ring_emit(ring, 0); + intel_ring_emit(ring, MI_NOOP); intel_ring_advance(ring); return 0; } @@ -1230,22 +1233,25 @@ static int blt_ring_begin(struct intel_ring_buffer *ring, } static int blt_ring_flush(struct intel_ring_buffer *ring, - u32 invalidate_domains, - u32 flush_domains) + u32 invalidate, u32 flush) { + uint32_t cmd; int ret; - if ((flush_domains & I915_GEM_DOMAIN_RENDER) == 0) + if (((invalidate | flush) & I915_GEM_DOMAIN_RENDER) == 0) return 0; ret = blt_ring_begin(ring, 4); if (ret) return ret; - intel_ring_emit(ring, MI_FLUSH_DW); - intel_ring_emit(ring, 0); + cmd = MI_FLUSH_DW; + if (invalidate & I915_GEM_DOMAIN_RENDER) + cmd |= MI_INVALIDATE_TLB; + intel_ring_emit(ring, cmd); intel_ring_emit(ring, 0); intel_ring_emit(ring, 0); + intel_ring_emit(ring, MI_NOOP); intel_ring_advance(ring); return 0; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 6d6fde8..3430686 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -14,22 +14,23 @@ struct intel_hw_status_page { struct drm_i915_gem_object *obj; }; -#define I915_RING_READ(reg) i915_safe_read(dev_priv, reg) +#define I915_RING_READ(reg) i915_gt_read(dev_priv, reg) +#define I915_RING_WRITE(reg, val) i915_gt_write(dev_priv, reg, val) #define I915_READ_TAIL(ring) I915_RING_READ(RING_TAIL((ring)->mmio_base)) -#define I915_WRITE_TAIL(ring, val) I915_WRITE(RING_TAIL((ring)->mmio_base), val) +#define I915_WRITE_TAIL(ring, val) I915_RING_WRITE(RING_TAIL((ring)->mmio_base), val) #define I915_READ_START(ring) I915_RING_READ(RING_START((ring)->mmio_base)) -#define I915_WRITE_START(ring, val) I915_WRITE(RING_START((ring)->mmio_base), val) +#define I915_WRITE_START(ring, val) I915_RING_WRITE(RING_START((ring)->mmio_base), val) #define I915_READ_HEAD(ring) I915_RING_READ(RING_HEAD((ring)->mmio_base)) -#define I915_WRITE_HEAD(ring, val) I915_WRITE(RING_HEAD((ring)->mmio_base), val) +#define I915_WRITE_HEAD(ring, val) I915_RING_WRITE(RING_HEAD((ring)->mmio_base), val) #define I915_READ_CTL(ring) I915_RING_READ(RING_CTL((ring)->mmio_base)) -#define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val) +#define I915_WRITE_CTL(ring, val) I915_RING_WRITE(RING_CTL((ring)->mmio_base), val) -#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val) #define I915_READ_IMR(ring) I915_RING_READ(RING_IMR((ring)->mmio_base)) +#define I915_WRITE_IMR(ring, val) I915_RING_WRITE(RING_IMR((ring)->mmio_base), val) #define I915_READ_NOPID(ring) I915_RING_READ(RING_NOPID((ring)->mmio_base)) #define I915_READ_SYNC_0(ring) I915_RING_READ(RING_SYNC_0((ring)->mmio_base)) diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 45cd376..7c50cdc 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -46,6 +46,7 @@ SDVO_TV_MASK) #define IS_TV(c) (c->output_flag & SDVO_TV_MASK) +#define IS_TMDS(c) (c->output_flag & SDVO_TMDS_MASK) #define IS_LVDS(c) (c->output_flag & SDVO_LVDS_MASK) #define IS_TV_OR_LVDS(c) (c->output_flag & (SDVO_TV_MASK | SDVO_LVDS_MASK)) @@ -473,20 +474,6 @@ static bool intel_sdvo_write_cmd(struct intel_sdvo *intel_sdvo, u8 cmd, return false; } - i = 3; - while (status == SDVO_CMD_STATUS_PENDING && i--) { - if (!intel_sdvo_read_byte(intel_sdvo, - SDVO_I2C_CMD_STATUS, - &status)) - return false; - } - if (status != SDVO_CMD_STATUS_SUCCESS) { - DRM_DEBUG_KMS("command returns response %s [%d]\n", - status <= SDVO_CMD_STATUS_SCALING_NOT_SUPP ? cmd_status_names[status] : "???", - status); - return false; - } - return true; } @@ -497,6 +484,8 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo, u8 status; int i; + DRM_DEBUG_KMS("%s: R: ", SDVO_NAME(intel_sdvo)); + /* * The documentation states that all commands will be * processed within 15µs, and that we need only poll @@ -505,14 +494,19 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo, * * Check 5 times in case the hardware failed to read the docs. */ - do { + if (!intel_sdvo_read_byte(intel_sdvo, + SDVO_I2C_CMD_STATUS, + &status)) + goto log_fail; + + while (status == SDVO_CMD_STATUS_PENDING && retry--) { + udelay(15); if (!intel_sdvo_read_byte(intel_sdvo, SDVO_I2C_CMD_STATUS, &status)) - return false; - } while (status == SDVO_CMD_STATUS_PENDING && --retry); + goto log_fail; + } - DRM_DEBUG_KMS("%s: R: ", SDVO_NAME(intel_sdvo)); if (status <= SDVO_CMD_STATUS_SCALING_NOT_SUPP) DRM_LOG_KMS("(%s)", cmd_status_names[status]); else @@ -533,7 +527,7 @@ static bool intel_sdvo_read_response(struct intel_sdvo *intel_sdvo, return true; log_fail: - DRM_LOG_KMS("\n"); + DRM_LOG_KMS("... failed\n"); return false; } @@ -550,6 +544,7 @@ static int intel_sdvo_get_pixel_multiplier(struct drm_display_mode *mode) static bool intel_sdvo_set_control_bus_switch(struct intel_sdvo *intel_sdvo, u8 ddc_bus) { + /* This must be the immediately preceding write before the i2c xfer */ return intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_CONTROL_BUS_SWITCH, &ddc_bus, 1); @@ -557,7 +552,10 @@ static bool intel_sdvo_set_control_bus_switch(struct intel_sdvo *intel_sdvo, static bool intel_sdvo_set_value(struct intel_sdvo *intel_sdvo, u8 cmd, const void *data, int len) { - return intel_sdvo_write_cmd(intel_sdvo, cmd, data, len); + if (!intel_sdvo_write_cmd(intel_sdvo, cmd, data, len)) + return false; + + return intel_sdvo_read_response(intel_sdvo, NULL, 0); } static bool @@ -859,18 +857,21 @@ static bool intel_sdvo_set_avi_infoframe(struct intel_sdvo *intel_sdvo) intel_dip_infoframe_csum(&avi_if); - if (!intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_HBUF_INDEX, + if (!intel_sdvo_set_value(intel_sdvo, + SDVO_CMD_SET_HBUF_INDEX, set_buf_index, 2)) return false; for (i = 0; i < sizeof(avi_if); i += 8) { - if (!intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_HBUF_DATA, + if (!intel_sdvo_set_value(intel_sdvo, + SDVO_CMD_SET_HBUF_DATA, data, 8)) return false; data++; } - return intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_HBUF_TXRATE, + return intel_sdvo_set_value(intel_sdvo, + SDVO_CMD_SET_HBUF_TXRATE, &tx_rate, 1); } @@ -1359,7 +1360,8 @@ intel_sdvo_hdmi_sink_detect(struct drm_connector *connector) intel_sdvo->has_hdmi_monitor = drm_detect_hdmi_monitor(edid); intel_sdvo->has_hdmi_audio = drm_detect_monitor_audio(edid); } - } + } else + status = connector_status_disconnected; connector->display_info.raw_edid = NULL; kfree(edid); } @@ -1407,10 +1409,25 @@ intel_sdvo_detect(struct drm_connector *connector, bool force) if ((intel_sdvo_connector->output_flag & response) == 0) ret = connector_status_disconnected; - else if (response & SDVO_TMDS_MASK) + else if (IS_TMDS(intel_sdvo_connector)) ret = intel_sdvo_hdmi_sink_detect(connector); - else - ret = connector_status_connected; + else { + struct edid *edid; + + /* if we have an edid check it matches the connection */ + edid = intel_sdvo_get_edid(connector); + if (edid == NULL) + edid = intel_sdvo_get_analog_edid(connector); + if (edid != NULL) { + if (edid->input & DRM_EDID_INPUT_DIGITAL) + ret = connector_status_disconnected; + else + ret = connector_status_connected; + connector->display_info.raw_edid = NULL; + kfree(edid); + } else + ret = connector_status_connected; + } /* May update encoder flag for like clock for SDVO TV, etc.*/ if (ret == connector_status_connected) { @@ -1446,10 +1463,15 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector) edid = intel_sdvo_get_analog_edid(connector); if (edid != NULL) { - if (edid->input & DRM_EDID_INPUT_DIGITAL) { + struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); + bool monitor_is_digital = !!(edid->input & DRM_EDID_INPUT_DIGITAL); + bool connector_is_digital = !!IS_TMDS(intel_sdvo_connector); + + if (connector_is_digital == monitor_is_digital) { drm_mode_connector_update_edid_property(connector, edid); drm_add_edid_modes(connector, edid); } + connector->display_info.raw_edid = NULL; kfree(edid); } @@ -1668,6 +1690,22 @@ static void intel_sdvo_destroy(struct drm_connector *connector) kfree(connector); } +static bool intel_sdvo_detect_hdmi_audio(struct drm_connector *connector) +{ + struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector); + struct edid *edid; + bool has_audio = false; + + if (!intel_sdvo->is_hdmi) + return false; + + edid = intel_sdvo_get_edid(connector); + if (edid != NULL && edid->input & DRM_EDID_INPUT_DIGITAL) + has_audio = drm_detect_monitor_audio(edid); + + return has_audio; +} + static int intel_sdvo_set_property(struct drm_connector *connector, struct drm_property *property, @@ -1684,17 +1722,23 @@ intel_sdvo_set_property(struct drm_connector *connector, return ret; if (property == intel_sdvo_connector->force_audio_property) { - if (val == intel_sdvo_connector->force_audio) + int i = val; + bool has_audio; + + if (i == intel_sdvo_connector->force_audio) return 0; - intel_sdvo_connector->force_audio = val; + intel_sdvo_connector->force_audio = i; - if (val > 0 && intel_sdvo->has_hdmi_audio) - return 0; - if (val < 0 && !intel_sdvo->has_hdmi_audio) + if (i == 0) + has_audio = intel_sdvo_detect_hdmi_audio(connector); + else + has_audio = i > 0; + + if (has_audio == intel_sdvo->has_hdmi_audio) return 0; - intel_sdvo->has_hdmi_audio = val > 0; + intel_sdvo->has_hdmi_audio = has_audio; goto done; } diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 93206e4..fe4a53a 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1234,7 +1234,8 @@ static const struct drm_display_mode reported_modes[] = { * \return false if TV is disconnected. */ static int -intel_tv_detect_type (struct intel_tv *intel_tv) +intel_tv_detect_type (struct intel_tv *intel_tv, + struct drm_connector *connector) { struct drm_encoder *encoder = &intel_tv->base.base; struct drm_device *dev = encoder->dev; @@ -1245,11 +1246,13 @@ intel_tv_detect_type (struct intel_tv *intel_tv) int type; /* Disable TV interrupts around load detect or we'll recurse */ - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - i915_disable_pipestat(dev_priv, 0, - PIPE_HOTPLUG_INTERRUPT_ENABLE | - PIPE_HOTPLUG_TV_INTERRUPT_ENABLE); - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + if (connector->polled & DRM_CONNECTOR_POLL_HPD) { + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + i915_disable_pipestat(dev_priv, 0, + PIPE_HOTPLUG_INTERRUPT_ENABLE | + PIPE_HOTPLUG_TV_INTERRUPT_ENABLE); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + } save_tv_dac = tv_dac = I915_READ(TV_DAC); save_tv_ctl = tv_ctl = I915_READ(TV_CTL); @@ -1302,11 +1305,13 @@ intel_tv_detect_type (struct intel_tv *intel_tv) I915_WRITE(TV_CTL, save_tv_ctl); /* Restore interrupt config */ - spin_lock_irqsave(&dev_priv->irq_lock, irqflags); - i915_enable_pipestat(dev_priv, 0, - PIPE_HOTPLUG_INTERRUPT_ENABLE | - PIPE_HOTPLUG_TV_INTERRUPT_ENABLE); - spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + if (connector->polled & DRM_CONNECTOR_POLL_HPD) { + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + i915_enable_pipestat(dev_priv, 0, + PIPE_HOTPLUG_INTERRUPT_ENABLE | + PIPE_HOTPLUG_TV_INTERRUPT_ENABLE); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + } return type; } @@ -1356,7 +1361,7 @@ intel_tv_detect(struct drm_connector *connector, bool force) drm_mode_set_crtcinfo(&mode, CRTC_INTERLACE_HALVE_V); if (intel_tv->base.base.crtc && intel_tv->base.base.crtc->enabled) { - type = intel_tv_detect_type(intel_tv); + type = intel_tv_detect_type(intel_tv, connector); } else if (force) { struct drm_crtc *crtc; int dpms_mode; @@ -1364,7 +1369,7 @@ intel_tv_detect(struct drm_connector *connector, bool force) crtc = intel_get_load_detect_pipe(&intel_tv->base, connector, &mode, &dpms_mode); if (crtc) { - type = intel_tv_detect_type(intel_tv); + type = intel_tv_detect_type(intel_tv, connector); intel_release_load_detect_pipe(&intel_tv->base, connector, dpms_mode); } else @@ -1658,6 +1663,18 @@ intel_tv_init(struct drm_device *dev) intel_encoder = &intel_tv->base; connector = &intel_connector->base; + /* The documentation, for the older chipsets at least, recommend + * using a polling method rather than hotplug detection for TVs. + * This is because in order to perform the hotplug detection, the PLLs + * for the TV must be kept alive increasing power drain and starving + * bandwidth from other encoders. Notably for instance, it causes + * pipe underruns on Crestline when this encoder is supposedly idle. + * + * More recent chipsets favour HDMI rather than integrated S-Video. + */ + connector->polled = + DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; + drm_connector_init(dev, connector, &intel_tv_connector_funcs, DRM_MODE_CONNECTOR_SVIDEO); diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 49e5e99..6bdab89 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -6228,7 +6228,7 @@ parse_dcb15_entry(struct drm_device *dev, struct dcb_table *dcb, entry->tvconf.has_component_output = false; break; case OUTPUT_LVDS: - if ((conn & 0x00003f00) != 0x10) + if ((conn & 0x00003f00) >> 8 != 0x10) entry->lvdsconf.use_straps_for_mode = true; entry->lvdsconf.use_power_scripts = true; break; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index a7fae26..a521840 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -49,7 +49,10 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo) DRM_ERROR("bo %p still attached to GEM object\n", bo); nv10_mem_put_tile_region(dev, nvbo->tile, NULL); - nouveau_vm_put(&nvbo->vma); + if (nvbo->vma.node) { + nouveau_vm_unmap(&nvbo->vma); + nouveau_vm_put(&nvbo->vma); + } kfree(nvbo); } @@ -128,6 +131,7 @@ nouveau_bo_new(struct drm_device *dev, struct nouveau_channel *chan, } } + nvbo->bo.mem.num_pages = size >> PAGE_SHIFT; nouveau_bo_placement_set(nvbo, flags, 0); nvbo->channel = chan; @@ -166,17 +170,17 @@ static void set_placement_range(struct nouveau_bo *nvbo, uint32_t type) { struct drm_nouveau_private *dev_priv = nouveau_bdev(nvbo->bo.bdev); + int vram_pages = dev_priv->vram_size >> PAGE_SHIFT; if (dev_priv->card_type == NV_10 && - nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM)) { + nvbo->tile_mode && (type & TTM_PL_FLAG_VRAM) && + nvbo->bo.mem.num_pages < vram_pages / 2) { /* * Make sure that the color and depth buffers are handled * by independent memory controller units. Up to a 9x * speed up when alpha-blending and depth-test are enabled * at the same time. */ - int vram_pages = dev_priv->vram_size >> PAGE_SHIFT; - if (nvbo->tile_flags & NOUVEAU_GEM_TILE_ZETA) { nvbo->placement.fpfn = vram_pages / 2; nvbo->placement.lpfn = ~0; @@ -785,7 +789,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr, if (ret) goto out; - ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, new_mem); + ret = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, new_mem); out: ttm_bo_mem_put(bo, &tmp_mem); return ret; @@ -811,11 +815,11 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr, if (ret) return ret; - ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, &tmp_mem); + ret = ttm_bo_move_ttm(bo, true, no_wait_reserve, no_wait_gpu, &tmp_mem); if (ret) goto out; - ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait_reserve, no_wait_gpu, new_mem); + ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait_reserve, no_wait_gpu, new_mem); if (ret) goto out; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index a21e000..390d82c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -507,6 +507,7 @@ nouveau_connector_native_mode(struct drm_connector *connector) int high_w = 0, high_h = 0, high_v = 0; list_for_each_entry(mode, &nv_connector->base.probed_modes, head) { + mode->vrefresh = drm_mode_vrefresh(mode); if (helper->mode_valid(connector, mode) != MODE_OK || (mode->flags & DRM_MODE_FLAG_INTERLACE)) continue; diff --git a/drivers/gpu/drm/nouveau/nouveau_dma.c b/drivers/gpu/drm/nouveau/nouveau_dma.c index 65699bf..b368ed7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dma.c +++ b/drivers/gpu/drm/nouveau/nouveau_dma.c @@ -83,7 +83,8 @@ nouveau_dma_init(struct nouveau_channel *chan) return ret; /* NV_MEMORY_TO_MEMORY_FORMAT requires a notifier object */ - ret = nouveau_notifier_alloc(chan, NvNotify0, 32, &chan->m2mf_ntfy); + ret = nouveau_notifier_alloc(chan, NvNotify0, 32, 0xfd0, 0x1000, + &chan->m2mf_ntfy); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 9821fca..982d70b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -852,7 +852,8 @@ extern const struct ttm_mem_type_manager_func nouveau_vram_manager; extern int nouveau_notifier_init_channel(struct nouveau_channel *); extern void nouveau_notifier_takedown_channel(struct nouveau_channel *); extern int nouveau_notifier_alloc(struct nouveau_channel *, uint32_t handle, - int cout, uint32_t *offset); + int cout, uint32_t start, uint32_t end, + uint32_t *offset); extern int nouveau_notifier_offset(struct nouveau_gpuobj *, uint32_t *); extern int nouveau_ioctl_notifier_alloc(struct drm_device *, void *data, struct drm_file *); diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index 26347b7..b0fb9bd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -725,8 +725,10 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man, ret = vram->get(dev, mem->num_pages << PAGE_SHIFT, mem->page_alignment << PAGE_SHIFT, size_nc, (nvbo->tile_flags >> 8) & 0xff, &node); - if (ret) - return ret; + if (ret) { + mem->mm_node = NULL; + return (ret == -ENOSPC) ? 0 : ret; + } node->page_shift = 12; if (nvbo->vma.node) diff --git a/drivers/gpu/drm/nouveau/nouveau_mm.c b/drivers/gpu/drm/nouveau/nouveau_mm.c index 8844b50c..7609756 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mm.c +++ b/drivers/gpu/drm/nouveau/nouveau_mm.c @@ -123,7 +123,7 @@ nouveau_mm_get(struct nouveau_mm *rmm, int type, u32 size, u32 size_nc, return 0; } - return -ENOMEM; + return -ENOSPC; } int diff --git a/drivers/gpu/drm/nouveau/nouveau_notifier.c b/drivers/gpu/drm/nouveau/nouveau_notifier.c index fe29d60..5ea1676 100644 --- a/drivers/gpu/drm/nouveau/nouveau_notifier.c +++ b/drivers/gpu/drm/nouveau/nouveau_notifier.c @@ -96,7 +96,8 @@ nouveau_notifier_gpuobj_dtor(struct drm_device *dev, int nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle, - int size, uint32_t *b_offset) + int size, uint32_t start, uint32_t end, + uint32_t *b_offset) { struct drm_device *dev = chan->dev; struct nouveau_gpuobj *nobj = NULL; @@ -104,9 +105,10 @@ nouveau_notifier_alloc(struct nouveau_channel *chan, uint32_t handle, uint32_t offset; int target, ret; - mem = drm_mm_search_free(&chan->notifier_heap, size, 0, 0); + mem = drm_mm_search_free_in_range(&chan->notifier_heap, size, 0, + start, end, 0); if (mem) - mem = drm_mm_get_block(mem, size, 0); + mem = drm_mm_get_block_range(mem, size, 0, start, end); if (!mem) { NV_ERROR(dev, "Channel %d notifier block full\n", chan->id); return -ENOMEM; @@ -177,7 +179,8 @@ nouveau_ioctl_notifier_alloc(struct drm_device *dev, void *data, if (IS_ERR(chan)) return PTR_ERR(chan); - ret = nouveau_notifier_alloc(chan, na->handle, na->size, &na->offset); + ret = nouveau_notifier_alloc(chan, na->handle, na->size, 0, 0x1000, + &na->offset); nouveau_channel_put(&chan); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_pm.c b/drivers/gpu/drm/nouveau/nouveau_pm.c index fb846a3..4399e2f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_pm.c +++ b/drivers/gpu/drm/nouveau/nouveau_pm.c @@ -443,7 +443,7 @@ nouveau_hwmon_fini(struct drm_device *dev) struct nouveau_pm_engine *pm = &dev_priv->engine.pm; if (pm->hwmon) { - sysfs_remove_group(&pm->hwmon->kobj, &hwmon_attrgroup); + sysfs_remove_group(&dev->pdev->dev.kobj, &hwmon_attrgroup); hwmon_device_unregister(pm->hwmon); } #endif @@ -543,7 +543,7 @@ nouveau_pm_resume(struct drm_device *dev) struct nouveau_pm_engine *pm = &dev_priv->engine.pm; struct nouveau_pm_level *perflvl; - if (pm->cur == &pm->boot) + if (!pm->cur || pm->cur == &pm->boot) return; perflvl = pm->cur; diff --git a/drivers/gpu/drm/nouveau/nv04_dfp.c b/drivers/gpu/drm/nouveau/nv04_dfp.c index ef23550..c82db37 100644 --- a/drivers/gpu/drm/nouveau/nv04_dfp.c +++ b/drivers/gpu/drm/nouveau/nv04_dfp.c @@ -342,8 +342,8 @@ static void nv04_dfp_mode_set(struct drm_encoder *encoder, if (nv_encoder->dcb->type == OUTPUT_LVDS) { bool duallink, dummy; - nouveau_bios_parse_lvds_table(dev, nv_connector->native_mode-> - clock, &duallink, &dummy); + nouveau_bios_parse_lvds_table(dev, output_mode->clock, + &duallink, &dummy); if (duallink) regp->fp_control |= (8 << 28); } else @@ -518,8 +518,6 @@ static void nv04_lvds_dpms(struct drm_encoder *encoder, int mode) return; if (nv_encoder->dcb->lvdsconf.use_power_scripts) { - struct nouveau_connector *nv_connector = nouveau_encoder_connector_get(nv_encoder); - /* when removing an output, crtc may not be set, but PANEL_OFF * must still be run */ @@ -527,12 +525,8 @@ static void nv04_lvds_dpms(struct drm_encoder *encoder, int mode) nv04_dfp_get_bound_head(dev, nv_encoder->dcb); if (mode == DRM_MODE_DPMS_ON) { - if (!nv_connector->native_mode) { - NV_ERROR(dev, "Not turning on LVDS without native mode\n"); - return; - } call_lvds_script(dev, nv_encoder->dcb, head, - LVDS_PANEL_ON, nv_connector->native_mode->clock); + LVDS_PANEL_ON, nv_encoder->mode.clock); } else /* pxclk of 0 is fine for PANEL_OFF, and for a * disconnected LVDS encoder there is no native_mode diff --git a/drivers/gpu/drm/nouveau/nv40_graph.c b/drivers/gpu/drm/nouveau/nv40_graph.c index 8870d72..18d30c2 100644 --- a/drivers/gpu/drm/nouveau/nv40_graph.c +++ b/drivers/gpu/drm/nouveau/nv40_graph.c @@ -211,18 +211,32 @@ nv40_graph_set_tile_region(struct drm_device *dev, int i) struct nouveau_tile_reg *tile = &dev_priv->tile.reg[i]; switch (dev_priv->chipset) { + case 0x40: + case 0x41: /* guess */ + case 0x42: + case 0x43: + case 0x45: /* guess */ + case 0x4e: + nv_wr32(dev, NV20_PGRAPH_TSIZE(i), tile->pitch); + nv_wr32(dev, NV20_PGRAPH_TLIMIT(i), tile->limit); + nv_wr32(dev, NV20_PGRAPH_TILE(i), tile->addr); + nv_wr32(dev, NV40_PGRAPH_TSIZE1(i), tile->pitch); + nv_wr32(dev, NV40_PGRAPH_TLIMIT1(i), tile->limit); + nv_wr32(dev, NV40_PGRAPH_TILE1(i), tile->addr); + break; case 0x44: case 0x4a: - case 0x4e: nv_wr32(dev, NV20_PGRAPH_TSIZE(i), tile->pitch); nv_wr32(dev, NV20_PGRAPH_TLIMIT(i), tile->limit); nv_wr32(dev, NV20_PGRAPH_TILE(i), tile->addr); break; - case 0x46: case 0x47: case 0x49: case 0x4b: + case 0x4c: + case 0x67: + default: nv_wr32(dev, NV47_PGRAPH_TSIZE(i), tile->pitch); nv_wr32(dev, NV47_PGRAPH_TLIMIT(i), tile->limit); nv_wr32(dev, NV47_PGRAPH_TILE(i), tile->addr); @@ -230,15 +244,6 @@ nv40_graph_set_tile_region(struct drm_device *dev, int i) nv_wr32(dev, NV40_PGRAPH_TLIMIT1(i), tile->limit); nv_wr32(dev, NV40_PGRAPH_TILE1(i), tile->addr); break; - - default: - nv_wr32(dev, NV20_PGRAPH_TSIZE(i), tile->pitch); - nv_wr32(dev, NV20_PGRAPH_TLIMIT(i), tile->limit); - nv_wr32(dev, NV20_PGRAPH_TILE(i), tile->addr); - nv_wr32(dev, NV40_PGRAPH_TSIZE1(i), tile->pitch); - nv_wr32(dev, NV40_PGRAPH_TLIMIT1(i), tile->limit); - nv_wr32(dev, NV40_PGRAPH_TILE1(i), tile->addr); - break; } } @@ -396,17 +401,20 @@ nv40_graph_init(struct drm_device *dev) break; default: switch (dev_priv->chipset) { - case 0x46: - case 0x47: - case 0x49: - case 0x4b: - nv_wr32(dev, 0x400DF0, nv_rd32(dev, NV04_PFB_CFG0)); - nv_wr32(dev, 0x400DF4, nv_rd32(dev, NV04_PFB_CFG1)); - break; - default: + case 0x41: + case 0x42: + case 0x43: + case 0x45: + case 0x4e: + case 0x44: + case 0x4a: nv_wr32(dev, 0x4009F0, nv_rd32(dev, NV04_PFB_CFG0)); nv_wr32(dev, 0x4009F4, nv_rd32(dev, NV04_PFB_CFG1)); break; + default: + nv_wr32(dev, 0x400DF0, nv_rd32(dev, NV04_PFB_CFG0)); + nv_wr32(dev, 0x400DF4, nv_rd32(dev, NV04_PFB_CFG1)); + break; } nv_wr32(dev, 0x4069F0, nv_rd32(dev, NV04_PFB_CFG0)); nv_wr32(dev, 0x4069F4, nv_rd32(dev, NV04_PFB_CFG1)); diff --git a/drivers/gpu/drm/nouveau/nv50_evo.c b/drivers/gpu/drm/nouveau/nv50_evo.c index 14e24e9..0ea090f 100644 --- a/drivers/gpu/drm/nouveau/nv50_evo.c +++ b/drivers/gpu/drm/nouveau/nv50_evo.c @@ -283,8 +283,7 @@ nv50_evo_create(struct drm_device *dev) nv50_evo_channel_del(&dev_priv->evo); return ret; } - } else - if (dev_priv->chipset != 0x50) { + } else { ret = nv50_evo_dmaobj_new(evo, 0x3d, NvEvoFB16, 0x70, 0x19, 0, 0xffffffff, 0x00010000); if (ret) { diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c index ea00418..e57caa2 100644 --- a/drivers/gpu/drm/nouveau/nv50_instmem.c +++ b/drivers/gpu/drm/nouveau/nv50_instmem.c @@ -403,16 +403,24 @@ nv50_instmem_unmap(struct nouveau_gpuobj *gpuobj) void nv50_instmem_flush(struct drm_device *dev) { + struct drm_nouveau_private *dev_priv = dev->dev_private; + + spin_lock(&dev_priv->ramin_lock); nv_wr32(dev, 0x00330c, 0x00000001); if (!nv_wait(dev, 0x00330c, 0x00000002, 0x00000000)) NV_ERROR(dev, "PRAMIN flush timeout\n"); + spin_unlock(&dev_priv->ramin_lock); } void nv84_instmem_flush(struct drm_device *dev) { + struct drm_nouveau_private *dev_priv = dev->dev_private; + + spin_lock(&dev_priv->ramin_lock); nv_wr32(dev, 0x070000, 0x00000001); if (!nv_wait(dev, 0x070000, 0x00000002, 0x00000000)) NV_ERROR(dev, "PRAMIN flush timeout\n"); + spin_unlock(&dev_priv->ramin_lock); } diff --git a/drivers/gpu/drm/nouveau/nv50_vm.c b/drivers/gpu/drm/nouveau/nv50_vm.c index 459ff08..6144156 100644 --- a/drivers/gpu/drm/nouveau/nv50_vm.c +++ b/drivers/gpu/drm/nouveau/nv50_vm.c @@ -169,7 +169,11 @@ nv50_vm_flush(struct nouveau_vm *vm) void nv50_vm_flush_engine(struct drm_device *dev, int engine) { + struct drm_nouveau_private *dev_priv = dev->dev_private; + + spin_lock(&dev_priv->ramin_lock); nv_wr32(dev, 0x100c80, (engine << 16) | 1); if (!nv_wait(dev, 0x100c80, 0x00000001, 0x00000000)) NV_ERROR(dev, "vm flush timeout: engine %d\n", engine); + spin_unlock(&dev_priv->ramin_lock); } diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 842954f..a4e5e53 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -48,29 +48,29 @@ static void atombios_overscan_setup(struct drm_crtc *crtc, switch (radeon_crtc->rmx_type) { case RMX_CENTER: - args.usOverscanTop = (adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2; - args.usOverscanBottom = (adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2; - args.usOverscanLeft = (adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2; - args.usOverscanRight = (adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2; + args.usOverscanTop = cpu_to_le16((adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2); + args.usOverscanBottom = cpu_to_le16((adjusted_mode->crtc_vdisplay - mode->crtc_vdisplay) / 2); + args.usOverscanLeft = cpu_to_le16((adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2); + args.usOverscanRight = cpu_to_le16((adjusted_mode->crtc_hdisplay - mode->crtc_hdisplay) / 2); break; case RMX_ASPECT: a1 = mode->crtc_vdisplay * adjusted_mode->crtc_hdisplay; a2 = adjusted_mode->crtc_vdisplay * mode->crtc_hdisplay; if (a1 > a2) { - args.usOverscanLeft = (adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2; - args.usOverscanRight = (adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2; + args.usOverscanLeft = cpu_to_le16((adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2); + args.usOverscanRight = cpu_to_le16((adjusted_mode->crtc_hdisplay - (a2 / mode->crtc_vdisplay)) / 2); } else if (a2 > a1) { - args.usOverscanLeft = (adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2; - args.usOverscanRight = (adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2; + args.usOverscanLeft = cpu_to_le16((adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2); + args.usOverscanRight = cpu_to_le16((adjusted_mode->crtc_vdisplay - (a1 / mode->crtc_hdisplay)) / 2); } break; case RMX_FULL: default: - args.usOverscanRight = radeon_crtc->h_border; - args.usOverscanLeft = radeon_crtc->h_border; - args.usOverscanBottom = radeon_crtc->v_border; - args.usOverscanTop = radeon_crtc->v_border; + args.usOverscanRight = cpu_to_le16(radeon_crtc->h_border); + args.usOverscanLeft = cpu_to_le16(radeon_crtc->h_border); + args.usOverscanBottom = cpu_to_le16(radeon_crtc->v_border); + args.usOverscanTop = cpu_to_le16(radeon_crtc->v_border); break; } atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); @@ -419,23 +419,23 @@ static void atombios_crtc_program_ss(struct drm_crtc *crtc, memset(&args, 0, sizeof(args)); if (ASIC_IS_DCE5(rdev)) { - args.v3.usSpreadSpectrumAmountFrac = 0; + args.v3.usSpreadSpectrumAmountFrac = cpu_to_le16(0); args.v3.ucSpreadSpectrumType = ss->type; switch (pll_id) { case ATOM_PPLL1: args.v3.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V3_P1PLL; - args.v3.usSpreadSpectrumAmount = ss->amount; - args.v3.usSpreadSpectrumStep = ss->step; + args.v3.usSpreadSpectrumAmount = cpu_to_le16(ss->amount); + args.v3.usSpreadSpectrumStep = cpu_to_le16(ss->step); break; case ATOM_PPLL2: args.v3.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V3_P2PLL; - args.v3.usSpreadSpectrumAmount = ss->amount; - args.v3.usSpreadSpectrumStep = ss->step; + args.v3.usSpreadSpectrumAmount = cpu_to_le16(ss->amount); + args.v3.usSpreadSpectrumStep = cpu_to_le16(ss->step); break; case ATOM_DCPLL: args.v3.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V3_DCPLL; - args.v3.usSpreadSpectrumAmount = 0; - args.v3.usSpreadSpectrumStep = 0; + args.v3.usSpreadSpectrumAmount = cpu_to_le16(0); + args.v3.usSpreadSpectrumStep = cpu_to_le16(0); break; case ATOM_PPLL_INVALID: return; @@ -447,18 +447,18 @@ static void atombios_crtc_program_ss(struct drm_crtc *crtc, switch (pll_id) { case ATOM_PPLL1: args.v2.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V2_P1PLL; - args.v2.usSpreadSpectrumAmount = ss->amount; - args.v2.usSpreadSpectrumStep = ss->step; + args.v2.usSpreadSpectrumAmount = cpu_to_le16(ss->amount); + args.v2.usSpreadSpectrumStep = cpu_to_le16(ss->step); break; case ATOM_PPLL2: args.v2.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V2_P2PLL; - args.v2.usSpreadSpectrumAmount = ss->amount; - args.v2.usSpreadSpectrumStep = ss->step; + args.v2.usSpreadSpectrumAmount = cpu_to_le16(ss->amount); + args.v2.usSpreadSpectrumStep = cpu_to_le16(ss->step); break; case ATOM_DCPLL: args.v2.ucSpreadSpectrumType |= ATOM_PPLL_SS_TYPE_V2_DCPLL; - args.v2.usSpreadSpectrumAmount = 0; - args.v2.usSpreadSpectrumStep = 0; + args.v2.usSpreadSpectrumAmount = cpu_to_le16(0); + args.v2.usSpreadSpectrumStep = cpu_to_le16(0); break; case ATOM_PPLL_INVALID: return; @@ -538,7 +538,6 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, pll->flags |= RADEON_PLL_PREFER_HIGH_FB_DIV; else pll->flags |= RADEON_PLL_PREFER_LOW_REF_DIV; - } list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) { @@ -555,23 +554,28 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, dp_clock = dig_connector->dp_clock; } } -#if 0 /* doesn't work properly on some laptops */ + /* use recommended ref_div for ss */ if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { if (ss_enabled) { if (ss->refdiv) { + pll->flags |= RADEON_PLL_PREFER_MINM_OVER_MAXP; pll->flags |= RADEON_PLL_USE_REF_DIV; pll->reference_div = ss->refdiv; + if (ASIC_IS_AVIVO(rdev)) + pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV; } } } -#endif + if (ASIC_IS_AVIVO(rdev)) { /* DVO wants 2x pixel clock if the DVO chip is in 12 bit mode */ if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_KLDSCP_DVO1) adjusted_clock = mode->clock * 2; if (radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT)) pll->flags |= RADEON_PLL_PREFER_CLOSEST_LOWER; + if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) + pll->flags |= RADEON_PLL_IS_LCD; } else { if (encoder->encoder_type != DRM_MODE_ENCODER_DAC) pll->flags |= RADEON_PLL_NO_ODD_POST_DIV; @@ -658,10 +662,12 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, index, (uint32_t *)&args); adjusted_clock = le32_to_cpu(args.v3.sOutput.ulDispPllFreq) * 10; if (args.v3.sOutput.ucRefDiv) { + pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV; pll->flags |= RADEON_PLL_USE_REF_DIV; pll->reference_div = args.v3.sOutput.ucRefDiv; } if (args.v3.sOutput.ucPostDiv) { + pll->flags |= RADEON_PLL_USE_FRAC_FB_DIV; pll->flags |= RADEON_PLL_USE_POST_DIV; pll->post_div = args.v3.sOutput.ucPostDiv; } @@ -715,14 +721,14 @@ static void atombios_crtc_set_dcpll(struct drm_crtc *crtc, * SetPixelClock provides the dividers */ args.v5.ucCRTC = ATOM_CRTC_INVALID; - args.v5.usPixelClock = dispclk; + args.v5.usPixelClock = cpu_to_le16(dispclk); args.v5.ucPpll = ATOM_DCPLL; break; case 6: /* if the default dcpll clock is specified, * SetPixelClock provides the dividers */ - args.v6.ulDispEngClkFreq = dispclk; + args.v6.ulDispEngClkFreq = cpu_to_le32(dispclk); args.v6.ucPpll = ATOM_DCPLL; break; default: @@ -951,8 +957,12 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode /* adjust pixel clock as needed */ adjusted_clock = atombios_adjust_pll(crtc, mode, pll, ss_enabled, &ss); - radeon_compute_pll(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div, - &ref_div, &post_div); + if (ASIC_IS_AVIVO(rdev)) + radeon_compute_pll_avivo(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div, + &ref_div, &post_div); + else + radeon_compute_pll_legacy(pll, adjusted_clock, &pll_clock, &fb_div, &frac_fb_div, + &ref_div, &post_div); atombios_crtc_program_ss(crtc, ATOM_DISABLE, radeon_crtc->pll_id, &ss); @@ -981,9 +991,9 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode } } -static int evergreen_crtc_do_set_base(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y, int atomic) +static int dce4_crtc_do_set_base(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y, int atomic) { struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct drm_device *dev = crtc->dev; @@ -1123,12 +1133,6 @@ static int evergreen_crtc_do_set_base(struct drm_crtc *crtc, WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset, (crtc->mode.hdisplay << 16) | crtc->mode.vdisplay); - if (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) - WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset, - EVERGREEN_INTERLEAVE_EN); - else - WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset, 0); - if (!atomic && fb && fb != crtc->fb) { radeon_fb = to_radeon_framebuffer(fb); rbo = radeon_fb->obj->driver_private; @@ -1286,12 +1290,6 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc, WREG32(AVIVO_D1MODE_VIEWPORT_SIZE + radeon_crtc->crtc_offset, (crtc->mode.hdisplay << 16) | crtc->mode.vdisplay); - if (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE) - WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, - AVIVO_D1MODE_INTERLEAVE_EN); - else - WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, 0); - if (!atomic && fb && fb != crtc->fb) { radeon_fb = to_radeon_framebuffer(fb); rbo = radeon_fb->obj->driver_private; @@ -1315,7 +1313,7 @@ int atombios_crtc_set_base(struct drm_crtc *crtc, int x, int y, struct radeon_device *rdev = dev->dev_private; if (ASIC_IS_DCE4(rdev)) - return evergreen_crtc_do_set_base(crtc, old_fb, x, y, 0); + return dce4_crtc_do_set_base(crtc, old_fb, x, y, 0); else if (ASIC_IS_AVIVO(rdev)) return avivo_crtc_do_set_base(crtc, old_fb, x, y, 0); else @@ -1330,7 +1328,7 @@ int atombios_crtc_set_base_atomic(struct drm_crtc *crtc, struct radeon_device *rdev = dev->dev_private; if (ASIC_IS_DCE4(rdev)) - return evergreen_crtc_do_set_base(crtc, fb, x, y, 1); + return dce4_crtc_do_set_base(crtc, fb, x, y, 1); else if (ASIC_IS_AVIVO(rdev)) return avivo_crtc_do_set_base(crtc, fb, x, y, 1); else diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 677af91..6140ea1 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -97,26 +97,29 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base) } /* get temperature in millidegrees */ -u32 evergreen_get_temp(struct radeon_device *rdev) +int evergreen_get_temp(struct radeon_device *rdev) { u32 temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >> ASIC_T_SHIFT; u32 actual_temp = 0; - if ((temp >> 10) & 1) - actual_temp = 0; - else if ((temp >> 9) & 1) + if (temp & 0x400) + actual_temp = -256; + else if (temp & 0x200) actual_temp = 255; - else - actual_temp = (temp >> 1) & 0xff; + else if (temp & 0x100) { + actual_temp = temp & 0x1ff; + actual_temp |= ~0x1ff; + } else + actual_temp = temp & 0xff; - return actual_temp * 1000; + return (actual_temp * 1000) / 2; } -u32 sumo_get_temp(struct radeon_device *rdev) +int sumo_get_temp(struct radeon_device *rdev) { u32 temp = RREG32(CG_THERMAL_STATUS) & 0xff; - u32 actual_temp = (temp >> 1) & 0xff; + int actual_temp = temp - 49; return actual_temp * 1000; } @@ -1182,6 +1185,22 @@ static void evergreen_mc_program(struct radeon_device *rdev) /* * CP. */ +void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) +{ + /* set to DX10/11 mode */ + radeon_ring_write(rdev, PACKET3(PACKET3_MODE_CONTROL, 0)); + radeon_ring_write(rdev, 1); + /* FIXME: implement */ + radeon_ring_write(rdev, PACKET3(PACKET3_INDIRECT_BUFFER, 2)); + radeon_ring_write(rdev, +#ifdef __BIG_ENDIAN + (2 << 0) | +#endif + (ib->gpu_addr & 0xFFFFFFFC)); + radeon_ring_write(rdev, upper_32_bits(ib->gpu_addr) & 0xFF); + radeon_ring_write(rdev, ib->length_dw); +} + static int evergreen_cp_load_microcode(struct radeon_device *rdev) { @@ -1192,7 +1211,11 @@ static int evergreen_cp_load_microcode(struct radeon_device *rdev) return -EINVAL; r700_cp_stop(rdev); - WREG32(CP_RB_CNTL, RB_NO_UPDATE | (15 << 8) | (3 << 0)); + WREG32(CP_RB_CNTL, +#ifdef __BIG_ENDIAN + BUF_SWAP_32BIT | +#endif + RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3)); fw_data = (const __be32 *)rdev->pfp_fw->data; WREG32(CP_PFP_UCODE_ADDR, 0); @@ -1233,7 +1256,7 @@ static int evergreen_cp_start(struct radeon_device *rdev) cp_me = 0xff; WREG32(CP_ME_CNTL, cp_me); - r = radeon_ring_lock(rdev, evergreen_default_size + 15); + r = radeon_ring_lock(rdev, evergreen_default_size + 19); if (r) { DRM_ERROR("radeon: cp failed to lock ring (%d).\n", r); return r; @@ -1266,6 +1289,11 @@ static int evergreen_cp_start(struct radeon_device *rdev) radeon_ring_write(rdev, 0xffffffff); radeon_ring_write(rdev, 0xffffffff); + radeon_ring_write(rdev, 0xc0026900); + radeon_ring_write(rdev, 0x00000316); + radeon_ring_write(rdev, 0x0000000e); /* VGT_VERTEX_REUSE_BLOCK_CNTL */ + radeon_ring_write(rdev, 0x00000010); /* */ + radeon_ring_unlock_commit(rdev); return 0; @@ -1306,7 +1334,11 @@ int evergreen_cp_resume(struct radeon_device *rdev) WREG32(CP_RB_WPTR, 0); /* set the wb address wether it's enabled or not */ - WREG32(CP_RB_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC); + WREG32(CP_RB_RPTR_ADDR, +#ifdef __BIG_ENDIAN + RB_RPTR_SWAP(2) | +#endif + ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC)); WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF); WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF); @@ -2072,6 +2104,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev) WREG32(VGT_CACHE_INVALIDATION, vgt_cache_invalidation); WREG32(VGT_GS_VERTEX_REUSE, 16); + WREG32(PA_SU_LINE_STIPPLE_VALUE, 0); WREG32(PA_SC_LINE_STIPPLE_STATE, 0); WREG32(VGT_VERTEX_REUSE_BLOCK_CNTL, 14); @@ -2161,7 +2194,6 @@ int evergreen_mc_init(struct radeon_device *rdev) rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024; } rdev->mc.visible_vram_size = rdev->mc.aper_size; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; r700_vram_gtt_location(rdev, &rdev->mc); radeon_update_bandwidth_info(rdev); @@ -2606,8 +2638,8 @@ restart_ih: while (rptr != wptr) { /* wptr/rptr are in bytes! */ ring_index = rptr / 4; - src_id = rdev->ih.ring[ring_index] & 0xff; - src_data = rdev->ih.ring[ring_index + 1] & 0xfffffff; + src_id = le32_to_cpu(rdev->ih.ring[ring_index]) & 0xff; + src_data = le32_to_cpu(rdev->ih.ring[ring_index + 1]) & 0xfffffff; switch (src_id) { case 1: /* D1 vblank/vline */ @@ -2901,7 +2933,7 @@ static int evergreen_startup(struct radeon_device *rdev) /* XXX: ontario has problems blitting to gart at the moment */ if (rdev->family == CHIP_PALM) { rdev->asic->copy = NULL; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); } /* allocate wb buffer */ diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c index d4d4db4..2be698e 100644 --- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c +++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c @@ -55,7 +55,7 @@ set_render_target(struct radeon_device *rdev, int format, if (h < 8) h = 8; - cb_color_info = ((format << 2) | (1 << 24)); + cb_color_info = ((format << 2) | (1 << 24) | (1 << 8)); pitch = (w / 8) - 1; slice = ((w * h) / 64) - 1; @@ -133,6 +133,9 @@ set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr) /* high addr, stride */ sq_vtx_constant_word2 = ((upper_32_bits(gpu_addr) & 0xff) | (16 << 8)); +#ifdef __BIG_ENDIAN + sq_vtx_constant_word2 |= (2 << 30); +#endif /* xyzw swizzles */ sq_vtx_constant_word3 = (0 << 3) | (1 << 6) | (2 << 9) | (3 << 12); @@ -173,7 +176,7 @@ set_tex_resource(struct radeon_device *rdev, sq_tex_resource_word0 = (1 << 0); /* 2D */ sq_tex_resource_word0 |= ((((pitch >> 3) - 1) << 6) | ((w - 1) << 18)); - sq_tex_resource_word1 = ((h - 1) << 0); + sq_tex_resource_word1 = ((h - 1) << 0) | (1 << 28); /* xyzw swizzles */ sq_tex_resource_word4 = (0 << 16) | (1 << 19) | (2 << 22) | (3 << 25); @@ -221,7 +224,11 @@ draw_auto(struct radeon_device *rdev) radeon_ring_write(rdev, DI_PT_RECTLIST); radeon_ring_write(rdev, PACKET3(PACKET3_INDEX_TYPE, 0)); - radeon_ring_write(rdev, DI_INDEX_SIZE_16_BIT); + radeon_ring_write(rdev, +#ifdef __BIG_ENDIAN + (2 << 2) | +#endif + DI_INDEX_SIZE_16_BIT); radeon_ring_write(rdev, PACKET3(PACKET3_NUM_INSTANCES, 0)); radeon_ring_write(rdev, 1); @@ -232,7 +239,7 @@ draw_auto(struct radeon_device *rdev) } -/* emits 34 */ +/* emits 36 */ static void set_default_state(struct radeon_device *rdev) { @@ -499,6 +506,10 @@ set_default_state(struct radeon_device *rdev) radeon_ring_write(rdev, 0x00000000); radeon_ring_write(rdev, 0x00000000); + /* set to DX10/11 mode */ + radeon_ring_write(rdev, PACKET3(PACKET3_MODE_CONTROL, 0)); + radeon_ring_write(rdev, 1); + /* emit an IB pointing at default state */ dwords = ALIGN(rdev->r600_blit.state_len, 0x10); gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.state_offset; @@ -537,7 +548,7 @@ static inline uint32_t i2f(uint32_t input) int evergreen_blit_init(struct radeon_device *rdev) { u32 obj_size; - int r, dwords; + int i, r, dwords; void *ptr; u32 packet2s[16]; int num_packet2s = 0; @@ -553,7 +564,7 @@ int evergreen_blit_init(struct radeon_device *rdev) dwords = rdev->r600_blit.state_len; while (dwords & 0xf) { - packet2s[num_packet2s++] = PACKET2(0); + packet2s[num_packet2s++] = cpu_to_le32(PACKET2(0)); dwords++; } @@ -594,8 +605,10 @@ int evergreen_blit_init(struct radeon_device *rdev) if (num_packet2s) memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4), packet2s, num_packet2s * 4); - memcpy(ptr + rdev->r600_blit.vs_offset, evergreen_vs, evergreen_vs_size * 4); - memcpy(ptr + rdev->r600_blit.ps_offset, evergreen_ps, evergreen_ps_size * 4); + for (i = 0; i < evergreen_vs_size; i++) + *(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]); + for (i = 0; i < evergreen_ps_size; i++) + *(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]); radeon_bo_kunmap(rdev->r600_blit.shader_obj); radeon_bo_unreserve(rdev->r600_blit.shader_obj); @@ -610,7 +623,7 @@ done: dev_err(rdev->dev, "(%d) pin blit object failed\n", r); return r; } - rdev->mc.active_vram_size = rdev->mc.real_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size); return 0; } @@ -618,7 +631,7 @@ void evergreen_blit_fini(struct radeon_device *rdev) { int r; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); if (rdev->r600_blit.shader_obj == NULL) return; /* If we can't reserve the bo, unref should be enough to destroy @@ -679,7 +692,7 @@ int evergreen_blit_prepare_copy(struct radeon_device *rdev, int size_bytes) /* calculate number of loops correctly */ ring_size = num_loops * dwords_per_loop; /* set default + shaders */ - ring_size += 50; /* shaders + def state */ + ring_size += 52; /* shaders + def state */ ring_size += 10; /* fence emit for VB IB */ ring_size += 5; /* done copy */ ring_size += 10; /* fence emit for done copy */ @@ -687,7 +700,7 @@ int evergreen_blit_prepare_copy(struct radeon_device *rdev, int size_bytes) if (r) return r; - set_default_state(rdev); /* 34 */ + set_default_state(rdev); /* 36 */ set_shaders(rdev); /* 16 */ return 0; } diff --git a/drivers/gpu/drm/radeon/evergreen_blit_shaders.c b/drivers/gpu/drm/radeon/evergreen_blit_shaders.c index ef1d28c..3a10399 100644 --- a/drivers/gpu/drm/radeon/evergreen_blit_shaders.c +++ b/drivers/gpu/drm/radeon/evergreen_blit_shaders.c @@ -311,11 +311,19 @@ const u32 evergreen_vs[] = 0x00000000, 0x3c000000, 0x67961001, +#ifdef __BIG_ENDIAN + 0x000a0000, +#else 0x00080000, +#endif 0x00000000, 0x1c000000, 0x67961000, +#ifdef __BIG_ENDIAN + 0x00020008, +#else 0x00000008, +#endif 0x00000000, }; diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 36d32d8..eb4acf4 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -98,6 +98,7 @@ #define BUF_SWAP_32BIT (2 << 16) #define CP_RB_RPTR 0x8700 #define CP_RB_RPTR_ADDR 0xC10C +#define RB_RPTR_SWAP(x) ((x) << 0) #define CP_RB_RPTR_ADDR_HI 0xC110 #define CP_RB_RPTR_WR 0xC108 #define CP_RB_WPTR 0xC114 @@ -240,6 +241,7 @@ #define FORCE_EOV_MAX_CLK_CNT(x) ((x) << 0) #define FORCE_EOV_MAX_REZ_CNT(x) ((x) << 16) #define PA_SC_LINE_STIPPLE 0x28A0C +#define PA_SU_LINE_STIPPLE_VALUE 0x8A60 #define PA_SC_LINE_STIPPLE_STATE 0x8B10 #define SCRATCH_REG0 0x8500 @@ -652,6 +654,7 @@ #define PACKET3_DISPATCH_DIRECT 0x15 #define PACKET3_DISPATCH_INDIRECT 0x16 #define PACKET3_INDIRECT_BUFFER_END 0x17 +#define PACKET3_MODE_CONTROL 0x18 #define PACKET3_SET_PREDICATION 0x20 #define PACKET3_REG_RMW 0x21 #define PACKET3_COND_EXEC 0x22 diff --git a/drivers/gpu/drm/radeon/mkregtable.c b/drivers/gpu/drm/radeon/mkregtable.c index 607241c..5a82b6b 100644 --- a/drivers/gpu/drm/radeon/mkregtable.c +++ b/drivers/gpu/drm/radeon/mkregtable.c @@ -673,8 +673,10 @@ static int parser_auth(struct table *t, const char *filename) last_reg = strtol(last_reg_s, NULL, 16); do { - if (fgets(buf, 1024, file) == NULL) + if (fgets(buf, 1024, file) == NULL) { + fclose(file); return -1; + } len = strlen(buf); if (ftell(file) == end) done = 1; @@ -685,6 +687,7 @@ static int parser_auth(struct table *t, const char *filename) fprintf(stderr, "Error matching regular expression %d in %s\n", r, filename); + fclose(file); return -1; } else { buf[match[0].rm_eo] = 0; diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 5f15820..e372f9e 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -70,23 +70,6 @@ MODULE_FIRMWARE(FIRMWARE_R520); void r100_pre_page_flip(struct radeon_device *rdev, int crtc) { - struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc]; - u32 tmp; - - /* make sure flip is at vb rather than hb */ - tmp = RREG32(RADEON_CRTC_OFFSET_CNTL + radeon_crtc->crtc_offset); - tmp &= ~RADEON_CRTC_OFFSET_FLIP_CNTL; - /* make sure pending bit is asserted */ - tmp |= RADEON_CRTC_GUI_TRIG_OFFSET_LEFT_EN; - WREG32(RADEON_CRTC_OFFSET_CNTL + radeon_crtc->crtc_offset, tmp); - - /* set pageflip to happen as late as possible in the vblank interval. - * same field for crtc1/2 - */ - tmp = RREG32(RADEON_CRTC_GEN_CNTL); - tmp &= ~RADEON_CRTC_VSTAT_MODE_MASK; - WREG32(RADEON_CRTC_GEN_CNTL, tmp); - /* enable the pflip int */ radeon_irq_kms_pflip_irq_get(rdev, crtc); } @@ -1041,7 +1024,7 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size) return r; } rdev->cp.ready = true; - rdev->mc.active_vram_size = rdev->mc.real_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size); return 0; } @@ -1059,7 +1042,7 @@ void r100_cp_fini(struct radeon_device *rdev) void r100_cp_disable(struct radeon_device *rdev) { /* Disable ring */ - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); rdev->cp.ready = false; WREG32(RADEON_CP_CSQ_MODE, 0); WREG32(RADEON_CP_CSQ_CNTL, 0); @@ -1427,6 +1410,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, } track->zb.robj = reloc->robj; track->zb.offset = idx_value; + track->zb_dirty = true; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); break; case RADEON_RB3D_COLOROFFSET: @@ -1439,6 +1423,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, } track->cb[0].robj = reloc->robj; track->cb[0].offset = idx_value; + track->cb_dirty = true; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); break; case RADEON_PP_TXOFFSET_0: @@ -1454,6 +1439,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, } ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); track->textures[i].robj = reloc->robj; + track->tex_dirty = true; break; case RADEON_PP_CUBIC_OFFSET_T0_0: case RADEON_PP_CUBIC_OFFSET_T0_1: @@ -1471,6 +1457,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, track->textures[0].cube_info[i].offset = idx_value; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); track->textures[0].cube_info[i].robj = reloc->robj; + track->tex_dirty = true; break; case RADEON_PP_CUBIC_OFFSET_T1_0: case RADEON_PP_CUBIC_OFFSET_T1_1: @@ -1488,6 +1475,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, track->textures[1].cube_info[i].offset = idx_value; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); track->textures[1].cube_info[i].robj = reloc->robj; + track->tex_dirty = true; break; case RADEON_PP_CUBIC_OFFSET_T2_0: case RADEON_PP_CUBIC_OFFSET_T2_1: @@ -1505,9 +1493,12 @@ static int r100_packet0_check(struct radeon_cs_parser *p, track->textures[2].cube_info[i].offset = idx_value; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); track->textures[2].cube_info[i].robj = reloc->robj; + track->tex_dirty = true; break; case RADEON_RE_WIDTH_HEIGHT: track->maxy = ((idx_value >> 16) & 0x7FF); + track->cb_dirty = true; + track->zb_dirty = true; break; case RADEON_RB3D_COLORPITCH: r = r100_cs_packet_next_reloc(p, &reloc); @@ -1528,9 +1519,11 @@ static int r100_packet0_check(struct radeon_cs_parser *p, ib[idx] = tmp; track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK; + track->cb_dirty = true; break; case RADEON_RB3D_DEPTHPITCH: track->zb.pitch = idx_value & RADEON_DEPTHPITCH_MASK; + track->zb_dirty = true; break; case RADEON_RB3D_CNTL: switch ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f) { @@ -1555,6 +1548,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p, return -EINVAL; } track->z_enabled = !!(idx_value & RADEON_Z_ENABLE); + track->cb_dirty = true; + track->zb_dirty = true; break; case RADEON_RB3D_ZSTENCILCNTL: switch (idx_value & 0xf) { @@ -1572,6 +1567,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, default: break; } + track->zb_dirty = true; break; case RADEON_RB3D_ZPASS_ADDR: r = r100_cs_packet_next_reloc(p, &reloc); @@ -1588,6 +1584,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, uint32_t temp = idx_value >> 4; for (i = 0; i < track->num_texture; i++) track->textures[i].enabled = !!(temp & (1 << i)); + track->tex_dirty = true; } break; case RADEON_SE_VF_CNTL: @@ -1602,12 +1599,14 @@ static int r100_packet0_check(struct radeon_cs_parser *p, i = (reg - RADEON_PP_TEX_SIZE_0) / 8; track->textures[i].width = (idx_value & RADEON_TEX_USIZE_MASK) + 1; track->textures[i].height = ((idx_value & RADEON_TEX_VSIZE_MASK) >> RADEON_TEX_VSIZE_SHIFT) + 1; + track->tex_dirty = true; break; case RADEON_PP_TEX_PITCH_0: case RADEON_PP_TEX_PITCH_1: case RADEON_PP_TEX_PITCH_2: i = (reg - RADEON_PP_TEX_PITCH_0) / 8; track->textures[i].pitch = idx_value + 32; + track->tex_dirty = true; break; case RADEON_PP_TXFILTER_0: case RADEON_PP_TXFILTER_1: @@ -1621,6 +1620,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, tmp = (idx_value >> 27) & 0x7; if (tmp == 2 || tmp == 6) track->textures[i].roundup_h = false; + track->tex_dirty = true; break; case RADEON_PP_TXFORMAT_0: case RADEON_PP_TXFORMAT_1: @@ -1673,6 +1673,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, } track->textures[i].cube_info[4].width = 1 << ((idx_value >> 16) & 0xf); track->textures[i].cube_info[4].height = 1 << ((idx_value >> 20) & 0xf); + track->tex_dirty = true; break; case RADEON_PP_CUBIC_FACES_0: case RADEON_PP_CUBIC_FACES_1: @@ -1683,6 +1684,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, track->textures[i].cube_info[face].width = 1 << ((tmp >> (face * 8)) & 0xf); track->textures[i].cube_info[face].height = 1 << ((tmp >> ((face * 8) + 4)) & 0xf); } + track->tex_dirty = true; break; default: printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n", @@ -2310,7 +2312,6 @@ void r100_vram_init_sizes(struct radeon_device *rdev) /* FIXME we don't use the second aperture yet when we could use it */ if (rdev->mc.visible_vram_size > rdev->mc.aper_size) rdev->mc.visible_vram_size = rdev->mc.aper_size; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; config_aper_size = RREG32(RADEON_CONFIG_APER_SIZE); if (rdev->flags & RADEON_IS_IGP) { uint32_t tom; @@ -3318,9 +3319,9 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) unsigned long size; unsigned prim_walk; unsigned nverts; - unsigned num_cb = track->num_cb; + unsigned num_cb = track->cb_dirty ? track->num_cb : 0; - if (!track->zb_cb_clear && !track->color_channel_mask && + if (num_cb && !track->zb_cb_clear && !track->color_channel_mask && !track->blend_read_enable) num_cb = 0; @@ -3341,7 +3342,9 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) return -EINVAL; } } - if (track->z_enabled) { + track->cb_dirty = false; + + if (track->zb_dirty && track->z_enabled) { if (track->zb.robj == NULL) { DRM_ERROR("[drm] No buffer for z buffer !\n"); return -EINVAL; @@ -3358,6 +3361,28 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) return -EINVAL; } } + track->zb_dirty = false; + + if (track->aa_dirty && track->aaresolve) { + if (track->aa.robj == NULL) { + DRM_ERROR("[drm] No buffer for AA resolve buffer %d !\n", i); + return -EINVAL; + } + /* I believe the format comes from colorbuffer0. */ + size = track->aa.pitch * track->cb[0].cpp * track->maxy; + size += track->aa.offset; + if (size > radeon_bo_size(track->aa.robj)) { + DRM_ERROR("[drm] Buffer too small for AA resolve buffer %d " + "(need %lu have %lu) !\n", i, size, + radeon_bo_size(track->aa.robj)); + DRM_ERROR("[drm] AA resolve buffer %d (%u %u %u %u)\n", + i, track->aa.pitch, track->cb[0].cpp, + track->aa.offset, track->maxy); + return -EINVAL; + } + } + track->aa_dirty = false; + prim_walk = (track->vap_vf_cntl >> 4) & 0x3; if (track->vap_vf_cntl & (1 << 14)) { nverts = track->vap_alt_nverts; @@ -3417,13 +3442,23 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track) prim_walk); return -EINVAL; } - return r100_cs_track_texture_check(rdev, track); + + if (track->tex_dirty) { + track->tex_dirty = false; + return r100_cs_track_texture_check(rdev, track); + } + return 0; } void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track) { unsigned i, face; + track->cb_dirty = true; + track->zb_dirty = true; + track->tex_dirty = true; + track->aa_dirty = true; + if (rdev->family < CHIP_R300) { track->num_cb = 1; if (rdev->family <= CHIP_RS200) @@ -3437,6 +3472,8 @@ void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track track->num_texture = 16; track->maxy = 4096; track->separate_cube = 0; + track->aaresolve = false; + track->aa.robj = NULL; } for (i = 0; i < track->num_cb; i++) { @@ -3746,8 +3783,6 @@ static int r100_startup(struct radeon_device *rdev) r100_mc_program(rdev); /* Resume clock */ r100_clock_startup(rdev); - /* Initialize GPU configuration (# pipes, ...) */ -// r100_gpu_init(rdev); /* Initialize GART (initialize after TTM so we can allocate * memory through TTM but finalize after TTM) */ r100_enable_bm(rdev); diff --git a/drivers/gpu/drm/radeon/r100_track.h b/drivers/gpu/drm/radeon/r100_track.h index af65600..2fef9de 100644 --- a/drivers/gpu/drm/radeon/r100_track.h +++ b/drivers/gpu/drm/radeon/r100_track.h @@ -52,14 +52,7 @@ struct r100_cs_track_texture { unsigned compress_format; }; -struct r100_cs_track_limits { - unsigned num_cb; - unsigned num_texture; - unsigned max_levels; -}; - struct r100_cs_track { - struct radeon_device *rdev; unsigned num_cb; unsigned num_texture; unsigned maxy; @@ -73,11 +66,17 @@ struct r100_cs_track { struct r100_cs_track_array arrays[11]; struct r100_cs_track_cb cb[R300_MAX_CB]; struct r100_cs_track_cb zb; + struct r100_cs_track_cb aa; struct r100_cs_track_texture textures[R300_TRACK_MAX_TEXTURE]; bool z_enabled; bool separate_cube; bool zb_cb_clear; bool blend_read_enable; + bool cb_dirty; + bool zb_dirty; + bool tex_dirty; + bool aa_dirty; + bool aaresolve; }; int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track); diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c index d2408c3..f240583 100644 --- a/drivers/gpu/drm/radeon/r200.c +++ b/drivers/gpu/drm/radeon/r200.c @@ -184,6 +184,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, } track->zb.robj = reloc->robj; track->zb.offset = idx_value; + track->zb_dirty = true; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); break; case RADEON_RB3D_COLOROFFSET: @@ -196,6 +197,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, } track->cb[0].robj = reloc->robj; track->cb[0].offset = idx_value; + track->cb_dirty = true; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); break; case R200_PP_TXOFFSET_0: @@ -214,6 +216,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, } ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); track->textures[i].robj = reloc->robj; + track->tex_dirty = true; break; case R200_PP_CUBIC_OFFSET_F1_0: case R200_PP_CUBIC_OFFSET_F2_0: @@ -257,9 +260,12 @@ int r200_packet0_check(struct radeon_cs_parser *p, track->textures[i].cube_info[face - 1].offset = idx_value; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); track->textures[i].cube_info[face - 1].robj = reloc->robj; + track->tex_dirty = true; break; case RADEON_RE_WIDTH_HEIGHT: track->maxy = ((idx_value >> 16) & 0x7FF); + track->cb_dirty = true; + track->zb_dirty = true; break; case RADEON_RB3D_COLORPITCH: r = r100_cs_packet_next_reloc(p, &reloc); @@ -280,9 +286,11 @@ int r200_packet0_check(struct radeon_cs_parser *p, ib[idx] = tmp; track->cb[0].pitch = idx_value & RADEON_COLORPITCH_MASK; + track->cb_dirty = true; break; case RADEON_RB3D_DEPTHPITCH: track->zb.pitch = idx_value & RADEON_DEPTHPITCH_MASK; + track->zb_dirty = true; break; case RADEON_RB3D_CNTL: switch ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f) { @@ -312,6 +320,8 @@ int r200_packet0_check(struct radeon_cs_parser *p, } track->z_enabled = !!(idx_value & RADEON_Z_ENABLE); + track->cb_dirty = true; + track->zb_dirty = true; break; case RADEON_RB3D_ZSTENCILCNTL: switch (idx_value & 0xf) { @@ -329,6 +339,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, default: break; } + track->zb_dirty = true; break; case RADEON_RB3D_ZPASS_ADDR: r = r100_cs_packet_next_reloc(p, &reloc); @@ -345,6 +356,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, uint32_t temp = idx_value >> 4; for (i = 0; i < track->num_texture; i++) track->textures[i].enabled = !!(temp & (1 << i)); + track->tex_dirty = true; } break; case RADEON_SE_VF_CNTL: @@ -369,6 +381,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, i = (reg - R200_PP_TXSIZE_0) / 32; track->textures[i].width = (idx_value & RADEON_TEX_USIZE_MASK) + 1; track->textures[i].height = ((idx_value & RADEON_TEX_VSIZE_MASK) >> RADEON_TEX_VSIZE_SHIFT) + 1; + track->tex_dirty = true; break; case R200_PP_TXPITCH_0: case R200_PP_TXPITCH_1: @@ -378,6 +391,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, case R200_PP_TXPITCH_5: i = (reg - R200_PP_TXPITCH_0) / 32; track->textures[i].pitch = idx_value + 32; + track->tex_dirty = true; break; case R200_PP_TXFILTER_0: case R200_PP_TXFILTER_1: @@ -394,6 +408,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, tmp = (idx_value >> 27) & 0x7; if (tmp == 2 || tmp == 6) track->textures[i].roundup_h = false; + track->tex_dirty = true; break; case R200_PP_TXMULTI_CTL_0: case R200_PP_TXMULTI_CTL_1: @@ -432,6 +447,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, track->textures[i].tex_coord_type = 1; break; } + track->tex_dirty = true; break; case R200_PP_TXFORMAT_0: case R200_PP_TXFORMAT_1: @@ -488,6 +504,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, } track->textures[i].cube_info[4].width = 1 << ((idx_value >> 16) & 0xf); track->textures[i].cube_info[4].height = 1 << ((idx_value >> 20) & 0xf); + track->tex_dirty = true; break; case R200_PP_CUBIC_FACES_0: case R200_PP_CUBIC_FACES_1: @@ -501,6 +518,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, track->textures[i].cube_info[face].width = 1 << ((tmp >> (face * 8)) & 0xf); track->textures[i].cube_info[face].height = 1 << ((tmp >> ((face * 8) + 4)) & 0xf); } + track->tex_dirty = true; break; default: printk(KERN_ERR "Forbidden register 0x%04X in cs at %d\n", diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 55fe5ba..069efa8 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -667,6 +667,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, } track->cb[i].robj = reloc->robj; track->cb[i].offset = idx_value; + track->cb_dirty = true; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); break; case R300_ZB_DEPTHOFFSET: @@ -679,6 +680,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, } track->zb.robj = reloc->robj; track->zb.offset = idx_value; + track->zb_dirty = true; ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); break; case R300_TX_OFFSET_0: @@ -717,6 +719,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, tmp |= tile_flags; ib[idx] = tmp; track->textures[i].robj = reloc->robj; + track->tex_dirty = true; break; /* Tracked registers */ case 0x2084: @@ -743,6 +746,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, if (p->rdev->family < CHIP_RV515) { track->maxy -= 1440; } + track->cb_dirty = true; + track->zb_dirty = true; break; case 0x4E00: /* RB3D_CCTL */ @@ -752,6 +757,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, return -EINVAL; } track->num_cb = ((idx_value >> 5) & 0x3) + 1; + track->cb_dirty = true; break; case 0x4E38: case 0x4E3C: @@ -814,6 +820,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, ((idx_value >> 21) & 0xF)); return -EINVAL; } + track->cb_dirty = true; break; case 0x4F00: /* ZB_CNTL */ @@ -822,6 +829,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, } else { track->z_enabled = false; } + track->zb_dirty = true; break; case 0x4F10: /* ZB_FORMAT */ @@ -838,6 +846,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, (idx_value & 0xF)); return -EINVAL; } + track->zb_dirty = true; break; case 0x4F24: /* ZB_DEPTHPITCH */ @@ -861,14 +870,17 @@ static int r300_packet0_check(struct radeon_cs_parser *p, ib[idx] = tmp; track->zb.pitch = idx_value & 0x3FFC; + track->zb_dirty = true; break; case 0x4104: + /* TX_ENABLE */ for (i = 0; i < 16; i++) { bool enabled; enabled = !!(idx_value & (1 << i)); track->textures[i].enabled = enabled; } + track->tex_dirty = true; break; case 0x44C0: case 0x44C4: @@ -898,6 +910,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, track->textures[i].compress_format = R100_TRACK_COMP_NONE; break; case R300_TX_FORMAT_X16: + case R300_TX_FORMAT_FL_I16: case R300_TX_FORMAT_Y8X8: case R300_TX_FORMAT_Z5Y6X5: case R300_TX_FORMAT_Z6Y5X5: @@ -910,6 +923,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, track->textures[i].compress_format = R100_TRACK_COMP_NONE; break; case R300_TX_FORMAT_Y16X16: + case R300_TX_FORMAT_FL_I16A16: case R300_TX_FORMAT_Z11Y11X10: case R300_TX_FORMAT_Z10Y11X11: case R300_TX_FORMAT_W8Z8Y8X8: @@ -951,8 +965,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, DRM_ERROR("Invalid texture format %u\n", (idx_value & 0x1F)); return -EINVAL; - break; } + track->tex_dirty = true; break; case 0x4400: case 0x4404: @@ -980,6 +994,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, if (tmp == 2 || tmp == 4 || tmp == 6) { track->textures[i].roundup_h = false; } + track->tex_dirty = true; break; case 0x4500: case 0x4504: @@ -1017,6 +1032,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, DRM_ERROR("Forbidden bit TXFORMAT_MSB\n"); return -EINVAL; } + track->tex_dirty = true; break; case 0x4480: case 0x4484: @@ -1046,6 +1062,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, track->textures[i].use_pitch = !!tmp; tmp = (idx_value >> 22) & 0xF; track->textures[i].txdepth = tmp; + track->tex_dirty = true; break; case R300_ZB_ZPASS_ADDR: r = r100_cs_packet_next_reloc(p, &reloc); @@ -1060,6 +1077,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case 0x4e0c: /* RB3D_COLOR_CHANNEL_MASK */ track->color_channel_mask = idx_value; + track->cb_dirty = true; break; case 0x43a4: /* SC_HYPERZ_EN */ @@ -1073,6 +1091,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case 0x4f1c: /* ZB_BW_CNTL */ track->zb_cb_clear = !!(idx_value & (1 << 5)); + track->cb_dirty = true; + track->zb_dirty = true; if (p->rdev->hyperz_filp != p->filp) { if (idx_value & (R300_HIZ_ENABLE | R300_RD_COMP_ENABLE | @@ -1084,8 +1104,28 @@ static int r300_packet0_check(struct radeon_cs_parser *p, case 0x4e04: /* RB3D_BLENDCNTL */ track->blend_read_enable = !!(idx_value & (1 << 2)); + track->cb_dirty = true; + break; + case R300_RB3D_AARESOLVE_OFFSET: + r = r100_cs_packet_next_reloc(p, &reloc); + if (r) { + DRM_ERROR("No reloc for ib[%d]=0x%04X\n", + idx, reg); + r100_cs_dump_packet(p, pkt); + return r; + } + track->aa.robj = reloc->robj; + track->aa.offset = idx_value; + track->aa_dirty = true; + ib[idx] = idx_value + ((u32)reloc->lobj.gpu_offset); + break; + case R300_RB3D_AARESOLVE_PITCH: + track->aa.pitch = idx_value & 0x3FFE; + track->aa_dirty = true; break; - case 0x4f28: /* ZB_DEPTHCLEARVALUE */ + case R300_RB3D_AARESOLVE_CTL: + track->aaresolve = idx_value & 0x1; + track->aa_dirty = true; break; case 0x4f30: /* ZB_MASK_OFFSET */ case 0x4f34: /* ZB_ZMASK_PITCH */ diff --git a/drivers/gpu/drm/radeon/r300_reg.h b/drivers/gpu/drm/radeon/r300_reg.h index 1a0d536..f0bce39 100644 --- a/drivers/gpu/drm/radeon/r300_reg.h +++ b/drivers/gpu/drm/radeon/r300_reg.h @@ -1371,6 +1371,8 @@ #define R300_RB3D_COLORPITCH2 0x4E40 /* GUESS */ #define R300_RB3D_COLORPITCH3 0x4E44 /* GUESS */ +#define R300_RB3D_AARESOLVE_OFFSET 0x4E80 +#define R300_RB3D_AARESOLVE_PITCH 0x4E84 #define R300_RB3D_AARESOLVE_CTL 0x4E88 /* gap */ diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 1e10e3e..9b3fad2 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -97,12 +97,16 @@ void r600_irq_disable(struct radeon_device *rdev); static void r600_pcie_gen2_enable(struct radeon_device *rdev); /* get temperature in millidegrees */ -u32 rv6xx_get_temp(struct radeon_device *rdev) +int rv6xx_get_temp(struct radeon_device *rdev) { u32 temp = (RREG32(CG_THERMAL_STATUS) & ASIC_T_MASK) >> ASIC_T_SHIFT; + int actual_temp = temp & 0xff; - return temp * 1000; + if (temp & 0x100) + actual_temp -= 256; + + return actual_temp * 1000; } void r600_pm_get_dynpm_state(struct radeon_device *rdev) @@ -1251,7 +1255,6 @@ int r600_mc_init(struct radeon_device *rdev) rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE); rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE); rdev->mc.visible_vram_size = rdev->mc.aper_size; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; r600_vram_gtt_location(rdev, &rdev->mc); if (rdev->flags & RADEON_IS_IGP) { @@ -1933,7 +1936,7 @@ void r600_pciep_wreg(struct radeon_device *rdev, u32 reg, u32 v) */ void r600_cp_stop(struct radeon_device *rdev) { - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); WREG32(R_0086D8_CP_ME_CNTL, S_0086D8_CP_ME_HALT(1)); WREG32(SCRATCH_UMSK, 0); } @@ -2101,7 +2104,11 @@ static int r600_cp_load_microcode(struct radeon_device *rdev) r600_cp_stop(rdev); - WREG32(CP_RB_CNTL, RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3)); + WREG32(CP_RB_CNTL, +#ifdef __BIG_ENDIAN + BUF_SWAP_32BIT | +#endif + RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3)); /* Reset cp */ WREG32(GRBM_SOFT_RESET, SOFT_RESET_CP); @@ -2188,7 +2195,11 @@ int r600_cp_resume(struct radeon_device *rdev) WREG32(CP_RB_WPTR, 0); /* set the wb address whether it's enabled or not */ - WREG32(CP_RB_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC); + WREG32(CP_RB_RPTR_ADDR, +#ifdef __BIG_ENDIAN + RB_RPTR_SWAP(2) | +#endif + ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC)); WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF); WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF); @@ -2624,7 +2635,11 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) { /* FIXME: implement */ radeon_ring_write(rdev, PACKET3(PACKET3_INDIRECT_BUFFER, 2)); - radeon_ring_write(rdev, ib->gpu_addr & 0xFFFFFFFC); + radeon_ring_write(rdev, +#ifdef __BIG_ENDIAN + (2 << 0) | +#endif + (ib->gpu_addr & 0xFFFFFFFC)); radeon_ring_write(rdev, upper_32_bits(ib->gpu_addr) & 0xFF); radeon_ring_write(rdev, ib->length_dw); } @@ -3293,8 +3308,8 @@ restart_ih: while (rptr != wptr) { /* wptr/rptr are in bytes! */ ring_index = rptr / 4; - src_id = rdev->ih.ring[ring_index] & 0xff; - src_data = rdev->ih.ring[ring_index + 1] & 0xfffffff; + src_id = le32_to_cpu(rdev->ih.ring[ring_index]) & 0xff; + src_data = le32_to_cpu(rdev->ih.ring[ring_index + 1]) & 0xfffffff; switch (src_id) { case 1: /* D1 vblank/vline */ diff --git a/drivers/gpu/drm/radeon/r600_blit.c b/drivers/gpu/drm/radeon/r600_blit.c index ca5c29f..7f10434 100644 --- a/drivers/gpu/drm/radeon/r600_blit.c +++ b/drivers/gpu/drm/radeon/r600_blit.c @@ -137,9 +137,9 @@ set_shaders(struct drm_device *dev) ps = (u32 *) ((char *)dev->agp_buffer_map->handle + dev_priv->blit_vb->offset + 256); for (i = 0; i < r6xx_vs_size; i++) - vs[i] = r6xx_vs[i]; + vs[i] = cpu_to_le32(r6xx_vs[i]); for (i = 0; i < r6xx_ps_size; i++) - ps[i] = r6xx_ps[i]; + ps[i] = cpu_to_le32(r6xx_ps[i]); dev_priv->blit_vb->used = 512; @@ -192,6 +192,9 @@ set_vtx_resource(drm_radeon_private_t *dev_priv, u64 gpu_addr) DRM_DEBUG("\n"); sq_vtx_constant_word2 = (((gpu_addr >> 32) & 0xff) | (16 << 8)); +#ifdef __BIG_ENDIAN + sq_vtx_constant_word2 |= (2 << 30); +#endif BEGIN_RING(9); OUT_RING(CP_PACKET3(R600_IT_SET_RESOURCE, 7)); @@ -291,7 +294,11 @@ draw_auto(drm_radeon_private_t *dev_priv) OUT_RING(DI_PT_RECTLIST); OUT_RING(CP_PACKET3(R600_IT_INDEX_TYPE, 0)); +#ifdef __BIG_ENDIAN + OUT_RING((2 << 2) | DI_INDEX_SIZE_16_BIT); +#else OUT_RING(DI_INDEX_SIZE_16_BIT); +#endif OUT_RING(CP_PACKET3(R600_IT_NUM_INSTANCES, 0)); OUT_RING(1); diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c index 86e5aa0..df68d91 100644 --- a/drivers/gpu/drm/radeon/r600_blit_kms.c +++ b/drivers/gpu/drm/radeon/r600_blit_kms.c @@ -54,7 +54,7 @@ set_render_target(struct radeon_device *rdev, int format, if (h < 8) h = 8; - cb_color_info = ((format << 2) | (1 << 27)); + cb_color_info = ((format << 2) | (1 << 27) | (1 << 8)); pitch = (w / 8) - 1; slice = ((w * h) / 64) - 1; @@ -165,6 +165,9 @@ set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr) u32 sq_vtx_constant_word2; sq_vtx_constant_word2 = ((upper_32_bits(gpu_addr) & 0xff) | (16 << 8)); +#ifdef __BIG_ENDIAN + sq_vtx_constant_word2 |= (2 << 30); +#endif radeon_ring_write(rdev, PACKET3(PACKET3_SET_RESOURCE, 7)); radeon_ring_write(rdev, 0x460); @@ -199,7 +202,7 @@ set_tex_resource(struct radeon_device *rdev, if (h < 1) h = 1; - sq_tex_resource_word0 = (1 << 0); + sq_tex_resource_word0 = (1 << 0) | (1 << 3); sq_tex_resource_word0 |= ((((pitch >> 3) - 1) << 8) | ((w - 1) << 19)); @@ -253,7 +256,11 @@ draw_auto(struct radeon_device *rdev) radeon_ring_write(rdev, DI_PT_RECTLIST); radeon_ring_write(rdev, PACKET3(PACKET3_INDEX_TYPE, 0)); - radeon_ring_write(rdev, DI_INDEX_SIZE_16_BIT); + radeon_ring_write(rdev, +#ifdef __BIG_ENDIAN + (2 << 2) | +#endif + DI_INDEX_SIZE_16_BIT); radeon_ring_write(rdev, PACKET3(PACKET3_NUM_INSTANCES, 0)); radeon_ring_write(rdev, 1); @@ -424,7 +431,11 @@ set_default_state(struct radeon_device *rdev) dwords = ALIGN(rdev->r600_blit.state_len, 0x10); gpu_addr = rdev->r600_blit.shader_gpu_addr + rdev->r600_blit.state_offset; radeon_ring_write(rdev, PACKET3(PACKET3_INDIRECT_BUFFER, 2)); - radeon_ring_write(rdev, gpu_addr & 0xFFFFFFFC); + radeon_ring_write(rdev, +#ifdef __BIG_ENDIAN + (2 << 0) | +#endif + (gpu_addr & 0xFFFFFFFC)); radeon_ring_write(rdev, upper_32_bits(gpu_addr) & 0xFF); radeon_ring_write(rdev, dwords); @@ -467,7 +478,7 @@ static inline uint32_t i2f(uint32_t input) int r600_blit_init(struct radeon_device *rdev) { u32 obj_size; - int r, dwords; + int i, r, dwords; void *ptr; u32 packet2s[16]; int num_packet2s = 0; @@ -486,7 +497,7 @@ int r600_blit_init(struct radeon_device *rdev) dwords = rdev->r600_blit.state_len; while (dwords & 0xf) { - packet2s[num_packet2s++] = PACKET2(0); + packet2s[num_packet2s++] = cpu_to_le32(PACKET2(0)); dwords++; } @@ -529,8 +540,10 @@ int r600_blit_init(struct radeon_device *rdev) if (num_packet2s) memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4), packet2s, num_packet2s * 4); - memcpy(ptr + rdev->r600_blit.vs_offset, r6xx_vs, r6xx_vs_size * 4); - memcpy(ptr + rdev->r600_blit.ps_offset, r6xx_ps, r6xx_ps_size * 4); + for (i = 0; i < r6xx_vs_size; i++) + *(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(r6xx_vs[i]); + for (i = 0; i < r6xx_ps_size; i++) + *(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(r6xx_ps[i]); radeon_bo_kunmap(rdev->r600_blit.shader_obj); radeon_bo_unreserve(rdev->r600_blit.shader_obj); @@ -545,7 +558,7 @@ done: dev_err(rdev->dev, "(%d) pin blit object failed\n", r); return r; } - rdev->mc.active_vram_size = rdev->mc.real_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size); return 0; } @@ -553,7 +566,7 @@ void r600_blit_fini(struct radeon_device *rdev) { int r; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); if (rdev->r600_blit.shader_obj == NULL) return; /* If we can't reserve the bo, unref should be enough to destroy diff --git a/drivers/gpu/drm/radeon/r600_blit_shaders.c b/drivers/gpu/drm/radeon/r600_blit_shaders.c index e8151c1..2d1f6c5 100644 --- a/drivers/gpu/drm/radeon/r600_blit_shaders.c +++ b/drivers/gpu/drm/radeon/r600_blit_shaders.c @@ -684,7 +684,11 @@ const u32 r6xx_vs[] = 0x00000000, 0x3c000000, 0x68cd1000, +#ifdef __BIG_ENDIAN + 0x000a0000, +#else 0x00080000, +#endif 0x00000000, }; diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c index 4f4cd8b..c3ab959 100644 --- a/drivers/gpu/drm/radeon/r600_cp.c +++ b/drivers/gpu/drm/radeon/r600_cp.c @@ -396,6 +396,9 @@ static void r600_cp_load_microcode(drm_radeon_private_t *dev_priv) r600_do_cp_stop(dev_priv); RADEON_WRITE(R600_CP_RB_CNTL, +#ifdef __BIG_ENDIAN + R600_BUF_SWAP_32BIT | +#endif R600_RB_NO_UPDATE | R600_RB_BLKSZ(15) | R600_RB_BUFSZ(3)); @@ -486,9 +489,12 @@ static void r700_cp_load_microcode(drm_radeon_private_t *dev_priv) r600_do_cp_stop(dev_priv); RADEON_WRITE(R600_CP_RB_CNTL, +#ifdef __BIG_ENDIAN + R600_BUF_SWAP_32BIT | +#endif R600_RB_NO_UPDATE | - (15 << 8) | - (3 << 0)); + R600_RB_BLKSZ(15) | + R600_RB_BUFSZ(3)); RADEON_WRITE(R600_GRBM_SOFT_RESET, R600_SOFT_RESET_CP); RADEON_READ(R600_GRBM_SOFT_RESET); @@ -550,8 +556,12 @@ static void r600_test_writeback(drm_radeon_private_t *dev_priv) if (!dev_priv->writeback_works) { /* Disable writeback to avoid unnecessary bus master transfer */ - RADEON_WRITE(R600_CP_RB_CNTL, RADEON_READ(R600_CP_RB_CNTL) | - RADEON_RB_NO_UPDATE); + RADEON_WRITE(R600_CP_RB_CNTL, +#ifdef __BIG_ENDIAN + R600_BUF_SWAP_32BIT | +#endif + RADEON_READ(R600_CP_RB_CNTL) | + R600_RB_NO_UPDATE); RADEON_WRITE(R600_SCRATCH_UMSK, 0); } } @@ -575,7 +585,11 @@ int r600_do_engine_reset(struct drm_device *dev) RADEON_WRITE(R600_CP_RB_WPTR_DELAY, 0); cp_rb_cntl = RADEON_READ(R600_CP_RB_CNTL); - RADEON_WRITE(R600_CP_RB_CNTL, R600_RB_RPTR_WR_ENA); + RADEON_WRITE(R600_CP_RB_CNTL, +#ifdef __BIG_ENDIAN + R600_BUF_SWAP_32BIT | +#endif + R600_RB_RPTR_WR_ENA); RADEON_WRITE(R600_CP_RB_RPTR_WR, cp_ptr); RADEON_WRITE(R600_CP_RB_WPTR, cp_ptr); @@ -1838,7 +1852,10 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev, + dev_priv->gart_vm_start; } RADEON_WRITE(R600_CP_RB_RPTR_ADDR, - rptr_addr & 0xffffffff); +#ifdef __BIG_ENDIAN + (2 << 0) | +#endif + (rptr_addr & 0xfffffffc)); RADEON_WRITE(R600_CP_RB_RPTR_ADDR_HI, upper_32_bits(rptr_addr)); @@ -1889,7 +1906,7 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev, { u64 scratch_addr; - scratch_addr = RADEON_READ(R600_CP_RB_RPTR_ADDR); + scratch_addr = RADEON_READ(R600_CP_RB_RPTR_ADDR) & 0xFFFFFFFC; scratch_addr |= ((u64)RADEON_READ(R600_CP_RB_RPTR_ADDR_HI)) << 32; scratch_addr += R600_SCRATCH_REG_OFFSET; scratch_addr >>= 8; diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 7831e08..153095f 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -295,17 +295,18 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) } if (!IS_ALIGNED(pitch, pitch_align)) { - dev_warn(p->dev, "%s:%d cb pitch (%d) invalid\n", - __func__, __LINE__, pitch); + dev_warn(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, pitch, pitch_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(height, height_align)) { - dev_warn(p->dev, "%s:%d cb height (%d) invalid\n", - __func__, __LINE__, height); + dev_warn(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, height, height_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(base_offset, base_align)) { - dev_warn(p->dev, "%s offset[%d] 0x%llx not aligned\n", __func__, i, base_offset); + dev_warn(p->dev, "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i, + base_offset, base_align, array_mode); return -EINVAL; } @@ -320,7 +321,10 @@ static inline int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) * broken userspace. */ } else { - dev_warn(p->dev, "%s offset[%d] %d %d %lu too big\n", __func__, i, track->cb_color_bo_offset[i], tmp, radeon_bo_size(track->cb_color_bo[i])); + dev_warn(p->dev, "%s offset[%d] %d %d %d %lu too big\n", __func__, i, + array_mode, + track->cb_color_bo_offset[i], tmp, + radeon_bo_size(track->cb_color_bo[i])); return -EINVAL; } } @@ -455,17 +459,18 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) } if (!IS_ALIGNED(pitch, pitch_align)) { - dev_warn(p->dev, "%s:%d db pitch (%d) invalid\n", - __func__, __LINE__, pitch); + dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, pitch, pitch_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(height, height_align)) { - dev_warn(p->dev, "%s:%d db height (%d) invalid\n", - __func__, __LINE__, height); + dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, height, height_align, array_mode); return -EINVAL; } if (!IS_ALIGNED(base_offset, base_align)) { - dev_warn(p->dev, "%s offset[%d] 0x%llx not aligned\n", __func__, i, base_offset); + dev_warn(p->dev, "%s offset[%d] 0x%llx, 0x%llx, %d not aligned\n", __func__, i, + base_offset, base_align, array_mode); return -EINVAL; } @@ -473,9 +478,10 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1; tmp = ntiles * bpe * 64 * nviews; if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) { - dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %d -> %u have %lu)\n", - track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset, - radeon_bo_size(track->db_bo)); + dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n", + array_mode, + track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset, + radeon_bo_size(track->db_bo)); return -EINVAL; } } @@ -1227,18 +1233,18 @@ static inline int r600_check_texture_resource(struct radeon_cs_parser *p, u32 i /* XXX check height as well... */ if (!IS_ALIGNED(pitch, pitch_align)) { - dev_warn(p->dev, "%s:%d tex pitch (%d) invalid\n", - __func__, __LINE__, pitch); + dev_warn(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n", + __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0)); return -EINVAL; } if (!IS_ALIGNED(base_offset, base_align)) { - dev_warn(p->dev, "%s:%d tex base offset (0x%llx) invalid\n", - __func__, __LINE__, base_offset); + dev_warn(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n", + __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0)); return -EINVAL; } if (!IS_ALIGNED(mip_offset, base_align)) { - dev_warn(p->dev, "%s:%d tex mip offset (0x%llx) invalid\n", - __func__, __LINE__, mip_offset); + dev_warn(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n", + __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0)); return -EINVAL; } diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h index a5d898b..04bac0b 100644 --- a/drivers/gpu/drm/radeon/r600d.h +++ b/drivers/gpu/drm/radeon/r600d.h @@ -154,13 +154,14 @@ #define ROQ_IB2_START(x) ((x) << 8) #define CP_RB_BASE 0xC100 #define CP_RB_CNTL 0xC104 -#define RB_BUFSZ(x) ((x)<<0) -#define RB_BLKSZ(x) ((x)<<8) -#define RB_NO_UPDATE (1<<27) -#define RB_RPTR_WR_ENA (1<<31) +#define RB_BUFSZ(x) ((x) << 0) +#define RB_BLKSZ(x) ((x) << 8) +#define RB_NO_UPDATE (1 << 27) +#define RB_RPTR_WR_ENA (1 << 31) #define BUF_SWAP_32BIT (2 << 16) #define CP_RB_RPTR 0x8700 #define CP_RB_RPTR_ADDR 0xC10C +#define RB_RPTR_SWAP(x) ((x) << 0) #define CP_RB_RPTR_ADDR_HI 0xC110 #define CP_RB_RPTR_WR 0xC108 #define CP_RB_WPTR 0xC114 diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 71d2a55..6b342949 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -179,10 +179,10 @@ void radeon_combios_get_power_modes(struct radeon_device *rdev); void radeon_atombios_get_power_modes(struct radeon_device *rdev); void radeon_atom_set_voltage(struct radeon_device *rdev, u16 level); void rs690_pm_info(struct radeon_device *rdev); -extern u32 rv6xx_get_temp(struct radeon_device *rdev); -extern u32 rv770_get_temp(struct radeon_device *rdev); -extern u32 evergreen_get_temp(struct radeon_device *rdev); -extern u32 sumo_get_temp(struct radeon_device *rdev); +extern int rv6xx_get_temp(struct radeon_device *rdev); +extern int rv770_get_temp(struct radeon_device *rdev); +extern int evergreen_get_temp(struct radeon_device *rdev); +extern int sumo_get_temp(struct radeon_device *rdev); /* * Fences. @@ -345,7 +345,6 @@ struct radeon_mc { * about vram size near mc fb location */ u64 mc_vram_size; u64 visible_vram_size; - u64 active_vram_size; u64 gtt_size; u64 gtt_start; u64 gtt_end; @@ -812,8 +811,7 @@ struct radeon_pm { fixed20_12 sclk; fixed20_12 mclk; fixed20_12 needed_bandwidth; - /* XXX: use a define for num power modes */ - struct radeon_power_state power_state[8]; + struct radeon_power_state *power_state; /* number of valid power states */ int num_power_states; int current_power_state_index; @@ -1449,6 +1447,7 @@ extern void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *m extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc); extern int radeon_resume_kms(struct drm_device *dev); extern int radeon_suspend_kms(struct drm_device *dev, pm_message_t state); +extern void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size); /* r600, rv610, rv630, rv620, rv635, rv670, rs780, rs880 */ extern bool r600_card_posted(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 3a1b161..793c5e6 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -759,7 +759,7 @@ static struct radeon_asic evergreen_asic = { .gart_tlb_flush = &evergreen_pcie_gart_tlb_flush, .gart_set_page = &rs600_gart_set_page, .ring_test = &r600_ring_test, - .ring_ib_execute = &r600_ring_ib_execute, + .ring_ib_execute = &evergreen_ring_ib_execute, .irq_set = &evergreen_irq_set, .irq_process = &evergreen_irq_process, .get_vblank_counter = &evergreen_get_vblank_counter, @@ -805,7 +805,7 @@ static struct radeon_asic sumo_asic = { .gart_tlb_flush = &evergreen_pcie_gart_tlb_flush, .gart_set_page = &rs600_gart_set_page, .ring_test = &r600_ring_test, - .ring_ib_execute = &r600_ring_ib_execute, + .ring_ib_execute = &evergreen_ring_ib_execute, .irq_set = &evergreen_irq_set, .irq_process = &evergreen_irq_process, .get_vblank_counter = &evergreen_get_vblank_counter, @@ -834,6 +834,9 @@ static struct radeon_asic sumo_asic = { .pm_finish = &evergreen_pm_finish, .pm_init_profile = &rs780_pm_init_profile, .pm_get_dynpm_state = &r600_pm_get_dynpm_state, + .pre_page_flip = &evergreen_pre_page_flip, + .page_flip = &evergreen_page_flip, + .post_page_flip = &evergreen_post_page_flip, }; static struct radeon_asic btc_asic = { @@ -848,7 +851,7 @@ static struct radeon_asic btc_asic = { .gart_tlb_flush = &evergreen_pcie_gart_tlb_flush, .gart_set_page = &rs600_gart_set_page, .ring_test = &r600_ring_test, - .ring_ib_execute = &r600_ring_ib_execute, + .ring_ib_execute = &evergreen_ring_ib_execute, .irq_set = &evergreen_irq_set, .irq_process = &evergreen_irq_process, .get_vblank_counter = &evergreen_get_vblank_counter, diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index e01f0771..c59bd98 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -355,6 +355,7 @@ int evergreen_resume(struct radeon_device *rdev); bool evergreen_gpu_is_lockup(struct radeon_device *rdev); int evergreen_asic_reset(struct radeon_device *rdev); void evergreen_bandwidth_update(struct radeon_device *rdev); +void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib); int evergreen_copy_blit(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_pages, struct radeon_fence *fence); diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 5277790..02d5c41 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -88,7 +88,7 @@ static inline struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_dev /* some evergreen boards have bad data for this entry */ if (ASIC_IS_DCE4(rdev)) { if ((i == 7) && - (gpio->usClkMaskRegisterIndex == 0x1936) && + (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) && (gpio->sucI2cId.ucAccess == 0)) { gpio->sucI2cId.ucAccess = 0x97; gpio->ucDataMaskShift = 8; @@ -101,7 +101,7 @@ static inline struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_dev /* some DCE3 boards have bad data for this entry */ if (ASIC_IS_DCE3(rdev)) { if ((i == 4) && - (gpio->usClkMaskRegisterIndex == 0x1fda) && + (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) && (gpio->sucI2cId.ucAccess == 0x94)) gpio->sucI2cId.ucAccess = 0x14; } @@ -172,7 +172,7 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev) /* some evergreen boards have bad data for this entry */ if (ASIC_IS_DCE4(rdev)) { if ((i == 7) && - (gpio->usClkMaskRegisterIndex == 0x1936) && + (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) && (gpio->sucI2cId.ucAccess == 0)) { gpio->sucI2cId.ucAccess = 0x97; gpio->ucDataMaskShift = 8; @@ -185,7 +185,7 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev) /* some DCE3 boards have bad data for this entry */ if (ASIC_IS_DCE3(rdev)) { if ((i == 4) && - (gpio->usClkMaskRegisterIndex == 0x1fda) && + (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) && (gpio->sucI2cId.ucAccess == 0x94)) gpio->sucI2cId.ucAccess = 0x14; } @@ -252,7 +252,7 @@ static inline struct radeon_gpio_rec radeon_lookup_gpio(struct radeon_device *rd pin = &gpio_info->asGPIO_Pin[i]; if (id == pin->ucGPIO_ID) { gpio.id = pin->ucGPIO_ID; - gpio.reg = pin->usGpioPin_AIndex * 4; + gpio.reg = le16_to_cpu(pin->usGpioPin_AIndex) * 4; gpio.mask = (1 << pin->ucGpioPinBitShift); gpio.valid = true; break; @@ -1163,16 +1163,6 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) p1pll->pll_out_min = 64800; else p1pll->pll_out_min = 20000; - } else if (p1pll->pll_out_min > 64800) { - /* Limiting the pll output range is a good thing generally as - * it limits the number of possible pll combinations for a given - * frequency presumably to the ones that work best on each card. - * However, certain duallink DVI monitors seem to like - * pll combinations that would be limited by this at least on - * pre-DCE 3.0 r6xx hardware. This might need to be adjusted per - * family. - */ - p1pll->pll_out_min = 64800; } p1pll->pll_in_min = @@ -1284,11 +1274,11 @@ bool radeon_atombios_sideport_present(struct radeon_device *rdev) data_offset); switch (crev) { case 1: - if (igp_info->info.ulBootUpMemoryClock) + if (le32_to_cpu(igp_info->info.ulBootUpMemoryClock)) return true; break; case 2: - if (igp_info->info_2.ulBootUpSidePortClock) + if (le32_to_cpu(igp_info->info_2.ulBootUpSidePortClock)) return true; break; default: @@ -1452,7 +1442,7 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, for (i = 0; i < num_indices; i++) { if ((ss_info->info.asSpreadSpectrum[i].ucClockIndication == id) && - (clock <= ss_info->info.asSpreadSpectrum[i].ulTargetClockRange)) { + (clock <= le32_to_cpu(ss_info->info.asSpreadSpectrum[i].ulTargetClockRange))) { ss->percentage = le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadSpectrumPercentage); ss->type = ss_info->info.asSpreadSpectrum[i].ucSpreadSpectrumMode; @@ -1466,7 +1456,7 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2); for (i = 0; i < num_indices; i++) { if ((ss_info->info_2.asSpreadSpectrum[i].ucClockIndication == id) && - (clock <= ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange)) { + (clock <= le32_to_cpu(ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange))) { ss->percentage = le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadSpectrumPercentage); ss->type = ss_info->info_2.asSpreadSpectrum[i].ucSpreadSpectrumMode; @@ -1480,7 +1470,7 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3); for (i = 0; i < num_indices; i++) { if ((ss_info->info_3.asSpreadSpectrum[i].ucClockIndication == id) && - (clock <= ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange)) { + (clock <= le32_to_cpu(ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange))) { ss->percentage = le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadSpectrumPercentage); ss->type = ss_info->info_3.asSpreadSpectrum[i].ucSpreadSpectrumMode; @@ -1563,8 +1553,8 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct if (misc & ATOM_DOUBLE_CLOCK_MODE) lvds->native_mode.flags |= DRM_MODE_FLAG_DBLSCAN; - lvds->native_mode.width_mm = lvds_info->info.sLCDTiming.usImageHSize; - lvds->native_mode.height_mm = lvds_info->info.sLCDTiming.usImageVSize; + lvds->native_mode.width_mm = le16_to_cpu(lvds_info->info.sLCDTiming.usImageHSize); + lvds->native_mode.height_mm = le16_to_cpu(lvds_info->info.sLCDTiming.usImageVSize); /* set crtc values */ drm_mode_set_crtcinfo(&lvds->native_mode, CRTC_INTERLACE_HALVE_V); @@ -1579,13 +1569,13 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct lvds->linkb = false; /* parse the lcd record table */ - if (lvds_info->info.usModePatchTableOffset) { + if (le16_to_cpu(lvds_info->info.usModePatchTableOffset)) { ATOM_FAKE_EDID_PATCH_RECORD *fake_edid_record; ATOM_PANEL_RESOLUTION_PATCH_RECORD *panel_res_record; bool bad_record = false; u8 *record = (u8 *)(mode_info->atom_context->bios + data_offset + - lvds_info->info.usModePatchTableOffset); + le16_to_cpu(lvds_info->info.usModePatchTableOffset)); while (*record != ATOM_RECORD_END_TYPE) { switch (*record) { case LCD_MODE_PATCH_RECORD_MODE_TYPE: @@ -1987,6 +1977,9 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev) num_modes = power_info->info.ucNumOfPowerModeEntries; if (num_modes > ATOM_MAX_NUMBEROF_POWER_BLOCK) num_modes = ATOM_MAX_NUMBEROF_POWER_BLOCK; + rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state) * num_modes, GFP_KERNEL); + if (!rdev->pm.power_state) + return state_index; /* last mode is usually default, array is low to high */ for (i = 0; i < num_modes; i++) { rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE; @@ -2196,7 +2189,7 @@ static u16 radeon_atombios_get_default_vddc(struct radeon_device *rdev) firmware_info = (union firmware_info *)(mode_info->atom_context->bios + data_offset); - vddc = firmware_info->info_14.usBootUpVDDCVoltage; + vddc = le16_to_cpu(firmware_info->info_14.usBootUpVDDCVoltage); } return vddc; @@ -2291,7 +2284,7 @@ static bool radeon_atombios_parse_pplib_clock_info(struct radeon_device *rdev, rdev->pm.power_state[state_index].clock_info[mode_index].voltage.type = VOLTAGE_SW; rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage = - clock_info->evergreen.usVDDC; + le16_to_cpu(clock_info->evergreen.usVDDC); } else { sclk = le16_to_cpu(clock_info->r600.usEngineClockLow); sclk |= clock_info->r600.ucEngineClockHigh << 16; @@ -2302,7 +2295,7 @@ static bool radeon_atombios_parse_pplib_clock_info(struct radeon_device *rdev, rdev->pm.power_state[state_index].clock_info[mode_index].voltage.type = VOLTAGE_SW; rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage = - clock_info->r600.usVDDC; + le16_to_cpu(clock_info->r600.usVDDC); } if (rdev->flags & RADEON_IS_IGP) { @@ -2338,6 +2331,10 @@ static int radeon_atombios_parse_power_table_4_5(struct radeon_device *rdev) power_info = (union power_info *)(mode_info->atom_context->bios + data_offset); radeon_atombios_add_pplib_thermal_controller(rdev, &power_info->pplib.sThermalController); + rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state) * + power_info->pplib.ucNumStates, GFP_KERNEL); + if (!rdev->pm.power_state) + return state_index; /* first mode is usually default, followed by low to high */ for (i = 0; i < power_info->pplib.ucNumStates; i++) { mode_index = 0; @@ -2411,13 +2408,17 @@ static int radeon_atombios_parse_power_table_6(struct radeon_device *rdev) radeon_atombios_add_pplib_thermal_controller(rdev, &power_info->pplib.sThermalController); state_array = (struct StateArray *) (mode_info->atom_context->bios + data_offset + - power_info->pplib.usStateArrayOffset); + le16_to_cpu(power_info->pplib.usStateArrayOffset)); clock_info_array = (struct ClockInfoArray *) (mode_info->atom_context->bios + data_offset + - power_info->pplib.usClockInfoArrayOffset); + le16_to_cpu(power_info->pplib.usClockInfoArrayOffset)); non_clock_info_array = (struct NonClockInfoArray *) (mode_info->atom_context->bios + data_offset + - power_info->pplib.usNonClockInfoArrayOffset); + le16_to_cpu(power_info->pplib.usNonClockInfoArrayOffset)); + rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state) * + state_array->ucNumEntries, GFP_KERNEL); + if (!rdev->pm.power_state) + return state_index; for (i = 0; i < state_array->ucNumEntries; i++) { mode_index = 0; power_state = (union pplib_power_state *)&state_array->states[i]; @@ -2491,19 +2492,22 @@ void radeon_atombios_get_power_modes(struct radeon_device *rdev) break; } } else { - /* add the default mode */ - rdev->pm.power_state[state_index].type = - POWER_STATE_TYPE_DEFAULT; - rdev->pm.power_state[state_index].num_clock_modes = 1; - rdev->pm.power_state[state_index].clock_info[0].mclk = rdev->clock.default_mclk; - rdev->pm.power_state[state_index].clock_info[0].sclk = rdev->clock.default_sclk; - rdev->pm.power_state[state_index].default_clock_mode = - &rdev->pm.power_state[state_index].clock_info[0]; - rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE; - rdev->pm.power_state[state_index].pcie_lanes = 16; - rdev->pm.default_power_state_index = state_index; - rdev->pm.power_state[state_index].flags = 0; - state_index++; + rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state), GFP_KERNEL); + if (rdev->pm.power_state) { + /* add the default mode */ + rdev->pm.power_state[state_index].type = + POWER_STATE_TYPE_DEFAULT; + rdev->pm.power_state[state_index].num_clock_modes = 1; + rdev->pm.power_state[state_index].clock_info[0].mclk = rdev->clock.default_mclk; + rdev->pm.power_state[state_index].clock_info[0].sclk = rdev->clock.default_sclk; + rdev->pm.power_state[state_index].default_clock_mode = + &rdev->pm.power_state[state_index].clock_info[0]; + rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE; + rdev->pm.power_state[state_index].pcie_lanes = 16; + rdev->pm.default_power_state_index = state_index; + rdev->pm.power_state[state_index].flags = 0; + state_index++; + } } rdev->pm.num_power_states = state_index; @@ -2529,7 +2533,7 @@ uint32_t radeon_atom_get_engine_clock(struct radeon_device *rdev) int index = GetIndexIntoMasterTable(COMMAND, GetEngineClock); atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); - return args.ulReturnEngineClock; + return le32_to_cpu(args.ulReturnEngineClock); } uint32_t radeon_atom_get_memory_clock(struct radeon_device *rdev) @@ -2538,7 +2542,7 @@ uint32_t radeon_atom_get_memory_clock(struct radeon_device *rdev) int index = GetIndexIntoMasterTable(COMMAND, GetMemoryClock); atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); - return args.ulReturnMemoryClock; + return le32_to_cpu(args.ulReturnMemoryClock); } void radeon_atom_set_engine_clock(struct radeon_device *rdev, @@ -2547,7 +2551,7 @@ void radeon_atom_set_engine_clock(struct radeon_device *rdev, SET_ENGINE_CLOCK_PS_ALLOCATION args; int index = GetIndexIntoMasterTable(COMMAND, SetEngineClock); - args.ulTargetEngineClock = eng_clock; /* 10 khz */ + args.ulTargetEngineClock = cpu_to_le32(eng_clock); /* 10 khz */ atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } @@ -2561,7 +2565,7 @@ void radeon_atom_set_memory_clock(struct radeon_device *rdev, if (rdev->flags & RADEON_IS_IGP) return; - args.ulTargetMemoryClock = mem_clock; /* 10 khz */ + args.ulTargetMemoryClock = cpu_to_le32(mem_clock); /* 10 khz */ atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } @@ -2619,7 +2623,7 @@ void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev) bios_2_scratch &= ~ATOM_S2_VRI_BRIGHT_ENABLE; /* tell the bios not to handle mode switching */ - bios_6_scratch |= (ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH | ATOM_S6_ACC_MODE); + bios_6_scratch |= ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH; if (rdev->family >= CHIP_R600) { WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch); @@ -2670,10 +2674,13 @@ void radeon_atom_output_lock(struct drm_encoder *encoder, bool lock) else bios_6_scratch = RREG32(RADEON_BIOS_6_SCRATCH); - if (lock) + if (lock) { bios_6_scratch |= ATOM_S6_CRITICAL_STATE; - else + bios_6_scratch &= ~ATOM_S6_ACC_MODE; + } else { bios_6_scratch &= ~ATOM_S6_CRITICAL_STATE; + bios_6_scratch |= ATOM_S6_ACC_MODE; + } if (rdev->family >= CHIP_R600) WREG32(R600_BIOS_6_SCRATCH, bios_6_scratch); diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c index 591fcae..cf7c8d5 100644 --- a/drivers/gpu/drm/radeon/radeon_combios.c +++ b/drivers/gpu/drm/radeon/radeon_combios.c @@ -1504,6 +1504,11 @@ bool radeon_get_legacy_connector_info_from_table(struct drm_device *dev) (rdev->pdev->subsystem_device == 0x4a48)) { /* Mac X800 */ rdev->mode_info.connector_table = CT_MAC_X800; + } else if ((rdev->pdev->device == 0x4150) && + (rdev->pdev->subsystem_vendor == 0x1002) && + (rdev->pdev->subsystem_device == 0x4150)) { + /* Mac G5 9600 */ + rdev->mode_info.connector_table = CT_MAC_G5_9600; } else #endif /* CONFIG_PPC_PMAC */ #ifdef CONFIG_PPC64 @@ -2022,6 +2027,48 @@ bool radeon_get_legacy_connector_info_from_table(struct drm_device *dev) CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I, &hpd); break; + case CT_MAC_G5_9600: + DRM_INFO("Connector Table: %d (mac g5 9600)\n", + rdev->mode_info.connector_table); + /* DVI - tv dac, dvo */ + ddc_i2c = combios_setup_i2c_bus(rdev, DDC_DVI, 0, 0); + hpd.hpd = RADEON_HPD_1; /* ??? */ + radeon_add_legacy_encoder(dev, + radeon_get_encoder_enum(dev, + ATOM_DEVICE_DFP2_SUPPORT, + 0), + ATOM_DEVICE_DFP2_SUPPORT); + radeon_add_legacy_encoder(dev, + radeon_get_encoder_enum(dev, + ATOM_DEVICE_CRT2_SUPPORT, + 2), + ATOM_DEVICE_CRT2_SUPPORT); + radeon_add_legacy_connector(dev, 0, + ATOM_DEVICE_DFP2_SUPPORT | + ATOM_DEVICE_CRT2_SUPPORT, + DRM_MODE_CONNECTOR_DVII, &ddc_i2c, + CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_I, + &hpd); + /* ADC - primary dac, internal tmds */ + ddc_i2c = combios_setup_i2c_bus(rdev, DDC_VGA, 0, 0); + hpd.hpd = RADEON_HPD_2; /* ??? */ + radeon_add_legacy_encoder(dev, + radeon_get_encoder_enum(dev, + ATOM_DEVICE_DFP1_SUPPORT, + 0), + ATOM_DEVICE_DFP1_SUPPORT); + radeon_add_legacy_encoder(dev, + radeon_get_encoder_enum(dev, + ATOM_DEVICE_CRT1_SUPPORT, + 1), + ATOM_DEVICE_CRT1_SUPPORT); + radeon_add_legacy_connector(dev, 1, + ATOM_DEVICE_DFP1_SUPPORT | + ATOM_DEVICE_CRT1_SUPPORT, + DRM_MODE_CONNECTOR_DVII, &ddc_i2c, + CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_I, + &hpd); + break; default: DRM_INFO("Connector table: %d (invalid)\n", rdev->mode_info.connector_table); @@ -2442,6 +2489,17 @@ void radeon_combios_get_power_modes(struct radeon_device *rdev) rdev->pm.default_power_state_index = -1; + /* allocate 2 power states */ + rdev->pm.power_state = kzalloc(sizeof(struct radeon_power_state) * 2, GFP_KERNEL); + if (!rdev->pm.power_state) { + rdev->pm.default_power_state_index = state_index; + rdev->pm.num_power_states = 0; + + rdev->pm.current_power_state_index = rdev->pm.default_power_state_index; + rdev->pm.current_clock_mode_index = 0; + return; + } + if (rdev->flags & RADEON_IS_MOBILITY) { offset = combios_get_table_offset(dev, COMBIOS_POWERPLAY_INFO_TABLE); if (offset) { diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 0d47893..4954e2d 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -936,8 +936,11 @@ int radeon_resume_kms(struct drm_device *dev) int radeon_gpu_reset(struct radeon_device *rdev) { int r; + int resched; radeon_save_bios_scratch_regs(rdev); + /* block TTM */ + resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev); radeon_suspend(rdev); r = radeon_asic_reset(rdev); @@ -946,6 +949,7 @@ int radeon_gpu_reset(struct radeon_device *rdev) radeon_resume(rdev); radeon_restore_bios_scratch_regs(rdev); drm_helper_resume_force_mode(rdev->ddev); + ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched); return 0; } /* bad news, how to tell it to userspace ? */ diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index d26dabf..3e7e7f9e 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -780,6 +780,125 @@ static int radeon_ddc_dump(struct drm_connector *connector) return ret; } +/* avivo */ +static void avivo_get_fb_div(struct radeon_pll *pll, + u32 target_clock, + u32 post_div, + u32 ref_div, + u32 *fb_div, + u32 *frac_fb_div) +{ + u32 tmp = post_div * ref_div; + + tmp *= target_clock; + *fb_div = tmp / pll->reference_freq; + *frac_fb_div = tmp % pll->reference_freq; + + if (*fb_div > pll->max_feedback_div) + *fb_div = pll->max_feedback_div; + else if (*fb_div < pll->min_feedback_div) + *fb_div = pll->min_feedback_div; +} + +static u32 avivo_get_post_div(struct radeon_pll *pll, + u32 target_clock) +{ + u32 vco, post_div, tmp; + + if (pll->flags & RADEON_PLL_USE_POST_DIV) + return pll->post_div; + + if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP) { + if (pll->flags & RADEON_PLL_IS_LCD) + vco = pll->lcd_pll_out_min; + else + vco = pll->pll_out_min; + } else { + if (pll->flags & RADEON_PLL_IS_LCD) + vco = pll->lcd_pll_out_max; + else + vco = pll->pll_out_max; + } + + post_div = vco / target_clock; + tmp = vco % target_clock; + + if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP) { + if (tmp) + post_div++; + } else { + if (!tmp) + post_div--; + } + + if (post_div > pll->max_post_div) + post_div = pll->max_post_div; + else if (post_div < pll->min_post_div) + post_div = pll->min_post_div; + + return post_div; +} + +#define MAX_TOLERANCE 10 + +void radeon_compute_pll_avivo(struct radeon_pll *pll, + u32 freq, + u32 *dot_clock_p, + u32 *fb_div_p, + u32 *frac_fb_div_p, + u32 *ref_div_p, + u32 *post_div_p) +{ + u32 target_clock = freq / 10; + u32 post_div = avivo_get_post_div(pll, target_clock); + u32 ref_div = pll->min_ref_div; + u32 fb_div = 0, frac_fb_div = 0, tmp; + + if (pll->flags & RADEON_PLL_USE_REF_DIV) + ref_div = pll->reference_div; + + if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV) { + avivo_get_fb_div(pll, target_clock, post_div, ref_div, &fb_div, &frac_fb_div); + frac_fb_div = (100 * frac_fb_div) / pll->reference_freq; + if (frac_fb_div >= 5) { + frac_fb_div -= 5; + frac_fb_div = frac_fb_div / 10; + frac_fb_div++; + } + if (frac_fb_div >= 10) { + fb_div++; + frac_fb_div = 0; + } + } else { + while (ref_div <= pll->max_ref_div) { + avivo_get_fb_div(pll, target_clock, post_div, ref_div, + &fb_div, &frac_fb_div); + if (frac_fb_div >= (pll->reference_freq / 2)) + fb_div++; + frac_fb_div = 0; + tmp = (pll->reference_freq * fb_div) / (post_div * ref_div); + tmp = (tmp * 10000) / target_clock; + + if (tmp > (10000 + MAX_TOLERANCE)) + ref_div++; + else if (tmp >= (10000 - MAX_TOLERANCE)) + break; + else + ref_div++; + } + } + + *dot_clock_p = ((pll->reference_freq * fb_div * 10) + (pll->reference_freq * frac_fb_div)) / + (ref_div * post_div * 10); + *fb_div_p = fb_div; + *frac_fb_div_p = frac_fb_div; + *ref_div_p = ref_div; + *post_div_p = post_div; + DRM_DEBUG_KMS("%d, pll dividers - fb: %d.%d ref: %d, post %d\n", + *dot_clock_p, fb_div, frac_fb_div, ref_div, post_div); +} + +/* pre-avivo */ static inline uint32_t radeon_div(uint64_t n, uint32_t d) { uint64_t mod; @@ -790,13 +909,13 @@ static inline uint32_t radeon_div(uint64_t n, uint32_t d) return n; } -void radeon_compute_pll(struct radeon_pll *pll, - uint64_t freq, - uint32_t *dot_clock_p, - uint32_t *fb_div_p, - uint32_t *frac_fb_div_p, - uint32_t *ref_div_p, - uint32_t *post_div_p) +void radeon_compute_pll_legacy(struct radeon_pll *pll, + uint64_t freq, + uint32_t *dot_clock_p, + uint32_t *fb_div_p, + uint32_t *frac_fb_div_p, + uint32_t *ref_div_p, + uint32_t *post_div_p) { uint32_t min_ref_div = pll->min_ref_div; uint32_t max_ref_div = pll->max_ref_div; @@ -826,6 +945,9 @@ void radeon_compute_pll(struct radeon_pll *pll, pll_out_max = pll->pll_out_max; } + if (pll_out_min > 64800) + pll_out_min = 64800; + if (pll->flags & RADEON_PLL_USE_REF_DIV) min_ref_div = max_ref_div = pll->reference_div; else { @@ -965,6 +1087,10 @@ void radeon_compute_pll(struct radeon_pll *pll, *frac_fb_div_p = best_frac_feedback_div; *ref_div_p = best_ref_div; *post_div_p = best_post_div; + DRM_DEBUG_KMS("%d %d, pll dividers - fb: %d.%d ref: %d, post %d\n", + freq, best_freq / 1000, best_feedback_div, best_frac_feedback_div, + best_ref_div, best_post_div); + } static void radeon_user_framebuffer_destroy(struct drm_framebuffer *fb) diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h index 448eba8..5cba46b 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.h +++ b/drivers/gpu/drm/radeon/radeon_drv.h @@ -1524,6 +1524,7 @@ extern u32 radeon_get_scratch(drm_radeon_private_t *dev_priv, int index); #define R600_CP_RB_CNTL 0xc104 # define R600_RB_BUFSZ(x) ((x) << 0) # define R600_RB_BLKSZ(x) ((x) << 8) +# define R600_BUF_SWAP_32BIT (2 << 16) # define R600_RB_NO_UPDATE (1 << 27) # define R600_RB_RPTR_WR_ENA (1 << 31) #define R600_CP_RB_RPTR_WR 0xc108 diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index 5e90984..b427488 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -910,7 +910,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t args.v1.ucAction = action; if (action == ATOM_TRANSMITTER_ACTION_INIT) { - args.v1.usInitInfo = connector_object_id; + args.v1.usInitInfo = cpu_to_le16(connector_object_id); } else if (action == ATOM_TRANSMITTER_ACTION_SETUP_VSEMPH) { args.v1.asMode.ucLaneSel = lane_num; args.v1.asMode.ucLaneSet = lane_set; @@ -1063,7 +1063,7 @@ atombios_set_edp_panel_power(struct drm_connector *connector, int action) if (!ASIC_IS_DCE4(rdev)) return; - if ((action != ATOM_TRANSMITTER_ACTION_POWER_ON) || + if ((action != ATOM_TRANSMITTER_ACTION_POWER_ON) && (action != ATOM_TRANSMITTER_ACTION_POWER_OFF)) return; @@ -1140,7 +1140,7 @@ atombios_external_encoder_setup(struct drm_encoder *encoder, case 3: args.v3.sExtEncoder.ucAction = action; if (action == EXTERNAL_ENCODER_ACTION_V3_ENCODER_INIT) - args.v3.sExtEncoder.usConnectorId = connector_object_id; + args.v3.sExtEncoder.usConnectorId = cpu_to_le16(connector_object_id); else args.v3.sExtEncoder.usPixelClock = cpu_to_le16(radeon_encoder->pixel_clock / 10); args.v3.sExtEncoder.ucEncoderMode = atombios_get_encoder_mode(encoder); @@ -1570,11 +1570,21 @@ atombios_apply_encoder_quirks(struct drm_encoder *encoder, } /* set scaler clears this on some chips */ - /* XXX check DCE4 */ - if (!(radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT))) { - if (ASIC_IS_AVIVO(rdev) && (mode->flags & DRM_MODE_FLAG_INTERLACE)) - WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, - AVIVO_D1MODE_INTERLEAVE_EN); + if (ASIC_IS_AVIVO(rdev) && + (!(radeon_encoder->active_device & (ATOM_DEVICE_TV_SUPPORT)))) { + if (ASIC_IS_DCE4(rdev)) { + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset, + EVERGREEN_INTERLEAVE_EN); + else + WREG32(EVERGREEN_DATA_FORMAT + radeon_crtc->crtc_offset, 0); + } else { + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, + AVIVO_D1MODE_INTERLEAVE_EN); + else + WREG32(AVIVO_D1MODE_DATA_FORMAT + radeon_crtc->crtc_offset, 0); + } } } diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c index 66324b5..cc44bdf 100644 --- a/drivers/gpu/drm/radeon/radeon_fb.c +++ b/drivers/gpu/drm/radeon/radeon_fb.c @@ -113,11 +113,14 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev, u32 tiling_flags = 0; int ret; int aligned_size, size; + int height = mode_cmd->height; /* need to align pitch with crtc limits */ mode_cmd->pitch = radeon_align_pitch(rdev, mode_cmd->width, mode_cmd->bpp, fb_tiled) * ((mode_cmd->bpp + 1) / 8); - size = mode_cmd->pitch * mode_cmd->height; + if (rdev->family >= CHIP_R600) + height = ALIGN(mode_cmd->height, 8); + size = mode_cmd->pitch * height; aligned_size = ALIGN(size, PAGE_SIZE); ret = radeon_gem_object_create(rdev, aligned_size, 0, RADEON_GEM_DOMAIN_VRAM, diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index df95eb8..1fe95df 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -156,9 +156,12 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data, { struct radeon_device *rdev = dev->dev_private; struct drm_radeon_gem_info *args = data; + struct ttm_mem_type_manager *man; + + man = &rdev->mman.bdev.man[TTM_PL_VRAM]; args->vram_size = rdev->mc.real_vram_size; - args->vram_visible = rdev->mc.real_vram_size; + args->vram_visible = (u64)man->size << PAGE_SHIFT; if (rdev->stollen_vga_memory) args->vram_visible -= radeon_bo_size(rdev->stollen_vga_memory); args->vram_visible -= radeon_fbdev_total_size(rdev); diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c index ace2e63..78968b7 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c @@ -443,7 +443,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc, (target_fb->bits_per_pixel * 8)); crtc_pitch |= crtc_pitch << 16; - + crtc_offset_cntl |= RADEON_CRTC_GUI_TRIG_OFFSET_LEFT_EN; if (tiling_flags & RADEON_TILING_MACRO) { if (ASIC_IS_R300(rdev)) crtc_offset_cntl |= (R300_CRTC_X_Y_MODE_EN | @@ -502,6 +502,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc, gen_cntl_val = RREG32(gen_cntl_reg); gen_cntl_val &= ~(0xf << 8); gen_cntl_val |= (format << 8); + gen_cntl_val &= ~RADEON_CRTC_VSTAT_MODE_MASK; WREG32(gen_cntl_reg, gen_cntl_val); crtc_offset = (u32)base; @@ -778,9 +779,9 @@ static void radeon_set_pll(struct drm_crtc *crtc, struct drm_display_mode *mode) DRM_DEBUG_KMS("\n"); if (!use_bios_divs) { - radeon_compute_pll(pll, mode->clock, - &freq, &feedback_div, &frac_fb_div, - &reference_div, &post_divider); + radeon_compute_pll_legacy(pll, mode->clock, + &freq, &feedback_div, &frac_fb_div, + &reference_div, &post_divider); for (post_div = &post_divs[0]; post_div->divider; ++post_div) { if (post_div->divider == post_divider) diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index 12bdeab..a670caa 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -149,6 +149,7 @@ struct radeon_tmds_pll { #define RADEON_PLL_PREFER_CLOSEST_LOWER (1 << 11) #define RADEON_PLL_USE_POST_DIV (1 << 12) #define RADEON_PLL_IS_LCD (1 << 13) +#define RADEON_PLL_PREFER_MINM_OVER_MAXP (1 << 14) struct radeon_pll { /* reference frequency */ @@ -208,6 +209,7 @@ enum radeon_connector_table { CT_EMAC, CT_RN50_POWER, CT_MAC_X800, + CT_MAC_G5_9600, }; enum radeon_dvo_chip { @@ -510,13 +512,21 @@ extern bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, struct radeon_atom_ss *ss, int id, u32 clock); -extern void radeon_compute_pll(struct radeon_pll *pll, - uint64_t freq, - uint32_t *dot_clock_p, - uint32_t *fb_div_p, - uint32_t *frac_fb_div_p, - uint32_t *ref_div_p, - uint32_t *post_div_p); +extern void radeon_compute_pll_legacy(struct radeon_pll *pll, + uint64_t freq, + uint32_t *dot_clock_p, + uint32_t *fb_div_p, + uint32_t *frac_fb_div_p, + uint32_t *ref_div_p, + uint32_t *post_div_p); + +extern void radeon_compute_pll_avivo(struct radeon_pll *pll, + u32 freq, + u32 *dot_clock_p, + u32 *fb_div_p, + u32 *frac_fb_div_p, + u32 *ref_div_p, + u32 *post_div_p); extern void radeon_setup_encoder_clones(struct drm_device *dev); diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 3b1b2bf..2aed03b 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -430,7 +430,7 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev, { struct drm_device *ddev = pci_get_drvdata(to_pci_dev(dev)); struct radeon_device *rdev = ddev->dev_private; - u32 temp; + int temp; switch (rdev->pm.int_thermal_type) { case THERMAL_TYPE_RV6XX: @@ -646,6 +646,9 @@ void radeon_pm_fini(struct radeon_device *rdev) #endif } + if (rdev->pm.power_state) + kfree(rdev->pm.power_state); + radeon_hwmon_fini(rdev); } diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 1272e4b..8389b4c 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -589,6 +589,20 @@ void radeon_ttm_fini(struct radeon_device *rdev) DRM_INFO("radeon: ttm finalized\n"); } +/* this should only be called at bootup or when userspace + * isn't running */ +void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size) +{ + struct ttm_mem_type_manager *man; + + if (!rdev->mman.initialized) + return; + + man = &rdev->mman.bdev.man[TTM_PL_VRAM]; + /* this just adjusts TTM size idea, which sets lpfn to the correct value */ + man->size = size >> PAGE_SHIFT; +} + static struct vm_operations_struct radeon_ttm_vm_ops; static const struct vm_operations_struct *ttm_vm_ops = NULL; @@ -787,9 +801,9 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev) radeon_mem_types_list[i].show = &radeon_mm_dump_table; radeon_mem_types_list[i].driver_features = 0; if (i == 0) - radeon_mem_types_list[i].data = &rdev->mman.bdev.man[TTM_PL_VRAM].priv; + radeon_mem_types_list[i].data = rdev->mman.bdev.man[TTM_PL_VRAM].priv; else - radeon_mem_types_list[i].data = &rdev->mman.bdev.man[TTM_PL_TT].priv; + radeon_mem_types_list[i].data = rdev->mman.bdev.man[TTM_PL_TT].priv; } /* Add ttm page pool to debugfs */ diff --git a/drivers/gpu/drm/radeon/reg_srcs/r300 b/drivers/gpu/drm/radeon/reg_srcs/r300 index b506ec1..e8a1786 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/r300 +++ b/drivers/gpu/drm/radeon/reg_srcs/r300 @@ -683,9 +683,7 @@ r300 0x4f60 0x4DF4 US_ALU_CONST_G_31 0x4DF8 US_ALU_CONST_B_31 0x4DFC US_ALU_CONST_A_31 -0x4E04 RB3D_BLENDCNTL_R3 0x4E08 RB3D_ABLENDCNTL_R3 -0x4E0C RB3D_COLOR_CHANNEL_MASK 0x4E10 RB3D_CONSTANT_COLOR 0x4E14 RB3D_COLOR_CLEAR_VALUE 0x4E18 RB3D_ROPCNTL_R3 @@ -706,13 +704,11 @@ r300 0x4f60 0x4E74 RB3D_CMASK_WRINDEX 0x4E78 RB3D_CMASK_DWORD 0x4E7C RB3D_CMASK_RDINDEX -0x4E80 RB3D_AARESOLVE_OFFSET -0x4E84 RB3D_AARESOLVE_PITCH -0x4E88 RB3D_AARESOLVE_CTL 0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD 0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD 0x4F04 ZB_ZSTENCILCNTL 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT +0x4F28 ZB_DEPTHCLEARVALUE 0x4F58 ZB_ZPASS_DATA diff --git a/drivers/gpu/drm/radeon/reg_srcs/r420 b/drivers/gpu/drm/radeon/reg_srcs/r420 index 8c1214c..722074e 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/r420 +++ b/drivers/gpu/drm/radeon/reg_srcs/r420 @@ -130,7 +130,6 @@ r420 0x4f60 0x401C GB_SELECT 0x4020 GB_AA_CONFIG 0x4024 GB_FIFO_SIZE -0x4028 GB_Z_PEQ_CONFIG 0x4100 TX_INVALTAGS 0x4200 GA_POINT_S0 0x4204 GA_POINT_T0 @@ -750,9 +749,7 @@ r420 0x4f60 0x4DF4 US_ALU_CONST_G_31 0x4DF8 US_ALU_CONST_B_31 0x4DFC US_ALU_CONST_A_31 -0x4E04 RB3D_BLENDCNTL_R3 0x4E08 RB3D_ABLENDCNTL_R3 -0x4E0C RB3D_COLOR_CHANNEL_MASK 0x4E10 RB3D_CONSTANT_COLOR 0x4E14 RB3D_COLOR_CLEAR_VALUE 0x4E18 RB3D_ROPCNTL_R3 @@ -773,13 +770,11 @@ r420 0x4f60 0x4E74 RB3D_CMASK_WRINDEX 0x4E78 RB3D_CMASK_DWORD 0x4E7C RB3D_CMASK_RDINDEX -0x4E80 RB3D_AARESOLVE_OFFSET -0x4E84 RB3D_AARESOLVE_PITCH -0x4E88 RB3D_AARESOLVE_CTL 0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD 0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD 0x4F04 ZB_ZSTENCILCNTL 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT +0x4F28 ZB_DEPTHCLEARVALUE 0x4F58 ZB_ZPASS_DATA diff --git a/drivers/gpu/drm/radeon/reg_srcs/rs600 b/drivers/gpu/drm/radeon/reg_srcs/rs600 index 0828d80..d9f6286 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/rs600 +++ b/drivers/gpu/drm/radeon/reg_srcs/rs600 @@ -749,9 +749,7 @@ rs600 0x6d40 0x4DF4 US_ALU_CONST_G_31 0x4DF8 US_ALU_CONST_B_31 0x4DFC US_ALU_CONST_A_31 -0x4E04 RB3D_BLENDCNTL_R3 0x4E08 RB3D_ABLENDCNTL_R3 -0x4E0C RB3D_COLOR_CHANNEL_MASK 0x4E10 RB3D_CONSTANT_COLOR 0x4E14 RB3D_COLOR_CLEAR_VALUE 0x4E18 RB3D_ROPCNTL_R3 @@ -772,13 +770,11 @@ rs600 0x6d40 0x4E74 RB3D_CMASK_WRINDEX 0x4E78 RB3D_CMASK_DWORD 0x4E7C RB3D_CMASK_RDINDEX -0x4E80 RB3D_AARESOLVE_OFFSET -0x4E84 RB3D_AARESOLVE_PITCH -0x4E88 RB3D_AARESOLVE_CTL 0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD 0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD 0x4F04 ZB_ZSTENCILCNTL 0x4F08 ZB_STENCILREFMASK 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT +0x4F28 ZB_DEPTHCLEARVALUE 0x4F58 ZB_ZPASS_DATA diff --git a/drivers/gpu/drm/radeon/reg_srcs/rv515 b/drivers/gpu/drm/radeon/reg_srcs/rv515 index ef422bb..911a8fb 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/rv515 +++ b/drivers/gpu/drm/radeon/reg_srcs/rv515 @@ -164,7 +164,6 @@ rv515 0x6d40 0x401C GB_SELECT 0x4020 GB_AA_CONFIG 0x4024 GB_FIFO_SIZE -0x4028 GB_Z_PEQ_CONFIG 0x4100 TX_INVALTAGS 0x4114 SU_TEX_WRAP_PS3 0x4118 PS3_ENABLE @@ -461,9 +460,7 @@ rv515 0x6d40 0x4DF4 US_ALU_CONST_G_31 0x4DF8 US_ALU_CONST_B_31 0x4DFC US_ALU_CONST_A_31 -0x4E04 RB3D_BLENDCNTL_R3 0x4E08 RB3D_ABLENDCNTL_R3 -0x4E0C RB3D_COLOR_CHANNEL_MASK 0x4E10 RB3D_CONSTANT_COLOR 0x4E14 RB3D_COLOR_CLEAR_VALUE 0x4E18 RB3D_ROPCNTL_R3 @@ -484,9 +481,6 @@ rv515 0x6d40 0x4E74 RB3D_CMASK_WRINDEX 0x4E78 RB3D_CMASK_DWORD 0x4E7C RB3D_CMASK_RDINDEX -0x4E80 RB3D_AARESOLVE_OFFSET -0x4E84 RB3D_AARESOLVE_PITCH -0x4E88 RB3D_AARESOLVE_CTL 0x4EA0 RB3D_DISCARD_SRC_PIXEL_LTE_THRESHOLD 0x4EA4 RB3D_DISCARD_SRC_PIXEL_GTE_THRESHOLD 0x4EF8 RB3D_CONSTANT_COLOR_AR @@ -496,4 +490,5 @@ rv515 0x6d40 0x4F14 ZB_ZTOP 0x4F18 ZB_ZCACHE_CTLSTAT 0x4F58 ZB_ZPASS_DATA +0x4F28 ZB_DEPTHCLEARVALUE 0x4FD4 ZB_STENCILREFMASK_BF diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 5afe294..8af4679 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -751,7 +751,6 @@ void rs600_mc_init(struct radeon_device *rdev) rdev->mc.real_vram_size = RREG32(RADEON_CONFIG_MEMSIZE); rdev->mc.mc_vram_size = rdev->mc.real_vram_size; rdev->mc.visible_vram_size = rdev->mc.aper_size; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); base = RREG32_MC(R_000004_MC_FB_LOCATION); base = G_000004_MC_FB_START(base) << 16; diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c index 0137d3e..66c949b 100644 --- a/drivers/gpu/drm/radeon/rs690.c +++ b/drivers/gpu/drm/radeon/rs690.c @@ -77,9 +77,9 @@ void rs690_pm_info(struct radeon_device *rdev) switch (crev) { case 1: tmp.full = dfixed_const(100); - rdev->pm.igp_sideport_mclk.full = dfixed_const(info->info.ulBootUpMemoryClock); + rdev->pm.igp_sideport_mclk.full = dfixed_const(le32_to_cpu(info->info.ulBootUpMemoryClock)); rdev->pm.igp_sideport_mclk.full = dfixed_div(rdev->pm.igp_sideport_mclk, tmp); - if (info->info.usK8MemoryClock) + if (le16_to_cpu(info->info.usK8MemoryClock)) rdev->pm.igp_system_mclk.full = dfixed_const(le16_to_cpu(info->info.usK8MemoryClock)); else if (rdev->clock.default_mclk) { rdev->pm.igp_system_mclk.full = dfixed_const(rdev->clock.default_mclk); @@ -91,16 +91,16 @@ void rs690_pm_info(struct radeon_device *rdev) break; case 2: tmp.full = dfixed_const(100); - rdev->pm.igp_sideport_mclk.full = dfixed_const(info->info_v2.ulBootUpSidePortClock); + rdev->pm.igp_sideport_mclk.full = dfixed_const(le32_to_cpu(info->info_v2.ulBootUpSidePortClock)); rdev->pm.igp_sideport_mclk.full = dfixed_div(rdev->pm.igp_sideport_mclk, tmp); - if (info->info_v2.ulBootUpUMAClock) - rdev->pm.igp_system_mclk.full = dfixed_const(info->info_v2.ulBootUpUMAClock); + if (le32_to_cpu(info->info_v2.ulBootUpUMAClock)) + rdev->pm.igp_system_mclk.full = dfixed_const(le32_to_cpu(info->info_v2.ulBootUpUMAClock)); else if (rdev->clock.default_mclk) rdev->pm.igp_system_mclk.full = dfixed_const(rdev->clock.default_mclk); else rdev->pm.igp_system_mclk.full = dfixed_const(66700); rdev->pm.igp_system_mclk.full = dfixed_div(rdev->pm.igp_system_mclk, tmp); - rdev->pm.igp_ht_link_clk.full = dfixed_const(info->info_v2.ulHTLinkFreq); + rdev->pm.igp_ht_link_clk.full = dfixed_const(le32_to_cpu(info->info_v2.ulHTLinkFreq)); rdev->pm.igp_ht_link_clk.full = dfixed_div(rdev->pm.igp_ht_link_clk, tmp); rdev->pm.igp_ht_link_width.full = dfixed_const(le16_to_cpu(info->info_v2.usMinHTLinkWidth)); break; @@ -157,7 +157,6 @@ void rs690_mc_init(struct radeon_device *rdev) rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); rdev->mc.visible_vram_size = rdev->mc.aper_size; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; base = RREG32_MC(R_000100_MCCFG_FB_LOCATION); base = G_000100_MC_FB_START(base) << 16; rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev); diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index 491dc90..714ad45 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -78,18 +78,23 @@ u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base) } /* get temperature in millidegrees */ -u32 rv770_get_temp(struct radeon_device *rdev) +int rv770_get_temp(struct radeon_device *rdev) { u32 temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >> ASIC_T_SHIFT; - u32 actual_temp = 0; - - if ((temp >> 9) & 1) - actual_temp = 0; - else - actual_temp = (temp >> 1) & 0xff; - - return actual_temp * 1000; + int actual_temp; + + if (temp & 0x400) + actual_temp = -256; + else if (temp & 0x200) + actual_temp = 255; + else if (temp & 0x100) { + actual_temp = temp & 0x1ff; + actual_temp |= ~0x1ff; + } else + actual_temp = temp & 0xff; + + return (actual_temp * 1000) / 2; } void rv770_pm_misc(struct radeon_device *rdev) @@ -302,7 +307,7 @@ static void rv770_mc_program(struct radeon_device *rdev) */ void r700_cp_stop(struct radeon_device *rdev) { - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; + radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); WREG32(CP_ME_CNTL, (CP_ME_HALT | CP_PFP_HALT)); WREG32(SCRATCH_UMSK, 0); } @@ -316,7 +321,11 @@ static int rv770_cp_load_microcode(struct radeon_device *rdev) return -EINVAL; r700_cp_stop(rdev); - WREG32(CP_RB_CNTL, RB_NO_UPDATE | (15 << 8) | (3 << 0)); + WREG32(CP_RB_CNTL, +#ifdef __BIG_ENDIAN + BUF_SWAP_32BIT | +#endif + RB_NO_UPDATE | RB_BLKSZ(15) | RB_BUFSZ(3)); /* Reset cp */ WREG32(GRBM_SOFT_RESET, SOFT_RESET_CP); @@ -1114,7 +1123,6 @@ int rv770_mc_init(struct radeon_device *rdev) rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE); rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE); rdev->mc.visible_vram_size = rdev->mc.aper_size; - rdev->mc.active_vram_size = rdev->mc.visible_vram_size; r700_vram_gtt_location(rdev, &rdev->mc); radeon_update_bandwidth_info(rdev); diff --git a/drivers/gpu/drm/radeon/rv770d.h b/drivers/gpu/drm/radeon/rv770d.h index abc8cf5..79fa588 100644 --- a/drivers/gpu/drm/radeon/rv770d.h +++ b/drivers/gpu/drm/radeon/rv770d.h @@ -76,10 +76,10 @@ #define ROQ_IB1_START(x) ((x) << 0) #define ROQ_IB2_START(x) ((x) << 8) #define CP_RB_CNTL 0xC104 -#define RB_BUFSZ(x) ((x)<<0) -#define RB_BLKSZ(x) ((x)<<8) -#define RB_NO_UPDATE (1<<27) -#define RB_RPTR_WR_ENA (1<<31) +#define RB_BUFSZ(x) ((x) << 0) +#define RB_BLKSZ(x) ((x) << 8) +#define RB_NO_UPDATE (1 << 27) +#define RB_RPTR_WR_ENA (1 << 31) #define BUF_SWAP_32BIT (2 << 16) #define CP_RB_RPTR 0x8700 #define CP_RB_RPTR_ADDR 0xC10C diff --git a/drivers/gpu/stub/Kconfig b/drivers/gpu/stub/Kconfig index 09aea5f..70e60a4 100644 --- a/drivers/gpu/stub/Kconfig +++ b/drivers/gpu/stub/Kconfig @@ -1,11 +1,13 @@ config STUB_POULSBO tristate "Intel GMA500 Stub Driver" depends on PCI + depends on NET # for THERMAL # Poulsbo stub depends on ACPI_VIDEO when ACPI is enabled # but for select to work, need to select ACPI_VIDEO's dependencies, ick select BACKLIGHT_CLASS_DEVICE if ACPI select INPUT if ACPI select ACPI_VIDEO if ACPI + select THERMAL if ACPI help Choose this option if you have a system that has Intel GMA500 (Poulsbo) integrated graphics. If M is selected, the module will diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 773e484..297bc9a 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -238,13 +238,13 @@ config SENSORS_K8TEMP will be called k8temp. config SENSORS_K10TEMP - tristate "AMD Phenom/Sempron/Turion/Opteron temperature sensor" + tristate "AMD Family 10h/11h/12h/14h temperature sensor" depends on X86 && PCI help If you say yes here you get support for the temperature sensor(s) inside your CPU. Supported are later revisions of - the AMD Family 10h and all revisions of the AMD Family 11h - microarchitectures. + the AMD Family 10h and all revisions of the AMD Family 11h, + 12h (Llano), and 14h (Brazos) microarchitectures. This driver can also be built as a module. If so, the module will be called k10temp. @@ -455,13 +455,14 @@ config SENSORS_JZ4740 called jz4740-hwmon. config SENSORS_JC42 - tristate "JEDEC JC42.4 compliant temperature sensors" + tristate "JEDEC JC42.4 compliant memory module temperature sensors" depends on I2C help - If you say yes here you get support for Jedec JC42.4 compliant - temperature sensors. Support will include, but not be limited to, - ADT7408, CAT34TS02,, CAT6095, MAX6604, MCP9805, MCP98242, MCP98243, - MCP9843, SE97, SE98, STTS424, TSE2002B3, and TS3000B3. + If you say yes here, you get support for JEDEC JC42.4 compliant + temperature sensors, which are used on many DDR3 memory modules for + mobile devices and servers. Support will include, but not be limited + to, ADT7408, CAT34TS02, CAT6095, MAX6604, MCP9805, MCP98242, MCP98243, + MCP9843, SE97, SE98, STTS424(E), TSE2002B3, and TS3000B3. This driver can also be built as a module. If so, the module will be called jc42. @@ -574,7 +575,7 @@ config SENSORS_LM85 help If you say yes here you get support for National Semiconductor LM85 sensor chips and clones: ADM1027, ADT7463, ADT7468, EMC6D100, - EMC6D101 and EMC6D102. + EMC6D101, EMC6D102, and EMC6D103. This driver can also be built as a module. If so, the module will be called lm85. diff --git a/drivers/hwmon/ad7414.c b/drivers/hwmon/ad7414.c index 86d822a..d46c0c7 100644 --- a/drivers/hwmon/ad7414.c +++ b/drivers/hwmon/ad7414.c @@ -242,6 +242,7 @@ static const struct i2c_device_id ad7414_id[] = { { "ad7414", 0 }, {} }; +MODULE_DEVICE_TABLE(i2c, ad7414_id); static struct i2c_driver ad7414_driver = { .driver = { diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c index f13c843..5cc3e37 100644 --- a/drivers/hwmon/adt7411.c +++ b/drivers/hwmon/adt7411.c @@ -334,6 +334,7 @@ static const struct i2c_device_id adt7411_id[] = { { "adt7411", 0 }, { } }; +MODULE_DEVICE_TABLE(i2c, adt7411_id); static struct i2c_driver adt7411_driver = { .driver = { diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c index 5dea9fa..cd2a6e4 100644 --- a/drivers/hwmon/emc1403.c +++ b/drivers/hwmon/emc1403.c @@ -344,7 +344,7 @@ static int emc1403_remove(struct i2c_client *client) } static const unsigned short emc1403_address_list[] = { - 0x18, 0x2a, 0x4c, 0x4d, I2C_CLIENT_END + 0x18, 0x29, 0x4c, 0x4d, I2C_CLIENT_END }; static const struct i2c_device_id emc1403_idtable[] = { diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c index 3f49dd3..6e06019 100644 --- a/drivers/hwmon/f71882fg.c +++ b/drivers/hwmon/f71882fg.c @@ -37,7 +37,7 @@ #define SIO_F71858FG_LD_HWM 0x02 /* Hardware monitor logical device */ #define SIO_F71882FG_LD_HWM 0x04 /* Hardware monitor logical device */ #define SIO_UNLOCK_KEY 0x87 /* Key to enable Super-I/O */ -#define SIO_LOCK_KEY 0xAA /* Key to diasble Super-I/O */ +#define SIO_LOCK_KEY 0xAA /* Key to disable Super-I/O */ #define SIO_REG_LDSEL 0x07 /* Logical device select */ #define SIO_REG_DEVID 0x20 /* Device ID (2 bytes) */ @@ -2111,7 +2111,6 @@ static int f71882fg_remove(struct platform_device *pdev) int nr_fans = (data->type == f71882fg) ? 4 : 3; u8 start_reg = f71882fg_read8(data, F71882FG_REG_START); - platform_set_drvdata(pdev, NULL); if (data->hwmon_dev) hwmon_device_unregister(data->hwmon_dev); @@ -2178,6 +2177,7 @@ static int f71882fg_remove(struct platform_device *pdev) } } + platform_set_drvdata(pdev, NULL); kfree(data); return 0; diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c index 340fc78..9349912 100644 --- a/drivers/hwmon/jc42.c +++ b/drivers/hwmon/jc42.c @@ -53,6 +53,8 @@ static const unsigned short normal_i2c[] = { /* Configuration register defines */ #define JC42_CFG_CRIT_ONLY (1 << 2) +#define JC42_CFG_TCRIT_LOCK (1 << 6) +#define JC42_CFG_EVENT_LOCK (1 << 7) #define JC42_CFG_SHUTDOWN (1 << 8) #define JC42_CFG_HYST_SHIFT 9 #define JC42_CFG_HYST_MASK 0x03 @@ -332,7 +334,7 @@ static ssize_t set_temp_crit_hyst(struct device *dev, { struct i2c_client *client = to_i2c_client(dev); struct jc42_data *data = i2c_get_clientdata(client); - long val; + unsigned long val; int diff, hyst; int err; int ret = count; @@ -380,14 +382,14 @@ static ssize_t show_alarm(struct device *dev, static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp_input, NULL); -static DEVICE_ATTR(temp1_crit, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, set_temp_crit); -static DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(temp1_min, S_IRUGO, show_temp_min, set_temp_min); -static DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(temp1_max, S_IRUGO, show_temp_max, set_temp_max); -static DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit_hyst, set_temp_crit_hyst); static DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_temp_max_hyst, NULL); @@ -412,8 +414,31 @@ static struct attribute *jc42_attributes[] = { NULL }; +static mode_t jc42_attribute_mode(struct kobject *kobj, + struct attribute *attr, int index) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct i2c_client *client = to_i2c_client(dev); + struct jc42_data *data = i2c_get_clientdata(client); + unsigned int config = data->config; + bool readonly; + + if (attr == &dev_attr_temp1_crit.attr) + readonly = config & JC42_CFG_TCRIT_LOCK; + else if (attr == &dev_attr_temp1_min.attr || + attr == &dev_attr_temp1_max.attr) + readonly = config & JC42_CFG_EVENT_LOCK; + else if (attr == &dev_attr_temp1_crit_hyst.attr) + readonly = config & (JC42_CFG_EVENT_LOCK | JC42_CFG_TCRIT_LOCK); + else + readonly = true; + + return S_IRUGO | (readonly ? 0 : S_IWUSR); +} + static const struct attribute_group jc42_group = { .attrs = jc42_attributes, + .is_visible = jc42_attribute_mode, }; /* Return 0 if detection is successful, -ENODEV otherwise */ diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index da5a240..82bf65a 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -1,5 +1,5 @@ /* - * k10temp.c - AMD Family 10h/11h processor hardware monitoring + * k10temp.c - AMD Family 10h/11h/12h/14h processor hardware monitoring * * Copyright (c) 2009 Clemens Ladisch <clemens@ladisch.de> * @@ -25,7 +25,7 @@ #include <linux/pci.h> #include <asm/processor.h> -MODULE_DESCRIPTION("AMD Family 10h/11h CPU core temperature monitor"); +MODULE_DESCRIPTION("AMD Family 10h/11h/12h/14h CPU core temperature monitor"); MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>"); MODULE_LICENSE("GPL"); @@ -208,6 +208,7 @@ static void __devexit k10temp_remove(struct pci_dev *pdev) static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; MODULE_DEVICE_TABLE(pci, k10temp_id_table); diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c index 776aeb3..508cb29 100644 --- a/drivers/hwmon/lm63.c +++ b/drivers/hwmon/lm63.c @@ -98,6 +98,9 @@ static const unsigned short normal_i2c[] = { 0x18, 0x4c, 0x4e, I2C_CLIENT_END }; * value, it uses signed 8-bit values with LSB = 1 degree Celsius. * For remote temperature, low and high limits, it uses signed 11-bit values * with LSB = 0.125 degree Celsius, left-justified in 16-bit registers. + * For LM64 the actual remote diode temperature is 16 degree Celsius higher + * than the register reading. Remote temperature setpoints have to be + * adapted accordingly. */ #define FAN_FROM_REG(reg) ((reg) == 0xFFFC || (reg) == 0 ? 0 : \ @@ -165,6 +168,8 @@ struct lm63_data { struct mutex update_lock; char valid; /* zero until following fields are valid */ unsigned long last_updated; /* in jiffies */ + int kind; + int temp2_offset; /* registers values */ u8 config, config_fan; @@ -247,16 +252,34 @@ static ssize_t show_pwm1_enable(struct device *dev, struct device_attribute *dum return sprintf(buf, "%d\n", data->config_fan & 0x20 ? 1 : 2); } -static ssize_t show_temp8(struct device *dev, struct device_attribute *devattr, - char *buf) +/* + * There are 8bit registers for both local(temp1) and remote(temp2) sensor. + * For remote sensor registers temp2_offset has to be considered, + * for local sensor it must not. + * So we need separate 8bit accessors for local and remote sensor. + */ +static ssize_t show_local_temp8(struct device *dev, + struct device_attribute *devattr, + char *buf) { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct lm63_data *data = lm63_update_device(dev); return sprintf(buf, "%d\n", TEMP8_FROM_REG(data->temp8[attr->index])); } -static ssize_t set_temp8(struct device *dev, struct device_attribute *dummy, - const char *buf, size_t count) +static ssize_t show_remote_temp8(struct device *dev, + struct device_attribute *devattr, + char *buf) +{ + struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); + struct lm63_data *data = lm63_update_device(dev); + return sprintf(buf, "%d\n", TEMP8_FROM_REG(data->temp8[attr->index]) + + data->temp2_offset); +} + +static ssize_t set_local_temp8(struct device *dev, + struct device_attribute *dummy, + const char *buf, size_t count) { struct i2c_client *client = to_i2c_client(dev); struct lm63_data *data = i2c_get_clientdata(client); @@ -274,7 +297,8 @@ static ssize_t show_temp11(struct device *dev, struct device_attribute *devattr, { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct lm63_data *data = lm63_update_device(dev); - return sprintf(buf, "%d\n", TEMP11_FROM_REG(data->temp11[attr->index])); + return sprintf(buf, "%d\n", TEMP11_FROM_REG(data->temp11[attr->index]) + + data->temp2_offset); } static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr, @@ -294,7 +318,7 @@ static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr, int nr = attr->index; mutex_lock(&data->update_lock); - data->temp11[nr] = TEMP11_TO_REG(val); + data->temp11[nr] = TEMP11_TO_REG(val - data->temp2_offset); i2c_smbus_write_byte_data(client, reg[(nr - 1) * 2], data->temp11[nr] >> 8); i2c_smbus_write_byte_data(client, reg[(nr - 1) * 2 + 1], @@ -310,6 +334,7 @@ static ssize_t show_temp2_crit_hyst(struct device *dev, struct device_attribute { struct lm63_data *data = lm63_update_device(dev); return sprintf(buf, "%d\n", TEMP8_FROM_REG(data->temp8[2]) + + data->temp2_offset - TEMP8_FROM_REG(data->temp2_crit_hyst)); } @@ -324,7 +349,7 @@ static ssize_t set_temp2_crit_hyst(struct device *dev, struct device_attribute * long hyst; mutex_lock(&data->update_lock); - hyst = TEMP8_FROM_REG(data->temp8[2]) - val; + hyst = TEMP8_FROM_REG(data->temp8[2]) + data->temp2_offset - val; i2c_smbus_write_byte_data(client, LM63_REG_REMOTE_TCRIT_HYST, HYST_TO_REG(hyst)); mutex_unlock(&data->update_lock); @@ -355,16 +380,21 @@ static SENSOR_DEVICE_ATTR(fan1_min, S_IWUSR | S_IRUGO, show_fan, static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm1, set_pwm1); static DEVICE_ATTR(pwm1_enable, S_IRUGO, show_pwm1_enable, NULL); -static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp8, NULL, 0); -static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp8, - set_temp8, 1); +static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_local_temp8, NULL, 0); +static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_local_temp8, + set_local_temp8, 1); static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, show_temp11, NULL, 0); static SENSOR_DEVICE_ATTR(temp2_min, S_IWUSR | S_IRUGO, show_temp11, set_temp11, 1); static SENSOR_DEVICE_ATTR(temp2_max, S_IWUSR | S_IRUGO, show_temp11, set_temp11, 2); -static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_temp8, NULL, 2); +/* + * On LM63, temp2_crit can be set only once, which should be job + * of the bootloader. + */ +static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_remote_temp8, + NULL, 2); static DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp2_crit_hyst, set_temp2_crit_hyst); @@ -479,7 +509,12 @@ static int lm63_probe(struct i2c_client *new_client, data->valid = 0; mutex_init(&data->update_lock); - /* Initialize the LM63 chip */ + /* Set the device type */ + data->kind = id->driver_data; + if (data->kind == lm64) + data->temp2_offset = 16000; + + /* Initialize chip */ lm63_init_client(new_client); /* Register sysfs hooks */ diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c index 1e22984..d2cc286 100644 --- a/drivers/hwmon/lm85.c +++ b/drivers/hwmon/lm85.c @@ -41,7 +41,7 @@ static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, I2C_CLIENT_END }; enum chips { any_chip, lm85b, lm85c, adm1027, adt7463, adt7468, - emc6d100, emc6d102 + emc6d100, emc6d102, emc6d103 }; /* The LM85 registers */ @@ -90,6 +90,9 @@ enum chips { #define LM85_VERSTEP_EMC6D100_A0 0x60 #define LM85_VERSTEP_EMC6D100_A1 0x61 #define LM85_VERSTEP_EMC6D102 0x65 +#define LM85_VERSTEP_EMC6D103_A0 0x68 +#define LM85_VERSTEP_EMC6D103_A1 0x69 +#define LM85_VERSTEP_EMC6D103S 0x6A /* Also known as EMC6D103:A2 */ #define LM85_REG_CONFIG 0x40 @@ -348,6 +351,7 @@ static const struct i2c_device_id lm85_id[] = { { "emc6d100", emc6d100 }, { "emc6d101", emc6d100 }, { "emc6d102", emc6d102 }, + { "emc6d103", emc6d103 }, { } }; MODULE_DEVICE_TABLE(i2c, lm85_id); @@ -1250,6 +1254,20 @@ static int lm85_detect(struct i2c_client *client, struct i2c_board_info *info) case LM85_VERSTEP_EMC6D102: type_name = "emc6d102"; break; + case LM85_VERSTEP_EMC6D103_A0: + case LM85_VERSTEP_EMC6D103_A1: + type_name = "emc6d103"; + break; + /* + * Registers apparently missing in EMC6D103S/EMC6D103:A2 + * compared to EMC6D103:A0, EMC6D103:A1, and EMC6D102 + * (according to the data sheets), but used unconditionally + * in the driver: 62[5:7], 6D[0:7], and 6E[0:7]. + * So skip EMC6D103S for now. + case LM85_VERSTEP_EMC6D103S: + type_name = "emc6d103s"; + break; + */ } } else { dev_dbg(&adapter->dev, @@ -1283,6 +1301,7 @@ static int lm85_probe(struct i2c_client *client, case adt7468: case emc6d100: case emc6d102: + case emc6d103: data->freq_map = adm1027_freq_map; break; default: @@ -1468,7 +1487,7 @@ static struct lm85_data *lm85_update_device(struct device *dev) /* More alarm bits */ data->alarms |= lm85_read_value(client, EMC6D100_REG_ALARM3) << 16; - } else if (data->type == emc6d102) { + } else if (data->type == emc6d102 || data->type == emc6d103) { /* Have to read LSB bits after the MSB ones because the reading of the MSB bits has frozen the LSBs (backward from the ADM1027). diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index 2e067dd..50ea1f4 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -29,6 +29,7 @@ #include <linux/pci.h> #include <linux/mutex.h> #include <linux/ktime.h> +#include <linux/slab.h> #define PCH_EVENT_SET 0 /* I2C Interrupt Event Set Status */ #define PCH_EVENT_NONE 1 /* I2C Interrupt Event Clear Status */ diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index ef3bcb1..61653f0 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -249,7 +249,7 @@ static struct i2c_adapter ocores_adapter = { static int ocores_i2c_of_probe(struct platform_device* pdev, struct ocores_i2c* i2c) { - __be32* val; + const __be32* val; val = of_get_property(pdev->dev.of_node, "regstep", NULL); if (!val) { diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index b605ff3..58a58c7 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -378,9 +378,7 @@ static int omap_i2c_init(struct omap_i2c_dev *dev) * REVISIT: Some wkup sources might not be needed. */ dev->westate = OMAP_I2C_WE_ALL; - if (dev->rev < OMAP_I2C_REV_ON_4430) - omap_i2c_write_reg(dev, OMAP_I2C_WE_REG, - dev->westate); + omap_i2c_write_reg(dev, OMAP_I2C_WE_REG, dev->westate); } } omap_i2c_write_reg(dev, OMAP_I2C_CON_REG, 0); @@ -847,11 +845,15 @@ complete: dev_err(dev->dev, "Arbitration lost\n"); err |= OMAP_I2C_STAT_AL; } + /* + * ProDB0017052: Clear ARDY bit twice + */ if (stat & (OMAP_I2C_STAT_ARDY | OMAP_I2C_STAT_NACK | OMAP_I2C_STAT_AL)) { omap_i2c_ack_stat(dev, stat & (OMAP_I2C_STAT_RRDY | OMAP_I2C_STAT_RDR | - OMAP_I2C_STAT_XRDY | OMAP_I2C_STAT_XDR)); + OMAP_I2C_STAT_XRDY | OMAP_I2C_STAT_XDR | + OMAP_I2C_STAT_ARDY)); omap_i2c_complete_cmd(dev, err); return IRQ_HANDLED; } @@ -1137,12 +1139,41 @@ omap_i2c_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_SUSPEND +static int omap_i2c_suspend(struct device *dev) +{ + if (!pm_runtime_suspended(dev)) + if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_suspend) + dev->bus->pm->runtime_suspend(dev); + + return 0; +} + +static int omap_i2c_resume(struct device *dev) +{ + if (!pm_runtime_suspended(dev)) + if (dev->bus && dev->bus->pm && dev->bus->pm->runtime_resume) + dev->bus->pm->runtime_resume(dev); + + return 0; +} + +static struct dev_pm_ops omap_i2c_pm_ops = { + .suspend = omap_i2c_suspend, + .resume = omap_i2c_resume, +}; +#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops) +#else +#define OMAP_I2C_PM_OPS NULL +#endif + static struct platform_driver omap_i2c_driver = { .probe = omap_i2c_probe, .remove = omap_i2c_remove, .driver = { .name = "omap_i2c", .owner = THIS_MODULE, + .pm = OMAP_I2C_PM_OPS, }, }; diff --git a/drivers/i2c/busses/i2c-stu300.c b/drivers/i2c/busses/i2c-stu300.c index 495be45..266135d 100644 --- a/drivers/i2c/busses/i2c-stu300.c +++ b/drivers/i2c/busses/i2c-stu300.c @@ -942,7 +942,7 @@ stu300_probe(struct platform_device *pdev) adap->owner = THIS_MODULE; /* DDC class but actually often used for more generic I2C */ adap->class = I2C_CLASS_DDC; - strncpy(adap->name, "ST Microelectronics DDC I2C adapter", + strlcpy(adap->name, "ST Microelectronics DDC I2C adapter", sizeof(adap->name)); adap->nr = bus_nr; adap->algo = &stu300_algo; diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 1fa091e..4a5c4a4 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -62,6 +62,7 @@ #include <linux/notifier.h> #include <linux/cpu.h> #include <asm/mwait.h> +#include <asm/msr.h> #define INTEL_IDLE_VERSION "0.4" #define PREFIX "intel_idle: " @@ -85,6 +86,12 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state); static struct cpuidle_state *cpuidle_state_table; /* + * Hardware C-state auto-demotion may not always be optimal. + * Indicate which enable bits to clear here. + */ +static unsigned long long auto_demotion_disable_flags; + +/* * Set this flag for states where the HW flushes the TLB for us * and so we don't need cross-calls to keep it consistent. * If this flag is set, SW flushes the TLB, so even if the @@ -281,6 +288,15 @@ static struct notifier_block setup_broadcast_notifier = { .notifier_call = setup_broadcast_cpuhp_notify, }; +static void auto_demotion_disable(void *dummy) +{ + unsigned long long msr_bits; + + rdmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits); + msr_bits &= ~auto_demotion_disable_flags; + wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits); +} + /* * intel_idle_probe() */ @@ -324,11 +340,17 @@ static int intel_idle_probe(void) case 0x25: /* Westmere */ case 0x2C: /* Westmere */ cpuidle_state_table = nehalem_cstates; + auto_demotion_disable_flags = + (NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE); break; case 0x1C: /* 28 - Atom Processor */ + cpuidle_state_table = atom_cstates; + break; + case 0x26: /* 38 - Lincroft Atom Processor */ cpuidle_state_table = atom_cstates; + auto_demotion_disable_flags = ATM_LNC_C6_AUTO_DEMOTE; break; case 0x2A: /* SNB */ @@ -436,6 +458,8 @@ static int intel_idle_cpuidle_devices_init(void) return -EIO; } } + if (auto_demotion_disable_flags) + smp_call_function(auto_demotion_disable, NULL, 1); return 0; } diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index e38be1bc..fbbfa24 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1079,7 +1079,7 @@ static void ib_sa_remove_one(struct ib_device *device) ib_unregister_event_handler(&sa_dev->event_handler); - flush_scheduled_work(); + flush_workqueue(ib_wq); for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) { if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) { diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ca12acf..ec1e9da 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -636,6 +636,16 @@ static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp, } } +static void ucma_copy_iw_route(struct rdma_ucm_query_route_resp *resp, + struct rdma_route *route) +{ + struct rdma_dev_addr *dev_addr; + + dev_addr = &route->addr.dev_addr; + rdma_addr_get_dgid(dev_addr, (union ib_gid *) &resp->ib_route[0].dgid); + rdma_addr_get_sgid(dev_addr, (union ib_gid *) &resp->ib_route[0].sgid); +} + static ssize_t ucma_query_route(struct ucma_file *file, const char __user *inbuf, int in_len, int out_len) @@ -670,8 +680,10 @@ static ssize_t ucma_query_route(struct ucma_file *file, resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid; resp.port_num = ctx->cm_id->port_num; - if (rdma_node_get_transport(ctx->cm_id->device->node_type) == RDMA_TRANSPORT_IB) { - switch (rdma_port_get_link_layer(ctx->cm_id->device, ctx->cm_id->port_num)) { + switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) { + case RDMA_TRANSPORT_IB: + switch (rdma_port_get_link_layer(ctx->cm_id->device, + ctx->cm_id->port_num)) { case IB_LINK_LAYER_INFINIBAND: ucma_copy_ib_route(&resp, &ctx->cm_id->route); break; @@ -681,6 +693,12 @@ static ssize_t ucma_query_route(struct ucma_file *file, default: break; } + break; + case RDMA_TRANSPORT_IWARP: + ucma_copy_iw_route(&resp, &ctx->cm_id->route); + break; + default: + break; } out: diff --git a/drivers/infiniband/hw/amso1100/c2_vq.c b/drivers/infiniband/hw/amso1100/c2_vq.c index 9ce7819b..2ec716f 100644 --- a/drivers/infiniband/hw/amso1100/c2_vq.c +++ b/drivers/infiniband/hw/amso1100/c2_vq.c @@ -107,7 +107,7 @@ struct c2_vq_req *vq_req_alloc(struct c2_dev *c2dev) r = kmalloc(sizeof(struct c2_vq_req), GFP_KERNEL); if (r) { init_waitqueue_head(&r->wait_object); - r->reply_msg = (u64) NULL; + r->reply_msg = 0; r->event = 0; r->cm_id = NULL; r->qp = NULL; @@ -123,7 +123,7 @@ struct c2_vq_req *vq_req_alloc(struct c2_dev *c2dev) */ void vq_req_free(struct c2_dev *c2dev, struct c2_vq_req *r) { - r->reply_msg = (u64) NULL; + r->reply_msg = 0; if (atomic_dec_and_test(&r->refcnt)) { kfree(r); } @@ -151,7 +151,7 @@ void vq_req_get(struct c2_dev *c2dev, struct c2_vq_req *r) void vq_req_put(struct c2_dev *c2dev, struct c2_vq_req *r) { if (atomic_dec_and_test(&r->refcnt)) { - if (r->reply_msg != (u64) NULL) + if (r->reply_msg != 0) vq_repbuf_free(c2dev, (void *) (unsigned long) r->reply_msg); kfree(r); diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 0dc62b1..8b00e6c 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -380,7 +380,7 @@ static void send_flowc(struct c4iw_ep *ep, struct sk_buff *skb) 16)) | FW_WR_FLOWID(ep->hwtid)); flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN; - flowc->mnemval[0].val = cpu_to_be32(0); + flowc->mnemval[0].val = cpu_to_be32(PCI_FUNC(ep->com.dev->rdev.lldi.pdev->devfn) << 8); flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH; flowc->mnemval[1].val = cpu_to_be32(ep->tx_chan); flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT; diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 2080090..4f0be25 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -220,7 +220,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, V_FW_RI_RES_WR_DCAEN(0) | V_FW_RI_RES_WR_DCACPU(0) | V_FW_RI_RES_WR_FBMIN(2) | - V_FW_RI_RES_WR_FBMAX(3) | + V_FW_RI_RES_WR_FBMAX(2) | V_FW_RI_RES_WR_CIDXFTHRESHO(0) | V_FW_RI_RES_WR_CIDXFTHRESH(0) | V_FW_RI_RES_WR_EQSIZE(eqsize)); @@ -243,7 +243,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, V_FW_RI_RES_WR_DCAEN(0) | V_FW_RI_RES_WR_DCACPU(0) | V_FW_RI_RES_WR_FBMIN(2) | - V_FW_RI_RES_WR_FBMAX(3) | + V_FW_RI_RES_WR_FBMAX(2) | V_FW_RI_RES_WR_CIDXFTHRESHO(0) | V_FW_RI_RES_WR_CIDXFTHRESH(0) | V_FW_RI_RES_WR_EQSIZE(eqsize)); diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c index 8b606fd..08c1948 100644 --- a/drivers/infiniband/hw/nes/nes_hw.c +++ b/drivers/infiniband/hw/nes/nes_hw.c @@ -2610,9 +2610,11 @@ static void nes_process_mac_intr(struct nes_device *nesdev, u32 mac_number) netif_carrier_on(nesvnic->netdev); spin_lock(&nesvnic->port_ibevent_lock); - if (nesdev->iw_status == 0) { - nesdev->iw_status = 1; - nes_port_ibevent(nesvnic); + if (nesvnic->of_device_registered) { + if (nesdev->iw_status == 0) { + nesdev->iw_status = 1; + nes_port_ibevent(nesvnic); + } } spin_unlock(&nesvnic->port_ibevent_lock); } @@ -2642,9 +2644,11 @@ static void nes_process_mac_intr(struct nes_device *nesdev, u32 mac_number) netif_carrier_off(nesvnic->netdev); spin_lock(&nesvnic->port_ibevent_lock); - if (nesdev->iw_status == 1) { - nesdev->iw_status = 0; - nes_port_ibevent(nesvnic); + if (nesvnic->of_device_registered) { + if (nesdev->iw_status == 1) { + nesdev->iw_status = 0; + nes_port_ibevent(nesvnic); + } } spin_unlock(&nesvnic->port_ibevent_lock); } @@ -2703,9 +2707,11 @@ void nes_recheck_link_status(struct work_struct *work) netif_carrier_on(nesvnic->netdev); spin_lock(&nesvnic->port_ibevent_lock); - if (nesdev->iw_status == 0) { - nesdev->iw_status = 1; - nes_port_ibevent(nesvnic); + if (nesvnic->of_device_registered) { + if (nesdev->iw_status == 0) { + nesdev->iw_status = 1; + nes_port_ibevent(nesvnic); + } } spin_unlock(&nesvnic->port_ibevent_lock); } @@ -2723,9 +2729,11 @@ void nes_recheck_link_status(struct work_struct *work) netif_carrier_off(nesvnic->netdev); spin_lock(&nesvnic->port_ibevent_lock); - if (nesdev->iw_status == 1) { - nesdev->iw_status = 0; - nes_port_ibevent(nesvnic); + if (nesvnic->of_device_registered) { + if (nesdev->iw_status == 1) { + nesdev->iw_status = 0; + nes_port_ibevent(nesvnic); + } } spin_unlock(&nesvnic->port_ibevent_lock); } diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 50cceb3..b01809a 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -623,7 +623,6 @@ struct qib_chippport_specific { u8 ibmalfusesnap; struct qib_qsfp_data qsfp_data; char epmsgbuf[192]; /* for port error interrupt msg buffer */ - u8 bounced; }; static struct { @@ -1881,23 +1880,7 @@ static noinline void handle_7322_p_errors(struct qib_pportdata *ppd) IB_PHYSPORTSTATE_DISABLED) qib_set_ib_7322_lstate(ppd, 0, QLOGIC_IB_IBCC_LINKINITCMD_DISABLE); - else { - u32 lstate; - /* - * We need the current logical link state before - * lflags are set in handle_e_ibstatuschanged. - */ - lstate = qib_7322_iblink_state(ibcs); - - if (IS_QMH(dd) && !ppd->cpspec->bounced && - ltstate == IB_PHYSPORTSTATE_LINKUP && - (lstate >= IB_PORT_INIT && - lstate <= IB_PORT_ACTIVE)) { - ppd->cpspec->bounced = 1; - qib_7322_set_ib_cfg(ppd, QIB_IB_CFG_LSTATE, - IB_LINKCMD_DOWN | IB_LINKINITCMD_POLL); - } - + else /* * Since going into a recovery state causes the link * state to go down and since recovery is transitory, @@ -1911,7 +1894,6 @@ static noinline void handle_7322_p_errors(struct qib_pportdata *ppd) ltstate != IB_PHYSPORTSTATE_RECOVERY_WAITRMT && ltstate != IB_PHYSPORTSTATE_RECOVERY_IDLE) qib_handle_e_ibstatuschanged(ppd, ibcs); - } } if (*msg && iserr) qib_dev_porterr(dd, ppd->port, "%s error\n", msg); @@ -2381,6 +2363,11 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd) qib_write_kreg_port(ppd, krp_rcvctrl, ppd->p_rcvctrl); spin_unlock_irqrestore(&dd->cspec->rcvmod_lock, flags); + /* Hold the link state machine for mezz boards */ + if (IS_QMH(dd) || IS_QME(dd)) + qib_set_ib_7322_lstate(ppd, 0, + QLOGIC_IB_IBCC_LINKINITCMD_DISABLE); + /* Also enable IBSTATUSCHG interrupt. */ val = qib_read_kreg_port(ppd, krp_errmask); qib_write_kreg_port(ppd, krp_errmask, @@ -5702,6 +5689,11 @@ static void set_no_qsfp_atten(struct qib_devdata *dd, int change) ppd->cpspec->h1_val = h1; /* now change the IBC and serdes, overriding generic */ init_txdds_table(ppd, 1); + /* Re-enable the physical state machine on mezz boards + * now that the correct settings have been set. */ + if (IS_QMH(dd) || IS_QME(dd)) + qib_set_ib_7322_lstate(ppd, 0, + QLOGIC_IB_IBCC_LINKINITCMD_SLEEP); any++; } if (*nxt == '\n') diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c index 8245237..eca0c41 100644 --- a/drivers/infiniband/hw/qib/qib_rc.c +++ b/drivers/infiniband/hw/qib/qib_rc.c @@ -1005,7 +1005,8 @@ void qib_rc_send_complete(struct qib_qp *qp, struct qib_ib_header *hdr) * there are still requests that haven't been acked. */ if ((psn & IB_BTH_REQ_ACK) && qp->s_acked != qp->s_tail && - !(qp->s_flags & (QIB_S_TIMER | QIB_S_WAIT_RNR | QIB_S_WAIT_PSN))) + !(qp->s_flags & (QIB_S_TIMER | QIB_S_WAIT_RNR | QIB_S_WAIT_PSN)) && + (ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) start_timer(qp); while (qp->s_last != qp->s_acked) { @@ -1439,6 +1440,8 @@ static void qib_rc_rcv_resp(struct qib_ibport *ibp, } spin_lock_irqsave(&qp->s_lock, flags); + if (!(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) + goto ack_done; /* Ignore invalid responses. */ if (qib_cmp24(psn, qp->s_next_psn) >= 0) diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c index 23cf8fc..5b8f59d 100644 --- a/drivers/input/gameport/gameport.c +++ b/drivers/input/gameport/gameport.c @@ -360,7 +360,7 @@ static int gameport_queue_event(void *object, struct module *owner, event->owner = owner; list_add_tail(&event->node, &gameport_event_list); - schedule_work(&gameport_event_work); + queue_work(system_long_wq, &gameport_event_work); out: spin_unlock_irqrestore(&gameport_event_lock, flags); diff --git a/drivers/input/input.c b/drivers/input/input.c index 7985114..11905b6 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -75,7 +75,6 @@ static int input_defuzz_abs_event(int value, int old_val, int fuzz) * dev->event_lock held and interrupts disabled. */ static void input_pass_event(struct input_dev *dev, - struct input_handler *src_handler, unsigned int type, unsigned int code, int value) { struct input_handler *handler; @@ -94,15 +93,6 @@ static void input_pass_event(struct input_dev *dev, continue; handler = handle->handler; - - /* - * If this is the handler that injected this - * particular event we want to skip it to avoid - * filters firing again and again. - */ - if (handler == src_handler) - continue; - if (!handler->filter) { if (filtered) break; @@ -132,7 +122,7 @@ static void input_repeat_key(unsigned long data) if (test_bit(dev->repeat_key, dev->key) && is_event_supported(dev->repeat_key, dev->keybit, KEY_MAX)) { - input_pass_event(dev, NULL, EV_KEY, dev->repeat_key, 2); + input_pass_event(dev, EV_KEY, dev->repeat_key, 2); if (dev->sync) { /* @@ -141,7 +131,7 @@ static void input_repeat_key(unsigned long data) * Otherwise assume that the driver will send * SYN_REPORT once it's done. */ - input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1); + input_pass_event(dev, EV_SYN, SYN_REPORT, 1); } if (dev->rep[REP_PERIOD]) @@ -174,7 +164,6 @@ static void input_stop_autorepeat(struct input_dev *dev) #define INPUT_PASS_TO_ALL (INPUT_PASS_TO_HANDLERS | INPUT_PASS_TO_DEVICE) static int input_handle_abs_event(struct input_dev *dev, - struct input_handler *src_handler, unsigned int code, int *pval) { bool is_mt_event; @@ -218,15 +207,13 @@ static int input_handle_abs_event(struct input_dev *dev, /* Flush pending "slot" event */ if (is_mt_event && dev->slot != input_abs_get_val(dev, ABS_MT_SLOT)) { input_abs_set_val(dev, ABS_MT_SLOT, dev->slot); - input_pass_event(dev, src_handler, - EV_ABS, ABS_MT_SLOT, dev->slot); + input_pass_event(dev, EV_ABS, ABS_MT_SLOT, dev->slot); } return INPUT_PASS_TO_HANDLERS; } static void input_handle_event(struct input_dev *dev, - struct input_handler *src_handler, unsigned int type, unsigned int code, int value) { int disposition = INPUT_IGNORE_EVENT; @@ -279,8 +266,7 @@ static void input_handle_event(struct input_dev *dev, case EV_ABS: if (is_event_supported(code, dev->absbit, ABS_MAX)) - disposition = input_handle_abs_event(dev, src_handler, - code, &value); + disposition = input_handle_abs_event(dev, code, &value); break; @@ -338,7 +324,7 @@ static void input_handle_event(struct input_dev *dev, dev->event(dev, type, code, value); if (disposition & INPUT_PASS_TO_HANDLERS) - input_pass_event(dev, src_handler, type, code, value); + input_pass_event(dev, type, code, value); } /** @@ -367,7 +353,7 @@ void input_event(struct input_dev *dev, spin_lock_irqsave(&dev->event_lock, flags); add_input_randomness(type, code, value); - input_handle_event(dev, NULL, type, code, value); + input_handle_event(dev, type, code, value); spin_unlock_irqrestore(&dev->event_lock, flags); } } @@ -397,8 +383,7 @@ void input_inject_event(struct input_handle *handle, rcu_read_lock(); grab = rcu_dereference(dev->grab); if (!grab || grab == handle) - input_handle_event(dev, handle->handler, - type, code, value); + input_handle_event(dev, type, code, value); rcu_read_unlock(); spin_unlock_irqrestore(&dev->event_lock, flags); @@ -611,10 +596,10 @@ static void input_dev_release_keys(struct input_dev *dev) for (code = 0; code <= KEY_MAX; code++) { if (is_event_supported(code, dev->keybit, KEY_MAX) && __test_and_clear_bit(code, dev->key)) { - input_pass_event(dev, NULL, EV_KEY, code, 0); + input_pass_event(dev, EV_KEY, code, 0); } } - input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1); + input_pass_event(dev, EV_SYN, SYN_REPORT, 1); } } @@ -889,9 +874,9 @@ int input_set_keycode(struct input_dev *dev, !is_event_supported(old_keycode, dev->keybit, KEY_MAX) && __test_and_clear_bit(old_keycode, dev->key)) { - input_pass_event(dev, NULL, EV_KEY, old_keycode, 0); + input_pass_event(dev, EV_KEY, old_keycode, 0); if (dev->sync) - input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1); + input_pass_event(dev, EV_SYN, SYN_REPORT, 1); } out: diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c index ac471b7..99ce903 100644 --- a/drivers/input/keyboard/tegra-kbc.c +++ b/drivers/input/keyboard/tegra-kbc.c @@ -71,8 +71,9 @@ struct tegra_kbc { spinlock_t lock; unsigned int repoll_dly; unsigned long cp_dly_jiffies; + bool use_fn_map; const struct tegra_kbc_platform_data *pdata; - unsigned short keycode[KBC_MAX_KEY]; + unsigned short keycode[KBC_MAX_KEY * 2]; unsigned short current_keys[KBC_MAX_KPENT]; unsigned int num_pressed_keys; struct timer_list timer; @@ -178,6 +179,40 @@ static const u32 tegra_kbc_default_keymap[] = { KEY(15, 5, KEY_F2), KEY(15, 6, KEY_CAPSLOCK), KEY(15, 7, KEY_F6), + + /* Software Handled Function Keys */ + KEY(20, 0, KEY_KP7), + + KEY(21, 0, KEY_KP9), + KEY(21, 1, KEY_KP8), + KEY(21, 2, KEY_KP4), + KEY(21, 4, KEY_KP1), + + KEY(22, 1, KEY_KPSLASH), + KEY(22, 2, KEY_KP6), + KEY(22, 3, KEY_KP5), + KEY(22, 4, KEY_KP3), + KEY(22, 5, KEY_KP2), + KEY(22, 7, KEY_KP0), + + KEY(27, 1, KEY_KPASTERISK), + KEY(27, 3, KEY_KPMINUS), + KEY(27, 4, KEY_KPPLUS), + KEY(27, 5, KEY_KPDOT), + + KEY(28, 5, KEY_VOLUMEUP), + + KEY(29, 3, KEY_HOME), + KEY(29, 4, KEY_END), + KEY(29, 5, KEY_BRIGHTNESSDOWN), + KEY(29, 6, KEY_VOLUMEDOWN), + KEY(29, 7, KEY_BRIGHTNESSUP), + + KEY(30, 0, KEY_NUMLOCK), + KEY(30, 1, KEY_SCROLLLOCK), + KEY(30, 2, KEY_MUTE), + + KEY(31, 4, KEY_HELP), }; static const struct matrix_keymap_data tegra_kbc_default_keymap_data = { @@ -224,6 +259,7 @@ static void tegra_kbc_report_keys(struct tegra_kbc *kbc) unsigned int i; unsigned int num_down = 0; unsigned long flags; + bool fn_keypress = false; spin_lock_irqsave(&kbc->lock, flags); for (i = 0; i < KBC_MAX_KPENT; i++) { @@ -237,11 +273,28 @@ static void tegra_kbc_report_keys(struct tegra_kbc *kbc) MATRIX_SCAN_CODE(row, col, KBC_ROW_SHIFT); scancodes[num_down] = scancode; - keycodes[num_down++] = kbc->keycode[scancode]; + keycodes[num_down] = kbc->keycode[scancode]; + /* If driver uses Fn map, do not report the Fn key. */ + if ((keycodes[num_down] == KEY_FN) && kbc->use_fn_map) + fn_keypress = true; + else + num_down++; } val >>= 8; } + + /* + * If the platform uses Fn keymaps, translate keys on a Fn keypress. + * Function keycodes are KBC_MAX_KEY apart from the plain keycodes. + */ + if (fn_keypress) { + for (i = 0; i < num_down; i++) { + scancodes[i] += KBC_MAX_KEY; + keycodes[i] = kbc->keycode[scancodes[i]]; + } + } + spin_unlock_irqrestore(&kbc->lock, flags); tegra_kbc_report_released_keys(kbc->idev, @@ -594,8 +647,11 @@ static int __devinit tegra_kbc_probe(struct platform_device *pdev) input_dev->keycode = kbc->keycode; input_dev->keycodesize = sizeof(kbc->keycode[0]); - input_dev->keycodemax = ARRAY_SIZE(kbc->keycode); + input_dev->keycodemax = KBC_MAX_KEY; + if (pdata->use_fn_map) + input_dev->keycodemax *= 2; + kbc->use_fn_map = pdata->use_fn_map; keymap_data = pdata->keymap_data ?: &tegra_kbc_default_keymap_data; matrix_keypad_build_keymap(keymap_data, KBC_ROW_SHIFT, input_dev->keycode, input_dev->keybit); diff --git a/drivers/input/misc/ixp4xx-beeper.c b/drivers/input/misc/ixp4xx-beeper.c index 9dfd6e5..1f38302 100644 --- a/drivers/input/misc/ixp4xx-beeper.c +++ b/drivers/input/misc/ixp4xx-beeper.c @@ -69,11 +69,7 @@ static int ixp4xx_spkr_event(struct input_dev *dev, unsigned int type, unsigned } if (value > 20 && value < 32767) -#ifndef FREQ - count = (ixp4xx_get_board_tick_rate() / (value * 4)) - 1; -#else - count = (FREQ / (value * 4)) - 1; -#endif + count = (IXP4XX_TIMER_FREQ / (value * 4)) - 1; ixp4xx_spkr_control(pin, count); diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c index 1f8e010..7e64d01 100644 --- a/drivers/input/misc/rotary_encoder.c +++ b/drivers/input/misc/rotary_encoder.c @@ -176,7 +176,7 @@ static int __devinit rotary_encoder_probe(struct platform_device *pdev) /* request the IRQs */ err = request_irq(encoder->irq_a, &rotary_encoder_irq, - IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, DRV_NAME, encoder); if (err) { dev_err(&pdev->dev, "unable to request IRQ %d\n", @@ -185,7 +185,7 @@ static int __devinit rotary_encoder_probe(struct platform_device *pdev) } err = request_irq(encoder->irq_b, &rotary_encoder_irq, - IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE, + IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, DRV_NAME, encoder); if (err) { dev_err(&pdev->dev, "unable to request IRQ %d\n", diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index 25e5d04..7453938 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -51,6 +51,29 @@ #define SYN_EXT_CAP_REQUESTS(c) (((c) & 0x700000) >> 20) #define SYN_CAP_MULTI_BUTTON_NO(ec) (((ec) & 0x00f000) >> 12) #define SYN_CAP_PRODUCT_ID(ec) (((ec) & 0xff0000) >> 16) + +/* + * The following describes response for the 0x0c query. + * + * byte mask name meaning + * ---- ---- ------- ------------ + * 1 0x01 adjustable threshold capacitive button sensitivity + * can be adjusted + * 1 0x02 report max query 0x0d gives max coord reported + * 1 0x04 clearpad sensor is ClearPad product + * 1 0x08 advanced gesture not particularly meaningful + * 1 0x10 clickpad bit 0 1-button ClickPad + * 1 0x60 multifinger mode identifies firmware finger counting + * (not reporting!) algorithm. + * Not particularly meaningful + * 1 0x80 covered pad W clipped to 14, 15 == pad mostly covered + * 2 0x01 clickpad bit 1 2-button ClickPad + * 2 0x02 deluxe LED controls touchpad support LED commands + * ala multimedia control bar + * 2 0x04 reduced filtering firmware does less filtering on + * position data, driver should watch + * for noise. + */ #define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */ #define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */ #define SYN_CAP_MAX_DIMENSIONS(ex0c) ((ex0c) & 0x020000) diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c index db5b0bc..ba70058 100644 --- a/drivers/input/serio/serio.c +++ b/drivers/input/serio/serio.c @@ -188,7 +188,8 @@ static void serio_free_event(struct serio_event *event) kfree(event); } -static void serio_remove_duplicate_events(struct serio_event *event) +static void serio_remove_duplicate_events(void *object, + enum serio_event_type type) { struct serio_event *e, *next; unsigned long flags; @@ -196,13 +197,13 @@ static void serio_remove_duplicate_events(struct serio_event *event) spin_lock_irqsave(&serio_event_lock, flags); list_for_each_entry_safe(e, next, &serio_event_list, node) { - if (event->object == e->object) { + if (object == e->object) { /* * If this event is of different type we should not * look further - we only suppress duplicate events * that were sent back-to-back. */ - if (event->type != e->type) + if (type != e->type) break; list_del_init(&e->node); @@ -245,7 +246,7 @@ static void serio_handle_event(struct work_struct *work) break; } - serio_remove_duplicate_events(event); + serio_remove_duplicate_events(event->object, event->type); serio_free_event(event); } @@ -298,7 +299,7 @@ static int serio_queue_event(void *object, struct module *owner, event->owner = owner; list_add_tail(&event->node, &serio_event_list); - schedule_work(&serio_event_work); + queue_work(system_long_wq, &serio_event_work); out: spin_unlock_irqrestore(&serio_event_lock, flags); @@ -436,10 +437,12 @@ static ssize_t serio_rebind_driver(struct device *dev, struct device_attribute * } else if (!strncmp(buf, "rescan", count)) { serio_disconnect_port(serio); serio_find_driver(serio); + serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT); } else if ((drv = driver_find(buf, &serio_bus)) != NULL) { serio_disconnect_port(serio); error = serio_bind_driver(serio, to_serio_driver(drv)); put_driver(drv); + serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT); } else { error = -EINVAL; } diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c index fc38149..cf8fb9f 100644 --- a/drivers/input/tablet/wacom_sys.c +++ b/drivers/input/tablet/wacom_sys.c @@ -519,7 +519,7 @@ static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *i /* Retrieve the physical and logical size for OEM devices */ error = wacom_retrieve_hid_descriptor(intf, features); if (error) - goto fail2; + goto fail3; wacom_setup_device_quirks(features); diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index 14ea54b..4bf2316 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -941,28 +941,29 @@ static int __devinit ads7846_setup_pendown(struct spi_device *spi, struct ads784 struct ads7846_platform_data *pdata = spi->dev.platform_data; int err; - /* REVISIT when the irq can be triggered active-low, or if for some + /* + * REVISIT when the irq can be triggered active-low, or if for some * reason the touchscreen isn't hooked up, we don't need to access * the pendown state. */ - if (!pdata->get_pendown_state && !gpio_is_valid(pdata->gpio_pendown)) { - dev_err(&spi->dev, "no get_pendown_state nor gpio_pendown?\n"); - return -EINVAL; - } if (pdata->get_pendown_state) { ts->get_pendown_state = pdata->get_pendown_state; - return 0; - } + } else if (gpio_is_valid(pdata->gpio_pendown)) { - err = gpio_request(pdata->gpio_pendown, "ads7846_pendown"); - if (err) { - dev_err(&spi->dev, "failed to request pendown GPIO%d\n", - pdata->gpio_pendown); - return err; - } + err = gpio_request(pdata->gpio_pendown, "ads7846_pendown"); + if (err) { + dev_err(&spi->dev, "failed to request pendown GPIO%d\n", + pdata->gpio_pendown); + return err; + } - ts->gpio_pendown = pdata->gpio_pendown; + ts->gpio_pendown = pdata->gpio_pendown; + + } else { + dev_err(&spi->dev, "no get_pendown_state nor gpio_pendown?\n"); + return -EINVAL; + } return 0; } @@ -1353,7 +1354,7 @@ static int __devinit ads7846_probe(struct spi_device *spi) err_put_regulator: regulator_put(ts->reg); err_free_gpio: - if (ts->gpio_pendown != -1) + if (!ts->get_pendown_state) gpio_free(ts->gpio_pendown); err_cleanup_filter: if (ts->filter_cleanup) @@ -1383,8 +1384,13 @@ static int __devexit ads7846_remove(struct spi_device *spi) regulator_disable(ts->reg); regulator_put(ts->reg); - if (ts->gpio_pendown != -1) + if (!ts->get_pendown_state) { + /* + * If we are not using specialized pendown method we must + * have been relying on gpio we set up ourselves. + */ gpio_free(ts->gpio_pendown); + } if (ts->filter_cleanup) ts->filter_cleanup(ts->filter_data); diff --git a/drivers/input/touchscreen/wacom_w8001.c b/drivers/input/touchscreen/wacom_w8001.c index 5cb8449..c14412e 100644 --- a/drivers/input/touchscreen/wacom_w8001.c +++ b/drivers/input/touchscreen/wacom_w8001.c @@ -51,6 +51,10 @@ MODULE_LICENSE("GPL"); #define W8001_PKTLEN_TPCCTL 11 /* control packet */ #define W8001_PKTLEN_TOUCH2FG 13 +/* resolution in points/mm */ +#define W8001_PEN_RESOLUTION 100 +#define W8001_TOUCH_RESOLUTION 10 + struct w8001_coord { u8 rdy; u8 tsw; @@ -198,7 +202,7 @@ static void parse_touchquery(u8 *data, struct w8001_touch_query *query) query->y = 1024; if (query->panel_res) query->x = query->y = (1 << query->panel_res); - query->panel_res = 10; + query->panel_res = W8001_TOUCH_RESOLUTION; } } @@ -394,6 +398,8 @@ static int w8001_setup(struct w8001 *w8001) input_set_abs_params(dev, ABS_X, 0, coord.x, 0, 0); input_set_abs_params(dev, ABS_Y, 0, coord.y, 0, 0); + input_abs_set_res(dev, ABS_X, W8001_PEN_RESOLUTION); + input_abs_set_res(dev, ABS_Y, W8001_PEN_RESOLUTION); input_set_abs_params(dev, ABS_PRESSURE, 0, coord.pen_pressure, 0, 0); if (coord.tilt_x && coord.tilt_y) { input_set_abs_params(dev, ABS_TILT_X, 0, coord.tilt_x, 0, 0); @@ -418,14 +424,17 @@ static int w8001_setup(struct w8001 *w8001) w8001->max_touch_x = touch.x; w8001->max_touch_y = touch.y; - /* scale to pen maximum */ if (w8001->max_pen_x && w8001->max_pen_y) { + /* if pen is supported scale to pen maximum */ touch.x = w8001->max_pen_x; touch.y = w8001->max_pen_y; + touch.panel_res = W8001_PEN_RESOLUTION; } input_set_abs_params(dev, ABS_X, 0, touch.x, 0, 0); input_set_abs_params(dev, ABS_Y, 0, touch.y, 0, 0); + input_abs_set_res(dev, ABS_X, touch.panel_res); + input_abs_set_res(dev, ABS_Y, touch.panel_res); switch (touch.sensor_id) { case 0: diff --git a/drivers/isdn/hardware/eicon/istream.c b/drivers/isdn/hardware/eicon/istream.c index 18f8798..7bd5baa 100644 --- a/drivers/isdn/hardware/eicon/istream.c +++ b/drivers/isdn/hardware/eicon/istream.c @@ -62,7 +62,7 @@ void diva_xdi_provide_istream_info (ADAPTER* a, stream interface. If synchronous service was requested, then function does return amount of data written to stream. - 'final' does indicate that pice of data to be written is + 'final' does indicate that piece of data to be written is final part of frame (necessary only by structured datatransfer) return 0 if zero lengh packet was written return -1 if stream is full diff --git a/drivers/isdn/hisax/isdnl2.c b/drivers/isdn/hisax/isdnl2.c index 0858791..cfff0c4 100644 --- a/drivers/isdn/hisax/isdnl2.c +++ b/drivers/isdn/hisax/isdnl2.c @@ -1247,10 +1247,10 @@ static void l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) { struct PStack *st = fi->userdata; - struct sk_buff *skb, *oskb; + struct sk_buff *skb; struct Layer2 *l2 = &st->l2; u_char header[MAX_HEADER_LEN]; - int i; + int i, hdr_space_needed; int unsigned p1; u_long flags; @@ -1261,6 +1261,16 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) if (!skb) return; + hdr_space_needed = l2headersize(l2, 0); + if (hdr_space_needed > skb_headroom(skb)) { + struct sk_buff *orig_skb = skb; + + skb = skb_realloc_headroom(skb, hdr_space_needed); + if (!skb) { + dev_kfree_skb(orig_skb); + return; + } + } spin_lock_irqsave(&l2->lock, flags); if(test_bit(FLG_MOD128, &l2->flag)) p1 = (l2->vs - l2->va) % 128; @@ -1285,19 +1295,7 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) l2->vs = (l2->vs + 1) % 8; } spin_unlock_irqrestore(&l2->lock, flags); - p1 = skb->data - skb->head; - if (p1 >= i) - memcpy(skb_push(skb, i), header, i); - else { - printk(KERN_WARNING - "isdl2 pull_iqueue skb header(%d/%d) too short\n", i, p1); - oskb = skb; - skb = alloc_skb(oskb->len + i, GFP_ATOMIC); - memcpy(skb_put(skb, i), header, i); - skb_copy_from_linear_data(oskb, - skb_put(skb, oskb->len), oskb->len); - dev_kfree_skb(oskb); - } + memcpy(skb_push(skb, i), header, i); st->l2.l2l1(st, PH_PULL | INDICATION, skb); test_and_clear_bit(FLG_ACK_PEND, &st->l2.flag); if (!test_and_set_bit(FLG_T200_RUN, &st->l2.flag)) { diff --git a/drivers/isdn/hysdn/hysdn_defs.h b/drivers/isdn/hysdn/hysdn_defs.h index 729df40..18b801a 100644 --- a/drivers/isdn/hysdn/hysdn_defs.h +++ b/drivers/isdn/hysdn/hysdn_defs.h @@ -227,7 +227,6 @@ extern hysdn_card *card_root; /* pointer to first card */ /*************************/ /* im/exported functions */ /*************************/ -extern char *hysdn_getrev(const char *); /* hysdn_procconf.c */ extern int hysdn_procconf_init(void); /* init proc config filesys */ @@ -259,7 +258,6 @@ extern int hysdn_tx_cfgline(hysdn_card *, unsigned char *, /* hysdn_net.c */ extern unsigned int hynet_enable; -extern char *hysdn_net_revision; extern int hysdn_net_create(hysdn_card *); /* create a new net device */ extern int hysdn_net_release(hysdn_card *); /* delete the device */ extern char *hysdn_net_getname(hysdn_card *); /* get name of net interface */ diff --git a/drivers/isdn/hysdn/hysdn_init.c b/drivers/isdn/hysdn/hysdn_init.c index b7cc5c2..0ab42ac 100644 --- a/drivers/isdn/hysdn/hysdn_init.c +++ b/drivers/isdn/hysdn/hysdn_init.c @@ -36,7 +36,6 @@ MODULE_DESCRIPTION("ISDN4Linux: Driver for HYSDN cards"); MODULE_AUTHOR("Werner Cornelius"); MODULE_LICENSE("GPL"); -static char *hysdn_init_revision = "$Revision: 1.6.6.6 $"; static int cardmax; /* number of found cards */ hysdn_card *card_root = NULL; /* pointer to first card */ static hysdn_card *card_last = NULL; /* pointer to first card */ @@ -49,25 +48,6 @@ static hysdn_card *card_last = NULL; /* pointer to first card */ /* Additionally newer versions may be activated without rebooting. */ /****************************************************************************/ -/******************************************************/ -/* extract revision number from string for log output */ -/******************************************************/ -char * -hysdn_getrev(const char *revision) -{ - char *rev; - char *p; - - if ((p = strchr(revision, ':'))) { - rev = p + 2; - p = strchr(rev, '$'); - *--p = 0; - } else - rev = "???"; - return rev; -} - - /****************************************************************************/ /* init_module is called once when the module is loaded to do all necessary */ /* things like autodetect... */ @@ -175,13 +155,9 @@ static int hysdn_have_procfs; static int __init hysdn_init(void) { - char tmp[50]; int rc; - strcpy(tmp, hysdn_init_revision); - printk(KERN_NOTICE "HYSDN: module Rev: %s loaded\n", hysdn_getrev(tmp)); - strcpy(tmp, hysdn_net_revision); - printk(KERN_NOTICE "HYSDN: network interface Rev: %s \n", hysdn_getrev(tmp)); + printk(KERN_NOTICE "HYSDN: module loaded\n"); rc = pci_register_driver(&hysdn_pci_driver); if (rc) diff --git a/drivers/isdn/hysdn/hysdn_net.c b/drivers/isdn/hysdn/hysdn_net.c index feec8d8..11f2cce 100644 --- a/drivers/isdn/hysdn/hysdn_net.c +++ b/drivers/isdn/hysdn/hysdn_net.c @@ -26,9 +26,6 @@ unsigned int hynet_enable = 0xffffffff; module_param(hynet_enable, uint, 0); -/* store the actual version for log reporting */ -char *hysdn_net_revision = "$Revision: 1.8.6.4 $"; - #define MAX_SKB_BUFFERS 20 /* number of buffers for keeping TX-data */ /****************************************************************************/ diff --git a/drivers/isdn/hysdn/hysdn_procconf.c b/drivers/isdn/hysdn/hysdn_procconf.c index 96b3e39..5fe83bd 100644 --- a/drivers/isdn/hysdn/hysdn_procconf.c +++ b/drivers/isdn/hysdn/hysdn_procconf.c @@ -23,7 +23,6 @@ #include "hysdn_defs.h" static DEFINE_MUTEX(hysdn_conf_mutex); -static char *hysdn_procconf_revision = "$Revision: 1.8.6.4 $"; #define INFO_OUT_LEN 80 /* length of info line including lf */ @@ -404,7 +403,7 @@ hysdn_procconf_init(void) card = card->next; /* next entry */ } - printk(KERN_NOTICE "HYSDN: procfs Rev. %s initialised\n", hysdn_getrev(hysdn_procconf_revision)); + printk(KERN_NOTICE "HYSDN: procfs initialised\n"); return (0); } /* hysdn_procconf_init */ diff --git a/drivers/isdn/icn/icn.c b/drivers/isdn/icn/icn.c index f2b5bab..1f355bb 100644 --- a/drivers/isdn/icn/icn.c +++ b/drivers/isdn/icn/icn.c @@ -1627,7 +1627,7 @@ __setup("icn=", icn_setup); static int __init icn_init(void) { char *p; - char rev[20]; + char rev[21]; memset(&dev, 0, sizeof(icn_dev)); dev.memaddr = (membase & 0x0ffc000); @@ -1638,6 +1638,7 @@ static int __init icn_init(void) if ((p = strchr(revision, ':'))) { strncpy(rev, p + 1, 20); + rev[20] = '\0'; p = strchr(rev, '$'); if (p) *p = 0; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 8a2f767..0ed7f6b 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -216,7 +216,6 @@ static int linear_run (mddev_t *mddev) if (md_check_no_bitmap(mddev)) return -EINVAL; - mddev->queue->queue_lock = &mddev->queue->__queue_lock; conf = linear_conf(mddev, mddev->raid_disks); if (!conf) diff --git a/drivers/md/md.c b/drivers/md/md.c index b76cfc8..818313e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -287,6 +287,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio) mddev_t *mddev = q->queuedata; int rv; int cpu; + unsigned int sectors; if (mddev == NULL || mddev->pers == NULL || !mddev->ready) { @@ -311,12 +312,16 @@ static int md_make_request(struct request_queue *q, struct bio *bio) atomic_inc(&mddev->active_io); rcu_read_unlock(); + /* + * save the sectors now since our bio can + * go away inside make_request + */ + sectors = bio_sectors(bio); rv = mddev->pers->make_request(mddev, bio); cpu = part_stat_lock(); part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); - part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], - bio_sectors(bio)); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors); part_stat_unlock(); if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended) @@ -548,6 +553,9 @@ static mddev_t * mddev_find(dev_t unit) { mddev_t *mddev, *new = NULL; + if (unit && MAJOR(unit) != MD_MAJOR) + unit &= ~((1<<MdpMinorShift)-1); + retry: spin_lock(&all_mddevs_lock); @@ -1947,8 +1955,6 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared) __bdevname(dev, b)); return PTR_ERR(bdev); } - if (!shared) - set_bit(AllReserved, &rdev->flags); rdev->bdev = bdev; return err; } @@ -2465,6 +2471,9 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) if (rdev->raid_disk != -1) return -EBUSY; + if (test_bit(MD_RECOVERY_RUNNING, &rdev->mddev->recovery)) + return -EBUSY; + if (rdev->mddev->pers->hot_add_disk == NULL) return -EINVAL; @@ -2610,12 +2619,11 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) mddev_lock(mddev); list_for_each_entry(rdev2, &mddev->disks, same_set) - if (test_bit(AllReserved, &rdev2->flags) || - (rdev->bdev == rdev2->bdev && - rdev != rdev2 && - overlaps(rdev->data_offset, rdev->sectors, - rdev2->data_offset, - rdev2->sectors))) { + if (rdev->bdev == rdev2->bdev && + rdev != rdev2 && + overlaps(rdev->data_offset, rdev->sectors, + rdev2->data_offset, + rdev2->sectors)) { overlap = 1; break; } @@ -4133,10 +4141,10 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len) } mddev->array_sectors = sectors; - set_capacity(mddev->gendisk, mddev->array_sectors); - if (mddev->pers) + if (mddev->pers) { + set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); - + } return len; } @@ -4619,6 +4627,7 @@ static int do_md_run(mddev_t *mddev) } set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); + mddev->changed = 1; kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE); out: return err; @@ -4707,6 +4716,7 @@ static void md_clean(mddev_t *mddev) mddev->sync_speed_min = mddev->sync_speed_max = 0; mddev->recovery = 0; mddev->in_sync = 0; + mddev->changed = 0; mddev->degraded = 0; mddev->safemode = 0; mddev->bitmap_info.offset = 0; @@ -4822,6 +4832,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) set_capacity(disk, 0); mutex_unlock(&mddev->open_mutex); + mddev->changed = 1; revalidate_disk(disk); if (mddev->ro) @@ -5578,6 +5589,8 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks) mddev->delta_disks = raid_disks - mddev->raid_disks; rv = mddev->pers->check_reshape(mddev); + if (rv < 0) + mddev->delta_disks = 0; return rv; } @@ -6004,7 +6017,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) atomic_inc(&mddev->openers); mutex_unlock(&mddev->open_mutex); - check_disk_size_change(mddev->gendisk, bdev); + check_disk_change(bdev); out: return err; } @@ -6019,6 +6032,21 @@ static int md_release(struct gendisk *disk, fmode_t mode) return 0; } + +static int md_media_changed(struct gendisk *disk) +{ + mddev_t *mddev = disk->private_data; + + return mddev->changed; +} + +static int md_revalidate(struct gendisk *disk) +{ + mddev_t *mddev = disk->private_data; + + mddev->changed = 0; + return 0; +} static const struct block_device_operations md_fops = { .owner = THIS_MODULE, @@ -6029,6 +6057,8 @@ static const struct block_device_operations md_fops = .compat_ioctl = md_compat_ioctl, #endif .getgeo = md_getgeo, + .media_changed = md_media_changed, + .revalidate_disk= md_revalidate, }; static int md_thread(void * arg) @@ -6985,9 +7015,6 @@ void md_do_sync(mddev_t *mddev) } else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) mddev->resync_min = mddev->curr_resync_completed; mddev->curr_resync = 0; - if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) - mddev->curr_resync_completed = 0; - sysfs_notify(&mddev->kobj, NULL, "sync_completed"); wake_up(&resync_wait); set_bit(MD_RECOVERY_DONE, &mddev->recovery); md_wakeup_thread(mddev->thread); @@ -7028,7 +7055,7 @@ static int remove_and_add_spares(mddev_t *mddev) } } - if (mddev->degraded && ! mddev->ro && !mddev->recovery_disabled) { + if (mddev->degraded && !mddev->recovery_disabled) { list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->raid_disk >= 0 && !test_bit(In_sync, &rdev->flags) && @@ -7151,7 +7178,20 @@ void md_check_recovery(mddev_t *mddev) /* Only thing we do on a ro array is remove * failed devices. */ - remove_and_add_spares(mddev); + mdk_rdev_t *rdev; + list_for_each_entry(rdev, &mddev->disks, same_set) + if (rdev->raid_disk >= 0 && + !test_bit(Blocked, &rdev->flags) && + test_bit(Faulty, &rdev->flags) && + atomic_read(&rdev->nr_pending)==0) { + if (mddev->pers->hot_remove_disk( + mddev, rdev->raid_disk)==0) { + char nm[20]; + sprintf(nm,"rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + rdev->raid_disk = -1; + } + } clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); goto unlock; } diff --git a/drivers/md/md.h b/drivers/md/md.h index eec517c..12215d4 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -93,8 +93,6 @@ struct mdk_rdev_s #define Faulty 1 /* device is known to have a fault */ #define In_sync 2 /* device is in_sync with rest of array */ #define WriteMostly 4 /* Avoid reading if at all possible */ -#define AllReserved 6 /* If whole device is reserved for - * one array */ #define AutoDetected 7 /* added by auto-detect */ #define Blocked 8 /* An error occured on an externally * managed array, don't allow writes @@ -276,6 +274,8 @@ struct mddev_s atomic_t active; /* general refcount */ atomic_t openers; /* number of active opens */ + int changed; /* True if we might need to + * reread partition info */ int degraded; /* whether md should consider * adding a spare */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 6d7ddf3..3a62d44 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -435,7 +435,6 @@ static int multipath_run (mddev_t *mddev) * bookkeeping area. [whatever we allocate in multipath_run(), * should be freed in multipath_stop()] */ - mddev->queue->queue_lock = &mddev->queue->__queue_lock; conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL); mddev->private = conf; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a39f4c3..c0ac457 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -179,6 +179,14 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) rdev1->new_raid_disk = j; } + if (mddev->level == 1) { + /* taiking over a raid1 array- + * we have only one active disk + */ + j = 0; + rdev1->new_raid_disk = j; + } + if (j < 0 || j >= mddev->raid_disks) { printk(KERN_ERR "md/raid0:%s: bad disk number %d - " "aborting!\n", mdname(mddev), j); @@ -353,7 +361,6 @@ static int raid0_run(mddev_t *mddev) if (md_check_no_bitmap(mddev)) return -EINVAL; blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - mddev->queue->queue_lock = &mddev->queue->__queue_lock; /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { @@ -644,12 +651,39 @@ static void *raid0_takeover_raid10(mddev_t *mddev) return priv_conf; } +static void *raid0_takeover_raid1(mddev_t *mddev) +{ + raid0_conf_t *priv_conf; + + /* Check layout: + * - (N - 1) mirror drives must be already faulty + */ + if ((mddev->raid_disks - 1) != mddev->degraded) { + printk(KERN_ERR "md/raid0:%s: (N - 1) mirrors drives must be already faulty!\n", + mdname(mddev)); + return ERR_PTR(-EINVAL); + } + + /* Set new parameters */ + mddev->new_level = 0; + mddev->new_layout = 0; + mddev->new_chunk_sectors = 128; /* by default set chunk size to 64k */ + mddev->delta_disks = 1 - mddev->raid_disks; + mddev->raid_disks = 1; + /* make sure it will be not marked as dirty */ + mddev->recovery_cp = MaxSector; + + create_strip_zones(mddev, &priv_conf); + return priv_conf; +} + static void *raid0_takeover(mddev_t *mddev) { /* raid0 can take over: * raid4 - if all data disks are active. * raid5 - providing it is Raid4 layout and one disk is faulty * raid10 - assuming we have all necessary active disks + * raid1 - with (N -1) mirror drives faulty */ if (mddev->level == 4) return raid0_takeover_raid45(mddev); @@ -665,6 +699,12 @@ static void *raid0_takeover(mddev_t *mddev) if (mddev->level == 10) return raid0_takeover_raid10(mddev); + if (mddev->level == 1) + return raid0_takeover_raid1(mddev); + + printk(KERN_ERR "Takeover from raid%i to raid0 not supported\n", + mddev->level); + return ERR_PTR(-EINVAL); } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a23ffa3..06cd712 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -593,7 +593,10 @@ static int flush_pending_writes(conf_t *conf) if (conf->pending_bio_list.head) { struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); + /* Only take the spinlock to quiet a warning */ + spin_lock(conf->mddev->queue->queue_lock); blk_remove_plug(conf->mddev->queue); + spin_unlock(conf->mddev->queue->queue_lock); spin_unlock_irq(&conf->device_lock); /* flush any pending bitmap writes to * disk before proceeding w/ I/O */ @@ -959,7 +962,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) atomic_inc(&r1_bio->remaining); spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - blk_plug_device(mddev->queue); + blk_plug_device_unlocked(mddev->queue); spin_unlock_irqrestore(&conf->device_lock, flags); } r1_bio_write_done(r1_bio, bio->bi_vcnt, behind_pages, behind_pages != NULL); @@ -2021,7 +2024,6 @@ static int run(mddev_t *mddev) if (IS_ERR(conf)) return PTR_ERR(conf); - mddev->queue->queue_lock = &conf->device_lock; list_for_each_entry(rdev, &mddev->disks, same_set) { disk_stack_limits(mddev->gendisk, rdev->bdev, rdev->data_offset << 9); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 69b6595..747d061 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -662,7 +662,10 @@ static int flush_pending_writes(conf_t *conf) if (conf->pending_bio_list.head) { struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); + /* Spinlock only taken to quiet a warning */ + spin_lock(conf->mddev->queue->queue_lock); blk_remove_plug(conf->mddev->queue); + spin_unlock(conf->mddev->queue->queue_lock); spin_unlock_irq(&conf->device_lock); /* flush any pending bitmap writes to disk * before proceeding w/ I/O */ @@ -971,7 +974,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) atomic_inc(&r10_bio->remaining); spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - blk_plug_device(mddev->queue); + blk_plug_device_unlocked(mddev->queue); spin_unlock_irqrestore(&conf->device_lock, flags); } @@ -2304,8 +2307,6 @@ static int run(mddev_t *mddev) if (!conf) goto out; - mddev->queue->queue_lock = &conf->device_lock; - mddev->thread = conf->thread; conf->thread = NULL; @@ -2463,11 +2464,13 @@ static void *raid10_takeover_raid0(mddev_t *mddev) mddev->recovery_cp = MaxSector; conf = setup_conf(mddev); - if (!IS_ERR(conf)) + if (!IS_ERR(conf)) { list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->raid_disk >= 0) rdev->new_raid_disk = rdev->raid_disk * 2; - + conf->barrier = 1; + } + return conf; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5044bab..78536fd 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5204,7 +5204,6 @@ static int run(mddev_t *mddev) mddev->queue->backing_dev_info.congested_data = mddev; mddev->queue->backing_dev_info.congested_fn = raid5_congested; - mddev->queue->queue_lock = &conf->device_lock; mddev->queue->unplug_fn = raid5_unplug_queue; chunk_size = mddev->chunk_sectors << 9; @@ -5517,7 +5516,6 @@ static int raid5_start_reshape(mddev_t *mddev) raid5_conf_t *conf = mddev->private; mdk_rdev_t *rdev; int spares = 0; - int added_devices = 0; unsigned long flags; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) @@ -5527,8 +5525,8 @@ static int raid5_start_reshape(mddev_t *mddev) return -ENOSPC; list_for_each_entry(rdev, &mddev->disks, same_set) - if ((rdev->raid_disk < 0 || rdev->raid_disk >= conf->raid_disks) - && !test_bit(Faulty, &rdev->flags)) + if (!test_bit(In_sync, &rdev->flags) + && !test_bit(Faulty, &rdev->flags)) spares++; if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded) @@ -5571,34 +5569,35 @@ static int raid5_start_reshape(mddev_t *mddev) * to correctly record the "partially reconstructed" state of * such devices during the reshape and confusion could result. */ - if (mddev->delta_disks >= 0) - list_for_each_entry(rdev, &mddev->disks, same_set) - if (rdev->raid_disk < 0 && - !test_bit(Faulty, &rdev->flags)) { - if (raid5_add_disk(mddev, rdev) == 0) { - char nm[20]; - if (rdev->raid_disk >= conf->previous_raid_disks) { - set_bit(In_sync, &rdev->flags); - added_devices++; - } else - rdev->recovery_offset = 0; - sprintf(nm, "rd%d", rdev->raid_disk); - if (sysfs_create_link(&mddev->kobj, - &rdev->kobj, nm)) - /* Failure here is OK */; - } else - break; - } else if (rdev->raid_disk >= conf->previous_raid_disks - && !test_bit(Faulty, &rdev->flags)) { - /* This is a spare that was manually added */ - set_bit(In_sync, &rdev->flags); - added_devices++; - } + if (mddev->delta_disks >= 0) { + int added_devices = 0; + list_for_each_entry(rdev, &mddev->disks, same_set) + if (rdev->raid_disk < 0 && + !test_bit(Faulty, &rdev->flags)) { + if (raid5_add_disk(mddev, rdev) == 0) { + char nm[20]; + if (rdev->raid_disk + >= conf->previous_raid_disks) { + set_bit(In_sync, &rdev->flags); + added_devices++; + } else + rdev->recovery_offset = 0; + sprintf(nm, "rd%d", rdev->raid_disk); + if (sysfs_create_link(&mddev->kobj, + &rdev->kobj, nm)) + /* Failure here is OK */; + } + } else if (rdev->raid_disk >= conf->previous_raid_disks + && !test_bit(Faulty, &rdev->flags)) { + /* This is a spare that was manually added */ + set_bit(In_sync, &rdev->flags); + added_devices++; + } - /* When a reshape changes the number of devices, ->degraded - * is measured against the larger of the pre and post number of - * devices.*/ - if (mddev->delta_disks > 0) { + /* When a reshape changes the number of devices, + * ->degraded is measured against the larger of the + * pre and post number of devices. + */ spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded += (conf->raid_disks - conf->previous_raid_disks) - added_devices; diff --git a/drivers/media/common/tuners/tda8290.c b/drivers/media/common/tuners/tda8290.c index bc6a677..8c48521 100644 --- a/drivers/media/common/tuners/tda8290.c +++ b/drivers/media/common/tuners/tda8290.c @@ -658,13 +658,13 @@ static int tda8290_probe(struct tuner_i2c_props *i2c_props) #define TDA8290_ID 0x89 u8 reg = 0x1f, id; struct i2c_msg msg_read[] = { - { .addr = 0x4b, .flags = 0, .len = 1, .buf = ® }, - { .addr = 0x4b, .flags = I2C_M_RD, .len = 1, .buf = &id }, + { .addr = i2c_props->addr, .flags = 0, .len = 1, .buf = ® }, + { .addr = i2c_props->addr, .flags = I2C_M_RD, .len = 1, .buf = &id }, }; /* detect tda8290 */ if (i2c_transfer(i2c_props->adap, msg_read, 2) != 2) { - printk(KERN_WARNING "%s: tda8290 couldn't read register 0x%02x\n", + printk(KERN_WARNING "%s: couldn't read register 0x%02x\n", __func__, reg); return -ENODEV; } @@ -685,13 +685,13 @@ static int tda8295_probe(struct tuner_i2c_props *i2c_props) #define TDA8295C2_ID 0x8b u8 reg = 0x2f, id; struct i2c_msg msg_read[] = { - { .addr = 0x4b, .flags = 0, .len = 1, .buf = ® }, - { .addr = 0x4b, .flags = I2C_M_RD, .len = 1, .buf = &id }, + { .addr = i2c_props->addr, .flags = 0, .len = 1, .buf = ® }, + { .addr = i2c_props->addr, .flags = I2C_M_RD, .len = 1, .buf = &id }, }; - /* detect tda8290 */ + /* detect tda8295 */ if (i2c_transfer(i2c_props->adap, msg_read, 2) != 2) { - printk(KERN_WARNING "%s: tda8290 couldn't read register 0x%02x\n", + printk(KERN_WARNING "%s: couldn't read register 0x%02x\n", __func__, reg); return -ENODEV; } diff --git a/drivers/media/dvb/dvb-usb/dib0700_devices.c b/drivers/media/dvb/dvb-usb/dib0700_devices.c index defd839..193cdb7 100644 --- a/drivers/media/dvb/dvb-usb/dib0700_devices.c +++ b/drivers/media/dvb/dvb-usb/dib0700_devices.c @@ -870,6 +870,23 @@ static int dib7070p_tuner_attach(struct dvb_usb_adapter *adap) return 0; } +static int stk7700p_pid_filter(struct dvb_usb_adapter *adapter, int index, + u16 pid, int onoff) +{ + struct dib0700_state *st = adapter->dev->priv; + if (st->is_dib7000pc) + return dib7000p_pid_filter(adapter->fe, index, pid, onoff); + return dib7000m_pid_filter(adapter->fe, index, pid, onoff); +} + +static int stk7700p_pid_filter_ctrl(struct dvb_usb_adapter *adapter, int onoff) +{ + struct dib0700_state *st = adapter->dev->priv; + if (st->is_dib7000pc) + return dib7000p_pid_filter_ctrl(adapter->fe, onoff); + return dib7000m_pid_filter_ctrl(adapter->fe, onoff); +} + static int stk70x0p_pid_filter(struct dvb_usb_adapter *adapter, int index, u16 pid, int onoff) { return dib7000p_pid_filter(adapter->fe, index, pid, onoff); @@ -1875,8 +1892,8 @@ struct dvb_usb_device_properties dib0700_devices[] = { { .caps = DVB_USB_ADAP_HAS_PID_FILTER | DVB_USB_ADAP_PID_FILTER_CAN_BE_TURNED_OFF, .pid_filter_count = 32, - .pid_filter = stk70x0p_pid_filter, - .pid_filter_ctrl = stk70x0p_pid_filter_ctrl, + .pid_filter = stk7700p_pid_filter, + .pid_filter_ctrl = stk7700p_pid_filter_ctrl, .frontend_attach = stk7700p_frontend_attach, .tuner_attach = stk7700p_tuner_attach, diff --git a/drivers/media/dvb/dvb-usb/lmedm04.c b/drivers/media/dvb/dvb-usb/lmedm04.c index 9eea418..46ccd01 100644 --- a/drivers/media/dvb/dvb-usb/lmedm04.c +++ b/drivers/media/dvb/dvb-usb/lmedm04.c @@ -659,7 +659,7 @@ static int lme2510_download_firmware(struct usb_device *dev, } /* Default firmware for LME2510C */ -const char lme_firmware[50] = "dvb-usb-lme2510c-s7395.fw"; +char lme_firmware[50] = "dvb-usb-lme2510c-s7395.fw"; static void lme_coldreset(struct usb_device *dev) { @@ -1006,7 +1006,7 @@ static struct dvb_usb_device_properties lme2510c_properties = { .caps = DVB_USB_IS_AN_I2C_ADAPTER, .usb_ctrl = DEVICE_SPECIFIC, .download_firmware = lme2510_download_firmware, - .firmware = lme_firmware, + .firmware = (const char *)&lme_firmware, .size_of_priv = sizeof(struct lme2510_state), .num_adapters = 1, .adapter = { @@ -1109,5 +1109,5 @@ module_exit(lme2510_module_exit); MODULE_AUTHOR("Malcolm Priestley <tvboxspy@gmail.com>"); MODULE_DESCRIPTION("LME2510(C) DVB-S USB2.0"); -MODULE_VERSION("1.74"); +MODULE_VERSION("1.75"); MODULE_LICENSE("GPL"); diff --git a/drivers/media/dvb/frontends/dib7000m.c b/drivers/media/dvb/frontends/dib7000m.c index c7f5ccf..289a798 100644 --- a/drivers/media/dvb/frontends/dib7000m.c +++ b/drivers/media/dvb/frontends/dib7000m.c @@ -1285,6 +1285,25 @@ struct i2c_adapter * dib7000m_get_i2c_master(struct dvb_frontend *demod, enum di } EXPORT_SYMBOL(dib7000m_get_i2c_master); +int dib7000m_pid_filter_ctrl(struct dvb_frontend *fe, u8 onoff) +{ + struct dib7000m_state *state = fe->demodulator_priv; + u16 val = dib7000m_read_word(state, 294 + state->reg_offs) & 0xffef; + val |= (onoff & 0x1) << 4; + dprintk("PID filter enabled %d", onoff); + return dib7000m_write_word(state, 294 + state->reg_offs, val); +} +EXPORT_SYMBOL(dib7000m_pid_filter_ctrl); + +int dib7000m_pid_filter(struct dvb_frontend *fe, u8 id, u16 pid, u8 onoff) +{ + struct dib7000m_state *state = fe->demodulator_priv; + dprintk("PID filter: index %x, PID %d, OnOff %d", id, pid, onoff); + return dib7000m_write_word(state, 300 + state->reg_offs + id, + onoff ? (1 << 13) | pid : 0); +} +EXPORT_SYMBOL(dib7000m_pid_filter); + #if 0 /* used with some prototype boards */ int dib7000m_i2c_enumeration(struct i2c_adapter *i2c, int no_of_demods, diff --git a/drivers/media/dvb/frontends/dib7000m.h b/drivers/media/dvb/frontends/dib7000m.h index 113819c..81fcf22 100644 --- a/drivers/media/dvb/frontends/dib7000m.h +++ b/drivers/media/dvb/frontends/dib7000m.h @@ -46,6 +46,8 @@ extern struct dvb_frontend *dib7000m_attach(struct i2c_adapter *i2c_adap, extern struct i2c_adapter *dib7000m_get_i2c_master(struct dvb_frontend *, enum dibx000_i2c_interface, int); +extern int dib7000m_pid_filter(struct dvb_frontend *, u8 id, u16 pid, u8 onoff); +extern int dib7000m_pid_filter_ctrl(struct dvb_frontend *fe, u8 onoff); #else static inline struct dvb_frontend *dib7000m_attach(struct i2c_adapter *i2c_adap, @@ -63,6 +65,19 @@ struct i2c_adapter *dib7000m_get_i2c_master(struct dvb_frontend *demod, printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__); return NULL; } +static inline int dib7000m_pid_filter(struct dvb_frontend *fe, u8 id, + u16 pid, u8 onoff) +{ + printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__); + return -ENODEV; +} + +static inline int dib7000m_pid_filter_ctrl(struct dvb_frontend *fe, + uint8_t onoff) +{ + printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__); + return -ENODEV; +} #endif /* TODO diff --git a/drivers/media/dvb/mantis/mantis_pci.c b/drivers/media/dvb/mantis/mantis_pci.c index 59feeb8..10a432a 100644 --- a/drivers/media/dvb/mantis/mantis_pci.c +++ b/drivers/media/dvb/mantis/mantis_pci.c @@ -22,7 +22,6 @@ #include <linux/moduleparam.h> #include <linux/kernel.h> #include <asm/io.h> -#include <asm/pgtable.h> #include <asm/page.h> #include <linux/kmod.h> #include <linux/vmalloc.h> diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c index f011c5d..1c5cc65 100644 --- a/drivers/media/rc/ir-lirc-codec.c +++ b/drivers/media/rc/ir-lirc-codec.c @@ -1,4 +1,4 @@ -/* ir-lirc-codec.c - ir-core to classic lirc interface bridge +/* ir-lirc-codec.c - rc-core to classic lirc interface bridge * * Copyright (C) 2010 by Jarod Wilson <jarod@redhat.com> * @@ -47,6 +47,7 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) /* Carrier reports */ if (ev.carrier_report) { sample = LIRC_FREQUENCY(ev.carrier); + IR_dprintk(2, "carrier report (freq: %d)\n", sample); /* Packet end */ } else if (ev.timeout) { @@ -62,6 +63,7 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) return 0; sample = LIRC_TIMEOUT(ev.duration / 1000); + IR_dprintk(2, "timeout report (duration: %d)\n", sample); /* Normal sample */ } else { @@ -85,6 +87,8 @@ static int ir_lirc_decode(struct rc_dev *dev, struct ir_raw_event ev) sample = ev.pulse ? LIRC_PULSE(ev.duration / 1000) : LIRC_SPACE(ev.duration / 1000); + IR_dprintk(2, "delivering %uus %s to lirc_dev\n", + TO_US(ev.duration), TO_STR(ev.pulse)); } lirc_buffer_write(dev->raw->lirc.drv->rbuf, diff --git a/drivers/media/rc/ir-raw.c b/drivers/media/rc/ir-raw.c index 73230ff..01f258a 100644 --- a/drivers/media/rc/ir-raw.c +++ b/drivers/media/rc/ir-raw.c @@ -112,7 +112,7 @@ int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type) { ktime_t now; s64 delta; /* ns */ - struct ir_raw_event ev; + DEFINE_IR_RAW_EVENT(ev); int rc = 0; if (!dev->raw) @@ -125,7 +125,6 @@ int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type) * being called for the first time, note that delta can't * possibly be negative. */ - ev.duration = 0; if (delta > IR_MAX_DURATION || !dev->raw->last_type) type |= IR_START_EVENT; else diff --git a/drivers/media/rc/keymaps/rc-rc6-mce.c b/drivers/media/rc/keymaps/rc-rc6-mce.c index 3bf3337..2f5dc06 100644 --- a/drivers/media/rc/keymaps/rc-rc6-mce.c +++ b/drivers/media/rc/keymaps/rc-rc6-mce.c @@ -3,6 +3,9 @@ * * Copyright (c) 2010 by Jarod Wilson <jarod@redhat.com> * + * See http://mediacenterguides.com/book/export/html/31 for details on + * key mappings. + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or @@ -60,6 +63,9 @@ static struct rc_map_table rc6_mce[] = { { 0x800f0426, KEY_EPG }, /* Guide */ { 0x800f0427, KEY_ZOOM }, /* Aspect */ + { 0x800f0432, KEY_MODE }, /* Visualization */ + { 0x800f0433, KEY_PRESENTATION }, /* Slide Show */ + { 0x800f0434, KEY_EJECTCD }, { 0x800f043a, KEY_BRIGHTNESSUP }, { 0x800f0446, KEY_TV }, diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index 079353e..e4f8eac 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -148,6 +148,7 @@ enum mceusb_model_type { MCE_GEN2_TX_INV, POLARIS_EVK, CX_HYBRID_TV, + MULTIFUNCTION, }; struct mceusb_model { @@ -155,9 +156,10 @@ struct mceusb_model { u32 mce_gen2:1; u32 mce_gen3:1; u32 tx_mask_normal:1; - u32 is_polaris:1; u32 no_tx:1; + int ir_intfnum; + const char *rc_map; /* Allow specify a per-board map */ const char *name; /* per-board name */ }; @@ -179,7 +181,6 @@ static const struct mceusb_model mceusb_model[] = { .tx_mask_normal = 1, }, [POLARIS_EVK] = { - .is_polaris = 1, /* * In fact, the EVK is shipped without * remotes, but we should have something handy, @@ -189,10 +190,13 @@ static const struct mceusb_model mceusb_model[] = { .name = "Conexant Hybrid TV (cx231xx) MCE IR", }, [CX_HYBRID_TV] = { - .is_polaris = 1, .no_tx = 1, /* tx isn't wired up at all */ .name = "Conexant Hybrid TV (cx231xx) MCE IR", }, + [MULTIFUNCTION] = { + .mce_gen2 = 1, + .ir_intfnum = 2, + }, }; static struct usb_device_id mceusb_dev_table[] = { @@ -216,8 +220,9 @@ static struct usb_device_id mceusb_dev_table[] = { { USB_DEVICE(VENDOR_PHILIPS, 0x206c) }, /* Philips/Spinel plus IR transceiver for ASUS */ { USB_DEVICE(VENDOR_PHILIPS, 0x2088) }, - /* Realtek MCE IR Receiver */ - { USB_DEVICE(VENDOR_REALTEK, 0x0161) }, + /* Realtek MCE IR Receiver and card reader */ + { USB_DEVICE(VENDOR_REALTEK, 0x0161), + .driver_info = MULTIFUNCTION }, /* SMK/Toshiba G83C0004D410 */ { USB_DEVICE(VENDOR_SMK, 0x031d), .driver_info = MCE_GEN2_TX_INV }, @@ -816,7 +821,7 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index) switch (ir->buf_in[index]) { /* 2-byte return value commands */ case MCE_CMD_S_TIMEOUT: - ir->rc->timeout = MS_TO_NS((hi << 8 | lo) / 2); + ir->rc->timeout = US_TO_NS((hi << 8 | lo) / 2); break; /* 1-byte return value commands */ @@ -855,9 +860,10 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) break; case PARSE_IRDATA: ir->rem--; + init_ir_raw_event(&rawir); rawir.pulse = ((ir->buf_in[i] & MCE_PULSE_BIT) != 0); rawir.duration = (ir->buf_in[i] & MCE_PULSE_MASK) - * MS_TO_US(MCE_TIME_UNIT); + * US_TO_NS(MCE_TIME_UNIT); dev_dbg(ir->dev, "Storing %s with duration %d\n", rawir.pulse ? "pulse" : "space", @@ -883,6 +889,8 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) i, ir->rem + 1, false); if (ir->rem) ir->parser_state = PARSE_IRDATA; + else + ir_raw_event_reset(ir->rc); break; } @@ -1060,7 +1068,7 @@ static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir) rc->priv = ir; rc->driver_type = RC_DRIVER_IR_RAW; rc->allowed_protos = RC_TYPE_ALL; - rc->timeout = MS_TO_NS(1000); + rc->timeout = US_TO_NS(1000); if (!ir->flags.no_tx) { rc->s_tx_mask = mceusb_set_tx_mask; rc->s_tx_carrier = mceusb_set_tx_carrier; @@ -1098,7 +1106,7 @@ static int __devinit mceusb_dev_probe(struct usb_interface *intf, bool is_gen3; bool is_microsoft_gen1; bool tx_mask_normal; - bool is_polaris; + int ir_intfnum; dev_dbg(&intf->dev, "%s called\n", __func__); @@ -1107,13 +1115,11 @@ static int __devinit mceusb_dev_probe(struct usb_interface *intf, is_gen3 = mceusb_model[model].mce_gen3; is_microsoft_gen1 = mceusb_model[model].mce_gen1; tx_mask_normal = mceusb_model[model].tx_mask_normal; - is_polaris = mceusb_model[model].is_polaris; + ir_intfnum = mceusb_model[model].ir_intfnum; - if (is_polaris) { - /* Interface 0 is IR */ - if (idesc->desc.bInterfaceNumber) - return -ENODEV; - } + /* There are multi-function devices with non-IR interfaces */ + if (idesc->desc.bInterfaceNumber != ir_intfnum) + return -ENODEV; /* step through the endpoints to find first bulk in and out endpoint */ for (i = 0; i < idesc->desc.bNumEndpoints; ++i) { diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c index dd4caf8..d4d6449 100644 --- a/drivers/media/rc/nuvoton-cir.c +++ b/drivers/media/rc/nuvoton-cir.c @@ -385,8 +385,9 @@ static void nvt_cir_regs_init(struct nvt_dev *nvt) static void nvt_cir_wake_regs_init(struct nvt_dev *nvt) { - /* set number of bytes needed for wake key comparison (default 67) */ - nvt_cir_wake_reg_write(nvt, CIR_WAKE_FIFO_LEN, CIR_WAKE_FIFO_CMP_DEEP); + /* set number of bytes needed for wake from s3 (default 65) */ + nvt_cir_wake_reg_write(nvt, CIR_WAKE_FIFO_CMP_BYTES, + CIR_WAKE_FIFO_CMP_DEEP); /* set tolerance/variance allowed per byte during wake compare */ nvt_cir_wake_reg_write(nvt, CIR_WAKE_CMP_TOLERANCE, @@ -460,7 +461,7 @@ static u32 nvt_rx_carrier_detect(struct nvt_dev *nvt) return 0; } - carrier = (count * 1000000) / duration; + carrier = MS_TO_NS(count) / duration; if ((carrier > MAX_CARRIER) || (carrier < MIN_CARRIER)) nvt_dbg("WTF? Carrier frequency out of range!"); @@ -612,8 +613,8 @@ static void nvt_process_rx_ir_data(struct nvt_dev *nvt) sample = nvt->buf[i]; rawir.pulse = ((sample & BUF_PULSE_BIT) != 0); - rawir.duration = (sample & BUF_LEN_MASK) - * SAMPLE_PERIOD * 1000; + rawir.duration = US_TO_NS((sample & BUF_LEN_MASK) + * SAMPLE_PERIOD); if ((sample & BUF_LEN_MASK) == BUF_LEN_MASK) { if (nvt->rawir.pulse == rawir.pulse) diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h index 1df8235..048135e 100644 --- a/drivers/media/rc/nuvoton-cir.h +++ b/drivers/media/rc/nuvoton-cir.h @@ -305,8 +305,11 @@ struct nvt_dev { #define CIR_WAKE_IRFIFOSTS_RX_EMPTY 0x20 #define CIR_WAKE_IRFIFOSTS_RX_FULL 0x10 -/* CIR Wake FIFO buffer is 67 bytes long */ -#define CIR_WAKE_FIFO_LEN 67 +/* + * The CIR Wake FIFO buffer is 67 bytes long, but the stock remote wakes + * the system comparing only 65 bytes (fails with this set to 67) + */ +#define CIR_WAKE_FIFO_CMP_BYTES 65 /* CIR Wake byte comparison tolerance */ #define CIR_WAKE_CMP_TOLERANCE 5 diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 512a2f4..5b4422e 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -850,7 +850,7 @@ static ssize_t store_protocols(struct device *device, count++; } else { for (i = 0; i < ARRAY_SIZE(proto_names); i++) { - if (!strncasecmp(tmp, proto_names[i].name, strlen(proto_names[i].name))) { + if (!strcasecmp(tmp, proto_names[i].name)) { tmp += strlen(proto_names[i].name); mask = proto_names[i].type; break; diff --git a/drivers/media/rc/streamzap.c b/drivers/media/rc/streamzap.c index 6e2911c..e435d94 100644 --- a/drivers/media/rc/streamzap.c +++ b/drivers/media/rc/streamzap.c @@ -164,7 +164,7 @@ static void sz_push_full_pulse(struct streamzap_ir *sz, sz->signal_start.tv_usec - sz->signal_last.tv_usec); rawir.duration -= sz->sum; - rawir.duration *= 1000; + rawir.duration = US_TO_NS(rawir.duration); rawir.duration &= IR_MAX_DURATION; } sz_push(sz, rawir); @@ -177,7 +177,7 @@ static void sz_push_full_pulse(struct streamzap_ir *sz, rawir.duration = ((int) value) * SZ_RESOLUTION; rawir.duration += SZ_RESOLUTION / 2; sz->sum += rawir.duration; - rawir.duration *= 1000; + rawir.duration = US_TO_NS(rawir.duration); rawir.duration &= IR_MAX_DURATION; sz_push(sz, rawir); } @@ -197,7 +197,7 @@ static void sz_push_full_space(struct streamzap_ir *sz, rawir.duration = ((int) value) * SZ_RESOLUTION; rawir.duration += SZ_RESOLUTION / 2; sz->sum += rawir.duration; - rawir.duration *= 1000; + rawir.duration = US_TO_NS(rawir.duration); sz_push(sz, rawir); } @@ -273,6 +273,7 @@ static void streamzap_callback(struct urb *urb) if (sz->timeout_enabled) sz_push(sz, rawir); ir_raw_event_handle(sz->rdev); + ir_raw_event_reset(sz->rdev); } else { sz_push_full_space(sz, sz->buf_in[i]); } @@ -290,6 +291,7 @@ static void streamzap_callback(struct urb *urb) } } + ir_raw_event_handle(sz->rdev); usb_submit_urb(urb, GFP_ATOMIC); return; @@ -430,13 +432,13 @@ static int __devinit streamzap_probe(struct usb_interface *intf, sz->decoder_state = PulseSpace; /* FIXME: don't yet have a way to set this */ sz->timeout_enabled = true; - sz->rdev->timeout = (((SZ_TIMEOUT * SZ_RESOLUTION * 1000) & + sz->rdev->timeout = ((US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION) & IR_MAX_DURATION) | 0x03000000); #if 0 /* not yet supported, depends on patches from maxim */ /* see also: LIRC_GET_REC_RESOLUTION and LIRC_SET_REC_TIMEOUT */ - sz->min_timeout = SZ_TIMEOUT * SZ_RESOLUTION * 1000; - sz->max_timeout = SZ_TIMEOUT * SZ_RESOLUTION * 1000; + sz->min_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION); + sz->max_timeout = US_TO_NS(SZ_TIMEOUT * SZ_RESOLUTION); #endif do_gettimeofday(&sz->signal_start); diff --git a/drivers/media/video/au0828/au0828-video.c b/drivers/media/video/au0828/au0828-video.c index e41e4ad..9c475c6 100644 --- a/drivers/media/video/au0828/au0828-video.c +++ b/drivers/media/video/au0828/au0828-video.c @@ -1758,7 +1758,12 @@ static int vidioc_reqbufs(struct file *file, void *priv, if (rc < 0) return rc; - return videobuf_reqbufs(&fh->vb_vidq, rb); + if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) + rc = videobuf_reqbufs(&fh->vb_vidq, rb); + else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) + rc = videobuf_reqbufs(&fh->vb_vbiq, rb); + + return rc; } static int vidioc_querybuf(struct file *file, void *priv, @@ -1772,7 +1777,12 @@ static int vidioc_querybuf(struct file *file, void *priv, if (rc < 0) return rc; - return videobuf_querybuf(&fh->vb_vidq, b); + if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) + rc = videobuf_querybuf(&fh->vb_vidq, b); + else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) + rc = videobuf_querybuf(&fh->vb_vbiq, b); + + return rc; } static int vidioc_qbuf(struct file *file, void *priv, struct v4l2_buffer *b) @@ -1785,7 +1795,12 @@ static int vidioc_qbuf(struct file *file, void *priv, struct v4l2_buffer *b) if (rc < 0) return rc; - return videobuf_qbuf(&fh->vb_vidq, b); + if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) + rc = videobuf_qbuf(&fh->vb_vidq, b); + else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) + rc = videobuf_qbuf(&fh->vb_vbiq, b); + + return rc; } static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b) @@ -1806,7 +1821,12 @@ static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *b) dev->greenscreen_detected = 0; } - return videobuf_dqbuf(&fh->vb_vidq, b, file->f_flags & O_NONBLOCK); + if (fh->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) + rc = videobuf_dqbuf(&fh->vb_vidq, b, file->f_flags & O_NONBLOCK); + else if (fh->type == V4L2_BUF_TYPE_VBI_CAPTURE) + rc = videobuf_dqbuf(&fh->vb_vbiq, b, file->f_flags & O_NONBLOCK); + + return rc; } static struct v4l2_file_operations au0828_v4l_fops = { diff --git a/drivers/media/video/cx18/cx18-cards.c b/drivers/media/video/cx18/cx18-cards.c index 8717773..68ad196 100644 --- a/drivers/media/video/cx18/cx18-cards.c +++ b/drivers/media/video/cx18/cx18-cards.c @@ -95,6 +95,53 @@ static const struct cx18_card cx18_card_hvr1600_esmt = { .i2c = &cx18_i2c_std, }; +static const struct cx18_card cx18_card_hvr1600_s5h1411 = { + .type = CX18_CARD_HVR_1600_S5H1411, + .name = "Hauppauge HVR-1600", + .comment = "Simultaneous Digital and Analog TV capture supported\n", + .v4l2_capabilities = CX18_CAP_ENCODER, + .hw_audio_ctrl = CX18_HW_418_AV, + .hw_muxer = CX18_HW_CS5345, + .hw_all = CX18_HW_TVEEPROM | CX18_HW_418_AV | CX18_HW_TUNER | + CX18_HW_CS5345 | CX18_HW_DVB | CX18_HW_GPIO_RESET_CTRL | + CX18_HW_Z8F0811_IR_HAUP, + .video_inputs = { + { CX18_CARD_INPUT_VID_TUNER, 0, CX18_AV_COMPOSITE7 }, + { CX18_CARD_INPUT_SVIDEO1, 1, CX18_AV_SVIDEO1 }, + { CX18_CARD_INPUT_COMPOSITE1, 1, CX18_AV_COMPOSITE3 }, + { CX18_CARD_INPUT_SVIDEO2, 2, CX18_AV_SVIDEO2 }, + { CX18_CARD_INPUT_COMPOSITE2, 2, CX18_AV_COMPOSITE4 }, + }, + .audio_inputs = { + { CX18_CARD_INPUT_AUD_TUNER, + CX18_AV_AUDIO8, CS5345_IN_1 | CS5345_MCLK_1_5 }, + { CX18_CARD_INPUT_LINE_IN1, + CX18_AV_AUDIO_SERIAL1, CS5345_IN_2 }, + { CX18_CARD_INPUT_LINE_IN2, + CX18_AV_AUDIO_SERIAL1, CS5345_IN_3 }, + }, + .radio_input = { CX18_CARD_INPUT_AUD_TUNER, + CX18_AV_AUDIO_SERIAL1, CS5345_IN_4 }, + .ddr = { + /* ESMT M13S128324A-5B memory */ + .chip_config = 0x003, + .refresh = 0x30c, + .timing1 = 0x44220e82, + .timing2 = 0x08, + .tune_lane = 0, + .initial_emrs = 0, + }, + .gpio_init.initial_value = 0x3001, + .gpio_init.direction = 0x3001, + .gpio_i2c_slave_reset = { + .active_lo_mask = 0x3001, + .msecs_asserted = 10, + .msecs_recovery = 40, + .ir_reset_mask = 0x0001, + }, + .i2c = &cx18_i2c_std, +}; + static const struct cx18_card cx18_card_hvr1600_samsung = { .type = CX18_CARD_HVR_1600_SAMSUNG, .name = "Hauppauge HVR-1600 (Preproduction)", @@ -523,7 +570,8 @@ static const struct cx18_card *cx18_card_list[] = { &cx18_card_toshiba_qosmio_dvbt, &cx18_card_leadtek_pvr2100, &cx18_card_leadtek_dvr3100h, - &cx18_card_gotview_dvd3 + &cx18_card_gotview_dvd3, + &cx18_card_hvr1600_s5h1411 }; const struct cx18_card *cx18_get_card(u16 index) diff --git a/drivers/media/video/cx18/cx18-driver.c b/drivers/media/video/cx18/cx18-driver.c index 944af8a..b1c3cbd 100644 --- a/drivers/media/video/cx18/cx18-driver.c +++ b/drivers/media/video/cx18/cx18-driver.c @@ -157,6 +157,7 @@ MODULE_PARM_DESC(cardtype, "\t\t\t 7 = Leadtek WinFast PVR2100\n" "\t\t\t 8 = Leadtek WinFast DVR3100 H\n" "\t\t\t 9 = GoTView PCI DVD3 Hybrid\n" + "\t\t\t 10 = Hauppauge HVR 1600 (S5H1411)\n" "\t\t\t 0 = Autodetect (default)\n" "\t\t\t-1 = Ignore this card\n\t\t"); MODULE_PARM_DESC(pal, "Set PAL standard: B, G, H, D, K, I, M, N, Nc, 60"); @@ -337,6 +338,7 @@ void cx18_read_eeprom(struct cx18 *cx, struct tveeprom *tv) switch (cx->card->type) { case CX18_CARD_HVR_1600_ESMT: case CX18_CARD_HVR_1600_SAMSUNG: + case CX18_CARD_HVR_1600_S5H1411: tveeprom_hauppauge_analog(&c, tv, eedata); break; case CX18_CARD_YUAN_MPC718: @@ -365,7 +367,25 @@ static void cx18_process_eeprom(struct cx18 *cx) from the model number. Use the cardtype module option if you have one of these preproduction models. */ switch (tv.model) { - case 74000 ... 74999: + case 74301: /* Retail models */ + case 74321: + case 74351: /* OEM models */ + case 74361: + /* Digital side is s5h1411/tda18271 */ + cx->card = cx18_get_card(CX18_CARD_HVR_1600_S5H1411); + break; + case 74021: /* Retail models */ + case 74031: + case 74041: + case 74141: + case 74541: /* OEM models */ + case 74551: + case 74591: + case 74651: + case 74691: + case 74751: + case 74891: + /* Digital side is s5h1409/mxl5005s */ cx->card = cx18_get_card(CX18_CARD_HVR_1600_ESMT); break; case 0x718: @@ -377,7 +397,8 @@ static void cx18_process_eeprom(struct cx18 *cx) CX18_ERR("Invalid EEPROM\n"); return; default: - CX18_ERR("Unknown model %d, defaulting to HVR-1600\n", tv.model); + CX18_ERR("Unknown model %d, defaulting to original HVR-1600 " + "(cardtype=1)\n", tv.model); cx->card = cx18_get_card(CX18_CARD_HVR_1600_ESMT); break; } diff --git a/drivers/media/video/cx18/cx18-driver.h b/drivers/media/video/cx18/cx18-driver.h index 306caac..f736679 100644 --- a/drivers/media/video/cx18/cx18-driver.h +++ b/drivers/media/video/cx18/cx18-driver.h @@ -85,7 +85,8 @@ #define CX18_CARD_LEADTEK_PVR2100 6 /* Leadtek WinFast PVR2100 */ #define CX18_CARD_LEADTEK_DVR3100H 7 /* Leadtek WinFast DVR3100 H */ #define CX18_CARD_GOTVIEW_PCI_DVD3 8 /* GoTView PCI DVD3 Hybrid */ -#define CX18_CARD_LAST 8 +#define CX18_CARD_HVR_1600_S5H1411 9 /* Hauppauge HVR 1600 s5h1411/tda18271*/ +#define CX18_CARD_LAST 9 #define CX18_ENC_STREAM_TYPE_MPG 0 #define CX18_ENC_STREAM_TYPE_TS 1 diff --git a/drivers/media/video/cx18/cx18-dvb.c b/drivers/media/video/cx18/cx18-dvb.c index f0381d6..f41922b 100644 --- a/drivers/media/video/cx18/cx18-dvb.c +++ b/drivers/media/video/cx18/cx18-dvb.c @@ -29,6 +29,8 @@ #include "cx18-gpio.h" #include "s5h1409.h" #include "mxl5005s.h" +#include "s5h1411.h" +#include "tda18271.h" #include "zl10353.h" #include <linux/firmware.h> @@ -77,6 +79,32 @@ static struct s5h1409_config hauppauge_hvr1600_config = { }; /* + * CX18_CARD_HVR_1600_S5H1411 + */ +static struct s5h1411_config hcw_s5h1411_config = { + .output_mode = S5H1411_SERIAL_OUTPUT, + .gpio = S5H1411_GPIO_OFF, + .vsb_if = S5H1411_IF_44000, + .qam_if = S5H1411_IF_4000, + .inversion = S5H1411_INVERSION_ON, + .status_mode = S5H1411_DEMODLOCKING, + .mpeg_timing = S5H1411_MPEGTIMING_CONTINOUS_NONINVERTING_CLOCK, +}; + +static struct tda18271_std_map hauppauge_tda18271_std_map = { + .atsc_6 = { .if_freq = 5380, .agc_mode = 3, .std = 3, + .if_lvl = 6, .rfagc_top = 0x37 }, + .qam_6 = { .if_freq = 4000, .agc_mode = 3, .std = 0, + .if_lvl = 6, .rfagc_top = 0x37 }, +}; + +static struct tda18271_config hauppauge_tda18271_config = { + .std_map = &hauppauge_tda18271_std_map, + .gate = TDA18271_GATE_DIGITAL, + .output_opt = TDA18271_OUTPUT_LT_OFF, +}; + +/* * CX18_CARD_LEADTEK_DVR3100H */ /* Information/confirmation of proper config values provided by Terry Wu */ @@ -244,6 +272,7 @@ static int cx18_dvb_start_feed(struct dvb_demux_feed *feed) switch (cx->card->type) { case CX18_CARD_HVR_1600_ESMT: case CX18_CARD_HVR_1600_SAMSUNG: + case CX18_CARD_HVR_1600_S5H1411: v = cx18_read_reg(cx, CX18_REG_DMUX_NUM_PORT_0_CONTROL); v |= 0x00400000; /* Serial Mode */ v |= 0x00002000; /* Data Length - Byte */ @@ -455,6 +484,15 @@ static int dvb_register(struct cx18_stream *stream) ret = 0; } break; + case CX18_CARD_HVR_1600_S5H1411: + dvb->fe = dvb_attach(s5h1411_attach, + &hcw_s5h1411_config, + &cx->i2c_adap[0]); + if (dvb->fe != NULL) + dvb_attach(tda18271_attach, dvb->fe, + 0x60, &cx->i2c_adap[0], + &hauppauge_tda18271_config); + break; case CX18_CARD_LEADTEK_DVR3100H: dvb->fe = dvb_attach(zl10353_attach, &leadtek_dvr3100h_demod, diff --git a/drivers/media/video/cx23885/cx23885-i2c.c b/drivers/media/video/cx23885/cx23885-i2c.c index ed3d8f5..307ff54 100644 --- a/drivers/media/video/cx23885/cx23885-i2c.c +++ b/drivers/media/video/cx23885/cx23885-i2c.c @@ -122,10 +122,6 @@ static int i2c_sendbytes(struct i2c_adapter *i2c_adap, if (!i2c_wait_done(i2c_adap)) goto eio; - if (!i2c_slave_did_ack(i2c_adap)) { - retval = -ENXIO; - goto err; - } if (i2c_debug) { printk(" <W %02x %02x", msg->addr << 1, msg->buf[0]); if (!(ctrl & I2C_NOSTOP)) @@ -158,7 +154,6 @@ static int i2c_sendbytes(struct i2c_adapter *i2c_adap, eio: retval = -EIO; - err: if (i2c_debug) printk(KERN_ERR " ERR: %d\n", retval); return retval; @@ -209,10 +204,6 @@ static int i2c_readbytes(struct i2c_adapter *i2c_adap, if (!i2c_wait_done(i2c_adap)) goto eio; - if (cnt == 0 && !i2c_slave_did_ack(i2c_adap)) { - retval = -ENXIO; - goto err; - } msg->buf[cnt] = cx_read(bus->reg_rdata) & 0xff; if (i2c_debug) { dprintk(1, " %02x", msg->buf[cnt]); @@ -224,7 +215,6 @@ static int i2c_readbytes(struct i2c_adapter *i2c_adap, eio: retval = -EIO; - err: if (i2c_debug) printk(KERN_ERR " ERR: %d\n", retval); return retval; diff --git a/drivers/media/video/cx25840/cx25840-core.c b/drivers/media/video/cx25840/cx25840-core.c index 6fc09dd..35796e0 100644 --- a/drivers/media/video/cx25840/cx25840-core.c +++ b/drivers/media/video/cx25840/cx25840-core.c @@ -2015,7 +2015,8 @@ static int cx25840_probe(struct i2c_client *client, kfree(state); return err; } - v4l2_ctrl_cluster(2, &state->volume); + if (!is_cx2583x(state)) + v4l2_ctrl_cluster(2, &state->volume); v4l2_ctrl_handler_setup(&state->hdl); if (client->dev.platform_data) { diff --git a/drivers/media/video/gspca/zc3xx.c b/drivers/media/video/gspca/zc3xx.c index 865216e..47236a5 100644 --- a/drivers/media/video/gspca/zc3xx.c +++ b/drivers/media/video/gspca/zc3xx.c @@ -5793,7 +5793,7 @@ static void usb_exchange(struct gspca_dev *gspca_dev, break; default: /* case 0xdd: * delay */ - msleep(action->val / 64 + 10); + msleep(action->idx); break; } action++; @@ -5830,7 +5830,7 @@ static void setmatrix(struct gspca_dev *gspca_dev) [SENSOR_GC0305] = gc0305_matrix, [SENSOR_HDCS2020b] = NULL, [SENSOR_HV7131B] = NULL, - [SENSOR_HV7131R] = NULL, + [SENSOR_HV7131R] = po2030_matrix, [SENSOR_ICM105A] = po2030_matrix, [SENSOR_MC501CB] = NULL, [SENSOR_MT9V111_1] = gc0305_matrix, @@ -5936,6 +5936,7 @@ static void setquality(struct gspca_dev *gspca_dev) case SENSOR_ADCM2700: case SENSOR_GC0305: case SENSOR_HV7131B: + case SENSOR_HV7131R: case SENSOR_OV7620: case SENSOR_PAS202B: case SENSOR_PO2030: @@ -6108,11 +6109,13 @@ static void send_unknown(struct gspca_dev *gspca_dev, int sensor) reg_w(gspca_dev, 0x02, 0x003b); reg_w(gspca_dev, 0x00, 0x0038); break; + case SENSOR_HV7131R: case SENSOR_PAS202B: reg_w(gspca_dev, 0x03, 0x003b); reg_w(gspca_dev, 0x0c, 0x003a); reg_w(gspca_dev, 0x0b, 0x0039); - reg_w(gspca_dev, 0x0b, 0x0038); + if (sensor == SENSOR_PAS202B) + reg_w(gspca_dev, 0x0b, 0x0038); break; } } @@ -6704,10 +6707,13 @@ static int sd_start(struct gspca_dev *gspca_dev) reg_w(gspca_dev, 0x02, 0x003b); reg_w(gspca_dev, 0x00, 0x0038); break; + case SENSOR_HV7131R: case SENSOR_PAS202B: reg_w(gspca_dev, 0x03, 0x003b); reg_w(gspca_dev, 0x0c, 0x003a); reg_w(gspca_dev, 0x0b, 0x0039); + if (sd->sensor == SENSOR_HV7131R) + reg_w(gspca_dev, 0x50, ZC3XX_R11D_GLOBALGAIN); break; } @@ -6720,6 +6726,7 @@ static int sd_start(struct gspca_dev *gspca_dev) break; case SENSOR_PAS202B: case SENSOR_GC0305: + case SENSOR_HV7131R: case SENSOR_TAS5130C: reg_r(gspca_dev, 0x0008); /* fall thru */ @@ -6760,6 +6767,12 @@ static int sd_start(struct gspca_dev *gspca_dev) /* ms-win + */ reg_w(gspca_dev, 0x40, 0x0117); break; + case SENSOR_HV7131R: + i2c_write(gspca_dev, 0x25, 0x04, 0x00); /* exposure */ + i2c_write(gspca_dev, 0x26, 0x93, 0x00); + i2c_write(gspca_dev, 0x27, 0xe0, 0x00); + reg_w(gspca_dev, 0x00, ZC3XX_R1A7_CALCGLOBALMEAN); + break; case SENSOR_GC0305: case SENSOR_TAS5130C: reg_w(gspca_dev, 0x09, 0x01ad); /* (from win traces) */ @@ -6808,9 +6821,17 @@ static void sd_pkt_scan(struct gspca_dev *gspca_dev, { struct sd *sd = (struct sd *) gspca_dev; - if (data[0] == 0xff && data[1] == 0xd8) { /* start of frame */ + /* check the JPEG end of frame */ + if (len >= 3 + && data[len - 3] == 0xff && data[len - 2] == 0xd9) { +/*fixme: what does the last byte mean?*/ gspca_frame_add(gspca_dev, LAST_PACKET, - NULL, 0); + data, len - 1); + return; + } + + /* check the JPEG start of a frame */ + if (data[0] == 0xff && data[1] == 0xd8) { /* put the JPEG header in the new frame */ gspca_frame_add(gspca_dev, FIRST_PACKET, sd->jpeg_hdr, JPEG_HDR_SZ); diff --git a/drivers/media/video/hdpvr/hdpvr-core.c b/drivers/media/video/hdpvr/hdpvr-core.c index a6572e5..a27d93b 100644 --- a/drivers/media/video/hdpvr/hdpvr-core.c +++ b/drivers/media/video/hdpvr/hdpvr-core.c @@ -283,6 +283,7 @@ static int hdpvr_probe(struct usb_interface *interface, struct hdpvr_device *dev; struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *endpoint; + struct i2c_client *client; size_t buffer_size; int i; int retval = -ENOMEM; @@ -381,13 +382,21 @@ static int hdpvr_probe(struct usb_interface *interface, #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) retval = hdpvr_register_i2c_adapter(dev); if (retval < 0) { - v4l2_err(&dev->v4l2_dev, "registering i2c adapter failed\n"); + v4l2_err(&dev->v4l2_dev, "i2c adapter register failed\n"); goto error; } - retval = hdpvr_register_i2c_ir(dev); - if (retval < 0) - v4l2_err(&dev->v4l2_dev, "registering i2c IR devices failed\n"); + client = hdpvr_register_ir_rx_i2c(dev); + if (!client) { + v4l2_err(&dev->v4l2_dev, "i2c IR RX device register failed\n"); + goto reg_fail; + } + + client = hdpvr_register_ir_tx_i2c(dev); + if (!client) { + v4l2_err(&dev->v4l2_dev, "i2c IR TX device register failed\n"); + goto reg_fail; + } #endif /* let the user know what node this device is now attached to */ @@ -395,6 +404,10 @@ static int hdpvr_probe(struct usb_interface *interface, video_device_node_name(dev->video_dev)); return 0; +reg_fail: +#if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) + i2c_del_adapter(&dev->i2c_adapter); +#endif error: if (dev) { /* Destroy single thread */ @@ -424,6 +437,9 @@ static void hdpvr_disconnect(struct usb_interface *interface) mutex_lock(&dev->io_mutex); hdpvr_cancel_queue(dev); mutex_unlock(&dev->io_mutex); +#if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE) + i2c_del_adapter(&dev->i2c_adapter); +#endif video_unregister_device(dev->video_dev); atomic_dec(&dev_nr); } diff --git a/drivers/media/video/hdpvr/hdpvr-i2c.c b/drivers/media/video/hdpvr/hdpvr-i2c.c index 89b71fa..e53fa55 100644 --- a/drivers/media/video/hdpvr/hdpvr-i2c.c +++ b/drivers/media/video/hdpvr/hdpvr-i2c.c @@ -31,26 +31,34 @@ #define Z8F0811_IR_RX_I2C_ADDR 0x71 -static struct i2c_board_info hdpvr_i2c_board_info = { - I2C_BOARD_INFO("ir_tx_z8f0811_hdpvr", Z8F0811_IR_TX_I2C_ADDR), - I2C_BOARD_INFO("ir_rx_z8f0811_hdpvr", Z8F0811_IR_RX_I2C_ADDR), -}; +struct i2c_client *hdpvr_register_ir_tx_i2c(struct hdpvr_device *dev) +{ + struct IR_i2c_init_data *init_data = &dev->ir_i2c_init_data; + struct i2c_board_info hdpvr_ir_tx_i2c_board_info = { + I2C_BOARD_INFO("ir_tx_z8f0811_hdpvr", Z8F0811_IR_TX_I2C_ADDR), + }; + + init_data->name = "HD-PVR"; + hdpvr_ir_tx_i2c_board_info.platform_data = init_data; -int hdpvr_register_i2c_ir(struct hdpvr_device *dev) + return i2c_new_device(&dev->i2c_adapter, &hdpvr_ir_tx_i2c_board_info); +} + +struct i2c_client *hdpvr_register_ir_rx_i2c(struct hdpvr_device *dev) { - struct i2c_client *c; struct IR_i2c_init_data *init_data = &dev->ir_i2c_init_data; + struct i2c_board_info hdpvr_ir_rx_i2c_board_info = { + I2C_BOARD_INFO("ir_rx_z8f0811_hdpvr", Z8F0811_IR_RX_I2C_ADDR), + }; /* Our default information for ir-kbd-i2c.c to use */ init_data->ir_codes = RC_MAP_HAUPPAUGE_NEW; init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR; init_data->type = RC_TYPE_RC5; - init_data->name = "HD PVR"; - hdpvr_i2c_board_info.platform_data = init_data; - - c = i2c_new_device(&dev->i2c_adapter, &hdpvr_i2c_board_info); + init_data->name = "HD-PVR"; + hdpvr_ir_rx_i2c_board_info.platform_data = init_data; - return (c == NULL) ? -ENODEV : 0; + return i2c_new_device(&dev->i2c_adapter, &hdpvr_ir_rx_i2c_board_info); } static int hdpvr_i2c_read(struct hdpvr_device *dev, int bus, diff --git a/drivers/media/video/hdpvr/hdpvr.h b/drivers/media/video/hdpvr/hdpvr.h index ee74e3b..072f23c 100644 --- a/drivers/media/video/hdpvr/hdpvr.h +++ b/drivers/media/video/hdpvr/hdpvr.h @@ -313,7 +313,8 @@ int hdpvr_cancel_queue(struct hdpvr_device *dev); /* i2c adapter registration */ int hdpvr_register_i2c_adapter(struct hdpvr_device *dev); -int hdpvr_register_i2c_ir(struct hdpvr_device *dev); +struct i2c_client *hdpvr_register_ir_rx_i2c(struct hdpvr_device *dev); +struct i2c_client *hdpvr_register_ir_tx_i2c(struct hdpvr_device *dev); /*========================================================================*/ /* buffer management */ diff --git a/drivers/media/video/ir-kbd-i2c.c b/drivers/media/video/ir-kbd-i2c.c index d2b20ad..a221ad6 100644 --- a/drivers/media/video/ir-kbd-i2c.c +++ b/drivers/media/video/ir-kbd-i2c.c @@ -128,6 +128,19 @@ static int get_key_haup(struct IR_i2c *ir, u32 *ir_key, u32 *ir_raw) static int get_key_haup_xvr(struct IR_i2c *ir, u32 *ir_key, u32 *ir_raw) { + int ret; + unsigned char buf[1] = { 0 }; + + /* + * This is the same apparent "are you ready?" poll command observed + * watching Windows driver traffic and implemented in lirc_zilog. With + * this added, we get far saner remote behavior with z8 chips on usb + * connected devices, even with the default polling interval of 100ms. + */ + ret = i2c_master_send(ir->c, buf, 1); + if (ret != 1) + return (ret < 0) ? ret : -EINVAL; + return get_key_haup_common (ir, ir_key, ir_raw, 6, 3); } diff --git a/drivers/media/video/ivtv/ivtv-irq.c b/drivers/media/video/ivtv/ivtv-irq.c index 9b4faf0..9c29e96 100644 --- a/drivers/media/video/ivtv/ivtv-irq.c +++ b/drivers/media/video/ivtv/ivtv-irq.c @@ -628,22 +628,66 @@ static void ivtv_irq_enc_pio_complete(struct ivtv *itv) static void ivtv_irq_dma_err(struct ivtv *itv) { u32 data[CX2341X_MBOX_MAX_DATA]; + u32 status; del_timer(&itv->dma_timer); + ivtv_api_get_data(&itv->enc_mbox, IVTV_MBOX_DMA_END, 2, data); + status = read_reg(IVTV_REG_DMASTATUS); IVTV_DEBUG_WARN("DMA ERROR %08x %08x %08x %d\n", data[0], data[1], - read_reg(IVTV_REG_DMASTATUS), itv->cur_dma_stream); - write_reg(read_reg(IVTV_REG_DMASTATUS) & 3, IVTV_REG_DMASTATUS); + status, itv->cur_dma_stream); + /* + * We do *not* write back to the IVTV_REG_DMASTATUS register to + * clear the error status, if either the encoder write (0x02) or + * decoder read (0x01) bus master DMA operation do not indicate + * completed. We can race with the DMA engine, which may have + * transitioned to completed status *after* we read the register. + * Setting a IVTV_REG_DMASTATUS flag back to "busy" status, after the + * DMA engine has completed, will cause the DMA engine to stop working. + */ + status &= 0x3; + if (status == 0x3) + write_reg(status, IVTV_REG_DMASTATUS); + if (!test_bit(IVTV_F_I_UDMA, &itv->i_flags) && itv->cur_dma_stream >= 0 && itv->cur_dma_stream < IVTV_MAX_STREAMS) { struct ivtv_stream *s = &itv->streams[itv->cur_dma_stream]; - /* retry */ - if (s->type >= IVTV_DEC_STREAM_TYPE_MPG) + if (s->type >= IVTV_DEC_STREAM_TYPE_MPG) { + /* retry */ + /* + * FIXME - handle cases of DMA error similar to + * encoder below, except conditioned on status & 0x1 + */ ivtv_dma_dec_start(s); - else - ivtv_dma_enc_start(s); - return; + return; + } else { + if ((status & 0x2) == 0) { + /* + * CX2341x Bus Master DMA write is ongoing. + * Reset the timer and let it complete. + */ + itv->dma_timer.expires = + jiffies + msecs_to_jiffies(600); + add_timer(&itv->dma_timer); + return; + } + + if (itv->dma_retries < 3) { + /* + * CX2341x Bus Master DMA write has ended. + * Retry the write, starting with the first + * xfer segment. Just retrying the current + * segment is not sufficient. + */ + s->sg_processed = 0; + itv->dma_retries++; + ivtv_dma_enc_start_xfer(s); + return; + } + /* Too many retries, give up on this one */ + } + } if (test_bit(IVTV_F_I_UDMA, &itv->i_flags)) { ivtv_udma_start(itv); diff --git a/drivers/media/video/mem2mem_testdev.c b/drivers/media/video/mem2mem_testdev.c index c179041..e7e7178 100644 --- a/drivers/media/video/mem2mem_testdev.c +++ b/drivers/media/video/mem2mem_testdev.c @@ -1011,7 +1011,6 @@ static int m2mtest_remove(struct platform_device *pdev) v4l2_m2m_release(dev->m2m_dev); del_timer_sync(&dev->timer); video_unregister_device(dev->vfd); - video_device_release(dev->vfd); v4l2_device_unregister(&dev->v4l2_dev); kfree(dev); diff --git a/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c b/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c index ccc8849..451ecd4 100644 --- a/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c +++ b/drivers/media/video/pvrusb2/pvrusb2-i2c-core.c @@ -597,7 +597,6 @@ static void pvr2_i2c_register_ir(struct pvr2_hdw *hdw) init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR; init_data->type = RC_TYPE_RC5; init_data->name = hdw->hdw_desc->description; - init_data->polling_interval = 260; /* ms From lirc_zilog */ /* IR Receiver */ info.addr = 0x71; info.platform_data = init_data; diff --git a/drivers/media/video/s2255drv.c b/drivers/media/video/s2255drv.c index b63f8ca..561909b 100644 --- a/drivers/media/video/s2255drv.c +++ b/drivers/media/video/s2255drv.c @@ -57,7 +57,7 @@ #include <linux/usb.h> #define S2255_MAJOR_VERSION 1 -#define S2255_MINOR_VERSION 20 +#define S2255_MINOR_VERSION 21 #define S2255_RELEASE 0 #define S2255_VERSION KERNEL_VERSION(S2255_MAJOR_VERSION, \ S2255_MINOR_VERSION, \ @@ -312,9 +312,9 @@ struct s2255_fh { }; /* current cypress EEPROM firmware version */ -#define S2255_CUR_USB_FWVER ((3 << 8) | 6) +#define S2255_CUR_USB_FWVER ((3 << 8) | 11) /* current DSP FW version */ -#define S2255_CUR_DSP_FWVER 8 +#define S2255_CUR_DSP_FWVER 10102 /* Need DSP version 5+ for video status feature */ #define S2255_MIN_DSP_STATUS 5 #define S2255_MIN_DSP_COLORFILTER 8 @@ -492,9 +492,11 @@ static void planar422p_to_yuv_packed(const unsigned char *in, static void s2255_reset_dsppower(struct s2255_dev *dev) { - s2255_vendor_req(dev, 0x40, 0x0b0b, 0x0b0b, NULL, 0, 1); + s2255_vendor_req(dev, 0x40, 0x0b0b, 0x0b01, NULL, 0, 1); msleep(10); s2255_vendor_req(dev, 0x50, 0x0000, 0x0000, NULL, 0, 1); + msleep(600); + s2255_vendor_req(dev, 0x10, 0x0000, 0x0000, NULL, 0, 1); return; } diff --git a/drivers/media/video/saa7115.c b/drivers/media/video/saa7115.c index f35459d..0db9092 100644 --- a/drivers/media/video/saa7115.c +++ b/drivers/media/video/saa7115.c @@ -1565,7 +1565,7 @@ static int saa711x_probe(struct i2c_client *client, chip_id = name[5]; /* Check whether this chip is part of the saa711x series */ - if (memcmp(name, "1f711", 5)) { + if (memcmp(name + 1, "f711", 4)) { v4l_dbg(1, debug, client, "chip found @ 0x%x (ID %s) does not match a known saa711x chip.\n", client->addr << 1, name); return -ENODEV; diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index e9a3eab..8c1d85e 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -621,7 +621,7 @@ static int __init memstick_init(void) { int rc; - workqueue = create_freezeable_workqueue("kmemstick"); + workqueue = create_freezable_workqueue("kmemstick"); if (!workqueue) return -ENOMEM; diff --git a/drivers/message/fusion/mptbase.h b/drivers/message/fusion/mptbase.h index f71f229..1735c84 100644 --- a/drivers/message/fusion/mptbase.h +++ b/drivers/message/fusion/mptbase.h @@ -76,8 +76,8 @@ #define COPYRIGHT "Copyright (c) 1999-2008 " MODULEAUTHOR #endif -#define MPT_LINUX_VERSION_COMMON "3.04.17" -#define MPT_LINUX_PACKAGE_NAME "@(#)mptlinux-3.04.17" +#define MPT_LINUX_VERSION_COMMON "3.04.18" +#define MPT_LINUX_PACKAGE_NAME "@(#)mptlinux-3.04.18" #define WHAT_MAGIC_STRING "@" "(" "#" ")" #define show_mptmod_ver(s,ver) \ diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c index a3856ed..e8deb8e 100644 --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -597,6 +597,13 @@ mptctl_event_process(MPT_ADAPTER *ioc, EventNotificationReply_t *pEvReply) } static int +mptctl_release(struct inode *inode, struct file *filep) +{ + fasync_helper(-1, filep, 0, &async_queue); + return 0; +} + +static int mptctl_fasync(int fd, struct file *filep, int mode) { MPT_ADAPTER *ioc; @@ -2815,6 +2822,7 @@ static const struct file_operations mptctl_fops = { .llseek = no_llseek, .fasync = mptctl_fasync, .unlocked_ioctl = mptctl_ioctl, + .release = mptctl_release, #ifdef CONFIG_COMPAT .compat_ioctl = compat_mpctl_ioctl, #endif diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c index 59b8f53..0d9b82a 100644 --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -1873,8 +1873,9 @@ mptscsih_abort(struct scsi_cmnd * SCpnt) } out: - printk(MYIOC_s_INFO_FMT "task abort: %s (sc=%p)\n", - ioc->name, ((retval == SUCCESS) ? "SUCCESS" : "FAILED"), SCpnt); + printk(MYIOC_s_INFO_FMT "task abort: %s (rv=%04x) (sc=%p) (sn=%ld)\n", + ioc->name, ((retval == SUCCESS) ? "SUCCESS" : "FAILED"), retval, + SCpnt, SCpnt->serial_number); return retval; } @@ -1911,7 +1912,7 @@ mptscsih_dev_reset(struct scsi_cmnd * SCpnt) vdevice = SCpnt->device->hostdata; if (!vdevice || !vdevice->vtarget) { - retval = SUCCESS; + retval = 0; goto out; } diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c index 6a1f940..c45e630 100644 --- a/drivers/mfd/asic3.c +++ b/drivers/mfd/asic3.c @@ -143,9 +143,9 @@ static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc) unsigned long flags; struct asic3 *asic; - desc->chip->ack(irq); + desc->irq_data.chip->irq_ack(&desc->irq_data); - asic = desc->handler_data; + asic = get_irq_data(irq); for (iter = 0 ; iter < MAX_ASIC_ISR_LOOPS; iter++) { u32 status; diff --git a/drivers/mfd/davinci_voicecodec.c b/drivers/mfd/davinci_voicecodec.c index 33c923d..fdd8a1b 100644 --- a/drivers/mfd/davinci_voicecodec.c +++ b/drivers/mfd/davinci_voicecodec.c @@ -118,12 +118,12 @@ static int __init davinci_vc_probe(struct platform_device *pdev) /* Voice codec interface client */ cell = &davinci_vc->cells[DAVINCI_VC_VCIF_CELL]; - cell->name = "davinci_vcif"; + cell->name = "davinci-vcif"; cell->driver_data = davinci_vc; /* Voice codec CQ93VC client */ cell = &davinci_vc->cells[DAVINCI_VC_CQ93VC_CELL]; - cell->name = "cq93vc"; + cell->name = "cq93vc-codec"; cell->driver_data = davinci_vc; ret = mfd_add_devices(&pdev->dev, pdev->id, davinci_vc->cells, diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c index 627cf57..e9018d1 100644 --- a/drivers/mfd/tps6586x.c +++ b/drivers/mfd/tps6586x.c @@ -150,12 +150,12 @@ static inline int __tps6586x_write(struct i2c_client *client, static inline int __tps6586x_writes(struct i2c_client *client, int reg, int len, uint8_t *val) { - int ret; + int ret, i; - ret = i2c_smbus_write_i2c_block_data(client, reg, len, val); - if (ret < 0) { - dev_err(&client->dev, "failed writings to 0x%02x\n", reg); - return ret; + for (i = 0; i < len; i++) { + ret = __tps6586x_write(client, reg + i, *(val + i)); + if (ret < 0) + return ret; } return 0; diff --git a/drivers/mfd/ucb1x00-ts.c b/drivers/mfd/ucb1x00-ts.c index 000cb41..92b85e2 100644 --- a/drivers/mfd/ucb1x00-ts.c +++ b/drivers/mfd/ucb1x00-ts.c @@ -385,12 +385,18 @@ static int ucb1x00_ts_add(struct ucb1x00_dev *dev) idev->close = ucb1x00_ts_close; __set_bit(EV_ABS, idev->evbit); - __set_bit(ABS_X, idev->absbit); - __set_bit(ABS_Y, idev->absbit); - __set_bit(ABS_PRESSURE, idev->absbit); input_set_drvdata(idev, ts); + ucb1x00_adc_enable(ts->ucb); + ts->x_res = ucb1x00_ts_read_xres(ts); + ts->y_res = ucb1x00_ts_read_yres(ts); + ucb1x00_adc_disable(ts->ucb); + + input_set_abs_params(idev, ABS_X, 0, ts->x_res, 0, 0); + input_set_abs_params(idev, ABS_Y, 0, ts->y_res, 0, 0); + input_set_abs_params(idev, ABS_PRESSURE, 0, 0, 0, 0); + err = input_register_device(idev); if (err) goto fail; diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index 41233c7..f4016a0 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -246,6 +246,16 @@ static int wm8994_suspend(struct device *dev) struct wm8994 *wm8994 = dev_get_drvdata(dev); int ret; + /* Don't actually go through with the suspend if the CODEC is + * still active (eg, for audio passthrough from CP. */ + ret = wm8994_reg_read(wm8994, WM8994_POWER_MANAGEMENT_1); + if (ret < 0) { + dev_err(dev, "Failed to read power status: %d\n", ret); + } else if (ret & WM8994_VMID_SEL_MASK) { + dev_dbg(dev, "CODEC still active, ignoring suspend\n"); + return 0; + } + /* GPIO configuration state is saved here since we may be configuring * the GPIO alternate functions even if we're not using the gpiolib * driver for them. @@ -261,6 +271,8 @@ static int wm8994_suspend(struct device *dev) if (ret < 0) dev_err(dev, "Failed to save LDO registers: %d\n", ret); + wm8994->suspended = true; + ret = regulator_bulk_disable(wm8994->num_supplies, wm8994->supplies); if (ret != 0) { @@ -276,6 +288,10 @@ static int wm8994_resume(struct device *dev) struct wm8994 *wm8994 = dev_get_drvdata(dev); int ret; + /* We may have lied to the PM core about suspending */ + if (!wm8994->suspended) + return 0; + ret = regulator_bulk_enable(wm8994->num_supplies, wm8994->supplies); if (ret != 0) { @@ -298,6 +314,8 @@ static int wm8994_resume(struct device *dev) if (ret < 0) dev_err(dev, "Failed to restore GPIO registers: %d\n", ret); + wm8994->suspended = false; + return 0; } #endif diff --git a/drivers/misc/bmp085.c b/drivers/misc/bmp085.c index 63ee4c1..b6e1c9a 100644 --- a/drivers/misc/bmp085.c +++ b/drivers/misc/bmp085.c @@ -449,6 +449,7 @@ static const struct i2c_device_id bmp085_id[] = { { "bmp085", 0 }, { } }; +MODULE_DEVICE_TABLE(i2c, bmp085_id); static struct i2c_driver bmp085_driver = { .driver = { diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c index 5f6852d..44d4475 100644 --- a/drivers/misc/tifm_core.c +++ b/drivers/misc/tifm_core.c @@ -329,7 +329,7 @@ static int __init tifm_init(void) { int rc; - workqueue = create_freezeable_workqueue("tifm"); + workqueue = create_freezable_workqueue("tifm"); if (!workqueue) return -ENOMEM; diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c index 4d2ea8e..6df5a55 100644 --- a/drivers/misc/vmw_balloon.c +++ b/drivers/misc/vmw_balloon.c @@ -785,7 +785,7 @@ static int __init vmballoon_init(void) if (x86_hyper != &x86_hyper_vmware) return -ENODEV; - vmballoon_wq = create_freezeable_workqueue("vmmemctl"); + vmballoon_wq = create_freezable_workqueue("vmmemctl"); if (!vmballoon_wq) { pr_err("failed to create workqueue\n"); return -ENOMEM; diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 6625c05..150b5f3 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1529,7 +1529,7 @@ void mmc_rescan(struct work_struct *work) * still present */ if (host->bus_ops && host->bus_ops->detect && !host->bus_dead - && mmc_card_is_removable(host)) + && !(host->caps & MMC_CAP_NONREMOVABLE)) host->bus_ops->detect(host); /* diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 5c4a54d..ebc62ad 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -792,7 +792,6 @@ int mmc_attach_sdio(struct mmc_host *host) */ mmc_release_host(host); err = mmc_add_card(host->card); - mmc_claim_host(host); if (err) goto remove_added; @@ -805,12 +804,12 @@ int mmc_attach_sdio(struct mmc_host *host) goto remove_added; } + mmc_claim_host(host); return 0; remove_added: /* Remove without lock if the device has been added. */ - mmc_release_host(host); mmc_sdio_remove(host); mmc_claim_host(host); remove: diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 4b8dcd5..2d6de3e 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -14,6 +14,7 @@ #include <linux/ioport.h> #include <linux/device.h> #include <linux/interrupt.h> +#include <linux/kernel.h> #include <linux/delay.h> #include <linux/err.h> #include <linux/highmem.h> @@ -283,19 +284,19 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data, u32 remain, success; /* Calculate how far we are into the transfer */ - remain = readl(host->base + MMCIDATACNT) << 2; + remain = readl(host->base + MMCIDATACNT); success = data->blksz * data->blocks - remain; dev_dbg(mmc_dev(host->mmc), "MCI ERROR IRQ (status %08x)\n", status); if (status & MCI_DATACRCFAIL) { /* Last block was not successful */ - host->data_xfered = ((success / data->blksz) - 1 * data->blksz); + host->data_xfered = round_down(success - 1, data->blksz); data->error = -EILSEQ; } else if (status & MCI_DATATIMEOUT) { - host->data_xfered = success; + host->data_xfered = round_down(success, data->blksz); data->error = -ETIMEDOUT; } else if (status & (MCI_TXUNDERRUN|MCI_RXOVERRUN)) { - host->data_xfered = success; + host->data_xfered = round_down(success, data->blksz); data->error = -EIO; } @@ -319,7 +320,7 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data, if (status & MCI_DATABLOCKEND) dev_err(mmc_dev(host->mmc), "stray MCI_DATABLOCKEND interrupt\n"); - if (status & MCI_DATAEND) { + if (status & MCI_DATAEND || data->error) { mmci_stop_data(host); if (!data->error) diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index a8c3e1c..4aaa88f 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -1230,10 +1230,32 @@ static int inval_cache_and_wait_for_operation( sleep_time = chip_op_time / 2; for (;;) { + if (chip->state != chip_state) { + /* Someone's suspended the operation: sleep */ + DECLARE_WAITQUEUE(wait, current); + set_current_state(TASK_UNINTERRUPTIBLE); + add_wait_queue(&chip->wq, &wait); + mutex_unlock(&chip->mutex); + schedule(); + remove_wait_queue(&chip->wq, &wait); + mutex_lock(&chip->mutex); + continue; + } + status = map_read(map, cmd_adr); if (map_word_andequal(map, status, status_OK, status_OK)) break; + if (chip->erase_suspended && chip_state == FL_ERASING) { + /* Erase suspend occured while sleep: reset timeout */ + timeo = reset_timeo; + chip->erase_suspended = 0; + } + if (chip->write_suspended && chip_state == FL_WRITING) { + /* Write suspend occured while sleep: reset timeout */ + timeo = reset_timeo; + chip->write_suspended = 0; + } if (!timeo) { map_write(map, CMD(0x70), cmd_adr); chip->state = FL_STATUS; @@ -1257,27 +1279,6 @@ static int inval_cache_and_wait_for_operation( timeo--; } mutex_lock(&chip->mutex); - - while (chip->state != chip_state) { - /* Someone's suspended the operation: sleep */ - DECLARE_WAITQUEUE(wait, current); - set_current_state(TASK_UNINTERRUPTIBLE); - add_wait_queue(&chip->wq, &wait); - mutex_unlock(&chip->mutex); - schedule(); - remove_wait_queue(&chip->wq, &wait); - mutex_lock(&chip->mutex); - } - if (chip->erase_suspended && chip_state == FL_ERASING) { - /* Erase suspend occured while sleep: reset timeout */ - timeo = reset_timeo; - chip->erase_suspended = 0; - } - if (chip->write_suspended && chip_state == FL_WRITING) { - /* Write suspend occured while sleep: reset timeout */ - timeo = reset_timeo; - chip->write_suspended = 0; - } } /* Done and happy. */ diff --git a/drivers/mtd/chips/jedec_probe.c b/drivers/mtd/chips/jedec_probe.c index d72a5fb..4e1be51 100644 --- a/drivers/mtd/chips/jedec_probe.c +++ b/drivers/mtd/chips/jedec_probe.c @@ -1935,14 +1935,14 @@ static void jedec_reset(u32 base, struct map_info *map, struct cfi_private *cfi) } -static int cfi_jedec_setup(struct cfi_private *p_cfi, int index) +static int cfi_jedec_setup(struct map_info *map, struct cfi_private *cfi, int index) { int i,num_erase_regions; uint8_t uaddr; - if (! (jedec_table[index].devtypes & p_cfi->device_type)) { + if (!(jedec_table[index].devtypes & cfi->device_type)) { DEBUG(MTD_DEBUG_LEVEL1, "Rejecting potential %s with incompatible %d-bit device type\n", - jedec_table[index].name, 4 * (1<<p_cfi->device_type)); + jedec_table[index].name, 4 * (1<<cfi->device_type)); return 0; } @@ -1950,27 +1950,28 @@ static int cfi_jedec_setup(struct cfi_private *p_cfi, int index) num_erase_regions = jedec_table[index].nr_regions; - p_cfi->cfiq = kmalloc(sizeof(struct cfi_ident) + num_erase_regions * 4, GFP_KERNEL); - if (!p_cfi->cfiq) { + cfi->cfiq = kmalloc(sizeof(struct cfi_ident) + num_erase_regions * 4, GFP_KERNEL); + if (!cfi->cfiq) { //xx printk(KERN_WARNING "%s: kmalloc failed for CFI ident structure\n", map->name); return 0; } - memset(p_cfi->cfiq,0,sizeof(struct cfi_ident)); + memset(cfi->cfiq, 0, sizeof(struct cfi_ident)); - p_cfi->cfiq->P_ID = jedec_table[index].cmd_set; - p_cfi->cfiq->NumEraseRegions = jedec_table[index].nr_regions; - p_cfi->cfiq->DevSize = jedec_table[index].dev_size; - p_cfi->cfi_mode = CFI_MODE_JEDEC; + cfi->cfiq->P_ID = jedec_table[index].cmd_set; + cfi->cfiq->NumEraseRegions = jedec_table[index].nr_regions; + cfi->cfiq->DevSize = jedec_table[index].dev_size; + cfi->cfi_mode = CFI_MODE_JEDEC; + cfi->sector_erase_cmd = CMD(0x30); for (i=0; i<num_erase_regions; i++){ - p_cfi->cfiq->EraseRegionInfo[i] = jedec_table[index].regions[i]; + cfi->cfiq->EraseRegionInfo[i] = jedec_table[index].regions[i]; } - p_cfi->cmdset_priv = NULL; + cfi->cmdset_priv = NULL; /* This may be redundant for some cases, but it doesn't hurt */ - p_cfi->mfr = jedec_table[index].mfr_id; - p_cfi->id = jedec_table[index].dev_id; + cfi->mfr = jedec_table[index].mfr_id; + cfi->id = jedec_table[index].dev_id; uaddr = jedec_table[index].uaddr; @@ -1978,8 +1979,8 @@ static int cfi_jedec_setup(struct cfi_private *p_cfi, int index) our brains explode when we see the datasheets talking about address lines numbered from A-1 to A18. The CFI table has unlock addresses in device-words according to the mode the device is connected in */ - p_cfi->addr_unlock1 = unlock_addrs[uaddr].addr1 / p_cfi->device_type; - p_cfi->addr_unlock2 = unlock_addrs[uaddr].addr2 / p_cfi->device_type; + cfi->addr_unlock1 = unlock_addrs[uaddr].addr1 / cfi->device_type; + cfi->addr_unlock2 = unlock_addrs[uaddr].addr2 / cfi->device_type; return 1; /* ok */ } @@ -2175,7 +2176,7 @@ static int jedec_probe_chip(struct map_info *map, __u32 base, "MTD %s(): matched device 0x%x,0x%x unlock_addrs: 0x%.4x 0x%.4x\n", __func__, cfi->mfr, cfi->id, cfi->addr_unlock1, cfi->addr_unlock2 ); - if (!cfi_jedec_setup(cfi, i)) + if (!cfi_jedec_setup(map, cfi, i)) return 0; goto ok_out; } diff --git a/drivers/mtd/maps/amd76xrom.c b/drivers/mtd/maps/amd76xrom.c index 77d64ce..92de7e3 100644 --- a/drivers/mtd/maps/amd76xrom.c +++ b/drivers/mtd/maps/amd76xrom.c @@ -151,6 +151,7 @@ static int __devinit amd76xrom_init_one (struct pci_dev *pdev, printk(KERN_ERR MOD_NAME " %s(): Unable to register resource %pR - kernel bug?\n", __func__, &window->rsrc); + return -EBUSY; } diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index cb20c67..e0a2373 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -413,7 +413,6 @@ error3: error2: list_del(&new->list); error1: - kfree(new); return ret; } diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index 15682ec..28af71c 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -968,6 +968,6 @@ static void __exit omap_nand_exit(void) module_init(omap_nand_init); module_exit(omap_nand_exit); -MODULE_ALIAS(DRIVER_NAME); +MODULE_ALIAS("platform:" DRIVER_NAME); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Glue layer for NAND flash on TI OMAP boards"); diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c index d9d7efb..6322d1f 100644 --- a/drivers/mtd/nand/r852.c +++ b/drivers/mtd/nand/r852.c @@ -930,7 +930,7 @@ int r852_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) init_completion(&dev->dma_done); - dev->card_workqueue = create_freezeable_workqueue(DRV_NAME); + dev->card_workqueue = create_freezable_workqueue(DRV_NAME); if (!dev->card_workqueue) goto error9; diff --git a/drivers/mtd/onenand/generic.c b/drivers/mtd/onenand/generic.c index e789149..ac08750 100644 --- a/drivers/mtd/onenand/generic.c +++ b/drivers/mtd/onenand/generic.c @@ -131,7 +131,7 @@ static struct platform_driver generic_onenand_driver = { .remove = __devexit_p(generic_onenand_remove), }; -MODULE_ALIAS(DRIVER_NAME); +MODULE_ALIAS("platform:" DRIVER_NAME); static int __init generic_onenand_init(void) { diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c index ac31f46..c849cac 100644 --- a/drivers/mtd/onenand/omap2.c +++ b/drivers/mtd/onenand/omap2.c @@ -860,7 +860,7 @@ static void __exit omap2_onenand_exit(void) module_init(omap2_onenand_init); module_exit(omap2_onenand_exit); -MODULE_ALIAS(DRIVER_NAME); +MODULE_ALIAS("platform:" DRIVER_NAME); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jarkko Lavinen <jarkko.lavinen@nokia.com>"); MODULE_DESCRIPTION("Glue layer for OneNAND flash on OMAP2 / OMAP3"); diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c index 67822cf..ac0d6a8 100644 --- a/drivers/mtd/sm_ftl.c +++ b/drivers/mtd/sm_ftl.c @@ -1258,7 +1258,7 @@ static struct mtd_blktrans_ops sm_ftl_ops = { static __init int sm_module_init(void) { int error = 0; - cache_flush_workqueue = create_freezeable_workqueue("smflush"); + cache_flush_workqueue = create_freezable_workqueue("smflush"); if (IS_ERR(cache_flush_workqueue)) return PTR_ERR(cache_flush_workqueue); diff --git a/drivers/net/ariadne.c b/drivers/net/ariadne.c index 39214e5..7ca0ede 100644 --- a/drivers/net/ariadne.c +++ b/drivers/net/ariadne.c @@ -425,11 +425,6 @@ static irqreturn_t ariadne_interrupt(int irq, void *data) int csr0, boguscnt; int handled = 0; - if (dev == NULL) { - printk(KERN_WARNING "ariadne_interrupt(): irq for unknown device.\n"); - return IRQ_NONE; - } - lance->RAP = CSR0; /* PCnet-ISA Controller Status */ if (!(lance->RDP & INTR)) /* Check if any interrupt has been */ diff --git a/drivers/net/atl1c/atl1c_main.c b/drivers/net/atl1c/atl1c_main.c index a699bbf..3824382 100644 --- a/drivers/net/atl1c/atl1c_main.c +++ b/drivers/net/atl1c/atl1c_main.c @@ -48,6 +48,7 @@ static DEFINE_PCI_DEVICE_TABLE(atl1c_pci_tbl) = { {PCI_DEVICE(PCI_VENDOR_ID_ATTANSIC, PCI_DEVICE_ID_ATHEROS_L2C_B)}, {PCI_DEVICE(PCI_VENDOR_ID_ATTANSIC, PCI_DEVICE_ID_ATHEROS_L2C_B2)}, {PCI_DEVICE(PCI_VENDOR_ID_ATTANSIC, PCI_DEVICE_ID_ATHEROS_L1D)}, + {PCI_DEVICE(PCI_VENDOR_ID_ATTANSIC, PCI_DEVICE_ID_ATHEROS_L1D_2_0)}, /* required last entry */ { 0 } }; diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index 0c7811f..a179cc6 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -1786,6 +1786,10 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter, spin_lock_bh(&adapter->mcc_lock); wrb = wrb_from_mccq(adapter); + if (!wrb) { + status = -EBUSY; + goto err; + } req = nonemb_cmd->va; sge = nonembedded_sgl(wrb); @@ -1801,6 +1805,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter, status = be_mcc_notify_wait(adapter); +err: spin_unlock_bh(&adapter->mcc_lock); return status; } diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index de40d3b..28a32a6 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -312,11 +312,9 @@ void be_link_status_update(struct be_adapter *adapter, bool link_up) if (adapter->link_up != link_up) { adapter->link_speed = -1; if (link_up) { - netif_start_queue(netdev); netif_carrier_on(netdev); printk(KERN_INFO "%s: Link up\n", netdev->name); } else { - netif_stop_queue(netdev); netif_carrier_off(netdev); printk(KERN_INFO "%s: Link down\n", netdev->name); } @@ -2628,8 +2626,6 @@ static void be_netdev_init(struct net_device *netdev) netif_napi_add(netdev, &adapter->tx_eq.napi, be_poll_tx_mcc, BE_NAPI_WEIGHT); - - netif_stop_queue(netdev); } static void be_unmap_pci_bars(struct be_adapter *adapter) diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h index 8e41837..8849699 100644 --- a/drivers/net/bnx2x/bnx2x.h +++ b/drivers/net/bnx2x/bnx2x.h @@ -22,8 +22,8 @@ * (you will need to reboot afterwards) */ /* #define BNX2X_STOP_ON_ERROR */ -#define DRV_MODULE_VERSION "1.62.00-4" -#define DRV_MODULE_RELDATE "2011/01/18" +#define DRV_MODULE_VERSION "1.62.00-6" +#define DRV_MODULE_RELDATE "2011/01/30" #define BNX2X_BC_VER 0x040200 #define BNX2X_MULTI_QUEUE @@ -1211,6 +1211,7 @@ struct bnx2x { /* DCBX Negotation results */ struct dcbx_features dcbx_local_feat; u32 dcbx_error; + u32 pending_max; }; /** @@ -1613,19 +1614,23 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms, #define BNX2X_BTR 4 #define MAX_SPQ_PENDING 8 - -/* CMNG constants - derived from lab experiments, and not from system spec calculations !!! */ -#define DEF_MIN_RATE 100 -/* resolution of the rate shaping timer - 100 usec */ -#define RS_PERIODIC_TIMEOUT_USEC 100 -/* resolution of fairness algorithm in usecs - - coefficient for calculating the actual t fair */ -#define T_FAIR_COEF 10000000 +/* CMNG constants, as derived from system spec calculations */ +/* default MIN rate in case VNIC min rate is configured to zero - 100Mbps */ +#define DEF_MIN_RATE 100 +/* resolution of the rate shaping timer - 400 usec */ +#define RS_PERIODIC_TIMEOUT_USEC 400 /* number of bytes in single QM arbitration cycle - - coefficient for calculating the fairness timer */ -#define QM_ARB_BYTES 40000 -#define FAIR_MEM 2 + * coefficient for calculating the fairness timer */ +#define QM_ARB_BYTES 160000 +/* resolution of Min algorithm 1:100 */ +#define MIN_RES 100 +/* how many bytes above threshold for the minimal credit of Min algorithm*/ +#define MIN_ABOVE_THRESH 32768 +/* Fairness algorithm integration time coefficient - + * for calculating the actual Tfair */ +#define T_FAIR_COEF ((MIN_ABOVE_THRESH + QM_ARB_BYTES) * 8 * MIN_RES) +/* Memory of fairness algorithm . 2 cycles */ +#define FAIR_MEM 2 #define ATTN_NIG_FOR_FUNC (1L << 8) diff --git a/drivers/net/bnx2x/bnx2x_cmn.c b/drivers/net/bnx2x/bnx2x_cmn.c index 710ce5d..a71b329 100644 --- a/drivers/net/bnx2x/bnx2x_cmn.c +++ b/drivers/net/bnx2x/bnx2x_cmn.c @@ -259,10 +259,44 @@ static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue, #endif } +/* Timestamp option length allowed for TPA aggregation: + * + * nop nop kind length echo val + */ +#define TPA_TSTAMP_OPT_LEN 12 +/** + * Calculate the approximate value of the MSS for this + * aggregation using the first packet of it. + * + * @param bp + * @param parsing_flags Parsing flags from the START CQE + * @param len_on_bd Total length of the first packet for the + * aggregation. + */ +static inline u16 bnx2x_set_lro_mss(struct bnx2x *bp, u16 parsing_flags, + u16 len_on_bd) +{ + /* TPA arrgregation won't have an IP options and TCP options + * other than timestamp. + */ + u16 hdrs_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct tcphdr); + + + /* Check if there was a TCP timestamp, if there is it's will + * always be 12 bytes length: nop nop kind length echo val. + * + * Otherwise FW would close the aggregation. + */ + if (parsing_flags & PARSING_FLAGS_TIME_STAMP_EXIST_FLAG) + hdrs_len += TPA_TSTAMP_OPT_LEN; + + return len_on_bd - hdrs_len; +} + static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp, struct sk_buff *skb, struct eth_fast_path_rx_cqe *fp_cqe, - u16 cqe_idx) + u16 cqe_idx, u16 parsing_flags) { struct sw_rx_page *rx_pg, old_rx_pg; u16 len_on_bd = le16_to_cpu(fp_cqe->len_on_bd); @@ -275,8 +309,8 @@ static int bnx2x_fill_frag_skb(struct bnx2x *bp, struct bnx2x_fastpath *fp, /* This is needed in order to enable forwarding support */ if (frag_size) - skb_shinfo(skb)->gso_size = min((u32)SGE_PAGE_SIZE, - max(frag_size, (u32)len_on_bd)); + skb_shinfo(skb)->gso_size = bnx2x_set_lro_mss(bp, parsing_flags, + len_on_bd); #ifdef BNX2X_STOP_ON_ERROR if (pages > min_t(u32, 8, MAX_SKB_FRAGS)*SGE_PAGE_SIZE*PAGES_PER_SGE) { @@ -344,6 +378,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp, if (likely(new_skb)) { /* fix ip xsum and give it to the stack */ /* (no need to map the new skb) */ + u16 parsing_flags = + le16_to_cpu(cqe->fast_path_cqe.pars_flags.flags); prefetch(skb); prefetch(((char *)(skb)) + L1_CACHE_BYTES); @@ -373,9 +409,9 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp, } if (!bnx2x_fill_frag_skb(bp, fp, skb, - &cqe->fast_path_cqe, cqe_idx)) { - if ((le16_to_cpu(cqe->fast_path_cqe. - pars_flags.flags) & PARSING_FLAGS_VLAN)) + &cqe->fast_path_cqe, cqe_idx, + parsing_flags)) { + if (parsing_flags & PARSING_FLAGS_VLAN) __vlan_hwaccel_put_tag(skb, le16_to_cpu(cqe->fast_path_cqe. vlan_tag)); @@ -703,19 +739,20 @@ u16 bnx2x_get_mf_speed(struct bnx2x *bp) { u16 line_speed = bp->link_vars.line_speed; if (IS_MF(bp)) { - u16 maxCfg = (bp->mf_config[BP_VN(bp)] & - FUNC_MF_CFG_MAX_BW_MASK) >> - FUNC_MF_CFG_MAX_BW_SHIFT; - /* Calculate the current MAX line speed limit for the DCC - * capable devices + u16 maxCfg = bnx2x_extract_max_cfg(bp, + bp->mf_config[BP_VN(bp)]); + + /* Calculate the current MAX line speed limit for the MF + * devices */ - if (IS_MF_SD(bp)) { + if (IS_MF_SI(bp)) + line_speed = (line_speed * maxCfg) / 100; + else { /* SD mode */ u16 vn_max_rate = maxCfg * 100; if (vn_max_rate < line_speed) line_speed = vn_max_rate; - } else /* IS_MF_SI(bp)) */ - line_speed = (line_speed * maxCfg) / 100; + } } return line_speed; @@ -959,6 +996,23 @@ void bnx2x_free_skbs(struct bnx2x *bp) bnx2x_free_rx_skbs(bp); } +void bnx2x_update_max_mf_config(struct bnx2x *bp, u32 value) +{ + /* load old values */ + u32 mf_cfg = bp->mf_config[BP_VN(bp)]; + + if (value != bnx2x_extract_max_cfg(bp, mf_cfg)) { + /* leave all but MAX value */ + mf_cfg &= ~FUNC_MF_CFG_MAX_BW_MASK; + + /* set new MAX value */ + mf_cfg |= (value << FUNC_MF_CFG_MAX_BW_SHIFT) + & FUNC_MF_CFG_MAX_BW_MASK; + + bnx2x_fw_command(bp, DRV_MSG_CODE_SET_MF_BW, mf_cfg); + } +} + static void bnx2x_free_msix_irqs(struct bnx2x *bp) { int i, offset = 1; @@ -1427,6 +1481,11 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) bnx2x_set_eth_mac(bp, 1); + if (bp->pending_max) { + bnx2x_update_max_mf_config(bp, bp->pending_max); + bp->pending_max = 0; + } + if (bp->port.pmf) bnx2x_initial_phy_init(bp, load_mode); diff --git a/drivers/net/bnx2x/bnx2x_cmn.h b/drivers/net/bnx2x/bnx2x_cmn.h index 03eb4d6..85ea7f2 100644 --- a/drivers/net/bnx2x/bnx2x_cmn.h +++ b/drivers/net/bnx2x/bnx2x_cmn.h @@ -341,6 +341,15 @@ void bnx2x_dcbx_init(struct bnx2x *bp); */ int bnx2x_set_power_state(struct bnx2x *bp, pci_power_t state); +/** + * Updates MAX part of MF configuration in HW + * (if required) + * + * @param bp + * @param value + */ +void bnx2x_update_max_mf_config(struct bnx2x *bp, u32 value); + /* dev_close main block */ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode); @@ -1044,4 +1053,24 @@ static inline void storm_memset_cmng(struct bnx2x *bp, void bnx2x_acquire_phy_lock(struct bnx2x *bp); void bnx2x_release_phy_lock(struct bnx2x *bp); +/** + * Extracts MAX BW part from MF configuration. + * + * @param bp + * @param mf_cfg + * + * @return u16 + */ +static inline u16 bnx2x_extract_max_cfg(struct bnx2x *bp, u32 mf_cfg) +{ + u16 max_cfg = (mf_cfg & FUNC_MF_CFG_MAX_BW_MASK) >> + FUNC_MF_CFG_MAX_BW_SHIFT; + if (!max_cfg) { + BNX2X_ERR("Illegal configuration detected for Max BW - " + "using 100 instead\n"); + max_cfg = 100; + } + return max_cfg; +} + #endif /* BNX2X_CMN_H */ diff --git a/drivers/net/bnx2x/bnx2x_ethtool.c b/drivers/net/bnx2x/bnx2x_ethtool.c index 5b44a8b..7e92f9d 100644 --- a/drivers/net/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/bnx2x/bnx2x_ethtool.c @@ -238,7 +238,7 @@ static int bnx2x_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) speed |= (cmd->speed_hi << 16); if (IS_MF_SI(bp)) { - u32 param = 0; + u32 part; u32 line_speed = bp->link_vars.line_speed; /* use 10G if no link detected */ @@ -251,23 +251,22 @@ static int bnx2x_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) REQ_BC_VER_4_SET_MF_BW); return -EINVAL; } - if (line_speed < speed) { - BNX2X_DEV_INFO("New speed should be less or equal " - "to actual line speed\n"); + + part = (speed * 100) / line_speed; + + if (line_speed < speed || !part) { + BNX2X_DEV_INFO("Speed setting should be in a range " + "from 1%% to 100%% " + "of actual line speed\n"); return -EINVAL; } - /* load old values */ - param = bp->mf_config[BP_VN(bp)]; - - /* leave only MIN value */ - param &= FUNC_MF_CFG_MIN_BW_MASK; - /* set new MAX value */ - param |= (((speed * 100) / line_speed) - << FUNC_MF_CFG_MAX_BW_SHIFT) - & FUNC_MF_CFG_MAX_BW_MASK; + if (bp->state != BNX2X_STATE_OPEN) + /* store value for following "load" */ + bp->pending_max = part; + else + bnx2x_update_max_mf_config(bp, part); - bnx2x_fw_command(bp, DRV_MSG_CODE_SET_MF_BW, param); return 0; } @@ -1781,9 +1780,7 @@ static int bnx2x_test_nvram(struct bnx2x *bp) { 0x100, 0x350 }, /* manuf_info */ { 0x450, 0xf0 }, /* feature_info */ { 0x640, 0x64 }, /* upgrade_key_info */ - { 0x6a4, 0x64 }, { 0x708, 0x70 }, /* manuf_key_info */ - { 0x778, 0x70 }, { 0, 0 } }; __be32 buf[0x350 / 4]; @@ -1933,11 +1930,11 @@ static void bnx2x_self_test(struct net_device *dev, buf[4] = 1; etest->flags |= ETH_TEST_FL_FAILED; } - if (bp->port.pmf) - if (bnx2x_link_test(bp, is_serdes) != 0) { - buf[5] = 1; - etest->flags |= ETH_TEST_FL_FAILED; - } + + if (bnx2x_link_test(bp, is_serdes) != 0) { + buf[5] = 1; + etest->flags |= ETH_TEST_FL_FAILED; + } #ifdef BNX2X_EXTRA_DEBUG bnx2x_panic_dump(bp); diff --git a/drivers/net/bnx2x/bnx2x_init.h b/drivers/net/bnx2x/bnx2x_init.h index 5a268e9..fa6dbe3 100644 --- a/drivers/net/bnx2x/bnx2x_init.h +++ b/drivers/net/bnx2x/bnx2x_init.h @@ -241,7 +241,7 @@ static const struct { /* Block IGU, MISC, PXP and PXP2 parity errors as long as we don't * want to handle "system kill" flow at the moment. */ - BLOCK_PRTY_INFO(PXP, 0x3ffffff, 0x3ffffff, 0x3ffffff, 0x3ffffff), + BLOCK_PRTY_INFO(PXP, 0x7ffffff, 0x3ffffff, 0x3ffffff, 0x7ffffff), BLOCK_PRTY_INFO_0(PXP2, 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff), BLOCK_PRTY_INFO_1(PXP2, 0x7ff, 0x7f, 0x7f, 0x7ff), BLOCK_PRTY_INFO(HC, 0x7, 0x7, 0x7, 0), diff --git a/drivers/net/bnx2x/bnx2x_link.c b/drivers/net/bnx2x/bnx2x_link.c index 7160ec5..dd1210f 100644 --- a/drivers/net/bnx2x/bnx2x_link.c +++ b/drivers/net/bnx2x/bnx2x_link.c @@ -3948,48 +3948,6 @@ static u8 bnx2x_8073_8727_external_rom_boot(struct bnx2x *bp, return rc; } -static void bnx2x_8073_set_xaui_low_power_mode(struct bnx2x *bp, - struct bnx2x_phy *phy) -{ - u16 val; - bnx2x_cl45_read(bp, phy, - MDIO_PMA_DEVAD, MDIO_PMA_REG_8073_CHIP_REV, &val); - - if (val == 0) { - /* Mustn't set low power mode in 8073 A0 */ - return; - } - - /* Disable PLL sequencer (use read-modify-write to clear bit 13) */ - bnx2x_cl45_read(bp, phy, - MDIO_XS_DEVAD, MDIO_XS_PLL_SEQUENCER, &val); - val &= ~(1<<13); - bnx2x_cl45_write(bp, phy, - MDIO_XS_DEVAD, MDIO_XS_PLL_SEQUENCER, val); - - /* PLL controls */ - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x805E, 0x1077); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x805D, 0x0000); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x805C, 0x030B); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x805B, 0x1240); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x805A, 0x2490); - - /* Tx Controls */ - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x80A7, 0x0C74); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x80A6, 0x9041); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x80A5, 0x4640); - - /* Rx Controls */ - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x80FE, 0x01C4); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x80FD, 0x9249); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, 0x80FC, 0x2015); - - /* Enable PLL sequencer (use read-modify-write to set bit 13) */ - bnx2x_cl45_read(bp, phy, MDIO_XS_DEVAD, MDIO_XS_PLL_SEQUENCER, &val); - val |= (1<<13); - bnx2x_cl45_write(bp, phy, MDIO_XS_DEVAD, MDIO_XS_PLL_SEQUENCER, val); -} - /******************************************************************/ /* BCM8073 PHY SECTION */ /******************************************************************/ @@ -4148,8 +4106,6 @@ static u8 bnx2x_8073_config_init(struct bnx2x_phy *phy, bnx2x_8073_set_pause_cl37(params, phy, vars); - bnx2x_8073_set_xaui_low_power_mode(bp, phy); - bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_M8051_MSGOUT_REG, &tmp1); @@ -6519,6 +6475,18 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED1_MASK, 0x80); + + /* Tell LED3 to blink on source */ + bnx2x_cl45_read(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LINK_SIGNAL, + &val); + val &= ~(7<<6); + val |= (1<<6); /* A83B[8:6]= 1 */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LINK_SIGNAL, + val); } break; } @@ -7720,10 +7688,13 @@ static u8 bnx2x_8073_common_init_phy(struct bnx2x *bp, struct bnx2x_phy phy[PORT_MAX]; struct bnx2x_phy *phy_blk[PORT_MAX]; u16 val; - s8 port; + s8 port = 0; s8 port_of_path = 0; - - bnx2x_ext_phy_hw_reset(bp, 0); + u32 swap_val, swap_override; + swap_val = REG_RD(bp, NIG_REG_PORT_SWAP); + swap_override = REG_RD(bp, NIG_REG_STRAP_OVERRIDE); + port ^= (swap_val && swap_override); + bnx2x_ext_phy_hw_reset(bp, port); /* PART1 - Reset both phys */ for (port = PORT_MAX - 1; port >= PORT_0; port--) { u32 shmem_base, shmem2_base; diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c index 8cdcf5b3..aa03233 100644 --- a/drivers/net/bnx2x/bnx2x_main.c +++ b/drivers/net/bnx2x/bnx2x_main.c @@ -1974,13 +1974,22 @@ static void bnx2x_init_vn_minmax(struct bnx2x *bp, int vn) vn_max_rate = 0; } else { + u32 maxCfg = bnx2x_extract_max_cfg(bp, vn_cfg); + vn_min_rate = ((vn_cfg & FUNC_MF_CFG_MIN_BW_MASK) >> FUNC_MF_CFG_MIN_BW_SHIFT) * 100; - /* If min rate is zero - set it to 1 */ + /* If fairness is enabled (not all min rates are zeroes) and + if current min rate is zero - set it to 1. + This is a requirement of the algorithm. */ if (bp->vn_weight_sum && (vn_min_rate == 0)) vn_min_rate = DEF_MIN_RATE; - vn_max_rate = ((vn_cfg & FUNC_MF_CFG_MAX_BW_MASK) >> - FUNC_MF_CFG_MAX_BW_SHIFT) * 100; + + if (IS_MF_SI(bp)) + /* maxCfg in percents of linkspeed */ + vn_max_rate = (bp->link_vars.line_speed * maxCfg) / 100; + else + /* maxCfg is absolute in 100Mb units */ + vn_max_rate = maxCfg * 100; } DP(NETIF_MSG_IFUP, @@ -2006,7 +2015,8 @@ static void bnx2x_init_vn_minmax(struct bnx2x *bp, int vn) m_fair_vn.vn_credit_delta = max_t(u32, (vn_min_rate * (T_FAIR_COEF / (8 * bp->vn_weight_sum))), - (bp->cmng.fair_vars.fair_threshold * 2)); + (bp->cmng.fair_vars.fair_threshold + + MIN_ABOVE_THRESH)); DP(NETIF_MSG_IFUP, "m_fair_vn.vn_credit_delta %d\n", m_fair_vn.vn_credit_delta); } @@ -2082,8 +2092,9 @@ static void bnx2x_cmng_fns_init(struct bnx2x *bp, u8 read_cfg, u8 cmng_type) bnx2x_calc_vn_weight_sum(bp); /* calculate and set min-max rate for each vn */ - for (vn = VN_0; vn < E1HVN_MAX; vn++) - bnx2x_init_vn_minmax(bp, vn); + if (bp->port.pmf) + for (vn = VN_0; vn < E1HVN_MAX; vn++) + bnx2x_init_vn_minmax(bp, vn); /* always enable rate shaping and fairness */ bp->cmng.flags.cmng_enables |= @@ -2152,13 +2163,6 @@ static void bnx2x_link_attn(struct bnx2x *bp) bnx2x_stats_handle(bp, STATS_EVENT_LINK_UP); } - /* indicate link status only if link status actually changed */ - if (prev_link_status != bp->link_vars.link_status) - bnx2x_link_report(bp); - - if (IS_MF(bp)) - bnx2x_link_sync_notify(bp); - if (bp->link_vars.link_up && bp->link_vars.line_speed) { int cmng_fns = bnx2x_get_cmng_fns_mode(bp); @@ -2170,6 +2174,13 @@ static void bnx2x_link_attn(struct bnx2x *bp) DP(NETIF_MSG_IFUP, "single function mode without fairness\n"); } + + if (IS_MF(bp)) + bnx2x_link_sync_notify(bp); + + /* indicate link status only if link status actually changed */ + if (prev_link_status != bp->link_vars.link_status) + bnx2x_link_report(bp); } void bnx2x__link_status_update(struct bnx2x *bp) @@ -2301,15 +2312,10 @@ static void bnx2x_rxq_set_mac_filters(struct bnx2x *bp, u16 cl_id, u32 filters) /* accept matched ucast */ drop_all_ucast = 0; } - if (filters & BNX2X_ACCEPT_MULTICAST) { + if (filters & BNX2X_ACCEPT_MULTICAST) /* accept matched mcast */ drop_all_mcast = 0; - if (IS_MF_SI(bp)) - /* since mcast addresses won't arrive with ovlan, - * fw needs to accept all of them in - * switch-independent mode */ - accp_all_mcast = 1; - } + if (filters & BNX2X_ACCEPT_ALL_UNICAST) { /* accept all mcast */ drop_all_ucast = 0; @@ -4281,9 +4287,12 @@ void bnx2x_set_storm_rx_mode(struct bnx2x *bp) def_q_filters |= BNX2X_ACCEPT_UNICAST | BNX2X_ACCEPT_BROADCAST | BNX2X_ACCEPT_MULTICAST; #ifdef BCM_CNIC - cl_id = bnx2x_fcoe(bp, cl_id); - bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_UNICAST | - BNX2X_ACCEPT_MULTICAST); + if (!NO_FCOE(bp)) { + cl_id = bnx2x_fcoe(bp, cl_id); + bnx2x_rxq_set_mac_filters(bp, cl_id, + BNX2X_ACCEPT_UNICAST | + BNX2X_ACCEPT_MULTICAST); + } #endif break; @@ -4291,18 +4300,29 @@ void bnx2x_set_storm_rx_mode(struct bnx2x *bp) def_q_filters |= BNX2X_ACCEPT_UNICAST | BNX2X_ACCEPT_BROADCAST | BNX2X_ACCEPT_ALL_MULTICAST; #ifdef BCM_CNIC - cl_id = bnx2x_fcoe(bp, cl_id); - bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_UNICAST | - BNX2X_ACCEPT_MULTICAST); + /* + * Prevent duplication of multicast packets by configuring FCoE + * L2 Client to receive only matched unicast frames. + */ + if (!NO_FCOE(bp)) { + cl_id = bnx2x_fcoe(bp, cl_id); + bnx2x_rxq_set_mac_filters(bp, cl_id, + BNX2X_ACCEPT_UNICAST); + } #endif break; case BNX2X_RX_MODE_PROMISC: def_q_filters |= BNX2X_PROMISCUOUS_MODE; #ifdef BCM_CNIC - cl_id = bnx2x_fcoe(bp, cl_id); - bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_UNICAST | - BNX2X_ACCEPT_MULTICAST); + /* + * Prevent packets duplication by configuring DROP_ALL for FCoE + * L2 Client. + */ + if (!NO_FCOE(bp)) { + cl_id = bnx2x_fcoe(bp, cl_id); + bnx2x_rxq_set_mac_filters(bp, cl_id, BNX2X_ACCEPT_NONE); + } #endif /* pass management unicast packets as well */ llh_mask |= NIG_LLH0_BRB1_DRV_MASK_REG_LLH0_BRB1_DRV_MASK_UNCST; @@ -5296,10 +5316,6 @@ static int bnx2x_init_hw_common(struct bnx2x *bp, u32 load_code) } } - bp->port.need_hw_lock = bnx2x_hw_lock_required(bp, - bp->common.shmem_base, - bp->common.shmem2_base); - bnx2x_setup_fan_failure_detection(bp); /* clear PXP2 attentions */ @@ -5503,9 +5519,6 @@ static int bnx2x_init_hw_port(struct bnx2x *bp) bnx2x_init_block(bp, MCP_BLOCK, init_stage); bnx2x_init_block(bp, DMAE_BLOCK, init_stage); - bp->port.need_hw_lock = bnx2x_hw_lock_required(bp, - bp->common.shmem_base, - bp->common.shmem2_base); if (bnx2x_fan_failure_det_req(bp, bp->common.shmem_base, bp->common.shmem2_base, port)) { u32 reg_addr = (port ? MISC_REG_AEU_ENABLE1_FUNC_1_OUT_0 : @@ -8379,6 +8392,17 @@ static void __devinit bnx2x_get_port_hwinfo(struct bnx2x *bp) (ext_phy_type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_NOT_CONN)) bp->mdio.prtad = XGXS_EXT_PHY_ADDR(ext_phy_config); + + /* + * Check if hw lock is required to access MDC/MDIO bus to the PHY(s) + * In MF mode, it is set to cover self test cases + */ + if (IS_MF(bp)) + bp->port.need_hw_lock = 1; + else + bp->port.need_hw_lock = bnx2x_hw_lock_required(bp, + bp->common.shmem_base, + bp->common.shmem2_base); } static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp) diff --git a/drivers/net/bnx2x/bnx2x_stats.c b/drivers/net/bnx2x/bnx2x_stats.c index bda60d5..3445ded 100644 --- a/drivers/net/bnx2x/bnx2x_stats.c +++ b/drivers/net/bnx2x/bnx2x_stats.c @@ -1239,14 +1239,14 @@ void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event) if (unlikely(bp->panic)) return; + bnx2x_stats_stm[bp->stats_state][event].action(bp); + /* Protect a state change flow */ spin_lock_bh(&bp->stats_lock); state = bp->stats_state; bp->stats_state = bnx2x_stats_stm[state][event].next_state; spin_unlock_bh(&bp->stats_lock); - bnx2x_stats_stm[state][event].action(bp); - if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp)) DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n", state, event, bp->stats_state); diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 1024ae1..a5d5d0b 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -281,23 +281,23 @@ static inline int __check_agg_selection_timer(struct port *port) } /** - * __get_rx_machine_lock - lock the port's RX machine + * __get_state_machine_lock - lock the port's state machines * @port: the port we're looking at * */ -static inline void __get_rx_machine_lock(struct port *port) +static inline void __get_state_machine_lock(struct port *port) { - spin_lock_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_lock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); } /** - * __release_rx_machine_lock - unlock the port's RX machine + * __release_state_machine_lock - unlock the port's state machines * @port: the port we're looking at * */ -static inline void __release_rx_machine_lock(struct port *port) +static inline void __release_state_machine_lock(struct port *port) { - spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); } /** @@ -388,14 +388,14 @@ static u8 __get_duplex(struct port *port) } /** - * __initialize_port_locks - initialize a port's RX machine spinlock + * __initialize_port_locks - initialize a port's STATE machine spinlock * @port: the port we're looking at * */ static inline void __initialize_port_locks(struct port *port) { // make sure it isn't called twice - spin_lock_init(&(SLAVE_AD_INFO(port->slave).rx_machine_lock)); + spin_lock_init(&(SLAVE_AD_INFO(port->slave).state_machine_lock)); } //conversions @@ -1025,9 +1025,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) { rx_states_t last_state; - // Lock to prevent 2 instances of this function to run simultaneously(rx interrupt and periodic machine callback) - __get_rx_machine_lock(port); - // keep current State Machine state to compare later if it was changed last_state = port->sm_rx_state; @@ -1133,7 +1130,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) pr_err("%s: An illegal loopback occurred on adapter (%s).\n" "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", port->slave->dev->master->name, port->slave->dev->name); - __release_rx_machine_lock(port); return; } __update_selected(lacpdu, port); @@ -1153,7 +1149,6 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) break; } } - __release_rx_machine_lock(port); } /** @@ -2155,6 +2150,12 @@ void bond_3ad_state_machine_handler(struct work_struct *work) goto re_arm; } + /* Lock around state machines to protect data accessed + * by all (e.g., port->sm_vars). ad_rx_machine may run + * concurrently due to incoming LACPDU. + */ + __get_state_machine_lock(port); + ad_rx_machine(NULL, port); ad_periodic_machine(port); ad_port_selection_logic(port); @@ -2164,6 +2165,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work) // turn off the BEGIN bit, since we already handled it if (port->sm_vars & AD_PORT_BEGIN) port->sm_vars &= ~AD_PORT_BEGIN; + + __release_state_machine_lock(port); } re_arm: @@ -2200,7 +2203,10 @@ static void bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave, u case AD_TYPE_LACPDU: pr_debug("Received LACPDU on port %d\n", port->actor_port_number); + /* Protect against concurrent state machines */ + __get_state_machine_lock(port); ad_rx_machine(lacpdu, port); + __release_state_machine_lock(port); break; case AD_TYPE_MARKER: diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index 2c46a154..b28baff 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -264,7 +264,8 @@ struct ad_bond_info { struct ad_slave_info { struct aggregator aggregator; // 802.3ad aggregator structure struct port port; // 802.3ad port structure - spinlock_t rx_machine_lock; // To avoid race condition between callback and receive interrupt + spinlock_t state_machine_lock; /* mutex state machines vs. + incoming LACPDU */ u16 id; }; diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 986195e..5dec456 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -23,7 +23,7 @@ config CAN_SLCAN As only the sending and receiving of CAN frames is implemented, this driver should work with the (serial/USB) CAN hardware from: - www.canusb.com / www.can232.com / www.mictronic.com / www.canhack.de + www.canusb.com / www.can232.com / www.mictronics.de / www.canhack.de Userspace tools to attach the SLCAN line discipline (slcan_attach, slcand) can be found in the can-utils at the SocketCAN SVN, see diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 2532b96..57d2ffb 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -1109,7 +1109,7 @@ static ssize_t at91_sysfs_set_mb0_id(struct device *dev, return ret; } -static DEVICE_ATTR(mb0_id, S_IWUGO | S_IRUGO, +static DEVICE_ATTR(mb0_id, S_IWUSR | S_IRUGO, at91_sysfs_show_mb0_id, at91_sysfs_set_mb0_id); static struct attribute *at91_sysfs_attrs[] = { diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index b9a6d7a..366f5cc 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1618,7 +1618,7 @@ static ssize_t ican3_sysfs_set_term(struct device *dev, return count; } -static DEVICE_ATTR(termination, S_IWUGO | S_IRUGO, ican3_sysfs_show_term, +static DEVICE_ATTR(termination, S_IWUSR | S_IRUGO, ican3_sysfs_show_term, ican3_sysfs_set_term); static struct attribute *ican3_sysfs_attrs[] = { diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index 7ab534a..7513c45 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -940,7 +940,7 @@ static int mcp251x_open(struct net_device *net) goto open_unlock; } - priv->wq = create_freezeable_workqueue("mcp251x_wq"); + priv->wq = create_freezable_workqueue("mcp251x_wq"); INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler); INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler); diff --git a/drivers/net/can/mscan/Kconfig b/drivers/net/can/mscan/Kconfig index 27d1d39..d387069 100644 --- a/drivers/net/can/mscan/Kconfig +++ b/drivers/net/can/mscan/Kconfig @@ -1,5 +1,5 @@ config CAN_MSCAN - depends on CAN_DEV && (PPC || M68K || M68KNOMMU) + depends on CAN_DEV && (PPC || M68K) tristate "Support for Freescale MSCAN based chips" ---help--- The Motorola Scalable Controller Area Network (MSCAN) definition diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c index c42e972..e54712b 100644 --- a/drivers/net/can/pch_can.c +++ b/drivers/net/can/pch_can.c @@ -185,7 +185,7 @@ struct pch_can_priv { static struct can_bittiming_const pch_can_bittiming_const = { .name = KBUILD_MODNAME, - .tseg1_min = 1, + .tseg1_min = 2, .tseg1_max = 16, .tseg2_min = 1, .tseg2_max = 8, @@ -959,13 +959,13 @@ static void __devexit pch_can_remove(struct pci_dev *pdev) struct pch_can_priv *priv = netdev_priv(ndev); unregister_candev(priv->ndev); - pci_iounmap(pdev, priv->regs); if (priv->use_msi) pci_disable_msi(priv->dev); pci_release_regions(pdev); pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); pch_can_reset(priv); + pci_iounmap(pdev, priv->regs); free_candev(priv->ndev); } @@ -1238,6 +1238,7 @@ static int __devinit pch_can_probe(struct pci_dev *pdev, priv->use_msi = 0; } else { netdev_err(ndev, "PCH CAN opened with MSI\n"); + pci_set_master(pdev); priv->use_msi = 1; } diff --git a/drivers/net/can/softing/Kconfig b/drivers/net/can/softing/Kconfig index 92bd6bd..5de46a9 100644 --- a/drivers/net/can/softing/Kconfig +++ b/drivers/net/can/softing/Kconfig @@ -1,6 +1,6 @@ config CAN_SOFTING tristate "Softing Gmbh CAN generic support" - depends on CAN_DEV + depends on CAN_DEV && HAS_IOMEM ---help--- Support for CAN cards from Softing Gmbh & some cards from Vector Gmbh. @@ -18,7 +18,7 @@ config CAN_SOFTING config CAN_SOFTING_CS tristate "Softing Gmbh CAN pcmcia cards" depends on PCMCIA - select CAN_SOFTING + depends on CAN_SOFTING ---help--- Support for PCMCIA cards from Softing Gmbh & some cards from Vector Gmbh. diff --git a/drivers/net/can/softing/softing_cs.c b/drivers/net/can/softing/softing_cs.c index 300fe75..c11bb4d 100644 --- a/drivers/net/can/softing/softing_cs.c +++ b/drivers/net/can/softing/softing_cs.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <pcmcia/cistpl.h> #include <pcmcia/ds.h> diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index 5157e15..aeea9f9 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -633,6 +633,7 @@ static const struct net_device_ops softing_netdev_ops = { }; static const struct can_bittiming_const softing_btr_const = { + .name = "softing", .tseg1_min = 1, .tseg1_max = 16, .tseg2_min = 1, diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c index 7ff170c..302be4a 100644 --- a/drivers/net/cnic.c +++ b/drivers/net/cnic.c @@ -2760,6 +2760,8 @@ static u32 cnic_service_bnx2_queues(struct cnic_dev *dev) u32 status_idx = (u16) *cp->kcq1.status_idx_ptr; int kcqe_cnt; + /* status block index must be read before reading other fields */ + rmb(); cp->kwq_con_idx = *cp->kwq_con_idx_ptr; while ((kcqe_cnt = cnic_get_kcqes(dev, &cp->kcq1))) { @@ -2770,6 +2772,8 @@ static u32 cnic_service_bnx2_queues(struct cnic_dev *dev) barrier(); if (status_idx != *cp->kcq1.status_idx_ptr) { status_idx = (u16) *cp->kcq1.status_idx_ptr; + /* status block index must be read first */ + rmb(); cp->kwq_con_idx = *cp->kwq_con_idx_ptr; } else break; @@ -2888,6 +2892,8 @@ static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info) u32 last_status = *info->status_idx_ptr; int kcqe_cnt; + /* status block index must be read before reading the KCQ */ + rmb(); while ((kcqe_cnt = cnic_get_kcqes(dev, info))) { service_kcqes(dev, kcqe_cnt); @@ -2898,6 +2904,8 @@ static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info) break; last_status = *info->status_idx_ptr; + /* status block index must be read before reading the KCQ */ + rmb(); } return last_status; } @@ -2906,26 +2914,35 @@ static void cnic_service_bnx2x_bh(unsigned long data) { struct cnic_dev *dev = (struct cnic_dev *) data; struct cnic_local *cp = dev->cnic_priv; - u32 status_idx; + u32 status_idx, new_status_idx; if (unlikely(!test_bit(CNIC_F_CNIC_UP, &dev->flags))) return; - status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq1); + while (1) { + status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq1); - CNIC_WR16(dev, cp->kcq1.io_addr, cp->kcq1.sw_prod_idx + MAX_KCQ_IDX); + CNIC_WR16(dev, cp->kcq1.io_addr, + cp->kcq1.sw_prod_idx + MAX_KCQ_IDX); - if (BNX2X_CHIP_IS_E2(cp->chip_id)) { - status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq2); + if (!BNX2X_CHIP_IS_E2(cp->chip_id)) { + cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, USTORM_ID, + status_idx, IGU_INT_ENABLE, 1); + break; + } + + new_status_idx = cnic_service_bnx2x_kcq(dev, &cp->kcq2); + + if (new_status_idx != status_idx) + continue; CNIC_WR16(dev, cp->kcq2.io_addr, cp->kcq2.sw_prod_idx + MAX_KCQ_IDX); cnic_ack_igu_sb(dev, cp->bnx2x_igu_sb_id, IGU_SEG_ACCESS_DEF, status_idx, IGU_INT_ENABLE, 1); - } else { - cnic_ack_bnx2x_int(dev, cp->bnx2x_igu_sb_id, USTORM_ID, - status_idx, IGU_INT_ENABLE, 1); + + break; } } diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c index 56166ae..6aad64d 100644 --- a/drivers/net/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/cxgb4vf/cxgb4vf_main.c @@ -2040,7 +2040,7 @@ static int __devinit setup_debugfs(struct adapter *adapter) { int i; - BUG_ON(adapter->debugfs_root == NULL); + BUG_ON(IS_ERR_OR_NULL(adapter->debugfs_root)); /* * Debugfs support is best effort. @@ -2061,7 +2061,7 @@ static int __devinit setup_debugfs(struct adapter *adapter) */ static void cleanup_debugfs(struct adapter *adapter) { - BUG_ON(adapter->debugfs_root == NULL); + BUG_ON(IS_ERR_OR_NULL(adapter->debugfs_root)); /* * Unlike our sister routine cleanup_proc(), we don't need to remove @@ -2489,17 +2489,6 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev, struct net_device *netdev; /* - * Vet our module parameters. - */ - if (msi != MSI_MSIX && msi != MSI_MSI) { - dev_err(&pdev->dev, "bad module parameter msi=%d; must be %d" - " (MSI-X or MSI) or %d (MSI)\n", msi, MSI_MSIX, - MSI_MSI); - err = -EINVAL; - goto err_out; - } - - /* * Print our driver banner the first time we're called to initialize a * device. */ @@ -2711,11 +2700,11 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev, /* * Set up our debugfs entries. */ - if (cxgb4vf_debugfs_root) { + if (!IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) { adapter->debugfs_root = debugfs_create_dir(pci_name(pdev), cxgb4vf_debugfs_root); - if (adapter->debugfs_root == NULL) + if (IS_ERR_OR_NULL(adapter->debugfs_root)) dev_warn(&pdev->dev, "could not create debugfs" " directory"); else @@ -2770,7 +2759,7 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev, */ err_free_debugfs: - if (adapter->debugfs_root) { + if (!IS_ERR_OR_NULL(adapter->debugfs_root)) { cleanup_debugfs(adapter); debugfs_remove_recursive(adapter->debugfs_root); } @@ -2802,7 +2791,6 @@ err_release_regions: err_disable_device: pci_disable_device(pdev); -err_out: return err; } @@ -2840,7 +2828,7 @@ static void __devexit cxgb4vf_pci_remove(struct pci_dev *pdev) /* * Tear down our debugfs entries. */ - if (adapter->debugfs_root) { + if (!IS_ERR_OR_NULL(adapter->debugfs_root)) { cleanup_debugfs(adapter); debugfs_remove_recursive(adapter->debugfs_root); } @@ -2874,6 +2862,46 @@ static void __devexit cxgb4vf_pci_remove(struct pci_dev *pdev) } /* + * "Shutdown" quiesce the device, stopping Ingress Packet and Interrupt + * delivery. + */ +static void __devexit cxgb4vf_pci_shutdown(struct pci_dev *pdev) +{ + struct adapter *adapter; + int pidx; + + adapter = pci_get_drvdata(pdev); + if (!adapter) + return; + + /* + * Disable all Virtual Interfaces. This will shut down the + * delivery of all ingress packets into the chip for these + * Virtual Interfaces. + */ + for_each_port(adapter, pidx) { + struct net_device *netdev; + struct port_info *pi; + + if (!test_bit(pidx, &adapter->registered_device_map)) + continue; + + netdev = adapter->port[pidx]; + if (!netdev) + continue; + + pi = netdev_priv(netdev); + t4vf_enable_vi(adapter, pi->viid, false, false); + } + + /* + * Free up all Queues which will prevent further DMA and + * Interrupts allowing various internal pathways to drain. + */ + t4vf_free_sge_resources(adapter); +} + +/* * PCI Device registration data structures. */ #define CH_DEVICE(devid, idx) \ @@ -2906,6 +2934,7 @@ static struct pci_driver cxgb4vf_driver = { .id_table = cxgb4vf_pci_tbl, .probe = cxgb4vf_pci_probe, .remove = __devexit_p(cxgb4vf_pci_remove), + .shutdown = __devexit_p(cxgb4vf_pci_shutdown), }; /* @@ -2915,14 +2944,25 @@ static int __init cxgb4vf_module_init(void) { int ret; + /* + * Vet our module parameters. + */ + if (msi != MSI_MSIX && msi != MSI_MSI) { + printk(KERN_WARNING KBUILD_MODNAME + ": bad module parameter msi=%d; must be %d" + " (MSI-X or MSI) or %d (MSI)\n", + msi, MSI_MSIX, MSI_MSI); + return -EINVAL; + } + /* Debugfs support is optional, just warn if this fails */ cxgb4vf_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (!cxgb4vf_debugfs_root) + if (IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) printk(KERN_WARNING KBUILD_MODNAME ": could not create" " debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4vf_driver); - if (ret < 0) + if (ret < 0 && !IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) debugfs_remove(cxgb4vf_debugfs_root); return ret; } diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c index 0f51c80..192db22 100644 --- a/drivers/net/cxgb4vf/t4vf_hw.c +++ b/drivers/net/cxgb4vf/t4vf_hw.c @@ -171,7 +171,7 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, delay_idx = 0; ms = delay[0]; - for (i = 0; i < 500; i += ms) { + for (i = 0; i < FW_CMD_MAX_TIMEOUT; i += ms) { if (sleep_ok) { ms = delay[delay_idx]; if (delay_idx < ARRAY_SIZE(delay) - 1) diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c index 2a628d1..7018bfe 100644 --- a/drivers/net/davinci_emac.c +++ b/drivers/net/davinci_emac.c @@ -1008,7 +1008,7 @@ static void emac_rx_handler(void *token, int len, int status) int ret; /* free and bail if we are shutting down */ - if (unlikely(!netif_running(ndev))) { + if (unlikely(!netif_running(ndev) || !netif_carrier_ok(ndev))) { dev_kfree_skb_any(skb); return; } diff --git a/drivers/net/depca.c b/drivers/net/depca.c index 1b48b68..8b0084d 100644 --- a/drivers/net/depca.c +++ b/drivers/net/depca.c @@ -1094,7 +1094,7 @@ static int depca_rx(struct net_device *dev) } } /* Change buffer ownership for this last frame, back to the adapter */ - for (; lp->rx_old != entry; lp->rx_old = (++lp->rx_old) & lp->rxRingMask) { + for (; lp->rx_old != entry; lp->rx_old = (lp->rx_old + 1) & lp->rxRingMask) { writel(readl(&lp->rx_ring[lp->rx_old].base) | R_OWN, &lp->rx_ring[lp->rx_old].base); } writel(readl(&lp->rx_ring[entry].base) | R_OWN, &lp->rx_ring[entry].base); @@ -1103,7 +1103,7 @@ static int depca_rx(struct net_device *dev) /* ** Update entry information */ - lp->rx_new = (++lp->rx_new) & lp->rxRingMask; + lp->rx_new = (lp->rx_new + 1) & lp->rxRingMask; } return 0; @@ -1148,7 +1148,7 @@ static int depca_tx(struct net_device *dev) } /* Update all the pointers */ - lp->tx_old = (++lp->tx_old) & lp->txRingMask; + lp->tx_old = (lp->tx_old + 1) & lp->txRingMask; } return 0; diff --git a/drivers/net/dl2k.c b/drivers/net/dl2k.c index e1a8216..c05db60 100644 --- a/drivers/net/dl2k.c +++ b/drivers/net/dl2k.c @@ -1753,8 +1753,6 @@ rio_close (struct net_device *dev) /* Free all the skbuffs in the queue. */ for (i = 0; i < RX_RING_SIZE; i++) { - np->rx_ring[i].status = 0; - np->rx_ring[i].fraginfo = 0; skb = np->rx_skbuff[i]; if (skb) { pci_unmap_single(np->pdev, @@ -1763,6 +1761,8 @@ rio_close (struct net_device *dev) dev_kfree_skb (skb); np->rx_skbuff[i] = NULL; } + np->rx_ring[i].status = 0; + np->rx_ring[i].fraginfo = 0; } for (i = 0; i < TX_RING_SIZE; i++) { skb = np->tx_skbuff[i]; diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c index 2d4c4fc..461dd6f 100644 --- a/drivers/net/dm9000.c +++ b/drivers/net/dm9000.c @@ -802,10 +802,7 @@ dm9000_init_dm9000(struct net_device *dev) /* Checksum mode */ dm9000_set_rx_csum_unlocked(dev, db->rx_csum); - /* GPIO0 on pre-activate PHY */ - iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */ iow(db, DM9000_GPCR, GPCR_GEP_CNTL); /* Let GPIO0 output */ - iow(db, DM9000_GPR, 0); /* Enable PHY */ ncr = (db->flags & DM9000_PLATF_EXT_PHY) ? NCR_EXT_PHY : 0; @@ -852,8 +849,8 @@ static void dm9000_timeout(struct net_device *dev) unsigned long flags; /* Save previous register address */ - reg_save = readb(db->io_addr); spin_lock_irqsave(&db->lock, flags); + reg_save = readb(db->io_addr); netif_stop_queue(dev); dm9000_reset(db); @@ -1194,6 +1191,10 @@ dm9000_open(struct net_device *dev) if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev)) return -EAGAIN; + /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */ + iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */ + mdelay(1); /* delay needs by DM9000B */ + /* Initialize DM9000 board */ dm9000_reset(db); dm9000_init_dm9000(dev); diff --git a/drivers/net/dnet.c b/drivers/net/dnet.c index 9d8a20b..8318ea0 100644 --- a/drivers/net/dnet.c +++ b/drivers/net/dnet.c @@ -337,8 +337,6 @@ static int dnet_mii_init(struct dnet *bp) for (i = 0; i < PHY_MAX_ADDR; i++) bp->mii_bus->irq[i] = PHY_POLL; - platform_set_drvdata(bp->dev, bp->mii_bus); - if (mdiobus_register(bp->mii_bus)) { err = -ENXIO; goto err_out_free_mdio_irq; @@ -863,6 +861,7 @@ static int __devinit dnet_probe(struct platform_device *pdev) bp = netdev_priv(dev); bp->dev = dev; + platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); spin_lock_init(&bp->lock); diff --git a/drivers/net/e1000/e1000_hw.c b/drivers/net/e1000/e1000_hw.c index aed223b..7501d97 100644 --- a/drivers/net/e1000/e1000_hw.c +++ b/drivers/net/e1000/e1000_hw.c @@ -124,6 +124,7 @@ static s32 e1000_set_phy_type(struct e1000_hw *hw) case M88E1000_I_PHY_ID: case M88E1011_I_PHY_ID: case M88E1111_I_PHY_ID: + case M88E1118_E_PHY_ID: hw->phy_type = e1000_phy_m88; break; case IGP01E1000_I_PHY_ID: @@ -3222,7 +3223,8 @@ static s32 e1000_detect_gig_phy(struct e1000_hw *hw) break; case e1000_ce4100: if ((hw->phy_id == RTL8211B_PHY_ID) || - (hw->phy_id == RTL8201N_PHY_ID)) + (hw->phy_id == RTL8201N_PHY_ID) || + (hw->phy_id == M88E1118_E_PHY_ID)) match = true; break; case e1000_82541: diff --git a/drivers/net/e1000/e1000_hw.h b/drivers/net/e1000/e1000_hw.h index 196eeda..c70b23d 100644 --- a/drivers/net/e1000/e1000_hw.h +++ b/drivers/net/e1000/e1000_hw.h @@ -2917,6 +2917,7 @@ struct e1000_host_command_info { #define M88E1000_14_PHY_ID M88E1000_E_PHY_ID #define M88E1011_I_REV_4 0x04 #define M88E1111_I_PHY_ID 0x01410CC0 +#define M88E1118_E_PHY_ID 0x01410E40 #define L1LXT971A_PHY_ID 0x001378E0 #define RTL8211B_PHY_ID 0x001CC910 diff --git a/drivers/net/e1000/e1000_osdep.h b/drivers/net/e1000/e1000_osdep.h index 55c1711..33e7c45a 100644 --- a/drivers/net/e1000/e1000_osdep.h +++ b/drivers/net/e1000/e1000_osdep.h @@ -42,7 +42,8 @@ #define GBE_CONFIG_RAM_BASE \ ((unsigned int)(CONFIG_RAM_BASE + GBE_CONFIG_OFFSET)) -#define GBE_CONFIG_BASE_VIRT phys_to_virt(GBE_CONFIG_RAM_BASE) +#define GBE_CONFIG_BASE_VIRT \ + ((void __iomem *)phys_to_virt(GBE_CONFIG_RAM_BASE)) #define GBE_CONFIG_FLASH_WRITE(base, offset, count, data) \ (iowrite16_rep(base + offset, data, count)) diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 1c18f26..2e50228 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -937,6 +937,9 @@ static void e1000_print_hw_hang(struct work_struct *work) u16 phy_status, phy_1000t_status, phy_ext_status; u16 pci_status; + if (test_bit(__E1000_DOWN, &adapter->state)) + return; + e1e_rphy(hw, PHY_STATUS, &phy_status); e1e_rphy(hw, PHY_1000T_STATUS, &phy_1000t_status); e1e_rphy(hw, PHY_EXT_STATUS, &phy_ext_status); @@ -1506,6 +1509,9 @@ static void e1000e_downshift_workaround(struct work_struct *work) struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, downshift_task); + if (test_bit(__E1000_DOWN, &adapter->state)) + return; + e1000e_gig_downshift_workaround_ich8lan(&adapter->hw); } @@ -3338,6 +3344,21 @@ int e1000e_up(struct e1000_adapter *adapter) return 0; } +static void e1000e_flush_descriptors(struct e1000_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (!(adapter->flags2 & FLAG2_DMA_BURST)) + return; + + /* flush pending descriptor writebacks to memory */ + ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD); + ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD); + + /* execute the writes immediately */ + e1e_flush(); +} + void e1000e_down(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -3377,6 +3398,9 @@ void e1000e_down(struct e1000_adapter *adapter) if (!pci_channel_offline(adapter->pdev)) e1000e_reset(adapter); + + e1000e_flush_descriptors(adapter); + e1000_clean_tx_ring(adapter); e1000_clean_rx_ring(adapter); @@ -3765,6 +3789,10 @@ static void e1000e_update_phy_task(struct work_struct *work) { struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, update_phy_task); + + if (test_bit(__E1000_DOWN, &adapter->state)) + return; + e1000_get_phy_info(&adapter->hw); } @@ -3775,6 +3803,10 @@ static void e1000e_update_phy_task(struct work_struct *work) static void e1000_update_phy_info(unsigned long data) { struct e1000_adapter *adapter = (struct e1000_adapter *) data; + + if (test_bit(__E1000_DOWN, &adapter->state)) + return; + schedule_work(&adapter->update_phy_task); } @@ -4149,6 +4181,9 @@ static void e1000_watchdog_task(struct work_struct *work) u32 link, tctl; int tx_pending = 0; + if (test_bit(__E1000_DOWN, &adapter->state)) + return; + link = e1000e_has_link(adapter); if ((netif_carrier_ok(netdev)) && link) { /* Cancel scheduled suspend requests. */ @@ -4309,7 +4344,6 @@ link_up: * to get done, so reset controller to flush Tx. * (Do the reset outside of interrupt context). */ - adapter->tx_timeout_count++; schedule_work(&adapter->reset_task); /* return immediately since reset is imminent */ return; @@ -4338,19 +4372,12 @@ link_up: else ew32(ICS, E1000_ICS_RXDMT0); + /* flush pending descriptors to memory before detecting Tx hang */ + e1000e_flush_descriptors(adapter); + /* Force detection of hung controller every watchdog period */ adapter->detect_tx_hung = 1; - /* flush partial descriptors to memory before detecting Tx hang */ - if (adapter->flags2 & FLAG2_DMA_BURST) { - ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD); - ew32(RDTR, adapter->rx_int_delay | E1000_RDTR_FPD); - /* - * no need to flush the writes because the timeout code does - * an er32 first thing - */ - } - /* * With 82571 controllers, LAA may be overwritten due to controller * reset from the other port. Set the appropriate LAA in RAR[0] @@ -4888,6 +4915,10 @@ static void e1000_reset_task(struct work_struct *work) struct e1000_adapter *adapter; adapter = container_of(work, struct e1000_adapter, reset_task); + /* don't run the task if already down */ + if (test_bit(__E1000_DOWN, &adapter->state)) + return; + if (!((adapter->flags & FLAG_RX_NEEDS_RESTART) && (adapter->flags & FLAG_RX_RESTART_NOW))) { e1000e_dump(adapter); @@ -5936,7 +5967,8 @@ static int __devinit e1000_probe(struct pci_dev *pdev, /* APME bit in EEPROM is mapped to WUC.APME */ eeprom_data = er32(WUC); eeprom_apme_mask = E1000_WUC_APME; - if (eeprom_data & E1000_WUC_PHY_WAKE) + if ((hw->mac.type > e1000_ich10lan) && + (eeprom_data & E1000_WUC_PHY_WAKE)) adapter->flags2 |= FLAG2_HAS_PHY_WAKEUP; } else if (adapter->flags & FLAG_APME_IN_CTRL3) { if (adapter->flags & FLAG_APME_CHECK_PORT_B && diff --git a/drivers/net/enc28j60.c b/drivers/net/enc28j60.c index 112c5aa..907b05a 100644 --- a/drivers/net/enc28j60.c +++ b/drivers/net/enc28j60.c @@ -812,7 +812,7 @@ static void enc28j60_read_tsv(struct enc28j60_net *priv, u8 tsv[TSV_SIZE]) if (netif_msg_hw(priv)) printk(KERN_DEBUG DRV_NAME ": reading TSV at addr:0x%04x\n", endptr + 1); - enc28j60_mem_read(priv, endptr + 1, sizeof(tsv), tsv); + enc28j60_mem_read(priv, endptr + 1, TSV_SIZE, tsv); } static void enc28j60_dump_tsv(struct enc28j60_net *priv, const char *msg, diff --git a/drivers/net/fec.c b/drivers/net/fec.c index 2a71373..cd0282d 100644 --- a/drivers/net/fec.c +++ b/drivers/net/fec.c @@ -74,7 +74,8 @@ static struct platform_device_id fec_devtype[] = { }, { .name = "imx28-fec", .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME, - } + }, + { } }; static unsigned char macaddr[ETH_ALEN]; diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index af09296..9c0b1ba 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -5645,6 +5645,8 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i goto out_error; } + netif_carrier_off(dev); + dev_info(&pci_dev->dev, "ifname %s, PHY OUI 0x%x @ %d, addr %pM\n", dev->name, np->phy_oui, np->phyaddr, dev->dev_addr); diff --git a/drivers/net/igbvf/vf.c b/drivers/net/igbvf/vf.c index 74486a8..af3822f 100644 --- a/drivers/net/igbvf/vf.c +++ b/drivers/net/igbvf/vf.c @@ -220,7 +220,7 @@ static u32 e1000_hash_mc_addr_vf(struct e1000_hw *hw, u8 *mc_addr) * The parameter rar_count will usually be hw->mac.rar_entry_count * unless there are workarounds that change this. **/ -void e1000_update_mc_addr_list_vf(struct e1000_hw *hw, +static void e1000_update_mc_addr_list_vf(struct e1000_hw *hw, u8 *mc_addr_list, u32 mc_addr_count, u32 rar_used_count, u32 rar_count) { diff --git a/drivers/net/ixgbe/ixgbe_common.c b/drivers/net/ixgbe/ixgbe_common.c index d5ede2d..ebbda7d 100644 --- a/drivers/net/ixgbe/ixgbe_common.c +++ b/drivers/net/ixgbe/ixgbe_common.c @@ -1370,6 +1370,9 @@ s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw) hw_dbg(hw, " New MAC Addr =%pM\n", hw->mac.addr); hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV); + + /* clear VMDq pool/queue selection for RAR 0 */ + hw->mac.ops.clear_vmdq(hw, 0, IXGBE_CLEAR_VMDQ_ALL); } hw->addr_ctrl.overflow_promisc = 0; diff --git a/drivers/net/ixgbe/ixgbe_fcoe.c b/drivers/net/ixgbe/ixgbe_fcoe.c index 6342d48..c54a882 100644 --- a/drivers/net/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ixgbe/ixgbe_fcoe.c @@ -159,13 +159,13 @@ int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, struct scatterlist *sg; unsigned int i, j, dmacount; unsigned int len; - static const unsigned int bufflen = 4096; + static const unsigned int bufflen = IXGBE_FCBUFF_MIN; unsigned int firstoff = 0; unsigned int lastsize; unsigned int thisoff = 0; unsigned int thislen = 0; u32 fcbuff, fcdmarw, fcfltrw; - dma_addr_t addr; + dma_addr_t addr = 0; if (!netdev || !sgl) return 0; @@ -254,6 +254,24 @@ int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, /* only the last buffer may have non-full bufflen */ lastsize = thisoff + thislen; + /* + * lastsize can not be buffer len. + * If it is then adding another buffer with lastsize = 1. + */ + if (lastsize == bufflen) { + if (j >= IXGBE_BUFFCNT_MAX) { + e_err(drv, "xid=%x:%d,%d,%d:addr=%llx " + "not enough user buffers. We need an extra " + "buffer because lastsize is bufflen.\n", + xid, i, j, dmacount, (u64)addr); + goto out_noddp_free; + } + + ddp->udl[j] = (u64)(fcoe->extra_ddp_buffer_dma); + j++; + lastsize = 1; + } + fcbuff = (IXGBE_FCBUFF_4KB << IXGBE_FCBUFF_BUFFSIZE_SHIFT); fcbuff |= ((j & 0xff) << IXGBE_FCBUFF_BUFFCNT_SHIFT); fcbuff |= (firstoff << IXGBE_FCBUFF_OFFSET_SHIFT); @@ -532,6 +550,24 @@ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) e_err(drv, "failed to allocated FCoE DDP pool\n"); spin_lock_init(&fcoe->lock); + + /* Extra buffer to be shared by all DDPs for HW work around */ + fcoe->extra_ddp_buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC); + if (fcoe->extra_ddp_buffer == NULL) { + e_err(drv, "failed to allocated extra DDP buffer\n"); + goto out_extra_ddp_buffer_alloc; + } + + fcoe->extra_ddp_buffer_dma = + dma_map_single(&adapter->pdev->dev, + fcoe->extra_ddp_buffer, + IXGBE_FCBUFF_MIN, + DMA_FROM_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + fcoe->extra_ddp_buffer_dma)) { + e_err(drv, "failed to map extra DDP buffer\n"); + goto out_extra_ddp_buffer_dma; + } } /* Enable L2 eth type filter for FCoE */ @@ -581,6 +617,14 @@ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) } } #endif + + return; + +out_extra_ddp_buffer_dma: + kfree(fcoe->extra_ddp_buffer); +out_extra_ddp_buffer_alloc: + pci_pool_destroy(fcoe->pool); + fcoe->pool = NULL; } /** @@ -600,6 +644,11 @@ void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter) if (fcoe->pool) { for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++) ixgbe_fcoe_ddp_put(adapter->netdev, i); + dma_unmap_single(&adapter->pdev->dev, + fcoe->extra_ddp_buffer_dma, + IXGBE_FCBUFF_MIN, + DMA_FROM_DEVICE); + kfree(fcoe->extra_ddp_buffer); pci_pool_destroy(fcoe->pool); fcoe->pool = NULL; } diff --git a/drivers/net/ixgbe/ixgbe_fcoe.h b/drivers/net/ixgbe/ixgbe_fcoe.h index 4bc2c55..65cc8fb 100644 --- a/drivers/net/ixgbe/ixgbe_fcoe.h +++ b/drivers/net/ixgbe/ixgbe_fcoe.h @@ -70,6 +70,8 @@ struct ixgbe_fcoe { spinlock_t lock; struct pci_pool *pool; struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX]; + unsigned char *extra_ddp_buffer; + dma_addr_t extra_ddp_buffer_dma; }; #endif /* _IXGBE_FCOE_H */ diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 602078b..30f9ccf 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -52,7 +52,7 @@ char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = "Intel(R) 10 Gigabit PCI Express Network Driver"; -#define DRV_VERSION "3.0.12-k2" +#define DRV_VERSION "3.2.9-k2" const char ixgbe_driver_version[] = DRV_VERSION; static char ixgbe_copyright[] = "Copyright (c) 1999-2010 Intel Corporation."; @@ -3176,9 +3176,16 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) u32 mhadd, hlreg0; /* Decide whether to use packet split mode or not */ + /* On by default */ + adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; + /* Do not use packet split if we're in SR-IOV Mode */ - if (!adapter->num_vfs) - adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; + if (adapter->num_vfs) + adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; + + /* Disable packet split due to 82599 erratum #45 */ + if (hw->mac.type == ixgbe_mac_82599EB) + adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; /* Set the RX buffer length according to the mode */ if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { @@ -3721,7 +3728,8 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) * We need to try and force an autonegotiation * session, then bring up link. */ - hw->mac.ops.setup_sfp(hw); + if (hw->mac.ops.setup_sfp) + hw->mac.ops.setup_sfp(hw); if (!(adapter->flags & IXGBE_FLAG_IN_SFP_LINK_TASK)) schedule_work(&adapter->multispeed_fiber_task); } else { @@ -4863,16 +4871,13 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) { int q_idx, num_q_vectors; struct ixgbe_q_vector *q_vector; - int napi_vectors; int (*poll)(struct napi_struct *, int); if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - napi_vectors = adapter->num_rx_queues; poll = &ixgbe_clean_rxtx_many; } else { num_q_vectors = 1; - napi_vectors = 1; poll = &ixgbe_poll; } @@ -5964,7 +5969,8 @@ static void ixgbe_sfp_config_module_task(struct work_struct *work) unregister_netdev(adapter->netdev); return; } - hw->mac.ops.setup_sfp(hw); + if (hw->mac.ops.setup_sfp) + hw->mac.ops.setup_sfp(hw); if (!(adapter->flags & IXGBE_FLAG_IN_SFP_LINK_TASK)) /* This will also work for DA Twinax connections */ diff --git a/drivers/net/ixgbe/ixgbe_sriov.c b/drivers/net/ixgbe/ixgbe_sriov.c index 47b1573..187b3a1 100644 --- a/drivers/net/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ixgbe/ixgbe_sriov.c @@ -110,12 +110,10 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add); } - static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) { u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); vmolr |= (IXGBE_VMOLR_ROMPE | - IXGBE_VMOLR_ROPE | IXGBE_VMOLR_BAM); if (aupe) vmolr |= IXGBE_VMOLR_AUPE; diff --git a/drivers/net/ixgbe/ixgbe_x540.c b/drivers/net/ixgbe/ixgbe_x540.c index 3a89239..f2518b0 100644 --- a/drivers/net/ixgbe/ixgbe_x540.c +++ b/drivers/net/ixgbe/ixgbe_x540.c @@ -133,17 +133,17 @@ static s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw) } ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); - IXGBE_WRITE_REG(hw, IXGBE_CTRL, (ctrl | IXGBE_CTRL_RST)); + IXGBE_WRITE_REG(hw, IXGBE_CTRL, (ctrl | reset_bit)); IXGBE_WRITE_FLUSH(hw); /* Poll for reset bit to self-clear indicating reset is complete */ for (i = 0; i < 10; i++) { udelay(1); ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); - if (!(ctrl & IXGBE_CTRL_RST)) + if (!(ctrl & reset_bit)) break; } - if (ctrl & IXGBE_CTRL_RST) { + if (ctrl & reset_bit) { status = IXGBE_ERR_RESET_FAILED; hw_dbg(hw, "Reset polling failed to complete.\n"); } diff --git a/drivers/net/macb.c b/drivers/net/macb.c index f69e73e..79ccb54 100644 --- a/drivers/net/macb.c +++ b/drivers/net/macb.c @@ -260,7 +260,7 @@ static int macb_mii_init(struct macb *bp) for (i = 0; i < PHY_MAX_ADDR; i++) bp->mii_bus->irq[i] = PHY_POLL; - platform_set_drvdata(bp->dev, bp->mii_bus); + dev_set_drvdata(&bp->dev->dev, bp->mii_bus); if (mdiobus_register(bp->mii_bus)) goto err_out_free_mdio_irq; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 5933621..fc27a99 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -528,8 +528,9 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, vnet_hdr_len = q->vnet_hdr_sz; err = -EINVAL; - if ((len -= vnet_hdr_len) < 0) + if (len < vnet_hdr_len) goto err; + len -= vnet_hdr_len; err = memcpy_fromiovecend((void *)&vnet_hdr, iv, 0, sizeof(vnet_hdr)); diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c index 4ffdc18..2765a3c 100644 --- a/drivers/net/mlx4/main.c +++ b/drivers/net/mlx4/main.c @@ -1286,6 +1286,21 @@ static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = { { PCI_VDEVICE(MELLANOX, 0x6764) }, /* MT26468 ConnectX EN 10GigE PCIe gen2*/ { PCI_VDEVICE(MELLANOX, 0x6746) }, /* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */ { PCI_VDEVICE(MELLANOX, 0x676e) }, /* MT26478 ConnectX2 40GigE PCIe gen2 */ + { PCI_VDEVICE(MELLANOX, 0x1002) }, /* MT25400 Family [ConnectX-2 Virtual Function] */ + { PCI_VDEVICE(MELLANOX, 0x1003) }, /* MT27500 Family [ConnectX-3] */ + { PCI_VDEVICE(MELLANOX, 0x1004) }, /* MT27500 Family [ConnectX-3 Virtual Function] */ + { PCI_VDEVICE(MELLANOX, 0x1005) }, /* MT27510 Family */ + { PCI_VDEVICE(MELLANOX, 0x1006) }, /* MT27511 Family */ + { PCI_VDEVICE(MELLANOX, 0x1007) }, /* MT27520 Family */ + { PCI_VDEVICE(MELLANOX, 0x1008) }, /* MT27521 Family */ + { PCI_VDEVICE(MELLANOX, 0x1009) }, /* MT27530 Family */ + { PCI_VDEVICE(MELLANOX, 0x100a) }, /* MT27531 Family */ + { PCI_VDEVICE(MELLANOX, 0x100b) }, /* MT27540 Family */ + { PCI_VDEVICE(MELLANOX, 0x100c) }, /* MT27541 Family */ + { PCI_VDEVICE(MELLANOX, 0x100d) }, /* MT27550 Family */ + { PCI_VDEVICE(MELLANOX, 0x100e) }, /* MT27551 Family */ + { PCI_VDEVICE(MELLANOX, 0x100f) }, /* MT27560 Family */ + { PCI_VDEVICE(MELLANOX, 0x1010) }, /* MT27561 Family */ { 0, } }; diff --git a/drivers/net/niu.c b/drivers/net/niu.c index 2541321..9fb59d3 100644 --- a/drivers/net/niu.c +++ b/drivers/net/niu.c @@ -4489,6 +4489,9 @@ static int niu_alloc_channels(struct niu *np) { struct niu_parent *parent = np->parent; int first_rx_channel, first_tx_channel; + int num_rx_rings, num_tx_rings; + struct rx_ring_info *rx_rings; + struct tx_ring_info *tx_rings; int i, port, err; port = np->port; @@ -4498,18 +4501,21 @@ static int niu_alloc_channels(struct niu *np) first_tx_channel += parent->txchan_per_port[i]; } - np->num_rx_rings = parent->rxchan_per_port[port]; - np->num_tx_rings = parent->txchan_per_port[port]; + num_rx_rings = parent->rxchan_per_port[port]; + num_tx_rings = parent->txchan_per_port[port]; - netif_set_real_num_rx_queues(np->dev, np->num_rx_rings); - netif_set_real_num_tx_queues(np->dev, np->num_tx_rings); - - np->rx_rings = kcalloc(np->num_rx_rings, sizeof(struct rx_ring_info), - GFP_KERNEL); + rx_rings = kcalloc(num_rx_rings, sizeof(struct rx_ring_info), + GFP_KERNEL); err = -ENOMEM; - if (!np->rx_rings) + if (!rx_rings) goto out_err; + np->num_rx_rings = num_rx_rings; + smp_wmb(); + np->rx_rings = rx_rings; + + netif_set_real_num_rx_queues(np->dev, num_rx_rings); + for (i = 0; i < np->num_rx_rings; i++) { struct rx_ring_info *rp = &np->rx_rings[i]; @@ -4538,12 +4544,18 @@ static int niu_alloc_channels(struct niu *np) return err; } - np->tx_rings = kcalloc(np->num_tx_rings, sizeof(struct tx_ring_info), - GFP_KERNEL); + tx_rings = kcalloc(num_tx_rings, sizeof(struct tx_ring_info), + GFP_KERNEL); err = -ENOMEM; - if (!np->tx_rings) + if (!tx_rings) goto out_err; + np->num_tx_rings = num_tx_rings; + smp_wmb(); + np->tx_rings = tx_rings; + + netif_set_real_num_tx_queues(np->dev, num_tx_rings); + for (i = 0; i < np->num_tx_rings; i++) { struct tx_ring_info *rp = &np->tx_rings[i]; @@ -6246,11 +6258,17 @@ static void niu_sync_mac_stats(struct niu *np) static void niu_get_rx_stats(struct niu *np) { unsigned long pkts, dropped, errors, bytes; + struct rx_ring_info *rx_rings; int i; pkts = dropped = errors = bytes = 0; + + rx_rings = ACCESS_ONCE(np->rx_rings); + if (!rx_rings) + goto no_rings; + for (i = 0; i < np->num_rx_rings; i++) { - struct rx_ring_info *rp = &np->rx_rings[i]; + struct rx_ring_info *rp = &rx_rings[i]; niu_sync_rx_discard_stats(np, rp, 0); @@ -6259,6 +6277,8 @@ static void niu_get_rx_stats(struct niu *np) dropped += rp->rx_dropped; errors += rp->rx_errors; } + +no_rings: np->dev->stats.rx_packets = pkts; np->dev->stats.rx_bytes = bytes; np->dev->stats.rx_dropped = dropped; @@ -6268,16 +6288,24 @@ static void niu_get_rx_stats(struct niu *np) static void niu_get_tx_stats(struct niu *np) { unsigned long pkts, errors, bytes; + struct tx_ring_info *tx_rings; int i; pkts = errors = bytes = 0; + + tx_rings = ACCESS_ONCE(np->tx_rings); + if (!tx_rings) + goto no_rings; + for (i = 0; i < np->num_tx_rings; i++) { - struct tx_ring_info *rp = &np->tx_rings[i]; + struct tx_ring_info *rp = &tx_rings[i]; pkts += rp->tx_packets; bytes += rp->tx_bytes; errors += rp->tx_errors; } + +no_rings: np->dev->stats.tx_packets = pkts; np->dev->stats.tx_bytes = bytes; np->dev->stats.tx_errors = errors; @@ -6287,9 +6315,10 @@ static struct net_device_stats *niu_get_stats(struct net_device *dev) { struct niu *np = netdev_priv(dev); - niu_get_rx_stats(np); - niu_get_tx_stats(np); - + if (netif_running(dev)) { + niu_get_rx_stats(np); + niu_get_tx_stats(np); + } return &dev->stats; } diff --git a/drivers/net/pch_gbe/pch_gbe.h b/drivers/net/pch_gbe/pch_gbe.h index a0c26a9..e1e33c8 100644 --- a/drivers/net/pch_gbe/pch_gbe.h +++ b/drivers/net/pch_gbe/pch_gbe.h @@ -73,7 +73,7 @@ struct pch_gbe_regs { struct pch_gbe_regs_mac_adr mac_adr[16]; u32 ADDR_MASK; u32 MIIM; - u32 reserve2; + u32 MAC_ADDR_LOAD; u32 RGMII_ST; u32 RGMII_CTRL; u32 reserve3[3]; diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c index 1bf1233..b99e90a 100644 --- a/drivers/net/pch_gbe/pch_gbe_main.c +++ b/drivers/net/pch_gbe/pch_gbe_main.c @@ -29,6 +29,7 @@ const char pch_driver_version[] = DRV_VERSION; #define PCH_GBE_SHORT_PKT 64 #define DSC_INIT16 0xC000 #define PCH_GBE_DMA_ALIGN 0 +#define PCH_GBE_DMA_PADDING 2 #define PCH_GBE_WATCHDOG_PERIOD (1 * HZ) /* watchdog time */ #define PCH_GBE_COPYBREAK_DEFAULT 256 #define PCH_GBE_PCI_BAR 1 @@ -88,6 +89,12 @@ static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT; static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg); static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg, int data); + +inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw) +{ + iowrite32(0x01, &hw->reg->MAC_ADDR_LOAD); +} + /** * pch_gbe_mac_read_mac_addr - Read MAC address * @hw: Pointer to the HW structure @@ -519,7 +526,9 @@ static void pch_gbe_reset_task(struct work_struct *work) struct pch_gbe_adapter *adapter; adapter = container_of(work, struct pch_gbe_adapter, reset_task); + rtnl_lock(); pch_gbe_reinit_locked(adapter); + rtnl_unlock(); } /** @@ -528,14 +537,8 @@ static void pch_gbe_reset_task(struct work_struct *work) */ void pch_gbe_reinit_locked(struct pch_gbe_adapter *adapter) { - struct net_device *netdev = adapter->netdev; - - rtnl_lock(); - if (netif_running(netdev)) { - pch_gbe_down(adapter); - pch_gbe_up(adapter); - } - rtnl_unlock(); + pch_gbe_down(adapter); + pch_gbe_up(adapter); } /** @@ -1369,16 +1372,13 @@ pch_gbe_clean_rx(struct pch_gbe_adapter *adapter, struct pch_gbe_buffer *buffer_info; struct pch_gbe_rx_desc *rx_desc; u32 length; - unsigned char tmp_packet[ETH_HLEN]; unsigned int i; unsigned int cleaned_count = 0; bool cleaned = false; - struct sk_buff *skb; + struct sk_buff *skb, *new_skb; u8 dma_status; u16 gbec_status; u32 tcp_ip_status; - u8 skb_copy_flag = 0; - u8 skb_padding_flag = 0; i = rx_ring->next_to_clean; @@ -1422,55 +1422,70 @@ pch_gbe_clean_rx(struct pch_gbe_adapter *adapter, pr_err("Receive CRC Error\n"); } else { /* get receive length */ - /* length convert[-3], padding[-2] */ - length = (rx_desc->rx_words_eob) - 3 - 2; + /* length convert[-3] */ + length = (rx_desc->rx_words_eob) - 3; /* Decide the data conversion method */ if (!adapter->rx_csum) { /* [Header:14][payload] */ - skb_padding_flag = 0; - skb_copy_flag = 1; + if (NET_IP_ALIGN) { + /* Because alignment differs, + * the new_skb is newly allocated, + * and data is copied to new_skb.*/ + new_skb = netdev_alloc_skb(netdev, + length + NET_IP_ALIGN); + if (!new_skb) { + /* dorrop error */ + pr_err("New skb allocation " + "Error\n"); + goto dorrop; + } + skb_reserve(new_skb, NET_IP_ALIGN); + memcpy(new_skb->data, skb->data, + length); + skb = new_skb; + } else { + /* DMA buffer is used as SKB as it is.*/ + buffer_info->skb = NULL; + } } else { /* [Header:14][padding:2][payload] */ - skb_padding_flag = 1; - if (length < copybreak) - skb_copy_flag = 1; - else - skb_copy_flag = 0; - } - - /* Data conversion */ - if (skb_copy_flag) { /* recycle skb */ - struct sk_buff *new_skb; - new_skb = - netdev_alloc_skb(netdev, - length + NET_IP_ALIGN); - if (new_skb) { - if (!skb_padding_flag) { - skb_reserve(new_skb, - NET_IP_ALIGN); + /* The length includes padding length */ + length = length - PCH_GBE_DMA_PADDING; + if ((length < copybreak) || + (NET_IP_ALIGN != PCH_GBE_DMA_PADDING)) { + /* Because alignment differs, + * the new_skb is newly allocated, + * and data is copied to new_skb. + * Padding data is deleted + * at the time of a copy.*/ + new_skb = netdev_alloc_skb(netdev, + length + NET_IP_ALIGN); + if (!new_skb) { + /* dorrop error */ + pr_err("New skb allocation " + "Error\n"); + goto dorrop; } + skb_reserve(new_skb, NET_IP_ALIGN); memcpy(new_skb->data, skb->data, - length); - /* save the skb - * in buffer_info as good */ + ETH_HLEN); + memcpy(&new_skb->data[ETH_HLEN], + &skb->data[ETH_HLEN + + PCH_GBE_DMA_PADDING], + length - ETH_HLEN); skb = new_skb; - } else if (!skb_padding_flag) { - /* dorrop error */ - pr_err("New skb allocation Error\n"); - goto dorrop; + } else { + /* Padding data is deleted + * by moving header data.*/ + memmove(&skb->data[PCH_GBE_DMA_PADDING], + &skb->data[0], ETH_HLEN); + skb_reserve(skb, NET_IP_ALIGN); + buffer_info->skb = NULL; } - } else { - buffer_info->skb = NULL; } - if (skb_padding_flag) { - memcpy(&tmp_packet[0], &skb->data[0], ETH_HLEN); - memcpy(&skb->data[NET_IP_ALIGN], &tmp_packet[0], - ETH_HLEN); - skb_reserve(skb, NET_IP_ALIGN); - - } - + /* The length includes FCS length */ + length = length - ETH_FCS_LEN; /* update status of driver */ adapter->stats.rx_bytes += length; adapter->stats.rx_packets++; @@ -2322,6 +2337,7 @@ static int pch_gbe_probe(struct pci_dev *pdev, netdev->features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_GRO; pch_gbe_set_ethtool_ops(netdev); + pch_gbe_mac_load_mac_addr(&adapter->hw); pch_gbe_mac_reset_hw(&adapter->hw); /* setup the private structure */ diff --git a/drivers/net/pcmcia/axnet_cs.c b/drivers/net/pcmcia/axnet_cs.c index 1f42f6a..d3cb772 100644 --- a/drivers/net/pcmcia/axnet_cs.c +++ b/drivers/net/pcmcia/axnet_cs.c @@ -1488,12 +1488,10 @@ static void ei_rx_overrun(struct net_device *dev) /* * Wait a full Tx time (1.2ms) + some guard time, NS says 1.6ms total. - * Early datasheets said to poll the reset bit, but now they say that - * it "is not a reliable indicator and subsequently should be ignored." - * We wait at least 10ms. + * We wait at least 2ms. */ - mdelay(10); + mdelay(2); /* * Reset RBCR[01] back to zero as per magic incantation. diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c index 9226cda..530ab5a 100644 --- a/drivers/net/pcmcia/fmvj18x_cs.c +++ b/drivers/net/pcmcia/fmvj18x_cs.c @@ -691,6 +691,7 @@ static struct pcmcia_device_id fmvj18x_ids[] = { PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0105, 0x0e0a), PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x0e01), PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x0a05), + PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x0b05), PCMCIA_PFC_DEVICE_MANF_CARD(0, 0x0032, 0x1101), PCMCIA_DEVICE_NULL, }; diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 27e6f6d..e3ebd90 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -49,8 +49,8 @@ #include <asm/processor.h> #define DRV_NAME "r6040" -#define DRV_VERSION "0.26" -#define DRV_RELDATE "30May2010" +#define DRV_VERSION "0.27" +#define DRV_RELDATE "23Feb2011" /* PHY CHIP Address */ #define PHY1_ADDR 1 /* For MAC1 */ @@ -69,6 +69,8 @@ /* MAC registers */ #define MCR0 0x00 /* Control register 0 */ +#define MCR0_PROMISC 0x0020 /* Promiscuous mode */ +#define MCR0_HASH_EN 0x0100 /* Enable multicast hash table function */ #define MCR1 0x04 /* Control register 1 */ #define MAC_RST 0x0001 /* Reset the MAC */ #define MBCR 0x08 /* Bus control */ @@ -851,77 +853,92 @@ static void r6040_multicast_list(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; - u16 reg; unsigned long flags; struct netdev_hw_addr *ha; int i; + u16 *adrp; + u16 hash_table[4] = { 0 }; + + spin_lock_irqsave(&lp->lock, flags); - /* MAC Address */ + /* Keep our MAC Address */ adrp = (u16 *)dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); - /* Promiscous Mode */ - spin_lock_irqsave(&lp->lock, flags); - /* Clear AMCP & PROM bits */ - reg = ioread16(ioaddr) & ~0x0120; - if (dev->flags & IFF_PROMISC) { - reg |= 0x0020; - lp->mcr0 |= 0x0020; - } - /* Too many multicast addresses - * accept all traffic */ - else if ((netdev_mc_count(dev) > MCAST_MAX) || - (dev->flags & IFF_ALLMULTI)) - reg |= 0x0020; + lp->mcr0 = ioread16(ioaddr + MCR0) & ~(MCR0_PROMISC | MCR0_HASH_EN); - iowrite16(reg, ioaddr); - spin_unlock_irqrestore(&lp->lock, flags); + /* Promiscuous mode */ + if (dev->flags & IFF_PROMISC) + lp->mcr0 |= MCR0_PROMISC; - /* Build the hash table */ - if (netdev_mc_count(dev) > MCAST_MAX) { - u16 hash_table[4]; - u32 crc; + /* Enable multicast hash table function to + * receive all multicast packets. */ + else if (dev->flags & IFF_ALLMULTI) { + lp->mcr0 |= MCR0_HASH_EN; - for (i = 0; i < 4; i++) - hash_table[i] = 0; + for (i = 0; i < MCAST_MAX ; i++) { + iowrite16(0, ioaddr + MID_1L + 8 * i); + iowrite16(0, ioaddr + MID_1M + 8 * i); + iowrite16(0, ioaddr + MID_1H + 8 * i); + } + for (i = 0; i < 4; i++) + hash_table[i] = 0xffff; + } + /* Use internal multicast address registers if the number of + * multicast addresses is not greater than MCAST_MAX. */ + else if (netdev_mc_count(dev) <= MCAST_MAX) { + i = 0; netdev_for_each_mc_addr(ha, dev) { - char *addrs = ha->addr; + u16 *adrp = (u16 *) ha->addr; + iowrite16(adrp[0], ioaddr + MID_1L + 8 * i); + iowrite16(adrp[1], ioaddr + MID_1M + 8 * i); + iowrite16(adrp[2], ioaddr + MID_1H + 8 * i); + i++; + } + while (i < MCAST_MAX) { + iowrite16(0, ioaddr + MID_1L + 8 * i); + iowrite16(0, ioaddr + MID_1M + 8 * i); + iowrite16(0, ioaddr + MID_1H + 8 * i); + i++; + } + } + /* Otherwise, Enable multicast hash table function. */ + else { + u32 crc; - if (!(*addrs & 1)) - continue; + lp->mcr0 |= MCR0_HASH_EN; + + for (i = 0; i < MCAST_MAX ; i++) { + iowrite16(0, ioaddr + MID_1L + 8 * i); + iowrite16(0, ioaddr + MID_1M + 8 * i); + iowrite16(0, ioaddr + MID_1H + 8 * i); + } - crc = ether_crc_le(6, addrs); + /* Build multicast hash table */ + netdev_for_each_mc_addr(ha, dev) { + u8 *addrs = ha->addr; + + crc = ether_crc(ETH_ALEN, addrs); crc >>= 26; - hash_table[crc >> 4] |= 1 << (15 - (crc & 0xf)); + hash_table[crc >> 4] |= 1 << (crc & 0xf); } - /* Fill the MAC hash tables with their values */ + } + + iowrite16(lp->mcr0, ioaddr + MCR0); + + /* Fill the MAC hash tables with their values */ + if (lp->mcr0 && MCR0_HASH_EN) { iowrite16(hash_table[0], ioaddr + MAR0); iowrite16(hash_table[1], ioaddr + MAR1); iowrite16(hash_table[2], ioaddr + MAR2); iowrite16(hash_table[3], ioaddr + MAR3); } - /* Multicast Address 1~4 case */ - i = 0; - netdev_for_each_mc_addr(ha, dev) { - if (i >= MCAST_MAX) - break; - adrp = (u16 *) ha->addr; - iowrite16(adrp[0], ioaddr + MID_1L + 8 * i); - iowrite16(adrp[1], ioaddr + MID_1M + 8 * i); - iowrite16(adrp[2], ioaddr + MID_1H + 8 * i); - i++; - } - while (i < MCAST_MAX) { - iowrite16(0xffff, ioaddr + MID_1L + 8 * i); - iowrite16(0xffff, ioaddr + MID_1M + 8 * i); - iowrite16(0xffff, ioaddr + MID_1H + 8 * i); - i++; - } + + spin_unlock_irqrestore(&lp->lock, flags); } static void netdev_get_drvinfo(struct net_device *dev, diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index bde7d61..7ffdb80 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -25,6 +25,7 @@ #include <linux/dma-mapping.h> #include <linux/pm_runtime.h> #include <linux/firmware.h> +#include <linux/pci-aspm.h> #include <asm/system.h> #include <asm/io.h> @@ -617,8 +618,9 @@ static void ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg, u32 data) } } -static void rtl8168_oob_notify(void __iomem *ioaddr, u8 cmd) +static void rtl8168_oob_notify(struct rtl8169_private *tp, u8 cmd) { + void __iomem *ioaddr = tp->mmio_addr; int i; RTL_W8(ERIDR, cmd); @@ -630,7 +632,7 @@ static void rtl8168_oob_notify(void __iomem *ioaddr, u8 cmd) break; } - ocp_write(ioaddr, 0x1, 0x30, 0x00000001); + ocp_write(tp, 0x1, 0x30, 0x00000001); } #define OOB_CMD_RESET 0x00 @@ -973,7 +975,8 @@ static void __rtl8169_check_link_status(struct net_device *dev, if (pm) pm_request_resume(&tp->pci_dev->dev); netif_carrier_on(dev); - netif_info(tp, ifup, dev, "link up\n"); + if (net_ratelimit()) + netif_info(tp, ifup, dev, "link up\n"); } else { netif_carrier_off(dev); netif_info(tp, ifdown, dev, "link down\n"); @@ -2867,8 +2870,11 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) { void __iomem *ioaddr = tp->mmio_addr; - if (tp->mac_version == RTL_GIGA_MAC_VER_27) + if (((tp->mac_version == RTL_GIGA_MAC_VER_27) || + (tp->mac_version == RTL_GIGA_MAC_VER_28)) && + (ocp_read(tp, 0x0f, 0x0010) & 0x00008000)) { return; + } if (((tp->mac_version == RTL_GIGA_MAC_VER_23) || (tp->mac_version == RTL_GIGA_MAC_VER_24)) && @@ -2890,6 +2896,8 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25: case RTL_GIGA_MAC_VER_26: + case RTL_GIGA_MAC_VER_27: + case RTL_GIGA_MAC_VER_28: RTL_W8(PMCH, RTL_R8(PMCH) & ~0x80); break; } @@ -2899,12 +2907,17 @@ static void r8168_pll_power_up(struct rtl8169_private *tp) { void __iomem *ioaddr = tp->mmio_addr; - if (tp->mac_version == RTL_GIGA_MAC_VER_27) + if (((tp->mac_version == RTL_GIGA_MAC_VER_27) || + (tp->mac_version == RTL_GIGA_MAC_VER_28)) && + (ocp_read(tp, 0x0f, 0x0010) & 0x00008000)) { return; + } switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25: case RTL_GIGA_MAC_VER_26: + case RTL_GIGA_MAC_VER_27: + case RTL_GIGA_MAC_VER_28: RTL_W8(PMCH, RTL_R8(PMCH) | 0x80); break; } @@ -3008,6 +3021,11 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) mii->reg_num_mask = 0x1f; mii->supports_gmii = !!(cfg->features & RTL_FEATURE_GMII); + /* disable ASPM completely as that cause random device stop working + * problems as well as full system hangs for some PCIe devices users */ + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 | + PCIE_LINK_STATE_CLKPM); + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pci_enable_device(pdev); if (rc < 0) { @@ -3041,7 +3059,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_mwi_2; } - tp->cp_cmd = PCIMulRW | RxChkSum; + tp->cp_cmd = RxChkSum; if ((sizeof(dma_addr_t) > 4) && !pci_set_dma_mask(pdev, DMA_BIT_MASK(64)) && use_dac) { @@ -3189,6 +3207,8 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); + netif_carrier_off(dev); + out: return rc; @@ -3315,7 +3335,8 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) /* Disable interrupts */ rtl8169_irq_mask_and_ack(ioaddr); - if (tp->mac_version == RTL_GIGA_MAC_VER_28) { + if (tp->mac_version == RTL_GIGA_MAC_VER_27 || + tp->mac_version == RTL_GIGA_MAC_VER_28) { while (RTL_R8(TxPoll) & NPQ) udelay(20); @@ -3757,7 +3778,8 @@ static void rtl_hw_start_8168(struct net_device *dev) RTL_W16(IntrMitigate, 0x5151); /* Work around for RxFIFO overflow. */ - if (tp->mac_version == RTL_GIGA_MAC_VER_11) { + if (tp->mac_version == RTL_GIGA_MAC_VER_11 || + tp->mac_version == RTL_GIGA_MAC_VER_22) { tp->intr_event |= RxFIFOOver | PCSTimeout; tp->intr_event &= ~RxOverflow; } @@ -3843,8 +3865,7 @@ static void rtl_hw_start_8168(struct net_device *dev) Cxpl_dbg_sel | \ ASF | \ PktCntrDisable | \ - PCIDAC | \ - PCIMulRW) + Mac_dbgo_sel) static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev) { @@ -3874,8 +3895,6 @@ static void rtl_hw_start_8102e_1(void __iomem *ioaddr, struct pci_dev *pdev) if ((cfg1 & LEDS0) && (cfg1 & LEDS1)) RTL_W8(Config1, cfg1 & ~LEDS0); - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R810X_CPCMD_QUIRK_MASK); - rtl_ephy_init(ioaddr, e_info_8102e_1, ARRAY_SIZE(e_info_8102e_1)); } @@ -3887,8 +3906,6 @@ static void rtl_hw_start_8102e_2(void __iomem *ioaddr, struct pci_dev *pdev) RTL_W8(Config1, MEMMAP | IOMAP | VPD | PMEnable); RTL_W8(Config3, RTL_R8(Config3) & ~Beacon_en); - - RTL_W16(CPlusCmd, RTL_R16(CPlusCmd) & ~R810X_CPCMD_QUIRK_MASK); } static void rtl_hw_start_8102e_3(void __iomem *ioaddr, struct pci_dev *pdev) @@ -3914,6 +3931,8 @@ static void rtl_hw_start_8101(struct net_device *dev) } } + RTL_W8(Cfg9346, Cfg9346_Unlock); + switch (tp->mac_version) { case RTL_GIGA_MAC_VER_07: rtl_hw_start_8102e_1(ioaddr, pdev); @@ -3928,14 +3947,13 @@ static void rtl_hw_start_8101(struct net_device *dev) break; } - RTL_W8(Cfg9346, Cfg9346_Unlock); + RTL_W8(Cfg9346, Cfg9346_Lock); RTL_W8(MaxTxPacketSize, TxPacketMax); rtl_set_rx_max_size(ioaddr, rx_buf_sz); - tp->cp_cmd |= rtl_rw_cpluscmd(ioaddr) | PCIMulRW; - + tp->cp_cmd &= ~R810X_CPCMD_QUIRK_MASK; RTL_W16(CPlusCmd, tp->cp_cmd); RTL_W16(IntrMitigate, 0x0000); @@ -3945,14 +3963,10 @@ static void rtl_hw_start_8101(struct net_device *dev) RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); rtl_set_rx_tx_config_registers(tp); - RTL_W8(Cfg9346, Cfg9346_Lock); - RTL_R8(IntrMask); rtl_set_rx_mode(dev); - RTL_W8(ChipCmd, CmdTxEnb | CmdRxEnb); - RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xf000); RTL_W16(IntrMask, tp->intr_event); @@ -4639,12 +4653,33 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) break; } - /* Work around for rx fifo overflow */ - if (unlikely(status & RxFIFOOver) && - (tp->mac_version == RTL_GIGA_MAC_VER_11)) { - netif_stop_queue(dev); - rtl8169_tx_timeout(dev); - break; + if (unlikely(status & RxFIFOOver)) { + switch (tp->mac_version) { + /* Work around for rx fifo overflow */ + case RTL_GIGA_MAC_VER_11: + case RTL_GIGA_MAC_VER_22: + case RTL_GIGA_MAC_VER_26: + netif_stop_queue(dev); + rtl8169_tx_timeout(dev); + goto done; + /* Testers needed. */ + case RTL_GIGA_MAC_VER_17: + case RTL_GIGA_MAC_VER_19: + case RTL_GIGA_MAC_VER_20: + case RTL_GIGA_MAC_VER_21: + case RTL_GIGA_MAC_VER_23: + case RTL_GIGA_MAC_VER_24: + case RTL_GIGA_MAC_VER_27: + case RTL_GIGA_MAC_VER_28: + /* Experimental science. Pktgen proof. */ + case RTL_GIGA_MAC_VER_12: + case RTL_GIGA_MAC_VER_25: + if (status == RxFIFOOver) + goto done; + break; + default: + break; + } } if (unlikely(status & SYSErr)) { @@ -4680,7 +4715,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) (status & RxFIFOOver) ? (status | RxOverflow) : status); status = RTL_R16(IntrStatus); } - +done: return IRQ_RETVAL(handled); } diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index 0e8bb19..ca886d9 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -569,9 +569,14 @@ static void efx_ethtool_self_test(struct net_device *net_dev, struct ethtool_test *test, u64 *data) { struct efx_nic *efx = netdev_priv(net_dev); - struct efx_self_tests efx_tests; + struct efx_self_tests *efx_tests; int already_up; - int rc; + int rc = -ENOMEM; + + efx_tests = kzalloc(sizeof(*efx_tests), GFP_KERNEL); + if (!efx_tests) + goto fail; + ASSERT_RTNL(); if (efx->state != STATE_RUNNING) { @@ -589,13 +594,11 @@ static void efx_ethtool_self_test(struct net_device *net_dev, if (rc) { netif_err(efx, drv, efx->net_dev, "failed opening device.\n"); - goto fail2; + goto fail1; } } - memset(&efx_tests, 0, sizeof(efx_tests)); - - rc = efx_selftest(efx, &efx_tests, test->flags); + rc = efx_selftest(efx, efx_tests, test->flags); if (!already_up) dev_close(efx->net_dev); @@ -604,10 +607,11 @@ static void efx_ethtool_self_test(struct net_device *net_dev, rc == 0 ? "passed" : "failed", (test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on"); - fail2: - fail1: +fail1: /* Fill ethtool results structures */ - efx_ethtool_fill_self_tests(efx, &efx_tests, NULL, data); + efx_ethtool_fill_self_tests(efx, efx_tests, NULL, data); + kfree(efx_tests); +fail: if (rc) test->flags |= ETH_TEST_FL_FAILED; } diff --git a/drivers/net/sis900.c b/drivers/net/sis900.c index 5976d1d..640e368 100644 --- a/drivers/net/sis900.c +++ b/drivers/net/sis900.c @@ -1777,6 +1777,7 @@ static int sis900_rx(struct net_device *net_dev) "cur_rx:%4.4d, dirty_rx:%4.4d\n", net_dev->name, sis_priv->cur_rx, sis_priv->dirty_rx); + dev_kfree_skb(skb); break; } diff --git a/drivers/net/skge.c b/drivers/net/skge.c index 42daf98..35b28f4 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -3856,9 +3856,6 @@ static struct net_device *skge_devinit(struct skge_hw *hw, int port, memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port*8, ETH_ALEN); memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); - /* device is off until link detection */ - netif_carrier_off(dev); - return dev; } diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index 64bfdae..d70bde95 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -1178,6 +1178,11 @@ static int smsc911x_open(struct net_device *dev) smsc911x_reg_write(pdata, HW_CFG, 0x00050000); smsc911x_reg_write(pdata, AFC_CFG, 0x006E3740); + /* Increase the legal frame size of VLAN tagged frames to 1522 bytes */ + spin_lock_irq(&pdata->mac_lock); + smsc911x_mac_write(pdata, VLAN1, ETH_P_8021Q); + spin_unlock_irq(&pdata->mac_lock); + /* Make sure EEPROM has finished loading before setting GPIO_CFG */ timeout = 50; while ((smsc911x_reg_read(pdata, E2P_CMD) & E2P_CMD_EPC_BUSY_) && diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index 34a0af3..0e5f031 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -1560,8 +1560,10 @@ static int stmmac_mac_device_setup(struct net_device *dev) priv->hw = device; - if (device_can_wakeup(priv->device)) + if (device_can_wakeup(priv->device)) { priv->wolopts = WAKE_MAGIC; /* Magic Frame as default */ + enable_irq_wake(dev->irq); + } return 0; } diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 93b32d3..06c0e503 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -11158,7 +11158,9 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (tp->phy_flags & TG3_PHYFLG_PHY_SERDES) break; /* We have no PHY */ - if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) + if ((tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) || + ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) && + !netif_running(dev))) return -EAGAIN; spin_lock_bh(&tp->lock); @@ -11174,7 +11176,9 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (tp->phy_flags & TG3_PHYFLG_PHY_SERDES) break; /* We have no PHY */ - if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) + if ((tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) || + ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) && + !netif_running(dev))) return -EAGAIN; spin_lock_bh(&tp->lock); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 04e8ce1..7113168 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1,7 +1,7 @@ /* * cdc_ncm.c * - * Copyright (C) ST-Ericsson 2010 + * Copyright (C) ST-Ericsson 2010-2011 * Contact: Alexey Orishko <alexey.orishko@stericsson.com> * Original author: Hans Petter Selasky <hans.petter.selasky@stericsson.com> * @@ -54,7 +54,7 @@ #include <linux/usb/usbnet.h> #include <linux/usb/cdc.h> -#define DRIVER_VERSION "17-Jan-2011" +#define DRIVER_VERSION "7-Feb-2011" /* CDC NCM subclass 3.2.1 */ #define USB_CDC_NCM_NDP16_LENGTH_MIN 0x10 @@ -77,6 +77,9 @@ */ #define CDC_NCM_DPT_DATAGRAMS_MAX 32 +/* Maximum amount of IN datagrams in NTB */ +#define CDC_NCM_DPT_DATAGRAMS_IN_MAX 0 /* unlimited */ + /* Restart the timer, if amount of datagrams is less than given value */ #define CDC_NCM_RESTART_TIMER_DATAGRAM_CNT 3 @@ -85,11 +88,6 @@ (sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \ (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16)) -struct connection_speed_change { - __le32 USBitRate; /* holds 3GPP downlink value, bits per second */ - __le32 DSBitRate; /* holds 3GPP uplink value, bits per second */ -} __attribute__ ((packed)); - struct cdc_ncm_data { struct usb_cdc_ncm_nth16 nth16; struct usb_cdc_ncm_ndp16 ndp16; @@ -198,10 +196,10 @@ static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx) { struct usb_cdc_notification req; u32 val; - __le16 max_datagram_size; u8 flags; u8 iface_no; int err; + u16 ntb_fmt_supported; iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber; @@ -223,6 +221,9 @@ static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx) ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder); ctx->tx_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutDivisor); ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment); + /* devices prior to NCM Errata shall set this field to zero */ + ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams); + ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported); if (ctx->func_desc != NULL) flags = ctx->func_desc->bmNetworkCapabilities; @@ -231,22 +232,58 @@ static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx) pr_debug("dwNtbInMaxSize=%u dwNtbOutMaxSize=%u " "wNdpOutPayloadRemainder=%u wNdpOutDivisor=%u " - "wNdpOutAlignment=%u flags=0x%x\n", + "wNdpOutAlignment=%u wNtbOutMaxDatagrams=%u flags=0x%x\n", ctx->rx_max, ctx->tx_max, ctx->tx_remainder, ctx->tx_modulus, - ctx->tx_ndp_modulus, flags); + ctx->tx_ndp_modulus, ctx->tx_max_datagrams, flags); - /* max count of tx datagrams without terminating NULL entry */ - ctx->tx_max_datagrams = CDC_NCM_DPT_DATAGRAMS_MAX; + /* max count of tx datagrams */ + if ((ctx->tx_max_datagrams == 0) || + (ctx->tx_max_datagrams > CDC_NCM_DPT_DATAGRAMS_MAX)) + ctx->tx_max_datagrams = CDC_NCM_DPT_DATAGRAMS_MAX; /* verify maximum size of received NTB in bytes */ - if ((ctx->rx_max < - (CDC_NCM_MIN_HDR_SIZE + CDC_NCM_MIN_DATAGRAM_SIZE)) || - (ctx->rx_max > CDC_NCM_NTB_MAX_SIZE_RX)) { + if (ctx->rx_max < USB_CDC_NCM_NTB_MIN_IN_SIZE) { + pr_debug("Using min receive length=%d\n", + USB_CDC_NCM_NTB_MIN_IN_SIZE); + ctx->rx_max = USB_CDC_NCM_NTB_MIN_IN_SIZE; + } + + if (ctx->rx_max > CDC_NCM_NTB_MAX_SIZE_RX) { pr_debug("Using default maximum receive length=%d\n", CDC_NCM_NTB_MAX_SIZE_RX); ctx->rx_max = CDC_NCM_NTB_MAX_SIZE_RX; } + /* inform device about NTB input size changes */ + if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) { + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | + USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_SET_NTB_INPUT_SIZE; + req.wValue = 0; + req.wIndex = cpu_to_le16(iface_no); + + if (flags & USB_CDC_NCM_NCAP_NTB_INPUT_SIZE) { + struct usb_cdc_ncm_ndp_input_size ndp_in_sz; + + req.wLength = 8; + ndp_in_sz.dwNtbInMaxSize = cpu_to_le32(ctx->rx_max); + ndp_in_sz.wNtbInMaxDatagrams = + cpu_to_le16(CDC_NCM_DPT_DATAGRAMS_MAX); + ndp_in_sz.wReserved = 0; + err = cdc_ncm_do_request(ctx, &req, &ndp_in_sz, 0, NULL, + 1000); + } else { + __le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max); + + req.wLength = 4; + err = cdc_ncm_do_request(ctx, &req, &dwNtbInMaxSize, 0, + NULL, 1000); + } + + if (err) + pr_debug("Setting NTB Input Size failed\n"); + } + /* verify maximum size of transmitted NTB in bytes */ if ((ctx->tx_max < (CDC_NCM_MIN_HDR_SIZE + CDC_NCM_MIN_DATAGRAM_SIZE)) || @@ -297,47 +334,84 @@ static u8 cdc_ncm_setup(struct cdc_ncm_ctx *ctx) /* additional configuration */ /* set CRC Mode */ - req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE; - req.bNotificationType = USB_CDC_SET_CRC_MODE; - req.wValue = cpu_to_le16(USB_CDC_NCM_CRC_NOT_APPENDED); - req.wIndex = cpu_to_le16(iface_no); - req.wLength = 0; - - err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000); - if (err) - pr_debug("Setting CRC mode off failed\n"); + if (flags & USB_CDC_NCM_NCAP_CRC_MODE) { + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | + USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_SET_CRC_MODE; + req.wValue = cpu_to_le16(USB_CDC_NCM_CRC_NOT_APPENDED); + req.wIndex = cpu_to_le16(iface_no); + req.wLength = 0; + + err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000); + if (err) + pr_debug("Setting CRC mode off failed\n"); + } - /* set NTB format */ - req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE; - req.bNotificationType = USB_CDC_SET_NTB_FORMAT; - req.wValue = cpu_to_le16(USB_CDC_NCM_NTB16_FORMAT); - req.wIndex = cpu_to_le16(iface_no); - req.wLength = 0; + /* set NTB format, if both formats are supported */ + if (ntb_fmt_supported & USB_CDC_NCM_NTH32_SIGN) { + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | + USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_SET_NTB_FORMAT; + req.wValue = cpu_to_le16(USB_CDC_NCM_NTB16_FORMAT); + req.wIndex = cpu_to_le16(iface_no); + req.wLength = 0; + + err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000); + if (err) + pr_debug("Setting NTB format to 16-bit failed\n"); + } - err = cdc_ncm_do_request(ctx, &req, NULL, 0, NULL, 1000); - if (err) - pr_debug("Setting NTB format to 16-bit failed\n"); + ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE; /* set Max Datagram Size (MTU) */ - req.bmRequestType = USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE; - req.bNotificationType = USB_CDC_GET_MAX_DATAGRAM_SIZE; - req.wValue = 0; - req.wIndex = cpu_to_le16(iface_no); - req.wLength = cpu_to_le16(2); + if (flags & USB_CDC_NCM_NCAP_MAX_DATAGRAM_SIZE) { + __le16 max_datagram_size; + u16 eth_max_sz = le16_to_cpu(ctx->ether_desc->wMaxSegmentSize); + + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_IN | + USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_GET_MAX_DATAGRAM_SIZE; + req.wValue = 0; + req.wIndex = cpu_to_le16(iface_no); + req.wLength = cpu_to_le16(2); + + err = cdc_ncm_do_request(ctx, &req, &max_datagram_size, 0, NULL, + 1000); + if (err) { + pr_debug("GET_MAX_DATAGRAM_SIZE failed, use size=%u\n", + CDC_NCM_MIN_DATAGRAM_SIZE); + } else { + ctx->max_datagram_size = le16_to_cpu(max_datagram_size); + /* Check Eth descriptor value */ + if (eth_max_sz < CDC_NCM_MAX_DATAGRAM_SIZE) { + if (ctx->max_datagram_size > eth_max_sz) + ctx->max_datagram_size = eth_max_sz; + } else { + if (ctx->max_datagram_size > + CDC_NCM_MAX_DATAGRAM_SIZE) + ctx->max_datagram_size = + CDC_NCM_MAX_DATAGRAM_SIZE; + } - err = cdc_ncm_do_request(ctx, &req, &max_datagram_size, 0, NULL, 1000); - if (err) { - pr_debug(" GET_MAX_DATAGRAM_SIZE failed, using size=%u\n", - CDC_NCM_MIN_DATAGRAM_SIZE); - /* use default */ - ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE; - } else { - ctx->max_datagram_size = le16_to_cpu(max_datagram_size); + if (ctx->max_datagram_size < CDC_NCM_MIN_DATAGRAM_SIZE) + ctx->max_datagram_size = + CDC_NCM_MIN_DATAGRAM_SIZE; + + /* if value changed, update device */ + req.bmRequestType = USB_TYPE_CLASS | USB_DIR_OUT | + USB_RECIP_INTERFACE; + req.bNotificationType = USB_CDC_SET_MAX_DATAGRAM_SIZE; + req.wValue = 0; + req.wIndex = cpu_to_le16(iface_no); + req.wLength = 2; + max_datagram_size = cpu_to_le16(ctx->max_datagram_size); + + err = cdc_ncm_do_request(ctx, &req, &max_datagram_size, + 0, NULL, 1000); + if (err) + pr_debug("SET_MAX_DATAGRAM_SIZE failed\n"); + } - if (ctx->max_datagram_size < CDC_NCM_MIN_DATAGRAM_SIZE) - ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE; - else if (ctx->max_datagram_size > CDC_NCM_MAX_DATAGRAM_SIZE) - ctx->max_datagram_size = CDC_NCM_MAX_DATAGRAM_SIZE; } if (ctx->netdev->mtu != (ctx->max_datagram_size - ETH_HLEN)) @@ -466,19 +540,13 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf) ctx->ether_desc = (const struct usb_cdc_ether_desc *)buf; - dev->hard_mtu = le16_to_cpu(ctx->ether_desc->wMaxSegmentSize); - if (dev->hard_mtu < - (CDC_NCM_MIN_DATAGRAM_SIZE - ETH_HLEN)) - dev->hard_mtu = - CDC_NCM_MIN_DATAGRAM_SIZE - ETH_HLEN; - - else if (dev->hard_mtu > - (CDC_NCM_MAX_DATAGRAM_SIZE - ETH_HLEN)) - dev->hard_mtu = - CDC_NCM_MAX_DATAGRAM_SIZE - ETH_HLEN; + if (dev->hard_mtu < CDC_NCM_MIN_DATAGRAM_SIZE) + dev->hard_mtu = CDC_NCM_MIN_DATAGRAM_SIZE; + else if (dev->hard_mtu > CDC_NCM_MAX_DATAGRAM_SIZE) + dev->hard_mtu = CDC_NCM_MAX_DATAGRAM_SIZE; break; case USB_CDC_NCM_TYPE: @@ -628,13 +696,13 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) u32 offset; u32 last_offset; u16 n = 0; - u8 timeout = 0; + u8 ready2send = 0; /* if there is a remaining skb, it gets priority */ if (skb != NULL) swap(skb, ctx->tx_rem_skb); else - timeout = 1; + ready2send = 1; /* * +----------------+ @@ -682,9 +750,10 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) for (; n < ctx->tx_max_datagrams; n++) { /* check if end of transmit buffer is reached */ - if (offset >= ctx->tx_max) + if (offset >= ctx->tx_max) { + ready2send = 1; break; - + } /* compute maximum buffer size */ rem = ctx->tx_max - offset; @@ -711,9 +780,7 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) } ctx->tx_rem_skb = skb; skb = NULL; - - /* loop one more time */ - timeout = 1; + ready2send = 1; } break; } @@ -756,7 +823,7 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) ctx->tx_curr_last_offset = last_offset; goto exit_no_skb; - } else if ((n < ctx->tx_max_datagrams) && (timeout == 0)) { + } else if ((n < ctx->tx_max_datagrams) && (ready2send == 0)) { /* wait for more frames */ /* push variables */ ctx->tx_curr_skb = skb_out; @@ -813,7 +880,7 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) cpu_to_le16(sizeof(ctx->tx_ncm.nth16)); ctx->tx_ncm.nth16.wSequence = cpu_to_le16(ctx->tx_seq); ctx->tx_ncm.nth16.wBlockLength = cpu_to_le16(last_offset); - ctx->tx_ncm.nth16.wFpIndex = ALIGN(sizeof(struct usb_cdc_ncm_nth16), + ctx->tx_ncm.nth16.wNdpIndex = ALIGN(sizeof(struct usb_cdc_ncm_nth16), ctx->tx_ndp_modulus); memcpy(skb_out->data, &(ctx->tx_ncm.nth16), sizeof(ctx->tx_ncm.nth16)); @@ -825,13 +892,13 @@ cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb) rem = sizeof(ctx->tx_ncm.ndp16) + ((ctx->tx_curr_frame_num + 1) * sizeof(struct usb_cdc_ncm_dpe16)); ctx->tx_ncm.ndp16.wLength = cpu_to_le16(rem); - ctx->tx_ncm.ndp16.wNextFpIndex = 0; /* reserved */ + ctx->tx_ncm.ndp16.wNextNdpIndex = 0; /* reserved */ - memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wFpIndex, + memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wNdpIndex, &(ctx->tx_ncm.ndp16), sizeof(ctx->tx_ncm.ndp16)); - memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wFpIndex + + memcpy(((u8 *)skb_out->data) + ctx->tx_ncm.nth16.wNdpIndex + sizeof(ctx->tx_ncm.ndp16), &(ctx->tx_ncm.dpe16), (ctx->tx_curr_frame_num + 1) * @@ -961,7 +1028,7 @@ static int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in) goto error; } - temp = le16_to_cpu(ctx->rx_ncm.nth16.wFpIndex); + temp = le16_to_cpu(ctx->rx_ncm.nth16.wNdpIndex); if ((temp + sizeof(ctx->rx_ncm.ndp16)) > actlen) { pr_debug("invalid DPT16 index\n"); goto error; @@ -1048,10 +1115,10 @@ error: static void cdc_ncm_speed_change(struct cdc_ncm_ctx *ctx, - struct connection_speed_change *data) + struct usb_cdc_speed_change *data) { - uint32_t rx_speed = le32_to_cpu(data->USBitRate); - uint32_t tx_speed = le32_to_cpu(data->DSBitRate); + uint32_t rx_speed = le32_to_cpu(data->DLBitRRate); + uint32_t tx_speed = le32_to_cpu(data->ULBitRate); /* * Currently the USB-NET API does not support reporting the actual @@ -1092,7 +1159,7 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) /* test for split data in 8-byte chunks */ if (test_and_clear_bit(EVENT_STS_SPLIT, &dev->flags)) { cdc_ncm_speed_change(ctx, - (struct connection_speed_change *)urb->transfer_buffer); + (struct usb_cdc_speed_change *)urb->transfer_buffer); return; } @@ -1120,12 +1187,12 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) break; case USB_CDC_NOTIFY_SPEED_CHANGE: - if (urb->actual_length < - (sizeof(*event) + sizeof(struct connection_speed_change))) + if (urb->actual_length < (sizeof(*event) + + sizeof(struct usb_cdc_speed_change))) set_bit(EVENT_STS_SPLIT, &dev->flags); else cdc_ncm_speed_change(ctx, - (struct connection_speed_change *) &event[1]); + (struct usb_cdc_speed_change *) &event[1]); break; default: diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 02b622e..5002f5b 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -651,6 +651,10 @@ static const struct usb_device_id products[] = { .driver_info = (unsigned long)&dm9601_info, }, { + USB_DEVICE(0x0fe6, 0x9700), /* DM9601 USB to Fast Ethernet Adapter */ + .driver_info = (unsigned long)&dm9601_info, + }, + { USB_DEVICE(0x0a46, 0x9000), /* DM9000E */ .driver_info = (unsigned long)&dm9601_info, }, diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index bed8fce..6d83812 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2628,15 +2628,15 @@ exit: static void hso_free_tiomget(struct hso_serial *serial) { - struct hso_tiocmget *tiocmget = serial->tiocmget; + struct hso_tiocmget *tiocmget; + if (!serial) + return; + tiocmget = serial->tiocmget; if (tiocmget) { - if (tiocmget->urb) { - usb_free_urb(tiocmget->urb); - tiocmget->urb = NULL; - } + usb_free_urb(tiocmget->urb); + tiocmget->urb = NULL; serial->tiocmget = NULL; kfree(tiocmget); - } } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index ed9a416..95c41d5 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -931,8 +931,10 @@ fail_halt: if (urb != NULL) { clear_bit (EVENT_RX_MEMORY, &dev->flags); status = usb_autopm_get_interface(dev->intf); - if (status < 0) + if (status < 0) { + usb_free_urb(urb); goto fail_lowmem; + } if (rx_submit (dev, urb, GFP_KERNEL) == -ENOLINK) resched = 0; usb_autopm_put_interface(dev->intf); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 90a23e4..82dba5a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -446,6 +446,20 @@ static void skb_recv_done(struct virtqueue *rvq) } } +static void virtnet_napi_enable(struct virtnet_info *vi) +{ + napi_enable(&vi->napi); + + /* If all buffers were filled by other side before we napi_enabled, we + * won't get another interrupt, so process any outstanding packets + * now. virtnet_poll wants re-enable the queue, so we disable here. + * We synchronize against interrupts via NAPI_STATE_SCHED */ + if (napi_schedule_prep(&vi->napi)) { + virtqueue_disable_cb(vi->rvq); + __napi_schedule(&vi->napi); + } +} + static void refill_work(struct work_struct *work) { struct virtnet_info *vi; @@ -454,7 +468,7 @@ static void refill_work(struct work_struct *work) vi = container_of(work, struct virtnet_info, refill.work); napi_disable(&vi->napi); still_empty = !try_fill_recv(vi, GFP_KERNEL); - napi_enable(&vi->napi); + virtnet_napi_enable(vi); /* In theory, this can happen: if we don't get any buffers in * we will *never* try to fill again. */ @@ -638,16 +652,7 @@ static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); - napi_enable(&vi->napi); - - /* If all buffers were filled by other side before we napi_enabled, we - * won't get another interrupt, so process any outstanding packets - * now. virtnet_poll wants re-enable the queue, so we disable here. - * We synchronize against interrupts via NAPI_STATE_SCHED */ - if (napi_schedule_prep(&vi->napi)) { - virtqueue_disable_cb(vi->rvq); - __napi_schedule(&vi->napi); - } + virtnet_napi_enable(vi); return 0; } diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c index 01c05f5..228d4f7 100644 --- a/drivers/net/vxge/vxge-config.c +++ b/drivers/net/vxge/vxge-config.c @@ -3690,7 +3690,7 @@ __vxge_hw_vpath_rts_table_get(struct __vxge_hw_vpath_handle *vp, if (status != VXGE_HW_OK) goto exit; - if ((rts_table != VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) || + if ((rts_table != VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) && (rts_table != VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) *data1 = 0; diff --git a/drivers/net/wireless/ath/ath5k/dma.c b/drivers/net/wireless/ath/ath5k/dma.c index 0064be7..21091c2 100644 --- a/drivers/net/wireless/ath/ath5k/dma.c +++ b/drivers/net/wireless/ath/ath5k/dma.c @@ -838,9 +838,9 @@ int ath5k_hw_dma_stop(struct ath5k_hw *ah) for (i = 0; i < qmax; i++) { err = ath5k_hw_stop_tx_dma(ah, i); /* -EINVAL -> queue inactive */ - if (err != -EINVAL) + if (err && err != -EINVAL) return err; } - return err; + return 0; } diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c index e5f2b96..a702817 100644 --- a/drivers/net/wireless/ath/ath5k/pcu.c +++ b/drivers/net/wireless/ath/ath5k/pcu.c @@ -86,7 +86,7 @@ int ath5k_hw_get_frame_duration(struct ath5k_hw *ah, if (!ah->ah_bwmode) { dur = ieee80211_generic_frame_duration(sc->hw, NULL, len, rate); - return dur; + return le16_to_cpu(dur); } bitrate = rate->bitrate; @@ -265,8 +265,6 @@ static inline void ath5k_hw_write_rate_duration(struct ath5k_hw *ah) * what rate we should choose to TX ACKs. */ tx_time = ath5k_hw_get_frame_duration(ah, 10, rate); - tx_time = le16_to_cpu(tx_time); - ath5k_hw_reg_write(ah, tx_time, reg); if (!(rate->flags & IEEE80211_RATE_SHORT_PREAMBLE)) diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c index 78c26fd..62ce2f4 100644 --- a/drivers/net/wireless/ath/ath5k/phy.c +++ b/drivers/net/wireless/ath/ath5k/phy.c @@ -282,6 +282,34 @@ int ath5k_hw_phy_disable(struct ath5k_hw *ah) return 0; } +/* + * Wait for synth to settle + */ +static void ath5k_hw_wait_for_synth(struct ath5k_hw *ah, + struct ieee80211_channel *channel) +{ + /* + * On 5211+ read activation -> rx delay + * and use it (100ns steps). + */ + if (ah->ah_version != AR5K_AR5210) { + u32 delay; + delay = ath5k_hw_reg_read(ah, AR5K_PHY_RX_DELAY) & + AR5K_PHY_RX_DELAY_M; + delay = (channel->hw_value & CHANNEL_CCK) ? + ((delay << 2) / 22) : (delay / 10); + if (ah->ah_bwmode == AR5K_BWMODE_10MHZ) + delay = delay << 1; + if (ah->ah_bwmode == AR5K_BWMODE_5MHZ) + delay = delay << 2; + /* XXX: /2 on turbo ? Let's be safe + * for now */ + udelay(100 + delay); + } else { + mdelay(1); + } +} + /**********************\ * RF Gain optimization * @@ -1253,6 +1281,7 @@ static int ath5k_hw_channel(struct ath5k_hw *ah, case AR5K_RF5111: ret = ath5k_hw_rf5111_channel(ah, channel); break; + case AR5K_RF2317: case AR5K_RF2425: ret = ath5k_hw_rf2425_channel(ah, channel); break; @@ -3237,6 +3266,13 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, /* Failed */ if (i >= 100) return -EIO; + + /* Set channel and wait for synth */ + ret = ath5k_hw_channel(ah, channel); + if (ret) + return ret; + + ath5k_hw_wait_for_synth(ah, channel); } /* @@ -3251,13 +3287,53 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, if (ret) return ret; + /* Write OFDM timings on 5212*/ + if (ah->ah_version == AR5K_AR5212 && + channel->hw_value & CHANNEL_OFDM) { + + ret = ath5k_hw_write_ofdm_timings(ah, channel); + if (ret) + return ret; + + /* Spur info is available only from EEPROM versions + * greater than 5.3, but the EEPROM routines will use + * static values for older versions */ + if (ah->ah_mac_srev >= AR5K_SREV_AR5424) + ath5k_hw_set_spur_mitigation_filter(ah, + channel); + } + + /* If we used fast channel switching + * we are done, release RF bus and + * fire up NF calibration. + * + * Note: Only NF calibration due to + * channel change, not AGC calibration + * since AGC is still running ! + */ + if (fast) { + /* + * Release RF Bus grant + */ + AR5K_REG_DISABLE_BITS(ah, AR5K_PHY_RFBUS_REQ, + AR5K_PHY_RFBUS_REQ_REQUEST); + + /* + * Start NF calibration + */ + AR5K_REG_ENABLE_BITS(ah, AR5K_PHY_AGCCTL, + AR5K_PHY_AGCCTL_NF); + + return ret; + } + /* * For 5210 we do all initialization using * initvals, so we don't have to modify * any settings (5210 also only supports * a/aturbo modes) */ - if ((ah->ah_version != AR5K_AR5210) && !fast) { + if (ah->ah_version != AR5K_AR5210) { /* * Write initial RF gain settings @@ -3276,22 +3352,6 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, if (ret) return ret; - /* Write OFDM timings on 5212*/ - if (ah->ah_version == AR5K_AR5212 && - channel->hw_value & CHANNEL_OFDM) { - - ret = ath5k_hw_write_ofdm_timings(ah, channel); - if (ret) - return ret; - - /* Spur info is available only from EEPROM versions - * greater than 5.3, but the EEPROM routines will use - * static values for older versions */ - if (ah->ah_mac_srev >= AR5K_SREV_AR5424) - ath5k_hw_set_spur_mitigation_filter(ah, - channel); - } - /*Enable/disable 802.11b mode on 5111 (enable 2111 frequency converter + CCK)*/ if (ah->ah_radio == AR5K_RF5111) { @@ -3322,47 +3382,20 @@ int ath5k_hw_phy_init(struct ath5k_hw *ah, struct ieee80211_channel *channel, */ ath5k_hw_reg_write(ah, AR5K_PHY_ACT_ENABLE, AR5K_PHY_ACT); + ath5k_hw_wait_for_synth(ah, channel); + /* - * On 5211+ read activation -> rx delay - * and use it. + * Perform ADC test to see if baseband is ready + * Set tx hold and check adc test register */ - if (ah->ah_version != AR5K_AR5210) { - u32 delay; - delay = ath5k_hw_reg_read(ah, AR5K_PHY_RX_DELAY) & - AR5K_PHY_RX_DELAY_M; - delay = (channel->hw_value & CHANNEL_CCK) ? - ((delay << 2) / 22) : (delay / 10); - if (ah->ah_bwmode == AR5K_BWMODE_10MHZ) - delay = delay << 1; - if (ah->ah_bwmode == AR5K_BWMODE_5MHZ) - delay = delay << 2; - /* XXX: /2 on turbo ? Let's be safe - * for now */ - udelay(100 + delay); - } else { - mdelay(1); - } - - if (fast) - /* - * Release RF Bus grant - */ - AR5K_REG_DISABLE_BITS(ah, AR5K_PHY_RFBUS_REQ, - AR5K_PHY_RFBUS_REQ_REQUEST); - else { - /* - * Perform ADC test to see if baseband is ready - * Set tx hold and check adc test register - */ - phy_tst1 = ath5k_hw_reg_read(ah, AR5K_PHY_TST1); - ath5k_hw_reg_write(ah, AR5K_PHY_TST1_TXHOLD, AR5K_PHY_TST1); - for (i = 0; i <= 20; i++) { - if (!(ath5k_hw_reg_read(ah, AR5K_PHY_ADC_TEST) & 0x10)) - break; - udelay(200); - } - ath5k_hw_reg_write(ah, phy_tst1, AR5K_PHY_TST1); + phy_tst1 = ath5k_hw_reg_read(ah, AR5K_PHY_TST1); + ath5k_hw_reg_write(ah, AR5K_PHY_TST1_TXHOLD, AR5K_PHY_TST1); + for (i = 0; i <= 20; i++) { + if (!(ath5k_hw_reg_read(ah, AR5K_PHY_ADC_TEST) & 0x10)) + break; + udelay(200); } + ath5k_hw_reg_write(ah, phy_tst1, AR5K_PHY_TST1); /* * Start automatic gain control calibration diff --git a/drivers/net/wireless/ath/ath9k/ar9002_hw.c b/drivers/net/wireless/ath/ath9k/ar9002_hw.c index f8a7771..f44c84a 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_hw.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_hw.c @@ -426,9 +426,8 @@ static void ar9002_hw_configpcipowersave(struct ath_hw *ah, } /* WAR for ASPM system hang */ - if (AR_SREV_9280(ah) || AR_SREV_9285(ah) || AR_SREV_9287(ah)) { + if (AR_SREV_9285(ah) || AR_SREV_9287(ah)) val |= (AR_WA_BIT6 | AR_WA_BIT7); - } if (AR_SREV_9285E_20(ah)) val |= AR_WA_BIT23; diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index 3681caf5..1a7fa6e 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -21,7 +21,6 @@ #include <linux/device.h> #include <linux/leds.h> #include <linux/completion.h> -#include <linux/pm_qos_params.h> #include "debug.h" #include "common.h" @@ -57,8 +56,6 @@ struct ath_node; #define A_MAX(a, b) ((a) > (b) ? (a) : (b)) -#define ATH9K_PM_QOS_DEFAULT_VALUE 55 - #define TSF_TO_TU(_h,_l) \ ((((u32)(_h)) << 22) | (((u32)(_l)) >> 10)) @@ -218,6 +215,7 @@ struct ath_frame_info { struct ath_buf_state { u8 bf_type; u8 bfs_paprd; + unsigned long bfs_paprd_timestamp; enum ath9k_internal_frame_type bfs_ftype; }; @@ -593,7 +591,6 @@ struct ath_softc { struct work_struct paprd_work; struct work_struct hw_check_work; struct completion paprd_complete; - bool paprd_pending; u32 intrstatus; u32 sc_flags; /* SC_OP_* */ @@ -633,8 +630,6 @@ struct ath_softc { struct ath_descdma txsdma; struct ath_ant_comb ant_comb; - - struct pm_qos_request_list pm_qos_req; }; struct ath_wiphy { @@ -666,7 +661,6 @@ static inline void ath_read_cachesize(struct ath_common *common, int *csz) extern struct ieee80211_ops ath9k_ops; extern int ath9k_modparam_nohwcrypt; extern int led_blink; -extern int ath9k_pm_qos_value; extern bool is_ath9k_unloaded; irqreturn_t ath_isr(int irq, void *dev); diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 5ab3084..07b1633 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -219,8 +219,9 @@ static int __hif_usb_tx(struct hif_device_usb *hif_dev) struct tx_buf *tx_buf = NULL; struct sk_buff *nskb = NULL; int ret = 0, i; - u16 *hdr, tx_skb_cnt = 0; + u16 tx_skb_cnt = 0; u8 *buf; + __le16 *hdr; if (hif_dev->tx.tx_skb_cnt == 0) return 0; @@ -245,9 +246,9 @@ static int __hif_usb_tx(struct hif_device_usb *hif_dev) buf = tx_buf->buf; buf += tx_buf->offset; - hdr = (u16 *)buf; - *hdr++ = nskb->len; - *hdr++ = ATH_USB_TX_STREAM_MODE_TAG; + hdr = (__le16 *)buf; + *hdr++ = cpu_to_le16(nskb->len); + *hdr++ = cpu_to_le16(ATH_USB_TX_STREAM_MODE_TAG); buf += 4; memcpy(buf, nskb->data, nskb->len); tx_buf->len = nskb->len + 4; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 38433f9..0352f09 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -142,9 +142,6 @@ static void ath9k_deinit_priv(struct ath9k_htc_priv *priv) { ath9k_htc_exit_debug(priv->ah); ath9k_hw_deinit(priv->ah); - tasklet_kill(&priv->swba_tasklet); - tasklet_kill(&priv->rx_tasklet); - tasklet_kill(&priv->tx_tasklet); kfree(priv->ah); priv->ah = NULL; } diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index f4d576b..6bb5995 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -1025,12 +1025,6 @@ static void ath9k_htc_stop(struct ieee80211_hw *hw) int ret = 0; u8 cmd_rsp; - /* Cancel all the running timers/work .. */ - cancel_work_sync(&priv->fatal_work); - cancel_work_sync(&priv->ps_work); - cancel_delayed_work_sync(&priv->ath9k_led_blink_work); - ath9k_led_stop_brightness(priv); - mutex_lock(&priv->mutex); if (priv->op_flags & OP_INVALID) { @@ -1044,8 +1038,23 @@ static void ath9k_htc_stop(struct ieee80211_hw *hw) WMI_CMD(WMI_DISABLE_INTR_CMDID); WMI_CMD(WMI_DRAIN_TXQ_ALL_CMDID); WMI_CMD(WMI_STOP_RECV_CMDID); + + tasklet_kill(&priv->swba_tasklet); + tasklet_kill(&priv->rx_tasklet); + tasklet_kill(&priv->tx_tasklet); + skb_queue_purge(&priv->tx_queue); + mutex_unlock(&priv->mutex); + + /* Cancel all the running timers/work .. */ + cancel_work_sync(&priv->fatal_work); + cancel_work_sync(&priv->ps_work); + cancel_delayed_work_sync(&priv->ath9k_led_blink_work); + ath9k_led_stop_brightness(priv); + + mutex_lock(&priv->mutex); + /* Remove monitor interface here */ if (ah->opmode == NL80211_IFTYPE_MONITOR) { if (ath9k_htc_remove_monitor_interface(priv)) diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 767d8b8..a033d01 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -41,10 +41,6 @@ static int ath9k_btcoex_enable; module_param_named(btcoex_enable, ath9k_btcoex_enable, int, 0444); MODULE_PARM_DESC(btcoex_enable, "Enable wifi-BT coexistence"); -int ath9k_pm_qos_value = ATH9K_PM_QOS_DEFAULT_VALUE; -module_param_named(pmqos, ath9k_pm_qos_value, int, S_IRUSR | S_IRGRP | S_IROTH); -MODULE_PARM_DESC(pmqos, "User specified PM-QOS value"); - bool is_ath9k_unloaded; /* We use the hw_value as an index into our private channel structure */ @@ -598,8 +594,6 @@ err_btcoex: err_queues: ath9k_hw_deinit(ah); err_hw: - tasklet_kill(&sc->intr_tq); - tasklet_kill(&sc->bcon_tasklet); kfree(ah); sc->sc_ah = NULL; @@ -764,9 +758,6 @@ int ath9k_init_device(u16 devid, struct ath_softc *sc, u16 subsysid, ath_init_leds(sc); ath_start_rfkill_poll(sc); - pm_qos_add_request(&sc->pm_qos_req, PM_QOS_CPU_DMA_LATENCY, - PM_QOS_DEFAULT_VALUE); - return 0; error_world: @@ -807,9 +798,6 @@ static void ath9k_deinit_softc(struct ath_softc *sc) ath9k_hw_deinit(sc->sc_ah); - tasklet_kill(&sc->intr_tq); - tasklet_kill(&sc->bcon_tasklet); - kfree(sc->sc_ah); sc->sc_ah = NULL; } @@ -824,6 +812,8 @@ void ath9k_deinit_device(struct ath_softc *sc) wiphy_rfkill_stop_polling(sc->hw->wiphy); ath_deinit_leds(sc); + ath9k_ps_restore(sc); + for (i = 0; i < sc->num_sec_wiphy; i++) { struct ath_wiphy *aphy = sc->sec_wiphy[i]; if (aphy == NULL) @@ -834,7 +824,6 @@ void ath9k_deinit_device(struct ath_softc *sc) } ieee80211_unregister_hw(hw); - pm_qos_remove_request(&sc->pm_qos_req); ath_rx_cleanup(sc); ath_tx_cleanup(sc); ath9k_deinit_softc(sc); diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index 180170d..2915b11 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -885,7 +885,7 @@ void ath9k_hw_set_interrupts(struct ath_hw *ah, enum ath9k_int ints) struct ath_common *common = ath9k_hw_common(ah); if (!(ints & ATH9K_INT_GLOBAL)) - ath9k_hw_enable_interrupts(ah); + ath9k_hw_disable_interrupts(ah); ath_dbg(common, ATH_DBG_INTERRUPT, "0x%x => 0x%x\n", omask, ints); @@ -963,7 +963,8 @@ void ath9k_hw_set_interrupts(struct ath_hw *ah, enum ath9k_int ints) REG_CLR_BIT(ah, AR_IMR_S5, AR_IMR_S5_TIM_TIMER); } - ath9k_hw_enable_interrupts(ah); + if (ints & ATH9K_INT_GLOBAL) + ath9k_hw_enable_interrupts(ah); return; } diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index c79c97b..a09d15f 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -325,6 +325,8 @@ static bool ath_paprd_send_frame(struct ath_softc *sc, struct sk_buff *skb, int { struct ieee80211_hw *hw = sc->hw; struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); struct ath_tx_control txctl; int time_left; @@ -340,14 +342,16 @@ static bool ath_paprd_send_frame(struct ath_softc *sc, struct sk_buff *skb, int tx_info->control.rates[1].idx = -1; init_completion(&sc->paprd_complete); - sc->paprd_pending = true; txctl.paprd = BIT(chain); - if (ath_tx_start(hw, skb, &txctl) != 0) + + if (ath_tx_start(hw, skb, &txctl) != 0) { + ath_dbg(common, ATH_DBG_XMIT, "PAPRD TX failed\n"); + dev_kfree_skb_any(skb); return false; + } time_left = wait_for_completion_timeout(&sc->paprd_complete, msecs_to_jiffies(ATH_PAPRD_TIMEOUT)); - sc->paprd_pending = false; if (!time_left) ath_dbg(ath9k_hw_common(sc->sc_ah), ATH_DBG_CALIBRATE, @@ -953,8 +957,6 @@ void ath_radio_disable(struct ath_softc *sc, struct ieee80211_hw *hw) spin_unlock_bh(&sc->sc_pcu_lock); ath9k_ps_restore(sc); - - ath9k_setpower(sc, ATH9K_PM_FULL_SLEEP); } int ath_reset(struct ath_softc *sc, bool retry_tx) @@ -1171,12 +1173,6 @@ static int ath9k_start(struct ieee80211_hw *hw) ath9k_btcoex_timer_resume(sc); } - /* User has the option to provide pm-qos value as a module - * parameter rather than using the default value of - * 'ATH9K_PM_QOS_DEFAULT_VALUE'. - */ - pm_qos_update_request(&sc->pm_qos_req, ath9k_pm_qos_value); - if (ah->caps.pcie_lcr_extsync_en && common->bus_ops->extn_synch_en) common->bus_ops->extn_synch_en(common); @@ -1309,6 +1305,9 @@ static void ath9k_stop(struct ieee80211_hw *hw) spin_lock_bh(&sc->sc_pcu_lock); + /* prevent tasklets to enable interrupts once we disable them */ + ah->imask &= ~ATH9K_INT_GLOBAL; + /* make sure h/w will not generate any interrupt * before setting the invalid flag. */ ath9k_hw_disable_interrupts(ah); @@ -1326,6 +1325,12 @@ static void ath9k_stop(struct ieee80211_hw *hw) spin_unlock_bh(&sc->sc_pcu_lock); + /* we can now sync irq and kill any running tasklets, since we already + * disabled interrupts and not holding a spin lock */ + synchronize_irq(sc->irq); + tasklet_kill(&sc->intr_tq); + tasklet_kill(&sc->bcon_tasklet); + ath9k_ps_restore(sc); sc->ps_idle = true; @@ -1334,8 +1339,6 @@ static void ath9k_stop(struct ieee80211_hw *hw) sc->sc_flags |= SC_OP_INVALID; - pm_qos_update_request(&sc->pm_qos_req, PM_QOS_DEFAULT_VALUE); - mutex_unlock(&sc->mutex); ath_dbg(common, ATH_DBG_CONFIG, "Driver halt\n"); diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 33a37ed..07b7804 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -1725,6 +1725,9 @@ static void ath_tx_start_dma(struct ath_softc *sc, struct ath_buf *bf, ar9003_hw_set_paprd_txdesc(sc->sc_ah, bf->bf_desc, bf->bf_state.bfs_paprd); + if (txctl->paprd) + bf->bf_state.bfs_paprd_timestamp = jiffies; + ath_tx_send_normal(sc, txctl->txq, tid, &bf_head); } @@ -1886,7 +1889,9 @@ static void ath_tx_complete_buf(struct ath_softc *sc, struct ath_buf *bf, bf->bf_buf_addr = 0; if (bf->bf_state.bfs_paprd) { - if (!sc->paprd_pending) + if (time_after(jiffies, + bf->bf_state.bfs_paprd_timestamp + + msecs_to_jiffies(ATH_PAPRD_TIMEOUT))) dev_kfree_skb_any(skb); else complete(&sc->paprd_complete); diff --git a/drivers/net/wireless/ath/carl9170/rx.c b/drivers/net/wireless/ath/carl9170/rx.c index 939a0e9..84866a4 100644 --- a/drivers/net/wireless/ath/carl9170/rx.c +++ b/drivers/net/wireless/ath/carl9170/rx.c @@ -564,7 +564,7 @@ static void carl9170_ps_beacon(struct ar9170 *ar, void *data, unsigned int len) cam = ieee80211_check_tim(tim_ie, tim_len, ar->common.curaid); /* 2. Maybe the AP wants to send multicast/broadcast data? */ - cam = !!(tim_ie->bitmap_ctrl & 0x01); + cam |= !!(tim_ie->bitmap_ctrl & 0x01); if (!cam) { /* back to low-power land. */ diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c index 537732e..f82c400 100644 --- a/drivers/net/wireless/ath/carl9170/usb.c +++ b/drivers/net/wireless/ath/carl9170/usb.c @@ -118,6 +118,8 @@ static struct usb_device_id carl9170_usb_ids[] = { { USB_DEVICE(0x057c, 0x8402) }, /* Qwest/Actiontec 802AIN Wireless N USB Network Adapter */ { USB_DEVICE(0x1668, 0x1200) }, + /* Airlive X.USB a/b/g/n */ + { USB_DEVICE(0x1b75, 0x9170) }, /* terminate */ {} diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.c b/drivers/net/wireless/iwlwifi/iwl-3945.c index a9b852b..39b6f16 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945.c @@ -402,72 +402,6 @@ static void iwl3945_accumulative_statistics(struct iwl_priv *priv, } #endif -/** - * iwl3945_good_plcp_health - checks for plcp error. - * - * When the plcp error is exceeding the thresholds, reset the radio - * to improve the throughput. - */ -static bool iwl3945_good_plcp_health(struct iwl_priv *priv, - struct iwl_rx_packet *pkt) -{ - bool rc = true; - struct iwl3945_notif_statistics current_stat; - int combined_plcp_delta; - unsigned int plcp_msec; - unsigned long plcp_received_jiffies; - - if (priv->cfg->base_params->plcp_delta_threshold == - IWL_MAX_PLCP_ERR_THRESHOLD_DISABLE) { - IWL_DEBUG_RADIO(priv, "plcp_err check disabled\n"); - return rc; - } - memcpy(¤t_stat, pkt->u.raw, sizeof(struct - iwl3945_notif_statistics)); - /* - * check for plcp_err and trigger radio reset if it exceeds - * the plcp error threshold plcp_delta. - */ - plcp_received_jiffies = jiffies; - plcp_msec = jiffies_to_msecs((long) plcp_received_jiffies - - (long) priv->plcp_jiffies); - priv->plcp_jiffies = plcp_received_jiffies; - /* - * check to make sure plcp_msec is not 0 to prevent division - * by zero. - */ - if (plcp_msec) { - combined_plcp_delta = - (le32_to_cpu(current_stat.rx.ofdm.plcp_err) - - le32_to_cpu(priv->_3945.statistics.rx.ofdm.plcp_err)); - - if ((combined_plcp_delta > 0) && - ((combined_plcp_delta * 100) / plcp_msec) > - priv->cfg->base_params->plcp_delta_threshold) { - /* - * if plcp_err exceed the threshold, the following - * data is printed in csv format: - * Text: plcp_err exceeded %d, - * Received ofdm.plcp_err, - * Current ofdm.plcp_err, - * combined_plcp_delta, - * plcp_msec - */ - IWL_DEBUG_RADIO(priv, "plcp_err exceeded %u, " - "%u, %d, %u mSecs\n", - priv->cfg->base_params->plcp_delta_threshold, - le32_to_cpu(current_stat.rx.ofdm.plcp_err), - combined_plcp_delta, plcp_msec); - /* - * Reset the RF radio due to the high plcp - * error rate - */ - rc = false; - } - } - return rc; -} - void iwl3945_hw_rx_statistics(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb) { @@ -2734,7 +2668,6 @@ static struct iwl_lib_ops iwl3945_lib = { .isr_ops = { .isr = iwl_isr_legacy, }, - .check_plcp_health = iwl3945_good_plcp_health, .debugfs_ops = { .rx_stats_read = iwl3945_ucode_rx_stats_read, diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c index 79ab0a6..537fb8c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-5000.c +++ b/drivers/net/wireless/iwlwifi/iwl-5000.c @@ -51,7 +51,7 @@ #include "iwl-agn-debugfs.h" /* Highest firmware API version supported */ -#define IWL5000_UCODE_API_MAX 2 +#define IWL5000_UCODE_API_MAX 5 #define IWL5150_UCODE_API_MAX 2 /* Lowest firmware API version supported */ diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index af505bc..ef36aff 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -681,6 +681,8 @@ struct iwl_cfg iwl6000i_2bg_cfg = { .fw_name_pre = IWL6050_FW_PRE, \ .ucode_api_max = IWL6050_UCODE_API_MAX, \ .ucode_api_min = IWL6050_UCODE_API_MIN, \ + .valid_tx_ant = ANT_AB, /* .cfg overwrite */ \ + .valid_rx_ant = ANT_AB, /* .cfg overwrite */ \ .ops = &iwl6050_ops, \ .eeprom_ver = EEPROM_6050_EEPROM_VERSION, \ .eeprom_calib_ver = EEPROM_6050_TX_POWER_VERSION, \ diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index 36335b1..c1cfd99 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -1157,6 +1157,9 @@ static void iwl_irq_tasklet_legacy(struct iwl_priv *priv) /* only Re-enable if disabled by irq */ if (test_bit(STATUS_INT_ENABLED, &priv->status)) iwl_enable_interrupts(priv); + /* Re-enable RF_KILL if it occurred */ + else if (handled & CSR_INT_BIT_RF_KILL) + iwl_enable_rfkill_int(priv); #ifdef CONFIG_IWLWIFI_DEBUG if (iwl_get_debug_level(priv) & (IWL_DL_ISR)) { @@ -1371,6 +1374,9 @@ static void iwl_irq_tasklet(struct iwl_priv *priv) /* only Re-enable if disabled by irq */ if (test_bit(STATUS_INT_ENABLED, &priv->status)) iwl_enable_interrupts(priv); + /* Re-enable RF_KILL if it occurred */ + else if (handled & CSR_INT_BIT_RF_KILL) + iwl_enable_rfkill_int(priv); } /* the threshold ratio of actual_ack_cnt to expected_ack_cnt in percent */ diff --git a/drivers/net/wireless/p54/p54pci.c b/drivers/net/wireless/p54/p54pci.c index 1eacba4..0494d7b 100644 --- a/drivers/net/wireless/p54/p54pci.c +++ b/drivers/net/wireless/p54/p54pci.c @@ -199,6 +199,7 @@ static void p54p_check_rx_ring(struct ieee80211_hw *dev, u32 *index, while (i != idx) { u16 len; struct sk_buff *skb; + dma_addr_t dma_addr; desc = &ring[i]; len = le16_to_cpu(desc->len); skb = rx_buf[i]; @@ -216,17 +217,20 @@ static void p54p_check_rx_ring(struct ieee80211_hw *dev, u32 *index, len = priv->common.rx_mtu; } + dma_addr = le32_to_cpu(desc->host_addr); + pci_dma_sync_single_for_cpu(priv->pdev, dma_addr, + priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE); skb_put(skb, len); if (p54_rx(dev, skb)) { - pci_unmap_single(priv->pdev, - le32_to_cpu(desc->host_addr), - priv->common.rx_mtu + 32, - PCI_DMA_FROMDEVICE); + pci_unmap_single(priv->pdev, dma_addr, + priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE); rx_buf[i] = NULL; - desc->host_addr = 0; + desc->host_addr = cpu_to_le32(0); } else { skb_trim(skb, 0); + pci_dma_sync_single_for_device(priv->pdev, dma_addr, + priv->common.rx_mtu + 32, PCI_DMA_FROMDEVICE); desc->len = cpu_to_le16(priv->common.rx_mtu + 32); } diff --git a/drivers/net/wireless/p54/p54usb.c b/drivers/net/wireless/p54/p54usb.c index 21713a7..9b344a9 100644 --- a/drivers/net/wireless/p54/p54usb.c +++ b/drivers/net/wireless/p54/p54usb.c @@ -98,6 +98,7 @@ static struct usb_device_id p54u_table[] __devinitdata = { {USB_DEVICE(0x1413, 0x5400)}, /* Telsey 802.11g USB2.0 Adapter */ {USB_DEVICE(0x1435, 0x0427)}, /* Inventel UR054G */ {USB_DEVICE(0x1668, 0x1050)}, /* Actiontec 802UIG-1 */ + {USB_DEVICE(0x1740, 0x1000)}, /* Senao NUB-350 */ {USB_DEVICE(0x2001, 0x3704)}, /* DLink DWL-G122 rev A2 */ {USB_DEVICE(0x2001, 0x3705)}, /* D-Link DWL-G120 rev C1 */ {USB_DEVICE(0x413c, 0x5513)}, /* Dell WLA3310 USB Wireless Adapter */ diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 848cc2c..518542b 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -2597,6 +2597,9 @@ static int rndis_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, __le32 mode; int ret; + if (priv->device_type != RNDIS_BCM4320B) + return -ENOTSUPP; + netdev_dbg(usbdev->net, "%s(): %s, %d\n", __func__, enabled ? "enabled" : "disabled", timeout); diff --git a/drivers/net/wireless/rt2x00/rt2800pci.c b/drivers/net/wireless/rt2x00/rt2800pci.c index aa97971..3b3f1e4 100644 --- a/drivers/net/wireless/rt2x00/rt2800pci.c +++ b/drivers/net/wireless/rt2x00/rt2800pci.c @@ -652,6 +652,12 @@ static void rt2800pci_fill_rxdone(struct queue_entry *entry, */ rxdesc->flags |= RX_FLAG_IV_STRIPPED; + /* + * The hardware has already checked the Michael Mic and has + * stripped it from the frame. Signal this to mac80211. + */ + rxdesc->flags |= RX_FLAG_MMIC_STRIPPED; + if (rxdesc->cipher_status == RX_CRYPTO_SUCCESS) rxdesc->flags |= RX_FLAG_DECRYPTED; else if (rxdesc->cipher_status == RX_CRYPTO_FAIL_MIC) @@ -1065,6 +1071,8 @@ static DEFINE_PCI_DEVICE_TABLE(rt2800pci_device_table) = { { PCI_DEVICE(0x1814, 0x3390), PCI_DEVICE_DATA(&rt2800pci_ops) }, #endif #ifdef CONFIG_RT2800PCI_RT35XX + { PCI_DEVICE(0x1432, 0x7711), PCI_DEVICE_DATA(&rt2800pci_ops) }, + { PCI_DEVICE(0x1432, 0x7722), PCI_DEVICE_DATA(&rt2800pci_ops) }, { PCI_DEVICE(0x1814, 0x3060), PCI_DEVICE_DATA(&rt2800pci_ops) }, { PCI_DEVICE(0x1814, 0x3062), PCI_DEVICE_DATA(&rt2800pci_ops) }, { PCI_DEVICE(0x1814, 0x3562), PCI_DEVICE_DATA(&rt2800pci_ops) }, diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index b97a4a5..197a36c 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -486,6 +486,12 @@ static void rt2800usb_fill_rxdone(struct queue_entry *entry, */ rxdesc->flags |= RX_FLAG_IV_STRIPPED; + /* + * The hardware has already checked the Michael Mic and has + * stripped it from the frame. Signal this to mac80211. + */ + rxdesc->flags |= RX_FLAG_MMIC_STRIPPED; + if (rxdesc->cipher_status == RX_CRYPTO_SUCCESS) rxdesc->flags |= RX_FLAG_DECRYPTED; else if (rxdesc->cipher_status == RX_CRYPTO_FAIL_MIC) diff --git a/drivers/net/wireless/rtlwifi/efuse.c b/drivers/net/wireless/rtlwifi/efuse.c index b8433f3..62876cd 100644 --- a/drivers/net/wireless/rtlwifi/efuse.c +++ b/drivers/net/wireless/rtlwifi/efuse.c @@ -726,9 +726,9 @@ static int efuse_pg_packet_read(struct ieee80211_hw *hw, u8 offset, u8 *data) } static void efuse_write_data_case1(struct ieee80211_hw *hw, u16 *efuse_addr, - u8 efuse_data, u8 offset, int *bcontinual, - u8 *write_state, struct pgpkt_struct target_pkt, - int *repeat_times, int *bresult, u8 word_en) + u8 efuse_data, u8 offset, int *bcontinual, + u8 *write_state, struct pgpkt_struct *target_pkt, + int *repeat_times, int *bresult, u8 word_en) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct pgpkt_struct tmp_pkt; @@ -744,8 +744,8 @@ static void efuse_write_data_case1(struct ieee80211_hw *hw, u16 *efuse_addr, tmp_pkt.word_en = tmp_header & 0x0F; tmp_word_cnts = efuse_calculate_word_cnts(tmp_pkt.word_en); - if (tmp_pkt.offset != target_pkt.offset) { - efuse_addr = efuse_addr + (tmp_word_cnts * 2) + 1; + if (tmp_pkt.offset != target_pkt->offset) { + *efuse_addr = *efuse_addr + (tmp_word_cnts * 2) + 1; *write_state = PG_STATE_HEADER; } else { for (tmpindex = 0; tmpindex < (tmp_word_cnts * 2); tmpindex++) { @@ -756,23 +756,23 @@ static void efuse_write_data_case1(struct ieee80211_hw *hw, u16 *efuse_addr, } if (bdataempty == false) { - efuse_addr = efuse_addr + (tmp_word_cnts * 2) + 1; + *efuse_addr = *efuse_addr + (tmp_word_cnts * 2) + 1; *write_state = PG_STATE_HEADER; } else { match_word_en = 0x0F; - if (!((target_pkt.word_en & BIT(0)) | + if (!((target_pkt->word_en & BIT(0)) | (tmp_pkt.word_en & BIT(0)))) match_word_en &= (~BIT(0)); - if (!((target_pkt.word_en & BIT(1)) | + if (!((target_pkt->word_en & BIT(1)) | (tmp_pkt.word_en & BIT(1)))) match_word_en &= (~BIT(1)); - if (!((target_pkt.word_en & BIT(2)) | + if (!((target_pkt->word_en & BIT(2)) | (tmp_pkt.word_en & BIT(2)))) match_word_en &= (~BIT(2)); - if (!((target_pkt.word_en & BIT(3)) | + if (!((target_pkt->word_en & BIT(3)) | (tmp_pkt.word_en & BIT(3)))) match_word_en &= (~BIT(3)); @@ -780,7 +780,7 @@ static void efuse_write_data_case1(struct ieee80211_hw *hw, u16 *efuse_addr, badworden = efuse_word_enable_data_write( hw, *efuse_addr + 1, tmp_pkt.word_en, - target_pkt.data); + target_pkt->data); if (0x0F != (badworden & 0x0F)) { u8 reorg_offset = offset; @@ -791,26 +791,26 @@ static void efuse_write_data_case1(struct ieee80211_hw *hw, u16 *efuse_addr, } tmp_word_en = 0x0F; - if ((target_pkt.word_en & BIT(0)) ^ + if ((target_pkt->word_en & BIT(0)) ^ (match_word_en & BIT(0))) tmp_word_en &= (~BIT(0)); - if ((target_pkt.word_en & BIT(1)) ^ + if ((target_pkt->word_en & BIT(1)) ^ (match_word_en & BIT(1))) tmp_word_en &= (~BIT(1)); - if ((target_pkt.word_en & BIT(2)) ^ + if ((target_pkt->word_en & BIT(2)) ^ (match_word_en & BIT(2))) tmp_word_en &= (~BIT(2)); - if ((target_pkt.word_en & BIT(3)) ^ + if ((target_pkt->word_en & BIT(3)) ^ (match_word_en & BIT(3))) tmp_word_en &= (~BIT(3)); if ((tmp_word_en & 0x0F) != 0x0F) { *efuse_addr = efuse_get_current_size(hw); - target_pkt.offset = offset; - target_pkt.word_en = tmp_word_en; + target_pkt->offset = offset; + target_pkt->word_en = tmp_word_en; } else *bcontinual = false; *write_state = PG_STATE_HEADER; @@ -821,8 +821,8 @@ static void efuse_write_data_case1(struct ieee80211_hw *hw, u16 *efuse_addr, } } else { *efuse_addr += (2 * tmp_word_cnts) + 1; - target_pkt.offset = offset; - target_pkt.word_en = word_en; + target_pkt->offset = offset; + target_pkt->word_en = word_en; *write_state = PG_STATE_HEADER; } } @@ -938,7 +938,7 @@ static int efuse_pg_packet_write(struct ieee80211_hw *hw, efuse_write_data_case1(hw, &efuse_addr, efuse_data, offset, &bcontinual, - &write_state, target_pkt, + &write_state, &target_pkt, &repeat_times, &bresult, word_en); else diff --git a/drivers/net/wireless/wl1251/main.c b/drivers/net/wireless/wl1251/main.c index 012e1a4..40372ba 100644 --- a/drivers/net/wireless/wl1251/main.c +++ b/drivers/net/wireless/wl1251/main.c @@ -1039,6 +1039,9 @@ static void wl1251_op_bss_info_changed(struct ieee80211_hw *hw, if (changed & BSS_CHANGED_BEACON) { beacon = ieee80211_beacon_get(hw, vif); + if (!beacon) + goto out_sleep; + ret = wl1251_cmd_template_set(wl, CMD_BEACON, beacon->data, beacon->len); diff --git a/drivers/net/wireless/wl12xx/spi.c b/drivers/net/wireless/wl12xx/spi.c index 46714910..7145ea5 100644 --- a/drivers/net/wireless/wl12xx/spi.c +++ b/drivers/net/wireless/wl12xx/spi.c @@ -110,9 +110,8 @@ static void wl1271_spi_reset(struct wl1271 *wl) spi_message_add_tail(&t, &m); spi_sync(wl_to_spi(wl), &m); - kfree(cmd); - wl1271_dump(DEBUG_SPI, "spi reset -> ", cmd, WSPI_INIT_CMD_LEN); + kfree(cmd); } static void wl1271_spi_init(struct wl1271 *wl) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 546de57..da1f121 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -120,6 +120,9 @@ struct netfront_info { unsigned long rx_pfn_array[NET_RX_RING_SIZE]; struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1]; struct mmu_update rx_mmu[NET_RX_RING_SIZE]; + + /* Statistics */ + int rx_gso_checksum_fixup; }; struct netfront_rx_info { @@ -770,11 +773,29 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np, return cons; } -static int skb_checksum_setup(struct sk_buff *skb) +static int checksum_setup(struct net_device *dev, struct sk_buff *skb) { struct iphdr *iph; unsigned char *th; int err = -EPROTO; + int recalculate_partial_csum = 0; + + /* + * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy + * peers can fail to set NETRXF_csum_blank when sending a GSO + * frame. In this case force the SKB to CHECKSUM_PARTIAL and + * recalculate the partial checksum. + */ + if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { + struct netfront_info *np = netdev_priv(dev); + np->rx_gso_checksum_fixup++; + skb->ip_summed = CHECKSUM_PARTIAL; + recalculate_partial_csum = 1; + } + + /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; if (skb->protocol != htons(ETH_P_IP)) goto out; @@ -788,9 +809,23 @@ static int skb_checksum_setup(struct sk_buff *skb) switch (iph->protocol) { case IPPROTO_TCP: skb->csum_offset = offsetof(struct tcphdr, check); + + if (recalculate_partial_csum) { + struct tcphdr *tcph = (struct tcphdr *)th; + tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, + skb->len - iph->ihl*4, + IPPROTO_TCP, 0); + } break; case IPPROTO_UDP: skb->csum_offset = offsetof(struct udphdr, check); + + if (recalculate_partial_csum) { + struct udphdr *udph = (struct udphdr *)th; + udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, + skb->len - iph->ihl*4, + IPPROTO_UDP, 0); + } break; default: if (net_ratelimit()) @@ -829,13 +864,11 @@ static int handle_incoming_queue(struct net_device *dev, /* Ethernet work: Delayed to here as it peeks the header. */ skb->protocol = eth_type_trans(skb, dev); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb_checksum_setup(skb)) { - kfree_skb(skb); - packets_dropped++; - dev->stats.rx_errors++; - continue; - } + if (checksum_setup(dev, skb)) { + kfree_skb(skb); + packets_dropped++; + dev->stats.rx_errors++; + continue; } dev->stats.rx_packets++; @@ -1632,12 +1665,59 @@ static void netback_changed(struct xenbus_device *dev, } } +static const struct xennet_stat { + char name[ETH_GSTRING_LEN]; + u16 offset; +} xennet_stats[] = { + { + "rx_gso_checksum_fixup", + offsetof(struct netfront_info, rx_gso_checksum_fixup) + }, +}; + +static int xennet_get_sset_count(struct net_device *dev, int string_set) +{ + switch (string_set) { + case ETH_SS_STATS: + return ARRAY_SIZE(xennet_stats); + default: + return -EINVAL; + } +} + +static void xennet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 * data) +{ + void *np = netdev_priv(dev); + int i; + + for (i = 0; i < ARRAY_SIZE(xennet_stats); i++) + data[i] = *(int *)(np + xennet_stats[i].offset); +} + +static void xennet_get_strings(struct net_device *dev, u32 stringset, u8 * data) +{ + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < ARRAY_SIZE(xennet_stats); i++) + memcpy(data + i * ETH_GSTRING_LEN, + xennet_stats[i].name, ETH_GSTRING_LEN); + break; + } +} + static const struct ethtool_ops xennet_ethtool_ops = { .set_tx_csum = ethtool_op_set_tx_csum, .set_sg = xennet_set_sg, .set_tso = xennet_set_tso, .get_link = ethtool_op_get_link, + + .get_sset_count = xennet_get_sset_count, + .get_ethtool_stats = xennet_get_ethtool_stats, + .get_strings = xennet_get_strings, }; #ifdef CONFIG_SYSFS diff --git a/drivers/nfc/Kconfig b/drivers/nfc/Kconfig index ffedfd4..ea15800 100644 --- a/drivers/nfc/Kconfig +++ b/drivers/nfc/Kconfig @@ -3,7 +3,7 @@ # menuconfig NFC_DEVICES - bool "NFC devices" + bool "Near Field Communication (NFC) devices" default n ---help--- You'll have to say Y if your computer contains an NFC device that diff --git a/drivers/nfc/pn544.c b/drivers/nfc/pn544.c index bae6472..724f65d 100644 --- a/drivers/nfc/pn544.c +++ b/drivers/nfc/pn544.c @@ -60,7 +60,7 @@ enum pn544_irq { struct pn544_info { struct miscdevice miscdev; struct i2c_client *i2c_dev; - struct regulator_bulk_data regs[2]; + struct regulator_bulk_data regs[3]; enum pn544_state state; wait_queue_head_t read_wait; @@ -74,6 +74,7 @@ struct pn544_info { static const char reg_vdd_io[] = "Vdd_IO"; static const char reg_vbat[] = "VBat"; +static const char reg_vsim[] = "VSim"; /* sysfs interface */ static ssize_t pn544_test(struct device *dev, @@ -740,6 +741,7 @@ static int __devinit pn544_probe(struct i2c_client *client, info->regs[0].supply = reg_vdd_io; info->regs[1].supply = reg_vbat; + info->regs[2].supply = reg_vsim; r = regulator_bulk_get(&client->dev, ARRAY_SIZE(info->regs), info->regs); if (r < 0) diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c index 28295d0..4d87b5d 100644 --- a/drivers/of/pdt.c +++ b/drivers/of/pdt.c @@ -36,19 +36,55 @@ unsigned int of_pdt_unique_id __initdata; (p)->unique_id = of_pdt_unique_id++; \ } while (0) -static inline const char *of_pdt_node_name(struct device_node *dp) +static char * __init of_pdt_build_full_name(struct device_node *dp) { - return dp->path_component_name; + int len, ourlen, plen; + char *n; + + dp->path_component_name = build_path_component(dp); + + plen = strlen(dp->parent->full_name); + ourlen = strlen(dp->path_component_name); + len = ourlen + plen + 2; + + n = prom_early_alloc(len); + strcpy(n, dp->parent->full_name); + if (!of_node_is_root(dp->parent)) { + strcpy(n + plen, "/"); + plen++; + } + strcpy(n + plen, dp->path_component_name); + + return n; } -#else +#else /* CONFIG_SPARC */ static inline void of_pdt_incr_unique_id(void *p) { } static inline void irq_trans_init(struct device_node *dp) { } -static inline const char *of_pdt_node_name(struct device_node *dp) +static char * __init of_pdt_build_full_name(struct device_node *dp) { - return dp->name; + static int failsafe_id = 0; /* for generating unique names on failure */ + char *buf; + int len; + + if (of_pdt_prom_ops->pkg2path(dp->phandle, NULL, 0, &len)) + goto failsafe; + + buf = prom_early_alloc(len + 1); + if (of_pdt_prom_ops->pkg2path(dp->phandle, buf, len, &len)) + goto failsafe; + return buf; + + failsafe: + buf = prom_early_alloc(strlen(dp->parent->full_name) + + strlen(dp->name) + 16); + sprintf(buf, "%s/%s@unknown%i", + of_node_is_root(dp->parent) ? "" : dp->parent->full_name, + dp->name, failsafe_id++); + pr_err("%s: pkg2path failed; assigning %s\n", __func__, buf); + return buf; } #endif /* !CONFIG_SPARC */ @@ -132,47 +168,6 @@ static char * __init of_pdt_get_one_property(phandle node, const char *name) return buf; } -static char * __init of_pdt_try_pkg2path(phandle node) -{ - char *res, *buf = NULL; - int len; - - if (!of_pdt_prom_ops->pkg2path) - return NULL; - - if (of_pdt_prom_ops->pkg2path(node, buf, 0, &len)) - return NULL; - buf = prom_early_alloc(len + 1); - if (of_pdt_prom_ops->pkg2path(node, buf, len, &len)) { - pr_err("%s: package-to-path failed\n", __func__); - return NULL; - } - - res = strrchr(buf, '/'); - if (!res) { - pr_err("%s: couldn't find / in %s\n", __func__, buf); - return NULL; - } - return res+1; -} - -/* - * When fetching the node's name, first try using package-to-path; if - * that fails (either because the arch hasn't supplied a PROM callback, - * or some other random failure), fall back to just looking at the node's - * 'name' property. - */ -static char * __init of_pdt_build_name(phandle node) -{ - char *buf; - - buf = of_pdt_try_pkg2path(node); - if (!buf) - buf = of_pdt_get_one_property(node, "name"); - - return buf; -} - static struct device_node * __init of_pdt_create_node(phandle node, struct device_node *parent) { @@ -187,7 +182,7 @@ static struct device_node * __init of_pdt_create_node(phandle node, kref_init(&dp->kref); - dp->name = of_pdt_build_name(node); + dp->name = of_pdt_get_one_property(node, "name"); dp->type = of_pdt_get_one_property(node, "device_type"); dp->phandle = node; @@ -198,26 +193,6 @@ static struct device_node * __init of_pdt_create_node(phandle node, return dp; } -static char * __init of_pdt_build_full_name(struct device_node *dp) -{ - int len, ourlen, plen; - char *n; - - plen = strlen(dp->parent->full_name); - ourlen = strlen(of_pdt_node_name(dp)); - len = ourlen + plen + 2; - - n = prom_early_alloc(len); - strcpy(n, dp->parent->full_name); - if (!of_node_is_root(dp->parent)) { - strcpy(n + plen, "/"); - plen++; - } - strcpy(n + plen, of_pdt_node_name(dp)); - - return n; -} - static struct device_node * __init of_pdt_build_tree(struct device_node *parent, phandle node, struct device_node ***nextp) @@ -240,9 +215,6 @@ static struct device_node * __init of_pdt_build_tree(struct device_node *parent, *(*nextp) = dp; *nextp = &dp->allnext; -#if defined(CONFIG_SPARC) - dp->path_component_name = build_path_component(dp); -#endif dp->full_name = of_pdt_build_full_name(dp); dp->child = of_pdt_build_tree(dp, diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 8ecaac9..ea25e5b 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -23,6 +23,7 @@ #include <linux/mm.h> #include <linux/fs.h> #include <linux/capability.h> +#include <linux/security.h> #include <linux/pci-aspm.h> #include <linux/slab.h> #include "pci.h" @@ -368,7 +369,7 @@ pci_read_config(struct file *filp, struct kobject *kobj, u8 *data = (u8*) buf; /* Several chips lock up trying to read undefined config space */ - if (cap_raised(filp->f_cred->cap_effective, CAP_SYS_ADMIN)) { + if (security_capable(filp->f_cred, CAP_SYS_ADMIN) == 0) { size = dev->cfg_size; } else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) { size = 128; diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 3a5a6fc..492b7d8 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -243,7 +243,7 @@ struct pci_ops pcifront_bus_ops = { #ifdef CONFIG_PCI_MSI static int pci_frontend_enable_msix(struct pci_dev *dev, - int **vector, int nvec) + int vector[], int nvec) { int err; int i; @@ -277,18 +277,24 @@ static int pci_frontend_enable_msix(struct pci_dev *dev, if (likely(!err)) { if (likely(!op.value)) { /* we get the result */ - for (i = 0; i < nvec; i++) - *(*vector+i) = op.msix_entries[i].vector; - return 0; + for (i = 0; i < nvec; i++) { + if (op.msix_entries[i].vector <= 0) { + dev_warn(&dev->dev, "MSI-X entry %d is invalid: %d!\n", + i, op.msix_entries[i].vector); + err = -EINVAL; + vector[i] = -1; + continue; + } + vector[i] = op.msix_entries[i].vector; + } } else { printk(KERN_DEBUG "enable msix get value %x\n", op.value); - return op.value; } } else { dev_err(&dev->dev, "enable msix get err %x\n", err); - return err; } + return err; } static void pci_frontend_disable_msix(struct pci_dev *dev) @@ -310,7 +316,7 @@ static void pci_frontend_disable_msix(struct pci_dev *dev) dev_err(&dev->dev, "pci_disable_msix get err %x\n", err); } -static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector) +static int pci_frontend_enable_msi(struct pci_dev *dev, int vector[]) { int err; struct xen_pci_op op = { @@ -324,7 +330,13 @@ static int pci_frontend_enable_msi(struct pci_dev *dev, int **vector) err = do_pci_op(pdev, &op); if (likely(!err)) { - *(*vector) = op.value; + vector[0] = op.value; + if (op.value <= 0) { + dev_warn(&dev->dev, "MSI entry is invalid: %d!\n", + op.value); + err = -EINVAL; + vector[0] = -1; + } } else { dev_err(&dev->dev, "pci frontend enable msi failed for dev " "%x:%x\n", op.bus, op.devfn); @@ -733,8 +745,7 @@ static void free_pdev(struct pcifront_device *pdev) pcifront_free_roots(pdev); - /*For PCIE_AER error handling job*/ - flush_scheduled_work(); + cancel_work_sync(&pdev->op_work); if (pdev->irq >= 0) unbind_from_irqhandler(pdev->irq, pdev); diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c index 0bdda5b3..42fbf1a 100644 --- a/drivers/pcmcia/pcmcia_resource.c +++ b/drivers/pcmcia/pcmcia_resource.c @@ -518,6 +518,8 @@ int pcmcia_enable_device(struct pcmcia_device *p_dev) flags |= CONF_ENABLE_IOCARD; if (flags & CONF_ENABLE_IOCARD) s->socket.flags |= SS_IOCARD; + if (flags & CONF_ENABLE_ZVCARD) + s->socket.flags |= SS_ZVCARD | SS_IOCARD; if (flags & CONF_ENABLE_SPKR) { s->socket.flags |= SS_SPKR_ENA; status = CCSR_AUDIO_ENA; diff --git a/drivers/pcmcia/pxa2xx_base.c b/drivers/pcmcia/pxa2xx_base.c index 3755e7c..2c54054 100644 --- a/drivers/pcmcia/pxa2xx_base.c +++ b/drivers/pcmcia/pxa2xx_base.c @@ -215,7 +215,7 @@ pxa2xx_pcmcia_frequency_change(struct soc_pcmcia_socket *skt, } #endif -static void pxa2xx_configure_sockets(struct device *dev) +void pxa2xx_configure_sockets(struct device *dev) { struct pcmcia_low_level *ops = dev->platform_data; /* diff --git a/drivers/pcmcia/pxa2xx_base.h b/drivers/pcmcia/pxa2xx_base.h index bb62ea8..b609b45 100644 --- a/drivers/pcmcia/pxa2xx_base.h +++ b/drivers/pcmcia/pxa2xx_base.h @@ -1,3 +1,4 @@ int pxa2xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt); void pxa2xx_drv_pcmcia_ops(struct pcmcia_low_level *ops); +void pxa2xx_configure_sockets(struct device *dev); diff --git a/drivers/pcmcia/pxa2xx_colibri.c b/drivers/pcmcia/pxa2xx_colibri.c index c3f7219..a520395 100644 --- a/drivers/pcmcia/pxa2xx_colibri.c +++ b/drivers/pcmcia/pxa2xx_colibri.c @@ -181,6 +181,9 @@ static int __init colibri_pcmcia_init(void) { int ret; + if (!machine_is_colibri() && !machine_is_colibri320()) + return -ENODEV; + colibri_pcmcia_device = platform_device_alloc("pxa2xx-pcmcia", -1); if (!colibri_pcmcia_device) return -ENOMEM; diff --git a/drivers/pcmcia/pxa2xx_lubbock.c b/drivers/pcmcia/pxa2xx_lubbock.c index b9f8c8f..25afe63 100644 --- a/drivers/pcmcia/pxa2xx_lubbock.c +++ b/drivers/pcmcia/pxa2xx_lubbock.c @@ -226,6 +226,7 @@ int pcmcia_lubbock_init(struct sa1111_dev *sadev) lubbock_set_misc_wr((1 << 15) | (1 << 14), 0); pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops); + pxa2xx_configure_sockets(&sadev->dev); ret = sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops, pxa2xx_drv_pcmcia_add_one); } diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index d163bc2..a59af5b 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -227,7 +227,7 @@ config SONYPI_COMPAT config IDEAPAD_LAPTOP tristate "Lenovo IdeaPad Laptop Extras" depends on ACPI - depends on RFKILL + depends on RFKILL && INPUT select INPUT_SPARSEKMAP help This is a driver for the rfkill switches on Lenovo IdeaPad netbooks. diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index c5c4b8c..38b34a7 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -84,7 +84,7 @@ MODULE_LICENSE("GPL"); */ #define AMW0_GUID1 "67C3371D-95A3-4C37-BB61-DD47B491DAAB" #define AMW0_GUID2 "431F16ED-0C2B-444C-B267-27DEB140CF9C" -#define WMID_GUID1 "6AF4F258-B401-42fd-BE91-3D4AC2D7C0D3" +#define WMID_GUID1 "6AF4F258-B401-42FD-BE91-3D4AC2D7C0D3" #define WMID_GUID2 "95764E09-FB56-4e83-B31A-37761F60994A" #define WMID_GUID3 "61EF69EA-865C-4BC3-A502-A0DEBA0CB531" @@ -1280,7 +1280,7 @@ static ssize_t set_bool_threeg(struct device *dev, return -EINVAL; return count; } -static DEVICE_ATTR(threeg, S_IWUGO | S_IRUGO | S_IWUSR, show_bool_threeg, +static DEVICE_ATTR(threeg, S_IRUGO | S_IWUSR, show_bool_threeg, set_bool_threeg); static ssize_t show_interface(struct device *dev, struct device_attribute *attr, diff --git a/drivers/platform/x86/asus_acpi.c b/drivers/platform/x86/asus_acpi.c index 4633fd8..fe49593 100644 --- a/drivers/platform/x86/asus_acpi.c +++ b/drivers/platform/x86/asus_acpi.c @@ -1081,14 +1081,8 @@ static int asus_hotk_add_fs(struct acpi_device *device) struct proc_dir_entry *proc; mode_t mode; - /* - * If parameter uid or gid is not changed, keep the default setting for - * our proc entries (-rw-rw-rw-) else, it means we care about security, - * and then set to -rw-rw---- - */ - if ((asus_uid == 0) && (asus_gid == 0)) { - mode = S_IFREG | S_IRUGO | S_IWUGO; + mode = S_IFREG | S_IRUGO | S_IWUSR | S_IWGRP; } else { mode = S_IFREG | S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP; printk(KERN_WARNING " asus_uid and asus_gid parameters are " diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index 34657f9..ad24ef3 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -290,9 +290,12 @@ static int dell_rfkill_set(void *data, bool blocked) dell_send_request(buffer, 17, 11); /* If the hardware switch controls this radio, and the hardware - switch is disabled, don't allow changing the software state */ + switch is disabled, don't allow changing the software state. + If the hardware switch is reported as not supported, always + fire the SMI to toggle the killswitch. */ if ((hwswitch_state & BIT(hwswitch_bit)) && - !(buffer->output[1] & BIT(16))) { + !(buffer->output[1] & BIT(16)) && + (buffer->output[1] & BIT(0))) { ret = -EINVAL; goto out; } @@ -398,6 +401,23 @@ static const struct file_operations dell_debugfs_fops = { static void dell_update_rfkill(struct work_struct *ignored) { + int status; + + get_buffer(); + dell_send_request(buffer, 17, 11); + status = buffer->output[1]; + release_buffer(); + + /* if hardware rfkill is not supported, set it explicitly */ + if (!(status & BIT(0))) { + if (wifi_rfkill) + dell_rfkill_set((void *)1, !((status & BIT(17)) >> 17)); + if (bluetooth_rfkill) + dell_rfkill_set((void *)2, !((status & BIT(18)) >> 18)); + if (wwan_rfkill) + dell_rfkill_set((void *)3, !((status & BIT(19)) >> 19)); + } + if (wifi_rfkill) dell_rfkill_query(wifi_rfkill, (void *)1); if (bluetooth_rfkill) diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c index 930e627..61433d4 100644 --- a/drivers/platform/x86/intel_pmic_gpio.c +++ b/drivers/platform/x86/intel_pmic_gpio.c @@ -60,69 +60,20 @@ enum pmic_gpio_register { #define GPOSW_DOU 0x08 #define GPOSW_RDRV 0x30 +#define GPIO_UPDATE_TYPE 0x80000000 #define NUM_GPIO 24 -struct pmic_gpio_irq { - spinlock_t lock; - u32 trigger[NUM_GPIO]; - u32 dirty; - struct work_struct work; -}; - - struct pmic_gpio { + struct mutex buslock; struct gpio_chip chip; - struct pmic_gpio_irq irqtypes; void *gpiointr; int irq; unsigned irq_base; + unsigned int update_type; + u32 trigger_type; }; -static void pmic_program_irqtype(int gpio, int type) -{ - if (type & IRQ_TYPE_EDGE_RISING) - intel_scu_ipc_update_register(GPIO0 + gpio, 0x20, 0x20); - else - intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x20); - - if (type & IRQ_TYPE_EDGE_FALLING) - intel_scu_ipc_update_register(GPIO0 + gpio, 0x10, 0x10); - else - intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x10); -}; - -static void pmic_irqtype_work(struct work_struct *work) -{ - struct pmic_gpio_irq *t = - container_of(work, struct pmic_gpio_irq, work); - unsigned long flags; - int i; - u16 type; - - spin_lock_irqsave(&t->lock, flags); - /* As we drop the lock, we may need multiple scans if we race the - pmic_irq_type function */ - while (t->dirty) { - /* - * For each pin that has the dirty bit set send an IPC - * message to configure the hardware via the PMIC - */ - for (i = 0; i < NUM_GPIO; i++) { - if (!(t->dirty & (1 << i))) - continue; - t->dirty &= ~(1 << i); - /* We can't trust the array entry or dirty - once the lock is dropped */ - type = t->trigger[i]; - spin_unlock_irqrestore(&t->lock, flags); - pmic_program_irqtype(i, type); - spin_lock_irqsave(&t->lock, flags); - } - } - spin_unlock_irqrestore(&t->lock, flags); -} - static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { if (offset > 8) { @@ -190,25 +141,24 @@ static void pmic_gpio_set(struct gpio_chip *chip, unsigned offset, int value) 1 << (offset - 16)); } -static int pmic_irq_type(unsigned irq, unsigned type) +/* + * This is called from genirq with pg->buslock locked and + * irq_desc->lock held. We can not access the scu bus here, so we + * store the change and update in the bus_sync_unlock() function below + */ +static int pmic_irq_type(struct irq_data *data, unsigned type) { - struct pmic_gpio *pg = get_irq_chip_data(irq); - u32 gpio = irq - pg->irq_base; - unsigned long flags; + struct pmic_gpio *pg = irq_data_get_irq_chip_data(data); + u32 gpio = data->irq - pg->irq_base; if (gpio >= pg->chip.ngpio) return -EINVAL; - spin_lock_irqsave(&pg->irqtypes.lock, flags); - pg->irqtypes.trigger[gpio] = type; - pg->irqtypes.dirty |= (1 << gpio); - spin_unlock_irqrestore(&pg->irqtypes.lock, flags); - schedule_work(&pg->irqtypes.work); + pg->trigger_type = type; + pg->update_type = gpio | GPIO_UPDATE_TYPE; return 0; } - - static int pmic_gpio_to_irq(struct gpio_chip *chip, unsigned offset) { struct pmic_gpio *pg = container_of(chip, struct pmic_gpio, chip); @@ -217,38 +167,32 @@ static int pmic_gpio_to_irq(struct gpio_chip *chip, unsigned offset) } /* the gpiointr register is read-clear, so just do nothing. */ -static void pmic_irq_unmask(unsigned irq) -{ -}; +static void pmic_irq_unmask(struct irq_data *data) { } -static void pmic_irq_mask(unsigned irq) -{ -}; +static void pmic_irq_mask(struct irq_data *data) { } static struct irq_chip pmic_irqchip = { .name = "PMIC-GPIO", - .mask = pmic_irq_mask, - .unmask = pmic_irq_unmask, - .set_type = pmic_irq_type, + .irq_mask = pmic_irq_mask, + .irq_unmask = pmic_irq_unmask, + .irq_set_type = pmic_irq_type, }; -static void pmic_irq_handler(unsigned irq, struct irq_desc *desc) +static irqreturn_t pmic_irq_handler(int irq, void *data) { - struct pmic_gpio *pg = (struct pmic_gpio *)get_irq_data(irq); + struct pmic_gpio *pg = data; u8 intsts = *((u8 *)pg->gpiointr + 4); int gpio; + irqreturn_t ret = IRQ_NONE; for (gpio = 0; gpio < 8; gpio++) { if (intsts & (1 << gpio)) { pr_debug("pmic pin %d triggered\n", gpio); generic_handle_irq(pg->irq_base + gpio); + ret = IRQ_HANDLED; } } - - if (desc->chip->irq_eoi) - desc->chip->irq_eoi(irq_get_irq_data(irq)); - else - dev_warn(pg->chip.dev, "missing EOI handler for irq %d\n", irq); + return ret; } static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev) @@ -297,8 +241,7 @@ static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev) pg->chip.can_sleep = 1; pg->chip.dev = dev; - INIT_WORK(&pg->irqtypes.work, pmic_irqtype_work); - spin_lock_init(&pg->irqtypes.lock); + mutex_init(&pg->buslock); pg->chip.dev = dev; retval = gpiochip_add(&pg->chip); @@ -306,8 +249,13 @@ static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev) printk(KERN_ERR "%s: Can not add pmic gpio chip.\n", __func__); goto err; } - set_irq_data(pg->irq, pg); - set_irq_chained_handler(pg->irq, pmic_irq_handler); + + retval = request_irq(pg->irq, pmic_irq_handler, 0, "pmic", pg); + if (retval) { + printk(KERN_WARNING "pmic: Interrupt request failed\n"); + goto err; + } + for (i = 0; i < 8; i++) { set_irq_chip_and_handler_name(i + pg->irq_base, &pmic_irqchip, handle_simple_irq, "demux"); diff --git a/drivers/platform/x86/tc1100-wmi.c b/drivers/platform/x86/tc1100-wmi.c index 1fe0f1f..865ef78 100644 --- a/drivers/platform/x86/tc1100-wmi.c +++ b/drivers/platform/x86/tc1100-wmi.c @@ -162,7 +162,7 @@ set_bool_##value(struct device *dev, struct device_attribute *attr, \ return -EINVAL; \ return count; \ } \ -static DEVICE_ATTR(value, S_IWUGO | S_IRUGO | S_IWUSR, \ +static DEVICE_ATTR(value, S_IRUGO | S_IWUSR, \ show_bool_##value, set_bool_##value); show_set_bool(wireless, TC1100_INSTANCE_WIRELESS); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index dd59958..eb99223 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -2275,16 +2275,12 @@ static void tpacpi_input_send_key(const unsigned int scancode) if (keycode != KEY_RESERVED) { mutex_lock(&tpacpi_inputdev_send_mutex); + input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN, scancode); input_report_key(tpacpi_inputdev, keycode, 1); - if (keycode == KEY_UNKNOWN) - input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN, - scancode); input_sync(tpacpi_inputdev); + input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN, scancode); input_report_key(tpacpi_inputdev, keycode, 0); - if (keycode == KEY_UNKNOWN) - input_event(tpacpi_inputdev, EV_MSC, MSC_SCAN, - scancode); input_sync(tpacpi_inputdev); mutex_unlock(&tpacpi_inputdev_send_mutex); diff --git a/drivers/pps/generators/Kconfig b/drivers/pps/generators/Kconfig index f3a73dd..e4c4f3d 100644 --- a/drivers/pps/generators/Kconfig +++ b/drivers/pps/generators/Kconfig @@ -6,7 +6,7 @@ comment "PPS generators support" config PPS_GENERATOR_PARPORT tristate "Parallel port PPS signal generator" - depends on PARPORT + depends on PARPORT && BROKEN help If you say yes here you get support for a PPS signal generator which utilizes STROBE pin of a parallel port to send PPS signals. It uses diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c index cba1b43..a4e8eb9 100644 --- a/drivers/pps/kapi.c +++ b/drivers/pps/kapi.c @@ -168,7 +168,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, { unsigned long flags; int captured = 0; - struct pps_ktime ts_real; + struct pps_ktime ts_real = { .sec = 0, .nsec = 0, .flags = 0 }; /* check event type */ BUG_ON((event & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR)) == 0); diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c index 76b4185..1269fbd 100644 --- a/drivers/rapidio/rio-sysfs.c +++ b/drivers/rapidio/rio-sysfs.c @@ -77,9 +77,9 @@ rio_read_config(struct file *filp, struct kobject *kobj, /* Several chips lock up trying to read undefined config space */ if (capable(CAP_SYS_ADMIN)) - size = 0x200000; + size = RIO_MAINT_SPACE_SZ; - if (off > size) + if (off >= size) return 0; if (off + count > size) { size -= off; @@ -147,10 +147,10 @@ rio_write_config(struct file *filp, struct kobject *kobj, loff_t init_off = off; u8 *data = (u8 *) buf; - if (off > 0x200000) + if (off >= RIO_MAINT_SPACE_SZ) return 0; - if (off + count > 0x200000) { - size = 0x200000 - off; + if (off + count > RIO_MAINT_SPACE_SZ) { + size = RIO_MAINT_SPACE_SZ - off; count = size; } @@ -200,7 +200,7 @@ static struct bin_attribute rio_config_attr = { .name = "config", .mode = S_IRUGO | S_IWUSR, }, - .size = 0x200000, + .size = RIO_MAINT_SPACE_SZ, .read = rio_read_config, .write = rio_write_config, }; diff --git a/drivers/regulator/mc13xxx-regulator-core.c b/drivers/regulator/mc13xxx-regulator-core.c index f53d31b..2bb5de1 100644 --- a/drivers/regulator/mc13xxx-regulator-core.c +++ b/drivers/regulator/mc13xxx-regulator-core.c @@ -174,7 +174,7 @@ static int mc13xxx_regulator_get_voltage(struct regulator_dev *rdev) dev_dbg(rdev_get_dev(rdev), "%s id: %d val: %d\n", __func__, id, val); - BUG_ON(val < 0 || val > mc13xxx_regulators[id].desc.n_voltages); + BUG_ON(val > mc13xxx_regulators[id].desc.n_voltages); return mc13xxx_regulators[id].voltages[val]; } diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c index 8b0d2c4..06df898 100644 --- a/drivers/regulator/wm831x-dcdc.c +++ b/drivers/regulator/wm831x-dcdc.c @@ -120,6 +120,7 @@ static unsigned int wm831x_dcdc_get_mode(struct regulator_dev *rdev) return REGULATOR_MODE_IDLE; default: BUG(); + return -EINVAL; } } diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index cdd9719..4941cad 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -97,6 +97,18 @@ config RTC_INTF_DEV If unsure, say Y. +config RTC_INTF_DEV_UIE_EMUL + bool "RTC UIE emulation on dev interface" + depends on RTC_INTF_DEV + help + Provides an emulation for RTC_UIE if the underlying rtc chip + driver does not expose RTC_UIE ioctls. Those requests generate + once-per-second update interrupts, used for synchronization. + + The emulation code will read the time from the hardware + clock several times per second, please enable this option + only if you know that you really need it. + config RTC_DRV_TEST tristate "Test driver/device" help diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 9583cbc..c404b61 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -143,6 +143,7 @@ struct rtc_device *rtc_device_register(const char *name, struct device *dev, rtc->id = id; rtc->ops = ops; rtc->owner = owner; + rtc->irq_freq = 1; rtc->max_user_freq = 64; rtc->dev.parent = dev; rtc->dev.class = rtc_class; diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 925006d..cb2f072 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -209,9 +209,8 @@ int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled) } if (err) - return err; - - if (!rtc->ops) + /* nothing */; + else if (!rtc->ops) err = -ENODEV; else if (!rtc->ops->alarm_irq_enable) err = -EINVAL; @@ -229,6 +228,12 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled) if (err) return err; +#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL + if (enabled == 0 && rtc->uie_irq_active) { + mutex_unlock(&rtc->ops_lock); + return rtc_dev_update_irq_enable_emul(rtc, 0); + } +#endif /* make sure we're changing state */ if (rtc->uie_rtctimer.enabled == enabled) goto out; @@ -248,6 +253,16 @@ int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled) out: mutex_unlock(&rtc->ops_lock); +#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL + /* + * Enable emulation if the driver did not provide + * the update_irq_enable function pointer or if returned + * -EINVAL to signal that it has been configured without + * interrupts or that are not available at the moment. + */ + if (err == -EINVAL) + err = rtc_dev_update_irq_enable_emul(rtc, enabled); +#endif return err; } @@ -263,7 +278,7 @@ EXPORT_SYMBOL_GPL(rtc_update_irq_enable); * * Triggers the registered irq_task function callback. */ -static void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode) +void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode) { unsigned long flags; @@ -464,6 +479,9 @@ int rtc_irq_set_freq(struct rtc_device *rtc, struct rtc_task *task, int freq) int err = 0; unsigned long flags; + if (freq <= 0) + return -EINVAL; + spin_lock_irqsave(&rtc->irq_task_lock, flags); if (rtc->irq_task != NULL && task == NULL) err = -EBUSY; diff --git a/drivers/rtc/rtc-at32ap700x.c b/drivers/rtc/rtc-at32ap700x.c index b2752b6..e725d51 100644 --- a/drivers/rtc/rtc-at32ap700x.c +++ b/drivers/rtc/rtc-at32ap700x.c @@ -134,36 +134,29 @@ static int at32_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) return ret; } -static int at32_rtc_ioctl(struct device *dev, unsigned int cmd, - unsigned long arg) +static int at32_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct rtc_at32ap700x *rtc = dev_get_drvdata(dev); int ret = 0; spin_lock_irq(&rtc->lock); - switch (cmd) { - case RTC_AIE_ON: + if(enabled) { if (rtc_readl(rtc, VAL) > rtc->alarm_time) { ret = -EINVAL; - break; + goto out; } rtc_writel(rtc, CTRL, rtc_readl(rtc, CTRL) | RTC_BIT(CTRL_TOPEN)); rtc_writel(rtc, ICR, RTC_BIT(ICR_TOPI)); rtc_writel(rtc, IER, RTC_BIT(IER_TOPI)); - break; - case RTC_AIE_OFF: + } else { rtc_writel(rtc, CTRL, rtc_readl(rtc, CTRL) & ~RTC_BIT(CTRL_TOPEN)); rtc_writel(rtc, IDR, RTC_BIT(IDR_TOPI)); rtc_writel(rtc, ICR, RTC_BIT(ICR_TOPI)); - break; - default: - ret = -ENOIOCTLCMD; - break; } - +out: spin_unlock_irq(&rtc->lock); return ret; @@ -195,11 +188,11 @@ static irqreturn_t at32_rtc_interrupt(int irq, void *dev_id) } static struct rtc_class_ops at32_rtc_ops = { - .ioctl = at32_rtc_ioctl, .read_time = at32_rtc_readtime, .set_time = at32_rtc_settime, .read_alarm = at32_rtc_readalarm, .set_alarm = at32_rtc_setalarm, + .alarm_irq_enable = at32_rtc_alarm_irq_enable, }; static int __init at32_rtc_probe(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index bc8bbca..26d1cf5 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -195,13 +195,6 @@ static int at91_rtc_ioctl(struct device *dev, unsigned int cmd, /* important: scrub old status before enabling IRQs */ switch (cmd) { - case RTC_AIE_OFF: /* alarm off */ - at91_sys_write(AT91_RTC_IDR, AT91_RTC_ALARM); - break; - case RTC_AIE_ON: /* alarm on */ - at91_sys_write(AT91_RTC_SCCR, AT91_RTC_ALARM); - at91_sys_write(AT91_RTC_IER, AT91_RTC_ALARM); - break; case RTC_UIE_OFF: /* update off */ at91_sys_write(AT91_RTC_IDR, AT91_RTC_SECEV); break; @@ -217,6 +210,18 @@ static int at91_rtc_ioctl(struct device *dev, unsigned int cmd, return ret; } +static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + pr_debug("%s(): cmd=%08x\n", __func__, enabled); + + if (enabled) { + at91_sys_write(AT91_RTC_SCCR, AT91_RTC_ALARM); + at91_sys_write(AT91_RTC_IER, AT91_RTC_ALARM); + } else + at91_sys_write(AT91_RTC_IDR, AT91_RTC_ALARM); + + return 0; +} /* * Provide additional RTC information in /proc/driver/rtc */ @@ -270,6 +275,7 @@ static const struct rtc_class_ops at91_rtc_ops = { .read_alarm = at91_rtc_readalarm, .set_alarm = at91_rtc_setalarm, .proc = at91_rtc_proc, + .alarm_irq_enable = at91_rtc_alarm_irq_enable, }; /* diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c index f677e07..5469c52 100644 --- a/drivers/rtc/rtc-at91sam9.c +++ b/drivers/rtc/rtc-at91sam9.c @@ -229,12 +229,6 @@ static int at91_rtc_ioctl(struct device *dev, unsigned int cmd, dev_dbg(dev, "ioctl: cmd=%08x, arg=%08lx, mr %08x\n", cmd, arg, mr); switch (cmd) { - case RTC_AIE_OFF: /* alarm off */ - rtt_writel(rtc, MR, mr & ~AT91_RTT_ALMIEN); - break; - case RTC_AIE_ON: /* alarm on */ - rtt_writel(rtc, MR, mr | AT91_RTT_ALMIEN); - break; case RTC_UIE_OFF: /* update off */ rtt_writel(rtc, MR, mr & ~AT91_RTT_RTTINCIEN); break; @@ -249,6 +243,19 @@ static int at91_rtc_ioctl(struct device *dev, unsigned int cmd, return ret; } +static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct sam9_rtc *rtc = dev_get_drvdata(dev); + u32 mr = rtt_readl(rtc, MR); + + dev_dbg(dev, "alarm_irq_enable: enabled=%08x, mr %08x\n", enabled, mr); + if (enabled) + rtt_writel(rtc, MR, mr | AT91_RTT_ALMIEN); + else + rtt_writel(rtc, MR, mr & ~AT91_RTT_ALMIEN); + return 0; +} + /* * Provide additional RTC information in /proc/driver/rtc */ @@ -302,6 +309,7 @@ static const struct rtc_class_ops at91_rtc_ops = { .read_alarm = at91_rtc_readalarm, .set_alarm = at91_rtc_setalarm, .proc = at91_rtc_proc, + .alarm_irq_enable = at91_rtc_alarm_irq_enable, }; /* diff --git a/drivers/rtc/rtc-bfin.c b/drivers/rtc/rtc-bfin.c index b4b6087..17971d9 100644 --- a/drivers/rtc/rtc-bfin.c +++ b/drivers/rtc/rtc-bfin.c @@ -259,15 +259,6 @@ static int bfin_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long ar bfin_rtc_int_clear(~RTC_ISTAT_SEC); break; - case RTC_AIE_ON: - dev_dbg_stamp(dev); - bfin_rtc_int_set_alarm(rtc); - break; - case RTC_AIE_OFF: - dev_dbg_stamp(dev); - bfin_rtc_int_clear(~(RTC_ISTAT_ALARM | RTC_ISTAT_ALARM_DAY)); - break; - default: dev_dbg_stamp(dev); ret = -ENOIOCTLCMD; @@ -276,6 +267,17 @@ static int bfin_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long ar return ret; } +static int bfin_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct bfin_rtc *rtc = dev_get_drvdata(dev); + + dev_dbg_stamp(dev); + if (enabled) + bfin_rtc_int_set_alarm(rtc); + else + bfin_rtc_int_clear(~(RTC_ISTAT_ALARM | RTC_ISTAT_ALARM_DAY)); +} + static int bfin_rtc_read_time(struct device *dev, struct rtc_time *tm) { struct bfin_rtc *rtc = dev_get_drvdata(dev); @@ -362,6 +364,7 @@ static struct rtc_class_ops bfin_rtc_ops = { .read_alarm = bfin_rtc_read_alarm, .set_alarm = bfin_rtc_set_alarm, .proc = bfin_rtc_proc, + .alarm_irq_enable = bfin_rtc_alarm_irq_enable, }; static int __devinit bfin_rtc_probe(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c index 212b16e..d0e06ed 100644 --- a/drivers/rtc/rtc-dev.c +++ b/drivers/rtc/rtc-dev.c @@ -46,6 +46,105 @@ static int rtc_dev_open(struct inode *inode, struct file *file) return err; } +#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL +/* + * Routine to poll RTC seconds field for change as often as possible, + * after first RTC_UIE use timer to reduce polling + */ +static void rtc_uie_task(struct work_struct *work) +{ + struct rtc_device *rtc = + container_of(work, struct rtc_device, uie_task); + struct rtc_time tm; + int num = 0; + int err; + + err = rtc_read_time(rtc, &tm); + + spin_lock_irq(&rtc->irq_lock); + if (rtc->stop_uie_polling || err) { + rtc->uie_task_active = 0; + } else if (rtc->oldsecs != tm.tm_sec) { + num = (tm.tm_sec + 60 - rtc->oldsecs) % 60; + rtc->oldsecs = tm.tm_sec; + rtc->uie_timer.expires = jiffies + HZ - (HZ/10); + rtc->uie_timer_active = 1; + rtc->uie_task_active = 0; + add_timer(&rtc->uie_timer); + } else if (schedule_work(&rtc->uie_task) == 0) { + rtc->uie_task_active = 0; + } + spin_unlock_irq(&rtc->irq_lock); + if (num) + rtc_handle_legacy_irq(rtc, num, RTC_UF); +} +static void rtc_uie_timer(unsigned long data) +{ + struct rtc_device *rtc = (struct rtc_device *)data; + unsigned long flags; + + spin_lock_irqsave(&rtc->irq_lock, flags); + rtc->uie_timer_active = 0; + rtc->uie_task_active = 1; + if ((schedule_work(&rtc->uie_task) == 0)) + rtc->uie_task_active = 0; + spin_unlock_irqrestore(&rtc->irq_lock, flags); +} + +static int clear_uie(struct rtc_device *rtc) +{ + spin_lock_irq(&rtc->irq_lock); + if (rtc->uie_irq_active) { + rtc->stop_uie_polling = 1; + if (rtc->uie_timer_active) { + spin_unlock_irq(&rtc->irq_lock); + del_timer_sync(&rtc->uie_timer); + spin_lock_irq(&rtc->irq_lock); + rtc->uie_timer_active = 0; + } + if (rtc->uie_task_active) { + spin_unlock_irq(&rtc->irq_lock); + flush_scheduled_work(); + spin_lock_irq(&rtc->irq_lock); + } + rtc->uie_irq_active = 0; + } + spin_unlock_irq(&rtc->irq_lock); + return 0; +} + +static int set_uie(struct rtc_device *rtc) +{ + struct rtc_time tm; + int err; + + err = rtc_read_time(rtc, &tm); + if (err) + return err; + spin_lock_irq(&rtc->irq_lock); + if (!rtc->uie_irq_active) { + rtc->uie_irq_active = 1; + rtc->stop_uie_polling = 0; + rtc->oldsecs = tm.tm_sec; + rtc->uie_task_active = 1; + if (schedule_work(&rtc->uie_task) == 0) + rtc->uie_task_active = 0; + } + rtc->irq_data = 0; + spin_unlock_irq(&rtc->irq_lock); + return 0; +} + +int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, unsigned int enabled) +{ + if (enabled) + return set_uie(rtc); + else + return clear_uie(rtc); +} +EXPORT_SYMBOL(rtc_dev_update_irq_enable_emul); + +#endif /* CONFIG_RTC_INTF_DEV_UIE_EMUL */ static ssize_t rtc_dev_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) @@ -154,19 +253,7 @@ static long rtc_dev_ioctl(struct file *file, if (err) goto done; - /* try the driver's ioctl interface */ - if (ops->ioctl) { - err = ops->ioctl(rtc->dev.parent, cmd, arg); - if (err != -ENOIOCTLCMD) { - mutex_unlock(&rtc->ops_lock); - return err; - } - } - - /* if the driver does not provide the ioctl interface - * or if that particular ioctl was not implemented - * (-ENOIOCTLCMD), we will try to emulate here. - * + /* * Drivers *SHOULD NOT* provide ioctl implementations * for these requests. Instead, provide methods to * support the following code, so that the RTC's main @@ -329,7 +416,12 @@ static long rtc_dev_ioctl(struct file *file, return err; default: - err = -ENOTTY; + /* Finally try the driver's ioctl interface */ + if (ops->ioctl) { + err = ops->ioctl(rtc->dev.parent, cmd, arg); + if (err == -ENOIOCTLCMD) + err = -ENOTTY; + } break; } @@ -394,6 +486,11 @@ void rtc_dev_prepare(struct rtc_device *rtc) rtc->dev.devt = MKDEV(MAJOR(rtc_devt), rtc->id); +#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL + INIT_WORK(&rtc->uie_task, rtc_uie_task); + setup_timer(&rtc->uie_timer, rtc_uie_timer, (unsigned long)rtc); +#endif + cdev_init(&rtc->char_dev, &rtc_dev_fops); rtc->char_dev.owner = rtc->owner; } diff --git a/drivers/rtc/rtc-ds1286.c b/drivers/rtc/rtc-ds1286.c index bf430f9..60ce696 100644 --- a/drivers/rtc/rtc-ds1286.c +++ b/drivers/rtc/rtc-ds1286.c @@ -40,6 +40,26 @@ static inline void ds1286_rtc_write(struct ds1286_priv *priv, u8 data, int reg) __raw_writel(data, &priv->rtcregs[reg]); } + +static int ds1286_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct ds1286_priv *priv = dev_get_drvdata(dev); + unsigned long flags; + unsigned char val; + + /* Allow or mask alarm interrupts */ + spin_lock_irqsave(&priv->lock, flags); + val = ds1286_rtc_read(priv, RTC_CMD); + if (enabled) + val &= ~RTC_TDM; + else + val |= RTC_TDM; + ds1286_rtc_write(priv, val, RTC_CMD); + spin_unlock_irqrestore(&priv->lock, flags); + + return 0; +} + #ifdef CONFIG_RTC_INTF_DEV static int ds1286_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) @@ -49,22 +69,6 @@ static int ds1286_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) unsigned char val; switch (cmd) { - case RTC_AIE_OFF: - /* Mask alarm int. enab. bit */ - spin_lock_irqsave(&priv->lock, flags); - val = ds1286_rtc_read(priv, RTC_CMD); - val |= RTC_TDM; - ds1286_rtc_write(priv, val, RTC_CMD); - spin_unlock_irqrestore(&priv->lock, flags); - break; - case RTC_AIE_ON: - /* Allow alarm interrupts. */ - spin_lock_irqsave(&priv->lock, flags); - val = ds1286_rtc_read(priv, RTC_CMD); - val &= ~RTC_TDM; - ds1286_rtc_write(priv, val, RTC_CMD); - spin_unlock_irqrestore(&priv->lock, flags); - break; case RTC_WIE_OFF: /* Mask watchdog int. enab. bit */ spin_lock_irqsave(&priv->lock, flags); @@ -316,12 +320,13 @@ static int ds1286_set_alarm(struct device *dev, struct rtc_wkalrm *alm) } static const struct rtc_class_ops ds1286_ops = { - .ioctl = ds1286_ioctl, - .proc = ds1286_proc, + .ioctl = ds1286_ioctl, + .proc = ds1286_proc, .read_time = ds1286_read_time, .set_time = ds1286_set_time, .read_alarm = ds1286_read_alarm, .set_alarm = ds1286_set_alarm, + .alarm_irq_enable = ds1286_alarm_irq_enable, }; static int __devinit ds1286_probe(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c index 077af1d..57fbcc1 100644 --- a/drivers/rtc/rtc-ds1305.c +++ b/drivers/rtc/rtc-ds1305.c @@ -139,49 +139,32 @@ static u8 hour2bcd(bool hr12, int hour) * Interface to RTC framework */ -#ifdef CONFIG_RTC_INTF_DEV - -/* - * Context: caller holds rtc->ops_lock (to protect ds1305->ctrl) - */ -static int ds1305_ioctl(struct device *dev, unsigned cmd, unsigned long arg) +static int ds1305_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct ds1305 *ds1305 = dev_get_drvdata(dev); u8 buf[2]; - int status = -ENOIOCTLCMD; + long err = -EINVAL; buf[0] = DS1305_WRITE | DS1305_CONTROL; buf[1] = ds1305->ctrl[0]; - switch (cmd) { - case RTC_AIE_OFF: - status = 0; - if (!(buf[1] & DS1305_AEI0)) - goto done; - buf[1] &= ~DS1305_AEI0; - break; - - case RTC_AIE_ON: - status = 0; + if (enabled) { if (ds1305->ctrl[0] & DS1305_AEI0) goto done; buf[1] |= DS1305_AEI0; - break; - } - if (status == 0) { - status = spi_write_then_read(ds1305->spi, buf, sizeof buf, - NULL, 0); - if (status >= 0) - ds1305->ctrl[0] = buf[1]; + } else { + if (!(buf[1] & DS1305_AEI0)) + goto done; + buf[1] &= ~DS1305_AEI0; } - + err = spi_write_then_read(ds1305->spi, buf, sizeof buf, NULL, 0); + if (err >= 0) + ds1305->ctrl[0] = buf[1]; done: - return status; + return err; + } -#else -#define ds1305_ioctl NULL -#endif /* * Get/set of date and time is pretty normal. @@ -460,12 +443,12 @@ done: #endif static const struct rtc_class_ops ds1305_ops = { - .ioctl = ds1305_ioctl, .read_time = ds1305_get_time, .set_time = ds1305_set_time, .read_alarm = ds1305_get_alarm, .set_alarm = ds1305_set_alarm, .proc = ds1305_proc, + .alarm_irq_enable = ds1305_alarm_irq_enable, }; static void ds1305_work(struct work_struct *work) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 0d559b6..4724ba3 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -495,50 +495,27 @@ static int ds1337_set_alarm(struct device *dev, struct rtc_wkalrm *t) return 0; } -static int ds1307_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +static int ds1307_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct i2c_client *client = to_i2c_client(dev); struct ds1307 *ds1307 = i2c_get_clientdata(client); int ret; - switch (cmd) { - case RTC_AIE_OFF: - if (!test_bit(HAS_ALARM, &ds1307->flags)) - return -ENOTTY; - - ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL); - if (ret < 0) - return ret; - - ret &= ~DS1337_BIT_A1IE; - - ret = i2c_smbus_write_byte_data(client, - DS1337_REG_CONTROL, ret); - if (ret < 0) - return ret; - - break; - - case RTC_AIE_ON: - if (!test_bit(HAS_ALARM, &ds1307->flags)) - return -ENOTTY; + if (!test_bit(HAS_ALARM, &ds1307->flags)) + return -ENOTTY; - ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL); - if (ret < 0) - return ret; + ret = i2c_smbus_read_byte_data(client, DS1337_REG_CONTROL); + if (ret < 0) + return ret; + if (enabled) ret |= DS1337_BIT_A1IE; + else + ret &= ~DS1337_BIT_A1IE; - ret = i2c_smbus_write_byte_data(client, - DS1337_REG_CONTROL, ret); - if (ret < 0) - return ret; - - break; - - default: - return -ENOIOCTLCMD; - } + ret = i2c_smbus_write_byte_data(client, DS1337_REG_CONTROL, ret); + if (ret < 0) + return ret; return 0; } @@ -548,7 +525,7 @@ static const struct rtc_class_ops ds13xx_rtc_ops = { .set_time = ds1307_set_time, .read_alarm = ds1337_read_alarm, .set_alarm = ds1337_set_alarm, - .ioctl = ds1307_ioctl, + .alarm_irq_enable = ds1307_alarm_irq_enable, }; /*----------------------------------------------------------------------*/ diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c index 47fb635..d834a63 100644 --- a/drivers/rtc/rtc-ds1374.c +++ b/drivers/rtc/rtc-ds1374.c @@ -307,42 +307,25 @@ unlock: mutex_unlock(&ds1374->mutex); } -static int ds1374_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +static int ds1374_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct i2c_client *client = to_i2c_client(dev); struct ds1374 *ds1374 = i2c_get_clientdata(client); - int ret = -ENOIOCTLCMD; + int ret; mutex_lock(&ds1374->mutex); - switch (cmd) { - case RTC_AIE_OFF: - ret = i2c_smbus_read_byte_data(client, DS1374_REG_CR); - if (ret < 0) - goto out; - - ret &= ~DS1374_REG_CR_WACE; - - ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, ret); - if (ret < 0) - goto out; - - break; - - case RTC_AIE_ON: - ret = i2c_smbus_read_byte_data(client, DS1374_REG_CR); - if (ret < 0) - goto out; + ret = i2c_smbus_read_byte_data(client, DS1374_REG_CR); + if (ret < 0) + goto out; + if (enabled) { ret |= DS1374_REG_CR_WACE | DS1374_REG_CR_AIE; ret &= ~DS1374_REG_CR_WDALM; - - ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, ret); - if (ret < 0) - goto out; - - break; + } else { + ret &= ~DS1374_REG_CR_WACE; } + ret = i2c_smbus_write_byte_data(client, DS1374_REG_CR, ret); out: mutex_unlock(&ds1374->mutex); @@ -354,7 +337,7 @@ static const struct rtc_class_ops ds1374_rtc_ops = { .set_time = ds1374_set_time, .read_alarm = ds1374_read_alarm, .set_alarm = ds1374_set_alarm, - .ioctl = ds1374_ioctl, + .alarm_irq_enable = ds1374_alarm_irq_enable, }; static int ds1374_probe(struct i2c_client *client, diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c index 23a9ee1..9507354 100644 --- a/drivers/rtc/rtc-ds3232.c +++ b/drivers/rtc/rtc-ds3232.c @@ -1,7 +1,7 @@ /* * RTC client/driver for the Maxim/Dallas DS3232 Real-Time Clock over I2C * - * Copyright (C) 2009-2010 Freescale Semiconductor. + * Copyright (C) 2009-2011 Freescale Semiconductor. * Author: Jack Lan <jack.lan@freescale.com> * * This program is free software; you can redistribute it and/or modify it @@ -141,9 +141,11 @@ static int ds3232_read_time(struct device *dev, struct rtc_time *time) time->tm_hour = bcd2bin(hour); } - time->tm_wday = bcd2bin(week); + /* Day of the week in linux range is 0~6 while 1~7 in RTC chip */ + time->tm_wday = bcd2bin(week) - 1; time->tm_mday = bcd2bin(day); - time->tm_mon = bcd2bin(month & 0x7F); + /* linux tm_mon range:0~11, while month range is 1~12 in RTC chip */ + time->tm_mon = bcd2bin(month & 0x7F) - 1; if (century) add_century = 100; @@ -162,9 +164,11 @@ static int ds3232_set_time(struct device *dev, struct rtc_time *time) buf[0] = bin2bcd(time->tm_sec); buf[1] = bin2bcd(time->tm_min); buf[2] = bin2bcd(time->tm_hour); - buf[3] = bin2bcd(time->tm_wday); /* Day of the week */ + /* Day of the week in linux range is 0~6 while 1~7 in RTC chip */ + buf[3] = bin2bcd(time->tm_wday + 1); buf[4] = bin2bcd(time->tm_mday); /* Date */ - buf[5] = bin2bcd(time->tm_mon); + /* linux tm_mon range:0~11, while month range is 1~12 in RTC chip */ + buf[5] = bin2bcd(time->tm_mon + 1); if (time->tm_year >= 100) { buf[5] |= 0x80; buf[6] = bin2bcd(time->tm_year - 100); diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 5a8daa3..69fe664 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -213,41 +213,27 @@ static int m41t80_rtc_set_time(struct device *dev, struct rtc_time *tm) return m41t80_set_datetime(to_i2c_client(dev), tm); } -#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE) -static int -m41t80_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +static int m41t80_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct i2c_client *client = to_i2c_client(dev); int rc; - switch (cmd) { - case RTC_AIE_OFF: - case RTC_AIE_ON: - break; - default: - return -ENOIOCTLCMD; - } - rc = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON); if (rc < 0) goto err; - switch (cmd) { - case RTC_AIE_OFF: - rc &= ~M41T80_ALMON_AFE; - break; - case RTC_AIE_ON: + + if (enabled) rc |= M41T80_ALMON_AFE; - break; - } + else + rc &= ~M41T80_ALMON_AFE; + if (i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON, rc) < 0) goto err; + return 0; err: return -EIO; } -#else -#define m41t80_rtc_ioctl NULL -#endif static int m41t80_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *t) { @@ -374,7 +360,7 @@ static struct rtc_class_ops m41t80_rtc_ops = { .read_alarm = m41t80_rtc_read_alarm, .set_alarm = m41t80_rtc_set_alarm, .proc = m41t80_rtc_proc, - .ioctl = m41t80_rtc_ioctl, + .alarm_irq_enable = m41t80_rtc_alarm_irq_enable, }; #if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE) diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c index a99a0b5..3978f4c 100644 --- a/drivers/rtc/rtc-m48t59.c +++ b/drivers/rtc/rtc-m48t59.c @@ -263,30 +263,21 @@ static int m48t59_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) /* * Handle commands from user-space */ -static int m48t59_rtc_ioctl(struct device *dev, unsigned int cmd, - unsigned long arg) +static int m48t59_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct platform_device *pdev = to_platform_device(dev); struct m48t59_plat_data *pdata = pdev->dev.platform_data; struct m48t59_private *m48t59 = platform_get_drvdata(pdev); unsigned long flags; - int ret = 0; spin_lock_irqsave(&m48t59->lock, flags); - switch (cmd) { - case RTC_AIE_OFF: /* alarm interrupt off */ - M48T59_WRITE(0x00, M48T59_INTR); - break; - case RTC_AIE_ON: /* alarm interrupt on */ + if (enabled) M48T59_WRITE(M48T59_INTR_AFE, M48T59_INTR); - break; - default: - ret = -ENOIOCTLCMD; - break; - } + else + M48T59_WRITE(0x00, M48T59_INTR); spin_unlock_irqrestore(&m48t59->lock, flags); - return ret; + return 0; } static int m48t59_rtc_proc(struct device *dev, struct seq_file *seq) @@ -330,12 +321,12 @@ static irqreturn_t m48t59_rtc_interrupt(int irq, void *dev_id) } static const struct rtc_class_ops m48t59_rtc_ops = { - .ioctl = m48t59_rtc_ioctl, .read_time = m48t59_rtc_read_time, .set_time = m48t59_rtc_set_time, .read_alarm = m48t59_rtc_readalarm, .set_alarm = m48t59_rtc_setalarm, .proc = m48t59_rtc_proc, + .alarm_irq_enable = m48t59_rtc_alarm_irq_enable, }; static const struct rtc_class_ops m48t02_rtc_ops = { diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c index bcd0cf6..1db62db 100644 --- a/drivers/rtc/rtc-mrst.c +++ b/drivers/rtc/rtc-mrst.c @@ -255,42 +255,21 @@ static int mrst_irq_set_state(struct device *dev, int enabled) return 0; } -#if defined(CONFIG_RTC_INTF_DEV) || defined(CONFIG_RTC_INTF_DEV_MODULE) - /* Currently, the vRTC doesn't support UIE ON/OFF */ -static int -mrst_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) +static int mrst_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct mrst_rtc *mrst = dev_get_drvdata(dev); unsigned long flags; - switch (cmd) { - case RTC_AIE_OFF: - case RTC_AIE_ON: - if (!mrst->irq) - return -EINVAL; - break; - default: - /* PIE ON/OFF is handled by mrst_irq_set_state() */ - return -ENOIOCTLCMD; - } - spin_lock_irqsave(&rtc_lock, flags); - switch (cmd) { - case RTC_AIE_OFF: /* alarm off */ - mrst_irq_disable(mrst, RTC_AIE); - break; - case RTC_AIE_ON: /* alarm on */ + if (enabled) mrst_irq_enable(mrst, RTC_AIE); - break; - } + else + mrst_irq_disable(mrst, RTC_AIE); spin_unlock_irqrestore(&rtc_lock, flags); return 0; } -#else -#define mrst_rtc_ioctl NULL -#endif #if defined(CONFIG_RTC_INTF_PROC) || defined(CONFIG_RTC_INTF_PROC_MODULE) @@ -317,13 +296,13 @@ static int mrst_procfs(struct device *dev, struct seq_file *seq) #endif static const struct rtc_class_ops mrst_rtc_ops = { - .ioctl = mrst_rtc_ioctl, .read_time = mrst_read_time, .set_time = mrst_set_time, .read_alarm = mrst_read_alarm, .set_alarm = mrst_set_alarm, .proc = mrst_procfs, .irq_set_state = mrst_irq_set_state, + .alarm_irq_enable = mrst_rtc_alarm_irq_enable, }; static struct mrst_rtc mrst_rtc; diff --git a/drivers/rtc/rtc-msm6242.c b/drivers/rtc/rtc-msm6242.c index b2fff0c..6782062 100644 --- a/drivers/rtc/rtc-msm6242.c +++ b/drivers/rtc/rtc-msm6242.c @@ -82,7 +82,7 @@ static inline unsigned int msm6242_read(struct msm6242_priv *priv, static inline void msm6242_write(struct msm6242_priv *priv, unsigned int val, unsigned int reg) { - return __raw_writel(val, &priv->regs[reg]); + __raw_writel(val, &priv->regs[reg]); } static inline void msm6242_set(struct msm6242_priv *priv, unsigned int val, diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c index bcca472..60627a7 100644 --- a/drivers/rtc/rtc-mv.c +++ b/drivers/rtc/rtc-mv.c @@ -169,25 +169,19 @@ static int mv_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) return 0; } -static int mv_rtc_ioctl(struct device *dev, unsigned int cmd, - unsigned long arg) +static int mv_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) { struct platform_device *pdev = to_platform_device(dev); struct rtc_plat_data *pdata = platform_get_drvdata(pdev); void __iomem *ioaddr = pdata->ioaddr; if (pdata->irq < 0) - return -ENOIOCTLCMD; /* fall back into rtc-dev's emulation */ - switch (cmd) { - case RTC_AIE_OFF: - writel(0, ioaddr + RTC_ALARM_INTERRUPT_MASK_REG_OFFS); - break; - case RTC_AIE_ON: + return -EINVAL; /* fall back into rtc-dev's emulation */ + + if (enabled) writel(1, ioaddr + RTC_ALARM_INTERRUPT_MASK_REG_OFFS); - break; - default: - return -ENOIOCTLCMD; - } + else + writel(0, ioaddr + RTC_ALARM_INTERRUPT_MASK_REG_OFFS); return 0; } @@ -216,7 +210,7 @@ static const struct rtc_class_ops mv_rtc_alarm_ops = { .set_time = mv_rtc_set_time, .read_alarm = mv_rtc_read_alarm, .set_alarm = mv_rtc_set_alarm, - .ioctl = mv_rtc_ioctl, + .alarm_irq_enable = mv_rtc_alarm_irq_enable, }; static int __devinit mv_rtc_probe(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index e72b523..b4dbf3a3 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -143,8 +143,6 @@ omap_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) u8 reg; switch (cmd) { - case RTC_AIE_OFF: - case RTC_AIE_ON: case RTC_UIE_OFF: case RTC_UIE_ON: break; @@ -156,13 +154,6 @@ omap_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) rtc_wait_not_busy(); reg = rtc_read(OMAP_RTC_INTERRUPTS_REG); switch (cmd) { - /* AIE = Alarm Interrupt Enable */ - case RTC_AIE_OFF: - reg &= ~OMAP_RTC_INTERRUPTS_IT_ALARM; - break; - case RTC_AIE_ON: - reg |= OMAP_RTC_INTERRUPTS_IT_ALARM; - break; /* UIE = Update Interrupt Enable (1/second) */ case RTC_UIE_OFF: reg &= ~OMAP_RTC_INTERRUPTS_IT_TIMER; @@ -182,6 +173,24 @@ omap_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) #define omap_rtc_ioctl NULL #endif +static int omap_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + u8 reg; + + local_irq_disable(); + rtc_wait_not_busy(); + reg = rtc_read(OMAP_RTC_INTERRUPTS_REG); + if (enabled) + reg |= OMAP_RTC_INTERRUPTS_IT_ALARM; + else + reg &= ~OMAP_RTC_INTERRUPTS_IT_ALARM; + rtc_wait_not_busy(); + rtc_write(reg, OMAP_RTC_INTERRUPTS_REG); + local_irq_enable(); + + return 0; +} + /* this hardware doesn't support "don't care" alarm fields */ static int tm2bcd(struct rtc_time *tm) { @@ -309,6 +318,7 @@ static struct rtc_class_ops omap_rtc_ops = { .set_time = omap_rtc_set_time, .read_alarm = omap_rtc_read_alarm, .set_alarm = omap_rtc_set_alarm, + .alarm_irq_enable = omap_rtc_alarm_irq_enable, }; static int omap_rtc_alarm; diff --git a/drivers/rtc/rtc-proc.c b/drivers/rtc/rtc-proc.c index c086fc3..242bbf8 100644 --- a/drivers/rtc/rtc-proc.c +++ b/drivers/rtc/rtc-proc.c @@ -81,12 +81,16 @@ static int rtc_proc_show(struct seq_file *seq, void *offset) static int rtc_proc_open(struct inode *inode, struct file *file) { + int ret; struct rtc_device *rtc = PDE(inode)->data; if (!try_module_get(THIS_MODULE)) return -ENODEV; - return single_open(file, rtc_proc_show, rtc); + ret = single_open(file, rtc_proc_show, rtc); + if (ret) + module_put(THIS_MODULE); + return ret; } static int rtc_proc_release(struct inode *inode, struct file *file) diff --git a/drivers/rtc/rtc-rp5c01.c b/drivers/rtc/rtc-rp5c01.c index 36eb661..694da39 100644 --- a/drivers/rtc/rtc-rp5c01.c +++ b/drivers/rtc/rtc-rp5c01.c @@ -76,7 +76,7 @@ static inline unsigned int rp5c01_read(struct rp5c01_priv *priv, static inline void rp5c01_write(struct rp5c01_priv *priv, unsigned int val, unsigned int reg) { - return __raw_writel(val, &priv->regs[reg]); + __raw_writel(val, &priv->regs[reg]); } static void rp5c01_lock(struct rp5c01_priv *priv) diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c index dd14e20..6aaa155 100644 --- a/drivers/rtc/rtc-rs5c372.c +++ b/drivers/rtc/rtc-rs5c372.c @@ -299,14 +299,6 @@ rs5c_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) if (rs5c->type == rtc_rs5c372a && (buf & RS5C372A_CTRL1_SL1)) return -ENOIOCTLCMD; - case RTC_AIE_OFF: - case RTC_AIE_ON: - /* these irq management calls only make sense for chips - * which are wired up to an IRQ. - */ - if (!rs5c->has_irq) - return -ENOIOCTLCMD; - break; default: return -ENOIOCTLCMD; } @@ -317,12 +309,6 @@ rs5c_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) addr = RS5C_ADDR(RS5C_REG_CTRL1); switch (cmd) { - case RTC_AIE_OFF: /* alarm off */ - buf &= ~RS5C_CTRL1_AALE; - break; - case RTC_AIE_ON: /* alarm on */ - buf |= RS5C_CTRL1_AALE; - break; case RTC_UIE_OFF: /* update off */ buf &= ~RS5C_CTRL1_CT_MASK; break; @@ -347,6 +333,39 @@ rs5c_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) #endif +static int rs5c_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct i2c_client *client = to_i2c_client(dev); + struct rs5c372 *rs5c = i2c_get_clientdata(client); + unsigned char buf; + int status, addr; + + buf = rs5c->regs[RS5C_REG_CTRL1]; + + if (!rs5c->has_irq) + return -EINVAL; + + status = rs5c_get_regs(rs5c); + if (status < 0) + return status; + + addr = RS5C_ADDR(RS5C_REG_CTRL1); + if (enabled) + buf |= RS5C_CTRL1_AALE; + else + buf &= ~RS5C_CTRL1_AALE; + + if (i2c_smbus_write_byte_data(client, addr, buf) < 0) { + printk(KERN_WARNING "%s: can't update alarm\n", + rs5c->rtc->name); + status = -EIO; + } else + rs5c->regs[RS5C_REG_CTRL1] = buf; + + return status; +} + + /* NOTE: Since RTC_WKALM_{RD,SET} were originally defined for EFI, * which only exposes a polled programming interface; and since * these calls map directly to those EFI requests; we don't demand @@ -466,6 +485,7 @@ static const struct rtc_class_ops rs5c372_rtc_ops = { .set_time = rs5c372_rtc_set_time, .read_alarm = rs5c_read_alarm, .set_alarm = rs5c_set_alarm, + .alarm_irq_enable = rs5c_rtc_alarm_irq_enable, }; #if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index cf953ec..b80fa28 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -77,18 +77,20 @@ static irqreturn_t s3c_rtc_tickirq(int irq, void *id) } /* Update control registers */ -static void s3c_rtc_setaie(int to) +static int s3c_rtc_setaie(struct device *dev, unsigned int enabled) { unsigned int tmp; - pr_debug("%s: aie=%d\n", __func__, to); + pr_debug("%s: aie=%d\n", __func__, enabled); tmp = readb(s3c_rtc_base + S3C2410_RTCALM) & ~S3C2410_RTCALM_ALMEN; - if (to) + if (enabled) tmp |= S3C2410_RTCALM_ALMEN; writeb(tmp, s3c_rtc_base + S3C2410_RTCALM); + + return 0; } static int s3c_rtc_setpie(struct device *dev, int enabled) @@ -308,7 +310,7 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) writeb(alrm_en, base + S3C2410_RTCALM); - s3c_rtc_setaie(alrm->enabled); + s3c_rtc_setaie(dev, alrm->enabled); return 0; } @@ -440,7 +442,7 @@ static int __devexit s3c_rtc_remove(struct platform_device *dev) rtc_device_unregister(rtc); s3c_rtc_setpie(&dev->dev, 0); - s3c_rtc_setaie(0); + s3c_rtc_setaie(&dev->dev, 0); clk_disable(rtc_clk); clk_put(rtc_clk); diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 88ea52b..5dfe5ff 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -314,16 +314,6 @@ static int sa1100_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { switch (cmd) { - case RTC_AIE_OFF: - spin_lock_irq(&sa1100_rtc_lock); - RTSR &= ~RTSR_ALE; - spin_unlock_irq(&sa1100_rtc_lock); - return 0; - case RTC_AIE_ON: - spin_lock_irq(&sa1100_rtc_lock); - RTSR |= RTSR_ALE; - spin_unlock_irq(&sa1100_rtc_lock); - return 0; case RTC_UIE_OFF: spin_lock_irq(&sa1100_rtc_lock); RTSR &= ~RTSR_HZE; @@ -338,6 +328,17 @@ static int sa1100_rtc_ioctl(struct device *dev, unsigned int cmd, return -ENOIOCTLCMD; } +static int sa1100_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + spin_lock_irq(&sa1100_rtc_lock); + if (enabled) + RTSR |= RTSR_ALE; + else + RTSR &= ~RTSR_ALE; + spin_unlock_irq(&sa1100_rtc_lock); + return 0; +} + static int sa1100_rtc_read_time(struct device *dev, struct rtc_time *tm) { rtc_time_to_tm(RCNR, tm); @@ -410,6 +411,7 @@ static const struct rtc_class_ops sa1100_rtc_ops = { .proc = sa1100_rtc_proc, .irq_set_freq = sa1100_irq_set_freq, .irq_set_state = sa1100_irq_set_state, + .alarm_irq_enable = sa1100_rtc_alarm_irq_enable, }; static int sa1100_rtc_probe(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c index 06e41ed..93314a9 100644 --- a/drivers/rtc/rtc-sh.c +++ b/drivers/rtc/rtc-sh.c @@ -350,10 +350,6 @@ static int sh_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) unsigned int ret = 0; switch (cmd) { - case RTC_AIE_OFF: - case RTC_AIE_ON: - sh_rtc_setaie(dev, cmd == RTC_AIE_ON); - break; case RTC_UIE_OFF: rtc->periodic_freq &= ~PF_OXS; sh_rtc_setcie(dev, 0); @@ -369,6 +365,12 @@ static int sh_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) return ret; } +static int sh_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + sh_rtc_setaie(dev, enabled); + return 0; +} + static int sh_rtc_read_time(struct device *dev, struct rtc_time *tm) { struct platform_device *pdev = to_platform_device(dev); @@ -604,6 +606,7 @@ static struct rtc_class_ops sh_rtc_ops = { .irq_set_state = sh_rtc_irq_set_state, .irq_set_freq = sh_rtc_irq_set_freq, .proc = sh_rtc_proc, + .alarm_irq_enable = sh_rtc_alarm_irq_enable, }; static int __init sh_rtc_probe(struct platform_device *pdev) diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c index 51725f7..a82d6fe 100644 --- a/drivers/rtc/rtc-test.c +++ b/drivers/rtc/rtc-test.c @@ -50,24 +50,9 @@ static int test_rtc_proc(struct device *dev, struct seq_file *seq) return 0; } -static int test_rtc_ioctl(struct device *dev, unsigned int cmd, - unsigned long arg) +static int test_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) { - /* We do support interrupts, they're generated - * using the sysfs interface. - */ - switch (cmd) { - case RTC_PIE_ON: - case RTC_PIE_OFF: - case RTC_UIE_ON: - case RTC_UIE_OFF: - case RTC_AIE_ON: - case RTC_AIE_OFF: - return 0; - - default: - return -ENOIOCTLCMD; - } + return 0; } static const struct rtc_class_ops test_rtc_ops = { @@ -76,7 +61,7 @@ static const struct rtc_class_ops test_rtc_ops = { .read_alarm = test_rtc_read_alarm, .set_alarm = test_rtc_set_alarm, .set_mmss = test_rtc_set_mmss, - .ioctl = test_rtc_ioctl, + .alarm_irq_enable = test_rtc_alarm_irq_enable, }; static ssize_t test_irq_show(struct device *dev, diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c index c324424..769190a 100644 --- a/drivers/rtc/rtc-vr41xx.c +++ b/drivers/rtc/rtc-vr41xx.c @@ -240,26 +240,6 @@ static int vr41xx_rtc_irq_set_state(struct device *dev, int enabled) static int vr41xx_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { switch (cmd) { - case RTC_AIE_ON: - spin_lock_irq(&rtc_lock); - - if (!alarm_enabled) { - enable_irq(aie_irq); - alarm_enabled = 1; - } - - spin_unlock_irq(&rtc_lock); - break; - case RTC_AIE_OFF: - spin_lock_irq(&rtc_lock); - - if (alarm_enabled) { - disable_irq(aie_irq); - alarm_enabled = 0; - } - - spin_unlock_irq(&rtc_lock); - break; case RTC_EPOCH_READ: return put_user(epoch, (unsigned long __user *)arg); case RTC_EPOCH_SET: @@ -275,6 +255,24 @@ static int vr41xx_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long return 0; } +static int vr41xx_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + spin_lock_irq(&rtc_lock); + if (enabled) { + if (!alarm_enabled) { + enable_irq(aie_irq); + alarm_enabled = 1; + } + } else { + if (alarm_enabled) { + disable_irq(aie_irq); + alarm_enabled = 0; + } + } + spin_unlock_irq(&rtc_lock); + return 0; +} + static irqreturn_t elapsedtime_interrupt(int irq, void *dev_id) { struct platform_device *pdev = (struct platform_device *)dev_id; diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 4155805..2b771f1 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -319,6 +319,9 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) private = (struct dasd_eckd_private *) device->private; lcu = private->lcu; + /* nothing to do if already disconnected */ + if (!lcu) + return; device->discipline->get_uid(device, &uid); spin_lock_irqsave(&lcu->lock, flags); list_del_init(&device->alias_list); @@ -680,6 +683,9 @@ int dasd_alias_remove_device(struct dasd_device *device) private = (struct dasd_eckd_private *) device->private; lcu = private->lcu; + /* nothing to do if already removed */ + if (!lcu) + return 0; spin_lock_irqsave(&lcu->lock, flags); _remove_device_from_lcu(lcu, device); spin_unlock_irqrestore(&lcu->lock, flags); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 318672d..a9fe23d 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -72,7 +72,7 @@ static struct dasd_discipline dasd_eckd_discipline; static struct ccw_device_id dasd_eckd_ids[] = { { CCW_DEVICE_DEVTYPE (0x3990, 0, 0x3390, 0), .driver_info = 0x1}, { CCW_DEVICE_DEVTYPE (0x2105, 0, 0x3390, 0), .driver_info = 0x2}, - { CCW_DEVICE_DEVTYPE (0x3880, 0, 0x3390, 0), .driver_info = 0x3}, + { CCW_DEVICE_DEVTYPE (0x3880, 0, 0x3380, 0), .driver_info = 0x3}, { CCW_DEVICE_DEVTYPE (0x3990, 0, 0x3380, 0), .driver_info = 0x4}, { CCW_DEVICE_DEVTYPE (0x2105, 0, 0x3380, 0), .driver_info = 0x5}, { CCW_DEVICE_DEVTYPE (0x9343, 0, 0x9345, 0), .driver_info = 0x6}, diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c index c881a14..1f6a4d8 100644 --- a/drivers/s390/block/xpram.c +++ b/drivers/s390/block/xpram.c @@ -62,8 +62,8 @@ static int xpram_devs; /* * Parameter parsing functions. */ -static int __initdata devs = XPRAM_DEVS; -static char __initdata *sizes[XPRAM_MAX_DEVS]; +static int devs = XPRAM_DEVS; +static char *sizes[XPRAM_MAX_DEVS]; module_param(devs, int, 0); module_param_array(sizes, charp, NULL, 0); diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c index 8cd58e4..5ad44da 100644 --- a/drivers/s390/char/keyboard.c +++ b/drivers/s390/char/keyboard.c @@ -460,7 +460,8 @@ kbd_ioctl(struct kbd_data *kbd, struct file *file, unsigned int cmd, unsigned long arg) { void __user *argp; - int ct, perm; + unsigned int ct; + int perm; argp = (void __user *)arg; diff --git a/drivers/s390/char/tape.h b/drivers/s390/char/tape.h index 7a242f0..267b54e 100644 --- a/drivers/s390/char/tape.h +++ b/drivers/s390/char/tape.h @@ -280,6 +280,14 @@ tape_do_io_free(struct tape_device *device, struct tape_request *request) return rc; } +static inline void +tape_do_io_async_free(struct tape_device *device, struct tape_request *request) +{ + request->callback = (void *) tape_free_request; + request->callback_data = NULL; + tape_do_io_async(device, request); +} + extern int tape_oper_handler(int irq, int status); extern void tape_noper_handler(int irq, int status); extern int tape_open(struct tape_device *); diff --git a/drivers/s390/char/tape_34xx.c b/drivers/s390/char/tape_34xx.c index c17f35b..c265111 100644 --- a/drivers/s390/char/tape_34xx.c +++ b/drivers/s390/char/tape_34xx.c @@ -53,23 +53,11 @@ static void tape_34xx_delete_sbid_from(struct tape_device *, int); * Medium sense for 34xx tapes. There is no 'real' medium sense call. * So we just do a normal sense. */ -static int -tape_34xx_medium_sense(struct tape_device *device) +static void __tape_34xx_medium_sense(struct tape_request *request) { - struct tape_request *request; - unsigned char *sense; - int rc; - - request = tape_alloc_request(1, 32); - if (IS_ERR(request)) { - DBF_EXCEPTION(6, "MSEN fail\n"); - return PTR_ERR(request); - } - - request->op = TO_MSEN; - tape_ccw_end(request->cpaddr, SENSE, 32, request->cpdata); + struct tape_device *device = request->device; + unsigned char *sense; - rc = tape_do_io_interruptible(device, request); if (request->rc == 0) { sense = request->cpdata; @@ -88,15 +76,47 @@ tape_34xx_medium_sense(struct tape_device *device) device->tape_generic_status |= GMT_WR_PROT(~0); else device->tape_generic_status &= ~GMT_WR_PROT(~0); - } else { + } else DBF_EVENT(4, "tape_34xx: medium sense failed with rc=%d\n", request->rc); - } tape_free_request(request); +} + +static int tape_34xx_medium_sense(struct tape_device *device) +{ + struct tape_request *request; + int rc; + + request = tape_alloc_request(1, 32); + if (IS_ERR(request)) { + DBF_EXCEPTION(6, "MSEN fail\n"); + return PTR_ERR(request); + } + request->op = TO_MSEN; + tape_ccw_end(request->cpaddr, SENSE, 32, request->cpdata); + rc = tape_do_io_interruptible(device, request); + __tape_34xx_medium_sense(request); return rc; } +static void tape_34xx_medium_sense_async(struct tape_device *device) +{ + struct tape_request *request; + + request = tape_alloc_request(1, 32); + if (IS_ERR(request)) { + DBF_EXCEPTION(6, "MSEN fail\n"); + return; + } + + request->op = TO_MSEN; + tape_ccw_end(request->cpaddr, SENSE, 32, request->cpdata); + request->callback = (void *) __tape_34xx_medium_sense; + request->callback_data = NULL; + tape_do_io_async(device, request); +} + struct tape_34xx_work { struct tape_device *device; enum tape_op op; @@ -109,6 +129,9 @@ struct tape_34xx_work { * is inserted but cannot call tape_do_io* from an interrupt context. * Maybe that's useful for other actions we want to start from the * interrupt handler. + * Note: the work handler is called by the system work queue. The tape + * commands started by the handler need to be asynchrounous, otherwise + * a deadlock can occur e.g. in case of a deferred cc=1 (see __tape_do_irq). */ static void tape_34xx_work_handler(struct work_struct *work) @@ -119,7 +142,7 @@ tape_34xx_work_handler(struct work_struct *work) switch(p->op) { case TO_MSEN: - tape_34xx_medium_sense(device); + tape_34xx_medium_sense_async(device); break; default: DBF_EVENT(3, "T34XX: internal error: unknown work\n"); diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c index fbe361f..de2e99e 100644 --- a/drivers/s390/char/tape_3590.c +++ b/drivers/s390/char/tape_3590.c @@ -329,17 +329,17 @@ out: /* * Enable encryption */ -static int tape_3592_enable_crypt(struct tape_device *device) +static struct tape_request *__tape_3592_enable_crypt(struct tape_device *device) { struct tape_request *request; char *data; DBF_EVENT(6, "tape_3592_enable_crypt\n"); if (!crypt_supported(device)) - return -ENOSYS; + return ERR_PTR(-ENOSYS); request = tape_alloc_request(2, 72); if (IS_ERR(request)) - return PTR_ERR(request); + return request; data = request->cpdata; memset(data,0,72); @@ -354,23 +354,42 @@ static int tape_3592_enable_crypt(struct tape_device *device) request->op = TO_CRYPT_ON; tape_ccw_cc(request->cpaddr, MODE_SET_CB, 36, data); tape_ccw_end(request->cpaddr + 1, MODE_SET_CB, 36, data + 36); + return request; +} + +static int tape_3592_enable_crypt(struct tape_device *device) +{ + struct tape_request *request; + + request = __tape_3592_enable_crypt(device); + if (IS_ERR(request)) + return PTR_ERR(request); return tape_do_io_free(device, request); } +static void tape_3592_enable_crypt_async(struct tape_device *device) +{ + struct tape_request *request; + + request = __tape_3592_enable_crypt(device); + if (!IS_ERR(request)) + tape_do_io_async_free(device, request); +} + /* * Disable encryption */ -static int tape_3592_disable_crypt(struct tape_device *device) +static struct tape_request *__tape_3592_disable_crypt(struct tape_device *device) { struct tape_request *request; char *data; DBF_EVENT(6, "tape_3592_disable_crypt\n"); if (!crypt_supported(device)) - return -ENOSYS; + return ERR_PTR(-ENOSYS); request = tape_alloc_request(2, 72); if (IS_ERR(request)) - return PTR_ERR(request); + return request; data = request->cpdata; memset(data,0,72); @@ -383,9 +402,28 @@ static int tape_3592_disable_crypt(struct tape_device *device) tape_ccw_cc(request->cpaddr, MODE_SET_CB, 36, data); tape_ccw_end(request->cpaddr + 1, MODE_SET_CB, 36, data + 36); + return request; +} + +static int tape_3592_disable_crypt(struct tape_device *device) +{ + struct tape_request *request; + + request = __tape_3592_disable_crypt(device); + if (IS_ERR(request)) + return PTR_ERR(request); return tape_do_io_free(device, request); } +static void tape_3592_disable_crypt_async(struct tape_device *device) +{ + struct tape_request *request; + + request = __tape_3592_disable_crypt(device); + if (!IS_ERR(request)) + tape_do_io_async_free(device, request); +} + /* * IOCTL: Set encryption status */ @@ -457,8 +495,7 @@ tape_3590_ioctl(struct tape_device *device, unsigned int cmd, unsigned long arg) /* * SENSE Medium: Get Sense data about medium state */ -static int -tape_3590_sense_medium(struct tape_device *device) +static int tape_3590_sense_medium(struct tape_device *device) { struct tape_request *request; @@ -470,6 +507,18 @@ tape_3590_sense_medium(struct tape_device *device) return tape_do_io_free(device, request); } +static void tape_3590_sense_medium_async(struct tape_device *device) +{ + struct tape_request *request; + + request = tape_alloc_request(1, 128); + if (IS_ERR(request)) + return; + request->op = TO_MSEN; + tape_ccw_end(request->cpaddr, MEDIUM_SENSE, 128, request->cpdata); + tape_do_io_async_free(device, request); +} + /* * MTTELL: Tell block. Return the number of block relative to current file. */ @@ -546,15 +595,14 @@ tape_3590_read_opposite(struct tape_device *device, * 2. The attention msg is written to the "read subsystem data" buffer. * In this case we probably should print it to the console. */ -static int -tape_3590_read_attmsg(struct tape_device *device) +static void tape_3590_read_attmsg_async(struct tape_device *device) { struct tape_request *request; char *buf; request = tape_alloc_request(3, 4096); if (IS_ERR(request)) - return PTR_ERR(request); + return; request->op = TO_READ_ATTMSG; buf = request->cpdata; buf[0] = PREP_RD_SS_DATA; @@ -562,12 +610,15 @@ tape_3590_read_attmsg(struct tape_device *device) tape_ccw_cc(request->cpaddr, PERFORM_SS_FUNC, 12, buf); tape_ccw_cc(request->cpaddr + 1, READ_SS_DATA, 4096 - 12, buf + 12); tape_ccw_end(request->cpaddr + 2, NOP, 0, NULL); - return tape_do_io_free(device, request); + tape_do_io_async_free(device, request); } /* * These functions are used to schedule follow-up actions from within an * interrupt context (like unsolicited interrupts). + * Note: the work handler is called by the system work queue. The tape + * commands started by the handler need to be asynchrounous, otherwise + * a deadlock can occur e.g. in case of a deferred cc=1 (see __tape_do_irq). */ struct work_handler_data { struct tape_device *device; @@ -583,16 +634,16 @@ tape_3590_work_handler(struct work_struct *work) switch (p->op) { case TO_MSEN: - tape_3590_sense_medium(p->device); + tape_3590_sense_medium_async(p->device); break; case TO_READ_ATTMSG: - tape_3590_read_attmsg(p->device); + tape_3590_read_attmsg_async(p->device); break; case TO_CRYPT_ON: - tape_3592_enable_crypt(p->device); + tape_3592_enable_crypt_async(p->device); break; case TO_CRYPT_OFF: - tape_3592_disable_crypt(p->device); + tape_3592_disable_crypt_async(p->device); break; default: DBF_EVENT(3, "T3590: work handler undefined for " diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index e9fff2b..5640c89 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -476,7 +476,7 @@ static inline void inbound_primed(struct qdio_q *q, int count) static int get_inbound_buffer_frontier(struct qdio_q *q) { int count, stop; - unsigned char state; + unsigned char state = 0; /* * Don't check 128 buffers, as otherwise qdio_inbound_q_moved @@ -643,7 +643,7 @@ void qdio_inbound_processing(unsigned long data) static int get_outbound_buffer_frontier(struct qdio_q *q) { int count, stop; - unsigned char state; + unsigned char state = 0; if (need_siga_sync(q)) if (((queue_type(q) != QDIO_IQDIO_QFMT) && diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 65ebee0..b6a6356 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -565,7 +565,7 @@ static int netiucv_callback_connreq(struct iucv_path *path, struct iucv_event ev; int rc; - if (memcmp(iucvMagic, ipuser, sizeof(ipuser))) + if (memcmp(iucvMagic, ipuser, 16)) /* ipuser must match iucvMagic. */ return -EINVAL; rc = -EINVAL; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 29f848b..019ae58 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -988,16 +988,30 @@ static void qeth_get_channel_path_desc(struct qeth_card *card) chp_dsc = (struct channelPath_dsc *)ccw_device_get_chp_desc(ccwdev, 0); if (chp_dsc != NULL) { /* CHPP field bit 6 == 1 -> single queue */ - if ((chp_dsc->chpp & 0x02) == 0x02) + if ((chp_dsc->chpp & 0x02) == 0x02) { + if ((atomic_read(&card->qdio.state) != + QETH_QDIO_UNINITIALIZED) && + (card->qdio.no_out_queues == 4)) + /* change from 4 to 1 outbound queues */ + qeth_free_qdio_buffers(card); card->qdio.no_out_queues = 1; + if (card->qdio.default_out_queue != 0) + dev_info(&card->gdev->dev, + "Priority Queueing not supported\n"); + card->qdio.default_out_queue = 0; + } else { + if ((atomic_read(&card->qdio.state) != + QETH_QDIO_UNINITIALIZED) && + (card->qdio.no_out_queues == 1)) { + /* change from 1 to 4 outbound queues */ + qeth_free_qdio_buffers(card); + card->qdio.default_out_queue = 2; + } + card->qdio.no_out_queues = 4; + } card->info.func_level = 0x4100 + chp_dsc->desc; kfree(chp_dsc); } - if (card->qdio.no_out_queues == 1) { - card->qdio.default_out_queue = 0; - dev_info(&card->gdev->dev, - "Priority Queueing not supported\n"); - } QETH_DBF_TEXT_(SETUP, 2, "nr:%x", card->qdio.no_out_queues); QETH_DBF_TEXT_(SETUP, 2, "lvl:%02x", card->info.func_level); return; @@ -1832,33 +1846,6 @@ static inline int qeth_get_initial_mtu_for_card(struct qeth_card *card) } } -static inline int qeth_get_max_mtu_for_card(int cardtype) -{ - switch (cardtype) { - - case QETH_CARD_TYPE_UNKNOWN: - case QETH_CARD_TYPE_OSD: - case QETH_CARD_TYPE_OSN: - case QETH_CARD_TYPE_OSM: - case QETH_CARD_TYPE_OSX: - return 61440; - case QETH_CARD_TYPE_IQD: - return 57344; - default: - return 1500; - } -} - -static inline int qeth_get_mtu_out_of_mpc(int cardtype) -{ - switch (cardtype) { - case QETH_CARD_TYPE_IQD: - return 1; - default: - return 0; - } -} - static inline int qeth_get_mtu_outof_framesize(int framesize) { switch (framesize) { @@ -1881,10 +1868,9 @@ static inline int qeth_mtu_is_valid(struct qeth_card *card, int mtu) case QETH_CARD_TYPE_OSD: case QETH_CARD_TYPE_OSM: case QETH_CARD_TYPE_OSX: - return ((mtu >= 576) && (mtu <= 61440)); case QETH_CARD_TYPE_IQD: return ((mtu >= 576) && - (mtu <= card->info.max_mtu + 4096 - 32)); + (mtu <= card->info.max_mtu)); case QETH_CARD_TYPE_OSN: case QETH_CARD_TYPE_UNKNOWN: default: @@ -1907,7 +1893,7 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply, memcpy(&card->token.ulp_filter_r, QETH_ULP_ENABLE_RESP_FILTER_TOKEN(iob->data), QETH_MPC_TOKEN_LENGTH); - if (qeth_get_mtu_out_of_mpc(card->info.type)) { + if (card->info.type == QETH_CARD_TYPE_IQD) { memcpy(&framesize, QETH_ULP_ENABLE_RESP_MAX_MTU(iob->data), 2); mtu = qeth_get_mtu_outof_framesize(framesize); if (!mtu) { @@ -1915,12 +1901,21 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply, QETH_DBF_TEXT_(SETUP, 2, " rc%d", iob->rc); return 0; } - card->info.max_mtu = mtu; + if (card->info.initial_mtu && (card->info.initial_mtu != mtu)) { + /* frame size has changed */ + if (card->dev && + ((card->dev->mtu == card->info.initial_mtu) || + (card->dev->mtu > mtu))) + card->dev->mtu = mtu; + qeth_free_qdio_buffers(card); + } card->info.initial_mtu = mtu; + card->info.max_mtu = mtu; card->qdio.in_buf_size = mtu + 2 * PAGE_SIZE; } else { card->info.initial_mtu = qeth_get_initial_mtu_for_card(card); - card->info.max_mtu = qeth_get_max_mtu_for_card(card->info.type); + card->info.max_mtu = *(__u16 *)QETH_ULP_ENABLE_RESP_MAX_MTU( + iob->data); card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT; } @@ -3775,6 +3770,47 @@ static inline int qeth_get_qdio_q_format(struct qeth_card *card) } } +static void qeth_determine_capabilities(struct qeth_card *card) +{ + int rc; + int length; + char *prcd; + struct ccw_device *ddev; + int ddev_offline = 0; + + QETH_DBF_TEXT(SETUP, 2, "detcapab"); + ddev = CARD_DDEV(card); + if (!ddev->online) { + ddev_offline = 1; + rc = ccw_device_set_online(ddev); + if (rc) { + QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); + goto out; + } + } + + rc = qeth_read_conf_data(card, (void **) &prcd, &length); + if (rc) { + QETH_DBF_MESSAGE(2, "%s qeth_read_conf_data returned %i\n", + dev_name(&card->gdev->dev), rc); + QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); + goto out_offline; + } + qeth_configure_unitaddr(card, prcd); + qeth_configure_blkt_default(card, prcd); + kfree(prcd); + + rc = qdio_get_ssqd_desc(ddev, &card->ssqd); + if (rc) + QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); + +out_offline: + if (ddev_offline == 1) + ccw_device_set_offline(ddev); +out: + return; +} + static int qeth_qdio_establish(struct qeth_card *card) { struct qdio_initialize init_data; @@ -3905,6 +3941,7 @@ int qeth_core_hardsetup_card(struct qeth_card *card) QETH_DBF_TEXT(SETUP, 2, "hrdsetup"); atomic_set(&card->force_alloc_skb, 0); + qeth_get_channel_path_desc(card); retry: if (retries) QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", @@ -3933,6 +3970,7 @@ retriable: else goto retry; } + qeth_determine_capabilities(card); qeth_init_tokens(card); qeth_init_func_level(card); rc = qeth_idx_activate_channel(&card->read, qeth_idx_read_cb); @@ -4202,41 +4240,6 @@ void qeth_core_free_discipline(struct qeth_card *card) card->discipline.ccwgdriver = NULL; } -static void qeth_determine_capabilities(struct qeth_card *card) -{ - int rc; - int length; - char *prcd; - - QETH_DBF_TEXT(SETUP, 2, "detcapab"); - rc = ccw_device_set_online(CARD_DDEV(card)); - if (rc) { - QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); - goto out; - } - - - rc = qeth_read_conf_data(card, (void **) &prcd, &length); - if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_read_conf_data returned %i\n", - dev_name(&card->gdev->dev), rc); - QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); - goto out_offline; - } - qeth_configure_unitaddr(card, prcd); - qeth_configure_blkt_default(card, prcd); - kfree(prcd); - - rc = qdio_get_ssqd_desc(CARD_DDEV(card), &card->ssqd); - if (rc) - QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); - -out_offline: - ccw_device_set_offline(CARD_DDEV(card)); -out: - return; -} - static int qeth_core_probe_device(struct ccwgroup_device *gdev) { struct qeth_card *card; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 2ac8f6a..ada0fe7 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -573,13 +573,13 @@ static int qeth_l2_send_setmac_cb(struct qeth_card *card, case IPA_RC_L2_DUP_LAYER3_MAC: dev_warn(&card->gdev->dev, "MAC address %pM already exists\n", - card->dev->dev_addr); + cmd->data.setdelmac.mac); break; case IPA_RC_L2_MAC_NOT_AUTH_BY_HYP: case IPA_RC_L2_MAC_NOT_AUTH_BY_ADP: dev_warn(&card->gdev->dev, "MAC address %pM is not authorized\n", - card->dev->dev_addr); + cmd->data.setdelmac.mac); break; default: break; diff --git a/drivers/s390/net/smsgiucv.c b/drivers/s390/net/smsgiucv.c index 65e1cf1..207b7d7 100644 --- a/drivers/s390/net/smsgiucv.c +++ b/drivers/s390/net/smsgiucv.c @@ -60,7 +60,7 @@ static struct iucv_handler smsg_handler = { static int smsg_path_pending(struct iucv_path *path, u8 ipvmid[8], u8 ipuser[16]) { - if (strncmp(ipvmid, "*MSG ", sizeof(ipvmid)) != 0) + if (strncmp(ipvmid, "*MSG ", 8) != 0) return -EINVAL; /* Path pending from *MSG. */ return iucv_path_accept(path, &smsg_handler, "SMSGIUCV ", NULL); diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h index 475c31a..77b26f5 100644 --- a/drivers/scsi/arcmsr/arcmsr.h +++ b/drivers/scsi/arcmsr/arcmsr.h @@ -2,7 +2,7 @@ ******************************************************************************* ** O.S : Linux ** FILE NAME : arcmsr.h -** BY : Erich Chen +** BY : Nick Cheng ** Description: SCSI RAID Device Driver for ** ARECA RAID Host adapter ******************************************************************************* @@ -46,8 +46,12 @@ struct device_attribute; /*The limit of outstanding scsi command that firmware can handle*/ #define ARCMSR_MAX_OUTSTANDING_CMD 256 -#define ARCMSR_MAX_FREECCB_NUM 320 -#define ARCMSR_DRIVER_VERSION "Driver Version 1.20.00.15 2010/02/02" +#ifdef CONFIG_XEN + #define ARCMSR_MAX_FREECCB_NUM 160 +#else + #define ARCMSR_MAX_FREECCB_NUM 320 +#endif +#define ARCMSR_DRIVER_VERSION "Driver Version 1.20.00.15 2010/08/05" #define ARCMSR_SCSI_INITIATOR_ID 255 #define ARCMSR_MAX_XFER_SECTORS 512 #define ARCMSR_MAX_XFER_SECTORS_B 4096 @@ -60,7 +64,6 @@ struct device_attribute; #define ARCMSR_MAX_HBB_POSTQUEUE 264 #define ARCMSR_MAX_XFER_LEN 0x26000 /* 152K */ #define ARCMSR_CDB_SG_PAGE_LENGTH 256 -#define SCSI_CMD_ARECA_SPECIFIC 0xE1 #ifndef PCI_DEVICE_ID_ARECA_1880 #define PCI_DEVICE_ID_ARECA_1880 0x1880 #endif diff --git a/drivers/scsi/arcmsr/arcmsr_attr.c b/drivers/scsi/arcmsr/arcmsr_attr.c index a4e04c5..acdae33 100644 --- a/drivers/scsi/arcmsr/arcmsr_attr.c +++ b/drivers/scsi/arcmsr/arcmsr_attr.c @@ -2,7 +2,7 @@ ******************************************************************************* ** O.S : Linux ** FILE NAME : arcmsr_attr.c -** BY : Erich Chen +** BY : Nick Cheng ** Description: attributes exported to sysfs and device host ******************************************************************************* ** Copyright (C) 2002 - 2005, Areca Technology Corporation All rights reserved diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index 1cadcd6..984bd52 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -2,7 +2,7 @@ ******************************************************************************* ** O.S : Linux ** FILE NAME : arcmsr_hba.c -** BY : Erich Chen +** BY : Nick Cheng ** Description: SCSI RAID Device Driver for ** ARECA RAID Host adapter ******************************************************************************* @@ -76,7 +76,7 @@ MODULE_DESCRIPTION("ARECA (ARC11xx/12xx/16xx/1880) SATA/SAS RAID Host Bus Adapte MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(ARCMSR_DRIVER_VERSION); static int sleeptime = 10; -static int retrycount = 30; +static int retrycount = 12; wait_queue_head_t wait_q; static int arcmsr_iop_message_xfer(struct AdapterControlBlock *acb, struct scsi_cmnd *cmd); @@ -187,7 +187,6 @@ int arcmsr_sleep_for_bus_reset(struct scsi_cmnd *cmd) if (isleep > 0) { msleep(isleep*1000); } - printk(KERN_NOTICE "wake-up\n"); return 0; } @@ -921,7 +920,6 @@ static void arcmsr_report_ccb_state(struct AdapterControlBlock *acb, } static void arcmsr_drain_donequeue(struct AdapterControlBlock *acb, struct CommandControlBlock *pCCB, bool error) - { int id, lun; if ((pCCB->acb != acb) || (pCCB->startdone != ARCMSR_CCB_START)) { @@ -948,7 +946,7 @@ static void arcmsr_drain_donequeue(struct AdapterControlBlock *acb, struct Comma , pCCB->startdone , atomic_read(&acb->ccboutstandingcount)); return; - } + } arcmsr_report_ccb_state(acb, pCCB, error); } @@ -981,7 +979,7 @@ static void arcmsr_done4abort_postqueue(struct AdapterControlBlock *acb) case ACB_ADAPTER_TYPE_B: { struct MessageUnit_B *reg = acb->pmuB; /*clear all outbound posted Q*/ - writel(ARCMSR_DOORBELL_INT_CLEAR_PATTERN, ®->iop2drv_doorbell); /* clear doorbell interrupt */ + writel(ARCMSR_DOORBELL_INT_CLEAR_PATTERN, reg->iop2drv_doorbell); /* clear doorbell interrupt */ for (i = 0; i < ARCMSR_MAX_HBB_POSTQUEUE; i++) { if ((flag_ccb = readl(®->done_qbuffer[i])) != 0) { writel(0, ®->done_qbuffer[i]); @@ -1511,7 +1509,6 @@ static void arcmsr_hba_postqueue_isr(struct AdapterControlBlock *acb) arcmsr_drain_donequeue(acb, pCCB, error); } } - static void arcmsr_hbb_postqueue_isr(struct AdapterControlBlock *acb) { uint32_t index; @@ -2106,10 +2103,6 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd, if (atomic_read(&acb->ccboutstandingcount) >= ARCMSR_MAX_OUTSTANDING_CMD) return SCSI_MLQUEUE_HOST_BUSY; - if ((scsicmd == SCSI_CMD_ARECA_SPECIFIC)) { - printk(KERN_NOTICE "Receiveing SCSI_CMD_ARECA_SPECIFIC command..\n"); - return 0; - } ccb = arcmsr_get_freeccb(acb); if (!ccb) return SCSI_MLQUEUE_HOST_BUSY; @@ -2393,6 +2386,7 @@ static int arcmsr_polling_hbb_ccbdone(struct AdapterControlBlock *acb, int index, rtn; bool error; polling_hbb_ccb_retry: + poll_count++; /* clear doorbell interrupt */ writel(ARCMSR_DOORBELL_INT_CLEAR_PATTERN, reg->iop2drv_doorbell); @@ -2663,6 +2657,7 @@ static void arcmsr_request_hba_device_map(struct AdapterControlBlock *acb) { struct MessageUnit_A __iomem *reg = acb->pmuA; if (unlikely(atomic_read(&acb->rq_map_token) == 0) || ((acb->acb_flags & ACB_F_BUS_RESET) != 0 ) || ((acb->acb_flags & ACB_F_ABORT) != 0 )){ + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; } else { acb->fw_flag = FW_NORMAL; @@ -2670,8 +2665,10 @@ static void arcmsr_request_hba_device_map(struct AdapterControlBlock *acb) atomic_set(&acb->rq_map_token, 16); } atomic_set(&acb->ante_token_value, atomic_read(&acb->rq_map_token)); - if (atomic_dec_and_test(&acb->rq_map_token)) + if (atomic_dec_and_test(&acb->rq_map_token)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; + } writel(ARCMSR_INBOUND_MESG0_GET_CONFIG, ®->inbound_msgaddr0); mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); } @@ -2682,15 +2679,18 @@ static void arcmsr_request_hbb_device_map(struct AdapterControlBlock *acb) { struct MessageUnit_B __iomem *reg = acb->pmuB; if (unlikely(atomic_read(&acb->rq_map_token) == 0) || ((acb->acb_flags & ACB_F_BUS_RESET) != 0 ) || ((acb->acb_flags & ACB_F_ABORT) != 0 )){ + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; } else { acb->fw_flag = FW_NORMAL; if (atomic_read(&acb->ante_token_value) == atomic_read(&acb->rq_map_token)) { - atomic_set(&acb->rq_map_token,16); + atomic_set(&acb->rq_map_token, 16); } atomic_set(&acb->ante_token_value, atomic_read(&acb->rq_map_token)); - if(atomic_dec_and_test(&acb->rq_map_token)) + if (atomic_dec_and_test(&acb->rq_map_token)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; + } writel(ARCMSR_MESSAGE_GET_CONFIG, reg->drv2iop_doorbell); mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); } @@ -2701,6 +2701,7 @@ static void arcmsr_request_hbc_device_map(struct AdapterControlBlock *acb) { struct MessageUnit_C __iomem *reg = acb->pmuC; if (unlikely(atomic_read(&acb->rq_map_token) == 0) || ((acb->acb_flags & ACB_F_BUS_RESET) != 0) || ((acb->acb_flags & ACB_F_ABORT) != 0)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; } else { acb->fw_flag = FW_NORMAL; @@ -2708,8 +2709,10 @@ static void arcmsr_request_hbc_device_map(struct AdapterControlBlock *acb) atomic_set(&acb->rq_map_token, 16); } atomic_set(&acb->ante_token_value, atomic_read(&acb->rq_map_token)); - if (atomic_dec_and_test(&acb->rq_map_token)) + if (atomic_dec_and_test(&acb->rq_map_token)) { + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); return; + } writel(ARCMSR_INBOUND_MESG0_GET_CONFIG, ®->inbound_msgaddr0); writel(ARCMSR_HBCMU_DRV2IOP_MESSAGE_CMD_DONE, ®->inbound_doorbell); mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); @@ -2897,6 +2900,8 @@ static uint8_t arcmsr_iop_reset(struct AdapterControlBlock *acb) uint32_t intmask_org; uint8_t rtnval = 0x00; int i = 0; + unsigned long flags; + if (atomic_read(&acb->ccboutstandingcount) != 0) { /* disable all outbound interrupt */ intmask_org = arcmsr_disable_outbound_ints(acb); @@ -2907,7 +2912,12 @@ static uint8_t arcmsr_iop_reset(struct AdapterControlBlock *acb) for (i = 0; i < ARCMSR_MAX_FREECCB_NUM; i++) { ccb = acb->pccb_pool[i]; if (ccb->startdone == ARCMSR_CCB_START) { - arcmsr_ccb_complete(ccb); + scsi_dma_unmap(ccb->pcmd); + ccb->startdone = ARCMSR_CCB_DONE; + ccb->ccb_flags = 0; + spin_lock_irqsave(&acb->ccblist_lock, flags); + list_add_tail(&ccb->list, &acb->ccb_free_list); + spin_unlock_irqrestore(&acb->ccblist_lock, flags); } } atomic_set(&acb->ccboutstandingcount, 0); @@ -2920,8 +2930,7 @@ static uint8_t arcmsr_iop_reset(struct AdapterControlBlock *acb) static int arcmsr_bus_reset(struct scsi_cmnd *cmd) { - struct AdapterControlBlock *acb = - (struct AdapterControlBlock *)cmd->device->host->hostdata; + struct AdapterControlBlock *acb; uint32_t intmask_org, outbound_doorbell; int retry_count = 0; int rtn = FAILED; @@ -2971,31 +2980,16 @@ sleep_again: atomic_set(&acb->rq_map_token, 16); atomic_set(&acb->ante_token_value, 16); acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); acb->acb_flags &= ~ACB_F_BUS_RESET; rtn = SUCCESS; printk(KERN_ERR "arcmsr: scsi bus reset eh returns with success\n"); } else { acb->acb_flags &= ~ACB_F_BUS_RESET; - if (atomic_read(&acb->rq_map_token) == 0) { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); - } else { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); - } + atomic_set(&acb->rq_map_token, 16); + atomic_set(&acb->ante_token_value, 16); + acb->fw_flag = FW_NORMAL; + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); rtn = SUCCESS; } break; @@ -3007,21 +3001,10 @@ sleep_again: rtn = FAILED; } else { acb->acb_flags &= ~ACB_F_BUS_RESET; - if (atomic_read(&acb->rq_map_token) == 0) { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); - } else { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); - } + atomic_set(&acb->rq_map_token, 16); + atomic_set(&acb->ante_token_value, 16); + acb->fw_flag = FW_NORMAL; + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); rtn = SUCCESS; } break; @@ -3067,31 +3050,16 @@ sleep: atomic_set(&acb->rq_map_token, 16); atomic_set(&acb->ante_token_value, 16); acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6 * HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6 * HZ)); acb->acb_flags &= ~ACB_F_BUS_RESET; rtn = SUCCESS; printk(KERN_ERR "arcmsr: scsi bus reset eh returns with success\n"); } else { acb->acb_flags &= ~ACB_F_BUS_RESET; - if (atomic_read(&acb->rq_map_token) == 0) { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - init_timer(&acb->eternal_timer); - acb->eternal_timer.expires = jiffies + msecs_to_jiffies(6*HZ); - acb->eternal_timer.data = (unsigned long) acb; - acb->eternal_timer.function = &arcmsr_request_device_map; - add_timer(&acb->eternal_timer); - } else { - atomic_set(&acb->rq_map_token, 16); - atomic_set(&acb->ante_token_value, 16); - acb->fw_flag = FW_NORMAL; - mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); - } + atomic_set(&acb->rq_map_token, 16); + atomic_set(&acb->ante_token_value, 16); + acb->fw_flag = FW_NORMAL; + mod_timer(&acb->eternal_timer, jiffies + msecs_to_jiffies(6*HZ)); rtn = SUCCESS; } break; diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 5815cbe..9a7aaf5 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -646,6 +646,7 @@ void sas_scsi_recover_host(struct Scsi_Host *shost) spin_lock_irqsave(shost->host_lock, flags); list_splice_init(&shost->eh_cmd_q, &eh_work_q); + shost->host_eh_scheduled = 0; spin_unlock_irqrestore(shost->host_lock, flags); SAS_DPRINTK("Enter %s\n", __func__); diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c index b2a8170..9ead039 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_base.c +++ b/drivers/scsi/mpt2sas/mpt2sas_base.c @@ -2176,9 +2176,9 @@ _base_allocate_memory_pools(struct MPT2SAS_ADAPTER *ioc, int sleep_flag) /* adjust hba_queue_depth, reply_free_queue_depth, * and queue_size */ - ioc->hba_queue_depth -= queue_diff; - ioc->reply_free_queue_depth -= queue_diff; - queue_size -= queue_diff; + ioc->hba_queue_depth -= (queue_diff / 2); + ioc->reply_free_queue_depth -= (queue_diff / 2); + queue_size = facts->MaxReplyDescriptorPostQueueDepth; } ioc->reply_post_queue_depth = queue_size; @@ -3941,6 +3941,8 @@ mpt2sas_base_detach(struct MPT2SAS_ADAPTER *ioc) static void _base_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) { + mpt2sas_scsih_reset_handler(ioc, reset_phase); + mpt2sas_ctl_reset_handler(ioc, reset_phase); switch (reset_phase) { case MPT2_IOC_PRE_RESET: dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s: " @@ -3971,8 +3973,6 @@ _base_reset_handler(struct MPT2SAS_ADAPTER *ioc, int reset_phase) "MPT2_IOC_DONE_RESET\n", ioc->name, __func__)); break; } - mpt2sas_scsih_reset_handler(ioc, reset_phase); - mpt2sas_ctl_reset_handler(ioc, reset_phase); } /** @@ -4026,6 +4026,7 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag, { int r; unsigned long flags; + u8 pe_complete = ioc->wait_for_port_enable_to_complete; dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s: enter\n", ioc->name, __func__)); @@ -4068,6 +4069,14 @@ mpt2sas_base_hard_reset_handler(struct MPT2SAS_ADAPTER *ioc, int sleep_flag, if (r) goto out; _base_reset_handler(ioc, MPT2_IOC_AFTER_RESET); + + /* If this hard reset is called while port enable is active, then + * there is no reason to call make_ioc_operational + */ + if (pe_complete) { + r = -EFAULT; + goto out; + } r = _base_make_ioc_operational(ioc, sleep_flag); if (!r) _base_reset_handler(ioc, MPT2_IOC_DONE_RESET); diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index eda347c..5ded3db 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -819,7 +819,7 @@ _scsih_is_end_device(u32 device_info) } /** - * mptscsih_get_scsi_lookup - returns scmd entry + * _scsih_scsi_lookup_get - returns scmd entry * @ioc: per adapter object * @smid: system request message index * @@ -832,6 +832,28 @@ _scsih_scsi_lookup_get(struct MPT2SAS_ADAPTER *ioc, u16 smid) } /** + * _scsih_scsi_lookup_get_clear - returns scmd entry + * @ioc: per adapter object + * @smid: system request message index + * + * Returns the smid stored scmd pointer. + * Then will derefrence the stored scmd pointer. + */ +static inline struct scsi_cmnd * +_scsih_scsi_lookup_get_clear(struct MPT2SAS_ADAPTER *ioc, u16 smid) +{ + unsigned long flags; + struct scsi_cmnd *scmd; + + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); + scmd = ioc->scsi_lookup[smid - 1].scmd; + ioc->scsi_lookup[smid - 1].scmd = NULL; + spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags); + + return scmd; +} + +/** * _scsih_scsi_lookup_find_by_scmd - scmd lookup * @ioc: per adapter object * @smid: system request message index @@ -2981,9 +3003,6 @@ _scsih_check_topo_delete_events(struct MPT2SAS_ADAPTER *ioc, u16 handle; for (i = 0 ; i < event_data->NumEntries; i++) { - if (event_data->PHY[i].PhyStatus & - MPI2_EVENT_SAS_TOPO_PHYSTATUS_VACANT) - continue; handle = le16_to_cpu(event_data->PHY[i].AttachedDevHandle); if (!handle) continue; @@ -3210,7 +3229,7 @@ _scsih_flush_running_cmds(struct MPT2SAS_ADAPTER *ioc) u16 count = 0; for (smid = 1; smid <= ioc->scsiio_depth; smid++) { - scmd = _scsih_scsi_lookup_get(ioc, smid); + scmd = _scsih_scsi_lookup_get_clear(ioc, smid); if (!scmd) continue; count++; @@ -3804,7 +3823,7 @@ _scsih_io_done(struct MPT2SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply) u32 response_code = 0; mpi_reply = mpt2sas_base_get_reply_virt_addr(ioc, reply); - scmd = _scsih_scsi_lookup_get(ioc, smid); + scmd = _scsih_scsi_lookup_get_clear(ioc, smid); if (scmd == NULL) return 1; @@ -5005,6 +5024,12 @@ _scsih_sas_device_status_change_event(struct MPT2SAS_ADAPTER *ioc, event_data); #endif + /* In MPI Revision K (0xC), the internal device reset complete was + * implemented, so avoid setting tm_busy flag for older firmware. + */ + if ((ioc->facts.HeaderVersion >> 8) < 0xC) + return; + if (event_data->ReasonCode != MPI2_EVENT_SAS_DEV_STAT_RC_INTERNAL_DEVICE_RESET && event_data->ReasonCode != @@ -5099,6 +5124,7 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, struct fw_event_work *fw_event) { struct scsi_cmnd *scmd; + struct scsi_device *sdev; u16 smid, handle; u32 lun; struct MPT2SAS_DEVICE *sas_device_priv_data; @@ -5109,12 +5135,17 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, Mpi2EventDataSasBroadcastPrimitive_t *event_data = fw_event->event_data; #endif u16 ioc_status; + unsigned long flags; + int r; + dewtprintk(ioc, printk(MPT2SAS_INFO_FMT "broadcast primative: " "phy number(%d), width(%d)\n", ioc->name, event_data->PhyNum, event_data->PortWidth)); dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s: enter\n", ioc->name, __func__)); + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); + ioc->broadcast_aen_busy = 0; termination_count = 0; query_count = 0; mpi_reply = ioc->tm_cmds.reply; @@ -5122,7 +5153,8 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, scmd = _scsih_scsi_lookup_get(ioc, smid); if (!scmd) continue; - sas_device_priv_data = scmd->device->hostdata; + sdev = scmd->device; + sas_device_priv_data = sdev->hostdata; if (!sas_device_priv_data || !sas_device_priv_data->sas_target) continue; /* skip hidden raid components */ @@ -5138,6 +5170,7 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, lun = sas_device_priv_data->lun; query_count++; + spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags); mpt2sas_scsih_issue_tm(ioc, handle, 0, 0, lun, MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK, smid, 30, NULL); ioc->tm_cmds.status = MPT2_CMD_NOT_USED; @@ -5147,14 +5180,20 @@ _scsih_sas_broadcast_primative_event(struct MPT2SAS_ADAPTER *ioc, (mpi_reply->ResponseCode == MPI2_SCSITASKMGMT_RSP_TM_SUCCEEDED || mpi_reply->ResponseCode == - MPI2_SCSITASKMGMT_RSP_IO_QUEUED_ON_IOC)) + MPI2_SCSITASKMGMT_RSP_IO_QUEUED_ON_IOC)) { + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); continue; - - mpt2sas_scsih_issue_tm(ioc, handle, 0, 0, lun, - MPI2_SCSITASKMGMT_TASKTYPE_ABRT_TASK_SET, 0, 30, NULL); + } + r = mpt2sas_scsih_issue_tm(ioc, handle, sdev->channel, sdev->id, + sdev->lun, MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30, + scmd); + if (r == FAILED) + sdev_printk(KERN_WARNING, sdev, "task abort: FAILED " + "scmd(%p)\n", scmd); termination_count += le32_to_cpu(mpi_reply->TerminationCount); + spin_lock_irqsave(&ioc->scsi_lookup_lock, flags); } - ioc->broadcast_aen_busy = 0; + spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags); dtmprintk(ioc, printk(MPT2SAS_INFO_FMT "%s - exit, query_count = %d termination_count = %d\n", @@ -6626,6 +6665,7 @@ _scsih_remove(struct pci_dev *pdev) destroy_workqueue(wq); /* release all the volumes */ + _scsih_ir_shutdown(ioc); list_for_each_entry_safe(raid_device, next, &ioc->raid_device_list, list) { if (raid_device->starget) { diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 44578b5..d3e58d7 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -1561,6 +1561,7 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport) { struct Scsi_Host *host = rport_to_shost(rport); fc_port_t *fcport = *(fc_port_t **)rport->dd_data; + unsigned long flags; if (!fcport) return; @@ -1573,10 +1574,10 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rport *rport) * Transport has effectively 'deleted' the rport, clear * all local references. */ - spin_lock_irq(host->host_lock); + spin_lock_irqsave(host->host_lock, flags); fcport->rport = fcport->drport = NULL; *((fc_port_t **)rport->dd_data) = NULL; - spin_unlock_irq(host->host_lock); + spin_unlock_irqrestore(host->host_lock, flags); if (test_bit(ABORT_ISP_ACTIVE, &fcport->vha->dpc_flags)) return; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index f948e1a..d9479c3 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -2505,11 +2505,12 @@ qla2x00_rport_del(void *data) { fc_port_t *fcport = data; struct fc_rport *rport; + unsigned long flags; - spin_lock_irq(fcport->vha->host->host_lock); + spin_lock_irqsave(fcport->vha->host->host_lock, flags); rport = fcport->drport ? fcport->drport: fcport->rport; fcport->drport = NULL; - spin_unlock_irq(fcport->vha->host->host_lock); + spin_unlock_irqrestore(fcport->vha->host->host_lock, flags); if (rport) fc_remote_port_delete(rport); } @@ -2879,6 +2880,7 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) struct fc_rport_identifiers rport_ids; struct fc_rport *rport; struct qla_hw_data *ha = vha->hw; + unsigned long flags; qla2x00_rport_del(fcport); @@ -2893,9 +2895,9 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport) "Unable to allocate fc remote port!\n"); return; } - spin_lock_irq(fcport->vha->host->host_lock); + spin_lock_irqsave(fcport->vha->host->host_lock, flags); *((fc_port_t **)rport->dd_data) = fcport; - spin_unlock_irq(fcport->vha->host->host_lock); + spin_unlock_irqrestore(fcport->vha->host->host_lock, flags); rport->supported_classes = fcport->supported_classes; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index c194c23..f27724d 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -562,7 +562,6 @@ qla2xxx_queuecommand_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *) } if (atomic_read(&fcport->state) != FCS_ONLINE) { if (atomic_read(&fcport->state) == FCS_DEVICE_DEAD || - atomic_read(&fcport->state) == FCS_DEVICE_LOST || atomic_read(&base_vha->loop_state) == LOOP_DEAD) { cmd->result = DID_NO_CONNECT << 16; goto qc24_fail_command; @@ -2513,6 +2512,7 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport, { struct fc_rport *rport; scsi_qla_host_t *base_vha; + unsigned long flags; if (!fcport->rport) return; @@ -2520,9 +2520,9 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport, rport = fcport->rport; if (defer) { base_vha = pci_get_drvdata(vha->hw->pdev); - spin_lock_irq(vha->host->host_lock); + spin_lock_irqsave(vha->host->host_lock, flags); fcport->drport = rport; - spin_unlock_irq(vha->host->host_lock); + spin_unlock_irqrestore(vha->host->host_lock, flags); set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags); qla2xxx_wake_dpc(base_vha); } else @@ -3282,10 +3282,10 @@ qla2x00_do_dpc(void *data) set_user_nice(current, -20); + set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { DEBUG3(printk("qla2x00: DPC handler sleeping\n")); - set_current_state(TASK_INTERRUPTIBLE); schedule(); __set_current_state(TASK_RUNNING); @@ -3454,7 +3454,9 @@ qla2x00_do_dpc(void *data) qla2x00_do_dpc_all_vps(base_vha); ha->dpc_active = 0; + set_current_state(TASK_INTERRUPTIBLE); } /* End of while(1) */ + __set_current_state(TASK_RUNNING); DEBUG(printk("scsi(%ld): DPC handler exiting\n", base_vha->host_no)); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 7b31093..a6b2d72 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1671,7 +1671,7 @@ static int do_device_access(struct scsi_cmnd *scmd, unsigned long long lba, unsigned int num, int write) { int ret; - unsigned int block, rest = 0; + unsigned long long block, rest = 0; int (*func)(struct scsi_cmnd *, unsigned char *, int); func = write ? fetch_to_dev_buffer : fill_from_dev_buffer; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9045c52..fb2bb35 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -443,7 +443,7 @@ static void scsi_run_queue(struct request_queue *q) &sdev->request_queue->queue_flags); if (flagset) queue_flag_set(QUEUE_FLAG_REENTER, sdev->request_queue); - __blk_run_queue(sdev->request_queue); + __blk_run_queue(sdev->request_queue, false); if (flagset) queue_flag_clear(QUEUE_FLAG_REENTER, sdev->request_queue); spin_unlock(sdev->request_queue->queue_lock); diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index 998c01b..5c3ccfc 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -3829,7 +3829,7 @@ fc_bsg_goose_queue(struct fc_rport *rport) !test_bit(QUEUE_FLAG_REENTER, &rport->rqst_q->queue_flags); if (flagset) queue_flag_set(QUEUE_FLAG_REENTER, rport->rqst_q); - __blk_run_queue(rport->rqst_q); + __blk_run_queue(rport->rqst_q, false); if (flagset) queue_flag_clear(QUEUE_FLAG_REENTER, rport->rqst_q); spin_unlock_irqrestore(rport->rqst_q->queue_lock, flags); diff --git a/drivers/spi/pxa2xx_spi_pci.c b/drivers/spi/pxa2xx_spi_pci.c index 351d8a375..19752b0 100644 --- a/drivers/spi/pxa2xx_spi_pci.c +++ b/drivers/spi/pxa2xx_spi_pci.c @@ -7,10 +7,9 @@ #include <linux/of_device.h> #include <linux/spi/pxa2xx_spi.h> -struct awesome_struct { +struct ce4100_info { struct ssp_device ssp; - struct platform_device spi_pdev; - struct pxa2xx_spi_master spi_pdata; + struct platform_device *spi_pdev; }; static DEFINE_MUTEX(ssp_lock); @@ -51,23 +50,15 @@ void pxa_ssp_free(struct ssp_device *ssp) } EXPORT_SYMBOL_GPL(pxa_ssp_free); -static void plat_dev_release(struct device *dev) -{ - struct awesome_struct *as = container_of(dev, - struct awesome_struct, spi_pdev.dev); - - of_device_node_put(&as->spi_pdev.dev); -} - static int __devinit ce4100_spi_probe(struct pci_dev *dev, const struct pci_device_id *ent) { int ret; resource_size_t phys_beg; resource_size_t phys_len; - struct awesome_struct *spi_info; + struct ce4100_info *spi_info; struct platform_device *pdev; - struct pxa2xx_spi_master *spi_pdata; + struct pxa2xx_spi_master spi_pdata; struct ssp_device *ssp; ret = pci_enable_device(dev); @@ -84,33 +75,30 @@ static int __devinit ce4100_spi_probe(struct pci_dev *dev, return ret; } + pdev = platform_device_alloc("pxa2xx-spi", dev->devfn); spi_info = kzalloc(sizeof(*spi_info), GFP_KERNEL); - if (!spi_info) { + if (!pdev || !spi_info ) { ret = -ENOMEM; - goto err_kz; + goto err_nomem; } - ssp = &spi_info->ssp; - pdev = &spi_info->spi_pdev; - spi_pdata = &spi_info->spi_pdata; + memset(&spi_pdata, 0, sizeof(spi_pdata)); + spi_pdata.num_chipselect = dev->devfn; - pdev->name = "pxa2xx-spi"; - pdev->id = dev->devfn; - pdev->dev.parent = &dev->dev; - pdev->dev.platform_data = &spi_info->spi_pdata; + ret = platform_device_add_data(pdev, &spi_pdata, sizeof(spi_pdata)); + if (ret) + goto err_nomem; + pdev->dev.parent = &dev->dev; #ifdef CONFIG_OF pdev->dev.of_node = dev->dev.of_node; #endif - pdev->dev.release = plat_dev_release; - - spi_pdata->num_chipselect = dev->devfn; - + ssp = &spi_info->ssp; ssp->phys_base = pci_resource_start(dev, 0); ssp->mmio_base = ioremap(phys_beg, phys_len); if (!ssp->mmio_base) { dev_err(&pdev->dev, "failed to ioremap() registers\n"); ret = -EIO; - goto err_remap; + goto err_nomem; } ssp->irq = dev->irq; ssp->port_id = pdev->id; @@ -122,7 +110,7 @@ static int __devinit ce4100_spi_probe(struct pci_dev *dev, pci_set_drvdata(dev, spi_info); - ret = platform_device_register(pdev); + ret = platform_device_add(pdev); if (ret) goto err_dev_add; @@ -135,27 +123,21 @@ err_dev_add: mutex_unlock(&ssp_lock); iounmap(ssp->mmio_base); -err_remap: - kfree(spi_info); - -err_kz: +err_nomem: release_mem_region(phys_beg, phys_len); - + platform_device_put(pdev); + kfree(spi_info); return ret; } static void __devexit ce4100_spi_remove(struct pci_dev *dev) { - struct awesome_struct *spi_info; - struct platform_device *pdev; + struct ce4100_info *spi_info; struct ssp_device *ssp; spi_info = pci_get_drvdata(dev); - ssp = &spi_info->ssp; - pdev = &spi_info->spi_pdev; - - platform_device_unregister(pdev); + platform_device_unregister(spi_info->spi_pdev); iounmap(ssp->mmio_base); release_mem_region(pci_resource_start(dev, 0), @@ -171,7 +153,6 @@ static void __devexit ce4100_spi_remove(struct pci_dev *dev) } static struct pci_device_id ce4100_spi_devices[] __devinitdata = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2e6a) }, { }, }; diff --git a/drivers/spi/spi_sh_msiof.c b/drivers/spi/spi_sh_msiof.c index 56f60c8..2c665fcea 100644 --- a/drivers/spi/spi_sh_msiof.c +++ b/drivers/spi/spi_sh_msiof.c @@ -509,9 +509,11 @@ static int sh_msiof_spi_txrx(struct spi_device *spi, struct spi_transfer *t) bytes_done = 0; while (bytes_done < t->len) { + void *rx_buf = t->rx_buf ? t->rx_buf + bytes_done : NULL; + const void *tx_buf = t->tx_buf ? t->tx_buf + bytes_done : NULL; n = sh_msiof_spi_txrx_once(p, tx_fifo, rx_fifo, - t->tx_buf + bytes_done, - t->rx_buf + bytes_done, + tx_buf, + rx_buf, words, bits); if (n < 0) break; diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c index c7345db..f853379 100644 --- a/drivers/ssb/pcmcia.c +++ b/drivers/ssb/pcmcia.c @@ -733,7 +733,7 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus, /* Fetch the vendor specific tuples. */ res = pcmcia_loop_tuple(bus->host_pcmcia, SSB_PCMCIA_CIS, - ssb_pcmcia_do_get_invariants, sprom); + ssb_pcmcia_do_get_invariants, iv); if ((res == 0) || (res == -ENOSPC)) return 0; diff --git a/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsconfig.c b/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsconfig.c index 0e298db..29b8ab4 100644 --- a/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsconfig.c +++ b/drivers/staging/ath6kl/miscdrv/ar3kps/ar3kpsconfig.c @@ -360,8 +360,8 @@ int PSSendOps(void *arg) status = 1; goto complete; } - len = (firmware->size > MAX_BDADDR_FORMAT_LENGTH)? MAX_BDADDR_FORMAT_LENGTH: firmware->size; - memcpy(config_bdaddr, firmware->data,len); + len = min(firmware->size, MAX_BDADDR_FORMAT_LENGTH - 1); + memcpy(config_bdaddr, firmware->data, len); config_bdaddr[len] = '\0'; write_bdaddr(hdev,config_bdaddr,BDADDR_TYPE_STRING); A_RELEASE_FIRMWARE(firmware); diff --git a/drivers/staging/brcm80211/sys/wl_mac80211.c b/drivers/staging/brcm80211/sys/wl_mac80211.c index bdd629d..cd8392b 100644 --- a/drivers/staging/brcm80211/sys/wl_mac80211.c +++ b/drivers/staging/brcm80211/sys/wl_mac80211.c @@ -209,11 +209,8 @@ static void wl_ops_stop(struct ieee80211_hw *hw) struct wl_info *wl = hw->priv; ASSERT(wl); WL_LOCK(wl); - wl_down(wl); ieee80211_stop_queues(hw); WL_UNLOCK(wl); - - return; } static int @@ -246,7 +243,14 @@ wl_ops_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) static void wl_ops_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { - return; + struct wl_info *wl; + + wl = HW_TO_WL(hw); + + /* put driver in down state */ + WL_LOCK(wl); + wl_down(wl); + WL_UNLOCK(wl); } static int @@ -259,9 +263,7 @@ ieee_set_channel(struct ieee80211_hw *hw, struct ieee80211_channel *chan, switch (type) { case NL80211_CHAN_HT20: case NL80211_CHAN_NO_HT: - WL_LOCK(wl); err = wlc_set(wl->wlc, WLC_SET_CHANNEL, chan->hw_value); - WL_UNLOCK(wl); break; case NL80211_CHAN_HT40MINUS: case NL80211_CHAN_HT40PLUS: @@ -281,6 +283,7 @@ static int wl_ops_config(struct ieee80211_hw *hw, u32 changed) int err = 0; int new_int; + WL_LOCK(wl); if (changed & IEEE80211_CONF_CHANGE_LISTEN_INTERVAL) { WL_NONE("%s: Setting listen interval to %d\n", __func__, conf->listen_interval); @@ -337,6 +340,7 @@ static int wl_ops_config(struct ieee80211_hw *hw, u32 changed) } config_out: + WL_UNLOCK(wl); return err; } @@ -455,13 +459,21 @@ wl_ops_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set) static void wl_ops_sw_scan_start(struct ieee80211_hw *hw) { + struct wl_info *wl = hw->priv; WL_NONE("Scan Start\n"); + WL_LOCK(wl); + wlc_scan_start(wl->wlc); + WL_UNLOCK(wl); return; } static void wl_ops_sw_scan_complete(struct ieee80211_hw *hw) { + struct wl_info *wl = hw->priv; WL_NONE("Scan Complete\n"); + WL_LOCK(wl); + wlc_scan_stop(wl->wlc); + WL_UNLOCK(wl); return; } @@ -779,7 +791,7 @@ static struct wl_info *wl_attach(u16 vendor, u16 device, unsigned long regs, wl_found++; return wl; - fail: +fail: wl_free(wl); fail1: return NULL; @@ -1090,7 +1102,6 @@ wl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; } -#ifdef LINUXSTA_PS static int wl_suspend(struct pci_dev *pdev, pm_message_t state) { struct wl_info *wl; @@ -1105,11 +1116,12 @@ static int wl_suspend(struct pci_dev *pdev, pm_message_t state) return -ENODEV; } + /* only need to flag hw is down for proper resume */ WL_LOCK(wl); - wl_down(wl); wl->pub->hw_up = false; WL_UNLOCK(wl); - pci_save_state(pdev, wl->pci_psstate); + + pci_save_state(pdev); pci_disable_device(pdev); return pci_set_power_state(pdev, PCI_D3hot); } @@ -1133,7 +1145,7 @@ static int wl_resume(struct pci_dev *pdev) if (err) return err; - pci_restore_state(pdev, wl->pci_psstate); + pci_restore_state(pdev); err = pci_enable_device(pdev); if (err) @@ -1145,13 +1157,12 @@ static int wl_resume(struct pci_dev *pdev) if ((val & 0x0000ff00) != 0) pci_write_config_dword(pdev, 0x40, val & 0xffff00ff); - WL_LOCK(wl); - err = wl_up(wl); - WL_UNLOCK(wl); - + /* + * done. driver will be put in up state + * in wl_ops_add_interface() call. + */ return err; } -#endif /* LINUXSTA_PS */ static void wl_remove(struct pci_dev *pdev) { @@ -1184,14 +1195,12 @@ static void wl_remove(struct pci_dev *pdev) } static struct pci_driver wl_pci_driver = { - .name = "brcm80211", - .probe = wl_pci_probe, -#ifdef LINUXSTA_PS - .suspend = wl_suspend, - .resume = wl_resume, -#endif /* LINUXSTA_PS */ - .remove = __devexit_p(wl_remove), - .id_table = wl_id_table, + .name = "brcm80211", + .probe = wl_pci_probe, + .suspend = wl_suspend, + .resume = wl_resume, + .remove = __devexit_p(wl_remove), + .id_table = wl_id_table, }; /** diff --git a/drivers/staging/brcm80211/sys/wlc_mac80211.c b/drivers/staging/brcm80211/sys/wlc_mac80211.c index 1d5d01a..e37e805 100644 --- a/drivers/staging/brcm80211/sys/wlc_mac80211.c +++ b/drivers/staging/brcm80211/sys/wlc_mac80211.c @@ -5126,7 +5126,6 @@ wlc_sendpkt_mac80211(struct wlc_info *wlc, struct sk_buff *sdu, fifo = prio2fifo[prio]; ASSERT((uint) skb_headroom(sdu) >= TXOFF); - ASSERT(!(sdu->cloned)); ASSERT(!(sdu->next)); ASSERT(!(sdu->prev)); ASSERT(fifo < NFIFO); @@ -8462,3 +8461,16 @@ static void wlc_txq_free(struct wlc_info *wlc, struct osl_info *osh, kfree(qi); } + +/* + * Flag 'scan in progress' to withold dynamic phy calibration + */ +void wlc_scan_start(struct wlc_info *wlc) +{ + wlc_phy_hold_upd(wlc->band->pi, PHY_HOLD_FOR_SCAN, true); +} + +void wlc_scan_stop(struct wlc_info *wlc) +{ + wlc_phy_hold_upd(wlc->band->pi, PHY_HOLD_FOR_SCAN, false); +} diff --git a/drivers/staging/brcm80211/sys/wlc_pub.h b/drivers/staging/brcm80211/sys/wlc_pub.h index 146a690..aff4130 100644 --- a/drivers/staging/brcm80211/sys/wlc_pub.h +++ b/drivers/staging/brcm80211/sys/wlc_pub.h @@ -570,6 +570,8 @@ extern void wlc_enable_mac(struct wlc_info *wlc); extern u16 wlc_rate_shm_offset(struct wlc_info *wlc, u8 rate); extern u32 wlc_get_rspec_history(struct wlc_bsscfg *cfg); extern u32 wlc_get_current_highest_rate(struct wlc_bsscfg *cfg); +extern void wlc_scan_start(struct wlc_info *wlc); +extern void wlc_scan_stop(struct wlc_info *wlc); static inline int wlc_iovar_getuint(struct wlc_info *wlc, const char *name, uint *arg) diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig index aad4732..1502d80 100644 --- a/drivers/staging/comedi/Kconfig +++ b/drivers/staging/comedi/Kconfig @@ -439,6 +439,7 @@ config COMEDI_NI_AT_AO config COMEDI_NI_ATMIO tristate "NI AT-MIO E series ISA-PNP card support" depends on ISAPNP && COMEDI_NI_TIO && COMEDI_NI_COMMON + select COMEDI_8255 default N ---help--- Enable support for National Instruments AT-MIO E series cards @@ -1040,6 +1041,8 @@ config COMEDI_NI_PCIDIO config COMEDI_NI_PCIMIO tristate "NI PCI-MIO-E series and M series support" depends on COMEDI_NI_TIO && COMEDI_NI_COMMON + select COMEDI_8255 + select COMEDI_FC default N ---help--- Enable support for National Instruments PCI-MIO-E series and M series @@ -1164,6 +1167,7 @@ config COMEDI_NI_LABPC_CS config COMEDI_NI_MIO_CS tristate "NI DAQCard E series PCMCIA support" depends on COMEDI_NI_TIO && COMEDI_NI_COMMON + select COMEDI_8255 select COMEDI_FC default N ---help--- @@ -1268,7 +1272,6 @@ config COMEDI_MITE config COMEDI_NI_TIO tristate "NI general purpose counter support" depends on COMEDI_MITE - select COMEDI_8255 default N ---help--- Enable support for National Instruments general purpose counters. diff --git a/drivers/staging/comedi/drivers/mite.c b/drivers/staging/comedi/drivers/mite.c index cd25b24..fd274e9 100644 --- a/drivers/staging/comedi/drivers/mite.c +++ b/drivers/staging/comedi/drivers/mite.c @@ -61,8 +61,6 @@ #define PCI_DAQ_SIZE 4096 #define PCI_DAQ_SIZE_660X 8192 -MODULE_LICENSE("GPL"); - struct mite_struct *mite_devices; EXPORT_SYMBOL(mite_devices); diff --git a/drivers/staging/comedi/drivers/ni_6527.c b/drivers/staging/comedi/drivers/ni_6527.c index 14e716e..54741c9 100644 --- a/drivers/staging/comedi/drivers/ni_6527.c +++ b/drivers/staging/comedi/drivers/ni_6527.c @@ -527,3 +527,7 @@ static void __exit driver_ni6527_cleanup_module(void) module_init(driver_ni6527_init_module); module_exit(driver_ni6527_cleanup_module); + +MODULE_AUTHOR("Comedi http://www.comedi.org"); +MODULE_DESCRIPTION("Comedi low-level driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/comedi/drivers/ni_65xx.c b/drivers/staging/comedi/drivers/ni_65xx.c index 8b8e2aa..403fc09 100644 --- a/drivers/staging/comedi/drivers/ni_65xx.c +++ b/drivers/staging/comedi/drivers/ni_65xx.c @@ -871,3 +871,7 @@ static void __exit driver_ni_65xx_cleanup_module(void) module_init(driver_ni_65xx_init_module); module_exit(driver_ni_65xx_cleanup_module); + +MODULE_AUTHOR("Comedi http://www.comedi.org"); +MODULE_DESCRIPTION("Comedi low-level driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/comedi/drivers/ni_660x.c b/drivers/staging/comedi/drivers/ni_660x.c index 6612b08..ca2aeaa 100644 --- a/drivers/staging/comedi/drivers/ni_660x.c +++ b/drivers/staging/comedi/drivers/ni_660x.c @@ -1421,3 +1421,7 @@ static int ni_660x_dio_insn_config(struct comedi_device *dev, }; return 0; } + +MODULE_AUTHOR("Comedi http://www.comedi.org"); +MODULE_DESCRIPTION("Comedi low-level driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/comedi/drivers/ni_670x.c b/drivers/staging/comedi/drivers/ni_670x.c index e9f034e..d8d91f9 100644 --- a/drivers/staging/comedi/drivers/ni_670x.c +++ b/drivers/staging/comedi/drivers/ni_670x.c @@ -384,3 +384,7 @@ static int ni_670x_find_device(struct comedi_device *dev, int bus, int slot) mite_list_devices(); return -EIO; } + +MODULE_AUTHOR("Comedi http://www.comedi.org"); +MODULE_DESCRIPTION("Comedi low-level driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/comedi/drivers/ni_labpc.c b/drivers/staging/comedi/drivers/ni_labpc.c index 4d1868d..0728c3c 100644 --- a/drivers/staging/comedi/drivers/ni_labpc.c +++ b/drivers/staging/comedi/drivers/ni_labpc.c @@ -575,7 +575,8 @@ int labpc_common_attach(struct comedi_device *dev, unsigned long iobase, /* grab our IRQ */ if (irq) { isr_flags = 0; - if (thisboard->bustype == pci_bustype) + if (thisboard->bustype == pci_bustype + || thisboard->bustype == pcmcia_bustype) isr_flags |= IRQF_SHARED; if (request_irq(irq, labpc_interrupt, isr_flags, driver_labpc.driver_name, dev)) { diff --git a/drivers/staging/comedi/drivers/ni_pcidio.c b/drivers/staging/comedi/drivers/ni_pcidio.c index 84a15c3..005d2fe 100644 --- a/drivers/staging/comedi/drivers/ni_pcidio.c +++ b/drivers/staging/comedi/drivers/ni_pcidio.c @@ -1354,3 +1354,7 @@ static void __exit driver_pcidio_cleanup_module(void) module_init(driver_pcidio_init_module); module_exit(driver_pcidio_cleanup_module); + +MODULE_AUTHOR("Comedi http://www.comedi.org"); +MODULE_DESCRIPTION("Comedi low-level driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/comedi/drivers/ni_pcimio.c b/drivers/staging/comedi/drivers/ni_pcimio.c index 23a3812..9148abd 100644 --- a/drivers/staging/comedi/drivers/ni_pcimio.c +++ b/drivers/staging/comedi/drivers/ni_pcimio.c @@ -1853,3 +1853,7 @@ static int pcimio_dio_change(struct comedi_device *dev, return 0; } + +MODULE_AUTHOR("Comedi http://www.comedi.org"); +MODULE_DESCRIPTION("Comedi low-level driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/hv/blkvsc_drv.c b/drivers/staging/hv/blkvsc_drv.c index b3d05fc..4fb8094 100644 --- a/drivers/staging/hv/blkvsc_drv.c +++ b/drivers/staging/hv/blkvsc_drv.c @@ -368,6 +368,7 @@ static int blkvsc_probe(struct device *device) blkdev->gd->first_minor = 0; blkdev->gd->fops = &block_ops; blkdev->gd->private_data = blkdev; + blkdev->gd->driverfs_dev = &(blkdev->device_ctx->device); sprintf(blkdev->gd->disk_name, "hd%c", 'a' + devnum); blkvsc_do_inquiry(blkdev); diff --git a/drivers/staging/hv/netvsc.c b/drivers/staging/hv/netvsc.c index df9cd13..0edbe74 100644 --- a/drivers/staging/hv/netvsc.c +++ b/drivers/staging/hv/netvsc.c @@ -1279,7 +1279,7 @@ static void netvsc_channel_cb(void *context) /* ASSERT(device); */ packet = kzalloc(NETVSC_PACKET_SIZE * sizeof(unsigned char), - GFP_KERNEL); + GFP_ATOMIC); if (!packet) return; buffer = packet; diff --git a/drivers/staging/hv/netvsc_drv.c b/drivers/staging/hv/netvsc_drv.c index 0147b40..b41c964 100644 --- a/drivers/staging/hv/netvsc_drv.c +++ b/drivers/staging/hv/netvsc_drv.c @@ -236,6 +236,7 @@ static void netvsc_linkstatus_callback(struct hv_device *device_obj, if (status == 1) { netif_carrier_on(net); netif_wake_queue(net); + netif_notify_peers(net); } else { netif_carrier_off(net); netif_stop_queue(net); @@ -358,7 +359,6 @@ static int netvsc_probe(struct device *device) /* Set initial state */ netif_carrier_off(net); - netif_stop_queue(net); net_device_ctx = netdev_priv(net); net_device_ctx->device_ctx = device_ctx; diff --git a/drivers/staging/iio/adc/ad7476_core.c b/drivers/staging/iio/adc/ad7476_core.c index deb68c8..b8b54da 100644 --- a/drivers/staging/iio/adc/ad7476_core.c +++ b/drivers/staging/iio/adc/ad7476_core.c @@ -68,7 +68,7 @@ static ssize_t ad7476_show_scale(struct device *dev, /* Corresponds to Vref / 2^(bits) */ unsigned int scale_uv = (st->int_vref_mv * 1000) >> st->chip_info->bits; - return sprintf(buf, "%d.%d\n", scale_uv / 1000, scale_uv % 1000); + return sprintf(buf, "%d.%03d\n", scale_uv / 1000, scale_uv % 1000); } static IIO_DEVICE_ATTR(in_scale, S_IRUGO, ad7476_show_scale, NULL, 0); diff --git a/drivers/staging/iio/adc/ad7887_core.c b/drivers/staging/iio/adc/ad7887_core.c index 6859089..5d85efa 100644 --- a/drivers/staging/iio/adc/ad7887_core.c +++ b/drivers/staging/iio/adc/ad7887_core.c @@ -68,7 +68,7 @@ static ssize_t ad7887_show_scale(struct device *dev, /* Corresponds to Vref / 2^(bits) */ unsigned int scale_uv = (st->int_vref_mv * 1000) >> st->chip_info->bits; - return sprintf(buf, "%d.%d\n", scale_uv / 1000, scale_uv % 1000); + return sprintf(buf, "%d.%03d\n", scale_uv / 1000, scale_uv % 1000); } static IIO_DEVICE_ATTR(in_scale, S_IRUGO, ad7887_show_scale, NULL, 0); diff --git a/drivers/staging/iio/adc/ad799x_core.c b/drivers/staging/iio/adc/ad799x_core.c index 6309d52..89ccf37 100644 --- a/drivers/staging/iio/adc/ad799x_core.c +++ b/drivers/staging/iio/adc/ad799x_core.c @@ -432,7 +432,7 @@ static ssize_t ad799x_show_scale(struct device *dev, /* Corresponds to Vref / 2^(bits) */ unsigned int scale_uv = (st->int_vref_mv * 1000) >> st->chip_info->bits; - return sprintf(buf, "%d.%d\n", scale_uv / 1000, scale_uv % 1000); + return sprintf(buf, "%d.%03d\n", scale_uv / 1000, scale_uv % 1000); } static IIO_DEVICE_ATTR(in_scale, S_IRUGO, ad799x_show_scale, NULL, 0); diff --git a/drivers/staging/iio/dac/ad5446.c b/drivers/staging/iio/dac/ad5446.c index e3387cd..0f87eca 100644 --- a/drivers/staging/iio/dac/ad5446.c +++ b/drivers/staging/iio/dac/ad5446.c @@ -87,7 +87,7 @@ static ssize_t ad5446_show_scale(struct device *dev, /* Corresponds to Vref / 2^(bits) */ unsigned int scale_uv = (st->vref_mv * 1000) >> st->chip_info->bits; - return sprintf(buf, "%d.%d\n", scale_uv / 1000, scale_uv % 1000); + return sprintf(buf, "%d.%03d\n", scale_uv / 1000, scale_uv % 1000); } static IIO_DEVICE_ATTR(out_scale, S_IRUGO, ad5446_show_scale, NULL, 0); diff --git a/drivers/staging/intel_sst/intelmid_v2_control.c b/drivers/staging/intel_sst/intelmid_v2_control.c index e38e89d..e2f6d6a 100644 --- a/drivers/staging/intel_sst/intelmid_v2_control.c +++ b/drivers/staging/intel_sst/intelmid_v2_control.c @@ -874,7 +874,10 @@ static int nc_set_selected_input_dev(u8 value) sc_access[3].reg_addr = 0x109; sc_access[3].mask = MASK6; sc_access[3].value = 0x00; - num_val = 4; + sc_access[4].reg_addr = 0x104; + sc_access[4].value = 0x3C; + sc_access[4].mask = 0xff; + num_val = 5; break; default: return -EINVAL; diff --git a/drivers/staging/lirc/lirc_zilog.c b/drivers/staging/lirc/lirc_zilog.c index 3fe5f41..0aad0d7 100644 --- a/drivers/staging/lirc/lirc_zilog.c +++ b/drivers/staging/lirc/lirc_zilog.c @@ -495,7 +495,7 @@ static int send_data_block(struct IR_tx *tx, unsigned char *data_block) /* send boot data to the IR TX device */ static int send_boot_data(struct IR_tx *tx) { - int ret; + int ret, i; unsigned char buf[4]; /* send the boot block */ @@ -503,7 +503,7 @@ static int send_boot_data(struct IR_tx *tx) if (ret != 0) return ret; - /* kick it off? */ + /* Hit the go button to activate the new boot data */ buf[0] = 0x00; buf[1] = 0x20; ret = i2c_master_send(tx->c, buf, 2); @@ -511,7 +511,19 @@ static int send_boot_data(struct IR_tx *tx) zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; } - ret = i2c_master_send(tx->c, buf, 1); + + /* + * Wait for zilog to settle after hitting go post boot block upload. + * Without this delay, the HD-PVR and HVR-1950 both return an -EIO + * upon attempting to get firmware revision, and tx probe thus fails. + */ + for (i = 0; i < 10; i++) { + ret = i2c_master_send(tx->c, buf, 1); + if (ret == 1) + break; + udelay(100); + } + if (ret != 1) { zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; @@ -523,8 +535,8 @@ static int send_boot_data(struct IR_tx *tx) zilog_error("i2c_master_recv failed with %d\n", ret); return 0; } - if (buf[0] != 0x80) { - zilog_error("unexpected IR TX response: %02x\n", buf[0]); + if ((buf[0] != 0x80) && (buf[0] != 0xa0)) { + zilog_error("unexpected IR TX init response: %02x\n", buf[0]); return 0; } zilog_notify("Zilog/Hauppauge IR blaster firmware version " @@ -827,7 +839,15 @@ static int send_code(struct IR_tx *tx, unsigned int code, unsigned int key) zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; } - ret = i2c_master_send(tx->c, buf, 1); + + /* Give the z8 a moment to process data block */ + for (i = 0; i < 10; i++) { + ret = i2c_master_send(tx->c, buf, 1); + if (ret == 1) + break; + udelay(100); + } + if (ret != 1) { zilog_error("i2c_master_send failed with %d\n", ret); return ret < 0 ? ret : -EFAULT; diff --git a/drivers/staging/rt2860/rt_main_dev.c b/drivers/staging/rt2860/rt_main_dev.c index 701561d..236dd36 100644 --- a/drivers/staging/rt2860/rt_main_dev.c +++ b/drivers/staging/rt2860/rt_main_dev.c @@ -484,8 +484,6 @@ struct net_device *RtmpPhyNetDevInit(struct rt_rtmp_adapter *pAd, net_dev->ml_priv = (void *)pAd; pAd->net_dev = net_dev; - netif_stop_queue(net_dev); - return net_dev; } diff --git a/drivers/staging/rt2860/usb_main_dev.c b/drivers/staging/rt2860/usb_main_dev.c index ee68d51..322bf49 100644 --- a/drivers/staging/rt2860/usb_main_dev.c +++ b/drivers/staging/rt2860/usb_main_dev.c @@ -106,6 +106,7 @@ struct usb_device_id rtusb_usb_id[] = { {USB_DEVICE(0x0411, 0x016f)}, /* MelCo.,Inc. WLI-UC-G301N */ {USB_DEVICE(0x1737, 0x0070)}, /* Linksys WUSB100 */ {USB_DEVICE(0x1737, 0x0071)}, /* Linksys WUSB600N */ + {USB_DEVICE(0x1737, 0x0078)}, /* Linksys WUSB100v2 */ {USB_DEVICE(0x0411, 0x00e8)}, /* Buffalo WLI-UC-G300N */ {USB_DEVICE(0x050d, 0x815c)}, /* Belkin F5D8053 */ {USB_DEVICE(0x100D, 0x9031)}, /* Motorola 2770 */ diff --git a/drivers/staging/rtl8712/hal_init.c b/drivers/staging/rtl8712/hal_init.c index 32088a6..84be383 100644 --- a/drivers/staging/rtl8712/hal_init.c +++ b/drivers/staging/rtl8712/hal_init.c @@ -128,12 +128,13 @@ static u8 rtl8712_dl_fw(struct _adapter *padapter) u8 *ptmpchar = NULL, *ppayload, *ptr; struct tx_desc *ptx_desc; u32 txdscp_sz = sizeof(struct tx_desc); + u8 ret = _FAIL; ulfilelength = rtl871x_open_fw(padapter, &phfwfile_hdl, &pmappedfw); if (pmappedfw && (ulfilelength > 0)) { update_fwhdr(&fwhdr, pmappedfw); if (chk_fwhdr(&fwhdr, ulfilelength) == _FAIL) - goto exit_fail; + goto firmware_rel; fill_fwpriv(padapter, &fwhdr.fwpriv); /* firmware check ok */ maxlen = (fwhdr.img_IMEM_size > fwhdr.img_SRAM_size) ? @@ -141,7 +142,7 @@ static u8 rtl8712_dl_fw(struct _adapter *padapter) maxlen += txdscp_sz; ptmpchar = _malloc(maxlen + FWBUFF_ALIGN_SZ); if (ptmpchar == NULL) - return _FAIL; + goto firmware_rel; ptx_desc = (struct tx_desc *)(ptmpchar + FWBUFF_ALIGN_SZ - ((addr_t)(ptmpchar) & (FWBUFF_ALIGN_SZ - 1))); @@ -273,11 +274,13 @@ static u8 rtl8712_dl_fw(struct _adapter *padapter) goto exit_fail; } else goto exit_fail; - return _SUCCESS; + ret = _SUCCESS; exit_fail: kfree(ptmpchar); - return _FAIL; +firmware_rel: + release_firmware((struct firmware *)phfwfile_hdl); + return ret; } uint rtl8712_hal_init(struct _adapter *padapter) diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c index a692ee8..21ce2af 100644 --- a/drivers/staging/rtl8712/usb_intf.c +++ b/drivers/staging/rtl8712/usb_intf.c @@ -47,54 +47,123 @@ static int r871xu_drv_init(struct usb_interface *pusb_intf, static void r871xu_dev_remove(struct usb_interface *pusb_intf); static struct usb_device_id rtl871x_usb_id_tbl[] = { - /*92SU - * Realtek */ - {USB_DEVICE(0x0bda, 0x8171)}, - {USB_DEVICE(0x0bda, 0x8172)}, + +/* RTL8188SU */ + /* Realtek */ + {USB_DEVICE(0x0BDA, 0x8171)}, {USB_DEVICE(0x0bda, 0x8173)}, - {USB_DEVICE(0x0bda, 0x8174)}, {USB_DEVICE(0x0bda, 0x8712)}, {USB_DEVICE(0x0bda, 0x8713)}, {USB_DEVICE(0x0bda, 0xC512)}, - /* Abocom */ + /* Abocom */ {USB_DEVICE(0x07B8, 0x8188)}, + /* ASUS */ + {USB_DEVICE(0x0B05, 0x1786)}, + {USB_DEVICE(0x0B05, 0x1791)}, /* 11n mode disable */ + /* Belkin */ + {USB_DEVICE(0x050D, 0x945A)}, /* Corega */ - {USB_DEVICE(0x07aa, 0x0047)}, - /* Dlink */ - {USB_DEVICE(0x07d1, 0x3303)}, - {USB_DEVICE(0x07d1, 0x3302)}, - {USB_DEVICE(0x07d1, 0x3300)}, - /* Dlink for Skyworth */ - {USB_DEVICE(0x14b2, 0x3300)}, - {USB_DEVICE(0x14b2, 0x3301)}, - {USB_DEVICE(0x14b2, 0x3302)}, + {USB_DEVICE(0x07AA, 0x0047)}, + /* D-Link */ + {USB_DEVICE(0x2001, 0x3306)}, + {USB_DEVICE(0x07D1, 0x3306)}, /* 11n mode disable */ + /* Edimax */ + {USB_DEVICE(0x7392, 0x7611)}, /* EnGenius */ {USB_DEVICE(0x1740, 0x9603)}, - {USB_DEVICE(0x1740, 0x9605)}, + /* Hawking */ + {USB_DEVICE(0x0E66, 0x0016)}, + /* Hercules */ + {USB_DEVICE(0x06F8, 0xE034)}, + {USB_DEVICE(0x06F8, 0xE032)}, + /* Logitec */ + {USB_DEVICE(0x0789, 0x0167)}, + /* PCI */ + {USB_DEVICE(0x2019, 0xAB28)}, + {USB_DEVICE(0x2019, 0xED16)}, + /* Sitecom */ + {USB_DEVICE(0x0DF6, 0x0057)}, + {USB_DEVICE(0x0DF6, 0x0045)}, + {USB_DEVICE(0x0DF6, 0x0059)}, /* 11n mode disable */ + {USB_DEVICE(0x0DF6, 0x004B)}, + {USB_DEVICE(0x0DF6, 0x0063)}, + /* Sweex */ + {USB_DEVICE(0x177F, 0x0154)}, + /* Thinkware */ + {USB_DEVICE(0x0BDA, 0x5077)}, + /* Toshiba */ + {USB_DEVICE(0x1690, 0x0752)}, + /* - */ + {USB_DEVICE(0x20F4, 0x646B)}, + {USB_DEVICE(0x083A, 0xC512)}, + +/* RTL8191SU */ + /* Realtek */ + {USB_DEVICE(0x0BDA, 0x8172)}, + /* Amigo */ + {USB_DEVICE(0x0EB0, 0x9061)}, + /* ASUS/EKB */ + {USB_DEVICE(0x0BDA, 0x8172)}, + {USB_DEVICE(0x13D3, 0x3323)}, + {USB_DEVICE(0x13D3, 0x3311)}, /* 11n mode disable */ + {USB_DEVICE(0x13D3, 0x3342)}, + /* ASUS/EKBLenovo */ + {USB_DEVICE(0x13D3, 0x3333)}, + {USB_DEVICE(0x13D3, 0x3334)}, + {USB_DEVICE(0x13D3, 0x3335)}, /* 11n mode disable */ + {USB_DEVICE(0x13D3, 0x3336)}, /* 11n mode disable */ + /* ASUS/Media BOX */ + {USB_DEVICE(0x13D3, 0x3309)}, /* Belkin */ - {USB_DEVICE(0x050d, 0x815F)}, - {USB_DEVICE(0x050d, 0x945A)}, - {USB_DEVICE(0x050d, 0x845A)}, - /* Guillemot */ - {USB_DEVICE(0x06f8, 0xe031)}, + {USB_DEVICE(0x050D, 0x815F)}, + /* D-Link */ + {USB_DEVICE(0x07D1, 0x3302)}, + {USB_DEVICE(0x07D1, 0x3300)}, + {USB_DEVICE(0x07D1, 0x3303)}, /* Edimax */ - {USB_DEVICE(0x7392, 0x7611)}, {USB_DEVICE(0x7392, 0x7612)}, - {USB_DEVICE(0x7392, 0x7622)}, - /* Sitecom */ - {USB_DEVICE(0x0DF6, 0x0045)}, + /* EnGenius */ + {USB_DEVICE(0x1740, 0x9605)}, + /* Guillemot */ + {USB_DEVICE(0x06F8, 0xE031)}, /* Hawking */ {USB_DEVICE(0x0E66, 0x0015)}, - {USB_DEVICE(0x0E66, 0x0016)}, - {USB_DEVICE(0x0b05, 0x1786)}, - {USB_DEVICE(0x0b05, 0x1791)}, /* 11n mode disable */ - + /* Mediao */ {USB_DEVICE(0x13D3, 0x3306)}, - {USB_DEVICE(0x13D3, 0x3309)}, + /* PCI */ + {USB_DEVICE(0x2019, 0xED18)}, + {USB_DEVICE(0x2019, 0x4901)}, + /* Sitecom */ + {USB_DEVICE(0x0DF6, 0x0058)}, + {USB_DEVICE(0x0DF6, 0x0049)}, + {USB_DEVICE(0x0DF6, 0x004C)}, + {USB_DEVICE(0x0DF6, 0x0064)}, + /* Skyworth */ + {USB_DEVICE(0x14b2, 0x3300)}, + {USB_DEVICE(0x14b2, 0x3301)}, + {USB_DEVICE(0x14B2, 0x3302)}, + /* - */ + {USB_DEVICE(0x04F2, 0xAFF2)}, + {USB_DEVICE(0x04F2, 0xAFF5)}, + {USB_DEVICE(0x04F2, 0xAFF6)}, + {USB_DEVICE(0x13D3, 0x3339)}, + {USB_DEVICE(0x13D3, 0x3340)}, /* 11n mode disable */ + {USB_DEVICE(0x13D3, 0x3341)}, /* 11n mode disable */ {USB_DEVICE(0x13D3, 0x3310)}, - {USB_DEVICE(0x13D3, 0x3311)}, /* 11n mode disable */ {USB_DEVICE(0x13D3, 0x3325)}, - {USB_DEVICE(0x083A, 0xC512)}, + +/* RTL8192SU */ + /* Realtek */ + {USB_DEVICE(0x0BDA, 0x8174)}, + {USB_DEVICE(0x0BDA, 0x8174)}, + /* Belkin */ + {USB_DEVICE(0x050D, 0x845A)}, + /* Corega */ + {USB_DEVICE(0x07AA, 0x0051)}, + /* Edimax */ + {USB_DEVICE(0x7392, 0x7622)}, + /* NEC */ + {USB_DEVICE(0x0409, 0x02B6)}, {} }; @@ -103,8 +172,20 @@ MODULE_DEVICE_TABLE(usb, rtl871x_usb_id_tbl); static struct specific_device_id specific_device_id_tbl[] = { {.idVendor = 0x0b05, .idProduct = 0x1791, .flags = SPEC_DEV_ID_DISABLE_HT}, + {.idVendor = 0x0df6, .idProduct = 0x0059, + .flags = SPEC_DEV_ID_DISABLE_HT}, + {.idVendor = 0x13d3, .idProduct = 0x3306, + .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13D3, .idProduct = 0x3311, .flags = SPEC_DEV_ID_DISABLE_HT}, + {.idVendor = 0x13d3, .idProduct = 0x3335, + .flags = SPEC_DEV_ID_DISABLE_HT}, + {.idVendor = 0x13d3, .idProduct = 0x3336, + .flags = SPEC_DEV_ID_DISABLE_HT}, + {.idVendor = 0x13d3, .idProduct = 0x3340, + .flags = SPEC_DEV_ID_DISABLE_HT}, + {.idVendor = 0x13d3, .idProduct = 0x3341, + .flags = SPEC_DEV_ID_DISABLE_HT}, {} }; diff --git a/drivers/staging/speakup/kobjects.c b/drivers/staging/speakup/kobjects.c index 408bb9b..07a7f54 100644 --- a/drivers/staging/speakup/kobjects.c +++ b/drivers/staging/speakup/kobjects.c @@ -332,7 +332,7 @@ static ssize_t silent_store(struct kobject *kobj, struct kobj_attribute *attr, unsigned long flags; len = strlen(buf); - if (len > 0 || len < 3) { + if (len > 0 && len < 3) { ch = buf[0]; if (ch == '\n') ch = '0'; diff --git a/drivers/staging/ste_rmi4/synaptics_i2c_rmi4.c b/drivers/staging/ste_rmi4/synaptics_i2c_rmi4.c index e8f047e..80183a7 100644 --- a/drivers/staging/ste_rmi4/synaptics_i2c_rmi4.c +++ b/drivers/staging/ste_rmi4/synaptics_i2c_rmi4.c @@ -986,12 +986,6 @@ static int __devinit synaptics_rmi4_probe input_set_abs_params(rmi4_data->input_dev, ABS_MT_TOUCH_MAJOR, 0, MAX_TOUCH_MAJOR, 0, 0); - retval = input_register_device(rmi4_data->input_dev); - if (retval) { - dev_err(&client->dev, "%s:input register failed\n", __func__); - goto err_input_register; - } - /* Clear interrupts */ synaptics_rmi4_i2c_block_read(rmi4_data, rmi4_data->fn01_data_base_addr + 1, intr_status, @@ -1003,15 +997,20 @@ static int __devinit synaptics_rmi4_probe if (retval) { dev_err(&client->dev, "%s:Unable to get attn irq %d\n", __func__, platformdata->irq_number); - goto err_request_irq; + goto err_unset_clientdata; + } + + retval = input_register_device(rmi4_data->input_dev); + if (retval) { + dev_err(&client->dev, "%s:input register failed\n", __func__); + goto err_free_irq; } return retval; -err_request_irq: +err_free_irq: free_irq(platformdata->irq_number, rmi4_data); - input_unregister_device(rmi4_data->input_dev); -err_input_register: +err_unset_clientdata: i2c_set_clientdata(client, NULL); err_query_dev: if (platformdata->regulator_en) { diff --git a/drivers/staging/tidspbridge/core/io_sm.c b/drivers/staging/tidspbridge/core/io_sm.c index 5718645..27e0aa8 100644 --- a/drivers/staging/tidspbridge/core/io_sm.c +++ b/drivers/staging/tidspbridge/core/io_sm.c @@ -949,7 +949,7 @@ func_end: * Calls the Bridge's CHNL_ISR to determine if this interrupt is ours, then * schedules a DPC to dispatch I/O. */ -void io_mbox_msg(u32 msg) +int io_mbox_msg(struct notifier_block *self, unsigned long len, void *msg) { struct io_mgr *pio_mgr; struct dev_object *dev_obj; @@ -959,9 +959,9 @@ void io_mbox_msg(u32 msg) dev_get_io_mgr(dev_obj, &pio_mgr); if (!pio_mgr) - return; + return NOTIFY_BAD; - pio_mgr->intr_val = (u16)msg; + pio_mgr->intr_val = (u16)((u32)msg); if (pio_mgr->intr_val & MBX_PM_CLASS) io_dispatch_pm(pio_mgr); @@ -973,7 +973,7 @@ void io_mbox_msg(u32 msg) spin_unlock_irqrestore(&pio_mgr->dpc_lock, flags); tasklet_schedule(&pio_mgr->dpc_tasklet); } - return; + return NOTIFY_OK; } /* diff --git a/drivers/staging/tidspbridge/core/tiomap3430.c b/drivers/staging/tidspbridge/core/tiomap3430.c index a3b0a18..a3f69f6 100644 --- a/drivers/staging/tidspbridge/core/tiomap3430.c +++ b/drivers/staging/tidspbridge/core/tiomap3430.c @@ -223,6 +223,10 @@ static struct bridge_drv_interface drv_interface_fxns = { bridge_msg_set_queue_id, }; +static struct notifier_block dsp_mbox_notifier = { + .notifier_call = io_mbox_msg, +}; + static inline void flush_all(struct bridge_dev_context *dev_context) { if (dev_context->dw_brd_state == BRD_DSP_HIBERNATION || @@ -553,7 +557,7 @@ static int bridge_brd_start(struct bridge_dev_context *dev_ctxt, * Enable Mailbox events and also drain any pending * stale messages. */ - dev_context->mbox = omap_mbox_get("dsp"); + dev_context->mbox = omap_mbox_get("dsp", &dsp_mbox_notifier); if (IS_ERR(dev_context->mbox)) { dev_context->mbox = NULL; pr_err("%s: Failed to get dsp mailbox handle\n", @@ -563,8 +567,6 @@ static int bridge_brd_start(struct bridge_dev_context *dev_ctxt, } if (!status) { - dev_context->mbox->rxq->callback = (int (*)(void *))io_mbox_msg; - /*PM_IVA2GRPSEL_PER = 0xC0;*/ temp = readl(resources->dw_per_pm_base + 0xA8); temp = (temp & 0xFFFFFF30) | 0xC0; @@ -685,7 +687,7 @@ static int bridge_brd_stop(struct bridge_dev_context *dev_ctxt) /* Disable the mailbox interrupts */ if (dev_context->mbox) { omap_mbox_disable_irq(dev_context->mbox, IRQ_RX); - omap_mbox_put(dev_context->mbox); + omap_mbox_put(dev_context->mbox, &dsp_mbox_notifier); dev_context->mbox = NULL; } /* Reset IVA2 clocks*/ @@ -786,10 +788,7 @@ static int bridge_dev_create(struct bridge_dev_context pt_attrs = kzalloc(sizeof(struct pg_table_attrs), GFP_KERNEL); if (pt_attrs != NULL) { - /* Assuming that we use only DSP's memory map - * until 0x4000:0000 , we would need only 1024 - * L1 enties i.e L1 size = 4K */ - pt_attrs->l1_size = 0x1000; + pt_attrs->l1_size = SZ_16K; /* 4096 entries of 32 bits */ align_size = pt_attrs->l1_size; /* Align sizes are expected to be power of 2 */ /* we like to get aligned on L1 table size */ diff --git a/drivers/staging/tidspbridge/include/dspbridge/io_sm.h b/drivers/staging/tidspbridge/include/dspbridge/io_sm.h index 18aec55..8242c70 100644 --- a/drivers/staging/tidspbridge/include/dspbridge/io_sm.h +++ b/drivers/staging/tidspbridge/include/dspbridge/io_sm.h @@ -72,22 +72,17 @@ extern void io_dpc(unsigned long ref_data); /* * ======== io_mbox_msg ======== * Purpose: - * Main interrupt handler for the shared memory Bridge channel manager. - * Calls the Bridge's chnlsm_isr to determine if this interrupt is ours, - * then schedules a DPC to dispatch I/O. + * Main message handler for the shared memory Bridge channel manager. + * Determine if this message is ours, then schedules a DPC to + * dispatch I/O. * Parameters: - * ref_data: Pointer to the channel manager object for this board. - * Set in an initial call to ISR_Install(). + * self: Pointer to its own notifier_block struct. + * len: Length of message. + * msg: Message code received. * Returns: - * TRUE if interrupt handled; FALSE otherwise. - * Requires: - * Must be in locked memory if executing in kernel mode. - * Must only call functions which are in locked memory if Kernel mode. - * Must only call asynchronous services. - * Interrupts are disabled and EOI for this interrupt has been sent. - * Ensures: + * NOTIFY_OK if handled; NOTIFY_BAD otherwise. */ -void io_mbox_msg(u32 msg); +int io_mbox_msg(struct notifier_block *self, unsigned long len, void *msg); /* * ======== io_request_chnl ======== diff --git a/drivers/staging/usbip/stub.h b/drivers/staging/usbip/stub.h index 30dbfb6..d732679 100644 --- a/drivers/staging/usbip/stub.h +++ b/drivers/staging/usbip/stub.h @@ -32,6 +32,7 @@ struct stub_device { struct usb_interface *interface; + struct usb_device *udev; struct list_head list; struct usbip_device ud; diff --git a/drivers/staging/usbip/stub_dev.c b/drivers/staging/usbip/stub_dev.c index b186b5f..a7ce51c 100644 --- a/drivers/staging/usbip/stub_dev.c +++ b/drivers/staging/usbip/stub_dev.c @@ -258,10 +258,11 @@ static void stub_shutdown_connection(struct usbip_device *ud) static void stub_device_reset(struct usbip_device *ud) { struct stub_device *sdev = container_of(ud, struct stub_device, ud); - struct usb_device *udev = interface_to_usbdev(sdev->interface); + struct usb_device *udev = sdev->udev; int ret; usbip_udbg("device reset"); + ret = usb_lock_device_for_reset(udev, sdev->interface); if (ret < 0) { dev_err(&udev->dev, "lock for reset\n"); @@ -309,7 +310,8 @@ static void stub_device_unusable(struct usbip_device *ud) * * Allocates and initializes a new stub_device struct. */ -static struct stub_device *stub_device_alloc(struct usb_interface *interface) +static struct stub_device *stub_device_alloc(struct usb_device *udev, + struct usb_interface *interface) { struct stub_device *sdev; int busnum = interface_to_busnum(interface); @@ -324,7 +326,8 @@ static struct stub_device *stub_device_alloc(struct usb_interface *interface) return NULL; } - sdev->interface = interface; + sdev->interface = usb_get_intf(interface); + sdev->udev = usb_get_dev(udev); /* * devid is defined with devnum when this driver is first allocated. @@ -450,11 +453,12 @@ static int stub_probe(struct usb_interface *interface, return err; } + usb_get_intf(interface); return 0; } /* ok. this is my device. */ - sdev = stub_device_alloc(interface); + sdev = stub_device_alloc(udev, interface); if (!sdev) return -ENOMEM; @@ -476,6 +480,8 @@ static int stub_probe(struct usb_interface *interface, dev_err(&interface->dev, "create sysfs files for %s\n", udev_busid); usb_set_intfdata(interface, NULL); + usb_put_intf(interface); + busid_priv->interf_count = 0; busid_priv->sdev = NULL; @@ -545,6 +551,7 @@ static void stub_disconnect(struct usb_interface *interface) if (busid_priv->interf_count > 1) { busid_priv->interf_count--; shutdown_busid(busid_priv); + usb_put_intf(interface); return; } @@ -554,6 +561,9 @@ static void stub_disconnect(struct usb_interface *interface) /* 1. shutdown the current connection */ shutdown_busid(busid_priv); + usb_put_dev(sdev->udev); + usb_put_intf(interface); + /* 3. free sdev */ busid_priv->sdev = NULL; stub_device_free(sdev); diff --git a/drivers/staging/usbip/stub_rx.c b/drivers/staging/usbip/stub_rx.c index 3de6fd2..ae6ac82 100644 --- a/drivers/staging/usbip/stub_rx.c +++ b/drivers/staging/usbip/stub_rx.c @@ -364,7 +364,7 @@ static struct stub_priv *stub_priv_alloc(struct stub_device *sdev, static int get_pipe(struct stub_device *sdev, int epnum, int dir) { - struct usb_device *udev = interface_to_usbdev(sdev->interface); + struct usb_device *udev = sdev->udev; struct usb_host_endpoint *ep; struct usb_endpoint_descriptor *epd = NULL; @@ -484,7 +484,7 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, int ret; struct stub_priv *priv; struct usbip_device *ud = &sdev->ud; - struct usb_device *udev = interface_to_usbdev(sdev->interface); + struct usb_device *udev = sdev->udev; int pipe = get_pipe(sdev, pdu->base.ep, pdu->base.direction); diff --git a/drivers/staging/usbip/vhci.h b/drivers/staging/usbip/vhci.h index 41a1fe5..afc3b1a 100644 --- a/drivers/staging/usbip/vhci.h +++ b/drivers/staging/usbip/vhci.h @@ -100,9 +100,6 @@ struct vhci_hcd { * But, the index of this array begins from 0. */ struct vhci_device vdev[VHCI_NPORTS]; - - /* vhci_device which has not been assiged its address yet */ - int pending_port; }; @@ -119,6 +116,9 @@ void rh_port_disconnect(int rhport); void vhci_rx_loop(struct usbip_task *ut); void vhci_tx_loop(struct usbip_task *ut); +struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, + __u32 seqnum); + #define hardware (&the_controller->pdev.dev) static inline struct vhci_device *port_to_vdev(__u32 port) diff --git a/drivers/staging/usbip/vhci_hcd.c b/drivers/staging/usbip/vhci_hcd.c index 08bd26a..a35fe61 100644 --- a/drivers/staging/usbip/vhci_hcd.c +++ b/drivers/staging/usbip/vhci_hcd.c @@ -138,8 +138,6 @@ void rh_port_connect(int rhport, enum usb_device_speed speed) * the_controller->vdev[rhport].ud.status = VDEV_CONNECT; * spin_unlock(&the_controller->vdev[rhport].ud.lock); */ - the_controller->pending_port = rhport; - spin_unlock_irqrestore(&the_controller->lock, flags); usb_hcd_poll_rh_status(vhci_to_hcd(the_controller)); @@ -559,6 +557,7 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, struct device *dev = &urb->dev->dev; int ret = 0; unsigned long flags; + struct vhci_device *vdev; usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n", hcd, urb, mem_flags); @@ -574,6 +573,18 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, return urb->status; } + vdev = port_to_vdev(urb->dev->portnum-1); + + /* refuse enqueue for dead connection */ + spin_lock(&vdev->ud.lock); + if (vdev->ud.status == VDEV_ST_NULL || vdev->ud.status == VDEV_ST_ERROR) { + usbip_uerr("enqueue for inactive port %d\n", vdev->rhport); + spin_unlock(&vdev->ud.lock); + spin_unlock_irqrestore(&the_controller->lock, flags); + return -ENODEV; + } + spin_unlock(&vdev->ud.lock); + ret = usb_hcd_link_urb_to_ep(hcd, urb); if (ret) goto no_need_unlink; @@ -592,8 +603,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, __u8 type = usb_pipetype(urb->pipe); struct usb_ctrlrequest *ctrlreq = (struct usb_ctrlrequest *) urb->setup_packet; - struct vhci_device *vdev = - port_to_vdev(the_controller->pending_port); if (type != PIPE_CONTROL || !ctrlreq) { dev_err(dev, "invalid request to devnum 0\n"); @@ -607,7 +616,9 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, dev_info(dev, "SetAddress Request (%d) to port %d\n", ctrlreq->wValue, vdev->rhport); - vdev->udev = urb->dev; + if (vdev->udev) + usb_put_dev(vdev->udev); + vdev->udev = usb_get_dev(urb->dev); spin_lock(&vdev->ud.lock); vdev->ud.status = VDEV_ST_USED; @@ -627,8 +638,9 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, "Get_Descriptor to device 0 " "(get max pipe size)\n"); - /* FIXME: reference count? (usb_get_dev()) */ - vdev->udev = urb->dev; + if (vdev->udev) + usb_put_dev(vdev->udev); + vdev->udev = usb_get_dev(urb->dev); goto out; default: @@ -805,7 +817,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) return 0; } - static void vhci_device_unlink_cleanup(struct vhci_device *vdev) { struct vhci_unlink *unlink, *tmp; @@ -813,11 +824,34 @@ static void vhci_device_unlink_cleanup(struct vhci_device *vdev) spin_lock(&vdev->priv_lock); list_for_each_entry_safe(unlink, tmp, &vdev->unlink_tx, list) { + usbip_uinfo("unlink cleanup tx %lu\n", unlink->unlink_seqnum); list_del(&unlink->list); kfree(unlink); } list_for_each_entry_safe(unlink, tmp, &vdev->unlink_rx, list) { + struct urb *urb; + + /* give back URB of unanswered unlink request */ + usbip_uinfo("unlink cleanup rx %lu\n", unlink->unlink_seqnum); + + urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum); + if (!urb) { + usbip_uinfo("the urb (seqnum %lu) was already given back\n", + unlink->unlink_seqnum); + list_del(&unlink->list); + kfree(unlink); + continue; + } + + urb->status = -ENODEV; + + spin_lock(&the_controller->lock); + usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb); + spin_unlock(&the_controller->lock); + + usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status); + list_del(&unlink->list); kfree(unlink); } @@ -887,6 +921,10 @@ static void vhci_device_reset(struct usbip_device *ud) vdev->speed = 0; vdev->devid = 0; + if (vdev->udev) + usb_put_dev(vdev->udev); + vdev->udev = NULL; + ud->tcp_socket = NULL; ud->status = VDEV_ST_NULL; diff --git a/drivers/staging/usbip/vhci_rx.c b/drivers/staging/usbip/vhci_rx.c index 8147d72..bf69914 100644 --- a/drivers/staging/usbip/vhci_rx.c +++ b/drivers/staging/usbip/vhci_rx.c @@ -23,16 +23,14 @@ #include "vhci.h" -/* get URB from transmitted urb queue */ -static struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, +/* get URB from transmitted urb queue. caller must hold vdev->priv_lock */ +struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum) { struct vhci_priv *priv, *tmp; struct urb *urb = NULL; int status; - spin_lock(&vdev->priv_lock); - list_for_each_entry_safe(priv, tmp, &vdev->priv_rx, list) { if (priv->seqnum == seqnum) { urb = priv->urb; @@ -63,8 +61,6 @@ static struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, } } - spin_unlock(&vdev->priv_lock); - return urb; } @@ -74,9 +70,11 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, struct usbip_device *ud = &vdev->ud; struct urb *urb; + spin_lock(&vdev->priv_lock); urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum); + spin_unlock(&vdev->priv_lock); if (!urb) { usbip_uerr("cannot find a urb of seqnum %u\n", @@ -161,7 +159,12 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev, return; } + spin_lock(&vdev->priv_lock); + urb = pickup_urb_and_free_priv(vdev, unlink->unlink_seqnum); + + spin_unlock(&vdev->priv_lock); + if (!urb) { /* * I get the result of a unlink request. But, it seems that I @@ -190,6 +193,19 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev, return; } +static int vhci_priv_tx_empty(struct vhci_device *vdev) +{ + int empty = 0; + + spin_lock(&vdev->priv_lock); + + empty = list_empty(&vdev->priv_rx); + + spin_unlock(&vdev->priv_lock); + + return empty; +} + /* recv a pdu */ static void vhci_rx_pdu(struct usbip_device *ud) { @@ -202,11 +218,29 @@ static void vhci_rx_pdu(struct usbip_device *ud) memset(&pdu, 0, sizeof(pdu)); - /* 1. receive a pdu header */ ret = usbip_xmit(0, ud->tcp_socket, (char *) &pdu, sizeof(pdu), 0); + if (ret < 0) { + if (ret == -ECONNRESET) + usbip_uinfo("connection reset by peer\n"); + else if (ret == -EAGAIN) { + /* ignore if connection was idle */ + if (vhci_priv_tx_empty(vdev)) + return; + usbip_uinfo("connection timed out with pending urbs\n"); + } else if (ret != -ERESTARTSYS) + usbip_uinfo("xmit failed %d\n", ret); + + usbip_event_add(ud, VDEV_EVENT_ERROR_TCP); + return; + } + if (ret == 0) { + usbip_uinfo("connection closed"); + usbip_event_add(ud, VDEV_EVENT_DOWN); + return; + } if (ret != sizeof(pdu)) { - usbip_uerr("receiving pdu failed! size is %d, should be %d\n", + usbip_uerr("received pdu size is %d, should be %d\n", ret, (unsigned int)sizeof(pdu)); usbip_event_add(ud, VDEV_EVENT_ERROR_TCP); return; diff --git a/drivers/staging/xgifb/vb_setmode.c b/drivers/staging/xgifb/vb_setmode.c index 7016fdd..e19b932 100644 --- a/drivers/staging/xgifb/vb_setmode.c +++ b/drivers/staging/xgifb/vb_setmode.c @@ -3954,8 +3954,8 @@ void XGI_GetCRT2ResInfo(unsigned short ModeNo, unsigned short ModeIdIndex, unsigned char XGI_IsLCDDualLink(struct vb_device_info *pVBInfo) { - if ((((pVBInfo->VBInfo & SetCRT2ToLCD) | SetCRT2ToLCDA)) - && (pVBInfo->LCDInfo & SetLCDDualLink)) /* shampoo0129 */ + if ((pVBInfo->VBInfo & (SetCRT2ToLCD | SetCRT2ToLCDA)) && + (pVBInfo->LCDInfo & SetLCDDualLink)) /* shampoo0129 */ return 1; return 0; @@ -8773,7 +8773,7 @@ unsigned short XGI_GetVCLK2Ptr(unsigned short ModeNo, if (pVBInfo->IF_DEF_LVDS == 0) { CRT2Index = CRT2Index >> 6; /* for LCD */ - if (((pVBInfo->VBInfo & SetCRT2ToLCD) | SetCRT2ToLCDA)) { /*301b*/ + if (pVBInfo->VBInfo & (SetCRT2ToLCD | SetCRT2ToLCDA)) { /*301b*/ if (pVBInfo->LCDResInfo != Panel1024x768) VCLKIndex = LCDXlat2VCLK[CRT2Index]; else diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c index 5415712..4bd8cbd 100644 --- a/drivers/staging/zram/zram_drv.c +++ b/drivers/staging/zram/zram_drv.c @@ -227,6 +227,7 @@ static int zram_read(struct zram *zram, struct bio *bio) if (zram_test_flag(zram, index, ZRAM_ZERO)) { handle_zero_page(page); + index++; continue; } @@ -235,12 +236,14 @@ static int zram_read(struct zram *zram, struct bio *bio) pr_debug("Read before write: sector=%lu, size=%u", (ulong)(bio->bi_sector), bio->bi_size); /* Do nothing */ + index++; continue; } /* Page is stored uncompressed since it's incompressible */ if (unlikely(zram_test_flag(zram, index, ZRAM_UNCOMPRESSED))) { handle_uncompressed_page(zram, page, index); + index++; continue; } @@ -320,6 +323,7 @@ static int zram_write(struct zram *zram, struct bio *bio) mutex_unlock(&zram->lock); zram_stat_inc(&zram->stats.pages_zero); zram_set_flag(zram, index, ZRAM_ZERO); + index++; continue; } diff --git a/drivers/target/Makefile b/drivers/target/Makefile index 5cfd708..973bb19 100644 --- a/drivers/target/Makefile +++ b/drivers/target/Makefile @@ -13,8 +13,7 @@ target_core_mod-y := target_core_configfs.o \ target_core_transport.o \ target_core_cdb.o \ target_core_ua.o \ - target_core_rd.o \ - target_core_mib.o + target_core_rd.o obj-$(CONFIG_TARGET_CORE) += target_core_mod.o diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 2764510..caf8dc18 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -37,7 +37,6 @@ #include <linux/parser.h> #include <linux/syscalls.h> #include <linux/configfs.h> -#include <linux/proc_fs.h> #include <target/target_core_base.h> #include <target/target_core_device.h> @@ -1971,13 +1970,35 @@ static void target_core_dev_release(struct config_item *item) { struct se_subsystem_dev *se_dev = container_of(to_config_group(item), struct se_subsystem_dev, se_dev_group); - struct config_group *dev_cg; - - if (!(se_dev)) - return; + struct se_hba *hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item); + struct se_subsystem_api *t = hba->transport; + struct config_group *dev_cg = &se_dev->se_dev_group; - dev_cg = &se_dev->se_dev_group; kfree(dev_cg->default_groups); + /* + * This pointer will set when the storage is enabled with: + *`echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable` + */ + if (se_dev->se_dev_ptr) { + printk(KERN_INFO "Target_Core_ConfigFS: Calling se_free_" + "virtual_device() for se_dev_ptr: %p\n", + se_dev->se_dev_ptr); + + se_free_virtual_device(se_dev->se_dev_ptr, hba); + } else { + /* + * Release struct se_subsystem_dev->se_dev_su_ptr.. + */ + printk(KERN_INFO "Target_Core_ConfigFS: Calling t->free_" + "device() for se_dev_su_ptr: %p\n", + se_dev->se_dev_su_ptr); + + t->free_device(se_dev->se_dev_su_ptr); + } + + printk(KERN_INFO "Target_Core_ConfigFS: Deallocating se_subsystem" + "_dev_t: %p\n", se_dev); + kfree(se_dev); } static ssize_t target_core_dev_show(struct config_item *item, @@ -2140,7 +2161,16 @@ static struct configfs_attribute *target_core_alua_lu_gp_attrs[] = { NULL, }; +static void target_core_alua_lu_gp_release(struct config_item *item) +{ + struct t10_alua_lu_gp *lu_gp = container_of(to_config_group(item), + struct t10_alua_lu_gp, lu_gp_group); + + core_alua_free_lu_gp(lu_gp); +} + static struct configfs_item_operations target_core_alua_lu_gp_ops = { + .release = target_core_alua_lu_gp_release, .show_attribute = target_core_alua_lu_gp_attr_show, .store_attribute = target_core_alua_lu_gp_attr_store, }; @@ -2191,9 +2221,11 @@ static void target_core_alua_drop_lu_gp( printk(KERN_INFO "Target_Core_ConfigFS: Releasing ALUA Logical Unit" " Group: core/alua/lu_gps/%s, ID: %hu\n", config_item_name(item), lu_gp->lu_gp_id); - + /* + * core_alua_free_lu_gp() is called from target_core_alua_lu_gp_ops->release() + * -> target_core_alua_lu_gp_release() + */ config_item_put(item); - core_alua_free_lu_gp(lu_gp); } static struct configfs_group_operations target_core_alua_lu_gps_group_ops = { @@ -2549,7 +2581,16 @@ static struct configfs_attribute *target_core_alua_tg_pt_gp_attrs[] = { NULL, }; +static void target_core_alua_tg_pt_gp_release(struct config_item *item) +{ + struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(to_config_group(item), + struct t10_alua_tg_pt_gp, tg_pt_gp_group); + + core_alua_free_tg_pt_gp(tg_pt_gp); +} + static struct configfs_item_operations target_core_alua_tg_pt_gp_ops = { + .release = target_core_alua_tg_pt_gp_release, .show_attribute = target_core_alua_tg_pt_gp_attr_show, .store_attribute = target_core_alua_tg_pt_gp_attr_store, }; @@ -2602,9 +2643,11 @@ static void target_core_alua_drop_tg_pt_gp( printk(KERN_INFO "Target_Core_ConfigFS: Releasing ALUA Target Port" " Group: alua/tg_pt_gps/%s, ID: %hu\n", config_item_name(item), tg_pt_gp->tg_pt_gp_id); - + /* + * core_alua_free_tg_pt_gp() is called from target_core_alua_tg_pt_gp_ops->release() + * -> target_core_alua_tg_pt_gp_release(). + */ config_item_put(item); - core_alua_free_tg_pt_gp(tg_pt_gp); } static struct configfs_group_operations target_core_alua_tg_pt_gps_group_ops = { @@ -2771,13 +2814,11 @@ static void target_core_drop_subdev( struct se_subsystem_api *t; struct config_item *df_item; struct config_group *dev_cg, *tg_pt_gp_cg; - int i, ret; + int i; hba = item_to_hba(&se_dev->se_dev_hba->hba_group.cg_item); - if (mutex_lock_interruptible(&hba->hba_access_mutex)) - goto out; - + mutex_lock(&hba->hba_access_mutex); t = hba->transport; spin_lock(&se_global->g_device_lock); @@ -2791,7 +2832,10 @@ static void target_core_drop_subdev( config_item_put(df_item); } kfree(tg_pt_gp_cg->default_groups); - core_alua_free_tg_pt_gp(T10_ALUA(se_dev)->default_tg_pt_gp); + /* + * core_alua_free_tg_pt_gp() is called from ->default_tg_pt_gp + * directly from target_core_alua_tg_pt_gp_release(). + */ T10_ALUA(se_dev)->default_tg_pt_gp = NULL; dev_cg = &se_dev->se_dev_group; @@ -2800,38 +2844,12 @@ static void target_core_drop_subdev( dev_cg->default_groups[i] = NULL; config_item_put(df_item); } - - config_item_put(item); /* - * This pointer will set when the storage is enabled with: - * `echo 1 > $CONFIGFS/core/$HBA/$DEV/dev_enable` + * The releasing of se_dev and associated se_dev->se_dev_ptr is done + * from target_core_dev_item_ops->release() ->target_core_dev_release(). */ - if (se_dev->se_dev_ptr) { - printk(KERN_INFO "Target_Core_ConfigFS: Calling se_free_" - "virtual_device() for se_dev_ptr: %p\n", - se_dev->se_dev_ptr); - - ret = se_free_virtual_device(se_dev->se_dev_ptr, hba); - if (ret < 0) - goto hba_out; - } else { - /* - * Release struct se_subsystem_dev->se_dev_su_ptr.. - */ - printk(KERN_INFO "Target_Core_ConfigFS: Calling t->free_" - "device() for se_dev_su_ptr: %p\n", - se_dev->se_dev_su_ptr); - - t->free_device(se_dev->se_dev_su_ptr); - } - - printk(KERN_INFO "Target_Core_ConfigFS: Deallocating se_subsystem" - "_dev_t: %p\n", se_dev); - -hba_out: + config_item_put(item); mutex_unlock(&hba->hba_access_mutex); -out: - kfree(se_dev); } static struct configfs_group_operations target_core_hba_group_ops = { @@ -2914,6 +2932,13 @@ SE_HBA_ATTR(hba_mode, S_IRUGO | S_IWUSR); CONFIGFS_EATTR_OPS(target_core_hba, se_hba, hba_group); +static void target_core_hba_release(struct config_item *item) +{ + struct se_hba *hba = container_of(to_config_group(item), + struct se_hba, hba_group); + core_delete_hba(hba); +} + static struct configfs_attribute *target_core_hba_attrs[] = { &target_core_hba_hba_info.attr, &target_core_hba_hba_mode.attr, @@ -2921,6 +2946,7 @@ static struct configfs_attribute *target_core_hba_attrs[] = { }; static struct configfs_item_operations target_core_hba_item_ops = { + .release = target_core_hba_release, .show_attribute = target_core_hba_attr_show, .store_attribute = target_core_hba_attr_store, }; @@ -2997,10 +3023,11 @@ static void target_core_call_delhbafromtarget( struct config_group *group, struct config_item *item) { - struct se_hba *hba = item_to_hba(item); - + /* + * core_delete_hba() is called from target_core_hba_item_ops->release() + * -> target_core_hba_release() + */ config_item_put(item); - core_delete_hba(hba); } static struct configfs_group_operations target_core_group_ops = { @@ -3022,7 +3049,6 @@ static int target_core_init_configfs(void) struct config_group *target_cg, *hba_cg = NULL, *alua_cg = NULL; struct config_group *lu_gp_cg = NULL; struct configfs_subsystem *subsys; - struct proc_dir_entry *scsi_target_proc = NULL; struct t10_alua_lu_gp *lu_gp; int ret; @@ -3128,21 +3154,10 @@ static int target_core_init_configfs(void) if (core_dev_setup_virtual_lun0() < 0) goto out; - scsi_target_proc = proc_mkdir("scsi_target", 0); - if (!(scsi_target_proc)) { - printk(KERN_ERR "proc_mkdir(scsi_target, 0) failed\n"); - goto out; - } - ret = init_scsi_target_mib(); - if (ret < 0) - goto out; - return 0; out: configfs_unregister_subsystem(subsys); - if (scsi_target_proc) - remove_proc_entry("scsi_target", 0); core_dev_release_virtual_lun0(); rd_module_exit(); out_global: @@ -3178,8 +3193,7 @@ static void target_core_exit_configfs(void) config_item_put(item); } kfree(lu_gp_cg->default_groups); - core_alua_free_lu_gp(se_global->default_lu_gp); - se_global->default_lu_gp = NULL; + lu_gp_cg->default_groups = NULL; alua_cg = &se_global->alua_group; for (i = 0; alua_cg->default_groups[i]; i++) { @@ -3188,6 +3202,7 @@ static void target_core_exit_configfs(void) config_item_put(item); } kfree(alua_cg->default_groups); + alua_cg->default_groups = NULL; hba_cg = &se_global->target_core_hbagroup; for (i = 0; hba_cg->default_groups[i]; i++) { @@ -3196,20 +3211,20 @@ static void target_core_exit_configfs(void) config_item_put(item); } kfree(hba_cg->default_groups); - - for (i = 0; subsys->su_group.default_groups[i]; i++) { - item = &subsys->su_group.default_groups[i]->cg_item; - subsys->su_group.default_groups[i] = NULL; - config_item_put(item); - } + hba_cg->default_groups = NULL; + /* + * We expect subsys->su_group.default_groups to be released + * by configfs subsystem provider logic.. + */ + configfs_unregister_subsystem(subsys); kfree(subsys->su_group.default_groups); - configfs_unregister_subsystem(subsys); + core_alua_free_lu_gp(se_global->default_lu_gp); + se_global->default_lu_gp = NULL; + printk(KERN_INFO "TARGET_CORE[0]: Released ConfigFS Fabric" " Infrastructure\n"); - remove_scsi_target_mib(); - remove_proc_entry("scsi_target", 0); core_dev_release_virtual_lun0(); rd_module_exit(); release_se_global(); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 317ce58..5da051a 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -373,11 +373,11 @@ int core_update_device_list_for_node( /* * deve->se_lun_acl will be NULL for demo-mode created LUNs * that have not been explictly concerted to MappedLUNs -> - * struct se_lun_acl. + * struct se_lun_acl, but we remove deve->alua_port_list from + * port->sep_alua_list. This also means that active UAs and + * NodeACL context specific PR metadata for demo-mode + * MappedLUN *deve will be released below.. */ - if (!(deve->se_lun_acl)) - return 0; - spin_lock_bh(&port->sep_alua_lock); list_del(&deve->alua_port_list); spin_unlock_bh(&port->sep_alua_lock); @@ -395,12 +395,14 @@ int core_update_device_list_for_node( printk(KERN_ERR "struct se_dev_entry->se_lun_acl" " already set for demo mode -> explict" " LUN ACL transition\n"); + spin_unlock_irq(&nacl->device_list_lock); return -1; } if (deve->se_lun != lun) { printk(KERN_ERR "struct se_dev_entry->se_lun does" " match passed struct se_lun for demo mode" " -> explict LUN ACL transition\n"); + spin_unlock_irq(&nacl->device_list_lock); return -1; } deve->se_lun_acl = lun_acl; @@ -865,9 +867,6 @@ static void se_dev_stop(struct se_device *dev) } } spin_unlock(&hba->device_lock); - - while (atomic_read(&hba->dev_mib_access_count)) - cpu_relax(); } int se_dev_check_online(struct se_device *dev) diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c index 32b148d..b65d1c8 100644 --- a/drivers/target/target_core_fabric_configfs.c +++ b/drivers/target/target_core_fabric_configfs.c @@ -214,12 +214,22 @@ TCM_MAPPEDLUN_ATTR(write_protect, S_IRUGO | S_IWUSR); CONFIGFS_EATTR_OPS(target_fabric_mappedlun, se_lun_acl, se_lun_group); +static void target_fabric_mappedlun_release(struct config_item *item) +{ + struct se_lun_acl *lacl = container_of(to_config_group(item), + struct se_lun_acl, se_lun_group); + struct se_portal_group *se_tpg = lacl->se_lun_nacl->se_tpg; + + core_dev_free_initiator_node_lun_acl(se_tpg, lacl); +} + static struct configfs_attribute *target_fabric_mappedlun_attrs[] = { &target_fabric_mappedlun_write_protect.attr, NULL, }; static struct configfs_item_operations target_fabric_mappedlun_item_ops = { + .release = target_fabric_mappedlun_release, .show_attribute = target_fabric_mappedlun_attr_show, .store_attribute = target_fabric_mappedlun_attr_store, .allow_link = target_fabric_mappedlun_link, @@ -337,15 +347,21 @@ static void target_fabric_drop_mappedlun( struct config_group *group, struct config_item *item) { - struct se_lun_acl *lacl = container_of(to_config_group(item), - struct se_lun_acl, se_lun_group); - struct se_portal_group *se_tpg = lacl->se_lun_nacl->se_tpg; - config_item_put(item); - core_dev_free_initiator_node_lun_acl(se_tpg, lacl); +} + +static void target_fabric_nacl_base_release(struct config_item *item) +{ + struct se_node_acl *se_nacl = container_of(to_config_group(item), + struct se_node_acl, acl_group); + struct se_portal_group *se_tpg = se_nacl->se_tpg; + struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf; + + tf->tf_ops.fabric_drop_nodeacl(se_nacl); } static struct configfs_item_operations target_fabric_nacl_base_item_ops = { + .release = target_fabric_nacl_base_release, .show_attribute = target_fabric_nacl_base_attr_show, .store_attribute = target_fabric_nacl_base_attr_store, }; @@ -404,9 +420,6 @@ static void target_fabric_drop_nodeacl( struct config_group *group, struct config_item *item) { - struct se_portal_group *se_tpg = container_of(group, - struct se_portal_group, tpg_acl_group); - struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf; struct se_node_acl *se_nacl = container_of(to_config_group(item), struct se_node_acl, acl_group); struct config_item *df_item; @@ -419,9 +432,10 @@ static void target_fabric_drop_nodeacl( nacl_cg->default_groups[i] = NULL; config_item_put(df_item); } - + /* + * struct se_node_acl free is done in target_fabric_nacl_base_release() + */ config_item_put(item); - tf->tf_ops.fabric_drop_nodeacl(se_nacl); } static struct configfs_group_operations target_fabric_nacl_group_ops = { @@ -437,7 +451,18 @@ TF_CIT_SETUP(tpg_nacl, NULL, &target_fabric_nacl_group_ops, NULL); CONFIGFS_EATTR_OPS(target_fabric_np_base, se_tpg_np, tpg_np_group); +static void target_fabric_np_base_release(struct config_item *item) +{ + struct se_tpg_np *se_tpg_np = container_of(to_config_group(item), + struct se_tpg_np, tpg_np_group); + struct se_portal_group *se_tpg = se_tpg_np->tpg_np_parent; + struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf; + + tf->tf_ops.fabric_drop_np(se_tpg_np); +} + static struct configfs_item_operations target_fabric_np_base_item_ops = { + .release = target_fabric_np_base_release, .show_attribute = target_fabric_np_base_attr_show, .store_attribute = target_fabric_np_base_attr_store, }; @@ -466,6 +491,7 @@ static struct config_group *target_fabric_make_np( if (!(se_tpg_np) || IS_ERR(se_tpg_np)) return ERR_PTR(-EINVAL); + se_tpg_np->tpg_np_parent = se_tpg; config_group_init_type_name(&se_tpg_np->tpg_np_group, name, &TF_CIT_TMPL(tf)->tfc_tpg_np_base_cit); @@ -476,14 +502,10 @@ static void target_fabric_drop_np( struct config_group *group, struct config_item *item) { - struct se_portal_group *se_tpg = container_of(group, - struct se_portal_group, tpg_np_group); - struct target_fabric_configfs *tf = se_tpg->se_tpg_wwn->wwn_tf; - struct se_tpg_np *se_tpg_np = container_of(to_config_group(item), - struct se_tpg_np, tpg_np_group); - + /* + * struct se_tpg_np is released via target_fabric_np_base_release() + */ config_item_put(item); - tf->tf_ops.fabric_drop_np(se_tpg_np); } static struct configfs_group_operations target_fabric_np_group_ops = { @@ -814,7 +836,18 @@ TF_CIT_SETUP(tpg_param, &target_fabric_tpg_param_item_ops, NULL, NULL); */ CONFIGFS_EATTR_OPS(target_fabric_tpg, se_portal_group, tpg_group); +static void target_fabric_tpg_release(struct config_item *item) +{ + struct se_portal_group *se_tpg = container_of(to_config_group(item), + struct se_portal_group, tpg_group); + struct se_wwn *wwn = se_tpg->se_tpg_wwn; + struct target_fabric_configfs *tf = wwn->wwn_tf; + + tf->tf_ops.fabric_drop_tpg(se_tpg); +} + static struct configfs_item_operations target_fabric_tpg_base_item_ops = { + .release = target_fabric_tpg_release, .show_attribute = target_fabric_tpg_attr_show, .store_attribute = target_fabric_tpg_attr_store, }; @@ -872,8 +905,6 @@ static void target_fabric_drop_tpg( struct config_group *group, struct config_item *item) { - struct se_wwn *wwn = container_of(group, struct se_wwn, wwn_group); - struct target_fabric_configfs *tf = wwn->wwn_tf; struct se_portal_group *se_tpg = container_of(to_config_group(item), struct se_portal_group, tpg_group); struct config_group *tpg_cg = &se_tpg->tpg_group; @@ -890,15 +921,28 @@ static void target_fabric_drop_tpg( } config_item_put(item); - tf->tf_ops.fabric_drop_tpg(se_tpg); } +static void target_fabric_release_wwn(struct config_item *item) +{ + struct se_wwn *wwn = container_of(to_config_group(item), + struct se_wwn, wwn_group); + struct target_fabric_configfs *tf = wwn->wwn_tf; + + tf->tf_ops.fabric_drop_wwn(wwn); +} + +static struct configfs_item_operations target_fabric_tpg_item_ops = { + .release = target_fabric_release_wwn, +}; + static struct configfs_group_operations target_fabric_tpg_group_ops = { .make_group = target_fabric_make_tpg, .drop_item = target_fabric_drop_tpg, }; -TF_CIT_SETUP(tpg, NULL, &target_fabric_tpg_group_ops, NULL); +TF_CIT_SETUP(tpg, &target_fabric_tpg_item_ops, &target_fabric_tpg_group_ops, + NULL); /* End of tfc_tpg_cit */ @@ -932,13 +976,7 @@ static void target_fabric_drop_wwn( struct config_group *group, struct config_item *item) { - struct target_fabric_configfs *tf = container_of(group, - struct target_fabric_configfs, tf_group); - struct se_wwn *wwn = container_of(to_config_group(item), - struct se_wwn, wwn_group); - config_item_put(item); - tf->tf_ops.fabric_drop_wwn(wwn); } static struct configfs_group_operations target_fabric_wwn_group_ops = { diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index c6e0d75..67f0c09 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -154,7 +154,7 @@ static struct se_device *iblock_create_virtdevice( bd = blkdev_get_by_path(ib_dev->ibd_udev_path, FMODE_WRITE|FMODE_READ|FMODE_EXCL, ib_dev); - if (!(bd)) + if (IS_ERR(bd)) goto failed; /* * Setup the local scope queue_limits from struct request_queue->limits @@ -220,8 +220,10 @@ static void iblock_free_device(void *p) { struct iblock_dev *ib_dev = p; - blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); - bioset_free(ib_dev->ibd_bio_set); + if (ib_dev->ibd_bd != NULL) + blkdev_put(ib_dev->ibd_bd, FMODE_WRITE|FMODE_READ|FMODE_EXCL); + if (ib_dev->ibd_bio_set != NULL) + bioset_free(ib_dev->ibd_bio_set); kfree(ib_dev); } diff --git a/drivers/target/target_core_mib.c b/drivers/target/target_core_mib.c deleted file mode 100644 index d5a48aa..0000000 --- a/drivers/target/target_core_mib.c +++ /dev/null @@ -1,1078 +0,0 @@ -/******************************************************************************* - * Filename: target_core_mib.c - * - * Copyright (c) 2006-2007 SBE, Inc. All Rights Reserved. - * Copyright (c) 2007-2010 Rising Tide Systems - * Copyright (c) 2008-2010 Linux-iSCSI.org - * - * Nicholas A. Bellinger <nab@linux-iscsi.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * - ******************************************************************************/ - - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/delay.h> -#include <linux/timer.h> -#include <linux/string.h> -#include <linux/version.h> -#include <generated/utsrelease.h> -#include <linux/utsname.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/blkdev.h> -#include <scsi/scsi.h> -#include <scsi/scsi_device.h> -#include <scsi/scsi_host.h> - -#include <target/target_core_base.h> -#include <target/target_core_transport.h> -#include <target/target_core_fabric_ops.h> -#include <target/target_core_configfs.h> - -#include "target_core_hba.h" -#include "target_core_mib.h" - -/* SCSI mib table index */ -static struct scsi_index_table scsi_index_table; - -#ifndef INITIAL_JIFFIES -#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) -#endif - -/* SCSI Instance Table */ -#define SCSI_INST_SW_INDEX 1 -#define SCSI_TRANSPORT_INDEX 1 - -#define NONE "None" -#define ISPRINT(a) ((a >= ' ') && (a <= '~')) - -static inline int list_is_first(const struct list_head *list, - const struct list_head *head) -{ - return list->prev == head; -} - -static void *locate_hba_start( - struct seq_file *seq, - loff_t *pos) -{ - spin_lock(&se_global->g_device_lock); - return seq_list_start(&se_global->g_se_dev_list, *pos); -} - -static void *locate_hba_next( - struct seq_file *seq, - void *v, - loff_t *pos) -{ - return seq_list_next(v, &se_global->g_se_dev_list, pos); -} - -static void locate_hba_stop(struct seq_file *seq, void *v) -{ - spin_unlock(&se_global->g_device_lock); -} - -/**************************************************************************** - * SCSI MIB Tables - ****************************************************************************/ - -/* - * SCSI Instance Table - */ -static void *scsi_inst_seq_start( - struct seq_file *seq, - loff_t *pos) -{ - spin_lock(&se_global->hba_lock); - return seq_list_start(&se_global->g_hba_list, *pos); -} - -static void *scsi_inst_seq_next( - struct seq_file *seq, - void *v, - loff_t *pos) -{ - return seq_list_next(v, &se_global->g_hba_list, pos); -} - -static void scsi_inst_seq_stop(struct seq_file *seq, void *v) -{ - spin_unlock(&se_global->hba_lock); -} - -static int scsi_inst_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba = list_entry(v, struct se_hba, hba_list); - - if (list_is_first(&hba->hba_list, &se_global->g_hba_list)) - seq_puts(seq, "inst sw_indx\n"); - - seq_printf(seq, "%u %u\n", hba->hba_index, SCSI_INST_SW_INDEX); - seq_printf(seq, "plugin: %s version: %s\n", - hba->transport->name, TARGET_CORE_VERSION); - - return 0; -} - -static const struct seq_operations scsi_inst_seq_ops = { - .start = scsi_inst_seq_start, - .next = scsi_inst_seq_next, - .stop = scsi_inst_seq_stop, - .show = scsi_inst_seq_show -}; - -static int scsi_inst_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_inst_seq_ops); -} - -static const struct file_operations scsi_inst_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_inst_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Device Table - */ -static void *scsi_dev_seq_start(struct seq_file *seq, loff_t *pos) -{ - return locate_hba_start(seq, pos); -} - -static void *scsi_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return locate_hba_next(seq, v, pos); -} - -static void scsi_dev_seq_stop(struct seq_file *seq, void *v) -{ - locate_hba_stop(seq, v); -} - -static int scsi_dev_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba; - struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev, - g_se_dev_list); - struct se_device *dev = se_dev->se_dev_ptr; - char str[28]; - int k; - - if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list)) - seq_puts(seq, "inst indx role ports\n"); - - if (!(dev)) - return 0; - - hba = dev->se_hba; - if (!(hba)) { - /* Log error ? */ - return 0; - } - - seq_printf(seq, "%u %u %s %u\n", hba->hba_index, - dev->dev_index, "Target", dev->dev_port_count); - - memcpy(&str[0], (void *)DEV_T10_WWN(dev), 28); - - /* vendor */ - for (k = 0; k < 8; k++) - str[k] = ISPRINT(DEV_T10_WWN(dev)->vendor[k]) ? - DEV_T10_WWN(dev)->vendor[k] : 0x20; - str[k] = 0x20; - - /* model */ - for (k = 0; k < 16; k++) - str[k+9] = ISPRINT(DEV_T10_WWN(dev)->model[k]) ? - DEV_T10_WWN(dev)->model[k] : 0x20; - str[k + 9] = 0; - - seq_printf(seq, "dev_alias: %s\n", str); - - return 0; -} - -static const struct seq_operations scsi_dev_seq_ops = { - .start = scsi_dev_seq_start, - .next = scsi_dev_seq_next, - .stop = scsi_dev_seq_stop, - .show = scsi_dev_seq_show -}; - -static int scsi_dev_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_dev_seq_ops); -} - -static const struct file_operations scsi_dev_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_dev_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Port Table - */ -static void *scsi_port_seq_start(struct seq_file *seq, loff_t *pos) -{ - return locate_hba_start(seq, pos); -} - -static void *scsi_port_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return locate_hba_next(seq, v, pos); -} - -static void scsi_port_seq_stop(struct seq_file *seq, void *v) -{ - locate_hba_stop(seq, v); -} - -static int scsi_port_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba; - struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev, - g_se_dev_list); - struct se_device *dev = se_dev->se_dev_ptr; - struct se_port *sep, *sep_tmp; - - if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list)) - seq_puts(seq, "inst device indx role busy_count\n"); - - if (!(dev)) - return 0; - - hba = dev->se_hba; - if (!(hba)) { - /* Log error ? */ - return 0; - } - - /* FIXME: scsiPortBusyStatuses count */ - spin_lock(&dev->se_port_lock); - list_for_each_entry_safe(sep, sep_tmp, &dev->dev_sep_list, sep_list) { - seq_printf(seq, "%u %u %u %s%u %u\n", hba->hba_index, - dev->dev_index, sep->sep_index, "Device", - dev->dev_index, 0); - } - spin_unlock(&dev->se_port_lock); - - return 0; -} - -static const struct seq_operations scsi_port_seq_ops = { - .start = scsi_port_seq_start, - .next = scsi_port_seq_next, - .stop = scsi_port_seq_stop, - .show = scsi_port_seq_show -}; - -static int scsi_port_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_port_seq_ops); -} - -static const struct file_operations scsi_port_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_port_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Transport Table - */ -static void *scsi_transport_seq_start(struct seq_file *seq, loff_t *pos) -{ - return locate_hba_start(seq, pos); -} - -static void *scsi_transport_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return locate_hba_next(seq, v, pos); -} - -static void scsi_transport_seq_stop(struct seq_file *seq, void *v) -{ - locate_hba_stop(seq, v); -} - -static int scsi_transport_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba; - struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev, - g_se_dev_list); - struct se_device *dev = se_dev->se_dev_ptr; - struct se_port *se, *se_tmp; - struct se_portal_group *tpg; - struct t10_wwn *wwn; - char buf[64]; - - if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list)) - seq_puts(seq, "inst device indx dev_name\n"); - - if (!(dev)) - return 0; - - hba = dev->se_hba; - if (!(hba)) { - /* Log error ? */ - return 0; - } - - wwn = DEV_T10_WWN(dev); - - spin_lock(&dev->se_port_lock); - list_for_each_entry_safe(se, se_tmp, &dev->dev_sep_list, sep_list) { - tpg = se->sep_tpg; - sprintf(buf, "scsiTransport%s", - TPG_TFO(tpg)->get_fabric_name()); - - seq_printf(seq, "%u %s %u %s+%s\n", - hba->hba_index, /* scsiTransportIndex */ - buf, /* scsiTransportType */ - (TPG_TFO(tpg)->tpg_get_inst_index != NULL) ? - TPG_TFO(tpg)->tpg_get_inst_index(tpg) : - 0, - TPG_TFO(tpg)->tpg_get_wwn(tpg), - (strlen(wwn->unit_serial)) ? - /* scsiTransportDevName */ - wwn->unit_serial : wwn->vendor); - } - spin_unlock(&dev->se_port_lock); - - return 0; -} - -static const struct seq_operations scsi_transport_seq_ops = { - .start = scsi_transport_seq_start, - .next = scsi_transport_seq_next, - .stop = scsi_transport_seq_stop, - .show = scsi_transport_seq_show -}; - -static int scsi_transport_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_transport_seq_ops); -} - -static const struct file_operations scsi_transport_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_transport_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Target Device Table - */ -static void *scsi_tgt_dev_seq_start(struct seq_file *seq, loff_t *pos) -{ - return locate_hba_start(seq, pos); -} - -static void *scsi_tgt_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return locate_hba_next(seq, v, pos); -} - -static void scsi_tgt_dev_seq_stop(struct seq_file *seq, void *v) -{ - locate_hba_stop(seq, v); -} - - -#define LU_COUNT 1 /* for now */ -static int scsi_tgt_dev_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba; - struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev, - g_se_dev_list); - struct se_device *dev = se_dev->se_dev_ptr; - int non_accessible_lus = 0; - char status[16]; - - if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list)) - seq_puts(seq, "inst indx num_LUs status non_access_LUs" - " resets\n"); - - if (!(dev)) - return 0; - - hba = dev->se_hba; - if (!(hba)) { - /* Log error ? */ - return 0; - } - - switch (dev->dev_status) { - case TRANSPORT_DEVICE_ACTIVATED: - strcpy(status, "activated"); - break; - case TRANSPORT_DEVICE_DEACTIVATED: - strcpy(status, "deactivated"); - non_accessible_lus = 1; - break; - case TRANSPORT_DEVICE_SHUTDOWN: - strcpy(status, "shutdown"); - non_accessible_lus = 1; - break; - case TRANSPORT_DEVICE_OFFLINE_ACTIVATED: - case TRANSPORT_DEVICE_OFFLINE_DEACTIVATED: - strcpy(status, "offline"); - non_accessible_lus = 1; - break; - default: - sprintf(status, "unknown(%d)", dev->dev_status); - non_accessible_lus = 1; - } - - seq_printf(seq, "%u %u %u %s %u %u\n", - hba->hba_index, dev->dev_index, LU_COUNT, - status, non_accessible_lus, dev->num_resets); - - return 0; -} - -static const struct seq_operations scsi_tgt_dev_seq_ops = { - .start = scsi_tgt_dev_seq_start, - .next = scsi_tgt_dev_seq_next, - .stop = scsi_tgt_dev_seq_stop, - .show = scsi_tgt_dev_seq_show -}; - -static int scsi_tgt_dev_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_tgt_dev_seq_ops); -} - -static const struct file_operations scsi_tgt_dev_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_tgt_dev_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Target Port Table - */ -static void *scsi_tgt_port_seq_start(struct seq_file *seq, loff_t *pos) -{ - return locate_hba_start(seq, pos); -} - -static void *scsi_tgt_port_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return locate_hba_next(seq, v, pos); -} - -static void scsi_tgt_port_seq_stop(struct seq_file *seq, void *v) -{ - locate_hba_stop(seq, v); -} - -static int scsi_tgt_port_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba; - struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev, - g_se_dev_list); - struct se_device *dev = se_dev->se_dev_ptr; - struct se_port *sep, *sep_tmp; - struct se_portal_group *tpg; - u32 rx_mbytes, tx_mbytes; - unsigned long long num_cmds; - char buf[64]; - - if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list)) - seq_puts(seq, "inst device indx name port_index in_cmds" - " write_mbytes read_mbytes hs_in_cmds\n"); - - if (!(dev)) - return 0; - - hba = dev->se_hba; - if (!(hba)) { - /* Log error ? */ - return 0; - } - - spin_lock(&dev->se_port_lock); - list_for_each_entry_safe(sep, sep_tmp, &dev->dev_sep_list, sep_list) { - tpg = sep->sep_tpg; - sprintf(buf, "%sPort#", - TPG_TFO(tpg)->get_fabric_name()); - - seq_printf(seq, "%u %u %u %s%d %s%s%d ", - hba->hba_index, - dev->dev_index, - sep->sep_index, - buf, sep->sep_index, - TPG_TFO(tpg)->tpg_get_wwn(tpg), "+t+", - TPG_TFO(tpg)->tpg_get_tag(tpg)); - - spin_lock(&sep->sep_lun->lun_sep_lock); - num_cmds = sep->sep_stats.cmd_pdus; - rx_mbytes = (sep->sep_stats.rx_data_octets >> 20); - tx_mbytes = (sep->sep_stats.tx_data_octets >> 20); - spin_unlock(&sep->sep_lun->lun_sep_lock); - - seq_printf(seq, "%llu %u %u %u\n", num_cmds, - rx_mbytes, tx_mbytes, 0); - } - spin_unlock(&dev->se_port_lock); - - return 0; -} - -static const struct seq_operations scsi_tgt_port_seq_ops = { - .start = scsi_tgt_port_seq_start, - .next = scsi_tgt_port_seq_next, - .stop = scsi_tgt_port_seq_stop, - .show = scsi_tgt_port_seq_show -}; - -static int scsi_tgt_port_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_tgt_port_seq_ops); -} - -static const struct file_operations scsi_tgt_port_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_tgt_port_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Authorized Initiator Table: - * It contains the SCSI Initiators authorized to be attached to one of the - * local Target ports. - * Iterates through all active TPGs and extracts the info from the ACLs - */ -static void *scsi_auth_intr_seq_start(struct seq_file *seq, loff_t *pos) -{ - spin_lock_bh(&se_global->se_tpg_lock); - return seq_list_start(&se_global->g_se_tpg_list, *pos); -} - -static void *scsi_auth_intr_seq_next(struct seq_file *seq, void *v, - loff_t *pos) -{ - return seq_list_next(v, &se_global->g_se_tpg_list, pos); -} - -static void scsi_auth_intr_seq_stop(struct seq_file *seq, void *v) -{ - spin_unlock_bh(&se_global->se_tpg_lock); -} - -static int scsi_auth_intr_seq_show(struct seq_file *seq, void *v) -{ - struct se_portal_group *se_tpg = list_entry(v, struct se_portal_group, - se_tpg_list); - struct se_dev_entry *deve; - struct se_lun *lun; - struct se_node_acl *se_nacl; - int j; - - if (list_is_first(&se_tpg->se_tpg_list, - &se_global->g_se_tpg_list)) - seq_puts(seq, "inst dev port indx dev_or_port intr_name " - "map_indx att_count num_cmds read_mbytes " - "write_mbytes hs_num_cmds creation_time row_status\n"); - - if (!(se_tpg)) - return 0; - - spin_lock(&se_tpg->acl_node_lock); - list_for_each_entry(se_nacl, &se_tpg->acl_node_list, acl_list) { - - atomic_inc(&se_nacl->mib_ref_count); - smp_mb__after_atomic_inc(); - spin_unlock(&se_tpg->acl_node_lock); - - spin_lock_irq(&se_nacl->device_list_lock); - for (j = 0; j < TRANSPORT_MAX_LUNS_PER_TPG; j++) { - deve = &se_nacl->device_list[j]; - if (!(deve->lun_flags & - TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) || - (!deve->se_lun)) - continue; - lun = deve->se_lun; - if (!lun->lun_se_dev) - continue; - - seq_printf(seq, "%u %u %u %u %u %s %u %u %u %u %u %u" - " %u %s\n", - /* scsiInstIndex */ - (TPG_TFO(se_tpg)->tpg_get_inst_index != NULL) ? - TPG_TFO(se_tpg)->tpg_get_inst_index(se_tpg) : - 0, - /* scsiDeviceIndex */ - lun->lun_se_dev->dev_index, - /* scsiAuthIntrTgtPortIndex */ - TPG_TFO(se_tpg)->tpg_get_tag(se_tpg), - /* scsiAuthIntrIndex */ - se_nacl->acl_index, - /* scsiAuthIntrDevOrPort */ - 1, - /* scsiAuthIntrName */ - se_nacl->initiatorname[0] ? - se_nacl->initiatorname : NONE, - /* FIXME: scsiAuthIntrLunMapIndex */ - 0, - /* scsiAuthIntrAttachedTimes */ - deve->attach_count, - /* scsiAuthIntrOutCommands */ - deve->total_cmds, - /* scsiAuthIntrReadMegaBytes */ - (u32)(deve->read_bytes >> 20), - /* scsiAuthIntrWrittenMegaBytes */ - (u32)(deve->write_bytes >> 20), - /* FIXME: scsiAuthIntrHSOutCommands */ - 0, - /* scsiAuthIntrLastCreation */ - (u32)(((u32)deve->creation_time - - INITIAL_JIFFIES) * 100 / HZ), - /* FIXME: scsiAuthIntrRowStatus */ - "Ready"); - } - spin_unlock_irq(&se_nacl->device_list_lock); - - spin_lock(&se_tpg->acl_node_lock); - atomic_dec(&se_nacl->mib_ref_count); - smp_mb__after_atomic_dec(); - } - spin_unlock(&se_tpg->acl_node_lock); - - return 0; -} - -static const struct seq_operations scsi_auth_intr_seq_ops = { - .start = scsi_auth_intr_seq_start, - .next = scsi_auth_intr_seq_next, - .stop = scsi_auth_intr_seq_stop, - .show = scsi_auth_intr_seq_show -}; - -static int scsi_auth_intr_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_auth_intr_seq_ops); -} - -static const struct file_operations scsi_auth_intr_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_auth_intr_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Attached Initiator Port Table: - * It lists the SCSI Initiators attached to one of the local Target ports. - * Iterates through all active TPGs and use active sessions from each TPG - * to list the info fo this table. - */ -static void *scsi_att_intr_port_seq_start(struct seq_file *seq, loff_t *pos) -{ - spin_lock_bh(&se_global->se_tpg_lock); - return seq_list_start(&se_global->g_se_tpg_list, *pos); -} - -static void *scsi_att_intr_port_seq_next(struct seq_file *seq, void *v, - loff_t *pos) -{ - return seq_list_next(v, &se_global->g_se_tpg_list, pos); -} - -static void scsi_att_intr_port_seq_stop(struct seq_file *seq, void *v) -{ - spin_unlock_bh(&se_global->se_tpg_lock); -} - -static int scsi_att_intr_port_seq_show(struct seq_file *seq, void *v) -{ - struct se_portal_group *se_tpg = list_entry(v, struct se_portal_group, - se_tpg_list); - struct se_dev_entry *deve; - struct se_lun *lun; - struct se_node_acl *se_nacl; - struct se_session *se_sess; - unsigned char buf[64]; - int j; - - if (list_is_first(&se_tpg->se_tpg_list, - &se_global->g_se_tpg_list)) - seq_puts(seq, "inst dev port indx port_auth_indx port_name" - " port_ident\n"); - - if (!(se_tpg)) - return 0; - - spin_lock(&se_tpg->session_lock); - list_for_each_entry(se_sess, &se_tpg->tpg_sess_list, sess_list) { - if ((TPG_TFO(se_tpg)->sess_logged_in(se_sess)) || - (!se_sess->se_node_acl) || - (!se_sess->se_node_acl->device_list)) - continue; - - atomic_inc(&se_sess->mib_ref_count); - smp_mb__after_atomic_inc(); - se_nacl = se_sess->se_node_acl; - atomic_inc(&se_nacl->mib_ref_count); - smp_mb__after_atomic_inc(); - spin_unlock(&se_tpg->session_lock); - - spin_lock_irq(&se_nacl->device_list_lock); - for (j = 0; j < TRANSPORT_MAX_LUNS_PER_TPG; j++) { - deve = &se_nacl->device_list[j]; - if (!(deve->lun_flags & - TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) || - (!deve->se_lun)) - continue; - - lun = deve->se_lun; - if (!lun->lun_se_dev) - continue; - - memset(buf, 0, 64); - if (TPG_TFO(se_tpg)->sess_get_initiator_sid != NULL) - TPG_TFO(se_tpg)->sess_get_initiator_sid( - se_sess, (unsigned char *)&buf[0], 64); - - seq_printf(seq, "%u %u %u %u %u %s+i+%s\n", - /* scsiInstIndex */ - (TPG_TFO(se_tpg)->tpg_get_inst_index != NULL) ? - TPG_TFO(se_tpg)->tpg_get_inst_index(se_tpg) : - 0, - /* scsiDeviceIndex */ - lun->lun_se_dev->dev_index, - /* scsiPortIndex */ - TPG_TFO(se_tpg)->tpg_get_tag(se_tpg), - /* scsiAttIntrPortIndex */ - (TPG_TFO(se_tpg)->sess_get_index != NULL) ? - TPG_TFO(se_tpg)->sess_get_index(se_sess) : - 0, - /* scsiAttIntrPortAuthIntrIdx */ - se_nacl->acl_index, - /* scsiAttIntrPortName */ - se_nacl->initiatorname[0] ? - se_nacl->initiatorname : NONE, - /* scsiAttIntrPortIdentifier */ - buf); - } - spin_unlock_irq(&se_nacl->device_list_lock); - - spin_lock(&se_tpg->session_lock); - atomic_dec(&se_nacl->mib_ref_count); - smp_mb__after_atomic_dec(); - atomic_dec(&se_sess->mib_ref_count); - smp_mb__after_atomic_dec(); - } - spin_unlock(&se_tpg->session_lock); - - return 0; -} - -static const struct seq_operations scsi_att_intr_port_seq_ops = { - .start = scsi_att_intr_port_seq_start, - .next = scsi_att_intr_port_seq_next, - .stop = scsi_att_intr_port_seq_stop, - .show = scsi_att_intr_port_seq_show -}; - -static int scsi_att_intr_port_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_att_intr_port_seq_ops); -} - -static const struct file_operations scsi_att_intr_port_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_att_intr_port_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/* - * SCSI Logical Unit Table - */ -static void *scsi_lu_seq_start(struct seq_file *seq, loff_t *pos) -{ - return locate_hba_start(seq, pos); -} - -static void *scsi_lu_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - return locate_hba_next(seq, v, pos); -} - -static void scsi_lu_seq_stop(struct seq_file *seq, void *v) -{ - locate_hba_stop(seq, v); -} - -#define SCSI_LU_INDEX 1 -static int scsi_lu_seq_show(struct seq_file *seq, void *v) -{ - struct se_hba *hba; - struct se_subsystem_dev *se_dev = list_entry(v, struct se_subsystem_dev, - g_se_dev_list); - struct se_device *dev = se_dev->se_dev_ptr; - int j; - char str[28]; - - if (list_is_first(&se_dev->g_se_dev_list, &se_global->g_se_dev_list)) - seq_puts(seq, "inst dev indx LUN lu_name vend prod rev" - " dev_type status state-bit num_cmds read_mbytes" - " write_mbytes resets full_stat hs_num_cmds creation_time\n"); - - if (!(dev)) - return 0; - - hba = dev->se_hba; - if (!(hba)) { - /* Log error ? */ - return 0; - } - - /* Fix LU state, if we can read it from the device */ - seq_printf(seq, "%u %u %u %llu %s", hba->hba_index, - dev->dev_index, SCSI_LU_INDEX, - (unsigned long long)0, /* FIXME: scsiLuDefaultLun */ - (strlen(DEV_T10_WWN(dev)->unit_serial)) ? - /* scsiLuWwnName */ - (char *)&DEV_T10_WWN(dev)->unit_serial[0] : - "None"); - - memcpy(&str[0], (void *)DEV_T10_WWN(dev), 28); - /* scsiLuVendorId */ - for (j = 0; j < 8; j++) - str[j] = ISPRINT(DEV_T10_WWN(dev)->vendor[j]) ? - DEV_T10_WWN(dev)->vendor[j] : 0x20; - str[8] = 0; - seq_printf(seq, " %s", str); - - /* scsiLuProductId */ - for (j = 0; j < 16; j++) - str[j] = ISPRINT(DEV_T10_WWN(dev)->model[j]) ? - DEV_T10_WWN(dev)->model[j] : 0x20; - str[16] = 0; - seq_printf(seq, " %s", str); - - /* scsiLuRevisionId */ - for (j = 0; j < 4; j++) - str[j] = ISPRINT(DEV_T10_WWN(dev)->revision[j]) ? - DEV_T10_WWN(dev)->revision[j] : 0x20; - str[4] = 0; - seq_printf(seq, " %s", str); - - seq_printf(seq, " %u %s %s %llu %u %u %u %u %u %u\n", - /* scsiLuPeripheralType */ - TRANSPORT(dev)->get_device_type(dev), - (dev->dev_status == TRANSPORT_DEVICE_ACTIVATED) ? - "available" : "notavailable", /* scsiLuStatus */ - "exposed", /* scsiLuState */ - (unsigned long long)dev->num_cmds, - /* scsiLuReadMegaBytes */ - (u32)(dev->read_bytes >> 20), - /* scsiLuWrittenMegaBytes */ - (u32)(dev->write_bytes >> 20), - dev->num_resets, /* scsiLuInResets */ - 0, /* scsiLuOutTaskSetFullStatus */ - 0, /* scsiLuHSInCommands */ - (u32)(((u32)dev->creation_time - INITIAL_JIFFIES) * - 100 / HZ)); - - return 0; -} - -static const struct seq_operations scsi_lu_seq_ops = { - .start = scsi_lu_seq_start, - .next = scsi_lu_seq_next, - .stop = scsi_lu_seq_stop, - .show = scsi_lu_seq_show -}; - -static int scsi_lu_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &scsi_lu_seq_ops); -} - -static const struct file_operations scsi_lu_seq_fops = { - .owner = THIS_MODULE, - .open = scsi_lu_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -/****************************************************************************/ - -/* - * Remove proc fs entries - */ -void remove_scsi_target_mib(void) -{ - remove_proc_entry("scsi_target/mib/scsi_inst", NULL); - remove_proc_entry("scsi_target/mib/scsi_dev", NULL); - remove_proc_entry("scsi_target/mib/scsi_port", NULL); - remove_proc_entry("scsi_target/mib/scsi_transport", NULL); - remove_proc_entry("scsi_target/mib/scsi_tgt_dev", NULL); - remove_proc_entry("scsi_target/mib/scsi_tgt_port", NULL); - remove_proc_entry("scsi_target/mib/scsi_auth_intr", NULL); - remove_proc_entry("scsi_target/mib/scsi_att_intr_port", NULL); - remove_proc_entry("scsi_target/mib/scsi_lu", NULL); - remove_proc_entry("scsi_target/mib", NULL); -} - -/* - * Create proc fs entries for the mib tables - */ -int init_scsi_target_mib(void) -{ - struct proc_dir_entry *dir_entry; - struct proc_dir_entry *scsi_inst_entry; - struct proc_dir_entry *scsi_dev_entry; - struct proc_dir_entry *scsi_port_entry; - struct proc_dir_entry *scsi_transport_entry; - struct proc_dir_entry *scsi_tgt_dev_entry; - struct proc_dir_entry *scsi_tgt_port_entry; - struct proc_dir_entry *scsi_auth_intr_entry; - struct proc_dir_entry *scsi_att_intr_port_entry; - struct proc_dir_entry *scsi_lu_entry; - - dir_entry = proc_mkdir("scsi_target/mib", NULL); - if (!(dir_entry)) { - printk(KERN_ERR "proc_mkdir() failed.\n"); - return -1; - } - - scsi_inst_entry = - create_proc_entry("scsi_target/mib/scsi_inst", 0, NULL); - if (scsi_inst_entry) - scsi_inst_entry->proc_fops = &scsi_inst_seq_fops; - else - goto error; - - scsi_dev_entry = - create_proc_entry("scsi_target/mib/scsi_dev", 0, NULL); - if (scsi_dev_entry) - scsi_dev_entry->proc_fops = &scsi_dev_seq_fops; - else - goto error; - - scsi_port_entry = - create_proc_entry("scsi_target/mib/scsi_port", 0, NULL); - if (scsi_port_entry) - scsi_port_entry->proc_fops = &scsi_port_seq_fops; - else - goto error; - - scsi_transport_entry = - create_proc_entry("scsi_target/mib/scsi_transport", 0, NULL); - if (scsi_transport_entry) - scsi_transport_entry->proc_fops = &scsi_transport_seq_fops; - else - goto error; - - scsi_tgt_dev_entry = - create_proc_entry("scsi_target/mib/scsi_tgt_dev", 0, NULL); - if (scsi_tgt_dev_entry) - scsi_tgt_dev_entry->proc_fops = &scsi_tgt_dev_seq_fops; - else - goto error; - - scsi_tgt_port_entry = - create_proc_entry("scsi_target/mib/scsi_tgt_port", 0, NULL); - if (scsi_tgt_port_entry) - scsi_tgt_port_entry->proc_fops = &scsi_tgt_port_seq_fops; - else - goto error; - - scsi_auth_intr_entry = - create_proc_entry("scsi_target/mib/scsi_auth_intr", 0, NULL); - if (scsi_auth_intr_entry) - scsi_auth_intr_entry->proc_fops = &scsi_auth_intr_seq_fops; - else - goto error; - - scsi_att_intr_port_entry = - create_proc_entry("scsi_target/mib/scsi_att_intr_port", 0, NULL); - if (scsi_att_intr_port_entry) - scsi_att_intr_port_entry->proc_fops = - &scsi_att_intr_port_seq_fops; - else - goto error; - - scsi_lu_entry = create_proc_entry("scsi_target/mib/scsi_lu", 0, NULL); - if (scsi_lu_entry) - scsi_lu_entry->proc_fops = &scsi_lu_seq_fops; - else - goto error; - - return 0; - -error: - printk(KERN_ERR "create_proc_entry() failed.\n"); - remove_scsi_target_mib(); - return -1; -} - -/* - * Initialize the index table for allocating unique row indexes to various mib - * tables - */ -void init_scsi_index_table(void) -{ - memset(&scsi_index_table, 0, sizeof(struct scsi_index_table)); - spin_lock_init(&scsi_index_table.lock); -} - -/* - * Allocate a new row index for the entry type specified - */ -u32 scsi_get_new_index(scsi_index_t type) -{ - u32 new_index; - - if ((type < 0) || (type >= SCSI_INDEX_TYPE_MAX)) { - printk(KERN_ERR "Invalid index type %d\n", type); - return -1; - } - - spin_lock(&scsi_index_table.lock); - new_index = ++scsi_index_table.scsi_mib_index[type]; - if (new_index == 0) - new_index = ++scsi_index_table.scsi_mib_index[type]; - spin_unlock(&scsi_index_table.lock); - - return new_index; -} -EXPORT_SYMBOL(scsi_get_new_index); diff --git a/drivers/target/target_core_mib.h b/drivers/target/target_core_mib.h deleted file mode 100644 index 2772046..0000000 --- a/drivers/target/target_core_mib.h +++ /dev/null @@ -1,28 +0,0 @@ -#ifndef TARGET_CORE_MIB_H -#define TARGET_CORE_MIB_H - -typedef enum { - SCSI_INST_INDEX, - SCSI_DEVICE_INDEX, - SCSI_AUTH_INTR_INDEX, - SCSI_INDEX_TYPE_MAX -} scsi_index_t; - -struct scsi_index_table { - spinlock_t lock; - u32 scsi_mib_index[SCSI_INDEX_TYPE_MAX]; -} ____cacheline_aligned; - -/* SCSI Port stats */ -struct scsi_port_stats { - u64 cmd_pdus; - u64 tx_data_octets; - u64 rx_data_octets; -} ____cacheline_aligned; - -extern int init_scsi_target_mib(void); -extern void remove_scsi_target_mib(void); -extern void init_scsi_index_table(void); -extern u32 scsi_get_new_index(scsi_index_t); - -#endif /*** TARGET_CORE_MIB_H ***/ diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 742d246..f2a08477a 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -462,8 +462,8 @@ static struct se_device *pscsi_create_type_disk( */ bd = blkdev_get_by_path(se_dev->se_dev_udev_path, FMODE_WRITE|FMODE_READ|FMODE_EXCL, pdv); - if (!(bd)) { - printk("pSCSI: blkdev_get_by_path() failed\n"); + if (IS_ERR(bd)) { + printk(KERN_ERR "pSCSI: blkdev_get_by_path() failed\n"); scsi_device_put(sd); return NULL; } diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 158cecb..4a10983 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -282,6 +282,9 @@ int core_tmr_lun_reset( atomic_set(&task->task_active, 0); atomic_set(&task->task_stop, 0); + } else { + if (atomic_read(&task->task_execute_queue) != 0) + transport_remove_task_from_execute_queue(task, dev); } __transport_stop_task_timer(task, &flags); @@ -301,6 +304,7 @@ int core_tmr_lun_reset( DEBUG_LR("LUN_RESET: got t_transport_active = 1 for" " task: %p, t_fe_count: %d dev: %p\n", task, fe_count, dev); + atomic_set(&T_TASK(cmd)->t_transport_aborted, 1); spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock, flags); core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count); @@ -310,6 +314,7 @@ int core_tmr_lun_reset( } DEBUG_LR("LUN_RESET: Got t_transport_active = 0 for task: %p," " t_fe_count: %d dev: %p\n", task, fe_count, dev); + atomic_set(&T_TASK(cmd)->t_transport_aborted, 1); spin_unlock_irqrestore(&T_TASK(cmd)->t_state_lock, flags); core_tmr_handle_tas_abort(tmr_nacl, cmd, tas, fe_count); diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c index abfa81a..c26f674 100644 --- a/drivers/target/target_core_tpg.c +++ b/drivers/target/target_core_tpg.c @@ -275,7 +275,6 @@ struct se_node_acl *core_tpg_check_initiator_node_acl( spin_lock_init(&acl->device_list_lock); spin_lock_init(&acl->nacl_sess_lock); atomic_set(&acl->acl_pr_ref_count, 0); - atomic_set(&acl->mib_ref_count, 0); acl->queue_depth = TPG_TFO(tpg)->tpg_get_default_depth(tpg); snprintf(acl->initiatorname, TRANSPORT_IQN_LEN, "%s", initiatorname); acl->se_tpg = tpg; @@ -318,12 +317,6 @@ void core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *nacl) cpu_relax(); } -void core_tpg_wait_for_mib_ref(struct se_node_acl *nacl) -{ - while (atomic_read(&nacl->mib_ref_count) != 0) - cpu_relax(); -} - void core_tpg_clear_object_luns(struct se_portal_group *tpg) { int i, ret; @@ -480,7 +473,6 @@ int core_tpg_del_initiator_node_acl( spin_unlock_bh(&tpg->session_lock); core_tpg_wait_for_nacl_pr_ref(acl); - core_tpg_wait_for_mib_ref(acl); core_clear_initiator_node_from_tpg(acl, tpg); core_free_device_list_for_node(acl, tpg); @@ -701,6 +693,8 @@ EXPORT_SYMBOL(core_tpg_register); int core_tpg_deregister(struct se_portal_group *se_tpg) { + struct se_node_acl *nacl, *nacl_tmp; + printk(KERN_INFO "TARGET_CORE[%s]: Deallocating %s struct se_portal_group" " for endpoint: %s Portal Tag %u\n", (se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) ? @@ -714,6 +708,25 @@ int core_tpg_deregister(struct se_portal_group *se_tpg) while (atomic_read(&se_tpg->tpg_pr_ref_count) != 0) cpu_relax(); + /* + * Release any remaining demo-mode generated se_node_acl that have + * not been released because of TFO->tpg_check_demo_mode_cache() == 1 + * in transport_deregister_session(). + */ + spin_lock_bh(&se_tpg->acl_node_lock); + list_for_each_entry_safe(nacl, nacl_tmp, &se_tpg->acl_node_list, + acl_list) { + list_del(&nacl->acl_list); + se_tpg->num_node_acls--; + spin_unlock_bh(&se_tpg->acl_node_lock); + + core_tpg_wait_for_nacl_pr_ref(nacl); + core_free_device_list_for_node(nacl, se_tpg); + TPG_TFO(se_tpg)->tpg_release_fabric_acl(se_tpg, nacl); + + spin_lock_bh(&se_tpg->acl_node_lock); + } + spin_unlock_bh(&se_tpg->acl_node_lock); if (se_tpg->se_tpg_type == TRANSPORT_TPG_TYPE_NORMAL) core_tpg_release_virtual_lun0(se_tpg); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 28b6292ff..4bbf6c1 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -379,6 +379,40 @@ void release_se_global(void) se_global = NULL; } +/* SCSI statistics table index */ +static struct scsi_index_table scsi_index_table; + +/* + * Initialize the index table for allocating unique row indexes to various mib + * tables. + */ +void init_scsi_index_table(void) +{ + memset(&scsi_index_table, 0, sizeof(struct scsi_index_table)); + spin_lock_init(&scsi_index_table.lock); +} + +/* + * Allocate a new row index for the entry type specified + */ +u32 scsi_get_new_index(scsi_index_t type) +{ + u32 new_index; + + if ((type < 0) || (type >= SCSI_INDEX_TYPE_MAX)) { + printk(KERN_ERR "Invalid index type %d\n", type); + return -EINVAL; + } + + spin_lock(&scsi_index_table.lock); + new_index = ++scsi_index_table.scsi_mib_index[type]; + if (new_index == 0) + new_index = ++scsi_index_table.scsi_mib_index[type]; + spin_unlock(&scsi_index_table.lock); + + return new_index; +} + void transport_init_queue_obj(struct se_queue_obj *qobj) { atomic_set(&qobj->queue_cnt, 0); @@ -437,7 +471,6 @@ struct se_session *transport_init_session(void) } INIT_LIST_HEAD(&se_sess->sess_list); INIT_LIST_HEAD(&se_sess->sess_acl_list); - atomic_set(&se_sess->mib_ref_count, 0); return se_sess; } @@ -546,12 +579,6 @@ void transport_deregister_session(struct se_session *se_sess) transport_free_session(se_sess); return; } - /* - * Wait for possible reference in drivers/target/target_core_mib.c: - * scsi_att_intr_port_seq_show() - */ - while (atomic_read(&se_sess->mib_ref_count) != 0) - cpu_relax(); spin_lock_bh(&se_tpg->session_lock); list_del(&se_sess->sess_list); @@ -574,7 +601,6 @@ void transport_deregister_session(struct se_session *se_sess) spin_unlock_bh(&se_tpg->acl_node_lock); core_tpg_wait_for_nacl_pr_ref(se_nacl); - core_tpg_wait_for_mib_ref(se_nacl); core_free_device_list_for_node(se_nacl, se_tpg); TPG_TFO(se_tpg)->tpg_release_fabric_acl(se_tpg, se_nacl); @@ -1181,7 +1207,7 @@ transport_get_task_from_execute_queue(struct se_device *dev) * * */ -static void transport_remove_task_from_execute_queue( +void transport_remove_task_from_execute_queue( struct se_task *task, struct se_device *dev) { @@ -4827,6 +4853,8 @@ static int transport_do_se_mem_map( return ret; } + + BUG_ON(list_empty(se_mem_list)); /* * This is the normal path for all normal non BIDI and BIDI-COMMAND * WRITE payloads.. If we need to do BIDI READ passthrough for @@ -5008,7 +5036,9 @@ transport_map_control_cmd_to_task(struct se_cmd *cmd) struct se_mem *se_mem = NULL, *se_mem_lout = NULL; u32 se_mem_cnt = 0, task_offset = 0; - BUG_ON(list_empty(cmd->t_task->t_mem_list)); + if (!list_empty(T_TASK(cmd)->t_mem_list)) + se_mem = list_entry(T_TASK(cmd)->t_mem_list->next, + struct se_mem, se_list); ret = transport_do_se_mem_map(dev, task, cmd->t_task->t_mem_list, NULL, se_mem, @@ -5519,7 +5549,8 @@ static void transport_generic_wait_for_tasks( atomic_set(&T_TASK(cmd)->transport_lun_stop, 0); } - if (!atomic_read(&T_TASK(cmd)->t_transport_active)) + if (!atomic_read(&T_TASK(cmd)->t_transport_active) || + atomic_read(&T_TASK(cmd)->t_transport_aborted)) goto remove; atomic_set(&T_TASK(cmd)->t_transport_stop, 1); @@ -5926,6 +5957,9 @@ static void transport_processing_shutdown(struct se_device *dev) atomic_set(&task->task_active, 0); atomic_set(&task->task_stop, 0); + } else { + if (atomic_read(&task->task_execute_queue) != 0) + transport_remove_task_from_execute_queue(task, dev); } __transport_stop_task_timer(task, &flags); diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index f7a5dba..bf7c687 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -4,7 +4,6 @@ menuconfig THERMAL tristate "Generic Thermal sysfs driver" - depends on NET help Generic Thermal Sysfs driver offers a generic mechanism for thermal management. Usually it's made up of one or more thermal diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c index 7d0e63c..713b7ea 100644 --- a/drivers/thermal/thermal_sys.c +++ b/drivers/thermal/thermal_sys.c @@ -62,20 +62,6 @@ static DEFINE_MUTEX(thermal_list_lock); static unsigned int thermal_event_seqnum; -static struct genl_family thermal_event_genl_family = { - .id = GENL_ID_GENERATE, - .name = THERMAL_GENL_FAMILY_NAME, - .version = THERMAL_GENL_VERSION, - .maxattr = THERMAL_GENL_ATTR_MAX, -}; - -static struct genl_multicast_group thermal_event_mcgrp = { - .name = THERMAL_GENL_MCAST_GROUP_NAME, -}; - -static int genetlink_init(void); -static void genetlink_exit(void); - static int get_idr(struct idr *idr, struct mutex *lock, int *id) { int err; @@ -1225,6 +1211,18 @@ void thermal_zone_device_unregister(struct thermal_zone_device *tz) EXPORT_SYMBOL(thermal_zone_device_unregister); +#ifdef CONFIG_NET +static struct genl_family thermal_event_genl_family = { + .id = GENL_ID_GENERATE, + .name = THERMAL_GENL_FAMILY_NAME, + .version = THERMAL_GENL_VERSION, + .maxattr = THERMAL_GENL_ATTR_MAX, +}; + +static struct genl_multicast_group thermal_event_mcgrp = { + .name = THERMAL_GENL_MCAST_GROUP_NAME, +}; + int generate_netlink_event(u32 orig, enum events event) { struct sk_buff *skb; @@ -1301,6 +1299,15 @@ static int genetlink_init(void) return result; } +static void genetlink_exit(void) +{ + genl_unregister_family(&thermal_event_genl_family); +} +#else /* !CONFIG_NET */ +static inline int genetlink_init(void) { return 0; } +static inline void genetlink_exit(void) {} +#endif /* !CONFIG_NET */ + static int __init thermal_init(void) { int result = 0; @@ -1316,11 +1323,6 @@ static int __init thermal_init(void) return result; } -static void genetlink_exit(void) -{ - genl_unregister_family(&thermal_event_genl_family); -} - static void __exit thermal_exit(void) { class_unregister(&thermal_class); diff --git a/drivers/tty/hvc/Makefile b/drivers/tty/hvc/Makefile index e6bed5f..d79e7e9 100644 --- a/drivers/tty/hvc/Makefile +++ b/drivers/tty/hvc/Makefile @@ -10,4 +10,3 @@ obj-$(CONFIG_HVC_XEN) += hvc_xen.o obj-$(CONFIG_HVC_IUCV) += hvc_iucv.o obj-$(CONFIG_HVC_UDBG) += hvc_udbg.o obj-$(CONFIG_HVCS) += hvcs.o -obj-$(CONFIG_VIRTIO_CONSOLE) += virtio_console.o diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 44b8412..aa2e5d3 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2414,6 +2414,7 @@ static int gsmld_config(struct tty_struct *tty, struct gsm_mux *gsm, gsm->initiator = c->initiator; gsm->mru = c->mru; + gsm->mtu = c->mtu; gsm->encoding = c->encapsulation; gsm->adaption = c->adaption; gsm->n2 = c->n2; diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 47d3228..52fc0c9 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -581,8 +581,9 @@ static ssize_t n_hdlc_tty_read(struct tty_struct *tty, struct file *file, __u8 __user *buf, size_t nr) { struct n_hdlc *n_hdlc = tty2n_hdlc(tty); - int ret; + int ret = 0; struct n_hdlc_buf *rbuf; + DECLARE_WAITQUEUE(wait, current); if (debuglevel >= DEBUG_LEVEL_INFO) printk("%s(%d)n_hdlc_tty_read() called\n",__FILE__,__LINE__); @@ -598,57 +599,55 @@ static ssize_t n_hdlc_tty_read(struct tty_struct *tty, struct file *file, return -EFAULT; } - tty_lock(); + add_wait_queue(&tty->read_wait, &wait); for (;;) { if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) { - tty_unlock(); - return -EIO; + ret = -EIO; + break; } + if (tty_hung_up_p(file)) + break; - n_hdlc = tty2n_hdlc (tty); - if (!n_hdlc || n_hdlc->magic != HDLC_MAGIC || - tty != n_hdlc->tty) { - tty_unlock(); - return 0; - } + set_current_state(TASK_INTERRUPTIBLE); rbuf = n_hdlc_buf_get(&n_hdlc->rx_buf_list); - if (rbuf) + if (rbuf) { + if (rbuf->count > nr) { + /* too large for caller's buffer */ + ret = -EOVERFLOW; + } else { + if (copy_to_user(buf, rbuf->buf, rbuf->count)) + ret = -EFAULT; + else + ret = rbuf->count; + } + + if (n_hdlc->rx_free_buf_list.count > + DEFAULT_RX_BUF_COUNT) + kfree(rbuf); + else + n_hdlc_buf_put(&n_hdlc->rx_free_buf_list, rbuf); break; + } /* no data */ if (file->f_flags & O_NONBLOCK) { - tty_unlock(); - return -EAGAIN; + ret = -EAGAIN; + break; } - - interruptible_sleep_on (&tty->read_wait); + + schedule(); + if (signal_pending(current)) { - tty_unlock(); - return -EINTR; + ret = -EINTR; + break; } } - - if (rbuf->count > nr) - /* frame too large for caller's buffer (discard frame) */ - ret = -EOVERFLOW; - else { - /* Copy the data to the caller's buffer */ - if (copy_to_user(buf, rbuf->buf, rbuf->count)) - ret = -EFAULT; - else - ret = rbuf->count; - } - - /* return HDLC buffer to free list unless the free list */ - /* count has exceeded the default value, in which case the */ - /* buffer is freed back to the OS to conserve memory */ - if (n_hdlc->rx_free_buf_list.count > DEFAULT_RX_BUF_COUNT) - kfree(rbuf); - else - n_hdlc_buf_put(&n_hdlc->rx_free_buf_list,rbuf); - tty_unlock(); + + remove_wait_queue(&tty->read_wait, &wait); + __set_current_state(TASK_RUNNING); + return ret; } /* end of n_hdlc_tty_read() */ @@ -691,14 +690,15 @@ static ssize_t n_hdlc_tty_write(struct tty_struct *tty, struct file *file, count = maxframe; } - tty_lock(); - add_wait_queue(&tty->write_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); + + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); - /* Allocate transmit buffer */ - /* sleep until transmit buffer available */ - while (!(tbuf = n_hdlc_buf_get(&n_hdlc->tx_free_buf_list))) { + tbuf = n_hdlc_buf_get(&n_hdlc->tx_free_buf_list); + if (tbuf) + break; + if (file->f_flags & O_NONBLOCK) { error = -EAGAIN; break; @@ -719,7 +719,7 @@ static ssize_t n_hdlc_tty_write(struct tty_struct *tty, struct file *file, } } - set_current_state(TASK_RUNNING); + __set_current_state(TASK_RUNNING); remove_wait_queue(&tty->write_wait, &wait); if (!error) { @@ -731,7 +731,7 @@ static ssize_t n_hdlc_tty_write(struct tty_struct *tty, struct file *file, n_hdlc_buf_put(&n_hdlc->tx_buf_list,tbuf); n_hdlc_send_frames(n_hdlc,tty); } - tty_unlock(); + return error; } /* end of n_hdlc_tty_write() */ diff --git a/drivers/tty/serial/68328serial.c b/drivers/tty/serial/68328serial.c index be0ebce..de0160e 100644 --- a/drivers/tty/serial/68328serial.c +++ b/drivers/tty/serial/68328serial.c @@ -262,7 +262,7 @@ static void status_handle(struct m68k_serial *info, unsigned short status) static void receive_chars(struct m68k_serial *info, unsigned short rx) { - struct tty_struct *tty = info->port.tty; + struct tty_struct *tty = info->tty; m68328_uart *uart = &uart_addr[info->line]; unsigned char ch, flag; @@ -329,7 +329,7 @@ static void transmit_chars(struct m68k_serial *info) goto clear_and_return; } - if((info->xmit_cnt <= 0) || info->port.tty->stopped) { + if((info->xmit_cnt <= 0) || info->tty->stopped) { /* That's peculiar... TX ints off */ uart->ustcnt &= ~USTCNT_TX_INTR_MASK; goto clear_and_return; @@ -383,7 +383,7 @@ static void do_softint(struct work_struct *work) struct m68k_serial *info = container_of(work, struct m68k_serial, tqueue); struct tty_struct *tty; - tty = info->port.tty; + tty = info->tty; if (!tty) return; #if 0 @@ -407,7 +407,7 @@ static void do_serial_hangup(struct work_struct *work) struct m68k_serial *info = container_of(work, struct m68k_serial, tqueue_hangup); struct tty_struct *tty; - tty = info->port.tty; + tty = info->tty; if (!tty) return; @@ -451,8 +451,8 @@ static int startup(struct m68k_serial * info) uart->ustcnt = USTCNT_UEN | USTCNT_RXEN | USTCNT_RX_INTR_MASK; #endif - if (info->port.tty) - clear_bit(TTY_IO_ERROR, &info->port.tty->flags); + if (info->tty) + clear_bit(TTY_IO_ERROR, &info->tty->flags); info->xmit_cnt = info->xmit_head = info->xmit_tail = 0; /* @@ -486,8 +486,8 @@ static void shutdown(struct m68k_serial * info) info->xmit_buf = 0; } - if (info->port.tty) - set_bit(TTY_IO_ERROR, &info->port.tty->flags); + if (info->tty) + set_bit(TTY_IO_ERROR, &info->tty->flags); info->flags &= ~S_INITIALIZED; local_irq_restore(flags); @@ -553,9 +553,9 @@ static void change_speed(struct m68k_serial *info) unsigned cflag; int i; - if (!info->port.tty || !info->port.tty->termios) + if (!info->tty || !info->tty->termios) return; - cflag = info->port.tty->termios->c_cflag; + cflag = info->tty->termios->c_cflag; if (!(port = info->port)) return; @@ -970,7 +970,6 @@ static void send_break(struct m68k_serial * info, unsigned int duration) static int rs_ioctl(struct tty_struct *tty, struct file * file, unsigned int cmd, unsigned long arg) { - int error; struct m68k_serial * info = (struct m68k_serial *)tty->driver_data; int retval; @@ -1104,7 +1103,7 @@ static void rs_close(struct tty_struct *tty, struct file * filp) tty_ldisc_flush(tty); tty->closing = 0; info->event = 0; - info->port.tty = NULL; + info->tty = NULL; #warning "This is not and has never been valid so fix it" #if 0 if (tty->ldisc.num != ldiscs[N_TTY].num) { @@ -1142,7 +1141,7 @@ void rs_hangup(struct tty_struct *tty) info->event = 0; info->count = 0; info->flags &= ~S_NORMAL_ACTIVE; - info->port.tty = NULL; + info->tty = NULL; wake_up_interruptible(&info->open_wait); } @@ -1261,7 +1260,7 @@ int rs_open(struct tty_struct *tty, struct file * filp) info->count++; tty->driver_data = info; - info->port.tty = tty; + info->tty = tty; /* * Start up serial port @@ -1338,7 +1337,7 @@ rs68328_init(void) info = &m68k_soft[i]; info->magic = SERIAL_MAGIC; info->port = (int) &uart_addr[i]; - info->port.tty = NULL; + info->tty = NULL; info->irq = uart_irqs[i]; info->custom_divisor = 16; info->close_delay = 50; diff --git a/drivers/tty/serial/68360serial.c b/drivers/tty/serial/68360serial.c index 88b1335..bc21eea 100644 --- a/drivers/tty/serial/68360serial.c +++ b/drivers/tty/serial/68360serial.c @@ -2428,6 +2428,7 @@ static const struct tty_operations rs_360_ops = { /* .read_proc = rs_360_read_proc, */ .tiocmget = rs_360_tiocmget, .tiocmset = rs_360_tiocmset, + .get_icount = rs_360_get_icount, }; static int __init rs_360_init(void) diff --git a/drivers/tty/serial/8250.c b/drivers/tty/serial/8250.c index b25e6e4..3975df6 100644 --- a/drivers/tty/serial/8250.c +++ b/drivers/tty/serial/8250.c @@ -236,7 +236,8 @@ static const struct serial8250_config uart_config[] = { .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, - .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, + /* UART_CAP_EFR breaks billionon CF bluetooth card. */ + .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_16654] = { .name = "ST16654", diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index b1682d7..2b83346 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1518,6 +1518,7 @@ config SERIAL_BCM63XX_CONSOLE config SERIAL_GRLIB_GAISLER_APBUART tristate "GRLIB APBUART serial support" depends on OF + select SERIAL_CORE ---help--- Add support for the GRLIB APBUART serial port. diff --git a/drivers/tty/serial/bfin_5xx.c b/drivers/tty/serial/bfin_5xx.c index e381b89..9b1ff2b 100644 --- a/drivers/tty/serial/bfin_5xx.c +++ b/drivers/tty/serial/bfin_5xx.c @@ -370,10 +370,8 @@ static irqreturn_t bfin_serial_rx_int(int irq, void *dev_id) { struct bfin_serial_port *uart = dev_id; - spin_lock(&uart->port.lock); while (UART_GET_LSR(uart) & DR) bfin_serial_rx_chars(uart); - spin_unlock(&uart->port.lock); return IRQ_HANDLED; } @@ -490,9 +488,8 @@ void bfin_serial_rx_dma_timeout(struct bfin_serial_port *uart) { int x_pos, pos; - dma_disable_irq(uart->tx_dma_channel); - dma_disable_irq(uart->rx_dma_channel); - spin_lock_bh(&uart->port.lock); + dma_disable_irq_nosync(uart->rx_dma_channel); + spin_lock_bh(&uart->rx_lock); /* 2D DMA RX buffer ring is used. Because curr_y_count and * curr_x_count can't be read as an atomic operation, @@ -523,8 +520,7 @@ void bfin_serial_rx_dma_timeout(struct bfin_serial_port *uart) uart->rx_dma_buf.tail = uart->rx_dma_buf.head; } - spin_unlock_bh(&uart->port.lock); - dma_enable_irq(uart->tx_dma_channel); + spin_unlock_bh(&uart->rx_lock); dma_enable_irq(uart->rx_dma_channel); mod_timer(&(uart->rx_dma_timer), jiffies + DMA_RX_FLUSH_JIFFIES); @@ -571,7 +567,7 @@ static irqreturn_t bfin_serial_dma_rx_int(int irq, void *dev_id) unsigned short irqstat; int x_pos, pos; - spin_lock(&uart->port.lock); + spin_lock(&uart->rx_lock); irqstat = get_dma_curr_irqstat(uart->rx_dma_channel); clear_dma_irqstat(uart->rx_dma_channel); @@ -589,7 +585,7 @@ static irqreturn_t bfin_serial_dma_rx_int(int irq, void *dev_id) uart->rx_dma_buf.tail = uart->rx_dma_buf.head; } - spin_unlock(&uart->port.lock); + spin_unlock(&uart->rx_lock); return IRQ_HANDLED; } @@ -1332,6 +1328,7 @@ static int bfin_serial_probe(struct platform_device *pdev) } #ifdef CONFIG_SERIAL_BFIN_DMA + spin_lock_init(&uart->rx_lock); uart->tx_done = 1; uart->tx_count = 0; diff --git a/drivers/tty/serial/max3100.c b/drivers/tty/serial/max3100.c index beb1afa2..7b951ad 100644 --- a/drivers/tty/serial/max3100.c +++ b/drivers/tty/serial/max3100.c @@ -601,7 +601,7 @@ static int max3100_startup(struct uart_port *port) s->rts = 0; sprintf(b, "max3100-%d", s->minor); - s->workqueue = create_freezeable_workqueue(b); + s->workqueue = create_freezable_workqueue(b); if (!s->workqueue) { dev_warn(&s->spi->dev, "cannot create workqueue\n"); return -EBUSY; diff --git a/drivers/tty/serial/max3107.c b/drivers/tty/serial/max3107.c index 910870e..750b4f6 100644 --- a/drivers/tty/serial/max3107.c +++ b/drivers/tty/serial/max3107.c @@ -833,7 +833,7 @@ static int max3107_startup(struct uart_port *port) struct max3107_port *s = container_of(port, struct max3107_port, port); /* Initialize work queue */ - s->workqueue = create_freezeable_workqueue("max3107"); + s->workqueue = create_freezable_workqueue("max3107"); if (!s->workqueue) { dev_err(&s->spi->dev, "Workqueue creation failed\n"); return -EBUSY; diff --git a/drivers/tty/serial/serial_cs.c b/drivers/tty/serial/serial_cs.c index 93760b2..1ef4df9 100644 --- a/drivers/tty/serial/serial_cs.c +++ b/drivers/tty/serial/serial_cs.c @@ -712,6 +712,7 @@ static struct pcmcia_device_id serial_ids[] = { PCMCIA_PFC_DEVICE_PROD_ID12(1, "Xircom", "CreditCard Ethernet+Modem II", 0x2e3ee845, 0xeca401bf), PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x0e01), PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x0a05), + PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x0b05), PCMCIA_PFC_DEVICE_MANF_CARD(1, 0x0032, 0x1101), PCMCIA_MFC_DEVICE_MANF_CARD(0, 0x0104, 0x0070), PCMCIA_MFC_DEVICE_MANF_CARD(1, 0x0101, 0x0562), diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 8e0dd25..81f1395 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -571,6 +571,7 @@ struct sysrq_state { unsigned int alt_use; bool active; bool need_reinject; + bool reinjecting; }; static void sysrq_reinject_alt_sysrq(struct work_struct *work) @@ -581,6 +582,10 @@ static void sysrq_reinject_alt_sysrq(struct work_struct *work) unsigned int alt_code = sysrq->alt_use; if (sysrq->need_reinject) { + /* we do not want the assignment to be reordered */ + sysrq->reinjecting = true; + mb(); + /* Simulate press and release of Alt + SysRq */ input_inject_event(handle, EV_KEY, alt_code, 1); input_inject_event(handle, EV_KEY, KEY_SYSRQ, 1); @@ -589,6 +594,9 @@ static void sysrq_reinject_alt_sysrq(struct work_struct *work) input_inject_event(handle, EV_KEY, KEY_SYSRQ, 0); input_inject_event(handle, EV_KEY, alt_code, 0); input_inject_event(handle, EV_SYN, SYN_REPORT, 1); + + mb(); + sysrq->reinjecting = false; } } @@ -599,6 +607,13 @@ static bool sysrq_filter(struct input_handle *handle, bool was_active = sysrq->active; bool suppress; + /* + * Do not filter anything if we are in the process of re-injecting + * Alt+SysRq combination. + */ + if (sysrq->reinjecting) + return false; + switch (type) { case EV_SYN: @@ -629,7 +644,7 @@ static bool sysrq_filter(struct input_handle *handle, sysrq->alt_use = sysrq->alt; /* * If nothing else will be pressed we'll need - * to * re-inject Alt-SysRq keysroke. + * to re-inject Alt-SysRq keysroke. */ sysrq->need_reinject = true; } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 6158eae..0065da4 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3257,7 +3257,7 @@ static ssize_t show_cons_active(struct device *dev, ssize_t count = 0; console_lock(); - for (c = console_drivers; c; c = c->next) { + for_each_console(c) { if (!c->device) continue; if (!c->write) @@ -3306,7 +3306,7 @@ int __init tty_init(void) if (IS_ERR(consdev)) consdev = NULL; else - device_create_file(consdev, &dev_attr_active); + WARN_ON(device_create_file(consdev, &dev_attr_active) < 0); #ifdef CONFIG_VT vty_init(&console_fops); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index b230bd3..147ede34 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -2994,7 +2994,7 @@ int __init vty_init(const struct file_operations *console_fops) if (IS_ERR(tty0dev)) tty0dev = NULL; else - device_create_file(tty0dev, &dev_attr_active); + WARN_ON(device_create_file(tty0dev, &dev_attr_active) < 0); vcs_init(); @@ -3545,7 +3545,7 @@ int register_con_driver(const struct consw *csw, int first, int last) /* already registered */ if (con_driver->con == csw) - retval = -EINVAL; + retval = -EBUSY; } if (retval) @@ -3656,7 +3656,12 @@ int take_over_console(const struct consw *csw, int first, int last, int deflt) int err; err = register_con_driver(csw, first, last); - + /* if we get an busy error we still want to bind the console driver + * and return success, as we may have unbound the console driver + Â * but not unregistered it. + */ + if (err == -EBUSY) + err = 0; if (!err) bind_con_driver(csw, first, last, deflt); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index d6ede98..4ab49d4 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1607,6 +1607,7 @@ static const struct usb_device_id acm_ids[] = { { NOKIA_PCSUITE_ACM_INFO(0x0154), }, /* Nokia 5800 XpressMusic */ { NOKIA_PCSUITE_ACM_INFO(0x04ce), }, /* Nokia E90 */ { NOKIA_PCSUITE_ACM_INFO(0x01d4), }, /* Nokia E55 */ + { NOKIA_PCSUITE_ACM_INFO(0x0302), }, /* Nokia N8 */ { SAMSUNG_PCSUITE_ACM_INFO(0x6651), }, /* Samsung GTi8510 (INNOV8) */ /* NOTE: non-Nokia COMM/ACM/0xff is likely MSFT RNDIS... NOT a modem! */ diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 6ee4451..47085e5 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -342,7 +342,7 @@ static ssize_t wdm_write goto outnp; } - if (!file->f_flags && O_NONBLOCK) + if (!(file->f_flags & O_NONBLOCK)) r = wait_event_interruptible(desc->wait, !test_bit(WDM_IN_USE, &desc->flags)); else diff --git a/drivers/usb/core/endpoint.c b/drivers/usb/core/endpoint.c index 9da2505..df502a9 100644 --- a/drivers/usb/core/endpoint.c +++ b/drivers/usb/core/endpoint.c @@ -192,12 +192,12 @@ int usb_create_ep_devs(struct device *parent, ep_dev->dev.parent = parent; ep_dev->dev.release = ep_device_release; dev_set_name(&ep_dev->dev, "ep_%02x", endpoint->desc.bEndpointAddress); - device_enable_async_suspend(&ep_dev->dev); retval = device_register(&ep_dev->dev); if (retval) goto error_register; + device_enable_async_suspend(&ep_dev->dev); endpoint->ep_dev = ep_dev; return retval; diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index b55d460..f71e8e3 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -405,7 +405,12 @@ static int suspend_common(struct device *dev, bool do_wakeup) return retval; } - synchronize_irq(pci_dev->irq); + /* If MSI-X is enabled, the driver will have synchronized all vectors + * in pci_suspend(). If MSI or legacy PCI is enabled, that will be + * synchronized here. + */ + if (!hcd->msix_enabled) + synchronize_irq(pci_dev->irq); /* Downstream ports from this root hub should already be quiesced, so * there will be no DMA activity. Now we can shut down the upstream diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 6a95017..e935f71 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1955,7 +1955,6 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg) dev_dbg(&rhdev->dev, "usb %s%s\n", (msg.event & PM_EVENT_AUTO ? "auto-" : ""), "resume"); - clear_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags); if (!hcd->driver->bus_resume) return -ENOENT; if (hcd->state == HC_STATE_RUNNING) @@ -1963,6 +1962,7 @@ int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg) hcd->state = HC_STATE_RESUMING; status = hcd->driver->bus_resume(hcd); + clear_bit(HCD_FLAG_WAKEUP_PENDING, &hcd->flags); if (status == 0) { /* TRSMRCY = 10 msec */ msleep(10); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index b98efae..0f299b7 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -676,6 +676,8 @@ static void hub_init_func3(struct work_struct *ws); static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) { struct usb_device *hdev = hub->hdev; + struct usb_hcd *hcd; + int ret; int port1; int status; bool need_debounce_delay = false; @@ -714,6 +716,25 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) usb_autopm_get_interface_no_resume( to_usb_interface(hub->intfdev)); return; /* Continues at init2: below */ + } else if (type == HUB_RESET_RESUME) { + /* The internal host controller state for the hub device + * may be gone after a host power loss on system resume. + * Update the device's info so the HW knows it's a hub. + */ + hcd = bus_to_hcd(hdev->bus); + if (hcd->driver->update_hub_device) { + ret = hcd->driver->update_hub_device(hcd, hdev, + &hub->tt, GFP_NOIO); + if (ret < 0) { + dev_err(hub->intfdev, "Host not " + "accepting hub info " + "update.\n"); + dev_err(hub->intfdev, "LS/FS devices " + "and hubs may not work " + "under this hub\n."); + } + } + hub_power_on(hub, true); } else { hub_power_on(hub, true); } @@ -2660,17 +2681,13 @@ hub_port_init (struct usb_hub *hub, struct usb_device *udev, int port1, mutex_lock(&usb_address0_mutex); - if (!udev->config && oldspeed == USB_SPEED_SUPER) { - /* Don't reset USB 3.0 devices during an initial setup */ - usb_set_device_state(udev, USB_STATE_DEFAULT); - } else { - /* Reset the device; full speed may morph to high speed */ - /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */ - retval = hub_port_reset(hub, port1, udev, delay); - if (retval < 0) /* error or disconnect */ - goto fail; - /* success, speed is known */ - } + /* Reset the device; full speed may morph to high speed */ + /* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */ + retval = hub_port_reset(hub, port1, udev, delay); + if (retval < 0) /* error or disconnect */ + goto fail; + /* success, speed is known */ + retval = -ENODEV; if (oldspeed != USB_SPEED_UNKNOWN && oldspeed != udev->speed) { @@ -2732,6 +2749,11 @@ hub_port_init (struct usb_hub *hub, struct usb_device *udev, int port1, udev->ttport = hdev->ttport; } else if (udev->speed != USB_SPEED_HIGH && hdev->speed == USB_SPEED_HIGH) { + if (!hub->tt.hub) { + dev_err(&udev->dev, "parent hub has no TT\n"); + retval = -EINVAL; + goto fail; + } udev->tt = &hub->tt; udev->ttport = port1; } diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 44c5954..81ce6a8 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -48,6 +48,10 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x04b4, 0x0526), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Samsung Android phone modem - ID conflict with SPH-I500 */ + { USB_DEVICE(0x04e8, 0x6601), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* Roland SC-8820 */ { USB_DEVICE(0x0582, 0x0007), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -68,6 +72,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* M-Systems Flash Disk Pioneers */ { USB_DEVICE(0x08ec, 0x1000), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Keytouch QWERTY Panel keyboard */ + { USB_DEVICE(0x0926, 0x3333), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* X-Rite/Gretag-Macbeth Eye-One Pro display colorimeter */ { USB_DEVICE(0x0971, 0x2000), .driver_info = USB_QUIRK_NO_SET_INTF }, diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 1dc9739..d500996 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -509,7 +509,7 @@ config USB_LANGWELL select USB_GADGET_SELECTED config USB_GADGET_EG20T - boolean "Intel EG20T(Topcliff) USB Device controller" + boolean "Intel EG20T PCH/OKI SEMICONDUCTOR ML7213 IOH UDC" depends on PCI select USB_GADGET_DUALSPEED help @@ -525,6 +525,11 @@ config USB_GADGET_EG20T This driver dose not support interrupt transfer or isochronous transfer modes. + This driver also can be used for OKI SEMICONDUCTOR's ML7213 which is + for IVI(In-Vehicle Infotainment) use. + ML7213 is companion chip for Intel Atom E6xx series. + ML7213 is completely compatible for Intel EG20T PCH. + config USB_EG20T tristate depends on USB_GADGET_EG20T @@ -541,6 +546,8 @@ config USB_GADGET_CI13XXX_MSM ci13xxx_udc core. This driver depends on OTG driver for PHY initialization, clock management, powering up VBUS, and power management. + This driver is not supported on boards like trout which + has an external PHY. Say "y" to link the driver statically, or "m" to build a dynamically linked module called "ci13xxx_msm" and force all diff --git a/drivers/usb/gadget/ci13xxx_udc.c b/drivers/usb/gadget/ci13xxx_udc.c index 31656a2..a1c67ae 100644 --- a/drivers/usb/gadget/ci13xxx_udc.c +++ b/drivers/usb/gadget/ci13xxx_udc.c @@ -76,10 +76,21 @@ static DEFINE_SPINLOCK(udc_lock); /* control endpoint description */ static const struct usb_endpoint_descriptor -ctrl_endpt_desc = { +ctrl_endpt_out_desc = { .bLength = USB_DT_ENDPOINT_SIZE, .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_OUT, + .bmAttributes = USB_ENDPOINT_XFER_CONTROL, + .wMaxPacketSize = cpu_to_le16(CTRL_PAYLOAD_MAX), +}; + +static const struct usb_endpoint_descriptor +ctrl_endpt_in_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bEndpointAddress = USB_DIR_IN, .bmAttributes = USB_ENDPOINT_XFER_CONTROL, .wMaxPacketSize = cpu_to_le16(CTRL_PAYLOAD_MAX), }; @@ -265,10 +276,10 @@ static int hw_device_init(void __iomem *base) hw_bank.size /= sizeof(u32); reg = hw_aread(ABS_DCCPARAMS, DCCPARAMS_DEN) >> ffs_nr(DCCPARAMS_DEN); - if (reg == 0 || reg > ENDPT_MAX) - return -ENODEV; + hw_ep_max = reg * 2; /* cache hw ENDPT_MAX */ - hw_ep_max = reg; /* cache hw ENDPT_MAX */ + if (hw_ep_max == 0 || hw_ep_max > ENDPT_MAX) + return -ENODEV; /* setup lock mode ? */ @@ -1197,16 +1208,17 @@ static ssize_t show_qheads(struct device *dev, struct device_attribute *attr, } spin_lock_irqsave(udc->lock, flags); - for (i = 0; i < hw_ep_max; i++) { - struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[i]; + for (i = 0; i < hw_ep_max/2; i++) { + struct ci13xxx_ep *mEpRx = &udc->ci13xxx_ep[i]; + struct ci13xxx_ep *mEpTx = &udc->ci13xxx_ep[i + hw_ep_max/2]; n += scnprintf(buf + n, PAGE_SIZE - n, "EP=%02i: RX=%08X TX=%08X\n", - i, (u32)mEp->qh[RX].dma, (u32)mEp->qh[TX].dma); + i, (u32)mEpRx->qh.dma, (u32)mEpTx->qh.dma); for (j = 0; j < (sizeof(struct ci13xxx_qh)/sizeof(u32)); j++) { n += scnprintf(buf + n, PAGE_SIZE - n, " %04X: %08X %08X\n", j, - *((u32 *)mEp->qh[RX].ptr + j), - *((u32 *)mEp->qh[TX].ptr + j)); + *((u32 *)mEpRx->qh.ptr + j), + *((u32 *)mEpTx->qh.ptr + j)); } } spin_unlock_irqrestore(udc->lock, flags); @@ -1293,7 +1305,7 @@ static ssize_t show_requests(struct device *dev, struct device_attribute *attr, unsigned long flags; struct list_head *ptr = NULL; struct ci13xxx_req *req = NULL; - unsigned i, j, k, n = 0, qSize = sizeof(struct ci13xxx_td)/sizeof(u32); + unsigned i, j, n = 0, qSize = sizeof(struct ci13xxx_td)/sizeof(u32); dbg_trace("[%s] %p\n", __func__, buf); if (attr == NULL || buf == NULL) { @@ -1303,22 +1315,20 @@ static ssize_t show_requests(struct device *dev, struct device_attribute *attr, spin_lock_irqsave(udc->lock, flags); for (i = 0; i < hw_ep_max; i++) - for (k = RX; k <= TX; k++) - list_for_each(ptr, &udc->ci13xxx_ep[i].qh[k].queue) - { - req = list_entry(ptr, - struct ci13xxx_req, queue); + list_for_each(ptr, &udc->ci13xxx_ep[i].qh.queue) + { + req = list_entry(ptr, struct ci13xxx_req, queue); + + n += scnprintf(buf + n, PAGE_SIZE - n, + "EP=%02i: TD=%08X %s\n", + i % hw_ep_max/2, (u32)req->dma, + ((i < hw_ep_max/2) ? "RX" : "TX")); + for (j = 0; j < qSize; j++) n += scnprintf(buf + n, PAGE_SIZE - n, - "EP=%02i: TD=%08X %s\n", - i, (u32)req->dma, - ((k == RX) ? "RX" : "TX")); - - for (j = 0; j < qSize; j++) - n += scnprintf(buf + n, PAGE_SIZE - n, - " %04X: %08X\n", j, - *((u32 *)req->ptr + j)); - } + " %04X: %08X\n", j, + *((u32 *)req->ptr + j)); + } spin_unlock_irqrestore(udc->lock, flags); return n; @@ -1467,12 +1477,12 @@ static int _hardware_enqueue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq) * At this point it's guaranteed exclusive access to qhead * (endpt is not primed) so it's no need to use tripwire */ - mEp->qh[mEp->dir].ptr->td.next = mReq->dma; /* TERMINATE = 0 */ - mEp->qh[mEp->dir].ptr->td.token &= ~TD_STATUS; /* clear status */ + mEp->qh.ptr->td.next = mReq->dma; /* TERMINATE = 0 */ + mEp->qh.ptr->td.token &= ~TD_STATUS; /* clear status */ if (mReq->req.zero == 0) - mEp->qh[mEp->dir].ptr->cap |= QH_ZLT; + mEp->qh.ptr->cap |= QH_ZLT; else - mEp->qh[mEp->dir].ptr->cap &= ~QH_ZLT; + mEp->qh.ptr->cap &= ~QH_ZLT; wmb(); /* synchronize before ep prime */ @@ -1542,11 +1552,11 @@ __acquires(mEp->lock) hw_ep_flush(mEp->num, mEp->dir); - while (!list_empty(&mEp->qh[mEp->dir].queue)) { + while (!list_empty(&mEp->qh.queue)) { /* pop oldest request */ struct ci13xxx_req *mReq = \ - list_entry(mEp->qh[mEp->dir].queue.next, + list_entry(mEp->qh.queue.next, struct ci13xxx_req, queue); list_del_init(&mReq->queue); mReq->req.status = -ESHUTDOWN; @@ -1571,8 +1581,6 @@ static int _gadget_stop_activity(struct usb_gadget *gadget) { struct usb_ep *ep; struct ci13xxx *udc = container_of(gadget, struct ci13xxx, gadget); - struct ci13xxx_ep *mEp = container_of(gadget->ep0, - struct ci13xxx_ep, ep); trace("%p", gadget); @@ -1583,7 +1591,8 @@ static int _gadget_stop_activity(struct usb_gadget *gadget) gadget_for_each_ep(ep, gadget) { usb_ep_fifo_flush(ep); } - usb_ep_fifo_flush(gadget->ep0); + usb_ep_fifo_flush(&udc->ep0out.ep); + usb_ep_fifo_flush(&udc->ep0in.ep); udc->driver->disconnect(gadget); @@ -1591,11 +1600,12 @@ static int _gadget_stop_activity(struct usb_gadget *gadget) gadget_for_each_ep(ep, gadget) { usb_ep_disable(ep); } - usb_ep_disable(gadget->ep0); + usb_ep_disable(&udc->ep0out.ep); + usb_ep_disable(&udc->ep0in.ep); - if (mEp->status != NULL) { - usb_ep_free_request(gadget->ep0, mEp->status); - mEp->status = NULL; + if (udc->status != NULL) { + usb_ep_free_request(&udc->ep0in.ep, udc->status); + udc->status = NULL; } return 0; @@ -1614,7 +1624,6 @@ static void isr_reset_handler(struct ci13xxx *udc) __releases(udc->lock) __acquires(udc->lock) { - struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[0]; int retval; trace("%p", udc); @@ -1635,11 +1644,15 @@ __acquires(udc->lock) if (retval) goto done; - retval = usb_ep_enable(&mEp->ep, &ctrl_endpt_desc); + retval = usb_ep_enable(&udc->ep0out.ep, &ctrl_endpt_out_desc); + if (retval) + goto done; + + retval = usb_ep_enable(&udc->ep0in.ep, &ctrl_endpt_in_desc); if (!retval) { - mEp->status = usb_ep_alloc_request(&mEp->ep, GFP_ATOMIC); - if (mEp->status == NULL) { - usb_ep_disable(&mEp->ep); + udc->status = usb_ep_alloc_request(&udc->ep0in.ep, GFP_ATOMIC); + if (udc->status == NULL) { + usb_ep_disable(&udc->ep0out.ep); retval = -ENOMEM; } } @@ -1672,16 +1685,17 @@ static void isr_get_status_complete(struct usb_ep *ep, struct usb_request *req) /** * isr_get_status_response: get_status request response - * @ep: endpoint + * @udc: udc struct * @setup: setup request packet * * This function returns an error code */ -static int isr_get_status_response(struct ci13xxx_ep *mEp, +static int isr_get_status_response(struct ci13xxx *udc, struct usb_ctrlrequest *setup) __releases(mEp->lock) __acquires(mEp->lock) { + struct ci13xxx_ep *mEp = &udc->ep0in; struct usb_request *req = NULL; gfp_t gfp_flags = GFP_ATOMIC; int dir, num, retval; @@ -1736,27 +1750,23 @@ __acquires(mEp->lock) /** * isr_setup_status_phase: queues the status phase of a setup transation - * @mEp: endpoint + * @udc: udc struct * * This function returns an error code */ -static int isr_setup_status_phase(struct ci13xxx_ep *mEp) +static int isr_setup_status_phase(struct ci13xxx *udc) __releases(mEp->lock) __acquires(mEp->lock) { int retval; + struct ci13xxx_ep *mEp; - trace("%p", mEp); - - /* mEp is always valid & configured */ - - if (mEp->type == USB_ENDPOINT_XFER_CONTROL) - mEp->dir = (mEp->dir == TX) ? RX : TX; + trace("%p", udc); - mEp->status->no_interrupt = 1; + mEp = (udc->ep0_dir == TX) ? &udc->ep0out : &udc->ep0in; spin_unlock(mEp->lock); - retval = usb_ep_queue(&mEp->ep, mEp->status, GFP_ATOMIC); + retval = usb_ep_queue(&mEp->ep, udc->status, GFP_ATOMIC); spin_lock(mEp->lock); return retval; @@ -1778,11 +1788,11 @@ __acquires(mEp->lock) trace("%p", mEp); - if (list_empty(&mEp->qh[mEp->dir].queue)) + if (list_empty(&mEp->qh.queue)) return -EINVAL; /* pop oldest request */ - mReq = list_entry(mEp->qh[mEp->dir].queue.next, + mReq = list_entry(mEp->qh.queue.next, struct ci13xxx_req, queue); list_del_init(&mReq->queue); @@ -1794,10 +1804,10 @@ __acquires(mEp->lock) dbg_done(_usb_addr(mEp), mReq->ptr->token, retval); - if (!list_empty(&mEp->qh[mEp->dir].queue)) { + if (!list_empty(&mEp->qh.queue)) { struct ci13xxx_req* mReqEnq; - mReqEnq = list_entry(mEp->qh[mEp->dir].queue.next, + mReqEnq = list_entry(mEp->qh.queue.next, struct ci13xxx_req, queue); _hardware_enqueue(mEp, mReqEnq); } @@ -1836,16 +1846,14 @@ __acquires(udc->lock) int type, num, err = -EINVAL; struct usb_ctrlrequest req; - if (mEp->desc == NULL) continue; /* not configured */ - if ((mEp->dir == RX && hw_test_and_clear_complete(i)) || - (mEp->dir == TX && hw_test_and_clear_complete(i + 16))) { + if (hw_test_and_clear_complete(i)) { err = isr_tr_complete_low(mEp); if (mEp->type == USB_ENDPOINT_XFER_CONTROL) { if (err > 0) /* needs status phase */ - err = isr_setup_status_phase(mEp); + err = isr_setup_status_phase(udc); if (err < 0) { dbg_event(_usb_addr(mEp), "ERROR", err); @@ -1866,15 +1874,22 @@ __acquires(udc->lock) continue; } + /* + * Flush data and handshake transactions of previous + * setup packet. + */ + _ep_nuke(&udc->ep0out); + _ep_nuke(&udc->ep0in); + /* read_setup_packet */ do { hw_test_and_set_setup_guard(); - memcpy(&req, &mEp->qh[RX].ptr->setup, sizeof(req)); + memcpy(&req, &mEp->qh.ptr->setup, sizeof(req)); } while (!hw_test_and_clear_setup_guard()); type = req.bRequestType; - mEp->dir = (type & USB_DIR_IN) ? TX : RX; + udc->ep0_dir = (type & USB_DIR_IN) ? TX : RX; dbg_setup(_usb_addr(mEp), &req); @@ -1895,7 +1910,7 @@ __acquires(udc->lock) if (err) break; } - err = isr_setup_status_phase(mEp); + err = isr_setup_status_phase(udc); break; case USB_REQ_GET_STATUS: if (type != (USB_DIR_IN|USB_RECIP_DEVICE) && @@ -1905,7 +1920,7 @@ __acquires(udc->lock) if (le16_to_cpu(req.wLength) != 2 || le16_to_cpu(req.wValue) != 0) break; - err = isr_get_status_response(mEp, &req); + err = isr_get_status_response(udc, &req); break; case USB_REQ_SET_ADDRESS: if (type != (USB_DIR_OUT|USB_RECIP_DEVICE)) @@ -1916,7 +1931,7 @@ __acquires(udc->lock) err = hw_usb_set_address((u8)le16_to_cpu(req.wValue)); if (err) break; - err = isr_setup_status_phase(mEp); + err = isr_setup_status_phase(udc); break; case USB_REQ_SET_FEATURE: if (type != (USB_DIR_OUT|USB_RECIP_ENDPOINT) && @@ -1932,12 +1947,12 @@ __acquires(udc->lock) spin_lock(udc->lock); if (err) break; - err = isr_setup_status_phase(mEp); + err = isr_setup_status_phase(udc); break; default: delegate: if (req.wLength == 0) /* no data phase */ - mEp->dir = TX; + udc->ep0_dir = TX; spin_unlock(udc->lock); err = udc->driver->setup(&udc->gadget, &req); @@ -1968,7 +1983,7 @@ static int ep_enable(struct usb_ep *ep, const struct usb_endpoint_descriptor *desc) { struct ci13xxx_ep *mEp = container_of(ep, struct ci13xxx_ep, ep); - int direction, retval = 0; + int retval = 0; unsigned long flags; trace("%p, %p", ep, desc); @@ -1982,7 +1997,7 @@ static int ep_enable(struct usb_ep *ep, mEp->desc = desc; - if (!list_empty(&mEp->qh[mEp->dir].queue)) + if (!list_empty(&mEp->qh.queue)) warn("enabling a non-empty endpoint!"); mEp->dir = usb_endpoint_dir_in(desc) ? TX : RX; @@ -1991,29 +2006,22 @@ static int ep_enable(struct usb_ep *ep, mEp->ep.maxpacket = __constant_le16_to_cpu(desc->wMaxPacketSize); - direction = mEp->dir; - do { - dbg_event(_usb_addr(mEp), "ENABLE", 0); + dbg_event(_usb_addr(mEp), "ENABLE", 0); - mEp->qh[mEp->dir].ptr->cap = 0; + mEp->qh.ptr->cap = 0; - if (mEp->type == USB_ENDPOINT_XFER_CONTROL) - mEp->qh[mEp->dir].ptr->cap |= QH_IOS; - else if (mEp->type == USB_ENDPOINT_XFER_ISOC) - mEp->qh[mEp->dir].ptr->cap &= ~QH_MULT; - else - mEp->qh[mEp->dir].ptr->cap &= ~QH_ZLT; - - mEp->qh[mEp->dir].ptr->cap |= - (mEp->ep.maxpacket << ffs_nr(QH_MAX_PKT)) & QH_MAX_PKT; - mEp->qh[mEp->dir].ptr->td.next |= TD_TERMINATE; /* needed? */ - - retval |= hw_ep_enable(mEp->num, mEp->dir, mEp->type); + if (mEp->type == USB_ENDPOINT_XFER_CONTROL) + mEp->qh.ptr->cap |= QH_IOS; + else if (mEp->type == USB_ENDPOINT_XFER_ISOC) + mEp->qh.ptr->cap &= ~QH_MULT; + else + mEp->qh.ptr->cap &= ~QH_ZLT; - if (mEp->type == USB_ENDPOINT_XFER_CONTROL) - mEp->dir = (mEp->dir == TX) ? RX : TX; + mEp->qh.ptr->cap |= + (mEp->ep.maxpacket << ffs_nr(QH_MAX_PKT)) & QH_MAX_PKT; + mEp->qh.ptr->td.next |= TD_TERMINATE; /* needed? */ - } while (mEp->dir != direction); + retval |= hw_ep_enable(mEp->num, mEp->dir, mEp->type); spin_unlock_irqrestore(mEp->lock, flags); return retval; @@ -2146,7 +2154,7 @@ static int ep_queue(struct usb_ep *ep, struct usb_request *req, spin_lock_irqsave(mEp->lock, flags); if (mEp->type == USB_ENDPOINT_XFER_CONTROL && - !list_empty(&mEp->qh[mEp->dir].queue)) { + !list_empty(&mEp->qh.queue)) { _ep_nuke(mEp); retval = -EOVERFLOW; warn("endpoint ctrl %X nuked", _usb_addr(mEp)); @@ -2170,9 +2178,9 @@ static int ep_queue(struct usb_ep *ep, struct usb_request *req, /* push request */ mReq->req.status = -EINPROGRESS; mReq->req.actual = 0; - list_add_tail(&mReq->queue, &mEp->qh[mEp->dir].queue); + list_add_tail(&mReq->queue, &mEp->qh.queue); - if (list_is_singular(&mEp->qh[mEp->dir].queue)) + if (list_is_singular(&mEp->qh.queue)) retval = _hardware_enqueue(mEp, mReq); if (retval == -EALREADY) { @@ -2199,7 +2207,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req) trace("%p, %p", ep, req); if (ep == NULL || req == NULL || mEp->desc == NULL || - list_empty(&mReq->queue) || list_empty(&mEp->qh[mEp->dir].queue)) + list_empty(&mReq->queue) || list_empty(&mEp->qh.queue)) return -EINVAL; spin_lock_irqsave(mEp->lock, flags); @@ -2244,7 +2252,7 @@ static int ep_set_halt(struct usb_ep *ep, int value) #ifndef STALL_IN /* g_file_storage MS compliant but g_zero fails chapter 9 compliance */ if (value && mEp->type == USB_ENDPOINT_XFER_BULK && mEp->dir == TX && - !list_empty(&mEp->qh[mEp->dir].queue)) { + !list_empty(&mEp->qh.queue)) { spin_unlock_irqrestore(mEp->lock, flags); return -EAGAIN; } @@ -2355,7 +2363,7 @@ static int ci13xxx_vbus_session(struct usb_gadget *_gadget, int is_active) if (is_active) { pm_runtime_get_sync(&_gadget->dev); hw_device_reset(udc); - hw_device_state(udc->ci13xxx_ep[0].qh[RX].dma); + hw_device_state(udc->ep0out.qh.dma); } else { hw_device_state(0); if (udc->udc_driver->notify_event) @@ -2390,7 +2398,8 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver, int (*bind)(struct usb_gadget *)) { struct ci13xxx *udc = _udc; - unsigned long i, k, flags; + unsigned long flags; + int i, j; int retval = -ENOMEM; trace("%p", driver); @@ -2427,45 +2436,46 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver, info("hw_ep_max = %d", hw_ep_max); - udc->driver = driver; udc->gadget.dev.driver = NULL; retval = 0; - for (i = 0; i < hw_ep_max; i++) { - struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[i]; + for (i = 0; i < hw_ep_max/2; i++) { + for (j = RX; j <= TX; j++) { + int k = i + j * hw_ep_max/2; + struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[k]; - scnprintf(mEp->name, sizeof(mEp->name), "ep%i", (int)i); + scnprintf(mEp->name, sizeof(mEp->name), "ep%i%s", i, + (j == TX) ? "in" : "out"); - mEp->lock = udc->lock; - mEp->device = &udc->gadget.dev; - mEp->td_pool = udc->td_pool; + mEp->lock = udc->lock; + mEp->device = &udc->gadget.dev; + mEp->td_pool = udc->td_pool; - mEp->ep.name = mEp->name; - mEp->ep.ops = &usb_ep_ops; - mEp->ep.maxpacket = CTRL_PAYLOAD_MAX; + mEp->ep.name = mEp->name; + mEp->ep.ops = &usb_ep_ops; + mEp->ep.maxpacket = CTRL_PAYLOAD_MAX; - /* this allocation cannot be random */ - for (k = RX; k <= TX; k++) { - INIT_LIST_HEAD(&mEp->qh[k].queue); + INIT_LIST_HEAD(&mEp->qh.queue); spin_unlock_irqrestore(udc->lock, flags); - mEp->qh[k].ptr = dma_pool_alloc(udc->qh_pool, - GFP_KERNEL, - &mEp->qh[k].dma); + mEp->qh.ptr = dma_pool_alloc(udc->qh_pool, GFP_KERNEL, + &mEp->qh.dma); spin_lock_irqsave(udc->lock, flags); - if (mEp->qh[k].ptr == NULL) + if (mEp->qh.ptr == NULL) retval = -ENOMEM; else - memset(mEp->qh[k].ptr, 0, - sizeof(*mEp->qh[k].ptr)); - } - if (i == 0) - udc->gadget.ep0 = &mEp->ep; - else + memset(mEp->qh.ptr, 0, sizeof(*mEp->qh.ptr)); + + /* skip ep0 out and in endpoints */ + if (i == 0) + continue; + list_add_tail(&mEp->ep.ep_list, &udc->gadget.ep_list); + } } if (retval) goto done; + udc->gadget.ep0 = &udc->ep0in.ep; /* bind gadget */ driver->driver.bus = NULL; udc->gadget.dev.driver = &driver->driver; @@ -2479,6 +2489,7 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver, goto done; } + udc->driver = driver; pm_runtime_get_sync(&udc->gadget.dev); if (udc->udc_driver->flags & CI13XXX_PULLUP_ON_VBUS) { if (udc->vbus_active) { @@ -2490,14 +2501,12 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver, } } - retval = hw_device_state(udc->ci13xxx_ep[0].qh[RX].dma); + retval = hw_device_state(udc->ep0out.qh.dma); if (retval) pm_runtime_put_sync(&udc->gadget.dev); done: spin_unlock_irqrestore(udc->lock, flags); - if (retval) - usb_gadget_unregister_driver(driver); return retval; } EXPORT_SYMBOL(usb_gadget_probe_driver); @@ -2510,7 +2519,7 @@ EXPORT_SYMBOL(usb_gadget_probe_driver); int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) { struct ci13xxx *udc = _udc; - unsigned long i, k, flags; + unsigned long i, flags; trace("%p", driver); @@ -2546,17 +2555,14 @@ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) for (i = 0; i < hw_ep_max; i++) { struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[i]; - if (i == 0) - udc->gadget.ep0 = NULL; - else if (!list_empty(&mEp->ep.ep_list)) + if (!list_empty(&mEp->ep.ep_list)) list_del_init(&mEp->ep.ep_list); - for (k = RX; k <= TX; k++) - if (mEp->qh[k].ptr != NULL) - dma_pool_free(udc->qh_pool, - mEp->qh[k].ptr, mEp->qh[k].dma); + if (mEp->qh.ptr != NULL) + dma_pool_free(udc->qh_pool, mEp->qh.ptr, mEp->qh.dma); } + udc->gadget.ep0 = NULL; udc->driver = NULL; spin_unlock_irqrestore(udc->lock, flags); diff --git a/drivers/usb/gadget/ci13xxx_udc.h b/drivers/usb/gadget/ci13xxx_udc.h index f61fed0..a2492b6 100644 --- a/drivers/usb/gadget/ci13xxx_udc.h +++ b/drivers/usb/gadget/ci13xxx_udc.h @@ -20,7 +20,7 @@ * DEFINE *****************************************************************************/ #define CI13XXX_PAGE_SIZE 4096ul /* page size for TD's */ -#define ENDPT_MAX (16) +#define ENDPT_MAX (32) #define CTRL_PAYLOAD_MAX (64) #define RX (0) /* similar to USB_DIR_OUT but can be used as an index */ #define TX (1) /* similar to USB_DIR_IN but can be used as an index */ @@ -88,8 +88,7 @@ struct ci13xxx_ep { struct list_head queue; struct ci13xxx_qh *ptr; dma_addr_t dma; - } qh[2]; - struct usb_request *status; + } qh; int wedge; /* global resources */ @@ -119,9 +118,13 @@ struct ci13xxx { struct dma_pool *qh_pool; /* DMA pool for queue heads */ struct dma_pool *td_pool; /* DMA pool for transfer descs */ + struct usb_request *status; /* ep0 status request */ struct usb_gadget gadget; /* USB slave device */ struct ci13xxx_ep ci13xxx_ep[ENDPT_MAX]; /* extended endpts */ + u32 ep0_dir; /* ep0 direction */ +#define ep0out ci13xxx_ep[0] +#define ep0in ci13xxx_ep[16] struct usb_gadget_driver *driver; /* 3rd party gadget driver */ struct ci13xxx_udc_driver *udc_driver; /* device controller driver */ diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index f6ff845..1ba4bef 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -928,8 +928,9 @@ unknown: */ switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_INTERFACE: - if (cdev->config) - f = cdev->config->interface[intf]; + if (!cdev->config || w_index >= MAX_CONFIG_INTERFACES) + break; + f = cdev->config->interface[intf]; break; case USB_RECIP_ENDPOINT: diff --git a/drivers/usb/gadget/f_mass_storage.c b/drivers/usb/gadget/f_mass_storage.c index b5dbb23..6d8e533 100644 --- a/drivers/usb/gadget/f_mass_storage.c +++ b/drivers/usb/gadget/f_mass_storage.c @@ -293,6 +293,7 @@ #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> +#include <linux/usb/composite.h> #include "gadget_chips.h" @@ -2763,7 +2764,7 @@ static struct fsg_common *fsg_common_init(struct fsg_common *common, return ERR_PTR(-ENOMEM); common->free_storage_on_release = 1; } else { - memset(common, 0, sizeof common); + memset(common, 0, sizeof *common); common->free_storage_on_release = 0; } diff --git a/drivers/usb/gadget/f_phonet.c b/drivers/usb/gadget/f_phonet.c index 3c6e1a0..5e14950 100644 --- a/drivers/usb/gadget/f_phonet.c +++ b/drivers/usb/gadget/f_phonet.c @@ -346,14 +346,19 @@ static void pn_rx_complete(struct usb_ep *ep, struct usb_request *req) if (unlikely(!skb)) break; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, 0, - req->actual); - page = NULL; - if (req->actual < req->length) { /* Last fragment */ + if (skb->len == 0) { /* First fragment */ skb->protocol = htons(ETH_P_PHONET); skb_reset_mac_header(skb); - pskb_pull(skb, 1); + /* Can't use pskb_pull() on page in IRQ */ + memcpy(skb_put(skb, 1), page_address(page), 1); + } + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + skb->len == 0, req->actual); + page = NULL; + + if (req->actual < req->length) { /* Last fragment */ skb->dev = dev; dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c index 0c8dd81..b120dbb 100644 --- a/drivers/usb/gadget/pch_udc.c +++ b/drivers/usb/gadget/pch_udc.c @@ -198,10 +198,10 @@ #define PCH_UDC_BRLEN 0x0F /* Burst length */ #define PCH_UDC_THLEN 0x1F /* Threshold length */ /* Value of EP Buffer Size */ -#define UDC_EP0IN_BUFF_SIZE 64 -#define UDC_EPIN_BUFF_SIZE 512 -#define UDC_EP0OUT_BUFF_SIZE 64 -#define UDC_EPOUT_BUFF_SIZE 512 +#define UDC_EP0IN_BUFF_SIZE 16 +#define UDC_EPIN_BUFF_SIZE 256 +#define UDC_EP0OUT_BUFF_SIZE 16 +#define UDC_EPOUT_BUFF_SIZE 256 /* Value of EP maximum packet size */ #define UDC_EP0IN_MAX_PKT_SIZE 64 #define UDC_EP0OUT_MAX_PKT_SIZE 64 @@ -351,7 +351,7 @@ struct pch_udc_dev { struct pci_pool *data_requests; struct pci_pool *stp_requests; dma_addr_t dma_addr; - unsigned long ep0out_buf[64]; + void *ep0out_buf; struct usb_ctrlrequest setup_data; unsigned long phys_addr; void __iomem *base_addr; @@ -361,6 +361,8 @@ struct pch_udc_dev { #define PCH_UDC_PCI_BAR 1 #define PCI_DEVICE_ID_INTEL_EG20T_UDC 0x8808 +#define PCI_VENDOR_ID_ROHM 0x10DB +#define PCI_DEVICE_ID_ML7213_IOH_UDC 0x801D static const char ep0_string[] = "ep0in"; static DEFINE_SPINLOCK(udc_stall_spinlock); /* stall spin lock */ @@ -1219,11 +1221,11 @@ static void complete_req(struct pch_udc_ep *ep, struct pch_udc_request *req, dev = ep->dev; if (req->dma_mapped) { if (ep->in) - pci_unmap_single(dev->pdev, req->req.dma, - req->req.length, PCI_DMA_TODEVICE); + dma_unmap_single(&dev->pdev->dev, req->req.dma, + req->req.length, DMA_TO_DEVICE); else - pci_unmap_single(dev->pdev, req->req.dma, - req->req.length, PCI_DMA_FROMDEVICE); + dma_unmap_single(&dev->pdev->dev, req->req.dma, + req->req.length, DMA_FROM_DEVICE); req->dma_mapped = 0; req->req.dma = DMA_ADDR_INVALID; } @@ -1414,7 +1416,6 @@ static void pch_udc_start_rxrequest(struct pch_udc_ep *ep, pch_udc_clear_dma(ep->dev, DMA_DIR_RX); td_data = req->td_data; - ep->td_data = req->td_data; /* Set the status bits for all descriptors */ while (1) { td_data->status = (td_data->status & ~PCH_UDC_BUFF_STS) | @@ -1613,15 +1614,19 @@ static int pch_udc_pcd_queue(struct usb_ep *usbep, struct usb_request *usbreq, if (usbreq->length && ((usbreq->dma == DMA_ADDR_INVALID) || !usbreq->dma)) { if (ep->in) - usbreq->dma = pci_map_single(dev->pdev, usbreq->buf, - usbreq->length, PCI_DMA_TODEVICE); + usbreq->dma = dma_map_single(&dev->pdev->dev, + usbreq->buf, + usbreq->length, + DMA_TO_DEVICE); else - usbreq->dma = pci_map_single(dev->pdev, usbreq->buf, - usbreq->length, PCI_DMA_FROMDEVICE); + usbreq->dma = dma_map_single(&dev->pdev->dev, + usbreq->buf, + usbreq->length, + DMA_FROM_DEVICE); req->dma_mapped = 1; } if (usbreq->length > 0) { - retval = prepare_dma(ep, req, gfp); + retval = prepare_dma(ep, req, GFP_ATOMIC); if (retval) goto probe_end; } @@ -1646,7 +1651,6 @@ static int pch_udc_pcd_queue(struct usb_ep *usbep, struct usb_request *usbreq, pch_udc_wait_ep_stall(ep); pch_udc_ep_clear_nak(ep); pch_udc_enable_ep_interrupts(ep->dev, (1 << ep->num)); - pch_udc_set_dma(dev, DMA_DIR_TX); } } /* Now add this request to the ep's pending requests */ @@ -1926,6 +1930,7 @@ static void pch_udc_complete_receiver(struct pch_udc_ep *ep) PCH_UDC_BS_DMA_DONE) return; pch_udc_clear_dma(ep->dev, DMA_DIR_RX); + pch_udc_ep_set_ddptr(ep, 0); if ((req->td_data_last->status & PCH_UDC_RXTX_STS) != PCH_UDC_RTS_SUCC) { dev_err(&dev->pdev->dev, "Invalid RXTX status (0x%08x) " @@ -1963,7 +1968,7 @@ static void pch_udc_svc_data_in(struct pch_udc_dev *dev, int ep_num) u32 epsts; struct pch_udc_ep *ep; - ep = &dev->ep[2*ep_num]; + ep = &dev->ep[UDC_EPIN_IDX(ep_num)]; epsts = ep->epsts; ep->epsts = 0; @@ -2008,7 +2013,7 @@ static void pch_udc_svc_data_out(struct pch_udc_dev *dev, int ep_num) struct pch_udc_ep *ep; struct pch_udc_request *req = NULL; - ep = &dev->ep[2*ep_num + 1]; + ep = &dev->ep[UDC_EPOUT_IDX(ep_num)]; epsts = ep->epsts; ep->epsts = 0; @@ -2025,10 +2030,11 @@ static void pch_udc_svc_data_out(struct pch_udc_dev *dev, int ep_num) } if (epsts & UDC_EPSTS_HE) return; - if (epsts & UDC_EPSTS_RSS) + if (epsts & UDC_EPSTS_RSS) { pch_udc_ep_set_stall(ep); pch_udc_enable_ep_interrupts(ep->dev, PCH_UDC_EPINT(ep->in, ep->num)); + } if (epsts & UDC_EPSTS_RCS) { if (!dev->prot_stall) { pch_udc_ep_clear_stall(ep); @@ -2060,8 +2066,10 @@ static void pch_udc_svc_control_in(struct pch_udc_dev *dev) { u32 epsts; struct pch_udc_ep *ep; + struct pch_udc_ep *ep_out; ep = &dev->ep[UDC_EP0IN_IDX]; + ep_out = &dev->ep[UDC_EP0OUT_IDX]; epsts = ep->epsts; ep->epsts = 0; @@ -2073,8 +2081,16 @@ static void pch_udc_svc_control_in(struct pch_udc_dev *dev) return; if (epsts & UDC_EPSTS_HE) return; - if ((epsts & UDC_EPSTS_TDC) && (!dev->stall)) + if ((epsts & UDC_EPSTS_TDC) && (!dev->stall)) { pch_udc_complete_transfer(ep); + pch_udc_clear_dma(dev, DMA_DIR_RX); + ep_out->td_data->status = (ep_out->td_data->status & + ~PCH_UDC_BUFF_STS) | + PCH_UDC_BS_HST_RDY; + pch_udc_ep_clear_nak(ep_out); + pch_udc_set_dma(dev, DMA_DIR_RX); + pch_udc_ep_set_rrdy(ep_out); + } /* On IN interrupt, provide data if we have any */ if ((epsts & UDC_EPSTS_IN) && !(epsts & UDC_EPSTS_TDC) && !(epsts & UDC_EPSTS_TXEMPTY)) @@ -2102,11 +2118,9 @@ static void pch_udc_svc_control_out(struct pch_udc_dev *dev) dev->stall = 0; dev->ep[UDC_EP0IN_IDX].halted = 0; dev->ep[UDC_EP0OUT_IDX].halted = 0; - /* In data not ready */ - pch_udc_ep_set_nak(&(dev->ep[UDC_EP0IN_IDX])); dev->setup_data = ep->td_stp->request; pch_udc_init_setup_buff(ep->td_stp); - pch_udc_clear_dma(dev, DMA_DIR_TX); + pch_udc_clear_dma(dev, DMA_DIR_RX); pch_udc_ep_fifo_flush(&(dev->ep[UDC_EP0IN_IDX]), dev->ep[UDC_EP0IN_IDX].in); if ((dev->setup_data.bRequestType & USB_DIR_IN)) @@ -2122,14 +2136,23 @@ static void pch_udc_svc_control_out(struct pch_udc_dev *dev) setup_supported = dev->driver->setup(&dev->gadget, &dev->setup_data); spin_lock(&dev->lock); + + if (dev->setup_data.bRequestType & USB_DIR_IN) { + ep->td_data->status = (ep->td_data->status & + ~PCH_UDC_BUFF_STS) | + PCH_UDC_BS_HST_RDY; + pch_udc_ep_set_ddptr(ep, ep->td_data_phys); + } /* ep0 in returns data on IN phase */ if (setup_supported >= 0 && setup_supported < UDC_EP0IN_MAX_PKT_SIZE) { pch_udc_ep_clear_nak(&(dev->ep[UDC_EP0IN_IDX])); /* Gadget would have queued a request when * we called the setup */ - pch_udc_set_dma(dev, DMA_DIR_RX); - pch_udc_ep_clear_nak(ep); + if (!(dev->setup_data.bRequestType & USB_DIR_IN)) { + pch_udc_set_dma(dev, DMA_DIR_RX); + pch_udc_ep_clear_nak(ep); + } } else if (setup_supported < 0) { /* if unsupported request, then stall */ pch_udc_ep_set_stall(&(dev->ep[UDC_EP0IN_IDX])); @@ -2142,22 +2165,13 @@ static void pch_udc_svc_control_out(struct pch_udc_dev *dev) } } else if ((((stat & UDC_EPSTS_OUT_MASK) >> UDC_EPSTS_OUT_SHIFT) == UDC_EPSTS_OUT_DATA) && !dev->stall) { - if (list_empty(&ep->queue)) { - dev_err(&dev->pdev->dev, "%s: No request\n", __func__); - ep->td_data->status = (ep->td_data->status & - ~PCH_UDC_BUFF_STS) | - PCH_UDC_BS_HST_RDY; - pch_udc_set_dma(dev, DMA_DIR_RX); - } else { - /* control write */ - /* next function will pickuo an clear the status */ + pch_udc_clear_dma(dev, DMA_DIR_RX); + pch_udc_ep_set_ddptr(ep, 0); + if (!list_empty(&ep->queue)) { ep->epsts = stat; - - pch_udc_svc_data_out(dev, 0); - /* re-program desc. pointer for possible ZLPs */ - pch_udc_ep_set_ddptr(ep, ep->td_data_phys); - pch_udc_set_dma(dev, DMA_DIR_RX); + pch_udc_svc_data_out(dev, PCH_UDC_EP0); } + pch_udc_set_dma(dev, DMA_DIR_RX); } pch_udc_ep_set_rrdy(ep); } @@ -2174,7 +2188,7 @@ static void pch_udc_postsvc_epinters(struct pch_udc_dev *dev, int ep_num) struct pch_udc_ep *ep; struct pch_udc_request *req; - ep = &dev->ep[2*ep_num]; + ep = &dev->ep[UDC_EPIN_IDX(ep_num)]; if (!list_empty(&ep->queue)) { req = list_entry(ep->queue.next, struct pch_udc_request, queue); pch_udc_enable_ep_interrupts(ep->dev, @@ -2196,13 +2210,13 @@ static void pch_udc_read_all_epstatus(struct pch_udc_dev *dev, u32 ep_intr) for (i = 0; i < PCH_UDC_USED_EP_NUM; i++) { /* IN */ if (ep_intr & (0x1 << i)) { - ep = &dev->ep[2*i]; + ep = &dev->ep[UDC_EPIN_IDX(i)]; ep->epsts = pch_udc_read_ep_status(ep); pch_udc_clear_ep_status(ep, ep->epsts); } /* OUT */ if (ep_intr & (0x10000 << i)) { - ep = &dev->ep[2*i+1]; + ep = &dev->ep[UDC_EPOUT_IDX(i)]; ep->epsts = pch_udc_read_ep_status(ep); pch_udc_clear_ep_status(ep, ep->epsts); } @@ -2563,9 +2577,6 @@ static void pch_udc_pcd_reinit(struct pch_udc_dev *dev) dev->ep[UDC_EP0IN_IDX].ep.maxpacket = UDC_EP0IN_MAX_PKT_SIZE; dev->ep[UDC_EP0OUT_IDX].ep.maxpacket = UDC_EP0OUT_MAX_PKT_SIZE; - dev->dma_addr = pci_map_single(dev->pdev, dev->ep0out_buf, 256, - PCI_DMA_FROMDEVICE); - /* remove ep0 in and out from the list. They have own pointer */ list_del_init(&dev->ep[UDC_EP0IN_IDX].ep.ep_list); list_del_init(&dev->ep[UDC_EP0OUT_IDX].ep.ep_list); @@ -2637,6 +2648,13 @@ static int init_dma_pools(struct pch_udc_dev *dev) dev->ep[UDC_EP0IN_IDX].td_stp_phys = 0; dev->ep[UDC_EP0IN_IDX].td_data = NULL; dev->ep[UDC_EP0IN_IDX].td_data_phys = 0; + + dev->ep0out_buf = kzalloc(UDC_EP0OUT_BUFF_SIZE * 4, GFP_KERNEL); + if (!dev->ep0out_buf) + return -ENOMEM; + dev->dma_addr = dma_map_single(&dev->pdev->dev, dev->ep0out_buf, + UDC_EP0OUT_BUFF_SIZE * 4, + DMA_FROM_DEVICE); return 0; } @@ -2700,7 +2718,8 @@ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) pch_udc_disable_interrupts(dev, UDC_DEVINT_MSK); - /* Assues that there are no pending requets with this driver */ + /* Assures that there are no pending requests with this driver */ + driver->disconnect(&dev->gadget); driver->unbind(&dev->gadget); dev->gadget.dev.driver = NULL; dev->driver = NULL; @@ -2750,6 +2769,11 @@ static void pch_udc_remove(struct pci_dev *pdev) pci_pool_destroy(dev->stp_requests); } + if (dev->dma_addr) + dma_unmap_single(&dev->pdev->dev, dev->dma_addr, + UDC_EP0OUT_BUFF_SIZE * 4, DMA_FROM_DEVICE); + kfree(dev->ep0out_buf); + pch_udc_exit(dev); if (dev->irq_registered) @@ -2792,11 +2816,7 @@ static int pch_udc_resume(struct pci_dev *pdev) int ret; pci_set_power_state(pdev, PCI_D0); - ret = pci_restore_state(pdev); - if (ret) { - dev_err(&pdev->dev, "%s: pci_restore_state failed\n", __func__); - return ret; - } + pci_restore_state(pdev); ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: pci_enable_device failed\n", __func__); @@ -2914,6 +2934,11 @@ static DEFINE_PCI_DEVICE_TABLE(pch_udc_pcidev_id) = { .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, .class_mask = 0xffffffff, }, + { + PCI_DEVICE(PCI_VENDOR_ID_ROHM, PCI_DEVICE_ID_ML7213_IOH_UDC), + .class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe, + .class_mask = 0xffffffff, + }, { 0 }, }; diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index 2fc8636..12ff6cf 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -131,31 +131,31 @@ static struct printer_dev usb_printer_gadget; * parameters are in UTF-8 (superset of ASCII's 7 bit characters). */ -static ushort __initdata idVendor; +static ushort idVendor; module_param(idVendor, ushort, S_IRUGO); MODULE_PARM_DESC(idVendor, "USB Vendor ID"); -static ushort __initdata idProduct; +static ushort idProduct; module_param(idProduct, ushort, S_IRUGO); MODULE_PARM_DESC(idProduct, "USB Product ID"); -static ushort __initdata bcdDevice; +static ushort bcdDevice; module_param(bcdDevice, ushort, S_IRUGO); MODULE_PARM_DESC(bcdDevice, "USB Device version (BCD)"); -static char *__initdata iManufacturer; +static char *iManufacturer; module_param(iManufacturer, charp, S_IRUGO); MODULE_PARM_DESC(iManufacturer, "USB Manufacturer string"); -static char *__initdata iProduct; +static char *iProduct; module_param(iProduct, charp, S_IRUGO); MODULE_PARM_DESC(iProduct, "USB Product string"); -static char *__initdata iSerialNum; +static char *iSerialNum; module_param(iSerialNum, charp, S_IRUGO); MODULE_PARM_DESC(iSerialNum, "1"); -static char *__initdata iPNPstring; +static char *iPNPstring; module_param(iPNPstring, charp, S_IRUGO); MODULE_PARM_DESC(iPNPstring, "MFG:linux;MDL:g_printer;CLS:PRINTER;SN:1;"); @@ -1596,13 +1596,12 @@ cleanup(void) int status; mutex_lock(&usb_printer_gadget.lock_printer_io); - class_destroy(usb_gadget_class); - unregister_chrdev_region(g_printer_devno, 2); - status = usb_gadget_unregister_driver(&printer_driver); if (status) ERROR(dev, "usb_gadget_unregister_driver %x\n", status); + unregister_chrdev_region(g_printer_devno, 2); + class_destroy(usb_gadget_class); mutex_unlock(&usb_printer_gadget.lock_printer_io); } module_exit(cleanup); diff --git a/drivers/usb/gadget/r8a66597-udc.c b/drivers/usb/gadget/r8a66597-udc.c index 20d43da..0151185 100644 --- a/drivers/usb/gadget/r8a66597-udc.c +++ b/drivers/usb/gadget/r8a66597-udc.c @@ -258,7 +258,7 @@ static int pipe_buffer_setting(struct r8a66597 *r8a66597, break; case R8A66597_BULK: /* isochronous pipes may be used as bulk pipes */ - if (info->pipe > R8A66597_BASE_PIPENUM_BULK) + if (info->pipe >= R8A66597_BASE_PIPENUM_BULK) bufnum = info->pipe - R8A66597_BASE_PIPENUM_BULK; else bufnum = info->pipe - R8A66597_BASE_PIPENUM_ISOC; diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index 24046c0..0e6afa2 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -151,6 +151,8 @@ config USB_EHCI_MSM Qualcomm chipsets. Root Hub has inbuilt TT. This driver depends on OTG driver for PHY initialization, clock management, powering up VBUS, and power management. + This driver is not supported on boards like trout which + has an external PHY. config USB_EHCI_HCD_PPC_OF bool "EHCI support for PPC USB controller on OF platform bus" diff --git a/drivers/usb/host/ehci-au1xxx.c b/drivers/usb/host/ehci-au1xxx.c index 2baf8a8..a869e3c 100644 --- a/drivers/usb/host/ehci-au1xxx.c +++ b/drivers/usb/host/ehci-au1xxx.c @@ -227,8 +227,8 @@ static int ehci_hcd_au1xxx_drv_suspend(struct device *dev) * mark HW unaccessible. The PM and USB cores make sure that * the root hub is either suspended or stopped. */ - spin_lock_irqsave(&ehci->lock, flags); ehci_prepare_ports_for_controller_suspend(ehci, device_may_wakeup(dev)); + spin_lock_irqsave(&ehci->lock, flags); ehci_writel(ehci, 0, &ehci->regs->intr_enable); (void)ehci_readl(ehci, &ehci->regs->intr_enable); diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 86e4289..5c761df 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -52,7 +52,6 @@ static int usb_hcd_fsl_probe(const struct hc_driver *driver, struct resource *res; int irq; int retval; - unsigned int temp; pr_debug("initializing FSL-SOC USB Controller\n"); @@ -126,18 +125,6 @@ static int usb_hcd_fsl_probe(const struct hc_driver *driver, goto err3; } - /* - * Check if it is MPC5121 SoC, otherwise set pdata->have_sysif_regs - * flag for 83xx or 8536 system interface registers. - */ - if (pdata->big_endian_mmio) - temp = in_be32(hcd->regs + FSL_SOC_USB_ID); - else - temp = in_le32(hcd->regs + FSL_SOC_USB_ID); - - if ((temp & ID_MSK) != (~((temp & NID_MSK) >> 8) & ID_MSK)) - pdata->have_sysif_regs = 1; - /* Enable USB controller, 83xx or 8536 */ if (pdata->have_sysif_regs) setbits32(hcd->regs + FSL_SOC_USB_CTRL, 0x4); diff --git a/drivers/usb/host/ehci-fsl.h b/drivers/usb/host/ehci-fsl.h index 2c83537..3fabed3 100644 --- a/drivers/usb/host/ehci-fsl.h +++ b/drivers/usb/host/ehci-fsl.h @@ -19,9 +19,6 @@ #define _EHCI_FSL_H /* offsets for the non-ehci registers in the FSL SOC USB controller */ -#define FSL_SOC_USB_ID 0x0 -#define ID_MSK 0x3f -#define NID_MSK 0x3f00 #define FSL_SOC_USB_ULPIVP 0x170 #define FSL_SOC_USB_PORTSC1 0x184 #define PORT_PTS_MSK (3<<30) diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 6fee3cd..74dcf49 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -572,6 +572,8 @@ static int ehci_init(struct usb_hcd *hcd) ehci->iaa_watchdog.function = ehci_iaa_watchdog; ehci->iaa_watchdog.data = (unsigned long) ehci; + hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params); + /* * hw default: 1K periodic list heads, one per frame. * periodic_size can shrink by USBCMD update if hcc_params allows. @@ -579,11 +581,20 @@ static int ehci_init(struct usb_hcd *hcd) ehci->periodic_size = DEFAULT_I_TDPS; INIT_LIST_HEAD(&ehci->cached_itd_list); INIT_LIST_HEAD(&ehci->cached_sitd_list); + + if (HCC_PGM_FRAMELISTLEN(hcc_params)) { + /* periodic schedule size can be smaller than default */ + switch (EHCI_TUNE_FLS) { + case 0: ehci->periodic_size = 1024; break; + case 1: ehci->periodic_size = 512; break; + case 2: ehci->periodic_size = 256; break; + default: BUG(); + } + } if ((retval = ehci_mem_init(ehci, GFP_KERNEL)) < 0) return retval; /* controllers may cache some of the periodic schedule ... */ - hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params); if (HCC_ISOC_CACHE(hcc_params)) // full frame cache ehci->i_thresh = 2 + 8; else // N microframes cached @@ -637,12 +648,6 @@ static int ehci_init(struct usb_hcd *hcd) /* periodic schedule size can be smaller than default */ temp &= ~(3 << 2); temp |= (EHCI_TUNE_FLS << 2); - switch (EHCI_TUNE_FLS) { - case 0: ehci->periodic_size = 1024; break; - case 1: ehci->periodic_size = 512; break; - case 2: ehci->periodic_size = 256; break; - default: BUG(); - } } if (HCC_LPM(hcc_params)) { /* support link power management EHCI 1.1 addendum */ diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index 796ea0c..8a515f0 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -111,6 +111,7 @@ static void ehci_adjust_port_wakeup_flags(struct ehci_hcd *ehci, { int port; u32 temp; + unsigned long flags; /* If remote wakeup is enabled for the root hub but disabled * for the controller, we must adjust all the port wakeup flags @@ -120,6 +121,8 @@ static void ehci_adjust_port_wakeup_flags(struct ehci_hcd *ehci, if (!ehci_to_hcd(ehci)->self.root_hub->do_remote_wakeup || do_wakeup) return; + spin_lock_irqsave(&ehci->lock, flags); + /* clear phy low-power mode before changing wakeup flags */ if (ehci->has_hostpc) { port = HCS_N_PORTS(ehci->hcs_params); @@ -131,7 +134,9 @@ static void ehci_adjust_port_wakeup_flags(struct ehci_hcd *ehci, temp = ehci_readl(ehci, hostpc_reg); ehci_writel(ehci, temp & ~HOSTPC_PHCD, hostpc_reg); } + spin_unlock_irqrestore(&ehci->lock, flags); msleep(5); + spin_lock_irqsave(&ehci->lock, flags); } port = HCS_N_PORTS(ehci->hcs_params); @@ -170,6 +175,8 @@ static void ehci_adjust_port_wakeup_flags(struct ehci_hcd *ehci, /* Does the root hub have a port wakeup pending? */ if (!suspending && (ehci_readl(ehci, &ehci->regs->status) & STS_PCD)) usb_hcd_resume_root_hub(ehci_to_hcd(ehci)); + + spin_unlock_irqrestore(&ehci->lock, flags); } static int ehci_bus_suspend (struct usb_hcd *hcd) diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c index fa59b26..c8e360d 100644 --- a/drivers/usb/host/ehci-mxc.c +++ b/drivers/usb/host/ehci-mxc.c @@ -21,10 +21,13 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/usb/otg.h> +#include <linux/usb/ulpi.h> #include <linux/slab.h> #include <mach/mxc_ehci.h> +#include <asm/mach-types.h> + #define ULPI_VIEWPORT_OFFSET 0x170 struct ehci_mxc_priv { @@ -114,6 +117,7 @@ static int ehci_mxc_drv_probe(struct platform_device *pdev) struct usb_hcd *hcd; struct resource *res; int irq, ret; + unsigned int flags; struct ehci_mxc_priv *priv; struct device *dev = &pdev->dev; struct ehci_hcd *ehci; @@ -177,8 +181,8 @@ static int ehci_mxc_drv_probe(struct platform_device *pdev) clk_enable(priv->ahbclk); } - /* "dr" device has its own clock */ - if (pdev->id == 0) { + /* "dr" device has its own clock on i.MX51 */ + if (cpu_is_mx51() && (pdev->id == 0)) { priv->phy1clk = clk_get(dev, "usb_phy1"); if (IS_ERR(priv->phy1clk)) { ret = PTR_ERR(priv->phy1clk); @@ -240,6 +244,23 @@ static int ehci_mxc_drv_probe(struct platform_device *pdev) if (ret) goto err_add; + if (pdata->otg) { + /* + * efikamx and efikasb have some hardware bug which is + * preventing usb to work unless CHRGVBUS is set. + * It's in violation of USB specs + */ + if (machine_is_mx51_efikamx() || machine_is_mx51_efikasb()) { + flags = otg_io_read(pdata->otg, ULPI_OTG_CTRL); + flags |= ULPI_OTG_CTRL_CHRGVBUS; + ret = otg_io_write(pdata->otg, flags, ULPI_OTG_CTRL); + if (ret) { + dev_err(dev, "unable to set CHRVBUS\n"); + goto err_add; + } + } + } + return 0; err_add: diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c index 680f2ef..f784ceb 100644 --- a/drivers/usb/host/ehci-omap.c +++ b/drivers/usb/host/ehci-omap.c @@ -796,7 +796,7 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) hcd = usb_create_hcd(&ehci_omap_hc_driver, &pdev->dev, dev_name(&pdev->dev)); if (!hcd) { - dev_dbg(&pdev->dev, "failed to create hcd with err %d\n", ret); + dev_err(&pdev->dev, "failed to create hcd with err %d\n", ret); ret = -ENOMEM; goto err_create_hcd; } @@ -864,7 +864,7 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) ret = omap_start_ehc(omap, hcd); if (ret) { - dev_dbg(&pdev->dev, "failed to start ehci\n"); + dev_err(&pdev->dev, "failed to start ehci with err %d\n", ret); goto err_start; } @@ -879,7 +879,7 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) ret = usb_add_hcd(hcd, irq, IRQF_DISABLED | IRQF_SHARED); if (ret) { - dev_dbg(&pdev->dev, "failed to add hcd with err %d\n", ret); + dev_err(&pdev->dev, "failed to add hcd with err %d\n", ret); goto err_add_hcd; } diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 76179c3..07bb982 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -44,28 +44,35 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev) return 0; } -static int ehci_quirk_amd_SB800(struct ehci_hcd *ehci) +static int ehci_quirk_amd_hudson(struct ehci_hcd *ehci) { struct pci_dev *amd_smbus_dev; u8 rev = 0; amd_smbus_dev = pci_get_device(PCI_VENDOR_ID_ATI, 0x4385, NULL); - if (!amd_smbus_dev) - return 0; - - pci_read_config_byte(amd_smbus_dev, PCI_REVISION_ID, &rev); - if (rev < 0x40) { - pci_dev_put(amd_smbus_dev); - amd_smbus_dev = NULL; - return 0; + if (amd_smbus_dev) { + pci_read_config_byte(amd_smbus_dev, PCI_REVISION_ID, &rev); + if (rev < 0x40) { + pci_dev_put(amd_smbus_dev); + amd_smbus_dev = NULL; + return 0; + } + } else { + amd_smbus_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x780b, NULL); + if (!amd_smbus_dev) + return 0; + pci_read_config_byte(amd_smbus_dev, PCI_REVISION_ID, &rev); + if (rev < 0x11 || rev > 0x18) { + pci_dev_put(amd_smbus_dev); + amd_smbus_dev = NULL; + return 0; + } } if (!amd_nb_dev) amd_nb_dev = pci_get_device(PCI_VENDOR_ID_AMD, 0x1510, NULL); - if (!amd_nb_dev) - ehci_err(ehci, "QUIRK: unable to get AMD NB device\n"); - ehci_info(ehci, "QUIRK: Enable AMD SB800 L1 fix\n"); + ehci_info(ehci, "QUIRK: Enable exception for AMD Hudson ASPM\n"); pci_dev_put(amd_smbus_dev); amd_smbus_dev = NULL; @@ -131,7 +138,7 @@ static int ehci_pci_setup(struct usb_hcd *hcd) /* cache this readonly data; minimize chip reads */ ehci->hcs_params = ehci_readl(ehci, &ehci->caps->hcs_params); - if (ehci_quirk_amd_SB800(ehci)) + if (ehci_quirk_amd_hudson(ehci)) ehci->amd_l1_fix = 1; retval = ehci_halt(ehci); @@ -360,8 +367,8 @@ static int ehci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * mark HW unaccessible. The PM and USB cores make sure that * the root hub is either suspended or stopped. */ - spin_lock_irqsave (&ehci->lock, flags); ehci_prepare_ports_for_controller_suspend(ehci, do_wakeup); + spin_lock_irqsave (&ehci->lock, flags); ehci_writel(ehci, 0, &ehci->regs->intr_enable); (void)ehci_readl(ehci, &ehci->regs->intr_enable); diff --git a/drivers/usb/host/ehci-xilinx-of.c b/drivers/usb/host/ehci-xilinx-of.c index e8f4f36..a6f21b8 100644 --- a/drivers/usb/host/ehci-xilinx-of.c +++ b/drivers/usb/host/ehci-xilinx-of.c @@ -29,6 +29,7 @@ #include <linux/of.h> #include <linux/of_platform.h> +#include <linux/of_address.h> /** * ehci_xilinx_of_setup - Initialize the device for ehci_reset() diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index 574b99e..79a66d6 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -262,19 +262,24 @@ static void fsl_usb2_mpc5121_exit(struct platform_device *pdev) } } -struct fsl_usb2_platform_data fsl_usb2_mpc5121_pd = { +static struct fsl_usb2_platform_data fsl_usb2_mpc5121_pd = { .big_endian_desc = 1, .big_endian_mmio = 1, .es = 1, + .have_sysif_regs = 0, .le_setup_buf = 1, .init = fsl_usb2_mpc5121_init, .exit = fsl_usb2_mpc5121_exit, }; #endif /* CONFIG_PPC_MPC512x */ +static struct fsl_usb2_platform_data fsl_usb2_mpc8xxx_pd = { + .have_sysif_regs = 1, +}; + static const struct of_device_id fsl_usb2_mph_dr_of_match[] = { - { .compatible = "fsl-usb2-mph", }, - { .compatible = "fsl-usb2-dr", }, + { .compatible = "fsl-usb2-mph", .data = &fsl_usb2_mpc8xxx_pd, }, + { .compatible = "fsl-usb2-dr", .data = &fsl_usb2_mpc8xxx_pd, }, #ifdef CONFIG_PPC_MPC512x { .compatible = "fsl,mpc5121-usb2-dr", .data = &fsl_usb2_mpc5121_pd, }, #endif diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c index 990f06b..2e9602a 100644 --- a/drivers/usb/host/sl811-hcd.c +++ b/drivers/usb/host/sl811-hcd.c @@ -861,6 +861,7 @@ static int sl811h_urb_enqueue( DBG("dev %d ep%d maxpacket %d\n", udev->devnum, epnum, ep->maxpacket); retval = -EINVAL; + kfree(ep); goto fail; } diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c index fcbf4ab..0231814 100644 --- a/drivers/usb/host/xhci-dbg.c +++ b/drivers/usb/host/xhci-dbg.c @@ -169,9 +169,10 @@ static void xhci_print_ports(struct xhci_hcd *xhci) } } -void xhci_print_ir_set(struct xhci_hcd *xhci, struct xhci_intr_reg *ir_set, int set_num) +void xhci_print_ir_set(struct xhci_hcd *xhci, int set_num) { - void *addr; + struct xhci_intr_reg __iomem *ir_set = &xhci->run_regs->ir_set[set_num]; + void __iomem *addr; u32 temp; u64 temp_64; @@ -449,7 +450,7 @@ char *xhci_get_slot_state(struct xhci_hcd *xhci, } } -void xhci_dbg_slot_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx) +static void xhci_dbg_slot_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx) { /* Fields are 32 bits wide, DMA addresses are in bytes */ int field_size = 32 / 8; @@ -488,7 +489,7 @@ void xhci_dbg_slot_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx) dbg_rsvd64(xhci, (u64 *)slot_ctx, dma); } -void xhci_dbg_ep_ctx(struct xhci_hcd *xhci, +static void xhci_dbg_ep_ctx(struct xhci_hcd *xhci, struct xhci_container_ctx *ctx, unsigned int last_ep) { diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 1d0f45f..a953439 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -307,7 +307,7 @@ struct xhci_ep_ctx *xhci_get_ep_ctx(struct xhci_hcd *xhci, /***************** Streams structures manipulation *************************/ -void xhci_free_stream_ctx(struct xhci_hcd *xhci, +static void xhci_free_stream_ctx(struct xhci_hcd *xhci, unsigned int num_stream_ctxs, struct xhci_stream_ctx *stream_ctx, dma_addr_t dma) { @@ -335,7 +335,7 @@ void xhci_free_stream_ctx(struct xhci_hcd *xhci, * The stream context array must be a power of 2, and can be as small as * 64 bytes or as large as 1MB. */ -struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci, +static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci, unsigned int num_stream_ctxs, dma_addr_t *dma, gfp_t mem_flags) { @@ -1900,11 +1900,11 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) val &= DBOFF_MASK; xhci_dbg(xhci, "// Doorbell array is located at offset 0x%x" " from cap regs base addr\n", val); - xhci->dba = (void *) xhci->cap_regs + val; + xhci->dba = (void __iomem *) xhci->cap_regs + val; xhci_dbg_regs(xhci); xhci_print_run_regs(xhci); /* Set ir_set to interrupt register set 0 */ - xhci->ir_set = (void *) xhci->run_regs->ir_set; + xhci->ir_set = &xhci->run_regs->ir_set[0]; /* * Event ring setup: Allocate a normal ring, but also setup @@ -1961,7 +1961,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) /* Set the event ring dequeue address */ xhci_set_hc_event_deq(xhci); xhci_dbg(xhci, "Wrote ERST address to ir_set 0.\n"); - xhci_print_ir_set(xhci, xhci->ir_set, 0); + xhci_print_ir_set(xhci, 0); /* * XXX: Might need to set the Interrupter Moderation Register to diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index df558f6..3289bf4 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -308,11 +308,8 @@ static int room_on_ring(struct xhci_hcd *xhci, struct xhci_ring *ring, /* Ring the host controller doorbell after placing a command on the ring */ void xhci_ring_cmd_db(struct xhci_hcd *xhci) { - u32 temp; - xhci_dbg(xhci, "// Ding dong!\n"); - temp = xhci_readl(xhci, &xhci->dba->doorbell[0]) & DB_MASK; - xhci_writel(xhci, temp | DB_TARGET_HOST, &xhci->dba->doorbell[0]); + xhci_writel(xhci, DB_VALUE_HOST, &xhci->dba->doorbell[0]); /* Flush PCI posted writes */ xhci_readl(xhci, &xhci->dba->doorbell[0]); } @@ -322,26 +319,24 @@ void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int ep_index, unsigned int stream_id) { - struct xhci_virt_ep *ep; - unsigned int ep_state; - u32 field; __u32 __iomem *db_addr = &xhci->dba->doorbell[slot_id]; + struct xhci_virt_ep *ep = &xhci->devs[slot_id]->eps[ep_index]; + unsigned int ep_state = ep->ep_state; - ep = &xhci->devs[slot_id]->eps[ep_index]; - ep_state = ep->ep_state; /* Don't ring the doorbell for this endpoint if there are pending - * cancellations because the we don't want to interrupt processing. + * cancellations because we don't want to interrupt processing. * We don't want to restart any stream rings if there's a set dequeue * pointer command pending because the device can choose to start any * stream once the endpoint is on the HW schedule. * FIXME - check all the stream rings for pending cancellations. */ - if (!(ep_state & EP_HALT_PENDING) && !(ep_state & SET_DEQ_PENDING) - && !(ep_state & EP_HALTED)) { - field = xhci_readl(xhci, db_addr) & DB_MASK; - field |= EPI_TO_DB(ep_index) | STREAM_ID_TO_DB(stream_id); - xhci_writel(xhci, field, db_addr); - } + if ((ep_state & EP_HALT_PENDING) || (ep_state & SET_DEQ_PENDING) || + (ep_state & EP_HALTED)) + return; + xhci_writel(xhci, DB_VALUE(ep_index, stream_id), db_addr); + /* The CPU has better things to do at this point than wait for a + * write-posting flush. It'll get there soon enough. + */ } /* Ring the doorbell for any rings with pending URBs */ @@ -479,8 +474,11 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci, state->new_deq_seg = find_trb_seg(cur_td->start_seg, dev->eps[ep_index].stopped_trb, &state->new_cycle_state); - if (!state->new_deq_seg) - BUG(); + if (!state->new_deq_seg) { + WARN_ON(1); + return; + } + /* Dig out the cycle state saved by the xHC during the stop ep cmd */ xhci_dbg(xhci, "Finding endpoint context\n"); ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, ep_index); @@ -491,8 +489,10 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci, state->new_deq_seg = find_trb_seg(state->new_deq_seg, state->new_deq_ptr, &state->new_cycle_state); - if (!state->new_deq_seg) - BUG(); + if (!state->new_deq_seg) { + WARN_ON(1); + return; + } trb = &state->new_deq_ptr->generic; if ((trb->field[3] & TRB_TYPE_BITMASK) == TRB_TYPE(TRB_LINK) && @@ -1188,7 +1188,7 @@ static void handle_port_status(struct xhci_hcd *xhci, addr = &xhci->op_regs->port_status_base + NUM_PORT_REGS * (port_id - 1); temp = xhci_readl(xhci, addr); - if ((temp & PORT_CONNECT) && (hcd->state == HC_STATE_SUSPENDED)) { + if (hcd->state == HC_STATE_SUSPENDED) { xhci_dbg(xhci, "resume root hub\n"); usb_hcd_resume_root_hub(hcd); } @@ -1710,8 +1710,7 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td, /* Others already handled above */ break; } - dev_dbg(&td->urb->dev->dev, - "ep %#x - asked for %d bytes, " + xhci_dbg(xhci, "ep %#x - asked for %d bytes, " "%d bytes untransferred\n", td->urb->ep->desc.bEndpointAddress, td->urb->transfer_buffer_length, @@ -2369,12 +2368,13 @@ static unsigned int count_sg_trbs_needed(struct xhci_hcd *xhci, struct urb *urb) /* Scatter gather list entries may cross 64KB boundaries */ running_total = TRB_MAX_BUFF_SIZE - - (sg_dma_address(sg) & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + (sg_dma_address(sg) & (TRB_MAX_BUFF_SIZE - 1)); + running_total &= TRB_MAX_BUFF_SIZE - 1; if (running_total != 0) num_trbs++; /* How many more 64KB chunks to transfer, how many more TRBs? */ - while (running_total < sg_dma_len(sg)) { + while (running_total < sg_dma_len(sg) && running_total < temp) { num_trbs++; running_total += TRB_MAX_BUFF_SIZE; } @@ -2389,7 +2389,8 @@ static unsigned int count_sg_trbs_needed(struct xhci_hcd *xhci, struct urb *urb) } xhci_dbg(xhci, "\n"); if (!in_interrupt()) - dev_dbg(&urb->dev->dev, "ep %#x - urb len = %d, sglist used, num_trbs = %d\n", + xhci_dbg(xhci, "ep %#x - urb len = %d, sglist used, " + "num_trbs = %d\n", urb->ep->desc.bEndpointAddress, urb->transfer_buffer_length, num_trbs); @@ -2399,11 +2400,11 @@ static unsigned int count_sg_trbs_needed(struct xhci_hcd *xhci, struct urb *urb) static void check_trb_math(struct urb *urb, int num_trbs, int running_total) { if (num_trbs != 0) - dev_dbg(&urb->dev->dev, "%s - ep %#x - Miscalculated number of " + dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated number of " "TRBs, %d left\n", __func__, urb->ep->desc.bEndpointAddress, num_trbs); if (running_total != urb->transfer_buffer_length) - dev_dbg(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, " + dev_err(&urb->dev->dev, "%s - ep %#x - Miscalculated tx length, " "queued %#x (%d), asked for %#x (%d)\n", __func__, urb->ep->desc.bEndpointAddress, @@ -2414,14 +2415,17 @@ static void check_trb_math(struct urb *urb, int num_trbs, int running_total) static void giveback_first_trb(struct xhci_hcd *xhci, int slot_id, unsigned int ep_index, unsigned int stream_id, int start_cycle, - struct xhci_generic_trb *start_trb, struct xhci_td *td) + struct xhci_generic_trb *start_trb) { /* * Pass all the TRBs to the hardware at once and make sure this write * isn't reordered. */ wmb(); - start_trb->field[3] |= start_cycle; + if (start_cycle) + start_trb->field[3] |= start_cycle; + else + start_trb->field[3] &= ~0x1; xhci_ring_ep_doorbell(xhci, slot_id, ep_index, stream_id); } @@ -2449,7 +2453,7 @@ int xhci_queue_intr_tx(struct xhci_hcd *xhci, gfp_t mem_flags, * to set the polling interval (once the API is added). */ if (xhci_interval != ep_interval) { - if (!printk_ratelimit()) + if (printk_ratelimit()) dev_dbg(&urb->dev->dev, "Driver uses different interval" " (%d microframe%s) than xHCI " "(%d microframe%s)\n", @@ -2535,8 +2539,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags, sg = urb->sg; addr = (u64) sg_dma_address(sg); this_sg_len = sg_dma_len(sg); - trb_buff_len = TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + trb_buff_len = TRB_MAX_BUFF_SIZE - (addr & (TRB_MAX_BUFF_SIZE - 1)); trb_buff_len = min_t(int, trb_buff_len, this_sg_len); if (trb_buff_len > urb->transfer_buffer_length) trb_buff_len = urb->transfer_buffer_length; @@ -2551,9 +2554,11 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags, u32 remainder = 0; /* Don't change the cycle bit of the first TRB until later */ - if (first_trb) + if (first_trb) { first_trb = false; - else + if (start_cycle == 0) + field |= 0x1; + } else field |= ep_ring->cycle_state; /* Chain all the TRBs together; clear the chain bit in the last @@ -2572,7 +2577,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags, (unsigned int) (addr + TRB_MAX_BUFF_SIZE) & ~(TRB_MAX_BUFF_SIZE - 1), (unsigned int) addr + trb_buff_len); if (TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)) < trb_buff_len) { + (addr & (TRB_MAX_BUFF_SIZE - 1)) < trb_buff_len) { xhci_warn(xhci, "WARN: sg dma xfer crosses 64KB boundaries!\n"); xhci_dbg(xhci, "Next boundary at %#x, end dma = %#x\n", (unsigned int) (addr + TRB_MAX_BUFF_SIZE) & ~(TRB_MAX_BUFF_SIZE - 1), @@ -2616,7 +2621,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags, } trb_buff_len = TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + (addr & (TRB_MAX_BUFF_SIZE - 1)); trb_buff_len = min_t(int, trb_buff_len, this_sg_len); if (running_total + trb_buff_len > urb->transfer_buffer_length) trb_buff_len = @@ -2625,7 +2630,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags, check_trb_math(urb, num_trbs, running_total); giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id, - start_cycle, start_trb, td); + start_cycle, start_trb); return 0; } @@ -2656,7 +2661,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, num_trbs = 0; /* How much data is (potentially) left before the 64KB boundary? */ running_total = TRB_MAX_BUFF_SIZE - - (urb->transfer_dma & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + (urb->transfer_dma & (TRB_MAX_BUFF_SIZE - 1)); + running_total &= TRB_MAX_BUFF_SIZE - 1; /* If there's some data on this 64KB chunk, or we have to send a * zero-length transfer, we need at least one TRB @@ -2671,7 +2677,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, /* FIXME: this doesn't deal with URB_ZERO_PACKET - need one more */ if (!in_interrupt()) - dev_dbg(&urb->dev->dev, "ep %#x - urb len = %#x (%d), addr = %#llx, num_trbs = %d\n", + xhci_dbg(xhci, "ep %#x - urb len = %#x (%d), " + "addr = %#llx, num_trbs = %d\n", urb->ep->desc.bEndpointAddress, urb->transfer_buffer_length, urb->transfer_buffer_length, @@ -2699,8 +2706,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, /* How much data is in the first TRB? */ addr = (u64) urb->transfer_dma; trb_buff_len = TRB_MAX_BUFF_SIZE - - (urb->transfer_dma & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); - if (urb->transfer_buffer_length < trb_buff_len) + (urb->transfer_dma & (TRB_MAX_BUFF_SIZE - 1)); + if (trb_buff_len > urb->transfer_buffer_length) trb_buff_len = urb->transfer_buffer_length; first_trb = true; @@ -2711,9 +2718,11 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, field = 0; /* Don't change the cycle bit of the first TRB until later */ - if (first_trb) + if (first_trb) { first_trb = false; - else + if (start_cycle == 0) + field |= 0x1; + } else field |= ep_ring->cycle_state; /* Chain all the TRBs together; clear the chain bit in the last @@ -2757,7 +2766,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, check_trb_math(urb, num_trbs, running_total); giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id, - start_cycle, start_trb, td); + start_cycle, start_trb); return 0; } @@ -2818,13 +2827,17 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags, /* Queue setup TRB - see section 6.4.1.2.1 */ /* FIXME better way to translate setup_packet into two u32 fields? */ setup = (struct usb_ctrlrequest *) urb->setup_packet; + field = 0; + field |= TRB_IDT | TRB_TYPE(TRB_SETUP); + if (start_cycle == 0) + field |= 0x1; queue_trb(xhci, ep_ring, false, true, /* FIXME endianness is probably going to bite my ass here. */ setup->bRequestType | setup->bRequest << 8 | setup->wValue << 16, setup->wIndex | setup->wLength << 16, TRB_LEN(8) | TRB_INTR_TARGET(0), /* Immediate data in pointer */ - TRB_IDT | TRB_TYPE(TRB_SETUP)); + field); /* If there's data, queue data TRBs */ field = 0; @@ -2859,7 +2872,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags, field | TRB_IOC | TRB_TYPE(TRB_STATUS) | ep_ring->cycle_state); giveback_first_trb(xhci, slot_id, ep_index, 0, - start_cycle, start_trb, td); + start_cycle, start_trb); return 0; } @@ -2872,8 +2885,8 @@ static int count_isoc_trbs_needed(struct xhci_hcd *xhci, addr = (u64) (urb->transfer_dma + urb->iso_frame_desc[i].offset); td_len = urb->iso_frame_desc[i].length; - running_total = TRB_MAX_BUFF_SIZE - - (addr & ((1 << TRB_MAX_BUFF_SHIFT) - 1)); + running_total = TRB_MAX_BUFF_SIZE - (addr & (TRB_MAX_BUFF_SIZE - 1)); + running_total &= TRB_MAX_BUFF_SIZE - 1; if (running_total != 0) num_trbs++; @@ -2900,6 +2913,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, int running_total, trb_buff_len, td_len, td_remain_len, ret; u64 start_addr, addr; int i, j; + bool more_trbs_coming; ep_ring = xhci->devs[slot_id]->eps[ep_index].ring; @@ -2910,7 +2924,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, } if (!in_interrupt()) - dev_dbg(&urb->dev->dev, "ep %#x - urb len = %#x (%d)," + xhci_dbg(xhci, "ep %#x - urb len = %#x (%d)," " addr = %#llx, num_tds = %d\n", urb->ep->desc.bEndpointAddress, urb->transfer_buffer_length, @@ -2950,7 +2964,10 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, field |= TRB_TYPE(TRB_ISOC); /* Assume URB_ISO_ASAP is set */ field |= TRB_SIA; - if (i > 0) + if (i == 0) { + if (start_cycle == 0) + field |= 0x1; + } else field |= ep_ring->cycle_state; first_trb = false; } else { @@ -2965,9 +2982,11 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, */ if (j < trbs_per_td - 1) { field |= TRB_CHAIN; + more_trbs_coming = true; } else { td->last_trb = ep_ring->enqueue; field |= TRB_IOC; + more_trbs_coming = false; } /* Calculate TRB length */ @@ -2980,7 +2999,7 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, length_field = TRB_LEN(trb_buff_len) | remainder | TRB_INTR_TARGET(0); - queue_trb(xhci, ep_ring, false, false, + queue_trb(xhci, ep_ring, false, more_trbs_coming, lower_32_bits(addr), upper_32_bits(addr), length_field, @@ -3003,10 +3022,8 @@ static int xhci_queue_isoc_tx(struct xhci_hcd *xhci, gfp_t mem_flags, } } - wmb(); - start_trb->field[3] |= start_cycle; - - xhci_ring_ep_doorbell(xhci, slot_id, ep_index, urb->stream_id); + giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id, + start_cycle, start_trb); return 0; } @@ -3064,7 +3081,7 @@ int xhci_queue_isoc_tx_prepare(struct xhci_hcd *xhci, gfp_t mem_flags, * to set the polling interval (once the API is added). */ if (xhci_interval != ep_interval) { - if (!printk_ratelimit()) + if (printk_ratelimit()) dev_dbg(&urb->dev->dev, "Driver uses different interval" " (%d microframe%s) than xHCI " "(%d microframe%s)\n", diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 45e4a31..2083fc2 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -109,7 +109,7 @@ int xhci_halt(struct xhci_hcd *xhci) /* * Set the run bit and wait for the host to be running. */ -int xhci_start(struct xhci_hcd *xhci) +static int xhci_start(struct xhci_hcd *xhci) { u32 temp; int ret; @@ -226,7 +226,8 @@ static int xhci_setup_msi(struct xhci_hcd *xhci) static int xhci_setup_msix(struct xhci_hcd *xhci) { int i, ret = 0; - struct pci_dev *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); + struct usb_hcd *hcd = xhci_to_hcd(xhci); + struct pci_dev *pdev = to_pci_dev(hcd->self.controller); /* * calculate number of msi-x vectors supported. @@ -265,6 +266,7 @@ static int xhci_setup_msix(struct xhci_hcd *xhci) goto disable_msix; } + hcd->msix_enabled = 1; return ret; disable_msix: @@ -280,7 +282,8 @@ free_entries: /* Free any IRQs and disable MSI-X */ static void xhci_cleanup_msix(struct xhci_hcd *xhci) { - struct pci_dev *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); + struct usb_hcd *hcd = xhci_to_hcd(xhci); + struct pci_dev *pdev = to_pci_dev(hcd->self.controller); xhci_free_irq(xhci); @@ -292,6 +295,7 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci) pci_disable_msi(pdev); } + hcd->msix_enabled = 0; return; } @@ -325,7 +329,7 @@ int xhci_init(struct usb_hcd *hcd) #ifdef CONFIG_USB_XHCI_HCD_DEBUGGING -void xhci_event_ring_work(unsigned long arg) +static void xhci_event_ring_work(unsigned long arg) { unsigned long flags; int temp; @@ -469,7 +473,7 @@ int xhci_run(struct usb_hcd *hcd) xhci->ir_set, (unsigned int) ER_IRQ_ENABLE(temp)); xhci_writel(xhci, ER_IRQ_ENABLE(temp), &xhci->ir_set->irq_pending); - xhci_print_ir_set(xhci, xhci->ir_set, 0); + xhci_print_ir_set(xhci, 0); if (NUM_TEST_NOOPS > 0) doorbell = xhci_setup_one_noop(xhci); @@ -508,9 +512,10 @@ void xhci_stop(struct usb_hcd *hcd) spin_lock_irq(&xhci->lock); xhci_halt(xhci); xhci_reset(xhci); - xhci_cleanup_msix(xhci); spin_unlock_irq(&xhci->lock); + xhci_cleanup_msix(xhci); + #ifdef CONFIG_USB_XHCI_HCD_DEBUGGING /* Tell the event ring poll function not to reschedule */ xhci->zombie = 1; @@ -523,7 +528,7 @@ void xhci_stop(struct usb_hcd *hcd) temp = xhci_readl(xhci, &xhci->ir_set->irq_pending); xhci_writel(xhci, ER_IRQ_DISABLE(temp), &xhci->ir_set->irq_pending); - xhci_print_ir_set(xhci, xhci->ir_set, 0); + xhci_print_ir_set(xhci, 0); xhci_dbg(xhci, "cleaning up memory\n"); xhci_mem_cleanup(xhci); @@ -544,9 +549,10 @@ void xhci_shutdown(struct usb_hcd *hcd) spin_lock_irq(&xhci->lock); xhci_halt(xhci); - xhci_cleanup_msix(xhci); spin_unlock_irq(&xhci->lock); + xhci_cleanup_msix(xhci); + xhci_dbg(xhci, "xhci_shutdown completed - status = %x\n", xhci_readl(xhci, &xhci->op_regs->status)); } @@ -647,6 +653,7 @@ int xhci_suspend(struct xhci_hcd *xhci) int rc = 0; struct usb_hcd *hcd = xhci_to_hcd(xhci); u32 command; + int i; spin_lock_irq(&xhci->lock); clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags); @@ -677,10 +684,15 @@ int xhci_suspend(struct xhci_hcd *xhci) spin_unlock_irq(&xhci->lock); return -ETIMEDOUT; } - /* step 5: remove core well power */ - xhci_cleanup_msix(xhci); spin_unlock_irq(&xhci->lock); + /* step 5: remove core well power */ + /* synchronize irq when using MSI-X */ + if (xhci->msix_entries) { + for (i = 0; i < xhci->msix_count; i++) + synchronize_irq(xhci->msix_entries[i].vector); + } + return rc; } @@ -694,7 +706,6 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) { u32 command, temp = 0; struct usb_hcd *hcd = xhci_to_hcd(xhci); - struct pci_dev *pdev = to_pci_dev(hcd->self.controller); int old_state, retval; old_state = hcd->state; @@ -729,9 +740,8 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) xhci_dbg(xhci, "Stop HCD\n"); xhci_halt(xhci); xhci_reset(xhci); - if (hibernated) - xhci_cleanup_msix(xhci); spin_unlock_irq(&xhci->lock); + xhci_cleanup_msix(xhci); #ifdef CONFIG_USB_XHCI_HCD_DEBUGGING /* Tell the event ring poll function not to reschedule */ @@ -745,7 +755,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) temp = xhci_readl(xhci, &xhci->ir_set->irq_pending); xhci_writel(xhci, ER_IRQ_DISABLE(temp), &xhci->ir_set->irq_pending); - xhci_print_ir_set(xhci, xhci->ir_set, 0); + xhci_print_ir_set(xhci, 0); xhci_dbg(xhci, "cleaning up memory\n"); xhci_mem_cleanup(xhci); @@ -765,30 +775,6 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) return retval; } - spin_unlock_irq(&xhci->lock); - /* Re-setup MSI-X */ - if (hcd->irq) - free_irq(hcd->irq, hcd); - hcd->irq = -1; - - retval = xhci_setup_msix(xhci); - if (retval) - /* fall back to msi*/ - retval = xhci_setup_msi(xhci); - - if (retval) { - /* fall back to legacy interrupt*/ - retval = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED, - hcd->irq_descr, hcd); - if (retval) { - xhci_err(xhci, "request interrupt %d failed\n", - pdev->irq); - return retval; - } - hcd->irq = pdev->irq; - } - - spin_lock_irq(&xhci->lock); /* step 4: set Run/Stop bit */ command = xhci_readl(xhci, &xhci->op_regs->command); command |= CMD_RUN; @@ -871,7 +857,7 @@ unsigned int xhci_last_valid_endpoint(u32 added_ctxs) /* Returns 1 if the arguments are OK; * returns 0 this is a root hub; returns -EINVAL for NULL pointers. */ -int xhci_check_args(struct usb_hcd *hcd, struct usb_device *udev, +static int xhci_check_args(struct usb_hcd *hcd, struct usb_device *udev, struct usb_host_endpoint *ep, int check_ep, bool check_virt_dev, const char *func) { struct xhci_hcd *xhci; @@ -1707,7 +1693,7 @@ static void xhci_setup_input_ctx_for_config_ep(struct xhci_hcd *xhci, xhci_dbg_ctx(xhci, in_ctx, xhci_last_valid_endpoint(add_flags)); } -void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci, +static void xhci_setup_input_ctx_for_quirk(struct xhci_hcd *xhci, unsigned int slot_id, unsigned int ep_index, struct xhci_dequeue_state *deq_state) { @@ -2445,8 +2431,12 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev) xhci_err(xhci, "Error while assigning device slot ID\n"); return 0; } - /* xhci_alloc_virt_device() does not touch rings; no need to lock */ - if (!xhci_alloc_virt_device(xhci, xhci->slot_id, udev, GFP_KERNEL)) { + /* xhci_alloc_virt_device() does not touch rings; no need to lock. + * Use GFP_NOIO, since this function can be called from + * xhci_discover_or_reset_device(), which may be called as part of + * mass storage driver error handling. + */ + if (!xhci_alloc_virt_device(xhci, xhci->slot_id, udev, GFP_NOIO)) { /* Disable slot, if we can do it without mem alloc */ xhci_warn(xhci, "Could not allocate xHCI USB device data structures\n"); spin_lock_irqsave(&xhci->lock, flags); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 170c367..7f127df 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -436,22 +436,18 @@ struct xhci_run_regs { /** * struct doorbell_array * + * Bits 0 - 7: Endpoint target + * Bits 8 - 15: RsvdZ + * Bits 16 - 31: Stream ID + * * Section 5.6 */ struct xhci_doorbell_array { u32 doorbell[256]; }; -#define DB_TARGET_MASK 0xFFFFFF00 -#define DB_STREAM_ID_MASK 0x0000FFFF -#define DB_TARGET_HOST 0x0 -#define DB_STREAM_ID_HOST 0x0 -#define DB_MASK (0xff << 8) - -/* Endpoint Target - bits 0:7 */ -#define EPI_TO_DB(p) (((p) + 1) & 0xff) -#define STREAM_ID_TO_DB(p) (((p) & 0xffff) << 16) - +#define DB_VALUE(ep, stream) ((((ep) + 1) & 0xff) | ((stream) << 16)) +#define DB_VALUE_HOST 0x00000000 /** * struct xhci_protocol_caps @@ -1352,7 +1348,7 @@ static inline int xhci_link_trb_quirk(struct xhci_hcd *xhci) } /* xHCI debugging */ -void xhci_print_ir_set(struct xhci_hcd *xhci, struct xhci_intr_reg *ir_set, int set_num); +void xhci_print_ir_set(struct xhci_hcd *xhci, int set_num); void xhci_print_registers(struct xhci_hcd *xhci); void xhci_dbg_regs(struct xhci_hcd *xhci); void xhci_print_run_regs(struct xhci_hcd *xhci); diff --git a/drivers/usb/misc/usbled.c b/drivers/usb/misc/usbled.c index 1732d9b..1616ad1 100644 --- a/drivers/usb/misc/usbled.c +++ b/drivers/usb/misc/usbled.c @@ -45,7 +45,7 @@ struct usb_led { static void change_color(struct usb_led *led) { - int retval; + int retval = 0; unsigned char *buffer; buffer = kmalloc(8, GFP_KERNEL); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 4ff2158..f7a2057 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -776,7 +776,6 @@ static const struct usb_device_id uss720_table[] = { { USB_DEVICE(0x0557, 0x2001) }, { USB_DEVICE(0x0729, 0x1284) }, { USB_DEVICE(0x1293, 0x0002) }, - { USB_DEVICE(0x1293, 0x0002) }, { USB_DEVICE(0x050d, 0x0002) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/musb/blackfin.c b/drivers/usb/musb/blackfin.c index eeba228..9d49d1c 100644 --- a/drivers/usb/musb/blackfin.c +++ b/drivers/usb/musb/blackfin.c @@ -404,6 +404,7 @@ static int bfin_musb_init(struct musb *musb) musb->xceiv->set_power = bfin_musb_set_power; musb->isr = blackfin_interrupt; + musb->double_buffer_not_ok = true; return 0; } diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 07cf394..c292d5c 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -128,12 +128,7 @@ MODULE_ALIAS("platform:" MUSB_DRIVER_NAME); static inline struct musb *dev_to_musb(struct device *dev) { -#ifdef CONFIG_USB_MUSB_HDRC_HCD - /* usbcore insists dev->driver_data is a "struct hcd *" */ - return hcd_to_musb(dev_get_drvdata(dev)); -#else return dev_get_drvdata(dev); -#endif } /*-------------------------------------------------------------------------*/ @@ -1869,6 +1864,7 @@ allocate_instance(struct device *dev, INIT_LIST_HEAD(&musb->out_bulk); hcd->uses_new_polling = 1; + hcd->has_tt = 1; musb->vbuserr_retry = VBUSERR_RETRY_COUNT; musb->a_wait_bcon = OTG_TIME_A_WAIT_BCON; @@ -1876,10 +1872,9 @@ allocate_instance(struct device *dev, musb = kzalloc(sizeof *musb, GFP_KERNEL); if (!musb) return NULL; - dev_set_drvdata(dev, musb); #endif - + dev_set_drvdata(dev, musb); musb->mregs = mbase; musb->ctrl_base = mbase; musb->nIrq = -ENODEV; @@ -2191,7 +2186,7 @@ static int __init musb_probe(struct platform_device *pdev) void __iomem *base; iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!iomem || irq == 0) + if (!iomem || irq <= 0) return -ENODEV; base = ioremap(iomem->start, resource_size(iomem)); diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index d0c236f..e6400be 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -497,6 +497,19 @@ struct musb { struct usb_gadget_driver *gadget_driver; /* its driver */ #endif + /* + * FIXME: Remove this flag. + * + * This is only added to allow Blackfin to work + * with current driver. For some unknown reason + * Blackfin doesn't work with double buffering + * and that's enabled by default. + * + * We added this flag to forcefully disable double + * buffering until we get it working. + */ + unsigned double_buffer_not_ok:1 __deprecated; + struct musb_hdrc_config *config; #ifdef MUSB_CONFIG_PROC_FS diff --git a/drivers/usb/musb/musb_dma.h b/drivers/usb/musb/musb_dma.h index 916065b..3a97c4e 100644 --- a/drivers/usb/musb/musb_dma.h +++ b/drivers/usb/musb/musb_dma.h @@ -169,6 +169,9 @@ struct dma_controller { dma_addr_t dma_addr, u32 length); int (*channel_abort)(struct dma_channel *); + int (*is_compatible)(struct dma_channel *channel, + u16 maxpacket, + void *buf, u32 length); }; /* called after channel_program(), may indicate a fault */ diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index ed58c6c..2fe3046 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -92,11 +92,33 @@ /* ----------------------------------------------------------------------- */ +#define is_buffer_mapped(req) (is_dma_capable() && \ + (req->map_state != UN_MAPPED)) + /* Maps the buffer to dma */ static inline void map_dma_buffer(struct musb_request *request, - struct musb *musb) + struct musb *musb, struct musb_ep *musb_ep) { + int compatible = true; + struct dma_controller *dma = musb->dma_controller; + + request->map_state = UN_MAPPED; + + if (!is_dma_capable() || !musb_ep->dma) + return; + + /* Check if DMA engine can handle this request. + * DMA code must reject the USB request explicitly. + * Default behaviour is to map the request. + */ + if (dma->is_compatible) + compatible = dma->is_compatible(musb_ep->dma, + musb_ep->packet_sz, request->request.buf, + request->request.length); + if (!compatible) + return; + if (request->request.dma == DMA_ADDR_INVALID) { request->request.dma = dma_map_single( musb->controller, @@ -105,7 +127,7 @@ static inline void map_dma_buffer(struct musb_request *request, request->tx ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - request->mapped = 1; + request->map_state = MUSB_MAPPED; } else { dma_sync_single_for_device(musb->controller, request->request.dma, @@ -113,7 +135,7 @@ static inline void map_dma_buffer(struct musb_request *request, request->tx ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - request->mapped = 0; + request->map_state = PRE_MAPPED; } } @@ -121,11 +143,14 @@ static inline void map_dma_buffer(struct musb_request *request, static inline void unmap_dma_buffer(struct musb_request *request, struct musb *musb) { + if (!is_buffer_mapped(request)) + return; + if (request->request.dma == DMA_ADDR_INVALID) { DBG(20, "not unmapping a never mapped buffer\n"); return; } - if (request->mapped) { + if (request->map_state == MUSB_MAPPED) { dma_unmap_single(musb->controller, request->request.dma, request->request.length, @@ -133,16 +158,15 @@ static inline void unmap_dma_buffer(struct musb_request *request, ? DMA_TO_DEVICE : DMA_FROM_DEVICE); request->request.dma = DMA_ADDR_INVALID; - request->mapped = 0; - } else { + } else { /* PRE_MAPPED */ dma_sync_single_for_cpu(musb->controller, request->request.dma, request->request.length, request->tx ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - } + request->map_state = UN_MAPPED; } /* @@ -172,8 +196,7 @@ __acquires(ep->musb->lock) ep->busy = 1; spin_unlock(&musb->lock); - if (is_dma_capable() && ep->dma) - unmap_dma_buffer(req, musb); + unmap_dma_buffer(req, musb); if (request->status == 0) DBG(5, "%s done request %p, %d/%d\n", ep->end_point.name, request, @@ -335,7 +358,7 @@ static void txstate(struct musb *musb, struct musb_request *req) csr); #ifndef CONFIG_MUSB_PIO_ONLY - if (is_dma_capable() && musb_ep->dma) { + if (is_buffer_mapped(req)) { struct dma_controller *c = musb->dma_controller; size_t request_size; @@ -436,8 +459,7 @@ static void txstate(struct musb *musb, struct musb_request *req) * Unmap the dma buffer back to cpu if dma channel * programming fails */ - if (is_dma_capable() && musb_ep->dma) - unmap_dma_buffer(req, musb); + unmap_dma_buffer(req, musb); musb_write_fifo(musb_ep->hw_ep, fifo_count, (u8 *) (request->buf + request->actual)); @@ -627,7 +649,7 @@ static void rxstate(struct musb *musb, struct musb_request *req) return; } - if (is_cppi_enabled() && musb_ep->dma) { + if (is_cppi_enabled() && is_buffer_mapped(req)) { struct dma_controller *c = musb->dma_controller; struct dma_channel *channel = musb_ep->dma; @@ -658,7 +680,7 @@ static void rxstate(struct musb *musb, struct musb_request *req) len = musb_readw(epio, MUSB_RXCOUNT); if (request->actual < request->length) { #ifdef CONFIG_USB_INVENTRA_DMA - if (is_dma_capable() && musb_ep->dma) { + if (is_buffer_mapped(req)) { struct dma_controller *c; struct dma_channel *channel; int use_dma = 0; @@ -742,7 +764,7 @@ static void rxstate(struct musb *musb, struct musb_request *req) fifo_count = min_t(unsigned, len, fifo_count); #ifdef CONFIG_USB_TUSB_OMAP_DMA - if (tusb_dma_omap() && musb_ep->dma) { + if (tusb_dma_omap() && is_buffer_mapped(req)) { struct dma_controller *c = musb->dma_controller; struct dma_channel *channel = musb_ep->dma; u32 dma_addr = request->dma + request->actual; @@ -762,7 +784,7 @@ static void rxstate(struct musb *musb, struct musb_request *req) * programming fails. This buffer is mapped if the * channel allocation is successful */ - if (is_dma_capable() && musb_ep->dma) { + if (is_buffer_mapped(req)) { unmap_dma_buffer(req, musb); /* @@ -989,7 +1011,11 @@ static int musb_gadget_enable(struct usb_ep *ep, /* Set TXMAXP with the FIFO size of the endpoint * to disable double buffering mode. */ - musb_writew(regs, MUSB_TXMAXP, musb_ep->packet_sz | (musb_ep->hb_mult << 11)); + if (musb->double_buffer_not_ok) + musb_writew(regs, MUSB_TXMAXP, hw_ep->max_packet_sz_tx); + else + musb_writew(regs, MUSB_TXMAXP, musb_ep->packet_sz + | (musb_ep->hb_mult << 11)); csr = MUSB_TXCSR_MODE | MUSB_TXCSR_CLRDATATOG; if (musb_readw(regs, MUSB_TXCSR) @@ -1025,7 +1051,11 @@ static int musb_gadget_enable(struct usb_ep *ep, /* Set RXMAXP with the FIFO size of the endpoint * to disable double buffering mode. */ - musb_writew(regs, MUSB_RXMAXP, musb_ep->packet_sz | (musb_ep->hb_mult << 11)); + if (musb->double_buffer_not_ok) + musb_writew(regs, MUSB_RXMAXP, hw_ep->max_packet_sz_tx); + else + musb_writew(regs, MUSB_RXMAXP, musb_ep->packet_sz + | (musb_ep->hb_mult << 11)); /* force shared fifo to OUT-only mode */ if (hw_ep->is_shared_fifo) { @@ -1214,10 +1244,7 @@ static int musb_gadget_queue(struct usb_ep *ep, struct usb_request *req, request->epnum = musb_ep->current_epnum; request->tx = musb_ep->is_in; - if (is_dma_capable() && musb_ep->dma) - map_dma_buffer(request, musb); - else - request->mapped = 0; + map_dma_buffer(request, musb, musb_ep); spin_lock_irqsave(&musb->lock, lockflags); diff --git a/drivers/usb/musb/musb_gadget.h b/drivers/usb/musb/musb_gadget.h index dec8dc0..a55354f 100644 --- a/drivers/usb/musb/musb_gadget.h +++ b/drivers/usb/musb/musb_gadget.h @@ -35,13 +35,19 @@ #ifndef __MUSB_GADGET_H #define __MUSB_GADGET_H +enum buffer_map_state { + UN_MAPPED = 0, + PRE_MAPPED, + MUSB_MAPPED +}; + struct musb_request { struct usb_request request; struct musb_ep *ep; struct musb *musb; u8 tx; /* endpoint direction */ u8 epnum; - u8 mapped; + enum buffer_map_state map_state; }; static inline struct musb_request *to_musb_request(struct usb_request *req) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 4d5bcb4..0f523d7 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -609,7 +609,7 @@ musb_rx_reinit(struct musb *musb, struct musb_qh *qh, struct musb_hw_ep *ep) /* Set RXMAXP with the FIFO size of the endpoint * to disable double buffer mode. */ - if (musb->hwvers < MUSB_HWVERS_2000) + if (musb->double_buffer_not_ok) musb_writew(ep->regs, MUSB_RXMAXP, ep->max_packet_sz_rx); else musb_writew(ep->regs, MUSB_RXMAXP, @@ -784,14 +784,13 @@ static void musb_ep_program(struct musb *musb, u8 epnum, /* protocol/endpoint/interval/NAKlimit */ if (epnum) { musb_writeb(epio, MUSB_TXTYPE, qh->type_reg); - if (can_bulk_split(musb, qh->type)) + if (musb->double_buffer_not_ok) musb_writew(epio, MUSB_TXMAXP, - packet_sz - | ((hw_ep->max_packet_sz_tx / - packet_sz) - 1) << 11); + hw_ep->max_packet_sz_tx); else musb_writew(epio, MUSB_TXMAXP, - packet_sz); + qh->maxpacket | + ((qh->hb_mult - 1) << 11)); musb_writeb(epio, MUSB_TXINTERVAL, qh->intv_reg); } else { musb_writeb(epio, MUSB_NAKLIMIT0, qh->intv_reg); diff --git a/drivers/usb/musb/musbhsdma.h b/drivers/usb/musb/musbhsdma.h index f763d62..21056c9 100644 --- a/drivers/usb/musb/musbhsdma.h +++ b/drivers/usb/musb/musbhsdma.h @@ -94,24 +94,33 @@ static inline void musb_write_hsdma_addr(void __iomem *mbase, { musb_writew(mbase, MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDR_LOW), - ((u16)((u32) dma_addr & 0xFFFF))); + dma_addr); musb_writew(mbase, MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_ADDR_HIGH), - ((u16)(((u32) dma_addr >> 16) & 0xFFFF))); + (dma_addr >> 16)); } static inline u32 musb_read_hsdma_count(void __iomem *mbase, u8 bchannel) { - return musb_readl(mbase, + u32 count = musb_readw(mbase, MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_HIGH)); + + count = count << 16; + + count |= musb_readw(mbase, + MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_LOW)); + + return count; } static inline void musb_write_hsdma_count(void __iomem *mbase, u8 bchannel, u32 len) { - musb_writel(mbase, + musb_writew(mbase, + MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_LOW),len); + musb_writew(mbase, MUSB_HSDMA_CHANNEL_OFFSET(bchannel, MUSB_HSDMA_COUNT_HIGH), - len); + (len >> 16)); } #endif /* CONFIG_BLACKFIN */ diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index a3f1233..bc8badd 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -362,6 +362,7 @@ static int omap2430_musb_init(struct musb *musb) static int omap2430_musb_exit(struct musb *musb) { + del_timer_sync(&musb_idle_timer); omap2430_low_level_exit(musb); otg_put_transceiver(musb->xceiv); diff --git a/drivers/usb/otg/Kconfig b/drivers/usb/otg/Kconfig index 9fb875d..9ffc823 100644 --- a/drivers/usb/otg/Kconfig +++ b/drivers/usb/otg/Kconfig @@ -103,6 +103,8 @@ config USB_MSM_OTG_72K required after resetting the hardware and power management. This driver is required even for peripheral only or host only mode configurations. + This driver is not supported on boards like trout which + has an external PHY. config AB8500_USB tristate "AB8500 USB Transceiver Driver" diff --git a/drivers/usb/otg/nop-usb-xceiv.c b/drivers/usb/otg/nop-usb-xceiv.c index e70014a..8acf165 100644 --- a/drivers/usb/otg/nop-usb-xceiv.c +++ b/drivers/usb/otg/nop-usb-xceiv.c @@ -132,6 +132,8 @@ static int __devinit nop_usb_xceiv_probe(struct platform_device *pdev) platform_set_drvdata(pdev, nop); + BLOCKING_INIT_NOTIFIER_HEAD(&nop->otg.notifier); + return 0; exit: kfree(nop); diff --git a/drivers/usb/otg/ulpi.c b/drivers/usb/otg/ulpi.c index 059d9ac..770d799 100644 --- a/drivers/usb/otg/ulpi.c +++ b/drivers/usb/otg/ulpi.c @@ -45,7 +45,7 @@ struct ulpi_info { /* ULPI hardcoded IDs, used for probing */ static struct ulpi_info ulpi_ids[] = { ULPI_INFO(ULPI_ID(0x04cc, 0x1504), "NXP ISP1504"), - ULPI_INFO(ULPI_ID(0x0424, 0x0006), "SMSC USB3319"), + ULPI_INFO(ULPI_ID(0x0424, 0x0006), "SMSC USB331x"), }; static int ulpi_set_otg_flags(struct otg_transceiver *otg) diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index 63f7cc4..7b8815d 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -486,12 +486,22 @@ static void ch341_read_int_callback(struct urb *urb) if (actual_length >= 4) { struct ch341_private *priv = usb_get_serial_port_data(port); unsigned long flags; + u8 prev_line_status = priv->line_status; spin_lock_irqsave(&priv->lock, flags); priv->line_status = (~(data[2])) & CH341_BITS_MODEM_STAT; if ((data[1] & CH341_MULT_STAT)) priv->multi_status_change = 1; spin_unlock_irqrestore(&priv->lock, flags); + + if ((priv->line_status ^ prev_line_status) & CH341_BIT_DCD) { + struct tty_struct *tty = tty_port_tty_get(&port->port); + if (tty) + usb_serial_handle_dcd_change(port, tty, + priv->line_status & CH341_BIT_DCD); + tty_kref_put(tty); + } + wake_up_interruptible(&priv->delta_msr_wait); } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 8d7731d..735ea03 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -49,7 +49,6 @@ static int cp210x_tiocmset_port(struct usb_serial_port *port, struct file *, static void cp210x_break_ctl(struct tty_struct *, int); static int cp210x_startup(struct usb_serial *); static void cp210x_dtr_rts(struct usb_serial_port *p, int on); -static int cp210x_carrier_raised(struct usb_serial_port *p); static int debug; @@ -87,7 +86,6 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8115) }, /* Arygon NFC/Mifare Reader */ { USB_DEVICE(0x10C4, 0x813D) }, /* Burnside Telecom Deskmobile */ { USB_DEVICE(0x10C4, 0x813F) }, /* Tams Master Easy Control */ - { USB_DEVICE(0x10C4, 0x8149) }, /* West Mountain Radio Computerized Battery Analyzer */ { USB_DEVICE(0x10C4, 0x814A) }, /* West Mountain Radio RIGblaster P&P */ { USB_DEVICE(0x10C4, 0x814B) }, /* West Mountain Radio RIGtalk */ { USB_DEVICE(0x10C4, 0x8156) }, /* B&G H3000 link cable */ @@ -110,7 +108,9 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ { USB_DEVICE(0x10C4, 0x83A8) }, /* Amber Wireless AMB2560 */ + { USB_DEVICE(0x10C4, 0x83D8) }, /* DekTec DTA Plus VHF/UHF Booster/Attenuator */ { USB_DEVICE(0x10C4, 0x8411) }, /* Kyocera GPS Module */ + { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ { USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ { USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */ @@ -165,8 +165,7 @@ static struct usb_serial_driver cp210x_device = { .tiocmget = cp210x_tiocmget, .tiocmset = cp210x_tiocmset, .attach = cp210x_startup, - .dtr_rts = cp210x_dtr_rts, - .carrier_raised = cp210x_carrier_raised + .dtr_rts = cp210x_dtr_rts }; /* Config request types */ @@ -765,15 +764,6 @@ static int cp210x_tiocmget (struct tty_struct *tty, struct file *file) return result; } -static int cp210x_carrier_raised(struct usb_serial_port *p) -{ - unsigned int control; - cp210x_get_config(p, CP210X_GET_MDMSTS, &control, 1); - if (control & CONTROL_DCD) - return 1; - return 0; -} - static void cp210x_break_ctl (struct tty_struct *tty, int break_state) { struct usb_serial_port *port = tty->driver_data; diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c index b92070c..666e5a6 100644 --- a/drivers/usb/serial/digi_acceleport.c +++ b/drivers/usb/serial/digi_acceleport.c @@ -455,7 +455,6 @@ static int digi_write_room(struct tty_struct *tty); static int digi_chars_in_buffer(struct tty_struct *tty); static int digi_open(struct tty_struct *tty, struct usb_serial_port *port); static void digi_close(struct usb_serial_port *port); -static int digi_carrier_raised(struct usb_serial_port *port); static void digi_dtr_rts(struct usb_serial_port *port, int on); static int digi_startup_device(struct usb_serial *serial); static int digi_startup(struct usb_serial *serial); @@ -511,7 +510,6 @@ static struct usb_serial_driver digi_acceleport_2_device = { .open = digi_open, .close = digi_close, .dtr_rts = digi_dtr_rts, - .carrier_raised = digi_carrier_raised, .write = digi_write, .write_room = digi_write_room, .write_bulk_callback = digi_write_bulk_callback, @@ -1339,14 +1337,6 @@ static void digi_dtr_rts(struct usb_serial_port *port, int on) digi_set_modem_signals(port, on * (TIOCM_DTR|TIOCM_RTS), 1); } -static int digi_carrier_raised(struct usb_serial_port *port) -{ - struct digi_port *priv = usb_get_serial_port_data(port); - if (priv->dp_modem_signals & TIOCM_CD) - return 1; - return 0; -} - static int digi_open(struct tty_struct *tty, struct usb_serial_port *port) { int ret; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index a2668d0..f349a36 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -100,6 +100,7 @@ struct ftdi_sio_quirk { static int ftdi_jtag_probe(struct usb_serial *serial); static int ftdi_mtxorb_hack_setup(struct usb_serial *serial); static int ftdi_NDI_device_setup(struct usb_serial *serial); +static int ftdi_stmclite_probe(struct usb_serial *serial); static void ftdi_USB_UIRT_setup(struct ftdi_private *priv); static void ftdi_HE_TIRA1_setup(struct ftdi_private *priv); @@ -123,6 +124,10 @@ static struct ftdi_sio_quirk ftdi_HE_TIRA1_quirk = { .port_probe = ftdi_HE_TIRA1_setup, }; +static struct ftdi_sio_quirk ftdi_stmclite_quirk = { + .probe = ftdi_stmclite_probe, +}; + /* * The 8U232AM has the same API as the sio except for: * - it can support MUCH higher baudrates; up to: @@ -616,6 +621,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, FTDI_OCEANIC_PID) }, { USB_DEVICE(TTI_VID, TTI_QL355P_PID) }, { USB_DEVICE(FTDI_VID, FTDI_RM_CANVIEW_PID) }, + { USB_DEVICE(ACTON_VID, ACTON_SPECTRAPRO_PID) }, { USB_DEVICE(CONTEC_VID, CONTEC_COM1USBH_PID) }, { USB_DEVICE(BANDB_VID, BANDB_USOTL4_PID) }, { USB_DEVICE(BANDB_VID, BANDB_USTL4_PID) }, @@ -676,7 +682,17 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, FTDI_PCDJ_DAC2_PID) }, { USB_DEVICE(FTDI_VID, FTDI_RRCIRKITS_LOCOBUFFER_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ASK_RDR400_PID) }, - { USB_DEVICE(ICOM_ID1_VID, ICOM_ID1_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_1_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_OPC_U_UC_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2C1_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2C2_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2D_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2VT_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2VR_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP4KVT_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP4KVR_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2KVT_PID) }, + { USB_DEVICE(ICOM_VID, ICOM_ID_RP2KVR_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) }, { USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) }, @@ -800,6 +816,8 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) }, { USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(ST_VID, ST_STMCLT1030_PID), + .driver_info = (kernel_ulong_t)&ftdi_stmclite_quirk }, { }, /* Optional parameter entry */ { } /* Terminating entry */ }; @@ -1699,6 +1717,25 @@ static int ftdi_jtag_probe(struct usb_serial *serial) } /* + * First and second port on STMCLiteadaptors is reserved for JTAG interface + * and the forth port for pio + */ +static int ftdi_stmclite_probe(struct usb_serial *serial) +{ + struct usb_device *udev = serial->dev; + struct usb_interface *interface = serial->interface; + + dbg("%s", __func__); + + if (interface == udev->actconfig->interface[2]) + return 0; + + dev_info(&udev->dev, "Ignoring serial port reserved for JTAG\n"); + + return -ENODEV; +} + +/* * The Matrix Orbital VK204-25-USB has an invalid IN endpoint. * We have to correct it if we want to read from it. */ diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index bf08672..117e8e6 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -518,6 +518,12 @@ #define RATOC_PRODUCT_ID_USB60F 0xb020 /* + * Acton Research Corp. + */ +#define ACTON_VID 0x0647 /* Vendor ID */ +#define ACTON_SPECTRAPRO_PID 0x0100 + +/* * Contec products (http://www.contec.com) * Submitted by Daniel Sangorrin */ @@ -569,11 +575,23 @@ #define OCT_US101_PID 0x0421 /* OCT US101 USB to RS-232 */ /* - * Icom ID-1 digital transceiver + * Definitions for Icom Inc. devices */ - -#define ICOM_ID1_VID 0x0C26 -#define ICOM_ID1_PID 0x0004 +#define ICOM_VID 0x0C26 /* Icom vendor ID */ +/* Note: ID-1 is a communications tranceiver for HAM-radio operators */ +#define ICOM_ID_1_PID 0x0004 /* ID-1 USB to RS-232 */ +/* Note: OPC is an Optional cable to connect an Icom Tranceiver */ +#define ICOM_OPC_U_UC_PID 0x0018 /* OPC-478UC, OPC-1122U cloning cable */ +/* Note: ID-RP* devices are Icom Repeater Devices for HAM-radio */ +#define ICOM_ID_RP2C1_PID 0x0009 /* ID-RP2C Asset 1 to RS-232 */ +#define ICOM_ID_RP2C2_PID 0x000A /* ID-RP2C Asset 2 to RS-232 */ +#define ICOM_ID_RP2D_PID 0x000B /* ID-RP2D configuration port*/ +#define ICOM_ID_RP2VT_PID 0x000C /* ID-RP2V Transmit config port */ +#define ICOM_ID_RP2VR_PID 0x000D /* ID-RP2V Receive config port */ +#define ICOM_ID_RP4KVT_PID 0x0010 /* ID-RP4000V Transmit config port */ +#define ICOM_ID_RP4KVR_PID 0x0011 /* ID-RP4000V Receive config port */ +#define ICOM_ID_RP2KVT_PID 0x0012 /* ID-RP2000V Transmit config port */ +#define ICOM_ID_RP2KVR_PID 0x0013 /* ID-RP2000V Receive config port */ /* * GN Otometrics (http://www.otometrics.com) @@ -1022,6 +1040,12 @@ #define WHT_PID 0x0004 /* Wireless Handheld Terminal */ /* + * STMicroelectonics + */ +#define ST_VID 0x0483 +#define ST_STMCLT1030_PID 0x3747 /* ST Micro Connect Lite STMCLT1030 */ + +/* * Papouch products (http://www.papouch.com/) * Submitted by Folkert van Heusden */ diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index e6833e2..e4db5ad 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -479,6 +479,26 @@ int usb_serial_handle_break(struct usb_serial_port *port) } EXPORT_SYMBOL_GPL(usb_serial_handle_break); +/** + * usb_serial_handle_dcd_change - handle a change of carrier detect state + * @port: usb_serial_port structure for the open port + * @tty: tty_struct structure for the port + * @status: new carrier detect status, nonzero if active + */ +void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, + struct tty_struct *tty, unsigned int status) +{ + struct tty_port *port = &usb_port->port; + + dbg("%s - port %d, status %d", __func__, usb_port->number, status); + + if (status) + wake_up_interruptible(&port->open_wait); + else if (tty && !C_CLOCAL(tty)) + tty_hangup(tty); +} +EXPORT_SYMBOL_GPL(usb_serial_handle_dcd_change); + int usb_serial_generic_resume(struct usb_serial *serial) { struct usb_serial_port *port; diff --git a/drivers/usb/serial/io_edgeport.c b/drivers/usb/serial/io_edgeport.c index cd769ef..3b246d9 100644 --- a/drivers/usb/serial/io_edgeport.c +++ b/drivers/usb/serial/io_edgeport.c @@ -2889,8 +2889,8 @@ static void load_application_firmware(struct edgeport_serial *edge_serial) dbg("%s %d.%d.%d", fw_info, rec->data[0], rec->data[1], build); - edge_serial->product_info.FirmwareMajorVersion = fw->data[0]; - edge_serial->product_info.FirmwareMinorVersion = fw->data[1]; + edge_serial->product_info.FirmwareMajorVersion = rec->data[0]; + edge_serial->product_info.FirmwareMinorVersion = rec->data[1]; edge_serial->product_info.FirmwareBuildNumber = cpu_to_le16(build); for (rec = ihex_next_binrec(rec); rec; diff --git a/drivers/usb/serial/io_tables.h b/drivers/usb/serial/io_tables.h index 6ab2a3f..178b22e 100644 --- a/drivers/usb/serial/io_tables.h +++ b/drivers/usb/serial/io_tables.h @@ -199,6 +199,7 @@ static struct usb_serial_driver epic_device = { .name = "epic", }, .description = "EPiC device", + .usb_driver = &io_driver, .id_table = Epic_port_id_table, .num_ports = 1, .open = edge_open, diff --git a/drivers/usb/serial/iuu_phoenix.c b/drivers/usb/serial/iuu_phoenix.c index 12ed594..99b97c0 100644 --- a/drivers/usb/serial/iuu_phoenix.c +++ b/drivers/usb/serial/iuu_phoenix.c @@ -1275,6 +1275,7 @@ static struct usb_serial_driver iuu_device = { .name = "iuu_phoenix", }, .id_table = id_table, + .usb_driver = &iuu_driver, .num_ports = 1, .bulk_in_size = 512, .bulk_out_size = 512, diff --git a/drivers/usb/serial/keyspan.h b/drivers/usb/serial/keyspan.h index 2d8baf6..ce134dc 100644 --- a/drivers/usb/serial/keyspan.h +++ b/drivers/usb/serial/keyspan.h @@ -546,6 +546,7 @@ static struct usb_serial_driver keyspan_pre_device = { .name = "keyspan_no_firm", }, .description = "Keyspan - (without firmware)", + .usb_driver = &keyspan_driver, .id_table = keyspan_pre_ids, .num_ports = 1, .attach = keyspan_fake_startup, @@ -557,6 +558,7 @@ static struct usb_serial_driver keyspan_1port_device = { .name = "keyspan_1", }, .description = "Keyspan 1 port adapter", + .usb_driver = &keyspan_driver, .id_table = keyspan_1port_ids, .num_ports = 1, .open = keyspan_open, @@ -579,6 +581,7 @@ static struct usb_serial_driver keyspan_2port_device = { .name = "keyspan_2", }, .description = "Keyspan 2 port adapter", + .usb_driver = &keyspan_driver, .id_table = keyspan_2port_ids, .num_ports = 2, .open = keyspan_open, @@ -601,6 +604,7 @@ static struct usb_serial_driver keyspan_4port_device = { .name = "keyspan_4", }, .description = "Keyspan 4 port adapter", + .usb_driver = &keyspan_driver, .id_table = keyspan_4port_ids, .num_ports = 4, .open = keyspan_open, diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c index a10dd56..554a869 100644 --- a/drivers/usb/serial/keyspan_pda.c +++ b/drivers/usb/serial/keyspan_pda.c @@ -679,22 +679,6 @@ static void keyspan_pda_dtr_rts(struct usb_serial_port *port, int on) } } -static int keyspan_pda_carrier_raised(struct usb_serial_port *port) -{ - struct usb_serial *serial = port->serial; - unsigned char modembits; - - /* If we can read the modem status and the DCD is low then - carrier is not raised yet */ - if (keyspan_pda_get_modem_info(serial, &modembits) >= 0) { - if (!(modembits & (1>>6))) - return 0; - } - /* Carrier raised, or we failed (eg disconnected) so - progress accordingly */ - return 1; -} - static int keyspan_pda_open(struct tty_struct *tty, struct usb_serial_port *port) @@ -881,7 +865,6 @@ static struct usb_serial_driver keyspan_pda_device = { .id_table = id_table_std, .num_ports = 1, .dtr_rts = keyspan_pda_dtr_rts, - .carrier_raised = keyspan_pda_carrier_raised, .open = keyspan_pda_open, .close = keyspan_pda_close, .write = keyspan_pda_write, diff --git a/drivers/usb/serial/moto_modem.c b/drivers/usb/serial/moto_modem.c index cf17183..653465f 100644 --- a/drivers/usb/serial/moto_modem.c +++ b/drivers/usb/serial/moto_modem.c @@ -44,6 +44,7 @@ static struct usb_serial_driver moto_device = { .name = "moto-modem", }, .id_table = id_table, + .usb_driver = &moto_driver, .num_ports = 1, }; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7487782..5f46838 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -382,7 +382,16 @@ static void option_instat_callback(struct urb *urb); #define HAIER_VENDOR_ID 0x201e #define HAIER_PRODUCT_CE100 0x2009 -#define CINTERION_VENDOR_ID 0x0681 +/* Cinterion (formerly Siemens) products */ +#define SIEMENS_VENDOR_ID 0x0681 +#define CINTERION_VENDOR_ID 0x1e2d +#define CINTERION_PRODUCT_HC25_MDM 0x0047 +#define CINTERION_PRODUCT_HC25_MDMNET 0x0040 +#define CINTERION_PRODUCT_HC28_MDM 0x004C +#define CINTERION_PRODUCT_HC28_MDMNET 0x004A /* same for HC28J */ +#define CINTERION_PRODUCT_EU3_E 0x0051 +#define CINTERION_PRODUCT_EU3_P 0x0052 +#define CINTERION_PRODUCT_PH8 0x0053 /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -944,7 +953,17 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_100F) }, { USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_1011)}, { USB_DEVICE(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_1012)}, - { USB_DEVICE(CINTERION_VENDOR_ID, 0x0047) }, + /* Cinterion */ + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) }, + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) }, + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */ + { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) }, { USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */ { USB_DEVICE(ONDA_VENDOR_ID, ONDA_MT825UP) }, /* ONDA MT825UP modem */ diff --git a/drivers/usb/serial/oti6858.c b/drivers/usb/serial/oti6858.c index 5be866b..7361320 100644 --- a/drivers/usb/serial/oti6858.c +++ b/drivers/usb/serial/oti6858.c @@ -157,6 +157,7 @@ static struct usb_serial_driver oti6858_device = { .name = "oti6858", }, .id_table = id_table, + .usb_driver = &oti6858_driver, .num_ports = 1, .open = oti6858_open, .close = oti6858_close, diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 8ae4c6c..08c9181 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -50,6 +50,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MMX) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) }, { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, @@ -677,9 +678,11 @@ static void pl2303_update_line_status(struct usb_serial_port *port, { struct pl2303_private *priv = usb_get_serial_port_data(port); + struct tty_struct *tty; unsigned long flags; u8 status_idx = UART_STATE; u8 length = UART_STATE + 1; + u8 prev_line_status; u16 idv, idp; idv = le16_to_cpu(port->serial->dev->descriptor.idVendor); @@ -701,11 +704,20 @@ static void pl2303_update_line_status(struct usb_serial_port *port, /* Save off the uart status for others to look at */ spin_lock_irqsave(&priv->lock, flags); + prev_line_status = priv->line_status; priv->line_status = data[status_idx]; spin_unlock_irqrestore(&priv->lock, flags); if (priv->line_status & UART_BREAK_ERROR) usb_serial_handle_break(port); wake_up_interruptible(&priv->delta_msr_wait); + + tty = tty_port_tty_get(&port->port); + if (!tty) + return; + if ((priv->line_status ^ prev_line_status) & UART_DCD) + usb_serial_handle_dcd_change(port, tty, + priv->line_status & UART_DCD); + tty_kref_put(tty); } static void pl2303_read_int_callback(struct urb *urb) diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 43eb9bd..1b025f7 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -21,6 +21,7 @@ #define PL2303_PRODUCT_ID_MMX 0x0612 #define PL2303_PRODUCT_ID_GPRS 0x0609 #define PL2303_PRODUCT_ID_HCR331 0x331a +#define PL2303_PRODUCT_ID_MOTOROLA 0x0307 #define ATEN_VENDOR_ID 0x0557 #define ATEN_VENDOR_ID2 0x0547 diff --git a/drivers/usb/serial/qcaux.c b/drivers/usb/serial/qcaux.c index 214a3e5..30b73e6 100644 --- a/drivers/usb/serial/qcaux.c +++ b/drivers/usb/serial/qcaux.c @@ -36,6 +36,7 @@ #define UTSTARCOM_PRODUCT_UM175_V1 0x3712 #define UTSTARCOM_PRODUCT_UM175_V2 0x3714 #define UTSTARCOM_PRODUCT_UM175_ALLTEL 0x3715 +#define PANTECH_PRODUCT_UML290_VZW 0x3718 /* CMOTECH devices */ #define CMOTECH_VENDOR_ID 0x16d8 @@ -66,6 +67,7 @@ static struct usb_device_id id_table[] = { { USB_DEVICE_AND_INTERFACE_INFO(LG_VENDOR_ID, LG_PRODUCT_VX4400_6000, 0xff, 0xff, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(SANYO_VENDOR_ID, SANYO_PRODUCT_KATANA_LX, 0xff, 0xff, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_U520, 0xff, 0x00, 0x00) }, + { USB_DEVICE_AND_INTERFACE_INFO(UTSTARCOM_VENDOR_ID, PANTECH_PRODUCT_UML290_VZW, 0xff, 0xff, 0xff) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); @@ -84,6 +86,7 @@ static struct usb_serial_driver qcaux_device = { .name = "qcaux", }, .id_table = id_table, + .usb_driver = &qcaux_driver, .num_ports = 1, }; diff --git a/drivers/usb/serial/siemens_mpi.c b/drivers/usb/serial/siemens_mpi.c index cb8195c..74cd4cc 100644 --- a/drivers/usb/serial/siemens_mpi.c +++ b/drivers/usb/serial/siemens_mpi.c @@ -42,6 +42,7 @@ static struct usb_serial_driver siemens_usb_mpi_device = { .name = "siemens_mpi", }, .id_table = id_table, + .usb_driver = &siemens_usb_mpi_driver, .num_ports = 1, }; diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c index 7481ff8..0457813 100644 --- a/drivers/usb/serial/sierra.c +++ b/drivers/usb/serial/sierra.c @@ -301,6 +301,9 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */ .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist }, + { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */ + .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist + }, { USB_DEVICE(0x413C, 0x08133) }, /* Dell Computer Corp. Wireless 5720 VZW Mobile Broadband (EVDO Rev-A) Minicard GPS Port */ { } diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c index 765aa98..cbfb70b 100644 --- a/drivers/usb/serial/spcp8x5.c +++ b/drivers/usb/serial/spcp8x5.c @@ -133,7 +133,7 @@ struct spcp8x5_usb_ctrl_arg { /* how come ??? */ #define UART_STATE 0x08 -#define UART_STATE_TRANSIENT_MASK 0x74 +#define UART_STATE_TRANSIENT_MASK 0x75 #define UART_DCD 0x01 #define UART_DSR 0x02 #define UART_BREAK_ERROR 0x04 @@ -525,6 +525,10 @@ static void spcp8x5_process_read_urb(struct urb *urb) /* overrun is special, not associated with a char */ if (status & UART_OVERRUN_ERROR) tty_insert_flip_char(tty, 0, TTY_OVERRUN); + + if (status & UART_DCD) + usb_serial_handle_dcd_change(port, tty, + priv->line_status & MSR_STATUS_LINE_DCD); } tty_insert_flip_string_fixed_flag(tty, data, tty_flag, @@ -645,6 +649,7 @@ static struct usb_serial_driver spcp8x5_device = { .name = "SPCP8x5", }, .id_table = id_table, + .usb_driver = &spcp8x5_driver, .num_ports = 1, .open = spcp8x5_open, .dtr_rts = spcp8x5_dtr_rts, diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index b2902f3..a910004 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -369,9 +369,9 @@ failed_1port: static void __exit ti_exit(void) { + usb_deregister(&ti_usb_driver); usb_serial_deregister(&ti_1port_device); usb_serial_deregister(&ti_2port_device); - usb_deregister(&ti_usb_driver); } diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index 6954de5..546a521 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1344,11 +1344,15 @@ int usb_serial_register(struct usb_serial_driver *driver) return -ENODEV; fixup_generic(driver); - if (driver->usb_driver) - driver->usb_driver->supports_autosuspend = 1; if (!driver->description) driver->description = driver->driver.name; + if (!driver->usb_driver) { + WARN(1, "Serial driver %s has no usb_driver\n", + driver->description); + return -EINVAL; + } + driver->usb_driver->supports_autosuspend = 1; /* Add this device to our list of devices */ mutex_lock(&table_lock); diff --git a/drivers/usb/serial/usb_debug.c b/drivers/usb/serial/usb_debug.c index f2ed6a3..95a8214 100644 --- a/drivers/usb/serial/usb_debug.c +++ b/drivers/usb/serial/usb_debug.c @@ -75,6 +75,7 @@ static struct usb_serial_driver debug_device = { .name = "debug", }, .id_table = id_table, + .usb_driver = &debug_driver, .num_ports = 1, .bulk_out_size = USB_DEBUG_MAX_PACKET_SIZE, .break_ctl = usb_debug_break_ctl, diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c index b004b2a..9c014e2 100644 --- a/drivers/usb/serial/usb_wwan.c +++ b/drivers/usb/serial/usb_wwan.c @@ -295,12 +295,15 @@ static void usb_wwan_indat_callback(struct urb *urb) __func__, status, endpoint); } else { tty = tty_port_tty_get(&port->port); - if (urb->actual_length) { - tty_insert_flip_string(tty, data, urb->actual_length); - tty_flip_buffer_push(tty); - } else - dbg("%s: empty read urb received", __func__); - tty_kref_put(tty); + if (tty) { + if (urb->actual_length) { + tty_insert_flip_string(tty, data, + urb->actual_length); + tty_flip_buffer_push(tty); + } else + dbg("%s: empty read urb received", __func__); + tty_kref_put(tty); + } /* Resubmit urb so we continue receiving */ if (status != -ESHUTDOWN) { diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c index 15a5d89..1c11959 100644 --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -27,6 +27,7 @@ #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/serial.h> +#include <linux/usb/cdc.h> #include "visor.h" /* @@ -479,6 +480,17 @@ static int visor_probe(struct usb_serial *serial, dbg("%s", __func__); + /* + * some Samsung Android phones in modem mode have the same ID + * as SPH-I500, but they are ACM devices, so dont bind to them + */ + if (id->idVendor == SAMSUNG_VENDOR_ID && + id->idProduct == SAMSUNG_SPH_I500_ID && + serial->dev->descriptor.bDeviceClass == USB_CLASS_COMM && + serial->dev->descriptor.bDeviceSubClass == + USB_CDC_SUBCLASS_ACM) + return -ENODEV; + if (serial->dev->actconfig->desc.bConfigurationValue != 1) { dev_err(&serial->dev->dev, "active config #%d != 1 ??\n", serial->dev->actconfig->desc.bConfigurationValue); diff --git a/drivers/usb/storage/unusual_cypress.h b/drivers/usb/storage/unusual_cypress.h index c854fde..2c85530 100644 --- a/drivers/usb/storage/unusual_cypress.h +++ b/drivers/usb/storage/unusual_cypress.h @@ -31,4 +31,9 @@ UNUSUAL_DEV( 0x04b4, 0x6831, 0x0000, 0x9999, "Cypress ISD-300LP", USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0), +UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x9999, + "Super Top", + "USB 2.0 SATA BRIDGE", + USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0), + #endif /* defined(CONFIG_USB_STORAGE_CYPRESS_ATACB) || ... */ diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index fcc1e32..c1602b8 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1044,6 +1044,15 @@ UNUSUAL_DEV( 0x084d, 0x0011, 0x0110, 0x0110, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BULK32), +/* Reported by <ttkspam@free.fr> + * The device reports a vendor-specific device class, requiring an + * explicit vendor/product match. + */ +UNUSUAL_DEV( 0x0851, 0x1542, 0x0002, 0x0002, + "MagicPixel", + "FW_Omega2", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, 0), + /* Andrew Lunn <andrew@lunn.ch> * PanDigital Digital Picture Frame. Does not like ALLOW_MEDIUM_REMOVAL * on LUN 4. @@ -1388,6 +1397,13 @@ UNUSUAL_DEV( 0x0f19, 0x0105, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE ), +/* Submitted by Nick Holloway */ +UNUSUAL_DEV( 0x0f88, 0x042e, 0x0100, 0x0100, + "VTech", + "Kidizoom", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_FIX_CAPACITY ), + /* Reported by Michael Stattmann <michael@stattmann.com> */ UNUSUAL_DEV( 0x0fce, 0xd008, 0x0000, 0x0000, "Sony Ericsson", @@ -1872,6 +1888,22 @@ UNUSUAL_DEV( 0x1908, 0x3335, 0x0200, 0x0200, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_READ_DISC_INFO ), +/* Patch by Richard Schütz <r.schtz@t-online.de> + * This external hard drive enclosure uses a JMicron chip which + * needs the US_FL_IGNORE_RESIDUE flag to work properly. */ +UNUSUAL_DEV( 0x1e68, 0x001b, 0x0000, 0x0000, + "TrekStor GmbH & Co. KG", + "DataStation maxi g.u", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ), + +/* Reported by Jasper Mackenzie <scarletpimpernal@hotmail.com> */ +UNUSUAL_DEV( 0x1e74, 0x4621, 0x0000, 0x0000, + "Coby Electronics", + "MP3 Player", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ), + UNUSUAL_DEV( 0x2116, 0x0320, 0x0001, 0x0001, "ST", "2A", diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9b3ca10..f616cef 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -128,8 +128,7 @@ static void handle_tx(struct vhost_net *net) size_t hdr_size; struct socket *sock; - /* TODO: check that we are running from vhost_worker? - * Not sure it's worth it, it's straight-forward enough. */ + /* TODO: check that we are running from vhost_worker? */ sock = rcu_dereference_check(vq->private_data, 1); if (!sock) return; @@ -306,7 +305,8 @@ static void handle_rx_big(struct vhost_net *net) size_t len, total_len = 0; int err; size_t hdr_size; - struct socket *sock = rcu_dereference(vq->private_data); + /* TODO: check that we are running from vhost_worker? */ + struct socket *sock = rcu_dereference_check(vq->private_data, 1); if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue)) return; @@ -415,7 +415,8 @@ static void handle_rx_mergeable(struct vhost_net *net) int err, headcount; size_t vhost_hlen, sock_hlen; size_t vhost_len, sock_len; - struct socket *sock = rcu_dereference(vq->private_data); + /* TODO: check that we are running from vhost_worker? */ + struct socket *sock = rcu_dereference_check(vq->private_data, 1); if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue)) return; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 2af44b7..b3363ae 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -173,9 +173,9 @@ static inline int vhost_has_feature(struct vhost_dev *dev, int bit) { unsigned acked_features; - acked_features = - rcu_dereference_index_check(dev->acked_features, - lockdep_is_held(&dev->mutex)); + /* TODO: check that we are running from vhost_worker or dev mutex is + * held? */ + acked_features = rcu_dereference_index_check(dev->acked_features, 1); return acked_features & (1 << bit); } diff --git a/drivers/video/backlight/ltv350qv.c b/drivers/video/backlight/ltv350qv.c index 8010aae..dd0e84a 100644 --- a/drivers/video/backlight/ltv350qv.c +++ b/drivers/video/backlight/ltv350qv.c @@ -239,11 +239,15 @@ static int __devinit ltv350qv_probe(struct spi_device *spi) lcd->spi = spi; lcd->power = FB_BLANK_POWERDOWN; lcd->buffer = kzalloc(8, GFP_KERNEL); + if (!lcd->buffer) { + ret = -ENOMEM; + goto out_free_lcd; + } ld = lcd_device_register("ltv350qv", &spi->dev, lcd, <v_ops); if (IS_ERR(ld)) { ret = PTR_ERR(ld); - goto out_free_lcd; + goto out_free_buffer; } lcd->ld = ld; @@ -257,6 +261,8 @@ static int __devinit ltv350qv_probe(struct spi_device *spi) out_unregister: lcd_device_unregister(ld); +out_free_buffer: + kfree(lcd->buffer); out_free_lcd: kfree(lcd); return ret; @@ -268,6 +274,7 @@ static int __devexit ltv350qv_remove(struct spi_device *spi) ltv350qv_power(lcd, FB_BLANK_POWERDOWN); lcd_device_unregister(lcd->ld); + kfree(lcd->buffer); kfree(lcd); return 0; diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c index 3a7e9ff..38e96ab 100644 --- a/drivers/w1/masters/omap_hdq.c +++ b/drivers/w1/masters/omap_hdq.c @@ -593,19 +593,17 @@ static int __devinit omap_hdq_probe(struct platform_device *pdev) /* get interface & functional clock objects */ hdq_data->hdq_ick = clk_get(&pdev->dev, "ick"); - hdq_data->hdq_fck = clk_get(&pdev->dev, "fck"); + if (IS_ERR(hdq_data->hdq_ick)) { + dev_dbg(&pdev->dev, "Can't get HDQ ick clock object\n"); + ret = PTR_ERR(hdq_data->hdq_ick); + goto err_ick; + } - if (IS_ERR(hdq_data->hdq_ick) || IS_ERR(hdq_data->hdq_fck)) { - dev_dbg(&pdev->dev, "Can't get HDQ clock objects\n"); - if (IS_ERR(hdq_data->hdq_ick)) { - ret = PTR_ERR(hdq_data->hdq_ick); - goto err_clk; - } - if (IS_ERR(hdq_data->hdq_fck)) { - ret = PTR_ERR(hdq_data->hdq_fck); - clk_put(hdq_data->hdq_ick); - goto err_clk; - } + hdq_data->hdq_fck = clk_get(&pdev->dev, "fck"); + if (IS_ERR(hdq_data->hdq_fck)) { + dev_dbg(&pdev->dev, "Can't get HDQ fck clock object\n"); + ret = PTR_ERR(hdq_data->hdq_fck); + goto err_fck; } hdq_data->hdq_usecount = 0; @@ -665,10 +663,12 @@ err_fnclk: clk_disable(hdq_data->hdq_ick); err_intfclk: - clk_put(hdq_data->hdq_ick); clk_put(hdq_data->hdq_fck); -err_clk: +err_fck: + clk_put(hdq_data->hdq_ick); + +err_ick: iounmap(hdq_data->hdq_base); err_ioremap: diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 2e2400e..31649b7 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -862,12 +862,12 @@ config SBC_EPX_C3_WATCHDOG # M68K Architecture -config M548x_WATCHDOG - tristate "MCF548x watchdog support" +config M54xx_WATCHDOG + tristate "MCF54xx watchdog support" depends on M548x help To compile this driver as a module, choose M here: the - module will be called m548x_wdt. + module will be called m54xx_wdt. # MIPS Architecture diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index dd77665..20e44c4 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -106,7 +106,7 @@ obj-$(CONFIG_SBC_EPX_C3_WATCHDOG) += sbc_epx_c3.o # M32R Architecture # M68K Architecture -obj-$(CONFIG_M548x_WATCHDOG) += m548x_wdt.o +obj-$(CONFIG_M54xx_WATCHDOG) += m54xx_wdt.o # MIPS Architecture obj-$(CONFIG_ATH79_WDT) += ath79_wdt.o diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index eca855a..3de4ba0 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -646,7 +646,7 @@ static int __devexit cpwd_remove(struct platform_device *op) struct cpwd *p = dev_get_drvdata(&op->dev); int i; - for (i = 0; i < 4; i++) { + for (i = 0; i < WD_NUMDEVS; i++) { misc_deregister(&p->devs[i].misc); if (!p->enabled) { diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index 24b966d..204a560 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -710,7 +710,7 @@ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev) return 0; } -static void __devexit hpwdt_exit_nmi_decoding(void) +static void hpwdt_exit_nmi_decoding(void) { unregister_die_notifier(&die_notifier); if (cru_rom_addr) @@ -726,7 +726,7 @@ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev) return 0; } -static void __devexit hpwdt_exit_nmi_decoding(void) +static void hpwdt_exit_nmi_decoding(void) { } #endif /* CONFIG_HPWDT_NMI_DECODING */ diff --git a/drivers/watchdog/m548x_wdt.c b/drivers/watchdog/m54xx_wdt.c index cabbcfe..4d43286 100644 --- a/drivers/watchdog/m548x_wdt.c +++ b/drivers/watchdog/m54xx_wdt.c @@ -1,7 +1,7 @@ /* - * drivers/watchdog/m548x_wdt.c + * drivers/watchdog/m54xx_wdt.c * - * Watchdog driver for ColdFire MCF548x processors + * Watchdog driver for ColdFire MCF547x & MCF548x processors * Copyright 2010 (c) Philippe De Muyter <phdm@macqel.be> * * Adapted from the IXP4xx watchdog driver, which carries these notices: @@ -29,8 +29,8 @@ #include <linux/uaccess.h> #include <asm/coldfire.h> -#include <asm/m548xsim.h> -#include <asm/m548xgpt.h> +#include <asm/m54xxsim.h> +#include <asm/m54xxgpt.h> static int nowayout = WATCHDOG_NOWAYOUT; static unsigned int heartbeat = 30; /* (secs) Default is 0.5 minute */ @@ -76,7 +76,7 @@ static void wdt_keepalive(void) __raw_writel(gms0, MCF_MBAR + MCF_GPT_GMS0); } -static int m548x_wdt_open(struct inode *inode, struct file *file) +static int m54xx_wdt_open(struct inode *inode, struct file *file) { if (test_and_set_bit(WDT_IN_USE, &wdt_status)) return -EBUSY; @@ -86,7 +86,7 @@ static int m548x_wdt_open(struct inode *inode, struct file *file) return nonseekable_open(inode, file); } -static ssize_t m548x_wdt_write(struct file *file, const char *data, +static ssize_t m54xx_wdt_write(struct file *file, const char *data, size_t len, loff_t *ppos) { if (len) { @@ -112,10 +112,10 @@ static ssize_t m548x_wdt_write(struct file *file, const char *data, static const struct watchdog_info ident = { .options = WDIOF_MAGICCLOSE | WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, - .identity = "Coldfire M548x Watchdog", + .identity = "Coldfire M54xx Watchdog", }; -static long m548x_wdt_ioctl(struct file *file, unsigned int cmd, +static long m54xx_wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret = -ENOTTY; @@ -161,7 +161,7 @@ static long m548x_wdt_ioctl(struct file *file, unsigned int cmd, return ret; } -static int m548x_wdt_release(struct inode *inode, struct file *file) +static int m54xx_wdt_release(struct inode *inode, struct file *file) { if (test_bit(WDT_OK_TO_CLOSE, &wdt_status)) wdt_disable(); @@ -177,45 +177,45 @@ static int m548x_wdt_release(struct inode *inode, struct file *file) } -static const struct file_operations m548x_wdt_fops = { +static const struct file_operations m54xx_wdt_fops = { .owner = THIS_MODULE, .llseek = no_llseek, - .write = m548x_wdt_write, - .unlocked_ioctl = m548x_wdt_ioctl, - .open = m548x_wdt_open, - .release = m548x_wdt_release, + .write = m54xx_wdt_write, + .unlocked_ioctl = m54xx_wdt_ioctl, + .open = m54xx_wdt_open, + .release = m54xx_wdt_release, }; -static struct miscdevice m548x_wdt_miscdev = { +static struct miscdevice m54xx_wdt_miscdev = { .minor = WATCHDOG_MINOR, .name = "watchdog", - .fops = &m548x_wdt_fops, + .fops = &m54xx_wdt_fops, }; -static int __init m548x_wdt_init(void) +static int __init m54xx_wdt_init(void) { if (!request_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4, - "Coldfire M548x Watchdog")) { + "Coldfire M54xx Watchdog")) { printk(KERN_WARNING - "Coldfire M548x Watchdog : I/O region busy\n"); + "Coldfire M54xx Watchdog : I/O region busy\n"); return -EBUSY; } printk(KERN_INFO "ColdFire watchdog driver is loaded.\n"); - return misc_register(&m548x_wdt_miscdev); + return misc_register(&m54xx_wdt_miscdev); } -static void __exit m548x_wdt_exit(void) +static void __exit m54xx_wdt_exit(void) { - misc_deregister(&m548x_wdt_miscdev); + misc_deregister(&m54xx_wdt_miscdev); release_mem_region(MCF_MBAR + MCF_GPT_GCIR0, 4); } -module_init(m548x_wdt_init); -module_exit(m548x_wdt_exit); +module_init(m54xx_wdt_init); +module_exit(m54xx_wdt_exit); MODULE_AUTHOR("Philippe De Muyter <phdm@macqel.be>"); -MODULE_DESCRIPTION("Coldfire M548x Watchdog"); +MODULE_DESCRIPTION("Coldfire M54xx Watchdog"); module_param(heartbeat, int, 0); MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds (default 30s)"); diff --git a/drivers/watchdog/sbc_fitpc2_wdt.c b/drivers/watchdog/sbc_fitpc2_wdt.c index c7d67e9..7990625 100644 --- a/drivers/watchdog/sbc_fitpc2_wdt.c +++ b/drivers/watchdog/sbc_fitpc2_wdt.c @@ -201,11 +201,14 @@ static struct miscdevice fitpc2_wdt_miscdev = { static int __init fitpc2_wdt_init(void) { int err; + const char *brd_name; - if (!strstr(dmi_get_system_info(DMI_BOARD_NAME), "SBC-FITPC2")) + brd_name = dmi_get_system_info(DMI_BOARD_NAME); + + if (!brd_name || !strstr(brd_name, "SBC-FITPC2")) return -ENODEV; - pr_info("%s found\n", dmi_get_system_info(DMI_BOARD_NAME)); + pr_info("%s found\n", brd_name); if (!request_region(COMMAND_PORT, 1, WATCHDOG_NAME)) { pr_err("I/O address 0x%04x already in use\n", COMMAND_PORT); diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c index 0461858..b61ab1c 100644 --- a/drivers/watchdog/sch311x_wdt.c +++ b/drivers/watchdog/sch311x_wdt.c @@ -508,7 +508,7 @@ static int __init sch311x_detect(int sio_config_port, unsigned short *addr) sch311x_sio_outb(sio_config_port, 0x07, 0x0a); /* Check if Logical Device Register is currently active */ - if (sch311x_sio_inb(sio_config_port, 0x30) && 0x01 == 0) + if ((sch311x_sio_inb(sio_config_port, 0x30) & 0x01) == 0) printk(KERN_INFO PFX "Seems that LDN 0x0a is not active...\n"); /* Get the base address of the runtime registers */ diff --git a/drivers/watchdog/w83697ug_wdt.c b/drivers/watchdog/w83697ug_wdt.c index a6c12de..df2a64d 100644 --- a/drivers/watchdog/w83697ug_wdt.c +++ b/drivers/watchdog/w83697ug_wdt.c @@ -109,7 +109,7 @@ static int w83697ug_select_wd_register(void) outb_p(0x08, WDT_EFDR); /* select logical device 8 (GPIO2) */ outb_p(0x30, WDT_EFER); /* select CR30 */ c = inb_p(WDT_EFDR); - outb_p(c || 0x01, WDT_EFDR); /* set bit 0 to activate GPIO2 */ + outb_p(c | 0x01, WDT_EFDR); /* set bit 0 to activate GPIO2 */ return 0; } diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 43f9f02..718050a 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -232,7 +232,7 @@ static int increase_reservation(unsigned long nr_pages) set_phys_to_machine(pfn, frame_list[i]); /* Link back into the page tables if not highmem. */ - if (pfn < max_low_pfn) { + if (!xen_hvm_domain() && pfn < max_low_pfn) { int ret; ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), @@ -280,7 +280,7 @@ static int decrease_reservation(unsigned long nr_pages) scrub_page(page); - if (!PageHighMem(page)) { + if (!xen_hvm_domain() && !PageHighMem(page)) { ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), __pte_ma(0), 0); @@ -296,7 +296,7 @@ static int decrease_reservation(unsigned long nr_pages) /* No more mappings: invalidate P2M and add to balloon. */ for (i = 0; i < nr_pages; i++) { pfn = mfn_to_pfn(frame_list[i]); - set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); balloon_append(pfn_to_page(pfn)); } @@ -392,15 +392,19 @@ static struct notifier_block xenstore_notifier; static int __init balloon_init(void) { - unsigned long pfn, extra_pfn_end; + unsigned long pfn, nr_pages, extra_pfn_end; struct page *page; - if (!xen_pv_domain()) + if (!xen_domain()) return -ENODEV; pr_info("xen_balloon: Initialising balloon driver.\n"); - balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn); + if (xen_pv_domain()) + nr_pages = xen_start_info->nr_pages; + else + nr_pages = max_pfn; + balloon_stats.current_pages = min(nr_pages, max_pfn); balloon_stats.target_pages = balloon_stats.current_pages; balloon_stats.balloon_low = 0; balloon_stats.balloon_high = 0; diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 7468147..149fa87 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -114,7 +114,7 @@ struct cpu_evtchn_s { static __initdata struct cpu_evtchn_s init_evtchn_mask = { .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul, }; -static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask; +static struct cpu_evtchn_s __refdata *cpu_evtchn_mask_p = &init_evtchn_mask; static inline unsigned long *cpu_evtchn_mask(int cpu) { @@ -277,7 +277,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) BUG_ON(irq == -1); #ifdef CONFIG_SMP - cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu)); + cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu)); #endif clear_bit(chn, cpu_evtchn_mask(cpu_from_irq(irq))); @@ -294,7 +294,7 @@ static void init_evtchn_cpu_bindings(void) /* By default all event channels notify CPU#0. */ for_each_irq_desc(i, desc) { - cpumask_copy(desc->affinity, cpumask_of(0)); + cpumask_copy(desc->irq_data.affinity, cpumask_of(0)); } #endif @@ -376,81 +376,69 @@ static void unmask_evtchn(int port) put_cpu(); } -static int get_nr_hw_irqs(void) +static int xen_allocate_irq_dynamic(void) { - int ret = 1; + int first = 0; + int irq; #ifdef CONFIG_X86_IO_APIC - ret = get_nr_irqs_gsi(); + /* + * For an HVM guest or domain 0 which see "real" (emulated or + * actual repectively) GSIs we allocate dynamic IRQs + * e.g. those corresponding to event channels or MSIs + * etc. from the range above those "real" GSIs to avoid + * collisions. + */ + if (xen_initial_domain() || xen_hvm_domain()) + first = get_nr_irqs_gsi(); #endif - return ret; -} +retry: + irq = irq_alloc_desc_from(first, -1); -static int find_unbound_pirq(int type) -{ - int rc, i; - struct physdev_get_free_pirq op_get_free_pirq; - op_get_free_pirq.type = type; + if (irq == -ENOMEM && first > NR_IRQS_LEGACY) { + printk(KERN_ERR "Out of dynamic IRQ space and eating into GSI space. You should increase nr_irqs\n"); + first = max(NR_IRQS_LEGACY, first - NR_IRQS_LEGACY); + goto retry; + } - rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq); - if (!rc) - return op_get_free_pirq.pirq; + if (irq < 0) + panic("No available IRQ to bind to: increase nr_irqs!\n"); - for (i = 0; i < nr_irqs; i++) { - if (pirq_to_irq[i] < 0) - return i; - } - return -1; + return irq; } -static int find_unbound_irq(void) +static int xen_allocate_irq_gsi(unsigned gsi) { - struct irq_data *data; - int irq, res; - int bottom = get_nr_hw_irqs(); - int top = nr_irqs-1; - - if (bottom == nr_irqs) - goto no_irqs; + int irq; - /* This loop starts from the top of IRQ space and goes down. - * We need this b/c if we have a PCI device in a Xen PV guest - * we do not have an IO-APIC (though the backend might have them) - * mapped in. To not have a collision of physical IRQs with the Xen - * event channels start at the top of the IRQ space for virtual IRQs. + /* + * A PV guest has no concept of a GSI (since it has no ACPI + * nor access to/knowledge of the physical APICs). Therefore + * all IRQs are dynamically allocated from the entire IRQ + * space. */ - for (irq = top; irq > bottom; irq--) { - data = irq_get_irq_data(irq); - /* only 15->0 have init'd desc; handle irq > 16 */ - if (!data) - break; - if (data->chip == &no_irq_chip) - break; - if (data->chip != &xen_dynamic_chip) - continue; - if (irq_info[irq].type == IRQT_UNBOUND) - return irq; - } - - if (irq == bottom) - goto no_irqs; + if (xen_pv_domain() && !xen_initial_domain()) + return xen_allocate_irq_dynamic(); - res = irq_alloc_desc_at(irq, -1); + /* Legacy IRQ descriptors are already allocated by the arch. */ + if (gsi < NR_IRQS_LEGACY) + return gsi; - if (WARN_ON(res != irq)) - return -1; + irq = irq_alloc_desc_at(gsi, -1); + if (irq < 0) + panic("Unable to allocate to IRQ%d (%d)\n", gsi, irq); return irq; - -no_irqs: - panic("No available IRQ to bind to: increase nr_irqs!\n"); } -static bool identity_mapped_irq(unsigned irq) +static void xen_free_irq(unsigned irq) { - /* identity map all the hardware irqs */ - return irq < get_nr_hw_irqs(); + /* Legacy IRQ descriptors are managed by the arch. */ + if (irq < NR_IRQS_LEGACY) + return; + + irq_free_desc(irq); } static void pirq_unmask_notify(int irq) @@ -486,7 +474,7 @@ static bool probing_irq(int irq) return desc && desc->action == NULL; } -static unsigned int startup_pirq(unsigned int irq) +static unsigned int __startup_pirq(unsigned int irq) { struct evtchn_bind_pirq bind_pirq; struct irq_info *info = info_for_irq(irq); @@ -524,9 +512,15 @@ out: return 0; } -static void shutdown_pirq(unsigned int irq) +static unsigned int startup_pirq(struct irq_data *data) +{ + return __startup_pirq(data->irq); +} + +static void shutdown_pirq(struct irq_data *data) { struct evtchn_close close; + unsigned int irq = data->irq; struct irq_info *info = info_for_irq(irq); int evtchn = evtchn_from_irq(irq); @@ -546,20 +540,20 @@ static void shutdown_pirq(unsigned int irq) info->evtchn = 0; } -static void enable_pirq(unsigned int irq) +static void enable_pirq(struct irq_data *data) { - startup_pirq(irq); + startup_pirq(data); } -static void disable_pirq(unsigned int irq) +static void disable_pirq(struct irq_data *data) { } -static void ack_pirq(unsigned int irq) +static void ack_pirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(irq); + int evtchn = evtchn_from_irq(data->irq); - move_native_irq(irq); + move_native_irq(data->irq); if (VALID_EVTCHN(evtchn)) { mask_evtchn(evtchn); @@ -567,23 +561,6 @@ static void ack_pirq(unsigned int irq) } } -static void end_pirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - struct irq_desc *desc = irq_to_desc(irq); - - if (WARN_ON(!desc)) - return; - - if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) == - (IRQ_DISABLED|IRQ_PENDING)) { - shutdown_pirq(irq); - } else if (VALID_EVTCHN(evtchn)) { - unmask_evtchn(evtchn); - pirq_unmask_notify(irq); - } -} - static int find_irq_by_gsi(unsigned gsi) { int irq; @@ -638,14 +615,7 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name) goto out; /* XXX need refcount? */ } - /* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore - * we are using the !xen_initial_domain() to drop in the function.*/ - if (identity_mapped_irq(gsi) || (!xen_initial_domain() && - xen_pv_domain())) { - irq = gsi; - irq_alloc_desc_at(irq, -1); - } else - irq = find_unbound_irq(); + irq = xen_allocate_irq_gsi(gsi); set_irq_chip_and_handler_name(irq, &xen_pirq_chip, handle_level_irq, name); @@ -658,7 +628,7 @@ int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name) * this in the priv domain. */ if (xen_initial_domain() && HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) { - irq_free_desc(irq); + xen_free_irq(irq); irq = -ENOSPC; goto out; } @@ -674,87 +644,46 @@ out: } #ifdef CONFIG_PCI_MSI -#include <linux/msi.h> -#include "../pci/msi.h" - -void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc) +int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc) { - spin_lock(&irq_mapping_update_lock); - - if (alloc & XEN_ALLOC_IRQ) { - *irq = find_unbound_irq(); - if (*irq == -1) - goto out; - } - - if (alloc & XEN_ALLOC_PIRQ) { - *pirq = find_unbound_pirq(MAP_PIRQ_TYPE_MSI); - if (*pirq == -1) - goto out; - } + int rc; + struct physdev_get_free_pirq op_get_free_pirq; - set_irq_chip_and_handler_name(*irq, &xen_pirq_chip, - handle_level_irq, name); + op_get_free_pirq.type = MAP_PIRQ_TYPE_MSI; + rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_free_pirq, &op_get_free_pirq); - irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0); - pirq_to_irq[*pirq] = *irq; + WARN_ONCE(rc == -ENOSYS, + "hypervisor does not support the PHYSDEVOP_get_free_pirq interface\n"); -out: - spin_unlock(&irq_mapping_update_lock); + return rc ? -1 : op_get_free_pirq.pirq; } -int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type) +int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, + int pirq, int vector, const char *name) { - int irq = -1; - struct physdev_map_pirq map_irq; - int rc; - int pos; - u32 table_offset, bir; - - memset(&map_irq, 0, sizeof(map_irq)); - map_irq.domid = DOMID_SELF; - map_irq.type = MAP_PIRQ_TYPE_MSI; - map_irq.index = -1; - map_irq.pirq = -1; - map_irq.bus = dev->bus->number; - map_irq.devfn = dev->devfn; - - if (type == PCI_CAP_ID_MSIX) { - pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); - - pci_read_config_dword(dev, msix_table_offset_reg(pos), - &table_offset); - bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); - - map_irq.table_base = pci_resource_start(dev, bir); - map_irq.entry_nr = msidesc->msi_attrib.entry_nr; - } + int irq, ret; spin_lock(&irq_mapping_update_lock); - irq = find_unbound_irq(); - + irq = xen_allocate_irq_dynamic(); if (irq == -1) goto out; - rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); - if (rc) { - printk(KERN_WARNING "xen map irq failed %d\n", rc); - - irq_free_desc(irq); - - irq = -1; - goto out; - } - irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index); - set_irq_chip_and_handler_name(irq, &xen_pirq_chip, - handle_level_irq, - (type == PCI_CAP_ID_MSIX) ? "msi-x":"msi"); + handle_level_irq, name); + irq_info[irq] = mk_pirq_info(0, pirq, 0, vector); + pirq_to_irq[pirq] = irq; + ret = set_irq_msi(irq, msidesc); + if (ret < 0) + goto error_irq; out: spin_unlock(&irq_mapping_update_lock); return irq; +error_irq: + spin_unlock(&irq_mapping_update_lock); + xen_free_irq(irq); + return -1; } #endif @@ -779,11 +708,12 @@ int xen_destroy_irq(int irq) printk(KERN_WARNING "unmap irq failed %d\n", rc); goto out; } - pirq_to_irq[info->u.pirq.pirq] = -1; } + pirq_to_irq[info->u.pirq.pirq] = -1; + irq_info[irq] = mk_unbound_info(); - irq_free_desc(irq); + xen_free_irq(irq); out: spin_unlock(&irq_mapping_update_lock); @@ -814,7 +744,7 @@ int bind_evtchn_to_irq(unsigned int evtchn) irq = evtchn_to_irq[evtchn]; if (irq == -1) { - irq = find_unbound_irq(); + irq = xen_allocate_irq_dynamic(); set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, handle_fasteoi_irq, "event"); @@ -839,7 +769,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) irq = per_cpu(ipi_to_irq, cpu)[ipi]; if (irq == -1) { - irq = find_unbound_irq(); + irq = xen_allocate_irq_dynamic(); if (irq < 0) goto out; @@ -875,7 +805,7 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu) irq = per_cpu(virq_to_irq, cpu)[virq]; if (irq == -1) { - irq = find_unbound_irq(); + irq = xen_allocate_irq_dynamic(); set_irq_chip_and_handler_name(irq, &xen_percpu_chip, handle_percpu_irq, "virq"); @@ -934,7 +864,7 @@ static void unbind_from_irq(unsigned int irq) if (irq_info[irq].type != IRQT_UNBOUND) { irq_info[irq] = mk_unbound_info(); - irq_free_desc(irq); + xen_free_irq(irq); } spin_unlock(&irq_mapping_update_lock); @@ -990,7 +920,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, if (irq < 0) return irq; - irqflags |= IRQF_NO_SUSPEND; + irqflags |= IRQF_NO_SUSPEND | IRQF_FORCE_RESUME; retval = request_irq(irq, handler, irqflags, devname, dev_id); if (retval != 0) { unbind_from_irq(irq); @@ -1234,11 +1164,12 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu) return 0; } -static int set_affinity_irq(unsigned irq, const struct cpumask *dest) +static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest, + bool force) { unsigned tcpu = cpumask_first(dest); - return rebind_irq_to_cpu(irq, tcpu); + return rebind_irq_to_cpu(data->irq, tcpu); } int resend_irq_on_evtchn(unsigned int irq) @@ -1257,35 +1188,35 @@ int resend_irq_on_evtchn(unsigned int irq) return 1; } -static void enable_dynirq(unsigned int irq) +static void enable_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(irq); + int evtchn = evtchn_from_irq(data->irq); if (VALID_EVTCHN(evtchn)) unmask_evtchn(evtchn); } -static void disable_dynirq(unsigned int irq) +static void disable_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(irq); + int evtchn = evtchn_from_irq(data->irq); if (VALID_EVTCHN(evtchn)) mask_evtchn(evtchn); } -static void ack_dynirq(unsigned int irq) +static void ack_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(irq); + int evtchn = evtchn_from_irq(data->irq); - move_masked_irq(irq); + move_masked_irq(data->irq); if (VALID_EVTCHN(evtchn)) unmask_evtchn(evtchn); } -static int retrigger_dynirq(unsigned int irq) +static int retrigger_dynirq(struct irq_data *data) { - int evtchn = evtchn_from_irq(irq); + int evtchn = evtchn_from_irq(data->irq); struct shared_info *sh = HYPERVISOR_shared_info; int ret = 0; @@ -1334,7 +1265,7 @@ static void restore_cpu_pirqs(void) printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq); - startup_pirq(irq); + __startup_pirq(irq); } } @@ -1445,7 +1376,6 @@ void xen_poll_irq(int irq) void xen_irq_resume(void) { unsigned int cpu, irq, evtchn; - struct irq_desc *desc; init_evtchn_cpu_bindings(); @@ -1465,66 +1395,48 @@ void xen_irq_resume(void) restore_cpu_ipis(cpu); } - /* - * Unmask any IRQF_NO_SUSPEND IRQs which are enabled. These - * are not handled by the IRQ core. - */ - for_each_irq_desc(irq, desc) { - if (!desc->action || !(desc->action->flags & IRQF_NO_SUSPEND)) - continue; - if (desc->status & IRQ_DISABLED) - continue; - - evtchn = evtchn_from_irq(irq); - if (evtchn == -1) - continue; - - unmask_evtchn(evtchn); - } - restore_cpu_pirqs(); } static struct irq_chip xen_dynamic_chip __read_mostly = { - .name = "xen-dyn", + .name = "xen-dyn", - .disable = disable_dynirq, - .mask = disable_dynirq, - .unmask = enable_dynirq, + .irq_disable = disable_dynirq, + .irq_mask = disable_dynirq, + .irq_unmask = enable_dynirq, - .eoi = ack_dynirq, - .set_affinity = set_affinity_irq, - .retrigger = retrigger_dynirq, + .irq_eoi = ack_dynirq, + .irq_set_affinity = set_affinity_irq, + .irq_retrigger = retrigger_dynirq, }; static struct irq_chip xen_pirq_chip __read_mostly = { - .name = "xen-pirq", + .name = "xen-pirq", - .startup = startup_pirq, - .shutdown = shutdown_pirq, + .irq_startup = startup_pirq, + .irq_shutdown = shutdown_pirq, - .enable = enable_pirq, - .unmask = enable_pirq, + .irq_enable = enable_pirq, + .irq_unmask = enable_pirq, - .disable = disable_pirq, - .mask = disable_pirq, + .irq_disable = disable_pirq, + .irq_mask = disable_pirq, - .ack = ack_pirq, - .end = end_pirq, + .irq_ack = ack_pirq, - .set_affinity = set_affinity_irq, + .irq_set_affinity = set_affinity_irq, - .retrigger = retrigger_dynirq, + .irq_retrigger = retrigger_dynirq, }; static struct irq_chip xen_percpu_chip __read_mostly = { - .name = "xen-percpu", + .name = "xen-percpu", - .disable = disable_dynirq, - .mask = disable_dynirq, - .unmask = enable_dynirq, + .irq_disable = disable_dynirq, + .irq_mask = disable_dynirq, + .irq_unmask = enable_dynirq, - .ack = ack_dynirq, + .irq_ack = ack_dynirq, }; int xen_set_callback_via(uint64_t via) diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index db8c4c4..ebb2928 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -34,32 +34,38 @@ enum shutdown_state { /* Ignore multiple shutdown requests. */ static enum shutdown_state shutting_down = SHUTDOWN_INVALID; -#ifdef CONFIG_PM_SLEEP -static int xen_hvm_suspend(void *data) -{ - struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; - int *cancelled = data; - - BUG_ON(!irqs_disabled()); - - *cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); +struct suspend_info { + int cancelled; + unsigned long arg; /* extra hypercall argument */ + void (*pre)(void); + void (*post)(int cancelled); +}; - xen_hvm_post_suspend(*cancelled); +static void xen_hvm_post_suspend(int cancelled) +{ + xen_arch_hvm_post_suspend(cancelled); gnttab_resume(); +} - if (!*cancelled) { - xen_irq_resume(); - xen_console_resume(); - xen_timer_resume(); - } +static void xen_pre_suspend(void) +{ + xen_mm_pin_all(); + gnttab_suspend(); + xen_arch_pre_suspend(); +} - return 0; +static void xen_post_suspend(int cancelled) +{ + xen_arch_post_suspend(cancelled); + gnttab_resume(); + xen_mm_unpin_all(); } +#ifdef CONFIG_PM_SLEEP static int xen_suspend(void *data) { + struct suspend_info *si = data; int err; - int *cancelled = data; BUG_ON(!irqs_disabled()); @@ -70,22 +76,20 @@ static int xen_suspend(void *data) return err; } - xen_mm_pin_all(); - gnttab_suspend(); - xen_pre_suspend(); + if (si->pre) + si->pre(); /* * This hypercall returns 1 if suspend was cancelled * or the domain was merely checkpointed, and 0 if it * is resuming in a new domain. */ - *cancelled = HYPERVISOR_suspend(virt_to_mfn(xen_start_info)); + si->cancelled = HYPERVISOR_suspend(si->arg); - xen_post_suspend(*cancelled); - gnttab_resume(); - xen_mm_unpin_all(); + if (si->post) + si->post(si->cancelled); - if (!*cancelled) { + if (!si->cancelled) { xen_irq_resume(); xen_console_resume(); xen_timer_resume(); @@ -99,7 +103,7 @@ static int xen_suspend(void *data) static void do_suspend(void) { int err; - int cancelled = 1; + struct suspend_info si; shutting_down = SHUTDOWN_SUSPEND; @@ -129,20 +133,29 @@ static void do_suspend(void) goto out_resume; } - if (xen_hvm_domain()) - err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0)); - else - err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); + si.cancelled = 1; + + if (xen_hvm_domain()) { + si.arg = 0UL; + si.pre = NULL; + si.post = &xen_hvm_post_suspend; + } else { + si.arg = virt_to_mfn(xen_start_info); + si.pre = &xen_pre_suspend; + si.post = &xen_post_suspend; + } + + err = stop_machine(xen_suspend, &si, cpumask_of(0)); dpm_resume_noirq(PMSG_RESUME); if (err) { printk(KERN_ERR "failed to start xen_suspend: %d\n", err); - cancelled = 1; + si.cancelled = 1; } out_resume: - if (!cancelled) { + if (!si.cancelled) { xen_arch_resume(); xs_resume(); } else @@ -162,12 +175,39 @@ out: } #endif /* CONFIG_PM_SLEEP */ +struct shutdown_handler { + const char *command; + void (*cb)(void); +}; + +static void do_poweroff(void) +{ + shutting_down = SHUTDOWN_POWEROFF; + orderly_poweroff(false); +} + +static void do_reboot(void) +{ + shutting_down = SHUTDOWN_POWEROFF; /* ? */ + ctrl_alt_del(); +} + static void shutdown_handler(struct xenbus_watch *watch, const char **vec, unsigned int len) { char *str; struct xenbus_transaction xbt; int err; + static struct shutdown_handler handlers[] = { + { "poweroff", do_poweroff }, + { "halt", do_poweroff }, + { "reboot", do_reboot }, +#ifdef CONFIG_PM_SLEEP + { "suspend", do_suspend }, +#endif + {NULL, NULL}, + }; + static struct shutdown_handler *handler; if (shutting_down != SHUTDOWN_INVALID) return; @@ -184,7 +224,14 @@ static void shutdown_handler(struct xenbus_watch *watch, return; } - xenbus_write(xbt, "control", "shutdown", ""); + for (handler = &handlers[0]; handler->command; handler++) { + if (strcmp(str, handler->command) == 0) + break; + } + + /* Only acknowledge commands which we are prepared to handle. */ + if (handler->cb) + xenbus_write(xbt, "control", "shutdown", ""); err = xenbus_transaction_end(xbt, 0); if (err == -EAGAIN) { @@ -192,17 +239,8 @@ static void shutdown_handler(struct xenbus_watch *watch, goto again; } - if (strcmp(str, "poweroff") == 0 || - strcmp(str, "halt") == 0) { - shutting_down = SHUTDOWN_POWEROFF; - orderly_poweroff(false); - } else if (strcmp(str, "reboot") == 0) { - shutting_down = SHUTDOWN_POWEROFF; /* ? */ - ctrl_alt_del(); -#ifdef CONFIG_PM_SLEEP - } else if (strcmp(str, "suspend") == 0) { - do_suspend(); -#endif + if (handler->cb) { + handler->cb(); } else { printk(KERN_INFO "Ignoring shutdown request: %s\n", str); shutting_down = SHUTDOWN_INVALID; @@ -281,27 +319,18 @@ static int shutdown_event(struct notifier_block *notifier, return NOTIFY_DONE; } -static int __init __setup_shutdown_event(void) -{ - /* Delay initialization in the PV on HVM case */ - if (xen_hvm_domain()) - return 0; - - if (!xen_pv_domain()) - return -ENODEV; - - return xen_setup_shutdown_event(); -} - int xen_setup_shutdown_event(void) { static struct notifier_block xenstore_notifier = { .notifier_call = shutdown_event }; + + if (!xen_domain()) + return -ENODEV; register_xenstore_notifier(&xenstore_notifier); return 0; } EXPORT_SYMBOL_GPL(xen_setup_shutdown_event); -subsys_initcall(__setup_shutdown_event); +subsys_initcall(xen_setup_shutdown_event); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index afbe041..319dd0a 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -156,9 +156,6 @@ static int __devinit platform_pci_init(struct pci_dev *pdev, if (ret) goto out; xenbus_probe(NULL); - ret = xen_setup_shutdown_event(); - if (ret) - goto out; return 0; out: @@ -47,7 +47,7 @@ config FS_POSIX_ACL def_bool n config EXPORTFS - tristate + bool config FILE_LOCKING bool "Enable POSIX file locking API" if EXPERT diff --git a/fs/Makefile b/fs/Makefile index a7f7cef..ba01202 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -48,6 +48,8 @@ obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o xattr_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_GENERIC_ACL) += generic_acl.o +obj-$(CONFIG_FHANDLE) += fhandle.o + obj-y += quota/ obj-$(CONFIG_PROC_FS) += proc/ diff --git a/fs/afs/write.c b/fs/afs/write.c index 15690bb..789b3af 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -140,6 +140,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, candidate->first = candidate->last = index; candidate->offset_first = from; candidate->to_last = to; + INIT_LIST_HEAD(&candidate->link); candidate->usage = 1; candidate->state = AFS_WBACK_PENDING; init_waitqueue_head(&candidate->waitq); @@ -239,15 +239,23 @@ static void __put_ioctx(struct kioctx *ctx) call_rcu(&ctx->rcu_head, ctx_rcu_free); } -#define get_ioctx(kioctx) do { \ - BUG_ON(atomic_read(&(kioctx)->users) <= 0); \ - atomic_inc(&(kioctx)->users); \ -} while (0) -#define put_ioctx(kioctx) do { \ - BUG_ON(atomic_read(&(kioctx)->users) <= 0); \ - if (unlikely(atomic_dec_and_test(&(kioctx)->users))) \ - __put_ioctx(kioctx); \ -} while (0) +static inline void get_ioctx(struct kioctx *kioctx) +{ + BUG_ON(atomic_read(&kioctx->users) <= 0); + atomic_inc(&kioctx->users); +} + +static inline int try_get_ioctx(struct kioctx *kioctx) +{ + return atomic_inc_not_zero(&kioctx->users); +} + +static inline void put_ioctx(struct kioctx *kioctx) +{ + BUG_ON(atomic_read(&kioctx->users) <= 0); + if (unlikely(atomic_dec_and_test(&kioctx->users))) + __put_ioctx(kioctx); +} /* ioctx_alloc * Allocates and initializes an ioctx. Returns an ERR_PTR if it failed. @@ -601,8 +609,13 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) rcu_read_lock(); hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) { - if (ctx->user_id == ctx_id && !ctx->dead) { - get_ioctx(ctx); + /* + * RCU protects us against accessing freed memory but + * we have to be careful not to get a reference when the + * reference count already dropped to 0 (ctx->dead test + * is unreliable because of races). + */ + if (ctx->user_id == ctx_id && !ctx->dead && try_get_ioctx(ctx)){ ret = ctx; break; } @@ -1629,6 +1642,23 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, goto out_put_req; spin_lock_irq(&ctx->ctx_lock); + /* + * We could have raced with io_destroy() and are currently holding a + * reference to ctx which should be destroyed. We cannot submit IO + * since ctx gets freed as soon as io_submit() puts its reference. The + * check here is reliable: io_destroy() sets ctx->dead before waiting + * for outstanding IO and the barrier between these two is realized by + * unlock of mm->ioctx_lock and lock of ctx->ctx_lock. Analogously we + * increment ctx->reqs_active before checking for ctx->dead and the + * barrier is realized by unlock and lock of ctx->ctx_lock. Thus if we + * don't see ctx->dead set here, io_destroy() waits for our IO to + * finish. + */ + if (ctx->dead) { + spin_unlock_irq(&ctx->ctx_lock); + ret = -EINVAL; + goto out_put_req; + } aio_run_iocb(req); if (!list_empty(&ctx->run_list)) { /* drain the run list */ diff --git a/fs/block_dev.c b/fs/block_dev.c index 333a7bb..8892870 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -873,6 +873,11 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); if (ret) goto out_del; + /* + * bdev could be deleted beneath us which would implicitly destroy + * the holder directory. Hold on to it. + */ + kobject_get(bdev->bd_part->holder_dir); list_add(&holder->list, &bdev->bd_holder_disks); goto out_unlock; @@ -909,6 +914,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj); del_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj); + kobject_put(bdev->bd_part->holder_dir); list_del_init(&holder->list); kfree(holder); } @@ -922,14 +928,15 @@ EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); * flush_disk - invalidates all buffer-cache entries on a disk * * @bdev: struct block device to be flushed + * @kill_dirty: flag to guide handling of dirty inodes * * Invalidates all buffer-cache entries on a disk. It should be called * when a disk has been changed -- either by a media change or online * resize. */ -static void flush_disk(struct block_device *bdev) +static void flush_disk(struct block_device *bdev, bool kill_dirty) { - if (__invalidate_device(bdev)) { + if (__invalidate_device(bdev, kill_dirty)) { char name[BDEVNAME_SIZE] = ""; if (bdev->bd_disk) @@ -966,7 +973,7 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev) "%s: detected capacity change from %lld to %lld\n", name, bdev_size, disk_size); i_size_write(bdev->bd_inode, disk_size); - flush_disk(bdev); + flush_disk(bdev, false); } } EXPORT_SYMBOL(check_disk_size_change); @@ -1019,7 +1026,7 @@ int check_disk_change(struct block_device *bdev) if (!(events & DISK_EVENT_MEDIA_CHANGE)) return 0; - flush_disk(bdev); + flush_disk(bdev, true); if (bdops->revalidate_disk) bdops->revalidate_disk(bdev->bd_disk); return 1; @@ -1215,12 +1222,6 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) res = __blkdev_get(bdev, mode, 0); - /* __blkdev_get() may alter read only status, check it afterwards */ - if (!res && (mode & FMODE_WRITE) && bdev_read_only(bdev)) { - __blkdev_put(bdev, mode, 0); - res = -EACCES; - } - if (whole) { /* finish claiming */ mutex_lock(&bdev->bd_mutex); @@ -1298,6 +1299,11 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, if (err) return ERR_PTR(err); + if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) { + blkdev_put(bdev, mode); + return ERR_PTR(-EACCES); + } + return bdev; } EXPORT_SYMBOL(blkdev_get_by_path); @@ -1601,7 +1607,7 @@ fail: } EXPORT_SYMBOL(lookup_bdev); -int __invalidate_device(struct block_device *bdev) +int __invalidate_device(struct block_device *bdev, bool kill_dirty) { struct super_block *sb = get_super(bdev); int res = 0; @@ -1614,7 +1620,7 @@ int __invalidate_device(struct block_device *bdev) * hold). */ shrink_dcache_sb(sb); - res = invalidate_inodes(sb); + res = invalidate_inodes(sb, kill_dirty); drop_super(sb); } invalidate_bdev(bdev); diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 15b5ca2..9c94934 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -37,6 +37,9 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type) char *value = NULL; struct posix_acl *acl; + if (!IS_POSIXACL(inode)) + return NULL; + acl = get_cached_acl(inode, type); if (acl != ACL_NOT_CACHED) return acl; @@ -84,6 +87,9 @@ static int btrfs_xattr_acl_get(struct dentry *dentry, const char *name, struct posix_acl *acl; int ret = 0; + if (!IS_POSIXACL(dentry->d_inode)) + return -EOPNOTSUPP; + acl = btrfs_get_acl(dentry->d_inode, type); if (IS_ERR(acl)) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index f745287..4d2110e 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -562,7 +562,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, u64 em_len; u64 em_start; struct extent_map *em; - int ret; + int ret = -ENOMEM; u32 *sums; tree = &BTRFS_I(inode)->io_tree; @@ -577,6 +577,9 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, compressed_len = em->block_len; cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS); + if (!cb) + goto out; + atomic_set(&cb->pending_bios, 0); cb->errors = 0; cb->inode = inode; @@ -597,13 +600,18 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, nr_pages = (compressed_len + PAGE_CACHE_SIZE - 1) / PAGE_CACHE_SIZE; - cb->compressed_pages = kmalloc(sizeof(struct page *) * nr_pages, + cb->compressed_pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS); + if (!cb->compressed_pages) + goto fail1; + bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev; for (page_index = 0; page_index < nr_pages; page_index++) { cb->compressed_pages[page_index] = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (!cb->compressed_pages[page_index]) + goto fail2; } cb->nr_pages = nr_pages; @@ -614,6 +622,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, cb->len = uncompressed_len; comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS); + if (!comp_bio) + goto fail2; comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; atomic_inc(&cb->pending_bios); @@ -681,6 +691,17 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, bio_put(comp_bio); return 0; + +fail2: + for (page_index = 0; page_index < nr_pages; page_index++) + free_page((unsigned long)cb->compressed_pages[page_index]); + + kfree(cb->compressed_pages); +fail1: + kfree(cb); +out: + free_extent_map(em); + return ret; } static struct list_head comp_idle_workspace[BTRFS_COMPRESS_TYPES]; @@ -900,7 +921,7 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page, return ret; } -void __exit btrfs_exit_compress(void) +void btrfs_exit_compress(void) { free_workspaces(); } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2c98b3a..7f78cc7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -729,6 +729,15 @@ struct btrfs_space_info { u64 disk_total; /* total bytes on disk, takes mirrors into account */ + /* + * we bump reservation progress every time we decrement + * bytes_reserved. This way people waiting for reservations + * know something good has happened and they can check + * for progress. The number here isn't to be trusted, it + * just shows reclaim activity + */ + unsigned long reservation_progress; + int full; /* indicates that we cannot allocate any more chunks for this space */ int force_alloc; /* set if we need to force a chunk alloc for @@ -1254,6 +1263,7 @@ struct btrfs_root { #define BTRFS_MOUNT_SPACE_CACHE (1 << 12) #define BTRFS_MOUNT_CLEAR_CACHE (1 << 13) #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14) +#define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@ -2218,6 +2228,8 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end); int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr, u64 num_bytes); +int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 type); /* ctree.c */ int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b531c36..e1aa8d6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -359,10 +359,14 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) tree = &BTRFS_I(page->mapping->host)->io_tree; - if (page->private == EXTENT_PAGE_PRIVATE) + if (page->private == EXTENT_PAGE_PRIVATE) { + WARN_ON(1); goto out; - if (!page->private) + } + if (!page->private) { + WARN_ON(1); goto out; + } len = page->private >> 2; WARN_ON(len == 0); @@ -1550,6 +1554,7 @@ static int transaction_kthread(void *arg) spin_unlock(&root->fs_info->new_trans_lock); trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); if (transid == trans->transid) { ret = btrfs_commit_transaction(trans, root); BUG_ON(ret); @@ -2453,10 +2458,14 @@ int btrfs_commit_super(struct btrfs_root *root) up_write(&root->fs_info->cleanup_work_sem); trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); ret = btrfs_commit_transaction(trans, root); BUG_ON(ret); /* run commit again to drop the original snapshot */ trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); btrfs_commit_transaction(trans, root); ret = btrfs_write_and_wait_transaction(NULL, root); BUG_ON(ret); @@ -2554,6 +2563,8 @@ int close_ctree(struct btrfs_root *root) kfree(fs_info->chunk_root); kfree(fs_info->dev_root); kfree(fs_info->csum_root); + kfree(fs_info); + return 0; } diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 9786963..b4ffad8 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -21,9 +21,13 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, int len = *max_len; int type; - if ((len < BTRFS_FID_SIZE_NON_CONNECTABLE) || - (connectable && len < BTRFS_FID_SIZE_CONNECTABLE)) + if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) { + *max_len = BTRFS_FID_SIZE_CONNECTABLE; return 255; + } else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) { + *max_len = BTRFS_FID_SIZE_NON_CONNECTABLE; + return 255; + } len = BTRFS_FID_SIZE_NON_CONNECTABLE; type = FILEID_BTRFS_WITHOUT_PARENT; @@ -171,6 +175,8 @@ static struct dentry *btrfs_get_parent(struct dentry *child) int ret; path = btrfs_alloc_path(); + if (!path) + return ERR_PTR(-ENOMEM); if (dir->i_ino == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = root->root_key.objectid; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b552693..7b3089b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -320,11 +320,6 @@ static int caching_kthread(void *data) if (!path) return -ENOMEM; - exclude_super_stripes(extent_root, block_group); - spin_lock(&block_group->space_info->lock); - block_group->space_info->bytes_readonly += block_group->bytes_super; - spin_unlock(&block_group->space_info->lock); - last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET); /* @@ -467,8 +462,10 @@ static int cache_block_group(struct btrfs_block_group_cache *cache, cache->cached = BTRFS_CACHE_NO; } spin_unlock(&cache->lock); - if (ret == 1) + if (ret == 1) { + free_excluded_extents(fs_info->extent_root, cache); return 0; + } } if (load_cache_only) @@ -3344,21 +3341,24 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, u64 reserved; u64 max_reclaim; u64 reclaimed = 0; - int pause = 1; + long time_left; int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT; + int loops = 0; + unsigned long progress; block_rsv = &root->fs_info->delalloc_block_rsv; space_info = block_rsv->space_info; smp_mb(); reserved = space_info->bytes_reserved; + progress = space_info->reservation_progress; if (reserved == 0) return 0; max_reclaim = min(reserved, to_reclaim); - while (1) { + while (loops < 1024) { /* have the flusher threads jump in and do some IO */ smp_mb(); nr_pages = min_t(unsigned long, nr_pages, @@ -3371,17 +3371,31 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, reserved = space_info->bytes_reserved; spin_unlock(&space_info->lock); + loops++; + if (reserved == 0 || reclaimed >= max_reclaim) break; if (trans && trans->transaction->blocked) return -EAGAIN; - __set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(pause); - pause <<= 1; - if (pause > HZ / 10) - pause = HZ / 10; + time_left = schedule_timeout_interruptible(1); + + /* We were interrupted, exit */ + if (time_left) + break; + + /* we've kicked the IO a few times, if anything has been freed, + * exit. There is no sense in looping here for a long time + * when we really need to commit the transaction, or there are + * just too many writers without enough free space + */ + + if (loops > 3) { + smp_mb(); + if (progress != space_info->reservation_progress) + break; + } } return reclaimed >= to_reclaim; @@ -3588,10 +3602,23 @@ void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv, if (num_bytes > 0) { if (dest) { - block_rsv_add_bytes(dest, num_bytes, 0); - } else { + spin_lock(&dest->lock); + if (!dest->full) { + u64 bytes_to_add; + + bytes_to_add = dest->size - dest->reserved; + bytes_to_add = min(num_bytes, bytes_to_add); + dest->reserved += bytes_to_add; + if (dest->reserved >= dest->size) + dest->full = 1; + num_bytes -= bytes_to_add; + } + spin_unlock(&dest->lock); + } + if (num_bytes) { spin_lock(&space_info->lock); space_info->bytes_reserved -= num_bytes; + space_info->reservation_progress++; spin_unlock(&space_info->lock); } } @@ -3824,6 +3851,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) if (block_rsv->reserved >= block_rsv->size) { num_bytes = block_rsv->reserved - block_rsv->size; sinfo->bytes_reserved -= num_bytes; + sinfo->reservation_progress++; block_rsv->reserved = block_rsv->size; block_rsv->full = 1; } @@ -3985,7 +4013,6 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) to_reserve = 0; } spin_unlock(&BTRFS_I(inode)->accounting_lock); - to_reserve += calc_csum_metadata_size(inode, num_bytes); ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1); if (ret) @@ -4012,6 +4039,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes) num_bytes = ALIGN(num_bytes, root->sectorsize); atomic_dec(&BTRFS_I(inode)->outstanding_extents); + WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents) < 0); spin_lock(&BTRFS_I(inode)->accounting_lock); nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents); @@ -4112,6 +4140,7 @@ static int update_block_group(struct btrfs_trans_handle *trans, btrfs_set_block_group_used(&cache->item, old_val); cache->reserved -= num_bytes; cache->space_info->bytes_reserved -= num_bytes; + cache->space_info->reservation_progress++; cache->space_info->bytes_used += num_bytes; cache->space_info->disk_used += num_bytes * factor; spin_unlock(&cache->lock); @@ -4163,6 +4192,7 @@ static int pin_down_extent(struct btrfs_root *root, if (reserved) { cache->reserved -= num_bytes; cache->space_info->bytes_reserved -= num_bytes; + cache->space_info->reservation_progress++; } spin_unlock(&cache->lock); spin_unlock(&cache->space_info->lock); @@ -4213,6 +4243,7 @@ static int update_reserved_bytes(struct btrfs_block_group_cache *cache, space_info->bytes_readonly += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; + space_info->reservation_progress++; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); @@ -4691,6 +4722,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (ret) { spin_lock(&cache->space_info->lock); cache->space_info->bytes_reserved -= buf->len; + cache->space_info->reservation_progress++; spin_unlock(&cache->space_info->lock); } goto out; @@ -5355,7 +5387,7 @@ again: num_bytes, data, 1); goto again; } - if (ret == -ENOSPC) { + if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) { struct btrfs_space_info *sinfo; sinfo = __find_space_info(root->fs_info, data); @@ -5633,6 +5665,7 @@ use_block_rsv(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize) { struct btrfs_block_rsv *block_rsv; + struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv; int ret; block_rsv = get_block_rsv(trans, root); @@ -5640,14 +5673,39 @@ use_block_rsv(struct btrfs_trans_handle *trans, if (block_rsv->size == 0) { ret = reserve_metadata_bytes(trans, root, block_rsv, blocksize, 0); - if (ret) + /* + * If we couldn't reserve metadata bytes try and use some from + * the global reserve. + */ + if (ret && block_rsv != global_rsv) { + ret = block_rsv_use_bytes(global_rsv, blocksize); + if (!ret) + return global_rsv; + return ERR_PTR(ret); + } else if (ret) { return ERR_PTR(ret); + } return block_rsv; } ret = block_rsv_use_bytes(block_rsv, blocksize); if (!ret) return block_rsv; + if (ret) { + WARN_ON(1); + ret = reserve_metadata_bytes(trans, root, block_rsv, blocksize, + 0); + if (!ret) { + spin_lock(&block_rsv->lock); + block_rsv->size += blocksize; + spin_unlock(&block_rsv->lock); + return block_rsv; + } else if (ret && block_rsv != global_rsv) { + ret = block_rsv_use_bytes(global_rsv, blocksize); + if (!ret) + return global_rsv; + } + } return ERR_PTR(-ENOSPC); } @@ -6221,6 +6279,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, BUG_ON(!wc); trans = btrfs_start_transaction(tree_root, 0); + BUG_ON(IS_ERR(trans)); + if (block_rsv) trans->block_rsv = block_rsv; @@ -6318,6 +6378,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, btrfs_end_transaction_throttle(trans, tree_root); trans = btrfs_start_transaction(tree_root, 0); + BUG_ON(IS_ERR(trans)); if (block_rsv) trans->block_rsv = block_rsv; } @@ -6446,6 +6507,8 @@ static noinline int relocate_inode_pages(struct inode *inode, u64 start, int ret = 0; ra = kzalloc(sizeof(*ra), GFP_NOFS); + if (!ra) + return -ENOMEM; mutex_lock(&inode->i_mutex); first_index = start >> PAGE_CACHE_SHIFT; @@ -6531,7 +6594,7 @@ static noinline int relocate_data_extent(struct inode *reloc_inode, u64 end = start + extent_key->offset - 1; em = alloc_extent_map(GFP_NOFS); - BUG_ON(!em || IS_ERR(em)); + BUG_ON(!em); em->start = start; em->len = extent_key->offset; @@ -7477,7 +7540,7 @@ int btrfs_drop_dead_reloc_roots(struct btrfs_root *root) BUG_ON(reloc_root->commit_root != NULL); while (1) { trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); mutex_lock(&root->fs_info->drop_mutex); ret = btrfs_drop_snapshot(trans, reloc_root); @@ -7535,7 +7598,7 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root) if (found) { trans = btrfs_start_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); ret = btrfs_commit_transaction(trans, root); BUG_ON(ret); } @@ -7779,7 +7842,7 @@ static noinline int relocate_one_extent(struct btrfs_root *extent_root, trans = btrfs_start_transaction(extent_root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); if (extent_key->objectid == 0) { ret = del_extent_zero(trans, extent_root, path, extent_key); @@ -8013,6 +8076,13 @@ out: return ret; } +int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, + struct btrfs_root *root, u64 type) +{ + u64 alloc_flags = get_alloc_profile(root, type); + return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1); +} + /* * helper to account the unused space of all the readonly block group in the * list. takes mirrors into account. @@ -8270,6 +8340,13 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) if (block_group->cached == BTRFS_CACHE_STARTED) wait_block_group_cache_done(block_group); + /* + * We haven't cached this block group, which means we could + * possibly have excluded extents on this block group. + */ + if (block_group->cached == BTRFS_CACHE_NO) + free_excluded_extents(info->extent_root, block_group); + btrfs_remove_free_space_cache(block_group); btrfs_put_block_group(block_group); @@ -8385,6 +8462,13 @@ int btrfs_read_block_groups(struct btrfs_root *root) cache->sectorsize = root->sectorsize; /* + * We need to exclude the super stripes now so that the space + * info has super bytes accounted for, otherwise we'll think + * we have more space than we actually do. + */ + exclude_super_stripes(root, cache); + + /* * check for two cases, either we are full, and therefore * don't need to bother with the caching work since we won't * find any space, or we are empty, and we can just add all @@ -8392,12 +8476,10 @@ int btrfs_read_block_groups(struct btrfs_root *root) * time, particularly in the full case. */ if (found_key.offset == btrfs_block_group_used(&cache->item)) { - exclude_super_stripes(root, cache); cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; free_excluded_extents(root, cache); } else if (btrfs_block_group_used(&cache->item) == 0) { - exclude_super_stripes(root, cache); cache->last_byte_to_unpin = (u64)-1; cache->cached = BTRFS_CACHE_FINISHED; add_new_free_space(cache, root->fs_info, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2e993cf..714adc4 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1433,12 +1433,13 @@ int extent_clear_unlock_delalloc(struct inode *inode, */ u64 count_range_bits(struct extent_io_tree *tree, u64 *start, u64 search_end, u64 max_bytes, - unsigned long bits) + unsigned long bits, int contig) { struct rb_node *node; struct extent_state *state; u64 cur_start = *start; u64 total_bytes = 0; + u64 last = 0; int found = 0; if (search_end <= cur_start) { @@ -1463,7 +1464,9 @@ u64 count_range_bits(struct extent_io_tree *tree, state = rb_entry(node, struct extent_state, rb_node); if (state->start > search_end) break; - if (state->end >= cur_start && (state->state & bits)) { + if (contig && found && state->start > last + 1) + break; + if (state->end >= cur_start && (state->state & bits) == bits) { total_bytes += min(search_end, state->end) + 1 - max(cur_start, state->start); if (total_bytes >= max_bytes) @@ -1472,6 +1475,9 @@ u64 count_range_bits(struct extent_io_tree *tree, *start = state->start; found = 1; } + last = state->end; + } else if (contig && found) { + break; } node = rb_next(node); if (!node) @@ -1865,7 +1871,7 @@ static int submit_one_bio(int rw, struct bio *bio, int mirror_num, bio_get(bio); if (tree->ops && tree->ops->submit_bio_hook) - tree->ops->submit_bio_hook(page->mapping->host, rw, bio, + ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio, mirror_num, bio_flags, start); else submit_bio(rw, bio); @@ -1920,6 +1926,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, nr = bio_get_nr_vecs(bdev); bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH); + if (!bio) + return -ENOMEM; bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; @@ -1944,6 +1952,7 @@ void set_page_extent_mapped(struct page *page) static void set_page_extent_head(struct page *page, unsigned long len) { + WARN_ON(!PagePrivate(page)); set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2); } @@ -2126,7 +2135,7 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page, ret = __extent_read_full_page(tree, page, get_extent, &bio, 0, &bio_flags); if (bio) - submit_one_bio(READ, bio, 0, bio_flags); + ret = submit_one_bio(READ, bio, 0, bio_flags); return ret; } @@ -2819,9 +2828,17 @@ int try_release_extent_state(struct extent_map_tree *map, * at this point we can safely clear everything except the * locked bit and the nodatasum bit */ - clear_extent_bit(tree, start, end, + ret = clear_extent_bit(tree, start, end, ~(EXTENT_LOCKED | EXTENT_NODATASUM), 0, 0, NULL, mask); + + /* if clear_extent_bit failed for enomem reasons, + * we can't allow the release to continue. + */ + if (ret < 0) + ret = 0; + else + ret = 1; } return ret; } @@ -2901,6 +2918,46 @@ out: return sector; } +/* + * helper function for fiemap, which doesn't want to see any holes. + * This maps until we find something past 'last' + */ +static struct extent_map *get_extent_skip_holes(struct inode *inode, + u64 offset, + u64 last, + get_extent_t *get_extent) +{ + u64 sectorsize = BTRFS_I(inode)->root->sectorsize; + struct extent_map *em; + u64 len; + + if (offset >= last) + return NULL; + + while(1) { + len = last - offset; + if (len == 0) + break; + len = (len + sectorsize - 1) & ~(sectorsize - 1); + em = get_extent(inode, NULL, 0, offset, len, 0); + if (!em || IS_ERR(em)) + return em; + + /* if this isn't a hole return it */ + if (!test_bit(EXTENT_FLAG_VACANCY, &em->flags) && + em->block_start != EXTENT_MAP_HOLE) { + return em; + } + + /* this is a hole, advance to the next extent */ + offset = extent_map_end(em); + free_extent_map(em); + if (offset >= last) + break; + } + return NULL; +} + int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len, get_extent_t *get_extent) { @@ -2910,16 +2967,19 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u32 flags = 0; u32 found_type; u64 last; + u64 last_for_get_extent = 0; u64 disko = 0; + u64 isize = i_size_read(inode); struct btrfs_key found_key; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; struct btrfs_path *path; struct btrfs_file_extent_item *item; int end = 0; - u64 em_start = 0, em_len = 0; + u64 em_start = 0; + u64 em_len = 0; + u64 em_end = 0; unsigned long emflags; - int hole = 0; if (len == 0) return -EINVAL; @@ -2929,6 +2989,10 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return -ENOMEM; path->leave_spinning = 1; + /* + * lookup the last file extent. We're not using i_size here + * because there might be preallocation past i_size + */ ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root, path, inode->i_ino, -1, 0); if (ret < 0) { @@ -2942,18 +3006,38 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); found_type = btrfs_key_type(&found_key); - /* No extents, just return */ + /* No extents, but there might be delalloc bits */ if (found_key.objectid != inode->i_ino || found_type != BTRFS_EXTENT_DATA_KEY) { - btrfs_free_path(path); - return 0; + /* have to trust i_size as the end */ + last = (u64)-1; + last_for_get_extent = isize; + } else { + /* + * remember the start of the last extent. There are a + * bunch of different factors that go into the length of the + * extent, so its much less complex to remember where it started + */ + last = found_key.offset; + last_for_get_extent = last + 1; } - last = found_key.offset; btrfs_free_path(path); + /* + * we might have some extents allocated but more delalloc past those + * extents. so, we trust isize unless the start of the last extent is + * beyond isize + */ + if (last < isize) { + last = (u64)-1; + last_for_get_extent = isize; + } + lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0, &cached_state, GFP_NOFS); - em = get_extent(inode, NULL, 0, off, max - off, 0); + + em = get_extent_skip_holes(inode, off, last_for_get_extent, + get_extent); if (!em) goto out; if (IS_ERR(em)) { @@ -2962,22 +3046,38 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } while (!end) { - hole = 0; - off = em->start + em->len; - if (off >= max) - end = 1; + u64 offset_in_extent; - if (em->block_start == EXTENT_MAP_HOLE) { - hole = 1; - goto next; - } + /* break if the extent we found is outside the range */ + if (em->start >= max || extent_map_end(em) < off) + break; - em_start = em->start; - em_len = em->len; + /* + * get_extent may return an extent that starts before our + * requested range. We have to make sure the ranges + * we return to fiemap always move forward and don't + * overlap, so adjust the offsets here + */ + em_start = max(em->start, off); + /* + * record the offset from the start of the extent + * for adjusting the disk offset below + */ + offset_in_extent = em_start - em->start; + em_end = extent_map_end(em); + em_len = em_end - em_start; + emflags = em->flags; disko = 0; flags = 0; + /* + * bump off for our next call to get_extent + */ + off = extent_map_end(em); + if (off >= max) + end = 1; + if (em->block_start == EXTENT_MAP_LAST_BYTE) { end = 1; flags |= FIEMAP_EXTENT_LAST; @@ -2988,42 +3088,34 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); } else { - disko = em->block_start; + disko = em->block_start + offset_in_extent; } if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) flags |= FIEMAP_EXTENT_ENCODED; -next: - emflags = em->flags; free_extent_map(em); em = NULL; - if (!end) { - em = get_extent(inode, NULL, 0, off, max - off, 0); - if (!em) - goto out; - if (IS_ERR(em)) { - ret = PTR_ERR(em); - goto out; - } - emflags = em->flags; - } - - if (test_bit(EXTENT_FLAG_VACANCY, &emflags)) { + if ((em_start >= last) || em_len == (u64)-1 || + (last == (u64)-1 && isize <= em_end)) { flags |= FIEMAP_EXTENT_LAST; end = 1; } - if (em_start == last) { + /* now scan forward to see if this is really the last extent. */ + em = get_extent_skip_holes(inode, off, last_for_get_extent, + get_extent); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out; + } + if (!em) { flags |= FIEMAP_EXTENT_LAST; end = 1; } - - if (!hole) { - ret = fiemap_fill_next_extent(fieinfo, em_start, disko, - em_len, flags); - if (ret) - goto out_free; - } + ret = fiemap_fill_next_extent(fieinfo, em_start, disko, + em_len, flags); + if (ret) + goto out_free; } out_free: free_extent_map(em); @@ -3192,7 +3284,13 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, } if (!PageUptodate(p)) uptodate = 0; - unlock_page(p); + + /* + * see below about how we avoid a nasty race with release page + * and why we unlock later + */ + if (i != 0) + unlock_page(p); } if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); @@ -3216,9 +3314,26 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, atomic_inc(&eb->refs); spin_unlock(&tree->buffer_lock); radix_tree_preload_end(); + + /* + * there is a race where release page may have + * tried to find this extent buffer in the radix + * but failed. It will tell the VM it is safe to + * reclaim the, and it will clear the page private bit. + * We must make sure to set the page private bit properly + * after the extent buffer is in the radix tree so + * it doesn't get lost + */ + set_page_extent_mapped(eb->first_page); + set_page_extent_head(eb->first_page, eb->len); + if (!page0) + unlock_page(eb->first_page); return eb; free_eb: + if (eb->first_page && !page0) + unlock_page(eb->first_page); + if (!atomic_dec_and_test(&eb->refs)) return exists; btrfs_release_extent_buffer(eb); @@ -3269,10 +3384,11 @@ int clear_extent_buffer_dirty(struct extent_io_tree *tree, continue; lock_page(page); + WARN_ON(!PagePrivate(page)); + + set_page_extent_mapped(page); if (i == 0) set_page_extent_head(page, eb->len); - else - set_page_private(page, EXTENT_PAGE_PRIVATE); clear_page_dirty_for_io(page); spin_lock_irq(&page->mapping->tree_lock); @@ -3462,6 +3578,13 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); + + WARN_ON(!PagePrivate(page)); + + set_page_extent_mapped(page); + if (i == 0) + set_page_extent_head(page, eb->len); + if (inc_all_pages) page_cache_get(page); if (!PageUptodate(page)) { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 7083cfa..9318dfe 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -191,7 +191,7 @@ void extent_io_exit(void); u64 count_range_bits(struct extent_io_tree *tree, u64 *start, u64 search_end, - u64 max_bytes, unsigned long bits); + u64 max_bytes, unsigned long bits, int contig); void free_extent_state(struct extent_state *state); int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index b0e1fce..2b6c12e 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -51,8 +51,8 @@ struct extent_map *alloc_extent_map(gfp_t mask) { struct extent_map *em; em = kmem_cache_alloc(extent_map_cache, mask); - if (!em || IS_ERR(em)) - return em; + if (!em) + return NULL; em->in_tree = 0; em->flags = 0; em->compress_type = BTRFS_COMPRESS_NONE; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index a562a25..4f19a3e 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -536,6 +536,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, root = root->fs_info->csum_root; path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; while (1) { key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; @@ -548,7 +550,10 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, if (path->slots[0] == 0) goto out; path->slots[0]--; + } else if (ret < 0) { + goto out; } + leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index c800d58..f447b78 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -70,6 +70,19 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, /* Flush processor's dcache for this page */ flush_dcache_page(page); + + /* + * if we get a partial write, we can end up with + * partially up to date pages. These add + * a lot of complexity, so make sure they don't + * happen by forcing this copy to be retried. + * + * The rest of the btrfs_file_write code will fall + * back to page at a time copies after we return 0. + */ + if (!PageUptodate(page) && copied < count) + copied = 0; + iov_iter_advance(i, copied); write_bytes -= copied; total_copied += copied; @@ -186,6 +199,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, split = alloc_extent_map(GFP_NOFS); if (!split2) split2 = alloc_extent_map(GFP_NOFS); + BUG_ON(!split || !split2); write_lock(&em_tree->lock); em = lookup_extent_mapping(em_tree, start, len); @@ -762,6 +776,27 @@ out: } /* + * on error we return an unlocked page and the error value + * on success we return a locked page and 0 + */ +static int prepare_uptodate_page(struct page *page, u64 pos) +{ + int ret = 0; + + if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) { + ret = btrfs_readpage(NULL, page); + if (ret) + return ret; + lock_page(page); + if (!PageUptodate(page)) { + unlock_page(page); + return -EIO; + } + } + return 0; +} + +/* * this gets pages into the page cache and locks them down, it also properly * waits for data=ordered extents to finish before allowing the pages to be * modified. @@ -776,6 +811,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, unsigned long index = pos >> PAGE_CACHE_SHIFT; struct inode *inode = fdentry(file)->d_inode; int err = 0; + int faili = 0; u64 start_pos; u64 last_pos; @@ -793,11 +829,24 @@ again: for (i = 0; i < num_pages; i++) { pages[i] = grab_cache_page(inode->i_mapping, index + i); if (!pages[i]) { + faili = i - 1; err = -ENOMEM; - BUG_ON(1); + goto fail; + } + + if (i == 0) + err = prepare_uptodate_page(pages[i], pos); + if (i == num_pages - 1) + err = prepare_uptodate_page(pages[i], + pos + write_bytes); + if (err) { + page_cache_release(pages[i]); + faili = i - 1; + goto fail; } wait_on_page_writeback(pages[i]); } + err = 0; if (start_pos < inode->i_size) { struct btrfs_ordered_extent *ordered; lock_extent_bits(&BTRFS_I(inode)->io_tree, @@ -837,6 +886,14 @@ again: WARN_ON(!PageLocked(pages[i])); } return 0; +fail: + while (faili >= 0) { + unlock_page(pages[faili]); + page_cache_release(pages[faili]); + faili--; + } + return err; + } static ssize_t btrfs_file_aio_write(struct kiocb *iocb, @@ -846,7 +903,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = fdentry(file)->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; - struct page *pinned[2]; struct page **pages = NULL; struct iov_iter i; loff_t *ppos = &iocb->ki_pos; @@ -867,9 +923,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) || (file->f_flags & O_DIRECT)); - pinned[0] = NULL; - pinned[1] = NULL; - start_pos = pos; vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); @@ -946,6 +999,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, PAGE_CACHE_SIZE, PAGE_CACHE_SIZE / (sizeof(struct page *))); pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL); + if (!pages) { + ret = -ENOMEM; + goto out; + } /* generic_write_checks can change our pos */ start_pos = pos; @@ -953,39 +1010,13 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, first_index = pos >> PAGE_CACHE_SHIFT; last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT; - /* - * there are lots of better ways to do this, but this code - * makes sure the first and last page in the file range are - * up to date and ready for cow - */ - if ((pos & (PAGE_CACHE_SIZE - 1))) { - pinned[0] = grab_cache_page(inode->i_mapping, first_index); - if (!PageUptodate(pinned[0])) { - ret = btrfs_readpage(NULL, pinned[0]); - BUG_ON(ret); - wait_on_page_locked(pinned[0]); - } else { - unlock_page(pinned[0]); - } - } - if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) { - pinned[1] = grab_cache_page(inode->i_mapping, last_index); - if (!PageUptodate(pinned[1])) { - ret = btrfs_readpage(NULL, pinned[1]); - BUG_ON(ret); - wait_on_page_locked(pinned[1]); - } else { - unlock_page(pinned[1]); - } - } - while (iov_iter_count(&i) > 0) { size_t offset = pos & (PAGE_CACHE_SIZE - 1); size_t write_bytes = min(iov_iter_count(&i), nrptrs * (size_t)PAGE_CACHE_SIZE - offset); - size_t num_pages = (write_bytes + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + size_t num_pages = (write_bytes + offset + + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; WARN_ON(num_pages > nrptrs); memset(pages, 0, sizeof(struct page *) * nrptrs); @@ -1015,8 +1046,20 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, copied = btrfs_copy_from_user(pos, num_pages, write_bytes, pages, &i); - dirty_pages = (copied + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + + /* + * if we have trouble faulting in the pages, fall + * back to one page at a time + */ + if (copied < write_bytes) + nrptrs = 1; + + if (copied == 0) + dirty_pages = 0; + else + dirty_pages = (copied + offset + + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; if (num_pages > dirty_pages) { if (copied > 0) @@ -1060,10 +1103,6 @@ out: err = ret; kfree(pages); - if (pinned[0]) - page_cache_release(pinned[0]); - if (pinned[1]) - page_cache_release(pinned[1]); *ppos = pos; /* diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 60d6842..a039065 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -987,11 +987,18 @@ tree_search_offset(struct btrfs_block_group_cache *block_group, return entry; } -static void unlink_free_space(struct btrfs_block_group_cache *block_group, - struct btrfs_free_space *info) +static inline void +__unlink_free_space(struct btrfs_block_group_cache *block_group, + struct btrfs_free_space *info) { rb_erase(&info->offset_index, &block_group->free_space_offset); block_group->free_extents--; +} + +static void unlink_free_space(struct btrfs_block_group_cache *block_group, + struct btrfs_free_space *info) +{ + __unlink_free_space(block_group, info); block_group->free_space -= info->bytes; } @@ -1016,14 +1023,18 @@ static void recalculate_thresholds(struct btrfs_block_group_cache *block_group) u64 max_bytes; u64 bitmap_bytes; u64 extent_bytes; + u64 size = block_group->key.offset; /* * The goal is to keep the total amount of memory used per 1gb of space * at or below 32k, so we need to adjust how much memory we allow to be * used by extent based free space tracking */ - max_bytes = MAX_CACHE_BYTES_PER_GIG * - (div64_u64(block_group->key.offset, 1024 * 1024 * 1024)); + if (size < 1024 * 1024 * 1024) + max_bytes = MAX_CACHE_BYTES_PER_GIG; + else + max_bytes = MAX_CACHE_BYTES_PER_GIG * + div64_u64(size, 1024 * 1024 * 1024); /* * we want to account for 1 more bitmap than what we have so we can make @@ -1171,6 +1182,16 @@ static void add_new_bitmap(struct btrfs_block_group_cache *block_group, recalculate_thresholds(block_group); } +static void free_bitmap(struct btrfs_block_group_cache *block_group, + struct btrfs_free_space *bitmap_info) +{ + unlink_free_space(block_group, bitmap_info); + kfree(bitmap_info->bitmap); + kfree(bitmap_info); + block_group->total_bitmaps--; + recalculate_thresholds(block_group); +} + static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_group, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes) @@ -1195,6 +1216,7 @@ again: */ search_start = *offset; search_bytes = *bytes; + search_bytes = min(search_bytes, end - search_start + 1); ret = search_bitmap(block_group, bitmap_info, &search_start, &search_bytes); BUG_ON(ret < 0 || search_start != *offset); @@ -1211,13 +1233,8 @@ again: if (*bytes) { struct rb_node *next = rb_next(&bitmap_info->offset_index); - if (!bitmap_info->bytes) { - unlink_free_space(block_group, bitmap_info); - kfree(bitmap_info->bitmap); - kfree(bitmap_info); - block_group->total_bitmaps--; - recalculate_thresholds(block_group); - } + if (!bitmap_info->bytes) + free_bitmap(block_group, bitmap_info); /* * no entry after this bitmap, but we still have bytes to @@ -1250,13 +1267,8 @@ again: return -EAGAIN; goto again; - } else if (!bitmap_info->bytes) { - unlink_free_space(block_group, bitmap_info); - kfree(bitmap_info->bitmap); - kfree(bitmap_info); - block_group->total_bitmaps--; - recalculate_thresholds(block_group); - } + } else if (!bitmap_info->bytes) + free_bitmap(block_group, bitmap_info); return 0; } @@ -1359,22 +1371,14 @@ out: return ret; } -int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes) +bool try_merge_free_space(struct btrfs_block_group_cache *block_group, + struct btrfs_free_space *info, bool update_stat) { - struct btrfs_free_space *right_info = NULL; - struct btrfs_free_space *left_info = NULL; - struct btrfs_free_space *info = NULL; - int ret = 0; - - info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS); - if (!info) - return -ENOMEM; - - info->offset = offset; - info->bytes = bytes; - - spin_lock(&block_group->tree_lock); + struct btrfs_free_space *left_info; + struct btrfs_free_space *right_info; + bool merged = false; + u64 offset = info->offset; + u64 bytes = info->bytes; /* * first we want to see if there is free space adjacent to the range we @@ -1388,37 +1392,62 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, else left_info = tree_search_offset(block_group, offset - 1, 0, 0); - /* - * If there was no extent directly to the left or right of this new - * extent then we know we're going to have to allocate a new extent, so - * before we do that see if we need to drop this into a bitmap - */ - if ((!left_info || left_info->bitmap) && - (!right_info || right_info->bitmap)) { - ret = insert_into_bitmap(block_group, info); - - if (ret < 0) { - goto out; - } else if (ret) { - ret = 0; - goto out; - } - } - if (right_info && !right_info->bitmap) { - unlink_free_space(block_group, right_info); + if (update_stat) + unlink_free_space(block_group, right_info); + else + __unlink_free_space(block_group, right_info); info->bytes += right_info->bytes; kfree(right_info); + merged = true; } if (left_info && !left_info->bitmap && left_info->offset + left_info->bytes == offset) { - unlink_free_space(block_group, left_info); + if (update_stat) + unlink_free_space(block_group, left_info); + else + __unlink_free_space(block_group, left_info); info->offset = left_info->offset; info->bytes += left_info->bytes; kfree(left_info); + merged = true; } + return merged; +} + +int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, + u64 offset, u64 bytes) +{ + struct btrfs_free_space *info; + int ret = 0; + + info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS); + if (!info) + return -ENOMEM; + + info->offset = offset; + info->bytes = bytes; + + spin_lock(&block_group->tree_lock); + + if (try_merge_free_space(block_group, info, true)) + goto link; + + /* + * There was no extent directly to the left or right of this new + * extent then we know we're going to have to allocate a new extent, so + * before we do that see if we need to drop this into a bitmap + */ + ret = insert_into_bitmap(block_group, info); + if (ret < 0) { + goto out; + } else if (ret) { + ret = 0; + goto out; + } +link: ret = link_free_space(block_group, info); if (ret) kfree(info); @@ -1621,6 +1650,7 @@ __btrfs_return_cluster_to_free_space( node = rb_next(&entry->offset_index); rb_erase(&entry->offset_index, &cluster->root); BUG_ON(entry->bitmap); + try_merge_free_space(block_group, entry, false); tree_insert_offset(&block_group->free_space_offset, entry->offset, &entry->offset_index, 0); } @@ -1685,13 +1715,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, ret = offset; if (entry->bitmap) { bitmap_clear_bits(block_group, entry, offset, bytes); - if (!entry->bytes) { - unlink_free_space(block_group, entry); - kfree(entry->bitmap); - kfree(entry); - block_group->total_bitmaps--; - recalculate_thresholds(block_group); - } + if (!entry->bytes) + free_bitmap(block_group, entry); } else { unlink_free_space(block_group, entry); entry->offset += bytes; @@ -1789,6 +1814,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, ret = search_start; bitmap_clear_bits(block_group, entry, ret, bytes); + if (entry->bytes == 0) + free_bitmap(block_group, entry); out: spin_unlock(&cluster->lock); spin_unlock(&block_group->tree_lock); @@ -1842,15 +1869,26 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, entry->offset += bytes; entry->bytes -= bytes; - if (entry->bytes == 0) { + if (entry->bytes == 0) rb_erase(&entry->offset_index, &cluster->root); - kfree(entry); - } break; } out: spin_unlock(&cluster->lock); + if (!ret) + return 0; + + spin_lock(&block_group->tree_lock); + + block_group->free_space -= bytes; + if (entry->bytes == 0) { + block_group->free_extents--; + kfree(entry); + } + + spin_unlock(&block_group->tree_lock); + return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 160b55b..4a0107e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -416,7 +416,7 @@ again: } if (start == 0) { trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -612,6 +612,7 @@ retry: GFP_NOFS); trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); ret = btrfs_reserve_extent(trans, root, async_extent->compressed_size, async_extent->compressed_size, @@ -643,6 +644,7 @@ retry: async_extent->ram_size - 1, 0); em = alloc_extent_map(GFP_NOFS); + BUG_ON(!em); em->start = async_extent->start; em->len = async_extent->ram_size; em->orig_start = em->start; @@ -771,7 +773,7 @@ static noinline int cow_file_range(struct inode *inode, BUG_ON(root == root->fs_info->tree_root); trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -819,6 +821,7 @@ static noinline int cow_file_range(struct inode *inode, BUG_ON(ret); em = alloc_extent_map(GFP_NOFS); + BUG_ON(!em); em->start = start; em->orig_start = em->start; ram_size = ins.offset; @@ -1049,7 +1052,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, } else { trans = btrfs_join_transaction(root, 1); } - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); cow_start = (u64)-1; cur_offset = start; @@ -1168,6 +1171,7 @@ out_check: struct extent_map_tree *em_tree; em_tree = &BTRFS_I(inode)->extent_tree; em = alloc_extent_map(GFP_NOFS); + BUG_ON(!em); em->start = cur_offset; em->orig_start = em->start; em->len = num_bytes; @@ -1557,6 +1561,7 @@ out: out_page: unlock_page(page); page_cache_release(page); + kfree(fixup); } /* @@ -1703,7 +1708,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) trans = btrfs_join_transaction_nolock(root, 1); else trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; ret = btrfs_update_inode(trans, root, inode); @@ -1720,6 +1725,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) trans = btrfs_join_transaction_nolock(root, 1); else trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -1907,7 +1913,7 @@ static int btrfs_clean_io_failures(struct inode *inode, u64 start) private = 0; if (count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private, - (u64)-1, 1, EXTENT_DIRTY)) { + (u64)-1, 1, EXTENT_DIRTY, 0)) { ret = get_state_private(&BTRFS_I(inode)->io_failure_tree, start, &private_failure); if (ret == 0) { @@ -2354,6 +2360,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) */ if (is_bad_inode(inode)) { trans = btrfs_start_transaction(root, 0); + BUG_ON(IS_ERR(trans)); btrfs_orphan_del(trans, inode); btrfs_end_transaction(trans, root); iput(inode); @@ -2381,6 +2388,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) if (root->orphan_block_rsv || root->orphan_item_inserted) { trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); btrfs_end_transaction(trans, root); } @@ -2641,7 +2649,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto err; + goto out; } path->leave_spinning = 1; @@ -2714,9 +2722,10 @@ static int check_path_shared(struct btrfs_root *root, struct extent_buffer *eb; int level; u64 refs = 1; - int uninitialized_var(ret); for (level = 0; level < BTRFS_MAX_LEVEL; level++) { + int ret; + if (!path->nodes[level]) break; eb = path->nodes[level]; @@ -2727,7 +2736,7 @@ static int check_path_shared(struct btrfs_root *root, if (refs > 1) return 1; } - return ret; /* XXX callers? */ + return 0; } /* @@ -4134,7 +4143,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) } srcu_read_unlock(&root->fs_info->subvol_srcu, index); - if (root != sub_root) { + if (!IS_ERR(inode) && root != sub_root) { down_read(&root->fs_info->cleanup_work_sem); if (!(inode->i_sb->s_flags & MS_RDONLY)) btrfs_orphan_cleanup(sub_root); @@ -4347,6 +4356,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc) trans = btrfs_join_transaction_nolock(root, 1); else trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); btrfs_set_trans_block_group(trans, inode); if (nolock) ret = btrfs_end_transaction_nolock(trans, root); @@ -4372,6 +4383,7 @@ void btrfs_dirty_inode(struct inode *inode) return; trans = btrfs_join_transaction(root, 1); + BUG_ON(IS_ERR(trans)); btrfs_set_trans_block_group(trans, inode); ret = btrfs_update_inode(trans, root, inode); @@ -4794,9 +4806,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, int err; int drop_inode = 0; - if (inode->i_nlink == 0) - return -ENOENT; - /* do not allow sys_link's with other subvols of the same device */ if (root->objectid != BTRFS_I(inode)->root->objectid) return -EPERM; @@ -4809,10 +4818,11 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, goto fail; /* - * 1 item for inode ref + * 2 items for inode and inode ref * 2 items for dir items + * 1 item for parent inode */ - trans = btrfs_start_transaction(root, 3); + trans = btrfs_start_transaction(root, 5); if (IS_ERR(trans)) { err = PTR_ERR(trans); goto fail; @@ -5176,6 +5186,8 @@ again: em = NULL; btrfs_release_path(root, path); trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + return ERR_CAST(trans); goto again; } map = kmap(page); @@ -5266,6 +5278,128 @@ out: return em; } +struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page, + size_t pg_offset, u64 start, u64 len, + int create) +{ + struct extent_map *em; + struct extent_map *hole_em = NULL; + u64 range_start = start; + u64 end; + u64 found; + u64 found_end; + int err = 0; + + em = btrfs_get_extent(inode, page, pg_offset, start, len, create); + if (IS_ERR(em)) + return em; + if (em) { + /* + * if our em maps to a hole, there might + * actually be delalloc bytes behind it + */ + if (em->block_start != EXTENT_MAP_HOLE) + return em; + else + hole_em = em; + } + + /* check to see if we've wrapped (len == -1 or similar) */ + end = start + len; + if (end < start) + end = (u64)-1; + else + end -= 1; + + em = NULL; + + /* ok, we didn't find anything, lets look for delalloc */ + found = count_range_bits(&BTRFS_I(inode)->io_tree, &range_start, + end, len, EXTENT_DELALLOC, 1); + found_end = range_start + found; + if (found_end < range_start) + found_end = (u64)-1; + + /* + * we didn't find anything useful, return + * the original results from get_extent() + */ + if (range_start > end || found_end <= start) { + em = hole_em; + hole_em = NULL; + goto out; + } + + /* adjust the range_start to make sure it doesn't + * go backwards from the start they passed in + */ + range_start = max(start,range_start); + found = found_end - range_start; + + if (found > 0) { + u64 hole_start = start; + u64 hole_len = len; + + em = alloc_extent_map(GFP_NOFS); + if (!em) { + err = -ENOMEM; + goto out; + } + /* + * when btrfs_get_extent can't find anything it + * returns one huge hole + * + * make sure what it found really fits our range, and + * adjust to make sure it is based on the start from + * the caller + */ + if (hole_em) { + u64 calc_end = extent_map_end(hole_em); + + if (calc_end <= start || (hole_em->start > end)) { + free_extent_map(hole_em); + hole_em = NULL; + } else { + hole_start = max(hole_em->start, start); + hole_len = calc_end - hole_start; + } + } + em->bdev = NULL; + if (hole_em && range_start > hole_start) { + /* our hole starts before our delalloc, so we + * have to return just the parts of the hole + * that go until the delalloc starts + */ + em->len = min(hole_len, + range_start - hole_start); + em->start = hole_start; + em->orig_start = hole_start; + /* + * don't adjust block start at all, + * it is fixed at EXTENT_MAP_HOLE + */ + em->block_start = hole_em->block_start; + em->block_len = hole_len; + } else { + em->start = range_start; + em->len = found; + em->orig_start = range_start; + em->block_start = EXTENT_MAP_DELALLOC; + em->block_len = found; + } + } else if (hole_em) { + return hole_em; + } +out: + + free_extent_map(hole_em); + if (err) { + free_extent_map(em); + return ERR_PTR(err); + } + return em; +} + static struct extent_map *btrfs_new_extent_direct(struct inode *inode, u64 start, u64 len) { @@ -5280,8 +5414,8 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, btrfs_drop_extent_cache(inode, start, start + len - 1, 0); trans = btrfs_join_transaction(root, 0); - if (!trans) - return ERR_PTR(-ENOMEM); + if (IS_ERR(trans)) + return ERR_CAST(trans); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -5505,7 +5639,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * while we look for nocow cross refs */ trans = btrfs_join_transaction(root, 0); - if (!trans) + if (IS_ERR(trans)) goto must_cow; if (can_nocow_odirect(trans, inode, start, len) == 1) { @@ -5640,7 +5774,7 @@ again: BUG_ON(!ordered); trans = btrfs_join_transaction(root, 1); - if (!trans) { + if (IS_ERR(trans)) { err = -ENOMEM; goto out; } @@ -5920,6 +6054,7 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, if (!skip_sum) { dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS); if (!dip->csums) { + kfree(dip); ret = -ENOMEM; goto free_ordered; } @@ -6088,7 +6223,7 @@ out: static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { - return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent); + return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent_fiemap); } int btrfs_readpage(struct file *file, struct page *page) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a506a22..5fdb2ab 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -203,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) trans = btrfs_join_transaction(root, 1); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); @@ -907,6 +907,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (new_size > old_size) { trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_unlock; + } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans, root); } else { @@ -1067,12 +1071,15 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, if (copy_from_user(&flags, arg, sizeof(flags))) return -EFAULT; - if (flags & ~BTRFS_SUBVOL_CREATE_ASYNC) + if (flags & BTRFS_SUBVOL_CREATE_ASYNC) return -EINVAL; if (flags & ~BTRFS_SUBVOL_RDONLY) return -EOPNOTSUPP; + if (!is_owner_or_cap(inode)) + return -EACCES; + down_write(&root->fs_info->subvol_sem); /* nothing to do */ @@ -1093,7 +1100,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file, goto out_reset; } - ret = btrfs_update_root(trans, root, + ret = btrfs_update_root(trans, root->fs_info->tree_root, &root->root_key, &root->root_item); btrfs_commit_transaction(trans, root); @@ -1898,7 +1905,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, memcpy(&new_key, &key, sizeof(new_key)); new_key.objectid = inode->i_ino; - new_key.offset = key.offset + destoff - off; + if (off <= key.offset) + new_key.offset = key.offset + destoff - off; + else + new_key.offset = destoff; trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { @@ -2082,7 +2092,7 @@ static long btrfs_ioctl_trans_start(struct file *file) ret = -ENOMEM; trans = btrfs_start_ioctl_transaction(root, 0); - if (!trans) + if (IS_ERR(trans)) goto out_drop; file->private_data = trans; @@ -2138,9 +2148,9 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) path->leave_spinning = 1; trans = btrfs_start_transaction(root, 1); - if (!trans) { + if (IS_ERR(trans)) { btrfs_free_path(path); - return -ENOMEM; + return PTR_ERR(trans); } dir_id = btrfs_super_root_dir(&root->fs_info->super_copy); @@ -2201,7 +2211,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) int num_types = 4; int alloc_size; int ret = 0; - int slot_count = 0; + u64 slot_count = 0; int i, c; if (copy_from_user(&space_args, @@ -2240,7 +2250,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) goto out; } - slot_count = min_t(int, space_args.space_slots, slot_count); + slot_count = min_t(u64, space_args.space_slots, slot_count); alloc_size = sizeof(*dest) * slot_count; @@ -2260,6 +2270,9 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) for (i = 0; i < num_types; i++) { struct btrfs_space_info *tmp; + if (!slot_count) + break; + info = NULL; rcu_read_lock(); list_for_each_entry_rcu(tmp, &root->fs_info->space_info, @@ -2281,7 +2294,10 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) memcpy(dest, &space, sizeof(space)); dest++; space_args.total_spaces++; + slot_count--; } + if (!slot_count) + break; } up_read(&info->groups_sem); } @@ -2334,6 +2350,8 @@ static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp u64 transid; trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) + return PTR_ERR(trans); transid = trans->transid; btrfs_commit_transaction_async(trans, root, 0); diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index cc9b450..a178f5e 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -280,6 +280,7 @@ static int lzo_decompress_biovec(struct list_head *ws, unsigned long tot_out; unsigned long tot_len; char *buf; + bool may_late_unmap, need_unmap; data_in = kmap(pages_in[0]); tot_len = read_compress_length(data_in); @@ -300,11 +301,13 @@ static int lzo_decompress_biovec(struct list_head *ws, tot_in += in_len; working_bytes = in_len; + may_late_unmap = need_unmap = false; /* fast path: avoid using the working buffer */ if (in_page_bytes_left >= in_len) { buf = data_in + in_offset; bytes = in_len; + may_late_unmap = true; goto cont; } @@ -329,14 +332,17 @@ cont: if (working_bytes == 0 && tot_in >= tot_len) break; - kunmap(pages_in[page_in_index]); - page_in_index++; - if (page_in_index >= total_pages_in) { + if (page_in_index + 1 >= total_pages_in) { ret = -1; - data_in = NULL; goto done; } - data_in = kmap(pages_in[page_in_index]); + + if (may_late_unmap) + need_unmap = true; + else + kunmap(pages_in[page_in_index]); + + data_in = kmap(pages_in[++page_in_index]); in_page_bytes_left = PAGE_CACHE_SIZE; in_offset = 0; @@ -346,6 +352,8 @@ cont: out_len = lzo1x_worst_compress(PAGE_CACHE_SIZE); ret = lzo1x_decompress_safe(buf, in_len, workspace->buf, &out_len); + if (need_unmap) + kunmap(pages_in[page_in_index - 1]); if (ret != LZO_E_OK) { printk(KERN_WARNING "btrfs decompress failed\n"); ret = -1; @@ -363,8 +371,7 @@ cont: break; } done: - if (data_in) - kunmap(pages_in[page_in_index]); + kunmap(pages_in[page_in_index]); return ret; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 2b61e1d..083a554 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -141,7 +141,7 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree, u64 file_offset) { struct rb_root *root = &tree->tree; - struct rb_node *prev; + struct rb_node *prev = NULL; struct rb_node *ret; struct btrfs_ordered_extent *entry; diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 0d126be..fb2605d 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -260,6 +260,7 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) #else BUG(); #endif + break; case BTRFS_BLOCK_GROUP_ITEM_KEY: bi = btrfs_item_ptr(l, i, struct btrfs_block_group_item); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 045c9c2..31ade58 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1157,6 +1157,7 @@ static int clone_backref_node(struct btrfs_trans_handle *trans, new_node->bytenr = dest->node->start; new_node->level = node->level; new_node->lowest = node->lowest; + new_node->checked = 1; new_node->root = dest; if (!node->lowest) { @@ -2028,6 +2029,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, while (1) { trans = btrfs_start_transaction(root, 0); + BUG_ON(IS_ERR(trans)); trans->block_rsv = rc->block_rsv; ret = btrfs_block_rsv_check(trans, root, rc->block_rsv, @@ -2147,6 +2149,12 @@ again: } trans = btrfs_join_transaction(rc->extent_root, 1); + if (IS_ERR(trans)) { + if (!err) + btrfs_block_rsv_release(rc->extent_root, + rc->block_rsv, num_bytes); + return PTR_ERR(trans); + } if (!err) { if (num_bytes != rc->merging_rsv_size) { @@ -3222,6 +3230,7 @@ truncate: trans = btrfs_join_transaction(root, 0); if (IS_ERR(trans)) { btrfs_free_path(path); + ret = PTR_ERR(trans); goto out; } @@ -3628,6 +3637,7 @@ int prepare_to_relocate(struct reloc_control *rc) set_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root, 1); + BUG_ON(IS_ERR(trans)); btrfs_commit_transaction(trans, rc->extent_root); return 0; } @@ -3644,6 +3654,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) u32 item_size; int ret; int err = 0; + int progress = 0; path = btrfs_alloc_path(); if (!path) @@ -3656,8 +3667,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) } while (1) { + progress++; trans = btrfs_start_transaction(rc->extent_root, 0); - + BUG_ON(IS_ERR(trans)); +restart: if (update_backref_cache(trans, &rc->backref_cache)) { btrfs_end_transaction(trans, rc->extent_root); continue; @@ -3770,6 +3783,15 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) } } } + if (trans && progress && err == -ENOSPC) { + ret = btrfs_force_chunk_alloc(trans, rc->extent_root, + rc->block_group->flags); + if (ret == 0) { + err = 0; + progress = 0; + goto restart; + } + } btrfs_release_path(rc->extent_root, path); clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY, @@ -3804,7 +3826,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) /* get rid of pinned extents */ trans = btrfs_join_transaction(rc->extent_root, 1); - btrfs_commit_transaction(trans, rc->extent_root); + if (IS_ERR(trans)) + err = PTR_ERR(trans); + else + btrfs_commit_transaction(trans, rc->extent_root); out_free: btrfs_free_block_rsv(rc->extent_root, rc->block_rsv); btrfs_free_path(path); @@ -4022,6 +4047,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root) int ret; trans = btrfs_start_transaction(root->fs_info->tree_root, 0); + BUG_ON(IS_ERR(trans)); memset(&root->root_item.drop_progress, 0, sizeof(root->root_item.drop_progress)); @@ -4125,6 +4151,11 @@ int btrfs_recover_relocation(struct btrfs_root *root) set_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root, 1); + if (IS_ERR(trans)) { + unset_reloc_control(rc); + err = PTR_ERR(trans); + goto out_free; + } rc->merge_reloc_tree = 1; @@ -4154,9 +4185,13 @@ int btrfs_recover_relocation(struct btrfs_root *root) unset_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root, 1); - btrfs_commit_transaction(trans, rc->extent_root); -out: + if (IS_ERR(trans)) + err = PTR_ERR(trans); + else + btrfs_commit_transaction(trans, rc->extent_root); +out_free: kfree(rc); +out: while (!list_empty(&reloc_roots)) { reloc_root = list_entry(reloc_roots.next, struct btrfs_root, root_list); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b2130c4..d39a989 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -155,7 +155,8 @@ enum { Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress, Opt_compress_type, Opt_compress_force, Opt_compress_force_type, Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard, - Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, Opt_err, + Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, + Opt_enospc_debug, Opt_err, }; static match_table_t tokens = { @@ -184,6 +185,7 @@ static match_table_t tokens = { {Opt_space_cache, "space_cache"}, {Opt_clear_cache, "clear_cache"}, {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, + {Opt_enospc_debug, "enospc_debug"}, {Opt_err, NULL}, }; @@ -358,6 +360,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_user_subvol_rm_allowed: btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED); break; + case Opt_enospc_debug: + btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG); + break; case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); @@ -383,7 +388,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, struct btrfs_fs_devices **fs_devices) { substring_t args[MAX_OPT_ARGS]; - char *opts, *p; + char *opts, *orig, *p; int error = 0; int intarg; @@ -397,6 +402,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, opts = kstrdup(options, GFP_KERNEL); if (!opts) return -ENOMEM; + orig = opts; while ((p = strsep(&opts, ",")) != NULL) { int token; @@ -432,7 +438,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags, } out_free_opts: - kfree(opts); + kfree(orig); out: /* * If no subvolume name is specified we use the default one. Allocate @@ -623,6 +629,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait) btrfs_wait_ordered_extents(root, 0, 0); trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) + return PTR_ERR(trans); ret = btrfs_commit_transaction(trans, root); return ret; } @@ -761,6 +769,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } btrfs_close_devices(fs_devices); + kfree(fs_info); + kfree(tree_root); } else { char b[BDEVNAME_SIZE]; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index bae5c7b..3d73c8d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1161,6 +1161,11 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, INIT_DELAYED_WORK(&ac->work, do_async_commit); ac->root = root; ac->newtrans = btrfs_join_transaction(root, 0); + if (IS_ERR(ac->newtrans)) { + int err = PTR_ERR(ac->newtrans); + kfree(ac); + return err; + } /* take transaction reference */ mutex_lock(&root->fs_info->trans_mutex); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 054744a..a4bbb85 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -338,6 +338,12 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, } dst_copy = kmalloc(item_size, GFP_NOFS); src_copy = kmalloc(item_size, GFP_NOFS); + if (!dst_copy || !src_copy) { + btrfs_release_path(root, path); + kfree(dst_copy); + kfree(src_copy); + return -ENOMEM; + } read_extent_buffer(eb, src_copy, src_ptr, item_size); @@ -665,6 +671,9 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, btrfs_dir_item_key_to_cpu(leaf, di, &location); name_len = btrfs_dir_name_len(leaf, di); name = kmalloc(name_len, GFP_NOFS); + if (!name) + return -ENOMEM; + read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len); btrfs_release_path(root, path); @@ -744,6 +753,9 @@ static noinline int backref_in_log(struct btrfs_root *log, int match = 0; path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + ret = btrfs_search_slot(NULL, log, key, path, 0, 0); if (ret != 0) goto out; @@ -967,6 +979,8 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, key.offset = (u64)-1; path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; while (1) { ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); @@ -1178,6 +1192,9 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, name_len = btrfs_dir_name_len(eb, di); name = kmalloc(name_len, GFP_NOFS); + if (!name) + return -ENOMEM; + log_type = btrfs_dir_type(eb, di); read_extent_buffer(eb, name, (unsigned long)(di + 1), name_len); @@ -1692,6 +1709,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, root_owner = btrfs_header_owner(parent); next = btrfs_find_create_tree_block(root, bytenr, blocksize); + if (!next) + return -ENOMEM; if (*level == 1) { wc->process_func(root, next, wc, ptr_gen); @@ -2032,6 +2051,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, wait_log_commit(trans, log_root_tree, log_root_tree->log_transid); mutex_unlock(&log_root_tree->log_mutex); + ret = 0; goto out; } atomic_set(&log_root_tree->log_commit[index2], 1); @@ -2096,7 +2116,7 @@ out: smp_mb(); if (waitqueue_active(&root->log_commit_wait[index1])) wake_up(&root->log_commit_wait[index1]); - return 0; + return ret; } static void free_log_tree(struct btrfs_trans_handle *trans, @@ -2194,6 +2214,9 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans, log = root->log_root; path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino, name, name_len, -1); if (IS_ERR(di)) { @@ -2594,6 +2617,9 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, ins_data = kmalloc(nr * sizeof(struct btrfs_key) + nr * sizeof(u32), GFP_NOFS); + if (!ins_data) + return -ENOMEM; + ins_sizes = (u32 *)ins_data; ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32)); @@ -2725,7 +2751,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, log = root->log_root; path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; dst_path = btrfs_alloc_path(); + if (!dst_path) { + btrfs_free_path(path); + return -ENOMEM; + } min_key.objectid = inode->i_ino; min_key.type = BTRFS_INODE_ITEM_KEY; @@ -3080,6 +3112,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) BUG_ON(!path); trans = btrfs_start_transaction(fs_info->tree_root, 0); + BUG_ON(IS_ERR(trans)); wc.trans = trans; wc.pin = 1; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d158530..dd13eb8 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1213,6 +1213,10 @@ static int btrfs_rm_dev_item(struct btrfs_root *root, return -ENOMEM; trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + btrfs_free_path(path); + return PTR_ERR(trans); + } key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.type = BTRFS_DEV_ITEM_KEY; key.offset = device->devid; @@ -1334,11 +1338,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) ret = btrfs_shrink_device(device, 0); if (ret) - goto error_brelse; + goto error_undo; ret = btrfs_rm_dev_item(root->fs_info->chunk_root, device); if (ret) - goto error_brelse; + goto error_undo; device->in_fs_metadata = 0; @@ -1412,6 +1416,13 @@ out: mutex_unlock(&root->fs_info->volume_mutex); mutex_unlock(&uuid_mutex); return ret; +error_undo: + if (device->writeable) { + list_add(&device->dev_alloc_list, + &root->fs_info->fs_devices->alloc_list); + root->fs_info->fs_devices->rw_devices++; + } + goto error_brelse; } /* @@ -1601,11 +1612,19 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = find_next_devid(root, &device->devid); if (ret) { + kfree(device->name); kfree(device); goto error; } trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + kfree(device->name); + kfree(device); + ret = PTR_ERR(trans); + goto error; + } + lock_chunks(root); device->writeable = 1; @@ -1621,7 +1640,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) device->dev_root = root->fs_info->dev_root; device->bdev = bdev; device->in_fs_metadata = 1; - device->mode = 0; + device->mode = FMODE_EXCL; set_blocksize(device->bdev, 4096); if (seeding_dev) { @@ -1873,7 +1892,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, return ret; trans = btrfs_start_transaction(root, 0); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); lock_chunks(root); @@ -2047,7 +2066,7 @@ int btrfs_balance(struct btrfs_root *dev_root) BUG_ON(ret); trans = btrfs_start_transaction(dev_root, 0); - BUG_ON(!trans); + BUG_ON(IS_ERR(trans)); ret = btrfs_grow_device(trans, device, old_size); BUG_ON(ret); @@ -2213,6 +2232,11 @@ again: /* Shrinking succeeded, else we would be at "done". */ trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto done; + } + lock_chunks(root); device->disk_total_bytes = new_size; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 0bc68de..ebafa65 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -409,7 +409,7 @@ more: spin_lock(&inode->i_lock); if (ci->i_release_count == fi->dir_release_count) { dout(" marking %p complete\n", inode); - ci->i_ceph_flags |= CEPH_I_COMPLETE; + /* ci->i_ceph_flags |= CEPH_I_COMPLETE; */ ci->i_max_offset = filp->f_pos; } spin_unlock(&inode->i_lock); @@ -496,6 +496,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req, /* .snap dir? */ if (err == -ENOENT && + ceph_snap(parent) == CEPH_NOSNAP && strcmp(dentry->d_name.name, fsc->mount_options->snapdir_name) == 0) { struct inode *inode = ceph_get_snapdir(parent); @@ -992,7 +993,7 @@ static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd) { struct inode *dir; - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; dir = dentry->d_parent->d_inode; @@ -1029,28 +1030,8 @@ out_touch: static void ceph_dentry_release(struct dentry *dentry) { struct ceph_dentry_info *di = ceph_dentry(dentry); - struct inode *parent_inode = NULL; - u64 snapid = CEPH_NOSNAP; - if (!IS_ROOT(dentry)) { - parent_inode = dentry->d_parent->d_inode; - if (parent_inode) - snapid = ceph_snap(parent_inode); - } - dout("dentry_release %p parent %p\n", dentry, parent_inode); - if (parent_inode && snapid != CEPH_SNAPDIR) { - struct ceph_inode_info *ci = ceph_inode(parent_inode); - - spin_lock(&parent_inode->i_lock); - if (ci->i_shared_gen == di->lease_shared_gen || - snapid <= CEPH_MAXSNAP) { - dout(" clearing %p complete (d_release)\n", - parent_inode); - ci->i_ceph_flags &= ~CEPH_I_COMPLETE; - ci->i_release_count++; - } - spin_unlock(&parent_inode->i_lock); - } + dout("dentry_release %p\n", dentry); if (di) { ceph_dentry_lru_del(dentry); if (di->lease_session) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 5625463..193bfa5 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -707,7 +707,7 @@ static int fill_inode(struct inode *inode, (issued & CEPH_CAP_FILE_EXCL) == 0 && (ci->i_ceph_flags & CEPH_I_COMPLETE) == 0) { dout(" marking %p complete (empty)\n", inode); - ci->i_ceph_flags |= CEPH_I_COMPLETE; + /* ci->i_ceph_flags |= CEPH_I_COMPLETE; */ ci->i_max_offset = 2; } break; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 39c243a..f40b913 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -584,10 +584,14 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm) if (lastinode) iput(lastinode); - dout("queue_realm_cap_snaps %p %llx children\n", realm, realm->ino); - list_for_each_entry(child, &realm->children, child_item) - queue_realm_cap_snaps(child); + list_for_each_entry(child, &realm->children, child_item) { + dout("queue_realm_cap_snaps %p %llx queue child %p %llx\n", + realm, realm->ino, child, child->ino); + list_del_init(&child->dirty_item); + list_add(&child->dirty_item, &realm->dirty_item); + } + list_del_init(&realm->dirty_item); dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino); } @@ -683,7 +687,9 @@ more: * queue cap snaps _after_ we've built the new snap contexts, * so that i_head_snapc can be set appropriately. */ - list_for_each_entry(realm, &dirty_realms, dirty_item) { + while (!list_empty(&dirty_realms)) { + realm = list_first_entry(&dirty_realms, struct ceph_snap_realm, + dirty_item); queue_realm_cap_snaps(realm); } diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index ee45648..7cb0f7f 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -3,6 +3,7 @@ config CIFS depends on INET select NLS select CRYPTO + select CRYPTO_MD4 select CRYPTO_MD5 select CRYPTO_HMAC select CRYPTO_ARC4 diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index f1c6862..0a265ad 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -282,8 +282,6 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) cFYI(1, "in %s", __func__); BUG_ON(IS_ROOT(mntpt)); - xid = GetXid(); - /* * The MSDFS spec states that paths in DFS referral requests and * responses must be prefixed by a single '\' character instead of @@ -293,7 +291,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) mnt = ERR_PTR(-ENOMEM); full_path = build_path_from_dentry(mntpt); if (full_path == NULL) - goto free_xid; + goto cdda_exit; cifs_sb = CIFS_SB(mntpt->d_inode->i_sb); tlink = cifs_sb_tlink(cifs_sb); @@ -303,9 +301,11 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) } ses = tlink_tcon(tlink)->ses; + xid = GetXid(); rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls, &num_referrals, &referrals, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + FreeXid(xid); cifs_put_tlink(tlink); @@ -338,8 +338,7 @@ success: free_dfs_info_array(referrals, num_referrals); free_full_path: kfree(full_path); -free_xid: - FreeXid(xid); +cdda_exit: cFYI(1, "leaving %s" , __func__); return mnt; } diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 1e7636b..beeebf1 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -372,6 +372,10 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl, ppace = kmalloc(num_aces * sizeof(struct cifs_ace *), GFP_KERNEL); + if (!ppace) { + cERROR(1, "DACL memory allocation error"); + return; + } for (i = 0; i < num_aces; ++i) { ppace[i] = (struct cifs_ace *) (acl_base + acl_size); diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 0db5f1d..a51585f 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -657,9 +657,10 @@ calc_seckey(struct cifsSesInfo *ses) get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE); tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); - if (!tfm_arc4 || IS_ERR(tfm_arc4)) { + if (IS_ERR(tfm_arc4)) { + rc = PTR_ERR(tfm_arc4); cERROR(1, "could not allocate crypto API arc4\n"); - return PTR_ERR(tfm_arc4); + return rc; } desc.tfm = tfm_arc4; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 14789a9..a9371b6 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -127,5 +127,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* EXPERIMENTAL */ -#define CIFS_VERSION "1.69" +#define CIFS_VERSION "1.71" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index edd5b29..17afb0f 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -188,6 +188,8 @@ struct TCP_Server_Info { /* multiplexed reads or writes */ unsigned int maxBuf; /* maxBuf specifies the maximum */ /* message size the server can send or receive for non-raw SMBs */ + /* maxBuf is returned by SMB NegotiateProtocol so maxBuf is only 0 */ + /* when socket is setup (and during reconnect) before NegProt sent */ unsigned int max_rw; /* maxRw specifies the maximum */ /* message size the server can send or receive for */ /* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */ @@ -652,7 +654,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param, #define MID_REQUEST_SUBMITTED 2 #define MID_RESPONSE_RECEIVED 4 #define MID_RETRY_NEEDED 8 /* session closed while this request out */ -#define MID_NO_RESP_NEEDED 0x10 +#define MID_RESPONSE_MALFORMED 0x10 /* Types of response buffer returned from SendReceive2 */ #define CIFS_NO_BUFFER 0 /* Response buffer not returned */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 3106f5e..904aa47 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -136,9 +136,6 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command) } } - if (ses->status == CifsExiting) - return -EIO; - /* * Give demultiplex thread up to 10 seconds to reconnect, should be * greater than cifs socket timeout which is 7 seconds @@ -156,7 +153,7 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command) * retrying until process is killed or server comes * back on-line */ - if (!tcon->retry || ses->status == CifsExiting) { + if (!tcon->retry) { cFYI(1, "gave up waiting on reconnect in smb_init"); return -EHOSTDOWN; } @@ -4914,7 +4911,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size, __u16 fid, __u32 pid_of_opener, bool SetAllocation) { struct smb_com_transaction2_sfi_req *pSMB = NULL; - char *data_offset; struct file_end_of_file_info *parm_data; int rc = 0; __u16 params, param_offset, offset, byte_count, count; @@ -4938,8 +4934,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size, param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4; offset = param_offset + params; - data_offset = (char *) (&pSMB->hdr.Protocol) + offset; - count = sizeof(struct file_end_of_file_info); pSMB->MaxParameterCount = cpu_to_le16(2); /* BB find exact max SMB PDU from sess structure BB */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 47d8ff6..8d6c17a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -337,8 +337,13 @@ cifs_echo_request(struct work_struct *work) struct TCP_Server_Info *server = container_of(work, struct TCP_Server_Info, echo.work); - /* no need to ping if we got a response recently */ - if (time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ)) + /* + * We cannot send an echo until the NEGOTIATE_PROTOCOL request is + * done, which is indicated by maxBuf != 0. Also, no need to ping if + * we got a response recently + */ + if (server->maxBuf == 0 || + time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ)) goto requeue_echo; rc = CIFSSMBEcho(server); @@ -578,14 +583,23 @@ incomplete_rcv: else if (reconnect == 1) continue; - length += 4; /* account for rfc1002 hdr */ + total_read += 4; /* account for rfc1002 hdr */ + dump_smb(smb_buffer, total_read); - dump_smb(smb_buffer, length); - if (checkSMB(smb_buffer, smb_buffer->Mid, total_read+4)) { - cifs_dump_mem("Bad SMB: ", smb_buffer, 48); - continue; - } + /* + * We know that we received enough to get to the MID as we + * checked the pdu_length earlier. Now check to see + * if the rest of the header is OK. We borrow the length + * var for the rest of the loop to avoid a new stack var. + * + * 48 bytes is enough to display the header and a little bit + * into the payload for debugging purposes. + */ + length = checkSMB(smb_buffer, smb_buffer->Mid, total_read); + if (length != 0) + cifs_dump_mem("Bad SMB: ", smb_buffer, + min_t(unsigned int, total_read, 48)); mid_entry = NULL; server->lstrp = jiffies; @@ -597,7 +611,8 @@ incomplete_rcv: if ((mid_entry->mid == smb_buffer->Mid) && (mid_entry->midState == MID_REQUEST_SUBMITTED) && (mid_entry->command == smb_buffer->Command)) { - if (check2ndT2(smb_buffer,server->maxBuf) > 0) { + if (length == 0 && + check2ndT2(smb_buffer, server->maxBuf) > 0) { /* We have a multipart transact2 resp */ isMultiRsp = true; if (mid_entry->resp_buf) { @@ -632,12 +647,17 @@ incomplete_rcv: mid_entry->resp_buf = smb_buffer; mid_entry->largeBuf = isLargeBuf; multi_t2_fnd: - mid_entry->midState = MID_RESPONSE_RECEIVED; - list_del_init(&mid_entry->qhead); - mid_entry->callback(mid_entry); + if (length == 0) + mid_entry->midState = + MID_RESPONSE_RECEIVED; + else + mid_entry->midState = + MID_RESPONSE_MALFORMED; #ifdef CONFIG_CIFS_STATS2 mid_entry->when_received = jiffies; #endif + list_del_init(&mid_entry->qhead); + mid_entry->callback(mid_entry); break; } mid_entry = NULL; @@ -653,6 +673,9 @@ multi_t2_fnd: else smallbuf = NULL; } + } else if (length != 0) { + /* response sanity checks failed */ + continue; } else if (!is_valid_oplock_break(smb_buffer, server) && !isMultiRsp) { cERROR(1, "No task to wake, unknown frame received! " diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0de17c1..e964b1c 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -346,7 +346,6 @@ int cifs_open(struct inode *inode, struct file *file) struct cifsTconInfo *tcon; struct tcon_link *tlink; struct cifsFileInfo *pCifsFile = NULL; - struct cifsInodeInfo *pCifsInode; char *full_path = NULL; bool posix_open_ok = false; __u16 netfid; @@ -361,8 +360,6 @@ int cifs_open(struct inode *inode, struct file *file) } tcon = tlink_tcon(tlink); - pCifsInode = CIFS_I(file->f_path.dentry->d_inode); - full_path = build_path_from_dentry(file->f_path.dentry); if (full_path == NULL) { rc = -ENOMEM; @@ -1146,7 +1143,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) char *write_data; int rc = -EFAULT; int bytes_written = 0; - struct cifs_sb_info *cifs_sb; struct inode *inode; struct cifsFileInfo *open_file; @@ -1154,7 +1150,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) return -EFAULT; inode = page->mapping->host; - cifs_sb = CIFS_SB(inode->i_sb); offset += (loff_t)from; write_data = kmap(page); @@ -1667,9 +1662,10 @@ static ssize_t cifs_iovec_write(struct file *file, const struct iovec *iov, unsigned long nr_segs, loff_t *poffset) { - size_t total_written = 0, written = 0; - unsigned long num_pages, npages; - size_t copied, len, cur_len, i; + unsigned int written; + unsigned long num_pages, npages, i; + size_t copied, len, cur_len; + ssize_t total_written = 0; struct kvec *to_send; struct page **pages; struct iov_iter it; @@ -1825,7 +1821,8 @@ cifs_iovec_read(struct file *file, const struct iovec *iov, { int rc; int xid; - unsigned int total_read, bytes_read = 0; + ssize_t total_read; + unsigned int bytes_read = 0; size_t len, cur_len; int iov_offset = 0; struct cifs_sb_info *cifs_sb; diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 02cd60a..e8804d3 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -55,8 +55,9 @@ symlink_hash(unsigned int link_len, const char *link_str, u8 *md5_hash) md5 = crypto_alloc_shash("md5", 0, 0); if (IS_ERR(md5)) { + rc = PTR_ERR(md5); cERROR(1, "%s: Crypto md5 allocation error %d\n", __func__, rc); - return PTR_ERR(md5); + return rc; } size = sizeof(struct shash_desc) + crypto_shash_descsize(md5); sdescmd5 = kmalloc(size, GFP_KERNEL); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index a09e077..2a930a7 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -236,10 +236,7 @@ __u16 GetNextMid(struct TCP_Server_Info *server) { __u16 mid = 0; __u16 last_mid; - int collision; - - if (server == NULL) - return mid; + bool collision; spin_lock(&GlobalMid_Lock); last_mid = server->CurrentMid; /* we do not want to loop forever */ @@ -252,24 +249,38 @@ __u16 GetNextMid(struct TCP_Server_Info *server) (and it would also have to have been a request that did not time out) */ while (server->CurrentMid != last_mid) { - struct list_head *tmp; struct mid_q_entry *mid_entry; + unsigned int num_mids; - collision = 0; + collision = false; if (server->CurrentMid == 0) server->CurrentMid++; - list_for_each(tmp, &server->pending_mid_q) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); - - if ((mid_entry->mid == server->CurrentMid) && - (mid_entry->midState == MID_REQUEST_SUBMITTED)) { + num_mids = 0; + list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { + ++num_mids; + if (mid_entry->mid == server->CurrentMid && + mid_entry->midState == MID_REQUEST_SUBMITTED) { /* This mid is in use, try a different one */ - collision = 1; + collision = true; break; } } - if (collision == 0) { + + /* + * if we have more than 32k mids in the list, then something + * is very wrong. Possibly a local user is trying to DoS the + * box by issuing long-running calls and SIGKILL'ing them. If + * we get to 2^16 mids then we're in big trouble as this + * function could loop forever. + * + * Go ahead and assign out the mid in this situation, but force + * an eventual reconnect to clean out the pending_mid_q. + */ + if (num_mids > 32768) + server->tcpStatus = CifsNeedReconnect; + + if (!collision) { mid = server->CurrentMid; break; } @@ -381,29 +392,31 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , } static int -checkSMBhdr(struct smb_hdr *smb, __u16 mid) +check_smb_hdr(struct smb_hdr *smb, __u16 mid) { - /* Make sure that this really is an SMB, that it is a response, - and that the message ids match */ - if ((*(__le32 *) smb->Protocol == cpu_to_le32(0x424d53ff)) && - (mid == smb->Mid)) { - if (smb->Flags & SMBFLG_RESPONSE) - return 0; - else { - /* only one valid case where server sends us request */ - if (smb->Command == SMB_COM_LOCKING_ANDX) - return 0; - else - cERROR(1, "Received Request not response"); - } - } else { /* bad signature or mid */ - if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff)) - cERROR(1, "Bad protocol string signature header %x", - *(unsigned int *) smb->Protocol); - if (mid != smb->Mid) - cERROR(1, "Mids do not match"); + /* does it have the right SMB "signature" ? */ + if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff)) { + cERROR(1, "Bad protocol string signature header 0x%x", + *(unsigned int *)smb->Protocol); + return 1; + } + + /* Make sure that message ids match */ + if (mid != smb->Mid) { + cERROR(1, "Mids do not match. received=%u expected=%u", + smb->Mid, mid); + return 1; } - cERROR(1, "bad smb detected. The Mid=%d", smb->Mid); + + /* if it's a response then accept */ + if (smb->Flags & SMBFLG_RESPONSE) + return 0; + + /* only one valid case where server sends us request */ + if (smb->Command == SMB_COM_LOCKING_ANDX) + return 0; + + cERROR(1, "Server sent request, not response. mid=%u", smb->Mid); return 1; } @@ -448,7 +461,7 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length) return 1; } - if (checkSMBhdr(smb, mid)) + if (check_smb_hdr(smb, mid)) return 1; clc_len = smbCalcSize_LE(smb); @@ -465,25 +478,26 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length) if (((4 + len) & 0xFFFF) == (clc_len & 0xFFFF)) return 0; /* bcc wrapped */ } - cFYI(1, "Calculated size %d vs length %d mismatch for mid %d", + cFYI(1, "Calculated size %u vs length %u mismatch for mid=%u", clc_len, 4 + len, smb->Mid); - /* Windows XP can return a few bytes too much, presumably - an illegal pad, at the end of byte range lock responses - so we allow for that three byte pad, as long as actual - received length is as long or longer than calculated length */ - /* We have now had to extend this more, since there is a - case in which it needs to be bigger still to handle a - malformed response to transact2 findfirst from WinXP when - access denied is returned and thus bcc and wct are zero - but server says length is 0x21 bytes too long as if the server - forget to reset the smb rfc1001 length when it reset the - wct and bcc to minimum size and drop the t2 parms and data */ - if ((4+len > clc_len) && (len <= clc_len + 512)) - return 0; - else { - cERROR(1, "RFC1001 size %d bigger than SMB for Mid=%d", + + if (4 + len < clc_len) { + cERROR(1, "RFC1001 size %u smaller than SMB for mid=%u", len, smb->Mid); return 1; + } else if (len > clc_len + 512) { + /* + * Some servers (Windows XP in particular) send more + * data than the lengths in the SMB packet would + * indicate on certain calls (byte range locks and + * trans2 find first calls in particular). While the + * client can handle such a frame by ignoring the + * trailing data, we choose limit the amount of extra + * data to 512 bytes. + */ + cERROR(1, "RFC1001 size %u more than 512 bytes larger " + "than SMB for mid=%u", len, smb->Mid); + return 1; } } return 0; diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 8d9189f..79f641e 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -170,7 +170,7 @@ cifs_convert_address(struct sockaddr *dst, const char *src, int len) { int rc, alen, slen; const char *pct; - char *endp, scope_id[13]; + char scope_id[13]; struct sockaddr_in *s4 = (struct sockaddr_in *) dst; struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) dst; @@ -197,9 +197,9 @@ cifs_convert_address(struct sockaddr *dst, const char *src, int len) memcpy(scope_id, pct + 1, slen); scope_id[slen] = '\0'; - s6->sin6_scope_id = (u32) simple_strtoul(pct, &endp, 0); - if (endp != scope_id + slen) - return 0; + rc = strict_strtoul(scope_id, 0, + (unsigned long *)&s6->sin6_scope_id); + rc = (rc == 0) ? 1 : 0; } return rc; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 7f25cc3..f8e4cd2 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -764,7 +764,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) { int rc = 0; int xid, i; - struct cifs_sb_info *cifs_sb; struct cifsTconInfo *pTcon; struct cifsFileInfo *cifsFile = NULL; char *current_entry; @@ -775,8 +774,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir) xid = GetXid(); - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - /* * Ensure FindFirst doesn't fail before doing filldir() for '.' and * '..'. Otherwise we won't be able to notify VFS in case of failure. diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 1adc962..1676570 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -656,13 +656,13 @@ ssetup_ntlmssp_authenticate: if (type == LANMAN) { #ifdef CONFIG_CIFS_WEAK_PW_HASH - char lnm_session_key[CIFS_SESS_KEY_SIZE]; + char lnm_session_key[CIFS_AUTH_RESP_SIZE]; pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE; /* no capabilities flags in old lanman negotiation */ - pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_SESS_KEY_SIZE); + pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE); /* Calculate hash with password and copy into bcc_ptr. * Encryption Key (stored as in cryptkey) gets used if the @@ -675,8 +675,8 @@ ssetup_ntlmssp_authenticate: true : false, lnm_session_key); ses->flags |= CIFS_SES_LANMAN; - memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_SESS_KEY_SIZE); - bcc_ptr += CIFS_SESS_KEY_SIZE; + memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; /* can not sign if LANMAN negotiated so no need to calculate signing key? but what if server diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index b5450e9..b5041c8 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -58,8 +58,9 @@ mdfour(unsigned char *md4_hash, unsigned char *link_str, int link_len) md4 = crypto_alloc_shash("md4", 0, 0); if (IS_ERR(md4)) { + rc = PTR_ERR(md4); cERROR(1, "%s: Crypto md4 allocation error %d\n", __func__, rc); - return PTR_ERR(md4); + return rc; } size = sizeof(struct shash_desc) + crypto_shash_descsize(md4); sdescmd4 = kmalloc(size, GFP_KERNEL); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index c1ccca1..46d8756f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -236,9 +236,9 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec) server->tcpStatus = CifsNeedReconnect; } - if (rc < 0) { + if (rc < 0 && rc != -EINTR) cERROR(1, "Error %d sending data on socket to server", rc); - } else + else rc = 0; /* Don't want to modify the buffer as a @@ -359,6 +359,10 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_hdr *in_buf, if (rc) return rc; + /* enable signing if server requires it */ + if (server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) + in_buf->Flags2 |= SMBFLG2_SECURITY_SIGNATURE; + mutex_lock(&server->srv_mutex); mid = AllocMidQEntry(in_buf, server); if (mid == NULL) { @@ -453,6 +457,9 @@ sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) case MID_RETRY_NEEDED: rc = -EAGAIN; break; + case MID_RESPONSE_MALFORMED: + rc = -EIO; + break; default: cERROR(1, "%s: invalid mid state mid=%d state=%d", __func__, mid->mid, mid->midState); @@ -570,17 +577,33 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, #endif mutex_unlock(&ses->server->srv_mutex); - cifs_small_buf_release(in_buf); - if (rc < 0) + if (rc < 0) { + cifs_small_buf_release(in_buf); goto out; + } - if (long_op == CIFS_ASYNC_OP) + if (long_op == CIFS_ASYNC_OP) { + cifs_small_buf_release(in_buf); goto out; + } rc = wait_for_response(ses->server, midQ); - if (rc != 0) - goto out; + if (rc != 0) { + send_nt_cancel(ses->server, in_buf, midQ); + spin_lock(&GlobalMid_Lock); + if (midQ->midState == MID_REQUEST_SUBMITTED) { + midQ->callback = DeleteMidQEntry; + spin_unlock(&GlobalMid_Lock); + cifs_small_buf_release(in_buf); + atomic_dec(&ses->server->inFlight); + wake_up(&ses->server->request_q); + return rc; + } + spin_unlock(&GlobalMid_Lock); + } + + cifs_small_buf_release(in_buf); rc = sync_mid_result(midQ, ses->server); if (rc != 0) { @@ -724,8 +747,19 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses, goto out; rc = wait_for_response(ses->server, midQ); - if (rc != 0) - goto out; + if (rc != 0) { + send_nt_cancel(ses->server, in_buf, midQ); + spin_lock(&GlobalMid_Lock); + if (midQ->midState == MID_REQUEST_SUBMITTED) { + /* no longer considered to be "in-flight" */ + midQ->callback = DeleteMidQEntry; + spin_unlock(&GlobalMid_Lock); + atomic_dec(&ses->server->inFlight); + wake_up(&ses->server->request_q); + return rc; + } + spin_unlock(&GlobalMid_Lock); + } rc = sync_mid_result(midQ, ses->server); if (rc != 0) { @@ -922,10 +956,21 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon, } } - if (wait_for_response(ses->server, midQ) == 0) { - /* We got the response - restart system call. */ - rstart = 1; + rc = wait_for_response(ses->server, midQ); + if (rc) { + send_nt_cancel(ses->server, in_buf, midQ); + spin_lock(&GlobalMid_Lock); + if (midQ->midState == MID_REQUEST_SUBMITTED) { + /* no longer considered to be "in-flight" */ + midQ->callback = DeleteMidQEntry; + spin_unlock(&GlobalMid_Lock); + return rc; + } + spin_unlock(&GlobalMid_Lock); } + + /* We got the response - restart system call. */ + rstart = 1; } rc = sync_mid_result(midQ, ses->server); diff --git a/fs/compat.c b/fs/compat.c index f6fd0a0..c6d31a3 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -262,35 +262,19 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * */ asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf) { - struct path path; - int error; - - error = user_path(pathname, &path); - if (!error) { - struct kstatfs tmp; - error = vfs_statfs(&path, &tmp); - if (!error) - error = put_compat_statfs(buf, &tmp); - path_put(&path); - } + struct kstatfs tmp; + int error = user_statfs(pathname, &tmp); + if (!error) + error = put_compat_statfs(buf, &tmp); return error; } asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf) { - struct file * file; struct kstatfs tmp; - int error; - - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = vfs_statfs(&file->f_path, &tmp); + int error = fd_statfs(fd, &tmp); if (!error) error = put_compat_statfs(buf, &tmp); - fput(file); -out: return error; } @@ -329,41 +313,29 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf) { - struct path path; + struct kstatfs tmp; int error; if (sz != sizeof(*buf)) return -EINVAL; - error = user_path(pathname, &path); - if (!error) { - struct kstatfs tmp; - error = vfs_statfs(&path, &tmp); - if (!error) - error = put_compat_statfs64(buf, &tmp); - path_put(&path); - } + error = user_statfs(pathname, &tmp); + if (!error) + error = put_compat_statfs64(buf, &tmp); return error; } asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf) { - struct file * file; struct kstatfs tmp; int error; if (sz != sizeof(*buf)) return -EINVAL; - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = vfs_statfs(&file->f_path, &tmp); + error = fd_statfs(fd, &tmp); if (!error) error = put_compat_statfs64(buf, &tmp); - fput(file); -out: return error; } @@ -1228,7 +1200,9 @@ compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, file = fget_light(fd, &fput_needed); if (!file) return -EBADF; - ret = compat_readv(file, vec, vlen, &pos); + ret = -ESPIPE; + if (file->f_mode & FMODE_PREAD) + ret = compat_readv(file, vec, vlen, &pos); fput_light(file, fput_needed); return ret; } @@ -1285,7 +1259,9 @@ compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, file = fget_light(fd, &fput_needed); if (!file) return -EBADF; - ret = compat_writev(file, vec, vlen, &pos); + ret = -ESPIPE; + if (file->f_mode & FMODE_PWRITE) + ret = compat_writev(file, vec, vlen, &pos); fput_light(file, fput_needed); return ret; } @@ -2308,3 +2284,16 @@ asmlinkage long compat_sys_timerfd_gettime(int ufd, } #endif /* CONFIG_TIMERFD */ + +#ifdef CONFIG_FHANDLE +/* + * Exactly like fs/open.c:sys_open_by_handle_at(), except that it + * doesn't set the O_LARGEFILE flag. + */ +asmlinkage long +compat_sys_open_by_handle_at(int mountdirfd, + struct file_handle __user *handle, int flags) +{ + return do_handle_open(mountdirfd, handle, flags); +} +#endif diff --git a/fs/dcache.c b/fs/dcache.c index 2a6bd9a4..a39fe47 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -296,8 +296,12 @@ static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) __releases(parent->d_lock) __releases(dentry->d_inode->i_lock) { - dentry->d_parent = NULL; list_del(&dentry->d_u.d_child); + /* + * Inform try_to_ascend() that we are no longer attached to the + * dentry tree + */ + dentry->d_flags |= DCACHE_DISCONNECTED; if (parent) spin_unlock(&parent->d_lock); dentry_iput(dentry); @@ -1012,6 +1016,35 @@ void shrink_dcache_for_umount(struct super_block *sb) } /* + * This tries to ascend one level of parenthood, but + * we can race with renaming, so we need to re-check + * the parenthood after dropping the lock and check + * that the sequence number still matches. + */ +static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq) +{ + struct dentry *new = old->d_parent; + + rcu_read_lock(); + spin_unlock(&old->d_lock); + spin_lock(&new->d_lock); + + /* + * might go back up the wrong parent if we have had a rename + * or deletion + */ + if (new != old->d_parent || + (old->d_flags & DCACHE_DISCONNECTED) || + (!locked && read_seqretry(&rename_lock, seq))) { + spin_unlock(&new->d_lock); + new = NULL; + } + rcu_read_unlock(); + return new; +} + + +/* * Search for at least 1 mount point in the dentry's subdirs. * We descend to the next level whenever the d_subdirs * list is non-empty and continue searching. @@ -1066,24 +1099,10 @@ resume: * All done at this level ... ascend and resume the search. */ if (this_parent != parent) { - struct dentry *tmp; - struct dentry *child; - - tmp = this_parent->d_parent; - rcu_read_lock(); - spin_unlock(&this_parent->d_lock); - child = this_parent; - this_parent = tmp; - spin_lock(&this_parent->d_lock); - /* might go back up the wrong parent if we have had a rename - * or deletion */ - if (this_parent != child->d_parent || - (!locked && read_seqretry(&rename_lock, seq))) { - spin_unlock(&this_parent->d_lock); - rcu_read_unlock(); + struct dentry *child = this_parent; + this_parent = try_to_ascend(this_parent, locked, seq); + if (!this_parent) goto rename_retry; - } - rcu_read_unlock(); next = child->d_u.d_child.next; goto resume; } @@ -1181,24 +1200,10 @@ resume: * All done at this level ... ascend and resume the search. */ if (this_parent != parent) { - struct dentry *tmp; - struct dentry *child; - - tmp = this_parent->d_parent; - rcu_read_lock(); - spin_unlock(&this_parent->d_lock); - child = this_parent; - this_parent = tmp; - spin_lock(&this_parent->d_lock); - /* might go back up the wrong parent if we have had a rename - * or deletion */ - if (this_parent != child->d_parent || - (!locked && read_seqretry(&rename_lock, seq))) { - spin_unlock(&this_parent->d_lock); - rcu_read_unlock(); + struct dentry *child = this_parent; + this_parent = try_to_ascend(this_parent, locked, seq); + if (!this_parent) goto rename_retry; - } - rcu_read_unlock(); next = child->d_u.d_child.next; goto resume; } @@ -1523,6 +1528,28 @@ struct dentry * d_alloc_root(struct inode * root_inode) } EXPORT_SYMBOL(d_alloc_root); +static struct dentry * __d_find_any_alias(struct inode *inode) +{ + struct dentry *alias; + + if (list_empty(&inode->i_dentry)) + return NULL; + alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias); + __dget(alias); + return alias; +} + +static struct dentry * d_find_any_alias(struct inode *inode) +{ + struct dentry *de; + + spin_lock(&inode->i_lock); + de = __d_find_any_alias(inode); + spin_unlock(&inode->i_lock); + return de; +} + + /** * d_obtain_alias - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for @@ -1552,7 +1579,7 @@ struct dentry *d_obtain_alias(struct inode *inode) if (IS_ERR(inode)) return ERR_CAST(inode); - res = d_find_alias(inode); + res = d_find_any_alias(inode); if (res) goto out_iput; @@ -1565,7 +1592,7 @@ struct dentry *d_obtain_alias(struct inode *inode) spin_lock(&inode->i_lock); - res = __d_find_alias(inode, 0); + res = __d_find_any_alias(inode); if (res) { spin_unlock(&inode->i_lock); dput(tmp); @@ -2920,28 +2947,14 @@ resume: spin_unlock(&dentry->d_lock); } if (this_parent != root) { - struct dentry *tmp; - struct dentry *child; - - tmp = this_parent->d_parent; + struct dentry *child = this_parent; if (!(this_parent->d_flags & DCACHE_GENOCIDE)) { this_parent->d_flags |= DCACHE_GENOCIDE; this_parent->d_count--; } - rcu_read_lock(); - spin_unlock(&this_parent->d_lock); - child = this_parent; - this_parent = tmp; - spin_lock(&this_parent->d_lock); - /* might go back up the wrong parent if we have had a rename - * or deletion */ - if (this_parent != child->d_parent || - (!locked && read_seqretry(&rename_lock, seq))) { - spin_unlock(&this_parent->d_lock); - rcu_read_unlock(); + this_parent = try_to_ascend(this_parent, locked, seq); + if (!this_parent) goto rename_retry; - } - rcu_read_unlock(); next = child->d_u.d_child.next; goto resume; } diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 9c64ae9..2d8c87b 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1468,15 +1468,13 @@ static void work_stop(void) static int work_start(void) { - recv_workqueue = alloc_workqueue("dlm_recv", WQ_MEM_RECLAIM | - WQ_HIGHPRI | WQ_FREEZEABLE, 0); + recv_workqueue = create_singlethread_workqueue("dlm_recv"); if (!recv_workqueue) { log_print("can't start dlm_recv"); return -ENOMEM; } - send_workqueue = alloc_workqueue("dlm_send", WQ_MEM_RECLAIM | - WQ_HIGHPRI | WQ_FREEZEABLE, 0); + send_workqueue = create_singlethread_workqueue("dlm_send"); if (!send_workqueue) { log_print("can't start dlm_send"); destroy_workqueue(recv_workqueue); diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index 6fc4f31..534c1d4 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -46,24 +46,28 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd) { struct dentry *lower_dentry; struct vfsmount *lower_mnt; - struct dentry *dentry_save; - struct vfsmount *vfsmount_save; + struct dentry *dentry_save = NULL; + struct vfsmount *vfsmount_save = NULL; int rc = 1; - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; lower_dentry = ecryptfs_dentry_to_lower(dentry); lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry); if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate) goto out; - dentry_save = nd->path.dentry; - vfsmount_save = nd->path.mnt; - nd->path.dentry = lower_dentry; - nd->path.mnt = lower_mnt; + if (nd) { + dentry_save = nd->path.dentry; + vfsmount_save = nd->path.mnt; + nd->path.dentry = lower_dentry; + nd->path.mnt = lower_mnt; + } rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd); - nd->path.dentry = dentry_save; - nd->path.mnt = vfsmount_save; + if (nd) { + nd->path.dentry = dentry_save; + nd->path.mnt = vfsmount_save; + } if (dentry->d_inode) { struct inode *lower_inode = ecryptfs_inode_to_lower(dentry->d_inode); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index dbc84ed..e007534 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -632,8 +632,7 @@ int ecryptfs_interpose(struct dentry *hidden_dentry, u32 flags); int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, struct dentry *lower_dentry, - struct inode *ecryptfs_dir_inode, - struct nameidata *ecryptfs_nd); + struct inode *ecryptfs_dir_inode); int ecryptfs_decode_and_decrypt_filename(char **decrypted_name, size_t *decrypted_name_size, struct dentry *ecryptfs_dentry, diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 81e10e6..7d1050e 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -317,6 +317,7 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations ecryptfs_dir_fops = { .readdir = ecryptfs_readdir, + .read = generic_read_dir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ecryptfs_compat_ioctl, diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index bd33f87..b592938 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -74,16 +74,20 @@ ecryptfs_create_underlying_file(struct inode *lower_dir_inode, unsigned int flags_save; int rc; - dentry_save = nd->path.dentry; - vfsmount_save = nd->path.mnt; - flags_save = nd->flags; - nd->path.dentry = lower_dentry; - nd->path.mnt = lower_mnt; - nd->flags &= ~LOOKUP_OPEN; + if (nd) { + dentry_save = nd->path.dentry; + vfsmount_save = nd->path.mnt; + flags_save = nd->flags; + nd->path.dentry = lower_dentry; + nd->path.mnt = lower_mnt; + nd->flags &= ~LOOKUP_OPEN; + } rc = vfs_create(lower_dir_inode, lower_dentry, mode, nd); - nd->path.dentry = dentry_save; - nd->path.mnt = vfsmount_save; - nd->flags = flags_save; + if (nd) { + nd->path.dentry = dentry_save; + nd->path.mnt = vfsmount_save; + nd->flags = flags_save; + } return rc; } @@ -241,8 +245,7 @@ out: */ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, struct dentry *lower_dentry, - struct inode *ecryptfs_dir_inode, - struct nameidata *ecryptfs_nd) + struct inode *ecryptfs_dir_inode) { struct dentry *lower_dir_dentry; struct vfsmount *lower_mnt; @@ -290,8 +293,6 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry, goto out; if (special_file(lower_inode->i_mode)) goto out; - if (!ecryptfs_nd) - goto out; /* Released in this function */ page_virt = kmem_cache_zalloc(ecryptfs_header_cache_2, GFP_USER); if (!page_virt) { @@ -349,75 +350,6 @@ out: } /** - * ecryptfs_new_lower_dentry - * @name: The name of the new dentry. - * @lower_dir_dentry: Parent directory of the new dentry. - * @nd: nameidata from last lookup. - * - * Create a new dentry or get it from lower parent dir. - */ -static struct dentry * -ecryptfs_new_lower_dentry(struct qstr *name, struct dentry *lower_dir_dentry, - struct nameidata *nd) -{ - struct dentry *new_dentry; - struct dentry *tmp; - struct inode *lower_dir_inode; - - lower_dir_inode = lower_dir_dentry->d_inode; - - tmp = d_alloc(lower_dir_dentry, name); - if (!tmp) - return ERR_PTR(-ENOMEM); - - mutex_lock(&lower_dir_inode->i_mutex); - new_dentry = lower_dir_inode->i_op->lookup(lower_dir_inode, tmp, nd); - mutex_unlock(&lower_dir_inode->i_mutex); - - if (!new_dentry) - new_dentry = tmp; - else - dput(tmp); - - return new_dentry; -} - - -/** - * ecryptfs_lookup_one_lower - * @ecryptfs_dentry: The eCryptfs dentry that we are looking up - * @lower_dir_dentry: lower parent directory - * @name: lower file name - * - * Get the lower dentry from vfs. If lower dentry does not exist yet, - * create it. - */ -static struct dentry * -ecryptfs_lookup_one_lower(struct dentry *ecryptfs_dentry, - struct dentry *lower_dir_dentry, struct qstr *name) -{ - struct nameidata nd; - struct vfsmount *lower_mnt; - int err; - - lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt( - ecryptfs_dentry->d_parent)); - err = vfs_path_lookup(lower_dir_dentry, lower_mnt, name->name , 0, &nd); - mntput(lower_mnt); - - if (!err) { - /* we dont need the mount */ - mntput(nd.path.mnt); - return nd.path.dentry; - } - if (err != -ENOENT) - return ERR_PTR(err); - - /* create a new lower dentry */ - return ecryptfs_new_lower_dentry(name, lower_dir_dentry, &nd); -} - -/** * ecryptfs_lookup * @ecryptfs_dir_inode: The eCryptfs directory inode * @ecryptfs_dentry: The eCryptfs dentry that we are looking up @@ -434,7 +366,6 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, size_t encrypted_and_encoded_name_size; struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL; struct dentry *lower_dir_dentry, *lower_dentry; - struct qstr lower_name; int rc = 0; if ((ecryptfs_dentry->d_name.len == 1 @@ -444,20 +375,14 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, goto out_d_drop; } lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent); - lower_name.name = ecryptfs_dentry->d_name.name; - lower_name.len = ecryptfs_dentry->d_name.len; - lower_name.hash = ecryptfs_dentry->d_name.hash; - if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) { - rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry, - lower_dir_dentry->d_inode, &lower_name); - if (rc < 0) - goto out_d_drop; - } - lower_dentry = ecryptfs_lookup_one_lower(ecryptfs_dentry, - lower_dir_dentry, &lower_name); + mutex_lock(&lower_dir_dentry->d_inode->i_mutex); + lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name, + lower_dir_dentry, + ecryptfs_dentry->d_name.len); + mutex_unlock(&lower_dir_dentry->d_inode->i_mutex); if (IS_ERR(lower_dentry)) { rc = PTR_ERR(lower_dentry); - ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_lower() returned " + ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " "[%d] on lower_dentry = [%s]\n", __func__, rc, encrypted_and_encoded_name); goto out_d_drop; @@ -479,28 +404,21 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, "filename; rc = [%d]\n", __func__, rc); goto out_d_drop; } - lower_name.name = encrypted_and_encoded_name; - lower_name.len = encrypted_and_encoded_name_size; - lower_name.hash = full_name_hash(lower_name.name, lower_name.len); - if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) { - rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry, - lower_dir_dentry->d_inode, &lower_name); - if (rc < 0) - goto out_d_drop; - } - lower_dentry = ecryptfs_lookup_one_lower(ecryptfs_dentry, - lower_dir_dentry, &lower_name); + mutex_lock(&lower_dir_dentry->d_inode->i_mutex); + lower_dentry = lookup_one_len(encrypted_and_encoded_name, + lower_dir_dentry, + encrypted_and_encoded_name_size); + mutex_unlock(&lower_dir_dentry->d_inode->i_mutex); if (IS_ERR(lower_dentry)) { rc = PTR_ERR(lower_dentry); - ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_lower() returned " + ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " "[%d] on lower_dentry = [%s]\n", __func__, rc, encrypted_and_encoded_name); goto out_d_drop; } lookup_and_interpose: rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry, - ecryptfs_dir_inode, - ecryptfs_nd); + ecryptfs_dir_inode); goto out; out_d_drop: d_drop(ecryptfs_dentry); @@ -1092,6 +1010,8 @@ int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry, rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry), ecryptfs_dentry_to_lower(dentry), &lower_stat); if (!rc) { + fsstack_copy_attr_all(dentry->d_inode, + ecryptfs_inode_to_lower(dentry->d_inode)); generic_fillattr(dentry->d_inode, stat); stat->blocks = lower_stat.blocks; } diff --git a/fs/eventfd.c b/fs/eventfd.c index e0194b3..d9a5917 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -99,7 +99,7 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_get); * @ctx: [in] Pointer to eventfd context. * * The eventfd context reference must have been previously acquired either - * with eventfd_ctx_get() or eventfd_ctx_fdget()). + * with eventfd_ctx_get() or eventfd_ctx_fdget(). */ void eventfd_ctx_put(struct eventfd_ctx *ctx) { @@ -146,9 +146,9 @@ static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. * @ctx: [in] Pointer to eventfd context. * @wait: [in] Wait queue to be removed. - * @cnt: [out] Pointer to the 64bit conter value. + * @cnt: [out] Pointer to the 64-bit counter value. * - * Returns zero if successful, or the following error codes: + * Returns %0 if successful, or the following error codes: * * -EAGAIN : The operation would have blocked. * @@ -175,11 +175,11 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue); * eventfd_ctx_read - Reads the eventfd counter or wait if it is zero. * @ctx: [in] Pointer to eventfd context. * @no_wait: [in] Different from zero if the operation should not block. - * @cnt: [out] Pointer to the 64bit conter value. + * @cnt: [out] Pointer to the 64-bit counter value. * - * Returns zero if successful, or the following error codes: + * Returns %0 if successful, or the following error codes: * - * -EAGAIN : The operation would have blocked but @no_wait was nonzero. + * -EAGAIN : The operation would have blocked but @no_wait was non-zero. * -ERESTARTSYS : A signal interrupted the wait operation. * * If @no_wait is zero, the function might sleep until the eventfd internal diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cc8a9b7..4a09af9 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -63,6 +63,13 @@ * cleanup path and it is also acquired by eventpoll_release_file() * if a file has been pushed inside an epoll set and it is then * close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL). + * It is also acquired when inserting an epoll fd onto another epoll + * fd. We do this so that we walk the epoll tree and ensure that this + * insertion does not create a cycle of epoll file descriptors, which + * could lead to deadlock. We need a global mutex to prevent two + * simultaneous inserts (A into B and B into A) from racing and + * constructing a cycle without either insert observing that it is + * going to. * It is possible to drop the "ep->mtx" and to use the global * mutex "epmutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. @@ -224,6 +231,9 @@ static long max_user_watches __read_mostly; */ static DEFINE_MUTEX(epmutex); +/* Used to check for epoll file descriptor inclusion loops */ +static struct nested_calls poll_loop_ncalls; + /* Used for safe wake up implementation */ static struct nested_calls poll_safewake_ncalls; @@ -1114,6 +1124,17 @@ static int ep_send_events(struct eventpoll *ep, return ep_scan_ready_list(ep, ep_send_events_proc, &esed); } +static inline struct timespec ep_set_mstimeout(long ms) +{ + struct timespec now, ts = { + .tv_sec = ms / MSEC_PER_SEC, + .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC), + }; + + ktime_get_ts(&now); + return timespec_add_safe(now, ts); +} + static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, long timeout) { @@ -1121,12 +1142,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, unsigned long flags; long slack; wait_queue_t wait; - struct timespec end_time; ktime_t expires, *to = NULL; if (timeout > 0) { - ktime_get_ts(&end_time); - timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC); + struct timespec end_time = ep_set_mstimeout(timeout); + slack = select_estimate_accuracy(&end_time); to = &expires; *to = timespec_to_ktime(end_time); @@ -1188,6 +1208,62 @@ retry: return res; } +/** + * ep_loop_check_proc - Callback function to be passed to the @ep_call_nested() + * API, to verify that adding an epoll file inside another + * epoll structure, does not violate the constraints, in + * terms of closed loops, or too deep chains (which can + * result in excessive stack usage). + * + * @priv: Pointer to the epoll file to be currently checked. + * @cookie: Original cookie for this call. This is the top-of-the-chain epoll + * data structure pointer. + * @call_nests: Current dept of the @ep_call_nested() call stack. + * + * Returns: Returns zero if adding the epoll @file inside current epoll + * structure @ep does not violate the constraints, or -1 otherwise. + */ +static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) +{ + int error = 0; + struct file *file = priv; + struct eventpoll *ep = file->private_data; + struct rb_node *rbp; + struct epitem *epi; + + mutex_lock(&ep->mtx); + for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + epi = rb_entry(rbp, struct epitem, rbn); + if (unlikely(is_file_epoll(epi->ffd.file))) { + error = ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + ep_loop_check_proc, epi->ffd.file, + epi->ffd.file->private_data, current); + if (error != 0) + break; + } + } + mutex_unlock(&ep->mtx); + + return error; +} + +/** + * ep_loop_check - Performs a check to verify that adding an epoll file (@file) + * another epoll file (represented by @ep) does not create + * closed loops or too deep chains. + * + * @ep: Pointer to the epoll private data structure. + * @file: Pointer to the epoll file to be checked. + * + * Returns: Returns zero if adding the epoll @file inside current epoll + * structure @ep does not violate the constraints, or -1 otherwise. + */ +static int ep_loop_check(struct eventpoll *ep, struct file *file) +{ + return ep_call_nested(&poll_loop_ncalls, EP_MAX_NESTS, + ep_loop_check_proc, file, ep, current); +} + /* * Open an eventpoll file descriptor. */ @@ -1236,6 +1312,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { int error; + int did_lock_epmutex = 0; struct file *file, *tfile; struct eventpoll *ep; struct epitem *epi; @@ -1277,6 +1354,25 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, */ ep = file->private_data; + /* + * When we insert an epoll file descriptor, inside another epoll file + * descriptor, there is the change of creating closed loops, which are + * better be handled here, than in more critical paths. + * + * We hold epmutex across the loop check and the insert in this case, in + * order to prevent two separate inserts from racing and each doing the + * insert "at the same time" such that ep_loop_check passes on both + * before either one does the insert, thereby creating a cycle. + */ + if (unlikely(is_file_epoll(tfile) && op == EPOLL_CTL_ADD)) { + mutex_lock(&epmutex); + did_lock_epmutex = 1; + error = -ELOOP; + if (ep_loop_check(ep, tfile) != 0) + goto error_tgt_fput; + } + + mutex_lock(&ep->mtx); /* @@ -1312,6 +1408,9 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, mutex_unlock(&ep->mtx); error_tgt_fput: + if (unlikely(did_lock_epmutex)) + mutex_unlock(&epmutex); + fput(tfile); error_fput: fput(file); @@ -1431,6 +1530,12 @@ static int __init eventpoll_init(void) EP_ITEM_COST; BUG_ON(max_user_watches < 0); + /* + * Initialize the structure used to perform epoll file descriptor + * inclusion loops checks. + */ + ep_nested_calls_init(&poll_loop_ncalls); + /* Initialize the structure used to perform safe poll wait head wake ups */ ep_nested_calls_init(&poll_safewake_ncalls); @@ -115,13 +115,16 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) struct file *file; char *tmp = getname(library); int error = PTR_ERR(tmp); + static const struct open_flags uselib_flags = { + .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, + .acc_mode = MAY_READ | MAY_EXEC | MAY_OPEN, + .intent = LOOKUP_OPEN + }; if (IS_ERR(tmp)) goto out; - file = do_filp_open(AT_FDCWD, tmp, - O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, - MAY_READ | MAY_EXEC | MAY_OPEN); + file = do_filp_open(AT_FDCWD, tmp, &uselib_flags, LOOKUP_FOLLOW); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) @@ -721,10 +724,13 @@ struct file *open_exec(const char *name) { struct file *file; int err; + static const struct open_flags open_exec_flags = { + .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, + .acc_mode = MAY_EXEC | MAY_OPEN, + .intent = LOOKUP_OPEN + }; - file = do_filp_open(AT_FDCWD, name, - O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0, - MAY_EXEC | MAY_OPEN); + file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW); if (IS_ERR(file)) goto out; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 4268542..a755523 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1030,7 +1030,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data)); } - inode->i_mapping->backing_dev_info = sb->s_bdi; if (S_ISREG(inode->i_mode)) { inode->i_op = &exofs_file_inode_operations; inode->i_fop = &exofs_file_operations; @@ -1131,7 +1130,6 @@ struct inode *exofs_new_inode(struct inode *dir, int mode) sbi = sb->s_fs_info; - inode->i_mapping->backing_dev_info = sb->s_bdi; sb->s_dirt = 1; inode_init_owner(inode, dir, mode); inode->i_ino = sbi->s_nextid++; diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index 264e95d..4d70db1 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -272,7 +272,6 @@ static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry, new_de = exofs_find_entry(new_dir, new_dentry, &new_page); if (!new_de) goto out_dir; - inode_inc_link_count(old_inode); err = exofs_set_link(new_dir, new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME; if (dir_de) @@ -286,12 +285,9 @@ static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dir->i_nlink >= EXOFS_LINK_MAX) goto out_dir; } - inode_inc_link_count(old_inode); err = exofs_add_link(new_dentry, old_inode); - if (err) { - inode_dec_link_count(old_inode); + if (err) goto out_dir; - } if (dir_de) inode_inc_link_count(new_dir); } @@ -299,7 +295,7 @@ static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry, old_inode->i_ctime = CURRENT_TIME; exofs_delete_entry(old_de, old_page); - inode_dec_link_count(old_inode); + mark_inode_dirty(old_inode); if (dir_de) { err = exofs_set_link(old_inode, dir_de, dir_page, new_dir); diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 4b68257..b05acb7 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -320,9 +320,14 @@ static int export_encode_fh(struct dentry *dentry, struct fid *fid, struct inode * inode = dentry->d_inode; int len = *max_len; int type = FILEID_INO32_GEN; - - if (len < 2 || (connectable && len < 4)) + + if (connectable && (len < 4)) { + *max_len = 4; + return 255; + } else if (len < 2) { + *max_len = 2; return 255; + } len = 2; fid->i32.ino = inode->i_ino; @@ -369,6 +374,8 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, /* * Try to get any dentry for the given file handle from the filesystem. */ + if (!nop || !nop->fh_to_dentry) + return ERR_PTR(-ESTALE); result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type); if (!result) result = ERR_PTR(-ESTALE); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 2e1d834..adb9185 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -344,7 +344,6 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page); if (!new_de) goto out_dir; - inode_inc_link_count(old_inode); ext2_set_link(new_dir, new_de, new_page, old_inode, 1); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) @@ -356,12 +355,9 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, if (new_dir->i_nlink >= EXT2_LINK_MAX) goto out_dir; } - inode_inc_link_count(old_inode); err = ext2_add_link(new_dentry, old_inode); - if (err) { - inode_dec_link_count(old_inode); + if (err) goto out_dir; - } if (dir_de) inode_inc_link_count(new_dir); } @@ -369,12 +365,11 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, /* * Like most other Unix systems, set the ctime for inodes on a * rename. - * inode_dec_link_count() will mark the inode dirty. */ old_inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(old_inode); ext2_delete_entry (old_de, old_page); - inode_dec_link_count(old_inode); if (dir_de) { if (old_dir != new_dir) diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index b27ba71..561f692 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -2253,13 +2253,6 @@ static int ext3_link (struct dentry * old_dentry, dquot_initialize(dir); - /* - * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing - * otherwise has the potential to corrupt the orphan inode list. - */ - if (inode->i_nlink == 0) - return -ENOENT; - retry: handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) + EXT3_INDEX_EXTRA_TRANS_BLOCKS); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 85c8cc8..9cc19a1d 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -1936,6 +1936,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sb->s_qcop = &ext3_qctl_operations; sb->dq_op = &ext3_quota_operations; #endif + memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); mutex_init(&sbi->s_resize_lock); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0c8d97b..3aa0b72 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -848,6 +848,7 @@ struct ext4_inode_info { atomic_t i_ioend_count; /* Number of outstanding io_end structs */ /* current io_end structure for async DIO write*/ ext4_io_end_t *cur_aio_dio; + atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */ spinlock_t i_block_reservation_lock; @@ -2119,6 +2120,15 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) +/* For ioend & aio unwritten conversion wait queues */ +#define EXT4_WQ_HASH_SZ 37 +#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\ + EXT4_WQ_HASH_SZ]) +#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\ + EXT4_WQ_HASH_SZ]) +extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; +extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; + #endif /* __KERNEL__ */ #endif /* _EXT4_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 63a7581..ccce8a7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3174,9 +3174,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, * that this IO needs to convertion to written when IO is * completed */ - if (io) + if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) { io->flag = EXT4_IO_END_UNWRITTEN; - else + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); if (ext4_should_dioread_nolock(inode)) map->m_flags |= EXT4_MAP_UNINIT; @@ -3463,9 +3464,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * that we need to perform convertion when IO is done. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - if (io) + if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) { io->flag = EXT4_IO_END_UNWRITTEN; - else + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2e8322c..7b80d54 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -55,11 +55,47 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } +static void ext4_aiodio_wait(struct inode *inode) +{ + wait_queue_head_t *wq = ext4_ioend_wq(inode); + + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0)); +} + +/* + * This tests whether the IO in question is block-aligned or not. + * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they + * are converted to written only after the IO is complete. Until they are + * mapped, these blocks appear as holes, so dio_zero_block() will assume that + * it needs to zero out portions of the start and/or end block. If 2 AIO + * threads are at work on the same unwritten block, they must be synchronized + * or one thread will zero the other's data, causing corruption. + */ +static int +ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct super_block *sb = inode->i_sb; + int blockmask = sb->s_blocksize - 1; + size_t count = iov_length(iov, nr_segs); + loff_t final_size = pos + count; + + if (pos >= inode->i_size) + return 0; + + if ((pos & blockmask) || (final_size & blockmask)) + return 1; + + return 0; +} + static ssize_t ext4_file_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; + int unaligned_aio = 0; + int ret; /* * If we have encountered a bitmap-format file, the size limit @@ -78,9 +114,31 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, nr_segs = iov_shorten((struct iovec *)iov, nr_segs, sbi->s_bitmap_maxbytes - pos); } + } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) && + !is_sync_kiocb(iocb))) { + unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); } - return generic_file_aio_write(iocb, iov, nr_segs, pos); + /* Unaligned direct AIO must be serialized; see comment above */ + if (unaligned_aio) { + static unsigned long unaligned_warn_time; + + /* Warn about this once per day */ + if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) + ext4_msg(inode->i_sb, KERN_WARNING, + "Unaligned AIO/DIO on inode %ld by %s; " + "performance will be poor.", + inode->i_ino, current->comm); + mutex_lock(ext4_aio_mutex(inode)); + ext4_aiodio_wait(inode); + } + + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); + + if (unaligned_aio) + mutex_unlock(ext4_aio_mutex(inode)); + + return ret; } static const struct vm_operations_struct ext4_file_vm_ops = { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 851f49b..d1fe09a 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -342,10 +342,15 @@ static struct kmem_cache *ext4_free_ext_cachep; /* We create slab caches for groupinfo data structures based on the * superblock block size. There will be one per mounted filesystem for * each unique s_blocksize_bits */ -#define NR_GRPINFO_CACHES \ - (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1) +#define NR_GRPINFO_CACHES 8 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; +static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { + "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k", + "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k", + "ext4_groupinfo_64k", "ext4_groupinfo_128k" +}; + static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, @@ -2414,6 +2419,55 @@ err_freesgi: return -ENOMEM; } +static void ext4_groupinfo_destroy_slabs(void) +{ + int i; + + for (i = 0; i < NR_GRPINFO_CACHES; i++) { + if (ext4_groupinfo_caches[i]) + kmem_cache_destroy(ext4_groupinfo_caches[i]); + ext4_groupinfo_caches[i] = NULL; + } +} + +static int ext4_groupinfo_create_slab(size_t size) +{ + static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex); + int slab_size; + int blocksize_bits = order_base_2(size); + int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; + struct kmem_cache *cachep; + + if (cache_index >= NR_GRPINFO_CACHES) + return -EINVAL; + + if (unlikely(cache_index < 0)) + cache_index = 0; + + mutex_lock(&ext4_grpinfo_slab_create_mutex); + if (ext4_groupinfo_caches[cache_index]) { + mutex_unlock(&ext4_grpinfo_slab_create_mutex); + return 0; /* Already created */ + } + + slab_size = offsetof(struct ext4_group_info, + bb_counters[blocksize_bits + 2]); + + cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index], + slab_size, 0, SLAB_RECLAIM_ACCOUNT, + NULL); + + mutex_unlock(&ext4_grpinfo_slab_create_mutex); + if (!cachep) { + printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n"); + return -ENOMEM; + } + + ext4_groupinfo_caches[cache_index] = cachep; + + return 0; +} + int ext4_mb_init(struct super_block *sb, int needs_recovery) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -2421,9 +2475,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) unsigned offset; unsigned max; int ret; - int cache_index; - struct kmem_cache *cachep; - char *namep = NULL; i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); @@ -2440,30 +2491,9 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) goto out; } - cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; - cachep = ext4_groupinfo_caches[cache_index]; - if (!cachep) { - char name[32]; - int len = offsetof(struct ext4_group_info, - bb_counters[sb->s_blocksize_bits + 2]); - - sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits); - namep = kstrdup(name, GFP_KERNEL); - if (!namep) { - ret = -ENOMEM; - goto out; - } - - /* Need to free the kmem_cache_name() when we - * destroy the slab */ - cachep = kmem_cache_create(namep, len, 0, - SLAB_RECLAIM_ACCOUNT, NULL); - if (!cachep) { - ret = -ENOMEM; - goto out; - } - ext4_groupinfo_caches[cache_index] = cachep; - } + ret = ext4_groupinfo_create_slab(sb->s_blocksize); + if (ret < 0) + goto out; /* order 0 is regular bitmap */ sbi->s_mb_maxs[0] = sb->s_blocksize << 3; @@ -2520,7 +2550,6 @@ out: if (ret) { kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); - kfree(namep); } return ret; } @@ -2734,7 +2763,6 @@ int __init ext4_init_mballoc(void) void ext4_exit_mballoc(void) { - int i; /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. @@ -2743,15 +2771,7 @@ void ext4_exit_mballoc(void) kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); - - for (i = 0; i < NR_GRPINFO_CACHES; i++) { - struct kmem_cache *cachep = ext4_groupinfo_caches[i]; - if (cachep) { - char *name = (char *)kmem_cache_name(cachep); - kmem_cache_destroy(cachep); - kfree(name); - } - } + ext4_groupinfo_destroy_slabs(); ext4_remove_debugfs_entry(); } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5485390..e781b7e 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2304,13 +2304,6 @@ static int ext4_link(struct dentry *old_dentry, dquot_initialize(dir); - /* - * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing - * otherwise has the potential to corrupt the orphan inode list. - */ - if (inode->i_nlink == 0) - return -ENOENT; - retry: handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) + EXT4_INDEX_EXTRA_TRANS_BLOCKS); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 7270dcf..955cc30 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -32,14 +32,8 @@ static struct kmem_cache *io_page_cachep, *io_end_cachep; -#define WQ_HASH_SZ 37 -#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ]) -static wait_queue_head_t ioend_wq[WQ_HASH_SZ]; - int __init ext4_init_pageio(void) { - int i; - io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT); if (io_page_cachep == NULL) return -ENOMEM; @@ -48,9 +42,6 @@ int __init ext4_init_pageio(void) kmem_cache_destroy(io_page_cachep); return -ENOMEM; } - for (i = 0; i < WQ_HASH_SZ; i++) - init_waitqueue_head(&ioend_wq[i]); - return 0; } @@ -62,7 +53,7 @@ void ext4_exit_pageio(void) void ext4_ioend_wait(struct inode *inode) { - wait_queue_head_t *wq = to_ioend_wq(inode); + wait_queue_head_t *wq = ext4_ioend_wq(inode); wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0)); } @@ -87,7 +78,7 @@ void ext4_free_io_end(ext4_io_end_t *io) for (i = 0; i < io->num_io_pages; i++) put_io_page(io->pages[i]); io->num_io_pages = 0; - wq = to_ioend_wq(io->inode); + wq = ext4_ioend_wq(io->inode); if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) && waitqueue_active(wq)) wake_up_all(wq); @@ -102,6 +93,7 @@ int ext4_end_io_nolock(ext4_io_end_t *io) struct inode *inode = io->inode; loff_t offset = io->offset; ssize_t size = io->size; + wait_queue_head_t *wq; int ret = 0; ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p," @@ -126,7 +118,16 @@ int ext4_end_io_nolock(ext4_io_end_t *io) if (io->iocb) aio_complete(io->iocb, io->result, 0); /* clear the DIO AIO unwritten flag */ - io->flag &= ~EXT4_IO_END_UNWRITTEN; + if (io->flag & EXT4_IO_END_UNWRITTEN) { + io->flag &= ~EXT4_IO_END_UNWRITTEN; + /* Wake up anyone waiting on unwritten extent conversion */ + wq = ext4_ioend_wq(io->inode); + if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) && + waitqueue_active(wq)) { + wake_up_all(wq); + } + } + return ret; } @@ -190,6 +191,7 @@ static void ext4_end_bio(struct bio *bio, int error) struct inode *inode; unsigned long flags; int i; + sector_t bi_sector = bio->bi_sector; BUG_ON(!io_end); bio->bi_private = NULL; @@ -207,9 +209,7 @@ static void ext4_end_bio(struct bio *bio, int error) if (error) SetPageError(page); BUG_ON(!head); - if (head->b_size == PAGE_CACHE_SIZE) - clear_buffer_dirty(head); - else { + if (head->b_size != PAGE_CACHE_SIZE) { loff_t offset; loff_t io_end_offset = io_end->offset + io_end->size; @@ -221,7 +221,6 @@ static void ext4_end_bio(struct bio *bio, int error) if (error) buffer_io_error(bh); - clear_buffer_dirty(bh); } if (buffer_delay(bh)) partial_write = 1; @@ -257,7 +256,7 @@ static void ext4_end_bio(struct bio *bio, int error) (unsigned long long) io_end->offset, (long) io_end->size, (unsigned long long) - bio->bi_sector >> (inode->i_blkbits - 9)); + bi_sector >> (inode->i_blkbits - 9)); } /* Add the io_end to per-inode completed io list*/ @@ -380,6 +379,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, blocksize = 1 << inode->i_blkbits; + BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); set_page_writeback(page); ClearPageError(page); @@ -397,12 +397,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io, for (bh = head = page_buffers(page), block_start = 0; bh != head || !block_start; block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; if (block_start >= len) { clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; } + clear_buffer_dirty(bh); ret = io_submit_add_bh(io, io_page, inode, wbc, bh); if (ret) { /* diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 48ce561..5977b35 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -77,6 +77,7 @@ static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data); static void ext4_destroy_lazyinit_thread(void); static void ext4_unregister_li_request(struct super_block *sb); +static void ext4_clear_request_list(void); #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext3_fs_type = { @@ -832,6 +833,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); + atomic_set(&ei->i_aiodio_unwritten, 0); return &ei->vfs_inode; } @@ -2716,6 +2718,8 @@ static void ext4_unregister_li_request(struct super_block *sb) mutex_unlock(&ext4_li_info->li_list_mtx); } +static struct task_struct *ext4_lazyinit_task; + /* * This is the function where ext4lazyinit thread lives. It walks * through the request list searching for next scheduled filesystem. @@ -2784,6 +2788,10 @@ cont_thread: if (time_before(jiffies, next_wakeup)) schedule(); finish_wait(&eli->li_wait_daemon, &wait); + if (kthread_should_stop()) { + ext4_clear_request_list(); + goto exit_thread; + } } exit_thread: @@ -2808,6 +2816,7 @@ exit_thread: wake_up(&eli->li_wait_task); kfree(ext4_li_info); + ext4_lazyinit_task = NULL; ext4_li_info = NULL; mutex_unlock(&ext4_li_mtx); @@ -2830,11 +2839,10 @@ static void ext4_clear_request_list(void) static int ext4_run_lazyinit_thread(void) { - struct task_struct *t; - - t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); - if (IS_ERR(t)) { - int err = PTR_ERR(t); + ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread, + ext4_li_info, "ext4lazyinit"); + if (IS_ERR(ext4_lazyinit_task)) { + int err = PTR_ERR(ext4_lazyinit_task); ext4_clear_request_list(); del_timer_sync(&ext4_li_info->li_timer); kfree(ext4_li_info); @@ -2985,16 +2993,10 @@ static void ext4_destroy_lazyinit_thread(void) * If thread exited earlier * there's nothing to be done. */ - if (!ext4_li_info) + if (!ext4_li_info || !ext4_lazyinit_task) return; - ext4_clear_request_list(); - - while (ext4_li_info->li_task) { - wake_up(&ext4_li_info->li_wait_daemon); - wait_event(ext4_li_info->li_wait_task, - ext4_li_info->li_task == NULL); - } + kthread_stop(ext4_lazyinit_task); } static int ext4_fill_super(struct super_block *sb, void *data, int silent) @@ -3413,6 +3415,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_qcop = &ext4_qctl_operations; sb->dq_op = &ext4_quota_operations; #endif + memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); + INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); mutex_init(&sbi->s_resize_lock); @@ -4768,7 +4772,7 @@ static struct file_system_type ext4_fs_type = { .fs_flags = FS_REQUIRES_DEV, }; -int __init ext4_init_feat_adverts(void) +static int __init ext4_init_feat_adverts(void) { struct ext4_features *ef; int ret = -ENOMEM; @@ -4792,23 +4796,44 @@ out: return ret; } +static void ext4_exit_feat_adverts(void) +{ + kobject_put(&ext4_feat->f_kobj); + wait_for_completion(&ext4_feat->f_kobj_unregister); + kfree(ext4_feat); +} + +/* Shared across all ext4 file systems */ +wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; +struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; + static int __init ext4_init_fs(void) { - int err; + int i, err; ext4_check_flag_values(); + + for (i = 0; i < EXT4_WQ_HASH_SZ; i++) { + mutex_init(&ext4__aio_mutex[i]); + init_waitqueue_head(&ext4__ioend_wq[i]); + } + err = ext4_init_pageio(); if (err) return err; err = ext4_init_system_zone(); if (err) - goto out5; + goto out7; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); if (!ext4_kset) - goto out4; + goto out6; ext4_proc_root = proc_mkdir("fs/ext4", NULL); + if (!ext4_proc_root) + goto out5; err = ext4_init_feat_adverts(); + if (err) + goto out4; err = ext4_init_mballoc(); if (err) @@ -4838,12 +4863,14 @@ out1: out2: ext4_exit_mballoc(); out3: - kfree(ext4_feat); + ext4_exit_feat_adverts(); +out4: remove_proc_entry("fs/ext4", NULL); +out5: kset_unregister(ext4_kset); -out4: +out6: ext4_exit_system_zone(); -out5: +out7: ext4_exit_pageio(); return err; } @@ -4857,6 +4884,7 @@ static void __exit ext4_exit_fs(void) destroy_inodecache(); ext4_exit_xattr(); ext4_exit_mballoc(); + ext4_exit_feat_adverts(); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); ext4_exit_system_zone(); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 86753fe..0e277ec 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -757,8 +757,10 @@ fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable) struct inode *inode = de->d_inode; u32 ipos_h, ipos_m, ipos_l; - if (len < 5) + if (len < 5) { + *lenp = 5; return 255; /* no room */ + } ipos_h = MSDOS_I(inode)->i_pos >> 8; ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index f88f752..adae3fb 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -43,7 +43,7 @@ static int vfat_revalidate_shortname(struct dentry *dentry) static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd) { - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; /* This is not negative dentry. Always valid. */ @@ -54,7 +54,7 @@ static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd) static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd) { - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; /* @@ -131,7 +131,7 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; - struct file *file = fget(fildes); + struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd(); @@ -426,15 +426,35 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, return err; } +static int check_fcntl_cmd(unsigned cmd) +{ + switch (cmd) { + case F_DUPFD: + case F_DUPFD_CLOEXEC: + case F_GETFD: + case F_SETFD: + case F_GETFL: + return 1; + } + return 0; +} + SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct file *filp; long err = -EBADF; - filp = fget(fd); + filp = fget_raw(fd); if (!filp) goto out; + if (unlikely(filp->f_mode & FMODE_PATH)) { + if (!check_fcntl_cmd(cmd)) { + fput(filp); + goto out; + } + } + err = security_file_fcntl(filp, cmd, arg); if (err) { fput(filp); @@ -456,10 +476,17 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, long err; err = -EBADF; - filp = fget(fd); + filp = fget_raw(fd); if (!filp) goto out; + if (unlikely(filp->f_mode & FMODE_PATH)) { + if (!check_fcntl_cmd(cmd)) { + fput(filp); + goto out; + } + } + err = security_file_fcntl(filp, cmd, arg); if (err) { fput(filp); @@ -808,14 +835,14 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(18 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( + BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( O_RDONLY | O_WRONLY | O_RDWR | O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC | O_APPEND | /* O_NONBLOCK | */ __O_SYNC | O_DSYNC | FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - FMODE_EXEC + __FMODE_EXEC | O_PATH )); fasync_cache = kmem_cache_create("fasync_cache", diff --git a/fs/fhandle.c b/fs/fhandle.c new file mode 100644 index 0000000..bf93ad2 --- /dev/null +++ b/fs/fhandle.c @@ -0,0 +1,265 @@ +#include <linux/syscalls.h> +#include <linux/slab.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/exportfs.h> +#include <linux/fs_struct.h> +#include <linux/fsnotify.h> +#include <asm/uaccess.h> +#include "internal.h" + +static long do_sys_name_to_handle(struct path *path, + struct file_handle __user *ufh, + int __user *mnt_id) +{ + long retval; + struct file_handle f_handle; + int handle_dwords, handle_bytes; + struct file_handle *handle = NULL; + + /* + * We need t make sure wether the file system + * support decoding of the file handle + */ + if (!path->mnt->mnt_sb->s_export_op || + !path->mnt->mnt_sb->s_export_op->fh_to_dentry) + return -EOPNOTSUPP; + + if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) + return -EFAULT; + + if (f_handle.handle_bytes > MAX_HANDLE_SZ) + return -EINVAL; + + handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + GFP_KERNEL); + if (!handle) + return -ENOMEM; + + /* convert handle size to multiple of sizeof(u32) */ + handle_dwords = f_handle.handle_bytes >> 2; + + /* we ask for a non connected handle */ + retval = exportfs_encode_fh(path->dentry, + (struct fid *)handle->f_handle, + &handle_dwords, 0); + handle->handle_type = retval; + /* convert handle size to bytes */ + handle_bytes = handle_dwords * sizeof(u32); + handle->handle_bytes = handle_bytes; + if ((handle->handle_bytes > f_handle.handle_bytes) || + (retval == 255) || (retval == -ENOSPC)) { + /* As per old exportfs_encode_fh documentation + * we could return ENOSPC to indicate overflow + * But file system returned 255 always. So handle + * both the values + */ + /* + * set the handle size to zero so we copy only + * non variable part of the file_handle + */ + handle_bytes = 0; + retval = -EOVERFLOW; + } else + retval = 0; + /* copy the mount id */ + if (copy_to_user(mnt_id, &path->mnt->mnt_id, sizeof(*mnt_id)) || + copy_to_user(ufh, handle, + sizeof(struct file_handle) + handle_bytes)) + retval = -EFAULT; + kfree(handle); + return retval; +} + +/** + * sys_name_to_handle_at: convert name to handle + * @dfd: directory relative to which name is interpreted if not absolute + * @name: name that should be converted to handle. + * @handle: resulting file handle + * @mnt_id: mount id of the file system containing the file + * @flag: flag value to indicate whether to follow symlink or not + * + * @handle->handle_size indicate the space available to store the + * variable part of the file handle in bytes. If there is not + * enough space, the field is updated to return the minimum + * value required. + */ +SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name, + struct file_handle __user *, handle, int __user *, mnt_id, + int, flag) +{ + struct path path; + int lookup_flags; + int err; + + if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) + return -EINVAL; + + lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0; + if (flag & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + err = user_path_at(dfd, name, lookup_flags, &path); + if (!err) { + err = do_sys_name_to_handle(&path, handle, mnt_id); + path_put(&path); + } + return err; +} + +static struct vfsmount *get_vfsmount_from_fd(int fd) +{ + struct path path; + + if (fd == AT_FDCWD) { + struct fs_struct *fs = current->fs; + spin_lock(&fs->lock); + path = fs->pwd; + mntget(path.mnt); + spin_unlock(&fs->lock); + } else { + int fput_needed; + struct file *file = fget_light(fd, &fput_needed); + if (!file) + return ERR_PTR(-EBADF); + path = file->f_path; + mntget(path.mnt); + fput_light(file, fput_needed); + } + return path.mnt; +} + +static int vfs_dentry_acceptable(void *context, struct dentry *dentry) +{ + return 1; +} + +static int do_handle_to_path(int mountdirfd, struct file_handle *handle, + struct path *path) +{ + int retval = 0; + int handle_dwords; + + path->mnt = get_vfsmount_from_fd(mountdirfd); + if (IS_ERR(path->mnt)) { + retval = PTR_ERR(path->mnt); + goto out_err; + } + /* change the handle size to multiple of sizeof(u32) */ + handle_dwords = handle->handle_bytes >> 2; + path->dentry = exportfs_decode_fh(path->mnt, + (struct fid *)handle->f_handle, + handle_dwords, handle->handle_type, + vfs_dentry_acceptable, NULL); + if (IS_ERR(path->dentry)) { + retval = PTR_ERR(path->dentry); + goto out_mnt; + } + return 0; +out_mnt: + mntput(path->mnt); +out_err: + return retval; +} + +static int handle_to_path(int mountdirfd, struct file_handle __user *ufh, + struct path *path) +{ + int retval = 0; + struct file_handle f_handle; + struct file_handle *handle = NULL; + + /* + * With handle we don't look at the execute bit on the + * the directory. Ideally we would like CAP_DAC_SEARCH. + * But we don't have that + */ + if (!capable(CAP_DAC_READ_SEARCH)) { + retval = -EPERM; + goto out_err; + } + if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) { + retval = -EFAULT; + goto out_err; + } + if ((f_handle.handle_bytes > MAX_HANDLE_SZ) || + (f_handle.handle_bytes == 0)) { + retval = -EINVAL; + goto out_err; + } + handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + GFP_KERNEL); + if (!handle) { + retval = -ENOMEM; + goto out_err; + } + /* copy the full handle */ + if (copy_from_user(handle, ufh, + sizeof(struct file_handle) + + f_handle.handle_bytes)) { + retval = -EFAULT; + goto out_handle; + } + + retval = do_handle_to_path(mountdirfd, handle, path); + +out_handle: + kfree(handle); +out_err: + return retval; +} + +long do_handle_open(int mountdirfd, + struct file_handle __user *ufh, int open_flag) +{ + long retval = 0; + struct path path; + struct file *file; + int fd; + + retval = handle_to_path(mountdirfd, ufh, &path); + if (retval) + return retval; + + fd = get_unused_fd_flags(open_flag); + if (fd < 0) { + path_put(&path); + return fd; + } + file = file_open_root(path.dentry, path.mnt, "", open_flag); + if (IS_ERR(file)) { + put_unused_fd(fd); + retval = PTR_ERR(file); + } else { + retval = fd; + fsnotify_open(file); + fd_install(fd, file); + } + path_put(&path); + return retval; +} + +/** + * sys_open_by_handle_at: Open the file handle + * @mountdirfd: directory file descriptor + * @handle: file handle to be opened + * @flag: open flags. + * + * @mountdirfd indicate the directory file descriptor + * of the mount point. file handle is decoded relative + * to the vfsmount pointed by the @mountdirfd. @flags + * value is same as the open(2) flags. + */ +SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, + struct file_handle __user *, handle, + int, flags) +{ + long ret; + + if (force_o_largefile()) + flags |= O_LARGEFILE; + + ret = do_handle_open(mountdirfd, handle, flags); + return ret; +} diff --git a/fs/file_table.c b/fs/file_table.c index c3e89ad..74a9544 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -125,13 +125,13 @@ struct file *get_empty_filp(void) goto fail; percpu_counter_inc(&nr_files); + f->f_cred = get_cred(cred); if (security_file_alloc(f)) goto fail_sec; INIT_LIST_HEAD(&f->f_u.fu_list); atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); - f->f_cred = get_cred(cred); spin_lock_init(&f->f_lock); eventpoll_init_file(f); /* f->f_version: 0 */ @@ -276,11 +276,10 @@ struct file *fget(unsigned int fd) rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - if (!atomic_long_inc_not_zero(&file->f_count)) { - /* File object ref couldn't be taken */ - rcu_read_unlock(); - return NULL; - } + /* File object ref couldn't be taken */ + if (file->f_mode & FMODE_PATH || + !atomic_long_inc_not_zero(&file->f_count)) + file = NULL; } rcu_read_unlock(); @@ -289,6 +288,25 @@ struct file *fget(unsigned int fd) EXPORT_SYMBOL(fget); +struct file *fget_raw(unsigned int fd) +{ + struct file *file; + struct files_struct *files = current->files; + + rcu_read_lock(); + file = fcheck_files(files, fd); + if (file) { + /* File object ref couldn't be taken */ + if (!atomic_long_inc_not_zero(&file->f_count)) + file = NULL; + } + rcu_read_unlock(); + + return file; +} + +EXPORT_SYMBOL(fget_raw); + /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * @@ -313,6 +331,33 @@ struct file *fget_light(unsigned int fd, int *fput_needed) *fput_needed = 0; if (atomic_read(&files->count) == 1) { file = fcheck_files(files, fd); + if (file && (file->f_mode & FMODE_PATH)) + file = NULL; + } else { + rcu_read_lock(); + file = fcheck_files(files, fd); + if (file) { + if (!(file->f_mode & FMODE_PATH) && + atomic_long_inc_not_zero(&file->f_count)) + *fput_needed = 1; + else + /* Didn't get the reference, someone's freed */ + file = NULL; + } + rcu_read_unlock(); + } + + return file; +} + +struct file *fget_raw_light(unsigned int fd, int *fput_needed) +{ + struct file *file; + struct files_struct *files = current->files; + + *fput_needed = 0; + if (atomic_read(&files->count) == 1) { + file = fcheck_files(files, fd); } else { rcu_read_lock(); file = fcheck_files(files, fd); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index bfed844..8bd0ef9 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -158,7 +158,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) { struct inode *inode; - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; inode = entry->d_inode; @@ -1283,8 +1283,11 @@ static int fuse_do_setattr(struct dentry *entry, struct iattr *attr, if (err) return err; - if ((attr->ia_valid & ATTR_OPEN) && fc->atomic_o_trunc) - return 0; + if (attr->ia_valid & ATTR_OPEN) { + if (fc->atomic_o_trunc) + return 0; + file = NULL; + } if (attr->ia_valid & ATTR_SIZE) is_truncate = true; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 95da1bc..9e0832d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -86,18 +86,52 @@ struct fuse_file *fuse_file_get(struct fuse_file *ff) return ff; } +static void fuse_release_async(struct work_struct *work) +{ + struct fuse_req *req; + struct fuse_conn *fc; + struct path path; + + req = container_of(work, struct fuse_req, misc.release.work); + path = req->misc.release.path; + fc = get_fuse_conn(path.dentry->d_inode); + + fuse_put_request(fc, req); + path_put(&path); +} + static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) { - path_put(&req->misc.release.path); + if (fc->destroy_req) { + /* + * If this is a fuseblk mount, then it's possible that + * releasing the path will result in releasing the + * super block and sending the DESTROY request. If + * the server is single threaded, this would hang. + * For this reason do the path_put() in a separate + * thread. + */ + atomic_inc(&req->count); + INIT_WORK(&req->misc.release.work, fuse_release_async); + schedule_work(&req->misc.release.work); + } else { + path_put(&req->misc.release.path); + } } -static void fuse_file_put(struct fuse_file *ff) +static void fuse_file_put(struct fuse_file *ff, bool sync) { if (atomic_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - req->end = fuse_release_end; - fuse_request_send_background(ff->fc, req); + if (sync) { + fuse_request_send(ff->fc, req); + path_put(&req->misc.release.path); + fuse_put_request(ff->fc, req); + } else { + req->end = fuse_release_end; + fuse_request_send_background(ff->fc, req); + } kfree(ff); } } @@ -219,8 +253,12 @@ void fuse_release_common(struct file *file, int opcode) * Normally this will send the RELEASE request, however if * some asynchronous READ or WRITE requests are outstanding, * the sending will be delayed. + * + * Make the release synchronous if this is a fuseblk mount, + * synchronous RELEASE is allowed (and desirable) in this case + * because the server can be trusted not to screw up. */ - fuse_file_put(ff); + fuse_file_put(ff, ff->fc->destroy_req != NULL); } static int fuse_open(struct inode *inode, struct file *file) @@ -558,7 +596,7 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) page_cache_release(page); } if (req->ff) - fuse_file_put(req->ff); + fuse_file_put(req->ff, false); } static void fuse_send_readpages(struct fuse_req *req, struct file *file) @@ -1137,7 +1175,7 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf, static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req) { __free_page(req->pages[0]); - fuse_file_put(req->ff); + fuse_file_put(req->ff, false); } static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ae5744a..d428694 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -21,6 +21,7 @@ #include <linux/rwsem.h> #include <linux/rbtree.h> #include <linux/poll.h> +#include <linux/workqueue.h> /** Max number of pages that can be used in a single read request */ #define FUSE_MAX_PAGES_PER_REQ 32 @@ -262,7 +263,10 @@ struct fuse_req { /** Data for asynchronous requests */ union { struct { - struct fuse_release_in in; + union { + struct fuse_release_in in; + struct work_struct work; + }; struct path path; } release; struct fuse_init_in init_in; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 9e3f68c..051b1a0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -637,8 +637,10 @@ static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, u64 nodeid; u32 generation; - if (*max_len < len) + if (*max_len < len) { + *max_len = len; return 255; + } nodeid = get_fuse_inode(inode)->nodeid; generation = inode->i_generation; diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 4a45633..0da8da2 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -44,7 +44,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) int error; int had_lock = 0; - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; parent = dget_parent(dentry); diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 9023db8..b5a5e60 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -36,9 +36,13 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len, struct super_block *sb = inode->i_sb; struct gfs2_inode *ip = GFS2_I(inode); - if (*len < GFS2_SMALL_FH_SIZE || - (connectable && *len < GFS2_LARGE_FH_SIZE)) + if (connectable && (*len < GFS2_LARGE_FH_SIZE)) { + *len = GFS2_LARGE_FH_SIZE; return 255; + } else if (*len < GFS2_SMALL_FH_SIZE) { + *len = GFS2_SMALL_FH_SIZE; + return 255; + } fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32); fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 08a8beb..7cd9a5a 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1779,11 +1779,11 @@ int __init gfs2_glock_init(void) #endif glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM | - WQ_HIGHPRI | WQ_FREEZEABLE, 0); + WQ_HIGHPRI | WQ_FREEZABLE, 0); if (IS_ERR(glock_workqueue)) return PTR_ERR(glock_workqueue); gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", - WQ_MEM_RECLAIM | WQ_FREEZEABLE, + WQ_MEM_RECLAIM | WQ_FREEZABLE, 0); if (IS_ERR(gfs2_delete_workqueue)) { destroy_workqueue(glock_workqueue); diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index ebef7ab..72c31a3 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -59,14 +59,7 @@ static void gfs2_init_gl_aspace_once(void *foo) struct address_space *mapping = (struct address_space *)(gl + 1); gfs2_init_glock_once(gl); - memset(mapping, 0, sizeof(*mapping)); - INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC); - spin_lock_init(&mapping->tree_lock); - spin_lock_init(&mapping->i_mmap_lock); - INIT_LIST_HEAD(&mapping->private_list); - spin_lock_init(&mapping->private_lock); - INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap); - INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); + address_space_init_once(mapping); } /** @@ -144,7 +137,7 @@ static int __init init_gfs2_fs(void) error = -ENOMEM; gfs_recovery_wq = alloc_workqueue("gfs_recovery", - WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0); + WQ_MEM_RECLAIM | WQ_FREEZABLE, 0); if (!gfs_recovery_wq) goto fail_wq; diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c index afa66aa..b4d70b1 100644 --- a/fs/hfs/dir.c +++ b/fs/hfs/dir.c @@ -238,46 +238,22 @@ static int hfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) } /* - * hfs_unlink() + * hfs_remove() * - * This is the unlink() entry in the inode_operations structure for - * regular HFS directories. The purpose is to delete an existing - * file, given the inode for the parent directory and the name - * (and its length) of the existing file. - */ -static int hfs_unlink(struct inode *dir, struct dentry *dentry) -{ - struct inode *inode; - int res; - - inode = dentry->d_inode; - res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name); - if (res) - return res; - - drop_nlink(inode); - hfs_delete_inode(inode); - inode->i_ctime = CURRENT_TIME_SEC; - mark_inode_dirty(inode); - - return res; -} - -/* - * hfs_rmdir() + * This serves as both unlink() and rmdir() in the inode_operations + * structure for regular HFS directories. The purpose is to delete + * an existing child, given the inode for the parent directory and + * the name (and its length) of the existing directory. * - * This is the rmdir() entry in the inode_operations structure for - * regular HFS directories. The purpose is to delete an existing - * directory, given the inode for the parent directory and the name - * (and its length) of the existing directory. + * HFS does not have hardlinks, so both rmdir and unlink set the + * link count to 0. The only difference is the emptiness check. */ -static int hfs_rmdir(struct inode *dir, struct dentry *dentry) +static int hfs_remove(struct inode *dir, struct dentry *dentry) { - struct inode *inode; + struct inode *inode = dentry->d_inode; int res; - inode = dentry->d_inode; - if (inode->i_size != 2) + if (S_ISDIR(inode->i_mode) && inode->i_size != 2) return -ENOTEMPTY; res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name); if (res) @@ -307,7 +283,7 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* Unlink destination if it already exists */ if (new_dentry->d_inode) { - res = hfs_unlink(new_dir, new_dentry); + res = hfs_remove(new_dir, new_dentry); if (res) return res; } @@ -332,9 +308,9 @@ const struct file_operations hfs_dir_operations = { const struct inode_operations hfs_dir_inode_operations = { .create = hfs_create, .lookup = hfs_lookup, - .unlink = hfs_unlink, + .unlink = hfs_remove, .mkdir = hfs_mkdir, - .rmdir = hfs_rmdir, + .rmdir = hfs_remove, .rename = hfs_rename, .setattr = hfs_inode_setattr, }; diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index 52a0bca..b1991a2 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -397,8 +397,8 @@ int hfsplus_file_extend(struct inode *inode) u32 start, len, goal; int res; - if (sbi->total_blocks - sbi->free_blocks + 8 > - sbi->alloc_file->i_size * 8) { + if (sbi->alloc_file->i_size * 8 < + sbi->total_blocks - sbi->free_blocks + 8) { /* extend alloc file */ printk(KERN_ERR "hfs: extend alloc file! " "(%llu,%u,%u)\n", diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c index d66ad11..40ad88c 100644 --- a/fs/hfsplus/part_tbl.c +++ b/fs/hfsplus/part_tbl.c @@ -134,7 +134,7 @@ int hfs_part_find(struct super_block *sb, res = hfsplus_submit_bio(sb->s_bdev, *part_start + HFS_PMAP_BLK, data, READ); if (res) - return res; + goto out; switch (be16_to_cpu(*((__be16 *)data))) { case HFS_OLD_PMAP_MAGIC: @@ -147,7 +147,7 @@ int hfs_part_find(struct super_block *sb, res = -ENOENT; break; } - +out: kfree(data); return res; } diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 9a3b479..b49b555 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -338,20 +338,22 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) struct inode *root, *inode; struct qstr str; struct nls_table *nls = NULL; - int err = -EINVAL; + int err; + err = -EINVAL; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) - return -ENOMEM; + goto out; sb->s_fs_info = sbi; mutex_init(&sbi->alloc_mutex); mutex_init(&sbi->vh_mutex); hfsplus_fill_defaults(sbi); + + err = -EINVAL; if (!hfsplus_parse_options(data, sbi)) { printk(KERN_ERR "hfs: unable to parse mount options\n"); - err = -EINVAL; - goto cleanup; + goto out_unload_nls; } /* temporarily use utf8 to correctly find the hidden dir below */ @@ -359,16 +361,14 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sbi->nls = load_nls("utf8"); if (!sbi->nls) { printk(KERN_ERR "hfs: unable to load nls for utf8\n"); - err = -EINVAL; - goto cleanup; + goto out_unload_nls; } /* Grab the volume header */ if (hfsplus_read_wrapper(sb)) { if (!silent) printk(KERN_WARNING "hfs: unable to find HFS+ superblock\n"); - err = -EINVAL; - goto cleanup; + goto out_unload_nls; } vhdr = sbi->s_vhdr; @@ -377,7 +377,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION || be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) { printk(KERN_ERR "hfs: wrong filesystem version\n"); - goto cleanup; + goto out_free_vhdr; } sbi->total_blocks = be32_to_cpu(vhdr->total_blocks); sbi->free_blocks = be32_to_cpu(vhdr->free_blocks); @@ -421,19 +421,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID); if (!sbi->ext_tree) { printk(KERN_ERR "hfs: failed to load extents file\n"); - goto cleanup; + goto out_free_vhdr; } sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID); if (!sbi->cat_tree) { printk(KERN_ERR "hfs: failed to load catalog file\n"); - goto cleanup; + goto out_close_ext_tree; } inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID); if (IS_ERR(inode)) { printk(KERN_ERR "hfs: failed to load allocation file\n"); err = PTR_ERR(inode); - goto cleanup; + goto out_close_cat_tree; } sbi->alloc_file = inode; @@ -442,14 +442,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (IS_ERR(root)) { printk(KERN_ERR "hfs: failed to load root directory\n"); err = PTR_ERR(root); - goto cleanup; - } - sb->s_d_op = &hfsplus_dentry_operations; - sb->s_root = d_alloc_root(root); - if (!sb->s_root) { - iput(root); - err = -ENOMEM; - goto cleanup; + goto out_put_alloc_file; } str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1; @@ -459,46 +452,69 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (!hfs_brec_read(&fd, &entry, sizeof(entry))) { hfs_find_exit(&fd); if (entry.type != cpu_to_be16(HFSPLUS_FOLDER)) - goto cleanup; + goto out_put_root; inode = hfsplus_iget(sb, be32_to_cpu(entry.folder.id)); if (IS_ERR(inode)) { err = PTR_ERR(inode); - goto cleanup; + goto out_put_root; } sbi->hidden_dir = inode; } else hfs_find_exit(&fd); - if (sb->s_flags & MS_RDONLY) - goto out; + if (!(sb->s_flags & MS_RDONLY)) { + /* + * H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused + * all three are registered with Apple for our use + */ + vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION); + vhdr->modify_date = hfsp_now2mt(); + be32_add_cpu(&vhdr->write_count, 1); + vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT); + vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT); + hfsplus_sync_fs(sb, 1); - /* H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused - * all three are registered with Apple for our use - */ - vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION); - vhdr->modify_date = hfsp_now2mt(); - be32_add_cpu(&vhdr->write_count, 1); - vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT); - vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT); - hfsplus_sync_fs(sb, 1); - - if (!sbi->hidden_dir) { - mutex_lock(&sbi->vh_mutex); - sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR); - hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode, - &str, sbi->hidden_dir); - mutex_unlock(&sbi->vh_mutex); - - hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY); + if (!sbi->hidden_dir) { + mutex_lock(&sbi->vh_mutex); + sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR); + hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str, + sbi->hidden_dir); + mutex_unlock(&sbi->vh_mutex); + + hfsplus_mark_inode_dirty(sbi->hidden_dir, + HFSPLUS_I_CAT_DIRTY); + } } -out: + + sb->s_d_op = &hfsplus_dentry_operations; + sb->s_root = d_alloc_root(root); + if (!sb->s_root) { + err = -ENOMEM; + goto out_put_hidden_dir; + } + unload_nls(sbi->nls); sbi->nls = nls; return 0; -cleanup: - hfsplus_put_super(sb); +out_put_hidden_dir: + iput(sbi->hidden_dir); +out_put_root: + iput(sbi->alloc_file); +out_put_alloc_file: + iput(sbi->alloc_file); +out_close_cat_tree: + hfs_btree_close(sbi->cat_tree); +out_close_ext_tree: + hfs_btree_close(sbi->ext_tree); +out_free_vhdr: + kfree(sbi->s_vhdr); + kfree(sbi->s_backup_vhdr); +out_unload_nls: + unload_nls(sbi->nls); unload_nls(nls); + kfree(sbi); +out: return err; } diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 1962317..3031d81 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -167,7 +167,7 @@ reread: break; case cpu_to_be16(HFSP_WRAP_MAGIC): if (!hfsplus_read_mdb(sbi->s_vhdr, &wd)) - goto out; + goto out_free_backup_vhdr; wd.ablk_size >>= HFSPLUS_SECTOR_SHIFT; part_start += wd.ablk_start + wd.embed_start * wd.ablk_size; part_size = wd.embed_count * wd.ablk_size; @@ -179,7 +179,7 @@ reread: * (should do this only for cdrom/loop though) */ if (hfs_part_find(sb, &part_start, &part_size)) - goto out; + goto out_free_backup_vhdr; goto reread; } @@ -295,6 +295,20 @@ static void destroy_inode(struct inode *inode) call_rcu(&inode->i_rcu, i_callback); } +void address_space_init_once(struct address_space *mapping) +{ + memset(mapping, 0, sizeof(*mapping)); + INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC); + spin_lock_init(&mapping->tree_lock); + spin_lock_init(&mapping->i_mmap_lock); + INIT_LIST_HEAD(&mapping->private_list); + spin_lock_init(&mapping->private_lock); + INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap); + INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); + mutex_init(&mapping->unmap_mutex); +} +EXPORT_SYMBOL(address_space_init_once); + /* * These are initializations that only need to be done * once, because the fields are idempotent across use @@ -308,13 +322,7 @@ void inode_init_once(struct inode *inode) INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); - INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC); - spin_lock_init(&inode->i_data.tree_lock); - spin_lock_init(&inode->i_data.i_mmap_lock); - INIT_LIST_HEAD(&inode->i_data.private_list); - spin_lock_init(&inode->i_data.private_lock); - INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap); - INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear); + address_space_init_once(&inode->i_data); i_size_ordered_init(inode); #ifdef CONFIG_FSNOTIFY INIT_HLIST_HEAD(&inode->i_fsnotify_marks); @@ -540,11 +548,14 @@ void evict_inodes(struct super_block *sb) /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on + * @kill_dirty: flag to guide handling of dirty inodes * * Attempts to free all inodes for a given superblock. If there were any * busy inodes return a non-zero value, else zero. + * If @kill_dirty is set, discard dirty inodes too, otherwise treat + * them as busy. */ -int invalidate_inodes(struct super_block *sb) +int invalidate_inodes(struct super_block *sb, bool kill_dirty) { int busy = 0; struct inode *inode, *next; @@ -556,6 +567,10 @@ int invalidate_inodes(struct super_block *sb) list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) continue; + if (inode->i_state & I_DIRTY && !kill_dirty) { + busy = 1; + continue; + } if (atomic_read(&inode->i_count)) { busy = 1; continue; diff --git a/fs/internal.h b/fs/internal.h index 0663568..f3d15de 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -106,10 +106,23 @@ extern void put_super(struct super_block *sb); struct nameidata; extern struct file *nameidata_to_filp(struct nameidata *); extern void release_open_intent(struct nameidata *); +struct open_flags { + int open_flag; + int mode; + int acc_mode; + int intent; +}; +extern struct file *do_filp_open(int dfd, const char *pathname, + const struct open_flags *op, int lookup_flags); +extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, + const char *, const struct open_flags *, int lookup_flags); + +extern long do_handle_open(int mountdirfd, + struct file_handle __user *ufh, int open_flag); /* * inode.c */ extern int get_nr_dirty_inodes(void); extern void evict_inodes(struct super_block *); -extern int invalidate_inodes(struct super_block *); +extern int invalidate_inodes(struct super_block *, bool); @@ -273,6 +273,13 @@ int __generic_block_fiemap(struct inode *inode, len = isize; } + /* + * Some filesystems can't deal with being asked to map less than + * blocksize, so make sure our len is at least block length. + */ + if (logical_to_blk(inode, len) == 0) + len = blk_to_logical(inode, 1); + start_blk = logical_to_blk(inode, start); last_blk = logical_to_blk(inode, start + len - 1); diff --git a/fs/isofs/export.c b/fs/isofs/export.c index ed752cb..dd4687f 100644 --- a/fs/isofs/export.c +++ b/fs/isofs/export.c @@ -124,9 +124,13 @@ isofs_export_encode_fh(struct dentry *dentry, * offset of the inode and the upper 16 bits of fh32[1] to * hold the offset of the parent. */ - - if (len < 3 || (connectable && len < 5)) + if (connectable && (len < 5)) { + *max_len = 5; + return 255; + } else if (len < 3) { + *max_len = 3; return 255; + } len = 3; fh32[0] = ei->i_iget5_block; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 9e46869..97e7346 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -473,7 +473,8 @@ int __jbd2_log_space_left(journal_t *journal) } /* - * Called under j_state_lock. Returns true if a transaction commit was started. + * Called with j_state_lock locked for writing. + * Returns true if a transaction commit was started. */ int __jbd2_log_start_commit(journal_t *journal, tid_t target) { @@ -520,11 +521,13 @@ int jbd2_journal_force_commit_nested(journal_t *journal) { transaction_t *transaction = NULL; tid_t tid; + int need_to_start = 0; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && !current->journal_info) { transaction = journal->j_running_transaction; - __jbd2_log_start_commit(journal, transaction->t_tid); + if (!tid_geq(journal->j_commit_request, transaction->t_tid)) + need_to_start = 1; } else if (journal->j_committing_transaction) transaction = journal->j_committing_transaction; @@ -535,6 +538,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal) tid = transaction->t_tid; read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); jbd2_log_wait_commit(journal, tid); return 1; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index faad2bd..1d11910 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -117,10 +117,10 @@ static inline void update_t_max_wait(transaction_t *transaction) static int start_this_handle(journal_t *journal, handle_t *handle, int gfp_mask) { - transaction_t *transaction; - int needed; - int nblocks = handle->h_buffer_credits; - transaction_t *new_transaction = NULL; + transaction_t *transaction, *new_transaction = NULL; + tid_t tid; + int needed, need_to_start; + int nblocks = handle->h_buffer_credits; if (nblocks > journal->j_max_transaction_buffers) { printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n", @@ -222,8 +222,11 @@ repeat: atomic_sub(nblocks, &transaction->t_outstanding_credits); prepare_to_wait(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); - __jbd2_log_start_commit(journal, transaction->t_tid); + tid = transaction->t_tid; + need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); schedule(); finish_wait(&journal->j_wait_transaction_locked, &wait); goto repeat; @@ -442,7 +445,8 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask) { transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; - int ret; + tid_t tid; + int need_to_start, ret; /* If we've had an abort of any type, don't even think about * actually doing the restart! */ @@ -465,8 +469,11 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask) spin_unlock(&transaction->t_handle_lock); jbd_debug(2, "restarting handle %p\n", handle); - __jbd2_log_start_commit(journal, transaction->t_tid); + tid = transaction->t_tid; + need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); lock_map_release(&handle->h_lockdep_map); handle->h_buffer_credits = nblocks; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 81ead85..3f04a180 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -809,9 +809,6 @@ static int jfs_link(struct dentry *old_dentry, if (ip->i_nlink == JFS_LINK_MAX) return -EMLINK; - if (ip->i_nlink == 0) - return -ENOENT; - dquot_initialize(dir); tid = txBegin(ip->i_sb, 0); @@ -1600,7 +1597,7 @@ out: static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd) { - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; /* * This is not negative dentry. Always valid. diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 5f1bcb2..b7c99bf 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -520,7 +520,7 @@ static struct nlm_host *next_host_state(struct hlist_head *cache, struct nsm_handle *nsm, const struct nlm_reboot *info) { - struct nlm_host *host = NULL; + struct nlm_host *host; struct hlist_head *chain; struct hlist_node *pos; @@ -532,12 +532,13 @@ static struct nlm_host *next_host_state(struct hlist_head *cache, host->h_state++; nlm_get_host(host); - goto out; + mutex_unlock(&nlm_host_mutex); + return host; } } -out: + mutex_unlock(&nlm_host_mutex); - return host; + return NULL; } /** diff --git a/fs/minix/namei.c b/fs/minix/namei.c index ce7337d..6e6777f 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -213,7 +213,6 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry, new_de = minix_find_entry(new_dentry, &new_page); if (!new_de) goto out_dir; - inode_inc_link_count(old_inode); minix_set_link(new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) @@ -225,18 +224,15 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry, if (new_dir->i_nlink >= info->s_link_max) goto out_dir; } - inode_inc_link_count(old_inode); err = minix_add_link(new_dentry, old_inode); - if (err) { - inode_dec_link_count(old_inode); + if (err) goto out_dir; - } if (dir_de) inode_inc_link_count(new_dir); } minix_delete_entry(old_de, old_page); - inode_dec_link_count(old_inode); + mark_inode_dirty(old_inode); if (dir_de) { minix_set_link(dir_de, dir_page, new_dir); @@ -136,7 +136,7 @@ static int do_getname(const char __user *filename, char *page) return retval; } -char * getname(const char __user * filename) +static char *getname_flags(const char __user * filename, int flags) { char *tmp, *result; @@ -147,14 +147,21 @@ char * getname(const char __user * filename) result = tmp; if (retval < 0) { - __putname(tmp); - result = ERR_PTR(retval); + if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) { + __putname(tmp); + result = ERR_PTR(retval); + } } } audit_getname(result); return result; } +char *getname(const char __user * filename) +{ + return getname_flags(filename, 0); +} + #ifdef CONFIG_AUDITSYSCALL void putname(const char *name) { @@ -401,9 +408,11 @@ static int nameidata_drop_rcu(struct nameidata *nd) { struct fs_struct *fs = current->fs; struct dentry *dentry = nd->path.dentry; + int want_root = 0; BUG_ON(!(nd->flags & LOOKUP_RCU)); - if (nd->root.mnt) { + if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) { + want_root = 1; spin_lock(&fs->lock); if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry) @@ -414,7 +423,7 @@ static int nameidata_drop_rcu(struct nameidata *nd) goto err; BUG_ON(nd->inode != dentry->d_inode); spin_unlock(&dentry->d_lock); - if (nd->root.mnt) { + if (want_root) { path_get(&nd->root); spin_unlock(&fs->lock); } @@ -427,7 +436,7 @@ static int nameidata_drop_rcu(struct nameidata *nd) err: spin_unlock(&dentry->d_lock); err_root: - if (nd->root.mnt) + if (want_root) spin_unlock(&fs->lock); return -ECHILD; } @@ -454,17 +463,11 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry { struct fs_struct *fs = current->fs; struct dentry *parent = nd->path.dentry; - - /* - * It can be possible to revalidate the dentry that we started - * the path walk with. force_reval_path may also revalidate the - * dentry already committed to the nameidata. - */ - if (unlikely(parent == dentry)) - return nameidata_drop_rcu(nd); + int want_root = 0; BUG_ON(!(nd->flags & LOOKUP_RCU)); - if (nd->root.mnt) { + if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) { + want_root = 1; spin_lock(&fs->lock); if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry) @@ -484,7 +487,7 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry parent->d_count++; spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); - if (nd->root.mnt) { + if (want_root) { path_get(&nd->root); spin_unlock(&fs->lock); } @@ -498,7 +501,7 @@ err: spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); err_root: - if (nd->root.mnt) + if (want_root) spin_unlock(&fs->lock); return -ECHILD; } @@ -506,8 +509,16 @@ err_root: /* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */ static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct dentry *dentry) { - if (nd->flags & LOOKUP_RCU) - return nameidata_dentry_drop_rcu(nd, dentry); + if (nd->flags & LOOKUP_RCU) { + if (unlikely(nameidata_dentry_drop_rcu(nd, dentry))) { + nd->flags &= ~LOOKUP_RCU; + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; + rcu_read_unlock(); + br_read_unlock(vfsmount_lock); + return -ECHILD; + } + } return 0; } @@ -526,7 +537,8 @@ static int nameidata_drop_rcu_last(struct nameidata *nd) BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; - nd->root.mnt = NULL; + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; spin_lock(&dentry->d_lock); if (!__d_rcu_to_refcount(dentry, nd->seq)) goto err_unlock; @@ -547,53 +559,31 @@ err_unlock: return -ECHILD; } -/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */ -static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd) -{ - if (likely(nd->flags & LOOKUP_RCU)) - return nameidata_drop_rcu_last(nd); - return 0; -} - /** * release_open_intent - free up open intent resources * @nd: pointer to nameidata */ void release_open_intent(struct nameidata *nd) { - if (nd->intent.open.file->f_path.dentry == NULL) - put_filp(nd->intent.open.file); - else - fput(nd->intent.open.file); -} + struct file *file = nd->intent.open.file; -/* - * Call d_revalidate and handle filesystems that request rcu-walk - * to be dropped. This may be called and return in rcu-walk mode, - * regardless of success or error. If -ECHILD is returned, the caller - * must return -ECHILD back up the path walk stack so path walk may - * be restarted in ref-walk mode. - */ -static int d_revalidate(struct dentry *dentry, struct nameidata *nd) -{ - int status; - - status = dentry->d_op->d_revalidate(dentry, nd); - if (status == -ECHILD) { - if (nameidata_dentry_drop_rcu(nd, dentry)) - return status; - status = dentry->d_op->d_revalidate(dentry, nd); + if (file && !IS_ERR(file)) { + if (file->f_path.dentry == NULL) + put_filp(file); + else + fput(file); } +} - return status; +static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + return dentry->d_op->d_revalidate(dentry, nd); } -static inline struct dentry * +static struct dentry * do_revalidate(struct dentry *dentry, struct nameidata *nd) { - int status; - - status = d_revalidate(dentry, nd); + int status = d_revalidate(dentry, nd); if (unlikely(status <= 0)) { /* * The dentry failed validation. @@ -602,37 +592,18 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd) * to return a fail status. */ if (status < 0) { - /* If we're in rcu-walk, we don't have a ref */ - if (!(nd->flags & LOOKUP_RCU)) - dput(dentry); + dput(dentry); dentry = ERR_PTR(status); - - } else { - /* Don't d_invalidate in rcu-walk mode */ - if (nameidata_dentry_drop_rcu_maybe(nd, dentry)) - return ERR_PTR(-ECHILD); - if (!d_invalidate(dentry)) { - dput(dentry); - dentry = NULL; - } + } else if (!d_invalidate(dentry)) { + dput(dentry); + dentry = NULL; } } return dentry; } -static inline int need_reval_dot(struct dentry *dentry) -{ - if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE))) - return 0; - - if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT))) - return 0; - - return 1; -} - /* - * force_reval_path - force revalidation of a dentry + * handle_reval_path - force revalidation of a dentry * * In some situations the path walking code will trust dentries without * revalidating them. This causes problems for filesystems that depend on @@ -646,30 +617,28 @@ static inline int need_reval_dot(struct dentry *dentry) * invalidate the dentry. It's up to the caller to handle putting references * to the path if necessary. */ -static int -force_reval_path(struct path *path, struct nameidata *nd) +static inline int handle_reval_path(struct nameidata *nd) { + struct dentry *dentry = nd->path.dentry; int status; - struct dentry *dentry = path->dentry; - /* - * only check on filesystems where it's possible for the dentry to - * become stale. - */ - if (!need_reval_dot(dentry)) + if (likely(!(nd->flags & LOOKUP_JUMPED))) + return 0; + + if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE))) + return 0; + + if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT))) return 0; + /* Note: we do not d_invalidate() */ status = d_revalidate(dentry, nd); if (status > 0) return 0; - if (!status) { - /* Don't d_invalidate in rcu-walk mode */ - if (nameidata_drop_rcu(nd)) - return -ECHILD; - d_invalidate(dentry); + if (!status) status = -ESTALE; - } + return status; } @@ -738,6 +707,7 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l path_put(&nd->path); nd->path = nd->root; path_get(&nd->root); + nd->flags |= LOOKUP_JUMPED; } nd->inode = nd->path.dentry->d_inode; @@ -767,18 +737,44 @@ static inline void path_to_nameidata(const struct path *path, nd->path.dentry = path->dentry; } +static inline void put_link(struct nameidata *nd, struct path *link, void *cookie) +{ + struct inode *inode = link->dentry->d_inode; + if (!IS_ERR(cookie) && inode->i_op->put_link) + inode->i_op->put_link(link->dentry, nd, cookie); + path_put(link); +} + static __always_inline int -__do_follow_link(const struct path *link, struct nameidata *nd, void **p) +follow_link(struct path *link, struct nameidata *nd, void **p) { int error; struct dentry *dentry = link->dentry; + BUG_ON(nd->flags & LOOKUP_RCU); + + if (unlikely(current->total_link_count >= 40)) { + *p = ERR_PTR(-ELOOP); /* no ->put_link(), please */ + path_put_conditional(link, nd); + path_put(&nd->path); + return -ELOOP; + } + cond_resched(); + current->total_link_count++; + touch_atime(link->mnt, dentry); nd_set_link(nd, NULL); if (link->mnt == nd->path.mnt) mntget(link->mnt); + error = security_inode_follow_link(link->dentry, nd); + if (error) { + *p = ERR_PTR(error); /* no ->put_link(), please */ + path_put(&nd->path); + return error; + } + nd->last_type = LAST_BIND; *p = dentry->d_inode->i_op->follow_link(dentry, nd); error = PTR_ERR(*p); @@ -788,50 +784,18 @@ __do_follow_link(const struct path *link, struct nameidata *nd, void **p) if (s) error = __vfs_follow_link(nd, s); else if (nd->last_type == LAST_BIND) { - error = force_reval_path(&nd->path, nd); - if (error) + nd->flags |= LOOKUP_JUMPED; + nd->inode = nd->path.dentry->d_inode; + if (nd->inode->i_op->follow_link) { + /* stepped on a _really_ weird one */ path_put(&nd->path); + error = -ELOOP; + } } } return error; } -/* - * This limits recursive symlink follows to 8, while - * limiting consecutive symlinks to 40. - * - * Without that kind of total limit, nasty chains of consecutive - * symlinks can cause almost arbitrarily long lookups. - */ -static inline int do_follow_link(struct path *path, struct nameidata *nd) -{ - void *cookie; - int err = -ELOOP; - if (current->link_count >= MAX_NESTED_LINKS) - goto loop; - if (current->total_link_count >= 40) - goto loop; - BUG_ON(nd->depth >= MAX_NESTED_LINKS); - cond_resched(); - err = security_inode_follow_link(path->dentry, nd); - if (err) - goto loop; - current->link_count++; - current->total_link_count++; - nd->depth++; - err = __do_follow_link(path, nd, &cookie); - if (!IS_ERR(cookie) && path->dentry->d_inode->i_op->put_link) - path->dentry->d_inode->i_op->put_link(path->dentry, nd, cookie); - path_put(path); - current->link_count--; - nd->depth--; - return err; -loop: - path_put_conditional(path, nd); - path_put(&nd->path); - return err; -} - static int follow_up_rcu(struct path *path) { struct vfsmount *parent; @@ -1070,7 +1034,7 @@ static int follow_dotdot_rcu(struct nameidata *nd) seq = read_seqcount_begin(&parent->d_seq); if (read_seqcount_retry(&old->d_seq, nd->seq)) - return -ECHILD; + goto failed; inode = parent->d_inode; nd->path.dentry = parent; nd->seq = seq; @@ -1083,8 +1047,15 @@ static int follow_dotdot_rcu(struct nameidata *nd) } __follow_mount_rcu(nd, &nd->path, &inode, true); nd->inode = inode; - return 0; + +failed: + nd->flags &= ~LOOKUP_RCU; + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; + rcu_read_unlock(); + br_read_unlock(vfsmount_lock); + return -ECHILD; } /* @@ -1218,57 +1189,85 @@ static int do_lookup(struct nameidata *nd, struct qstr *name, { struct vfsmount *mnt = nd->path.mnt; struct dentry *dentry, *parent = nd->path.dentry; - struct inode *dir; + int need_reval = 1; + int status = 1; int err; /* - * See if the low-level filesystem might want - * to use its own hash.. - */ - if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { - err = parent->d_op->d_hash(parent, nd->inode, name); - if (err < 0) - return err; - } - - /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, we're going to * do the non-racy lookup, below. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; - *inode = nd->inode; dentry = __d_lookup_rcu(parent, name, &seq, inode); - if (!dentry) { - if (nameidata_drop_rcu(nd)) - return -ECHILD; - goto need_lookup; - } + if (!dentry) + goto unlazy; + /* Memory barrier in read_seqcount_begin of child is enough */ if (__read_seqcount_retry(&parent->d_seq, nd->seq)) return -ECHILD; - nd->seq = seq; - if (dentry->d_flags & DCACHE_OP_REVALIDATE) - goto need_revalidate; -done2: + + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) { + status = d_revalidate(dentry, nd); + if (unlikely(status <= 0)) { + if (status != -ECHILD) + need_reval = 0; + goto unlazy; + } + } path->mnt = mnt; path->dentry = dentry; if (likely(__follow_mount_rcu(nd, path, inode, false))) return 0; - if (nameidata_drop_rcu(nd)) - return -ECHILD; - /* fallthru */ +unlazy: + if (dentry) { + if (nameidata_dentry_drop_rcu(nd, dentry)) + return -ECHILD; + } else { + if (nameidata_drop_rcu(nd)) + return -ECHILD; + } + } else { + dentry = __d_lookup(parent, name); } - dentry = __d_lookup(parent, name); - if (!dentry) - goto need_lookup; -found: - if (dentry->d_flags & DCACHE_OP_REVALIDATE) - goto need_revalidate; -done: + +retry: + if (unlikely(!dentry)) { + struct inode *dir = parent->d_inode; + BUG_ON(nd->inode != dir); + + mutex_lock(&dir->i_mutex); + dentry = d_lookup(parent, name); + if (likely(!dentry)) { + dentry = d_alloc_and_lookup(parent, name, nd); + if (IS_ERR(dentry)) { + mutex_unlock(&dir->i_mutex); + return PTR_ERR(dentry); + } + /* known good */ + need_reval = 0; + status = 1; + } + mutex_unlock(&dir->i_mutex); + } + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval) + status = d_revalidate(dentry, nd); + if (unlikely(status <= 0)) { + if (status < 0) { + dput(dentry); + return status; + } + if (!d_invalidate(dentry)) { + dput(dentry); + dentry = NULL; + need_reval = 1; + goto retry; + } + } + path->mnt = mnt; path->dentry = dentry; err = follow_managed(path, nd->flags); @@ -1278,49 +1277,113 @@ done: } *inode = path->dentry->d_inode; return 0; +} -need_lookup: - dir = parent->d_inode; - BUG_ON(nd->inode != dir); +static inline int may_lookup(struct nameidata *nd) +{ + if (nd->flags & LOOKUP_RCU) { + int err = exec_permission(nd->inode, IPERM_FLAG_RCU); + if (err != -ECHILD) + return err; + if (nameidata_drop_rcu(nd)) + return -ECHILD; + } + return exec_permission(nd->inode, 0); +} - mutex_lock(&dir->i_mutex); - /* - * First re-do the cached lookup just in case it was created - * while we waited for the directory semaphore, or the first - * lookup failed due to an unrelated rename. - * - * This could use version numbering or similar to avoid unnecessary - * cache lookups, but then we'd have to do the first lookup in the - * non-racy way. However in the common case here, everything should - * be hot in cache, so would it be a big win? - */ - dentry = d_lookup(parent, name); - if (likely(!dentry)) { - dentry = d_alloc_and_lookup(parent, name, nd); - mutex_unlock(&dir->i_mutex); - if (IS_ERR(dentry)) - goto fail; - goto done; +static inline int handle_dots(struct nameidata *nd, int type) +{ + if (type == LAST_DOTDOT) { + if (nd->flags & LOOKUP_RCU) { + if (follow_dotdot_rcu(nd)) + return -ECHILD; + } else + follow_dotdot(nd); + } + return 0; +} + +static void terminate_walk(struct nameidata *nd) +{ + if (!(nd->flags & LOOKUP_RCU)) { + path_put(&nd->path); + } else { + nd->flags &= ~LOOKUP_RCU; + if (!(nd->flags & LOOKUP_ROOT)) + nd->root.mnt = NULL; + rcu_read_unlock(); + br_read_unlock(vfsmount_lock); } +} + +static inline int walk_component(struct nameidata *nd, struct path *path, + struct qstr *name, int type, int follow) +{ + struct inode *inode; + int err; /* - * Uhhuh! Nasty case: the cache was re-populated while - * we waited on the semaphore. Need to revalidate. + * "." and ".." are special - ".." especially so because it has + * to be able to know about the current root directory and + * parent relationships. */ - mutex_unlock(&dir->i_mutex); - goto found; + if (unlikely(type != LAST_NORM)) + return handle_dots(nd, type); + err = do_lookup(nd, name, path, &inode); + if (unlikely(err)) { + terminate_walk(nd); + return err; + } + if (!inode) { + path_to_nameidata(path, nd); + terminate_walk(nd); + return -ENOENT; + } + if (unlikely(inode->i_op->follow_link) && follow) { + if (nameidata_dentry_drop_rcu_maybe(nd, path->dentry)) + return -ECHILD; + BUG_ON(inode != path->dentry->d_inode); + return 1; + } + path_to_nameidata(path, nd); + nd->inode = inode; + return 0; +} -need_revalidate: - dentry = do_revalidate(dentry, nd); - if (!dentry) - goto need_lookup; - if (IS_ERR(dentry)) - goto fail; - if (nd->flags & LOOKUP_RCU) - goto done2; - goto done; +/* + * This limits recursive symlink follows to 8, while + * limiting consecutive symlinks to 40. + * + * Without that kind of total limit, nasty chains of consecutive + * symlinks can cause almost arbitrarily long lookups. + */ +static inline int nested_symlink(struct path *path, struct nameidata *nd) +{ + int res; -fail: - return PTR_ERR(dentry); + BUG_ON(nd->depth >= MAX_NESTED_LINKS); + if (unlikely(current->link_count >= MAX_NESTED_LINKS)) { + path_put_conditional(path, nd); + path_put(&nd->path); + return -ELOOP; + } + + nd->depth++; + current->link_count++; + + do { + struct path link = *path; + void *cookie; + + res = follow_link(&link, nd, &cookie); + if (!res) + res = walk_component(nd, path, &nd->last, + nd->last_type, LOOKUP_FOLLOW); + put_link(nd, &link, cookie); + } while (res > 0); + + current->link_count--; + nd->depth--; + return res; } /* @@ -1340,30 +1403,18 @@ static int link_path_walk(const char *name, struct nameidata *nd) while (*name=='/') name++; if (!*name) - goto return_reval; - - if (nd->depth) - lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE); + return 0; /* At this point we know we have a real path component. */ for(;;) { - struct inode *inode; unsigned long hash; struct qstr this; unsigned int c; + int type; nd->flags |= LOOKUP_CONTINUE; - if (nd->flags & LOOKUP_RCU) { - err = exec_permission(nd->inode, IPERM_FLAG_RCU); - if (err == -ECHILD) { - if (nameidata_drop_rcu(nd)) - return -ECHILD; - goto exec_again; - } - } else { -exec_again: - err = exec_permission(nd->inode, 0); - } + + err = may_lookup(nd); if (err) break; @@ -1379,56 +1430,43 @@ exec_again: this.len = name - (const char *) this.name; this.hash = end_name_hash(hash); + type = LAST_NORM; + if (this.name[0] == '.') switch (this.len) { + case 2: + if (this.name[1] == '.') { + type = LAST_DOTDOT; + nd->flags |= LOOKUP_JUMPED; + } + break; + case 1: + type = LAST_DOT; + } + if (likely(type == LAST_NORM)) { + struct dentry *parent = nd->path.dentry; + nd->flags &= ~LOOKUP_JUMPED; + if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { + err = parent->d_op->d_hash(parent, nd->inode, + &this); + if (err < 0) + break; + } + } + /* remove trailing slashes? */ if (!c) goto last_component; while (*++name == '/'); if (!*name) - goto last_with_slashes; + goto last_component; - /* - * "." and ".." are special - ".." especially so because it has - * to be able to know about the current root directory and - * parent relationships. - */ - if (this.name[0] == '.') switch (this.len) { - default: - break; - case 2: - if (this.name[1] != '.') - break; - if (nd->flags & LOOKUP_RCU) { - if (follow_dotdot_rcu(nd)) - return -ECHILD; - } else - follow_dotdot(nd); - /* fallthrough */ - case 1: - continue; - } - /* This does the actual lookups.. */ - err = do_lookup(nd, &this, &next, &inode); - if (err) - break; - err = -ENOENT; - if (!inode) - goto out_dput; + err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW); + if (err < 0) + return err; - if (inode->i_op->follow_link) { - /* We commonly drop rcu-walk here */ - if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry)) - return -ECHILD; - BUG_ON(inode != next.dentry->d_inode); - err = do_follow_link(&next, nd); + if (err) { + err = nested_symlink(&next, nd); if (err) - goto return_err; - nd->inode = nd->path.dentry->d_inode; - err = -ENOENT; - if (!nd->inode) - break; - } else { - path_to_nameidata(&next, nd); - nd->inode = inode; + return err; } err = -ENOTDIR; if (!nd->inode->i_op->lookup) @@ -1436,209 +1474,109 @@ exec_again: continue; /* here ends the main loop */ -last_with_slashes: - lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; last_component: /* Clear LOOKUP_CONTINUE iff it was previously unset */ nd->flags &= lookup_flags | ~LOOKUP_CONTINUE; - if (lookup_flags & LOOKUP_PARENT) - goto lookup_parent; - if (this.name[0] == '.') switch (this.len) { - default: - break; - case 2: - if (this.name[1] != '.') - break; - if (nd->flags & LOOKUP_RCU) { - if (follow_dotdot_rcu(nd)) - return -ECHILD; - } else - follow_dotdot(nd); - /* fallthrough */ - case 1: - goto return_reval; - } - err = do_lookup(nd, &this, &next, &inode); - if (err) - break; - if (inode && unlikely(inode->i_op->follow_link) && - (lookup_flags & LOOKUP_FOLLOW)) { - if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry)) - return -ECHILD; - BUG_ON(inode != next.dentry->d_inode); - err = do_follow_link(&next, nd); - if (err) - goto return_err; - nd->inode = nd->path.dentry->d_inode; - } else { - path_to_nameidata(&next, nd); - nd->inode = inode; - } - err = -ENOENT; - if (!nd->inode) - break; - if (lookup_flags & LOOKUP_DIRECTORY) { - err = -ENOTDIR; - if (!nd->inode->i_op->lookup) - break; - } - goto return_base; -lookup_parent: nd->last = this; - nd->last_type = LAST_NORM; - if (this.name[0] != '.') - goto return_base; - if (this.len == 1) - nd->last_type = LAST_DOT; - else if (this.len == 2 && this.name[1] == '.') - nd->last_type = LAST_DOTDOT; - else - goto return_base; -return_reval: - /* - * We bypassed the ordinary revalidation routines. - * We may need to check the cached dentry for staleness. - */ - if (need_reval_dot(nd->path.dentry)) { - /* Note: we do not d_invalidate() */ - err = d_revalidate(nd->path.dentry, nd); - if (!err) - err = -ESTALE; - if (err < 0) - break; - } -return_base: - if (nameidata_drop_rcu_last_maybe(nd)) - return -ECHILD; + nd->last_type = type; return 0; -out_dput: - if (!(nd->flags & LOOKUP_RCU)) - path_put_conditional(&next, nd); - break; } - if (!(nd->flags & LOOKUP_RCU)) - path_put(&nd->path); -return_err: + terminate_walk(nd); return err; } -static inline int path_walk_rcu(const char *name, struct nameidata *nd) -{ - current->total_link_count = 0; - - return link_path_walk(name, nd); -} - -static inline int path_walk_simple(const char *name, struct nameidata *nd) -{ - current->total_link_count = 0; - - return link_path_walk(name, nd); -} - -static int path_walk(const char *name, struct nameidata *nd) -{ - struct path save = nd->path; - int result; - - current->total_link_count = 0; - - /* make sure the stuff we saved doesn't go away */ - path_get(&save); - - result = link_path_walk(name, nd); - if (result == -ESTALE) { - /* nd->path had been dropped */ - current->total_link_count = 0; - nd->path = save; - path_get(&nd->path); - nd->flags |= LOOKUP_REVAL; - result = link_path_walk(name, nd); - } - - path_put(&save); - - return result; -} - -static void path_finish_rcu(struct nameidata *nd) -{ - if (nd->flags & LOOKUP_RCU) { - /* RCU dangling. Cancel it. */ - nd->flags &= ~LOOKUP_RCU; - nd->root.mnt = NULL; - rcu_read_unlock(); - br_read_unlock(vfsmount_lock); - } - if (nd->file) - fput(nd->file); -} - -static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct nameidata *nd) +static int path_init(int dfd, const char *name, unsigned int flags, + struct nameidata *nd, struct file **fp) { int retval = 0; int fput_needed; struct file *file; nd->last_type = LAST_ROOT; /* if there are only slashes... */ - nd->flags = flags | LOOKUP_RCU; + nd->flags = flags | LOOKUP_JUMPED; nd->depth = 0; + if (flags & LOOKUP_ROOT) { + struct inode *inode = nd->root.dentry->d_inode; + if (*name) { + if (!inode->i_op->lookup) + return -ENOTDIR; + retval = inode_permission(inode, MAY_EXEC); + if (retval) + return retval; + } + nd->path = nd->root; + nd->inode = inode; + if (flags & LOOKUP_RCU) { + br_read_lock(vfsmount_lock); + rcu_read_lock(); + nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); + } else { + path_get(&nd->path); + } + return 0; + } + nd->root.mnt = NULL; - nd->file = NULL; if (*name=='/') { - struct fs_struct *fs = current->fs; - unsigned seq; - - br_read_lock(vfsmount_lock); - rcu_read_lock(); - - do { - seq = read_seqcount_begin(&fs->seq); - nd->root = fs->root; - nd->path = nd->root; - nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); - + if (flags & LOOKUP_RCU) { + br_read_lock(vfsmount_lock); + rcu_read_lock(); + set_root_rcu(nd); + } else { + set_root(nd); + path_get(&nd->root); + } + nd->path = nd->root; } else if (dfd == AT_FDCWD) { - struct fs_struct *fs = current->fs; - unsigned seq; - - br_read_lock(vfsmount_lock); - rcu_read_lock(); + if (flags & LOOKUP_RCU) { + struct fs_struct *fs = current->fs; + unsigned seq; - do { - seq = read_seqcount_begin(&fs->seq); - nd->path = fs->pwd; - nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); - } while (read_seqcount_retry(&fs->seq, seq)); + br_read_lock(vfsmount_lock); + rcu_read_lock(); + do { + seq = read_seqcount_begin(&fs->seq); + nd->path = fs->pwd; + nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); + } while (read_seqcount_retry(&fs->seq, seq)); + } else { + get_fs_pwd(current->fs, &nd->path); + } } else { struct dentry *dentry; - file = fget_light(dfd, &fput_needed); + file = fget_raw_light(dfd, &fput_needed); retval = -EBADF; if (!file) goto out_fail; dentry = file->f_path.dentry; - retval = -ENOTDIR; - if (!S_ISDIR(dentry->d_inode->i_mode)) - goto fput_fail; + if (*name) { + retval = -ENOTDIR; + if (!S_ISDIR(dentry->d_inode->i_mode)) + goto fput_fail; - retval = file_permission(file, MAY_EXEC); - if (retval) - goto fput_fail; + retval = file_permission(file, MAY_EXEC); + if (retval) + goto fput_fail; + } nd->path = file->f_path; - if (fput_needed) - nd->file = file; - - nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); - br_read_lock(vfsmount_lock); - rcu_read_lock(); + if (flags & LOOKUP_RCU) { + if (fput_needed) + *fp = file; + nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); + br_read_lock(vfsmount_lock); + rcu_read_lock(); + } else { + path_get(&file->f_path); + fput_light(file, fput_needed); + } } + nd->inode = nd->path.dentry->d_inode; return 0; @@ -1648,60 +1586,23 @@ out_fail: return retval; } -static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd) +static inline int lookup_last(struct nameidata *nd, struct path *path) { - int retval = 0; - int fput_needed; - struct file *file; - - nd->last_type = LAST_ROOT; /* if there are only slashes... */ - nd->flags = flags; - nd->depth = 0; - nd->root.mnt = NULL; + if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) + nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; - if (*name=='/') { - set_root(nd); - nd->path = nd->root; - path_get(&nd->root); - } else if (dfd == AT_FDCWD) { - get_fs_pwd(current->fs, &nd->path); - } else { - struct dentry *dentry; - - file = fget_light(dfd, &fput_needed); - retval = -EBADF; - if (!file) - goto out_fail; - - dentry = file->f_path.dentry; - - retval = -ENOTDIR; - if (!S_ISDIR(dentry->d_inode->i_mode)) - goto fput_fail; - - retval = file_permission(file, MAY_EXEC); - if (retval) - goto fput_fail; - - nd->path = file->f_path; - path_get(&file->f_path); - - fput_light(file, fput_needed); - } - nd->inode = nd->path.dentry->d_inode; - return 0; - -fput_fail: - fput_light(file, fput_needed); -out_fail: - return retval; + nd->flags &= ~LOOKUP_PARENT; + return walk_component(nd, path, &nd->last, nd->last_type, + nd->flags & LOOKUP_FOLLOW); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ -static int do_path_lookup(int dfd, const char *name, +static int path_lookupat(int dfd, const char *name, unsigned int flags, struct nameidata *nd) { - int retval; + struct file *base = NULL; + struct path path; + int err; /* * Path walking is largely split up into 2 different synchronisation @@ -1717,44 +1618,75 @@ static int do_path_lookup(int dfd, const char *name, * be handled by restarting a traditional ref-walk (which will always * be able to complete). */ - retval = path_init_rcu(dfd, name, flags, nd); - if (unlikely(retval)) - return retval; - retval = path_walk_rcu(name, nd); - path_finish_rcu(nd); - if (nd->root.mnt) { - path_put(&nd->root); - nd->root.mnt = NULL; + err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base); + + if (unlikely(err)) + return err; + + current->total_link_count = 0; + err = link_path_walk(name, nd); + + if (!err && !(flags & LOOKUP_PARENT)) { + err = lookup_last(nd, &path); + while (err > 0) { + void *cookie; + struct path link = path; + nd->flags |= LOOKUP_PARENT; + err = follow_link(&link, nd, &cookie); + if (!err) + err = lookup_last(nd, &path); + put_link(nd, &link, cookie); + } } - if (unlikely(retval == -ECHILD || retval == -ESTALE)) { - /* slower, locked walk */ - if (retval == -ESTALE) - flags |= LOOKUP_REVAL; - retval = path_init(dfd, name, flags, nd); - if (unlikely(retval)) - return retval; - retval = path_walk(name, nd); - if (nd->root.mnt) { - path_put(&nd->root); - nd->root.mnt = NULL; + if (nd->flags & LOOKUP_RCU) { + /* went all way through without dropping RCU */ + BUG_ON(err); + if (nameidata_drop_rcu_last(nd)) + err = -ECHILD; + } + + if (!err) + err = handle_reval_path(nd); + + if (!err && nd->flags & LOOKUP_DIRECTORY) { + if (!nd->inode->i_op->lookup) { + path_put(&nd->path); + return -ENOTDIR; } } + if (base) + fput(base); + + if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) { + path_put(&nd->root); + nd->root.mnt = NULL; + } + return err; +} + +static int do_path_lookup(int dfd, const char *name, + unsigned int flags, struct nameidata *nd) +{ + int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd); + if (unlikely(retval == -ECHILD)) + retval = path_lookupat(dfd, name, flags, nd); + if (unlikely(retval == -ESTALE)) + retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd); + if (likely(!retval)) { if (unlikely(!audit_dummy_context())) { if (nd->path.dentry && nd->inode) audit_inode(name, nd->path.dentry); } } - return retval; } -int path_lookup(const char *name, unsigned int flags, - struct nameidata *nd) +int kern_path_parent(const char *name, struct nameidata *nd) { - return do_path_lookup(AT_FDCWD, name, flags, nd); + return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd); } int kern_path(const char *name, unsigned int flags, struct path *path) @@ -1778,29 +1710,10 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct nameidata *nd) { - int retval; - - /* same as do_path_lookup */ - nd->last_type = LAST_ROOT; - nd->flags = flags; - nd->depth = 0; - - nd->path.dentry = dentry; - nd->path.mnt = mnt; - path_get(&nd->path); - nd->root = nd->path; - path_get(&nd->root); - nd->inode = nd->path.dentry->d_inode; - - retval = path_walk(name, nd); - if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && - nd->inode)) - audit_inode(name, nd->path.dentry); - - path_put(&nd->root); - nd->root.mnt = NULL; - - return retval; + nd->root.dentry = dentry; + nd->root.mnt = mnt; + /* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */ + return do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, nd); } static struct dentry *__lookup_hash(struct qstr *name, @@ -1815,17 +1728,6 @@ static struct dentry *__lookup_hash(struct qstr *name, return ERR_PTR(err); /* - * See if the low-level filesystem might want - * to use its own hash.. - */ - if (base->d_flags & DCACHE_OP_HASH) { - err = base->d_op->d_hash(base, inode, name); - dentry = ERR_PTR(err); - if (err < 0) - goto out; - } - - /* * Don't bother with __d_lookup: callers are for creat as * well as unlink, so a lot of the time it would cost * a double lookup. @@ -1837,7 +1739,7 @@ static struct dentry *__lookup_hash(struct qstr *name, if (!dentry) dentry = d_alloc_and_lookup(base, name, nd); -out: + return dentry; } @@ -1851,28 +1753,6 @@ static struct dentry *lookup_hash(struct nameidata *nd) return __lookup_hash(&nd->last, nd->path.dentry, nd); } -static int __lookup_one_len(const char *name, struct qstr *this, - struct dentry *base, int len) -{ - unsigned long hash; - unsigned int c; - - this->name = name; - this->len = len; - if (!len) - return -EACCES; - - hash = init_name_hash(); - while (len--) { - c = *(const unsigned char *)name++; - if (c == '/' || c == '\0') - return -EACCES; - hash = partial_name_hash(c, hash); - } - this->hash = end_name_hash(hash); - return 0; -} - /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup @@ -1886,14 +1766,34 @@ static int __lookup_one_len(const char *name, struct qstr *this, */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { - int err; struct qstr this; + unsigned long hash; + unsigned int c; WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex)); - err = __lookup_one_len(name, &this, base, len); - if (err) - return ERR_PTR(err); + this.name = name; + this.len = len; + if (!len) + return ERR_PTR(-EACCES); + + hash = init_name_hash(); + while (len--) { + c = *(const unsigned char *)name++; + if (c == '/' || c == '\0') + return ERR_PTR(-EACCES); + hash = partial_name_hash(c, hash); + } + this.hash = end_name_hash(hash); + /* + * See if the low-level filesystem might want + * to use its own hash.. + */ + if (base->d_flags & DCACHE_OP_HASH) { + int err = base->d_op->d_hash(base, base->d_inode, &this); + if (err < 0) + return ERR_PTR(err); + } return __lookup_hash(&this, base, NULL); } @@ -1902,7 +1802,7 @@ int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { struct nameidata nd; - char *tmp = getname(name); + char *tmp = getname_flags(name, flags); int err = PTR_ERR(tmp); if (!IS_ERR(tmp)) { @@ -2082,12 +1982,16 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode, return error; } -int may_open(struct path *path, int acc_mode, int flag) +static int may_open(struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; + /* O_PATH? */ + if (!acc_mode) + return 0; + if (!inode) return -ENOENT; @@ -2156,34 +2060,6 @@ static int handle_truncate(struct file *filp) } /* - * Be careful about ever adding any more callers of this - * function. Its flags must be in the namei format, not - * what get passed to sys_open(). - */ -static int __open_namei_create(struct nameidata *nd, struct path *path, - int open_flag, int mode) -{ - int error; - struct dentry *dir = nd->path.dentry; - - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); - error = security_path_mknod(&nd->path, path->dentry, mode, 0); - if (error) - goto out_unlock; - error = vfs_create(dir->d_inode, path->dentry, mode, nd); -out_unlock: - mutex_unlock(&dir->d_inode->i_mutex); - dput(nd->path.dentry); - nd->path.dentry = path->dentry; - - if (error) - return error; - /* Don't check for write permission, don't truncate */ - return may_open(&nd->path, 0, open_flag & ~O_TRUNC); -} - -/* * Note that while the flag value (low two bits) for sys_open means: * 00 - read-only * 01 - write-only @@ -2207,128 +2083,115 @@ static inline int open_to_namei_flags(int flag) return flag; } -static int open_will_truncate(int flag, struct inode *inode) -{ - /* - * We'll never write to the fs underlying - * a device file. - */ - if (special_file(inode->i_mode)) - return 0; - return (flag & O_TRUNC); -} - -static struct file *finish_open(struct nameidata *nd, - int open_flag, int acc_mode) -{ - struct file *filp; - int will_truncate; - int error; - - will_truncate = open_will_truncate(open_flag, nd->path.dentry->d_inode); - if (will_truncate) { - error = mnt_want_write(nd->path.mnt); - if (error) - goto exit; - } - error = may_open(&nd->path, acc_mode, open_flag); - if (error) { - if (will_truncate) - mnt_drop_write(nd->path.mnt); - goto exit; - } - filp = nameidata_to_filp(nd); - if (!IS_ERR(filp)) { - error = ima_file_check(filp, acc_mode); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } - if (!IS_ERR(filp)) { - if (will_truncate) { - error = handle_truncate(filp); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } - } - /* - * It is now safe to drop the mnt write - * because the filp has had a write taken - * on its behalf. - */ - if (will_truncate) - mnt_drop_write(nd->path.mnt); - path_put(&nd->path); - return filp; - -exit: - if (!IS_ERR(nd->intent.open.file)) - release_open_intent(nd); - path_put(&nd->path); - return ERR_PTR(error); -} - /* - * Handle O_CREAT case for do_filp_open + * Handle the last step of open() */ static struct file *do_last(struct nameidata *nd, struct path *path, - int open_flag, int acc_mode, - int mode, const char *pathname) + const struct open_flags *op, const char *pathname) { struct dentry *dir = nd->path.dentry; + struct dentry *dentry; + int open_flag = op->open_flag; + int will_truncate = open_flag & O_TRUNC; + int want_write = 0; + int acc_mode = op->acc_mode; struct file *filp; - int error = -EISDIR; + int error; + + nd->flags &= ~LOOKUP_PARENT; + nd->flags |= op->intent; switch (nd->last_type) { case LAST_DOTDOT: - follow_dotdot(nd); - dir = nd->path.dentry; case LAST_DOT: - if (need_reval_dot(dir)) { - int status = d_revalidate(nd->path.dentry, nd); - if (!status) - status = -ESTALE; - if (status < 0) { - error = status; - goto exit; - } - } + error = handle_dots(nd, nd->last_type); + if (error) + return ERR_PTR(error); /* fallthrough */ case LAST_ROOT: - goto exit; + if (nd->flags & LOOKUP_RCU) { + if (nameidata_drop_rcu_last(nd)) + return ERR_PTR(-ECHILD); + } + error = handle_reval_path(nd); + if (error) + goto exit; + audit_inode(pathname, nd->path.dentry); + if (open_flag & O_CREAT) { + error = -EISDIR; + goto exit; + } + goto ok; case LAST_BIND: + /* can't be RCU mode here */ + error = handle_reval_path(nd); + if (error) + goto exit; audit_inode(pathname, dir); goto ok; } + if (!(open_flag & O_CREAT)) { + int symlink_ok = 0; + if (nd->last.name[nd->last.len]) + nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; + if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW)) + symlink_ok = 1; + /* we _can_ be in RCU mode here */ + error = walk_component(nd, path, &nd->last, LAST_NORM, + !symlink_ok); + if (error < 0) + return ERR_PTR(error); + if (error) /* symlink */ + return NULL; + /* sayonara */ + if (nd->flags & LOOKUP_RCU) { + if (nameidata_drop_rcu_last(nd)) + return ERR_PTR(-ECHILD); + } + + error = -ENOTDIR; + if (nd->flags & LOOKUP_DIRECTORY) { + if (!nd->inode->i_op->lookup) + goto exit; + } + audit_inode(pathname, nd->path.dentry); + goto ok; + } + + /* create side of things */ + + if (nd->flags & LOOKUP_RCU) { + if (nameidata_drop_rcu_last(nd)) + return ERR_PTR(-ECHILD); + } + + audit_inode(pathname, dir); + error = -EISDIR; /* trailing slashes? */ if (nd->last.name[nd->last.len]) goto exit; mutex_lock(&dir->d_inode->i_mutex); - path->dentry = lookup_hash(nd); - path->mnt = nd->path.mnt; - - error = PTR_ERR(path->dentry); - if (IS_ERR(path->dentry)) { + dentry = lookup_hash(nd); + error = PTR_ERR(dentry); + if (IS_ERR(dentry)) { mutex_unlock(&dir->d_inode->i_mutex); goto exit; } - if (IS_ERR(nd->intent.open.file)) { - error = PTR_ERR(nd->intent.open.file); - goto exit_mutex_unlock; - } + path->dentry = dentry; + path->mnt = nd->path.mnt; /* Negative dentry, just create the file */ - if (!path->dentry->d_inode) { + if (!dentry->d_inode) { + int mode = op->mode; + if (!IS_POSIXACL(dir->d_inode)) + mode &= ~current_umask(); /* * This write is needed to ensure that a - * ro->rw transition does not occur between + * rw->ro transition does not occur between * the time when the file is created and when * a permanent write count is taken through * the 'struct file' in nameidata_to_filp(). @@ -2336,22 +2199,21 @@ static struct file *do_last(struct nameidata *nd, struct path *path, error = mnt_want_write(nd->path.mnt); if (error) goto exit_mutex_unlock; - error = __open_namei_create(nd, path, open_flag, mode); - if (error) { - mnt_drop_write(nd->path.mnt); - goto exit; - } - filp = nameidata_to_filp(nd); - mnt_drop_write(nd->path.mnt); - path_put(&nd->path); - if (!IS_ERR(filp)) { - error = ima_file_check(filp, acc_mode); - if (error) { - fput(filp); - filp = ERR_PTR(error); - } - } - return filp; + want_write = 1; + /* Don't check for write permission, don't truncate */ + open_flag &= ~O_TRUNC; + will_truncate = 0; + acc_mode = MAY_OPEN; + error = security_path_mknod(&nd->path, dentry, mode, 0); + if (error) + goto exit_mutex_unlock; + error = vfs_create(dir->d_inode, dentry, mode, nd); + if (error) + goto exit_mutex_unlock; + mutex_unlock(&dir->d_inode->i_mutex); + dput(nd->path.dentry); + nd->path.dentry = dentry; + goto common; } /* @@ -2381,7 +2243,40 @@ static struct file *do_last(struct nameidata *nd, struct path *path, if (S_ISDIR(nd->inode->i_mode)) goto exit; ok: - filp = finish_open(nd, open_flag, acc_mode); + if (!S_ISREG(nd->inode->i_mode)) + will_truncate = 0; + + if (will_truncate) { + error = mnt_want_write(nd->path.mnt); + if (error) + goto exit; + want_write = 1; + } +common: + error = may_open(&nd->path, acc_mode, open_flag); + if (error) + goto exit; + filp = nameidata_to_filp(nd); + if (!IS_ERR(filp)) { + error = ima_file_check(filp, op->acc_mode); + if (error) { + fput(filp); + filp = ERR_PTR(error); + } + } + if (!IS_ERR(filp)) { + if (will_truncate) { + error = handle_truncate(filp); + if (error) { + fput(filp); + filp = ERR_PTR(error); + } + } + } +out: + if (want_write) + mnt_drop_write(nd->path.mnt); + path_put(&nd->path); return filp; exit_mutex_unlock: @@ -2389,199 +2284,103 @@ exit_mutex_unlock: exit_dput: path_put_conditional(path, nd); exit: - if (!IS_ERR(nd->intent.open.file)) - release_open_intent(nd); - path_put(&nd->path); - return ERR_PTR(error); + filp = ERR_PTR(error); + goto out; } -/* - * Note that the low bits of the passed in "open_flag" - * are not the same as in the local variable "flag". See - * open_to_namei_flags() for more details. - */ -struct file *do_filp_open(int dfd, const char *pathname, - int open_flag, int mode, int acc_mode) +static struct file *path_openat(int dfd, const char *pathname, + struct nameidata *nd, const struct open_flags *op, int flags) { + struct file *base = NULL; struct file *filp; - struct nameidata nd; - int error; struct path path; - int count = 0; - int flag = open_to_namei_flags(open_flag); - int flags; - - if (!(open_flag & O_CREAT)) - mode = 0; - - /* Must never be set by userspace */ - open_flag &= ~FMODE_NONOTIFY; - - /* - * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only - * check for O_DSYNC if the need any syncing at all we enforce it's - * always set instead of having to deal with possibly weird behaviour - * for malicious applications setting only __O_SYNC. - */ - if (open_flag & __O_SYNC) - open_flag |= O_DSYNC; - - if (!acc_mode) - acc_mode = MAY_OPEN | ACC_MODE(open_flag); - - /* O_TRUNC implies we need access checks for write permissions */ - if (open_flag & O_TRUNC) - acc_mode |= MAY_WRITE; - - /* Allow the LSM permission hook to distinguish append - access from general write access. */ - if (open_flag & O_APPEND) - acc_mode |= MAY_APPEND; - - flags = LOOKUP_OPEN; - if (open_flag & O_CREAT) { - flags |= LOOKUP_CREATE; - if (open_flag & O_EXCL) - flags |= LOOKUP_EXCL; - } - if (open_flag & O_DIRECTORY) - flags |= LOOKUP_DIRECTORY; - if (!(open_flag & O_NOFOLLOW)) - flags |= LOOKUP_FOLLOW; + int error; filp = get_empty_filp(); if (!filp) return ERR_PTR(-ENFILE); - filp->f_flags = open_flag; - nd.intent.open.file = filp; - nd.intent.open.flags = flag; - nd.intent.open.create_mode = mode; + filp->f_flags = op->open_flag; + nd->intent.open.file = filp; + nd->intent.open.flags = open_to_namei_flags(op->open_flag); + nd->intent.open.create_mode = op->mode; - if (open_flag & O_CREAT) - goto creat; - - /* !O_CREAT, simple open */ - error = do_path_lookup(dfd, pathname, flags, &nd); + error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base); if (unlikely(error)) goto out_filp; - error = -ELOOP; - if (!(nd.flags & LOOKUP_FOLLOW)) { - if (nd.inode->i_op->follow_link) - goto out_path; - } - error = -ENOTDIR; - if (nd.flags & LOOKUP_DIRECTORY) { - if (!nd.inode->i_op->lookup) - goto out_path; - } - audit_inode(pathname, nd.path.dentry); - filp = finish_open(&nd, open_flag, acc_mode); - return filp; -creat: - /* OK, have to create the file. Find the parent. */ - error = path_init_rcu(dfd, pathname, - LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd); - if (error) - goto out_filp; - error = path_walk_rcu(pathname, &nd); - path_finish_rcu(&nd); - if (unlikely(error == -ECHILD || error == -ESTALE)) { - /* slower, locked walk */ - if (error == -ESTALE) { -reval: - flags |= LOOKUP_REVAL; - } - error = path_init(dfd, pathname, - LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd); - if (error) - goto out_filp; - - error = path_walk_simple(pathname, &nd); - } + current->total_link_count = 0; + error = link_path_walk(pathname, nd); if (unlikely(error)) goto out_filp; - if (unlikely(!audit_dummy_context())) - audit_inode(pathname, nd.path.dentry); - /* - * We have the parent and last component. - */ - nd.flags = flags; - filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname); + filp = do_last(nd, &path, op, pathname); while (unlikely(!filp)) { /* trailing symlink */ struct path link = path; - struct inode *linki = link.dentry->d_inode; void *cookie; - error = -ELOOP; - if (!(nd.flags & LOOKUP_FOLLOW)) - goto exit_dput; - if (count++ == 32) - goto exit_dput; - /* - * This is subtle. Instead of calling do_follow_link() we do - * the thing by hands. The reason is that this way we have zero - * link_count and path_walk() (called from ->follow_link) - * honoring LOOKUP_PARENT. After that we have the parent and - * last component, i.e. we are in the same situation as after - * the first path_walk(). Well, almost - if the last component - * is normal we get its copy stored in nd->last.name and we will - * have to putname() it when we are done. Procfs-like symlinks - * just set LAST_BIND. - */ - nd.flags |= LOOKUP_PARENT; - error = security_inode_follow_link(link.dentry, &nd); - if (error) - goto exit_dput; - error = __do_follow_link(&link, &nd, &cookie); - if (unlikely(error)) { - if (!IS_ERR(cookie) && linki->i_op->put_link) - linki->i_op->put_link(link.dentry, &nd, cookie); - /* nd.path had been dropped */ - nd.path = link; - goto out_path; + if (!(nd->flags & LOOKUP_FOLLOW)) { + path_put_conditional(&path, nd); + path_put(&nd->path); + filp = ERR_PTR(-ELOOP); + break; } - nd.flags &= ~LOOKUP_PARENT; - filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname); - if (linki->i_op->put_link) - linki->i_op->put_link(link.dentry, &nd, cookie); - path_put(&link); + nd->flags |= LOOKUP_PARENT; + nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); + error = follow_link(&link, nd, &cookie); + if (unlikely(error)) + filp = ERR_PTR(error); + else + filp = do_last(nd, &path, op, pathname); + put_link(nd, &link, cookie); } out: - if (nd.root.mnt) - path_put(&nd.root); - if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL)) - goto reval; + if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) + path_put(&nd->root); + if (base) + fput(base); + release_open_intent(nd); return filp; -exit_dput: - path_put_conditional(&path, &nd); -out_path: - path_put(&nd.path); out_filp: - if (!IS_ERR(nd.intent.open.file)) - release_open_intent(&nd); filp = ERR_PTR(error); goto out; } -/** - * filp_open - open file and return file pointer - * - * @filename: path to open - * @flags: open flags as per the open(2) second argument - * @mode: mode for the new file if O_CREAT is set, else ignored - * - * This is the helper to open a file from kernelspace if you really - * have to. But in generally you should not do this, so please move - * along, nothing to see here.. - */ -struct file *filp_open(const char *filename, int flags, int mode) +struct file *do_filp_open(int dfd, const char *pathname, + const struct open_flags *op, int flags) { - return do_filp_open(AT_FDCWD, filename, flags, mode, 0); + struct nameidata nd; + struct file *filp; + + filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_RCU); + if (unlikely(filp == ERR_PTR(-ECHILD))) + filp = path_openat(dfd, pathname, &nd, op, flags); + if (unlikely(filp == ERR_PTR(-ESTALE))) + filp = path_openat(dfd, pathname, &nd, op, flags | LOOKUP_REVAL); + return filp; +} + +struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, + const char *name, const struct open_flags *op, int flags) +{ + struct nameidata nd; + struct file *file; + + nd.root.mnt = mnt; + nd.root.dentry = dentry; + + flags |= LOOKUP_ROOT; + + if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN) + return ERR_PTR(-ELOOP); + + file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU); + if (unlikely(file == ERR_PTR(-ECHILD))) + file = path_openat(-1, name, &nd, op, flags); + if (unlikely(file == ERR_PTR(-ESTALE))) + file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL); + return file; } -EXPORT_SYMBOL(filp_open); /** * lookup_create - lookup a dentry, creating it if it doesn't exist @@ -3120,7 +2919,11 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de return error; mutex_lock(&inode->i_mutex); - error = dir->i_op->link(old_dentry, dir, new_dentry); + /* Make sure we don't allow creating hardlink to an unlinked file */ + if (inode->i_nlink == 0) + error = -ENOENT; + else + error = dir->i_op->link(old_dentry, dir, new_dentry); mutex_unlock(&inode->i_mutex); if (!error) fsnotify_link(dir, inode, new_dentry); @@ -3142,15 +2945,27 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, struct dentry *new_dentry; struct nameidata nd; struct path old_path; + int how = 0; int error; char *to; - if ((flags & ~AT_SYMLINK_FOLLOW) != 0) + if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; + /* + * To use null names we require CAP_DAC_READ_SEARCH + * This ensures that not everyone will be able to create + * handlink using the passed filedescriptor. + */ + if (flags & AT_EMPTY_PATH) { + if (!capable(CAP_DAC_READ_SEARCH)) + return -ENOENT; + how = LOOKUP_EMPTY; + } + + if (flags & AT_SYMLINK_FOLLOW) + how |= LOOKUP_FOLLOW; - error = user_path_at(olddfd, oldname, - flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0, - &old_path); + error = user_path_at(olddfd, oldname, how, &old_path); if (error) return error; @@ -3587,7 +3402,7 @@ EXPORT_SYMBOL(page_readlink); EXPORT_SYMBOL(__page_symlink); EXPORT_SYMBOL(page_symlink); EXPORT_SYMBOL(page_symlink_inode_operations); -EXPORT_SYMBOL(path_lookup); +EXPORT_SYMBOL(kern_path_parent); EXPORT_SYMBOL(kern_path); EXPORT_SYMBOL(vfs_path_lookup); EXPORT_SYMBOL(inode_permission); diff --git a/fs/namespace.c b/fs/namespace.c index 7b0b953..dffe6f4 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1002,6 +1002,18 @@ const struct seq_operations mounts_op = { .show = show_vfsmnt }; +static int uuid_is_nil(u8 *uuid) +{ + int i; + u8 *cp = (u8 *)uuid; + + for (i = 0; i < 16; i++) { + if (*cp++) + return 0; + } + return 1; +} + static int show_mountinfo(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; @@ -1040,6 +1052,10 @@ static int show_mountinfo(struct seq_file *m, void *v) if (IS_MNT_UNBINDABLE(mnt)) seq_puts(m, " unbindable"); + if (!uuid_is_nil(mnt->mnt_sb->s_uuid)) + /* print the uuid */ + seq_printf(m, " uuid:%pU", mnt->mnt_sb->s_uuid); + /* Filesystem specific data */ seq_puts(m, " - "); show_type(m, sb); @@ -1244,7 +1260,7 @@ static int do_umount(struct vfsmount *mnt, int flags) */ br_write_lock(vfsmount_lock); if (mnt_get_count(mnt) != 2) { - br_write_lock(vfsmount_lock); + br_write_unlock(vfsmount_lock); return -EBUSY; } br_write_unlock(vfsmount_lock); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 1990165..e3d2942 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -135,33 +135,6 @@ out_err: #if defined(CONFIG_NFS_V4_1) /* - * * CB_SEQUENCE operations will fail until the callback sessionid is set. - * */ -int nfs4_set_callback_sessionid(struct nfs_client *clp) -{ - struct svc_serv *serv = clp->cl_rpcclient->cl_xprt->bc_serv; - struct nfs4_sessionid *bc_sid; - - if (!serv->sv_bc_xprt) - return -EINVAL; - - /* on success freed in xprt_free */ - bc_sid = kmalloc(sizeof(struct nfs4_sessionid), GFP_KERNEL); - if (!bc_sid) - return -ENOMEM; - memcpy(bc_sid->data, &clp->cl_session->sess_id.data, - NFS4_MAX_SESSIONID_LEN); - spin_lock_bh(&serv->sv_cb_lock); - serv->sv_bc_xprt->xpt_bc_sid = bc_sid; - spin_unlock_bh(&serv->sv_cb_lock); - dprintk("%s set xpt_bc_sid=%u:%u:%u:%u for sv_bc_xprt %p\n", __func__, - ((u32 *)bc_sid->data)[0], ((u32 *)bc_sid->data)[1], - ((u32 *)bc_sid->data)[2], ((u32 *)bc_sid->data)[3], - serv->sv_bc_xprt); - return 0; -} - -/* * The callback service for NFSv4.1 callbacks */ static int @@ -266,10 +239,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt, struct nfs_callback_data *cb_info) { } -int nfs4_set_callback_sessionid(struct nfs_client *clp) -{ - return 0; -} #endif /* CONFIG_NFS_V4_1 */ /* @@ -359,78 +328,58 @@ void nfs_callback_down(int minorversion) mutex_unlock(&nfs_callback_mutex); } -static int check_gss_callback_principal(struct nfs_client *clp, - struct svc_rqst *rqstp) +/* Boolean check of RPC_AUTH_GSS principal */ +int +check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp) { struct rpc_clnt *r = clp->cl_rpcclient; char *p = svc_gss_principal(rqstp); + if (rqstp->rq_authop->flavour != RPC_AUTH_GSS) + return 1; + /* No RPC_AUTH_GSS on NFSv4.1 back channel yet */ if (clp->cl_minorversion != 0) - return SVC_DROP; + return 0; /* * It might just be a normal user principal, in which case * userspace won't bother to tell us the name at all. */ if (p == NULL) - return SVC_DENIED; + return 0; /* Expect a GSS_C_NT_HOSTBASED_NAME like "nfs@serverhostname" */ if (memcmp(p, "nfs@", 4) != 0) - return SVC_DENIED; + return 0; p += 4; if (strcmp(p, r->cl_server) != 0) - return SVC_DENIED; - return SVC_OK; + return 0; + return 1; } -/* pg_authenticate method helper */ -static struct nfs_client *nfs_cb_find_client(struct svc_rqst *rqstp) -{ - struct nfs4_sessionid *sessionid = bc_xprt_sid(rqstp); - int is_cb_compound = rqstp->rq_proc == CB_COMPOUND ? 1 : 0; - - dprintk("--> %s rq_proc %d\n", __func__, rqstp->rq_proc); - if (svc_is_backchannel(rqstp)) - /* Sessionid (usually) set after CB_NULL ping */ - return nfs4_find_client_sessionid(svc_addr(rqstp), sessionid, - is_cb_compound); - else - /* No callback identifier in pg_authenticate */ - return nfs4_find_client_no_ident(svc_addr(rqstp)); -} - -/* pg_authenticate method for nfsv4 callback threads. */ +/* + * pg_authenticate method for nfsv4 callback threads. + * + * The authflavor has been negotiated, so an incorrect flavor is a server + * bug. Drop packets with incorrect authflavor. + * + * All other checking done after NFS decoding where the nfs_client can be + * found in nfs4_callback_compound + */ static int nfs_callback_authenticate(struct svc_rqst *rqstp) { - struct nfs_client *clp; - RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); - int ret = SVC_OK; - - /* Don't talk to strangers */ - clp = nfs_cb_find_client(rqstp); - if (clp == NULL) - return SVC_DROP; - - dprintk("%s: %s NFSv4 callback!\n", __func__, - svc_print_addr(rqstp, buf, sizeof(buf))); - switch (rqstp->rq_authop->flavour) { - case RPC_AUTH_NULL: - if (rqstp->rq_proc != CB_NULL) - ret = SVC_DENIED; - break; - case RPC_AUTH_UNIX: - break; - case RPC_AUTH_GSS: - ret = check_gss_callback_principal(clp, rqstp); - break; - default: - ret = SVC_DENIED; + case RPC_AUTH_NULL: + if (rqstp->rq_proc != CB_NULL) + return SVC_DROP; + break; + case RPC_AUTH_GSS: + /* No RPC_AUTH_GSS support yet in NFSv4.1 */ + if (svc_is_backchannel(rqstp)) + return SVC_DROP; } - nfs_put_client(clp); - return ret; + return SVC_OK; } /* diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index d3b44f9..46d93ce 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -7,6 +7,7 @@ */ #ifndef __LINUX_FS_NFS_CALLBACK_H #define __LINUX_FS_NFS_CALLBACK_H +#include <linux/sunrpc/svc.h> #define NFS4_CALLBACK 0x40000000 #define NFS4_CALLBACK_XDRSIZE 2048 @@ -37,7 +38,6 @@ enum nfs4_callback_opnum { struct cb_process_state { __be32 drc_status; struct nfs_client *clp; - struct nfs4_sessionid *svc_sid; /* v4.1 callback service sessionid */ }; struct cb_compound_hdr_arg { @@ -168,7 +168,7 @@ extern unsigned nfs4_callback_layoutrecall( extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses); extern void nfs4_cb_take_slot(struct nfs_client *clp); #endif /* CONFIG_NFS_V4_1 */ - +extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *); extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *res, struct cb_process_state *cps); diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 4bb91cb..8958757 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -373,17 +373,11 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, { struct nfs_client *clp; int i; - __be32 status; + __be32 status = htonl(NFS4ERR_BADSESSION); cps->clp = NULL; - status = htonl(NFS4ERR_BADSESSION); - /* Incoming session must match the callback session */ - if (memcmp(&args->csa_sessionid, cps->svc_sid, NFS4_MAX_SESSIONID_LEN)) - goto out; - - clp = nfs4_find_client_sessionid(args->csa_addr, - &args->csa_sessionid, 1); + clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid); if (clp == NULL) goto out; @@ -414,9 +408,9 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1; res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1; nfs4_cb_take_slot(clp); - cps->clp = clp; /* put in nfs4_callback_compound */ out: + cps->clp = clp; /* put in nfs4_callback_compound */ for (i = 0; i < args->csa_nrclists; i++) kfree(args->csa_rclists[i].rcl_refcalls); kfree(args->csa_rclists); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 23112c2..14e0f93 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -794,10 +794,9 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r if (hdr_arg.minorversion == 0) { cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident); - if (!cps.clp) + if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp)) return rpc_drop_reply; - } else - cps.svc_sid = bc_xprt_sid(rqstp); + } hdr_res.taglen = hdr_arg.taglen; hdr_res.tag = hdr_arg.tag; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 192f2f8..bd3ca32 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1206,16 +1206,11 @@ nfs4_find_client_ident(int cb_ident) * For CB_COMPOUND calls, find a client by IP address, protocol version, * minorversion, and sessionID * - * CREATE_SESSION triggers a CB_NULL ping from servers. The callback service - * sessionid can only be set after the CREATE_SESSION return, so a CB_NULL - * can arrive before the callback sessionid is set. For CB_NULL calls, - * find a client by IP address protocol version, and minorversion. - * * Returns NULL if no such client */ struct nfs_client * nfs4_find_client_sessionid(const struct sockaddr *addr, - struct nfs4_sessionid *sid, int is_cb_compound) + struct nfs4_sessionid *sid) { struct nfs_client *clp; @@ -1227,9 +1222,9 @@ nfs4_find_client_sessionid(const struct sockaddr *addr, if (!nfs4_has_session(clp)) continue; - /* Match sessionid unless cb_null call*/ - if (is_cb_compound && (memcmp(clp->cl_session->sess_id.data, - sid->data, NFS4_MAX_SESSIONID_LEN) != 0)) + /* Match sessionid*/ + if (memcmp(clp->cl_session->sess_id.data, + sid->data, NFS4_MAX_SESSIONID_LEN) != 0) continue; atomic_inc(&clp->cl_count); @@ -1244,7 +1239,7 @@ nfs4_find_client_sessionid(const struct sockaddr *addr, struct nfs_client * nfs4_find_client_sessionid(const struct sockaddr *addr, - struct nfs4_sessionid *sid, int is_cb_compound) + struct nfs4_sessionid *sid) { return NULL; } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 364e432..bbbc6bf 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -23,8 +23,6 @@ static void nfs_do_free_delegation(struct nfs_delegation *delegation) { - if (delegation->cred) - put_rpccred(delegation->cred); kfree(delegation); } @@ -37,6 +35,10 @@ static void nfs_free_delegation_callback(struct rcu_head *head) static void nfs_free_delegation(struct nfs_delegation *delegation) { + if (delegation->cred) { + put_rpccred(delegation->cred); + delegation->cred = NULL; + } call_rcu(&delegation->rcu, nfs_free_delegation_callback); } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e6ace0d..9943a75 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -407,15 +407,18 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + if (put_dreq(dreq)) nfs_direct_complete(dreq); - - if (requested_bytes != 0) - return 0; - - if (result < 0) - return result; - return -EIO; + return 0; } static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, @@ -841,15 +844,18 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + if (put_dreq(dreq)) nfs_direct_write_complete(dreq, dreq->inode); - - if (requested_bytes != 0) - return 0; - - if (result < 0) - return result; - return -EIO; + return 0; } static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index d851242..2f8e618 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -37,6 +37,7 @@ #include <linux/inet.h> #include <linux/nfs_xdr.h> #include <linux/slab.h> +#include <linux/compat.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -89,7 +90,11 @@ int nfs_wait_bit_killable(void *word) */ u64 nfs_compat_user_ino64(u64 fileid) { - int ino; +#ifdef CONFIG_COMPAT + compat_ulong_t ino; +#else + unsigned long ino; +#endif if (enable_ino64) return fileid; @@ -881,9 +886,10 @@ out: return ret; } -static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) +static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); + unsigned long ret = 0; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) @@ -891,25 +897,32 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->change_attr = fattr->change_attr; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; + ret |= NFS_INO_INVALID_ATTR; } /* If we have atomic WCC data, we may update some attributes */ if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) - && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) - memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); + && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) { + memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); + ret |= NFS_INO_INVALID_ATTR; + } if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) { - memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_INVALID_DATA; + memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); + if (S_ISDIR(inode->i_mode)) + nfsi->cache_validity |= NFS_INO_INVALID_DATA; + ret |= NFS_INO_INVALID_ATTR; } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) - && nfsi->npages == 0) - i_size_write(inode, nfs_size_to_loff_t(fattr->size)); + && nfsi->npages == 0) { + i_size_write(inode, nfs_size_to_loff_t(fattr->size)); + ret |= NFS_INO_INVALID_ATTR; + } + return ret; } /** @@ -1223,7 +1236,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) | NFS_INO_REVAL_PAGECACHE); /* Do atomic weak cache consistency updates */ - nfs_wcc_update_inode(inode, fattr); + invalid |= nfs_wcc_update_inode(inode, fattr); /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 4644f04..cf9fdbd 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -133,8 +133,7 @@ extern void nfs_put_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_no_ident(const struct sockaddr *); extern struct nfs_client *nfs4_find_client_ident(int); extern struct nfs_client * -nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *, - int); +nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *); extern struct nfs_server *nfs_create_server( const struct nfs_parsed_mount_data *, struct nfs_fh *); diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 9f88c5f..2743427 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -311,8 +311,8 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, if (!nfs_server_capable(inode, NFS_CAP_ACLS)) goto out; - /* We are doing this here, because XDR marshalling can only - return -ENOMEM. */ + /* We are doing this here because XDR marshalling does not + * return any results, it BUGs. */ status = -ENOSPC; if (acl != NULL && acl->a_count > NFS_ACL_MAX_ENTRIES) goto out; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 01c5e8b..183c6b1 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1328,10 +1328,13 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, encode_nfs_fh3(xdr, NFS_FH(args->inode)); encode_uint32(xdr, args->mask); + + base = req->rq_slen; if (args->npages != 0) xdr_write_pages(xdr, args->pages, 0, args->len); + else + xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE); - base = req->rq_slen; error = nfsacl_encode(xdr->buf, base, args->inode, (args->mask & NFS_ACL) ? args->acl_access : NULL, 1, 0); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 7a74740..1be36cf 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -298,6 +298,11 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp); #if defined(CONFIG_NFS_V4_1) struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp); struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp); +extern void nfs4_schedule_session_recovery(struct nfs4_session *); +#else +static inline void nfs4_schedule_session_recovery(struct nfs4_session *session) +{ +} #endif /* CONFIG_NFS_V4_1 */ extern struct nfs4_state_owner * nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *); @@ -307,10 +312,9 @@ extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct path *, struct nfs4_state *, fmode_t); extern void nfs4_close_sync(struct path *, struct nfs4_state *, fmode_t); extern void nfs4_state_set_mode_locked(struct nfs4_state *, fmode_t); -extern void nfs4_schedule_state_recovery(struct nfs_client *); +extern void nfs4_schedule_lease_recovery(struct nfs_client *); extern void nfs4_schedule_state_manager(struct nfs_client *); -extern int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state); -extern int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state); +extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_recall_slot(struct nfs_client *clp); extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index 51fe64ac..b73c343 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -214,17 +214,26 @@ decode_and_add_ds(__be32 **pp, struct inode *inode) /* ipv6 length plus port is legal */ if (rlen > INET6_ADDRSTRLEN + 8) { - dprintk("%s Invalid address, length %d\n", __func__, + dprintk("%s: Invalid address, length %d\n", __func__, rlen); goto out_err; } buf = kmalloc(rlen + 1, GFP_KERNEL); + if (!buf) { + dprintk("%s: Not enough memory\n", __func__); + goto out_err; + } buf[rlen] = '\0'; memcpy(buf, r_addr, rlen); /* replace the port dots with dashes for the in4_pton() delimiter*/ for (i = 0; i < 2; i++) { char *res = strrchr(buf, '.'); + if (!res) { + dprintk("%s: Failed finding expected dots in port\n", + __func__); + goto out_free; + } *res = '-'; } @@ -240,7 +249,7 @@ decode_and_add_ds(__be32 **pp, struct inode *inode) port = htons((tmp[0] << 8) | (tmp[1])); ds = nfs4_pnfs_ds_add(inode, ip_addr, port); - dprintk("%s Decoded address and port %s\n", __func__, buf); + dprintk("%s: Decoded address and port %s\n", __func__, buf); out_free: kfree(buf); out_err: diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9d992b0..0a07e35 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -50,6 +50,7 @@ #include <linux/module.h> #include <linux/sunrpc/bc_xprt.h> #include <linux/xattr.h> +#include <linux/utsname.h> #include "nfs4_fs.h" #include "delegation.h" @@ -255,12 +256,13 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, case -NFS4ERR_OPENMODE: if (state == NULL) break; - nfs4_state_mark_reclaim_nograce(clp, state); - goto do_state_recovery; + nfs4_schedule_stateid_recovery(server, state); + goto wait_on_recovery; case -NFS4ERR_STALE_STATEID: case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_EXPIRED: - goto do_state_recovery; + nfs4_schedule_lease_recovery(clp); + goto wait_on_recovery; #if defined(CONFIG_NFS_V4_1) case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -271,7 +273,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, case -NFS4ERR_SEQ_MISORDERED: dprintk("%s ERROR: %d Reset session\n", __func__, errorcode); - nfs4_schedule_state_recovery(clp); + nfs4_schedule_session_recovery(clp->cl_session); exception->retry = 1; break; #endif /* defined(CONFIG_NFS_V4_1) */ @@ -294,8 +296,7 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, } /* We failed to handle the error */ return nfs4_map_errors(ret); -do_state_recovery: - nfs4_schedule_state_recovery(clp); +wait_on_recovery: ret = nfs4_wait_clnt_recover(clp); if (ret == 0) exception->retry = 1; @@ -434,8 +435,8 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res * clp = res->sr_session->clp; do_renew_lease(clp, timestamp); /* Check sequence flags */ - if (atomic_read(&clp->cl_count) > 1) - nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); + if (res->sr_status_flags != 0) + nfs4_schedule_lease_recovery(clp); break; case -NFS4ERR_DELAY: /* The server detected a resend of the RPC call and @@ -1254,14 +1255,13 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - nfs4_schedule_state_recovery( - server->nfs_client); + nfs4_schedule_session_recovery(server->nfs_client->cl_session); goto out; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: /* Don't recall a delegation if it was lost */ - nfs4_schedule_state_recovery(server->nfs_client); + nfs4_schedule_lease_recovery(server->nfs_client); goto out; case -ERESTARTSYS: /* @@ -1270,7 +1270,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state */ case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - nfs4_state_mark_reclaim_nograce(server->nfs_client, state); + nfs4_schedule_stateid_recovery(server, state); case -EKEYEXPIRED: /* * User RPCSEC_GSS context has expired. @@ -1586,7 +1586,7 @@ static int nfs4_recover_expired_lease(struct nfs_server *server) if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) && !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state)) break; - nfs4_schedule_state_recovery(clp); + nfs4_schedule_state_manager(clp); ret = -EIO; } return ret; @@ -3177,7 +3177,7 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata) if (task->tk_status < 0) { /* Unless we're shutting down, schedule state recovery! */ if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) != 0) - nfs4_schedule_state_recovery(clp); + nfs4_schedule_lease_recovery(clp); return; } do_renew_lease(clp, timestamp); @@ -3251,6 +3251,35 @@ static void buf_to_pages(const void *buf, size_t buflen, } } +static int buf_to_pages_noslab(const void *buf, size_t buflen, + struct page **pages, unsigned int *pgbase) +{ + struct page *newpage, **spages; + int rc = 0; + size_t len; + spages = pages; + + do { + len = min_t(size_t, PAGE_CACHE_SIZE, buflen); + newpage = alloc_page(GFP_KERNEL); + + if (newpage == NULL) + goto unwind; + memcpy(page_address(newpage), buf, len); + buf += len; + buflen -= len; + *pages++ = newpage; + rc++; + } while (buflen != 0); + + return rc; + +unwind: + for(; rc > 0; rc--) + __free_page(spages[rc-1]); + return -ENOMEM; +} + struct nfs4_cached_acl { int cached; size_t len; @@ -3419,13 +3448,23 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl .rpc_argp = &arg, .rpc_resp = &res, }; - int ret; + int ret, i; if (!nfs4_server_supports_acls(server)) return -EOPNOTSUPP; + i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase); + if (i < 0) + return i; nfs_inode_return_delegation(inode); - buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase); ret = nfs4_call_sync(server, &msg, &arg, &res, 1); + + /* + * Free each page after tx, so the only ref left is + * held by the network stack + */ + for (; i > 0; i--) + put_page(pages[i-1]); + /* * Acl update can result in inode attribute update. * so mark the attribute cache invalid. @@ -3463,12 +3502,13 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, case -NFS4ERR_OPENMODE: if (state == NULL) break; - nfs4_state_mark_reclaim_nograce(clp, state); - goto do_state_recovery; + nfs4_schedule_stateid_recovery(server, state); + goto wait_on_recovery; case -NFS4ERR_STALE_STATEID: case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_EXPIRED: - goto do_state_recovery; + nfs4_schedule_lease_recovery(clp); + goto wait_on_recovery; #if defined(CONFIG_NFS_V4_1) case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -3479,7 +3519,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, case -NFS4ERR_SEQ_MISORDERED: dprintk("%s ERROR %d, Reset session\n", __func__, task->tk_status); - nfs4_schedule_state_recovery(clp); + nfs4_schedule_session_recovery(clp->cl_session); task->tk_status = 0; return -EAGAIN; #endif /* CONFIG_NFS_V4_1 */ @@ -3496,9 +3536,8 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, } task->tk_status = nfs4_map_errors(task->tk_status); return 0; -do_state_recovery: +wait_on_recovery: rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); - nfs4_schedule_state_recovery(clp); if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); task->tk_status = 0; @@ -4109,7 +4148,7 @@ static void nfs4_lock_release(void *calldata) task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, data->arg.lock_seqid); if (!IS_ERR(task)) - rpc_put_task(task); + rpc_put_task_async(task); dprintk("%s: cancelling lock!\n", __func__); } else nfs_free_seqid(data->arg.lock_seqid); @@ -4133,23 +4172,18 @@ static const struct rpc_call_ops nfs4_recover_lock_ops = { static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_state *lsp, int new_lock_owner, int error) { - struct nfs_client *clp = server->nfs_client; - struct nfs4_state *state = lsp->ls_state; - switch (error) { case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_EXPIRED: + lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED; if (new_lock_owner != 0 || (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0) - nfs4_state_mark_reclaim_nograce(clp, state); - lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED; + nfs4_schedule_stateid_recovery(server, lsp->ls_state); break; case -NFS4ERR_STALE_STATEID: - if (new_lock_owner != 0 || - (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0) - nfs4_state_mark_reclaim_reboot(clp, state); lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED; + case -NFS4ERR_EXPIRED: + nfs4_schedule_lease_recovery(server->nfs_client); }; } @@ -4365,12 +4399,14 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl) case -NFS4ERR_EXPIRED: case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: + nfs4_schedule_lease_recovery(server->nfs_client); + goto out; case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - nfs4_schedule_state_recovery(server->nfs_client); + nfs4_schedule_session_recovery(server->nfs_client->cl_session); goto out; case -ERESTARTSYS: /* @@ -4380,7 +4416,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl) case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OPENMODE: - nfs4_state_mark_reclaim_nograce(server->nfs_client, state); + nfs4_schedule_stateid_recovery(server, state); err = 0; goto out; case -EKEYEXPIRED: @@ -4572,27 +4608,16 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) *p = htonl((u32)clp->cl_boot_time.tv_nsec); args.verifier = &verifier; - while (1) { - args.id_len = scnprintf(args.id, sizeof(args.id), - "%s/%s %u", - clp->cl_ipaddr, - rpc_peeraddr2str(clp->cl_rpcclient, - RPC_DISPLAY_ADDR), - clp->cl_id_uniquifier); - - status = rpc_call_sync(clp->cl_rpcclient, &msg, 0); - - if (status != -NFS4ERR_CLID_INUSE) - break; - - if (signalled()) - break; - - if (++clp->cl_id_uniquifier == 0) - break; - } + args.id_len = scnprintf(args.id, sizeof(args.id), + "%s/%s.%s/%u", + clp->cl_ipaddr, + init_utsname()->nodename, + init_utsname()->domainname, + clp->cl_rpcclient->cl_auth->au_flavor); - status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); + status = rpc_call_sync(clp->cl_rpcclient, &msg, 0); + if (!status) + status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); dprintk("<-- %s status= %d\n", __func__, status); return status; } @@ -4998,10 +5023,20 @@ int nfs4_proc_create_session(struct nfs_client *clp) int status; unsigned *ptr; struct nfs4_session *session = clp->cl_session; + long timeout = 0; + int err; dprintk("--> %s clp=%p session=%p\n", __func__, clp, session); - status = _nfs4_proc_create_session(clp); + do { + status = _nfs4_proc_create_session(clp); + if (status == -NFS4ERR_DELAY) { + err = nfs4_delay(clp->cl_rpcclient, &timeout); + if (err) + status = err; + } + } while (status == -NFS4ERR_DELAY); + if (status) goto out; @@ -5110,7 +5145,7 @@ static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client rpc_delay(task, NFS4_POLL_RETRY_MAX); return -EAGAIN; default: - nfs4_schedule_state_recovery(clp); + nfs4_schedule_lease_recovery(clp); } return 0; } @@ -5197,7 +5232,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr if (IS_ERR(task)) ret = PTR_ERR(task); else - rpc_put_task(task); + rpc_put_task_async(task); dprintk("<-- %s status=%d\n", __func__, ret); return ret; } @@ -5213,8 +5248,13 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred) goto out; } ret = rpc_wait_for_completion_task(task); - if (!ret) + if (!ret) { + struct nfs4_sequence_res *res = task->tk_msg.rpc_resp; + + if (task->tk_status == 0) + nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); ret = task->tk_status; + } rpc_put_task(task); out: dprintk("<-- %s status=%d\n", __func__, ret); @@ -5251,7 +5291,7 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf rpc_delay(task, NFS4_POLL_RETRY_MAX); return -EAGAIN; default: - nfs4_schedule_state_recovery(clp); + nfs4_schedule_lease_recovery(clp); } return 0; } @@ -5319,6 +5359,9 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp) status = PTR_ERR(task); goto out; } + status = nfs4_wait_for_completion_rpc_task(task); + if (status == 0) + status = task->tk_status; rpc_put_task(task); return 0; out: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 2336d53..0592288 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -232,12 +232,6 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) status = nfs4_proc_create_session(clp); if (status != 0) goto out; - status = nfs4_set_callback_sessionid(clp); - if (status != 0) { - printk(KERN_WARNING "Sessionid not set. No callback service\n"); - nfs_callback_down(1); - status = 0; - } nfs41_setup_state_renewal(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: @@ -1013,9 +1007,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) } /* - * Schedule a state recovery attempt + * Schedule a lease recovery attempt */ -void nfs4_schedule_state_recovery(struct nfs_client *clp) +void nfs4_schedule_lease_recovery(struct nfs_client *clp) { if (!clp) return; @@ -1024,7 +1018,7 @@ void nfs4_schedule_state_recovery(struct nfs_client *clp) nfs4_schedule_state_manager(clp); } -int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state) +static int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *state) { set_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags); @@ -1038,7 +1032,7 @@ int nfs4_state_mark_reclaim_reboot(struct nfs_client *clp, struct nfs4_state *st return 1; } -int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state) +static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *state) { set_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags); clear_bit(NFS_STATE_RECLAIM_REBOOT, &state->flags); @@ -1047,6 +1041,14 @@ int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_state *s return 1; } +void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state) +{ + struct nfs_client *clp = server->nfs_client; + + nfs4_state_mark_reclaim_nograce(clp, state); + nfs4_schedule_state_manager(clp); +} + static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops) { struct inode *inode = state->inode; @@ -1442,10 +1444,15 @@ static int nfs4_reclaim_lease(struct nfs_client *clp) } #ifdef CONFIG_NFS_V4_1 +void nfs4_schedule_session_recovery(struct nfs4_session *session) +{ + nfs4_schedule_lease_recovery(session->clp); +} + void nfs41_handle_recall_slot(struct nfs_client *clp) { set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state); - nfs4_schedule_state_recovery(clp); + nfs4_schedule_state_manager(clp); } static void nfs4_reset_all_state(struct nfs_client *clp) @@ -1453,7 +1460,7 @@ static void nfs4_reset_all_state(struct nfs_client *clp) if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) { clp->cl_boot_time = CURRENT_TIME; nfs4_state_start_reclaim_nograce(clp); - nfs4_schedule_state_recovery(clp); + nfs4_schedule_state_manager(clp); } } @@ -1461,7 +1468,7 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp) { if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) { nfs4_state_start_reclaim_reboot(clp); - nfs4_schedule_state_recovery(clp); + nfs4_schedule_state_manager(clp); } } @@ -1481,7 +1488,7 @@ static void nfs41_handle_cb_path_down(struct nfs_client *clp) { nfs_expire_all_delegations(clp); if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0) - nfs4_schedule_state_recovery(clp); + nfs4_schedule_state_manager(clp); } void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 2ab8e5c..94d50e8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1660,7 +1660,7 @@ static void encode_create_session(struct xdr_stream *xdr, p = reserve_space(xdr, 20 + 2*28 + 20 + len + 12); *p++ = cpu_to_be32(OP_CREATE_SESSION); - p = xdr_encode_hyper(p, clp->cl_ex_clid); + p = xdr_encode_hyper(p, clp->cl_clientid); *p++ = cpu_to_be32(clp->cl_seqid); /*Sequence id */ *p++ = cpu_to_be32(args->flags); /*flags */ @@ -4694,7 +4694,7 @@ static int decode_exchange_id(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - xdr_decode_hyper(p, &clp->cl_ex_clid); + xdr_decode_hyper(p, &clp->cl_clientid); p = xdr_inline_decode(xdr, 12); if (unlikely(!p)) goto out_overflow; @@ -6086,11 +6086,11 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, __be32 *p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - if (!ntohl(*p++)) { + if (*p == xdr_zero) { p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; - if (!ntohl(*p++)) + if (*p == xdr_zero) return -EAGAIN; entry->eof = 1; return -EBADCOOKIE; @@ -6101,7 +6101,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, goto out_overflow; entry->prev_cookie = entry->cookie; p = xdr_decode_hyper(p, &entry->cookie); - entry->len = ntohl(*p++); + entry->len = be32_to_cpup(p); p = xdr_inline_decode(xdr, entry->len); if (unlikely(!p)) @@ -6132,9 +6132,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE) entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); - if (verify_attr_len(xdr, p, len) < 0) - goto out_overflow; - return 0; out_overflow: diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 903908a..c541093 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -86,11 +86,14 @@ /* Default path we try to mount. "%s" gets replaced by our IP address */ #define NFS_ROOT "/tftpboot/%s" +/* Default NFSROOT mount options. */ +#define NFS_DEF_OPTIONS "udp" + /* Parameters passed from the kernel command line */ static char nfs_root_parms[256] __initdata = ""; /* Text-based mount options passed to super.c */ -static char nfs_root_options[256] __initdata = ""; +static char nfs_root_options[256] __initdata = NFS_DEF_OPTIONS; /* Address of NFS server */ static __be32 servaddr __initdata = htonl(INADDR_NONE); @@ -160,8 +163,14 @@ static int __init root_nfs_copy(char *dest, const char *src, } static int __init root_nfs_cat(char *dest, const char *src, - const size_t destlen) + const size_t destlen) { + size_t len = strlen(dest); + + if (len && dest[len - 1] != ',') + if (strlcat(dest, ",", destlen) > destlen) + return -1; + if (strlcat(dest, src, destlen) > destlen) return -1; return 0; @@ -194,16 +203,6 @@ static int __init root_nfs_parse_options(char *incoming, char *exppath, if (root_nfs_cat(nfs_root_options, incoming, sizeof(nfs_root_options))) return -1; - - /* - * Possibly prepare for more options to be appended - */ - if (nfs_root_options[0] != '\0' && - nfs_root_options[strlen(nfs_root_options)] != ',') - if (root_nfs_cat(nfs_root_options, ",", - sizeof(nfs_root_options))) - return -1; - return 0; } @@ -217,7 +216,7 @@ static int __init root_nfs_parse_options(char *incoming, char *exppath, */ static int __init root_nfs_data(char *cmdline) { - char addr_option[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1]; + char mand_options[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1]; int len, retval = -1; char *tmp = NULL; const size_t tmplen = sizeof(nfs_export_path); @@ -244,9 +243,9 @@ static int __init root_nfs_data(char *cmdline) * Append mandatory options for nfsroot so they override * what has come before */ - snprintf(addr_option, sizeof(addr_option), "nolock,addr=%pI4", + snprintf(mand_options, sizeof(mand_options), "nolock,addr=%pI4", &servaddr); - if (root_nfs_cat(nfs_root_options, addr_option, + if (root_nfs_cat(nfs_root_options, mand_options, sizeof(nfs_root_options))) goto out_optionstoolong; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index bc40897..1b1bc1a 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -951,7 +951,7 @@ pnfs_put_deviceid_cache(struct nfs_client *clp) { struct pnfs_deviceid_cache *local = clp->cl_devid_cache; - dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache); + dprintk("--> %s ({%d})\n", __func__, atomic_read(&local->dc_ref)); if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) { int i; /* Verify cache is empty */ diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index e313a51..6481d53 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -180,7 +180,7 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n task_setup_data.rpc_client = NFS_CLIENT(dir); task = rpc_run_task(&task_setup_data); if (!IS_ERR(task)) - rpc_put_task(task); + rpc_put_task_async(task); return 1; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 10d648ea..42b92d7 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -932,7 +932,7 @@ out_bad: while (!list_empty(&list)) { data = list_entry(list.next, struct nfs_write_data, pages); list_del(&data->pages); - nfs_writedata_release(data); + nfs_writedata_free(data); } nfs_redirty_request(req); return -ENOMEM; @@ -1292,6 +1292,8 @@ static int nfs_commit_rpcsetup(struct list_head *head, task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); + if (how & FLUSH_SYNC) + rpc_wait_for_completion_task(task); rpc_put_task(task); return 0; } diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c index fc1c525..84c27d6 100644 --- a/fs/nfs_common/nfsacl.c +++ b/fs/nfs_common/nfsacl.c @@ -42,6 +42,11 @@ struct nfsacl_encode_desc { gid_t gid; }; +struct nfsacl_simple_acl { + struct posix_acl acl; + struct posix_acl_entry ace[4]; +}; + static int xdr_nfsace_encode(struct xdr_array2_desc *desc, void *elem) { @@ -72,9 +77,20 @@ xdr_nfsace_encode(struct xdr_array2_desc *desc, void *elem) return 0; } -unsigned int -nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, - struct posix_acl *acl, int encode_entries, int typeflag) +/** + * nfsacl_encode - Encode an NFSv3 ACL + * + * @buf: destination xdr_buf to contain XDR encoded ACL + * @base: byte offset in xdr_buf where XDR'd ACL begins + * @inode: inode of file whose ACL this is + * @acl: posix_acl to encode + * @encode_entries: whether to encode ACEs as well + * @typeflag: ACL type: NFS_ACL_DEFAULT or zero + * + * Returns size of encoded ACL in bytes or a negative errno value. + */ +int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, + struct posix_acl *acl, int encode_entries, int typeflag) { int entries = (acl && acl->a_count) ? max_t(int, acl->a_count, 4) : 0; struct nfsacl_encode_desc nfsacl_desc = { @@ -88,17 +104,22 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, .uid = inode->i_uid, .gid = inode->i_gid, }; + struct nfsacl_simple_acl aclbuf; int err; - struct posix_acl *acl2 = NULL; if (entries > NFS_ACL_MAX_ENTRIES || xdr_encode_word(buf, base, entries)) return -EINVAL; if (encode_entries && acl && acl->a_count == 3) { - /* Fake up an ACL_MASK entry. */ - acl2 = posix_acl_alloc(4, GFP_KERNEL); - if (!acl2) - return -ENOMEM; + struct posix_acl *acl2 = &aclbuf.acl; + + /* Avoid the use of posix_acl_alloc(). nfsacl_encode() is + * invoked in contexts where a memory allocation failure is + * fatal. Fortunately this fake ACL is small enough to + * construct on the stack. */ + memset(acl2, 0, sizeof(acl2)); + posix_acl_init(acl2, 4); + /* Insert entries in canonical order: other orders seem to confuse Solaris VxFS. */ acl2->a_entries[0] = acl->a_entries[0]; /* ACL_USER_OBJ */ @@ -109,8 +130,6 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, nfsacl_desc.acl = acl2; } err = xdr_encode_array2(buf, base + 4, &nfsacl_desc.desc); - if (acl2) - posix_acl_release(acl2); if (!err) err = 8 + nfsacl_desc.desc.elem_size * nfsacl_desc.desc.array_len; @@ -224,9 +243,18 @@ posix_acl_from_nfsacl(struct posix_acl *acl) return 0; } -unsigned int -nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt, - struct posix_acl **pacl) +/** + * nfsacl_decode - Decode an NFSv3 ACL + * + * @buf: xdr_buf containing XDR'd ACL data to decode + * @base: byte offset in xdr_buf where XDR'd ACL begins + * @aclcnt: count of ACEs in decoded posix_acl + * @pacl: buffer in which to place decoded posix_acl + * + * Returns the length of the decoded ACL in bytes, or a negative errno value. + */ +int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt, + struct posix_acl **pacl) { struct nfsacl_decode_desc nfsacl_desc = { .desc = { diff --git a/fs/nfsctl.c b/fs/nfsctl.c index bf9cbd2..124e8fc 100644 --- a/fs/nfsctl.c +++ b/fs/nfsctl.c @@ -22,30 +22,17 @@ static struct file *do_open(char *name, int flags) { - struct nameidata nd; struct vfsmount *mnt; - int error; + struct file *file; mnt = do_kern_mount("nfsd", 0, "nfsd", NULL); if (IS_ERR(mnt)) return (struct file *)mnt; - error = vfs_path_lookup(mnt->mnt_root, mnt, name, 0, &nd); - mntput(mnt); /* drop do_kern_mount reference */ - if (error) - return ERR_PTR(error); - - if (flags == O_RDWR) - error = may_open(&nd.path, MAY_READ|MAY_WRITE, flags); - else - error = may_open(&nd.path, MAY_WRITE, flags); + file = file_open_root(mnt->mnt_root, mnt, name, flags); - if (!error) - return dentry_open(nd.path.dentry, nd.path.mnt, flags, - current_cred()); - - path_put(&nd.path); - return ERR_PTR(error); + mntput(mnt); /* drop do_kern_mount reference */ + return file; } static struct { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 3be975e..02eb4ed 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -432,7 +432,7 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, * If the server returns different values for sessionID, slotID or * sequence number, the server is looney tunes. */ - p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4); + p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4); if (unlikely(p == NULL)) goto out_overflow; memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN); @@ -484,7 +484,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr, out: return status; out_default: - return nfs_cb_stat_to_errno(status); + return nfs_cb_stat_to_errno(nfserr); } /* @@ -564,11 +564,9 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, if (unlikely(status)) goto out; if (unlikely(nfserr != NFS4_OK)) - goto out_default; + status = nfs_cb_stat_to_errno(nfserr); out: return status; -out_default: - return nfs_cb_stat_to_errno(status); } /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index d98d021..7b566ec 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -230,9 +230,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f dp->dl_client = clp; get_nfs4_file(fp); dp->dl_file = fp; - dp->dl_vfs_file = find_readable_file(fp); - get_file(dp->dl_vfs_file); - dp->dl_flock = NULL; dp->dl_type = type; dp->dl_stateid.si_boot = boot_time; dp->dl_stateid.si_stateownerid = current_delegid++; @@ -241,8 +238,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle); dp->dl_time = 0; atomic_set(&dp->dl_count, 1); - list_add(&dp->dl_perfile, &fp->fi_delegations); - list_add(&dp->dl_perclnt, &clp->cl_delegations); INIT_WORK(&dp->dl_recall.cb_work, nfsd4_do_callback_rpc); return dp; } @@ -253,36 +248,30 @@ nfs4_put_delegation(struct nfs4_delegation *dp) if (atomic_dec_and_test(&dp->dl_count)) { dprintk("NFSD: freeing dp %p\n",dp); put_nfs4_file(dp->dl_file); - fput(dp->dl_vfs_file); kmem_cache_free(deleg_slab, dp); num_delegations--; } } -/* Remove the associated file_lock first, then remove the delegation. - * lease_modify() is called to remove the FS_LEASE file_lock from - * the i_flock list, eventually calling nfsd's lock_manager - * fl_release_callback. - */ -static void -nfs4_close_delegation(struct nfs4_delegation *dp) +static void nfs4_put_deleg_lease(struct nfs4_file *fp) { - dprintk("NFSD: close_delegation dp %p\n",dp); - /* XXX: do we even need this check?: */ - if (dp->dl_flock) - vfs_setlease(dp->dl_vfs_file, F_UNLCK, &dp->dl_flock); + if (atomic_dec_and_test(&fp->fi_delegees)) { + vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease); + fp->fi_lease = NULL; + fp->fi_deleg_file = NULL; + } } /* Called under the state lock. */ static void unhash_delegation(struct nfs4_delegation *dp) { - list_del_init(&dp->dl_perfile); list_del_init(&dp->dl_perclnt); spin_lock(&recall_lock); + list_del_init(&dp->dl_perfile); list_del_init(&dp->dl_recall_lru); spin_unlock(&recall_lock); - nfs4_close_delegation(dp); + nfs4_put_deleg_lease(dp->dl_file); nfs4_put_delegation(dp); } @@ -958,8 +947,6 @@ expire_client(struct nfs4_client *clp) spin_lock(&recall_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); - dprintk("NFSD: expire client. dp %p, fp %p\n", dp, - dp->dl_flock); list_del_init(&dp->dl_perclnt); list_move(&dp->dl_recall_lru, &reaplist); } @@ -2078,6 +2065,7 @@ alloc_init_file(struct inode *ino) fp->fi_inode = igrab(ino); fp->fi_id = current_fileid++; fp->fi_had_conflict = false; + fp->fi_lease = NULL; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); spin_lock(&recall_lock); @@ -2329,23 +2317,8 @@ nfs4_file_downgrade(struct nfs4_file *fp, unsigned int share_access) nfs4_file_put_access(fp, O_RDONLY); } -/* - * Spawn a thread to perform a recall on the delegation represented - * by the lease (file_lock) - * - * Called from break_lease() with lock_flocks() held. - * Note: we assume break_lease will only call this *once* for any given - * lease. - */ -static -void nfsd_break_deleg_cb(struct file_lock *fl) +static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { - struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; - - dprintk("NFSD nfsd_break_deleg_cb: dp %p fl %p\n",dp,fl); - if (!dp) - return; - /* We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the kernel @@ -2353,22 +2326,35 @@ void nfsd_break_deleg_cb(struct file_lock *fl) * it's safe to take a reference: */ atomic_inc(&dp->dl_count); - spin_lock(&recall_lock); list_add_tail(&dp->dl_recall_lru, &del_recall_lru); - spin_unlock(&recall_lock); /* only place dl_time is set. protected by lock_flocks*/ dp->dl_time = get_seconds(); + nfsd4_cb_recall(dp); +} + +/* Called from break_lease() with lock_flocks() held. */ +static void nfsd_break_deleg_cb(struct file_lock *fl) +{ + struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner; + struct nfs4_delegation *dp; + + BUG_ON(!fp); + /* We assume break_lease is only called once per lease: */ + BUG_ON(fp->fi_had_conflict); /* * We don't want the locks code to timeout the lease for us; - * we'll remove it ourself if the delegation isn't returned - * in time. + * we'll remove it ourself if a delegation isn't returned + * in time: */ fl->fl_break_time = 0; - dp->dl_file->fi_had_conflict = true; - nfsd4_cb_recall(dp); + spin_lock(&recall_lock); + fp->fi_had_conflict = true; + list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) + nfsd_break_one_deleg(dp); + spin_unlock(&recall_lock); } static @@ -2461,10 +2447,13 @@ find_delegation_file(struct nfs4_file *fp, stateid_t *stid) { struct nfs4_delegation *dp; - list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) { - if (dp->dl_stateid.si_stateownerid == stid->si_stateownerid) + spin_lock(&recall_lock); + list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) + if (dp->dl_stateid.si_stateownerid == stid->si_stateownerid) { + spin_unlock(&recall_lock); return dp; - } + } + spin_unlock(&recall_lock); return NULL; } @@ -2641,6 +2630,66 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } +static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int flag) +{ + struct file_lock *fl; + + fl = locks_alloc_lock(); + if (!fl) + return NULL; + locks_init_lock(fl); + fl->fl_lmops = &nfsd_lease_mng_ops; + fl->fl_flags = FL_LEASE; + fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; + fl->fl_end = OFFSET_MAX; + fl->fl_owner = (fl_owner_t)(dp->dl_file); + fl->fl_pid = current->tgid; + return fl; +} + +static int nfs4_setlease(struct nfs4_delegation *dp, int flag) +{ + struct nfs4_file *fp = dp->dl_file; + struct file_lock *fl; + int status; + + fl = nfs4_alloc_init_lease(dp, flag); + if (!fl) + return -ENOMEM; + fl->fl_file = find_readable_file(fp); + list_add(&dp->dl_perclnt, &dp->dl_client->cl_delegations); + status = vfs_setlease(fl->fl_file, fl->fl_type, &fl); + if (status) { + list_del_init(&dp->dl_perclnt); + locks_free_lock(fl); + return -ENOMEM; + } + fp->fi_lease = fl; + fp->fi_deleg_file = fl->fl_file; + get_file(fp->fi_deleg_file); + atomic_set(&fp->fi_delegees, 1); + list_add(&dp->dl_perfile, &fp->fi_delegations); + return 0; +} + +static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag) +{ + struct nfs4_file *fp = dp->dl_file; + + if (!fp->fi_lease) + return nfs4_setlease(dp, flag); + spin_lock(&recall_lock); + if (fp->fi_had_conflict) { + spin_unlock(&recall_lock); + return -EAGAIN; + } + atomic_inc(&fp->fi_delegees); + list_add(&dp->dl_perfile, &fp->fi_delegations); + spin_unlock(&recall_lock); + list_add(&dp->dl_perclnt, &dp->dl_client->cl_delegations); + return 0; +} + /* * Attempt to hand out a delegation. */ @@ -2650,7 +2699,6 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta struct nfs4_delegation *dp; struct nfs4_stateowner *sop = stp->st_stateowner; int cb_up; - struct file_lock *fl; int status, flag = 0; cb_up = nfsd4_cb_channel_good(sop->so_client); @@ -2681,36 +2729,11 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta } dp = alloc_init_deleg(sop->so_client, stp, fh, flag); - if (dp == NULL) { - flag = NFS4_OPEN_DELEGATE_NONE; - goto out; - } - status = -ENOMEM; - fl = locks_alloc_lock(); - if (!fl) - goto out; - locks_init_lock(fl); - fl->fl_lmops = &nfsd_lease_mng_ops; - fl->fl_flags = FL_LEASE; - fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; - fl->fl_end = OFFSET_MAX; - fl->fl_owner = (fl_owner_t)dp; - fl->fl_file = find_readable_file(stp->st_file); - BUG_ON(!fl->fl_file); - fl->fl_pid = current->tgid; - dp->dl_flock = fl; - - /* vfs_setlease checks to see if delegation should be handed out. - * the lock_manager callback fl_change is used - */ - if ((status = vfs_setlease(fl->fl_file, fl->fl_type, &fl))) { - dprintk("NFSD: setlease failed [%d], no delegation\n", status); - dp->dl_flock = NULL; - locks_free_lock(fl); - unhash_delegation(dp); - flag = NFS4_OPEN_DELEGATE_NONE; - goto out; - } + if (dp == NULL) + goto out_no_deleg; + status = nfs4_set_delegation(dp, flag); + if (status) + goto out_free; memcpy(&open->op_delegate_stateid, &dp->dl_stateid, sizeof(dp->dl_stateid)); @@ -2722,6 +2745,12 @@ out: && open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) dprintk("NFSD: WARNING: refusing delegation reclaim\n"); open->op_delegate_type = flag; + return; +out_free: + nfs4_put_delegation(dp); +out_no_deleg: + flag = NFS4_OPEN_DELEGATE_NONE; + goto out; } /* @@ -2916,8 +2945,6 @@ nfs4_laundromat(void) test_val = u; break; } - dprintk("NFSD: purging unused delegation dp %p, fp %p\n", - dp, dp->dl_flock); list_move(&dp->dl_recall_lru, &reaplist); } spin_unlock(&recall_lock); @@ -3128,7 +3155,7 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, goto out; renew_client(dp->dl_client); if (filpp) { - *filpp = find_readable_file(dp->dl_file); + *filpp = dp->dl_file->fi_deleg_file; BUG_ON(!*filpp); } } else { /* open or lock stateid */ diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 956629b..615f0a9 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -317,8 +317,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); - if ((host_err = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid))) - goto out_nfserr; + if ((status = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid))) + return status; iattr->ia_valid |= ATTR_UID; } if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) { @@ -328,8 +328,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, READ_BUF(dummy32); len += (XDR_QUADLEN(dummy32) << 2); READMEM(buf, dummy32); - if ((host_err = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid))) - goto out_nfserr; + if ((status = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid))) + return status; iattr->ia_valid |= ATTR_GID; } if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { @@ -1142,7 +1142,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, u32 dummy; char *machine_name; - int i; + int i, j; int nr_secflavs; READ_BUF(16); @@ -1215,7 +1215,7 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, READ_BUF(4); READ32(dummy); READ_BUF(dummy * 4); - for (i = 0; i < dummy; ++i) + for (j = 0; j < dummy; ++j) READ32(dummy); break; case RPC_AUTH_GSS: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 3074656..2d31224 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -83,8 +83,6 @@ struct nfs4_delegation { atomic_t dl_count; /* ref count */ struct nfs4_client *dl_client; struct nfs4_file *dl_file; - struct file *dl_vfs_file; - struct file_lock *dl_flock; u32 dl_type; time_t dl_time; /* For recall: */ @@ -379,6 +377,9 @@ struct nfs4_file { */ atomic_t fi_readers; atomic_t fi_writers; + struct file *fi_deleg_file; + struct file_lock *fi_lease; + atomic_t fi_delegees; struct inode *fi_inode; u32 fi_id; /* used with stateowner->so_id * for stateid_hashtbl hash */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 641117f..da1d970 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -808,7 +808,7 @@ nfsd_get_raparms(dev_t dev, ino_t ino) if (ra->p_count == 0) frap = rap; } - depth = nfsdstats.ra_size*11/10; + depth = nfsdstats.ra_size; if (!frap) { spin_unlock(&rab->pb_lock); return NULL; @@ -1744,6 +1744,13 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, host_err = nfsd_break_lease(odentry->d_inode); if (host_err) goto out_drop_write; + if (ndentry->d_inode) { + host_err = nfsd_break_lease(ndentry->d_inode); + if (host_err) + goto out_drop_write; + } + if (host_err) + goto out_drop_write; host_err = vfs_rename(fdir, odentry, tdir, ndentry); if (!host_err) { host_err = commit_metadata(tfhp); @@ -1812,22 +1819,22 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, host_err = mnt_want_write(fhp->fh_export->ex_path.mnt); if (host_err) - goto out_nfserr; + goto out_put; host_err = nfsd_break_lease(rdentry->d_inode); if (host_err) - goto out_put; + goto out_drop_write; if (type != S_IFDIR) host_err = vfs_unlink(dirp, rdentry); else host_err = vfs_rmdir(dirp, rdentry); -out_put: - dput(rdentry); - if (!host_err) host_err = commit_metadata(fhp); - +out_drop_write: mnt_drop_write(fhp->fh_export->ex_path.mnt); +out_put: + dput(rdentry); + out_nfserr: err = nfserrno(host_err); out: diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 388e9e8..85f7baa 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -35,11 +35,6 @@ #include "btnode.h" -void nilfs_btnode_cache_init_once(struct address_space *btnc) -{ - nilfs_mapping_init_once(btnc); -} - static const struct address_space_operations def_btnode_aops = { .sync_page = block_sync_page, }; diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 7903749..1b8ebd8 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -37,7 +37,6 @@ struct nilfs_btnode_chkey_ctxt { struct buffer_head *newbh; }; -void nilfs_btnode_cache_init_once(struct address_space *); void nilfs_btnode_cache_init(struct address_space *, struct backing_dev_info *); void nilfs_btnode_cache_clear(struct address_space *); struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc, diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 6a0e2a1..a0babd2 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -454,9 +454,9 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode, struct backing_dev_info *bdi = inode->i_sb->s_bdi; INIT_LIST_HEAD(&shadow->frozen_buffers); - nilfs_mapping_init_once(&shadow->frozen_data); + address_space_init_once(&shadow->frozen_data); nilfs_mapping_init(&shadow->frozen_data, bdi, &shadow_map_aops); - nilfs_mapping_init_once(&shadow->frozen_btnodes); + address_space_init_once(&shadow->frozen_btnodes); nilfs_mapping_init(&shadow->frozen_btnodes, bdi, &shadow_map_aops); mi->mi_shadow = shadow; return 0; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9803427..161791d 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -397,7 +397,6 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry, new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_page); if (!new_de) goto out_dir; - inc_nlink(old_inode); nilfs_set_link(new_dir, new_de, new_page, old_inode); nilfs_mark_inode_dirty(new_dir); new_inode->i_ctime = CURRENT_TIME; @@ -411,13 +410,9 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dir->i_nlink >= NILFS_LINK_MAX) goto out_dir; } - inc_nlink(old_inode); err = nilfs_add_link(new_dentry, old_inode); - if (err) { - drop_nlink(old_inode); - nilfs_mark_inode_dirty(old_inode); + if (err) goto out_dir; - } if (dir_de) { inc_nlink(new_dir); nilfs_mark_inode_dirty(new_dir); @@ -431,7 +426,6 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry, old_inode->i_ctime = CURRENT_TIME; nilfs_delete_entry(old_de, old_page); - drop_nlink(old_inode); if (dir_de) { nilfs_set_link(old_inode, dir_de, dir_page, new_dir); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 0c43241..a585b35 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -492,19 +492,6 @@ unsigned nilfs_page_count_clean_buffers(struct page *page, return nc; } -void nilfs_mapping_init_once(struct address_space *mapping) -{ - memset(mapping, 0, sizeof(*mapping)); - INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC); - spin_lock_init(&mapping->tree_lock); - INIT_LIST_HEAD(&mapping->private_list); - spin_lock_init(&mapping->private_lock); - - spin_lock_init(&mapping->i_mmap_lock); - INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap); - INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); -} - void nilfs_mapping_init(struct address_space *mapping, struct backing_dev_info *bdi, const struct address_space_operations *aops) diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index 622df27..2a00953 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -61,7 +61,6 @@ void nilfs_free_private_page(struct page *); int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); void nilfs_clear_dirty_pages(struct address_space *); -void nilfs_mapping_init_once(struct address_space *mapping); void nilfs_mapping_init(struct address_space *mapping, struct backing_dev_info *bdi, const struct address_space_operations *aops); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 55ebae5..2de9f63 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -430,7 +430,8 @@ static void nilfs_segctor_begin_finfo(struct nilfs_sc_info *sci, nilfs_segctor_map_segsum_entry( sci, &sci->sc_binfo_ptr, sizeof(struct nilfs_finfo)); - if (inode->i_sb && !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags)) + if (NILFS_I(inode)->i_root && + !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags)) set_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags); /* skip finfo */ } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 58fd707..1673b3d 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1279,7 +1279,7 @@ static void nilfs_inode_init_once(void *obj) #ifdef CONFIG_NILFS_XATTR init_rwsem(&ii->xattr_sem); #endif - nilfs_btnode_cache_init_once(&ii->i_btnode_cache); + address_space_init_once(&ii->i_btnode_cache); ii->i_bmap = &ii->i_bmap_data; inode_init_once(&ii->vfs_inode); } diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 6d80ecc..7eb9040 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -56,7 +56,7 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, int ret = 0; /* if all else fails, just return false */ struct ocfs2_super *osb; - if (nd->flags & LOOKUP_RCU) + if (nd && nd->flags & LOOKUP_RCU) return -ECHILD; inode = dentry->d_inode; diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 5dbc306..254652a 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -197,8 +197,12 @@ static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len, dentry->d_name.len, dentry->d_name.name, fh, len, connectable); - if (len < 3 || (connectable && len < 6)) { - mlog(ML_ERROR, "fh buffer is too small for encoding\n"); + if (connectable && (len < 6)) { + *max_len = 6; + type = 255; + goto bail; + } else if (len < 3) { + *max_len = 3; type = 255; goto bail; } diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 43e56b9..6180da1 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -405,9 +405,9 @@ static inline int ocfs2_remove_extent_credits(struct super_block *sb) ocfs2_quota_trans_credits(sb); } -/* data block for new dir/symlink, 2 for bitmap updates (bitmap fe + - * bitmap block for the new bit) dx_root update for free list */ -#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2 + 1) +/* data block for new dir/symlink, allocation of directory block, dx_root + * update for free list */ +#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + OCFS2_SUBALLOC_ALLOC + 1) static inline int ocfs2_add_dir_index_credits(struct super_block *sb) { diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index b5f9160..29623da 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3228,7 +3228,7 @@ static int ocfs2_make_clusters_writable(struct super_block *sb, u32 num_clusters, unsigned int e_flags) { int ret, delete, index, credits = 0; - u32 new_bit, new_len; + u32 new_bit, new_len, orig_num_clusters; unsigned int set_len; struct ocfs2_super *osb = OCFS2_SB(sb); handle_t *handle; @@ -3261,6 +3261,8 @@ static int ocfs2_make_clusters_writable(struct super_block *sb, goto out; } + orig_num_clusters = num_clusters; + while (num_clusters) { ret = ocfs2_get_refcount_rec(ref_ci, context->ref_root_bh, p_cluster, num_clusters, @@ -3348,7 +3350,8 @@ static int ocfs2_make_clusters_writable(struct super_block *sb, * in write-back mode. */ if (context->get_clusters == ocfs2_di_get_clusters) { - ret = ocfs2_cow_sync_writeback(sb, context, cpos, num_clusters); + ret = ocfs2_cow_sync_writeback(sb, context, cpos, + orig_num_clusters); if (ret) mlog_errno(ret); } @@ -4376,7 +4379,7 @@ static int ocfs2_user_path_parent(const char __user *path, if (IS_ERR(s)) return PTR_ERR(s); - error = path_lookup(s, LOOKUP_PARENT, nd); + error = kern_path_parent(s, nd); if (error) putname(s); else diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 38f986d..36c423f 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1316,7 +1316,7 @@ static int ocfs2_parse_options(struct super_block *sb, struct mount_options *mopt, int is_remount) { - int status; + int status, user_stack = 0; char *p; u32 tmp; @@ -1459,6 +1459,15 @@ static int ocfs2_parse_options(struct super_block *sb, memcpy(mopt->cluster_stack, args[0].from, OCFS2_STACK_LABEL_LEN); mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0'; + /* + * Open code the memcmp here as we don't have + * an osb to pass to + * ocfs2_userspace_stack(). + */ + if (memcmp(mopt->cluster_stack, + OCFS2_CLASSIC_CLUSTER_STACK, + OCFS2_STACK_LABEL_LEN)) + user_stack = 1; break; case Opt_inode64: mopt->mount_opt |= OCFS2_MOUNT_INODE64; @@ -1514,13 +1523,16 @@ static int ocfs2_parse_options(struct super_block *sb, } } - /* Ensure only one heartbeat mode */ - tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL | - OCFS2_MOUNT_HB_NONE); - if (hweight32(tmp) != 1) { - mlog(ML_ERROR, "Invalid heartbeat mount options\n"); - status = 0; - goto bail; + if (user_stack == 0) { + /* Ensure only one heartbeat mode */ + tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL | + OCFS2_MOUNT_HB_GLOBAL | + OCFS2_MOUNT_HB_NONE); + if (hweight32(tmp) != 1) { + mlog(ML_ERROR, "Invalid heartbeat mount options\n"); + status = 0; + goto bail; + } } status = 1; @@ -233,6 +233,14 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (!(file->f_mode & FMODE_WRITE)) return -EBADF; + + /* It's not possible punch hole on append only file */ + if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode)) + return -EPERM; + + if (IS_IMMUTABLE(inode)) + return -EPERM; + /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. @@ -565,13 +573,15 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, { struct path path; int error = -EINVAL; - int follow; + int lookup_flags; - if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0) + if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) goto out; - follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; - error = user_path_at(dfd, filename, follow, &path); + lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; + if (flag & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; + error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = mnt_want_write(path.mnt); @@ -661,11 +671,16 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, int (*open)(struct inode *, struct file *), const struct cred *cred) { + static const struct file_operations empty_fops = {}; struct inode *inode; int error; f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; + + if (unlikely(f->f_flags & O_PATH)) + f->f_mode = FMODE_PATH; + inode = dentry->d_inode; if (f->f_mode & FMODE_WRITE) { error = __get_file_write_access(inode, mnt); @@ -679,9 +694,15 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, f->f_path.dentry = dentry; f->f_path.mnt = mnt; f->f_pos = 0; - f->f_op = fops_get(inode->i_fop); file_sb_list_add(f, inode->i_sb); + if (unlikely(f->f_mode & FMODE_PATH)) { + f->f_op = &empty_fops; + return f; + } + + f->f_op = fops_get(inode->i_fop); + error = security_dentry_open(f, cred); if (error) goto cleanup_all; @@ -790,6 +811,8 @@ struct file *nameidata_to_filp(struct nameidata *nd) /* Pick up the filp from the open intent */ filp = nd->intent.open.file; + nd->intent.open.file = NULL; + /* Has the filesystem initialised the file for us? */ if (filp->f_path.dentry == NULL) { path_get(&nd->path); @@ -880,15 +903,110 @@ void fd_install(unsigned int fd, struct file *file) EXPORT_SYMBOL(fd_install); +static inline int build_open_flags(int flags, int mode, struct open_flags *op) +{ + int lookup_flags = 0; + int acc_mode; + + if (!(flags & O_CREAT)) + mode = 0; + op->mode = mode; + + /* Must never be set by userspace */ + flags &= ~FMODE_NONOTIFY; + + /* + * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only + * check for O_DSYNC if the need any syncing at all we enforce it's + * always set instead of having to deal with possibly weird behaviour + * for malicious applications setting only __O_SYNC. + */ + if (flags & __O_SYNC) + flags |= O_DSYNC; + + /* + * If we have O_PATH in the open flag. Then we + * cannot have anything other than the below set of flags + */ + if (flags & O_PATH) { + flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH; + acc_mode = 0; + } else { + acc_mode = MAY_OPEN | ACC_MODE(flags); + } + + op->open_flag = flags; + + /* O_TRUNC implies we need access checks for write permissions */ + if (flags & O_TRUNC) + acc_mode |= MAY_WRITE; + + /* Allow the LSM permission hook to distinguish append + access from general write access. */ + if (flags & O_APPEND) + acc_mode |= MAY_APPEND; + + op->acc_mode = acc_mode; + + op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; + + if (flags & O_CREAT) { + op->intent |= LOOKUP_CREATE; + if (flags & O_EXCL) + op->intent |= LOOKUP_EXCL; + } + + if (flags & O_DIRECTORY) + lookup_flags |= LOOKUP_DIRECTORY; + if (!(flags & O_NOFOLLOW)) + lookup_flags |= LOOKUP_FOLLOW; + return lookup_flags; +} + +/** + * filp_open - open file and return file pointer + * + * @filename: path to open + * @flags: open flags as per the open(2) second argument + * @mode: mode for the new file if O_CREAT is set, else ignored + * + * This is the helper to open a file from kernelspace if you really + * have to. But in generally you should not do this, so please move + * along, nothing to see here.. + */ +struct file *filp_open(const char *filename, int flags, int mode) +{ + struct open_flags op; + int lookup = build_open_flags(flags, mode, &op); + return do_filp_open(AT_FDCWD, filename, &op, lookup); +} +EXPORT_SYMBOL(filp_open); + +struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, + const char *filename, int flags) +{ + struct open_flags op; + int lookup = build_open_flags(flags, 0, &op); + if (flags & O_CREAT) + return ERR_PTR(-EINVAL); + if (!filename && (flags & O_DIRECTORY)) + if (!dentry->d_inode->i_op->lookup) + return ERR_PTR(-ENOTDIR); + return do_file_open_root(dentry, mnt, filename, &op, lookup); +} +EXPORT_SYMBOL(file_open_root); + long do_sys_open(int dfd, const char __user *filename, int flags, int mode) { + struct open_flags op; + int lookup = build_open_flags(flags, mode, &op); char *tmp = getname(filename); int fd = PTR_ERR(tmp); if (!IS_ERR(tmp)) { fd = get_unused_fd_flags(flags); if (fd >= 0) { - struct file *f = do_filp_open(dfd, tmp, flags, mode, 0); + struct file *f = do_filp_open(dfd, tmp, &op, lookup); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); @@ -958,8 +1076,10 @@ int filp_close(struct file *filp, fl_owner_t id) if (filp->f_op && filp->f_op->flush) retval = filp->f_op->flush(filp, id); - dnotify_flush(filp, id); - locks_remove_posix(filp, id); + if (likely(!(filp->f_mode & FMODE_PATH))) { + dnotify_flush(filp, id); + locks_remove_posix(filp, id); + } fput(filp); return retval; } diff --git a/fs/partitions/ldm.c b/fs/partitions/ldm.c index 789c625..b10e354 100644 --- a/fs/partitions/ldm.c +++ b/fs/partitions/ldm.c @@ -251,6 +251,11 @@ static bool ldm_parse_vmdb (const u8 *data, struct vmdb *vm) } vm->vblk_size = get_unaligned_be32(data + 0x08); + if (vm->vblk_size == 0) { + ldm_error ("Illegal VBLK size"); + return false; + } + vm->vblk_offset = get_unaligned_be32(data + 0x0C); vm->last_vblk_seq = get_unaligned_be32(data + 0x04); diff --git a/fs/partitions/mac.c b/fs/partitions/mac.c index 68d6a21..11f688b 100644 --- a/fs/partitions/mac.c +++ b/fs/partitions/mac.c @@ -29,10 +29,9 @@ static inline void mac_fix_string(char *stg, int len) int mac_partition(struct parsed_partitions *state) { - int slot = 1; Sector sect; unsigned char *data; - int blk, blocks_in_map; + int slot, blocks_in_map; unsigned secsize; #ifdef CONFIG_PPC_PMAC int found_root = 0; @@ -59,10 +58,14 @@ int mac_partition(struct parsed_partitions *state) put_dev_sector(sect); return 0; /* not a MacOS disk */ } - strlcat(state->pp_buf, " [mac]", PAGE_SIZE); blocks_in_map = be32_to_cpu(part->map_count); - for (blk = 1; blk <= blocks_in_map; ++blk) { - int pos = blk * secsize; + if (blocks_in_map < 0 || blocks_in_map >= DISK_MAX_PARTS) { + put_dev_sector(sect); + return 0; + } + strlcat(state->pp_buf, " [mac]", PAGE_SIZE); + for (slot = 1; slot <= blocks_in_map; ++slot) { + int pos = slot * secsize; put_dev_sector(sect); data = read_part_sector(state, pos/512, §); if (!data) @@ -113,13 +116,11 @@ int mac_partition(struct parsed_partitions *state) } if (goodness > found_root_goodness) { - found_root = blk; + found_root = slot; found_root_goodness = goodness; } } #endif /* CONFIG_PPC_PMAC */ - - ++slot; } #ifdef CONFIG_PPC_PMAC if (found_root_goodness) diff --git a/fs/partitions/osf.c b/fs/partitions/osf.c index 48cec7c..be03a0b 100644 --- a/fs/partitions/osf.c +++ b/fs/partitions/osf.c @@ -10,10 +10,13 @@ #include "check.h" #include "osf.h" +#define MAX_OSF_PARTITIONS 8 + int osf_partition(struct parsed_partitions *state) { int i; int slot = 1; + unsigned int npartitions; Sector sect; unsigned char *data; struct disklabel { @@ -45,7 +48,7 @@ int osf_partition(struct parsed_partitions *state) u8 p_fstype; u8 p_frag; __le16 p_cpg; - } d_partitions[8]; + } d_partitions[MAX_OSF_PARTITIONS]; } * label; struct d_partition * partition; @@ -63,7 +66,12 @@ int osf_partition(struct parsed_partitions *state) put_dev_sector(sect); return 0; } - for (i = 0 ; i < le16_to_cpu(label->d_npartitions); i++, partition++) { + npartitions = le16_to_cpu(label->d_npartitions); + if (npartitions > MAX_OSF_PARTITIONS) { + put_dev_sector(sect); + return 0; + } + for (i = 0 ; i < npartitions; i++, partition++) { if (slot == state->limit) break; if (le32_to_cpu(partition->p_size)) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 39df95a..b1cf6bf 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -22,6 +22,7 @@ #include <linux/errno.h> +EXPORT_SYMBOL(posix_acl_init); EXPORT_SYMBOL(posix_acl_alloc); EXPORT_SYMBOL(posix_acl_clone); EXPORT_SYMBOL(posix_acl_valid); @@ -32,6 +33,16 @@ EXPORT_SYMBOL(posix_acl_chmod_masq); EXPORT_SYMBOL(posix_acl_permission); /* + * Init a fresh posix_acl + */ +void +posix_acl_init(struct posix_acl *acl, int count) +{ + atomic_set(&acl->a_refcount, 1); + acl->a_count = count; +} + +/* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * @@ -40,10 +51,8 @@ posix_acl_alloc(int count, gfp_t flags) const size_t size = sizeof(struct posix_acl) + count * sizeof(struct posix_acl_entry); struct posix_acl *acl = kmalloc(size, flags); - if (acl) { - atomic_set(&acl->a_refcount, 1); - acl->a_count = count; - } + if (acl) + posix_acl_init(acl, count); return acl; } diff --git a/fs/proc/array.c b/fs/proc/array.c index df2b703..7c99c1c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -353,9 +353,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, task_cap(m, task); task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); -#if defined(CONFIG_S390) - task_show_regs(m, task); -#endif task_context_switch_counts(m, task); return 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 9d096e8..d49c4b5 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2620,35 +2620,6 @@ static const struct pid_entry proc_base_stuff[] = { &proc_self_inode_operations, NULL, {}), }; -/* - * Exceptional case: normally we are not allowed to unhash a busy - * directory. In this case, however, we can do it - no aliasing problems - * due to the way we treat inodes. - */ -static int proc_base_revalidate(struct dentry *dentry, struct nameidata *nd) -{ - struct inode *inode; - struct task_struct *task; - - if (nd->flags & LOOKUP_RCU) - return -ECHILD; - - inode = dentry->d_inode; - task = get_proc_task(inode); - if (task) { - put_task_struct(task); - return 1; - } - d_drop(dentry); - return 0; -} - -static const struct dentry_operations proc_base_dentry_operations = -{ - .d_revalidate = proc_base_revalidate, - .d_delete = pid_delete_dentry, -}; - static struct dentry *proc_base_instantiate(struct inode *dir, struct dentry *dentry, struct task_struct *task, const void *ptr) { @@ -2685,7 +2656,6 @@ static struct dentry *proc_base_instantiate(struct inode *dir, if (p->fop) inode->i_fop = p->fop; ei->op = p->op; - d_set_d_op(dentry, &proc_base_dentry_operations); d_add(dentry, inode); error = NULL; out: diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 176ce4c..d6a7ca1 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -27,6 +27,7 @@ static void proc_evict_inode(struct inode *inode) { struct proc_dir_entry *de; + struct ctl_table_header *head; truncate_inode_pages(&inode->i_data, 0); end_writeback(inode); @@ -38,8 +39,11 @@ static void proc_evict_inode(struct inode *inode) de = PROC_I(inode)->pde; if (de) pde_put(de); - if (PROC_I(inode)->sysctl) - sysctl_head_put(PROC_I(inode)->sysctl); + head = PROC_I(inode)->sysctl; + if (head) { + rcu_assign_pointer(PROC_I(inode)->sysctl, NULL); + sysctl_head_put(head); + } } struct vfsmount *proc_mnt; diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index d9396a4..927cbd1 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -233,7 +233,7 @@ void __init proc_device_tree_init(void) return; root = of_find_node_by_path("/"); if (root == NULL) { - printk(KERN_ERR "/proc/device-tree: can't find root\n"); + pr_debug("/proc/device-tree: can't find root\n"); return; } proc_device_tree_add_node(root, proc_device_tree); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 09a1f92..8eb2522 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -408,15 +408,18 @@ static int proc_sys_compare(const struct dentry *parent, const struct dentry *dentry, const struct inode *inode, unsigned int len, const char *str, const struct qstr *name) { + struct ctl_table_header *head; /* Although proc doesn't have negative dentries, rcu-walk means * that inode here can be NULL */ + /* AV: can it, indeed? */ if (!inode) - return 0; + return 1; if (name->len != len) return 1; if (memcmp(name->name, str, len)) return 1; - return !sysctl_is_seen(PROC_I(inode)->sysctl); + head = rcu_dereference(PROC_I(inode)->sysctl); + return !head || !sysctl_is_seen(head); } static const struct dentry_operations proc_sys_dentry_operations = { diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 0bae036..1bba24b 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1593,8 +1593,13 @@ int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp, struct inode *inode = dentry->d_inode; int maxlen = *lenp; - if (maxlen < 3) + if (need_parent && (maxlen < 5)) { + *lenp = 5; return 255; + } else if (maxlen < 3) { + *lenp = 3; + return 255; + } data[0] = inode->i_ino; data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index ba5f51e..4b2eb56 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -771,7 +771,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) EMPTY_DIR_SIZE_V1 : EMPTY_DIR_SIZE, dentry, inode, &security); if (retval) { - dir->i_nlink--; + DEC_DIR_INODE_NLINK(dir) goto out_failed; } @@ -1122,10 +1122,6 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir, reiserfs_write_unlock(dir->i_sb); return -EMLINK; } - if (inode->i_nlink == 0) { - reiserfs_write_unlock(dir->i_sb); - return -ENOENT; - } /* inc before scheduling so reiserfs_unlink knows we are here */ inc_nlink(inode); diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 3cfb2e9..5c11ca8 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -978,8 +978,6 @@ int reiserfs_permission(struct inode *inode, int mask, unsigned int flags) static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd) { - if (nd->flags & LOOKUP_RCU) - return -ECHILD; return -EPERM; } @@ -75,13 +75,16 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int error = -EINVAL; int lookup_flags = 0; - if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) != 0) + if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | + AT_EMPTY_PATH)) != 0) goto out; if (!(flag & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (flag & AT_NO_AUTOMOUNT) lookup_flags |= LOOKUP_NO_AUTOMOUNT; + if (flag & AT_EMPTY_PATH) + lookup_flags |= LOOKUP_EMPTY; error = user_path_at(dfd, filename, lookup_flags, &path); if (error) @@ -297,7 +300,7 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, if (bufsiz <= 0) return -EINVAL; - error = user_path_at(dfd, pathname, 0, &path); + error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path); if (!error) { struct inode *inode = path.dentry->d_inode; diff --git a/fs/statfs.c b/fs/statfs.c index 30ea8c8..8244924 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -73,149 +73,135 @@ int vfs_statfs(struct path *path, struct kstatfs *buf) } EXPORT_SYMBOL(vfs_statfs); -static int do_statfs_native(struct path *path, struct statfs *buf) +int user_statfs(const char __user *pathname, struct kstatfs *st) { - struct kstatfs st; - int retval; + struct path path; + int error = user_path(pathname, &path); + if (!error) { + error = vfs_statfs(&path, st); + path_put(&path); + } + return error; +} - retval = vfs_statfs(path, &st); - if (retval) - return retval; +int fd_statfs(int fd, struct kstatfs *st) +{ + struct file *file = fget(fd); + int error = -EBADF; + if (file) { + error = vfs_statfs(&file->f_path, st); + fput(file); + } + return error; +} - if (sizeof(*buf) == sizeof(st)) - memcpy(buf, &st, sizeof(st)); +static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) +{ + struct statfs buf; + + if (sizeof(buf) == sizeof(*st)) + memcpy(&buf, st, sizeof(*st)); else { - if (sizeof buf->f_blocks == 4) { - if ((st.f_blocks | st.f_bfree | st.f_bavail | - st.f_bsize | st.f_frsize) & + if (sizeof buf.f_blocks == 4) { + if ((st->f_blocks | st->f_bfree | st->f_bavail | + st->f_bsize | st->f_frsize) & 0xffffffff00000000ULL) return -EOVERFLOW; /* * f_files and f_ffree may be -1; it's okay to stuff * that into 32 bits */ - if (st.f_files != -1 && - (st.f_files & 0xffffffff00000000ULL)) + if (st->f_files != -1 && + (st->f_files & 0xffffffff00000000ULL)) return -EOVERFLOW; - if (st.f_ffree != -1 && - (st.f_ffree & 0xffffffff00000000ULL)) + if (st->f_ffree != -1 && + (st->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } - buf->f_type = st.f_type; - buf->f_bsize = st.f_bsize; - buf->f_blocks = st.f_blocks; - buf->f_bfree = st.f_bfree; - buf->f_bavail = st.f_bavail; - buf->f_files = st.f_files; - buf->f_ffree = st.f_ffree; - buf->f_fsid = st.f_fsid; - buf->f_namelen = st.f_namelen; - buf->f_frsize = st.f_frsize; - buf->f_flags = st.f_flags; - memset(buf->f_spare, 0, sizeof(buf->f_spare)); + buf.f_type = st->f_type; + buf.f_bsize = st->f_bsize; + buf.f_blocks = st->f_blocks; + buf.f_bfree = st->f_bfree; + buf.f_bavail = st->f_bavail; + buf.f_files = st->f_files; + buf.f_ffree = st->f_ffree; + buf.f_fsid = st->f_fsid; + buf.f_namelen = st->f_namelen; + buf.f_frsize = st->f_frsize; + buf.f_flags = st->f_flags; + memset(buf.f_spare, 0, sizeof(buf.f_spare)); } + if (copy_to_user(p, &buf, sizeof(buf))) + return -EFAULT; return 0; } -static int do_statfs64(struct path *path, struct statfs64 *buf) +static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) { - struct kstatfs st; - int retval; - - retval = vfs_statfs(path, &st); - if (retval) - return retval; - - if (sizeof(*buf) == sizeof(st)) - memcpy(buf, &st, sizeof(st)); + struct statfs64 buf; + if (sizeof(buf) == sizeof(*st)) + memcpy(&buf, st, sizeof(*st)); else { - buf->f_type = st.f_type; - buf->f_bsize = st.f_bsize; - buf->f_blocks = st.f_blocks; - buf->f_bfree = st.f_bfree; - buf->f_bavail = st.f_bavail; - buf->f_files = st.f_files; - buf->f_ffree = st.f_ffree; - buf->f_fsid = st.f_fsid; - buf->f_namelen = st.f_namelen; - buf->f_frsize = st.f_frsize; - buf->f_flags = st.f_flags; - memset(buf->f_spare, 0, sizeof(buf->f_spare)); + buf.f_type = st->f_type; + buf.f_bsize = st->f_bsize; + buf.f_blocks = st->f_blocks; + buf.f_bfree = st->f_bfree; + buf.f_bavail = st->f_bavail; + buf.f_files = st->f_files; + buf.f_ffree = st->f_ffree; + buf.f_fsid = st->f_fsid; + buf.f_namelen = st->f_namelen; + buf.f_frsize = st->f_frsize; + buf.f_flags = st->f_flags; + memset(buf.f_spare, 0, sizeof(buf.f_spare)); } + if (copy_to_user(p, &buf, sizeof(buf))) + return -EFAULT; return 0; } SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf) { - struct path path; - int error; - - error = user_path(pathname, &path); - if (!error) { - struct statfs tmp; - error = do_statfs_native(&path, &tmp); - if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) - error = -EFAULT; - path_put(&path); - } + struct kstatfs st; + int error = user_statfs(pathname, &st); + if (!error) + error = do_statfs_native(&st, buf); return error; } SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf) { - struct path path; - long error; - + struct kstatfs st; + int error; if (sz != sizeof(*buf)) return -EINVAL; - error = user_path(pathname, &path); - if (!error) { - struct statfs64 tmp; - error = do_statfs64(&path, &tmp); - if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) - error = -EFAULT; - path_put(&path); - } + error = user_statfs(pathname, &st); + if (!error) + error = do_statfs64(&st, buf); return error; } SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf) { - struct file *file; - struct statfs tmp; - int error; - - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = do_statfs_native(&file->f_path, &tmp); - if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) - error = -EFAULT; - fput(file); -out: + struct kstatfs st; + int error = fd_statfs(fd, &st); + if (!error) + error = do_statfs_native(&st, buf); return error; } SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf) { - struct file *file; - struct statfs64 tmp; + struct kstatfs st; int error; if (sz != sizeof(*buf)) return -EINVAL; - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = do_statfs64(&file->f_path, &tmp); - if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) - error = -EFAULT; - fput(file); -out: + error = fd_statfs(fd, &st); + if (!error) + error = do_statfs64(&st, buf); return error; } @@ -177,6 +177,11 @@ void deactivate_locked_super(struct super_block *s) struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { fs->kill_sb(s); + /* + * We need to call rcu_barrier so all the delayed rcu free + * inodes are flushed before we release the fs module. + */ + rcu_barrier(); put_filesystem(fs); put_super(s); } else { diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index b427b12..e474fbc 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -245,7 +245,6 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry, new_de = sysv_find_entry(new_dentry, &new_page); if (!new_de) goto out_dir; - inode_inc_link_count(old_inode); sysv_set_link(new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) @@ -257,18 +256,15 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry, if (new_dir->i_nlink >= SYSV_SB(new_dir->i_sb)->s_link_max) goto out_dir; } - inode_inc_link_count(old_inode); err = sysv_add_link(new_dentry, old_inode); - if (err) { - inode_dec_link_count(old_inode); + if (err) goto out_dir; - } if (dir_de) inode_inc_link_count(new_dir); } sysv_delete_entry(old_de, old_page); - inode_dec_link_count(old_inode); + mark_inode_dirty(old_inode); if (dir_de) { sysv_set_link(dir_de, dir_page, new_dir); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 14f64b6..7217d67 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -522,24 +522,6 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, ubifs_assert(mutex_is_locked(&dir->i_mutex)); ubifs_assert(mutex_is_locked(&inode->i_mutex)); - /* - * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing - * otherwise has the potential to corrupt the orphan inode list. - * - * Indeed, consider a scenario when 'vfs_link(dirA/fileA)' and - * 'vfs_unlink(dirA/fileA, dirB/fileB)' race. 'vfs_link()' does not - * lock 'dirA->i_mutex', so this is possible. Both of the functions - * lock 'fileA->i_mutex' though. Suppose 'vfs_unlink()' wins, and takes - * 'fileA->i_mutex' mutex first. Suppose 'fileA->i_nlink' is 1. In this - * case 'ubifs_unlink()' will drop the last reference, and put 'inodeA' - * to the list of orphans. After this, 'vfs_link()' will link - * 'dirB/fileB' to 'inodeA'. This is a problem because, for example, - * the subsequent 'vfs_unlink(dirB/fileB)' will add the same inode - * to the list of orphans. - */ - if (inode->i_nlink == 0) - return -ENOENT; - err = dbg_check_synced_i_size(inode); if (err) return err; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 2be0f9e..f1dce84 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -32,6 +32,8 @@ #include <linux/crc-itu-t.h> #include <linux/exportfs.h> +enum { UDF_MAX_LINKS = 0xffff }; + static inline int udf_match(int len1, const unsigned char *name1, int len2, const unsigned char *name2) { @@ -650,7 +652,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, int mode) struct udf_inode_info *iinfo; err = -EMLINK; - if (dir->i_nlink >= (256 << sizeof(dir->i_nlink)) - 1) + if (dir->i_nlink >= UDF_MAX_LINKS) goto out; err = -EIO; @@ -1034,9 +1036,8 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, struct fileIdentDesc cfi, *fi; int err; - if (inode->i_nlink >= (256 << sizeof(inode->i_nlink)) - 1) { + if (inode->i_nlink >= UDF_MAX_LINKS) return -EMLINK; - } fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err); if (!fi) { @@ -1131,9 +1132,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; retval = -EMLINK; - if (!new_inode && - new_dir->i_nlink >= - (256 << sizeof(new_dir->i_nlink)) - 1) + if (!new_inode && new_dir->i_nlink >= UDF_MAX_LINKS) goto end_rename; } if (!nfi) { @@ -1287,8 +1286,13 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp, struct fid *fid = (struct fid *)fh; int type = FILEID_UDF_WITHOUT_PARENT; - if (len < 3 || (connectable && len < 5)) + if (connectable && (len < 5)) { + *lenp = 5; return 255; + } else if (len < 3) { + *lenp = 3; + return 255; + } *lenp = 3; fid->udf.block = location.logicalBlockNum; diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 12f39b9..d6f6815 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -306,7 +306,6 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_page); if (!new_de) goto out_dir; - inode_inc_link_count(old_inode); ufs_set_link(new_dir, new_de, new_page, old_inode); new_inode->i_ctime = CURRENT_TIME_SEC; if (dir_de) @@ -318,12 +317,9 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_dir->i_nlink >= UFS_LINK_MAX) goto out_dir; } - inode_inc_link_count(old_inode); err = ufs_add_link(new_dentry, old_inode); - if (err) { - inode_dec_link_count(old_inode); + if (err) goto out_dir; - } if (dir_de) inode_inc_link_count(new_dir); } @@ -331,12 +327,11 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry, /* * Like most other Unix systems, set the ctime for inodes on a * rename. - * inode_dec_link_count() will mark the inode dirty. */ old_inode->i_ctime = CURRENT_TIME_SEC; ufs_delete_entry(old_dir, old_de, old_page); - inode_dec_link_count(old_inode); + mark_inode_dirty(old_inode); if (dir_de) { ufs_set_link(old_inode, dir_de, dir_page, new_dir); diff --git a/fs/xfs/linux-2.6/xfs_discard.c b/fs/xfs/linux-2.6/xfs_discard.c index 05201ae..d61611c 100644 --- a/fs/xfs/linux-2.6/xfs_discard.c +++ b/fs/xfs/linux-2.6/xfs_discard.c @@ -152,6 +152,8 @@ xfs_ioc_trim( if (!capable(CAP_SYS_ADMIN)) return -XFS_ERROR(EPERM); + if (!blk_queue_discard(q)) + return -XFS_ERROR(EOPNOTSUPP); if (copy_from_user(&range, urange, sizeof(range))) return -XFS_ERROR(EFAULT); diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index fc0114d..f4f878f 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -89,8 +89,10 @@ xfs_fs_encode_fh( * seven combinations work. The real answer is "don't use v2". */ len = xfs_fileid_length(fileid_type); - if (*max_len < len) + if (*max_len < len) { + *max_len = len; return 255; + } *max_len = len; switch (fileid_type) { diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index b06ede1..0ca0e3c 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -695,14 +695,19 @@ xfs_ioc_fsgeometry_v1( xfs_mount_t *mp, void __user *arg) { - xfs_fsop_geom_v1_t fsgeo; + xfs_fsop_geom_t fsgeo; int error; - error = xfs_fs_geometry(mp, (xfs_fsop_geom_t *)&fsgeo, 3); + error = xfs_fs_geometry(mp, &fsgeo, 3); if (error) return -error; - if (copy_to_user(arg, &fsgeo, sizeof(fsgeo))) + /* + * Caller should have passed an argument of type + * xfs_fsop_geom_v1_t. This is a proper subset of the + * xfs_fsop_geom_t that xfs_fs_geometry() fills in. + */ + if (copy_to_user(arg, &fsgeo, sizeof(xfs_fsop_geom_v1_t))) return -XFS_ERROR(EFAULT); return 0; } @@ -985,10 +990,22 @@ xfs_ioctl_setattr( /* * Extent size must be a multiple of the appropriate block - * size, if set at all. + * size, if set at all. It must also be smaller than the + * maximum extent size supported by the filesystem. + * + * Also, for non-realtime files, limit the extent size hint to + * half the size of the AGs in the filesystem so alignment + * doesn't result in extents larger than an AG. */ if (fa->fsx_extsize != 0) { - xfs_extlen_t size; + xfs_extlen_t size; + xfs_fsblock_t extsize_fsb; + + extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); + if (extsize_fsb > MAXEXTLEN) { + code = XFS_ERROR(EINVAL); + goto error_return; + } if (XFS_IS_REALTIME_INODE(ip) || ((mask & FSX_XFLAGS) && @@ -997,6 +1014,10 @@ xfs_ioctl_setattr( mp->m_sb.sb_blocklog; } else { size = mp->m_sb.sb_blocksize; + if (extsize_fsb > mp->m_sb.sb_agblocks / 2) { + code = XFS_ERROR(EINVAL); + goto error_return; + } } if (fa->fsx_extsize % size) { diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index f8e854b..206a281 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -1863,12 +1863,14 @@ xfs_qm_dqreclaim_one(void) xfs_dquot_t *dqpout; xfs_dquot_t *dqp; int restarts; + int startagain; restarts = 0; dqpout = NULL; /* lockorder: hashchainlock, freelistlock, mplistlock, dqlock, dqflock */ -startagain: +again: + startagain = 0; mutex_lock(&xfs_Gqm->qm_dqfrlist_lock); list_for_each_entry(dqp, &xfs_Gqm->qm_dqfrlist, q_freelist) { @@ -1885,13 +1887,10 @@ startagain: ASSERT(! (dqp->dq_flags & XFS_DQ_INACTIVE)); trace_xfs_dqreclaim_want(dqp); - - xfs_dqunlock(dqp); - mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock); - if (++restarts >= XFS_QM_RECLAIM_MAX_RESTARTS) - return NULL; XQM_STATS_INC(xqmstats.xs_qm_dqwants); - goto startagain; + restarts++; + startagain = 1; + goto dqunlock; } /* @@ -1906,23 +1905,20 @@ startagain: ASSERT(list_empty(&dqp->q_mplist)); list_del_init(&dqp->q_freelist); xfs_Gqm->qm_dqfrlist_cnt--; - xfs_dqunlock(dqp); dqpout = dqp; XQM_STATS_INC(xqmstats.xs_qm_dqinact_reclaims); - break; + goto dqunlock; } ASSERT(dqp->q_hash); ASSERT(!list_empty(&dqp->q_mplist)); /* - * Try to grab the flush lock. If this dquot is in the process of - * getting flushed to disk, we don't want to reclaim it. + * Try to grab the flush lock. If this dquot is in the process + * of getting flushed to disk, we don't want to reclaim it. */ - if (!xfs_dqflock_nowait(dqp)) { - xfs_dqunlock(dqp); - continue; - } + if (!xfs_dqflock_nowait(dqp)) + goto dqunlock; /* * We have the flush lock so we know that this is not in the @@ -1944,8 +1940,7 @@ startagain: xfs_fs_cmn_err(CE_WARN, mp, "xfs_qm_dqreclaim: dquot %p flush failed", dqp); } - xfs_dqunlock(dqp); /* dqflush unlocks dqflock */ - continue; + goto dqunlock; } /* @@ -1967,13 +1962,8 @@ startagain: */ if (!mutex_trylock(&mp->m_quotainfo->qi_dqlist_lock)) { restarts++; - mutex_unlock(&dqp->q_hash->qh_lock); - xfs_dqfunlock(dqp); - xfs_dqunlock(dqp); - mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock); - if (restarts++ >= XFS_QM_RECLAIM_MAX_RESTARTS) - return NULL; - goto startagain; + startagain = 1; + goto qhunlock; } ASSERT(dqp->q_nrefs == 0); @@ -1986,14 +1976,20 @@ startagain: xfs_Gqm->qm_dqfrlist_cnt--; dqpout = dqp; mutex_unlock(&mp->m_quotainfo->qi_dqlist_lock); +qhunlock: mutex_unlock(&dqp->q_hash->qh_lock); dqfunlock: xfs_dqfunlock(dqp); +dqunlock: xfs_dqunlock(dqp); if (dqpout) break; if (restarts >= XFS_QM_RECLAIM_MAX_RESTARTS) - return NULL; + break; + if (startagain) { + mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock); + goto again; + } } mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock); return dqpout; diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h index 0ab56b3..d0b3bc7 100644 --- a/fs/xfs/xfs_alloc.h +++ b/fs/xfs/xfs_alloc.h @@ -75,6 +75,22 @@ typedef unsigned int xfs_alloctype_t; #define XFS_ALLOC_SET_ASIDE(mp) (4 + ((mp)->m_sb.sb_agcount * 4)) /* + * When deciding how much space to allocate out of an AG, we limit the + * allocation maximum size to the size the AG. However, we cannot use all the + * blocks in the AG - some are permanently used by metadata. These + * blocks are generally: + * - the AG superblock, AGF, AGI and AGFL + * - the AGF (bno and cnt) and AGI btree root blocks + * - 4 blocks on the AGFL according to XFS_ALLOC_SET_ASIDE() limits + * + * The AG headers are sector sized, so the amount of space they take up is + * dependent on filesystem geometry. The others are all single blocks. + */ +#define XFS_ALLOC_AG_MAX_USABLE(mp) \ + ((mp)->m_sb.sb_agblocks - XFS_BB_TO_FSB(mp, XFS_FSS_TO_BB(mp, 4)) - 7) + + +/* * Argument structure for xfs_alloc routines. * This is turned into a structure to avoid having 20 arguments passed * down several levels of the stack. diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 4111cd3..dc3afd77 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -1038,17 +1038,34 @@ xfs_bmap_add_extent_delay_real( * Filling in the middle part of a previous delayed allocation. * Contiguity is impossible here. * This case is avoided almost all the time. + * + * We start with a delayed allocation: + * + * +ddddddddddddddddddddddddddddddddddddddddddddddddddddddd+ + * PREV @ idx + * + * and we are allocating: + * +rrrrrrrrrrrrrrrrr+ + * new + * + * and we set it up for insertion as: + * +ddddddddddddddddddd+rrrrrrrrrrrrrrrrr+ddddddddddddddddd+ + * new + * PREV @ idx LEFT RIGHT + * inserted at idx + 1 */ temp = new->br_startoff - PREV.br_startoff; - trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - r[0] = *new; - r[1].br_state = PREV.br_state; - r[1].br_startblock = 0; - r[1].br_startoff = new_endoff; temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff; - r[1].br_blockcount = temp2; - xfs_iext_insert(ip, idx + 1, 2, &r[0], state); + trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_); + xfs_bmbt_set_blockcount(ep, temp); /* truncate PREV */ + LEFT = *new; + RIGHT.br_state = PREV.br_state; + RIGHT.br_startblock = nullstartblock( + (int)xfs_bmap_worst_indlen(ip, temp2)); + RIGHT.br_startoff = new_endoff; + RIGHT.br_blockcount = temp2; + /* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */ + xfs_iext_insert(ip, idx + 1, 2, &LEFT, state); ip->i_df.if_lastex = idx + 1; ip->i_d.di_nextents++; if (cur == NULL) @@ -2430,7 +2447,7 @@ xfs_bmap_btalloc_nullfb( startag = ag = 0; pag = xfs_perag_get(mp, ag); - while (*blen < ap->alen) { + while (*blen < args->maxlen) { if (!pag->pagf_init) { error = xfs_alloc_pagf_init(mp, args->tp, ag, XFS_ALLOC_FLAG_TRYLOCK); @@ -2452,7 +2469,7 @@ xfs_bmap_btalloc_nullfb( notinit = 1; if (xfs_inode_is_filestream(ap->ip)) { - if (*blen >= ap->alen) + if (*blen >= args->maxlen) break; if (ap->userdata) { @@ -2498,14 +2515,14 @@ xfs_bmap_btalloc_nullfb( * If the best seen length is less than the request * length, use the best as the minimum. */ - else if (*blen < ap->alen) + else if (*blen < args->maxlen) args->minlen = *blen; /* - * Otherwise we've seen an extent as big as alen, + * Otherwise we've seen an extent as big as maxlen, * use that as the minimum. */ else - args->minlen = ap->alen; + args->minlen = args->maxlen; /* * set the failure fallback case to look in the selected @@ -2573,7 +2590,9 @@ xfs_bmap_btalloc( args.tp = ap->tp; args.mp = mp; args.fsbno = ap->rval; - args.maxlen = MIN(ap->alen, mp->m_sb.sb_agblocks); + + /* Trim the allocation back to the maximum an AG can fit. */ + args.maxlen = MIN(ap->alen, XFS_ALLOC_AG_MAX_USABLE(mp)); args.firstblock = ap->firstblock; blen = 0; if (nullfb) { @@ -2621,7 +2640,7 @@ xfs_bmap_btalloc( /* * Adjust for alignment */ - if (blen > args.alignment && blen <= ap->alen) + if (blen > args.alignment && blen <= args.maxlen) args.minlen = blen - args.alignment; args.minalignslop = 0; } else { @@ -2640,7 +2659,7 @@ xfs_bmap_btalloc( * of minlen+alignment+slop doesn't go up * between the calls. */ - if (blen > mp->m_dalign && blen <= ap->alen) + if (blen > mp->m_dalign && blen <= args.maxlen) nextminlen = blen - mp->m_dalign; else nextminlen = args.minlen; @@ -4485,6 +4504,16 @@ xfs_bmapi( /* Figure out the extent size, adjust alen */ extsz = xfs_get_extsz_hint(ip); if (extsz) { + /* + * make sure we don't exceed a single + * extent length when we align the + * extent by reducing length we are + * going to allocate by the maximum + * amount extent size aligment may + * require. + */ + alen = XFS_FILBLKS_MIN(len, + MAXEXTLEN - (2 * extsz - 1)); error = xfs_bmap_extsize_align(mp, &got, &prev, extsz, rt, eof, diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 98c6f73..6f8c21c 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -427,13 +427,15 @@ xfs_buf_item_unpin( if (remove) { /* - * We have to remove the log item from the transaction - * as we are about to release our reference to the - * buffer. If we don't, the unlock that occurs later - * in xfs_trans_uncommit() will ry to reference the + * If we are in a transaction context, we have to + * remove the log item from the transaction as we are + * about to release our reference to the buffer. If we + * don't, the unlock that occurs later in + * xfs_trans_uncommit() will try to reference the * buffer which we no longer have a hold on. */ - xfs_trans_del_item(lip); + if (lip->li_desc) + xfs_trans_del_item(lip); /* * Since the transaction no longer refers to the buffer, diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 75f2ef6..d22e626 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -138,7 +138,8 @@ xfs_efi_item_unpin( if (remove) { ASSERT(!(lip->li_flags & XFS_LI_IN_AIL)); - xfs_trans_del_item(lip); + if (lip->li_desc) + xfs_trans_del_item(lip); xfs_efi_item_free(efip); return; } diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index cec89dd..85668ef 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -53,6 +53,9 @@ xfs_fs_geometry( xfs_fsop_geom_t *geo, int new_version) { + + memset(geo, 0, sizeof(*geo)); + geo->blocksize = mp->m_sb.sb_blocksize; geo->rtextsize = mp->m_sb.sb_rextsize; geo->agblocks = mp->m_sb.sb_agblocks; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 55582bd..8a0f044 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -337,7 +337,12 @@ xfs_iomap_prealloc_size( int shift = 0; int64_t freesp; - alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size); + /* + * rounddown_pow_of_two() returns an undefined result + * if we pass in alloc_blocks = 0. Hence the "+ 1" to + * ensure we always pass in a non-zero value. + */ + alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size) + 1; alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN, rounddown_pow_of_two(alloc_blocks)); diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 916eb7d..3bd3291 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -191,7 +191,7 @@ void xfs_log_ticket_put(struct xlog_ticket *ticket); xlog_tid_t xfs_log_get_trans_ident(struct xfs_trans *tp); -int xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp, +void xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_log_vec *log_vector, xfs_lsn_t *commit_lsn, int flags); bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 9dc8125..9ca59be 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -543,7 +543,7 @@ xlog_cil_push( error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0); if (error) - goto out_abort; + goto out_abort_free_ticket; /* * now that we've written the checkpoint into the log, strictly @@ -569,8 +569,9 @@ restart: } spin_unlock(&cil->xc_cil_lock); + /* xfs_log_done always frees the ticket on error. */ commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, 0); - if (error || commit_lsn == -1) + if (commit_lsn == -1) goto out_abort; /* attach all the transactions w/ busy extents to iclog */ @@ -600,6 +601,8 @@ out_free_ticket: kmem_free(new_ctx); return 0; +out_abort_free_ticket: + xfs_log_ticket_put(tic); out_abort: xlog_cil_committed(ctx, XFS_LI_ABORTED); return XFS_ERROR(EIO); @@ -622,7 +625,7 @@ out_abort: * background commit, returns without it held once background commits are * allowed again. */ -int +void xfs_log_commit_cil( struct xfs_mount *mp, struct xfs_trans *tp, @@ -637,11 +640,6 @@ xfs_log_commit_cil( if (flags & XFS_TRANS_RELEASE_LOG_RES) log_flags = XFS_LOG_REL_PERM_RESERV; - if (XLOG_FORCED_SHUTDOWN(log)) { - xlog_cil_free_logvec(log_vector); - return XFS_ERROR(EIO); - } - /* * do all the hard work of formatting items (including memory * allocation) outside the CIL context lock. This prevents stalling CIL @@ -701,7 +699,6 @@ xfs_log_commit_cil( */ if (push) xlog_cil_push(log, 0); - return 0; } /* diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 33dbc4e..7692279 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -1446,6 +1446,14 @@ xfs_log_item_batch_insert( * Bulk operation version of xfs_trans_committed that takes a log vector of * items to insert into the AIL. This uses bulk AIL insertion techniques to * minimise lock traffic. + * + * If we are called with the aborted flag set, it is because a log write during + * a CIL checkpoint commit has failed. In this case, all the items in the + * checkpoint have already gone through IOP_COMMITED and IOP_UNLOCK, which + * means that checkpoint commit abort handling is treated exactly the same + * as an iclog write error even though we haven't started any IO yet. Hence in + * this case all we need to do is IOP_COMMITTED processing, followed by an + * IOP_UNPIN(aborted) call. */ void xfs_trans_committed_bulk( @@ -1472,6 +1480,16 @@ xfs_trans_committed_bulk( if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0) continue; + /* + * if we are aborting the operation, no point in inserting the + * object into the AIL as we are in a shutdown situation. + */ + if (aborted) { + ASSERT(XFS_FORCED_SHUTDOWN(ailp->xa_mount)); + IOP_UNPIN(lip, 1); + continue; + } + if (item_lsn != commit_lsn) { /* @@ -1503,20 +1521,24 @@ xfs_trans_committed_bulk( } /* - * Called from the trans_commit code when we notice that - * the filesystem is in the middle of a forced shutdown. + * Called from the trans_commit code when we notice that the filesystem is in + * the middle of a forced shutdown. + * + * When we are called here, we have already pinned all the items in the + * transaction. However, neither IOP_COMMITTING or IOP_UNLOCK has been called + * so we can simply walk the items in the transaction, unpin them with an abort + * flag and then free the items. Note that unpinning the items can result in + * them being freed immediately, so we need to use a safe list traversal method + * here. */ STATIC void xfs_trans_uncommit( struct xfs_trans *tp, uint flags) { - struct xfs_log_item_desc *lidp; + struct xfs_log_item_desc *lidp, *n; - list_for_each_entry(lidp, &tp->t_items, lid_trans) { - /* - * Unpin all but those that aren't dirty. - */ + list_for_each_entry_safe(lidp, n, &tp->t_items, lid_trans) { if (lidp->lid_flags & XFS_LID_DIRTY) IOP_UNPIN(lidp->lid_item, 1); } @@ -1733,7 +1755,6 @@ xfs_trans_commit_cil( int flags) { struct xfs_log_vec *log_vector; - int error; /* * Get each log item to allocate a vector structure for @@ -1744,9 +1765,7 @@ xfs_trans_commit_cil( if (!log_vector) return ENOMEM; - error = xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags); - if (error) - return error; + xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags); current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS); xfs_trans_free(tp); diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h index 2bcc5c7..61e03dd 100644 --- a/include/asm-generic/cputime.h +++ b/include/asm-generic/cputime.h @@ -30,6 +30,9 @@ typedef u64 cputime64_t; #define cputime64_to_jiffies64(__ct) (__ct) #define jiffies64_to_cputime64(__jif) (__jif) #define cputime_to_cputime64(__ct) ((u64) __ct) +#define cputime64_gt(__a, __b) ((__a) > (__b)) + +#define nsecs_to_cputime64(__ct) nsecs_to_jiffies64(__ct) /* diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h index 0fc16e3..84793c70 100644 --- a/include/asm-generic/fcntl.h +++ b/include/asm-generic/fcntl.h @@ -80,6 +80,10 @@ #define O_SYNC (__O_SYNC|O_DSYNC) #endif +#ifndef O_PATH +#define O_PATH 010000000 +#endif + #ifndef O_NDELAY #define O_NDELAY O_NONBLOCK #endif diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h index 3c2344f..01f227e 100644 --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -6,7 +6,7 @@ #include <asm/errno.h> static inline int -futex_atomic_op_inuser (int encoded_op, int __user *uaddr) +futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) { int op = (encoded_op >> 28) & 7; int cmp = (encoded_op >> 24) & 15; @@ -16,7 +16,7 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int))) + if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; pagefault_disable(); @@ -48,7 +48,8 @@ futex_atomic_op_inuser (int encoded_op, int __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval) +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) { return -ENOSYS; } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 31b6188..b4bfe33 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -4,6 +4,8 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU +#include <linux/mm_types.h> + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index b3bfabc..c1a1216 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -11,6 +11,7 @@ extern char _sinittext[], _einittext[]; extern char _end[]; extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[]; extern char __kprobes_text_start[], __kprobes_text_end[]; +extern char __entry_text_start[], __entry_text_end[]; extern char __initdata_begin[], __initdata_end[]; extern char __start_rodata[], __end_rodata[]; diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h index b969770..57af033 100644 --- a/include/asm-generic/unistd.h +++ b/include/asm-generic/unistd.h @@ -646,9 +646,13 @@ __SYSCALL(__NR_prlimit64, sys_prlimit64) __SYSCALL(__NR_fanotify_init, sys_fanotify_init) #define __NR_fanotify_mark 263 __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_name_to_handle_at 264 +__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) +#define __NR_open_by_handle_at 265 +__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) #undef __NR_syscalls -#define __NR_syscalls 264 +#define __NR_syscalls 266 /* * All syscalls below here should go away really, diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6ebb810..906c3ce 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -124,7 +124,8 @@ #endif #ifdef CONFIG_EVENT_TRACING -#define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .; \ +#define FTRACE_EVENTS() . = ALIGN(8); \ + VMLINUX_SYMBOL(__start_ftrace_events) = .; \ *(_ftrace_events) \ VMLINUX_SYMBOL(__stop_ftrace_events) = .; #else @@ -140,7 +141,8 @@ #endif #ifdef CONFIG_FTRACE_SYSCALLS -#define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \ +#define TRACE_SYSCALLS() . = ALIGN(8); \ + VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \ *(__syscalls_metadata) \ VMLINUX_SYMBOL(__stop_syscalls_metadata) = .; #else @@ -165,10 +167,8 @@ CPU_KEEP(exit.data) \ MEM_KEEP(init.data) \ MEM_KEEP(exit.data) \ - . = ALIGN(32); \ - VMLINUX_SYMBOL(__start___tracepoints) = .; \ + STRUCT_ALIGN(); \ *(__tracepoints) \ - VMLINUX_SYMBOL(__stop___tracepoints) = .; \ /* implement dynamic printk debug */ \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___verbose) = .; \ @@ -176,13 +176,7 @@ VMLINUX_SYMBOL(__stop___verbose) = .; \ LIKELY_PROFILE() \ BRANCH_PROFILE() \ - TRACE_PRINTKS() \ - \ - STRUCT_ALIGN(); \ - FTRACE_EVENTS() \ - \ - STRUCT_ALIGN(); \ - TRACE_SYSCALLS() + TRACE_PRINTKS() /* * Data section helpers @@ -220,6 +214,10 @@ VMLINUX_SYMBOL(__start_rodata) = .; \ *(.rodata) *(.rodata.*) \ *(__vermagic) /* Kernel version magic */ \ + . = ALIGN(8); \ + VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \ + *(__tracepoints_ptrs) /* Tracepoints: pointer array */\ + VMLINUX_SYMBOL(__stop___tracepoints_ptrs) = .; \ *(__markers_strings) /* Markers: strings */ \ *(__tracepoints_strings)/* Tracepoints: strings */ \ } \ @@ -426,6 +424,12 @@ *(.kprobes.text) \ VMLINUX_SYMBOL(__kprobes_text_end) = .; +#define ENTRY_TEXT \ + ALIGN_FUNCTION(); \ + VMLINUX_SYMBOL(__entry_text_start) = .; \ + *(.entry.text) \ + VMLINUX_SYMBOL(__entry_text_end) = .; + #ifdef CONFIG_FUNCTION_GRAPH_TRACER #define IRQENTRY_TEXT \ ALIGN_FUNCTION(); \ @@ -482,6 +486,8 @@ KERNEL_CTORS() \ *(.init.rodata) \ MCOUNT_REC() \ + FTRACE_EVENTS() \ + TRACE_SYSCALLS() \ DEV_DISCARD(init.rodata) \ CPU_DISCARD(init.rodata) \ MEM_DISCARD(init.rodata) \ diff --git a/include/drm/drmP.h b/include/drm/drmP.h index a4694c6..348843b 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1101,7 +1101,7 @@ struct drm_device { struct platform_device *platformdev; /**< Platform device struture */ struct drm_sg_mem *sg; /**< Scatter gather memory */ - int num_crtcs; /**< Number of CRTCs on this device */ + unsigned int num_crtcs; /**< Number of CRTCs on this device */ void *dev_private; /**< device private data */ void *mm_private; struct address_space *dev_mapping; @@ -1367,7 +1367,7 @@ extern int drm_vblank_wait(struct drm_device *dev, unsigned int *vbl_seq); extern u32 drm_vblank_count(struct drm_device *dev, int crtc); extern u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc, struct timeval *vblanktime); -extern void drm_handle_vblank(struct drm_device *dev, int crtc); +extern bool drm_handle_vblank(struct drm_device *dev, int crtc); extern int drm_vblank_get(struct drm_device *dev, int crtc); extern void drm_vblank_put(struct drm_device *dev, int crtc); extern void drm_vblank_off(struct drm_device *dev, int crtc); diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index acd7fad..801be59 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -275,6 +275,7 @@ struct drm_pending_vblank_event; /** * drm_crtc_funcs - control CRTCs for a given device + * @reset: reset CRTC after state has been invalidate (e.g. resume) * @dpms: control display power levels * @save: save CRTC state * @resore: restore CRTC state @@ -302,6 +303,8 @@ struct drm_crtc_funcs { void (*save)(struct drm_crtc *crtc); /* suspend? */ /* Restore CRTC state */ void (*restore)(struct drm_crtc *crtc); /* resume? */ + /* Reset CRTC state */ + void (*reset)(struct drm_crtc *crtc); /* cursor controls */ int (*cursor_set)(struct drm_crtc *crtc, struct drm_file *file_priv, @@ -379,6 +382,7 @@ struct drm_crtc { * @dpms: set power state (see drm_crtc_funcs above) * @save: save connector state * @restore: restore connector state + * @reset: reset connector after state has been invalidate (e.g. resume) * @mode_valid: is this mode valid on the given connector? * @mode_fixup: try to fixup proposed mode for this connector * @mode_set: set this mode @@ -396,6 +400,7 @@ struct drm_connector_funcs { void (*dpms)(struct drm_connector *connector, int mode); void (*save)(struct drm_connector *connector); void (*restore)(struct drm_connector *connector); + void (*reset)(struct drm_connector *connector); /* Check to see if anything is attached to the connector. * @force is set to false whilst polling, true when checking the @@ -413,6 +418,7 @@ struct drm_connector_funcs { }; struct drm_encoder_funcs { + void (*reset)(struct drm_encoder *encoder); void (*destroy)(struct drm_encoder *encoder); }; @@ -656,6 +662,7 @@ extern struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev, struct drm_display_mode *mode); extern void drm_mode_debug_printmodeline(struct drm_display_mode *mode); extern void drm_mode_config_init(struct drm_device *dev); +extern void drm_mode_config_reset(struct drm_device *dev); extern void drm_mode_config_cleanup(struct drm_device *dev); extern void drm_mode_set_name(struct drm_display_mode *mode); extern bool drm_mode_equal(struct drm_display_mode *mode1, struct drm_display_mode *mode2); diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index fe29ae3..5ff1194 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -28,7 +28,6 @@ {0x1002, 0x4156, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV350}, \ {0x1002, 0x4237, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS200|RADEON_IS_IGP}, \ {0x1002, 0x4242, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R200}, \ - {0x1002, 0x4243, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R200}, \ {0x1002, 0x4336, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS100|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \ {0x1002, 0x4337, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS200|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \ {0x1002, 0x4437, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS200|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \ diff --git a/include/keys/rxrpc-type.h b/include/keys/rxrpc-type.h index 5cb86c3..fc48754 100644 --- a/include/keys/rxrpc-type.h +++ b/include/keys/rxrpc-type.h @@ -99,7 +99,6 @@ struct rxrpc_key_token { * structure of raw payloads passed to add_key() or instantiate key */ struct rxrpc_key_data_v1 { - u32 kif_version; /* 1 */ u16 security_index; u16 ticket_length; u32 expiry; /* time_t */ diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 2296d8b..b0ada6f 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -1,5 +1,6 @@ header-y += byteorder/ header-y += can/ +header-y += caif/ header-y += dvb/ header-y += hdlc/ header-y += isdn/ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4d18ff3..d5063e1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -699,7 +699,7 @@ extern void blk_start_queue(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); -extern void __blk_run_queue(struct request_queue *); +extern void __blk_run_queue(struct request_queue *q, bool force_kblockd); extern void blk_run_queue(struct request_queue *); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, @@ -1088,7 +1088,6 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); -int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP /* @@ -1136,7 +1135,6 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) extern int blk_throtl_init(struct request_queue *q); extern void blk_throtl_exit(struct request_queue *q); extern int blk_throtl_bio(struct request_queue *q, struct bio **bio); -extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay); extern void throtl_shutdown_timer_wq(struct request_queue *q); #else /* CONFIG_BLK_DEV_THROTTLING */ static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio) @@ -1146,7 +1144,6 @@ static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio) static inline int blk_throtl_init(struct request_queue *q) { return 0; } static inline int blk_throtl_exit(struct request_queue *q) { return 0; } -static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {} static inline void throtl_shutdown_timer_wq(struct request_queue *q) {} #endif /* CONFIG_BLK_DEV_THROTTLING */ diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 3395cf7..b22fb0d 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -245,7 +245,6 @@ static inline int blk_cmd_buf_len(struct request *rq) extern void blk_dump_cmd(char *buf, struct request *rq); extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes); -extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq); #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */ diff --git a/include/linux/caif/Kbuild b/include/linux/caif/Kbuild new file mode 100644 index 0000000..a9cf250 --- /dev/null +++ b/include/linux/caif/Kbuild @@ -0,0 +1,2 @@ +header-y += caif_socket.h +header-y += if_caif.h diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c3011be..31d91a6 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -123,6 +123,7 @@ struct ceph_msg_pos { #define SOCK_CLOSED 11 /* socket state changed to closed */ #define OPENING 13 /* open connection w/ (possibly new) peer */ #define DEAD 14 /* dead, about to kfree */ +#define BACKOFF 15 /* * A single connection with another host. @@ -160,7 +161,6 @@ struct ceph_connection { struct list_head out_queue; struct list_head out_sent; /* sending or sent but unacked */ u64 out_seq; /* last message queued for send */ - bool out_keepalive_pending; u64 in_seq, in_seq_acked; /* last message received, acked */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ce104e3..e654fa2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -474,7 +474,8 @@ struct cgroup_subsys { struct cgroup *old_cgrp, struct task_struct *tsk, bool threadgroup); void (*fork)(struct cgroup_subsys *ss, struct task_struct *task); - void (*exit)(struct cgroup_subsys *ss, struct task_struct *task); + void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup *old_cgrp, struct task_struct *task); int (*populate)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp); @@ -626,6 +627,7 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg, /* Get id and depth of css */ unsigned short css_id(struct cgroup_subsys_state *css); unsigned short css_depth(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id); #else /* !CONFIG_CGROUPS */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index ccefff0..cdbfcb8 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -65,4 +65,8 @@ SUBSYS(net_cls) SUBSYS(blkio) #endif +#ifdef CONFIG_CGROUP_PERF +SUBSYS(perf) +#endif + /* */ diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 68cd248..66900e3 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -101,8 +101,8 @@ struct ieee_pfc { */ struct dcb_app { __u8 selector; - __u32 protocol; __u8 priority; + __u16 protocol; }; struct dcbmsg { diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 597692f..65970b8 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -34,7 +34,10 @@ struct debug_obj { /** * struct debug_obj_descr - object type specific debug description structure + * * @name: name of the object typee + * @debug_hint: function returning address, which have associated + * kernel symbol, to allow identify the object * @fixup_init: fixup function, which is called when the init check * fails * @fixup_activate: fixup function, which is called when the activate check @@ -46,7 +49,7 @@ struct debug_obj { */ struct debug_obj_descr { const char *name; - + void *(*debug_hint) (void *addr); int (*fixup_init) (void *addr, enum debug_obj_state state); int (*fixup_activate) (void *addr, enum debug_obj_state state); int (*fixup_destroy) (void *addr, enum debug_obj_state state); diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 2802898..33a42f2 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -8,6 +8,9 @@ struct inode; struct super_block; struct vfsmount; +/* limit the handle size to NFSv4 handle size now */ +#define MAX_HANDLE_SZ 128 + /* * The fileid_type identifies how the file within the filesystem is encoded. * In theory this is freely set and parsed by the filesystem, but we try to @@ -121,8 +124,10 @@ struct fid { * set, the encode_fh() should store sufficient information so that a good * attempt can be made to find not only the file but also it's place in the * filesystem. This typically means storing a reference to de->d_parent in - * the filehandle fragment. encode_fh() should return the number of bytes - * stored or a negative error code such as %-ENOSPC + * the filehandle fragment. encode_fh() should return the fileid_type on + * success and on error returns 255 (if the space needed to encode fh is + * greater than @max_len*4 bytes). On error @max_len contains the minimum + * size(in 4 byte unit) needed to encode the file handle. * * fh_to_dentry: * @fh_to_dentry is given a &struct super_block (@sb) and a file handle diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index a562fa5..f550f89 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -46,6 +46,7 @@ unlinking file. */ #define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ #define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */ +#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */ #ifdef __KERNEL__ diff --git a/include/linux/file.h b/include/linux/file.h index e85baeb..21a7995 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -29,6 +29,8 @@ static inline void fput_light(struct file *file, int fput_needed) extern struct file *fget(unsigned int fd); extern struct file *fget_light(unsigned int fd, int *fput_needed); +extern struct file *fget_raw(unsigned int fd); +extern struct file *fget_raw_light(unsigned int fd, int *fput_needed); extern void set_close_on_exec(unsigned int fd, int flag); extern void put_filp(struct file *); extern int alloc_fd(unsigned start, unsigned flags); diff --git a/include/linux/freezer.h b/include/linux/freezer.h index da7e52b..1effc8b 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -109,7 +109,7 @@ static inline void freezer_count(void) } /* - * Check if the task should be counted as freezeable by the freezer + * Check if the task should be counted as freezable by the freezer */ static inline int freezer_should_skip(struct task_struct *p) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 32b38cd..13df14e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -102,6 +102,9 @@ struct inodes_stat_t { /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +/* File is opened with O_PATH; almost nothing can be done with it */ +#define FMODE_PATH ((__force fmode_t)0x4000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x1000000) @@ -649,6 +652,7 @@ struct address_space { spinlock_t private_lock; /* for use by the address_space */ struct list_head private_list; /* ditto */ struct address_space *assoc_mapping; /* ditto */ + struct mutex unmap_mutex; /* to protect unmapping */ } __attribute__((aligned(sizeof(long)))); /* * On most architectures that alignment is already the case; but @@ -977,6 +981,13 @@ struct file { #endif }; +struct file_handle { + __u32 handle_bytes; + int handle_type; + /* file identifier */ + unsigned char f_handle[0]; +}; + #define get_file(x) atomic_long_inc(&(x)->f_count) #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) @@ -1400,6 +1411,7 @@ struct super_block { wait_queue_head_t s_wait_unfrozen; char s_id[32]; /* Informational name */ + u8 s_uuid[16]; /* UUID */ void *s_fs_info; /* Filesystem private info */ fmode_t s_mode; @@ -1873,6 +1885,8 @@ extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); extern int vfs_statfs(struct path *, struct kstatfs *); +extern int user_statfs(const char __user *, struct kstatfs *); +extern int fd_statfs(int, struct kstatfs *); extern int statfs_by_dentry(struct dentry *, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); @@ -1989,6 +2003,8 @@ extern int do_fallocate(struct file *file, int mode, loff_t offset, extern long do_sys_open(int dfd, const char __user *filename, int flags, int mode); extern struct file *filp_open(const char *, int, int); +extern struct file *file_open_root(struct dentry *, struct vfsmount *, + const char *, int); extern struct file * dentry_open(struct dentry *, struct vfsmount *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); @@ -2139,7 +2155,7 @@ extern void check_disk_size_change(struct gendisk *disk, struct block_device *bdev); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); -extern int __invalidate_device(struct block_device *); +extern int __invalidate_device(struct block_device *, bool); extern int invalidate_partition(struct gendisk *, int); #endif unsigned long invalidate_mapping_pages(struct address_space *mapping, @@ -2204,10 +2220,6 @@ extern struct file *create_read_pipe(struct file *f, int flags); extern struct file *create_write_pipe(int flags); extern void free_write_pipe(struct file *); -extern struct file *do_filp_open(int dfd, const char *pathname, - int open_flag, int mode, int acc_mode); -extern int may_open(struct path *, int, int); - extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern struct file * open_exec(const char *); @@ -2225,6 +2237,7 @@ extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); +extern void address_space_init_once(struct address_space *mapping); extern void ihold(struct inode * inode); extern void iput(struct inode *); extern struct inode * igrab(struct inode *); @@ -2555,9 +2568,12 @@ int proc_nr_inodes(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); +#define __FMODE_EXEC ((__force int) FMODE_EXEC) +#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) + #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ - (flag & FMODE_NONOTIFY))) + (flag & __FMODE_NONOTIFY))) #endif /* __KERNEL__ */ #endif /* _LINUX_FS_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index dcd6a7c..ca29e03 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -428,6 +428,7 @@ extern void unregister_ftrace_graph(void); extern void ftrace_graph_init_task(struct task_struct *t); extern void ftrace_graph_exit_task(struct task_struct *t); +extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu); static inline int task_curr_ret_stack(struct task_struct *t) { @@ -451,6 +452,7 @@ static inline void unpause_graph_tracing(void) static inline void ftrace_graph_init_task(struct task_struct *t) { } static inline void ftrace_graph_exit_task(struct task_struct *t) { } +static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { } static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc, trace_func_graph_ent_t entryfunc) diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 47e3997..22b32af 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -37,7 +37,6 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; - int lock_depth; }; #define FTRACE_MAX_EVENT \ @@ -208,7 +207,6 @@ struct ftrace_event_call { #define PERF_MAX_TRACE_SIZE 2048 -#define MAX_FILTER_PRED 32 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ extern void destroy_preds(struct ftrace_event_call *call); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0b84c61..dca3176 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -332,16 +332,19 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) return alloc_pages_current(gfp_mask, order); } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, - struct vm_area_struct *vma, unsigned long addr); + struct vm_area_struct *vma, unsigned long addr, + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -#define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr) +#define alloc_page_vma(gfp_mask, vma, addr) \ + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) +#define alloc_page_vma_node(gfp_mask, vma, addr, node) \ + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8e6c8c4..df29c8f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -57,7 +57,8 @@ extern pmd_t *page_check_address_pmd(struct page *page, (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \ ((__vma)->vm_flags & VM_HUGEPAGE))) && \ - !((__vma)->vm_flags & VM_NOHUGEPAGE)) + !((__vma)->vm_flags & VM_NOHUGEPAGE) && \ + !is_vma_temporary_stack(__vma)) #define transparent_hugepage_defrag(__vma) \ ((transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) || \ diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 6974746..fe7c4b9 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -4,8 +4,8 @@ #include <linux/types.h> #include <linux/input.h> -#define MATRIX_MAX_ROWS 16 -#define MATRIX_MAX_COLS 16 +#define MATRIX_MAX_ROWS 32 +#define MATRIX_MAX_COLS 32 #define KEY(row, col, val) ((((row) & (MATRIX_MAX_ROWS - 1)) << 24) |\ (((col) & (MATRIX_MAX_COLS - 1)) << 16) |\ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 55e0d42..2eb16e0 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -55,7 +55,7 @@ * Used by threaded interrupts which need to keep the * irq line disabled until the threaded handler has been run. * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend - * + * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set */ #define IRQF_DISABLED 0x00000020 #define IRQF_SAMPLE_RANDOM 0x00000040 @@ -67,6 +67,7 @@ #define IRQF_IRQPOLL 0x00001000 #define IRQF_ONESHOT 0x00002000 #define IRQF_NO_SUSPEND 0x00004000 +#define IRQF_FORCE_RESUME 0x00008000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND) @@ -426,6 +427,13 @@ extern void raise_softirq(unsigned int nr); */ DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list); +DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + +static inline struct task_struct *this_cpu_ksoftirqd(void) +{ + return this_cpu_read(ksoftirqd); +} + /* Try to send a softirq to a remote cpu. If this cannot be done, the * work will be queued to the local cpu. */ diff --git a/include/linux/irq.h b/include/linux/irq.h index abde252..80fcb53 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -74,7 +74,8 @@ typedef void (*irq_flow_handler_t)(unsigned int irq, #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ - IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL) + IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_PER_CPU) #ifdef CONFIG_IRQ_PER_CPU # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 6811f4b..922aa31 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -307,6 +307,7 @@ extern clock_t jiffies_to_clock_t(long x); extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); +extern u64 nsecs_to_jiffies64(u64 n); extern unsigned long nsecs_to_jiffies(u64 n); #define TIMESTAMP_SIZE 30 diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e2f4d6a..2fe6e84 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -588,7 +588,7 @@ struct sysinfo { /** * BUILD_BUG_ON - break compile if a condition is true. - * @cond: the condition which the compiler should know is false. + * @condition: the condition which the compiler should know is false. * * If you have some code which relies on certain constants being equal, or * other compile-time-evaluated condition, you should use BUILD_BUG_ON to diff --git a/include/linux/klist.h b/include/linux/klist.h index e91a4e5..a370ce5 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -22,7 +22,7 @@ struct klist { struct list_head k_list; void (*get)(struct klist_node *); void (*put)(struct klist_node *); -} __attribute__ ((aligned (4))); +} __attribute__ ((aligned (sizeof(void *)))); #define KLIST_INIT(_name, _get, _put) \ { .k_lock = __SPIN_LOCK_UNLOCKED(_name.k_lock), \ diff --git a/include/linux/kthread.h b/include/linux/kthread.h index ce0775a..7ff16f7 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -64,7 +64,7 @@ struct kthread_work { }; #define KTHREAD_WORKER_INIT(worker) { \ - .lock = SPIN_LOCK_UNLOCKED, \ + .lock = __SPIN_LOCK_UNLOCKED((worker).lock), \ .work_list = LIST_HEAD_INIT((worker).work_list), \ } diff --git a/include/linux/list.h b/include/linux/list.h index 9a5f8a7..3a54266 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -96,6 +96,11 @@ static inline void __list_del(struct list_head * prev, struct list_head * next) * in an undefined state. */ #ifndef CONFIG_DEBUG_LIST +static inline void __list_del_entry(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); +} + static inline void list_del(struct list_head *entry) { __list_del(entry->prev, entry->next); @@ -103,6 +108,7 @@ static inline void list_del(struct list_head *entry) entry->prev = LIST_POISON2; } #else +extern void __list_del_entry(struct list_head *entry); extern void list_del(struct list_head *entry); #endif @@ -135,7 +141,7 @@ static inline void list_replace_init(struct list_head *old, */ static inline void list_del_init(struct list_head *entry) { - __list_del(entry->prev, entry->next); + __list_del_entry(entry); INIT_LIST_HEAD(entry); } @@ -146,7 +152,7 @@ static inline void list_del_init(struct list_head *entry) */ static inline void list_move(struct list_head *list, struct list_head *head) { - __list_del(list->prev, list->next); + __list_del_entry(list); list_add(list, head); } @@ -158,7 +164,7 @@ static inline void list_move(struct list_head *list, struct list_head *head) static inline void list_move_tail(struct list_head *list, struct list_head *head) { - __list_del(list->prev, list->next); + __list_del_entry(list); list_add_tail(list, head); } diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h index 3fd3684..ef4f0b6 100644 --- a/include/linux/mfd/wm8994/core.h +++ b/include/linux/mfd/wm8994/core.h @@ -71,6 +71,7 @@ struct wm8994 { u16 irq_masks_cache[WM8994_NUM_IRQ_REGS]; /* Used over suspend/resume */ + bool suspended; u16 ldo_regs[WM8994_NUM_LDO_REGS]; u16 gpio_regs[WM8994_NUM_GPIO_REGS]; diff --git a/include/linux/module.h b/include/linux/module.h index e7c6385..5de4204 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -62,7 +62,7 @@ struct module_version_attribute { struct module_attribute mattr; const char *module_name; const char *version; -}; +} __attribute__ ((__aligned__(sizeof(void *)))); struct module_kobject { @@ -377,7 +377,7 @@ struct module keeping pointers to this stuff */ char *args; #ifdef CONFIG_TRACEPOINTS - struct tracepoint *tracepoints; + struct tracepoint * const *tracepoints_ptrs; unsigned int num_tracepoints; #endif #ifdef HAVE_JUMP_LABEL @@ -389,7 +389,7 @@ struct module unsigned int num_trace_bprintk_fmt; #endif #ifdef CONFIG_EVENT_TRACING - struct ftrace_event_call *trace_events; + struct ftrace_event_call **trace_events; unsigned int num_trace_events; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 0fa7a3a..b21d567 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -150,6 +150,7 @@ static inline int ip_mroute_opt(int opt) extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); +extern int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); extern int ip_mr_init(void); #else static inline diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 6091ab7..9d2deb2 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -136,6 +136,7 @@ extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, unsigned int extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); +extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); extern int ip6_mr_init(void); extern void ip6_mr_cleanup(void); #else diff --git a/include/linux/namei.h b/include/linux/namei.h index f276d4f..9c86038 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -19,7 +19,6 @@ struct nameidata { struct path path; struct qstr last; struct path root; - struct file *file; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags; unsigned seq; @@ -63,6 +62,10 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_EXCL 0x0400 #define LOOKUP_RENAME_TARGET 0x0800 +#define LOOKUP_JUMPED 0x1000 +#define LOOKUP_ROOT 0x2000 +#define LOOKUP_EMPTY 0x4000 + extern int user_path_at(int, const char __user *, unsigned, struct path *); #define user_path(name, path) user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW, path) @@ -72,7 +75,7 @@ extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int kern_path(const char *, unsigned, struct path *); -extern int path_lookup(const char *, unsigned, struct nameidata *); +extern int kern_path_parent(const char *, struct nameidata *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct nameidata *); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d971346..71caf7a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2392,6 +2392,9 @@ extern int netdev_notice(const struct net_device *dev, const char *format, ...) extern int netdev_info(const struct net_device *dev, const char *format, ...) __attribute__ ((format (printf, 2, 3))); +#define MODULE_ALIAS_NETDEV(device) \ + MODULE_ALIAS("netdev-" device) + #if defined(DEBUG) #define netdev_dbg(__dev, format, args...) \ netdev_printk(KERN_DEBUG, __dev, format, ##args) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b197563..3e112de 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -68,11 +68,7 @@ struct nfs_client { unsigned char cl_id_uniquifier; u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; -#endif /* CONFIG_NFS_V4 */ -#ifdef CONFIG_NFS_V4_1 - /* clientid returned from EXCHANGE_ID, used by session operations */ - u64 cl_ex_clid; /* The sequence id to use for the next CREATE_SESSION */ u32 cl_seqid; /* The flags used for obtaining the clientid during EXCHANGE_ID */ @@ -80,7 +76,7 @@ struct nfs_client { struct nfs4_session *cl_session; /* sharred session */ struct list_head cl_layouts; struct pnfs_deviceid_cache *cl_devid_cache; /* pNFS deviceid cache */ -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ @@ -185,7 +181,7 @@ struct nfs_server { /* maximum number of slots to use */ #define NFS4_MAX_SLOT_TABLE RPC_MAX_SLOT_TABLE -#if defined(CONFIG_NFS_V4_1) +#if defined(CONFIG_NFS_V4) /* Sessions */ #define SLOT_TABLE_SZ (NFS4_MAX_SLOT_TABLE/(8*sizeof(long))) @@ -225,5 +221,5 @@ struct nfs4_session { struct nfs_client *clp; }; -#endif /* CONFIG_NFS_V4_1 */ +#endif /* CONFIG_NFS_V4 */ #endif diff --git a/include/linux/nfsacl.h b/include/linux/nfsacl.h index f321b57..fabcb1e 100644 --- a/include/linux/nfsacl.h +++ b/include/linux/nfsacl.h @@ -51,10 +51,10 @@ nfsacl_size(struct posix_acl *acl_access, struct posix_acl *acl_default) return w; } -extern unsigned int +extern int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, struct posix_acl *acl, int encode_entries, int typeflag); -extern unsigned int +extern int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt, struct posix_acl **pacl); diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 32fb812..1ca64113 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -16,6 +16,8 @@ #include <linux/types.h> #include <linux/spinlock.h> #include <linux/init.h> +#include <linux/errno.h> +#include <linux/printk.h> #include <asm/atomic.h> /* Each escaped entry is prefixed by ESCAPE_CODE @@ -186,10 +188,17 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val); int oprofile_add_data64(struct op_entry *entry, u64 val); int oprofile_write_commit(struct op_entry *entry); -#ifdef CONFIG_PERF_EVENTS +#ifdef CONFIG_HW_PERF_EVENTS int __init oprofile_perf_init(struct oprofile_operations *ops); void oprofile_perf_exit(void); char *op_name_from_perf_id(void); -#endif /* CONFIG_PERF_EVENTS */ +#else +static inline int __init oprofile_perf_init(struct oprofile_operations *ops) +{ + pr_info("oprofile: hardware counters not available\n"); + return -ENODEV; +} +static inline void oprofile_perf_exit(void) { } +#endif /* CONFIG_HW_PERF_EVENTS */ #endif /* OPROFILE_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index dda5b0a..614615b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -225,8 +225,14 @@ struct perf_event_attr { }; __u32 bp_type; - __u64 bp_addr; - __u64 bp_len; + union { + __u64 bp_addr; + __u64 config1; /* extension of config */ + }; + union { + __u64 bp_len; + __u64 config2; /* extension of config1 */ + }; }; /* @@ -464,6 +470,7 @@ enum perf_callchain_context { #define PERF_FLAG_FD_NO_GROUP (1U << 0) #define PERF_FLAG_FD_OUTPUT (1U << 1) +#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */ #ifdef __KERNEL__ /* @@ -471,6 +478,7 @@ enum perf_callchain_context { */ #ifdef CONFIG_PERF_EVENTS +# include <linux/cgroup.h> # include <asm/perf_event.h> # include <asm/local64.h> #endif @@ -539,6 +547,9 @@ struct hw_perf_event { unsigned long event_base; int idx; int last_cpu; + unsigned int extra_reg; + u64 extra_config; + int extra_alloc; }; struct { /* software */ struct hrtimer hrtimer; @@ -716,6 +727,22 @@ struct swevent_hlist { #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 +#ifdef CONFIG_CGROUP_PERF +/* + * perf_cgroup_info keeps track of time_enabled for a cgroup. + * This is a per-cpu dynamically allocated data structure. + */ +struct perf_cgroup_info { + u64 time; + u64 timestamp; +}; + +struct perf_cgroup { + struct cgroup_subsys_state css; + struct perf_cgroup_info *info; /* timing info, one per cpu */ +}; +#endif + /** * struct perf_event - performance event kernel representation: */ @@ -832,6 +859,11 @@ struct perf_event { struct event_filter *filter; #endif +#ifdef CONFIG_CGROUP_PERF + struct perf_cgroup *cgrp; /* cgroup event is attach to */ + int cgrp_defer_enabled; +#endif + #endif /* CONFIG_PERF_EVENTS */ }; @@ -886,6 +918,7 @@ struct perf_event_context { u64 generation; int pin_count; struct rcu_head rcu_head; + int nr_cgroups; /* cgroup events present */ }; /* @@ -905,6 +938,9 @@ struct perf_cpu_context { struct list_head rotation_list; int jiffies_interval; struct pmu *active_pmu; +#ifdef CONFIG_CGROUP_PERF + struct perf_cgroup *cgrp; +#endif }; struct perf_output_handle { @@ -1040,11 +1076,11 @@ have_event: __perf_sw_event(event_id, nr, nmi, regs, addr); } -extern atomic_t perf_task_events; +extern atomic_t perf_sched_events; static inline void perf_event_task_sched_in(struct task_struct *task) { - COND_STMT(&perf_task_events, __perf_event_task_sched_in(task)); + COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task)); } static inline @@ -1052,7 +1088,7 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex { perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0); - COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next)); + COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next)); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -1083,6 +1119,10 @@ extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; +extern int perf_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); + static inline bool perf_paranoid_tracepoint_raw(void) { return sysctl_perf_event_paranoid > -1; diff --git a/include/linux/plist.h b/include/linux/plist.h index 7254eda0..c9b9f32 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -31,15 +31,17 @@ * * Simple ASCII art explanation: * - * |HEAD | - * | | - * |prio_list.prev|<------------------------------------| - * |prio_list.next|<->|pl|<->|pl|<--------------->|pl|<-| - * |10 | |10| |21| |21| |21| |40| (prio) - * | | | | | | | | | | | | - * | | | | | | | | | | | | - * |node_list.next|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-| - * |node_list.prev|<------------------------------------| + * pl:prio_list (only for plist_node) + * nl:node_list + * HEAD| NODE(S) + * | + * ||------------------------------------| + * ||->|pl|<->|pl|<--------------->|pl|<-| + * | |10| |21| |21| |21| |40| (prio) + * | | | | | | | | | | | + * | | | | | | | | | | | + * |->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<->|nl|<-| + * |-------------------------------------------| * * The nodes on the prio_list list are sorted by priority to simplify * the insertion of new nodes. There are no nodes with duplicate @@ -78,7 +80,6 @@ #include <linux/spinlock_types.h> struct plist_head { - struct list_head prio_list; struct list_head node_list; #ifdef CONFIG_DEBUG_PI_LIST raw_spinlock_t *rawlock; @@ -88,7 +89,8 @@ struct plist_head { struct plist_node { int prio; - struct plist_head plist; + struct list_head prio_list; + struct list_head node_list; }; #ifdef CONFIG_DEBUG_PI_LIST @@ -100,7 +102,6 @@ struct plist_node { #endif #define _PLIST_HEAD_INIT(head) \ - .prio_list = LIST_HEAD_INIT((head).prio_list), \ .node_list = LIST_HEAD_INIT((head).node_list) /** @@ -133,7 +134,8 @@ struct plist_node { #define PLIST_NODE_INIT(node, __prio) \ { \ .prio = (__prio), \ - .plist = { _PLIST_HEAD_INIT((node).plist) }, \ + .prio_list = LIST_HEAD_INIT((node).prio_list), \ + .node_list = LIST_HEAD_INIT((node).node_list), \ } /** @@ -144,7 +146,6 @@ struct plist_node { static inline void plist_head_init(struct plist_head *head, spinlock_t *lock) { - INIT_LIST_HEAD(&head->prio_list); INIT_LIST_HEAD(&head->node_list); #ifdef CONFIG_DEBUG_PI_LIST head->spinlock = lock; @@ -160,7 +161,6 @@ plist_head_init(struct plist_head *head, spinlock_t *lock) static inline void plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock) { - INIT_LIST_HEAD(&head->prio_list); INIT_LIST_HEAD(&head->node_list); #ifdef CONFIG_DEBUG_PI_LIST head->rawlock = lock; @@ -176,7 +176,8 @@ plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock) static inline void plist_node_init(struct plist_node *node, int prio) { node->prio = prio; - plist_head_init(&node->plist, NULL); + INIT_LIST_HEAD(&node->prio_list); + INIT_LIST_HEAD(&node->node_list); } extern void plist_add(struct plist_node *node, struct plist_head *head); @@ -188,7 +189,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); * @head: the head for your list */ #define plist_for_each(pos, head) \ - list_for_each_entry(pos, &(head)->node_list, plist.node_list) + list_for_each_entry(pos, &(head)->node_list, node_list) /** * plist_for_each_safe - iterate safely over a plist of given type @@ -199,7 +200,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); * Iterate over a plist of given type, safe against removal of list entry. */ #define plist_for_each_safe(pos, n, head) \ - list_for_each_entry_safe(pos, n, &(head)->node_list, plist.node_list) + list_for_each_entry_safe(pos, n, &(head)->node_list, node_list) /** * plist_for_each_entry - iterate over list of given type @@ -208,7 +209,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); * @mem: the name of the list_struct within the struct */ #define plist_for_each_entry(pos, head, mem) \ - list_for_each_entry(pos, &(head)->node_list, mem.plist.node_list) + list_for_each_entry(pos, &(head)->node_list, mem.node_list) /** * plist_for_each_entry_safe - iterate safely over list of given type @@ -220,7 +221,7 @@ extern void plist_del(struct plist_node *node, struct plist_head *head); * Iterate over list of given type, safe against removal of list entry. */ #define plist_for_each_entry_safe(pos, n, head, m) \ - list_for_each_entry_safe(pos, n, &(head)->node_list, m.plist.node_list) + list_for_each_entry_safe(pos, n, &(head)->node_list, m.node_list) /** * plist_head_empty - return !0 if a plist_head is empty @@ -237,7 +238,7 @@ static inline int plist_head_empty(const struct plist_head *head) */ static inline int plist_node_empty(const struct plist_node *node) { - return plist_head_empty(&node->plist); + return list_empty(&node->node_list); } /* All functions below assume the plist_head is not empty. */ @@ -285,7 +286,7 @@ static inline int plist_node_empty(const struct plist_node *node) static inline struct plist_node *plist_first(const struct plist_head *head) { return list_entry(head->node_list.next, - struct plist_node, plist.node_list); + struct plist_node, node_list); } /** @@ -297,7 +298,7 @@ static inline struct plist_node *plist_first(const struct plist_head *head) static inline struct plist_node *plist_last(const struct plist_head *head) { return list_entry(head->node_list.prev, - struct plist_node, plist.node_list); + struct plist_node, node_list); } #endif diff --git a/include/linux/pm.h b/include/linux/pm.h index dd9c7ab..21415cc 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -431,6 +431,8 @@ struct dev_pm_info { struct list_head entry; struct completion completion; struct wakeup_source *wakeup; +#else + unsigned int should_wakeup:1; #endif #ifdef CONFIG_PM_RUNTIME struct timer_list suspend_timer; diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 9cff00d..03a67db 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -109,11 +109,6 @@ static inline bool device_can_wakeup(struct device *dev) return dev->power.can_wakeup; } -static inline bool device_may_wakeup(struct device *dev) -{ - return false; -} - static inline struct wakeup_source *wakeup_source_create(const char *name) { return NULL; @@ -134,24 +129,32 @@ static inline void wakeup_source_unregister(struct wakeup_source *ws) {} static inline int device_wakeup_enable(struct device *dev) { - return -EINVAL; + dev->power.should_wakeup = true; + return 0; } static inline int device_wakeup_disable(struct device *dev) { + dev->power.should_wakeup = false; return 0; } -static inline int device_init_wakeup(struct device *dev, bool val) +static inline int device_set_wakeup_enable(struct device *dev, bool enable) { - dev->power.can_wakeup = val; - return val ? -EINVAL : 0; + dev->power.should_wakeup = enable; + return 0; } +static inline int device_init_wakeup(struct device *dev, bool val) +{ + device_set_wakeup_capable(dev, val); + device_set_wakeup_enable(dev, val); + return 0; +} -static inline int device_set_wakeup_enable(struct device *dev, bool enable) +static inline bool device_may_wakeup(struct device *dev) { - return -EINVAL; + return dev->power.can_wakeup && dev->power.should_wakeup; } static inline void __pm_stay_awake(struct wakeup_source *ws) {} diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index d68283a..54211c1 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -71,6 +71,7 @@ posix_acl_release(struct posix_acl *acl) /* posix_acl.c */ +extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern struct posix_acl *posix_acl_clone(const struct posix_acl *, gfp_t); extern int posix_acl_valid(const struct posix_acl *); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 092a04f..a1147e5 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -102,11 +102,8 @@ extern long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); -extern int ptrace_traceme(void); extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len); extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len); -extern int ptrace_attach(struct task_struct *tsk); -extern int ptrace_detach(struct task_struct *, unsigned int); extern void ptrace_disable(struct task_struct *); extern int ptrace_check_attach(struct task_struct *task, int kill); extern int ptrace_request(struct task_struct *child, long request, diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index fcb9884..a5930cb 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -182,6 +182,26 @@ static inline bool res_counter_check_under_limit(struct res_counter *cnt) return ret; } +/** + * res_counter_check_margin - check if the counter allows charging + * @cnt: the resource counter to check + * @bytes: the number of bytes to check the remaining space against + * + * Returns a boolean value on whether the counter can be charged + * @bytes or whether this would exceed the limit. + */ +static inline bool res_counter_check_margin(struct res_counter *cnt, + unsigned long bytes) +{ + bool ret; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + ret = cnt->limit - cnt->usage >= bytes; + spin_unlock_irqrestore(&cnt->lock, flags); + return ret; +} + static inline bool res_counter_check_under_soft_limit(struct res_counter *cnt) { bool ret; diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 8d3a248..ab38ac8 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer); int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size); +void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val); + struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length); int ring_buffer_unlock_commit(struct ring_buffer *buffer, diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index d63dcba..9026b30 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -14,10 +14,12 @@ #define LINUX_RIO_REGS_H /* - * In RapidIO, each device has a 2MB configuration space that is + * In RapidIO, each device has a 16MB configuration space that is * accessed via maintenance transactions. Portions of configuration * space are standardized and/or reserved. */ +#define RIO_MAINT_SPACE_SZ 0x1000000 /* 16MB of RapidIO mainenance space */ + #define RIO_DEV_ID_CAR 0x00 /* [I] Device Identity CAR */ #define RIO_DEV_INFO_CAR 0x04 /* [I] Device Information CAR */ #define RIO_ASM_ID_CAR 0x08 /* [I] Assembly Identity CAR */ diff --git a/include/linux/rtc.h b/include/linux/rtc.h index a0b639f..89c3e51 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -203,6 +203,18 @@ struct rtc_device struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ int pie_enabled; struct work_struct irqwork; + + +#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL + struct work_struct uie_task; + struct timer_list uie_timer; + /* Those fields are protected by rtc->irq_lock */ + unsigned int oldsecs; + unsigned int uie_irq_active:1; + unsigned int stop_uie_polling:1; + unsigned int uie_task_active:1; + unsigned int uie_timer_active:1; +#endif }; #define to_rtc_device(d) container_of(d, struct rtc_device, dev) @@ -235,7 +247,10 @@ extern int rtc_irq_set_freq(struct rtc_device *rtc, struct rtc_task *task, int freq); extern int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled); extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled); +extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, + unsigned int enabled); +void rtc_handle_legacy_irq(struct rtc_device *rtc, int num, int mode); void rtc_aie_update_irq(void *private); void rtc_uie_update_irq(void *private); enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer); diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h index bd31808..cc0072e 100644 --- a/include/linux/rwlock_types.h +++ b/include/linux/rwlock_types.h @@ -43,14 +43,6 @@ typedef struct { RW_DEP_MAP_INIT(lockname) } #endif -/* - * RW_LOCK_UNLOCKED defeat lockdep state tracking and is hence - * deprecated. - * - * Please use DEFINE_RWLOCK() or __RW_LOCK_UNLOCKED() as appropriate. - */ -#define RW_LOCK_UNLOCKED __RW_LOCK_UNLOCKED(old_style_rw_init) - #define DEFINE_RWLOCK(x) rwlock_t x = __RW_LOCK_UNLOCKED(x) #endif /* __LINUX_RWLOCK_TYPES_H */ diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index bdfcc25..3470124 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -12,15 +12,7 @@ #error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead" #endif -#include <linux/spinlock.h> -#include <linux/list.h> - #ifdef __KERNEL__ - -#include <linux/types.h> - -struct rwsem_waiter; - /* * the rw-semaphore definition * - if activity is 0 then there are no active readers or writers @@ -37,28 +29,7 @@ struct rw_semaphore { #endif }; -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } -#else -# define __RWSEM_DEP_MAP_INIT(lockname) -#endif - -#define __RWSEM_INITIALIZER(name) \ -{ 0, __SPIN_LOCK_UNLOCKED(name.wait_lock), LIST_HEAD_INIT((name).wait_list) \ - __RWSEM_DEP_MAP_INIT(name) } - -#define DECLARE_RWSEM(name) \ - struct rw_semaphore name = __RWSEM_INITIALIZER(name) - -extern void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key); - -#define init_rwsem(sem) \ -do { \ - static struct lock_class_key __key; \ - \ - __init_rwsem((sem), #sem, &__key); \ -} while (0) +#define RWSEM_UNLOCKED_VALUE 0x00000000 extern void __down_read(struct rw_semaphore *sem); extern int __down_read_trylock(struct rw_semaphore *sem); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index efd348f..a8afe9c 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -11,6 +11,9 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/list.h> +#include <linux/spinlock.h> + #include <asm/system.h> #include <asm/atomic.h> @@ -19,9 +22,57 @@ struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK #include <linux/rwsem-spinlock.h> /* use a generic implementation */ #else -#include <asm/rwsem.h> /* use an arch-specific implementation */ +/* All arch specific implementations share the same struct */ +struct rw_semaphore { + long count; + spinlock_t wait_lock; + struct list_head wait_list; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif +}; + +extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); +extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); + +/* Include the arch specific part */ +#include <asm/rwsem.h> + +/* In all implementations count != 0 means locked */ +static inline int rwsem_is_locked(struct rw_semaphore *sem) +{ + return sem->count != 0; +} + +#endif + +/* Common initializer macros and functions */ + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname } +#else +# define __RWSEM_DEP_MAP_INIT(lockname) #endif +#define __RWSEM_INITIALIZER(name) \ + { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED(name.wait_lock), \ + LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) } + +#define DECLARE_RWSEM(name) \ + struct rw_semaphore name = __RWSEM_INITIALIZER(name) + +extern void __init_rwsem(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key); + +#define init_rwsem(sem) \ +do { \ + static struct lock_class_key __key; \ + \ + __init_rwsem((sem), #sem, &__key); \ +} while (0) + /* * lock for reading */ diff --git a/include/linux/sched.h b/include/linux/sched.h index cdef640..c15936f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1058,6 +1058,7 @@ struct sched_class { void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); void (*yield_task) (struct rq *rq); + bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); @@ -1084,12 +1085,10 @@ struct sched_class { void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); void (*task_fork) (struct task_struct *p); - void (*switched_from) (struct rq *this_rq, struct task_struct *task, - int running); - void (*switched_to) (struct rq *this_rq, struct task_struct *task, - int running); + void (*switched_from) (struct rq *this_rq, struct task_struct *task); + void (*switched_to) (struct rq *this_rq, struct task_struct *task); void (*prio_changed) (struct rq *this_rq, struct task_struct *task, - int oldprio, int running); + int oldprio); unsigned int (*get_rr_interval) (struct rq *rq, struct task_struct *task); @@ -1715,7 +1714,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * /* * Per process flags */ -#define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */ #define PF_STARTING 0x00000002 /* being created */ #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ @@ -1744,7 +1742,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ -#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezeable */ +#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_FREEZER_NOSIG 0x80000000 /* Freezer won't send signals to it */ /* @@ -1945,8 +1943,6 @@ int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -extern unsigned int sysctl_sched_compat_yield; - #ifdef CONFIG_SCHED_AUTOGROUP extern unsigned int sysctl_sched_autogroup_enabled; @@ -1977,6 +1973,7 @@ static inline int rt_mutex_getprio(struct task_struct *p) # define rt_mutex_adjust_pi(p) do { } while (0) #endif +extern bool yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); extern int task_nice(const struct task_struct *p); @@ -2578,13 +2575,6 @@ static inline void inc_syscw(struct task_struct *tsk) #define TASK_SIZE_OF(tsk) TASK_SIZE #endif -/* - * Call the function if the target task is executing on a CPU right now: - */ -extern void task_oncpu_function_call(struct task_struct *p, - void (*func) (void *info), void *info); - - #ifdef CONFIG_MM_OWNER extern void mm_update_next_owner(struct mm_struct *mm); extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p); diff --git a/include/linux/security.h b/include/linux/security.h index c096aa6..debbd97 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1662,7 +1662,7 @@ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -int security_capable(int cap); +int security_capable(const struct cred *cred, int cap); int security_real_capable(struct task_struct *tsk, int cap); int security_real_capable_noaudit(struct task_struct *tsk, int cap); int security_sysctl(struct ctl_table *table, int op); @@ -1856,9 +1856,9 @@ static inline int security_capset(struct cred *new, return cap_capset(new, old, effective, inheritable, permitted); } -static inline int security_capable(int cap) +static inline int security_capable(const struct cred *cred, int cap) { - return cap_capable(current, current_cred(), cap, SECURITY_CAP_AUDIT); + return cap_capable(current, cred, cap, SECURITY_CAP_AUDIT); } static inline int security_real_capable(struct task_struct *tsk, int cap) diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h index 851b778..73548eb 100644 --- a/include/linux/spinlock_types.h +++ b/include/linux/spinlock_types.h @@ -81,14 +81,6 @@ typedef struct spinlock { #define __SPIN_LOCK_UNLOCKED(lockname) \ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) -/* - * SPIN_LOCK_UNLOCKED defeats lockdep state tracking and is hence - * deprecated. - * Please use DEFINE_SPINLOCK() or __SPIN_LOCK_UNLOCKED() as - * appropriate. - */ -#define SPIN_LOCK_UNLOCKED __SPIN_LOCK_UNLOCKED(old_style_spin_init) - #define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) #include <linux/rwlock_types.h> diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index c50b458..0828842 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -47,14 +47,6 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) return 1; return 0; } -static inline struct nfs4_sessionid *bc_xprt_sid(struct svc_rqst *rqstp) -{ - if (svc_is_backchannel(rqstp)) - return (struct nfs4_sessionid *) - rqstp->rq_server->sv_bc_xprt->xpt_bc_sid; - return NULL; -} - #else /* CONFIG_NFS_V4_1 */ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, unsigned int min_reqs) @@ -67,11 +59,6 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) return 0; } -static inline struct nfs4_sessionid *bc_xprt_sid(struct svc_rqst *rqstp) -{ - return NULL; -} - static inline void xprt_free_bc_request(struct rpc_rqst *req) { } diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 88513fd..d81db80 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -212,6 +212,7 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *); struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, const struct rpc_call_ops *ops); void rpc_put_task(struct rpc_task *); +void rpc_put_task_async(struct rpc_task *); void rpc_exit_task(struct rpc_task *); void rpc_exit(struct rpc_task *, int); void rpc_release_calldata(const struct rpc_call_ops *, void *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 059877b..7ad9751 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -77,7 +77,6 @@ struct svc_xprt { size_t xpt_remotelen; /* length of address */ struct rpc_wait_queue xpt_bc_pending; /* backchannel wait queue */ struct list_head xpt_users; /* callbacks on free */ - void *xpt_bc_sid; /* back channel session ID */ struct net *xpt_net; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index bfacab9..1f5c18e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -62,6 +62,7 @@ struct robust_list_head; struct getcpu_cache; struct old_linux_dirent; struct perf_event_attr; +struct file_handle; #include <linux/types.h> #include <linux/aio_abi.h> @@ -125,62 +126,66 @@ extern struct trace_event_functions enter_syscall_print_funcs; extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ - static struct syscall_metadata \ - __attribute__((__aligned__(4))) __syscall_meta_##sname; \ + static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call __used \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_events"))) \ event_enter_##sname = { \ .name = "sys_enter"#sname, \ .class = &event_class_syscall_enter, \ .event.funcs = &enter_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ + .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ - __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY) + static struct ftrace_event_call __used \ + __attribute__((section("_ftrace_events"))) \ + *__event_enter_##sname = &event_enter_##sname; #define SYSCALL_TRACE_EXIT_EVENT(sname) \ - static struct syscall_metadata \ - __attribute__((__aligned__(4))) __syscall_meta_##sname; \ + static struct syscall_metadata __syscall_meta_##sname; \ static struct ftrace_event_call __used \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_events"))) \ event_exit_##sname = { \ .name = "sys_exit"#sname, \ .class = &event_class_syscall_exit, \ .event.funcs = &exit_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ + .flags = TRACE_EVENT_FL_CAP_ANY, \ }; \ - __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY) + static struct ftrace_event_call __used \ + __attribute__((section("_ftrace_events"))) \ + *__event_exit_##sname = &event_exit_##sname; #define SYSCALL_METADATA(sname, nb) \ SYSCALL_TRACE_ENTER_EVENT(sname); \ SYSCALL_TRACE_EXIT_EVENT(sname); \ static struct syscall_metadata __used \ - __attribute__((__aligned__(4))) \ - __attribute__((section("__syscalls_metadata"))) \ __syscall_meta_##sname = { \ .name = "sys"#sname, \ + .syscall_nr = -1, /* Filled in at boot */ \ .nb_args = nb, \ .types = types_##sname, \ .args = args_##sname, \ .enter_event = &event_enter_##sname, \ .exit_event = &event_exit_##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \ - }; + }; \ + static struct syscall_metadata __used \ + __attribute__((section("__syscalls_metadata"))) \ + *__p_syscall_meta_##sname = &__syscall_meta_##sname; #define SYSCALL_DEFINE0(sname) \ SYSCALL_TRACE_ENTER_EVENT(_##sname); \ SYSCALL_TRACE_EXIT_EVENT(_##sname); \ static struct syscall_metadata __used \ - __attribute__((__aligned__(4))) \ - __attribute__((section("__syscalls_metadata"))) \ __syscall_meta__##sname = { \ .name = "sys_"#sname, \ + .syscall_nr = -1, /* Filled in at boot */ \ .nb_args = 0, \ .enter_event = &event_enter__##sname, \ .exit_event = &event_exit__##sname, \ .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \ }; \ + static struct syscall_metadata __used \ + __attribute__((section("__syscalls_metadata"))) \ + *__p_syscall_meta_##sname = &__syscall_meta__##sname; \ asmlinkage long sys_##sname(void) #else #define SYSCALL_DEFINE0(name) asmlinkage long sys_##name(void) @@ -832,5 +837,10 @@ asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); - +asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name, + struct file_handle __user *handle, + int __user *mnt_id, int flag); +asmlinkage long sys_open_by_handle_at(int mountdirfd, + struct file_handle __user *handle, + int flags); #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 7bb5cb6..11684d9 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -930,6 +930,7 @@ enum #ifdef __KERNEL__ #include <linux/list.h> +#include <linux/rcupdate.h> /* For the /proc/sys support */ struct ctl_table; @@ -1037,10 +1038,15 @@ struct ctl_table_root { struct ctl_table trees. */ struct ctl_table_header { - struct ctl_table *ctl_table; - struct list_head ctl_entry; - int used; - int count; + union { + struct { + struct ctl_table *ctl_table; + struct list_head ctl_entry; + int used; + int count; + }; + struct rcu_head rcu; + }; struct completion *unregistering; struct ctl_table *ctl_table_arg; struct ctl_table_root *root; diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 8651556..d3ec89f 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -172,6 +172,14 @@ void thermal_zone_device_update(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); + +#ifdef CONFIG_NET extern int generate_netlink_event(u32 orig, enum events event); +#else +static inline int generate_netlink_event(u32 orig, enum events event) +{ + return 0; +} +#endif #endif /* __THERMAL_H__ */ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index c681461..97c84a5 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -33,12 +33,7 @@ struct tracepoint { void (*regfunc)(void); void (*unregfunc)(void); struct tracepoint_func __rcu *funcs; -} __attribute__((aligned(32))); /* - * Aligned on 32 bytes because it is - * globally visible and gcc happily - * align these on the structure size. - * Keep in sync with vmlinux.lds.h. - */ +}; /* * Connect a probe to a tracepoint. @@ -61,15 +56,15 @@ extern void tracepoint_probe_update_all(void); struct tracepoint_iter { struct module *module; - struct tracepoint *tracepoint; + struct tracepoint * const *tracepoint; }; extern void tracepoint_iter_start(struct tracepoint_iter *iter); extern void tracepoint_iter_next(struct tracepoint_iter *iter); extern void tracepoint_iter_stop(struct tracepoint_iter *iter); extern void tracepoint_iter_reset(struct tracepoint_iter *iter); -extern int tracepoint_get_iter_range(struct tracepoint **tracepoint, - struct tracepoint *begin, struct tracepoint *end); +extern int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, + struct tracepoint * const *begin, struct tracepoint * const *end); /* * tracepoint_synchronize_unregister must be called between the last tracepoint @@ -84,11 +79,13 @@ static inline void tracepoint_synchronize_unregister(void) #define PARAMS(args...) args #ifdef CONFIG_TRACEPOINTS -extern void tracepoint_update_probe_range(struct tracepoint *begin, - struct tracepoint *end); +extern +void tracepoint_update_probe_range(struct tracepoint * const *begin, + struct tracepoint * const *end); #else -static inline void tracepoint_update_probe_range(struct tracepoint *begin, - struct tracepoint *end) +static inline +void tracepoint_update_probe_range(struct tracepoint * const *begin, + struct tracepoint * const *end) { } #endif /* CONFIG_TRACEPOINTS */ @@ -174,12 +171,20 @@ do_trace: \ { \ } +/* + * We have no guarantee that gcc and the linker won't up-align the tracepoint + * structures, so we create an array of pointers that will be used for iteration + * on the tracepoints. + */ #define DEFINE_TRACE_FN(name, reg, unreg) \ static const char __tpstrtab_##name[] \ __attribute__((section("__tracepoints_strings"))) = #name; \ struct tracepoint __tracepoint_##name \ - __attribute__((section("__tracepoints"), aligned(32))) = \ - { __tpstrtab_##name, 0, reg, unreg, NULL } + __attribute__((section("__tracepoints"))) = \ + { __tpstrtab_##name, 0, reg, unreg, NULL }; \ + static struct tracepoint * const __tracepoint_ptr_##name __used \ + __attribute__((section("__tracepoints_ptrs"))) = \ + &__tracepoint_##name; #define DEFINE_TRACE(name) \ DEFINE_TRACE_FN(name, NULL, NULL); diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h index 5e86dc7..81a9279 100644 --- a/include/linux/usb/cdc.h +++ b/include/linux/usb/cdc.h @@ -89,7 +89,7 @@ struct usb_cdc_acm_descriptor { #define USB_CDC_COMM_FEATURE 0x01 #define USB_CDC_CAP_LINE 0x02 -#define USB_CDC_CAP_BRK 0x04 +#define USB_CDC_CAP_BRK 0x04 #define USB_CDC_CAP_NOTIFY 0x08 /* "Union Functional Descriptor" from CDC spec 5.2.3.8 */ @@ -271,6 +271,11 @@ struct usb_cdc_notification { __le16 wLength; } __attribute__ ((packed)); +struct usb_cdc_speed_change { + __le32 DLBitRRate; /* contains the downlink bit rate (IN pipe) */ + __le32 ULBitRate; /* contains the uplink bit rate (OUT pipe) */ +} __attribute__ ((packed)); + /*-------------------------------------------------------------------------*/ /* @@ -292,7 +297,7 @@ struct usb_cdc_ncm_ntb_parameters { __le16 wNdpOutDivisor; __le16 wNdpOutPayloadRemainder; __le16 wNdpOutAlignment; - __le16 wPadding2; + __le16 wNtbOutMaxDatagrams; } __attribute__ ((packed)); /* @@ -307,7 +312,7 @@ struct usb_cdc_ncm_nth16 { __le16 wHeaderLength; __le16 wSequence; __le16 wBlockLength; - __le16 wFpIndex; + __le16 wNdpIndex; } __attribute__ ((packed)); struct usb_cdc_ncm_nth32 { @@ -315,7 +320,7 @@ struct usb_cdc_ncm_nth32 { __le16 wHeaderLength; __le16 wSequence; __le32 dwBlockLength; - __le32 dwFpIndex; + __le32 dwNdpIndex; } __attribute__ ((packed)); /* @@ -337,7 +342,7 @@ struct usb_cdc_ncm_dpe16 { struct usb_cdc_ncm_ndp16 { __le32 dwSignature; __le16 wLength; - __le16 wNextFpIndex; + __le16 wNextNdpIndex; struct usb_cdc_ncm_dpe16 dpe16[0]; } __attribute__ ((packed)); @@ -375,6 +380,7 @@ struct usb_cdc_ncm_ndp32 { #define USB_CDC_NCM_NCAP_ENCAP_COMMAND (1 << 2) #define USB_CDC_NCM_NCAP_MAX_DATAGRAM_SIZE (1 << 3) #define USB_CDC_NCM_NCAP_CRC_MODE (1 << 4) +#define USB_CDC_NCM_NCAP_NTB_INPUT_SIZE (1 << 5) /* CDC NCM subclass Table 6-3: NTB Parameter Structure */ #define USB_CDC_NCM_NTB16_SUPPORTED (1 << 0) @@ -392,6 +398,13 @@ struct usb_cdc_ncm_ndp32 { #define USB_CDC_NCM_NTB_MIN_IN_SIZE 2048 #define USB_CDC_NCM_NTB_MIN_OUT_SIZE 2048 +/* NTB Input Size Structure */ +struct usb_cdc_ncm_ndp_input_size { + __le32 dwNtbInMaxSize; + __le16 wNtbInMaxDatagrams; + __le16 wReserved; +} __attribute__ ((packed)); + /* CDC NCM subclass 6.2.11 SetCrcMode */ #define USB_CDC_NCM_CRC_NOT_APPENDED 0x00 #define USB_CDC_NCM_CRC_APPENDED 0x01 diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index dd6ee49..a854fe8 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -112,6 +112,7 @@ struct usb_hcd { /* Flags that get set only during HCD registration or removal. */ unsigned rh_registered:1;/* is root hub registered? */ unsigned rh_pollable:1; /* may we poll the root hub? */ + unsigned msix_enabled:1; /* driver has MSI-X enabled? */ /* The next flag is a stopgap, to be removed when all the HCDs * support the new root-hub polling mechanism. */ diff --git a/include/linux/usb/msm_hsusb_hw.h b/include/linux/usb/msm_hsusb_hw.h index b92e173..7d1babb 100644 --- a/include/linux/usb/msm_hsusb_hw.h +++ b/include/linux/usb/msm_hsusb_hw.h @@ -16,12 +16,8 @@ #ifndef __LINUX_USB_GADGET_MSM72K_UDC_H__ #define __LINUX_USB_GADGET_MSM72K_UDC_H__ -#ifdef CONFIG_ARCH_MSM7X00A -#define USB_SBUSCFG (MSM_USB_BASE + 0x0090) -#else #define USB_AHBBURST (MSM_USB_BASE + 0x0090) #define USB_AHBMODE (MSM_USB_BASE + 0x0098) -#endif #define USB_CAPLENGTH (MSM_USB_BASE + 0x0100) /* 8 bit */ #define USB_USBCMD (MSM_USB_BASE + 0x0140) diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 16d682f..c904913 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -347,6 +347,9 @@ extern int usb_serial_generic_prepare_write_buffer(struct usb_serial_port *port, extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch); extern int usb_serial_handle_break(struct usb_serial_port *port); +extern void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, + struct tty_struct *tty, + unsigned int status); extern int usb_serial_bus_register(struct usb_serial_driver *device); diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h index a85064d..e4d3335 100644 --- a/include/linux/virtio_console.h +++ b/include/linux/virtio_console.h @@ -7,7 +7,8 @@ * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so * anyone can use the definitions to implement compatible drivers/servers. * - * Copyright (C) Red Hat, Inc., 2009, 2010 + * Copyright (C) Red Hat, Inc., 2009, 2010, 2011 + * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011 */ /* Feature bits */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1ac1158..f7998a3 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -250,7 +250,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } enum { WQ_NON_REENTRANT = 1 << 0, /* guarantee non-reentrance */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ - WQ_FREEZEABLE = 1 << 2, /* freeze during suspend */ + WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ @@ -318,7 +318,7 @@ __alloc_workqueue_key(const char *name, unsigned int flags, int max_active, /** * alloc_ordered_workqueue - allocate an ordered workqueue * @name: name of the workqueue - * @flags: WQ_* flags (only WQ_FREEZEABLE and WQ_MEM_RECLAIM are meaningful) + * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are @@ -335,8 +335,8 @@ alloc_ordered_workqueue(const char *name, unsigned int flags) #define create_workqueue(name) \ alloc_workqueue((name), WQ_MEM_RECLAIM, 1) -#define create_freezeable_workqueue(name) \ - alloc_workqueue((name), WQ_FREEZEABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1) +#define create_freezable_workqueue(name) \ + alloc_workqueue((name), WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1) #define create_singlethread_workqueue(name) \ alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1) diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8a64b81..b4c7c1c 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -195,7 +195,8 @@ static inline int genlmsg_end(struct sk_buff *skb, void *hdr) */ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { - nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); + if (hdr) + nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4a3cd2c..96e50e0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -89,6 +89,18 @@ #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* + * Addr flags + */ +#ifdef __KERNEL__ +#define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ + ((a)->s6_addr[1] & 0x10) +#define IPV6_ADDR_MC_FLAG_PREFIX(a) \ + ((a)->s6_addr[1] & 0x20) +#define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ + ((a)->s6_addr[1] & 0x40) +#endif + +/* * fragmentation header */ diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 96ba5f7..349cefe 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -77,9 +77,6 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) if (e == NULL) return; - if (!(e->ctmask & (1 << event))) - return; - set_bit(event, &e->cache); } diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h index cd85b3b..e505358 100644 --- a/include/net/netfilter/nf_tproxy_core.h +++ b/include/net/netfilter/nf_tproxy_core.h @@ -201,18 +201,8 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, } #endif -static inline void -nf_tproxy_put_sock(struct sock *sk) -{ - /* TIME_WAIT inet sockets have to be handled differently */ - if ((sk->sk_protocol == IPPROTO_TCP) && (sk->sk_state == TCP_TIME_WAIT)) - inet_twsk_put(inet_twsk(sk)); - else - sock_put(sk); -} - /* assign a socket to the skb -- consumes sk */ -int +void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk); #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 160a407..04f8556 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -199,7 +199,7 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; - char data[]; + long data[]; }; static inline int qdisc_qlen(struct Qdisc *q) diff --git a/include/net/sock.h b/include/net/sock.h index d884d26..bc1cf7d8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -753,6 +753,8 @@ struct proto { int level, int optname, char __user *optval, int __user *option); + int (*compat_ioctl)(struct sock *sk, + unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); diff --git a/include/pcmcia/ds.h b/include/pcmcia/ds.h index 8479b66..3fd5064 100644 --- a/include/pcmcia/ds.h +++ b/include/pcmcia/ds.h @@ -261,6 +261,7 @@ void pcmcia_disable_device(struct pcmcia_device *p_dev); #define CONF_ENABLE_ESR 0x0008 #define CONF_ENABLE_IOCARD 0x0010 /* auto-enabled if IO resources or IRQ * (CONF_ENABLE_IRQ) in use */ +#define CONF_ENABLE_ZVCARD 0x0020 /* flags used by pcmcia_loop_config() autoconfiguration */ #define CONF_AUTO_CHECK_VCC 0x0100 /* check for matching Vcc? */ diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 648d233..b76d400 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -9,6 +9,7 @@ #define _SCSI_SCSI_H #include <linux/types.h> +#include <linux/scatterlist.h> struct scsi_cmnd; diff --git a/include/sound/wm8903.h b/include/sound/wm8903.h index b4a0db23..1eeebd5 100644 --- a/include/sound/wm8903.h +++ b/include/sound/wm8903.h @@ -17,13 +17,9 @@ /* * R6 (0x06) - Mic Bias Control 0 */ -#define WM8903_MICDET_HYST_ENA 0x0080 /* MICDET_HYST_ENA */ -#define WM8903_MICDET_HYST_ENA_MASK 0x0080 /* MICDET_HYST_ENA */ -#define WM8903_MICDET_HYST_ENA_SHIFT 7 /* MICDET_HYST_ENA */ -#define WM8903_MICDET_HYST_ENA_WIDTH 1 /* MICDET_HYST_ENA */ -#define WM8903_MICDET_THR_MASK 0x0070 /* MICDET_THR - [6:4] */ -#define WM8903_MICDET_THR_SHIFT 4 /* MICDET_THR - [6:4] */ -#define WM8903_MICDET_THR_WIDTH 3 /* MICDET_THR - [6:4] */ +#define WM8903_MICDET_THR_MASK 0x0030 /* MICDET_THR - [5:4] */ +#define WM8903_MICDET_THR_SHIFT 4 /* MICDET_THR - [5:4] */ +#define WM8903_MICDET_THR_WIDTH 2 /* MICDET_THR - [5:4] */ #define WM8903_MICSHORT_THR_MASK 0x000C /* MICSHORT_THR - [3:2] */ #define WM8903_MICSHORT_THR_SHIFT 2 /* MICSHORT_THR - [3:2] */ #define WM8903_MICSHORT_THR_WIDTH 2 /* MICSHORT_THR - [3:2] */ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 07fdfb6..0828b6c 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -8,7 +8,6 @@ #include <scsi/scsi_cmnd.h> #include <net/sock.h> #include <net/tcp.h> -#include "target_core_mib.h" #define TARGET_CORE_MOD_VERSION "v4.0.0-rc6" #define SHUTDOWN_SIGS (sigmask(SIGKILL)|sigmask(SIGINT)|sigmask(SIGABRT)) @@ -195,6 +194,21 @@ typedef enum { SAM_TASK_ATTR_EMULATED } t10_task_attr_index_t; +/* + * Used for target SCSI statistics + */ +typedef enum { + SCSI_INST_INDEX, + SCSI_DEVICE_INDEX, + SCSI_AUTH_INTR_INDEX, + SCSI_INDEX_TYPE_MAX +} scsi_index_t; + +struct scsi_index_table { + spinlock_t lock; + u32 scsi_mib_index[SCSI_INDEX_TYPE_MAX]; +} ____cacheline_aligned; + struct se_cmd; struct t10_alua { @@ -578,8 +592,6 @@ struct se_node_acl { spinlock_t stats_lock; /* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */ atomic_t acl_pr_ref_count; - /* Used for MIB access */ - atomic_t mib_ref_count; struct se_dev_entry *device_list; struct se_session *nacl_sess; struct se_portal_group *se_tpg; @@ -595,8 +607,6 @@ struct se_node_acl { } ____cacheline_aligned; struct se_session { - /* Used for MIB access */ - atomic_t mib_ref_count; u64 sess_bin_isid; struct se_node_acl *se_node_acl; struct se_portal_group *se_tpg; @@ -806,7 +816,6 @@ struct se_hba { /* Virtual iSCSI devices attached. */ u32 dev_count; u32 hba_index; - atomic_t dev_mib_access_count; atomic_t load_balance_queue; atomic_t left_queue_depth; /* Maximum queue depth the HBA can handle. */ @@ -845,6 +854,12 @@ struct se_lun { #define SE_LUN(c) ((struct se_lun *)(c)->se_lun) +struct scsi_port_stats { + u64 cmd_pdus; + u64 tx_data_octets; + u64 rx_data_octets; +} ____cacheline_aligned; + struct se_port { /* RELATIVE TARGET PORT IDENTIFER */ u16 sep_rtpi; @@ -867,6 +882,7 @@ struct se_port { } ____cacheline_aligned; struct se_tpg_np { + struct se_portal_group *tpg_np_parent; struct config_group tpg_np_group; } ____cacheline_aligned; diff --git a/include/target/target_core_transport.h b/include/target/target_core_transport.h index 66f44e5..2e8ec51 100644 --- a/include/target/target_core_transport.h +++ b/include/target/target_core_transport.h @@ -111,6 +111,8 @@ struct se_subsystem_api; extern int init_se_global(void); extern void release_se_global(void); +extern void init_scsi_index_table(void); +extern u32 scsi_get_new_index(scsi_index_t); extern void transport_init_queue_obj(struct se_queue_obj *); extern int transport_subsystem_check_init(void); extern int transport_subsystem_register(struct se_subsystem_api *); @@ -133,6 +135,8 @@ extern void transport_complete_task(struct se_task *, int); extern void transport_add_task_to_execute_queue(struct se_task *, struct se_task *, struct se_device *); +extern void transport_remove_task_from_execute_queue(struct se_task *, + struct se_device *); unsigned char *transport_dump_cmd_direction(struct se_cmd *); extern void transport_dump_dev_state(struct se_device *, char *, int *); extern void transport_dump_dev_info(struct se_device *, struct se_lun *, diff --git a/include/trace/events/block.h b/include/trace/events/block.h index aba421d..78f18ad 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -31,7 +31,7 @@ DECLARE_EVENT_CLASS(block_rq_with_error, 0 : blk_rq_sectors(rq); __entry->errors = rq->errors; - blk_fill_rwbs_rq(__entry->rwbs, rq); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); blk_dump_cmd(__get_str(cmd), rq); ), @@ -118,7 +118,7 @@ DECLARE_EVENT_CLASS(block_rq, __entry->bytes = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? blk_rq_bytes(rq) : 0; - blk_fill_rwbs_rq(__entry->rwbs, rq); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); blk_dump_cmd(__get_str(cmd), rq); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -563,7 +563,7 @@ TRACE_EVENT(block_rq_remap, __entry->nr_sector = blk_rq_sectors(rq); __entry->old_dev = dev; __entry->old_sector = from; - blk_fill_rwbs_rq(__entry->rwbs, rq); + blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h index 7eee778..4cbbcef 100644 --- a/include/trace/events/mce.h +++ b/include/trace/events/mce.h @@ -17,36 +17,36 @@ TRACE_EVENT(mce_record, TP_STRUCT__entry( __field( u64, mcgcap ) __field( u64, mcgstatus ) - __field( u8, bank ) __field( u64, status ) __field( u64, addr ) __field( u64, misc ) __field( u64, ip ) - __field( u8, cs ) __field( u64, tsc ) __field( u64, walltime ) __field( u32, cpu ) __field( u32, cpuid ) __field( u32, apicid ) __field( u32, socketid ) + __field( u8, cs ) + __field( u8, bank ) __field( u8, cpuvendor ) ), TP_fast_assign( __entry->mcgcap = m->mcgcap; __entry->mcgstatus = m->mcgstatus; - __entry->bank = m->bank; __entry->status = m->status; __entry->addr = m->addr; __entry->misc = m->misc; __entry->ip = m->ip; - __entry->cs = m->cs; __entry->tsc = m->tsc; __entry->walltime = m->time; __entry->cpu = m->extcpu; __entry->cpuid = m->cpuid; __entry->apicid = m->apicid; __entry->socketid = m->socketid; + __entry->cs = m->cs; + __entry->bank = m->bank; __entry->cpuvendor = m->cpuvendor; ), diff --git a/include/trace/events/module.h b/include/trace/events/module.h index c6bae36..21a546d 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -108,14 +108,14 @@ TRACE_EVENT(module_request, TP_ARGS(name, wait, ip), TP_STRUCT__entry( - __field( bool, wait ) __field( unsigned long, ip ) + __field( bool, wait ) __string( name, name ) ), TP_fast_assign( - __entry->wait = wait; __entry->ip = ip; + __entry->wait = wait; __assign_str(name, name); ), @@ -129,4 +129,3 @@ TRACE_EVENT(module_request, /* This part must be outside protection */ #include <trace/define_trace.h> - diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index f10293c..0c68ae22 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb, TP_STRUCT__entry( __field( void *, skbaddr ) - __field( unsigned short, protocol ) __field( void *, location ) + __field( unsigned short, protocol ) ), TP_fast_assign( __entry->skbaddr = skb; - __entry->protocol = ntohs(skb->protocol); __entry->location = location; + __entry->protocol = ntohs(skb->protocol); ), TP_printk("skbaddr=%p protocol=%u location=%p", diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index e16610c..3e68366 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -446,14 +446,16 @@ static inline notrace int ftrace_get_offsets_##call( \ * .reg = ftrace_event_reg, * }; * - * static struct ftrace_event_call __used - * __attribute__((__aligned__(4))) - * __attribute__((section("_ftrace_events"))) event_<call> = { + * static struct ftrace_event_call event_<call> = { * .name = "<call>", * .class = event_class_<template>, * .event = &ftrace_event_type_<call>, * .print_fmt = print_fmt_<call>, * }; + * // its only safe to use pointers when doing linker tricks to + * // create an array. + * static struct ftrace_event_call __used + * __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>; * */ @@ -579,28 +581,28 @@ static struct ftrace_event_class __used event_class_##call = { \ #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ \ -static struct ftrace_event_call __used \ -__attribute__((__aligned__(4))) \ -__attribute__((section("_ftrace_events"))) event_##call = { \ +static struct ftrace_event_call __used event_##call = { \ .name = #call, \ .class = &event_class_##template, \ .event.funcs = &ftrace_event_type_funcs_##template, \ .print_fmt = print_fmt_##template, \ -}; +}; \ +static struct ftrace_event_call __used \ +__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, call, proto, args, print) \ \ static const char print_fmt_##call[] = print; \ \ -static struct ftrace_event_call __used \ -__attribute__((__aligned__(4))) \ -__attribute__((section("_ftrace_events"))) event_##call = { \ +static struct ftrace_event_call __used event_##call = { \ .name = #call, \ .class = &event_class_##template, \ .event.funcs = &ftrace_event_type_funcs_##call, \ .print_fmt = print_fmt_##call, \ -} +}; \ +static struct ftrace_event_call __used \ +__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) diff --git a/include/xen/events.h b/include/xen/events.h index 00f53dd..962da2c 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -75,11 +75,9 @@ int xen_allocate_pirq(unsigned gsi, int shareable, char *name); int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name); #ifdef CONFIG_PCI_MSI -/* Allocate an irq and a pirq to be used with MSIs. */ -#define XEN_ALLOC_PIRQ (1 << 0) -#define XEN_ALLOC_IRQ (1 << 1) -void xen_allocate_pirq_msi(char *name, int *irq, int *pirq, int alloc_mask); -int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type); +int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc); +int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, + int pirq, int vector, const char *name); #endif /* De-allocates the above mentioned physical interrupt. */ diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index c2d1fa4..61e523a 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -51,11 +51,7 @@ typedef uint64_t blkif_sector_t; */ #define BLKIF_MAX_SEGMENTS_PER_REQUEST 11 -struct blkif_request { - uint8_t operation; /* BLKIF_OP_??? */ - uint8_t nr_segments; /* number of segments */ - blkif_vdev_t handle; /* only for read/write requests */ - uint64_t id; /* private guest value, echoed in resp */ +struct blkif_request_rw { blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ struct blkif_request_segment { grant_ref_t gref; /* reference to I/O buffer frame */ @@ -65,6 +61,16 @@ struct blkif_request { } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; }; +struct blkif_request { + uint8_t operation; /* BLKIF_OP_??? */ + uint8_t nr_segments; /* number of segments */ + blkif_vdev_t handle; /* only for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + union { + struct blkif_request_rw rw; + } u; +}; + struct blkif_response { uint64_t id; /* copied from request */ uint8_t operation; /* copied from request */ @@ -91,4 +97,25 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response); #define VDISK_REMOVABLE 0x2 #define VDISK_READONLY 0x4 +/* Xen-defined major numbers for virtual disks, they look strangely + * familiar */ +#define XEN_IDE0_MAJOR 3 +#define XEN_IDE1_MAJOR 22 +#define XEN_SCSI_DISK0_MAJOR 8 +#define XEN_SCSI_DISK1_MAJOR 65 +#define XEN_SCSI_DISK2_MAJOR 66 +#define XEN_SCSI_DISK3_MAJOR 67 +#define XEN_SCSI_DISK4_MAJOR 68 +#define XEN_SCSI_DISK5_MAJOR 69 +#define XEN_SCSI_DISK6_MAJOR 70 +#define XEN_SCSI_DISK7_MAJOR 71 +#define XEN_SCSI_DISK8_MAJOR 128 +#define XEN_SCSI_DISK9_MAJOR 129 +#define XEN_SCSI_DISK10_MAJOR 130 +#define XEN_SCSI_DISK11_MAJOR 131 +#define XEN_SCSI_DISK12_MAJOR 132 +#define XEN_SCSI_DISK13_MAJOR 133 +#define XEN_SCSI_DISK14_MAJOR 134 +#define XEN_SCSI_DISK15_MAJOR 135 + #endif /* __XEN_PUBLIC_IO_BLKIF_H__ */ diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h index 2befa3e..b33257b 100644 --- a/include/xen/interface/xen.h +++ b/include/xen/interface/xen.h @@ -30,7 +30,7 @@ #define __HYPERVISOR_stack_switch 3 #define __HYPERVISOR_set_callbacks 4 #define __HYPERVISOR_fpu_taskswitch 5 -#define __HYPERVISOR_sched_op 6 +#define __HYPERVISOR_sched_op_compat 6 #define __HYPERVISOR_dom0_op 7 #define __HYPERVISOR_set_debugreg 8 #define __HYPERVISOR_get_debugreg 9 @@ -52,7 +52,7 @@ #define __HYPERVISOR_mmuext_op 26 #define __HYPERVISOR_acm_op 27 #define __HYPERVISOR_nmi_op 28 -#define __HYPERVISOR_sched_op_new 29 +#define __HYPERVISOR_sched_op 29 #define __HYPERVISOR_callback_op 30 #define __HYPERVISOR_xenoprof_op 31 #define __HYPERVISOR_event_channel_op 32 diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 98b9215..03c85d7 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -5,9 +5,9 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); -void xen_pre_suspend(void); -void xen_post_suspend(int suspend_cancelled); -void xen_hvm_post_suspend(int suspend_cancelled); +void xen_arch_pre_suspend(void); +void xen_arch_post_suspend(int suspend_cancelled); +void xen_arch_hvm_post_suspend(int suspend_cancelled); void xen_mm_pin_all(void); void xen_mm_unpin_all(void); diff --git a/init/Kconfig b/init/Kconfig index be788c0..5721d27 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -287,6 +287,18 @@ config BSD_PROCESS_ACCT_V3 for processing it. A preliminary version of these tools is available at <http://www.gnu.org/software/acct/>. +config FHANDLE + bool "open by fhandle syscalls" + select EXPORTFS + help + If you say Y here, a user level program will be able to map + file names to handle and then later use the handle for + different file system operations. This is useful in implementing + userspace file servers, which now track files using handles instead + of names. The handle would remain the same even if file names + get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2) + syscalls. + config TASKSTATS bool "Export task/process statistics through netlink (EXPERIMENTAL)" depends on NET @@ -683,6 +695,16 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED select this option (if, for some reason, they need to disable it then noswapaccount does the trick). +config CGROUP_PERF + bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" + depends on PERF_EVENTS && CGROUPS + help + This option extends the per-cpu mode to restrict monitoring to + threads which belong to the cgroup specified and run on the + designated cpu. + + Say N if unsure. + menuconfig CGROUP_SCHED bool "Group CPU scheduler" depends on EXPERIMENTAL diff --git a/init/calibrate.c b/init/calibrate.c index 6eb48e5..24fe022 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -66,7 +66,7 @@ static unsigned long __cpuinit calibrate_delay_direct(void) pre_start = 0; read_current_timer(&start); start_jiffies = jiffies; - while (jiffies <= (start_jiffies + 1)) { + while (time_before_eq(jiffies, start_jiffies + 1)) { pre_start = start; read_current_timer(&start); } @@ -74,8 +74,8 @@ static unsigned long __cpuinit calibrate_delay_direct(void) pre_end = 0; end = post_start; - while (jiffies <= - (start_jiffies + 1 + DELAY_CALIBRATION_TICKS)) { + while (time_before_eq(jiffies, start_jiffies + 1 + + DELAY_CALIBRATION_TICKS)) { pre_end = end; read_current_timer(&end); } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index d2e3c78..e683869 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -144,9 +144,9 @@ int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev) } /* Initialize a parent watch entry. */ -static struct audit_parent *audit_init_parent(struct nameidata *ndp) +static struct audit_parent *audit_init_parent(struct path *path) { - struct inode *inode = ndp->path.dentry->d_inode; + struct inode *inode = path->dentry->d_inode; struct audit_parent *parent; int ret; @@ -353,53 +353,40 @@ static void audit_remove_parent_watches(struct audit_parent *parent) } /* Get path information necessary for adding watches. */ -static int audit_get_nd(char *path, struct nameidata **ndp, struct nameidata **ndw) +static int audit_get_nd(struct audit_watch *watch, struct path *parent) { - struct nameidata *ndparent, *ndwatch; + struct nameidata nd; + struct dentry *d; int err; - ndparent = kmalloc(sizeof(*ndparent), GFP_KERNEL); - if (unlikely(!ndparent)) - return -ENOMEM; + err = kern_path_parent(watch->path, &nd); + if (err) + return err; - ndwatch = kmalloc(sizeof(*ndwatch), GFP_KERNEL); - if (unlikely(!ndwatch)) { - kfree(ndparent); - return -ENOMEM; + if (nd.last_type != LAST_NORM) { + path_put(&nd.path); + return -EINVAL; } - err = path_lookup(path, LOOKUP_PARENT, ndparent); - if (err) { - kfree(ndparent); - kfree(ndwatch); - return err; + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len); + if (IS_ERR(d)) { + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); + return PTR_ERR(d); } - - err = path_lookup(path, 0, ndwatch); - if (err) { - kfree(ndwatch); - ndwatch = NULL; + if (d->d_inode) { + /* update watch filter fields */ + watch->dev = d->d_inode->i_sb->s_dev; + watch->ino = d->d_inode->i_ino; } + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); - *ndp = ndparent; - *ndw = ndwatch; - + *parent = nd.path; + dput(d); return 0; } -/* Release resources used for watch path information. */ -static void audit_put_nd(struct nameidata *ndp, struct nameidata *ndw) -{ - if (ndp) { - path_put(&ndp->path); - kfree(ndp); - } - if (ndw) { - path_put(&ndw->path); - kfree(ndw); - } -} - /* Associate the given rule with an existing parent. * Caller must hold audit_filter_mutex. */ static void audit_add_to_parent(struct audit_krule *krule, @@ -440,31 +427,24 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) { struct audit_watch *watch = krule->watch; struct audit_parent *parent; - struct nameidata *ndp = NULL, *ndw = NULL; + struct path parent_path; int h, ret = 0; mutex_unlock(&audit_filter_mutex); /* Avoid calling path_lookup under audit_filter_mutex. */ - ret = audit_get_nd(watch->path, &ndp, &ndw); - if (ret) { - /* caller expects mutex locked */ - mutex_lock(&audit_filter_mutex); - goto error; - } + ret = audit_get_nd(watch, &parent_path); + /* caller expects mutex locked */ mutex_lock(&audit_filter_mutex); - /* update watch filter fields */ - if (ndw) { - watch->dev = ndw->path.dentry->d_inode->i_sb->s_dev; - watch->ino = ndw->path.dentry->d_inode->i_ino; - } + if (ret) + return ret; /* either find an old parent or attach a new one */ - parent = audit_find_parent(ndp->path.dentry->d_inode); + parent = audit_find_parent(parent_path.dentry->d_inode); if (!parent) { - parent = audit_init_parent(ndp); + parent = audit_init_parent(&parent_path); if (IS_ERR(parent)) { ret = PTR_ERR(parent); goto error; @@ -479,9 +459,8 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) h = audit_hash_ino((u32)watch->ino); *list = &audit_inode_hash[h]; error: - audit_put_nd(ndp, ndw); /* NULL args OK */ + path_put(&parent_path); return ret; - } void audit_remove_watch_rule(struct audit_krule *krule) diff --git a/kernel/capability.c b/kernel/capability.c index 2f05303..9e9385f 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -306,7 +306,7 @@ int capable(int cap) BUG(); } - if (security_capable(cap) == 0) { + if (security_capable(current_cred(), cap) == 0) { current->flags |= PF_SUPERPRIV; return 1; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b24d702..95362d1 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4230,20 +4230,8 @@ void cgroup_post_fork(struct task_struct *child) */ void cgroup_exit(struct task_struct *tsk, int run_callbacks) { - int i; struct css_set *cg; - - if (run_callbacks && need_forkexit_callback) { - /* - * modular subsystems can't use callbacks, so no need to lock - * the subsys array - */ - for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { - struct cgroup_subsys *ss = subsys[i]; - if (ss->exit) - ss->exit(ss, tsk); - } - } + int i; /* * Unlink from the css_set task list if necessary. @@ -4261,7 +4249,24 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) task_lock(tsk); cg = tsk->cgroups; tsk->cgroups = &init_css_set; + + if (run_callbacks && need_forkexit_callback) { + /* + * modular subsystems can't use callbacks, so no need to lock + * the subsys array + */ + for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->exit) { + struct cgroup *old_cgrp = + rcu_dereference_raw(cg->subsys[i])->cgroup; + struct cgroup *cgrp = task_cgroup(tsk, i); + ss->exit(ss, cgrp, old_cgrp, tsk); + } + } + } task_unlock(tsk); + if (cg) put_css_set_taskexit(cg); } @@ -4813,6 +4818,29 @@ css_get_next(struct cgroup_subsys *ss, int id, return ret; } +/* + * get corresponding css from file open on cgroupfs directory + */ +struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id) +{ + struct cgroup *cgrp; + struct inode *inode; + struct cgroup_subsys_state *css; + + inode = f->f_dentry->d_inode; + /* check in cgroup filesystem dir */ + if (inode->i_op != &cgroup_dir_inode_operations) + return ERR_PTR(-EBADF); + + if (id < 0 || id >= CGROUP_SUBSYS_COUNT) + return ERR_PTR(-EINVAL); + + /* get cgroup */ + cgrp = __d_cgrp(f->f_dentry); + css = cgrp->subsys[id]; + return css ? css : ERR_PTR(-ENOENT); +} + #ifdef CONFIG_CGROUP_DEBUG static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss, struct cgroup *cont) diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4349935..e92e981 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, return -ENODEV; trialcs = alloc_trial_cpuset(cs); - if (!trialcs) - return -ENOMEM; + if (!trialcs) { + retval = -ENOMEM; + goto out; + } switch (cft->private) { case FILE_CPULIST: @@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, } free_trial_cpuset(trialcs); +out: cgroup_unlock(); return retval; } diff --git a/kernel/cred.c b/kernel/cred.c index 6a1aa00..2343c132 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -35,7 +35,7 @@ static struct kmem_cache *cred_jar; static struct thread_group_cred init_tgcred = { .usage = ATOMIC_INIT(2), .tgid = 0, - .lock = SPIN_LOCK_UNLOCKED, + .lock = __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock), }; #endif @@ -252,13 +252,13 @@ struct cred *cred_alloc_blank(void) #endif atomic_set(&new->usage, 1); +#ifdef CONFIG_DEBUG_CREDENTIALS + new->magic = CRED_MAGIC; +#endif if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) goto error; -#ifdef CONFIG_DEBUG_CREDENTIALS - new->magic = CRED_MAGIC; -#endif return new; error: @@ -657,6 +657,8 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) validate_creds(old); *new = *old; + atomic_set(&new->usage, 1); + set_cred_subscribers(new, 0); get_uid(new->user); get_group_info(new->group_info); @@ -674,8 +676,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (security_prepare_creds(new, old, GFP_KERNEL) < 0) goto error; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); put_cred(old); validate_creds(new); return new; @@ -748,7 +748,11 @@ bool creds_are_invalid(const struct cred *cred) if (cred->magic != CRED_MAGIC) return true; #ifdef CONFIG_SECURITY_SELINUX - if (selinux_is_enabled()) { + /* + * cred->security == NULL if security_cred_alloc_blank() or + * security_prepare_creds() returned an error. + */ + if (selinux_is_enabled() && cred->security) { if ((unsigned long) cred->security < PAGE_SIZE) return true; if ((*(u32 *)cred->security & 0xffffff00) == diff --git a/kernel/futex.c b/kernel/futex.c index b766d28..bda4157 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -381,15 +381,16 @@ static struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, return NULL; } -static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval) +static int cmpxchg_futex_value_locked(u32 *curval, u32 __user *uaddr, + u32 uval, u32 newval) { - u32 curval; + int ret; pagefault_disable(); - curval = futex_atomic_cmpxchg_inatomic(uaddr, uval, newval); + ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); - return curval; + return ret; } static int get_futex_value_locked(u32 *dest, u32 __user *from) @@ -674,7 +675,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, struct task_struct *task, int set_waiters) { int lock_taken, ret, ownerdied = 0; - u32 uval, newval, curval; + u32 uval, newval, curval, vpid = task_pid_vnr(task); retry: ret = lock_taken = 0; @@ -684,19 +685,17 @@ retry: * (by doing a 0 -> TID atomic cmpxchg), while holding all * the locks. It will most likely not succeed. */ - newval = task_pid_vnr(task); + newval = vpid; if (set_waiters) newval |= FUTEX_WAITERS; - curval = cmpxchg_futex_value_locked(uaddr, 0, newval); - - if (unlikely(curval == -EFAULT)) + if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval))) return -EFAULT; /* * Detect deadlocks. */ - if ((unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(task)))) + if ((unlikely((curval & FUTEX_TID_MASK) == vpid))) return -EDEADLK; /* @@ -723,14 +722,12 @@ retry: */ if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) { /* Keep the OWNER_DIED bit */ - newval = (curval & ~FUTEX_TID_MASK) | task_pid_vnr(task); + newval = (curval & ~FUTEX_TID_MASK) | vpid; ownerdied = 0; lock_taken = 1; } - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); - - if (unlikely(curval == -EFAULT)) + if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))) return -EFAULT; if (unlikely(curval != uval)) goto retry; @@ -775,6 +772,24 @@ retry: return ret; } +/** + * __unqueue_futex() - Remove the futex_q from its futex_hash_bucket + * @q: The futex_q to unqueue + * + * The q->lock_ptr must not be NULL and must be held by the caller. + */ +static void __unqueue_futex(struct futex_q *q) +{ + struct futex_hash_bucket *hb; + + if (WARN_ON(!q->lock_ptr || !spin_is_locked(q->lock_ptr) + || plist_node_empty(&q->list))) + return; + + hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); + plist_del(&q->list, &hb->chain); +} + /* * The hash bucket lock must be held when this is called. * Afterwards, the futex_q must not be accessed. @@ -792,7 +807,7 @@ static void wake_futex(struct futex_q *q) */ get_task_struct(p); - plist_del(&q->list, &q->list.plist); + __unqueue_futex(q); /* * The waiting task can free the futex_q as soon as * q->lock_ptr = NULL is written, without taking any locks. A @@ -843,9 +858,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) newval = FUTEX_WAITERS | task_pid_vnr(new_owner); - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); - - if (curval == -EFAULT) + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) ret = -EFAULT; else if (curval != uval) ret = -EINVAL; @@ -880,10 +893,8 @@ static int unlock_futex_pi(u32 __user *uaddr, u32 uval) * There is no waiter, so we unlock the futex. The owner died * bit has not to be preserved here. We are the owner: */ - oldval = cmpxchg_futex_value_locked(uaddr, uval, 0); - - if (oldval == -EFAULT) - return oldval; + if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0)) + return -EFAULT; if (oldval != uval) return -EAGAIN; @@ -1071,9 +1082,6 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, plist_del(&q->list, &hb1->chain); plist_add(&q->list, &hb2->chain); q->lock_ptr = &hb2->lock; -#ifdef CONFIG_DEBUG_PI_LIST - q->list.plist.spinlock = &hb2->lock; -#endif } get_futex_key_refs(key2); q->key = *key2; @@ -1100,16 +1108,12 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, get_futex_key_refs(key); q->key = *key; - WARN_ON(plist_node_empty(&q->list)); - plist_del(&q->list, &q->list.plist); + __unqueue_futex(q); WARN_ON(!q->rt_waiter); q->rt_waiter = NULL; q->lock_ptr = &hb->lock; -#ifdef CONFIG_DEBUG_PI_LIST - q->list.plist.spinlock = &hb->lock; -#endif wake_up_state(q->task, TASK_NORMAL); } @@ -1457,9 +1461,6 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); -#ifdef CONFIG_DEBUG_PI_LIST - q->list.plist.spinlock = &hb->lock; -#endif plist_add(&q->list, &hb->chain); q->task = current; spin_unlock(&hb->lock); @@ -1504,8 +1505,7 @@ retry: spin_unlock(lock_ptr); goto retry; } - WARN_ON(plist_node_empty(&q->list)); - plist_del(&q->list, &q->list.plist); + __unqueue_futex(q); BUG_ON(q->pi_state); @@ -1525,8 +1525,7 @@ retry: static void unqueue_me_pi(struct futex_q *q) __releases(q->lock_ptr) { - WARN_ON(plist_node_empty(&q->list)); - plist_del(&q->list, &q->list.plist); + __unqueue_futex(q); BUG_ON(!q->pi_state); free_pi_state(q->pi_state); @@ -1556,10 +1555,10 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, /* * We are here either because we stole the rtmutex from the - * pending owner or we are the pending owner which failed to - * get the rtmutex. We have to replace the pending owner TID - * in the user space variable. This must be atomic as we have - * to preserve the owner died bit here. + * previous highest priority waiter or we are the highest priority + * waiter but failed to get the rtmutex the first time. + * We have to replace the newowner TID in the user space variable. + * This must be atomic as we have to preserve the owner died bit here. * * Note: We write the user space value _before_ changing the pi_state * because we can fault here. Imagine swapped out pages or a fork @@ -1578,9 +1577,7 @@ retry: while (1) { newval = (uval & FUTEX_OWNER_DIED) | newtid; - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); - - if (curval == -EFAULT) + if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) goto handle_fault; if (curval == uval) break; @@ -1608,8 +1605,8 @@ retry: /* * To handle the page fault we need to drop the hash bucket - * lock here. That gives the other task (either the pending - * owner itself or the task which stole the rtmutex) the + * lock here. That gives the other task (either the highest priority + * waiter itself or the task which stole the rtmutex) the * chance to try the fixup of the pi_state. So once we are * back from handling the fault we need to check the pi_state * after reacquiring the hash bucket lock and before trying to @@ -1685,18 +1682,20 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) /* * pi_state is incorrect, some other task did a lock steal and * we returned due to timeout or signal without taking the - * rt_mutex. Too late. We can access the rt_mutex_owner without - * locking, as the other task is now blocked on the hash bucket - * lock. Fix the state up. + * rt_mutex. Too late. */ + raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); owner = rt_mutex_owner(&q->pi_state->pi_mutex); + if (!owner) + owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); + raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); ret = fixup_pi_state_owner(uaddr, q, owner); goto out; } /* * Paranoia check. If we did not take the lock, then we should not be - * the owner, nor the pending owner, of the rt_mutex. + * the owner of the rt_mutex. */ if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p " @@ -1781,13 +1780,14 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, * * The basic logical guarantee of a futex is that it blocks ONLY * if cond(var) is known to be true at the time of blocking, for - * any cond. If we queued after testing *uaddr, that would open - * a race condition where we could block indefinitely with + * any cond. If we locked the hash-bucket after testing *uaddr, that + * would open a race condition where we could block indefinitely with * cond(var) false, which would violate the guarantee. * - * A consequence is that futex_wait() can return zero and absorb - * a wakeup when *uaddr != val on entry to the syscall. This is - * rare, but normal. + * On the other hand, we insert q and release the hash-bucket only + * after testing *uaddr. This guarantees that futex_wait() will NOT + * absorb a wakeup if *uaddr does not match the desired values + * while the syscall executes. */ retry: ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q->key); @@ -2046,9 +2046,9 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { struct futex_hash_bucket *hb; struct futex_q *this, *next; - u32 uval; struct plist_head *head; union futex_key key = FUTEX_KEY_INIT; + u32 uval, vpid = task_pid_vnr(current); int ret; retry: @@ -2057,7 +2057,7 @@ retry: /* * We release only a lock we actually own: */ - if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) + if ((uval & FUTEX_TID_MASK) != vpid) return -EPERM; ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key); @@ -2072,17 +2072,14 @@ retry: * again. If it succeeds then we can return without waking * anyone else up: */ - if (!(uval & FUTEX_OWNER_DIED)) - uval = cmpxchg_futex_value_locked(uaddr, task_pid_vnr(current), 0); - - - if (unlikely(uval == -EFAULT)) + if (!(uval & FUTEX_OWNER_DIED) && + cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0)) goto pi_faulted; /* * Rare case: we managed to release the lock atomically, * no need to wake anyone else up: */ - if (unlikely(uval == task_pid_vnr(current))) + if (unlikely(uval == vpid)) goto out_unlock; /* @@ -2167,7 +2164,7 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * We were woken prior to requeue by a timeout or a signal. * Unqueue the futex_q and determine which it was. */ - plist_del(&q->list, &q->list.plist); + plist_del(&q->list, &hb->chain); /* Handle spurious wakeups gracefully */ ret = -EWOULDBLOCK; @@ -2463,11 +2460,20 @@ retry: * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; - nval = futex_atomic_cmpxchg_inatomic(uaddr, uval, mval); - - if (nval == -EFAULT) - return -1; - + /* + * We are not holding a lock here, but we want to have + * the pagefault_disable/enable() protection because + * we want to handle the fault gracefully. If the + * access fails we try to fault in the futex with R/W + * verification via get_user_pages. get_user() above + * does not guarantee R/W access. If that fails we + * give up and leave the futex locked. + */ + if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) { + if (fault_in_user_writeable(uaddr)) + return -1; + goto retry; + } if (nval != uval) goto retry; @@ -2678,8 +2684,7 @@ static int __init futex_init(void) * implementation, the non-functional ones will return * -ENOSYS. */ - curval = cmpxchg_futex_value_locked(NULL, 0, 0); - if (curval == -EFAULT) + if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT) futex_cmpxchg_enabled = 1; for (i = 0; i < ARRAY_SIZE(futex_queues); i++) { diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 63fb749..9017478 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -343,6 +343,11 @@ EXPORT_SYMBOL_GPL(ktime_add_safe); static struct debug_obj_descr hrtimer_debug_descr; +static void *hrtimer_debug_hint(void *addr) +{ + return ((struct hrtimer *) addr)->function; +} + /* * fixup_init is called when: * - an active object is initialized @@ -402,6 +407,7 @@ static int hrtimer_fixup_free(void *addr, enum debug_obj_state state) static struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", + .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 4571ae7..99c3bc8 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -3,6 +3,12 @@ */ #include <linux/irqdesc.h> +#ifdef CONFIG_SPARSE_IRQ +# define IRQ_BITMAP_BITS (NR_IRQS + 8196) +#else +# define IRQ_BITMAP_BITS NR_IRQS +#endif + extern int noirqdebug; #define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data) diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 282f202..2039bea 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -94,7 +94,7 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); -static DECLARE_BITMAP(allocated_irqs, NR_IRQS); +static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS); #ifdef CONFIG_SPARSE_IRQ @@ -217,6 +217,15 @@ int __init early_irq_init(void) initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt); + if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) + nr_irqs = IRQ_BITMAP_BITS; + + if (WARN_ON(initcnt > IRQ_BITMAP_BITS)) + initcnt = IRQ_BITMAP_BITS; + + if (initcnt > nr_irqs) + nr_irqs = initcnt; + for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node); set_bit(i, allocated_irqs); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0caa59f..2782bac 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -282,8 +282,17 @@ EXPORT_SYMBOL(disable_irq); void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) { - if (resume) + if (resume) { + if (!(desc->status & IRQ_SUSPENDED)) { + if (!desc->action) + return; + if (!(desc->action->flags & IRQF_FORCE_RESUME)) + return; + /* Pretend that it got disabled ! */ + desc->depth++; + } desc->status &= ~IRQ_SUSPENDED; + } switch (desc->depth) { case 0: @@ -1100,7 +1109,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, if (retval) kfree(action); -#ifdef CONFIG_DEBUG_SHIRQ +#ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 1d25419..441fd62 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -56,6 +56,7 @@ void move_masked_irq(int irq) void move_native_irq(int irq) { struct irq_desc *desc = irq_to_desc(irq); + bool masked; if (likely(!(desc->status & IRQ_MOVE_PENDING))) return; @@ -63,8 +64,15 @@ void move_native_irq(int irq) if (unlikely(desc->status & IRQ_DISABLED)) return; - desc->irq_data.chip->irq_mask(&desc->irq_data); + /* + * Be careful vs. already masked interrupts. If this is a + * threaded interrupt with ONESHOT set, we can end up with an + * interrupt storm. + */ + masked = desc->status & IRQ_MASKED; + if (!masked) + desc->irq_data.chip->irq_mask(&desc->irq_data); move_masked_irq(irq); - desc->irq_data.chip->irq_unmask(&desc->irq_data); + if (!masked) + desc->irq_data.chip->irq_unmask(&desc->irq_data); } - diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index 0d4005d8..d6bfb89 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -53,9 +53,6 @@ void resume_device_irqs(void) for_each_irq_desc(irq, desc) { unsigned long flags; - if (!(desc->status & IRQ_SUSPENDED)) - continue; - raw_spin_lock_irqsave(&desc->lock, flags); __enable_irq(desc, irq, true); raw_spin_unlock_irqrestore(&desc->lock, flags); diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 891115a..dc49358 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -23,7 +23,7 @@ #ifdef CONFIG_HARDIRQS_SW_RESEND /* Bitmap to handle software resend of interrupts: */ -static DECLARE_BITMAP(irqs_resend, NR_IRQS); +static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS); /* * Run software resends of IRQ's diff --git a/kernel/module.c b/kernel/module.c index 34e00b7..efa290e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2460,9 +2460,9 @@ static void find_module_sections(struct module *mod, struct load_info *info) #endif #ifdef CONFIG_TRACEPOINTS - mod->tracepoints = section_objs(info, "__tracepoints", - sizeof(*mod->tracepoints), - &mod->num_tracepoints); + mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", + sizeof(*mod->tracepoints_ptrs), + &mod->num_tracepoints); #endif #ifdef HAVE_JUMP_LABEL mod->jump_entries = section_objs(info, "__jump_table", @@ -3393,7 +3393,7 @@ void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp, struct kernel_symbol *ks, - struct tracepoint *tp) + struct tracepoint * const *tp) { } EXPORT_SYMBOL(module_layout); @@ -3407,8 +3407,8 @@ void module_update_tracepoints(void) mutex_lock(&module_mutex); list_for_each_entry(mod, &modules, list) if (!mod->taints) - tracepoint_update_probe_range(mod->tracepoints, - mod->tracepoints + mod->num_tracepoints); + tracepoint_update_probe_range(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints); mutex_unlock(&module_mutex); } @@ -3432,8 +3432,8 @@ int module_get_iter_tracepoints(struct tracepoint_iter *iter) else if (iter_mod > iter->module) iter->tracepoint = NULL; found = tracepoint_get_iter_range(&iter->tracepoint, - iter_mod->tracepoints, - iter_mod->tracepoints + iter_mod->tracepoints_ptrs, + iter_mod->tracepoints_ptrs + iter_mod->num_tracepoints); if (found) { iter->module = iter_mod; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 126a302..ed253aa 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -38,13 +38,96 @@ #include <asm/irq_regs.h> +struct remote_function_call { + struct task_struct *p; + int (*func)(void *info); + void *info; + int ret; +}; + +static void remote_function(void *data) +{ + struct remote_function_call *tfc = data; + struct task_struct *p = tfc->p; + + if (p) { + tfc->ret = -EAGAIN; + if (task_cpu(p) != smp_processor_id() || !task_curr(p)) + return; + } + + tfc->ret = tfc->func(tfc->info); +} + +/** + * task_function_call - call a function on the cpu on which a task runs + * @p: the task to evaluate + * @func: the function to be called + * @info: the function call argument + * + * Calls the function @func when the task is currently running. This might + * be on the current CPU, which just calls the function directly + * + * returns: @func return value, or + * -ESRCH - when the process isn't running + * -EAGAIN - when the process moved away + */ +static int +task_function_call(struct task_struct *p, int (*func) (void *info), void *info) +{ + struct remote_function_call data = { + .p = p, + .func = func, + .info = info, + .ret = -ESRCH, /* No such (running) process */ + }; + + if (task_curr(p)) + smp_call_function_single(task_cpu(p), remote_function, &data, 1); + + return data.ret; +} + +/** + * cpu_function_call - call a function on the cpu + * @func: the function to be called + * @info: the function call argument + * + * Calls the function @func on the remote cpu. + * + * returns: @func return value or -ENXIO when the cpu is offline + */ +static int cpu_function_call(int cpu, int (*func) (void *info), void *info) +{ + struct remote_function_call data = { + .p = NULL, + .func = func, + .info = info, + .ret = -ENXIO, /* No such CPU */ + }; + + smp_call_function_single(cpu, remote_function, &data, 1); + + return data.ret; +} + +#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ + PERF_FLAG_FD_OUTPUT |\ + PERF_FLAG_PID_CGROUP) + enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; -atomic_t perf_task_events __read_mostly; +/* + * perf_sched_events : >0 events exist + * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu + */ +atomic_t perf_sched_events __read_mostly; +static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); + static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; static atomic_t nr_task_events __read_mostly; @@ -67,7 +150,24 @@ int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */ /* * max perf event sample rate */ -int sysctl_perf_event_sample_rate __read_mostly = 100000; +#define DEFAULT_MAX_SAMPLE_RATE 100000 +int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE; +static int max_samples_per_tick __read_mostly = + DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ); + +int perf_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (ret || !write) + return ret; + + max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ); + + return 0; +} static atomic64_t perf_event_id; @@ -75,7 +175,11 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type); + enum event_type_t event_type, + struct task_struct *task); + +static void update_context_time(struct perf_event_context *ctx); +static u64 perf_event_time(struct perf_event *event); void __weak perf_event_print_debug(void) { } @@ -89,6 +193,360 @@ static inline u64 perf_clock(void) return local_clock(); } +static inline struct perf_cpu_context * +__get_cpu_context(struct perf_event_context *ctx) +{ + return this_cpu_ptr(ctx->pmu->pmu_cpu_context); +} + +#ifdef CONFIG_CGROUP_PERF + +/* + * Must ensure cgroup is pinned (css_get) before calling + * this function. In other words, we cannot call this function + * if there is no cgroup event for the current CPU context. + */ +static inline struct perf_cgroup * +perf_cgroup_from_task(struct task_struct *task) +{ + return container_of(task_subsys_state(task, perf_subsys_id), + struct perf_cgroup, css); +} + +static inline bool +perf_cgroup_match(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + + return !event->cgrp || event->cgrp == cpuctx->cgrp; +} + +static inline void perf_get_cgroup(struct perf_event *event) +{ + css_get(&event->cgrp->css); +} + +static inline void perf_put_cgroup(struct perf_event *event) +{ + css_put(&event->cgrp->css); +} + +static inline void perf_detach_cgroup(struct perf_event *event) +{ + perf_put_cgroup(event); + event->cgrp = NULL; +} + +static inline int is_cgroup_event(struct perf_event *event) +{ + return event->cgrp != NULL; +} + +static inline u64 perf_cgroup_event_time(struct perf_event *event) +{ + struct perf_cgroup_info *t; + + t = per_cpu_ptr(event->cgrp->info, event->cpu); + return t->time; +} + +static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +{ + struct perf_cgroup_info *info; + u64 now; + + now = perf_clock(); + + info = this_cpu_ptr(cgrp->info); + + info->time += now - info->timestamp; + info->timestamp = now; +} + +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +{ + struct perf_cgroup *cgrp_out = cpuctx->cgrp; + if (cgrp_out) + __update_cgrp_time(cgrp_out); +} + +static inline void update_cgrp_time_from_event(struct perf_event *event) +{ + struct perf_cgroup *cgrp; + + /* + * ensure we access cgroup data only when needed and + * when we know the cgroup is pinned (css_get) + */ + if (!is_cgroup_event(event)) + return; + + cgrp = perf_cgroup_from_task(current); + /* + * Do not update time when cgroup is not active + */ + if (cgrp == event->cgrp) + __update_cgrp_time(event->cgrp); +} + +static inline void +perf_cgroup_set_timestamp(struct task_struct *task, + struct perf_event_context *ctx) +{ + struct perf_cgroup *cgrp; + struct perf_cgroup_info *info; + + /* + * ctx->lock held by caller + * ensure we do not access cgroup data + * unless we have the cgroup pinned (css_get) + */ + if (!task || !ctx->nr_cgroups) + return; + + cgrp = perf_cgroup_from_task(task); + info = this_cpu_ptr(cgrp->info); + info->timestamp = ctx->timestamp; +} + +#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ +#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ + +/* + * reschedule events based on the cgroup constraint of task. + * + * mode SWOUT : schedule out everything + * mode SWIN : schedule in based on cgroup for next + */ +void perf_cgroup_switch(struct task_struct *task, int mode) +{ + struct perf_cpu_context *cpuctx; + struct pmu *pmu; + unsigned long flags; + + /* + * disable interrupts to avoid geting nr_cgroup + * changes via __perf_event_disable(). Also + * avoids preemption. + */ + local_irq_save(flags); + + /* + * we reschedule only in the presence of cgroup + * constrained events. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(pmu, &pmus, entry) { + + cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + + perf_pmu_disable(cpuctx->ctx.pmu); + + /* + * perf_cgroup_events says at least one + * context on this CPU has cgroup events. + * + * ctx->nr_cgroups reports the number of cgroup + * events for a context. + */ + if (cpuctx->ctx.nr_cgroups > 0) { + + if (mode & PERF_CGROUP_SWOUT) { + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to event_filter_match() in event_sched_out() + */ + cpuctx->cgrp = NULL; + } + + if (mode & PERF_CGROUP_SWIN) { + /* set cgrp before ctxsw in to + * allow event_filter_match() to not + * have to pass task around + */ + cpuctx->cgrp = perf_cgroup_from_task(task); + cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); + } + } + + perf_pmu_enable(cpuctx->ctx.pmu); + } + + rcu_read_unlock(); + + local_irq_restore(flags); +} + +static inline void perf_cgroup_sched_out(struct task_struct *task) +{ + perf_cgroup_switch(task, PERF_CGROUP_SWOUT); +} + +static inline void perf_cgroup_sched_in(struct task_struct *task) +{ + perf_cgroup_switch(task, PERF_CGROUP_SWIN); +} + +static inline int perf_cgroup_connect(int fd, struct perf_event *event, + struct perf_event_attr *attr, + struct perf_event *group_leader) +{ + struct perf_cgroup *cgrp; + struct cgroup_subsys_state *css; + struct file *file; + int ret = 0, fput_needed; + + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + + css = cgroup_css_from_dir(file, perf_subsys_id); + if (IS_ERR(css)) { + ret = PTR_ERR(css); + goto out; + } + + cgrp = container_of(css, struct perf_cgroup, css); + event->cgrp = cgrp; + + /* must be done before we fput() the file */ + perf_get_cgroup(event); + + /* + * all events in a group must monitor + * the same cgroup because a task belongs + * to only one perf cgroup at a time + */ + if (group_leader && group_leader->cgrp != cgrp) { + perf_detach_cgroup(event); + ret = -EINVAL; + } +out: + fput_light(file, fput_needed); + return ret; +} + +static inline void +perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +{ + struct perf_cgroup_info *t; + t = per_cpu_ptr(event->cgrp->info, event->cpu); + event->shadow_ctx_time = now - t->timestamp; +} + +static inline void +perf_cgroup_defer_enabled(struct perf_event *event) +{ + /* + * when the current task's perf cgroup does not match + * the event's, we need to remember to call the + * perf_mark_enable() function the first time a task with + * a matching perf cgroup is scheduled in. + */ + if (is_cgroup_event(event) && !perf_cgroup_match(event)) + event->cgrp_defer_enabled = 1; +} + +static inline void +perf_cgroup_mark_enabled(struct perf_event *event, + struct perf_event_context *ctx) +{ + struct perf_event *sub; + u64 tstamp = perf_event_time(event); + + if (!event->cgrp_defer_enabled) + return; + + event->cgrp_defer_enabled = 0; + + event->tstamp_enabled = tstamp - event->total_time_enabled; + list_for_each_entry(sub, &event->sibling_list, group_entry) { + if (sub->state >= PERF_EVENT_STATE_INACTIVE) { + sub->tstamp_enabled = tstamp - sub->total_time_enabled; + sub->cgrp_defer_enabled = 0; + } + } +} +#else /* !CONFIG_CGROUP_PERF */ + +static inline bool +perf_cgroup_match(struct perf_event *event) +{ + return true; +} + +static inline void perf_detach_cgroup(struct perf_event *event) +{} + +static inline int is_cgroup_event(struct perf_event *event) +{ + return 0; +} + +static inline u64 perf_cgroup_event_cgrp_time(struct perf_event *event) +{ + return 0; +} + +static inline void update_cgrp_time_from_event(struct perf_event *event) +{ +} + +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +{ +} + +static inline void perf_cgroup_sched_out(struct task_struct *task) +{ +} + +static inline void perf_cgroup_sched_in(struct task_struct *task) +{ +} + +static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, + struct perf_event_attr *attr, + struct perf_event *group_leader) +{ + return -EINVAL; +} + +static inline void +perf_cgroup_set_timestamp(struct task_struct *task, + struct perf_event_context *ctx) +{ +} + +void +perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +{ +} + +static inline void +perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +{ +} + +static inline u64 perf_cgroup_event_time(struct perf_event *event) +{ + return 0; +} + +static inline void +perf_cgroup_defer_enabled(struct perf_event *event) +{ +} + +static inline void +perf_cgroup_mark_enabled(struct perf_event *event, + struct perf_event_context *ctx) +{ +} +#endif + void perf_pmu_disable(struct pmu *pmu) { int *count = this_cpu_ptr(pmu->pmu_disable_count); @@ -254,7 +712,6 @@ static void perf_unpin_context(struct perf_event_context *ctx) raw_spin_lock_irqsave(&ctx->lock, flags); --ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); - put_ctx(ctx); } /* @@ -271,6 +728,10 @@ static void update_context_time(struct perf_event_context *ctx) static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time(event); + return ctx ? ctx->time : 0; } @@ -285,9 +746,20 @@ static void update_event_times(struct perf_event *event) if (event->state < PERF_EVENT_STATE_INACTIVE || event->group_leader->state < PERF_EVENT_STATE_INACTIVE) return; - - if (ctx->is_active) + /* + * in cgroup mode, time_enabled represents + * the time the event was enabled AND active + * tasks were in the monitored cgroup. This is + * independent of the activity of the context as + * there may be a mix of cgroup and non-cgroup events. + * + * That is why we treat cgroup events differently + * here. + */ + if (is_cgroup_event(event)) run_end = perf_event_time(event); + else if (ctx->is_active) + run_end = ctx->time; else run_end = event->tstamp_stopped; @@ -299,6 +771,7 @@ static void update_event_times(struct perf_event *event) run_end = perf_event_time(event); event->total_time_running = run_end - event->tstamp_running; + } /* @@ -347,6 +820,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) list_add_tail(&event->group_entry, list); } + if (is_cgroup_event(event)) + ctx->nr_cgroups++; + list_add_rcu(&event->event_entry, &ctx->event_list); if (!ctx->nr_events) perf_pmu_rotate_start(ctx->pmu); @@ -473,6 +949,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; + if (is_cgroup_event(event)) + ctx->nr_cgroups--; + ctx->nr_events--; if (event->attr.inherit_stat) ctx->nr_stat--; @@ -544,7 +1023,8 @@ out: static inline int event_filter_match(struct perf_event *event) { - return event->cpu == -1 || event->cpu == smp_processor_id(); + return (event->cpu == -1 || event->cpu == smp_processor_id()) + && perf_cgroup_match(event); } static void @@ -562,7 +1042,7 @@ event_sched_out(struct perf_event *event, */ if (event->state == PERF_EVENT_STATE_INACTIVE && !event_filter_match(event)) { - delta = ctx->time - event->tstamp_stopped; + delta = tstamp - event->tstamp_stopped; event->tstamp_running += delta; event->tstamp_stopped = tstamp; } @@ -606,47 +1086,30 @@ group_sched_out(struct perf_event *group_event, cpuctx->exclusive = 0; } -static inline struct perf_cpu_context * -__get_cpu_context(struct perf_event_context *ctx) -{ - return this_cpu_ptr(ctx->pmu->pmu_cpu_context); -} - /* * Cross CPU call to remove a performance event * * We disable the event on the hardware level first. After that we * remove it from the context list. */ -static void __perf_event_remove_from_context(void *info) +static int __perf_remove_from_context(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - /* - * If this is a task context, we need to check whether it is - * the current task context of this cpu. If not it has been - * scheduled out before the smp call arrived. - */ - if (ctx->task && cpuctx->task_ctx != ctx) - return; - raw_spin_lock(&ctx->lock); - event_sched_out(event, cpuctx, ctx); - list_del_event(event, ctx); - raw_spin_unlock(&ctx->lock); + + return 0; } /* * Remove the event from a task's (or a CPU's) list of events. * - * Must be called with ctx->mutex held. - * * CPU events are removed with a smp call. For task events we only * call when the task is on a CPU. * @@ -657,49 +1120,48 @@ static void __perf_event_remove_from_context(void *info) * When called from perf_event_exit_task, it's OK because the * context has been detached from its task. */ -static void perf_event_remove_from_context(struct perf_event *event) +static void perf_remove_from_context(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; struct task_struct *task = ctx->task; + lockdep_assert_held(&ctx->mutex); + if (!task) { /* * Per cpu events are removed via an smp call and * the removal is always successful. */ - smp_call_function_single(event->cpu, - __perf_event_remove_from_context, - event, 1); + cpu_function_call(event->cpu, __perf_remove_from_context, event); return; } retry: - task_oncpu_function_call(task, __perf_event_remove_from_context, - event); + if (!task_function_call(task, __perf_remove_from_context, event)) + return; raw_spin_lock_irq(&ctx->lock); /* - * If the context is active we need to retry the smp call. + * If we failed to find a running task, but find the context active now + * that we've acquired the ctx->lock, retry. */ - if (ctx->nr_active && !list_empty(&event->group_entry)) { + if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); goto retry; } /* - * The lock prevents that this context is scheduled in so we - * can remove the event safely, if the call above did not - * succeed. + * Since the task isn't running, its safe to remove the event, us + * holding the ctx->lock ensures the task won't get scheduled in. */ - if (!list_empty(&event->group_entry)) - list_del_event(event, ctx); + list_del_event(event, ctx); raw_spin_unlock_irq(&ctx->lock); } /* * Cross CPU call to disable a performance event */ -static void __perf_event_disable(void *info) +static int __perf_event_disable(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; @@ -708,9 +1170,12 @@ static void __perf_event_disable(void *info) /* * If this is a per-task event, need to check whether this * event's task is the current task on this cpu. + * + * Can trigger due to concurrent perf_event_context_sched_out() + * flipping contexts around. */ if (ctx->task && cpuctx->task_ctx != ctx) - return; + return -EINVAL; raw_spin_lock(&ctx->lock); @@ -720,6 +1185,7 @@ static void __perf_event_disable(void *info) */ if (event->state >= PERF_EVENT_STATE_INACTIVE) { update_context_time(ctx); + update_cgrp_time_from_event(event); update_group_times(event); if (event == event->group_leader) group_sched_out(event, cpuctx, ctx); @@ -729,6 +1195,8 @@ static void __perf_event_disable(void *info) } raw_spin_unlock(&ctx->lock); + + return 0; } /* @@ -753,13 +1221,13 @@ void perf_event_disable(struct perf_event *event) /* * Disable the event on the cpu that it's on */ - smp_call_function_single(event->cpu, __perf_event_disable, - event, 1); + cpu_function_call(event->cpu, __perf_event_disable, event); return; } retry: - task_oncpu_function_call(task, __perf_event_disable, event); + if (!task_function_call(task, __perf_event_disable, event)) + return; raw_spin_lock_irq(&ctx->lock); /* @@ -767,6 +1235,11 @@ retry: */ if (event->state == PERF_EVENT_STATE_ACTIVE) { raw_spin_unlock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; goto retry; } @@ -778,10 +1251,48 @@ retry: update_group_times(event); event->state = PERF_EVENT_STATE_OFF; } - raw_spin_unlock_irq(&ctx->lock); } +static void perf_set_shadow_time(struct perf_event *event, + struct perf_event_context *ctx, + u64 tstamp) +{ + /* + * use the correct time source for the time snapshot + * + * We could get by without this by leveraging the + * fact that to get to this function, the caller + * has most likely already called update_context_time() + * and update_cgrp_time_xx() and thus both timestamp + * are identical (or very close). Given that tstamp is, + * already adjusted for cgroup, we could say that: + * tstamp - ctx->timestamp + * is equivalent to + * tstamp - cgrp->timestamp. + * + * Then, in perf_output_read(), the calculation would + * work with no changes because: + * - event is guaranteed scheduled in + * - no scheduled out in between + * - thus the timestamp would be the same + * + * But this is a bit hairy. + * + * So instead, we have an explicit cgroup call to remain + * within the time time source all along. We believe it + * is cleaner and simpler to understand. + */ + if (is_cgroup_event(event)) + perf_cgroup_set_shadow_time(event, tstamp); + else + event->shadow_ctx_time = tstamp - ctx->timestamp; +} + +#define MAX_INTERRUPTS (~0ULL) + +static void perf_log_throttle(struct perf_event *event, int enable); + static int event_sched_in(struct perf_event *event, struct perf_cpu_context *cpuctx, @@ -794,6 +1305,17 @@ event_sched_in(struct perf_event *event, event->state = PERF_EVENT_STATE_ACTIVE; event->oncpu = smp_processor_id(); + + /* + * Unthrottle events, since we scheduled we might have missed several + * ticks already, also for a heavily scheduling task there is little + * guarantee it'll get a tick in a timely manner. + */ + if (unlikely(event->hw.interrupts == MAX_INTERRUPTS)) { + perf_log_throttle(event, 1); + event->hw.interrupts = 0; + } + /* * The new state must be visible before we turn it on in the hardware: */ @@ -807,7 +1329,7 @@ event_sched_in(struct perf_event *event, event->tstamp_running += tstamp - event->tstamp_stopped; - event->shadow_ctx_time = tstamp - ctx->timestamp; + perf_set_shadow_time(event, ctx, tstamp); if (!is_software_event(event)) cpuctx->active_oncpu++; @@ -928,12 +1450,15 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } +static void perf_event_context_sched_in(struct perf_event_context *ctx, + struct task_struct *tsk); + /* * Cross CPU call to install and enable a performance event * * Must be called with ctx->mutex held */ -static void __perf_install_in_context(void *info) +static int __perf_install_in_context(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; @@ -942,21 +1467,22 @@ static void __perf_install_in_context(void *info) int err; /* - * If this is a task context, we need to check whether it is - * the current task context of this cpu. If not it has been - * scheduled out before the smp call arrived. - * Or possibly this is the right context but it isn't - * on this cpu because it had no events. + * In case we're installing a new context to an already running task, + * could also happen before perf_event_task_sched_in() on architectures + * which do context switches with IRQs enabled. */ - if (ctx->task && cpuctx->task_ctx != ctx) { - if (cpuctx->task_ctx || ctx->task != current) - return; - cpuctx->task_ctx = ctx; - } + if (ctx->task && !cpuctx->task_ctx) + perf_event_context_sched_in(ctx, ctx->task); raw_spin_lock(&ctx->lock); ctx->is_active = 1; update_context_time(ctx); + /* + * update cgrp time only if current cgrp + * matches event->cgrp. Must be done before + * calling add_event_to_ctx() + */ + update_cgrp_time_from_event(event); add_event_to_ctx(event, ctx); @@ -997,6 +1523,8 @@ static void __perf_install_in_context(void *info) unlock: raw_spin_unlock(&ctx->lock); + + return 0; } /* @@ -1008,8 +1536,6 @@ unlock: * If the event is attached to a task which is on a CPU we use a smp * call to enable it in the task context. The task might have been * scheduled away, but we check this in the smp call again. - * - * Must be called with ctx->mutex held. */ static void perf_install_in_context(struct perf_event_context *ctx, @@ -1018,6 +1544,8 @@ perf_install_in_context(struct perf_event_context *ctx, { struct task_struct *task = ctx->task; + lockdep_assert_held(&ctx->mutex); + event->ctx = ctx; if (!task) { @@ -1025,31 +1553,29 @@ perf_install_in_context(struct perf_event_context *ctx, * Per cpu events are installed via an smp call and * the install is always successful. */ - smp_call_function_single(cpu, __perf_install_in_context, - event, 1); + cpu_function_call(cpu, __perf_install_in_context, event); return; } retry: - task_oncpu_function_call(task, __perf_install_in_context, - event); + if (!task_function_call(task, __perf_install_in_context, event)) + return; raw_spin_lock_irq(&ctx->lock); /* - * we need to retry the smp call. + * If we failed to find a running task, but find the context active now + * that we've acquired the ctx->lock, retry. */ - if (ctx->is_active && list_empty(&event->group_entry)) { + if (ctx->is_active) { raw_spin_unlock_irq(&ctx->lock); goto retry; } /* - * The lock prevents that this context is scheduled in so we - * can add the event safely, if it the call above did not - * succeed. + * Since the task isn't running, its safe to add the event, us holding + * the ctx->lock ensures the task won't get scheduled in. */ - if (list_empty(&event->group_entry)) - add_event_to_ctx(event, ctx); + add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); } @@ -1078,7 +1604,7 @@ static void __perf_event_mark_enabled(struct perf_event *event, /* * Cross CPU call to enable a performance event */ -static void __perf_event_enable(void *info) +static int __perf_event_enable(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; @@ -1086,26 +1612,27 @@ static void __perf_event_enable(void *info) struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); int err; - /* - * If this is a per-task event, need to check whether this - * event's task is the current task on this cpu. - */ - if (ctx->task && cpuctx->task_ctx != ctx) { - if (cpuctx->task_ctx || ctx->task != current) - return; - cpuctx->task_ctx = ctx; - } + if (WARN_ON_ONCE(!ctx->is_active)) + return -EINVAL; raw_spin_lock(&ctx->lock); - ctx->is_active = 1; update_context_time(ctx); if (event->state >= PERF_EVENT_STATE_INACTIVE) goto unlock; + + /* + * set current task's cgroup time reference point + */ + perf_cgroup_set_timestamp(current, ctx); + __perf_event_mark_enabled(event, ctx); - if (!event_filter_match(event)) + if (!event_filter_match(event)) { + if (is_cgroup_event(event)) + perf_cgroup_defer_enabled(event); goto unlock; + } /* * If the event is in a group and isn't the group leader, @@ -1138,6 +1665,8 @@ static void __perf_event_enable(void *info) unlock: raw_spin_unlock(&ctx->lock); + + return 0; } /* @@ -1158,8 +1687,7 @@ void perf_event_enable(struct perf_event *event) /* * Enable the event on the cpu that it's on */ - smp_call_function_single(event->cpu, __perf_event_enable, - event, 1); + cpu_function_call(event->cpu, __perf_event_enable, event); return; } @@ -1178,8 +1706,15 @@ void perf_event_enable(struct perf_event *event) event->state = PERF_EVENT_STATE_OFF; retry: + if (!ctx->is_active) { + __perf_event_mark_enabled(event, ctx); + goto out; + } + raw_spin_unlock_irq(&ctx->lock); - task_oncpu_function_call(task, __perf_event_enable, event); + + if (!task_function_call(task, __perf_event_enable, event)) + return; raw_spin_lock_irq(&ctx->lock); @@ -1187,15 +1722,14 @@ retry: * If the context is active and the event is still off, * we need to retry the cross-call. */ - if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) + if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) { + /* + * task could have been flipped by a concurrent + * perf_event_context_sched_out() + */ + task = ctx->task; goto retry; - - /* - * Since we have the lock this context can't be scheduled - * in, so we can change the state safely. - */ - if (event->state == PERF_EVENT_STATE_OFF) - __perf_event_mark_enabled(event, ctx); + } out: raw_spin_unlock_irq(&ctx->lock); @@ -1227,6 +1761,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (likely(!ctx->nr_events)) goto out; update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); if (!ctx->nr_active) goto out; @@ -1339,8 +1874,8 @@ static void perf_event_sync_stat(struct perf_event_context *ctx, } } -void perf_event_context_sched_out(struct task_struct *task, int ctxn, - struct task_struct *next) +static void perf_event_context_sched_out(struct task_struct *task, int ctxn, + struct task_struct *next) { struct perf_event_context *ctx = task->perf_event_ctxp[ctxn]; struct perf_event_context *next_ctx; @@ -1416,6 +1951,14 @@ void __perf_event_task_sched_out(struct task_struct *task, for_each_task_context_nr(ctxn) perf_event_context_sched_out(task, ctxn, next); + + /* + * if cgroup events exist on this CPU, then we need + * to check if we have to switch out PMU state. + * cgroup event are system-wide mode only + */ + if (atomic_read(&__get_cpu_var(perf_cgroup_events))) + perf_cgroup_sched_out(task); } static void task_ctx_sched_out(struct perf_event_context *ctx, @@ -1454,6 +1997,10 @@ ctx_pinned_sched_in(struct perf_event_context *ctx, if (!event_filter_match(event)) continue; + /* may need to reset tstamp_enabled */ + if (is_cgroup_event(event)) + perf_cgroup_mark_enabled(event, ctx); + if (group_can_go_on(event, cpuctx, 1)) group_sched_in(event, cpuctx, ctx); @@ -1486,6 +2033,10 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, if (!event_filter_match(event)) continue; + /* may need to reset tstamp_enabled */ + if (is_cgroup_event(event)) + perf_cgroup_mark_enabled(event, ctx); + if (group_can_go_on(event, cpuctx, can_add_hw)) { if (group_sched_in(event, cpuctx, ctx)) can_add_hw = 0; @@ -1496,15 +2047,19 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type) + enum event_type_t event_type, + struct task_struct *task) { + u64 now; + raw_spin_lock(&ctx->lock); ctx->is_active = 1; if (likely(!ctx->nr_events)) goto out; - ctx->timestamp = perf_clock(); - + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. @@ -1521,11 +2076,12 @@ out: } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type) + enum event_type_t event_type, + struct task_struct *task) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type); + ctx_sched_in(ctx, cpuctx, event_type, task); } static void task_ctx_sched_in(struct perf_event_context *ctx, @@ -1533,15 +2089,16 @@ static void task_ctx_sched_in(struct perf_event_context *ctx, { struct perf_cpu_context *cpuctx; - cpuctx = __get_cpu_context(ctx); + cpuctx = __get_cpu_context(ctx); if (cpuctx->task_ctx == ctx) return; - ctx_sched_in(ctx, cpuctx, event_type); + ctx_sched_in(ctx, cpuctx, event_type, NULL); cpuctx->task_ctx = ctx; } -void perf_event_context_sched_in(struct perf_event_context *ctx) +static void perf_event_context_sched_in(struct perf_event_context *ctx, + struct task_struct *task) { struct perf_cpu_context *cpuctx; @@ -1557,9 +2114,9 @@ void perf_event_context_sched_in(struct perf_event_context *ctx) */ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - ctx_sched_in(ctx, cpuctx, EVENT_PINNED); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); cpuctx->task_ctx = ctx; @@ -1592,14 +2149,17 @@ void __perf_event_task_sched_in(struct task_struct *task) if (likely(!ctx)) continue; - perf_event_context_sched_in(ctx); + perf_event_context_sched_in(ctx, task); } + /* + * if cgroup events exist on this CPU, then we need + * to check if we have to switch in PMU state. + * cgroup event are system-wide mode only + */ + if (atomic_read(&__get_cpu_var(perf_cgroup_events))) + perf_cgroup_sched_in(task); } -#define MAX_INTERRUPTS (~0ULL) - -static void perf_log_throttle(struct perf_event *event, int enable); - static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) { u64 frequency = event->attr.sample_freq; @@ -1627,7 +2187,7 @@ static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) * Reduce accuracy by one bit such that @a and @b converge * to a similar magnitude. */ -#define REDUCE_FLS(a, b) \ +#define REDUCE_FLS(a, b) \ do { \ if (a##_fls > b##_fls) { \ a >>= 1; \ @@ -1797,7 +2357,7 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx) if (ctx) rotate_ctx(ctx); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current); if (ctx) task_ctx_sched_in(ctx, EVENT_FLEXIBLE); @@ -1876,7 +2436,7 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) raw_spin_unlock(&ctx->lock); - perf_event_context_sched_in(ctx); + perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); } @@ -1901,11 +2461,14 @@ static void __perf_event_read(void *info) return; raw_spin_lock(&ctx->lock); - update_context_time(ctx); + if (ctx->is_active) { + update_context_time(ctx); + update_cgrp_time_from_event(event); + } update_event_times(event); + if (event->state == PERF_EVENT_STATE_ACTIVE) + event->pmu->read(event); raw_spin_unlock(&ctx->lock); - - event->pmu->read(event); } static inline u64 perf_event_count(struct perf_event *event) @@ -1932,8 +2495,10 @@ static u64 perf_event_read(struct perf_event *event) * (e.g., thread is blocked), in that case * we cannot update context time */ - if (ctx->is_active) + if (ctx->is_active) { update_context_time(ctx); + update_cgrp_time_from_event(event); + } update_event_times(event); raw_spin_unlock_irqrestore(&ctx->lock, flags); } @@ -1999,8 +2564,7 @@ static int alloc_callchain_buffers(void) * accessed from NMI. Use a temporary manual per cpu allocation * until that gets sorted out. */ - size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) * - num_possible_cpus(); + size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]); entries = kzalloc(size, GFP_KERNEL); if (!entries) @@ -2213,6 +2777,9 @@ errout: } +/* + * Returns a matching context with refcount and pincount. + */ static struct perf_event_context * find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) { @@ -2237,6 +2804,7 @@ find_get_context(struct pmu *pmu, struct task_struct *task, int cpu) cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); ctx = &cpuctx->ctx; get_ctx(ctx); + ++ctx->pin_count; return ctx; } @@ -2250,6 +2818,7 @@ retry: ctx = perf_lock_task_context(task, ctxn, &flags); if (ctx) { unclone_ctx(ctx); + ++ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); } @@ -2271,8 +2840,10 @@ retry: err = -ESRCH; else if (task->perf_event_ctxp[ctxn]) err = -EAGAIN; - else + else { + ++ctx->pin_count; rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx); + } mutex_unlock(&task->perf_event_mutex); if (unlikely(err)) { @@ -2312,7 +2883,7 @@ static void free_event(struct perf_event *event) if (!event->parent) { if (event->attach_state & PERF_ATTACH_TASK) - jump_label_dec(&perf_task_events); + jump_label_dec(&perf_sched_events); if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.comm) @@ -2321,6 +2892,10 @@ static void free_event(struct perf_event *event) atomic_dec(&nr_task_events); if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) put_callchain_buffers(); + if (is_cgroup_event(event)) { + atomic_dec(&per_cpu(perf_cgroup_events, event->cpu)); + jump_label_dec(&perf_sched_events); + } } if (event->buffer) { @@ -2328,6 +2903,9 @@ static void free_event(struct perf_event *event) event->buffer = NULL; } + if (is_cgroup_event(event)) + perf_detach_cgroup(event); + if (event->destroy) event->destroy(event); @@ -4395,26 +4973,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi, if (unlikely(!is_sampling_event(event))) return 0; - if (!throttle) { - hwc->interrupts++; - } else { - if (hwc->interrupts != MAX_INTERRUPTS) { - hwc->interrupts++; - if (HZ * hwc->interrupts > - (u64)sysctl_perf_event_sample_rate) { - hwc->interrupts = MAX_INTERRUPTS; - perf_log_throttle(event, 0); - ret = 1; - } - } else { - /* - * Keep re-disabling events even though on the previous - * pass we disabled it - just in case we raced with a - * sched-in and the event got enabled again: - */ + if (unlikely(hwc->interrupts >= max_samples_per_tick)) { + if (throttle) { + hwc->interrupts = MAX_INTERRUPTS; + perf_log_throttle(event, 0); ret = 1; } - } + } else + hwc->interrupts++; if (event->attr.freq) { u64 now = perf_clock(); @@ -5051,6 +5617,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) u64 period; event = container_of(hrtimer, struct perf_event, hw.hrtimer); + + if (event->state != PERF_EVENT_STATE_ACTIVE) + return HRTIMER_NORESTART; + event->pmu->read(event); perf_sample_data_init(&data, 0); @@ -5077,9 +5647,6 @@ static void perf_swevent_start_hrtimer(struct perf_event *event) if (!is_sampling_event(event)) return; - hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hwc->hrtimer.function = perf_swevent_hrtimer; - period = local64_read(&hwc->period_left); if (period) { if (period < 0) @@ -5106,6 +5673,30 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event) } } +static void perf_swevent_init_hrtimer(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (!is_sampling_event(event)) + return; + + hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hwc->hrtimer.function = perf_swevent_hrtimer; + + /* + * Since hrtimers have a fixed rate, we can do a static freq->period + * mapping and avoid the whole period adjust feedback stuff. + */ + if (event->attr.freq) { + long freq = event->attr.sample_freq; + + event->attr.sample_period = NSEC_PER_SEC / freq; + hwc->sample_period = event->attr.sample_period; + local64_set(&hwc->period_left, hwc->sample_period); + event->attr.freq = 0; + } +} + /* * Software event: cpu wall time clock */ @@ -5158,6 +5749,8 @@ static int cpu_clock_event_init(struct perf_event *event) if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK) return -ENOENT; + perf_swevent_init_hrtimer(event); + return 0; } @@ -5213,16 +5806,9 @@ static void task_clock_event_del(struct perf_event *event, int flags) static void task_clock_event_read(struct perf_event *event) { - u64 time; - - if (!in_nmi()) { - update_context_time(event->ctx); - time = event->ctx->time; - } else { - u64 now = perf_clock(); - u64 delta = now - event->ctx->timestamp; - time = event->ctx->time + delta; - } + u64 now = perf_clock(); + u64 delta = now - event->ctx->timestamp; + u64 time = event->ctx->time + delta; task_clock_event_update(event, time); } @@ -5235,6 +5821,8 @@ static int task_clock_event_init(struct perf_event *event) if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK) return -ENOENT; + perf_swevent_init_hrtimer(event); + return 0; } @@ -5506,17 +6094,22 @@ struct pmu *perf_init_event(struct perf_event *event) { struct pmu *pmu = NULL; int idx; + int ret; idx = srcu_read_lock(&pmus_srcu); rcu_read_lock(); pmu = idr_find(&pmu_idr, event->attr.type); rcu_read_unlock(); - if (pmu) + if (pmu) { + ret = pmu->event_init(event); + if (ret) + pmu = ERR_PTR(ret); goto unlock; + } list_for_each_entry_rcu(pmu, &pmus, entry) { - int ret = pmu->event_init(event); + ret = pmu->event_init(event); if (!ret) goto unlock; @@ -5642,7 +6235,7 @@ done: if (!event->parent) { if (event->attach_state & PERF_ATTACH_TASK) - jump_label_inc(&perf_task_events); + jump_label_inc(&perf_sched_events); if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); if (event->attr.comm) @@ -5817,7 +6410,7 @@ SYSCALL_DEFINE5(perf_event_open, int err; /* for future expandability... */ - if (flags & ~(PERF_FLAG_FD_NO_GROUP | PERF_FLAG_FD_OUTPUT)) + if (flags & ~PERF_FLAG_ALL) return -EINVAL; err = perf_copy_attr(attr_uptr, &attr); @@ -5834,6 +6427,15 @@ SYSCALL_DEFINE5(perf_event_open, return -EINVAL; } + /* + * In cgroup mode, the pid argument is used to pass the fd + * opened to the cgroup directory in cgroupfs. The cpu argument + * designates the cpu on which to monitor threads from that + * cgroup. + */ + if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1)) + return -EINVAL; + event_fd = get_unused_fd_flags(O_RDWR); if (event_fd < 0) return event_fd; @@ -5851,7 +6453,7 @@ SYSCALL_DEFINE5(perf_event_open, group_leader = NULL; } - if (pid != -1) { + if (pid != -1 && !(flags & PERF_FLAG_PID_CGROUP)) { task = find_lively_task_by_vpid(pid); if (IS_ERR(task)) { err = PTR_ERR(task); @@ -5865,6 +6467,19 @@ SYSCALL_DEFINE5(perf_event_open, goto err_task; } + if (flags & PERF_FLAG_PID_CGROUP) { + err = perf_cgroup_connect(pid, event, &attr, group_leader); + if (err) + goto err_alloc; + /* + * one more event: + * - that has cgroup constraint on event->cpu + * - that may need work on context switch + */ + atomic_inc(&per_cpu(perf_cgroup_events, event->cpu)); + jump_label_inc(&perf_sched_events); + } + /* * Special case software events and allow them to be part of * any hardware group. @@ -5950,10 +6565,10 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event_context *gctx = group_leader->ctx; mutex_lock(&gctx->mutex); - perf_event_remove_from_context(group_leader); + perf_remove_from_context(group_leader); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_event_remove_from_context(sibling); + perf_remove_from_context(sibling); put_ctx(gctx); } mutex_unlock(&gctx->mutex); @@ -5976,6 +6591,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_install_in_context(ctx, event, cpu); ++ctx->generation; + perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); event->owner = current; @@ -6001,6 +6617,7 @@ SYSCALL_DEFINE5(perf_event_open, return event_fd; err_context: + perf_unpin_context(ctx); put_ctx(ctx); err_alloc: free_event(event); @@ -6051,6 +6668,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, mutex_lock(&ctx->mutex); perf_install_in_context(ctx, event, cpu); ++ctx->generation; + perf_unpin_context(ctx); mutex_unlock(&ctx->mutex); return event; @@ -6104,7 +6722,7 @@ __perf_event_exit_task(struct perf_event *child_event, { struct perf_event *parent_event; - perf_event_remove_from_context(child_event); + perf_remove_from_context(child_event); parent_event = child_event->parent; /* @@ -6411,7 +7029,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, return 0; } - child_ctx = child->perf_event_ctxp[ctxn]; + child_ctx = child->perf_event_ctxp[ctxn]; if (!child_ctx) { /* * This is executed from the parent task context, so @@ -6526,6 +7144,7 @@ int perf_event_init_context(struct task_struct *child, int ctxn) mutex_unlock(&parent_ctx->mutex); perf_unpin_context(parent_ctx); + put_ctx(parent_ctx); return ret; } @@ -6595,9 +7214,9 @@ static void __perf_event_exit_context(void *__info) perf_pmu_rotate_stop(ctx->pmu); list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry) - __perf_event_remove_from_context(event); + __perf_remove_from_context(event); list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry) - __perf_event_remove_from_context(event); + __perf_remove_from_context(event); } static void perf_event_exit_cpu_context(int cpu) @@ -6721,3 +7340,83 @@ unlock: return ret; } device_initcall(perf_event_sysfs_init); + +#ifdef CONFIG_CGROUP_PERF +static struct cgroup_subsys_state *perf_cgroup_create( + struct cgroup_subsys *ss, struct cgroup *cont) +{ + struct perf_cgroup *jc; + + jc = kzalloc(sizeof(*jc), GFP_KERNEL); + if (!jc) + return ERR_PTR(-ENOMEM); + + jc->info = alloc_percpu(struct perf_cgroup_info); + if (!jc->info) { + kfree(jc); + return ERR_PTR(-ENOMEM); + } + + return &jc->css; +} + +static void perf_cgroup_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + struct perf_cgroup *jc; + jc = container_of(cgroup_subsys_state(cont, perf_subsys_id), + struct perf_cgroup, css); + free_percpu(jc->info); + kfree(jc); +} + +static int __perf_cgroup_move(void *info) +{ + struct task_struct *task = info; + perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + return 0; +} + +static void perf_cgroup_move(struct task_struct *task) +{ + task_function_call(task, __perf_cgroup_move, task); +} + +static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup *old_cgrp, struct task_struct *task, + bool threadgroup) +{ + perf_cgroup_move(task); + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &task->thread_group, thread_group) { + perf_cgroup_move(c); + } + rcu_read_unlock(); + } +} + +static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup *old_cgrp, struct task_struct *task) +{ + /* + * cgroup_exit() is called in the copy_process() failure path. + * Ignore this case since the task hasn't ran yet, this avoids + * trying to poke a half freed task state from generic code. + */ + if (!(task->flags & PF_EXITING)) + return; + + perf_cgroup_move(task); +} + +struct cgroup_subsys perf_subsys = { + .name = "perf_event", + .subsys_id = perf_subsys_id, + .create = perf_cgroup_create, + .destroy = perf_cgroup_destroy, + .exit = perf_cgroup_exit, + .attach = perf_cgroup_attach, +}; +#endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/power/main.c b/kernel/power/main.c index 7b5db6a..7018530 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(pm_wq); static int __init pm_start_workqueue(void) { - pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0); + pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0); return pm_wq ? 0 : -ENOMEM; } diff --git a/kernel/power/process.c b/kernel/power/process.c index d6d2a10..0cf3a27 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -22,7 +22,7 @@ */ #define TIMEOUT (20 * HZ) -static inline int freezeable(struct task_struct * p) +static inline int freezable(struct task_struct * p) { if ((p == current) || (p->flags & PF_NOFREEZE) || @@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only) todo = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { - if (frozen(p) || !freezeable(p)) + if (frozen(p) || !freezable(p)) continue; if (!freeze_task(p, sig_only)) @@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only) read_lock(&tasklist_lock); do_each_thread(g, p) { - if (!freezeable(p)) + if (!freezable(p)) continue; if (nosig_only && should_send_signal(p)) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 0dac75e..64db648 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1519,11 +1519,8 @@ static int swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, unsigned int nr_pages, unsigned int nr_highmem) { - int error = 0; - if (nr_highmem > 0) { - error = get_highmem_buffer(PG_ANY); - if (error) + if (get_highmem_buffer(PG_ANY)) goto err_out; if (nr_highmem > alloc_highmem) { nr_highmem -= alloc_highmem; @@ -1546,7 +1543,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, err_out: swsusp_free(); - return error; + return -ENOMEM; } asmlinkage int swsusp_save(void) diff --git a/kernel/printk.c b/kernel/printk.c index 2ddbdc7..3623152 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -262,25 +262,47 @@ int dmesg_restrict = 1; int dmesg_restrict; #endif +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* Unless restricted, we allow "read all" and "get buffer size" for everybody */ + return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; +} + +static int check_syslog_permissions(int type, bool from_file) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (from_file && type != SYSLOG_ACTION_OPEN) + return 0; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + return 0; + /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */ + if (capable(CAP_SYS_ADMIN)) { + WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN " + "but no CAP_SYSLOG (deprecated).\n"); + return 0; + } + return -EPERM; + } + return 0; +} + int do_syslog(int type, char __user *buf, int len, bool from_file) { unsigned i, j, limit, count; int do_clear = 0; char c; - int error = 0; + int error; - /* - * If this is from /proc/kmsg we only do the capabilities checks - * at open time. - */ - if (type == SYSLOG_ACTION_OPEN || !from_file) { - if (dmesg_restrict && !capable(CAP_SYSLOG)) - goto warn; /* switch to return -EPERM after 2.6.39 */ - if ((type != SYSLOG_ACTION_READ_ALL && - type != SYSLOG_ACTION_SIZE_BUFFER) && - !capable(CAP_SYSLOG)) - goto warn; /* switch to return -EPERM after 2.6.39 */ - } + error = check_syslog_permissions(type, from_file); + if (error) + goto out; error = security_syslog(type); if (error) @@ -423,12 +445,6 @@ int do_syslog(int type, char __user *buf, int len, bool from_file) } out: return error; -warn: - /* remove after 2.6.39 */ - if (capable(CAP_SYS_ADMIN)) - WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN " - "but no CAP_SYSLOG (deprecated and denied).\n"); - return -EPERM; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 99bbaa3..e2302e4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) return !err; } -int ptrace_attach(struct task_struct *task) +static int ptrace_attach(struct task_struct *task) { int retval; @@ -219,7 +219,7 @@ out: * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ -int ptrace_traceme(void) +static int ptrace_traceme(void) { int ret = -EPERM; @@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) return false; } -int ptrace_detach(struct task_struct *child, unsigned int data) +static int ptrace_detach(struct task_struct *child, unsigned int data) { bool dead = false; @@ -313,7 +313,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data) child->exit_code = data; dead = __ptrace_detach(current, child); if (!child->exit_state) - wake_up_process(child); + wake_up_state(child, TASK_TRACED | TASK_STOPPED); } write_unlock_irq(&tasklist_lock); diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c index ddabb54..3c7cbc2 100644 --- a/kernel/rtmutex-debug.c +++ b/kernel/rtmutex-debug.c @@ -215,7 +215,6 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter) put_pid(waiter->deadlock_task_pid); TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry)); TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry)); - TRACE_WARN_ON(waiter->task); memset(waiter, 0x22, sizeof(*waiter)); } diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c index 66cb89b..5c9ccd3 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/rtmutex-tester.c @@ -9,7 +9,6 @@ #include <linux/kthread.h> #include <linux/module.h> #include <linux/sched.h> -#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/sysdev.h> #include <linux/timer.h> @@ -27,7 +26,6 @@ struct test_thread_data { int opcode; int opdata; int mutexes[MAX_RT_TEST_MUTEXES]; - int bkl; int event; struct sys_device sysdev; }; @@ -46,9 +44,8 @@ enum test_opcodes { RTTEST_LOCKINTNOWAIT, /* 6 Lock interruptible no wait in wakeup, data = lockindex */ RTTEST_LOCKCONT, /* 7 Continue locking after the wakeup delay */ RTTEST_UNLOCK, /* 8 Unlock, data = lockindex */ - RTTEST_LOCKBKL, /* 9 Lock BKL */ - RTTEST_UNLOCKBKL, /* 10 Unlock BKL */ - RTTEST_SIGNAL, /* 11 Signal other test thread, data = thread id */ + /* 9, 10 - reserved for BKL commemoration */ + RTTEST_SIGNAL = 11, /* 11 Signal other test thread, data = thread id */ RTTEST_RESETEVENT = 98, /* 98 Reset event counter */ RTTEST_RESET = 99, /* 99 Reset all pending operations */ }; @@ -74,13 +71,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup) td->mutexes[i] = 0; } } - - if (!lockwakeup && td->bkl == 4) { -#ifdef CONFIG_LOCK_KERNEL - unlock_kernel(); -#endif - td->bkl = 0; - } return 0; case RTTEST_RESETEVENT: @@ -131,25 +121,6 @@ static int handle_op(struct test_thread_data *td, int lockwakeup) td->mutexes[id] = 0; return 0; - case RTTEST_LOCKBKL: - if (td->bkl) - return 0; - td->bkl = 1; -#ifdef CONFIG_LOCK_KERNEL - lock_kernel(); -#endif - td->bkl = 4; - return 0; - - case RTTEST_UNLOCKBKL: - if (td->bkl != 4) - break; -#ifdef CONFIG_LOCK_KERNEL - unlock_kernel(); -#endif - td->bkl = 0; - return 0; - default: break; } @@ -196,7 +167,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex) td->event = atomic_add_return(1, &rttest_event); break; - case RTTEST_LOCKBKL: default: break; } @@ -229,8 +199,6 @@ void schedule_rt_mutex_test(struct rt_mutex *mutex) td->event = atomic_add_return(1, &rttest_event); return; - case RTTEST_LOCKBKL: - return; default: return; } @@ -380,11 +348,11 @@ static ssize_t sysfs_test_status(struct sys_device *dev, struct sysdev_attribute spin_lock(&rttest_lock); curr += sprintf(curr, - "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, K: %d, M:", + "O: %4d, E:%8d, S: 0x%08lx, P: %4d, N: %4d, B: %p, M:", td->opcode, td->event, tsk->state, (MAX_RT_PRIO - 1) - tsk->prio, (MAX_RT_PRIO - 1) - tsk->normal_prio, - tsk->pi_blocked_on, td->bkl); + tsk->pi_blocked_on); for (i = MAX_RT_TEST_MUTEXES - 1; i >=0 ; i--) curr += sprintf(curr, "%d", td->mutexes[i]); diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index a960481..ab44911 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -20,41 +20,34 @@ /* * lock->owner state tracking: * - * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1 - * are used to keep track of the "owner is pending" and "lock has - * waiters" state. + * lock->owner holds the task_struct pointer of the owner. Bit 0 + * is used to keep track of the "lock has waiters" state. * - * owner bit1 bit0 - * NULL 0 0 lock is free (fast acquire possible) - * NULL 0 1 invalid state - * NULL 1 0 Transitional State* - * NULL 1 1 invalid state - * taskpointer 0 0 lock is held (fast release possible) - * taskpointer 0 1 task is pending owner - * taskpointer 1 0 lock is held and has waiters - * taskpointer 1 1 task is pending owner and lock has more waiters - * - * Pending ownership is assigned to the top (highest priority) - * waiter of the lock, when the lock is released. The thread is woken - * up and can now take the lock. Until the lock is taken (bit 0 - * cleared) a competing higher priority thread can steal the lock - * which puts the woken up thread back on the waiters list. + * owner bit0 + * NULL 0 lock is free (fast acquire possible) + * NULL 1 lock is free and has waiters and the top waiter + * is going to take the lock* + * taskpointer 0 lock is held (fast release possible) + * taskpointer 1 lock is held and has waiters** * * The fast atomic compare exchange based acquire and release is only - * possible when bit 0 and 1 of lock->owner are 0. + * possible when bit 0 of lock->owner is 0. + * + * (*) It also can be a transitional state when grabbing the lock + * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock, + * we need to set the bit0 before looking at the lock, and the owner may be + * NULL in this small time, hence this can be a transitional state. * - * (*) There's a small time where the owner can be NULL and the - * "lock has waiters" bit is set. This can happen when grabbing the lock. - * To prevent a cmpxchg of the owner releasing the lock, we need to set this - * bit before looking at the lock, hence the reason this is a transitional - * state. + * (**) There is a small time when bit 0 is set but there are no + * waiters. This can happen when grabbing the lock in the slow path. + * To prevent a cmpxchg of the owner releasing the lock, we need to + * set this bit before looking at the lock. */ static void -rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner, - unsigned long mask) +rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner) { - unsigned long val = (unsigned long)owner | mask; + unsigned long val = (unsigned long)owner; if (rt_mutex_has_waiters(lock)) val |= RT_MUTEX_HAS_WAITERS; @@ -203,15 +196,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * reached or the state of the chain has changed while we * dropped the locks. */ - if (!waiter || !waiter->task) + if (!waiter) goto out_unlock_pi; /* * Check the orig_waiter state. After we dropped the locks, - * the previous owner of the lock might have released the lock - * and made us the pending owner: + * the previous owner of the lock might have released the lock. */ - if (orig_waiter && !orig_waiter->task) + if (orig_waiter && !rt_mutex_owner(orig_lock)) goto out_unlock_pi; /* @@ -254,6 +246,17 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* Release the task */ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + if (!rt_mutex_owner(lock)) { + /* + * If the requeue above changed the top waiter, then we need + * to wake the new top waiter up to try to get the lock. + */ + + if (top_waiter != rt_mutex_top_waiter(lock)) + wake_up_process(rt_mutex_top_waiter(lock)->task); + raw_spin_unlock(&lock->wait_lock); + goto out_put_task; + } put_task_struct(task); /* Grab the next task */ @@ -296,78 +299,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, } /* - * Optimization: check if we can steal the lock from the - * assigned pending owner [which might not have taken the - * lock yet]: - */ -static inline int try_to_steal_lock(struct rt_mutex *lock, - struct task_struct *task) -{ - struct task_struct *pendowner = rt_mutex_owner(lock); - struct rt_mutex_waiter *next; - unsigned long flags; - - if (!rt_mutex_owner_pending(lock)) - return 0; - - if (pendowner == task) - return 1; - - raw_spin_lock_irqsave(&pendowner->pi_lock, flags); - if (task->prio >= pendowner->prio) { - raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags); - return 0; - } - - /* - * Check if a waiter is enqueued on the pending owners - * pi_waiters list. Remove it and readjust pending owners - * priority. - */ - if (likely(!rt_mutex_has_waiters(lock))) { - raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags); - return 1; - } - - /* No chain handling, pending owner is not blocked on anything: */ - next = rt_mutex_top_waiter(lock); - plist_del(&next->pi_list_entry, &pendowner->pi_waiters); - __rt_mutex_adjust_prio(pendowner); - raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags); - - /* - * We are going to steal the lock and a waiter was - * enqueued on the pending owners pi_waiters queue. So - * we have to enqueue this waiter into - * task->pi_waiters list. This covers the case, - * where task is boosted because it holds another - * lock and gets unboosted because the booster is - * interrupted, so we would delay a waiter with higher - * priority as task->normal_prio. - * - * Note: in the rare case of a SCHED_OTHER task changing - * its priority and thus stealing the lock, next->task - * might be task: - */ - if (likely(next->task != task)) { - raw_spin_lock_irqsave(&task->pi_lock, flags); - plist_add(&next->pi_list_entry, &task->pi_waiters); - __rt_mutex_adjust_prio(task); - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - } - return 1; -} - -/* * Try to take an rt-mutex * - * This fails - * - when the lock has a real owner - * - when a different pending owner exists and has higher priority than current - * * Must be called with lock->wait_lock held. + * + * @lock: the lock to be acquired. + * @task: the task which wants to acquire the lock + * @waiter: the waiter that is queued to the lock's wait list. (could be NULL) */ -static int try_to_take_rt_mutex(struct rt_mutex *lock) +static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) { /* * We have to be careful here if the atomic speedups are @@ -390,15 +331,52 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock) */ mark_rt_mutex_waiters(lock); - if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current)) + if (rt_mutex_owner(lock)) return 0; + /* + * It will get the lock because of one of these conditions: + * 1) there is no waiter + * 2) higher priority than waiters + * 3) it is top waiter + */ + if (rt_mutex_has_waiters(lock)) { + if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) { + if (!waiter || waiter != rt_mutex_top_waiter(lock)) + return 0; + } + } + + if (waiter || rt_mutex_has_waiters(lock)) { + unsigned long flags; + struct rt_mutex_waiter *top; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + + /* remove the queued waiter. */ + if (waiter) { + plist_del(&waiter->list_entry, &lock->wait_list); + task->pi_blocked_on = NULL; + } + + /* + * We have to enqueue the top waiter(if it exists) into + * task->pi_waiters list. + */ + if (rt_mutex_has_waiters(lock)) { + top = rt_mutex_top_waiter(lock); + top->pi_list_entry.prio = top->list_entry.prio; + plist_add(&top->pi_list_entry, &task->pi_waiters); + } + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + } + /* We got the lock. */ debug_rt_mutex_lock(lock); - rt_mutex_set_owner(lock, current, 0); + rt_mutex_set_owner(lock, task); - rt_mutex_deadlock_account_lock(lock, current); + rt_mutex_deadlock_account_lock(lock, task); return 1; } @@ -436,6 +414,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, raw_spin_unlock_irqrestore(&task->pi_lock, flags); + if (!owner) + return 0; + if (waiter == rt_mutex_top_waiter(lock)) { raw_spin_lock_irqsave(&owner->pi_lock, flags); plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters); @@ -472,21 +453,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, /* * Wake up the next waiter on the lock. * - * Remove the top waiter from the current tasks waiter list and from - * the lock waiter list. Set it as pending owner. Then wake it up. + * Remove the top waiter from the current tasks waiter list and wake it up. * * Called with lock->wait_lock held. */ static void wakeup_next_waiter(struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; - struct task_struct *pendowner; unsigned long flags; raw_spin_lock_irqsave(¤t->pi_lock, flags); waiter = rt_mutex_top_waiter(lock); - plist_del(&waiter->list_entry, &lock->wait_list); /* * Remove it from current->pi_waiters. We do not adjust a @@ -495,43 +473,19 @@ static void wakeup_next_waiter(struct rt_mutex *lock) * lock->wait_lock. */ plist_del(&waiter->pi_list_entry, ¤t->pi_waiters); - pendowner = waiter->task; - waiter->task = NULL; - rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING); + rt_mutex_set_owner(lock, NULL); raw_spin_unlock_irqrestore(¤t->pi_lock, flags); - /* - * Clear the pi_blocked_on variable and enqueue a possible - * waiter into the pi_waiters list of the pending owner. This - * prevents that in case the pending owner gets unboosted a - * waiter with higher priority than pending-owner->normal_prio - * is blocked on the unboosted (pending) owner. - */ - raw_spin_lock_irqsave(&pendowner->pi_lock, flags); - - WARN_ON(!pendowner->pi_blocked_on); - WARN_ON(pendowner->pi_blocked_on != waiter); - WARN_ON(pendowner->pi_blocked_on->lock != lock); - - pendowner->pi_blocked_on = NULL; - - if (rt_mutex_has_waiters(lock)) { - struct rt_mutex_waiter *next; - - next = rt_mutex_top_waiter(lock); - plist_add(&next->pi_list_entry, &pendowner->pi_waiters); - } - raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags); - - wake_up_process(pendowner); + wake_up_process(waiter->task); } /* - * Remove a waiter from a lock + * Remove a waiter from a lock and give up * - * Must be called with lock->wait_lock held + * Must be called with lock->wait_lock held and + * have just failed to try_to_take_rt_mutex(). */ static void remove_waiter(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) @@ -543,11 +497,13 @@ static void remove_waiter(struct rt_mutex *lock, raw_spin_lock_irqsave(¤t->pi_lock, flags); plist_del(&waiter->list_entry, &lock->wait_list); - waiter->task = NULL; current->pi_blocked_on = NULL; raw_spin_unlock_irqrestore(¤t->pi_lock, flags); - if (first && owner != current) { + if (!owner) + return; + + if (first) { raw_spin_lock_irqsave(&owner->pi_lock, flags); @@ -614,21 +570,19 @@ void rt_mutex_adjust_pi(struct task_struct *task) * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter - * @detect_deadlock: passed to task_blocks_on_rt_mutex * * lock->wait_lock must be held by the caller. */ static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, - struct rt_mutex_waiter *waiter, - int detect_deadlock) + struct rt_mutex_waiter *waiter) { int ret = 0; for (;;) { /* Try to acquire the lock: */ - if (try_to_take_rt_mutex(lock)) + if (try_to_take_rt_mutex(lock, current, waiter)) break; /* @@ -645,39 +599,11 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, break; } - /* - * waiter->task is NULL the first time we come here and - * when we have been woken up by the previous owner - * but the lock got stolen by a higher prio task. - */ - if (!waiter->task) { - ret = task_blocks_on_rt_mutex(lock, waiter, current, - detect_deadlock); - /* - * If we got woken up by the owner then start loop - * all over without going into schedule to try - * to get the lock now: - */ - if (unlikely(!waiter->task)) { - /* - * Reset the return value. We might - * have returned with -EDEADLK and the - * owner released the lock while we - * were walking the pi chain. - */ - ret = 0; - continue; - } - if (unlikely(ret)) - break; - } - raw_spin_unlock(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); - if (waiter->task) - schedule_rt_mutex(lock); + schedule_rt_mutex(lock); raw_spin_lock(&lock->wait_lock); set_current_state(state); @@ -698,12 +624,11 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, int ret = 0; debug_rt_mutex_init_waiter(&waiter); - waiter.task = NULL; raw_spin_lock(&lock->wait_lock); /* Try to acquire the lock again: */ - if (try_to_take_rt_mutex(lock)) { + if (try_to_take_rt_mutex(lock, current, NULL)) { raw_spin_unlock(&lock->wait_lock); return 0; } @@ -717,12 +642,14 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, timeout->task = NULL; } - ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, - detect_deadlock); + ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock); + + if (likely(!ret)) + ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); set_current_state(TASK_RUNNING); - if (unlikely(waiter.task)) + if (unlikely(ret)) remove_waiter(lock, &waiter); /* @@ -737,14 +664,6 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, if (unlikely(timeout)) hrtimer_cancel(&timeout->timer); - /* - * Readjust priority, when we did not get the lock. We might - * have been the pending owner and boosted. Since we did not - * take the lock, the PI boost has to go. - */ - if (unlikely(ret)) - rt_mutex_adjust_prio(current); - debug_rt_mutex_free_waiter(&waiter); return ret; @@ -762,7 +681,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock) if (likely(rt_mutex_owner(lock) != current)) { - ret = try_to_take_rt_mutex(lock); + ret = try_to_take_rt_mutex(lock, current, NULL); /* * try_to_take_rt_mutex() sets the lock waiters * bit unconditionally. Clean this up. @@ -992,7 +911,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, { __rt_mutex_init(lock, NULL); debug_rt_mutex_proxy_lock(lock, proxy_owner); - rt_mutex_set_owner(lock, proxy_owner, 0); + rt_mutex_set_owner(lock, proxy_owner); rt_mutex_deadlock_account_lock(lock, proxy_owner); } @@ -1008,7 +927,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, struct task_struct *proxy_owner) { debug_rt_mutex_proxy_unlock(lock); - rt_mutex_set_owner(lock, NULL, 0); + rt_mutex_set_owner(lock, NULL); rt_mutex_deadlock_account_unlock(proxy_owner); } @@ -1034,20 +953,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, raw_spin_lock(&lock->wait_lock); - mark_rt_mutex_waiters(lock); - - if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) { - /* We got the lock for task. */ - debug_rt_mutex_lock(lock); - rt_mutex_set_owner(lock, task, 0); + if (try_to_take_rt_mutex(lock, task, NULL)) { raw_spin_unlock(&lock->wait_lock); - rt_mutex_deadlock_account_lock(lock, task); return 1; } ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); - if (ret && !waiter->task) { + if (ret && !rt_mutex_owner(lock)) { /* * Reset the return value. We might have * returned with -EDEADLK and the owner @@ -1056,6 +969,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, */ ret = 0; } + + if (unlikely(ret)) + remove_waiter(lock, waiter); + raw_spin_unlock(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); @@ -1110,12 +1027,11 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, set_current_state(TASK_INTERRUPTIBLE); - ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, - detect_deadlock); + ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); set_current_state(TASK_RUNNING); - if (unlikely(waiter->task)) + if (unlikely(ret)) remove_waiter(lock, waiter); /* @@ -1126,13 +1042,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, raw_spin_unlock(&lock->wait_lock); - /* - * Readjust priority, when we did not get the lock. We might have been - * the pending owner and boosted. Since we did not take the lock, the - * PI boost has to go. - */ - if (unlikely(ret)) - rt_mutex_adjust_prio(current); - return ret; } diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h index 97a2f81..53a66c8 100644 --- a/kernel/rtmutex_common.h +++ b/kernel/rtmutex_common.h @@ -91,9 +91,8 @@ task_top_pi_waiter(struct task_struct *p) /* * lock->owner state tracking: */ -#define RT_MUTEX_OWNER_PENDING 1UL -#define RT_MUTEX_HAS_WAITERS 2UL -#define RT_MUTEX_OWNER_MASKALL 3UL +#define RT_MUTEX_HAS_WAITERS 1UL +#define RT_MUTEX_OWNER_MASKALL 1UL static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) { @@ -101,17 +100,6 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL); } -static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock) -{ - return (struct task_struct *) - ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS); -} - -static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock) -{ - return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING; -} - /* * PI-futex support (proxy locking functions, etc.): */ diff --git a/kernel/sched.c b/kernel/sched.c index 18d38e4..27125e4 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -324,7 +324,7 @@ struct cfs_rq { * 'curr' points to currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). */ - struct sched_entity *curr, *next, *last; + struct sched_entity *curr, *next, *last, *skip; unsigned int nr_spread_over; @@ -606,9 +606,6 @@ static inline struct task_group *task_group(struct task_struct *p) struct task_group *tg; struct cgroup_subsys_state *css; - if (p->flags & PF_EXITING) - return &root_task_group; - css = task_subsys_state_check(p, cpu_cgroup_subsys_id, lockdep_is_held(&task_rq(p)->lock)); tg = container_of(css, struct task_group, css); @@ -1686,6 +1683,39 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) __release(rq2->lock); } +#else /* CONFIG_SMP */ + +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) +{ + BUG_ON(!irqs_disabled()); + BUG_ON(rq1 != rq2); + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + BUG_ON(rq1 != rq2); + raw_spin_unlock(&rq1->lock); + __release(rq2->lock); +} + #endif static void calc_load_account_idle(struct rq *this_rq); @@ -1880,7 +1910,7 @@ void account_system_vtime(struct task_struct *curr) */ if (hardirq_count()) __this_cpu_add(cpu_hardirq_time, delta); - else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) __this_cpu_add(cpu_softirq_time, delta); irq_time_write_end(); @@ -1920,8 +1950,40 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) sched_rt_avg_update(rq, irq_delta); } +static int irqtime_account_hi_update(void) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_hardirq_time); + if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq)) + ret = 1; + local_irq_restore(flags); + return ret; +} + +static int irqtime_account_si_update(void) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_softirq_time); + if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq)) + ret = 1; + local_irq_restore(flags); + return ret; +} + #else /* CONFIG_IRQ_TIME_ACCOUNTING */ +#define sched_clock_irqtime (0) + static void update_rq_clock_task(struct rq *rq, s64 delta) { rq->clock_task += delta; @@ -2025,14 +2087,14 @@ inline int task_curr(const struct task_struct *p) static inline void check_class_changed(struct rq *rq, struct task_struct *p, const struct sched_class *prev_class, - int oldprio, int running) + int oldprio) { if (prev_class != p->sched_class) { if (prev_class->switched_from) - prev_class->switched_from(rq, p, running); - p->sched_class->switched_to(rq, p, running); - } else - p->sched_class->prio_changed(rq, p, oldprio, running); + prev_class->switched_from(rq, p); + p->sched_class->switched_to(rq, p); + } else if (oldprio != p->prio) + p->sched_class->prio_changed(rq, p, oldprio); } static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) @@ -2265,27 +2327,6 @@ void kick_process(struct task_struct *p) EXPORT_SYMBOL_GPL(kick_process); #endif /* CONFIG_SMP */ -/** - * task_oncpu_function_call - call a function on the cpu on which a task runs - * @p: the task to evaluate - * @func: the function to be called - * @info: the function call argument - * - * Calls the function @func when the task is currently running. This might - * be on the current CPU, which just calls the function directly - */ -void task_oncpu_function_call(struct task_struct *p, - void (*func) (void *info), void *info) -{ - int cpu; - - preempt_disable(); - cpu = task_cpu(p); - if (task_curr(p)) - smp_call_function_single(cpu, func, info, 1); - preempt_enable(); -} - #ifdef CONFIG_SMP /* * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. @@ -2566,6 +2607,7 @@ static void __sched_fork(struct task_struct *p) p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; + p->se.vruntime = 0; #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); @@ -2776,9 +2818,12 @@ static inline void prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { + sched_info_switch(prev, next); + perf_event_task_sched_out(prev, next); fire_sched_out_preempt_notifiers(prev, next); prepare_lock_switch(rq, next); prepare_arch_switch(next); + trace_sched_switch(prev, next); } /** @@ -2911,7 +2956,7 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); - trace_sched_switch(prev, next); + mm = next->mm; oldmm = prev->active_mm; /* @@ -3568,6 +3613,32 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, } /* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, cputime64_t *target_cputime64) +{ + cputime64_t tmp = cputime_to_cputime64(cputime); + + /* Add system time to process. */ + p->stime = cputime_add(p->stime, cputime); + p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + *target_cputime64 = cputime64_add(*target_cputime64, tmp); + cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); + + /* Account for system time used */ + acct_update_integrals(p); +} + +/* * Account system cpu time to a process. * @p: the process that the cpu time gets accounted to * @hardirq_offset: the offset to subtract from hardirq_count() @@ -3578,36 +3649,26 @@ void account_system_time(struct task_struct *p, int hardirq_offset, cputime_t cputime, cputime_t cputime_scaled) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t tmp; + cputime64_t *target_cputime64; if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { account_guest_time(p, cputime, cputime_scaled); return; } - /* Add system time to process. */ - p->stime = cputime_add(p->stime, cputime); - p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); - account_group_system_time(p, cputime); - - /* Add system time to cpustat. */ - tmp = cputime_to_cputime64(cputime); if (hardirq_count() - hardirq_offset) - cpustat->irq = cputime64_add(cpustat->irq, tmp); + target_cputime64 = &cpustat->irq; else if (in_serving_softirq()) - cpustat->softirq = cputime64_add(cpustat->softirq, tmp); + target_cputime64 = &cpustat->softirq; else - cpustat->system = cputime64_add(cpustat->system, tmp); + target_cputime64 = &cpustat->system; - cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); - - /* Account for system time used */ - acct_update_integrals(p); + __account_system_time(p, cputime, cputime_scaled, target_cputime64); } /* * Account for involuntary wait time. - * @steal: the cpu time spent in involuntary wait + * @cputime: the cpu time spent in involuntary wait */ void account_steal_time(cputime_t cputime) { @@ -3635,6 +3696,73 @@ void account_idle_time(cputime_t cputime) #ifndef CONFIG_VIRT_CPU_ACCOUNTING +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * Account a tick to a process and cpustat + * @p: the process that the cpu time gets accounted to + * @user_tick: is the tick from userspace + * @rq: the pointer to rq + * + * Tick demultiplexing follows the order + * - pending hardirq update + * - pending softirq update + * - user_time + * - idle_time + * - system time + * - check for guest_time + * - else account as system_time + * + * Check for hardirq is done both for system and user time as there is + * no timer going off while we are on hardirq and hence we may never get an + * opportunity to update it solely in system time. + * p->stime and friends are only updated on system time and not on irq + * softirq as those do not count in task exec_runtime any more. + */ +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + + if (irqtime_account_hi_update()) { + cpustat->irq = cputime64_add(cpustat->irq, tmp); + } else if (irqtime_account_si_update()) { + cpustat->softirq = cputime64_add(cpustat->softirq, tmp); + } else if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + * Also, p->stime needs to be updated for ksoftirqd. + */ + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + &cpustat->softirq); + } else if (user_tick) { + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else if (p == rq->idle) { + account_idle_time(cputime_one_jiffy); + } else if (p->flags & PF_VCPU) { /* System time or guest time */ + account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else { + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + &cpustat->system); + } +} + +static void irqtime_account_idle_ticks(int ticks) +{ + int i; + struct rq *rq = this_rq(); + + for (i = 0; i < ticks; i++) + irqtime_account_process_tick(current, 0, rq); +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ +static void irqtime_account_idle_ticks(int ticks) {} +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) {} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + /* * Account a single tick of cpu time. * @p: the process that the cpu time gets accounted to @@ -3645,6 +3773,11 @@ void account_process_tick(struct task_struct *p, int user_tick) cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq); + return; + } + if (user_tick) account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) @@ -3670,6 +3803,12 @@ void account_steal_ticks(unsigned long ticks) */ void account_idle_ticks(unsigned long ticks) { + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + account_idle_time(jiffies_to_cputime(ticks)); } @@ -3989,9 +4128,6 @@ need_resched_nonpreemptible: rq->skip_clock_update = 0; if (likely(prev != next)) { - sched_info_switch(prev, next); - perf_event_task_sched_out(prev, next); - rq->nr_switches++; rq->curr = next; ++*switch_count; @@ -4213,6 +4349,7 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) { __wake_up_common(q, mode, 1, 0, key); } +EXPORT_SYMBOL_GPL(__wake_up_locked_key); /** * __wake_up_sync_key - wake up threads blocked on a waitqueue. @@ -4570,11 +4707,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); - if (on_rq) { + if (on_rq) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); - check_class_changed(rq, p, prev_class, oldprio, running); - } + check_class_changed(rq, p, prev_class, oldprio); task_rq_unlock(rq, &flags); } @@ -4822,12 +4958,15 @@ recheck: param->sched_priority > rlim_rtprio) return -EPERM; } + /* - * Like positive nice levels, dont allow tasks to - * move out of SCHED_IDLE either: + * Treat SCHED_IDLE as nice 20. Only allow a switch to + * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ - if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) - return -EPERM; + if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { + if (!can_nice(p, TASK_NICE(p))) + return -EPERM; + } /* can't change other user's priorities */ if (!check_same_owner(p)) @@ -4902,11 +5041,10 @@ recheck: if (running) p->sched_class->set_curr_task(rq); - if (on_rq) { + if (on_rq) activate_task(rq, p, 0); - check_class_changed(rq, p, prev_class, oldprio, running); - } + check_class_changed(rq, p, prev_class, oldprio); __task_rq_unlock(rq); raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -5323,6 +5461,65 @@ void __sched yield(void) } EXPORT_SYMBOL(yield); +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * Returns true if we indeed boosted the target task. + */ +bool __sched yield_to(struct task_struct *p, bool preempt) +{ + struct task_struct *curr = current; + struct rq *rq, *p_rq; + unsigned long flags; + bool yielded = 0; + + local_irq_save(flags); + rq = this_rq(); + +again: + p_rq = task_rq(p); + double_rq_lock(rq, p_rq); + while (task_rq(p) != p_rq) { + double_rq_unlock(rq, p_rq); + goto again; + } + + if (!curr->sched_class->yield_to_task) + goto out; + + if (curr->sched_class != p->sched_class) + goto out; + + if (task_running(p_rq, p) || p->state) + goto out; + + yielded = curr->sched_class->yield_to_task(rq, p, preempt); + if (yielded) { + schedstat_inc(rq, yld_count); + /* + * Make p's CPU reschedule; pick_next_entity takes care of + * fairness. + */ + if (preempt && rq != p_rq) + resched_task(p_rq->curr); + } + +out: + double_rq_unlock(rq, p_rq); + local_irq_restore(flags); + + if (yielded) + schedule(); + + return yielded; +} +EXPORT_SYMBOL_GPL(yield_to); + /* * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. @@ -5571,7 +5768,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; - ftrace_graph_init_task(idle); + ftrace_graph_init_idle_task(idle, cpu); } /* @@ -7796,6 +7993,10 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) INIT_LIST_HEAD(&cfs_rq->tasks); #ifdef CONFIG_FAIR_GROUP_SCHED cfs_rq->rq = rq; + /* allow initial update_cfs_load() to truncate */ +#ifdef CONFIG_SMP + cfs_rq->load_stamp = 1; +#endif #endif cfs_rq->min_vruntime = (u64)(-(1LL << 20)); } @@ -8109,6 +8310,8 @@ EXPORT_SYMBOL(__might_sleep); #ifdef CONFIG_MAGIC_SYSRQ static void normalize_task(struct rq *rq, struct task_struct *p) { + const struct sched_class *prev_class = p->sched_class; + int old_prio = p->prio; int on_rq; on_rq = p->se.on_rq; @@ -8119,6 +8322,8 @@ static void normalize_task(struct rq *rq, struct task_struct *p) activate_task(rq, p, 0); resched_task(rq->curr); } + + check_class_changed(rq, p, prev_class, old_prio); } void normalize_rt_tasks(void) @@ -8510,7 +8715,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) /* Propagate contribution to hierarchy */ raw_spin_lock_irqsave(&rq->lock, flags); for_each_sched_entity(se) - update_cfs_shares(group_cfs_rq(se), 0); + update_cfs_shares(group_cfs_rq(se)); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -8884,7 +9089,8 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, } static void -cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task) +cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup *old_cgrp, struct task_struct *task) { /* * cgroup_exit() is called in the copy_process() failure path. diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c index 9fb6562..5946ac5 100644 --- a/kernel/sched_autogroup.c +++ b/kernel/sched_autogroup.c @@ -12,7 +12,6 @@ static atomic_t autogroup_seq_nr; static void __init autogroup_init(struct task_struct *init_task) { autogroup_default.tg = &root_task_group; - root_task_group.autogroup = &autogroup_default; kref_init(&autogroup_default.kref); init_rwsem(&autogroup_default.lock); init_task->signal->autogroup = &autogroup_default; @@ -130,7 +129,7 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg) static inline bool task_group_is_autogroup(struct task_group *tg) { - return tg != &root_task_group && tg->autogroup; + return !!tg->autogroup; } static inline struct task_group * @@ -161,11 +160,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) p->signal->autogroup = autogroup_kref_get(ag); + if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled)) + goto out; + t = p; do { sched_move_task(t); } while_each_thread(p, t); +out: unlock_task_sighand(p, &flags); autogroup_kref_put(prev); } @@ -247,10 +250,14 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) { struct autogroup *ag = autogroup_task_get(p); + if (!task_group_is_autogroup(ag->tg)) + goto out; + down_read(&ag->lock); seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice); up_read(&ag->lock); +out: autogroup_kref_put(ag); } #endif /* CONFIG_PROC_FS */ @@ -258,9 +265,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m) #ifdef CONFIG_SCHED_DEBUG static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) { - int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled); - - if (!enabled || !tg->autogroup) + if (!task_group_is_autogroup(tg)) return 0; return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h index 7b859ff..0557705 100644 --- a/kernel/sched_autogroup.h +++ b/kernel/sched_autogroup.h @@ -1,6 +1,11 @@ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup { + /* + * reference doesn't mean how many thread attach to this + * autogroup now. It just stands for the number of task + * could use this autogroup. + */ struct kref kref; struct task_group *tg; struct rw_semaphore lock; diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index eb6cb8e..7bacd83 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -179,7 +179,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) raw_spin_lock_irqsave(&rq->lock, flags); if (cfs_rq->rb_leftmost) - MIN_vruntime = (__pick_next_entity(cfs_rq))->vruntime; + MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime; last = __pick_last_entity(cfs_rq); if (last) max_vruntime = last->vruntime; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 0c26e2d..3f7ec9e 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -69,14 +69,6 @@ static unsigned int sched_nr_latency = 8; unsigned int sysctl_sched_child_runs_first __read_mostly; /* - * sys_sched_yield() compat mode - * - * This option switches the agressive yield implementation of the - * old scheduler back on. - */ -unsigned int __read_mostly sysctl_sched_compat_yield; - -/* * SCHED_OTHER wake-up granularity. * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) * @@ -419,7 +411,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) rb_erase(&se->run_node, &cfs_rq->tasks_timeline); } -static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq) +static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) { struct rb_node *left = cfs_rq->rb_leftmost; @@ -429,6 +421,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq) return rb_entry(left, struct sched_entity, run_node); } +static struct sched_entity *__pick_next_entity(struct sched_entity *se) +{ + struct rb_node *next = rb_next(&se->run_node); + + if (!next) + return NULL; + + return rb_entry(next, struct sched_entity, run_node); +} + +#ifdef CONFIG_SCHED_DEBUG static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) { struct rb_node *last = rb_last(&cfs_rq->tasks_timeline); @@ -443,7 +446,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) * Scheduling class statistics methods: */ -#ifdef CONFIG_SCHED_DEBUG int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -540,7 +542,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update); -static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta); +static void update_cfs_shares(struct cfs_rq *cfs_rq); /* * Update the current task's runtime statistics. Skip current tasks that @@ -733,6 +735,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update) now - cfs_rq->load_last > 4 * period) { cfs_rq->load_period = 0; cfs_rq->load_avg = 0; + delta = period - 1; } cfs_rq->load_stamp = now; @@ -763,16 +766,15 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update) list_del_leaf_cfs_rq(cfs_rq); } -static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg, - long weight_delta) +static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) { long load_weight, load, shares; - load = cfs_rq->load.weight + weight_delta; + load = cfs_rq->load.weight; load_weight = atomic_read(&tg->load_weight); - load_weight -= cfs_rq->load_contribution; load_weight += load; + load_weight -= cfs_rq->load_contribution; shares = (tg->shares * load); if (load_weight) @@ -790,7 +792,7 @@ static void update_entity_shares_tick(struct cfs_rq *cfs_rq) { if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) { update_cfs_load(cfs_rq, 0); - update_cfs_shares(cfs_rq, 0); + update_cfs_shares(cfs_rq); } } # else /* CONFIG_SMP */ @@ -798,8 +800,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update) { } -static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg, - long weight_delta) +static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) { return tg->shares; } @@ -824,7 +825,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, account_entity_enqueue(cfs_rq, se); } -static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta) +static void update_cfs_shares(struct cfs_rq *cfs_rq) { struct task_group *tg; struct sched_entity *se; @@ -838,7 +839,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta) if (likely(se->load.weight == tg->shares)) return; #endif - shares = calc_cfs_shares(cfs_rq, tg, weight_delta); + shares = calc_cfs_shares(cfs_rq, tg); reweight_entity(cfs_rq_of(se), se, shares); } @@ -847,7 +848,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update) { } -static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta) +static inline void update_cfs_shares(struct cfs_rq *cfs_rq) { } @@ -978,8 +979,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) */ update_curr(cfs_rq); update_cfs_load(cfs_rq, 0); - update_cfs_shares(cfs_rq, se->load.weight); account_entity_enqueue(cfs_rq, se); + update_cfs_shares(cfs_rq); if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); @@ -996,19 +997,49 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) list_add_leaf_cfs_rq(cfs_rq); } -static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +static void __clear_buddies_last(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->last == se) + cfs_rq->last = NULL; + else + break; + } +} + +static void __clear_buddies_next(struct sched_entity *se) { - if (!se || cfs_rq->last == se) - cfs_rq->last = NULL; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->next == se) + cfs_rq->next = NULL; + else + break; + } +} - if (!se || cfs_rq->next == se) - cfs_rq->next = NULL; +static void __clear_buddies_skip(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->skip == se) + cfs_rq->skip = NULL; + else + break; + } } static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) { - for_each_sched_entity(se) - __clear_buddies(cfs_rq_of(se), se); + if (cfs_rq->last == se) + __clear_buddies_last(se); + + if (cfs_rq->next == se) + __clear_buddies_next(se); + + if (cfs_rq->skip == se) + __clear_buddies_skip(se); } static void @@ -1041,7 +1072,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_cfs_load(cfs_rq, 0); account_entity_dequeue(cfs_rq, se); update_min_vruntime(cfs_rq); - update_cfs_shares(cfs_rq, 0); + update_cfs_shares(cfs_rq); /* * Normalize the entity after updating the min_vruntime because the @@ -1084,7 +1115,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) return; if (cfs_rq->nr_running > 1) { - struct sched_entity *se = __pick_next_entity(cfs_rq); + struct sched_entity *se = __pick_first_entity(cfs_rq); s64 delta = curr->vruntime - se->vruntime; if (delta < 0) @@ -1128,13 +1159,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) static int wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); +/* + * Pick the next process, keeping these things in mind, in this order: + * 1) keep things fair between processes/task groups + * 2) pick the "next" process, since someone really wants that to run + * 3) pick the "last" process, for cache locality + * 4) do not run the "skip" process, if something else is available + */ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) { - struct sched_entity *se = __pick_next_entity(cfs_rq); + struct sched_entity *se = __pick_first_entity(cfs_rq); struct sched_entity *left = se; - if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) - se = cfs_rq->next; + /* + * Avoid running the skip buddy, if running something else can + * be done without getting too unfair. + */ + if (cfs_rq->skip == se) { + struct sched_entity *second = __pick_next_entity(se); + if (second && wakeup_preempt_entity(second, left) < 1) + se = second; + } /* * Prefer last buddy, try to return the CPU to a preempted task. @@ -1142,6 +1187,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) se = cfs_rq->last; + /* + * Someone really wants this to run. If it's not unfair, run it. + */ + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + se = cfs_rq->next; + clear_buddies(cfs_rq, se); return se; @@ -1282,7 +1333,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq = cfs_rq_of(se); update_cfs_load(cfs_rq, 0); - update_cfs_shares(cfs_rq, 0); + update_cfs_shares(cfs_rq); } hrtick_update(rq); @@ -1312,58 +1363,12 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq = cfs_rq_of(se); update_cfs_load(cfs_rq, 0); - update_cfs_shares(cfs_rq, 0); + update_cfs_shares(cfs_rq); } hrtick_update(rq); } -/* - * sched_yield() support is very simple - we dequeue and enqueue. - * - * If compat_yield is turned on then we requeue to the end of the tree. - */ -static void yield_task_fair(struct rq *rq) -{ - struct task_struct *curr = rq->curr; - struct cfs_rq *cfs_rq = task_cfs_rq(curr); - struct sched_entity *rightmost, *se = &curr->se; - - /* - * Are we the only task in the tree? - */ - if (unlikely(cfs_rq->nr_running == 1)) - return; - - clear_buddies(cfs_rq, se); - - if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) { - update_rq_clock(rq); - /* - * Update run-time statistics of the 'current'. - */ - update_curr(cfs_rq); - - return; - } - /* - * Find the rightmost entry in the rbtree: - */ - rightmost = __pick_last_entity(cfs_rq); - /* - * Already in the rightmost position? - */ - if (unlikely(!rightmost || entity_before(rightmost, se))) - return; - - /* - * Minimally necessary key value to be last in the tree: - * Upon rescheduling, sched_class::put_prev_task() will place - * 'current' within the tree based on its new key value. - */ - se->vruntime = rightmost->vruntime + 1; -} - #ifdef CONFIG_SMP static void task_waking_fair(struct rq *rq, struct task_struct *p) @@ -1834,6 +1839,14 @@ static void set_next_buddy(struct sched_entity *se) } } +static void set_skip_buddy(struct sched_entity *se) +{ + if (likely(task_of(se)->policy != SCHED_IDLE)) { + for_each_sched_entity(se) + cfs_rq_of(se)->skip = se; + } +} + /* * Preempt the current task with a newly woken task if needed: */ @@ -1857,16 +1870,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (test_tsk_need_resched(curr)) return; + /* Idle tasks are by definition preempted by non-idle tasks. */ + if (unlikely(curr->policy == SCHED_IDLE) && + likely(p->policy != SCHED_IDLE)) + goto preempt; + /* - * Batch and idle tasks do not preempt (their preemption is driven by - * the tick): + * Batch and idle tasks do not preempt non-idle tasks (their preemption + * is driven by the tick): */ if (unlikely(p->policy != SCHED_NORMAL)) return; - /* Idle tasks are by definition preempted by everybody. */ - if (unlikely(curr->policy == SCHED_IDLE)) - goto preempt; if (!sched_feat(WAKEUP_PREEMPT)) return; @@ -1932,6 +1947,51 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) } } +/* + * sched_yield() is very simple + * + * The magic of dealing with the ->skip buddy is in pick_next_entity. + */ +static void yield_task_fair(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + struct sched_entity *se = &curr->se; + + /* + * Are we the only task in the tree? + */ + if (unlikely(rq->nr_running == 1)) + return; + + clear_buddies(cfs_rq, se); + + if (curr->policy != SCHED_BATCH) { + update_rq_clock(rq); + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + } + + set_skip_buddy(se); +} + +static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt) +{ + struct sched_entity *se = &p->se; + + if (!se->on_rq) + return false; + + /* Tell the scheduler that we'd really like pse to run next. */ + set_next_buddy(se); + + yield_task_fair(rq); + + return true; +} + #ifdef CONFIG_SMP /************************************************** * Fair scheduling class load-balancing methods: @@ -2123,7 +2183,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu) * We need to update shares after updating tg->load_weight in * order to adjust the weight of groups with long running tasks. */ - update_cfs_shares(cfs_rq, 0); + update_cfs_shares(cfs_rq); raw_spin_unlock_irqrestore(&rq->lock, flags); @@ -2610,7 +2670,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) * @this_cpu: Cpu for which load balance is currently performed. * @idle: Idle status of this_cpu * @load_idx: Load index of sched_domain of this_cpu for load calc. - * @sd_idle: Idle status of the sched_domain containing group. * @local_group: Does group contain this_cpu. * @cpus: Set of cpus considered for load balancing. * @balance: Should we balance. @@ -2618,7 +2677,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) */ static inline void update_sg_lb_stats(struct sched_domain *sd, struct sched_group *group, int this_cpu, - enum cpu_idle_type idle, int load_idx, int *sd_idle, + enum cpu_idle_type idle, int load_idx, int local_group, const struct cpumask *cpus, int *balance, struct sg_lb_stats *sgs) { @@ -2638,9 +2697,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, for_each_cpu_and(i, sched_group_cpus(group), cpus) { struct rq *rq = cpu_rq(i); - if (*sd_idle && rq->nr_running) - *sd_idle = 0; - /* Bias balancing toward cpus of our domain */ if (local_group) { if (idle_cpu(i) && !first_idle_cpu) { @@ -2685,7 +2741,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, /* * Consider the group unbalanced when the imbalance is larger - * than the average weight of two tasks. + * than the average weight of a task. * * APZ: with cgroup the avg task weight can vary wildly and * might not be a suitable number - should we keep a @@ -2695,7 +2751,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, if (sgs->sum_nr_running) avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1) + if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1) sgs->group_imb = 1; sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); @@ -2755,15 +2811,13 @@ static bool update_sd_pick_busiest(struct sched_domain *sd, * @sd: sched_domain whose statistics are to be updated. * @this_cpu: Cpu for which load balance is currently performed. * @idle: Idle status of this_cpu - * @sd_idle: Idle status of the sched_domain containing sg. * @cpus: Set of cpus considered for load balancing. * @balance: Should we balance. * @sds: variable to hold the statistics for this sched_domain. */ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, - enum cpu_idle_type idle, int *sd_idle, - const struct cpumask *cpus, int *balance, - struct sd_lb_stats *sds) + enum cpu_idle_type idle, const struct cpumask *cpus, + int *balance, struct sd_lb_stats *sds) { struct sched_domain *child = sd->child; struct sched_group *sg = sd->groups; @@ -2781,7 +2835,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg)); memset(&sgs, 0, sizeof(sgs)); - update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle, + update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, local_group, cpus, balance, &sgs); if (local_group && !(*balance)) @@ -3033,7 +3087,6 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, * @imbalance: Variable which stores amount of weighted load which should * be moved to restore balance/put a group to idle. * @idle: The idle status of this_cpu. - * @sd_idle: The idleness of sd * @cpus: The set of CPUs under consideration for load-balancing. * @balance: Pointer to a variable indicating if this_cpu * is the appropriate cpu to perform load balancing at this_level. @@ -3046,7 +3099,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, static struct sched_group * find_busiest_group(struct sched_domain *sd, int this_cpu, unsigned long *imbalance, enum cpu_idle_type idle, - int *sd_idle, const struct cpumask *cpus, int *balance) + const struct cpumask *cpus, int *balance) { struct sd_lb_stats sds; @@ -3056,22 +3109,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, * Compute the various statistics relavent for load balancing at * this level. */ - update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, - balance, &sds); - - /* Cases where imbalance does not exist from POV of this_cpu */ - /* 1) this_cpu is not the appropriate cpu to perform load balancing - * at this level. - * 2) There is no busy sibling group to pull from. - * 3) This group is the busiest group. - * 4) This group is more busy than the avg busieness at this - * sched_domain. - * 5) The imbalance is within the specified limit. - * - * Note: when doing newidle balance, if the local group has excess - * capacity (i.e. nr_running < group_capacity) and the busiest group - * does not have any capacity, we force a load balance to pull tasks - * to the local group. In this case, we skip past checks 3, 4 and 5. + update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds); + + /* + * this_cpu is not the appropriate cpu to perform load balancing at + * this level. */ if (!(*balance)) goto ret; @@ -3080,41 +3122,55 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, check_asym_packing(sd, &sds, this_cpu, imbalance)) return sds.busiest; + /* There is no busy sibling group to pull tasks from */ if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; - /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ + /* + * If the busiest group is imbalanced the below checks don't + * work because they assumes all things are equal, which typically + * isn't true due to cpus_allowed constraints and the like. + */ + if (sds.group_imb) + goto force_balance; + + /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity && !sds.busiest_has_capacity) goto force_balance; + /* + * If the local group is more busy than the selected busiest group + * don't try and pull any tasks. + */ if (sds.this_load >= sds.max_load) goto out_balanced; + /* + * Don't pull any tasks if this group is already above the domain + * average load. + */ sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; - if (sds.this_load >= sds.avg_load) goto out_balanced; - /* - * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative. - * And to check for busy balance use !idle_cpu instead of - * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE - * even when they are idle. - */ - if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) { - if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) - goto out_balanced; - } else { + if (idle == CPU_IDLE) { /* * This cpu is idle. If the busiest group load doesn't * have more tasks than the number of available cpu's and * there is no imbalance between this and busiest group * wrt to idle cpu's, it is balanced. */ - if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) && + if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) && sds.busiest_nr_running <= sds.busiest_group_weight) goto out_balanced; + } else { + /* + * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use + * imbalance_pct to be conservative. + */ + if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + goto out_balanced; } force_balance: @@ -3193,7 +3249,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, /* Working cpumask for load_balance and load_balance_newidle. */ static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); -static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle, +static int need_active_balance(struct sched_domain *sd, int idle, int busiest_cpu, int this_cpu) { if (idle == CPU_NEWLY_IDLE) { @@ -3225,10 +3281,6 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle, * move_tasks() will succeed. ld_moved will be true and this * active balance code will not be triggered. */ - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return 0; - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) return 0; } @@ -3246,7 +3298,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, int *balance) { - int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; + int ld_moved, all_pinned = 0, active_balance = 0; struct sched_group *group; unsigned long imbalance; struct rq *busiest; @@ -3255,20 +3307,10 @@ static int load_balance(int this_cpu, struct rq *this_rq, cpumask_copy(cpus, cpu_active_mask); - /* - * When power savings policy is enabled for the parent domain, idle - * sibling can pick up load irrespective of busy siblings. In this case, - * let the state of idle sibling percolate up as CPU_IDLE, instead of - * portraying it as CPU_NOT_IDLE. - */ - if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - sd_idle = 1; - schedstat_inc(sd, lb_count[idle]); redo: - group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, + group = find_busiest_group(sd, this_cpu, &imbalance, idle, cpus, balance); if (*balance == 0) @@ -3330,8 +3372,7 @@ redo: if (idle != CPU_NEWLY_IDLE) sd->nr_balance_failed++; - if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest), - this_cpu)) { + if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) { raw_spin_lock_irqsave(&busiest->lock, flags); /* don't kick the active_load_balance_cpu_stop, @@ -3386,10 +3427,6 @@ redo: sd->balance_interval *= 2; } - if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - goto out; out_balanced: @@ -3403,11 +3440,7 @@ out_one_pinned: (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - else - ld_moved = 0; + ld_moved = 0; out: return ld_moved; } @@ -3831,8 +3864,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (load_balance(cpu, rq, sd, idle, &balance)) { /* * We've pulled tasks over so either we're no - * longer idle, or one of our SMT siblings is - * not idle. + * longer idle. */ idle = CPU_NOT_IDLE; } @@ -4079,33 +4111,62 @@ static void task_fork_fair(struct task_struct *p) * Priority of the task has changed. Check to see if we preempt * the current task. */ -static void prio_changed_fair(struct rq *rq, struct task_struct *p, - int oldprio, int running) +static void +prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) { + if (!p->se.on_rq) + return; + /* * Reschedule if we are currently running on this runqueue and * our priority decreased, or if we are not currently running on * this runqueue and our priority is higher than the current's */ - if (running) { + if (rq->curr == p) { if (p->prio > oldprio) resched_task(rq->curr); } else check_preempt_curr(rq, p, 0); } +static void switched_from_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + /* + * Ensure the task's vruntime is normalized, so that when its + * switched back to the fair class the enqueue_entity(.flags=0) will + * do the right thing. + * + * If it was on_rq, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it was !on_rq, then only when + * the task is sleeping will it still have non-normalized vruntime. + */ + if (!se->on_rq && p->state != TASK_RUNNING) { + /* + * Fix up our vruntime so that the current sleep doesn't + * cause 'unlimited' sleep bonus. + */ + place_entity(cfs_rq, se, 0); + se->vruntime -= cfs_rq->min_vruntime; + } +} + /* * We switched to the sched_fair class. */ -static void switched_to_fair(struct rq *rq, struct task_struct *p, - int running) +static void switched_to_fair(struct rq *rq, struct task_struct *p) { + if (!p->se.on_rq) + return; + /* * We were most likely switched from sched_rt, so * kick off the schedule if running, otherwise just see * if we can still preempt the current task. */ - if (running) + if (rq->curr == p) resched_task(rq->curr); else check_preempt_curr(rq, p, 0); @@ -4171,6 +4232,7 @@ static const struct sched_class fair_sched_class = { .enqueue_task = enqueue_task_fair, .dequeue_task = dequeue_task_fair, .yield_task = yield_task_fair, + .yield_to_task = yield_to_task_fair, .check_preempt_curr = check_preempt_wakeup, @@ -4191,6 +4253,7 @@ static const struct sched_class fair_sched_class = { .task_fork = task_fork_fair, .prio_changed = prio_changed_fair, + .switched_from = switched_from_fair, .switched_to = switched_to_fair, .get_rr_interval = get_rr_interval_fair, diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index 9fa0f40..c82f26c1 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -52,31 +52,15 @@ static void set_curr_task_idle(struct rq *rq) { } -static void switched_to_idle(struct rq *rq, struct task_struct *p, - int running) +static void switched_to_idle(struct rq *rq, struct task_struct *p) { - /* Can this actually happen?? */ - if (running) - resched_task(rq->curr); - else - check_preempt_curr(rq, p, 0); + BUG(); } -static void prio_changed_idle(struct rq *rq, struct task_struct *p, - int oldprio, int running) +static void +prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio) { - /* This can happen for hot plug CPUS */ - - /* - * Reschedule if we are currently running on this runqueue and - * our priority decreased, or if we are not currently running on - * this runqueue and our priority is higher than the current's - */ - if (running) { - if (p->prio > oldprio) - resched_task(rq->curr); - } else - check_preempt_curr(rq, p, 0); + BUG(); } static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index c914ec7..db308cb 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -210,11 +210,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { - int this_cpu = smp_processor_id(); struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; struct sched_rt_entity *rt_se; - rt_se = rt_rq->tg->rt_se[this_cpu]; + int cpu = cpu_of(rq_of_rt_rq(rt_rq)); + + rt_se = rt_rq->tg->rt_se[cpu]; if (rt_rq->rt_nr_running) { if (rt_se && !on_rt_rq(rt_se)) @@ -226,10 +227,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { - int this_cpu = smp_processor_id(); struct sched_rt_entity *rt_se; + int cpu = cpu_of(rq_of_rt_rq(rt_rq)); - rt_se = rt_rq->tg->rt_se[this_cpu]; + rt_se = rt_rq->tg->rt_se[cpu]; if (rt_se && on_rt_rq(rt_se)) dequeue_rt_entity(rt_se); @@ -565,8 +566,11 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (rt_rq->rt_time || rt_rq->rt_nr_running) idle = 0; raw_spin_unlock(&rt_rq->rt_runtime_lock); - } else if (rt_rq->rt_nr_running) + } else if (rt_rq->rt_nr_running) { idle = 0; + if (!rt_rq_throttled(rt_rq)) + enqueue = 1; + } if (enqueue) sched_rt_rq_enqueue(rt_rq); @@ -625,7 +629,7 @@ static void update_curr_rt(struct rq *rq) struct rt_rq *rt_rq = rt_rq_of_se(rt_se); u64 delta_exec; - if (!task_has_rt_policy(curr)) + if (curr->sched_class != &rt_sched_class) return; delta_exec = rq->clock_task - curr->se.exec_start; @@ -1595,8 +1599,7 @@ static void rq_offline_rt(struct rq *rq) * When switch from the rt queue, we bring ourselves to a position * that we might want to pull RT tasks from other runqueues. */ -static void switched_from_rt(struct rq *rq, struct task_struct *p, - int running) +static void switched_from_rt(struct rq *rq, struct task_struct *p) { /* * If there are other RT tasks then we will reschedule @@ -1605,7 +1608,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p, * we may need to handle the pulling of RT tasks * now. */ - if (!rq->rt.rt_nr_running) + if (p->se.on_rq && !rq->rt.rt_nr_running) pull_rt_task(rq); } @@ -1624,8 +1627,7 @@ static inline void init_sched_rt_class(void) * with RT tasks. In this case we try to push them off to * other runqueues. */ -static void switched_to_rt(struct rq *rq, struct task_struct *p, - int running) +static void switched_to_rt(struct rq *rq, struct task_struct *p) { int check_resched = 1; @@ -1636,7 +1638,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p, * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (!running) { + if (p->se.on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->rt.overloaded && push_rt_task(rq) && /* Don't resched if we changed runqueues */ @@ -1652,10 +1654,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p, * Priority of the task has changed. This may cause * us to initiate a push or pull. */ -static void prio_changed_rt(struct rq *rq, struct task_struct *p, - int oldprio, int running) +static void +prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (running) { + if (!p->se.on_rq) + return; + + if (rq->curr == p) { #ifdef CONFIG_SMP /* * If our priority decreases while running, we diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 2bf6b47..84ec9bc 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -59,14 +59,13 @@ static void set_curr_task_stop(struct rq *rq) { } -static void switched_to_stop(struct rq *rq, struct task_struct *p, - int running) +static void switched_to_stop(struct rq *rq, struct task_struct *p) { BUG(); /* its impossible to change to this class */ } -static void prio_changed_stop(struct rq *rq, struct task_struct *p, - int oldprio, int running) +static void +prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio) { BUG(); /* how!?, what priority? */ } diff --git a/kernel/softirq.c b/kernel/softirq.c index 68eb5ef..0cee504 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -54,7 +54,7 @@ EXPORT_SYMBOL(irq_stat); static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; -static DEFINE_PER_CPU(struct task_struct *, ksoftirqd); +DEFINE_PER_CPU(struct task_struct *, ksoftirqd); char *softirq_to_name[NR_SOFTIRQS] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", @@ -721,7 +721,6 @@ static int run_ksoftirqd(void * __bind_cpu) { set_current_state(TASK_INTERRUPTIBLE); - current->flags |= PF_KSOFTIRQD; while (!kthread_should_stop()) { preempt_disable(); if (!local_softirq_pending()) { diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index c782fe9..25cc41c 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -186,3 +186,8 @@ cond_syscall(sys_perf_event_open); /* fanotify! */ cond_syscall(sys_fanotify_init); cond_syscall(sys_fanotify_mark); + +/* open by handle */ +cond_syscall(sys_name_to_handle_at); +cond_syscall(sys_open_by_handle_at); +cond_syscall(compat_sys_open_by_handle_at); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0f1bd83..51054fe 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write, static struct ctl_table root_table[]; static struct ctl_table_root sysctl_table_root; static struct ctl_table_header root_table_header = { - .count = 1, + {{.count = 1, .ctl_table = root_table, - .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list), + .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}}, .root = &sysctl_table_root, .set = &sysctl_table_root.default_set, }; @@ -361,20 +361,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sched_rt_handler, }, - { - .procname = "sched_compat_yield", - .data = &sysctl_sched_compat_yield, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, #ifdef CONFIG_SCHED_AUTOGROUP { .procname = "sched_autogroup_enabled", .data = &sysctl_sched_autogroup_enabled, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, @@ -948,7 +941,7 @@ static struct ctl_table kern_table[] = { .data = &sysctl_perf_event_sample_rate, .maxlen = sizeof(sysctl_perf_event_sample_rate), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = perf_proc_update_handler, }, #endif #ifdef CONFIG_KMEMCHECK @@ -1567,11 +1560,16 @@ void sysctl_head_get(struct ctl_table_header *head) spin_unlock(&sysctl_lock); } +static void free_head(struct rcu_head *rcu) +{ + kfree(container_of(rcu, struct ctl_table_header, rcu)); +} + void sysctl_head_put(struct ctl_table_header *head) { spin_lock(&sysctl_lock); if (!--head->count) - kfree(head); + call_rcu(&head->rcu, free_head); spin_unlock(&sysctl_lock); } @@ -1948,10 +1946,10 @@ void unregister_sysctl_table(struct ctl_table_header * header) start_unregistering(header); if (!--header->parent->count) { WARN_ON(1); - kfree(header->parent); + call_rcu(&header->parent->rcu, free_head); } if (!--header->count) - kfree(header); + call_rcu(&header->rcu, free_head); spin_unlock(&sysctl_lock); } diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index b875bed..3b8e028 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1321,13 +1321,11 @@ static ssize_t binary_sysctl(const int *name, int nlen, void __user *oldval, size_t oldlen, void __user *newval, size_t newlen) { const struct bin_table *table = NULL; - struct nameidata nd; struct vfsmount *mnt; struct file *file; ssize_t result; char *pathname; int flags; - int acc_mode; pathname = sysctl_getname(name, nlen, &table); result = PTR_ERR(pathname); @@ -1337,28 +1335,17 @@ static ssize_t binary_sysctl(const int *name, int nlen, /* How should the sysctl be accessed? */ if (oldval && oldlen && newval && newlen) { flags = O_RDWR; - acc_mode = MAY_READ | MAY_WRITE; } else if (newval && newlen) { flags = O_WRONLY; - acc_mode = MAY_WRITE; } else if (oldval && oldlen) { flags = O_RDONLY; - acc_mode = MAY_READ; } else { result = 0; goto out_putname; } mnt = current->nsproxy->pid_ns->proc_mnt; - result = vfs_path_lookup(mnt->mnt_root, mnt, pathname, 0, &nd); - if (result) - goto out_putname; - - result = may_open(&nd.path, acc_mode, flags); - if (result) - goto out_putpath; - - file = dentry_open(nd.path.dentry, nd.path.mnt, flags, current_cred()); + file = file_open_root(mnt->mnt_root, mnt, pathname, flags); result = PTR_ERR(file); if (IS_ERR(file)) goto out_putname; @@ -1370,10 +1357,6 @@ out_putname: putname(pathname); out: return result; - -out_putpath: - path_put(&nd.path); - goto out_putname; } diff --git a/kernel/time.c b/kernel/time.c index 5cb8053..8e8dc6d 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -645,7 +645,7 @@ u64 nsec_to_clock_t(u64 x) } /** - * nsecs_to_jiffies - Convert nsecs in u64 to jiffies + * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * @@ -657,7 +657,7 @@ u64 nsec_to_clock_t(u64 x) * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years */ -unsigned long nsecs_to_jiffies(u64 n) +u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ @@ -674,6 +674,24 @@ unsigned long nsecs_to_jiffies(u64 n) #endif } +/** + * nsecs_to_jiffies - Convert nsecs in u64 to jiffies + * + * @n: nsecs in u64 + * + * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. + * And this doesn't return MAX_JIFFY_OFFSET since this function is designed + * for scheduler, not for use in device drivers to calculate timeout value. + * + * note: + * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) + * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years + */ +unsigned long nsecs_to_jiffies(u64 n) +{ + return (unsigned long)nsecs_to_jiffies64(n); +} + /* * Add two timespec values and do a safety check for overflow. * It's assumed that both values are valid (>= 0) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 92ef9a5..da800ff 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -599,4 +599,14 @@ int tick_broadcast_oneshot_active(void) return tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT; } +/* + * Check whether the broadcast device supports oneshot. + */ +bool tick_broadcast_oneshot_available(void) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; +} + #endif diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 0e98fac..119528d 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -50,7 +50,11 @@ int tick_is_oneshot_available(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - return dev && (dev->features & CLOCK_EVT_FEAT_ONESHOT); + if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return 0; + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) + return 1; + return tick_broadcast_oneshot_available(); } /* diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index f77b93d..1009b06 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -40,6 +40,7 @@ extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast(int cpu); +bool tick_broadcast_oneshot_available(void); # else /* BROADCAST */ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { @@ -50,6 +51,7 @@ static inline void tick_broadcast_switch_to_oneshot(void) { } static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast(int cpu) { } +static inline bool tick_broadcast_oneshot_available(void) { return true; } # endif /* !BROADCAST */ #else /* !ONESHOT */ @@ -80,6 +82,7 @@ static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc) return 0; } static inline int tick_broadcast_oneshot_active(void) { return 0; } +static inline bool tick_broadcast_oneshot_available(void) { return false; } #endif /* !TICK_ONESHOT */ /* diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 32a19f9..3258455 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -41,7 +41,7 @@ static void print_name_offset(struct seq_file *m, void *sym) char symname[KSYM_NAME_LEN]; if (lookup_symbol_name((unsigned long)sym, symname) < 0) - SEQ_printf(m, "<%p>", sym); + SEQ_printf(m, "<%pK>", sym); else SEQ_printf(m, "%s", symname); } @@ -112,7 +112,7 @@ next_one: static void print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) { - SEQ_printf(m, " .base: %p\n", base); + SEQ_printf(m, " .base: %pK\n", base); SEQ_printf(m, " .index: %d\n", base->index); SEQ_printf(m, " .resolution: %Lu nsecs\n", diff --git a/kernel/timer.c b/kernel/timer.c index 87f656c..fd61986 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -404,6 +404,11 @@ static void timer_stats_account_timer(struct timer_list *timer) {} static struct debug_obj_descr timer_debug_descr; +static void *timer_debug_hint(void *addr) +{ + return ((struct timer_list *) addr)->function; +} + /* * fixup_init is called when: * - an active object is initialized @@ -477,6 +482,7 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state) static struct debug_obj_descr timer_debug_descr = { .name = "timer_list", + .debug_hint = timer_debug_hint, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, @@ -959,20 +965,45 @@ EXPORT_SYMBOL(try_to_del_timer_sync); * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from - * hardirq contexts. The caller must not hold locks which would prevent + * interrupt contexts. The caller must not hold locks which would prevent * completion of the timer's handler. The timer's handler must not call * add_timer_on(). Upon exit the timer is not queued and the handler is * not running on any CPU. * + * Note: You must not hold locks that are held in interrupt context + * while calling this function. Even if the lock has nothing to do + * with the timer in question. Here's why: + * + * CPU0 CPU1 + * ---- ---- + * <SOFTIRQ> + * call_timer_fn(); + * base->running_timer = mytimer; + * spin_lock_irq(somelock); + * <IRQ> + * spin_lock(somelock); + * del_timer_sync(mytimer); + * while (base->running_timer == mytimer); + * + * Now del_timer_sync() will never return and never release somelock. + * The interrupt on the other CPU is waiting to grab somelock but + * it has interrupted the softirq that CPU0 is waiting to finish. + * * The function returns whether it has deactivated a pending timer or not. */ int del_timer_sync(struct timer_list *timer) { #ifdef CONFIG_LOCKDEP - local_bh_disable(); + unsigned long flags; + + /* + * If lockdep gives a backtrace here, please reference + * the synchronization rules above. + */ + local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); - local_bh_enable(); + local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 153562d..cbafed7 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -138,6 +138,13 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...) !blk_tracer_enabled)) return; + /* + * If the BLK_TC_NOTIFY action mask isn't set, don't send any note + * message to the trace. + */ + if (!(bt->act_mask & BLK_TC_NOTIFY)) + return; + local_irq_save(flags); buf = per_cpu_ptr(bt->msg_data, smp_processor_id()); va_start(args, fmt); @@ -1820,21 +1827,5 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) rwbs[i] = '\0'; } -void blk_fill_rwbs_rq(char *rwbs, struct request *rq) -{ - int rw = rq->cmd_flags & 0x03; - int bytes; - - if (rq->cmd_flags & REQ_DISCARD) - rw |= REQ_DISCARD; - - if (rq->cmd_flags & REQ_SECURE) - rw |= REQ_SECURE; - - bytes = blk_rq_bytes(rq); - - blk_fill_rwbs(rwbs, rw, bytes); -} - #endif /* CONFIG_EVENT_TRACING */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f3dadae..888b611 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3328,7 +3328,7 @@ static int start_graph_tracing(void) /* The cpu_boot init_task->ret_stack will never be freed */ for_each_online_cpu(cpu) { if (!idle_task(cpu)->ret_stack) - ftrace_graph_init_task(idle_task(cpu)); + ftrace_graph_init_idle_task(idle_task(cpu), cpu); } do { @@ -3418,6 +3418,49 @@ void unregister_ftrace_graph(void) mutex_unlock(&ftrace_lock); } +static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); + +static void +graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) +{ + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + t->ftrace_timestamp = 0; + /* make curr_ret_stack visable before we add the ret_stack */ + smp_wmb(); + t->ret_stack = ret_stack; +} + +/* + * Allocate a return stack for the idle task. May be the first + * time through, or it may be done by CPU hotplug online. + */ +void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) +{ + t->curr_ret_stack = -1; + /* + * The idle task has no parent, it either has its own + * stack or no stack at all. + */ + if (t->ret_stack) + WARN_ON(t->ret_stack != per_cpu(idle_ret_stack, cpu)); + + if (ftrace_graph_active) { + struct ftrace_ret_stack *ret_stack; + + ret_stack = per_cpu(idle_ret_stack, cpu); + if (!ret_stack) { + ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack) + return; + per_cpu(idle_ret_stack, cpu) = ret_stack; + } + graph_init_task(t, ret_stack); + } +} + /* Allocate a return stack for newly created task */ void ftrace_graph_init_task(struct task_struct *t) { @@ -3433,12 +3476,7 @@ void ftrace_graph_init_task(struct task_struct *t) GFP_KERNEL); if (!ret_stack) return; - atomic_set(&t->tracing_graph_pause, 0); - atomic_set(&t->trace_overrun, 0); - t->ftrace_timestamp = 0; - /* make curr_ret_stack visable before we add the ret_stack */ - smp_wmb(); - t->ret_stack = ret_stack; + graph_init_task(t, ret_stack); } } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bd1c35a..db7b439 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5,7 +5,6 @@ */ #include <linux/ring_buffer.h> #include <linux/trace_clock.h> -#include <linux/ftrace_irq.h> #include <linux/spinlock.h> #include <linux/debugfs.h> #include <linux/uaccess.h> @@ -1429,6 +1428,17 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) } EXPORT_SYMBOL_GPL(ring_buffer_resize); +void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val) +{ + mutex_lock(&buffer->mutex); + if (val) + buffer->flags |= RB_FL_OVERWRITE; + else + buffer->flags &= ~RB_FL_OVERWRITE; + mutex_unlock(&buffer->mutex); +} +EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite); + static inline void * __rb_data_page_index(struct buffer_data_page *bpage, unsigned index) { @@ -2162,11 +2172,19 @@ rb_reserve_next_event(struct ring_buffer *buffer, if (likely(ts >= cpu_buffer->write_stamp)) { delta = diff; if (unlikely(test_time_stamp(delta))) { + int local_clock_stable = 1; +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + local_clock_stable = sched_clock_stable; +#endif WARN_ONCE(delta > (1ULL << 59), - KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n", + KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s", (unsigned long long)delta, (unsigned long long)ts, - (unsigned long long)cpu_buffer->write_stamp); + (unsigned long long)cpu_buffer->write_stamp, + local_clock_stable ? "" : + "If you just came from a suspend/resume,\n" + "please switch to the trace global clock:\n" + " echo global > /sys/kernel/debug/tracing/trace_clock\n"); add_timestamp = 1; } } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dc53ecb..9541c27 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -41,8 +41,6 @@ #include "trace.h" #include "trace_output.h" -#define TRACE_BUFFER_FLAGS (RB_FL_OVERWRITE) - /* * On boot up, the ring buffer is set to the minimum size, so that * we do not waste memory on systems that are not using tracing. @@ -340,7 +338,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); /* trace_flags holds trace_options default values */ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | - TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD; + TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE; static int trace_stop_count; static DEFINE_SPINLOCK(tracing_start_lock); @@ -425,6 +423,7 @@ static const char *trace_options[] = { "sleep-time", "graph-time", "record-cmd", + "overwrite", NULL }; @@ -780,6 +779,11 @@ __acquires(kernel_lock) tracing_reset_online_cpus(tr); current_trace = type; + + /* If we expanded the buffers, make sure the max is expanded too */ + if (ring_buffer_expanded && type->use_max_tr) + ring_buffer_resize(max_tr.buffer, trace_buf_size); + /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); ret = type->selftest(type, tr); @@ -792,6 +796,10 @@ __acquires(kernel_lock) /* Only reset on passing, to avoid touching corrupted buffers */ tracing_reset_online_cpus(tr); + /* Shrink the max buffer again */ + if (ring_buffer_expanded && type->use_max_tr) + ring_buffer_resize(max_tr.buffer, 1); + printk(KERN_CONT "PASSED\n"); } #endif @@ -1102,7 +1110,6 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; - entry->lock_depth = (tsk) ? tsk->lock_depth : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -1749,10 +1756,9 @@ static void print_lat_help_header(struct seq_file *m) seq_puts(m, "# | / _----=> need-resched \n"); seq_puts(m, "# || / _---=> hardirq/softirq \n"); seq_puts(m, "# ||| / _--=> preempt-depth \n"); - seq_puts(m, "# |||| /_--=> lock-depth \n"); - seq_puts(m, "# |||||/ delay \n"); - seq_puts(m, "# cmd pid |||||| time | caller \n"); - seq_puts(m, "# \\ / |||||| \\ | / \n"); + seq_puts(m, "# |||| / delay \n"); + seq_puts(m, "# cmd pid ||||| time | caller \n"); + seq_puts(m, "# \\ / ||||| \\ | / \n"); } static void print_func_help_header(struct seq_file *m) @@ -2529,6 +2535,9 @@ static void set_tracer_flags(unsigned int mask, int enabled) if (mask == TRACE_ITER_RECORD_CMD) trace_event_enable_cmd_record(enabled); + + if (mask == TRACE_ITER_OVERWRITE) + ring_buffer_change_overwrite(global_trace.buffer, enabled); } static ssize_t @@ -2710,6 +2719,10 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf, mutex_lock(&trace_types_lock); if (tracer_enabled ^ val) { + + /* Only need to warn if this is used to change the state */ + WARN_ONCE(1, "tracing_enabled is deprecated. Use tracing_on"); + if (val) { tracer_enabled = 1; if (current_trace->start) @@ -4551,9 +4564,11 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) __init static int tracer_alloc_buffers(void) { int ring_buf_size; + enum ring_buffer_flags rb_flags; int i; int ret = -ENOMEM; + if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL)) goto out; @@ -4566,12 +4581,13 @@ __init static int tracer_alloc_buffers(void) else ring_buf_size = 1; + rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; + cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(tracing_cpumask, cpu_all_mask); /* TODO: make the number of buffers hot pluggable with CPUS */ - global_trace.buffer = ring_buffer_alloc(ring_buf_size, - TRACE_BUFFER_FLAGS); + global_trace.buffer = ring_buffer_alloc(ring_buf_size, rb_flags); if (!global_trace.buffer) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); @@ -4581,7 +4597,7 @@ __init static int tracer_alloc_buffers(void) #ifdef CONFIG_TRACER_MAX_TRACE - max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS); + max_tr.buffer = ring_buffer_alloc(1, rb_flags); if (!max_tr.buffer) { printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); WARN_ON(1); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9021f8c..5e9dfc6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -272,8 +272,8 @@ struct tracer { /* If you handled the flag setting, return 0 */ int (*set_flag)(u32 old_flags, u32 bit, int set); struct tracer *next; - int print_max; struct tracer_flags *flags; + int print_max; int use_max_tr; }; @@ -606,6 +606,7 @@ enum trace_iterator_flags { TRACE_ITER_SLEEP_TIME = 0x40000, TRACE_ITER_GRAPH_TIME = 0x80000, TRACE_ITER_RECORD_CMD = 0x100000, + TRACE_ITER_OVERWRITE = 0x200000, }; /* @@ -661,8 +662,10 @@ struct ftrace_event_field { }; struct event_filter { - int n_preds; - struct filter_pred **preds; + int n_preds; /* Number assigned */ + int a_preds; /* allocated */ + struct filter_pred *preds; + struct filter_pred *root; char *filter_string; }; @@ -674,11 +677,23 @@ struct event_subsystem { int nr_events; }; +#define FILTER_PRED_INVALID ((unsigned short)-1) +#define FILTER_PRED_IS_RIGHT (1 << 15) +#define FILTER_PRED_FOLD (1 << 15) + +/* + * The max preds is the size of unsigned short with + * two flags at the MSBs. One bit is used for both the IS_RIGHT + * and FOLD flags. The other is reserved. + * + * 2^14 preds is way more than enough. + */ +#define MAX_FILTER_PRED 16384 + struct filter_pred; struct regex; -typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event, - int val1, int val2); +typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event); typedef int (*regex_match_func)(char *str, struct regex *r, int len); @@ -700,11 +715,23 @@ struct filter_pred { filter_pred_fn_t fn; u64 val; struct regex regex; - char *field_name; + /* + * Leaf nodes use field_name, ops is used by AND and OR + * nodes. The field_name is always freed when freeing a pred. + * We can overload field_name for ops and have it freed + * as well. + */ + union { + char *field_name; + unsigned short *ops; + }; int offset; int not; int op; - int pop_n; + unsigned short index; + unsigned short parent; + unsigned short left; + unsigned short right; }; extern struct list_head ftrace_common_fields; diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 6cf2237..1516cb3 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -109,12 +109,12 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry, */ #define FTRACE_CTX_FIELDS \ __field( unsigned int, prev_pid ) \ + __field( unsigned int, next_pid ) \ + __field( unsigned int, next_cpu ) \ __field( unsigned char, prev_prio ) \ __field( unsigned char, prev_state ) \ - __field( unsigned int, next_pid ) \ __field( unsigned char, next_prio ) \ - __field( unsigned char, next_state ) \ - __field( unsigned int, next_cpu ) + __field( unsigned char, next_state ) FTRACE_ENTRY(context_switch, ctx_switch_entry, diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 35fde09..e88f74f 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,7 +116,6 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); - __common_field(int, lock_depth); return ret; } @@ -326,6 +325,7 @@ int trace_set_clr_event(const char *system, const char *event, int set) { return __ftrace_set_clr_event(NULL, system, event, set); } +EXPORT_SYMBOL_GPL(trace_set_clr_event); /* 128 should be much more than enough */ #define EVENT_BUF_SIZE 127 @@ -1284,7 +1284,7 @@ trace_create_file_ops(struct module *mod) static void trace_module_add_events(struct module *mod) { struct ftrace_module_file_ops *file_ops = NULL; - struct ftrace_event_call *call, *start, *end; + struct ftrace_event_call **call, **start, **end; start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; @@ -1297,7 +1297,7 @@ static void trace_module_add_events(struct module *mod) return; for_each_event(call, start, end) { - __trace_add_event_call(call, mod, + __trace_add_event_call(*call, mod, &file_ops->id, &file_ops->enable, &file_ops->filter, &file_ops->format); } @@ -1367,8 +1367,8 @@ static struct notifier_block trace_module_nb = { .priority = 0, }; -extern struct ftrace_event_call __start_ftrace_events[]; -extern struct ftrace_event_call __stop_ftrace_events[]; +extern struct ftrace_event_call *__start_ftrace_events[]; +extern struct ftrace_event_call *__stop_ftrace_events[]; static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; @@ -1384,7 +1384,7 @@ __setup("trace_event=", setup_trace_event); static __init int event_trace_init(void) { - struct ftrace_event_call *call; + struct ftrace_event_call **call; struct dentry *d_tracer; struct dentry *entry; struct dentry *d_events; @@ -1430,7 +1430,7 @@ static __init int event_trace_init(void) pr_warning("tracing: Failed to allocate common fields"); for_each_event(call, __start_ftrace_events, __stop_ftrace_events) { - __trace_add_event_call(call, NULL, &ftrace_event_id_fops, + __trace_add_event_call(*call, NULL, &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 36d4010..3249b4f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -123,9 +123,13 @@ struct filter_parse_state { } operand; }; +struct pred_stack { + struct filter_pred **preds; + int index; +}; + #define DEFINE_COMPARISON_PRED(type) \ -static int filter_pred_##type(struct filter_pred *pred, void *event, \ - int val1, int val2) \ +static int filter_pred_##type(struct filter_pred *pred, void *event) \ { \ type *addr = (type *)(event + pred->offset); \ type val = (type)pred->val; \ @@ -152,8 +156,7 @@ static int filter_pred_##type(struct filter_pred *pred, void *event, \ } #define DEFINE_EQUALITY_PRED(size) \ -static int filter_pred_##size(struct filter_pred *pred, void *event, \ - int val1, int val2) \ +static int filter_pred_##size(struct filter_pred *pred, void *event) \ { \ u##size *addr = (u##size *)(event + pred->offset); \ u##size val = (u##size)pred->val; \ @@ -178,23 +181,8 @@ DEFINE_EQUALITY_PRED(32); DEFINE_EQUALITY_PRED(16); DEFINE_EQUALITY_PRED(8); -static int filter_pred_and(struct filter_pred *pred __attribute((unused)), - void *event __attribute((unused)), - int val1, int val2) -{ - return val1 && val2; -} - -static int filter_pred_or(struct filter_pred *pred __attribute((unused)), - void *event __attribute((unused)), - int val1, int val2) -{ - return val1 || val2; -} - /* Filter predicate for fixed sized arrays of characters */ -static int filter_pred_string(struct filter_pred *pred, void *event, - int val1, int val2) +static int filter_pred_string(struct filter_pred *pred, void *event) { char *addr = (char *)(event + pred->offset); int cmp, match; @@ -207,8 +195,7 @@ static int filter_pred_string(struct filter_pred *pred, void *event, } /* Filter predicate for char * pointers */ -static int filter_pred_pchar(struct filter_pred *pred, void *event, - int val1, int val2) +static int filter_pred_pchar(struct filter_pred *pred, void *event) { char **addr = (char **)(event + pred->offset); int cmp, match; @@ -231,8 +218,7 @@ static int filter_pred_pchar(struct filter_pred *pred, void *event, * and add it to the address of the entry, and at last we have * the address of the string. */ -static int filter_pred_strloc(struct filter_pred *pred, void *event, - int val1, int val2) +static int filter_pred_strloc(struct filter_pred *pred, void *event) { u32 str_item = *(u32 *)(event + pred->offset); int str_loc = str_item & 0xffff; @@ -247,8 +233,7 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event, return match; } -static int filter_pred_none(struct filter_pred *pred, void *event, - int val1, int val2) +static int filter_pred_none(struct filter_pred *pred, void *event) { return 0; } @@ -377,32 +362,147 @@ static void filter_build_regex(struct filter_pred *pred) pred->not ^= not; } +enum move_type { + MOVE_DOWN, + MOVE_UP_FROM_LEFT, + MOVE_UP_FROM_RIGHT +}; + +static struct filter_pred * +get_pred_parent(struct filter_pred *pred, struct filter_pred *preds, + int index, enum move_type *move) +{ + if (pred->parent & FILTER_PRED_IS_RIGHT) + *move = MOVE_UP_FROM_RIGHT; + else + *move = MOVE_UP_FROM_LEFT; + pred = &preds[pred->parent & ~FILTER_PRED_IS_RIGHT]; + + return pred; +} + +/* + * A series of AND or ORs where found together. Instead of + * climbing up and down the tree branches, an array of the + * ops were made in order of checks. We can just move across + * the array and short circuit if needed. + */ +static int process_ops(struct filter_pred *preds, + struct filter_pred *op, void *rec) +{ + struct filter_pred *pred; + int type; + int match; + int i; + + /* + * Micro-optimization: We set type to true if op + * is an OR and false otherwise (AND). Then we + * just need to test if the match is equal to + * the type, and if it is, we can short circuit the + * rest of the checks: + * + * if ((match && op->op == OP_OR) || + * (!match && op->op == OP_AND)) + * return match; + */ + type = op->op == OP_OR; + + for (i = 0; i < op->val; i++) { + pred = &preds[op->ops[i]]; + match = pred->fn(pred, rec); + if (!!match == type) + return match; + } + return match; +} + /* return 1 if event matches, 0 otherwise (discard) */ int filter_match_preds(struct event_filter *filter, void *rec) { - int match, top = 0, val1 = 0, val2 = 0; - int stack[MAX_FILTER_PRED]; + int match = -1; + enum move_type move = MOVE_DOWN; + struct filter_pred *preds; struct filter_pred *pred; - int i; + struct filter_pred *root; + int n_preds; + int done = 0; + + /* no filter is considered a match */ + if (!filter) + return 1; + + n_preds = filter->n_preds; + + if (!n_preds) + return 1; + + /* + * n_preds, root and filter->preds are protect with preemption disabled. + */ + preds = rcu_dereference_sched(filter->preds); + root = rcu_dereference_sched(filter->root); + if (!root) + return 1; + + pred = root; - for (i = 0; i < filter->n_preds; i++) { - pred = filter->preds[i]; - if (!pred->pop_n) { - match = pred->fn(pred, rec, val1, val2); - stack[top++] = match; + /* match is currently meaningless */ + match = -1; + + do { + switch (move) { + case MOVE_DOWN: + /* only AND and OR have children */ + if (pred->left != FILTER_PRED_INVALID) { + /* If ops is set, then it was folded. */ + if (!pred->ops) { + /* keep going to down the left side */ + pred = &preds[pred->left]; + continue; + } + /* We can treat folded ops as a leaf node */ + match = process_ops(preds, pred, rec); + } else + match = pred->fn(pred, rec); + /* If this pred is the only pred */ + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + case MOVE_UP_FROM_LEFT: + /* + * Check for short circuits. + * + * Optimization: !!match == (pred->op == OP_OR) + * is the same as: + * if ((match && pred->op == OP_OR) || + * (!match && pred->op == OP_AND)) + */ + if (!!match == (pred->op == OP_OR)) { + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + } + /* now go down the right side of the tree. */ + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + /* We finished this equation. */ + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); continue; } - if (pred->pop_n > top) { - WARN_ON_ONCE(1); - return 0; - } - val1 = stack[--top]; - val2 = stack[--top]; - match = pred->fn(pred, rec, val1, val2); - stack[top++] = match; - } + done = 1; + } while (!done); - return stack[--top]; + return match; } EXPORT_SYMBOL_GPL(filter_match_preds); @@ -414,6 +514,9 @@ static void parse_error(struct filter_parse_state *ps, int err, int pos) static void remove_filter_string(struct event_filter *filter) { + if (!filter) + return; + kfree(filter->filter_string); filter->filter_string = NULL; } @@ -473,9 +576,10 @@ static void append_filter_err(struct filter_parse_state *ps, void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) { - struct event_filter *filter = call->filter; + struct event_filter *filter; mutex_lock(&event_mutex); + filter = call->filter; if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else @@ -486,9 +590,10 @@ void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) void print_subsystem_event_filter(struct event_subsystem *system, struct trace_seq *s) { - struct event_filter *filter = system->filter; + struct event_filter *filter; mutex_lock(&event_mutex); + filter = system->filter; if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); else @@ -539,10 +644,58 @@ static void filter_clear_pred(struct filter_pred *pred) pred->regex.len = 0; } -static int filter_set_pred(struct filter_pred *dest, +static int __alloc_pred_stack(struct pred_stack *stack, int n_preds) +{ + stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL); + if (!stack->preds) + return -ENOMEM; + stack->index = n_preds; + return 0; +} + +static void __free_pred_stack(struct pred_stack *stack) +{ + kfree(stack->preds); + stack->index = 0; +} + +static int __push_pred_stack(struct pred_stack *stack, + struct filter_pred *pred) +{ + int index = stack->index; + + if (WARN_ON(index == 0)) + return -ENOSPC; + + stack->preds[--index] = pred; + stack->index = index; + return 0; +} + +static struct filter_pred * +__pop_pred_stack(struct pred_stack *stack) +{ + struct filter_pred *pred; + int index = stack->index; + + pred = stack->preds[index++]; + if (!pred) + return NULL; + + stack->index = index; + return pred; +} + +static int filter_set_pred(struct event_filter *filter, + int idx, + struct pred_stack *stack, struct filter_pred *src, filter_pred_fn_t fn) { + struct filter_pred *dest = &filter->preds[idx]; + struct filter_pred *left; + struct filter_pred *right; + *dest = *src; if (src->field_name) { dest->field_name = kstrdup(src->field_name, GFP_KERNEL); @@ -550,116 +703,140 @@ static int filter_set_pred(struct filter_pred *dest, return -ENOMEM; } dest->fn = fn; + dest->index = idx; - return 0; + if (dest->op == OP_OR || dest->op == OP_AND) { + right = __pop_pred_stack(stack); + left = __pop_pred_stack(stack); + if (!left || !right) + return -EINVAL; + /* + * If both children can be folded + * and they are the same op as this op or a leaf, + * then this op can be folded. + */ + if (left->index & FILTER_PRED_FOLD && + (left->op == dest->op || + left->left == FILTER_PRED_INVALID) && + right->index & FILTER_PRED_FOLD && + (right->op == dest->op || + right->left == FILTER_PRED_INVALID)) + dest->index |= FILTER_PRED_FOLD; + + dest->left = left->index & ~FILTER_PRED_FOLD; + dest->right = right->index & ~FILTER_PRED_FOLD; + left->parent = dest->index & ~FILTER_PRED_FOLD; + right->parent = dest->index | FILTER_PRED_IS_RIGHT; + } else { + /* + * Make dest->left invalid to be used as a quick + * way to know this is a leaf node. + */ + dest->left = FILTER_PRED_INVALID; + + /* All leafs allow folding the parent ops. */ + dest->index |= FILTER_PRED_FOLD; + } + + return __push_pred_stack(stack, dest); } -static void filter_disable_preds(struct ftrace_event_call *call) +static void __free_preds(struct event_filter *filter) { - struct event_filter *filter = call->filter; int i; - call->flags &= ~TRACE_EVENT_FL_FILTERED; + if (filter->preds) { + for (i = 0; i < filter->a_preds; i++) + kfree(filter->preds[i].field_name); + kfree(filter->preds); + filter->preds = NULL; + } + filter->a_preds = 0; filter->n_preds = 0; - - for (i = 0; i < MAX_FILTER_PRED; i++) - filter->preds[i]->fn = filter_pred_none; } -static void __free_preds(struct event_filter *filter) +static void filter_disable(struct ftrace_event_call *call) { - int i; + call->flags &= ~TRACE_EVENT_FL_FILTERED; +} +static void __free_filter(struct event_filter *filter) +{ if (!filter) return; - for (i = 0; i < MAX_FILTER_PRED; i++) { - if (filter->preds[i]) - filter_free_pred(filter->preds[i]); - } - kfree(filter->preds); + __free_preds(filter); kfree(filter->filter_string); kfree(filter); } +/* + * Called when destroying the ftrace_event_call. + * The call is being freed, so we do not need to worry about + * the call being currently used. This is for module code removing + * the tracepoints from within it. + */ void destroy_preds(struct ftrace_event_call *call) { - __free_preds(call->filter); + __free_filter(call->filter); call->filter = NULL; - call->flags &= ~TRACE_EVENT_FL_FILTERED; } -static struct event_filter *__alloc_preds(void) +static struct event_filter *__alloc_filter(void) { struct event_filter *filter; + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + return filter; +} + +static int __alloc_preds(struct event_filter *filter, int n_preds) +{ struct filter_pred *pred; int i; - filter = kzalloc(sizeof(*filter), GFP_KERNEL); - if (!filter) - return ERR_PTR(-ENOMEM); + if (filter->preds) + __free_preds(filter); - filter->n_preds = 0; + filter->preds = + kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL); - filter->preds = kzalloc(MAX_FILTER_PRED * sizeof(pred), GFP_KERNEL); if (!filter->preds) - goto oom; + return -ENOMEM; - for (i = 0; i < MAX_FILTER_PRED; i++) { - pred = kzalloc(sizeof(*pred), GFP_KERNEL); - if (!pred) - goto oom; + filter->a_preds = n_preds; + filter->n_preds = 0; + + for (i = 0; i < n_preds; i++) { + pred = &filter->preds[i]; pred->fn = filter_pred_none; - filter->preds[i] = pred; } - return filter; - -oom: - __free_preds(filter); - return ERR_PTR(-ENOMEM); -} - -static int init_preds(struct ftrace_event_call *call) -{ - if (call->filter) - return 0; - - call->flags &= ~TRACE_EVENT_FL_FILTERED; - call->filter = __alloc_preds(); - if (IS_ERR(call->filter)) - return PTR_ERR(call->filter); - return 0; } -static int init_subsystem_preds(struct event_subsystem *system) +static void filter_free_subsystem_preds(struct event_subsystem *system) { struct ftrace_event_call *call; - int err; list_for_each_entry(call, &ftrace_events, list) { if (strcmp(call->class->system, system->name) != 0) continue; - err = init_preds(call); - if (err) - return err; + filter_disable(call); + remove_filter_string(call->filter); } - - return 0; } -static void filter_free_subsystem_preds(struct event_subsystem *system) +static void filter_free_subsystem_filters(struct event_subsystem *system) { struct ftrace_event_call *call; list_for_each_entry(call, &ftrace_events, list) { if (strcmp(call->class->system, system->name) != 0) continue; - - filter_disable_preds(call); - remove_filter_string(call->filter); + __free_filter(call->filter); + call->filter = NULL; } } @@ -667,18 +844,19 @@ static int filter_add_pred_fn(struct filter_parse_state *ps, struct ftrace_event_call *call, struct event_filter *filter, struct filter_pred *pred, + struct pred_stack *stack, filter_pred_fn_t fn) { int idx, err; - if (filter->n_preds == MAX_FILTER_PRED) { + if (WARN_ON(filter->n_preds == filter->a_preds)) { parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); return -ENOSPC; } idx = filter->n_preds; - filter_clear_pred(filter->preds[idx]); - err = filter_set_pred(filter->preds[idx], pred, fn); + filter_clear_pred(&filter->preds[idx]); + err = filter_set_pred(filter, idx, stack, pred, fn); if (err) return err; @@ -763,6 +941,7 @@ static int filter_add_pred(struct filter_parse_state *ps, struct ftrace_event_call *call, struct event_filter *filter, struct filter_pred *pred, + struct pred_stack *stack, bool dry_run) { struct ftrace_event_field *field; @@ -770,17 +949,12 @@ static int filter_add_pred(struct filter_parse_state *ps, unsigned long long val; int ret; - pred->fn = filter_pred_none; + fn = pred->fn = filter_pred_none; - if (pred->op == OP_AND) { - pred->pop_n = 2; - fn = filter_pred_and; + if (pred->op == OP_AND) goto add_pred_fn; - } else if (pred->op == OP_OR) { - pred->pop_n = 2; - fn = filter_pred_or; + else if (pred->op == OP_OR) goto add_pred_fn; - } field = find_event_field(call, pred->field_name); if (!field) { @@ -829,7 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps, add_pred_fn: if (!dry_run) - return filter_add_pred_fn(ps, call, filter, pred, fn); + return filter_add_pred_fn(ps, call, filter, pred, stack, fn); return 0; } @@ -1187,6 +1361,234 @@ static int check_preds(struct filter_parse_state *ps) return 0; } +static int count_preds(struct filter_parse_state *ps) +{ + struct postfix_elt *elt; + int n_preds = 0; + + list_for_each_entry(elt, &ps->postfix, list) { + if (elt->op == OP_NONE) + continue; + n_preds++; + } + + return n_preds; +} + +/* + * The tree is walked at filtering of an event. If the tree is not correctly + * built, it may cause an infinite loop. Check here that the tree does + * indeed terminate. + */ +static int check_pred_tree(struct event_filter *filter, + struct filter_pred *root) +{ + struct filter_pred *preds; + struct filter_pred *pred; + enum move_type move = MOVE_DOWN; + int count = 0; + int done = 0; + int max; + + /* + * The max that we can hit a node is three times. + * Once going down, once coming up from left, and + * once coming up from right. This is more than enough + * since leafs are only hit a single time. + */ + max = 3 * filter->n_preds; + + preds = filter->preds; + if (!preds) + return -EINVAL; + pred = root; + + do { + if (WARN_ON(count++ > max)) + return -EINVAL; + + switch (move) { + case MOVE_DOWN: + if (pred->left != FILTER_PRED_INVALID) { + pred = &preds[pred->left]; + continue; + } + /* A leaf at the root is just a leaf in the tree */ + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + case MOVE_UP_FROM_LEFT: + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + } + done = 1; + } while (!done); + + /* We are fine. */ + return 0; +} + +static int count_leafs(struct filter_pred *preds, struct filter_pred *root) +{ + struct filter_pred *pred; + enum move_type move = MOVE_DOWN; + int count = 0; + int done = 0; + + pred = root; + + do { + switch (move) { + case MOVE_DOWN: + if (pred->left != FILTER_PRED_INVALID) { + pred = &preds[pred->left]; + continue; + } + /* A leaf at the root is just a leaf in the tree */ + if (pred == root) + return 1; + count++; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + case MOVE_UP_FROM_LEFT: + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + } + done = 1; + } while (!done); + + return count; +} + +static int fold_pred(struct filter_pred *preds, struct filter_pred *root) +{ + struct filter_pred *pred; + enum move_type move = MOVE_DOWN; + int count = 0; + int children; + int done = 0; + + /* No need to keep the fold flag */ + root->index &= ~FILTER_PRED_FOLD; + + /* If the root is a leaf then do nothing */ + if (root->left == FILTER_PRED_INVALID) + return 0; + + /* count the children */ + children = count_leafs(preds, &preds[root->left]); + children += count_leafs(preds, &preds[root->right]); + + root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL); + if (!root->ops) + return -ENOMEM; + + root->val = children; + + pred = root; + do { + switch (move) { + case MOVE_DOWN: + if (pred->left != FILTER_PRED_INVALID) { + pred = &preds[pred->left]; + continue; + } + if (WARN_ON(count == children)) + return -EINVAL; + pred->index &= ~FILTER_PRED_FOLD; + root->ops[count++] = pred->index; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + case MOVE_UP_FROM_LEFT: + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + } + done = 1; + } while (!done); + + return 0; +} + +/* + * To optimize the processing of the ops, if we have several "ors" or + * "ands" together, we can put them in an array and process them all + * together speeding up the filter logic. + */ +static int fold_pred_tree(struct event_filter *filter, + struct filter_pred *root) +{ + struct filter_pred *preds; + struct filter_pred *pred; + enum move_type move = MOVE_DOWN; + int done = 0; + int err; + + preds = filter->preds; + if (!preds) + return -EINVAL; + pred = root; + + do { + switch (move) { + case MOVE_DOWN: + if (pred->index & FILTER_PRED_FOLD) { + err = fold_pred(preds, pred); + if (err) + return err; + /* Folded nodes are like leafs */ + } else if (pred->left != FILTER_PRED_INVALID) { + pred = &preds[pred->left]; + continue; + } + + /* A leaf at the root is just a leaf in the tree */ + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + case MOVE_UP_FROM_LEFT: + pred = &preds[pred->right]; + move = MOVE_DOWN; + continue; + case MOVE_UP_FROM_RIGHT: + if (pred == root) + break; + pred = get_pred_parent(pred, preds, + pred->parent, &move); + continue; + } + done = 1; + } while (!done); + + return 0; +} + static int replace_preds(struct ftrace_event_call *call, struct event_filter *filter, struct filter_parse_state *ps, @@ -1195,14 +1597,32 @@ static int replace_preds(struct ftrace_event_call *call, { char *operand1 = NULL, *operand2 = NULL; struct filter_pred *pred; + struct filter_pred *root; struct postfix_elt *elt; + struct pred_stack stack = { }; /* init to NULL */ int err; int n_preds = 0; + n_preds = count_preds(ps); + if (n_preds >= MAX_FILTER_PRED) { + parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); + return -ENOSPC; + } + err = check_preds(ps); if (err) return err; + if (!dry_run) { + err = __alloc_pred_stack(&stack, n_preds); + if (err) + return err; + err = __alloc_preds(filter, n_preds); + if (err) + goto fail; + } + + n_preds = 0; list_for_each_entry(elt, &ps->postfix, list) { if (elt->op == OP_NONE) { if (!operand1) @@ -1211,14 +1631,16 @@ static int replace_preds(struct ftrace_event_call *call, operand2 = elt->operand; else { parse_error(ps, FILT_ERR_TOO_MANY_OPERANDS, 0); - return -EINVAL; + err = -EINVAL; + goto fail; } continue; } - if (n_preds++ == MAX_FILTER_PRED) { + if (WARN_ON(n_preds++ == MAX_FILTER_PRED)) { parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0); - return -ENOSPC; + err = -ENOSPC; + goto fail; } if (elt->op == OP_AND || elt->op == OP_OR) { @@ -1228,76 +1650,181 @@ static int replace_preds(struct ftrace_event_call *call, if (!operand1 || !operand2) { parse_error(ps, FILT_ERR_MISSING_FIELD, 0); - return -EINVAL; + err = -EINVAL; + goto fail; } pred = create_pred(elt->op, operand1, operand2); add_pred: - if (!pred) - return -ENOMEM; - err = filter_add_pred(ps, call, filter, pred, dry_run); + if (!pred) { + err = -ENOMEM; + goto fail; + } + err = filter_add_pred(ps, call, filter, pred, &stack, dry_run); filter_free_pred(pred); if (err) - return err; + goto fail; operand1 = operand2 = NULL; } - return 0; + if (!dry_run) { + /* We should have one item left on the stack */ + pred = __pop_pred_stack(&stack); + if (!pred) + return -EINVAL; + /* This item is where we start from in matching */ + root = pred; + /* Make sure the stack is empty */ + pred = __pop_pred_stack(&stack); + if (WARN_ON(pred)) { + err = -EINVAL; + filter->root = NULL; + goto fail; + } + err = check_pred_tree(filter, root); + if (err) + goto fail; + + /* Optimize the tree */ + err = fold_pred_tree(filter, root); + if (err) + goto fail; + + /* We don't set root until we know it works */ + barrier(); + filter->root = root; + } + + err = 0; +fail: + __free_pred_stack(&stack); + return err; } +struct filter_list { + struct list_head list; + struct event_filter *filter; +}; + static int replace_system_preds(struct event_subsystem *system, struct filter_parse_state *ps, char *filter_string) { struct ftrace_event_call *call; + struct filter_list *filter_item; + struct filter_list *tmp; + LIST_HEAD(filter_list); bool fail = true; int err; list_for_each_entry(call, &ftrace_events, list) { - struct event_filter *filter = call->filter; if (strcmp(call->class->system, system->name) != 0) continue; - /* try to see if the filter can be applied */ - err = replace_preds(call, filter, ps, filter_string, true); + /* + * Try to see if the filter can be applied + * (filter arg is ignored on dry_run) + */ + err = replace_preds(call, NULL, ps, filter_string, true); if (err) + goto fail; + } + + list_for_each_entry(call, &ftrace_events, list) { + struct event_filter *filter; + + if (strcmp(call->class->system, system->name) != 0) continue; - /* really apply the filter */ - filter_disable_preds(call); - err = replace_preds(call, filter, ps, filter_string, false); + filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL); + if (!filter_item) + goto fail_mem; + + list_add_tail(&filter_item->list, &filter_list); + + filter_item->filter = __alloc_filter(); + if (!filter_item->filter) + goto fail_mem; + filter = filter_item->filter; + + /* Can only fail on no memory */ + err = replace_filter_string(filter, filter_string); if (err) - filter_disable_preds(call); - else { + goto fail_mem; + + err = replace_preds(call, filter, ps, filter_string, false); + if (err) { + filter_disable(call); + parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); + append_filter_err(ps, filter); + } else call->flags |= TRACE_EVENT_FL_FILTERED; - replace_filter_string(filter, filter_string); - } + /* + * Regardless of if this returned an error, we still + * replace the filter for the call. + */ + filter = call->filter; + call->filter = filter_item->filter; + filter_item->filter = filter; + fail = false; } - if (fail) { - parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); - return -EINVAL; + if (fail) + goto fail; + + /* + * The calls can still be using the old filters. + * Do a synchronize_sched() to ensure all calls are + * done with them before we free them. + */ + synchronize_sched(); + list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { + __free_filter(filter_item->filter); + list_del(&filter_item->list); + kfree(filter_item); } return 0; + fail: + /* No call succeeded */ + list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { + list_del(&filter_item->list); + kfree(filter_item); + } + parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); + return -EINVAL; + fail_mem: + /* If any call succeeded, we still need to sync */ + if (!fail) + synchronize_sched(); + list_for_each_entry_safe(filter_item, tmp, &filter_list, list) { + __free_filter(filter_item->filter); + list_del(&filter_item->list); + kfree(filter_item); + } + return -ENOMEM; } int apply_event_filter(struct ftrace_event_call *call, char *filter_string) { - int err; struct filter_parse_state *ps; + struct event_filter *filter; + struct event_filter *tmp; + int err = 0; mutex_lock(&event_mutex); - err = init_preds(call); - if (err) - goto out_unlock; - if (!strcmp(strstrip(filter_string), "0")) { - filter_disable_preds(call); - remove_filter_string(call->filter); + filter_disable(call); + filter = call->filter; + if (!filter) + goto out_unlock; + call->filter = NULL; + /* Make sure the filter is not being used */ + synchronize_sched(); + __free_filter(filter); goto out_unlock; } @@ -1306,22 +1833,41 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) if (!ps) goto out_unlock; - filter_disable_preds(call); - replace_filter_string(call->filter, filter_string); + filter = __alloc_filter(); + if (!filter) { + kfree(ps); + goto out_unlock; + } + + replace_filter_string(filter, filter_string); parse_init(ps, filter_ops, filter_string); err = filter_parse(ps); if (err) { - append_filter_err(ps, call->filter); + append_filter_err(ps, filter); goto out; } - err = replace_preds(call, call->filter, ps, filter_string, false); - if (err) - append_filter_err(ps, call->filter); - else + err = replace_preds(call, filter, ps, filter_string, false); + if (err) { + filter_disable(call); + append_filter_err(ps, filter); + } else call->flags |= TRACE_EVENT_FL_FILTERED; out: + /* + * Always swap the call filter with the new filter + * even if there was an error. If there was an error + * in the filter, we disable the filter and show the error + * string + */ + tmp = call->filter; + call->filter = filter; + if (tmp) { + /* Make sure the call is done with the filter */ + synchronize_sched(); + __free_filter(tmp); + } filter_opstack_clear(ps); postfix_clear(ps); kfree(ps); @@ -1334,18 +1880,21 @@ out_unlock: int apply_subsystem_event_filter(struct event_subsystem *system, char *filter_string) { - int err; struct filter_parse_state *ps; + struct event_filter *filter; + int err = 0; mutex_lock(&event_mutex); - err = init_subsystem_preds(system); - if (err) - goto out_unlock; - if (!strcmp(strstrip(filter_string), "0")) { filter_free_subsystem_preds(system); remove_filter_string(system->filter); + filter = system->filter; + system->filter = NULL; + /* Ensure all filters are no longer used */ + synchronize_sched(); + filter_free_subsystem_filters(system); + __free_filter(filter); goto out_unlock; } @@ -1354,7 +1903,17 @@ int apply_subsystem_event_filter(struct event_subsystem *system, if (!ps) goto out_unlock; - replace_filter_string(system->filter, filter_string); + filter = __alloc_filter(); + if (!filter) + goto out; + + replace_filter_string(filter, filter_string); + /* + * No event actually uses the system filter + * we can free it without synchronize_sched(). + */ + __free_filter(system->filter); + system->filter = filter; parse_init(ps, filter_ops, filter_string); err = filter_parse(ps); @@ -1384,7 +1943,7 @@ void ftrace_profile_free_filter(struct perf_event *event) struct event_filter *filter = event->filter; event->filter = NULL; - __free_preds(filter); + __free_filter(filter); } int ftrace_profile_set_filter(struct perf_event *event, int event_id, @@ -1410,8 +1969,8 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, if (event->filter) goto out_unlock; - filter = __alloc_preds(); - if (IS_ERR(filter)) { + filter = __alloc_filter(); + if (!filter) { err = PTR_ERR(filter); goto out_unlock; } @@ -1419,7 +1978,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id, err = -ENOMEM; ps = kzalloc(sizeof(*ps), GFP_KERNEL); if (!ps) - goto free_preds; + goto free_filter; parse_init(ps, filter_ops, filter_str); err = filter_parse(ps); @@ -1435,9 +1994,9 @@ free_ps: postfix_clear(ps); kfree(ps); -free_preds: +free_filter: if (err) - __free_preds(filter); + __free_filter(filter); out_unlock: mutex_unlock(&event_mutex); diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 4b74d71..bbeec31 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -161,13 +161,13 @@ struct ftrace_event_class event_class_ftrace_##call = { \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ }; \ \ -struct ftrace_event_call __used \ -__attribute__((__aligned__(4))) \ -__attribute__((section("_ftrace_events"))) event_##call = { \ +struct ftrace_event_call __used event_##call = { \ .name = #call, \ .event.type = etype, \ .class = &event_class_ftrace_##call, \ .print_fmt = print, \ }; \ +struct ftrace_event_call __used \ +__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; #include "trace_entries.h" diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 2dec9bc..8435b43 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -353,6 +353,43 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) kfree(data); } +/* Bitfield fetch function */ +struct bitfield_fetch_param { + struct fetch_param orig; + unsigned char hi_shift; + unsigned char low_shift; +}; + +#define DEFINE_FETCH_bitfield(type) \ +static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\ + void *data, void *dest) \ +{ \ + struct bitfield_fetch_param *bprm = data; \ + type buf = 0; \ + call_fetch(&bprm->orig, regs, &buf); \ + if (buf) { \ + buf <<= bprm->hi_shift; \ + buf >>= bprm->low_shift; \ + } \ + *(type *)dest = buf; \ +} +DEFINE_BASIC_FETCH_FUNCS(bitfield) +#define fetch_bitfield_string NULL +#define fetch_bitfield_string_size NULL + +static __kprobes void +free_bitfield_fetch_param(struct bitfield_fetch_param *data) +{ + /* + * Don't check the bitfield itself, because this must be the + * last fetch function. + */ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + free_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + free_symbol_cache(data->orig.data); + kfree(data); +} /* Default (unsigned long) fetch type */ #define __DEFAULT_FETCH_TYPE(t) u##t #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t) @@ -367,6 +404,7 @@ enum { FETCH_MTD_memory, FETCH_MTD_symbol, FETCH_MTD_deref, + FETCH_MTD_bitfield, FETCH_MTD_END, }; @@ -387,6 +425,7 @@ ASSIGN_FETCH_FUNC(retval, ftype), \ ASSIGN_FETCH_FUNC(memory, ftype), \ ASSIGN_FETCH_FUNC(symbol, ftype), \ ASSIGN_FETCH_FUNC(deref, ftype), \ +ASSIGN_FETCH_FUNC(bitfield, ftype), \ } \ } @@ -430,9 +469,33 @@ static const struct fetch_type *find_fetch_type(const char *type) if (!type) type = DEFAULT_FETCH_TYPE_STR; + /* Special case: bitfield */ + if (*type == 'b') { + unsigned long bs; + type = strchr(type, '/'); + if (!type) + goto fail; + type++; + if (strict_strtoul(type, 0, &bs)) + goto fail; + switch (bs) { + case 8: + return find_fetch_type("u8"); + case 16: + return find_fetch_type("u16"); + case 32: + return find_fetch_type("u32"); + case 64: + return find_fetch_type("u64"); + default: + goto fail; + } + } + for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++) if (strcmp(type, fetch_type_table[i].name) == 0) return &fetch_type_table[i]; +fail: return NULL; } @@ -586,7 +649,9 @@ error: static void free_probe_arg(struct probe_arg *arg) { - if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) + if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) + free_bitfield_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) free_deref_fetch_param(arg->fetch.data); else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) free_symbol_cache(arg->fetch.data); @@ -767,16 +832,15 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t, } break; case '+': /* deref memory */ + arg++; /* Skip '+', because strict_strtol() rejects it. */ case '-': tmp = strchr(arg, '('); if (!tmp) break; *tmp = '\0'; - ret = strict_strtol(arg + 1, 0, &offset); + ret = strict_strtol(arg, 0, &offset); if (ret) break; - if (arg[0] == '-') - offset = -offset; arg = tmp + 1; tmp = strrchr(arg, ')'); if (tmp) { @@ -807,6 +871,41 @@ static int __parse_probe_arg(char *arg, const struct fetch_type *t, return ret; } +#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long)) + +/* Bitfield type needs to be parsed into a fetch function */ +static int __parse_bitfield_probe_arg(const char *bf, + const struct fetch_type *t, + struct fetch_param *f) +{ + struct bitfield_fetch_param *bprm; + unsigned long bw, bo; + char *tail; + + if (*bf != 'b') + return 0; + + bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); + if (!bprm) + return -ENOMEM; + bprm->orig = *f; + f->fn = t->fetch[FETCH_MTD_bitfield]; + f->data = (void *)bprm; + + bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */ + if (bw == 0 || *tail != '@') + return -EINVAL; + + bf = tail + 1; + bo = simple_strtoul(bf, &tail, 0); + if (tail == bf || *tail != '/') + return -EINVAL; + + bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo); + bprm->low_shift = bprm->hi_shift + bo; + return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0; +} + /* String length checking wrapper */ static int parse_probe_arg(char *arg, struct trace_probe *tp, struct probe_arg *parg, int is_return) @@ -836,6 +935,8 @@ static int parse_probe_arg(char *arg, struct trace_probe *tp, parg->offset = tp->size; tp->size += parg->type->size; ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return); + if (ret >= 0 && t != NULL) + ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch); if (ret >= 0) { parg->fetch_size.fn = get_fetch_size_function(parg->type, parg->fetch.fn); @@ -1130,7 +1231,7 @@ static int command_trace_probe(const char *buf) return ret; } -#define WRITE_BUFSIZE 128 +#define WRITE_BUFSIZE 4096 static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 02272ba..456be90 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -529,24 +529,34 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) * @entry: The trace entry field from the ring buffer * * Prints the generic fields of irqs off, in hard or softirq, preempt - * count and lock depth. + * count. */ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) { - int hardirq, softirq; + char hardsoft_irq; + char need_resched; + char irqs_off; + int hardirq; + int softirq; int ret; hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + irqs_off = + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : + '.'; + need_resched = + (entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.'; + hardsoft_irq = + (hardirq && softirq) ? 'H' : + hardirq ? 'h' : + softirq ? 's' : + '.'; + if (!trace_seq_printf(s, "%c%c%c", - (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : - (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? - 'X' : '.', - (entry->flags & TRACE_FLAG_NEED_RESCHED) ? - 'N' : '.', - (hardirq && softirq) ? 'H' : - hardirq ? 'h' : softirq ? 's' : '.')) + irqs_off, need_resched, hardsoft_irq)) return 0; if (entry->preempt_count) @@ -554,13 +564,7 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) else ret = trace_seq_putc(s, '.'); - if (!ret) - return 0; - - if (entry->lock_depth < 0) - return trace_seq_putc(s, '.'); - - return trace_seq_printf(s, "%d", entry->lock_depth); + return ret; } static int diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 8f758d0..7e62c0a 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -247,51 +247,3 @@ void tracing_sched_switch_assign_trace(struct trace_array *tr) ctx_trace = tr; } -static void stop_sched_trace(struct trace_array *tr) -{ - tracing_stop_sched_switch_record(); -} - -static int sched_switch_trace_init(struct trace_array *tr) -{ - ctx_trace = tr; - tracing_reset_online_cpus(tr); - tracing_start_sched_switch_record(); - return 0; -} - -static void sched_switch_trace_reset(struct trace_array *tr) -{ - if (sched_ref) - stop_sched_trace(tr); -} - -static void sched_switch_trace_start(struct trace_array *tr) -{ - sched_stopped = 0; -} - -static void sched_switch_trace_stop(struct trace_array *tr) -{ - sched_stopped = 1; -} - -static struct tracer sched_switch_trace __read_mostly = -{ - .name = "sched_switch", - .init = sched_switch_trace_init, - .reset = sched_switch_trace_reset, - .start = sched_switch_trace_start, - .stop = sched_switch_trace_stop, - .wait_pipe = poll_wait_pipe, -#ifdef CONFIG_FTRACE_SELFTEST - .selftest = trace_selftest_startup_sched_switch, -#endif -}; - -__init static int init_sched_switch_trace(void) -{ - return register_tracer(&sched_switch_trace); -} -device_initcall(init_sched_switch_trace); - diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index b706529..ee7b5a0 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -55,31 +55,42 @@ struct ftrace_event_class event_class_syscall_exit = { .raw_init = init_syscall_trace, }; -extern unsigned long __start_syscalls_metadata[]; -extern unsigned long __stop_syscalls_metadata[]; +extern struct syscall_metadata *__start_syscalls_metadata[]; +extern struct syscall_metadata *__stop_syscalls_metadata[]; static struct syscall_metadata **syscalls_metadata; -static struct syscall_metadata *find_syscall_meta(unsigned long syscall) +#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { - struct syscall_metadata *start; - struct syscall_metadata *stop; + /* + * Only compare after the "sys" prefix. Archs that use + * syscall wrappers may have syscalls symbols aliases prefixed + * with "SyS" instead of "sys", leading to an unwanted + * mismatch. + */ + return !strcmp(sym + 3, name + 3); +} +#endif + +static __init struct syscall_metadata * +find_syscall_meta(unsigned long syscall) +{ + struct syscall_metadata **start; + struct syscall_metadata **stop; char str[KSYM_SYMBOL_LEN]; - start = (struct syscall_metadata *)__start_syscalls_metadata; - stop = (struct syscall_metadata *)__stop_syscalls_metadata; + start = __start_syscalls_metadata; + stop = __stop_syscalls_metadata; kallsyms_lookup(syscall, NULL, NULL, NULL, str); + if (arch_syscall_match_sym_name(str, "sys_ni_syscall")) + return NULL; + for ( ; start < stop; start++) { - /* - * Only compare after the "sys" prefix. Archs that use - * syscall wrappers may have syscalls symbols aliases prefixed - * with "SyS" instead of "sys", leading to an unwanted - * mismatch. - */ - if (start->name && !strcmp(start->name + 3, str + 3)) - return start; + if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name)) + return *start; } return NULL; } @@ -358,7 +369,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call) int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; - if (num < 0 || num >= NR_syscalls) + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) return -ENOSYS; mutex_lock(&syscall_trace_lock); if (!sys_refcount_enter) @@ -376,7 +387,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call) int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; - if (num < 0 || num >= NR_syscalls) + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) return; mutex_lock(&syscall_trace_lock); sys_refcount_enter--; @@ -392,7 +403,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call) int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; - if (num < 0 || num >= NR_syscalls) + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) return -ENOSYS; mutex_lock(&syscall_trace_lock); if (!sys_refcount_exit) @@ -410,7 +421,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call) int num; num = ((struct syscall_metadata *)call->data)->syscall_nr; - if (num < 0 || num >= NR_syscalls) + if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls)) return; mutex_lock(&syscall_trace_lock); sys_refcount_exit--; @@ -423,6 +434,14 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call) int init_syscall_trace(struct ftrace_event_call *call) { int id; + int num; + + num = ((struct syscall_metadata *)call->data)->syscall_nr; + if (num < 0 || num >= NR_syscalls) { + pr_debug("syscall %s metadata not mapped, disabling ftrace event\n", + ((struct syscall_metadata *)call->data)->name); + return -ENOSYS; + } if (set_syscall_print_fmt(call) < 0) return -ENOMEM; @@ -437,7 +456,7 @@ int init_syscall_trace(struct ftrace_event_call *call) return id; } -unsigned long __init arch_syscall_addr(int nr) +unsigned long __init __weak arch_syscall_addr(int nr) { return (unsigned long)sys_call_table[nr]; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index e95ee7f..68187af 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -27,8 +27,8 @@ #include <linux/sched.h> #include <linux/jump_label.h> -extern struct tracepoint __start___tracepoints[]; -extern struct tracepoint __stop___tracepoints[]; +extern struct tracepoint * const __start___tracepoints_ptrs[]; +extern struct tracepoint * const __stop___tracepoints_ptrs[]; /* Set to 1 to enable tracepoint debug output */ static const int tracepoint_debug; @@ -298,10 +298,10 @@ static void disable_tracepoint(struct tracepoint *elem) * * Updates the probe callback corresponding to a range of tracepoints. */ -void -tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end) +void tracepoint_update_probe_range(struct tracepoint * const *begin, + struct tracepoint * const *end) { - struct tracepoint *iter; + struct tracepoint * const *iter; struct tracepoint_entry *mark_entry; if (!begin) @@ -309,12 +309,12 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end) mutex_lock(&tracepoints_mutex); for (iter = begin; iter < end; iter++) { - mark_entry = get_tracepoint(iter->name); + mark_entry = get_tracepoint((*iter)->name); if (mark_entry) { - set_tracepoint(&mark_entry, iter, + set_tracepoint(&mark_entry, *iter, !!mark_entry->refcount); } else { - disable_tracepoint(iter); + disable_tracepoint(*iter); } } mutex_unlock(&tracepoints_mutex); @@ -326,8 +326,8 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end) static void tracepoint_update_probes(void) { /* Core kernel tracepoints */ - tracepoint_update_probe_range(__start___tracepoints, - __stop___tracepoints); + tracepoint_update_probe_range(__start___tracepoints_ptrs, + __stop___tracepoints_ptrs); /* tracepoints in modules. */ module_update_tracepoints(); } @@ -514,8 +514,8 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_update_all); * Will return the first tracepoint in the range if the input tracepoint is * NULL. */ -int tracepoint_get_iter_range(struct tracepoint **tracepoint, - struct tracepoint *begin, struct tracepoint *end) +int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, + struct tracepoint * const *begin, struct tracepoint * const *end) { if (!*tracepoint && begin != end) { *tracepoint = begin; @@ -534,7 +534,8 @@ static void tracepoint_get_iter(struct tracepoint_iter *iter) /* Core kernel tracepoints */ if (!iter->module) { found = tracepoint_get_iter_range(&iter->tracepoint, - __start___tracepoints, __stop___tracepoints); + __start___tracepoints_ptrs, + __stop___tracepoints_ptrs); if (found) goto end; } @@ -585,8 +586,8 @@ int tracepoint_module_notify(struct notifier_block *self, switch (val) { case MODULE_STATE_COMING: case MODULE_STATE_GOING: - tracepoint_update_probe_range(mod->tracepoints, - mod->tracepoints + mod->num_tracepoints); + tracepoint_update_probe_range(mod->tracepoints_ptrs, + mod->tracepoints_ptrs + mod->num_tracepoints); break; } return 0; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d7ebdf4..18bb157 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -27,7 +27,7 @@ #include <asm/irq_regs.h> #include <linux/perf_event.h> -int watchdog_enabled; +int watchdog_enabled = 1; int __read_mostly softlockup_thresh = 60; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif -static int no_watchdog; - - /* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: @@ -58,7 +55,7 @@ static int __init hardlockup_panic_setup(char *str) if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "0", 1)) - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); @@ -77,7 +74,7 @@ __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); @@ -85,7 +82,7 @@ __setup("nowatchdog", nowatchdog_setup); /* deprecated */ static int __init nosoftlockup_setup(char *str) { - no_watchdog = 1; + watchdog_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); @@ -366,8 +363,14 @@ static int watchdog_nmi_enable(int cpu) goto out_save; } - printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); + + /* vary the KERN level based on the returned errno */ + if (PTR_ERR(event) == -EOPNOTSUPP) + printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu); + else if (PTR_ERR(event) == -ENOENT) + printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu); + else + printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event)); return PTR_ERR(event); /* success path */ @@ -432,9 +435,6 @@ static int watchdog_enable(int cpu) wake_up_process(p); } - /* if any cpu succeeds, watchdog is considered enabled for the system */ - watchdog_enabled = 1; - return 0; } @@ -462,12 +462,16 @@ static void watchdog_disable(int cpu) static void watchdog_enable_all_cpus(void) { int cpu; - int result = 0; + + watchdog_enabled = 0; for_each_online_cpu(cpu) - result += watchdog_enable(cpu); + if (!watchdog_enable(cpu)) + /* if any cpu succeeds, watchdog is considered + enabled for the system */ + watchdog_enabled = 1; - if (result) + if (!watchdog_enabled) printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); } @@ -476,9 +480,6 @@ static void watchdog_disable_all_cpus(void) { int cpu; - if (no_watchdog) - return; - for_each_online_cpu(cpu) watchdog_disable(cpu); @@ -498,10 +499,12 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write, { proc_dointvec(table, write, buffer, length, ppos); - if (watchdog_enabled) - watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); + if (write) { + if (watchdog_enabled) + watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + } return 0; } @@ -530,7 +533,8 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - err = watchdog_enable(hotcpu); + if (watchdog_enabled) + err = watchdog_enable(hotcpu); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: @@ -555,9 +559,6 @@ void __init lockup_detector_init(void) void *cpu = (void *)(long)smp_processor_id(); int err; - if (no_watchdog) - return; - err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); WARN_ON(notifier_to_errno(err)); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 11869fa..b5fe4c0 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -79,7 +79,9 @@ enum { MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ - MAYDAY_INITIAL_TIMEOUT = HZ / 100, /* call for help after 10ms */ + MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, + /* call for help after 10ms + (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ TRUSTEE_COOLDOWN = HZ / 10, /* for trustee draining */ @@ -314,6 +316,11 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask, static struct debug_obj_descr work_debug_descr; +static void *work_debug_hint(void *addr) +{ + return ((struct work_struct *) addr)->func; +} + /* * fixup_init is called when: * - an active object is initialized @@ -385,6 +392,7 @@ static int work_fixup_free(void *addr, enum debug_obj_state state) static struct debug_obj_descr work_debug_descr = { .name = "work_struct", + .debug_hint = work_debug_hint, .fixup_init = work_fixup_init, .fixup_activate = work_fixup_activate, .fixup_free = work_fixup_free, @@ -2047,6 +2055,15 @@ repeat: move_linked_works(work, scheduled, &n); process_scheduled_works(rescuer); + + /* + * Leave this gcwq. If keep_working() is %true, notify a + * regular worker; otherwise, we end up with 0 concurrency + * and stalling the execution. + */ + if (keep_working(gcwq)) + wake_up_worker(gcwq); + spin_unlock_irq(&gcwq->lock); } @@ -2956,7 +2973,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name, */ spin_lock(&workqueue_lock); - if (workqueue_freezing && wq->flags & WQ_FREEZEABLE) + if (workqueue_freezing && wq->flags & WQ_FREEZABLE) for_each_cwq_cpu(cpu, wq) get_cwq(cpu, wq)->max_active = 0; @@ -3068,7 +3085,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) spin_lock_irq(&gcwq->lock); - if (!(wq->flags & WQ_FREEZEABLE) || + if (!(wq->flags & WQ_FREEZABLE) || !(gcwq->flags & GCWQ_FREEZING)) get_cwq(gcwq->cpu, wq)->max_active = max_active; @@ -3318,7 +3335,7 @@ static int __cpuinit trustee_thread(void *__gcwq) * want to get it over with ASAP - spam rescuers, wake up as * many idlers as necessary and create new ones till the * worklist is empty. Note that if the gcwq is frozen, there - * may be frozen works in freezeable cwqs. Don't declare + * may be frozen works in freezable cwqs. Don't declare * completion while frozen. */ while (gcwq->nr_workers != gcwq->nr_idle || @@ -3576,9 +3593,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu); /** * freeze_workqueues_begin - begin freezing workqueues * - * Start freezing workqueues. After this function returns, all - * freezeable workqueues will queue new works to their frozen_works - * list instead of gcwq->worklist. + * Start freezing workqueues. After this function returns, all freezable + * workqueues will queue new works to their frozen_works list instead of + * gcwq->worklist. * * CONTEXT: * Grabs and releases workqueue_lock and gcwq->lock's. @@ -3604,7 +3621,7 @@ void freeze_workqueues_begin(void) list_for_each_entry(wq, &workqueues, list) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - if (cwq && wq->flags & WQ_FREEZEABLE) + if (cwq && wq->flags & WQ_FREEZABLE) cwq->max_active = 0; } @@ -3615,7 +3632,7 @@ void freeze_workqueues_begin(void) } /** - * freeze_workqueues_busy - are freezeable workqueues still busy? + * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). @@ -3624,8 +3641,8 @@ void freeze_workqueues_begin(void) * Grabs and releases workqueue_lock. * * RETURNS: - * %true if some freezeable workqueues are still busy. %false if - * freezing is complete. + * %true if some freezable workqueues are still busy. %false if freezing + * is complete. */ bool freeze_workqueues_busy(void) { @@ -3645,7 +3662,7 @@ bool freeze_workqueues_busy(void) list_for_each_entry(wq, &workqueues, list) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - if (!cwq || !(wq->flags & WQ_FREEZEABLE)) + if (!cwq || !(wq->flags & WQ_FREEZABLE)) continue; BUG_ON(cwq->nr_active < 0); @@ -3690,7 +3707,7 @@ void thaw_workqueues(void) list_for_each_entry(wq, &workqueues, list) { struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - if (!cwq || !(wq->flags & WQ_FREEZEABLE)) + if (!cwq || !(wq->flags & WQ_FREEZABLE)) continue; /* restore max_active and repopulate worklist */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 3967c235..2b97418 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -805,7 +805,7 @@ config ARCH_WANT_FRAME_POINTERS config FRAME_POINTER bool "Compile the kernel with frame pointers" depends on DEBUG_KERNEL && \ - (CRIS || M68K || M68KNOMMU || FRV || UML || \ + (CRIS || M68K || FRV || UML || \ AVR32 || SUPERH || BLACKFIN || MN10300) || \ ARCH_WANT_FRAME_POINTERS default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS diff --git a/lib/debugobjects.c b/lib/debugobjects.c index deebcc5..9d86e45 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -249,14 +249,17 @@ static struct debug_bucket *get_bucket(unsigned long addr) static void debug_print_object(struct debug_obj *obj, char *msg) { + struct debug_obj_descr *descr = obj->descr; static int limit; - if (limit < 5 && obj->descr != descr_test) { + if (limit < 5 && descr != descr_test) { + void *hint = descr->debug_hint ? + descr->debug_hint(obj->object) : NULL; limit++; WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) " - "object type: %s\n", + "object type: %s hint: %pS\n", msg, obj_states[obj->state], obj->astate, - obj->descr->name); + descr->name, hint); } debug_objects_warnings++; } diff --git a/lib/list_debug.c b/lib/list_debug.c index 344c710..b8029a5 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -35,6 +35,31 @@ void __list_add(struct list_head *new, } EXPORT_SYMBOL(__list_add); +void __list_del_entry(struct list_head *entry) +{ + struct list_head *prev, *next; + + prev = entry->prev; + next = entry->next; + + if (WARN(next == LIST_POISON1, + "list_del corruption, %p->next is LIST_POISON1 (%p)\n", + entry, LIST_POISON1) || + WARN(prev == LIST_POISON2, + "list_del corruption, %p->prev is LIST_POISON2 (%p)\n", + entry, LIST_POISON2) || + WARN(prev->next != entry, + "list_del corruption. prev->next should be %p, " + "but was %p\n", entry, prev->next) || + WARN(next->prev != entry, + "list_del corruption. next->prev should be %p, " + "but was %p\n", entry, next->prev)) + return; + + __list_del(prev, next); +} +EXPORT_SYMBOL(__list_del_entry); + /** * list_del - deletes entry from list. * @entry: the element to delete from the list. @@ -43,19 +68,7 @@ EXPORT_SYMBOL(__list_add); */ void list_del(struct list_head *entry) { - WARN(entry->next == LIST_POISON1, - "list_del corruption, next is LIST_POISON1 (%p)\n", - LIST_POISON1); - WARN(entry->next != LIST_POISON1 && entry->prev == LIST_POISON2, - "list_del corruption, prev is LIST_POISON2 (%p)\n", - LIST_POISON2); - WARN(entry->prev->next != entry, - "list_del corruption. prev->next should be %p, " - "but was %p\n", entry, entry->prev->next); - WARN(entry->next->prev != entry, - "list_del corruption. next->prev should be %p, " - "but was %p\n", entry, entry->next->prev); - __list_del(entry->prev, entry->next); + __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } diff --git a/lib/nlattr.c b/lib/nlattr.c index 5021cbc..ac09f22 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -148,7 +148,7 @@ nla_policy_len(const struct nla_policy *p, int n) { int i, len = 0; - for (i = 0; i < n; i++) { + for (i = 0; i < n; i++, p++) { if (p->len) len += nla_total_size(p->len); else if (nla_attr_minlen[p->type]) diff --git a/lib/plist.c b/lib/plist.c index 1471988..0ae7e64 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -28,6 +28,8 @@ #ifdef CONFIG_DEBUG_PI_LIST +static struct plist_head test_head; + static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { @@ -54,12 +56,13 @@ static void plist_check_list(struct list_head *top) static void plist_check_head(struct plist_head *head) { - WARN_ON(!head->rawlock && !head->spinlock); + WARN_ON(head != &test_head && !head->rawlock && !head->spinlock); if (head->rawlock) WARN_ON_SMP(!raw_spin_is_locked(head->rawlock)); if (head->spinlock) WARN_ON_SMP(!spin_is_locked(head->spinlock)); - plist_check_list(&head->prio_list); + if (!plist_head_empty(head)) + plist_check_list(&plist_first(head)->prio_list); plist_check_list(&head->node_list); } @@ -75,25 +78,33 @@ static void plist_check_head(struct plist_head *head) */ void plist_add(struct plist_node *node, struct plist_head *head) { - struct plist_node *iter; + struct plist_node *first, *iter, *prev = NULL; + struct list_head *node_next = &head->node_list; plist_check_head(head); WARN_ON(!plist_node_empty(node)); + WARN_ON(!list_empty(&node->prio_list)); + + if (plist_head_empty(head)) + goto ins_node; - list_for_each_entry(iter, &head->prio_list, plist.prio_list) { - if (node->prio < iter->prio) - goto lt_prio; - else if (node->prio == iter->prio) { - iter = list_entry(iter->plist.prio_list.next, - struct plist_node, plist.prio_list); - goto eq_prio; + first = iter = plist_first(head); + + do { + if (node->prio < iter->prio) { + node_next = &iter->node_list; + break; } - } -lt_prio: - list_add_tail(&node->plist.prio_list, &iter->plist.prio_list); -eq_prio: - list_add_tail(&node->plist.node_list, &iter->plist.node_list); + prev = iter; + iter = list_entry(iter->prio_list.next, + struct plist_node, prio_list); + } while (iter != first); + + if (!prev || prev->prio != node->prio) + list_add_tail(&node->prio_list, &iter->prio_list); +ins_node: + list_add_tail(&node->node_list, node_next); plist_check_head(head); } @@ -108,14 +119,98 @@ void plist_del(struct plist_node *node, struct plist_head *head) { plist_check_head(head); - if (!list_empty(&node->plist.prio_list)) { - struct plist_node *next = plist_first(&node->plist); + if (!list_empty(&node->prio_list)) { + if (node->node_list.next != &head->node_list) { + struct plist_node *next; + + next = list_entry(node->node_list.next, + struct plist_node, node_list); - list_move_tail(&next->plist.prio_list, &node->plist.prio_list); - list_del_init(&node->plist.prio_list); + /* add the next plist_node into prio_list */ + if (list_empty(&next->prio_list)) + list_add(&next->prio_list, &node->prio_list); + } + list_del_init(&node->prio_list); } - list_del_init(&node->plist.node_list); + list_del_init(&node->node_list); plist_check_head(head); } + +#ifdef CONFIG_DEBUG_PI_LIST +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/init.h> + +static struct plist_node __initdata test_node[241]; + +static void __init plist_test_check(int nr_expect) +{ + struct plist_node *first, *prio_pos, *node_pos; + + if (plist_head_empty(&test_head)) { + BUG_ON(nr_expect != 0); + return; + } + + prio_pos = first = plist_first(&test_head); + plist_for_each(node_pos, &test_head) { + if (nr_expect-- < 0) + break; + if (node_pos == first) + continue; + if (node_pos->prio == prio_pos->prio) { + BUG_ON(!list_empty(&node_pos->prio_list)); + continue; + } + + BUG_ON(prio_pos->prio > node_pos->prio); + BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list); + prio_pos = node_pos; + } + + BUG_ON(nr_expect != 0); + BUG_ON(prio_pos->prio_list.next != &first->prio_list); +} + +static int __init plist_test(void) +{ + int nr_expect = 0, i, loop; + unsigned int r = local_clock(); + + printk(KERN_INFO "start plist test\n"); + plist_head_init(&test_head, NULL); + for (i = 0; i < ARRAY_SIZE(test_node); i++) + plist_node_init(test_node + i, 0); + + for (loop = 0; loop < 1000; loop++) { + r = r * 193939 % 47629; + i = r % ARRAY_SIZE(test_node); + if (plist_node_empty(test_node + i)) { + r = r * 193939 % 47629; + test_node[i].prio = r % 99; + plist_add(test_node + i, &test_head); + nr_expect++; + } else { + plist_del(test_node + i, &test_head); + nr_expect--; + } + plist_test_check(nr_expect); + } + + for (i = 0; i < ARRAY_SIZE(test_node); i++) { + if (plist_node_empty(test_node + i)) + continue; + plist_del(test_node + i, &test_head); + nr_expect--; + plist_test_check(nr_expect); + } + + printk(KERN_INFO "end plist test\n"); + return 0; +} + +module_init(plist_test); + +#endif diff --git a/lib/rwsem.c b/lib/rwsem.c index f236d7c..aa7c305 100644 --- a/lib/rwsem.c +++ b/lib/rwsem.c @@ -222,8 +222,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem, /* * wait for the read lock to be granted */ -asmregparm struct rw_semaphore __sched * -rwsem_down_read_failed(struct rw_semaphore *sem) +struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) { return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_READ, -RWSEM_ACTIVE_READ_BIAS); @@ -232,8 +231,7 @@ rwsem_down_read_failed(struct rw_semaphore *sem) /* * wait for the write lock to be granted */ -asmregparm struct rw_semaphore __sched * -rwsem_down_write_failed(struct rw_semaphore *sem) +struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) { return rwsem_down_failed_common(sem, RWSEM_WAITING_FOR_WRITE, -RWSEM_ACTIVE_WRITE_BIAS); @@ -243,7 +241,7 @@ rwsem_down_write_failed(struct rw_semaphore *sem) * handle waking up a waiter on the semaphore * - up_read/up_write has decremented the active part of count if we come here */ -asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) +struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; @@ -263,7 +261,7 @@ asmregparm struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) * - caller incremented waiting part of count and discovered it still negative * - just wake up any readers at the front of the queue */ -asmregparm struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) +struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) { unsigned long flags; diff --git a/lib/swiotlb.c b/lib/swiotlb.c index c47bbe1..93ca08b 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -686,8 +686,10 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* * Ensure that the address returned is DMA'ble */ - if (!dma_capable(dev, dev_addr, size)) - panic("map_single: bounce buffer is not DMA'ble"); + if (!dma_capable(dev, dev_addr, size)) { + swiotlb_tbl_unmap_single(dev, map, size, dir); + dev_addr = swiotlb_virt_to_bus(dev, io_tlb_overflow_buffer); + } return dev_addr; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e187454..113e35c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -650,10 +650,10 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag) static inline struct page *alloc_hugepage_vma(int defrag, struct vm_area_struct *vma, - unsigned long haddr) + unsigned long haddr, int nd) { return alloc_pages_vma(alloc_hugepage_gfpmask(defrag), - HPAGE_PMD_ORDER, vma, haddr); + HPAGE_PMD_ORDER, vma, haddr, nd); } #ifndef CONFIG_NUMA @@ -678,7 +678,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(khugepaged_enter(vma))) return VM_FAULT_OOM; page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr); + vma, haddr, numa_node_id()); if (unlikely(!page)) goto out; if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { @@ -799,8 +799,8 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, } for (i = 0; i < HPAGE_PMD_NR; i++) { - pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE, - vma, address); + pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, + vma, address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_newpage_charge(pages[i], mm, GFP_KERNEL))) { @@ -902,7 +902,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr); + vma, haddr, numa_node_id()); else new_page = NULL; @@ -1162,7 +1162,12 @@ static void __split_huge_page_refcount(struct page *page) /* after clearing PageTail the gup refcount can be released */ smp_mb(); - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + /* + * retain hwpoison flag of the poisoned tail page: + * fix for the unsuitable process killed on Guest Machine(KVM) + * by the memory-failure. + */ + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; page_tail->flags |= (page->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | @@ -1740,7 +1745,8 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, - struct vm_area_struct *vma) + struct vm_area_struct *vma, + int node) { pgd_t *pgd; pud_t *pud; @@ -1756,6 +1762,10 @@ static void collapse_huge_page(struct mm_struct *mm, #ifndef CONFIG_NUMA VM_BUG_ON(!*hpage); new_page = *hpage; + if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + up_read(&mm->mmap_sem); + return; + } #else VM_BUG_ON(*hpage); /* @@ -1768,18 +1778,19 @@ static void collapse_huge_page(struct mm_struct *mm, * mmap_sem in read mode is good idea also to allow greater * scalability. */ - new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address); + new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address, + node); if (unlikely(!new_page)) { up_read(&mm->mmap_sem); *hpage = ERR_PTR(-ENOMEM); return; } -#endif if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { up_read(&mm->mmap_sem); put_page(new_page); return; } +#endif /* after allocating the hugepage upgrade to mmap_sem write mode */ up_read(&mm->mmap_sem); @@ -1806,6 +1817,8 @@ static void collapse_huge_page(struct mm_struct *mm, /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ if (!vma->anon_vma || vma->vm_ops || vma->vm_file) goto out; + if (is_vma_temporary_stack(vma)) + goto out; VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); pgd = pgd_offset(mm, address); @@ -1847,7 +1860,6 @@ static void collapse_huge_page(struct mm_struct *mm, set_pmd_at(mm, address, pmd, _pmd); spin_unlock(&mm->page_table_lock); anon_vma_unlock(vma->anon_vma); - mem_cgroup_uncharge_page(new_page); goto out; } @@ -1893,6 +1905,7 @@ out_up_write: return; out: + mem_cgroup_uncharge_page(new_page); #ifdef CONFIG_NUMA put_page(new_page); #endif @@ -1912,6 +1925,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, struct page *page; unsigned long _address; spinlock_t *ptl; + int node = -1; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -1942,6 +1956,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, page = vm_normal_page(vma, _address, pteval); if (unlikely(!page)) goto out_unmap; + /* + * Chose the node of the first page. This could + * be more sophisticated and look at more pages, + * but isn't for now. + */ + if (node == -1) + node = page_to_nid(page); VM_BUG_ON(PageCompound(page)); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; @@ -1958,7 +1979,7 @@ out_unmap: pte_unmap_unlock(pte, ptl); if (ret) /* collapse_huge_page will return with the mmap_sem released */ - collapse_huge_page(mm, address, hpage, vma); + collapse_huge_page(mm, address, hpage, vma, node); out: return ret; } @@ -2027,32 +2048,27 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || (vma->vm_flags & VM_NOHUGEPAGE)) { + skip: progress++; continue; } - /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ - if (!vma->anon_vma || vma->vm_ops || vma->vm_file) { - khugepaged_scan.address = vma->vm_end; - progress++; - continue; - } + if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + goto skip; + if (is_vma_temporary_stack(vma)) + goto skip; + VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart >= hend) { - progress++; - continue; - } + if (hstart >= hend) + goto skip; + if (khugepaged_scan.address > hend) + goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; - if (khugepaged_scan.address > hend) { - khugepaged_scan.address = hend + HPAGE_PMD_SIZE; - progress++; - continue; - } - BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); + VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { int ret; @@ -2081,7 +2097,7 @@ breakouterloop: breakouterloop_mmap_sem: spin_lock(&khugepaged_mm_lock); - BUG_ON(khugepaged_scan.mm_slot != mm_slot); + VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. @@ -2236,9 +2252,9 @@ static int khugepaged(void *none) for (;;) { mutex_unlock(&khugepaged_mutex); - BUG_ON(khugepaged_thread != current); + VM_BUG_ON(khugepaged_thread != current); khugepaged_loop(); - BUG_ON(khugepaged_thread != current); + VM_BUG_ON(khugepaged_thread != current); mutex_lock(&khugepaged_mutex); if (!khugepaged_enabled()) diff --git a/mm/memblock.c b/mm/memblock.c index bdba245..4618fda 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -137,8 +137,6 @@ static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size, BUG_ON(0 == size); - size = memblock_align_up(size, align); - /* Pump up max_addr */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) end = memblock.current_limit; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3878cfe..da53a25 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -612,8 +612,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]); - else + else { __this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]); + nr_pages = -nr_pages; /* for event */ + } __this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages); @@ -1111,6 +1113,23 @@ static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem) return false; } +/** + * mem_cgroup_check_margin - check if the memory cgroup allows charging + * @mem: memory cgroup to check + * @bytes: the number of bytes the caller intends to charge + * + * Returns a boolean value on whether @mem can be charged @bytes or + * whether this would exceed the limit. + */ +static bool mem_cgroup_check_margin(struct mem_cgroup *mem, unsigned long bytes) +{ + if (!res_counter_check_margin(&mem->res, bytes)) + return false; + if (do_swap_account && !res_counter_check_margin(&mem->memsw, bytes)) + return false; + return true; +} + static unsigned int get_swappiness(struct mem_cgroup *memcg) { struct cgroup *cgrp = memcg->css.cgroup; @@ -1837,23 +1856,34 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask, flags |= MEM_CGROUP_RECLAIM_NOSWAP; } else mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); - - if (csize > PAGE_SIZE) /* change csize and retry */ + /* + * csize can be either a huge page (HPAGE_SIZE), a batch of + * regular pages (CHARGE_SIZE), or a single regular page + * (PAGE_SIZE). + * + * Never reclaim on behalf of optional batching, retry with a + * single page instead. + */ + if (csize == CHARGE_SIZE) return CHARGE_RETRY; if (!(gfp_mask & __GFP_WAIT)) return CHARGE_WOULDBLOCK; ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL, - gfp_mask, flags); + gfp_mask, flags); + if (mem_cgroup_check_margin(mem_over_limit, csize)) + return CHARGE_RETRY; /* - * try_to_free_mem_cgroup_pages() might not give us a full - * picture of reclaim. Some pages are reclaimed and might be - * moved to swap cache or just unmapped from the cgroup. - * Check the limit again to see if the reclaim reduced the - * current usage of the cgroup before giving up + * Even though the limit is exceeded at this point, reclaim + * may have been able to free some pages. Retry the charge + * before killing the task. + * + * Only for regular pages, though: huge pages are rather + * unlikely to succeed so close to the limit, and we fall back + * to regular pages anyway in case of failure. */ - if (ret || mem_cgroup_check_under_limit(mem_over_limit)) + if (csize == PAGE_SIZE && ret) return CHARGE_RETRY; /* @@ -2323,13 +2353,19 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, enum charge_type ctype) { struct mem_cgroup *mem = NULL; + int page_size = PAGE_SIZE; struct page_cgroup *pc; + bool oom = true; int ret; - int page_size = PAGE_SIZE; if (PageTransHuge(page)) { page_size <<= compound_order(page); VM_BUG_ON(!PageTransHuge(page)); + /* + * Never OOM-kill a process for a huge page. The + * fault handler will fall back to regular pages. + */ + oom = false; } pc = lookup_page_cgroup(page); @@ -2338,7 +2374,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, return 0; prefetchw(pc); - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page_size); + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size); if (ret || !mem) return ret; @@ -5024,9 +5060,9 @@ struct cgroup_subsys mem_cgroup_subsys = { static int __init enable_swap_account(char *s) { /* consider enabled if no parameter or 1 is given */ - if (!s || !strcmp(s, "1")) + if (!(*s) || !strcmp(s, "=1")) really_do_swap_account = 1; - else if (!strcmp(s, "0")) + else if (!strcmp(s, "=0")) really_do_swap_account = 0; return 1; } @@ -5034,7 +5070,8 @@ __setup("swapaccount", enable_swap_account); static int __init disable_swap_account(char *s) { - enable_swap_account("0"); + printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n"); + enable_swap_account("=0"); return 1; } __setup("noswapaccount", disable_swap_account); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 548fbd7..0207c2f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -233,8 +233,8 @@ void shake_page(struct page *p, int access) } /* - * Only all shrink_slab here (which would also - * shrink other caches) if access is not potentially fatal. + * Only call shrink_slab here (which would also shrink other caches) if + * access is not potentially fatal. */ if (access) { int nr; @@ -386,8 +386,6 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct task_struct *tsk; struct anon_vma *av; - if (!PageHuge(page) && unlikely(split_huge_page(page))) - return; read_lock(&tasklist_lock); av = page_lock_anon_vma(page); if (av == NULL) /* Not actually mapped anymore */ @@ -856,6 +854,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, int ret; int kill = 1; struct page *hpage = compound_head(p); + struct page *ppage; if (PageReserved(p) || PageSlab(p)) return SWAP_SUCCESS; @@ -897,6 +896,44 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, } /* + * ppage: poisoned page + * if p is regular page(4k page) + * ppage == real poisoned page; + * else p is hugetlb or THP, ppage == head page. + */ + ppage = hpage; + + if (PageTransHuge(hpage)) { + /* + * Verify that this isn't a hugetlbfs head page, the check for + * PageAnon is just for avoid tripping a split_huge_page + * internal debug check, as split_huge_page refuses to deal with + * anything that isn't an anon page. PageAnon can't go away fro + * under us because we hold a refcount on the hpage, without a + * refcount on the hpage. split_huge_page can't be safely called + * in the first place, having a refcount on the tail isn't + * enough * to be safe. + */ + if (!PageHuge(hpage) && PageAnon(hpage)) { + if (unlikely(split_huge_page(hpage))) { + /* + * FIXME: if splitting THP is failed, it is + * better to stop the following operation rather + * than causing panic by unmapping. System might + * survive if the page is freed later. + */ + printk(KERN_INFO + "MCE %#lx: failed to split THP\n", pfn); + + BUG_ON(!PageHWPoison(p)); + return SWAP_FAIL; + } + /* THP is split, so ppage should be the real poisoned page. */ + ppage = p; + } + } + + /* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. @@ -905,12 +942,18 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * there's nothing that can be done. */ if (kill) - collect_procs(hpage, &tokill); + collect_procs(ppage, &tokill); + + if (hpage != ppage) + lock_page_nosync(ppage); - ret = try_to_unmap(hpage, ttu); + ret = try_to_unmap(ppage, ttu); if (ret != SWAP_SUCCESS) printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(ppage)); + + if (hpage != ppage) + unlock_page(ppage); /* * Now that the dirty bit has been propagated to the @@ -921,7 +964,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs_ao(&tokill, !!PageDirty(hpage), trapno, + kill_procs_ao(&tokill, !!PageDirty(ppage), trapno, ret != SWAP_SUCCESS, p, pfn); return ret; @@ -1022,19 +1065,22 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - if (!PageLRU(p) && !PageHuge(p)) - shake_page(p, 0); - if (!PageLRU(p) && !PageHuge(p)) { - /* - * shake_page could have turned it free. - */ - if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy, 2nd try", DELAYED); - return 0; + if (!PageHuge(p) && !PageTransCompound(p)) { + if (!PageLRU(p)) + shake_page(p, 0); + if (!PageLRU(p)) { + /* + * shake_page could have turned it free. + */ + if (is_free_buddy_page(p)) { + action_result(pfn, "free buddy, 2nd try", + DELAYED); + return 0; + } + action_result(pfn, "non LRU", IGNORED); + put_page(p); + return -EBUSY; } - action_result(pfn, "non LRU", IGNORED); - put_page(p); - return -EBUSY; } /* @@ -1064,7 +1110,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * For error on the tail page, we should set PG_hwpoison * on the head page to show that the hugepage is hwpoisoned */ - if (PageTail(p) && TestSetPageHWPoison(hpage)) { + if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { action_result(pfn, "hugepage already hardware poisoned", IGNORED); unlock_page(hpage); @@ -1295,7 +1341,10 @@ static int soft_offline_huge_page(struct page *page, int flags) ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, true); if (ret) { - putback_lru_pages(&pagelist); + struct page *page1, *page2; + list_for_each_entry_safe(page1, page2, &pagelist, lru) + put_page(page1); + pr_debug("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) @@ -1419,6 +1468,7 @@ int soft_offline_page(struct page *page, int flags) ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0, true); if (ret) { + putback_lru_pages(&pagelist); pr_info("soft offline: %#lx: migration failed %d, type %lx\n", pfn, ret, page->flags); if (ret > 0) diff --git a/mm/memory.c b/mm/memory.c index 31250fa..5823698 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2219,7 +2219,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, &ptl); if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); - page_cache_release(old_page); goto unlock; } page_cache_release(old_page); @@ -2289,7 +2288,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, &ptl); if (!pte_same(*page_table, orig_pte)) { unlock_page(old_page); - page_cache_release(old_page); goto unlock; } @@ -2367,16 +2365,6 @@ gotten: } __SetPageUptodate(new_page); - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if ((vma->vm_flags & VM_LOCKED) && old_page) { - lock_page(old_page); /* for LRU manipulation */ - clear_page_mlock(old_page); - unlock_page(old_page); - } - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; @@ -2444,10 +2432,20 @@ gotten: if (new_page) page_cache_release(new_page); - if (old_page) - page_cache_release(old_page); unlock: pte_unmap_unlock(page_table, ptl); + if (old_page) { + /* + * Don't let another task, with possibly unlocked vma, + * keep the mlocked page. + */ + if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) { + lock_page(old_page); /* LRU manipulation */ + munlock_vma_page(old_page); + unlock_page(old_page); + } + page_cache_release(old_page); + } return ret; oom_free_new: page_cache_release(new_page); @@ -2650,6 +2648,7 @@ void unmap_mapping_range(struct address_space *mapping, details.last_index = ULONG_MAX; details.i_mmap_lock = &mapping->i_mmap_lock; + mutex_lock(&mapping->unmap_mutex); spin_lock(&mapping->i_mmap_lock); /* Protect against endless unmapping loops */ @@ -2666,6 +2665,7 @@ void unmap_mapping_range(struct address_space *mapping, if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->unmap_mutex); } EXPORT_SYMBOL(unmap_mapping_range); @@ -3053,12 +3053,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto out; } charged = 1; - /* - * Don't let another task, with possibly unlocked vma, - * keep the mlocked page. - */ - if (vma->vm_flags & VM_LOCKED) - clear_page_mlock(vmf.page); copy_user_highpage(page, vmf.page, address, vma); __SetPageUptodate(page); } else { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 368fc9d..b53ec99 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1524,10 +1524,9 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) } /* Return a zonelist indicated by gfp for node representing a mempolicy */ -static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy) +static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, + int nd) { - int nd = numa_node_id(); - switch (policy->mode) { case MPOL_PREFERRED: if (!(policy->flags & MPOL_F_LOCAL)) @@ -1679,7 +1678,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, zl = node_zonelist(interleave_nid(*mpol, vma, addr, huge_page_shift(hstate_vma(vma))), gfp_flags); } else { - zl = policy_zonelist(gfp_flags, *mpol); + zl = policy_zonelist(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) *nodemask = &(*mpol)->v.nodes; } @@ -1820,7 +1819,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr) + unsigned long addr, int node) { struct mempolicy *pol = get_vma_policy(current, vma, addr); struct zonelist *zl; @@ -1830,13 +1829,13 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT); + nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); put_mems_allowed(); return page; } - zl = policy_zonelist(gfp, pol); + zl = policy_zonelist(gfp, pol, node); if (unlikely(mpol_needs_cond_ref(pol))) { /* * slow path: ref counted shared policy @@ -1892,7 +1891,8 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol), policy_nodemask(gfp, pol)); + policy_zonelist(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol)); put_mems_allowed(); return page; } diff --git a/mm/migrate.c b/mm/migrate.c index 9f29a3b..352de555 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -772,6 +772,7 @@ uncharge: unlock: unlock_page(page); +move_newpage: if (rc != -EAGAIN) { /* * A page that has been migrated has all references @@ -785,8 +786,6 @@ unlock: putback_lru_page(page); } -move_newpage: - /* * Move the new page to the LRU. If migration was not successful * then this will free the page. @@ -981,10 +980,6 @@ int migrate_huge_pages(struct list_head *from, } rc = 0; out: - - list_for_each_entry_safe(page, page2, from, lru) - put_page(page); - if (rc) return rc; @@ -1292,14 +1287,14 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, return -EPERM; /* Find the mm_struct */ - read_lock(&tasklist_lock); + rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { - read_unlock(&tasklist_lock); + rcu_read_unlock(); return -ESRCH; } mm = get_task_mm(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!mm) return -EINVAL; @@ -178,6 +178,13 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; + /* + * We want mlock to succeed for regions that have any permissions + * other than PROT_NONE. + */ + if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) + gup_flags |= FOLL_FORCE; + if (vma->vm_flags & VM_LOCKED) gup_flags |= FOLL_MLOCK; diff --git a/mm/mremap.c b/mm/mremap.c index 9925b63..1de98d4 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -94,9 +94,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, */ mapping = vma->vm_file->f_mapping; spin_lock(&mapping->i_mmap_lock); - if (new_vma->vm_truncate_count && - new_vma->vm_truncate_count != vma->vm_truncate_count) - new_vma->vm_truncate_count = 0; + new_vma->vm_truncate_count = 0; } /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a873e61..cdef1d4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5376,10 +5376,9 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; - if (!pfn_valid_within(check)) { - iter++; + if (!pfn_valid_within(check)) continue; - } + page = pfn_to_page(check); if (!page_count(page)) { if (PageBuddy(page)) @@ -497,41 +497,51 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int referenced = 0; - /* - * Don't want to elevate referenced for mlocked page that gets this far, - * in order that it progresses to try_to_unmap and is moved to the - * unevictable list. - */ - if (vma->vm_flags & VM_LOCKED) { - *mapcount = 0; /* break early from loop */ - *vm_flags |= VM_LOCKED; - goto out; - } - - /* Pretend the page is referenced if the task has the - swap token and is in the middle of a page fault. */ - if (mm != current->mm && has_swap_token(mm) && - rwsem_is_locked(&mm->mmap_sem)) - referenced++; - if (unlikely(PageTransHuge(page))) { pmd_t *pmd; spin_lock(&mm->page_table_lock); + /* + * rmap might return false positives; we must filter + * these out using page_check_address_pmd(). + */ pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_FLAG); - if (pmd && !pmd_trans_splitting(*pmd) && - pmdp_clear_flush_young_notify(vma, address, pmd)) + if (!pmd) { + spin_unlock(&mm->page_table_lock); + goto out; + } + + if (vma->vm_flags & VM_LOCKED) { + spin_unlock(&mm->page_table_lock); + *mapcount = 0; /* break early from loop */ + *vm_flags |= VM_LOCKED; + goto out; + } + + /* go ahead even if the pmd is pmd_trans_splitting() */ + if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; spin_unlock(&mm->page_table_lock); } else { pte_t *pte; spinlock_t *ptl; + /* + * rmap might return false positives; we must filter + * these out using page_check_address(). + */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) goto out; + if (vma->vm_flags & VM_LOCKED) { + pte_unmap_unlock(pte, ptl); + *mapcount = 0; /* break early from loop */ + *vm_flags |= VM_LOCKED; + goto out; + } + if (ptep_clear_flush_young_notify(vma, address, pte)) { /* * Don't treat a reference through a sequentially read @@ -546,6 +556,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } + /* Pretend the page is referenced if the task has the + swap token and is in the middle of a page fault. */ + if (mm != current->mm && has_swap_token(mm) && + rwsem_is_locked(&mm->mmap_sem)) + referenced++; + (*mapcount)--; if (referenced) @@ -2144,8 +2144,10 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len, { struct inode *inode = dentry->d_inode; - if (*len < 3) + if (*len < 3) { + *len = 3; return 255; + } if (inode_unhashed(inode)) { /* Unfortunately insert_inode_hash is not idempotent, diff --git a/mm/swapfile.c b/mm/swapfile.c index 07a458d..0341c57 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1940,7 +1940,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = -EINVAL; if (S_ISBLK(inode->i_mode)) { - bdev = I_BDEV(inode); + bdev = bdgrab(I_BDEV(inode)); error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, sys_swapon); if (error < 0) { diff --git a/mm/truncate.c b/mm/truncate.c index 49feb46..d64296b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -225,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping, next = start; while (next <= end && pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { + mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; pgoff_t page_index = page->index; @@ -247,6 +248,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unlock_page(page); } pagevec_release(&pvec); + mem_cgroup_uncharge_end(); cond_resched(); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 148c6e6..6771ea7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1841,16 +1841,28 @@ static inline bool should_continue_reclaim(struct zone *zone, if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION)) return false; - /* - * If we failed to reclaim and have scanned the full list, stop. - * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far - * faster but obviously would be less likely to succeed - * allocation. If this is desirable, use GFP_REPEAT to decide - * if both reclaimed and scanned should be checked or just - * reclaimed - */ - if (!nr_reclaimed && !nr_scanned) - return false; + /* Consider stopping depending on scan and reclaim activity */ + if (sc->gfp_mask & __GFP_REPEAT) { + /* + * For __GFP_REPEAT allocations, stop reclaiming if the + * full LRU list has been scanned and we are still failing + * to reclaim pages. This full LRU scan is potentially + * expensive but a __GFP_REPEAT caller really wants to succeed + */ + if (!nr_reclaimed && !nr_scanned) + return false; + } else { + /* + * For non-__GFP_REPEAT allocations which can presumably + * fail without consequence, stop if we failed to reclaim + * any pages from the last SWAP_CLUSTER_MAX number of + * pages that were scanned. This will return to the + * caller faster at the risk reclaim/compaction and + * the resulting allocation attempt fails + */ + if (!nr_reclaimed) + return false; + } /* * If we have not reclaimed enough pages for compaction and the @@ -1882,12 +1894,12 @@ static void shrink_zone(int priority, struct zone *zone, unsigned long nr[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list l; - unsigned long nr_reclaimed; + unsigned long nr_reclaimed, nr_scanned; unsigned long nr_to_reclaim = sc->nr_to_reclaim; - unsigned long nr_scanned = sc->nr_scanned; restart: nr_reclaimed = 0; + nr_scanned = sc->nr_scanned; get_scan_count(zone, sc, nr, priority); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || diff --git a/net/Makefile b/net/Makefile index a3330eb..a51d946 100644 --- a/net/Makefile +++ b/net/Makefile @@ -19,9 +19,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ -ifneq ($(CONFIG_IPV6),) -obj-y += ipv6/ -endif +obj-$(CONFIG_NET) += ipv6/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index ee41fef..d1a6113 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -50,12 +50,12 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, skb = tfp->skb; } + if (skb_linearize(skb) < 0 || skb_linearize(tmp_skb) < 0) + goto err; + skb_pull(tmp_skb, sizeof(struct unicast_frag_packet)); - if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0) { - /* free buffered skb, skb will be freed later */ - kfree_skb(tfp->skb); - return NULL; - } + if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0) + goto err; /* move free entry to end */ tfp->skb = NULL; @@ -70,6 +70,11 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, unicast_packet->packet_type = BAT_UNICAST; return skb; + +err: + /* free buffered skb, skb will be freed later */ + kfree_skb(tfp->skb); + return NULL; } static void frag_create_entry(struct list_head *head, struct sk_buff *skb) diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index cd4c423..de1022c 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -64,6 +64,7 @@ static void free_info(struct kref *ref) spin_unlock_bh(&bat_priv->vis_list_lock); kfree_skb(info->skb_packet); + kfree(info); } /* Compare two vis packets, used by the hashing algorithm */ @@ -268,10 +269,10 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) buff_pos += sprintf(buff + buff_pos, "%pM,", entry->addr); - for (i = 0; i < packet->entries; i++) + for (j = 0; j < packet->entries; j++) buff_pos += vis_data_read_entry( buff + buff_pos, - &entries[i], + &entries[j], entry->addr, entry->primary); @@ -444,7 +445,7 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, info); if (hash_added < 0) { /* did not work (for some reason) */ - kref_put(&old_info->refcount, free_info); + kref_put(&info->refcount, free_info); info = NULL; } @@ -815,7 +816,7 @@ static void send_vis_packets(struct work_struct *work) container_of(work, struct delayed_work, work); struct bat_priv *bat_priv = container_of(delayed_work, struct bat_priv, vis_work); - struct vis_info *info, *temp; + struct vis_info *info; spin_lock_bh(&bat_priv->vis_hash_lock); purge_vis_packets(bat_priv); @@ -825,8 +826,9 @@ static void send_vis_packets(struct work_struct *work) send_list_add(bat_priv, bat_priv->my_vis_info); } - list_for_each_entry_safe(info, temp, &bat_priv->vis_send_list, - send_list) { + while (!list_empty(&bat_priv->vis_send_list)) { + info = list_first_entry(&bat_priv->vis_send_list, + typeof(*info), send_list); kref_get(&info->refcount); spin_unlock_bh(&bat_priv->vis_hash_lock); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 7550abb..675614e 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -859,6 +859,7 @@ static void __l2cap_sock_close(struct sock *sk, int reason) result = L2CAP_CR_SEC_BLOCK; else result = L2CAP_CR_BAD_PSM; + sk->sk_state = BT_DISCONN; rsp.scid = cpu_to_le16(l2cap_pi(sk)->dcid); rsp.dcid = cpu_to_le16(l2cap_pi(sk)->scid); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 2575c2d..d7b9af4 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -727,7 +727,9 @@ static int rfcomm_tty_open(struct tty_struct *tty, struct file *filp) break; } + tty_unlock(); schedule(); + tty_lock(); } set_current_state(TASK_RUNNING); remove_wait_queue(&dev->wait, &wait); diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index 9190ae4..6dee7bf 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -6,6 +6,7 @@ config BRIDGE tristate "802.1d Ethernet Bridging" select LLC select STP + depends on IPV6 || IPV6=n ---help--- If you say Y here, then your Linux box will be able to act as an Ethernet bridge, which means that the different Ethernet segments it diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 2872393..88485cc 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -328,12 +328,12 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (fdb) { memcpy(fdb->addr.addr, addr, ETH_ALEN); - hlist_add_head_rcu(&fdb->hlist, head); - fdb->dst = source; fdb->is_local = is_local; fdb->is_static = is_local; fdb->ageing_timer = jiffies; + + hlist_add_head_rcu(&fdb->hlist, head); } return fdb; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 6f6d8e1..88e4aa9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -80,7 +80,7 @@ int br_handle_frame_finish(struct sk_buff *skb) if (is_multicast_ether_addr(dest)) { mdst = br_mdb_get(br, skb); if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) { - if ((mdst && !hlist_unhashed(&mdst->mglist)) || + if ((mdst && mdst->mglist) || br_multicast_is_router(br)) skb2 = skb; br_multicast_forward(mdst, skb, skb2); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f701a21..030a002 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -37,10 +37,9 @@ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static inline int ipv6_is_local_multicast(const struct in6_addr *addr) +static inline int ipv6_is_transient_multicast(const struct in6_addr *addr) { - if (ipv6_addr_is_multicast(addr) && - IPV6_ADDR_MC_SCOPE(addr) <= IPV6_ADDR_SCOPE_LINKLOCAL) + if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr)) return 1; return 0; } @@ -232,8 +231,7 @@ static void br_multicast_group_expired(unsigned long data) if (!netif_running(br->dev) || timer_pending(&mp->timer)) goto out; - if (!hlist_unhashed(&mp->mglist)) - hlist_del_init(&mp->mglist); + mp->mglist = false; if (mp->ports) goto out; @@ -276,7 +274,7 @@ static void br_multicast_del_pg(struct net_bridge *br, del_timer(&p->query_timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && hlist_unhashed(&mp->mglist) && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -436,7 +434,6 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, eth = eth_hdr(skb); memcpy(eth->h_source, br->dev->dev_addr, 6); - ipv6_eth_mc_map(group, eth->h_dest); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); @@ -448,8 +445,10 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, ip6h->payload_len = htons(8 + sizeof(*mldq)); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; - ipv6_addr_set(&ip6h->saddr, 0, 0, 0, 0); + ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, + &ip6h->saddr); ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); + ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); hopopt[0] = IPPROTO_ICMPV6; /* next hdr */ @@ -528,7 +527,7 @@ static void br_multicast_group_query_expired(unsigned long data) struct net_bridge *br = mp->br; spin_lock(&br->multicast_lock); - if (!netif_running(br->dev) || hlist_unhashed(&mp->mglist) || + if (!netif_running(br->dev) || !mp->mglist || mp->queries_sent >= br->multicast_last_member_count) goto out; @@ -719,7 +718,7 @@ static int br_multicast_add_group(struct net_bridge *br, goto err; if (!port) { - hlist_add_head(&mp->mglist, &br->mglist); + mp->mglist = true; mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -781,11 +780,11 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, { struct br_ip br_group; - if (ipv6_is_local_multicast(group)) + if (!ipv6_is_transient_multicast(group)) return 0; ipv6_addr_copy(&br_group.u.ip6, group); - br_group.proto = htons(ETH_P_IP); + br_group.proto = htons(ETH_P_IPV6); return br_multicast_add_group(br, port, &br_group); } @@ -1014,18 +1013,19 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs = skb_header_pointer(skb, len + offsetof(struct mld2_grec, - grec_mca), + grec_nsrcs), sizeof(_nsrcs), &_nsrcs); if (!nsrcs) return -EINVAL; if (!pskb_may_pull(skb, len + sizeof(*grec) + - sizeof(struct in6_addr) * (*nsrcs))) + sizeof(struct in6_addr) * ntohs(*nsrcs))) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); - len += sizeof(*grec) + sizeof(struct in6_addr) * (*nsrcs); + len += sizeof(*grec) + + sizeof(struct in6_addr) * ntohs(*nsrcs); /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1165,7 +1165,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, max_delay *= br->multicast_last_member_count; - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1177,7 +1177,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) - mod_timer(&mp->timer, now + max_delay); + mod_timer(&p->timer, now + max_delay); } out: @@ -1236,7 +1236,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, goto out; max_delay *= br->multicast_last_member_count; - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) @@ -1248,7 +1248,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) - mod_timer(&mp->timer, now + max_delay); + mod_timer(&p->timer, now + max_delay); } out: @@ -1283,7 +1283,7 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (!hlist_unhashed(&mp->mglist) && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { @@ -1341,7 +1341,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, { struct br_ip br_group; - if (ipv6_is_local_multicast(group)) + if (!ipv6_is_transient_multicast(group)) return; ipv6_addr_copy(&br_group.u.ip6, group); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 84aac77..4e1b620 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -84,13 +84,13 @@ struct net_bridge_port_group { struct net_bridge_mdb_entry { struct hlist_node hlist[2]; - struct hlist_node mglist; struct net_bridge *br; struct net_bridge_port_group __rcu *ports; struct rcu_head rcu; struct timer_list timer; struct timer_list query_timer; struct br_ip addr; + bool mglist; u32 queries_sent; }; @@ -238,7 +238,6 @@ struct net_bridge spinlock_t multicast_lock; struct net_bridge_mdb_htable __rcu *mdb; struct hlist_head router_list; - struct hlist_head mglist; struct timer_list multicast_router_timer; struct timer_list multicast_querier_timer; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index fa9dab3..6008d6d 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -394,9 +394,7 @@ static void ipcaif_net_setup(struct net_device *dev) priv->conn_req.sockaddr.u.dgm.connection_id = -1; priv->flowenabled = false; - ASSERT_RTNL(); init_waitqueue_head(&priv->netmgmt_wq); - list_add(&priv->list_field, &chnl_net_list); } @@ -453,6 +451,8 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev, ret = register_netdevice(dev); if (ret) pr_warn("device rtml registration failed\n"); + else + list_add(&caifdev->list_field, &chnl_net_list); return ret; } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index dff633d..05f3578 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -252,8 +252,12 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) { struct kvec iov = {buf, len}; struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + int r; - return kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); + r = kernel_recvmsg(sock, &msg, &iov, 1, len, msg.msg_flags); + if (r == -EAGAIN) + r = 0; + return r; } /* @@ -264,13 +268,17 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, size_t kvlen, size_t len, int more) { struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL }; + int r; if (more) msg.msg_flags |= MSG_MORE; else msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ - return kernel_sendmsg(sock, &msg, iov, kvlen, len); + r = kernel_sendmsg(sock, &msg, iov, kvlen, len); + if (r == -EAGAIN) + r = 0; + return r; } @@ -328,7 +336,6 @@ static void reset_connection(struct ceph_connection *con) ceph_msg_put(con->out_msg); con->out_msg = NULL; } - con->out_keepalive_pending = false; con->in_seq = 0; con->in_seq_acked = 0; } @@ -847,6 +854,8 @@ static int write_partial_msg_pages(struct ceph_connection *con) (msg->pages || msg->pagelist || msg->bio || in_trail)) kunmap(page); + if (ret == -EAGAIN) + ret = 0; if (ret <= 0) goto out; @@ -1238,8 +1247,6 @@ static int process_connect(struct ceph_connection *con) con->auth_retry); if (con->auth_retry == 2) { con->error_msg = "connect authorization failure"; - reset_connection(con); - set_bit(CLOSED, &con->state); return -1; } con->auth_retry = 1; @@ -1705,14 +1712,6 @@ more: /* open the socket first? */ if (con->sock == NULL) { - /* - * if we were STANDBY and are reconnecting _this_ - * connection, bump connect_seq now. Always bump - * global_seq. - */ - if (test_and_clear_bit(STANDBY, &con->state)) - con->connect_seq++; - prepare_write_banner(msgr, con); prepare_write_connect(msgr, con, 1); prepare_read_banner(con); @@ -1737,16 +1736,12 @@ more_kvec: if (con->out_skip) { ret = write_partial_skip(con); if (ret <= 0) - goto done; - if (ret < 0) { - dout("try_write write_partial_skip err %d\n", ret); - goto done; - } + goto out; } if (con->out_kvec_left) { ret = write_partial_kvec(con); if (ret <= 0) - goto done; + goto out; } /* msg pages? */ @@ -1761,11 +1756,11 @@ more_kvec: if (ret == 1) goto more_kvec; /* we need to send the footer, too! */ if (ret == 0) - goto done; + goto out; if (ret < 0) { dout("try_write write_partial_msg_pages err %d\n", ret); - goto done; + goto out; } } @@ -1789,10 +1784,9 @@ do_next: /* Nothing to do! */ clear_bit(WRITE_PENDING, &con->state); dout("try_write nothing else to write.\n"); -done: ret = 0; out: - dout("try_write done on %p\n", con); + dout("try_write done on %p ret %d\n", con, ret); return ret; } @@ -1821,19 +1815,17 @@ more: dout("try_read connecting\n"); ret = read_partial_banner(con); if (ret <= 0) - goto done; - if (process_banner(con) < 0) { - ret = -1; goto out; - } + ret = process_banner(con); + if (ret < 0) + goto out; } ret = read_partial_connect(con); if (ret <= 0) - goto done; - if (process_connect(con) < 0) { - ret = -1; goto out; - } + ret = process_connect(con); + if (ret < 0) + goto out; goto more; } @@ -1848,7 +1840,7 @@ more: dout("skipping %d / %d bytes\n", skip, -con->in_base_pos); ret = ceph_tcp_recvmsg(con->sock, buf, skip); if (ret <= 0) - goto done; + goto out; con->in_base_pos += ret; if (con->in_base_pos) goto more; @@ -1859,7 +1851,7 @@ more: */ ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1); if (ret <= 0) - goto done; + goto out; dout("try_read got tag %d\n", (int)con->in_tag); switch (con->in_tag) { case CEPH_MSGR_TAG_MSG: @@ -1870,7 +1862,7 @@ more: break; case CEPH_MSGR_TAG_CLOSE: set_bit(CLOSED, &con->state); /* fixme */ - goto done; + goto out; default: goto bad_tag; } @@ -1882,13 +1874,12 @@ more: case -EBADMSG: con->error_msg = "bad crc"; ret = -EIO; - goto out; + break; case -EIO: con->error_msg = "io error"; - goto out; - default: - goto done; + break; } + goto out; } if (con->in_tag == CEPH_MSGR_TAG_READY) goto more; @@ -1898,15 +1889,13 @@ more: if (con->in_tag == CEPH_MSGR_TAG_ACK) { ret = read_partial_ack(con); if (ret <= 0) - goto done; + goto out; process_ack(con); goto more; } -done: - ret = 0; out: - dout("try_read done on %p\n", con); + dout("try_read done on %p ret %d\n", con, ret); return ret; bad_tag: @@ -1951,7 +1940,24 @@ static void con_work(struct work_struct *work) work.work); mutex_lock(&con->mutex); + if (test_and_clear_bit(BACKOFF, &con->state)) { + dout("con_work %p backing off\n", con); + if (queue_delayed_work(ceph_msgr_wq, &con->work, + round_jiffies_relative(con->delay))) { + dout("con_work %p backoff %lu\n", con, con->delay); + mutex_unlock(&con->mutex); + return; + } else { + con->ops->put(con); + dout("con_work %p FAILED to back off %lu\n", con, + con->delay); + } + } + if (test_bit(STANDBY, &con->state)) { + dout("con_work %p STANDBY\n", con); + goto done; + } if (test_bit(CLOSED, &con->state)) { /* e.g. if we are replaced */ dout("con_work CLOSED\n"); con_close_socket(con); @@ -2008,10 +2014,12 @@ static void ceph_fault(struct ceph_connection *con) /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); - /* If there are no messages in the queue, place the connection - * in a STANDBY state (i.e., don't try to reconnect just yet). */ - if (list_empty(&con->out_queue) && !con->out_keepalive_pending) { - dout("fault setting STANDBY\n"); + /* If there are no messages queued or keepalive pending, place + * the connection in a STANDBY state */ + if (list_empty(&con->out_queue) && + !test_bit(KEEPALIVE_PENDING, &con->state)) { + dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); + clear_bit(WRITE_PENDING, &con->state); set_bit(STANDBY, &con->state); } else { /* retry after a delay. */ @@ -2019,11 +2027,24 @@ static void ceph_fault(struct ceph_connection *con) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - dout("fault queueing %p delay %lu\n", con, con->delay); con->ops->get(con); if (queue_delayed_work(ceph_msgr_wq, &con->work, - round_jiffies_relative(con->delay)) == 0) + round_jiffies_relative(con->delay))) { + dout("fault queued %p delay %lu\n", con, con->delay); + } else { con->ops->put(con); + dout("fault failed to queue %p delay %lu, backoff\n", + con, con->delay); + /* + * In many cases we see a socket state change + * while con_work is running and end up + * queuing (non-delayed) work, such that we + * can't backoff with a delay. Set a flag so + * that when con_work restarts we schedule the + * delay then. + */ + set_bit(BACKOFF, &con->state); + } } out_unlock: @@ -2094,6 +2115,19 @@ void ceph_messenger_destroy(struct ceph_messenger *msgr) } EXPORT_SYMBOL(ceph_messenger_destroy); +static void clear_standby(struct ceph_connection *con) +{ + /* come back from STANDBY? */ + if (test_and_clear_bit(STANDBY, &con->state)) { + mutex_lock(&con->mutex); + dout("clear_standby %p and ++connect_seq\n", con); + con->connect_seq++; + WARN_ON(test_bit(WRITE_PENDING, &con->state)); + WARN_ON(test_bit(KEEPALIVE_PENDING, &con->state)); + mutex_unlock(&con->mutex); + } +} + /* * Queue up an outgoing message on the given connection. */ @@ -2126,6 +2160,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) /* if there wasn't anything waiting to send before, queue * new work */ + clear_standby(con); if (test_and_set_bit(WRITE_PENDING, &con->state) == 0) queue_con(con); } @@ -2191,6 +2226,8 @@ void ceph_con_revoke_message(struct ceph_connection *con, struct ceph_msg *msg) */ void ceph_con_keepalive(struct ceph_connection *con) { + dout("con_keepalive %p\n", con); + clear_standby(con); if (test_and_set_bit(KEEPALIVE_PENDING, &con->state) == 0 && test_and_set_bit(WRITE_PENDING, &con->state) == 0) queue_con(con); diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index 1a040e6..cd9c21d 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -16,22 +16,30 @@ struct page **ceph_get_direct_page_vector(const char __user *data, int num_pages, bool write_page) { struct page **pages; - int rc; + int got = 0; + int rc = 0; pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS); if (!pages) return ERR_PTR(-ENOMEM); down_read(¤t->mm->mmap_sem); - rc = get_user_pages(current, current->mm, (unsigned long)data, - num_pages, write_page, 0, pages, NULL); + while (got < num_pages) { + rc = get_user_pages(current, current->mm, + (unsigned long)data + ((unsigned long)got * PAGE_SIZE), + num_pages - got, write_page, 0, pages + got, NULL); + if (rc < 0) + break; + BUG_ON(rc == 0); + got += rc; + } up_read(¤t->mm->mmap_sem); - if (rc < num_pages) + if (rc < 0) goto fail; return pages; fail: - ceph_put_page_vector(pages, rc > 0 ? rc : 0, false); + ceph_put_page_vector(pages, got, false); return ERR_PTR(rc); } EXPORT_SYMBOL(ceph_get_direct_page_vector); diff --git a/net/core/dev.c b/net/core/dev.c index 24ea2d7..6561021 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1114,13 +1114,21 @@ EXPORT_SYMBOL(netdev_bonding_change); void dev_load(struct net *net, const char *name) { struct net_device *dev; + int no_module; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); rcu_read_unlock(); - if (!dev && capable(CAP_NET_ADMIN)) - request_module("%s", name); + no_module = !dev; + if (no_module && capable(CAP_NET_ADMIN)) + no_module = request_module("netdev-%s", name); + if (no_module && capable(CAP_SYS_MODULE)) { + if (!request_module("%s", name)) + pr_err("Loading kernel module for a network device " +"with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s " +"instead\n", name); + } } EXPORT_SYMBOL(dev_load); @@ -1280,10 +1288,13 @@ static int __dev_close_many(struct list_head *head) static int __dev_close(struct net_device *dev) { + int retval; LIST_HEAD(single); list_add(&dev->unreg_list, &single); - return __dev_close_many(&single); + retval = __dev_close_many(&single); + list_del(&single); + return retval; } int dev_close_many(struct list_head *head) @@ -1325,7 +1336,7 @@ int dev_close(struct net_device *dev) list_add(&dev->unreg_list, &single); dev_close_many(&single); - + list_del(&single); return 0; } EXPORT_SYMBOL(dev_close); @@ -2563,7 +2574,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, map = rcu_dereference(rxqueue->rps_map); if (map) { - if (map->len == 1) { + if (map->len == 1 && + !rcu_dereference_raw(rxqueue->rps_flow_table)) { tcpu = map->cpus[0]; if (cpu_online(tcpu)) cpu = tcpu; @@ -3424,6 +3436,8 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) __skb_pull(skb, skb_headlen(skb)); skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb)); skb->vlan_tci = 0; + skb->dev = napi->dev; + skb->skb_iif = 0; napi->skb = skb; } @@ -5060,6 +5074,7 @@ static void rollback_registered(struct net_device *dev) list_add(&dev->unreg_list, &single); rollback_registered_many(&single); + list_del(&single); } unsigned long netdev_fix_features(unsigned long features, const char *name) @@ -5657,30 +5672,35 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); + dev->gso_max_size = GSO_MAX_SIZE; + + INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); + dev->ethtool_ntuple_list.count = 0; + INIT_LIST_HEAD(&dev->napi_list); + INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->link_watch_list); + dev->priv_flags = IFF_XMIT_DST_RELEASE; + setup(dev); + dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) - goto free_pcpu; + goto free_all; #ifdef CONFIG_RPS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) - goto free_pcpu; + goto free_all; #endif - dev->gso_max_size = GSO_MAX_SIZE; - - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); - dev->ethtool_ntuple_list.count = 0; - INIT_LIST_HEAD(&dev->napi_list); - INIT_LIST_HEAD(&dev->unreg_list); - INIT_LIST_HEAD(&dev->link_watch_list); - dev->priv_flags = IFF_XMIT_DST_RELEASE; - setup(dev); strcpy(dev->name, name); return dev; +free_all: + free_netdev(dev); + return NULL; + free_pcpu: free_percpu(dev->pcpu_refcnt); kfree(dev->_tx); @@ -6208,6 +6228,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); + list_del(&dev_kill_list); rtnl_unlock(); } diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 508f9c1..133fd22 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -144,7 +144,7 @@ void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, list_for_each_entry(ha, &from_list->list, list) { type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, addr_type); + __hw_addr_del(to_list, ha->addr, addr_len, type); } } EXPORT_SYMBOL(__hw_addr_del_multiple); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a9e7fc4..b5bada9 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3321,7 +3321,7 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) pkt_dev->started_at); ktime_t idle = ns_to_ktime(pkt_dev->idle_acc); - p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n", + p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", (unsigned long long)ktime_to_us(elapsed), (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)), (unsigned long long)ktime_to_us(idle), diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 750db57..2d65c6b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1121,8 +1121,7 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return -EOPNOTSUPP; if (af_ops->validate_link_af) { - err = af_ops->validate_link_af(dev, - tb[IFLA_AF_SPEC]); + err = af_ops->validate_link_af(dev, af); if (err < 0) return err; } @@ -1672,6 +1671,9 @@ replay: snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); dest_net = rtnl_link_get_net(net, tb); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + dev = rtnl_create_link(net, dest_net, ifname, ops, tb); if (IS_ERR(dev)) diff --git a/net/core/scm.c b/net/core/scm.c index bbe4544..4c1ef02 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -95,7 +95,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) int fd = fdp[i]; struct file *file; - if (fd < 0 || !(file = fget(fd))) + if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; *fpp++ = file; fpl->count++; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7cd1bc8..d883dcc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -210,6 +210,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); if (fclone) { struct sk_buff *child = skb + 1; diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 6b03f56..c44348a 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -626,6 +626,9 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb, dcb->cmd = DCB_CMD_GAPP; app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP); + if (!app_nest) + goto out_cancel; + ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype); if (ret) goto out_cancel; @@ -1190,7 +1193,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, goto err; } - if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setets) { + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); err = ops->ieee_setpfc(netdev, pfc); if (err) @@ -1613,6 +1616,10 @@ EXPORT_SYMBOL(dcb_getapp); u8 dcb_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type *itr; + struct dcb_app_type event; + + memcpy(&event.name, dev->name, sizeof(event.name)); + memcpy(&event.app, new, sizeof(event.app)); spin_lock(&dcb_lock); /* Search for existing match and replace */ @@ -1644,7 +1651,7 @@ u8 dcb_setapp(struct net_device *dev, struct dcb_app *new) } out: spin_unlock(&dcb_lock); - call_dcbevent_notifiers(DCB_APP_EVENT, new); + call_dcbevent_notifiers(DCB_APP_EVENT, &event); return 0; } EXPORT_SYMBOL(dcb_setapp); diff --git a/net/dccp/input.c b/net/dccp/input.c index 8cde009..4222e7a 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -614,6 +614,9 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Caller (dccp_v4_do_rcv) will send Reset */ dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; return 1; + } else if (sk->sk_state == DCCP_CLOSED) { + dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; + return 1; } if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) { @@ -668,10 +671,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } switch (sk->sk_state) { - case DCCP_CLOSED: - dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - return 1; - case DCCP_REQUESTING: queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 739435a..cfa7a5e 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -67,8 +67,9 @@ dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen) size_t result_len = 0; const char *data = _data, *end, *opt; - kenter("%%%d,%s,'%s',%zu", - key->serial, key->description, data, datalen); + kenter("%%%d,%s,'%*.*s',%zu", + key->serial, key->description, + (int)datalen, (int)datalen, data, datalen); if (datalen <= 1 || !data || data[datalen - 1] != '\0') return -EINVAL; @@ -217,6 +218,19 @@ static void dns_resolver_describe(const struct key *key, struct seq_file *m) seq_printf(m, ": %u", key->datalen); } +/* + * read the DNS data + * - the key's semaphore is read-locked + */ +static long dns_resolver_read(const struct key *key, + char __user *buffer, size_t buflen) +{ + if (key->type_data.x[0]) + return key->type_data.x[0]; + + return user_read(key, buffer, buflen); +} + struct key_type key_type_dns_resolver = { .name = "dns_resolver", .instantiate = dns_resolver_instantiate, @@ -224,7 +238,7 @@ struct key_type key_type_dns_resolver = { .revoke = user_revoke, .destroy = user_destroy, .describe = dns_resolver_describe, - .read = user_read, + .read = dns_resolver_read, }; static int __init init_dns_resolver(void) diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 15dcc1a..0c28263 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -265,13 +265,13 @@ static void ec_tx_done(struct sk_buff *skb, int result) static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { - struct sock *sk = sock->sk; struct sockaddr_ec *saddr=(struct sockaddr_ec *)msg->msg_name; struct net_device *dev; struct ec_addr addr; int err; unsigned char port, cb; #if defined(CONFIG_ECONET_AUNUDP) || defined(CONFIG_ECONET_NATIVE) + struct sock *sk = sock->sk; struct sk_buff *skb; struct ec_cb *eb; #endif @@ -488,10 +488,10 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, error_free_buf: vfree(userbuf); +error: #else err = -EPROTOTYPE; #endif - error: mutex_unlock(&econet_mutex); return err; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f2b6110..45b89d7 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -880,6 +880,19 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } EXPORT_SYMBOL(inet_ioctl); +#ifdef CONFIG_COMPAT +int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + struct sock *sk = sock->sk; + int err = -ENOIOCTLCMD; + + if (sk->sk_prot->compat_ioctl) + err = sk->sk_prot->compat_ioctl(sk, cmd, arg); + + return err; +} +#endif + const struct proto_ops inet_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, @@ -903,6 +916,7 @@ const struct proto_ops inet_stream_ops = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_stream_ops); @@ -929,6 +943,7 @@ const struct proto_ops inet_dgram_ops = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_dgram_ops); @@ -959,6 +974,7 @@ static const struct proto_ops inet_sockraw_ops = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, + .compat_ioctl = inet_compat_ioctl, #endif }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 748cb5b..036652c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -670,7 +670,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) ifap = &ifa->ifa_next) { if (!strcmp(ifr.ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == - ifa->ifa_address) { + ifa->ifa_local) { break; /* found */ } } @@ -1030,6 +1030,21 @@ static inline bool inetdev_valid_mtu(unsigned mtu) return mtu >= 68; } +static void inetdev_send_gratuitous_arp(struct net_device *dev, + struct in_device *in_dev) + +{ + struct in_ifaddr *ifa = in_dev->ifa_list; + + if (!ifa) + return; + + arp_send(ARPOP_REQUEST, ETH_P_ARP, + ifa->ifa_local, dev, + ifa->ifa_local, NULL, + dev->dev_addr, NULL); +} + /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, @@ -1082,18 +1097,13 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, } ip_mc_up(in_dev); /* fall through */ - case NETDEV_NOTIFY_PEERS: case NETDEV_CHANGEADDR: + if (!IN_DEV_ARP_NOTIFY(in_dev)) + break; + /* fall through */ + case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ - if (IN_DEV_ARP_NOTIFY(in_dev)) { - struct in_ifaddr *ifa = in_dev->ifa_list; - - if (ifa) - arp_send(ARPOP_REQUEST, ETH_P_ARP, - ifa->ifa_address, dev, - ifa->ifa_address, NULL, - dev->dev_addr, NULL); - } + inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c5af909..3c8dfa1 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -505,7 +505,9 @@ restart: } rcu_read_unlock(); + local_bh_disable(); inet_twsk_deschedule(tw, twdr); + local_bh_enable(); inet_twsk_put(tw); goto restart_rcu; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index eb68a0e..d1d0e2c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -775,6 +775,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev .fl4_dst = dst, .fl4_src = tiph->saddr, .fl4_tos = RT_TOS(tos), + .proto = IPPROTO_GRE, .fl_gre_key = tunnel->parms.o_key }; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { @@ -1764,4 +1765,4 @@ module_exit(ipgre_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); -MODULE_ALIAS("gre0"); +MODULE_ALIAS_NETDEV("gre0"); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 988f52f..a5f58e7 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -913,4 +913,4 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); -MODULE_ALIAS("tunl0"); +MODULE_ALIAS_NETDEV("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3f3a9af..8b65a12 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -60,6 +60,7 @@ #include <linux/notifier.h> #include <linux/if_arp.h> #include <linux/netfilter_ipv4.h> +#include <linux/compat.h> #include <net/ipip.h> #include <net/checksum.h> #include <net/netlink.h> @@ -1434,6 +1435,81 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) } } +#ifdef CONFIG_COMPAT +struct compat_sioc_sg_req { + struct in_addr src; + struct in_addr grp; + compat_ulong_t pktcnt; + compat_ulong_t bytecnt; + compat_ulong_t wrong_if; +}; + +struct compat_sioc_vif_req { + vifi_t vifi; /* Which iface */ + compat_ulong_t icount; + compat_ulong_t ocount; + compat_ulong_t ibytes; + compat_ulong_t obytes; +}; + +int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + struct compat_sioc_sg_req sr; + struct compat_sioc_vif_req vr; + struct vif_device *vif; + struct mfc_cache *c; + struct net *net = sock_net(sk); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; + + switch (cmd) { + case SIOCGETVIFCNT: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.vifi >= mrt->maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &mrt->vif_table[vr.vifi]; + if (VIF_EXISTS(mrt, vr.vifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + rcu_read_lock(); + c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + rcu_read_unlock(); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + rcu_read_unlock(); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} +#endif + static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index b8ddcc4..a5e52a9 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -60,12 +60,12 @@ static int checkentry(const struct xt_tgchk_param *par) if (mangle->flags & ~ARPT_MANGLE_MASK || !(mangle->flags & ARPT_MANGLE_MASK)) - return false; + return -EINVAL; if (mangle->target != NF_DROP && mangle->target != NF_ACCEPT && mangle->target != XT_CONTINUE) - return false; - return true; + return -EINVAL; + return 0; } static struct xt_target arpt_mangle_reg __read_mostly = { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a3d5ab7..6390ba2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -76,6 +76,7 @@ #include <linux/seq_file.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> +#include <linux/compat.h> static struct raw_hashinfo raw_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock), @@ -838,6 +839,23 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) } } +#ifdef CONFIG_COMPAT +static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case SIOCOUTQ: + case SIOCINQ: + return -ENOIOCTLCMD; + default: +#ifdef CONFIG_IP_MROUTE + return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg)); +#else + return -ENOIOCTLCMD; +#endif + } +} +#endif + struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, @@ -860,6 +878,7 @@ struct proto raw_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_raw_setsockopt, .compat_getsockopt = compat_raw_getsockopt, + .compat_ioctl = compat_raw_ioctl, #endif }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 351dc4e..6ed6603 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2707,6 +2707,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } +static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +{ + return 0; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2716,6 +2721,8 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, + .default_mtu = ipv4_blackhole_default_mtu, + .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb7f82e..65f6c04 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1222,7 +1222,7 @@ static int tcp_check_dsack(struct sock *sk, struct sk_buff *ack_skb, } /* D-SACK for already forgotten data... Do dumb counting. */ - if (dup_sack && + if (dup_sack && tp->undo_marker && tp->undo_retrans && !after(end_seq_0, prior_snd_una) && after(end_seq_0, tp->undo_marker)) tp->undo_retrans--; @@ -1299,7 +1299,8 @@ static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { - if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) + if (tp->undo_marker && tp->undo_retrans && + after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 406f320..dfa5beb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2162,7 +2162,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (!tp->retrans_stamp) tp->retrans_stamp = TCP_SKB_CB(skb)->when; - tp->undo_retrans++; + tp->undo_retrans += tcp_skb_pcount(skb); /* snd_nxt is stored to detect loss of retransmitted segment, * see tcp_input.c tcp_sacktag_write_queue(). diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4f4483e..e528a42 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -57,6 +57,7 @@ MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NETDEV("ip6tnl0"); #ifdef IP6_TNL_DEBUG #define IP6_TNL_TRACE(x...) printk(KERN_DEBUG "%s:" x "\n", __func__) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9fab274..0e1d53b 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -34,6 +34,7 @@ #include <linux/seq_file.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/compat.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> @@ -1804,6 +1805,80 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) } } +#ifdef CONFIG_COMPAT +struct compat_sioc_sg_req6 { + struct sockaddr_in6 src; + struct sockaddr_in6 grp; + compat_ulong_t pktcnt; + compat_ulong_t bytecnt; + compat_ulong_t wrong_if; +}; + +struct compat_sioc_mif_req6 { + mifi_t mifi; + compat_ulong_t icount; + compat_ulong_t ocount; + compat_ulong_t ibytes; + compat_ulong_t obytes; +}; + +int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + struct compat_sioc_sg_req6 sr; + struct compat_sioc_mif_req6 vr; + struct mif_device *vif; + struct mfc6_cache *c; + struct net *net = sock_net(sk); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + + switch (cmd) { + case SIOCGETMIFCNT_IN6: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.mifi >= mrt->maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT_IN6: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + read_lock(&mrt_lock); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} +#endif static inline int ip6mr_forward2_finish(struct sk_buff *skb) { diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 09c8889..de33803 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -410,7 +410,7 @@ fallback: if (p != NULL) { sb_add(m, "%02x", *p++); for (i = 1; i < len; i++) - sb_add(m, ":%02x", p[i]); + sb_add(m, ":%02x", *p++); } sb_add(m, " "); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 86c3952..c5b0915 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -31,6 +31,7 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> +#include <linux/compat.h> #include <asm/uaccess.h> #include <asm/ioctls.h> @@ -1157,6 +1158,23 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) } } +#ifdef CONFIG_COMPAT +static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case SIOCOUTQ: + case SIOCINQ: + return -ENOIOCTLCMD; + default: +#ifdef CONFIG_IPV6_MROUTE + return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); +#else + return -ENOIOCTLCMD; +#endif + } +} +#endif + static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) @@ -1215,6 +1233,7 @@ struct proto rawv6_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_rawv6_setsockopt, .compat_getsockopt = compat_rawv6_getsockopt, + .compat_ioctl = compat_rawv6_ioctl, #endif }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1534508..e7db701 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -113,6 +113,11 @@ static struct dst_ops ip6_dst_ops_template = { .local_out = __ip6_local_out, }; +static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +{ + return 0; +} + static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -122,6 +127,8 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, + .default_mtu = ip6_blackhole_default_mtu, + .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, }; @@ -194,7 +201,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } if (peer) { - BUG_ON(!(rt->rt6i_flags & RTF_CACHE)); rt->rt6i_peer = NULL; inet_putpeer(peer); } @@ -204,9 +210,6 @@ void rt6_bind_peer(struct rt6_info *rt, int create) { struct inet_peer *peer; - if (WARN_ON(!(rt->rt6i_flags & RTF_CACHE))) - return; - peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create); if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL) inet_putpeer(peer); @@ -736,8 +739,10 @@ restart: if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src); - else + else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl->fl6_dst); + else + goto out2; dst_release(&rt->dst); rt = nrt ? : net->ipv6.ip6_null_entry; @@ -2554,14 +2559,16 @@ static int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; - int delay = net->ipv6.sysctl.flush_delay; - if (write) { - proc_dointvec(ctl, write, buffer, lenp, ppos); - fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); - return 0; - } else + struct net *net; + int delay; + if (!write) return -EINVAL; + + net = (struct net *)ctl->extra1; + delay = net->ipv6.sysctl.flush_delay; + proc_dointvec(ctl, write, buffer, lenp, ppos); + fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net); + return 0; } ctl_table ipv6_route_table_template[] = { @@ -2648,6 +2655,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) if (table) { table[0].data = &net->ipv6.sysctl.flush_delay; + table[0].extra1 = net; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.ip6_rt_max_size; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 8ce38f1..d2c16e1 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1290,4 +1290,4 @@ static int __init sit_init(void) module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); -MODULE_ALIAS("sit0"); +MODULE_ALIAS_NETDEV("sit0"); diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index fa1d8f4..7cb65ef 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -15,6 +15,8 @@ #include <net/addrconf.h> #include <net/inet_frag.h> +static struct ctl_table empty[1]; + static ctl_table ipv6_table_template[] = { { .procname = "route", @@ -35,6 +37,12 @@ static ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "neigh", + .maxlen = 0, + .mode = 0555, + .child = empty, + }, { } }; @@ -152,7 +160,6 @@ static struct ctl_table_header *ip6_base; int ipv6_static_sysctl_register(void) { - static struct ctl_table empty[1]; ip6_base = register_sysctl_paths(net_ipv6_ctl_path, empty); if (ip6_base == NULL) return -ENOMEM; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4bc8a92..9cd73b1 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1822,6 +1822,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct net_device *dev, *cookie ^= 2; IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_TX_OFFCHAN; local->hw_roc_skb = skb; + local->hw_roc_skb_for_status = skb; mutex_unlock(&local->mtx); return 0; @@ -1875,6 +1876,7 @@ static int ieee80211_mgmt_tx_cancel_wait(struct wiphy *wiphy, if (ret == 0) { kfree_skb(local->hw_roc_skb); local->hw_roc_skb = NULL; + local->hw_roc_skb_for_status = NULL; } mutex_unlock(&local->mtx); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c47d7c0..533fd32 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -953,7 +953,7 @@ struct ieee80211_local { struct ieee80211_channel *hw_roc_channel; struct net_device *hw_roc_dev; - struct sk_buff *hw_roc_skb; + struct sk_buff *hw_roc_skb, *hw_roc_skb_for_status; struct work_struct hw_roc_start, hw_roc_done; enum nl80211_channel_type hw_roc_channel_type; unsigned int hw_roc_duration; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8acba45..7a10a8d 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1229,6 +1229,7 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local) } mutex_unlock(&local->iflist_mtx); unregister_netdevice_many(&unreg_list); + list_del(&unreg_list); } static u32 ieee80211_idle_off(struct ieee80211_local *local, diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 45fbb9e..c9ceb4d 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1033,6 +1033,12 @@ void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, if (is_multicast_ether_addr(hdr->addr1)) return; + /* + * In case we receive frames after disassociation. + */ + if (!sdata->u.mgd.associated) + return; + ieee80211_sta_reset_conn_monitor(sdata); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 38a7972..071ac95 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -323,6 +323,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) { struct ieee80211_work *wk; + u64 cookie = (unsigned long)skb; rcu_read_lock(); list_for_each_entry_rcu(wk, &local->work_list, list) { @@ -334,8 +335,12 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) break; } rcu_read_unlock(); + if (local->hw_roc_skb_for_status == skb) { + cookie = local->hw_roc_cookie ^ 2; + local->hw_roc_skb_for_status = NULL; + } cfg80211_mgmt_tx_status( - skb->dev, (unsigned long) skb, skb->data, skb->len, + skb->dev, cookie, skb->data, skb->len, !!(info->flags & IEEE80211_TX_STAT_ACK), GFP_ATOMIC); } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b64b42b..b0beaa5 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1547,7 +1547,7 @@ static int ieee80211_skb_resize(struct ieee80211_local *local, skb_orphan(skb); } - if (skb_header_cloned(skb)) + if (skb_cloned(skb)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index cf68700..d036597 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1210,7 +1210,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: changed |= BSS_CHANGED_ASSOC; + mutex_lock(&sdata->u.mgd.mtx); ieee80211_bss_info_change_notify(sdata, changed); + mutex_unlock(&sdata->u.mgd.mtx); break; case NL80211_IFTYPE_ADHOC: changed |= BSS_CHANGED_IBSS; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 32fcbe2..4aa614b 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -133,6 +133,7 @@ unsigned int nf_iterate(struct list_head *head, /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ +repeat: verdict = elem->hook(hook, skb, indev, outdev, okfn); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG @@ -145,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head, #endif if (verdict != NF_REPEAT) return verdict; - *i = (*i)->prev; + goto repeat; } } return NF_ACCEPT; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 22f7ad5..ba98e13 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -808,9 +808,9 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, dest->u_threshold = udest->u_threshold; dest->l_threshold = udest->l_threshold; - spin_lock(&dest->dst_lock); + spin_lock_bh(&dest->dst_lock); ip_vs_dst_reset(dest); - spin_unlock(&dest->dst_lock); + spin_unlock_bh(&dest->dst_lock); if (add) ip_vs_new_estimator(&dest->stats); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e615119..84f4fcc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -942,8 +942,15 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_REPLY, ct); out: - if (tmpl) - nf_ct_put(tmpl); + if (tmpl) { + /* Special case: we have to repeat this hook, assign the + * template again to this packet. We assume that this packet + * has no conntrack assigned. This is used by nf_ct_tcp. */ + if (ret == NF_REPEAT) + skb->nfct = (struct nf_conntrack *)tmpl; + else + nf_ct_put(tmpl); + } return ret; } diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 5702de3..63a1b91 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -63,6 +63,9 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct) * this does not harm and it happens very rarely. */ unsigned long missed = e->missed; + if (!((events | missed) & e->ctmask)) + goto out_unlock; + ret = notify->fcn(events | missed, &item); if (unlikely(ret < 0 || missed)) { spin_lock_bh(&ct->lock); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 93297aa..eead9db 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -667,6 +667,7 @@ restart: if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, IPCTNL_MSG_CT_NEW, ct) < 0) { + nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; goto out; } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index b07393e..9181699 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -85,6 +85,8 @@ EXPORT_SYMBOL(nf_log_unregister); int nf_log_bind_pf(u_int8_t pf, const struct nf_logger *logger) { + if (pf >= ARRAY_SIZE(nf_loggers)) + return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); @@ -98,6 +100,8 @@ EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(u_int8_t pf) { + if (pf >= ARRAY_SIZE(nf_loggers)) + return; mutex_lock(&nf_log_mutex); rcu_assign_pointer(nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index 4d87bef..474d621 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -28,26 +28,23 @@ nf_tproxy_destructor(struct sk_buff *skb) skb->destructor = NULL; if (sk) - nf_tproxy_put_sock(sk); + sock_put(sk); } /* consumes sk */ -int +void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { - bool transparent = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_transparent : - inet_sk(sk)->transparent; - - if (transparent) { - skb_orphan(skb); - skb->sk = sk; - skb->destructor = nf_tproxy_destructor; - return 1; - } else - nf_tproxy_put_sock(sk); - - return 0; + /* assigning tw sockets complicates things; most + * skb->sk->X checks would have to test sk->sk_state first */ + if (sk->sk_state == TCP_TIME_WAIT) { + inet_twsk_put(inet_twsk(sk)); + return; + } + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = nf_tproxy_destructor; } EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 640678f..dcfd57e 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -33,6 +33,20 @@ #include <net/netfilter/nf_tproxy_core.h> #include <linux/netfilter/xt_TPROXY.h> +static bool tproxy_sk_is_transparent(struct sock *sk) +{ + if (sk->sk_state != TCP_TIME_WAIT) { + if (inet_sk(sk)->transparent) + return true; + sock_put(sk); + } else { + if (inet_twsk(sk)->tw_transparent) + return true; + inet_twsk_put(inet_twsk(sk)); + } + return false; +} + static inline __be32 tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) { @@ -141,7 +155,7 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, skb->dev, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ - if (sk && nf_tproxy_assign_sock(skb, sk)) { + if (sk && tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~mark_mask) ^ mark_value; @@ -149,6 +163,8 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, pr_debug("redirecting: proto %hhu %pI4:%hu -> %pI4:%hu, mark: %x\n", iph->protocol, &iph->daddr, ntohs(hp->dest), &laddr, ntohs(lport), skb->mark); + + nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } @@ -306,7 +322,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) par->in, NFT_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ - if (sk && nf_tproxy_assign_sock(skb, sk)) { + if (sk && tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; @@ -314,6 +330,8 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) pr_debug("redirecting: proto %hhu %pI6:%hu -> %pI6:%hu, mark: %x\n", tproto, &iph->saddr, ntohs(hp->source), laddr, ntohs(lport), skb->mark); + + nf_tproxy_assign_sock(skb, sk); return NF_ACCEPT; } diff --git a/net/netfilter/xt_iprange.c b/net/netfilter/xt_iprange.c index 88f7c35..73c33a4 100644 --- a/net/netfilter/xt_iprange.c +++ b/net/netfilter/xt_iprange.c @@ -53,15 +53,13 @@ iprange_mt4(const struct sk_buff *skb, struct xt_action_param *par) } static inline int -iprange_ipv6_sub(const struct in6_addr *a, const struct in6_addr *b) +iprange_ipv6_lt(const struct in6_addr *a, const struct in6_addr *b) { unsigned int i; - int r; for (i = 0; i < 4; ++i) { - r = ntohl(a->s6_addr32[i]) - ntohl(b->s6_addr32[i]); - if (r != 0) - return r; + if (a->s6_addr32[i] != b->s6_addr32[i]) + return ntohl(a->s6_addr32[i]) < ntohl(b->s6_addr32[i]); } return 0; @@ -75,15 +73,15 @@ iprange_mt6(const struct sk_buff *skb, struct xt_action_param *par) bool m; if (info->flags & IPRANGE_SRC) { - m = iprange_ipv6_sub(&iph->saddr, &info->src_min.in6) < 0; - m |= iprange_ipv6_sub(&iph->saddr, &info->src_max.in6) > 0; + m = iprange_ipv6_lt(&iph->saddr, &info->src_min.in6); + m |= iprange_ipv6_lt(&info->src_max.in6, &iph->saddr); m ^= !!(info->flags & IPRANGE_SRC_INV); if (m) return false; } if (info->flags & IPRANGE_DST) { - m = iprange_ipv6_sub(&iph->daddr, &info->dst_min.in6) < 0; - m |= iprange_ipv6_sub(&iph->daddr, &info->dst_max.in6) > 0; + m = iprange_ipv6_lt(&iph->daddr, &info->dst_min.in6); + m |= iprange_ipv6_lt(&info->dst_max.in6, &iph->daddr); m ^= !!(info->flags & IPRANGE_DST_INV); if (m) return false; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 00d6ae83..9cc4635 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -35,6 +35,15 @@ #include <net/netfilter/nf_conntrack.h> #endif +static void +xt_socket_put_sk(struct sock *sk) +{ + if (sk->sk_state == TCP_TIME_WAIT) + inet_twsk_put(inet_twsk(sk)); + else + sock_put(sk); +} + static int extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol, @@ -164,7 +173,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); - nf_tproxy_put_sock(sk); + xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; @@ -298,7 +307,7 @@ socket_mt6_v1(const struct sk_buff *skb, struct xt_action_param *par) (sk->sk_state == TCP_TIME_WAIT && inet_twsk(sk)->tw_transparent)); - nf_tproxy_put_sock(sk); + xt_socket_put_sk(sk); if (wildcard || !transparent) sk = NULL; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 478181d..1f92459 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1407,7 +1407,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, int noblock = flags&MSG_DONTWAIT; size_t copied; struct sk_buff *skb, *data_skb; - int err; + int err, ret; if (flags&MSG_OOB) return -EOPNOTSUPP; @@ -1470,8 +1470,13 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, skb_free_datagram(sk, skb); - if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) - netlink_dump(sk); + if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { + ret = netlink_dump(sk); + if (ret) { + sk->sk_err = ret; + sk->sk_error_report(sk); + } + } scm_recv(sock, msg, siocb->scm, flags); out: @@ -1736,6 +1741,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct netlink_callback *cb; struct sock *sk; struct netlink_sock *nlk; + int ret; cb = kzalloc(sizeof(*cb), GFP_KERNEL); if (cb == NULL) @@ -1764,9 +1770,13 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, nlk->cb = cb; mutex_unlock(nlk->cb_mutex); - netlink_dump(sk); + ret = netlink_dump(sk); + sock_put(sk); + if (ret) + return ret; + /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 71f373c..c47a511 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -551,7 +551,10 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, if (conn->c_loopback && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); - return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + scat = &rm->data.op_sg[sg]; + ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + ret = min_t(int, ret, scat->length - conn->c_xmit_data_off); + return ret; } /* FIXME we may overallocate here */ diff --git a/net/rds/loop.c b/net/rds/loop.c index aeec1d4..bca6761 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -61,10 +61,15 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, unsigned int hdr_off, unsigned int sg, unsigned int off) { + struct scatterlist *sgp = &rm->data.op_sg[sg]; + int ret = sizeof(struct rds_header) + + be32_to_cpu(rm->m_inc.i_hdr.h_len); + /* Do not send cong updates to loopback */ if (rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { rds_cong_map_updated(conn->c_fcong, ~(u64) 0); - return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + ret = min_t(int, ret, sgp->length - conn->c_xmit_data_off); + goto out; } BUG_ON(hdr_off || sg || off); @@ -80,8 +85,8 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm, NULL); rds_inc_put(&rm->m_inc); - - return sizeof(struct rds_header) + be32_to_cpu(rm->m_inc.i_hdr.h_len); +out: + return ret; } /* diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 8931500..1a2b0633 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -423,6 +423,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) goto protocol_error; } + case RXRPC_PACKET_TYPE_ACKALL: case RXRPC_PACKET_TYPE_ACK: /* ACK processing is done in process context */ read_lock_bh(&call->state_lock); diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 5ee16f0..d763793 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -89,11 +89,11 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr, return ret; plen -= sizeof(*token); - token = kmalloc(sizeof(*token), GFP_KERNEL); + token = kzalloc(sizeof(*token), GFP_KERNEL); if (!token) return -ENOMEM; - token->kad = kmalloc(plen, GFP_KERNEL); + token->kad = kzalloc(plen, GFP_KERNEL); if (!token->kad) { kfree(token); return -ENOMEM; @@ -731,10 +731,10 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen) goto error; ret = -ENOMEM; - token = kmalloc(sizeof(*token), GFP_KERNEL); + token = kzalloc(sizeof(*token), GFP_KERNEL); if (!token) goto error; - token->kad = kmalloc(plen, GFP_KERNEL); + token->kad = kzalloc(plen, GFP_KERNEL); if (!token->kad) goto error_free; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 34dc598..1bc6980 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -839,6 +839,7 @@ void dev_deactivate(struct net_device *dev) list_add(&dev->unreg_list, &single); dev_deactivate_many(&single); + list_del(&single); } static void dev_init_scheduler_queue(struct net_device *dev, diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 2cc46f0..b23428f 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2029,11 +2029,11 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc, *errp = sctp_make_op_error_fixed(asoc, chunk); if (*errp) { - sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, - WORD_ROUND(ntohs(param.p->length))); - sctp_addto_chunk_fixed(*errp, - WORD_ROUND(ntohs(param.p->length)), - param.v); + if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, + WORD_ROUND(ntohs(param.p->length)))) + sctp_addto_chunk_fixed(*errp, + WORD_ROUND(ntohs(param.p->length)), + param.v); } else { /* If there is no memory for generating the ERROR * report as specified, an ABORT will be triggered diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 243fc09..59e5994 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -252,23 +252,37 @@ static void rpc_set_active(struct rpc_task *task) /* * Mark an RPC call as having completed by clearing the 'active' bit + * and then waking up all tasks that were sleeping. */ -static void rpc_mark_complete_task(struct rpc_task *task) +static int rpc_complete_task(struct rpc_task *task) { - smp_mb__before_clear_bit(); + void *m = &task->tk_runstate; + wait_queue_head_t *wq = bit_waitqueue(m, RPC_TASK_ACTIVE); + struct wait_bit_key k = __WAIT_BIT_KEY_INITIALIZER(m, RPC_TASK_ACTIVE); + unsigned long flags; + int ret; + + spin_lock_irqsave(&wq->lock, flags); clear_bit(RPC_TASK_ACTIVE, &task->tk_runstate); - smp_mb__after_clear_bit(); - wake_up_bit(&task->tk_runstate, RPC_TASK_ACTIVE); + ret = atomic_dec_and_test(&task->tk_count); + if (waitqueue_active(wq)) + __wake_up_locked_key(wq, TASK_NORMAL, &k); + spin_unlock_irqrestore(&wq->lock, flags); + return ret; } /* * Allow callers to wait for completion of an RPC call + * + * Note the use of out_of_line_wait_on_bit() rather than wait_on_bit() + * to enforce taking of the wq->lock and hence avoid races with + * rpc_complete_task(). */ int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *)) { if (action == NULL) action = rpc_wait_bit_killable; - return wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE, + return out_of_line_wait_on_bit(&task->tk_runstate, RPC_TASK_ACTIVE, action, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task); @@ -857,34 +871,67 @@ static void rpc_async_release(struct work_struct *work) rpc_free_task(container_of(work, struct rpc_task, u.tk_work)); } -void rpc_put_task(struct rpc_task *task) +static void rpc_release_resources_task(struct rpc_task *task) { - if (!atomic_dec_and_test(&task->tk_count)) - return; - /* Release resources */ if (task->tk_rqstp) xprt_release(task); if (task->tk_msg.rpc_cred) put_rpccred(task->tk_msg.rpc_cred); rpc_task_release_client(task); - if (task->tk_workqueue != NULL) { +} + +static void rpc_final_put_task(struct rpc_task *task, + struct workqueue_struct *q) +{ + if (q != NULL) { INIT_WORK(&task->u.tk_work, rpc_async_release); - queue_work(task->tk_workqueue, &task->u.tk_work); + queue_work(q, &task->u.tk_work); } else rpc_free_task(task); } + +static void rpc_do_put_task(struct rpc_task *task, struct workqueue_struct *q) +{ + if (atomic_dec_and_test(&task->tk_count)) { + rpc_release_resources_task(task); + rpc_final_put_task(task, q); + } +} + +void rpc_put_task(struct rpc_task *task) +{ + rpc_do_put_task(task, NULL); +} EXPORT_SYMBOL_GPL(rpc_put_task); +void rpc_put_task_async(struct rpc_task *task) +{ + rpc_do_put_task(task, task->tk_workqueue); +} +EXPORT_SYMBOL_GPL(rpc_put_task_async); + static void rpc_release_task(struct rpc_task *task) { dprintk("RPC: %5u release task\n", task->tk_pid); BUG_ON (RPC_IS_QUEUED(task)); - /* Wake up anyone who is waiting for task completion */ - rpc_mark_complete_task(task); + rpc_release_resources_task(task); - rpc_put_task(task); + /* + * Note: at this point we have been removed from rpc_clnt->cl_tasks, + * so it should be safe to use task->tk_count as a test for whether + * or not any other processes still hold references to our rpc_task. + */ + if (atomic_read(&task->tk_count) != 1 + !RPC_IS_ASYNC(task)) { + /* Wake up anyone who may be waiting for task completion */ + if (!rpc_complete_task(task)) + return; + } else { + if (!atomic_dec_and_test(&task->tk_count)) + return; + } + rpc_final_put_task(task, task->tk_workqueue); } int rpciod_up(void) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 7bd3bbb..d802e94 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1609,9 +1609,7 @@ static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, */ static void svc_bc_sock_free(struct svc_xprt *xprt) { - if (xprt) { - kfree(xprt->xpt_bc_sid); + if (xprt) kfree(container_of(xprt, struct svc_sock, sk_xprt)); - } } #endif /* CONFIG_NFS_V4_1 */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 9df1ead..1a10dcd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -1335,6 +1335,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, p, 0, length, DMA_FROM_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[0].addr)) { put_page(p); + svc_rdma_put_context(ctxt, 1); return; } atomic_inc(&xprt->sc_dma_used); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c431f5a..be96d42 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1631,7 +1631,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt, } xs_reclassify_socket(family, sock); - if (xs_bind(transport, sock)) { + err = xs_bind(transport, sock); + if (err) { sock_release(sock); goto out; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dd419d2..ba5b8c2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -850,7 +850,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * Get the parent directory, calculate the hash for last * component. */ - err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd); + err = kern_path_parent(sunaddr->sun_path, &nd); if (err) goto out_mknod_parent; @@ -1724,7 +1724,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = 0; - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) { + err = sock_intr_errno(sock_rcvtimeo(sk, noblock)); + goto out; + } skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { @@ -1864,7 +1868,11 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, memset(&tmp_scm, 0, sizeof(tmp_scm)); } - mutex_lock(&u->readlock); + err = mutex_lock_interruptible(&u->readlock); + if (err) { + err = sock_intr_errno(timeo); + goto out; + } do { int chunk; @@ -1895,11 +1903,12 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, timeo = unix_stream_data_wait(sk, timeo); - if (signal_pending(current)) { + if (signal_pending(current) + || mutex_lock_interruptible(&u->readlock)) { err = sock_intr_errno(timeo); goto out; } - mutex_lock(&u->readlock); + continue; unlock: unix_state_unlock(sk); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index f89f83b..b6f4b99 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -104,7 +104,7 @@ struct sock *unix_get_socket(struct file *filp) /* * Socket ? */ - if (S_ISSOCK(inode->i_mode)) { + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { struct socket *sock = SOCKET_I(inode); struct sock *s = sock->sk; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 3e5dbd4..d112f03 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -802,11 +802,11 @@ int cfg80211_wext_siwfreq(struct net_device *dev, return freq; if (freq == 0) return -EINVAL; - wdev_lock(wdev); mutex_lock(&rdev->devlist_mtx); + wdev_lock(wdev); err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); - mutex_unlock(&rdev->devlist_mtx); wdev_unlock(wdev); + mutex_unlock(&rdev->devlist_mtx); return err; default: return -EOPNOTSUPP; diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 55187c8..4062075 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -27,9 +27,19 @@ #include <net/sock.h> #include <net/x25.h> -/* - * Parse a set of facilities into the facilities structures. Unrecognised - * facilities are written to the debug log file. +/** + * x25_parse_facilities - Parse facilities from skb into the facilities structs + * + * @skb: sk_buff to parse + * @facilities: Regular facilites, updated as facilities are found + * @dte_facs: ITU DTE facilities, updated as DTE facilities are found + * @vc_fac_mask: mask is updated with all facilities found + * + * Return codes: + * -1 - Parsing error, caller should drop call and clean up + * 0 - Parse OK, this skb has no facilities + * >0 - Parse OK, returns the length of the facilities header + * */ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, struct x25_dte_facilities *dte_facs, unsigned long *vc_fac_mask) @@ -62,7 +72,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, switch (*p & X25_FAC_CLASS_MASK) { case X25_FAC_CLASS_A: if (len < 2) - return 0; + return -1; switch (*p) { case X25_FAC_REVERSE: if((p[1] & 0x81) == 0x81) { @@ -107,7 +117,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, break; case X25_FAC_CLASS_B: if (len < 3) - return 0; + return -1; switch (*p) { case X25_FAC_PACKET_SIZE: facilities->pacsize_in = p[1]; @@ -130,7 +140,7 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, break; case X25_FAC_CLASS_C: if (len < 4) - return 0; + return -1; printk(KERN_DEBUG "X.25: unknown facility %02X, " "values %02X, %02X, %02X\n", p[0], p[1], p[2], p[3]); @@ -139,18 +149,18 @@ int x25_parse_facilities(struct sk_buff *skb, struct x25_facilities *facilities, break; case X25_FAC_CLASS_D: if (len < p[1] + 2) - return 0; + return -1; switch (*p) { case X25_FAC_CALLING_AE: if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1) - return 0; + return -1; dte_facs->calling_len = p[2]; memcpy(dte_facs->calling_ae, &p[3], p[1] - 1); *vc_fac_mask |= X25_MASK_CALLING_AE; break; case X25_FAC_CALLED_AE: if (p[1] > X25_MAX_DTE_FACIL_LEN || p[1] <= 1) - return 0; + return -1; dte_facs->called_len = p[2]; memcpy(dte_facs->called_ae, &p[3], p[1] - 1); *vc_fac_mask |= X25_MASK_CALLED_AE; diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index f729f02..15de65f 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -91,10 +91,10 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp { struct x25_address source_addr, dest_addr; int len; + struct x25_sock *x25 = x25_sk(sk); switch (frametype) { case X25_CALL_ACCEPTED: { - struct x25_sock *x25 = x25_sk(sk); x25_stop_timer(sk); x25->condition = 0x00; @@ -113,14 +113,16 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp &dest_addr); if (len > 0) skb_pull(skb, len); + else if (len < 0) + goto out_clear; len = x25_parse_facilities(skb, &x25->facilities, &x25->dte_facilities, &x25->vc_facil_mask); if (len > 0) skb_pull(skb, len); - else - return -1; + else if (len < 0) + goto out_clear; /* * Copy any Call User Data. */ @@ -144,6 +146,12 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp } return 0; + +out_clear: + x25_write_internal(sk, X25_CLEAR_REQUEST); + x25->state = X25_STATE_2; + x25_start_t23timer(sk); + return 0; } /* diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 4cbc942..2130692 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -396,9 +396,12 @@ void __exit x25_link_free(void) write_lock_bh(&x25_neigh_list_lock); list_for_each_safe(entry, tmp, &x25_neigh_list) { + struct net_device *dev; + nb = list_entry(entry, struct x25_neigh, node); + dev = nb->dev; __x25_remove_neigh(nb); - dev_put(nb->dev); + dev_put(dev); } write_unlock_bh(&x25_neigh_list_lock); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8b3ef40..6459588 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1340,10 +1340,13 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS); + xdst = dst_alloc(dst_ops); xfrm_policy_put_afinfo(afinfo); - xdst->flo.ops = &xfrm_bundle_fc_ops; + if (likely(xdst)) + xdst->flo.ops = &xfrm_bundle_fc_ops; + else + xdst = ERR_PTR(-ENOBUFS); return xdst; } diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index c9a16ab..291228e 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -309,12 +309,18 @@ static void do_config_file(const char *filename) close(fd); } +/* + * Important: The below generated source_foo.o and deps_foo.o variable + * assignments are parsed not only by make, but also by the rather simple + * parser in scripts/mod/sumversion.c. + */ static void parse_dep_file(void *map, size_t len) { char *m = map; char *end = m + len; char *p; char s[PATH_MAX]; + int first; p = strchr(m, ':'); if (!p) { @@ -322,11 +328,11 @@ static void parse_dep_file(void *map, size_t len) exit(1); } memcpy(s, m, p-m); s[p-m] = 0; - printf("deps_%s := \\\n", target); m = p+1; clear_config(); + first = 1; while (m < end) { while (m < end && (*m == ' ' || *m == '\\' || *m == '\n')) m++; @@ -340,9 +346,20 @@ static void parse_dep_file(void *map, size_t len) if (strrcmp(s, "include/generated/autoconf.h") && strrcmp(s, "arch/um/include/uml-config.h") && strrcmp(s, ".ver")) { - printf(" %s \\\n", s); + /* + * Do not list the source file as dependency, so that + * kbuild is not confused if a .c file is rewritten + * into .S or vice versa. Storing it in source_* is + * needed for modpost to compute srcversions. + */ + if (first) { + printf("source_%s := %s\n\n", target, s); + printf("deps_%s := \\\n", target); + } else + printf(" %s \\\n", s); do_config_file(s); } + first = 0; m = p + 1; } printf("\n%s: $(deps_%s)\n\n", target, target); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4c0383d..58848e3 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -2654,11 +2654,6 @@ sub process { WARN("Use of volatile is usually wrong: see Documentation/volatile-considered-harmful.txt\n" . $herecurr); } -# SPIN_LOCK_UNLOCKED & RW_LOCK_UNLOCKED are deprecated - if ($line =~ /\b(SPIN_LOCK_UNLOCKED|RW_LOCK_UNLOCKED)/) { - ERROR("Use of $1 is deprecated: see Documentation/spinlocks.txt\n" . $herecurr); - } - # warn about #if 0 if ($line =~ /^.\s*\#\s*if\s+0\b/) { CHK("if this code is redundant consider removing it\n" . diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index fd81fc3..a4fe923 100644 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -1,6 +1,6 @@ #!/usr/bin/perl -w # -# Copywrite 2005-2009 - Steven Rostedt +# Copyright 2005-2009 - Steven Rostedt # Licensed under the terms of the GNU GPL License version 2 # # It's simple enough to figure out how this works. diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index ecf9c7d..9dfcd6d9 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -300,8 +300,8 @@ static int is_static_library(const char *objfile) return 0; } -/* We have dir/file.o. Open dir/.file.o.cmd, look for deps_ line to - * figure out source file. */ +/* We have dir/file.o. Open dir/.file.o.cmd, look for source_ and deps_ line + * to figure out source files. */ static int parse_source_files(const char *objfile, struct md4_ctx *md) { char *cmd, *file, *line, *dir; @@ -340,6 +340,21 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) */ while ((line = get_next_line(&pos, file, flen)) != NULL) { char* p = line; + + if (strncmp(line, "source_", sizeof("source_")-1) == 0) { + p = strrchr(line, ' '); + if (!p) { + warn("malformed line: %s\n", line); + goto out_file; + } + p++; + if (!parse_file(p, md)) { + warn("could not open %s: %s\n", + p, strerror(errno)); + goto out_file; + } + continue; + } if (strncmp(line, "deps_", sizeof("deps_")-1) == 0) { check_files = 1; continue; diff --git a/scripts/package/builddeb b/scripts/package/builddeb index b0b2357..f6cbc3d 100644 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -238,12 +238,12 @@ EOF fi # Build header package -find . -name Makefile -o -name Kconfig\* -o -name \*.pl > /tmp/files$$ -find arch/x86/include include scripts -type f >> /tmp/files$$ +(cd $srctree; find . -name Makefile -o -name Kconfig\* -o -name \*.pl > /tmp/files$$) +(cd $srctree; find arch/$SRCARCH/include include scripts -type f >> /tmp/files$$) (cd $objtree; find .config Module.symvers include scripts -type f >> /tmp/objfiles$$) destdir=$kernel_headers_dir/usr/src/linux-headers-$version mkdir -p "$destdir" -tar -c -f - -T /tmp/files$$ | (cd $destdir; tar -xf -) +(cd $srctree; tar -c -f - -T /tmp/files$$) | (cd $destdir; tar -xf -) (cd $objtree; tar -c -f - -T /tmp/objfiles$$) | (cd $destdir; tar -xf -) rm -f /tmp/files$$ /tmp/objfiles$$ arch=$(dpkg --print-architecture) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 038b3d1..f9f6f52 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -206,7 +206,8 @@ static uint32_t (*w2)(uint16_t); static int is_mcounted_section_name(char const *const txtname) { - return 0 == strcmp(".text", txtname) || + return 0 == strcmp(".text", txtname) || + 0 == strcmp(".ref.text", txtname) || 0 == strcmp(".sched.text", txtname) || 0 == strcmp(".spinlock.text", txtname) || 0 == strcmp(".irqentry.text", txtname) || diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 1d7963f..4be0dee 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -130,6 +130,7 @@ if ($inputfile =~ m,kernel/trace/ftrace\.o$,) { # Acceptable sections to record. my %text_sections = ( ".text" => 1, + ".ref.text" => 1, ".sched.text" => 1, ".spinlock.text" => 1, ".irqentry.text" => 1, diff --git a/scripts/rt-tester/rt-tester.py b/scripts/rt-tester/rt-tester.py index 44423b4..8c81d76 100644 --- a/scripts/rt-tester/rt-tester.py +++ b/scripts/rt-tester/rt-tester.py @@ -33,8 +33,6 @@ cmd_opcodes = { "lockintnowait" : "6", "lockcont" : "7", "unlock" : "8", - "lockbkl" : "9", - "unlockbkl" : "10", "signal" : "11", "resetevent" : "98", "reset" : "99", diff --git a/scripts/rt-tester/t2-l1-2rt-sameprio.tst b/scripts/rt-tester/t2-l1-2rt-sameprio.tst index 8821f27..3710c8b 100644 --- a/scripts/rt-tester/t2-l1-2rt-sameprio.tst +++ b/scripts/rt-tester/t2-l1-2rt-sameprio.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal 0 # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t2-l1-pi.tst b/scripts/rt-tester/t2-l1-pi.tst index cde1f18..b4cc959 100644 --- a/scripts/rt-tester/t2-l1-pi.tst +++ b/scripts/rt-tester/t2-l1-pi.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal 0 # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t2-l1-signal.tst b/scripts/rt-tester/t2-l1-signal.tst index 3ab0bfc..1b57376 100644 --- a/scripts/rt-tester/t2-l1-signal.tst +++ b/scripts/rt-tester/t2-l1-signal.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal 0 # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t2-l2-2rt-deadlock.tst b/scripts/rt-tester/t2-l2-2rt-deadlock.tst index f4b5d5d..68b1062 100644 --- a/scripts/rt-tester/t2-l2-2rt-deadlock.tst +++ b/scripts/rt-tester/t2-l2-2rt-deadlock.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal 0 # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t3-l1-pi-1rt.tst b/scripts/rt-tester/t3-l1-pi-1rt.tst index 63440ca..8e6c8b1 100644 --- a/scripts/rt-tester/t3-l1-pi-1rt.tst +++ b/scripts/rt-tester/t3-l1-pi-1rt.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t3-l1-pi-2rt.tst b/scripts/rt-tester/t3-l1-pi-2rt.tst index e5816fe..69c2212 100644 --- a/scripts/rt-tester/t3-l1-pi-2rt.tst +++ b/scripts/rt-tester/t3-l1-pi-2rt.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t3-l1-pi-3rt.tst b/scripts/rt-tester/t3-l1-pi-3rt.tst index 718b82b..9b0f1eb 100644 --- a/scripts/rt-tester/t3-l1-pi-3rt.tst +++ b/scripts/rt-tester/t3-l1-pi-3rt.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t3-l1-pi-signal.tst b/scripts/rt-tester/t3-l1-pi-signal.tst index c6e2135..39ec74a 100644 --- a/scripts/rt-tester/t3-l1-pi-signal.tst +++ b/scripts/rt-tester/t3-l1-pi-signal.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t3-l1-pi-steal.tst b/scripts/rt-tester/t3-l1-pi-steal.tst index f53749d..e03db7e 100644 --- a/scripts/rt-tester/t3-l1-pi-steal.tst +++ b/scripts/rt-tester/t3-l1-pi-steal.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t3-l2-pi.tst b/scripts/rt-tester/t3-l2-pi.tst index cdc3e4f..7b59100 100644 --- a/scripts/rt-tester/t3-l2-pi.tst +++ b/scripts/rt-tester/t3-l2-pi.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t4-l2-pi-deboost.tst b/scripts/rt-tester/t4-l2-pi-deboost.tst index baa1413..2f0e049 100644 --- a/scripts/rt-tester/t4-l2-pi-deboost.tst +++ b/scripts/rt-tester/t4-l2-pi-deboost.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst b/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst index e6ec0c8..04f4034 100644 --- a/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst +++ b/scripts/rt-tester/t5-l4-pi-boost-deboost-setsched.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/scripts/rt-tester/t5-l4-pi-boost-deboost.tst b/scripts/rt-tester/t5-l4-pi-boost-deboost.tst index ca64f8b..a48a6ee 100644 --- a/scripts/rt-tester/t5-l4-pi-boost-deboost.tst +++ b/scripts/rt-tester/t5-l4-pi-boost-deboost.tst @@ -19,8 +19,6 @@ # lockintnowait lock nr (0-7) # lockcont lock nr (0-7) # unlock lock nr (0-7) -# lockbkl lock nr (0-7) -# unlockbkl lock nr (0-7) # signal thread to signal (0-7) # reset 0 # resetevent 0 @@ -39,9 +37,6 @@ # blocked lock nr (0-7) # blockedwake lock nr (0-7) # unlocked lock nr (0-7) -# lockedbkl dont care -# blockedbkl dont care -# unlockedbkl dont care # opcodeeq command opcode or number # opcodelt number # opcodegt number diff --git a/security/security.c b/security/security.c index b995428..bb33eca 100644 --- a/security/security.c +++ b/security/security.c @@ -154,10 +154,9 @@ int security_capset(struct cred *new, const struct cred *old, effective, inheritable, permitted); } -int security_capable(int cap) +int security_capable(const struct cred *cred, int cap) { - return security_ops->capable(current, current_cred(), cap, - SECURITY_CAP_AUDIT); + return security_ops->capable(current, cred, cap, SECURITY_CAP_AUDIT); } int security_real_capable(struct task_struct *tsk, int cap) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e276eb4..c8d6992 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3198,7 +3198,11 @@ static void selinux_cred_free(struct cred *cred) { struct task_security_struct *tsec = cred->security; - BUG_ON((unsigned long) cred->security < PAGE_SIZE); + /* + * cred->security == NULL if security_cred_alloc_blank() or + * security_prepare_creds() returned an error. + */ + BUG_ON(cred->security && (unsigned long) cred->security < PAGE_SIZE); cred->security = (void *) 0x7UL; kfree(tsec); } diff --git a/sound/arm/aaci.c b/sound/arm/aaci.c index 24d3013..7c1fc64 100644 --- a/sound/arm/aaci.c +++ b/sound/arm/aaci.c @@ -50,7 +50,11 @@ static void aaci_ac97_select_codec(struct aaci *aaci, struct snd_ac97 *ac97) if (v & SLFR_1RXV) readl(aaci->base + AACI_SL1RX); - writel(maincr, aaci->base + AACI_MAINCR); + if (maincr != readl(aaci->base + AACI_MAINCR)) { + writel(maincr, aaci->base + AACI_MAINCR); + readl(aaci->base + AACI_MAINCR); + udelay(1); + } } /* @@ -993,6 +997,8 @@ static unsigned int __devinit aaci_size_fifo(struct aaci *aaci) * disabling the channel doesn't clear the FIFO. */ writel(aaci->maincr & ~MAINCR_IE, aaci->base + AACI_MAINCR); + readl(aaci->base + AACI_MAINCR); + udelay(1); writel(aaci->maincr, aaci->base + AACI_MAINCR); /* diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c index 7730575..b8b31c4 100644 --- a/sound/core/hrtimer.c +++ b/sound/core/hrtimer.c @@ -45,12 +45,13 @@ static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt) { struct snd_hrtimer *stime = container_of(hrt, struct snd_hrtimer, hrt); struct snd_timer *t = stime->timer; + unsigned long oruns; if (!atomic_read(&stime->running)) return HRTIMER_NORESTART; - hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution)); - snd_timer_interrupt(stime->timer, t->sticks); + oruns = hrtimer_forward_now(hrt, ns_to_ktime(t->sticks * resolution)); + snd_timer_interrupt(stime->timer, t->sticks * oruns); if (!atomic_read(&stime->running)) return HRTIMER_NORESTART; @@ -104,7 +105,7 @@ static int snd_hrtimer_stop(struct snd_timer *t) } static struct snd_timer_hardware hrtimer_hw = { - .flags = SNDRV_TIMER_HW_AUTO, + .flags = SNDRV_TIMER_HW_AUTO | SNDRV_TIMER_HW_TASKLET, .open = snd_hrtimer_open, .close = snd_hrtimer_close, .start = snd_hrtimer_start, diff --git a/sound/core/jack.c b/sound/core/jack.c index 4902ae5..53b53e9 100644 --- a/sound/core/jack.c +++ b/sound/core/jack.c @@ -141,6 +141,7 @@ int snd_jack_new(struct snd_card *card, const char *id, int type, fail_input: input_free_device(jack->input_dev); + kfree(jack->id); kfree(jack); return err; } diff --git a/sound/drivers/mtpav.c b/sound/drivers/mtpav.c index da03597..5c426df 100644 --- a/sound/drivers/mtpav.c +++ b/sound/drivers/mtpav.c @@ -55,14 +55,13 @@ #include <linux/err.h> #include <linux/platform_device.h> #include <linux/ioport.h> +#include <linux/io.h> #include <linux/moduleparam.h> #include <sound/core.h> #include <sound/initval.h> #include <sound/rawmidi.h> #include <linux/delay.h> -#include <asm/io.h> - /* * globals */ diff --git a/sound/oss/Makefile b/sound/oss/Makefile index 96f14dc..90ffb99 100644 --- a/sound/oss/Makefile +++ b/sound/oss/Makefile @@ -87,7 +87,7 @@ ifeq ($(CONFIG_PSS_HAVE_BOOT),y) $(obj)/bin2hex pss_synth < $< > $@ else $(obj)/pss_boot.h: - ( \ + $(Q)( \ echo 'static unsigned char * pss_synth = NULL;'; \ echo 'static int pss_synthLen = 0;'; \ ) > $@ @@ -102,7 +102,7 @@ ifeq ($(CONFIG_TRIX_HAVE_BOOT),y) $(obj)/hex2hex -i trix_boot < $< > $@ else $(obj)/trix_boot.h: - ( \ + $(Q)( \ echo 'static unsigned char * trix_boot = NULL;'; \ echo 'static int trix_boot_len = 0;'; \ ) > $@ diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c index 23f49f3..16c0bdf 100644 --- a/sound/pci/au88x0/au88x0_core.c +++ b/sound/pci/au88x0/au88x0_core.c @@ -1252,11 +1252,19 @@ static void vortex_adbdma_resetup(vortex_t *vortex, int adbdma) { static int inline vortex_adbdma_getlinearpos(vortex_t * vortex, int adbdma) { stream_t *dma = &vortex->dma_adb[adbdma]; - int temp; + int temp, page, delta; temp = hwread(vortex->mmio, VORTEX_ADBDMA_STAT + (adbdma << 2)); - temp = (dma->period_virt * dma->period_bytes) + (temp & (dma->period_bytes - 1)); - return temp; + page = (temp & ADB_SUBBUF_MASK) >> ADB_SUBBUF_SHIFT; + if (dma->nr_periods >= 4) + delta = (page - dma->period_real) & 3; + else { + delta = (page - dma->period_real); + if (delta < 0) + delta += dma->nr_periods; + } + return (dma->period_virt + delta) * dma->period_bytes + + (temp & (dma->period_bytes - 1)); } static void vortex_adbdma_startfifo(vortex_t * vortex, int adbdma) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 2e91a99..fcedad9 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2308,6 +2308,7 @@ static struct snd_pci_quirk position_fix_list[] __devinitdata = { SND_PCI_QUIRK(0x1043, 0x813d, "ASUS P5AD2", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB), + SND_PCI_QUIRK(0x1043, 0x8410, "ASUS", POS_FIX_LPIB), SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB), SND_PCI_QUIRK(0x1106, 0x3288, "ASUS M2V-MX SE", POS_FIX_LPIB), SND_PCI_QUIRK(0x1179, 0xff10, "Toshiba A100-259", POS_FIX_LPIB), @@ -2703,7 +2704,7 @@ static int __devinit azx_probe(struct pci_dev *pci, if (err < 0) goto out_free; #ifdef CONFIG_SND_HDA_PATCH_LOADER - if (patch[dev]) { + if (patch[dev] && *patch[dev]) { snd_printk(KERN_ERR SFX "Applying patch firmware '%s'\n", patch[dev]); err = snd_hda_load_patch(chip->bus, patch[dev]); diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index a07b031..067982f4 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -1039,9 +1039,11 @@ static struct hda_verb cs_errata_init_verbs[] = { {0x11, AC_VERB_SET_PROC_COEF, 0x0008}, {0x11, AC_VERB_SET_PROC_STATE, 0x00}, +#if 0 /* Don't to set to D3 as we are in power-up sequence */ {0x07, AC_VERB_SET_POWER_STATE, 0x03}, /* S/PDIF Rx: D3 */ {0x08, AC_VERB_SET_POWER_STATE, 0x03}, /* S/PDIF Tx: D3 */ /*{0x01, AC_VERB_SET_POWER_STATE, 0x03},*/ /* AFG: D3 This is already handled */ +#endif {} /* terminator */ }; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 9bb030a..4d5004e 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -85,6 +85,7 @@ struct conexant_spec { unsigned int auto_mic; int auto_mic_ext; /* autocfg.inputs[] index for ext mic */ unsigned int need_dac_fix; + hda_nid_t slave_dig_outs[2]; /* capture */ unsigned int num_adc_nids; @@ -127,6 +128,7 @@ struct conexant_spec { unsigned int ideapad:1; unsigned int thinkpad:1; unsigned int hp_laptop:1; + unsigned int asus:1; unsigned int ext_mic_present; unsigned int recording; @@ -352,6 +354,8 @@ static int conexant_build_pcms(struct hda_codec *codec) info->stream[SNDRV_PCM_STREAM_CAPTURE].nid = spec->dig_in_nid; } + if (spec->slave_dig_outs[0]) + codec->slave_dig_outs = spec->slave_dig_outs; } return 0; @@ -403,10 +407,16 @@ static int conexant_add_jack(struct hda_codec *codec, struct conexant_spec *spec; struct conexant_jack *jack; const char *name; - int err; + int i, err; spec = codec->spec; snd_array_init(&spec->jacks, sizeof(*jack), 32); + + jack = spec->jacks.list; + for (i = 0; i < spec->jacks.used; i++, jack++) + if (jack->nid == nid) + return 0 ; /* already present */ + jack = snd_array_new(&spec->jacks); name = (type == SND_JACK_HEADPHONE) ? "Headphone" : "Mic" ; @@ -2100,7 +2110,7 @@ static int patch_cxt5051(struct hda_codec *codec) static hda_nid_t cxt5066_dac_nids[1] = { 0x10 }; static hda_nid_t cxt5066_adc_nids[3] = { 0x14, 0x15, 0x16 }; static hda_nid_t cxt5066_capsrc_nids[1] = { 0x17 }; -#define CXT5066_SPDIF_OUT 0x21 +static hda_nid_t cxt5066_digout_pin_nids[2] = { 0x20, 0x22 }; /* OLPC's microphone port is DC coupled for use with external sensors, * therefore we use a 50% mic bias in order to center the input signal with @@ -2312,6 +2322,19 @@ static void cxt5066_ideapad_automic(struct hda_codec *codec) } } + +/* toggle input of built-in digital mic and mic jack appropriately */ +static void cxt5066_asus_automic(struct hda_codec *codec) +{ + unsigned int present; + + present = snd_hda_jack_detect(codec, 0x1b); + snd_printdd("CXT5066: external microphone present=%d\n", present); + snd_hda_codec_write(codec, 0x17, 0, AC_VERB_SET_CONNECT_SEL, + present ? 1 : 0); +} + + /* toggle input of built-in digital mic and mic jack appropriately */ static void cxt5066_hp_laptop_automic(struct hda_codec *codec) { @@ -2387,79 +2410,55 @@ static void cxt5066_hp_automute(struct hda_codec *codec) cxt5066_update_speaker(codec); } -/* unsolicited event for jack sensing */ -static void cxt5066_olpc_unsol_event(struct hda_codec *codec, unsigned int res) +/* Dispatch the right mic autoswitch function */ +static void cxt5066_automic(struct hda_codec *codec) { struct conexant_spec *spec = codec->spec; - snd_printdd("CXT5066: unsol event %x (%x)\n", res, res >> 26); - switch (res >> 26) { - case CONEXANT_HP_EVENT: - cxt5066_hp_automute(codec); - break; - case CONEXANT_MIC_EVENT: - /* ignore mic events in DC mode; we're always using the jack */ - if (!spec->dc_enable) - cxt5066_olpc_automic(codec); - break; - } -} -/* unsolicited event for jack sensing */ -static void cxt5066_vostro_event(struct hda_codec *codec, unsigned int res) -{ - snd_printdd("CXT5066_vostro: unsol event %x (%x)\n", res, res >> 26); - switch (res >> 26) { - case CONEXANT_HP_EVENT: - cxt5066_hp_automute(codec); - break; - case CONEXANT_MIC_EVENT: + if (spec->dell_vostro) cxt5066_vostro_automic(codec); - break; - } -} - -/* unsolicited event for jack sensing */ -static void cxt5066_ideapad_event(struct hda_codec *codec, unsigned int res) -{ - snd_printdd("CXT5066_ideapad: unsol event %x (%x)\n", res, res >> 26); - switch (res >> 26) { - case CONEXANT_HP_EVENT: - cxt5066_hp_automute(codec); - break; - case CONEXANT_MIC_EVENT: + else if (spec->ideapad) cxt5066_ideapad_automic(codec); - break; - } + else if (spec->thinkpad) + cxt5066_thinkpad_automic(codec); + else if (spec->hp_laptop) + cxt5066_hp_laptop_automic(codec); + else if (spec->asus) + cxt5066_asus_automic(codec); } /* unsolicited event for jack sensing */ -static void cxt5066_hp_laptop_event(struct hda_codec *codec, unsigned int res) +static void cxt5066_olpc_unsol_event(struct hda_codec *codec, unsigned int res) { - snd_printdd("CXT5066_hp_laptop: unsol event %x (%x)\n", res, res >> 26); + struct conexant_spec *spec = codec->spec; + snd_printdd("CXT5066: unsol event %x (%x)\n", res, res >> 26); switch (res >> 26) { case CONEXANT_HP_EVENT: cxt5066_hp_automute(codec); break; case CONEXANT_MIC_EVENT: - cxt5066_hp_laptop_automic(codec); + /* ignore mic events in DC mode; we're always using the jack */ + if (!spec->dc_enable) + cxt5066_olpc_automic(codec); break; } } /* unsolicited event for jack sensing */ -static void cxt5066_thinkpad_event(struct hda_codec *codec, unsigned int res) +static void cxt5066_unsol_event(struct hda_codec *codec, unsigned int res) { - snd_printdd("CXT5066_thinkpad: unsol event %x (%x)\n", res, res >> 26); + snd_printdd("CXT5066: unsol event %x (%x)\n", res, res >> 26); switch (res >> 26) { case CONEXANT_HP_EVENT: cxt5066_hp_automute(codec); break; case CONEXANT_MIC_EVENT: - cxt5066_thinkpad_automic(codec); + cxt5066_automic(codec); break; } } + static const struct hda_input_mux cxt5066_analog_mic_boost = { .num_items = 5, .items = { @@ -2633,6 +2632,27 @@ static void cxt5066_olpc_capture_cleanup(struct hda_codec *codec) spec->recording = 0; } +static void conexant_check_dig_outs(struct hda_codec *codec, + hda_nid_t *dig_pins, + int num_pins) +{ + struct conexant_spec *spec = codec->spec; + hda_nid_t *nid_loc = &spec->multiout.dig_out_nid; + int i; + + for (i = 0; i < num_pins; i++, dig_pins++) { + unsigned int cfg = snd_hda_codec_get_pincfg(codec, *dig_pins); + if (get_defcfg_connect(cfg) == AC_JACK_PORT_NONE) + continue; + if (snd_hda_get_connections(codec, *dig_pins, nid_loc, 1) != 1) + continue; + if (spec->slave_dig_outs[0]) + nid_loc++; + else + nid_loc = spec->slave_dig_outs; + } +} + static struct hda_input_mux cxt5066_capture_source = { .num_items = 4, .items = { @@ -3039,20 +3059,11 @@ static struct hda_verb cxt5066_init_verbs_hp_laptop[] = { /* initialize jack-sensing, too */ static int cxt5066_init(struct hda_codec *codec) { - struct conexant_spec *spec = codec->spec; - snd_printdd("CXT5066: init\n"); conexant_init(codec); if (codec->patch_ops.unsol_event) { cxt5066_hp_automute(codec); - if (spec->dell_vostro) - cxt5066_vostro_automic(codec); - else if (spec->ideapad) - cxt5066_ideapad_automic(codec); - else if (spec->thinkpad) - cxt5066_thinkpad_automic(codec); - else if (spec->hp_laptop) - cxt5066_hp_laptop_automic(codec); + cxt5066_automic(codec); } cxt5066_set_mic_boost(codec); return 0; @@ -3080,6 +3091,7 @@ enum { CXT5066_DELL_VOSTRO, /* Dell Vostro 1015i */ CXT5066_IDEAPAD, /* Lenovo IdeaPad U150 */ CXT5066_THINKPAD, /* Lenovo ThinkPad T410s, others? */ + CXT5066_ASUS, /* Asus K52JU, Lenovo G560 - Int mic at 0x1a and Ext mic at 0x1b */ CXT5066_HP_LAPTOP, /* HP Laptop */ CXT5066_MODELS }; @@ -3091,6 +3103,7 @@ static const char * const cxt5066_models[CXT5066_MODELS] = { [CXT5066_DELL_VOSTRO] = "dell-vostro", [CXT5066_IDEAPAD] = "ideapad", [CXT5066_THINKPAD] = "thinkpad", + [CXT5066_ASUS] = "asus", [CXT5066_HP_LAPTOP] = "hp-laptop", }; @@ -3101,8 +3114,12 @@ static struct snd_pci_quirk cxt5066_cfg_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0401, "Dell Vostro 1014", CXT5066_DELL_VOSTRO), SND_PCI_QUIRK(0x1028, 0x0402, "Dell Vostro", CXT5066_DELL_VOSTRO), SND_PCI_QUIRK(0x1028, 0x0408, "Dell Inspiron One 19T", CXT5066_IDEAPAD), + SND_PCI_QUIRK(0x1028, 0x050f, "Dell Inspiron", CXT5066_IDEAPAD), + SND_PCI_QUIRK(0x1028, 0x0510, "Dell Vostro", CXT5066_IDEAPAD), SND_PCI_QUIRK(0x103c, 0x360b, "HP G60", CXT5066_HP_LAPTOP), - SND_PCI_QUIRK(0x1043, 0x13f3, "Asus A52J", CXT5066_HP_LAPTOP), + SND_PCI_QUIRK(0x1043, 0x13f3, "Asus A52J", CXT5066_ASUS), + SND_PCI_QUIRK(0x1043, 0x1643, "Asus K52JU", CXT5066_ASUS), + SND_PCI_QUIRK(0x1043, 0x1993, "Asus U50F", CXT5066_ASUS), SND_PCI_QUIRK(0x1179, 0xff1e, "Toshiba Satellite C650D", CXT5066_IDEAPAD), SND_PCI_QUIRK(0x1179, 0xff50, "Toshiba Satellite P500-PSPGSC-01800T", CXT5066_OLPC_XO_1_5), SND_PCI_QUIRK(0x1179, 0xffe0, "Toshiba Satellite Pro T130-15F", CXT5066_OLPC_XO_1_5), @@ -3111,7 +3128,9 @@ static struct snd_pci_quirk cxt5066_cfg_tbl[] = { SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT5066_OLPC_XO_1_5), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400s", CXT5066_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x21c5, "Thinkpad Edge 13", CXT5066_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x21c6, "Thinkpad Edge 13", CXT5066_ASUS), SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo Thinkpad", CXT5066_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo G560", CXT5066_ASUS), SND_PCI_QUIRK_VENDOR(0x17aa, "Lenovo", CXT5066_IDEAPAD), /* Fallback for Lenovos without dock mic */ {} }; @@ -3133,7 +3152,8 @@ static int patch_cxt5066(struct hda_codec *codec) spec->multiout.max_channels = 2; spec->multiout.num_dacs = ARRAY_SIZE(cxt5066_dac_nids); spec->multiout.dac_nids = cxt5066_dac_nids; - spec->multiout.dig_out_nid = CXT5066_SPDIF_OUT; + conexant_check_dig_outs(codec, cxt5066_digout_pin_nids, + ARRAY_SIZE(cxt5066_digout_pin_nids)); spec->num_adc_nids = 1; spec->adc_nids = cxt5066_adc_nids; spec->capsrc_nids = cxt5066_capsrc_nids; @@ -3167,17 +3187,20 @@ static int patch_cxt5066(struct hda_codec *codec) spec->num_init_verbs++; spec->dell_automute = 1; break; + case CXT5066_ASUS: case CXT5066_HP_LAPTOP: codec->patch_ops.init = cxt5066_init; - codec->patch_ops.unsol_event = cxt5066_hp_laptop_event; + codec->patch_ops.unsol_event = cxt5066_unsol_event; spec->init_verbs[spec->num_init_verbs] = cxt5066_init_verbs_hp_laptop; spec->num_init_verbs++; - spec->hp_laptop = 1; + spec->hp_laptop = board_config == CXT5066_HP_LAPTOP; + spec->asus = board_config == CXT5066_ASUS; spec->mixers[spec->num_mixers++] = cxt5066_mixer_master; spec->mixers[spec->num_mixers++] = cxt5066_mixers; /* no S/PDIF out */ - spec->multiout.dig_out_nid = 0; + if (board_config == CXT5066_HP_LAPTOP) + spec->multiout.dig_out_nid = 0; /* input source automatically selected */ spec->input_mux = NULL; spec->port_d_mode = 0; @@ -3207,7 +3230,7 @@ static int patch_cxt5066(struct hda_codec *codec) break; case CXT5066_DELL_VOSTRO: codec->patch_ops.init = cxt5066_init; - codec->patch_ops.unsol_event = cxt5066_vostro_event; + codec->patch_ops.unsol_event = cxt5066_unsol_event; spec->init_verbs[0] = cxt5066_init_verbs_vostro; spec->mixers[spec->num_mixers++] = cxt5066_mixer_master_olpc; spec->mixers[spec->num_mixers++] = cxt5066_mixers; @@ -3224,7 +3247,7 @@ static int patch_cxt5066(struct hda_codec *codec) break; case CXT5066_IDEAPAD: codec->patch_ops.init = cxt5066_init; - codec->patch_ops.unsol_event = cxt5066_ideapad_event; + codec->patch_ops.unsol_event = cxt5066_unsol_event; spec->mixers[spec->num_mixers++] = cxt5066_mixer_master; spec->mixers[spec->num_mixers++] = cxt5066_mixers; spec->init_verbs[0] = cxt5066_init_verbs_ideapad; @@ -3240,7 +3263,7 @@ static int patch_cxt5066(struct hda_codec *codec) break; case CXT5066_THINKPAD: codec->patch_ops.init = cxt5066_init; - codec->patch_ops.unsol_event = cxt5066_thinkpad_event; + codec->patch_ops.unsol_event = cxt5066_unsol_event; spec->mixers[spec->num_mixers++] = cxt5066_mixer_master; spec->mixers[spec->num_mixers++] = cxt5066_mixers; spec->init_verbs[0] = cxt5066_init_verbs_thinkpad; @@ -3389,7 +3412,7 @@ static void cx_auto_parse_output(struct hda_codec *codec) } } spec->multiout.dac_nids = spec->private_dac_nids; - spec->multiout.max_channels = nums * 2; + spec->multiout.max_channels = spec->multiout.num_dacs * 2; if (cfg->hp_outs > 0) spec->auto_mute = 1; @@ -3708,9 +3731,9 @@ static int cx_auto_init(struct hda_codec *codec) return 0; } -static int cx_auto_add_volume(struct hda_codec *codec, const char *basename, +static int cx_auto_add_volume_idx(struct hda_codec *codec, const char *basename, const char *dir, int cidx, - hda_nid_t nid, int hda_dir) + hda_nid_t nid, int hda_dir, int amp_idx) { static char name[32]; static struct snd_kcontrol_new knew[] = { @@ -3722,7 +3745,8 @@ static int cx_auto_add_volume(struct hda_codec *codec, const char *basename, for (i = 0; i < 2; i++) { struct snd_kcontrol *kctl; - knew[i].private_value = HDA_COMPOSE_AMP_VAL(nid, 3, 0, hda_dir); + knew[i].private_value = HDA_COMPOSE_AMP_VAL(nid, 3, amp_idx, + hda_dir); knew[i].subdevice = HDA_SUBDEV_AMP_FLAG; knew[i].index = cidx; snprintf(name, sizeof(name), "%s%s %s", basename, dir, sfx[i]); @@ -3738,6 +3762,9 @@ static int cx_auto_add_volume(struct hda_codec *codec, const char *basename, return 0; } +#define cx_auto_add_volume(codec, str, dir, cidx, nid, hda_dir) \ + cx_auto_add_volume_idx(codec, str, dir, cidx, nid, hda_dir, 0) + #define cx_auto_add_pb_volume(codec, nid, str, idx) \ cx_auto_add_volume(codec, str, " Playback", idx, nid, HDA_OUTPUT) @@ -3787,29 +3814,60 @@ static int cx_auto_build_input_controls(struct hda_codec *codec) struct conexant_spec *spec = codec->spec; struct auto_pin_cfg *cfg = &spec->autocfg; static const char *prev_label; - int i, err, cidx; + int i, err, cidx, conn_len; + hda_nid_t conn[HDA_MAX_CONNECTIONS]; + + int multi_adc_volume = 0; /* If the ADC nid has several input volumes */ + int adc_nid = spec->adc_nids[0]; + + conn_len = snd_hda_get_connections(codec, adc_nid, conn, + HDA_MAX_CONNECTIONS); + if (conn_len < 0) + return conn_len; + + multi_adc_volume = cfg->num_inputs > 1 && conn_len > 1; + if (!multi_adc_volume) { + err = cx_auto_add_volume(codec, "Capture", "", 0, adc_nid, + HDA_INPUT); + if (err < 0) + return err; + } - err = cx_auto_add_volume(codec, "Capture", "", 0, spec->adc_nids[0], - HDA_INPUT); - if (err < 0) - return err; prev_label = NULL; cidx = 0; for (i = 0; i < cfg->num_inputs; i++) { hda_nid_t nid = cfg->inputs[i].pin; const char *label; - if (!(get_wcaps(codec, nid) & AC_WCAP_IN_AMP)) + int j; + int pin_amp = get_wcaps(codec, nid) & AC_WCAP_IN_AMP; + if (!pin_amp && !multi_adc_volume) continue; + label = hda_get_autocfg_input_label(codec, cfg, i); if (label == prev_label) cidx++; else cidx = 0; prev_label = label; - err = cx_auto_add_volume(codec, label, " Capture", cidx, - nid, HDA_INPUT); - if (err < 0) - return err; + + if (pin_amp) { + err = cx_auto_add_volume(codec, label, " Boost", cidx, + nid, HDA_INPUT); + if (err < 0) + return err; + } + + if (!multi_adc_volume) + continue; + for (j = 0; j < conn_len; j++) { + if (conn[j] == nid) { + err = cx_auto_add_volume_idx(codec, label, + " Capture", cidx, adc_nid, HDA_INPUT, j); + if (err < 0) + return err; + break; + } + } } return 0; } @@ -3881,6 +3939,8 @@ static struct hda_codec_preset snd_hda_preset_conexant[] = { .patch = patch_cxt5066 }, { .id = 0x14f15069, .name = "CX20585", .patch = patch_cxt5066 }, + { .id = 0x14f1506e, .name = "CX20590", + .patch = patch_cxt5066 }, { .id = 0x14f15097, .name = "CX20631", .patch = patch_conexant_auto }, { .id = 0x14f15098, .name = "CX20632", @@ -3907,6 +3967,7 @@ MODULE_ALIAS("snd-hda-codec-id:14f15066"); MODULE_ALIAS("snd-hda-codec-id:14f15067"); MODULE_ALIAS("snd-hda-codec-id:14f15068"); MODULE_ALIAS("snd-hda-codec-id:14f15069"); +MODULE_ALIAS("snd-hda-codec-id:14f1506e"); MODULE_ALIAS("snd-hda-codec-id:14f15097"); MODULE_ALIAS("snd-hda-codec-id:14f15098"); MODULE_ALIAS("snd-hda-codec-id:14f150a1"); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 2d5b83f..ec0fa2d 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -642,6 +642,7 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec, hda_nid_t nid, hdmi_ai->ver = 0x01; hdmi_ai->len = 0x0a; hdmi_ai->CC02_CT47 = channels - 1; + hdmi_ai->CA = ca; hdmi_checksum_audio_infoframe(hdmi_ai); } else if (spec->sink_eld[i].conn_type == 1) { /* DisplayPort */ struct dp_audio_infoframe *dp_ai; @@ -651,6 +652,7 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec, hda_nid_t nid, dp_ai->len = 0x1b; dp_ai->ver = 0x11 << 2; dp_ai->CC02_CT47 = channels - 1; + dp_ai->CA = ca; } else { snd_printd("HDMI: unknown connection type at pin %d\n", pin_nid); @@ -1632,6 +1634,9 @@ static struct hda_codec_preset snd_hda_preset_hdmi[] = { { .id = 0x10de0012, .name = "GPU 12 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, { .id = 0x10de0013, .name = "GPU 13 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, { .id = 0x10de0014, .name = "GPU 14 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, +{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, +{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, +/* 17 is known to be absent */ { .id = 0x10de0018, .name = "GPU 18 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, { .id = 0x10de0019, .name = "GPU 19 HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, { .id = 0x10de001a, .name = "GPU 1a HDMI/DP", .patch = patch_nvhdmi_8ch_89 }, @@ -1674,6 +1679,8 @@ MODULE_ALIAS("snd-hda-codec-id:10de0011"); MODULE_ALIAS("snd-hda-codec-id:10de0012"); MODULE_ALIAS("snd-hda-codec-id:10de0013"); MODULE_ALIAS("snd-hda-codec-id:10de0014"); +MODULE_ALIAS("snd-hda-codec-id:10de0015"); +MODULE_ALIAS("snd-hda-codec-id:10de0016"); MODULE_ALIAS("snd-hda-codec-id:10de0018"); MODULE_ALIAS("snd-hda-codec-id:10de0019"); MODULE_ALIAS("snd-hda-codec-id:10de001a"); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2fa9ed9..4261bb8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1133,11 +1133,8 @@ static void alc_automute_speaker(struct hda_codec *codec, int pinctl) nid = spec->autocfg.hp_pins[i]; if (!nid) break; - if (snd_hda_jack_detect(codec, nid)) { - spec->jack_present = 1; - break; - } - alc_report_jack(codec, spec->autocfg.hp_pins[i]); + alc_report_jack(codec, nid); + spec->jack_present |= snd_hda_jack_detect(codec, nid); } mute = spec->jack_present ? HDA_AMP_MUTE : 0; @@ -2290,6 +2287,29 @@ static struct snd_kcontrol_new alc888_base_mixer[] = { { } /* end */ }; +static struct snd_kcontrol_new alc888_acer_aspire_4930g_mixer[] = { + HDA_CODEC_VOLUME("Front Playback Volume", 0x0c, 0x0, HDA_OUTPUT), + HDA_BIND_MUTE("Front Playback Switch", 0x0c, 2, HDA_INPUT), + HDA_CODEC_VOLUME("Surround Playback Volume", 0x0d, 0x0, HDA_OUTPUT), + HDA_BIND_MUTE("Surround Playback Switch", 0x0d, 2, HDA_INPUT), + HDA_CODEC_VOLUME_MONO("Center Playback Volume", 0x0f, 2, 0x0, + HDA_OUTPUT), + HDA_BIND_MUTE_MONO("Center Playback Switch", 0x0f, 2, 2, HDA_INPUT), + HDA_CODEC_VOLUME_MONO("LFE Playback Volume", 0x0f, 1, 0x0, HDA_OUTPUT), + HDA_BIND_MUTE_MONO("LFE Playback Switch", 0x0f, 1, 2, HDA_INPUT), + HDA_CODEC_VOLUME("Side Playback Volume", 0x0e, 0x0, HDA_OUTPUT), + HDA_BIND_MUTE("Side Playback Switch", 0x0e, 2, HDA_INPUT), + HDA_CODEC_VOLUME("CD Playback Volume", 0x0b, 0x04, HDA_INPUT), + HDA_CODEC_MUTE("CD Playback Switch", 0x0b, 0x04, HDA_INPUT), + HDA_CODEC_VOLUME("Line Playback Volume", 0x0b, 0x02, HDA_INPUT), + HDA_CODEC_MUTE("Line Playback Switch", 0x0b, 0x02, HDA_INPUT), + HDA_CODEC_VOLUME("Mic Playback Volume", 0x0b, 0x0, HDA_INPUT), + HDA_CODEC_VOLUME("Mic Boost Volume", 0x18, 0, HDA_INPUT), + HDA_CODEC_MUTE("Mic Playback Switch", 0x0b, 0x0, HDA_INPUT), + { } /* end */ +}; + + static struct snd_kcontrol_new alc889_acer_aspire_8930g_mixer[] = { HDA_CODEC_VOLUME("Front Playback Volume", 0x0c, 0x0, HDA_OUTPUT), HDA_BIND_MUTE("Front Playback Switch", 0x0c, 2, HDA_INPUT), @@ -10359,7 +10379,7 @@ static struct alc_config_preset alc882_presets[] = { .init_hook = alc_automute_amp, }, [ALC888_ACER_ASPIRE_4930G] = { - .mixers = { alc888_base_mixer, + .mixers = { alc888_acer_aspire_4930g_mixer, alc883_chmode_mixer }, .init_verbs = { alc883_init_verbs, alc880_gpio1_init_verbs, alc888_acer_aspire_4930g_verbs }, @@ -14992,7 +15012,7 @@ static struct snd_pci_quirk alc269_cfg_tbl[] = { SND_PCI_QUIRK(0x1043, 0x11e3, "ASUS U33Jc", ALC269VB_AMIC), SND_PCI_QUIRK(0x1043, 0x1273, "ASUS UL80Jt", ALC269VB_AMIC), SND_PCI_QUIRK(0x1043, 0x1283, "ASUS U53Jc", ALC269_AMIC), - SND_PCI_QUIRK(0x1043, 0x12b3, "ASUS N82Jv", ALC269_AMIC), + SND_PCI_QUIRK(0x1043, 0x12b3, "ASUS N82JV", ALC269VB_AMIC), SND_PCI_QUIRK(0x1043, 0x12d3, "ASUS N61Jv", ALC269_AMIC), SND_PCI_QUIRK(0x1043, 0x13a3, "ASUS UL30Vt", ALC269_AMIC), SND_PCI_QUIRK(0x1043, 0x1373, "ASUS G73JX", ALC269_AMIC), @@ -18802,6 +18822,7 @@ static struct snd_pci_quirk alc662_cfg_tbl[] = { ALC662_3ST_6ch_DIG), SND_PCI_QUIRK_MASK(0x1854, 0xf000, 0x2000, "ASUS H13-200x", ALC663_ASUS_H13), + SND_PCI_QUIRK(0x1991, 0x5628, "Ordissimo EVE", ALC662_LENOVO_101E), {} }; @@ -19494,6 +19515,7 @@ static const struct alc_fixup alc662_fixups[] = { }; static struct snd_pci_quirk alc662_fixup_tbl[] = { + SND_PCI_QUIRK(0x1025, 0x0308, "Acer Aspire 8942G", ALC662_FIXUP_ASPIRE), SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE), SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 9ea48b4..bd7b123 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -586,7 +586,12 @@ static hda_nid_t stac92hd83xxx_pin_nids[10] = { 0x0f, 0x10, 0x11, 0x1f, 0x20, }; -static hda_nid_t stac92hd88xxx_pin_nids[10] = { +static hda_nid_t stac92hd87xxx_pin_nids[6] = { + 0x0a, 0x0b, 0x0c, 0x0d, + 0x0f, 0x11, +}; + +static hda_nid_t stac92hd88xxx_pin_nids[8] = { 0x0a, 0x0b, 0x0c, 0x0d, 0x0f, 0x11, 0x1f, 0x20, }; @@ -5430,12 +5435,13 @@ again: switch (codec->vendor_id) { case 0x111d76d1: case 0x111d76d9: + case 0x111d76e5: spec->dmic_nids = stac92hd87b_dmic_nids; spec->num_dmics = stac92xx_connected_ports(codec, stac92hd87b_dmic_nids, STAC92HD87B_NUM_DMICS); - spec->num_pins = ARRAY_SIZE(stac92hd88xxx_pin_nids); - spec->pin_nids = stac92hd88xxx_pin_nids; + spec->num_pins = ARRAY_SIZE(stac92hd87xxx_pin_nids); + spec->pin_nids = stac92hd87xxx_pin_nids; spec->mono_nid = 0; spec->num_pwrs = 0; break; @@ -5443,6 +5449,7 @@ again: case 0x111d7667: case 0x111d7668: case 0x111d7669: + case 0x111d76e3: spec->num_dmics = stac92xx_connected_ports(codec, stac92hd88xxx_dmic_nids, STAC92HD88XXX_NUM_DMICS); @@ -6387,6 +6394,8 @@ static struct hda_codec_preset snd_hda_preset_sigmatel[] = { { .id = 0x111d76cd, .name = "92HD89F2", .patch = patch_stac92hd73xx }, { .id = 0x111d76ce, .name = "92HD89F1", .patch = patch_stac92hd73xx }, { .id = 0x111d76e0, .name = "92HD91BXX", .patch = patch_stac92hd83xxx}, + { .id = 0x111d76e3, .name = "92HD98BXX", .patch = patch_stac92hd83xxx}, + { .id = 0x111d76e5, .name = "92HD99BXX", .patch = patch_stac92hd83xxx}, { .id = 0x111d76e7, .name = "92HD90BXX", .patch = patch_stac92hd83xxx}, {} /* terminator */ }; diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index a76c326..63b0054 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -567,7 +567,7 @@ static void via_auto_init_analog_input(struct hda_codec *codec) hda_nid_t nid = cfg->inputs[i].pin; if (spec->smart51_enabled && is_smart51_pins(spec, nid)) ctl = PIN_OUT; - else if (i == AUTO_PIN_MIC) + else if (cfg->inputs[i].type == AUTO_PIN_MIC) ctl = PIN_VREF50; else ctl = PIN_IN; diff --git a/sound/pci/oxygen/oxygen.h b/sound/pci/oxygen/oxygen.h index c2ae63d..f53897a 100644 --- a/sound/pci/oxygen/oxygen.h +++ b/sound/pci/oxygen/oxygen.h @@ -92,6 +92,8 @@ struct oxygen_model { void (*update_dac_volume)(struct oxygen *chip); void (*update_dac_mute)(struct oxygen *chip); void (*update_center_lfe_mix)(struct oxygen *chip, bool mixed); + unsigned int (*adjust_dac_routing)(struct oxygen *chip, + unsigned int play_routing); void (*gpio_changed)(struct oxygen *chip); void (*uart_input)(struct oxygen *chip); void (*ac97_switch)(struct oxygen *chip, diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c index 9bff14d..26c7e8b 100644 --- a/sound/pci/oxygen/oxygen_mixer.c +++ b/sound/pci/oxygen/oxygen_mixer.c @@ -180,6 +180,8 @@ void oxygen_update_dac_routing(struct oxygen *chip) (1 << OXYGEN_PLAY_DAC1_SOURCE_SHIFT) | (2 << OXYGEN_PLAY_DAC2_SOURCE_SHIFT) | (3 << OXYGEN_PLAY_DAC3_SOURCE_SHIFT); + if (chip->model.adjust_dac_routing) + reg_value = chip->model.adjust_dac_routing(chip, reg_value); oxygen_write16_masked(chip, OXYGEN_PLAY_ROUTING, reg_value, OXYGEN_PLAY_DAC0_SOURCE_MASK | OXYGEN_PLAY_DAC1_SOURCE_MASK | diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c index e1fa602..bc6eb58 100644 --- a/sound/pci/oxygen/xonar_dg.c +++ b/sound/pci/oxygen/xonar_dg.c @@ -24,6 +24,11 @@ * * SPI 0 -> CS4245 * + * I²S 1 -> CS4245 + * I²S 2 -> CS4361 (center/LFE) + * I²S 3 -> CS4361 (surround) + * I²S 4 -> CS4361 (front) + * * GPIO 3 <- ? * GPIO 4 <- headphone detect * GPIO 5 -> route input jack to line-in (0) or mic-in (1) @@ -36,6 +41,7 @@ * input 1 <- aux * input 2 <- front mic * input 4 <- line/mic + * DAC out -> headphones * aux out -> front panel headphones */ @@ -207,6 +213,35 @@ static void set_cs4245_adc_params(struct oxygen *chip, cs4245_write_cached(chip, CS4245_ADC_CTRL, value); } +static inline unsigned int shift_bits(unsigned int value, + unsigned int shift_from, + unsigned int shift_to, + unsigned int mask) +{ + if (shift_from < shift_to) + return (value << (shift_to - shift_from)) & mask; + else + return (value >> (shift_from - shift_to)) & mask; +} + +static unsigned int adjust_dg_dac_routing(struct oxygen *chip, + unsigned int play_routing) +{ + return (play_routing & OXYGEN_PLAY_DAC0_SOURCE_MASK) | + shift_bits(play_routing, + OXYGEN_PLAY_DAC2_SOURCE_SHIFT, + OXYGEN_PLAY_DAC1_SOURCE_SHIFT, + OXYGEN_PLAY_DAC1_SOURCE_MASK) | + shift_bits(play_routing, + OXYGEN_PLAY_DAC1_SOURCE_SHIFT, + OXYGEN_PLAY_DAC2_SOURCE_SHIFT, + OXYGEN_PLAY_DAC2_SOURCE_MASK) | + shift_bits(play_routing, + OXYGEN_PLAY_DAC0_SOURCE_SHIFT, + OXYGEN_PLAY_DAC3_SOURCE_SHIFT, + OXYGEN_PLAY_DAC3_SOURCE_MASK); +} + static int output_switch_info(struct snd_kcontrol *ctl, struct snd_ctl_elem_info *info) { @@ -557,6 +592,7 @@ struct oxygen_model model_xonar_dg = { .resume = dg_resume, .set_dac_params = set_cs4245_dac_params, .set_adc_params = set_cs4245_adc_params, + .adjust_dac_routing = adjust_dg_dac_routing, .dump_registers = dump_cs4245_registers, .model_data_size = sizeof(struct dg), .device_config = PLAYBACK_0_TO_I2S | diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf.h b/sound/pcmcia/pdaudiocf/pdaudiocf.h index bd26e09..6ce9ad7 100644 --- a/sound/pcmcia/pdaudiocf/pdaudiocf.h +++ b/sound/pcmcia/pdaudiocf/pdaudiocf.h @@ -22,7 +22,7 @@ #define __PDAUDIOCF_H #include <sound/pcm.h> -#include <asm/io.h> +#include <linux/io.h> #include <linux/interrupt.h> #include <pcmcia/cistpl.h> #include <pcmcia/ds.h> diff --git a/sound/pcmcia/vx/vxp_ops.c b/sound/pcmcia/vx/vxp_ops.c index 989e04a..fe33e12 100644 --- a/sound/pcmcia/vx/vxp_ops.c +++ b/sound/pcmcia/vx/vxp_ops.c @@ -23,8 +23,8 @@ #include <linux/delay.h> #include <linux/device.h> #include <linux/firmware.h> +#include <linux/io.h> #include <sound/core.h> -#include <asm/io.h> #include "vxpocket.h" diff --git a/sound/soc/codecs/cq93vc.c b/sound/soc/codecs/cq93vc.c index 46dbfd0..347a567 100644 --- a/sound/soc/codecs/cq93vc.c +++ b/sound/soc/codecs/cq93vc.c @@ -153,7 +153,7 @@ static int cq93vc_resume(struct snd_soc_codec *codec) static int cq93vc_probe(struct snd_soc_codec *codec) { - struct davinci_vc *davinci_vc = codec->dev->platform_data; + struct davinci_vc *davinci_vc = snd_soc_codec_get_drvdata(codec); davinci_vc->cq93vc.codec = codec; codec->control_data = davinci_vc; diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c index 03d1e86..0bb424a 100644 --- a/sound/soc/codecs/cx20442.c +++ b/sound/soc/codecs/cx20442.c @@ -367,9 +367,12 @@ static int cx20442_codec_remove(struct snd_soc_codec *codec) return 0; } +static const u8 cx20442_reg; + static struct snd_soc_codec_driver cx20442_codec_dev = { .probe = cx20442_codec_probe, .remove = cx20442_codec_remove, + .reg_cache_default = &cx20442_reg, .reg_cache_size = 1, .reg_word_size = sizeof(u8), .read = cx20442_read_reg_cache, diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c index 987476a..017d99c 100644 --- a/sound/soc/codecs/wm8903.c +++ b/sound/soc/codecs/wm8903.c @@ -1482,7 +1482,7 @@ int wm8903_mic_detect(struct snd_soc_codec *codec, struct snd_soc_jack *jack, WM8903_MICDET_EINT | WM8903_MICSHRT_EINT, irq_mask); - if (det && shrt) { + if (det || shrt) { /* Enable mic detection, this may not have been set through * platform data (eg, if the defaults are OK). */ snd_soc_update_bits(codec, WM8903_WRITE_SEQUENCER_0, diff --git a/sound/soc/codecs/wm8903.h b/sound/soc/codecs/wm8903.h index e8490f3..e3ec243 100644 --- a/sound/soc/codecs/wm8903.h +++ b/sound/soc/codecs/wm8903.h @@ -165,7 +165,7 @@ extern int wm8903_mic_detect(struct snd_soc_codec *codec, #define WM8903_VMID_RES_50K 2 #define WM8903_VMID_RES_250K 3 -#define WM8903_VMID_RES_5K 4 +#define WM8903_VMID_RES_5K 6 /* * R8 (0x08) - Analogue DAC 0 diff --git a/sound/soc/codecs/wm8978.c b/sound/soc/codecs/wm8978.c index 4bbc344..8dfb0a0 100644 --- a/sound/soc/codecs/wm8978.c +++ b/sound/soc/codecs/wm8978.c @@ -145,18 +145,18 @@ static const struct snd_kcontrol_new wm8978_snd_controls[] = { SOC_SINGLE("DAC Playback Limiter Threshold", WM8978_DAC_LIMITER_2, 4, 7, 0), SOC_SINGLE("DAC Playback Limiter Boost", - WM8978_DAC_LIMITER_2, 0, 15, 0), + WM8978_DAC_LIMITER_2, 0, 12, 0), SOC_ENUM("ALC Enable Switch", alc1), SOC_SINGLE("ALC Capture Min Gain", WM8978_ALC_CONTROL_1, 0, 7, 0), SOC_SINGLE("ALC Capture Max Gain", WM8978_ALC_CONTROL_1, 3, 7, 0), - SOC_SINGLE("ALC Capture Hold", WM8978_ALC_CONTROL_2, 4, 7, 0), + SOC_SINGLE("ALC Capture Hold", WM8978_ALC_CONTROL_2, 4, 10, 0), SOC_SINGLE("ALC Capture Target", WM8978_ALC_CONTROL_2, 0, 15, 0), SOC_ENUM("ALC Capture Mode", alc3), - SOC_SINGLE("ALC Capture Decay", WM8978_ALC_CONTROL_3, 4, 15, 0), - SOC_SINGLE("ALC Capture Attack", WM8978_ALC_CONTROL_3, 0, 15, 0), + SOC_SINGLE("ALC Capture Decay", WM8978_ALC_CONTROL_3, 4, 10, 0), + SOC_SINGLE("ALC Capture Attack", WM8978_ALC_CONTROL_3, 0, 10, 0), SOC_SINGLE("ALC Capture Noise Gate Switch", WM8978_NOISE_GATE, 3, 1, 0), SOC_SINGLE("ALC Capture Noise Gate Threshold", @@ -211,8 +211,10 @@ static const struct snd_kcontrol_new wm8978_snd_controls[] = { WM8978_LOUT2_SPK_CONTROL, WM8978_ROUT2_SPK_CONTROL, 6, 1, 1), /* DAC / ADC oversampling */ - SOC_SINGLE("DAC 128x Oversampling Switch", WM8978_DAC_CONTROL, 8, 1, 0), - SOC_SINGLE("ADC 128x Oversampling Switch", WM8978_ADC_CONTROL, 8, 1, 0), + SOC_SINGLE("DAC 128x Oversampling Switch", WM8978_DAC_CONTROL, + 5, 1, 0), + SOC_SINGLE("ADC 128x Oversampling Switch", WM8978_ADC_CONTROL, + 5, 1, 0), }; /* Mixer #1: Output (OUT1, OUT2) Mixer: mix AUX, Input mixer output and DAC */ diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 3351f77..c6c958e 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -107,6 +107,12 @@ struct wm8994_priv { int revision; struct wm8994_pdata *pdata; + + unsigned int aif1clk_enable:1; + unsigned int aif2clk_enable:1; + + unsigned int aif1clk_disable:1; + unsigned int aif2clk_disable:1; }; static int wm8994_readable(unsigned int reg) @@ -1004,6 +1010,110 @@ static void wm8994_update_class_w(struct snd_soc_codec *codec) } } +static int late_enable_ev(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_codec *codec = w->codec; + struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); + + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + if (wm8994->aif1clk_enable) { + snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1, + WM8994_AIF1CLK_ENA_MASK, + WM8994_AIF1CLK_ENA); + wm8994->aif1clk_enable = 0; + } + if (wm8994->aif2clk_enable) { + snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1, + WM8994_AIF2CLK_ENA_MASK, + WM8994_AIF2CLK_ENA); + wm8994->aif2clk_enable = 0; + } + break; + } + + return 0; +} + +static int late_disable_ev(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_codec *codec = w->codec; + struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); + + switch (event) { + case SND_SOC_DAPM_POST_PMD: + if (wm8994->aif1clk_disable) { + snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1, + WM8994_AIF1CLK_ENA_MASK, 0); + wm8994->aif1clk_disable = 0; + } + if (wm8994->aif2clk_disable) { + snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1, + WM8994_AIF2CLK_ENA_MASK, 0); + wm8994->aif2clk_disable = 0; + } + break; + } + + return 0; +} + +static int aif1clk_ev(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_codec *codec = w->codec; + struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); + + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + wm8994->aif1clk_enable = 1; + break; + case SND_SOC_DAPM_POST_PMD: + wm8994->aif1clk_disable = 1; + break; + } + + return 0; +} + +static int aif2clk_ev(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_codec *codec = w->codec; + struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); + + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + wm8994->aif2clk_enable = 1; + break; + case SND_SOC_DAPM_POST_PMD: + wm8994->aif2clk_disable = 1; + break; + } + + return 0; +} + +static int adc_mux_ev(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + late_enable_ev(w, kcontrol, event); + return 0; +} + +static int dac_ev(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) +{ + struct snd_soc_codec *codec = w->codec; + unsigned int mask = 1 << w->shift; + + snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5, + mask, mask); + return 0; +} + static const char *hp_mux_text[] = { "Mixer", "DAC", @@ -1272,6 +1382,59 @@ static const struct soc_enum aif2dacr_src_enum = static const struct snd_kcontrol_new aif2dacr_src_mux = SOC_DAPM_ENUM("AIF2DACR Mux", aif2dacr_src_enum); +static const struct snd_soc_dapm_widget wm8994_lateclk_revd_widgets[] = { +SND_SOC_DAPM_SUPPLY("AIF1CLK", SND_SOC_NOPM, 0, 0, aif1clk_ev, + SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), +SND_SOC_DAPM_SUPPLY("AIF2CLK", SND_SOC_NOPM, 0, 0, aif2clk_ev, + SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), + +SND_SOC_DAPM_PGA_E("Late DAC1L Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0, + late_enable_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_PGA_E("Late DAC1R Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0, + late_enable_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_PGA_E("Late DAC2L Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0, + late_enable_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_PGA_E("Late DAC2R Enable PGA", SND_SOC_NOPM, 0, 0, NULL, 0, + late_enable_ev, SND_SOC_DAPM_PRE_PMU), + +SND_SOC_DAPM_POST("Late Disable PGA", late_disable_ev) +}; + +static const struct snd_soc_dapm_widget wm8994_lateclk_widgets[] = { +SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, NULL, 0), +SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, NULL, 0) +}; + +static const struct snd_soc_dapm_widget wm8994_dac_revd_widgets[] = { +SND_SOC_DAPM_DAC_E("DAC2L", NULL, SND_SOC_NOPM, 3, 0, + dac_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_DAC_E("DAC2R", NULL, SND_SOC_NOPM, 2, 0, + dac_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_DAC_E("DAC1L", NULL, SND_SOC_NOPM, 1, 0, + dac_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_DAC_E("DAC1R", NULL, SND_SOC_NOPM, 0, 0, + dac_ev, SND_SOC_DAPM_PRE_PMU), +}; + +static const struct snd_soc_dapm_widget wm8994_dac_widgets[] = { +SND_SOC_DAPM_DAC("DAC2L", NULL, WM8994_POWER_MANAGEMENT_5, 3, 0), +SND_SOC_DAPM_DAC("DAC2R", NULL, WM8994_POWER_MANAGEMENT_5, 2, 0), +SND_SOC_DAPM_DAC("DAC1L", NULL, WM8994_POWER_MANAGEMENT_5, 1, 0), +SND_SOC_DAPM_DAC("DAC1R", NULL, WM8994_POWER_MANAGEMENT_5, 0, 0), +}; + +static const struct snd_soc_dapm_widget wm8994_adc_revd_widgets[] = { +SND_SOC_DAPM_MUX_E("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux, + adc_mux_ev, SND_SOC_DAPM_PRE_PMU), +SND_SOC_DAPM_MUX_E("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux, + adc_mux_ev, SND_SOC_DAPM_PRE_PMU), +}; + +static const struct snd_soc_dapm_widget wm8994_adc_widgets[] = { +SND_SOC_DAPM_MUX("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux), +SND_SOC_DAPM_MUX("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux), +}; + static const struct snd_soc_dapm_widget wm8994_dapm_widgets[] = { SND_SOC_DAPM_INPUT("DMIC1DAT"), SND_SOC_DAPM_INPUT("DMIC2DAT"), @@ -1284,12 +1447,9 @@ SND_SOC_DAPM_SUPPLY("DSP1CLK", WM8994_CLOCKING_1, 3, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("DSP2CLK", WM8994_CLOCKING_1, 2, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("DSPINTCLK", WM8994_CLOCKING_1, 1, 0, NULL, 0), -SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, NULL, 0), -SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, NULL, 0), - -SND_SOC_DAPM_AIF_OUT("AIF1ADC1L", "AIF1 Capture", +SND_SOC_DAPM_AIF_OUT("AIF1ADC1L", NULL, 0, WM8994_POWER_MANAGEMENT_4, 9, 0), -SND_SOC_DAPM_AIF_OUT("AIF1ADC1R", "AIF1 Capture", +SND_SOC_DAPM_AIF_OUT("AIF1ADC1R", NULL, 0, WM8994_POWER_MANAGEMENT_4, 8, 0), SND_SOC_DAPM_AIF_IN_E("AIF1DAC1L", NULL, 0, WM8994_POWER_MANAGEMENT_5, 9, 0, wm8958_aif_ev, @@ -1298,9 +1458,9 @@ SND_SOC_DAPM_AIF_IN_E("AIF1DAC1R", NULL, 0, WM8994_POWER_MANAGEMENT_5, 8, 0, wm8958_aif_ev, SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD), -SND_SOC_DAPM_AIF_OUT("AIF1ADC2L", "AIF1 Capture", +SND_SOC_DAPM_AIF_OUT("AIF1ADC2L", NULL, 0, WM8994_POWER_MANAGEMENT_4, 11, 0), -SND_SOC_DAPM_AIF_OUT("AIF1ADC2R", "AIF1 Capture", +SND_SOC_DAPM_AIF_OUT("AIF1ADC2R", NULL, 0, WM8994_POWER_MANAGEMENT_4, 10, 0), SND_SOC_DAPM_AIF_IN_E("AIF1DAC2L", NULL, 0, WM8994_POWER_MANAGEMENT_5, 11, 0, wm8958_aif_ev, @@ -1345,6 +1505,7 @@ SND_SOC_DAPM_AIF_IN_E("AIF2DACR", NULL, 0, SND_SOC_DAPM_AIF_IN("AIF1DACDAT", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("AIF2DACDAT", "AIF2 Playback", 0, SND_SOC_NOPM, 0, 0), +SND_SOC_DAPM_AIF_OUT("AIF1ADCDAT", "AIF1 Capture", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("AIF2ADCDAT", "AIF2 Capture", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_MUX("AIF1DAC Mux", SND_SOC_NOPM, 0, 0, &aif1dac_mux), @@ -1368,14 +1529,6 @@ SND_SOC_DAPM_ADC("DMIC1R", NULL, WM8994_POWER_MANAGEMENT_4, 2, 0), SND_SOC_DAPM_ADC("ADCL", NULL, SND_SOC_NOPM, 1, 0), SND_SOC_DAPM_ADC("ADCR", NULL, SND_SOC_NOPM, 0, 0), -SND_SOC_DAPM_MUX("ADCL Mux", WM8994_POWER_MANAGEMENT_4, 1, 0, &adcl_mux), -SND_SOC_DAPM_MUX("ADCR Mux", WM8994_POWER_MANAGEMENT_4, 0, 0, &adcr_mux), - -SND_SOC_DAPM_DAC("DAC2L", NULL, WM8994_POWER_MANAGEMENT_5, 3, 0), -SND_SOC_DAPM_DAC("DAC2R", NULL, WM8994_POWER_MANAGEMENT_5, 2, 0), -SND_SOC_DAPM_DAC("DAC1L", NULL, WM8994_POWER_MANAGEMENT_5, 1, 0), -SND_SOC_DAPM_DAC("DAC1R", NULL, WM8994_POWER_MANAGEMENT_5, 0, 0), - SND_SOC_DAPM_MUX("Left Headphone Mux", SND_SOC_NOPM, 0, 0, &hpl_mux), SND_SOC_DAPM_MUX("Right Headphone Mux", SND_SOC_NOPM, 0, 0, &hpr_mux), @@ -1515,14 +1668,12 @@ static const struct snd_soc_dapm_route intercon[] = { { "AIF2ADC Mux", "AIF3DACDAT", "AIF3ADCDAT" }, /* DAC1 inputs */ - { "DAC1L", NULL, "DAC1L Mixer" }, { "DAC1L Mixer", "AIF2 Switch", "AIF2DACL" }, { "DAC1L Mixer", "AIF1.2 Switch", "AIF1DAC2L" }, { "DAC1L Mixer", "AIF1.1 Switch", "AIF1DAC1L" }, { "DAC1L Mixer", "Left Sidetone Switch", "Left Sidetone" }, { "DAC1L Mixer", "Right Sidetone Switch", "Right Sidetone" }, - { "DAC1R", NULL, "DAC1R Mixer" }, { "DAC1R Mixer", "AIF2 Switch", "AIF2DACR" }, { "DAC1R Mixer", "AIF1.2 Switch", "AIF1DAC2R" }, { "DAC1R Mixer", "AIF1.1 Switch", "AIF1DAC1R" }, @@ -1531,7 +1682,6 @@ static const struct snd_soc_dapm_route intercon[] = { /* DAC2/AIF2 outputs */ { "AIF2ADCL", NULL, "AIF2DAC2L Mixer" }, - { "DAC2L", NULL, "AIF2DAC2L Mixer" }, { "AIF2DAC2L Mixer", "AIF2 Switch", "AIF2DACL" }, { "AIF2DAC2L Mixer", "AIF1.2 Switch", "AIF1DAC2L" }, { "AIF2DAC2L Mixer", "AIF1.1 Switch", "AIF1DAC1L" }, @@ -1539,13 +1689,17 @@ static const struct snd_soc_dapm_route intercon[] = { { "AIF2DAC2L Mixer", "Right Sidetone Switch", "Right Sidetone" }, { "AIF2ADCR", NULL, "AIF2DAC2R Mixer" }, - { "DAC2R", NULL, "AIF2DAC2R Mixer" }, { "AIF2DAC2R Mixer", "AIF2 Switch", "AIF2DACR" }, { "AIF2DAC2R Mixer", "AIF1.2 Switch", "AIF1DAC2R" }, { "AIF2DAC2R Mixer", "AIF1.1 Switch", "AIF1DAC1R" }, { "AIF2DAC2R Mixer", "Left Sidetone Switch", "Left Sidetone" }, { "AIF2DAC2R Mixer", "Right Sidetone Switch", "Right Sidetone" }, + { "AIF1ADCDAT", NULL, "AIF1ADC1L" }, + { "AIF1ADCDAT", NULL, "AIF1ADC1R" }, + { "AIF1ADCDAT", NULL, "AIF1ADC2L" }, + { "AIF1ADCDAT", NULL, "AIF1ADC2R" }, + { "AIF2ADCDAT", NULL, "AIF2ADC Mux" }, /* AIF3 output */ @@ -1578,6 +1732,31 @@ static const struct snd_soc_dapm_route intercon[] = { { "Right Headphone Mux", "DAC", "DAC1R" }, }; +static const struct snd_soc_dapm_route wm8994_lateclk_revd_intercon[] = { + { "DAC1L", NULL, "Late DAC1L Enable PGA" }, + { "Late DAC1L Enable PGA", NULL, "DAC1L Mixer" }, + { "DAC1R", NULL, "Late DAC1R Enable PGA" }, + { "Late DAC1R Enable PGA", NULL, "DAC1R Mixer" }, + { "DAC2L", NULL, "Late DAC2L Enable PGA" }, + { "Late DAC2L Enable PGA", NULL, "AIF2DAC2L Mixer" }, + { "DAC2R", NULL, "Late DAC2R Enable PGA" }, + { "Late DAC2R Enable PGA", NULL, "AIF2DAC2R Mixer" } +}; + +static const struct snd_soc_dapm_route wm8994_lateclk_intercon[] = { + { "DAC1L", NULL, "DAC1L Mixer" }, + { "DAC1R", NULL, "DAC1R Mixer" }, + { "DAC2L", NULL, "AIF2DAC2L Mixer" }, + { "DAC2R", NULL, "AIF2DAC2R Mixer" }, +}; + +static const struct snd_soc_dapm_route wm8994_revd_intercon[] = { + { "AIF1DACDAT", NULL, "AIF2DACDAT" }, + { "AIF2DACDAT", NULL, "AIF1DACDAT" }, + { "AIF1ADCDAT", NULL, "AIF2ADCDAT" }, + { "AIF2ADCDAT", NULL, "AIF1ADCDAT" }, +}; + static const struct snd_soc_dapm_route wm8994_intercon[] = { { "AIF2DACL", NULL, "AIF2DAC Mux" }, { "AIF2DACR", NULL, "AIF2DAC Mux" }, @@ -2501,6 +2680,22 @@ static int wm8994_resume(struct snd_soc_codec *codec) { struct wm8994_priv *wm8994 = snd_soc_codec_get_drvdata(codec); int i, ret; + unsigned int val, mask; + + if (wm8994->revision < 4) { + /* force a HW read */ + val = wm8994_reg_read(codec->control_data, + WM8994_POWER_MANAGEMENT_5); + + /* modify the cache only */ + codec->cache_only = 1; + mask = WM8994_DAC1R_ENA | WM8994_DAC1L_ENA | + WM8994_DAC2R_ENA | WM8994_DAC2L_ENA; + val &= mask; + snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5, + mask, val); + codec->cache_only = 0; + } /* Restore the registers */ ret = snd_soc_cache_sync(codec); @@ -2834,11 +3029,10 @@ static void wm8958_default_micdet(u16 status, void *data) report |= SND_JACK_BTN_5; done: - snd_soc_jack_report(wm8994->micdet[0].jack, + snd_soc_jack_report(wm8994->micdet[0].jack, report, SND_JACK_BTN_0 | SND_JACK_BTN_1 | SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_BTN_4 | SND_JACK_BTN_5 | - SND_JACK_MICROPHONE | SND_JACK_VIDEOOUT, - report); + SND_JACK_MICROPHONE | SND_JACK_VIDEOOUT); } /** @@ -3112,10 +3306,31 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec) case WM8994: snd_soc_dapm_new_controls(dapm, wm8994_specific_dapm_widgets, ARRAY_SIZE(wm8994_specific_dapm_widgets)); + if (wm8994->revision < 4) { + snd_soc_dapm_new_controls(dapm, wm8994_lateclk_revd_widgets, + ARRAY_SIZE(wm8994_lateclk_revd_widgets)); + snd_soc_dapm_new_controls(dapm, wm8994_adc_revd_widgets, + ARRAY_SIZE(wm8994_adc_revd_widgets)); + snd_soc_dapm_new_controls(dapm, wm8994_dac_revd_widgets, + ARRAY_SIZE(wm8994_dac_revd_widgets)); + } else { + snd_soc_dapm_new_controls(dapm, wm8994_lateclk_widgets, + ARRAY_SIZE(wm8994_lateclk_widgets)); + snd_soc_dapm_new_controls(dapm, wm8994_adc_widgets, + ARRAY_SIZE(wm8994_adc_widgets)); + snd_soc_dapm_new_controls(dapm, wm8994_dac_widgets, + ARRAY_SIZE(wm8994_dac_widgets)); + } break; case WM8958: snd_soc_add_controls(codec, wm8958_snd_controls, ARRAY_SIZE(wm8958_snd_controls)); + snd_soc_dapm_new_controls(dapm, wm8994_lateclk_widgets, + ARRAY_SIZE(wm8994_lateclk_widgets)); + snd_soc_dapm_new_controls(dapm, wm8994_adc_widgets, + ARRAY_SIZE(wm8994_adc_widgets)); + snd_soc_dapm_new_controls(dapm, wm8994_dac_widgets, + ARRAY_SIZE(wm8994_dac_widgets)); snd_soc_dapm_new_controls(dapm, wm8958_dapm_widgets, ARRAY_SIZE(wm8958_dapm_widgets)); break; @@ -3129,8 +3344,20 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec) case WM8994: snd_soc_dapm_add_routes(dapm, wm8994_intercon, ARRAY_SIZE(wm8994_intercon)); + + if (wm8994->revision < 4) { + snd_soc_dapm_add_routes(dapm, wm8994_revd_intercon, + ARRAY_SIZE(wm8994_revd_intercon)); + snd_soc_dapm_add_routes(dapm, wm8994_lateclk_revd_intercon, + ARRAY_SIZE(wm8994_lateclk_revd_intercon)); + } else { + snd_soc_dapm_add_routes(dapm, wm8994_lateclk_intercon, + ARRAY_SIZE(wm8994_lateclk_intercon)); + } break; case WM8958: + snd_soc_dapm_add_routes(dapm, wm8994_lateclk_intercon, + ARRAY_SIZE(wm8994_lateclk_intercon)); snd_soc_dapm_add_routes(dapm, wm8958_intercon, ARRAY_SIZE(wm8958_intercon)); break; diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c index 43825b2..cce704c 100644 --- a/sound/soc/codecs/wm9081.c +++ b/sound/soc/codecs/wm9081.c @@ -15,6 +15,7 @@ #include <linux/moduleparam.h> #include <linux/init.h> #include <linux/delay.h> +#include <linux/device.h> #include <linux/pm.h> #include <linux/i2c.h> #include <linux/platform_device.h> @@ -1341,6 +1342,10 @@ static __devinit int wm9081_i2c_probe(struct i2c_client *i2c, wm9081->control_type = SND_SOC_I2C; wm9081->control_data = i2c; + if (dev_get_platdata(&i2c->dev)) + memcpy(&wm9081->retune, dev_get_platdata(&i2c->dev), + sizeof(wm9081->retune)); + ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_wm9081, &wm9081_dai, 1); if (ret < 0) diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c index 613df5d..5168927 100644 --- a/sound/soc/codecs/wm_hubs.c +++ b/sound/soc/codecs/wm_hubs.c @@ -674,6 +674,9 @@ SND_SOC_DAPM_OUTPUT("LINEOUT2N"), }; static const struct snd_soc_dapm_route analogue_routes[] = { + { "MICBIAS1", NULL, "CLK_SYS" }, + { "MICBIAS2", NULL, "CLK_SYS" }, + { "IN1L PGA", "IN1LP Switch", "IN1LP" }, { "IN1L PGA", "IN1LN Switch", "IN1LN" }, diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c index b36f0b3..fe79842 100644 --- a/sound/soc/davinci/davinci-evm.c +++ b/sound/soc/davinci/davinci-evm.c @@ -218,7 +218,19 @@ static struct snd_soc_dai_link dm6467_evm_dai[] = { .ops = &evm_spdif_ops, }, }; -static struct snd_soc_dai_link da8xx_evm_dai = { + +static struct snd_soc_dai_link da830_evm_dai = { + .name = "TLV320AIC3X", + .stream_name = "AIC3X", + .cpu_dai_name = "davinci-mcasp.1", + .codec_dai_name = "tlv320aic3x-hifi", + .codec_name = "tlv320aic3x-codec.1-0018", + .platform_name = "davinci-pcm-audio", + .init = evm_aic3x_init, + .ops = &evm_ops, +}; + +static struct snd_soc_dai_link da850_evm_dai = { .name = "TLV320AIC3X", .stream_name = "AIC3X", .cpu_dai_name= "davinci-mcasp.0", @@ -259,13 +271,13 @@ static struct snd_soc_card dm6467_snd_soc_card_evm = { static struct snd_soc_card da830_snd_soc_card = { .name = "DA830/OMAP-L137 EVM", - .dai_link = &da8xx_evm_dai, + .dai_link = &da830_evm_dai, .num_links = 1, }; static struct snd_soc_card da850_snd_soc_card = { .name = "DA850/OMAP-L138 EVM", - .dai_link = &da8xx_evm_dai, + .dai_link = &da850_evm_dai, .num_links = 1, }; diff --git a/sound/soc/imx/eukrea-tlv320.c b/sound/soc/imx/eukrea-tlv320.c index e20c9e1..1e9bcca 100644 --- a/sound/soc/imx/eukrea-tlv320.c +++ b/sound/soc/imx/eukrea-tlv320.c @@ -79,7 +79,7 @@ static struct snd_soc_dai_link eukrea_tlv320_dai = { .name = "tlv320aic23", .stream_name = "TLV320AIC23", .codec_dai_name = "tlv320aic23-hifi", - .platform_name = "imx-pcm-audio.0", + .platform_name = "imx-fiq-pcm-audio.0", .codec_name = "tlv320aic23-codec.0-001a", .cpu_dai_name = "imx-ssi.0", .ops = &eukrea_tlv320_snd_ops, diff --git a/sound/soc/omap/am3517evm.c b/sound/soc/omap/am3517evm.c index 1617504..73dde4a 100644 --- a/sound/soc/omap/am3517evm.c +++ b/sound/soc/omap/am3517evm.c @@ -139,7 +139,7 @@ static struct snd_soc_dai_link am3517evm_dai = { .cpu_dai_name ="omap-mcbsp-dai.0", .codec_dai_name = "tlv320aic23-hifi", .platform_name = "omap-pcm-audio", - .codec_name = "tlv320aic23-codec", + .codec_name = "tlv320aic23-codec.2-001a", .init = am3517evm_aic23_init, .ops = &am3517evm_ops, }; diff --git a/sound/soc/omap/ams-delta.c b/sound/soc/omap/ams-delta.c index 2101bdc..3167be6 100644 --- a/sound/soc/omap/ams-delta.c +++ b/sound/soc/omap/ams-delta.c @@ -507,8 +507,6 @@ static int ams_delta_cx20442_init(struct snd_soc_pcm_runtime *rtd) /* Set up digital mute if not provided by the codec */ if (!codec_dai->driver->ops) { codec_dai->driver->ops = &ams_delta_dai_ops; - } else if (!codec_dai->driver->ops->digital_mute) { - codec_dai->driver->ops->digital_mute = ams_delta_digital_mute; } else { ams_delta_ops.startup = ams_delta_startup; ams_delta_ops.shutdown = ams_delta_shutdown; diff --git a/sound/soc/pxa/e740_wm9705.c b/sound/soc/pxa/e740_wm9705.c index 28333e7..dc65650 100644 --- a/sound/soc/pxa/e740_wm9705.c +++ b/sound/soc/pxa/e740_wm9705.c @@ -117,7 +117,7 @@ static struct snd_soc_dai_link e740_dai[] = { { .name = "AC97", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9705-hifi", .platform_name = "pxa-pcm-audio", .codec_name = "wm9705-codec", @@ -126,7 +126,7 @@ static struct snd_soc_dai_link e740_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name = "wm9705-aux", .platform_name = "pxa-pcm-audio", .codec_name = "wm9705-codec", diff --git a/sound/soc/pxa/e750_wm9705.c b/sound/soc/pxa/e750_wm9705.c index 01bf316..51897fc 100644 --- a/sound/soc/pxa/e750_wm9705.c +++ b/sound/soc/pxa/e750_wm9705.c @@ -99,7 +99,7 @@ static struct snd_soc_dai_link e750_dai[] = { { .name = "AC97", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9705-hifi", .platform_name = "pxa-pcm-audio", .codec_name = "wm9705-codec", @@ -109,7 +109,7 @@ static struct snd_soc_dai_link e750_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name ="wm9705-aux", .platform_name = "pxa-pcm-audio", .codec_name = "wm9705-codec", diff --git a/sound/soc/pxa/e800_wm9712.c b/sound/soc/pxa/e800_wm9712.c index c6a37c6e..053ed20 100644 --- a/sound/soc/pxa/e800_wm9712.c +++ b/sound/soc/pxa/e800_wm9712.c @@ -89,7 +89,7 @@ static struct snd_soc_dai_link e800_dai[] = { { .name = "AC97", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9712-hifi", .platform_name = "pxa-pcm-audio", .codec_name = "wm9712-codec", @@ -98,7 +98,7 @@ static struct snd_soc_dai_link e800_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name ="wm9712-aux", .platform_name = "pxa-pcm-audio", .codec_name = "wm9712-codec", diff --git a/sound/soc/pxa/em-x270.c b/sound/soc/pxa/em-x270.c index fc22e6e..b13a425 100644 --- a/sound/soc/pxa/em-x270.c +++ b/sound/soc/pxa/em-x270.c @@ -37,7 +37,7 @@ static struct snd_soc_dai_link em_x270_dai[] = { { .name = "AC97", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9712-hifi", .platform_name = "pxa-pcm-audio", .codec_name = "wm9712-codec", @@ -45,7 +45,7 @@ static struct snd_soc_dai_link em_x270_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name ="wm9712-aux", .platform_name = "pxa-pcm-audio", .codec_name = "wm9712-codec", diff --git a/sound/soc/pxa/mioa701_wm9713.c b/sound/soc/pxa/mioa701_wm9713.c index 0d70fc8..38ca675 100644 --- a/sound/soc/pxa/mioa701_wm9713.c +++ b/sound/soc/pxa/mioa701_wm9713.c @@ -162,7 +162,7 @@ static struct snd_soc_dai_link mioa701_dai[] = { { .name = "AC97", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9713-hifi", .codec_name = "wm9713-codec", .init = mioa701_wm9713_init, @@ -172,7 +172,7 @@ static struct snd_soc_dai_link mioa701_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name ="wm9713-aux", .codec_name = "wm9713-codec", .platform_name = "pxa-pcm-audio", diff --git a/sound/soc/pxa/palm27x.c b/sound/soc/pxa/palm27x.c index 857db96..504e400 100644 --- a/sound/soc/pxa/palm27x.c +++ b/sound/soc/pxa/palm27x.c @@ -132,7 +132,7 @@ static struct snd_soc_dai_link palm27x_dai[] = { { .name = "AC97 HiFi", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9712-hifi", .codec_name = "wm9712-codec", .platform_name = "pxa-pcm-audio", @@ -141,7 +141,7 @@ static struct snd_soc_dai_link palm27x_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name = "wm9712-aux", .codec_name = "wm9712-codec", .platform_name = "pxa-pcm-audio", diff --git a/sound/soc/pxa/tosa.c b/sound/soc/pxa/tosa.c index f75804e..4b6e5d6 100644 --- a/sound/soc/pxa/tosa.c +++ b/sound/soc/pxa/tosa.c @@ -219,7 +219,7 @@ static struct snd_soc_dai_link tosa_dai[] = { { .name = "AC97", .stream_name = "AC97 HiFi", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_dai_name = "wm9712-hifi", .platform_name = "pxa-pcm-audio", .codec_name = "wm9712-codec", @@ -229,7 +229,7 @@ static struct snd_soc_dai_link tosa_dai[] = { { .name = "AC97 Aux", .stream_name = "AC97 Aux", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_dai_name = "wm9712-aux", .platform_name = "pxa-pcm-audio", .codec_name = "wm9712-codec", diff --git a/sound/soc/pxa/zylonite.c b/sound/soc/pxa/zylonite.c index b222a7d..25bba10 100644 --- a/sound/soc/pxa/zylonite.c +++ b/sound/soc/pxa/zylonite.c @@ -166,7 +166,7 @@ static struct snd_soc_dai_link zylonite_dai[] = { .stream_name = "AC97 HiFi", .codec_name = "wm9713-codec", .platform_name = "pxa-pcm-audio", - .cpu_dai_name = "pxa-ac97.0", + .cpu_dai_name = "pxa2xx-ac97", .codec_name = "wm9713-hifi", .init = zylonite_wm9713_init, }, @@ -175,7 +175,7 @@ static struct snd_soc_dai_link zylonite_dai[] = { .stream_name = "AC97 Aux", .codec_name = "wm9713-codec", .platform_name = "pxa-pcm-audio", - .cpu_dai_name = "pxa-ac97.1", + .cpu_dai_name = "pxa2xx-ac97-aux", .codec_name = "wm9713-aux", }, { diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index bac7291..c3f6f1e7 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1449,6 +1449,7 @@ static int soc_post_component_init(struct snd_soc_card *card, rtd = &card->rtd_aux[num]; name = aux_dev->name; } + rtd->card = card; /* machine controls, routes and widgets are not prefixed */ temp = codec->name_prefix; @@ -1471,7 +1472,6 @@ static int soc_post_component_init(struct snd_soc_card *card, /* register the rtd device */ rtd->codec = codec; - rtd->card = card; rtd->dev.parent = card->dev; rtd->dev.release = rtd_release; rtd->dev.init_name = name; @@ -1664,9 +1664,6 @@ static int soc_probe_aux_dev(struct snd_soc_card *card, int num) goto out; found: - if (!try_module_get(codec->dev->driver->owner)) - return -ENODEV; - ret = soc_probe_codec(card, codec); if (ret < 0) return ret; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 499730a..1790f83 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -712,7 +712,15 @@ static int dapm_supply_check_power(struct snd_soc_dapm_widget *w) !path->connected(path->source, path->sink)) continue; - if (path->sink && path->sink->power_check && + if (!path->sink) + continue; + + if (path->sink->force) { + power = 1; + break; + } + + if (path->sink->power_check && path->sink->power_check(path->sink)) { power = 1; break; @@ -933,7 +941,7 @@ static void dapm_seq_run(struct snd_soc_dapm_context *dapm, } if (!list_empty(&pending)) - dapm_seq_run_coalesced(dapm, &pending); + dapm_seq_run_coalesced(cur_dapm, &pending); } static void dapm_widget_update(struct snd_soc_dapm_context *dapm) @@ -1627,6 +1635,7 @@ EXPORT_SYMBOL_GPL(snd_soc_dapm_add_routes); int snd_soc_dapm_new_widgets(struct snd_soc_dapm_context *dapm) { struct snd_soc_dapm_widget *w; + unsigned int val; list_for_each_entry(w, &dapm->card->widgets, list) { @@ -1675,6 +1684,18 @@ int snd_soc_dapm_new_widgets(struct snd_soc_dapm_context *dapm) case snd_soc_dapm_post: break; } + + /* Read the initial power state from the device */ + if (w->reg >= 0) { + val = snd_soc_read(w->codec, w->reg); + val &= 1 << w->shift; + if (w->invert) + val = !val; + + if (val) + w->power = 1; + } + w->new = 1; } @@ -1742,7 +1763,7 @@ int snd_soc_dapm_put_volsw(struct snd_kcontrol *kcontrol, int max = mc->max; unsigned int mask = (1 << fls(max)) - 1; unsigned int invert = mc->invert; - unsigned int val, val_mask; + unsigned int val; int connect, change; struct snd_soc_dapm_update update; @@ -1750,13 +1771,13 @@ int snd_soc_dapm_put_volsw(struct snd_kcontrol *kcontrol, if (invert) val = max - val; - val_mask = mask << shift; + mask = mask << shift; val = val << shift; mutex_lock(&widget->codec->mutex); widget->value = val; - change = snd_soc_test_bits(widget->codec, reg, val_mask, val); + change = snd_soc_test_bits(widget->codec, reg, mask, val); if (change) { if (val) /* new connection */ diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c index 68b9747..66eabaf 100644 --- a/sound/usb/caiaq/audio.c +++ b/sound/usb/caiaq/audio.c @@ -785,7 +785,7 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *dev) } dev->pcm->private_data = dev; - strcpy(dev->pcm->name, dev->product_name); + strlcpy(dev->pcm->name, dev->product_name, sizeof(dev->pcm->name)); memset(dev->sub_playback, 0, sizeof(dev->sub_playback)); memset(dev->sub_capture, 0, sizeof(dev->sub_capture)); diff --git a/sound/usb/caiaq/midi.c b/sound/usb/caiaq/midi.c index 2f218c7..a1a47088 100644 --- a/sound/usb/caiaq/midi.c +++ b/sound/usb/caiaq/midi.c @@ -136,7 +136,7 @@ int snd_usb_caiaq_midi_init(struct snd_usb_caiaqdev *device) if (ret < 0) return ret; - strcpy(rmidi->name, device->product_name); + strlcpy(rmidi->name, device->product_name, sizeof(rmidi->name)); rmidi->info_flags = SNDRV_RAWMIDI_INFO_DUPLEX; rmidi->private_data = device; diff --git a/sound/usb/card.c b/sound/usb/card.c index 800f7cb..c0f8270b 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -323,6 +323,7 @@ static int snd_usb_audio_create(struct usb_device *dev, int idx, return -ENOMEM; } + mutex_init(&chip->shutdown_mutex); chip->index = idx; chip->dev = dev; chip->card = card; @@ -531,6 +532,7 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, void *ptr) chip = ptr; card = chip->card; mutex_lock(®ister_mutex); + mutex_lock(&chip->shutdown_mutex); chip->shutdown = 1; chip->num_interfaces--; if (chip->num_interfaces <= 0) { @@ -548,9 +550,11 @@ static void snd_usb_audio_disconnect(struct usb_device *dev, void *ptr) snd_usb_mixer_disconnect(p); } usb_chip[chip->index] = NULL; + mutex_unlock(&chip->shutdown_mutex); mutex_unlock(®ister_mutex); snd_card_free_when_closed(card); } else { + mutex_unlock(&chip->shutdown_mutex); mutex_unlock(®ister_mutex); } } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 7df89b3..85af605 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -95,7 +95,7 @@ enum { }; -/*E-mu 0202(0404) eXtension Unit(XU) control*/ +/*E-mu 0202/0404/0204 eXtension Unit(XU) control*/ enum { USB_XU_CLOCK_RATE = 0xe301, USB_XU_CLOCK_SOURCE = 0xe302, @@ -1566,7 +1566,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, void *raw cval->initialized = 1; } else { if (type == USB_XU_CLOCK_RATE) { - /* E-Mu USB 0404/0202/TrackerPre + /* E-Mu USB 0404/0202/TrackerPre/0204 * samplerate control quirk */ cval->min = 0; diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 4132522..e3f6805 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -361,6 +361,7 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream, } if (changed) { + mutex_lock(&subs->stream->chip->shutdown_mutex); /* format changed */ snd_usb_release_substream_urbs(subs, 0); /* influenced: period_bytes, channels, rate, format, */ @@ -368,6 +369,7 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream, params_rate(hw_params), snd_pcm_format_physical_width(params_format(hw_params)) * params_channels(hw_params)); + mutex_unlock(&subs->stream->chip->shutdown_mutex); } return ret; @@ -385,8 +387,9 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream) subs->cur_audiofmt = NULL; subs->cur_rate = 0; subs->period_bytes = 0; - if (!subs->stream->chip->shutdown) - snd_usb_release_substream_urbs(subs, 0); + mutex_lock(&subs->stream->chip->shutdown_mutex); + snd_usb_release_substream_urbs(subs, 0); + mutex_unlock(&subs->stream->chip->shutdown_mutex); return snd_pcm_lib_free_vmalloc_buffer(substream); } diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 3599987..921a86f 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -79,6 +79,13 @@ .idProduct = 0x3f0a, .bInterfaceClass = USB_CLASS_AUDIO, }, +{ + /* E-Mu 0204 USB */ + .match_flags = USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x041e, + .idProduct = 0x3f19, + .bInterfaceClass = USB_CLASS_AUDIO, +}, /* * Logitech QuickCam: bDeviceClass is vendor-specific, so generic interface diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index cf8bf08..e314cdb 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -532,7 +532,7 @@ int snd_usb_is_big_endian_format(struct snd_usb_audio *chip, struct audioformat } /* - * For E-Mu 0404USB/0202USB/TrackerPre sample rate should be set for device, + * For E-Mu 0404USB/0202USB/TrackerPre/0204 sample rate should be set for device, * not for interface. */ @@ -589,6 +589,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs, case USB_ID(0x041e, 0x3f02): /* E-Mu 0202 USB */ case USB_ID(0x041e, 0x3f04): /* E-Mu 0404 USB */ case USB_ID(0x041e, 0x3f0a): /* E-Mu Tracker Pre */ + case USB_ID(0x041e, 0x3f19): /* E-Mu 0204 USB */ set_format_emu_quirk(subs, fmt); break; } diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index db3eb21..6e66fff 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -36,6 +36,7 @@ struct snd_usb_audio { struct snd_card *card; u32 usb_id; int shutdown; + struct mutex shutdown_mutex; unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */ int num_interfaces; int num_suspended_intf; diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index cb43289..416684b 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -1,4 +1,3 @@ -PERF-BUILD-OPTIONS PERF-CFLAGS PERF-GUI-VARS PERF-VERSION-FILE diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index bd498d4..4626a39 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -178,8 +178,8 @@ install-pdf: pdf $(INSTALL) -d -m 755 $(DESTDIR)$(pdfdir) $(INSTALL) -m 644 user-manual.pdf $(DESTDIR)$(pdfdir) -install-html: html - '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) +#install-html: html +# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir) ../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE @@ -288,15 +288,16 @@ $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \ mv $@+ $@ -install-webdoc : html - '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST) +# UNIMPLEMENTED +#install-webdoc : html +# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(WEBDOC_DEST) -quick-install: quick-install-man +# quick-install: quick-install-man -quick-install-man: - '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir) +# quick-install-man: +# '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(DOC_REF) $(DESTDIR)$(mandir) -quick-install-html: - '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir) +#quick-install-html: +# '$(SHELL_PATH_SQ)' ./install-doc-quick.sh $(HTML_REF) $(DESTDIR)$(htmldir) .PHONY: .FORCE-PERF-VERSION-FILE diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 399751b..7a527f7 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -8,7 +8,7 @@ perf-list - List all symbolic event types SYNOPSIS -------- [verse] -'perf list' +'perf list' [hw|sw|cache|tracepoint|event_glob] DESCRIPTION ----------- @@ -63,7 +63,26 @@ details. Some of them are referenced in the SEE ALSO section below. OPTIONS ------- -None + +Without options all known events will be listed. + +To limit the list use: + +. 'hw' or 'hardware' to list hardware events such as cache-misses, etc. + +. 'sw' or 'software' to list software events such as context switches, etc. + +. 'cache' or 'hwcache' to list hardware cache events such as L1-dcache-loads, etc. + +. 'tracepoint' to list all tracepoint events, alternatively use + 'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched, + block, etc. + +. If none of the above is matched, it will apply the supplied glob to all + events, printing the ones that match. + +One or more types can be used at the same time, listing the events for the +types specified. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 921de25..4a26a2f 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -24,8 +24,8 @@ and statistics with this 'perf lock' command. 'perf lock report' reports statistical data. -OPTIONS -------- +COMMON OPTIONS +-------------- -i:: --input=<file>:: @@ -39,6 +39,14 @@ OPTIONS --dump-raw-trace:: Dump raw trace in ASCII. +REPORT OPTIONS +-------------- + +-k:: +--key=<value>:: + Sorting key. Possible values: acquired (default), contended, + wait_total, wait_max, wait_min. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 86b797a..02bafce 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -16,7 +16,7 @@ or or 'perf probe' --list or -'perf probe' [options] --line='FUNC[:RLN[+NUM|:RLN2]]|SRC:ALN[+NUM|:ALN2]' +'perf probe' [options] --line='LINE' or 'perf probe' [options] --vars='PROBEPOINT' @@ -73,6 +73,17 @@ OPTIONS (Only for --vars) Show external defined variables in addition to local variables. +-F:: +--funcs:: + Show available functions in given module or kernel. + +--filter=FILTER:: + (Only for --vars and --funcs) Set filter. FILTER is a combination of glob + pattern, see FILTER PATTERN for detail. + Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*" + for --funcs. + If several filters are specified, only the last filter is used. + -f:: --force:: Forcibly add events with existing name. @@ -117,13 +128,14 @@ LINE SYNTAX ----------- Line range is described by following syntax. - "FUNC[:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]" + "FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]" FUNC specifies the function name of showing lines. 'RLN' is the start line number from function entry line, and 'RLN2' is the end line number. As same as probe syntax, 'SRC' means the source file path, 'ALN' is start line number, and 'ALN2' is end line number in the file. It is also possible to specify how -many lines to show by using 'NUM'. +many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good +for searching a specific function when several functions share same name. So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function. LAZY MATCHING @@ -135,6 +147,14 @@ e.g. This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.) +FILTER PATTERN +-------------- + The filter pattern is a glob matching pattern(s) to filter variables. + In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")". + +e.g. + With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar". + With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out. EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e032716..5a520f8 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -137,6 +137,17 @@ Do not update the builid cache. This saves some overhead in situations where the information in the perf.data file (which includes buildids) is sufficient. +-G name,...:: +--cgroup name,...:: +monitor only in the container (cgroup) called "name". This option is available only +in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to +container "name" are monitored when they run on the monitored CPUs. Multiple cgroups +can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup +to first event, second cgroup to second event and so on. It is possible to provide +an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have +corresponding events, i.e., they always refer to events defined earlier on the command +line. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index b6da7af..918cc38 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -83,6 +83,17 @@ This option is only valid in system-wide mode. print counts using a CSV-style output to make it easy to import directly into spreadsheets. Columns are separated by the string specified in SEP. +-G name:: +--cgroup name:: +monitor only in the container (cgroup) called "name". This option is available only +in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to +container "name" are monitored when they run on the monitored CPUs. Multiple cgroups +can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup +to first event, second cgroup to second event and so on. It is possible to provide +an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have +corresponding events, i.e., they always refer to events defined earlier on the command +line. + EXAMPLES -------- diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 7141c42..9b84218 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -3,7 +3,7 @@ ifeq ("$(origin O)", "command line") endif # The default target of this Makefile is... -all:: +all: ifneq ($(OUTPUT),) # check that the output directory actually exists @@ -11,152 +11,12 @@ OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) endif -# Define V=1 to have a more verbose compile. -# Define V=2 to have an even more verbose compile. -# -# Define SNPRINTF_RETURNS_BOGUS if your are on a system which snprintf() -# or vsnprintf() return -1 instead of number of characters which would -# have been written to the final string if enough space had been available. -# -# Define FREAD_READS_DIRECTORIES if your are on a system which succeeds -# when attempting to read from an fopen'ed directory. -# -# Define NO_OPENSSL environment variable if you do not have OpenSSL. -# This also implies MOZILLA_SHA1. -# -# Define CURLDIR=/foo/bar if your curl header and library files are in -# /foo/bar/include and /foo/bar/lib directories. -# -# Define EXPATDIR=/foo/bar if your expat header and library files are in -# /foo/bar/include and /foo/bar/lib directories. -# -# Define NO_D_INO_IN_DIRENT if you don't have d_ino in your struct dirent. -# -# Define NO_D_TYPE_IN_DIRENT if your platform defines DT_UNKNOWN but lacks -# d_type in struct dirent (latest Cygwin -- will be fixed soonish). -# -# Define NO_C99_FORMAT if your formatted IO functions (printf/scanf et.al.) -# do not support the 'size specifiers' introduced by C99, namely ll, hh, -# j, z, t. (representing long long int, char, intmax_t, size_t, ptrdiff_t). -# some C compilers supported these specifiers prior to C99 as an extension. -# -# Define NO_STRCASESTR if you don't have strcasestr. -# -# Define NO_MEMMEM if you don't have memmem. -# -# Define NO_STRTOUMAX if you don't have strtoumax in the C library. -# If your compiler also does not support long long or does not have -# strtoull, define NO_STRTOULL. -# -# Define NO_SETENV if you don't have setenv in the C library. -# -# Define NO_UNSETENV if you don't have unsetenv in the C library. -# -# Define NO_MKDTEMP if you don't have mkdtemp in the C library. -# -# Define NO_SYS_SELECT_H if you don't have sys/select.h. -# -# Define NO_SYMLINK_HEAD if you never want .perf/HEAD to be a symbolic link. -# Enable it on Windows. By default, symrefs are still used. -# -# Define NO_SVN_TESTS if you want to skip time-consuming SVN interoperability -# tests. These tests take up a significant amount of the total test time -# but are not needed unless you plan to talk to SVN repos. -# -# Define NO_FINK if you are building on Darwin/Mac OS X, have Fink -# installed in /sw, but don't want PERF to link against any libraries -# installed there. If defined you may specify your own (or Fink's) -# include directories and library directories by defining CFLAGS -# and LDFLAGS appropriately. -# -# Define NO_DARWIN_PORTS if you are building on Darwin/Mac OS X, -# have DarwinPorts installed in /opt/local, but don't want PERF to -# link against any libraries installed there. If defined you may -# specify your own (or DarwinPort's) include directories and -# library directories by defining CFLAGS and LDFLAGS appropriately. -# -# Define PPC_SHA1 environment variable when running make to make use of -# a bundled SHA1 routine optimized for PowerPC. -# -# Define ARM_SHA1 environment variable when running make to make use of -# a bundled SHA1 routine optimized for ARM. -# -# Define MOZILLA_SHA1 environment variable when running make to make use of -# a bundled SHA1 routine coming from Mozilla. It is GPL'd and should be fast -# on non-x86 architectures (e.g. PowerPC), while the OpenSSL version (default -# choice) has very fast version optimized for i586. -# -# Define NEEDS_SSL_WITH_CRYPTO if you need -lcrypto with -lssl (Darwin). -# -# Define NEEDS_LIBICONV if linking with libc is not enough (Darwin). -# -# Define NEEDS_SOCKET if linking with libc is not enough (SunOS, -# Patrick Mauritz). -# -# Define NO_MMAP if you want to avoid mmap. -# -# Define NO_PTHREADS if you do not have or do not want to use Pthreads. -# -# Define NO_PREAD if you have a problem with pread() system call (e.g. -# cygwin.dll before v1.5.22). -# -# Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is -# generally faster on your platform than accessing the working directory. -# -# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support -# the executable mode bit, but doesn't really do so. -# -# Define NO_IPV6 if you lack IPv6 support and getaddrinfo(). -# -# Define NO_SOCKADDR_STORAGE if your platform does not have struct -# sockaddr_storage. -# -# Define NO_ICONV if your libc does not properly support iconv. -# -# Define OLD_ICONV if your library has an old iconv(), where the second -# (input buffer pointer) parameter is declared with type (const char **). -# -# Define NO_DEFLATE_BOUND if your zlib does not have deflateBound. -# -# Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib" -# that tells runtime paths to dynamic libraries; -# "-Wl,-rpath=/path/lib" is used instead. -# -# Define USE_NSEC below if you want perf to care about sub-second file mtimes -# and ctimes. Note that you need recent glibc (at least 2.2.4) for this, and -# it will BREAK YOUR LOCAL DIFFS! show-diff and anything using it will likely -# randomly break unless your underlying filesystem supports those sub-second -# times (my ext3 doesn't). -# -# Define USE_ST_TIMESPEC if your "struct stat" uses "st_ctimespec" instead of -# "st_ctim" -# -# Define NO_NSEC if your "struct stat" does not have "st_ctim.tv_nsec" -# available. This automatically turns USE_NSEC off. -# -# Define USE_STDEV below if you want perf to care about the underlying device -# change being considered an inode change from the update-index perspective. -# -# Define NO_ST_BLOCKS_IN_STRUCT_STAT if your platform does not have st_blocks -# field that counts the on-disk footprint in 512-byte blocks. +# Define V to have a more verbose compile. # # Define ASCIIDOC8 if you want to format documentation with AsciiDoc 8 # # Define DOCBOOK_XSL_172 if you want to format man pages with DocBook XSL v1.72. # -# Define NO_PERL_MAKEMAKER if you cannot use Makefiles generated by perl's -# MakeMaker (e.g. using ActiveState under Cygwin). -# -# Define NO_PERL if you do not want Perl scripts or libraries at all. -# -# Define INTERNAL_QSORT to use Git's implementation of qsort(), which -# is a simplified version of the merge sort used in glibc. This is -# recommended if Git triggers O(n^2) behavior in your platform's qsort(). -# -# Define NO_EXTERNAL_GREP if you don't want "perf grep" to ever call -# your external grep (e.g., if your system lacks grep, if its grep is -# broken, or spawning external process is slower than built-in grep perf has). -# # Define LDFLAGS=-static to build a static binary. # # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. @@ -167,12 +27,7 @@ $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) -include $(OUTPUT)PERF-VERSION-FILE -uname_S := $(shell sh -c 'uname -s 2>/dev/null || echo not') -uname_M := $(shell sh -c 'uname -m 2>/dev/null || echo not') -uname_O := $(shell sh -c 'uname -o 2>/dev/null || echo not') -uname_R := $(shell sh -c 'uname -r 2>/dev/null || echo not') -uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') -uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not') +uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ @@ -191,8 +46,6 @@ ifeq ($(ARCH),x86_64) ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S endif -# CFLAGS and LDFLAGS are for the users to override from the command line. - # # Include saner warnings here, which can catch bugs: # @@ -270,22 +123,13 @@ CC = $(CROSS_COMPILE)gcc AR = $(CROSS_COMPILE)ar RM = rm -f MKDIR = mkdir -TAR = tar FIND = find INSTALL = install -RPMBUILD = rpmbuild -PTHREAD_LIBS = -lpthread # sparse is architecture-neutral, which means that we need to tell it # explicitly what architecture to check for. Fix this up for yours.. SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__ -ifeq ($(V), 2) - QUIET_STDERR = ">/dev/null" -else - QUIET_STDERR = ">/dev/null 2>&1" -endif - -include feature-tests.mak ifeq ($(call try-cc,$(SOURCE_HELLO),-Werror -fstack-protector-all),y) @@ -310,49 +154,37 @@ BASIC_LDFLAGS = # Guard against environment variables BUILTIN_OBJS = -BUILT_INS = -COMPAT_CFLAGS = -COMPAT_OBJS = LIB_H = LIB_OBJS = -SCRIPT_PERL = +PYRF_OBJS = SCRIPT_SH = -TEST_PROGRAMS = SCRIPT_SH += perf-archive.sh grep-libs = $(filter -l%,$(1)) strip-libs = $(filter-out -l%,$(1)) +$(OUTPUT)python/perf.so: $(PYRF_OBJS) + $(QUIET_GEN)python util/setup.py --quiet build_ext --build-lib='$(OUTPUT)python' \ + --build-temp='$(OUTPUT)python/temp' # # No Perl scripts right now: # -# SCRIPT_PERL += perf-add--interactive.perl - -SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) \ - $(patsubst %.perl,%,$(SCRIPT_PERL)) - -# Empty... -EXTRA_PROGRAMS = - -# ... and all the rest that could be moved out of bindir to perfexecdir -PROGRAMS += $(EXTRA_PROGRAMS) +SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH)) # # Single 'perf' binary right now: # PROGRAMS += $(OUTPUT)perf -# List built-in command $C whose implementation cmd_$C() is not in -# builtin-$C.o but is linked in as part of some other command. -# +LANG_BINDINGS = # what 'all' will build and 'install' will install, in perfexecdir ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS) # what 'all' will build but not install in perfexecdir -OTHER_PROGRAMS = $(OUTPUT)perf$X +OTHER_PROGRAMS = $(OUTPUT)perf # Set paths to tools early so that they can be used for version tests. ifndef SHELL_PATH @@ -395,6 +227,7 @@ LIB_H += util/include/dwarf-regs.h LIB_H += util/include/asm/dwarf2.h LIB_H += util/include/asm/cpufeature.h LIB_H += perf.h +LIB_H += util/annotate.h LIB_H += util/cache.h LIB_H += util/callchain.h LIB_H += util/build-id.h @@ -402,6 +235,7 @@ LIB_H += util/debug.h LIB_H += util/debugfs.h LIB_H += util/event.h LIB_H += util/evsel.h +LIB_H += util/evlist.h LIB_H += util/exec_cmd.h LIB_H += util/types.h LIB_H += util/levenshtein.h @@ -416,6 +250,7 @@ LIB_H += util/help.h LIB_H += util/session.h LIB_H += util/strbuf.h LIB_H += util/strlist.h +LIB_H += util/strfilter.h LIB_H += util/svghelper.h LIB_H += util/run-command.h LIB_H += util/sigchain.h @@ -425,21 +260,26 @@ LIB_H += util/values.h LIB_H += util/sort.h LIB_H += util/hist.h LIB_H += util/thread.h +LIB_H += util/thread_map.h LIB_H += util/trace-event.h LIB_H += util/probe-finder.h LIB_H += util/probe-event.h LIB_H += util/pstack.h LIB_H += util/cpumap.h +LIB_H += util/top.h LIB_H += $(ARCH_INCLUDE) +LIB_H += util/cgroup.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o +LIB_OBJS += $(OUTPUT)util/annotate.o LIB_OBJS += $(OUTPUT)util/build-id.o LIB_OBJS += $(OUTPUT)util/config.o LIB_OBJS += $(OUTPUT)util/ctype.o LIB_OBJS += $(OUTPUT)util/debugfs.o LIB_OBJS += $(OUTPUT)util/environment.o LIB_OBJS += $(OUTPUT)util/event.o +LIB_OBJS += $(OUTPUT)util/evlist.o LIB_OBJS += $(OUTPUT)util/evsel.o LIB_OBJS += $(OUTPUT)util/exec_cmd.o LIB_OBJS += $(OUTPUT)util/help.o @@ -455,6 +295,8 @@ LIB_OBJS += $(OUTPUT)util/quote.o LIB_OBJS += $(OUTPUT)util/strbuf.o LIB_OBJS += $(OUTPUT)util/string.o LIB_OBJS += $(OUTPUT)util/strlist.o +LIB_OBJS += $(OUTPUT)util/strfilter.o +LIB_OBJS += $(OUTPUT)util/top.o LIB_OBJS += $(OUTPUT)util/usage.o LIB_OBJS += $(OUTPUT)util/wrapper.o LIB_OBJS += $(OUTPUT)util/sigchain.o @@ -469,6 +311,7 @@ LIB_OBJS += $(OUTPUT)util/map.o LIB_OBJS += $(OUTPUT)util/pstack.o LIB_OBJS += $(OUTPUT)util/session.o LIB_OBJS += $(OUTPUT)util/thread.o +LIB_OBJS += $(OUTPUT)util/thread_map.o LIB_OBJS += $(OUTPUT)util/trace-event-parse.o LIB_OBJS += $(OUTPUT)util/trace-event-read.o LIB_OBJS += $(OUTPUT)util/trace-event-info.o @@ -480,6 +323,7 @@ LIB_OBJS += $(OUTPUT)util/probe-event.o LIB_OBJS += $(OUTPUT)util/util.o LIB_OBJS += $(OUTPUT)util/xyarray.o LIB_OBJS += $(OUTPUT)util/cpumap.o +LIB_OBJS += $(OUTPUT)util/cgroup.o BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o @@ -514,6 +358,20 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o PERFLIBS = $(LIB_FILE) +# Files needed for the python binding, perf.so +# pyrf is just an internal name needed for all those wrappers. +# This has to be in sync with what is in the 'sources' variable in +# tools/perf/util/setup.py + +PYRF_OBJS += $(OUTPUT)util/cpumap.o +PYRF_OBJS += $(OUTPUT)util/ctype.o +PYRF_OBJS += $(OUTPUT)util/evlist.o +PYRF_OBJS += $(OUTPUT)util/evsel.o +PYRF_OBJS += $(OUTPUT)util/python.o +PYRF_OBJS += $(OUTPUT)util/thread_map.o +PYRF_OBJS += $(OUTPUT)util/util.o +PYRF_OBJS += $(OUTPUT)util/xyarray.o + # # Platform specific tweaks # @@ -535,22 +393,6 @@ endif # NO_DWARF -include arch/$(ARCH)/Makefile -ifeq ($(uname_S),Darwin) - ifndef NO_FINK - ifeq ($(shell test -d /sw/lib && echo y),y) - BASIC_CFLAGS += -I/sw/include - BASIC_LDFLAGS += -L/sw/lib - endif - endif - ifndef NO_DARWIN_PORTS - ifeq ($(shell test -d /opt/local/lib && echo y),y) - BASIC_CFLAGS += -I/opt/local/include - BASIC_LDFLAGS += -L/opt/local/lib - endif - endif - PTHREAD_LIBS = -endif - ifneq ($(OUTPUT),) BASIC_CFLAGS += -I$(OUTPUT) endif @@ -595,6 +437,7 @@ else LIB_OBJS += $(OUTPUT)util/ui/browsers/annotate.o LIB_OBJS += $(OUTPUT)util/ui/browsers/hists.o LIB_OBJS += $(OUTPUT)util/ui/browsers/map.o + LIB_OBJS += $(OUTPUT)util/ui/browsers/top.o LIB_OBJS += $(OUTPUT)util/ui/helpline.o LIB_OBJS += $(OUTPUT)util/ui/progress.o LIB_OBJS += $(OUTPUT)util/ui/util.o @@ -604,6 +447,7 @@ else LIB_H += util/ui/libslang.h LIB_H += util/ui/progress.h LIB_H += util/ui/util.h + LIB_H += util/ui/ui.h endif endif @@ -635,12 +479,14 @@ else PYTHON_EMBED_CCOPTS = `python-config --cflags 2>/dev/null` FLAGS_PYTHON_EMBED=$(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) ifneq ($(call try-cc,$(SOURCE_PYTHON_EMBED),$(FLAGS_PYTHON_EMBED)),y) + msg := $(warning No Python.h found, install python-dev[el] to have python support in 'perf script' and to build the python bindings) BASIC_CFLAGS += -DNO_LIBPYTHON else ALL_LDFLAGS += $(PYTHON_EMBED_LDFLAGS) EXTLIBS += $(PYTHON_EMBED_LIBADD) LIB_OBJS += $(OUTPUT)util/scripting-engines/trace-event-python.o LIB_OBJS += $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o + LANG_BINDINGS += $(OUTPUT)python/perf.so endif endif @@ -690,201 +536,13 @@ else endif endif -ifndef CC_LD_DYNPATH - ifdef NO_R_TO_GCC_LINKER - # Some gcc does not accept and pass -R to the linker to specify - # the runtime dynamic library path. - CC_LD_DYNPATH = -Wl,-rpath, - else - CC_LD_DYNPATH = -R - endif -endif - -ifdef NEEDS_SOCKET - EXTLIBS += -lsocket -endif -ifdef NEEDS_NSL - EXTLIBS += -lnsl -endif -ifdef NO_D_TYPE_IN_DIRENT - BASIC_CFLAGS += -DNO_D_TYPE_IN_DIRENT -endif -ifdef NO_D_INO_IN_DIRENT - BASIC_CFLAGS += -DNO_D_INO_IN_DIRENT -endif -ifdef NO_ST_BLOCKS_IN_STRUCT_STAT - BASIC_CFLAGS += -DNO_ST_BLOCKS_IN_STRUCT_STAT -endif -ifdef USE_NSEC - BASIC_CFLAGS += -DUSE_NSEC -endif -ifdef USE_ST_TIMESPEC - BASIC_CFLAGS += -DUSE_ST_TIMESPEC -endif -ifdef NO_NSEC - BASIC_CFLAGS += -DNO_NSEC -endif -ifdef NO_C99_FORMAT - BASIC_CFLAGS += -DNO_C99_FORMAT -endif -ifdef SNPRINTF_RETURNS_BOGUS - COMPAT_CFLAGS += -DSNPRINTF_RETURNS_BOGUS - COMPAT_OBJS += $(OUTPUT)compat/snprintf.o -endif -ifdef FREAD_READS_DIRECTORIES - COMPAT_CFLAGS += -DFREAD_READS_DIRECTORIES - COMPAT_OBJS += $(OUTPUT)compat/fopen.o -endif -ifdef NO_SYMLINK_HEAD - BASIC_CFLAGS += -DNO_SYMLINK_HEAD -endif -ifdef NO_STRCASESTR - COMPAT_CFLAGS += -DNO_STRCASESTR - COMPAT_OBJS += $(OUTPUT)compat/strcasestr.o -endif -ifdef NO_STRTOUMAX - COMPAT_CFLAGS += -DNO_STRTOUMAX - COMPAT_OBJS += $(OUTPUT)compat/strtoumax.o -endif -ifdef NO_STRTOULL - COMPAT_CFLAGS += -DNO_STRTOULL -endif -ifdef NO_SETENV - COMPAT_CFLAGS += -DNO_SETENV - COMPAT_OBJS += $(OUTPUT)compat/setenv.o -endif -ifdef NO_MKDTEMP - COMPAT_CFLAGS += -DNO_MKDTEMP - COMPAT_OBJS += $(OUTPUT)compat/mkdtemp.o -endif -ifdef NO_UNSETENV - COMPAT_CFLAGS += -DNO_UNSETENV - COMPAT_OBJS += $(OUTPUT)compat/unsetenv.o -endif -ifdef NO_SYS_SELECT_H - BASIC_CFLAGS += -DNO_SYS_SELECT_H -endif -ifdef NO_MMAP - COMPAT_CFLAGS += -DNO_MMAP - COMPAT_OBJS += $(OUTPUT)compat/mmap.o -else - ifdef USE_WIN32_MMAP - COMPAT_CFLAGS += -DUSE_WIN32_MMAP - COMPAT_OBJS += $(OUTPUT)compat/win32mmap.o - endif -endif -ifdef NO_PREAD - COMPAT_CFLAGS += -DNO_PREAD - COMPAT_OBJS += $(OUTPUT)compat/pread.o -endif -ifdef NO_FAST_WORKING_DIRECTORY - BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY -endif -ifdef NO_TRUSTABLE_FILEMODE - BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE -endif -ifdef NO_IPV6 - BASIC_CFLAGS += -DNO_IPV6 -endif -ifdef NO_UINTMAX_T - BASIC_CFLAGS += -Duintmax_t=uint32_t -endif -ifdef NO_SOCKADDR_STORAGE -ifdef NO_IPV6 - BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in -else - BASIC_CFLAGS += -Dsockaddr_storage=sockaddr_in6 -endif -endif -ifdef NO_INET_NTOP - LIB_OBJS += $(OUTPUT)compat/inet_ntop.o -endif -ifdef NO_INET_PTON - LIB_OBJS += $(OUTPUT)compat/inet_pton.o -endif - -ifdef NO_ICONV - BASIC_CFLAGS += -DNO_ICONV -endif - -ifdef OLD_ICONV - BASIC_CFLAGS += -DOLD_ICONV -endif - -ifdef NO_DEFLATE_BOUND - BASIC_CFLAGS += -DNO_DEFLATE_BOUND -endif - -ifdef PPC_SHA1 - SHA1_HEADER = "ppc/sha1.h" - LIB_OBJS += $(OUTPUT)ppc/sha1.o ppc/sha1ppc.o -else -ifdef ARM_SHA1 - SHA1_HEADER = "arm/sha1.h" - LIB_OBJS += $(OUTPUT)arm/sha1.o $(OUTPUT)arm/sha1_arm.o -else -ifdef MOZILLA_SHA1 - SHA1_HEADER = "mozilla-sha1/sha1.h" - LIB_OBJS += $(OUTPUT)mozilla-sha1/sha1.o -else - SHA1_HEADER = <openssl/sha.h> - EXTLIBS += $(LIB_4_CRYPTO) -endif -endif -endif -ifdef NO_PERL_MAKEMAKER - export NO_PERL_MAKEMAKER -endif -ifdef NO_HSTRERROR - COMPAT_CFLAGS += -DNO_HSTRERROR - COMPAT_OBJS += $(OUTPUT)compat/hstrerror.o -endif -ifdef NO_MEMMEM - COMPAT_CFLAGS += -DNO_MEMMEM - COMPAT_OBJS += $(OUTPUT)compat/memmem.o -endif -ifdef INTERNAL_QSORT - COMPAT_CFLAGS += -DINTERNAL_QSORT - COMPAT_OBJS += $(OUTPUT)compat/qsort.o -endif -ifdef RUNTIME_PREFIX - COMPAT_CFLAGS += -DRUNTIME_PREFIX -endif - -ifdef DIR_HAS_BSD_GROUP_SEMANTICS - COMPAT_CFLAGS += -DDIR_HAS_BSD_GROUP_SEMANTICS -endif -ifdef NO_EXTERNAL_GREP - BASIC_CFLAGS += -DNO_EXTERNAL_GREP -endif - -ifeq ($(PERL_PATH),) -NO_PERL=NoThanks -endif - -QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir -QUIET_SUBDIR1 = - -ifneq ($(findstring $(MAKEFLAGS),w),w) -PRINT_DIR = --no-print-directory -else # "make -w" -NO_SUBDIR = : -endif - ifneq ($(findstring $(MAKEFLAGS),s),s) ifndef V QUIET_CC = @echo ' ' CC $@; QUIET_AR = @echo ' ' AR $@; QUIET_LINK = @echo ' ' LINK $@; QUIET_MKDIR = @echo ' ' MKDIR $@; - QUIET_BUILT_IN = @echo ' ' BUILTIN $@; QUIET_GEN = @echo ' ' GEN $@; - QUIET_SUBDIR0 = +@subdir= - QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ - $(MAKE) $(PRINT_DIR) -C $$subdir - export V - export QUIET_GEN - export QUIET_BUILT_IN endif endif @@ -894,7 +552,6 @@ endif # Shell quote (do not use $(call) to accommodate ancient setups); -SHA1_HEADER_SQ = $(subst ','\'',$(SHA1_HEADER)) ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) @@ -908,46 +565,36 @@ htmldir_SQ = $(subst ','\'',$(htmldir)) prefix_SQ = $(subst ','\'',$(prefix)) SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) -PERL_PATH_SQ = $(subst ','\'',$(PERL_PATH)) LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS) -BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \ - $(COMPAT_CFLAGS) -LIB_OBJS += $(COMPAT_OBJS) - ALL_CFLAGS += $(BASIC_CFLAGS) ALL_CFLAGS += $(ARCH_CFLAGS) ALL_LDFLAGS += $(BASIC_LDFLAGS) -export TAR INSTALL DESTDIR SHELL_PATH +export INSTALL SHELL_PATH ### Build rules SHELL = $(SHELL_PATH) -all:: shell_compatibility_test $(ALL_PROGRAMS) $(BUILT_INS) $(OTHER_PROGRAMS) $(OUTPUT)PERF-BUILD-OPTIONS -ifneq (,$X) - $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) perf$X)), test '$p' -ef '$p$X' || $(RM) '$p';) -endif - -all:: +all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) please_set_SHELL_PATH_to_a_more_modern_shell: @$$(:) shell_compatibility_test: please_set_SHELL_PATH_to_a_more_modern_shell -strip: $(PROGRAMS) $(OUTPUT)perf$X - $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf$X +strip: $(PROGRAMS) $(OUTPUT)perf + $(STRIP) $(STRIP_OPTS) $(PROGRAMS) $(OUTPUT)perf $(OUTPUT)perf.o: perf.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -DPERF_VERSION='"$(PERF_VERSION)"' \ '-DPERF_HTML_PATH="$(htmldir_SQ)"' \ $(ALL_CFLAGS) -c $(filter %.c,$^) -o $@ -$(OUTPUT)perf$X: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) +$(OUTPUT)perf: $(OUTPUT)perf.o $(BUILTIN_OBJS) $(PERFLIBS) $(QUIET_LINK)$(CC) $(ALL_CFLAGS) $(ALL_LDFLAGS) $(OUTPUT)perf.o \ $(BUILTIN_OBJS) $(LIBS) -o $@ @@ -963,39 +610,17 @@ $(OUTPUT)builtin-timechart.o: builtin-timechart.c $(OUTPUT)common-cmds.h $(OUTPU '-DPERF_MAN_PATH="$(mandir_SQ)"' \ '-DPERF_INFO_PATH="$(infodir_SQ)"' $< -$(BUILT_INS): $(OUTPUT)perf$X - $(QUIET_BUILT_IN)$(RM) $@ && \ - ln perf$X $@ 2>/dev/null || \ - ln -s perf$X $@ 2>/dev/null || \ - cp perf$X $@ - $(OUTPUT)common-cmds.h: util/generate-cmdlist.sh command-list.txt $(OUTPUT)common-cmds.h: $(wildcard Documentation/perf-*.txt) $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@ -$(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh - $(QUIET_GEN)$(RM) $(OUTPUT)$@ $(OUTPUT)$@+ && \ - sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' \ - -e 's|@SHELL_PATH@|$(SHELL_PATH_SQ)|' \ - -e 's|@@PERL@@|$(PERL_PATH_SQ)|g' \ - -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \ - -e 's/@@NO_CURL@@/$(NO_CURL)/g' \ - $@.sh > $(OUTPUT)$@+ && \ - chmod +x $(OUTPUT)$@+ && \ - mv $(OUTPUT)$@+ $(OUTPUT)$@ - -configure: configure.ac - $(QUIET_GEN)$(RM) $@ $<+ && \ - sed -e 's/@@PERF_VERSION@@/$(PERF_VERSION)/g' \ - $< > $<+ && \ - autoconf -o $@ $<+ && \ - $(RM) $<+ +$(SCRIPTS) : % : %.sh + $(QUIET_GEN)$(INSTALL) '$@.sh' '$(OUTPUT)$@' # These can record PERF_VERSION $(OUTPUT)perf.o perf.spec \ - $(patsubst %.sh,%,$(SCRIPT_SH)) \ - $(patsubst %.perl,%,$(SCRIPT_PERL)) \ + $(SCRIPTS) \ : $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS @@ -1012,9 +637,6 @@ $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS '-DPREFIX="$(prefix_SQ)"' \ $< -$(OUTPUT)builtin-init-db.o: builtin-init-db.c $(OUTPUT)PERF-CFLAGS - $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DDEFAULT_PERF_TEMPLATE_DIR='"$(template_dir_SQ)"' $< - $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< @@ -1024,6 +646,9 @@ $(OUTPUT)util/ui/browser.o: util/ui/browser.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/ui/browsers/annotate.o: util/ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< +$(OUTPUT)util/ui/browsers/top.o: util/ui/browsers/top.c $(OUTPUT)PERF-CFLAGS + $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< + $(OUTPUT)util/ui/browsers/hists.o: util/ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< @@ -1045,12 +670,11 @@ $(OUTPUT)util/scripting-engines/trace-event-python.o: util/scripting-engines/tra $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Util/Context.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs $< -$(OUTPUT)perf-%$X: %.o $(PERFLIBS) +$(OUTPUT)perf-%: %.o $(PERFLIBS) $(QUIET_LINK)$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS) $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H) -$(patsubst perf-%$X,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) -builtin-revert.o wt-status.o: wt-status.h +$(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h) # we compile into subdirectories. if the target directory is not the source directory, they might not exists. So # we depend the various files onto their directories. @@ -1063,6 +687,36 @@ $(sort $(dir $(DIRECTORY_DEPS))): $(LIB_FILE): $(LIB_OBJS) $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIB_OBJS) +help: + @echo 'Perf make targets:' + @echo ' doc - make *all* documentation (see below)' + @echo ' man - make manpage documentation (access with man <foo>)' + @echo ' html - make html documentation' + @echo ' info - make GNU info documentation (access with info <foo>)' + @echo ' pdf - make pdf documentation' + @echo ' TAGS - use etags to make tag information for source browsing' + @echo ' tags - use ctags to make tag information for source browsing' + @echo ' cscope - use cscope to make interactive browsing database' + @echo '' + @echo 'Perf install targets:' + @echo ' NOTE: documentation build requires asciidoc, xmlto packages to be installed' + @echo ' HINT: use "make prefix=<path> <install target>" to install to a particular' + @echo ' path like make prefix=/usr/local install install-doc' + @echo ' install - install compiled binaries' + @echo ' install-doc - install *all* documentation' + @echo ' install-man - install manpage documentation' + @echo ' install-html - install html documentation' + @echo ' install-info - install GNU info documentation' + @echo ' install-pdf - install pdf documentation' + @echo '' + @echo ' quick-install-doc - alias for quick-install-man' + @echo ' quick-install-man - install the documentation quickly' + @echo ' quick-install-html - install the html documentation quickly' + @echo '' + @echo 'Perf maintainer targets:' + @echo ' distclean - alias to clean' + @echo ' clean - clean all binary objects and build output' + doc: $(MAKE) -C Documentation all @@ -1101,30 +755,12 @@ $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS echo "$$FLAGS" >$(OUTPUT)PERF-CFLAGS; \ fi -# We need to apply sq twice, once to protect from the shell -# that runs $(OUTPUT)PERF-BUILD-OPTIONS, and then again to protect it -# and the first level quoting from the shell that runs "echo". -$(OUTPUT)PERF-BUILD-OPTIONS: .FORCE-PERF-BUILD-OPTIONS - @echo SHELL_PATH=\''$(subst ','\'',$(SHELL_PATH_SQ))'\' >$@ - @echo TAR=\''$(subst ','\'',$(subst ','\'',$(TAR)))'\' >>$@ - @echo NO_CURL=\''$(subst ','\'',$(subst ','\'',$(NO_CURL)))'\' >>$@ - @echo NO_PERL=\''$(subst ','\'',$(subst ','\'',$(NO_PERL)))'\' >>$@ - ### Testing rules -# -# None right now: -# -# TEST_PROGRAMS += test-something$X - -all:: $(TEST_PROGRAMS) - # GNU make supports exporting all variables by "export" without parameters. # However, the environment gets quite big, and some programs have problems # with that. -export NO_SVN_TESTS - check: $(OUTPUT)common-cmds.h if sparse; \ then \ @@ -1133,33 +769,21 @@ check: $(OUTPUT)common-cmds.h sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; \ done; \ else \ - echo 2>&1 "Did you mean 'make test'?"; \ exit 1; \ fi -remove-dashes: - ./fixup-builtins $(BUILT_INS) $(PROGRAMS) $(SCRIPTS) - ### Installation rules -ifneq ($(filter /%,$(firstword $(template_dir))),) -template_instdir = $(template_dir) -else -template_instdir = $(prefix)/$(template_dir) -endif -export template_instdir - ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) else perfexec_instdir = $(prefix)/$(perfexecdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) -export perfexec_instdir install: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' - $(INSTALL) $(OUTPUT)perf$X '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/bin' $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' @@ -1172,14 +796,6 @@ install: all $(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python' $(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin' -ifdef BUILT_INS - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' - $(INSTALL) $(BUILT_INS) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' -ifneq (,$X) - $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) $(OUTPUT)perf$X)), $(RM) '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/$p';) -endif -endif - install-doc: $(MAKE) -C Documentation install @@ -1204,104 +820,17 @@ quick-install-man: quick-install-html: $(MAKE) -C Documentation quick-install-html - -### Maintainer's dist rules -# -# None right now -# -# -# perf.spec: perf.spec.in -# sed -e 's/@@VERSION@@/$(PERF_VERSION)/g' < $< > $@+ -# mv $@+ $@ -# -# PERF_TARNAME=perf-$(PERF_VERSION) -# dist: perf.spec perf-archive$(X) configure -# ./perf-archive --format=tar \ -# --prefix=$(PERF_TARNAME)/ HEAD^{tree} > $(PERF_TARNAME).tar -# @mkdir -p $(PERF_TARNAME) -# @cp perf.spec configure $(PERF_TARNAME) -# @echo $(PERF_VERSION) > $(PERF_TARNAME)/version -# $(TAR) rf $(PERF_TARNAME).tar \ -# $(PERF_TARNAME)/perf.spec \ -# $(PERF_TARNAME)/configure \ -# $(PERF_TARNAME)/version -# @$(RM) -r $(PERF_TARNAME) -# gzip -f -9 $(PERF_TARNAME).tar -# -# htmldocs = perf-htmldocs-$(PERF_VERSION) -# manpages = perf-manpages-$(PERF_VERSION) -# dist-doc: -# $(RM) -r .doc-tmp-dir -# mkdir .doc-tmp-dir -# $(MAKE) -C Documentation WEBDOC_DEST=../.doc-tmp-dir install-webdoc -# cd .doc-tmp-dir && $(TAR) cf ../$(htmldocs).tar . -# gzip -n -9 -f $(htmldocs).tar -# : -# $(RM) -r .doc-tmp-dir -# mkdir -p .doc-tmp-dir/man1 .doc-tmp-dir/man5 .doc-tmp-dir/man7 -# $(MAKE) -C Documentation DESTDIR=./ \ -# man1dir=../.doc-tmp-dir/man1 \ -# man5dir=../.doc-tmp-dir/man5 \ -# man7dir=../.doc-tmp-dir/man7 \ -# install -# cd .doc-tmp-dir && $(TAR) cf ../$(manpages).tar . -# gzip -n -9 -f $(manpages).tar -# $(RM) -r .doc-tmp-dir -# -# rpm: dist -# $(RPMBUILD) -ta $(PERF_TARNAME).tar.gz - ### Cleaning rules -distclean: clean -# $(RM) configure - clean: - $(RM) *.o */*.o */*/*.o */*/*/*.o $(LIB_FILE) - $(RM) $(ALL_PROGRAMS) $(BUILT_INS) perf$X - $(RM) $(TEST_PROGRAMS) + $(RM) $(OUTPUT){*.o,*/*.o,*/*/*.o,*/*/*/*.o,$(LIB_FILE),perf-archive} + $(RM) $(ALL_PROGRAMS) perf $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* - $(RM) -r autom4te.cache - $(RM) config.log config.mak.autogen config.mak.append config.status config.cache - $(RM) -r $(PERF_TARNAME) .doc-tmp-dir - $(RM) $(PERF_TARNAME).tar.gz perf-core_$(PERF_VERSION)-*.tar.gz - $(RM) $(htmldocs).tar.gz $(manpages).tar.gz $(MAKE) -C Documentation/ clean - $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-BUILD-OPTIONS + $(RM) $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS + @python util/setup.py clean --build-lib='$(OUTPUT)python' \ + --build-temp='$(OUTPUT)python/temp' .PHONY: all install clean strip .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope .FORCE-PERF-CFLAGS -.PHONY: .FORCE-PERF-BUILD-OPTIONS - -### Make sure built-ins do not have dups and listed in perf.c -# -check-builtins:: - ./check-builtins.sh - -### Test suite coverage testing -# -# None right now -# -# .PHONY: coverage coverage-clean coverage-build coverage-report -# -# coverage: -# $(MAKE) coverage-build -# $(MAKE) coverage-report -# -# coverage-clean: -# rm -f *.gcda *.gcno -# -# COVERAGE_CFLAGS = $(CFLAGS) -O0 -ftest-coverage -fprofile-arcs -# COVERAGE_LDFLAGS = $(CFLAGS) -O0 -lgcov -# -# coverage-build: coverage-clean -# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" all -# $(MAKE) CFLAGS="$(COVERAGE_CFLAGS)" LDFLAGS="$(COVERAGE_LDFLAGS)" \ -# -j1 test -# -# coverage-report: -# gcov -b *.c */*.c -# grep '^function.*called 0 ' *.c.gcov */*.c.gcov \ -# | sed -e 's/\([^:]*\)\.gcov: *function \([^ ]*\) called.*/\1: \2/' \ -# | tee coverage-untested-functions diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index d9ab3ce..0c7454f 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -55,7 +55,7 @@ int bench_sched_pipe(int argc, const char **argv, * discarding returned value of read(), write() * causes error in building environment for perf */ - int ret, wait_stat; + int __used ret, wait_stat; pid_t pid, retpid; argc = parse_options(argc, argv, options, diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 8879463..695de4b 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -9,6 +9,7 @@ #include "util/util.h" +#include "util/util.h" #include "util/color.h" #include <linux/list.h> #include "util/cache.h" @@ -18,6 +19,9 @@ #include "perf.h" #include "util/debug.h" +#include "util/evlist.h" +#include "util/evsel.h" +#include "util/annotate.h" #include "util/event.h" #include "util/parse-options.h" #include "util/parse-events.h" @@ -36,9 +40,13 @@ static bool print_line; static const char *sym_hist_filter; -static int hists__add_entry(struct hists *self, struct addr_location *al) +static int perf_evlist__add_sample(struct perf_evlist *evlist, + struct perf_sample *sample, + struct addr_location *al) { + struct perf_evsel *evsel; struct hist_entry *he; + int ret; if (sym_hist_filter != NULL && (al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) { @@ -51,25 +59,51 @@ static int hists__add_entry(struct hists *self, struct addr_location *al) return 0; } - he = __hists__add_entry(self, al, NULL, 1); + evsel = perf_evlist__id2evsel(evlist, sample->id); + if (evsel == NULL) { + /* + * FIXME: Propagate this back, but at least we're in a builtin, + * where exit() is allowed. ;-) + */ + ui__warning("Invalid %s file, contains samples with id not in " + "its header!\n", input_name); + exit_browser(0); + exit(1); + } + + he = __hists__add_entry(&evsel->hists, al, NULL, 1); if (he == NULL) return -ENOMEM; - return hist_entry__inc_addr_samples(he, al->addr); + ret = 0; + if (he->ms.sym != NULL) { + struct annotation *notes = symbol__annotation(he->ms.sym); + if (notes->src == NULL && + symbol__alloc_hist(he->ms.sym, evlist->nr_entries) < 0) + return -ENOMEM; + + ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + } + + evsel->hists.stats.total_period += sample->period; + hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + return ret; } -static int process_sample_event(event_t *event, struct sample_data *sample, +static int process_sample_event(union perf_event *event, + struct perf_sample *sample, struct perf_session *session) { struct addr_location al; - if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) { + if (perf_event__preprocess_sample(event, session, &al, sample, + symbol__annotate_init) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; } - if (!al.filtered && hists__add_entry(&session->hists, &al)) { + if (!al.filtered && perf_evlist__add_sample(session->evlist, sample, &al)) { pr_warning("problem incrementing symbol count, " "skipping event\n"); return -1; @@ -78,261 +112,26 @@ static int process_sample_event(event_t *event, struct sample_data *sample, return 0; } -static int objdump_line__print(struct objdump_line *self, - struct list_head *head, - struct hist_entry *he, u64 len) -{ - struct symbol *sym = he->ms.sym; - static const char *prev_line; - static const char *prev_color; - - if (self->offset != -1) { - const char *path = NULL; - unsigned int hits = 0; - double percent = 0.0; - const char *color; - struct sym_priv *priv = symbol__priv(sym); - struct sym_ext *sym_ext = priv->ext; - struct sym_hist *h = priv->hist; - s64 offset = self->offset; - struct objdump_line *next = objdump__get_next_ip_line(head, self); - - while (offset < (s64)len && - (next == NULL || offset < next->offset)) { - if (sym_ext) { - if (path == NULL) - path = sym_ext[offset].path; - percent += sym_ext[offset].percent; - } else - hits += h->ip[offset]; - - ++offset; - } - - if (sym_ext == NULL && h->sum) - percent = 100.0 * hits / h->sum; - - color = get_percent_color(percent); - - /* - * Also color the filename and line if needed, with - * the same color than the percentage. Don't print it - * twice for close colored ip with the same filename:line - */ - if (path) { - if (!prev_line || strcmp(prev_line, path) - || color != prev_color) { - color_fprintf(stdout, color, " %s", path); - prev_line = path; - prev_color = color; - } - } - - color_fprintf(stdout, color, " %7.2f", percent); - printf(" : "); - color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", self->line); - } else { - if (!*self->line) - printf(" :\n"); - else - printf(" : %s\n", self->line); - } - - return 0; -} - -static struct rb_root root_sym_ext; - -static void insert_source_line(struct sym_ext *sym_ext) -{ - struct sym_ext *iter; - struct rb_node **p = &root_sym_ext.rb_node; - struct rb_node *parent = NULL; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct sym_ext, node); - - if (sym_ext->percent > iter->percent) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&sym_ext->node, parent, p); - rb_insert_color(&sym_ext->node, &root_sym_ext); -} - -static void free_source_line(struct hist_entry *he, int len) -{ - struct sym_priv *priv = symbol__priv(he->ms.sym); - struct sym_ext *sym_ext = priv->ext; - int i; - - if (!sym_ext) - return; - - for (i = 0; i < len; i++) - free(sym_ext[i].path); - free(sym_ext); - - priv->ext = NULL; - root_sym_ext = RB_ROOT; -} - -/* Get the filename:line for the colored entries */ -static void -get_source_line(struct hist_entry *he, int len, const char *filename) -{ - struct symbol *sym = he->ms.sym; - u64 start; - int i; - char cmd[PATH_MAX * 2]; - struct sym_ext *sym_ext; - struct sym_priv *priv = symbol__priv(sym); - struct sym_hist *h = priv->hist; - - if (!h->sum) - return; - - sym_ext = priv->ext = calloc(len, sizeof(struct sym_ext)); - if (!priv->ext) - return; - - start = he->ms.map->unmap_ip(he->ms.map, sym->start); - - for (i = 0; i < len; i++) { - char *path = NULL; - size_t line_len; - u64 offset; - FILE *fp; - - sym_ext[i].percent = 100.0 * h->ip[i] / h->sum; - if (sym_ext[i].percent <= 0.5) - continue; - - offset = start + i; - sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset); - fp = popen(cmd, "r"); - if (!fp) - continue; - - if (getline(&path, &line_len, fp) < 0 || !line_len) - goto next; - - sym_ext[i].path = malloc(sizeof(char) * line_len + 1); - if (!sym_ext[i].path) - goto next; - - strcpy(sym_ext[i].path, path); - insert_source_line(&sym_ext[i]); - - next: - pclose(fp); - } -} - -static void print_summary(const char *filename) -{ - struct sym_ext *sym_ext; - struct rb_node *node; - - printf("\nSorted summary for file %s\n", filename); - printf("----------------------------------------------\n\n"); - - if (RB_EMPTY_ROOT(&root_sym_ext)) { - printf(" Nothing higher than %1.1f%%\n", MIN_GREEN); - return; - } - - node = rb_first(&root_sym_ext); - while (node) { - double percent; - const char *color; - char *path; - - sym_ext = rb_entry(node, struct sym_ext, node); - percent = sym_ext->percent; - color = get_percent_color(percent); - path = sym_ext->path; - - color_fprintf(stdout, color, " %7.2f %s", percent, path); - node = rb_next(node); - } -} - -static void hist_entry__print_hits(struct hist_entry *self) -{ - struct symbol *sym = self->ms.sym; - struct sym_priv *priv = symbol__priv(sym); - struct sym_hist *h = priv->hist; - u64 len = sym->end - sym->start, offset; - - for (offset = 0; offset < len; ++offset) - if (h->ip[offset] != 0) - printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, - sym->start + offset, h->ip[offset]); - printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); -} - -static int hist_entry__tty_annotate(struct hist_entry *he) +static int hist_entry__tty_annotate(struct hist_entry *he, int evidx) { - struct map *map = he->ms.map; - struct dso *dso = map->dso; - struct symbol *sym = he->ms.sym; - const char *filename = dso->long_name, *d_filename; - u64 len; - LIST_HEAD(head); - struct objdump_line *pos, *n; - - if (hist_entry__annotate(he, &head, 0) < 0) - return -1; - - if (full_paths) - d_filename = filename; - else - d_filename = basename(filename); - - len = sym->end - sym->start; - - if (print_line) { - get_source_line(he, len, filename); - print_summary(filename); - } - - printf("\n\n------------------------------------------------\n"); - printf(" Percent | Source code & Disassembly of %s\n", d_filename); - printf("------------------------------------------------\n"); - - if (verbose) - hist_entry__print_hits(he); - - list_for_each_entry_safe(pos, n, &head, node) { - objdump_line__print(pos, &head, he, len); - list_del(&pos->node); - objdump_line__free(pos); - } - - if (print_line) - free_source_line(he, len); - - return 0; + return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx, + print_line, full_paths, 0, 0); } -static void hists__find_annotations(struct hists *self) +static void hists__find_annotations(struct hists *self, int evidx) { struct rb_node *nd = rb_first(&self->entries), *next; int key = KEY_RIGHT; while (nd) { struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); - struct sym_priv *priv; + struct annotation *notes; if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned) goto find_next; - priv = symbol__priv(he->ms.sym); - if (priv->hist == NULL) { + notes = symbol__annotation(he->ms.sym); + if (notes->src == NULL) { find_next: if (key == KEY_LEFT) nd = rb_prev(nd); @@ -342,7 +141,7 @@ find_next: } if (use_browser > 0) { - key = hist_entry__tui_annotate(he); + key = hist_entry__tui_annotate(he, evidx); switch (key) { case KEY_RIGHT: next = rb_next(nd); @@ -357,24 +156,24 @@ find_next: if (next != NULL) nd = next; } else { - hist_entry__tty_annotate(he); + hist_entry__tty_annotate(he, evidx); nd = rb_next(nd); /* * Since we have a hist_entry per IP for the same - * symbol, free he->ms.sym->hist to signal we already + * symbol, free he->ms.sym->src to signal we already * processed this symbol. */ - free(priv->hist); - priv->hist = NULL; + free(notes->src); + notes->src = NULL; } } } static struct perf_event_ops event_ops = { .sample = process_sample_event, - .mmap = event__process_mmap, - .comm = event__process_comm, - .fork = event__process_task, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .fork = perf_event__process_task, .ordered_samples = true, .ordering_requires_timestamps = true, }; @@ -383,6 +182,8 @@ static int __cmd_annotate(void) { int ret; struct perf_session *session; + struct perf_evsel *pos; + u64 total_nr_samples; session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops); if (session == NULL) @@ -403,12 +204,36 @@ static int __cmd_annotate(void) if (verbose > 2) perf_session__fprintf_dsos(session, stdout); - hists__collapse_resort(&session->hists); - hists__output_resort(&session->hists); - hists__find_annotations(&session->hists); -out_delete: - perf_session__delete(session); + total_nr_samples = 0; + list_for_each_entry(pos, &session->evlist->entries, node) { + struct hists *hists = &pos->hists; + u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE]; + + if (nr_samples > 0) { + total_nr_samples += nr_samples; + hists__collapse_resort(hists); + hists__output_resort(hists); + hists__find_annotations(hists, pos->idx); + } + } + if (total_nr_samples == 0) { + ui__warning("The %s file has no samples!\n", input_name); + goto out_delete; + } +out_delete: + /* + * Speed up the exit process, for large files this can + * take quite a while. + * + * XXX Enable this when using valgrind or if we ever + * librarize this command. + * + * Also experiment with obstacks to see how much speed + * up we'll get here. + * + * perf_session__delete(session); + */ return ret; } @@ -451,9 +276,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __used) else if (use_tui) use_browser = 1; - setup_browser(); + setup_browser(true); - symbol_conf.priv_size = sizeof(struct sym_priv); + symbol_conf.priv_size = sizeof(struct annotation); symbol_conf.try_vmlinux_path = true; if (symbol__init() < 0) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 3153e49..6b7d911 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -30,13 +30,13 @@ static int hists__add_entry(struct hists *self, return -ENOMEM; } -static int diff__process_sample_event(event_t *event, - struct sample_data *sample, +static int diff__process_sample_event(union perf_event *event, + struct perf_sample *sample, struct perf_session *session) { struct addr_location al; - if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) { + if (perf_event__preprocess_sample(event, session, &al, sample, NULL) < 0) { pr_warning("problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -56,11 +56,11 @@ static int diff__process_sample_event(event_t *event, static struct perf_event_ops event_ops = { .sample = diff__process_sample_event, - .mmap = event__process_mmap, - .comm = event__process_comm, - .exit = event__process_task, - .fork = event__process_task, - .lost = event__process_lost, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .exit = perf_event__process_task, + .fork = perf_event__process_task, + .lost = perf_event__process_lost, .ordered_samples = true, .ordering_requires_timestamps = true, }; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 0c78ffa..e29f04e 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -16,8 +16,8 @@ static char const *input_name = "-"; static bool inject_build_ids; -static int event__repipe_synth(event_t *event, - struct perf_session *session __used) +static int perf_event__repipe_synth(union perf_event *event, + struct perf_session *session __used) { uint32_t size; void *buf = event; @@ -36,41 +36,44 @@ static int event__repipe_synth(event_t *event, return 0; } -static int event__repipe(event_t *event, struct sample_data *sample __used, - struct perf_session *session) +static int perf_event__repipe(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { - return event__repipe_synth(event, session); + return perf_event__repipe_synth(event, session); } -static int event__repipe_mmap(event_t *self, struct sample_data *sample, - struct perf_session *session) +static int perf_event__repipe_mmap(union perf_event *event, + struct perf_sample *sample, + struct perf_session *session) { int err; - err = event__process_mmap(self, sample, session); - event__repipe(self, sample, session); + err = perf_event__process_mmap(event, sample, session); + perf_event__repipe(event, sample, session); return err; } -static int event__repipe_task(event_t *self, struct sample_data *sample, - struct perf_session *session) +static int perf_event__repipe_task(union perf_event *event, + struct perf_sample *sample, + struct perf_session *session) { int err; - err = event__process_task(self, sample, session); - event__repipe(self, sample, session); + err = perf_event__process_task(event, sample, session); + perf_event__repipe(event, sample, session); return err; } -static int event__repipe_tracing_data(event_t *self, - struct perf_session *session) +static int perf_event__repipe_tracing_data(union perf_event *event, + struct perf_session *session) { int err; - event__repipe_synth(self, session); - err = event__process_tracing_data(self, session); + perf_event__repipe_synth(event, session); + err = perf_event__process_tracing_data(event, session); return err; } @@ -109,8 +112,8 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session) if (self->kernel) misc = PERF_RECORD_MISC_KERNEL; - err = event__synthesize_build_id(self, misc, event__repipe, - machine, session); + err = perf_event__synthesize_build_id(self, misc, perf_event__repipe, + machine, session); if (err) { pr_err("Can't synthesize build_id event for %s\n", self->long_name); return -1; @@ -119,8 +122,9 @@ static int dso__inject_build_id(struct dso *self, struct perf_session *session) return 0; } -static int event__inject_buildid(event_t *event, struct sample_data *sample, - struct perf_session *session) +static int perf_event__inject_buildid(union perf_event *event, + struct perf_sample *sample, + struct perf_session *session) { struct addr_location al; struct thread *thread; @@ -155,24 +159,24 @@ static int event__inject_buildid(event_t *event, struct sample_data *sample, } repipe: - event__repipe(event, sample, session); + perf_event__repipe(event, sample, session); return 0; } struct perf_event_ops inject_ops = { - .sample = event__repipe, - .mmap = event__repipe, - .comm = event__repipe, - .fork = event__repipe, - .exit = event__repipe, - .lost = event__repipe, - .read = event__repipe, - .throttle = event__repipe, - .unthrottle = event__repipe, - .attr = event__repipe_synth, - .event_type = event__repipe_synth, - .tracing_data = event__repipe_synth, - .build_id = event__repipe_synth, + .sample = perf_event__repipe, + .mmap = perf_event__repipe, + .comm = perf_event__repipe, + .fork = perf_event__repipe, + .exit = perf_event__repipe, + .lost = perf_event__repipe, + .read = perf_event__repipe, + .throttle = perf_event__repipe, + .unthrottle = perf_event__repipe, + .attr = perf_event__repipe_synth, + .event_type = perf_event__repipe_synth, + .tracing_data = perf_event__repipe_synth, + .build_id = perf_event__repipe_synth, }; extern volatile int session_done; @@ -190,10 +194,10 @@ static int __cmd_inject(void) signal(SIGINT, sig_handler); if (inject_build_ids) { - inject_ops.sample = event__inject_buildid; - inject_ops.mmap = event__repipe_mmap; - inject_ops.fork = event__repipe_task; - inject_ops.tracing_data = event__repipe_tracing_data; + inject_ops.sample = perf_event__inject_buildid; + inject_ops.mmap = perf_event__repipe_mmap; + inject_ops.fork = perf_event__repipe_task; + inject_ops.tracing_data = perf_event__repipe_tracing_data; } session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index d97256d..7f618f4 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -275,9 +275,8 @@ static void process_free_event(void *data, s_alloc->alloc_cpu = -1; } -static void -process_raw_event(event_t *raw_event __used, void *data, - int cpu, u64 timestamp, struct thread *thread) +static void process_raw_event(union perf_event *raw_event __used, void *data, + int cpu, u64 timestamp, struct thread *thread) { struct event *event; int type; @@ -304,7 +303,8 @@ process_raw_event(event_t *raw_event __used, void *data, } } -static int process_sample_event(event_t *event, struct sample_data *sample, +static int process_sample_event(union perf_event *event, + struct perf_sample *sample, struct perf_session *session) { struct thread *thread = perf_session__findnew(session, event->ip.pid); @@ -325,7 +325,7 @@ static int process_sample_event(event_t *event, struct sample_data *sample, static struct perf_event_ops event_ops = { .sample = process_sample_event, - .comm = event__process_comm, + .comm = perf_event__process_comm, .ordered_samples = true, }; diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index d88c696..6313b6e 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -5,6 +5,7 @@ * * Copyright (C) 2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2009, Red Hat Inc, Ingo Molnar <mingo@redhat.com> + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> */ #include "builtin.h" @@ -13,9 +14,47 @@ #include "util/parse-events.h" #include "util/cache.h" -int cmd_list(int argc __used, const char **argv __used, const char *prefix __used) +int cmd_list(int argc, const char **argv, const char *prefix __used) { setup_pager(); - print_events(); + + if (argc == 1) + print_events(NULL); + else { + int i; + + for (i = 1; i < argc; ++i) { + if (i > 1) + putchar('\n'); + if (strncmp(argv[i], "tracepoint", 10) == 0) + print_tracepoint_events(NULL, NULL); + else if (strcmp(argv[i], "hw") == 0 || + strcmp(argv[i], "hardware") == 0) + print_events_type(PERF_TYPE_HARDWARE); + else if (strcmp(argv[i], "sw") == 0 || + strcmp(argv[i], "software") == 0) + print_events_type(PERF_TYPE_SOFTWARE); + else if (strcmp(argv[i], "cache") == 0 || + strcmp(argv[i], "hwcache") == 0) + print_hwcache_events(NULL); + else { + char *sep = strchr(argv[i], ':'), *s; + int sep_idx; + + if (sep == NULL) { + print_events(argv[i]); + continue; + } + sep_idx = sep - argv[i]; + s = strdup(argv[i]); + if (s == NULL) + return -1; + + s[sep_idx] = '\0'; + print_tracepoint_events(s, s + sep_idx + 1); + free(s); + } + } + } return 0; } diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 2b36def..2e93f99 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -834,14 +834,14 @@ static void dump_info(void) die("Unknown type of information\n"); } -static int process_sample_event(event_t *self, struct sample_data *sample, +static int process_sample_event(union perf_event *event, struct perf_sample *sample, struct perf_session *s) { struct thread *thread = perf_session__findnew(s, sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", - self->header.type); + event->header.type); return -1; } @@ -852,7 +852,7 @@ static int process_sample_event(event_t *self, struct sample_data *sample, static struct perf_event_ops eops = { .sample = process_sample_event, - .comm = event__process_comm, + .comm = perf_event__process_comm, .ordered_samples = true, }; @@ -893,7 +893,7 @@ static const char * const report_usage[] = { static const struct option report_options[] = { OPT_STRING('k', "key", &sort_key, "acquired", - "key for sorting"), + "key for sorting (acquired / contended / wait_total / wait_max / wait_min)"), /* TODO: type */ OPT_END() }; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index add163c..2c0e64d 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -36,6 +36,7 @@ #include "builtin.h" #include "util/util.h" #include "util/strlist.h" +#include "util/strfilter.h" #include "util/symbol.h" #include "util/debug.h" #include "util/debugfs.h" @@ -43,6 +44,8 @@ #include "util/probe-finder.h" #include "util/probe-event.h" +#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*" +#define DEFAULT_FUNC_FILTER "!_*" #define MAX_PATH_LEN 256 /* Session management structure */ @@ -52,6 +55,7 @@ static struct { bool show_lines; bool show_vars; bool show_ext_vars; + bool show_funcs; bool mod_events; int nevents; struct perf_probe_event events[MAX_PROBES]; @@ -59,6 +63,7 @@ static struct { struct line_range line_range; const char *target_module; int max_probe_points; + struct strfilter *filter; } params; /* Parse an event definition. Note that any error must die. */ @@ -157,6 +162,27 @@ static int opt_show_vars(const struct option *opt __used, } #endif +static int opt_set_filter(const struct option *opt __used, + const char *str, int unset __used) +{ + const char *err; + + if (str) { + pr_debug2("Set filter: %s\n", str); + if (params.filter) + strfilter__delete(params.filter); + params.filter = strfilter__new(str, &err); + if (!params.filter) { + pr_err("Filter parse error at %td.\n", err - str + 1); + pr_err("Source: \"%s\"\n", str); + pr_err(" %*c\n", (int)(err - str + 1), '^'); + return -EINVAL; + } + } + + return 0; +} + static const char * const probe_usage[] = { "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", "perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]", @@ -221,6 +247,13 @@ static const struct option options[] = { OPT__DRY_RUN(&probe_event_dry_run), OPT_INTEGER('\0', "max-probes", ¶ms.max_probe_points, "Set how many probe points can be found for a probe."), + OPT_BOOLEAN('F', "funcs", ¶ms.show_funcs, + "Show potential probe-able functions."), + OPT_CALLBACK('\0', "filter", NULL, + "[!]FILTER", "Set a filter (with --vars/funcs only)\n" + "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n" + "\t\t\t \"" DEFAULT_FUNC_FILTER "\" for --funcs)", + opt_set_filter), OPT_END() }; @@ -246,7 +279,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) params.max_probe_points = MAX_PROBES; if ((!params.nevents && !params.dellist && !params.list_events && - !params.show_lines)) + !params.show_lines && !params.show_funcs)) usage_with_options(probe_usage, options); /* @@ -267,12 +300,41 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) pr_err(" Error: Don't use --list with --vars.\n"); usage_with_options(probe_usage, options); } + if (params.show_funcs) { + pr_err(" Error: Don't use --list with --funcs.\n"); + usage_with_options(probe_usage, options); + } ret = show_perf_probe_events(); if (ret < 0) pr_err(" Error: Failed to show event list. (%d)\n", ret); return ret; } + if (params.show_funcs) { + if (params.nevents != 0 || params.dellist) { + pr_err(" Error: Don't use --funcs with" + " --add/--del.\n"); + usage_with_options(probe_usage, options); + } + if (params.show_lines) { + pr_err(" Error: Don't use --funcs with --line.\n"); + usage_with_options(probe_usage, options); + } + if (params.show_vars) { + pr_err(" Error: Don't use --funcs with --vars.\n"); + usage_with_options(probe_usage, options); + } + if (!params.filter) + params.filter = strfilter__new(DEFAULT_FUNC_FILTER, + NULL); + ret = show_available_funcs(params.target_module, + params.filter); + strfilter__delete(params.filter); + if (ret < 0) + pr_err(" Error: Failed to show functions." + " (%d)\n", ret); + return ret; + } #ifdef DWARF_SUPPORT if (params.show_lines) { @@ -297,10 +359,16 @@ int cmd_probe(int argc, const char **argv, const char *prefix __used) " --add/--del.\n"); usage_with_options(probe_usage, options); } + if (!params.filter) + params.filter = strfilter__new(DEFAULT_VAR_FILTER, + NULL); + ret = show_available_vars(params.events, params.nevents, params.max_probe_points, params.target_module, + params.filter, params.show_ext_vars); + strfilter__delete(params.filter); if (ret < 0) pr_err(" Error: Failed to show vars. (%d)\n", ret); return ret; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index b2f729f..6febcc1 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -18,11 +18,13 @@ #include "util/header.h" #include "util/event.h" +#include "util/evlist.h" #include "util/evsel.h" #include "util/debug.h" #include "util/session.h" #include "util/symbol.h" #include "util/cpumap.h" +#include "util/thread_map.h" #include <unistd.h> #include <sched.h> @@ -37,16 +39,14 @@ enum write_mode_t { static u64 user_interval = ULLONG_MAX; static u64 default_interval = 0; -static u64 sample_type; -static struct cpu_map *cpus; static unsigned int page_size; static unsigned int mmap_pages = 128; static unsigned int user_freq = UINT_MAX; static int freq = 1000; static int output; static int pipe_output = 0; -static const char *output_name = "perf.data"; +static const char *output_name = NULL; static int group = 0; static int realtime_prio = 0; static bool nodelay = false; @@ -55,7 +55,6 @@ static bool sample_id_all_avail = true; static bool system_wide = false; static pid_t target_pid = -1; static pid_t target_tid = -1; -static struct thread_map *threads; static pid_t child_pid = -1; static bool no_inherit = false; static enum write_mode_t write_mode = WRITE_FORCE; @@ -66,51 +65,17 @@ static bool sample_address = false; static bool sample_time = false; static bool no_buildid = false; static bool no_buildid_cache = false; +static struct perf_evlist *evsel_list; static long samples = 0; static u64 bytes_written = 0; -static struct pollfd *event_array; - -static int nr_poll = 0; -static int nr_cpu = 0; - static int file_new = 1; static off_t post_processing_offset; static struct perf_session *session; static const char *cpu_list; -struct mmap_data { - void *base; - unsigned int mask; - unsigned int prev; -}; - -static struct mmap_data mmap_array[MAX_NR_CPUS]; - -static unsigned long mmap_read_head(struct mmap_data *md) -{ - struct perf_event_mmap_page *pc = md->base; - long head; - - head = pc->data_head; - rmb(); - - return head; -} - -static void mmap_write_tail(struct mmap_data *md, unsigned long tail) -{ - struct perf_event_mmap_page *pc = md->base; - - /* - * ensure all reads are done before we write the tail out. - */ - /* mb(); */ - pc->data_tail = tail; -} - static void advance_output(size_t size) { bytes_written += size; @@ -131,42 +96,26 @@ static void write_output(void *buf, size_t size) } } -static int process_synthesized_event(event_t *event, - struct sample_data *sample __used, +static int process_synthesized_event(union perf_event *event, + struct perf_sample *sample __used, struct perf_session *self __used) { write_output(event, event->header.size); return 0; } -static void mmap_read(struct mmap_data *md) +static void mmap_read(struct perf_mmap *md) { - unsigned int head = mmap_read_head(md); + unsigned int head = perf_mmap__read_head(md); unsigned int old = md->prev; unsigned char *data = md->base + page_size; unsigned long size; void *buf; - int diff; - /* - * If we're further behind than half the buffer, there's a chance - * the writer will bite our tail and mess up the samples under us. - * - * If we somehow ended up ahead of the head, we got messed up. - * - * In either case, truncate and restart at head. - */ - diff = head - old; - if (diff < 0) { - fprintf(stderr, "WARNING: failed to keep up with mmap data\n"); - /* - * head points to a known good entry, start there. - */ - old = head; - } + if (old == head) + return; - if (old != head) - samples++; + samples++; size = head - old; @@ -185,7 +134,7 @@ static void mmap_read(struct mmap_data *md) write_output(buf, size); md->prev = old; - mmap_write_tail(md, old); + perf_mmap__write_tail(md, old); } static volatile int done = 0; @@ -209,53 +158,10 @@ static void sig_atexit(void) kill(getpid(), signr); } -static int group_fd; - -static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int nr) -{ - struct perf_header_attr *h_attr; - - if (nr < session->header.attrs) { - h_attr = session->header.attr[nr]; - } else { - h_attr = perf_header_attr__new(a); - if (h_attr != NULL) - if (perf_header__add_attr(&session->header, h_attr) < 0) { - perf_header_attr__delete(h_attr); - h_attr = NULL; - } - } - - return h_attr; -} - -static void create_counter(struct perf_evsel *evsel, int cpu) +static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist) { - char *filter = evsel->filter; struct perf_event_attr *attr = &evsel->attr; - struct perf_header_attr *h_attr; int track = !evsel->idx; /* only the first counter needs these */ - int thread_index; - int ret; - struct { - u64 count; - u64 time_enabled; - u64 time_running; - u64 id; - } read_data; - /* - * Check if parse_single_tracepoint_event has already asked for - * PERF_SAMPLE_TIME. - * - * XXX this is kludgy but short term fix for problems introduced by - * eac23d1c that broke 'perf script' by having different sample_types - * when using multiple tracepoint events when we use a perf binary - * that tries to use sample_id_all on an older kernel. - * - * We need to move counter creation to perf_session, support - * different sample_types, etc. - */ - bool time_needed = attr->sample_type & PERF_SAMPLE_TIME; attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING | @@ -263,7 +169,7 @@ static void create_counter(struct perf_evsel *evsel, int cpu) attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID; - if (nr_counters > 1) + if (evlist->nr_entries > 1) attr->sample_type |= PERF_SAMPLE_ID; /* @@ -315,19 +221,58 @@ static void create_counter(struct perf_evsel *evsel, int cpu) attr->mmap = track; attr->comm = track; - attr->inherit = !no_inherit; + if (target_pid == -1 && target_tid == -1 && !system_wide) { attr->disabled = 1; attr->enable_on_exec = 1; } -retry_sample_id: - attr->sample_id_all = sample_id_all_avail ? 1 : 0; +} - for (thread_index = 0; thread_index < threads->nr; thread_index++) { -try_again: - FD(evsel, nr_cpu, thread_index) = sys_perf_event_open(attr, threads->map[thread_index], cpu, group_fd, 0); +static bool perf_evlist__equal(struct perf_evlist *evlist, + struct perf_evlist *other) +{ + struct perf_evsel *pos, *pair; + + if (evlist->nr_entries != other->nr_entries) + return false; + + pair = list_entry(other->entries.next, struct perf_evsel, node); - if (FD(evsel, nr_cpu, thread_index) < 0) { + list_for_each_entry(pos, &evlist->entries, node) { + if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0)) + return false; + pair = list_entry(pair->node.next, struct perf_evsel, node); + } + + return true; +} + +static void open_counters(struct perf_evlist *evlist) +{ + struct perf_evsel *pos; + + list_for_each_entry(pos, &evlist->entries, node) { + struct perf_event_attr *attr = &pos->attr; + /* + * Check if parse_single_tracepoint_event has already asked for + * PERF_SAMPLE_TIME. + * + * XXX this is kludgy but short term fix for problems introduced by + * eac23d1c that broke 'perf script' by having different sample_types + * when using multiple tracepoint events when we use a perf binary + * that tries to use sample_id_all on an older kernel. + * + * We need to move counter creation to perf_session, support + * different sample_types, etc. + */ + bool time_needed = attr->sample_type & PERF_SAMPLE_TIME; + + config_attr(pos, evlist); +retry_sample_id: + attr->sample_id_all = sample_id_all_avail ? 1 : 0; +try_again: + if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group, + !no_inherit) < 0) { int err = errno; if (err == EPERM || err == EACCES) @@ -364,7 +309,7 @@ try_again: } printf("\n"); error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n", - FD(evsel, nr_cpu, thread_index), strerror(err)); + err, strerror(err)); #if defined(__i386__) || defined(__x86_64__) if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP) @@ -375,90 +320,28 @@ try_again: #endif die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); - exit(-1); } + } - h_attr = get_header_attr(attr, evsel->idx); - if (h_attr == NULL) - die("nomem\n"); + if (perf_evlist__set_filters(evlist)) { + error("failed to set filter with %d (%s)\n", errno, + strerror(errno)); + exit(-1); + } - if (!file_new) { - if (memcmp(&h_attr->attr, attr, sizeof(*attr))) { - fprintf(stderr, "incompatible append\n"); - exit(-1); - } - } + if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) + die("failed to mmap with %d (%s)\n", errno, strerror(errno)); - if (read(FD(evsel, nr_cpu, thread_index), &read_data, sizeof(read_data)) == -1) { - perror("Unable to read perf file descriptor"); + if (file_new) + session->evlist = evlist; + else { + if (!perf_evlist__equal(session->evlist, evlist)) { + fprintf(stderr, "incompatible append\n"); exit(-1); } + } - if (perf_header_attr__add_id(h_attr, read_data.id) < 0) { - pr_warning("Not enough memory to add id\n"); - exit(-1); - } - - assert(FD(evsel, nr_cpu, thread_index) >= 0); - fcntl(FD(evsel, nr_cpu, thread_index), F_SETFL, O_NONBLOCK); - - /* - * First counter acts as the group leader: - */ - if (group && group_fd == -1) - group_fd = FD(evsel, nr_cpu, thread_index); - - if (evsel->idx || thread_index) { - struct perf_evsel *first; - first = list_entry(evsel_list.next, struct perf_evsel, node); - ret = ioctl(FD(evsel, nr_cpu, thread_index), - PERF_EVENT_IOC_SET_OUTPUT, - FD(first, nr_cpu, 0)); - if (ret) { - error("failed to set output: %d (%s)\n", errno, - strerror(errno)); - exit(-1); - } - } else { - mmap_array[nr_cpu].prev = 0; - mmap_array[nr_cpu].mask = mmap_pages*page_size - 1; - mmap_array[nr_cpu].base = mmap(NULL, (mmap_pages+1)*page_size, - PROT_READ | PROT_WRITE, MAP_SHARED, FD(evsel, nr_cpu, thread_index), 0); - if (mmap_array[nr_cpu].base == MAP_FAILED) { - error("failed to mmap with %d (%s)\n", errno, strerror(errno)); - exit(-1); - } - - event_array[nr_poll].fd = FD(evsel, nr_cpu, thread_index); - event_array[nr_poll].events = POLLIN; - nr_poll++; - } - - if (filter != NULL) { - ret = ioctl(FD(evsel, nr_cpu, thread_index), - PERF_EVENT_IOC_SET_FILTER, filter); - if (ret) { - error("failed to set filter with %d (%s)\n", errno, - strerror(errno)); - exit(-1); - } - } - } - - if (!sample_type) - sample_type = attr->sample_type; -} - -static void open_counters(int cpu) -{ - struct perf_evsel *pos; - - group_fd = -1; - - list_for_each_entry(pos, &evsel_list, node) - create_counter(pos, cpu); - - nr_cpu++; + perf_session__update_sample_type(session); } static int process_buildids(void) @@ -481,14 +364,14 @@ static void atexit_header(void) if (!no_buildid) process_buildids(); - perf_header__write(&session->header, output, true); + perf_session__write_header(session, evsel_list, output, true); perf_session__delete(session); - perf_evsel_list__delete(); + perf_evlist__delete(evsel_list); symbol__exit(); } } -static void event__synthesize_guest_os(struct machine *machine, void *data) +static void perf_event__synthesize_guest_os(struct machine *machine, void *data) { int err; struct perf_session *psession = data; @@ -504,8 +387,8 @@ static void event__synthesize_guest_os(struct machine *machine, void *data) *method is used to avoid symbol missing when the first addr is *in module instead of in guest kernel. */ - err = event__synthesize_modules(process_synthesized_event, - psession, machine); + err = perf_event__synthesize_modules(process_synthesized_event, + psession, machine); if (err < 0) pr_err("Couldn't record guest kernel [%d]'s reference" " relocation symbol.\n", machine->pid); @@ -514,11 +397,12 @@ static void event__synthesize_guest_os(struct machine *machine, void *data) * We use _stext for guest kernel because guest kernel's /proc/kallsyms * have no _text sometimes. */ - err = event__synthesize_kernel_mmap(process_synthesized_event, - psession, machine, "_text"); + err = perf_event__synthesize_kernel_mmap(process_synthesized_event, + psession, machine, "_text"); if (err < 0) - err = event__synthesize_kernel_mmap(process_synthesized_event, - psession, machine, "_stext"); + err = perf_event__synthesize_kernel_mmap(process_synthesized_event, + psession, machine, + "_stext"); if (err < 0) pr_err("Couldn't record guest kernel [%d]'s reference" " relocation symbol.\n", machine->pid); @@ -533,9 +417,9 @@ static void mmap_read_all(void) { int i; - for (i = 0; i < nr_cpu; i++) { - if (mmap_array[i].base) - mmap_read(&mmap_array[i]); + for (i = 0; i < evsel_list->cpus->nr; i++) { + if (evsel_list->mmap[i].base) + mmap_read(&evsel_list->mmap[i]); } if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO)) @@ -566,18 +450,26 @@ static int __cmd_record(int argc, const char **argv) exit(-1); } - if (!strcmp(output_name, "-")) - pipe_output = 1; - else if (!stat(output_name, &st) && st.st_size) { - if (write_mode == WRITE_FORCE) { - char oldname[PATH_MAX]; - snprintf(oldname, sizeof(oldname), "%s.old", - output_name); - unlink(oldname); - rename(output_name, oldname); + if (!output_name) { + if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode)) + pipe_output = 1; + else + output_name = "perf.data"; + } + if (output_name) { + if (!strcmp(output_name, "-")) + pipe_output = 1; + else if (!stat(output_name, &st) && st.st_size) { + if (write_mode == WRITE_FORCE) { + char oldname[PATH_MAX]; + snprintf(oldname, sizeof(oldname), "%s.old", + output_name); + unlink(oldname); + rename(output_name, oldname); + } + } else if (write_mode == WRITE_APPEND) { + write_mode = WRITE_FORCE; } - } else if (write_mode == WRITE_APPEND) { - write_mode = WRITE_FORCE; } flags = O_CREAT|O_RDWR; @@ -606,19 +498,14 @@ static int __cmd_record(int argc, const char **argv) perf_header__set_feat(&session->header, HEADER_BUILD_ID); if (!file_new) { - err = perf_header__read(session, output); + err = perf_session__read_header(session, output); if (err < 0) goto out_delete_session; } - if (have_tracepoints(&evsel_list)) + if (have_tracepoints(&evsel_list->entries)) perf_header__set_feat(&session->header, HEADER_TRACE_INFO); - /* - * perf_session__delete(session) will be called at atexit_header() - */ - atexit(atexit_header); - if (forks) { child_pid = fork(); if (child_pid < 0) { @@ -659,7 +546,7 @@ static int __cmd_record(int argc, const char **argv) } if (!system_wide && target_tid == -1 && target_pid == -1) - threads->map[0] = child_pid; + evsel_list->threads->map[0] = child_pid; close(child_ready_pipe[1]); close(go_pipe[0]); @@ -673,46 +560,42 @@ static int __cmd_record(int argc, const char **argv) close(child_ready_pipe[0]); } - if (!system_wide && no_inherit && !cpu_list) { - open_counters(-1); - } else { - for (i = 0; i < cpus->nr; i++) - open_counters(cpus->map[i]); - } + open_counters(evsel_list); - perf_session__set_sample_type(session, sample_type); + /* + * perf_session__delete(session) will be called at atexit_header() + */ + atexit(atexit_header); if (pipe_output) { err = perf_header__write_pipe(output); if (err < 0) return err; } else if (file_new) { - err = perf_header__write(&session->header, output, false); + err = perf_session__write_header(session, evsel_list, + output, false); if (err < 0) return err; } post_processing_offset = lseek(output, 0, SEEK_CUR); - perf_session__set_sample_id_all(session, sample_id_all_avail); - if (pipe_output) { - err = event__synthesize_attrs(&session->header, - process_synthesized_event, - session); + err = perf_session__synthesize_attrs(session, + process_synthesized_event); if (err < 0) { pr_err("Couldn't synthesize attrs.\n"); return err; } - err = event__synthesize_event_types(process_synthesized_event, - session); + err = perf_event__synthesize_event_types(process_synthesized_event, + session); if (err < 0) { pr_err("Couldn't synthesize event_types.\n"); return err; } - if (have_tracepoints(&evsel_list)) { + if (have_tracepoints(&evsel_list->entries)) { /* * FIXME err <= 0 here actually means that * there were no tracepoints so its not really @@ -721,9 +604,9 @@ static int __cmd_record(int argc, const char **argv) * return this more properly and also * propagate errors that now are calling die() */ - err = event__synthesize_tracing_data(output, &evsel_list, - process_synthesized_event, - session); + err = perf_event__synthesize_tracing_data(output, evsel_list, + process_synthesized_event, + session); if (err <= 0) { pr_err("Couldn't record tracing data.\n"); return err; @@ -738,31 +621,34 @@ static int __cmd_record(int argc, const char **argv) return -1; } - err = event__synthesize_kernel_mmap(process_synthesized_event, - session, machine, "_text"); + err = perf_event__synthesize_kernel_mmap(process_synthesized_event, + session, machine, "_text"); if (err < 0) - err = event__synthesize_kernel_mmap(process_synthesized_event, - session, machine, "_stext"); + err = perf_event__synthesize_kernel_mmap(process_synthesized_event, + session, machine, "_stext"); if (err < 0) pr_err("Couldn't record kernel reference relocation symbol\n" "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" "Check /proc/kallsyms permission or run as root.\n"); - err = event__synthesize_modules(process_synthesized_event, - session, machine); + err = perf_event__synthesize_modules(process_synthesized_event, + session, machine); if (err < 0) pr_err("Couldn't record kernel module information.\n" "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n" "Check /proc/modules permission or run as root.\n"); if (perf_guest) - perf_session__process_machines(session, event__synthesize_guest_os); + perf_session__process_machines(session, + perf_event__synthesize_guest_os); if (!system_wide) - event__synthesize_thread(target_tid, process_synthesized_event, - session); + perf_event__synthesize_thread_map(evsel_list->threads, + process_synthesized_event, + session); else - event__synthesize_threads(process_synthesized_event, session); + perf_event__synthesize_threads(process_synthesized_event, + session); if (realtime_prio) { struct sched_param param; @@ -789,17 +675,17 @@ static int __cmd_record(int argc, const char **argv) if (hits == samples) { if (done) break; - err = poll(event_array, nr_poll, -1); + err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1); waking++; } if (done) { - for (i = 0; i < nr_cpu; i++) { + for (i = 0; i < evsel_list->cpus->nr; i++) { struct perf_evsel *pos; - list_for_each_entry(pos, &evsel_list, node) { + list_for_each_entry(pos, &evsel_list->entries, node) { for (thread = 0; - thread < threads->nr; + thread < evsel_list->threads->nr; thread++) ioctl(FD(pos, i, thread), PERF_EVENT_IOC_DISABLE); @@ -838,10 +724,10 @@ static const char * const record_usage[] = { static bool force, append_file; const struct option record_options[] = { - OPT_CALLBACK('e', "event", NULL, "event", + OPT_CALLBACK('e', "event", &evsel_list, "event", "event selector. use 'perf list' to list available events", parse_events), - OPT_CALLBACK(0, "filter", NULL, "filter", + OPT_CALLBACK(0, "filter", &evsel_list, "filter", "event filter", parse_filter), OPT_INTEGER('p', "pid", &target_pid, "record events on existing process id"), @@ -884,6 +770,9 @@ const struct option record_options[] = { "do not update the buildid cache"), OPT_BOOLEAN('B', "no-buildid", &no_buildid, "do not collect buildids in perf.data"), + OPT_CALLBACK('G', "cgroup", &evsel_list, "name", + "monitor event in cgroup name only", + parse_cgroups), OPT_END() }; @@ -892,6 +781,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) int err = -ENOMEM; struct perf_evsel *pos; + evsel_list = perf_evlist__new(NULL, NULL); + if (evsel_list == NULL) + return -ENOMEM; + argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); if (!argc && target_pid == -1 && target_tid == -1 && @@ -908,12 +801,19 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) write_mode = WRITE_FORCE; } + if (nr_cgroups && !system_wide) { + fprintf(stderr, "cgroup monitoring only available in" + " system-wide mode\n"); + usage_with_options(record_usage, record_options); + } + symbol__init(); if (no_buildid_cache || no_buildid) disable_buildid_cache(); - if (list_empty(&evsel_list) && perf_evsel_list__create_default() < 0) { + if (evsel_list->nr_entries == 0 && + perf_evlist__add_default(evsel_list) < 0) { pr_err("Not enough memory for event selector list\n"); goto out_symbol_exit; } @@ -921,27 +821,19 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) if (target_pid != -1) target_tid = target_pid; - threads = thread_map__new(target_pid, target_tid); - if (threads == NULL) { - pr_err("Problems finding threads of monitor\n"); + if (perf_evlist__create_maps(evsel_list, target_pid, + target_tid, cpu_list) < 0) usage_with_options(record_usage, record_options); - } - cpus = cpu_map__new(cpu_list); - if (cpus == NULL) { - perror("failed to parse CPUs map"); - return -1; - } - - list_for_each_entry(pos, &evsel_list, node) { - if (perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0) + list_for_each_entry(pos, &evsel_list->entries, node) { + if (perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, + evsel_list->threads->nr) < 0) goto out_free_fd; if (perf_header__push_event(pos->attr.config, event_name(pos))) goto out_free_fd; } - event_array = malloc((sizeof(struct pollfd) * MAX_NR_CPUS * - MAX_COUNTERS * threads->nr)); - if (!event_array) + + if (perf_evlist__alloc_pollfd(evsel_list) < 0) goto out_free_fd; if (user_interval != ULLONG_MAX) @@ -959,16 +851,12 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) } else { fprintf(stderr, "frequency and count are zero, aborting\n"); err = -EINVAL; - goto out_free_event_array; + goto out_free_fd; } err = __cmd_record(argc, argv); - -out_free_event_array: - free(event_array); out_free_fd: - thread_map__delete(threads); - threads = NULL; + perf_evlist__delete_maps(evsel_list); out_symbol_exit: symbol__exit(); return err; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c27e31f..b1b8200 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -9,6 +9,7 @@ #include "util/util.h" +#include "util/annotate.h" #include "util/color.h" #include <linux/list.h> #include "util/cache.h" @@ -20,6 +21,8 @@ #include "perf.h" #include "util/debug.h" +#include "util/evlist.h" +#include "util/evsel.h" #include "util/header.h" #include "util/session.h" @@ -43,120 +46,79 @@ static const char default_pretty_printing_style[] = "normal"; static const char *pretty_printing_style = default_pretty_printing_style; static char callchain_default_opt[] = "fractal,0.5"; +static symbol_filter_t annotate_init; -static struct hists *perf_session__hists_findnew(struct perf_session *self, - u64 event_stream, u32 type, - u64 config) -{ - struct rb_node **p = &self->hists_tree.rb_node; - struct rb_node *parent = NULL; - struct hists *iter, *new; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct hists, rb_node); - if (iter->config == config) - return iter; - - - if (config > iter->config) - p = &(*p)->rb_right; - else - p = &(*p)->rb_left; - } - - new = malloc(sizeof(struct hists)); - if (new == NULL) - return NULL; - memset(new, 0, sizeof(struct hists)); - new->event_stream = event_stream; - new->config = config; - new->type = type; - rb_link_node(&new->rb_node, parent, p); - rb_insert_color(&new->rb_node, &self->hists_tree); - return new; -} - -static int perf_session__add_hist_entry(struct perf_session *self, +static int perf_session__add_hist_entry(struct perf_session *session, struct addr_location *al, - struct sample_data *data) + struct perf_sample *sample) { - struct map_symbol *syms = NULL; struct symbol *parent = NULL; - int err = -ENOMEM; + int err = 0; struct hist_entry *he; - struct hists *hists; - struct perf_event_attr *attr; - - if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) { - syms = perf_session__resolve_callchain(self, al->thread, - data->callchain, &parent); - if (syms == NULL) - return -ENOMEM; + struct perf_evsel *evsel; + + if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) { + err = perf_session__resolve_callchain(session, al->thread, + sample->callchain, &parent); + if (err) + return err; } - attr = perf_header__find_attr(data->id, &self->header); - if (attr) - hists = perf_session__hists_findnew(self, data->id, attr->type, attr->config); - else - hists = perf_session__hists_findnew(self, data->id, 0, 0); - if (hists == NULL) - goto out_free_syms; - he = __hists__add_entry(hists, al, parent, data->period); + evsel = perf_evlist__id2evsel(session->evlist, sample->id); + if (evsel == NULL) { + /* + * FIXME: Propagate this back, but at least we're in a builtin, + * where exit() is allowed. ;-) + */ + ui__warning("Invalid %s file, contains samples with id %" PRIu64 " not in " + "its header!\n", input_name, sample->id); + exit_browser(0); + exit(1); + } + + he = __hists__add_entry(&evsel->hists, al, parent, sample->period); if (he == NULL) - goto out_free_syms; - err = 0; + return -ENOMEM; + if (symbol_conf.use_callchain) { - err = callchain_append(he->callchain, data->callchain, syms, - data->period); + err = callchain_append(he->callchain, &session->callchain_cursor, + sample->period); if (err) - goto out_free_syms; + return err; } /* * Only in the newt browser we are doing integrated annotation, * so we don't allocated the extra space needed because the stdio * code will not use it. */ - if (use_browser > 0) - err = hist_entry__inc_addr_samples(he, al->addr); -out_free_syms: - free(syms); - return err; -} + if (al->sym != NULL && use_browser > 0) { + struct annotation *notes = symbol__annotation(he->ms.sym); -static int add_event_total(struct perf_session *session, - struct sample_data *data, - struct perf_event_attr *attr) -{ - struct hists *hists; + assert(evsel != NULL); - if (attr) - hists = perf_session__hists_findnew(session, data->id, - attr->type, attr->config); - else - hists = perf_session__hists_findnew(session, data->id, 0, 0); + err = -ENOMEM; + if (notes->src == NULL && + symbol__alloc_hist(he->ms.sym, session->evlist->nr_entries) < 0) + goto out; - if (!hists) - return -ENOMEM; + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + } - hists->stats.total_period += data->period; - /* - * FIXME: add_event_total should be moved from here to - * perf_session__process_event so that the proper hist is passed to - * the event_op methods. - */ - hists__inc_nr_events(hists, PERF_RECORD_SAMPLE); - session->hists.stats.total_period += data->period; - return 0; + evsel->hists.stats.total_period += sample->period; + hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); +out: + return err; } -static int process_sample_event(event_t *event, struct sample_data *sample, + +static int process_sample_event(union perf_event *event, + struct perf_sample *sample, struct perf_session *session) { struct addr_location al; - struct perf_event_attr *attr; - if (event__preprocess_sample(event, session, &al, sample, NULL) < 0) { + if (perf_event__preprocess_sample(event, session, &al, sample, + annotate_init) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", event->header.type); return -1; @@ -170,26 +132,17 @@ static int process_sample_event(event_t *event, struct sample_data *sample, return -1; } - attr = perf_header__find_attr(sample->id, &session->header); - - if (add_event_total(session, sample, attr)) { - pr_debug("problem adding event period\n"); - return -1; - } - return 0; } -static int process_read_event(event_t *event, struct sample_data *sample __used, - struct perf_session *session __used) +static int process_read_event(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { - struct perf_event_attr *attr; - - attr = perf_header__find_attr(event->read.id, &session->header); - + struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, + event->read.id); if (show_threads) { - const char *name = attr ? __event_name(attr->type, attr->config) - : "unknown"; + const char *name = evsel ? event_name(evsel) : "unknown"; perf_read_values_add_value(&show_threads_values, event->read.pid, event->read.tid, event->read.id, @@ -198,7 +151,7 @@ static int process_read_event(event_t *event, struct sample_data *sample __used, } dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid, - attr ? __event_name(attr->type, attr->config) : "FAIL", + evsel ? event_name(evsel) : "FAIL", event->read.value); return 0; @@ -222,7 +175,7 @@ static int perf_session__setup_sample_type(struct perf_session *self) } else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE && !symbol_conf.use_callchain) { symbol_conf.use_callchain = true; - if (register_callchain_param(&callchain_param) < 0) { + if (callchain_register_param(&callchain_param) < 0) { fprintf(stderr, "Can't register callchain" " params\n"); return -EINVAL; @@ -233,17 +186,17 @@ static int perf_session__setup_sample_type(struct perf_session *self) } static struct perf_event_ops event_ops = { - .sample = process_sample_event, - .mmap = event__process_mmap, - .comm = event__process_comm, - .exit = event__process_task, - .fork = event__process_task, - .lost = event__process_lost, - .read = process_read_event, - .attr = event__process_attr, - .event_type = event__process_event_type, - .tracing_data = event__process_tracing_data, - .build_id = event__process_build_id, + .sample = process_sample_event, + .mmap = perf_event__process_mmap, + .comm = perf_event__process_comm, + .exit = perf_event__process_task, + .fork = perf_event__process_task, + .lost = perf_event__process_lost, + .read = process_read_event, + .attr = perf_event__process_attr, + .event_type = perf_event__process_event_type, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, .ordered_samples = true, .ordering_requires_timestamps = true, }; @@ -269,21 +222,21 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, return ret + fprintf(fp, "\n#\n"); } -static int hists__tty_browse_tree(struct rb_root *tree, const char *help) +static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, + const char *help) { - struct rb_node *next = rb_first(tree); + struct perf_evsel *pos; - while (next) { - struct hists *hists = rb_entry(next, struct hists, rb_node); + list_for_each_entry(pos, &evlist->entries, node) { + struct hists *hists = &pos->hists; const char *evname = NULL; if (rb_first(&hists->entries) != rb_last(&hists->entries)) - evname = __event_name(hists->type, hists->config); + evname = event_name(pos); hists__fprintf_nr_sample_events(hists, evname, stdout); hists__fprintf(hists, NULL, false, stdout); fprintf(stdout, "\n\n"); - next = rb_next(&hists->rb_node); } if (sort_order == default_sort_order && @@ -304,8 +257,9 @@ static int hists__tty_browse_tree(struct rb_root *tree, const char *help) static int __cmd_report(void) { int ret = -EINVAL; + u64 nr_samples; struct perf_session *session; - struct rb_node *next; + struct perf_evsel *pos; const char *help = "For a higher level overview, try: perf report --sort comm,dso"; signal(SIGINT, sig_handler); @@ -336,20 +290,24 @@ static int __cmd_report(void) if (verbose > 2) perf_session__fprintf_dsos(session, stdout); - next = rb_first(&session->hists_tree); - while (next) { - struct hists *hists; + nr_samples = 0; + list_for_each_entry(pos, &session->evlist->entries, node) { + struct hists *hists = &pos->hists; - hists = rb_entry(next, struct hists, rb_node); hists__collapse_resort(hists); hists__output_resort(hists); - next = rb_next(&hists->rb_node); + nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE]; + } + + if (nr_samples == 0) { + ui__warning("The %s file has no samples!\n", input_name); + goto out_delete; } if (use_browser > 0) - hists__tui_browse_tree(&session->hists_tree, help); + perf_evlist__tui_browse_hists(session->evlist, help); else - hists__tty_browse_tree(&session->hists_tree, help); + perf_evlist__tty_browse_hists(session->evlist, help); out_delete: /* @@ -424,7 +382,7 @@ parse_callchain_opt(const struct option *opt __used, const char *arg, if (tok2) callchain_param.print_limit = strtod(tok2, &endptr); setup: - if (register_callchain_param(&callchain_param) < 0) { + if (callchain_register_param(&callchain_param) < 0) { fprintf(stderr, "Can't register callchain params\n"); return -1; } @@ -498,7 +456,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) use_browser = 1; if (strcmp(input_name, "-") != 0) - setup_browser(); + setup_browser(true); else use_browser = 0; /* @@ -507,7 +465,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) * implementation. */ if (use_browser > 0) { - symbol_conf.priv_size = sizeof(struct sym_priv); + symbol_conf.priv_size = sizeof(struct annotation); + annotate_init = symbol__annotate_init; /* * For searching by name on the "Browse map details". * providing it only in verbose mode not to bloat too diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 29acb894..a32f411 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -369,11 +369,6 @@ static void process_sched_event(struct task_desc *this_task __used, struct sched_atom *atom) { int ret = 0; - u64 now; - long long delta; - - now = get_nsecs(); - delta = start_time + atom->timestamp - now; switch (atom->type) { case SCHED_EVENT_RUN: @@ -562,7 +557,7 @@ static void wait_for_tasks(void) static void run_one_test(void) { - u64 T0, T1, delta, avg_delta, fluct, std_dev; + u64 T0, T1, delta, avg_delta, fluct; T0 = get_nsecs(); wait_for_tasks(); @@ -578,7 +573,6 @@ static void run_one_test(void) else fluct = delta - avg_delta; sum_fluct += fluct; - std_dev = sum_fluct / nr_runs / sqrt(nr_runs); if (!run_avg) run_avg = delta; run_avg = (run_avg*9 + delta)/10; @@ -799,7 +793,7 @@ replay_switch_event(struct trace_switch_event *switch_event, u64 timestamp, struct thread *thread __used) { - struct task_desc *prev, *next; + struct task_desc *prev, __used *next; u64 timestamp0; s64 delta; @@ -1404,7 +1398,7 @@ map_switch_event(struct trace_switch_event *switch_event, u64 timestamp, struct thread *thread __used) { - struct thread *sched_out, *sched_in; + struct thread *sched_out __used, *sched_in; int new_shortname; u64 timestamp0; s64 delta; @@ -1580,9 +1574,9 @@ process_sched_migrate_task_event(void *data, struct perf_session *session, event, cpu, timestamp, thread); } -static void -process_raw_event(event_t *raw_event __used, struct perf_session *session, - void *data, int cpu, u64 timestamp, struct thread *thread) +static void process_raw_event(union perf_event *raw_event __used, + struct perf_session *session, void *data, int cpu, + u64 timestamp, struct thread *thread) { struct event *event; int type; @@ -1607,7 +1601,8 @@ process_raw_event(event_t *raw_event __used, struct perf_session *session, process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread); } -static int process_sample_event(event_t *event, struct sample_data *sample, +static int process_sample_event(union perf_event *event, + struct perf_sample *sample, struct perf_session *session) { struct thread *thread; @@ -1635,9 +1630,9 @@ static int process_sample_event(event_t *event, struct sample_data *sample, static struct perf_event_ops event_ops = { .sample = process_sample_event, - .comm = event__process_comm, - .lost = event__process_lost, - .fork = event__process_task, + .comm = perf_event__process_comm, + .lost = perf_event__process_lost, + .fork = perf_event__process_task, .ordered_samples = true, }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index b766c2a..5f40df6 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -63,7 +63,8 @@ static int cleanup_scripting(void) static char const *input_name = "perf.data"; -static int process_sample_event(event_t *event, struct sample_data *sample, +static int process_sample_event(union perf_event *event, + struct perf_sample *sample, struct perf_session *session) { struct thread *thread = perf_session__findnew(session, event->ip.pid); @@ -100,14 +101,14 @@ static int process_sample_event(event_t *event, struct sample_data *sample, } static struct perf_event_ops event_ops = { - .sample = process_sample_event, - .comm = event__process_comm, - .attr = event__process_attr, - .event_type = event__process_event_type, - .tracing_data = event__process_tracing_data, - .build_id = event__process_build_id, - .ordering_requires_timestamps = true, + .sample = process_sample_event, + .comm = perf_event__process_comm, + .attr = perf_event__process_attr, + .event_type = perf_event__process_event_type, + .tracing_data = perf_event__process_tracing_data, + .build_id = perf_event__process_build_id, .ordered_samples = true, + .ordering_requires_timestamps = true, }; extern volatile int session_done; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a482a19..21c0252 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -43,11 +43,13 @@ #include "util/parse-options.h" #include "util/parse-events.h" #include "util/event.h" +#include "util/evlist.h" #include "util/evsel.h" #include "util/debug.h" #include "util/header.h" #include "util/cpumap.h" #include "util/thread.h" +#include "util/thread_map.h" #include <sys/prctl.h> #include <math.h> @@ -71,8 +73,9 @@ static struct perf_event_attr default_attrs[] = { }; +struct perf_evlist *evsel_list; + static bool system_wide = false; -static struct cpu_map *cpus; static int run_idx = 0; static int run_count = 1; @@ -81,7 +84,6 @@ static bool scale = true; static bool no_aggr = false; static pid_t target_pid = -1; static pid_t target_tid = -1; -static struct thread_map *threads; static pid_t child_pid = -1; static bool null_run = false; static bool big_num = true; @@ -166,7 +168,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) PERF_FORMAT_TOTAL_TIME_RUNNING; if (system_wide) - return perf_evsel__open_per_cpu(evsel, cpus); + return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false); attr->inherit = !no_inherit; if (target_pid == -1 && target_tid == -1) { @@ -174,7 +176,7 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) attr->enable_on_exec = 1; } - return perf_evsel__open_per_thread(evsel, threads); + return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false); } /* @@ -199,7 +201,8 @@ static int read_counter_aggr(struct perf_evsel *counter) u64 *count = counter->counts->aggr.values; int i; - if (__perf_evsel__read(counter, cpus->nr, threads->nr, scale) < 0) + if (__perf_evsel__read(counter, evsel_list->cpus->nr, + evsel_list->threads->nr, scale) < 0) return -1; for (i = 0; i < 3; i++) @@ -232,7 +235,7 @@ static int read_counter(struct perf_evsel *counter) u64 *count; int cpu; - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) { if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0) return -1; @@ -297,7 +300,7 @@ static int run_perf_stat(int argc __used, const char **argv) } if (target_tid == -1 && target_pid == -1 && !system_wide) - threads->map[0] = child_pid; + evsel_list->threads->map[0] = child_pid; /* * Wait for the child to be ready to exec. @@ -309,7 +312,7 @@ static int run_perf_stat(int argc __used, const char **argv) close(child_ready_pipe[0]); } - list_for_each_entry(counter, &evsel_list, node) { + list_for_each_entry(counter, &evsel_list->entries, node) { if (create_perf_stat_counter(counter) < 0) { if (errno == -EPERM || errno == -EACCES) { error("You may not have permission to collect %sstats.\n" @@ -347,14 +350,15 @@ static int run_perf_stat(int argc __used, const char **argv) update_stats(&walltime_nsecs_stats, t1 - t0); if (no_aggr) { - list_for_each_entry(counter, &evsel_list, node) { + list_for_each_entry(counter, &evsel_list->entries, node) { read_counter(counter); - perf_evsel__close_fd(counter, cpus->nr, 1); + perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1); } } else { - list_for_each_entry(counter, &evsel_list, node) { + list_for_each_entry(counter, &evsel_list->entries, node) { read_counter_aggr(counter); - perf_evsel__close_fd(counter, cpus->nr, threads->nr); + perf_evsel__close_fd(counter, evsel_list->cpus->nr, + evsel_list->threads->nr); } } @@ -382,10 +386,13 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg) if (no_aggr) sprintf(cpustr, "CPU%*d%s", csv_output ? 0 : -4, - cpus->map[cpu], csv_sep); + evsel_list->cpus->map[cpu], csv_sep); fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel)); + if (evsel->cgrp) + fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name); + if (csv_output) return; @@ -410,12 +417,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg) if (no_aggr) sprintf(cpustr, "CPU%*d%s", csv_output ? 0 : -4, - cpus->map[cpu], csv_sep); + evsel_list->cpus->map[cpu], csv_sep); else cpu = 0; fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel)); + if (evsel->cgrp) + fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name); + if (csv_output) return; @@ -456,9 +466,17 @@ static void print_counter_aggr(struct perf_evsel *counter) int scaled = counter->counts->scaled; if (scaled == -1) { - fprintf(stderr, "%*s%s%-24s\n", + fprintf(stderr, "%*s%s%*s", csv_output ? 0 : 18, - "<not counted>", csv_sep, event_name(counter)); + "<not counted>", + csv_sep, + csv_output ? 0 : -24, + event_name(counter)); + + if (counter->cgrp) + fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name); + + fputc('\n', stderr); return; } @@ -483,7 +501,6 @@ static void print_counter_aggr(struct perf_evsel *counter) fprintf(stderr, " (scaled from %.2f%%)", 100 * avg_running / avg_enabled); } - fprintf(stderr, "\n"); } @@ -496,19 +513,23 @@ static void print_counter(struct perf_evsel *counter) u64 ena, run, val; int cpu; - for (cpu = 0; cpu < cpus->nr; cpu++) { + for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) { val = counter->counts->cpu[cpu].val; ena = counter->counts->cpu[cpu].ena; run = counter->counts->cpu[cpu].run; if (run == 0 || ena == 0) { - fprintf(stderr, "CPU%*d%s%*s%s%-24s", + fprintf(stderr, "CPU%*d%s%*s%s%*s", csv_output ? 0 : -4, - cpus->map[cpu], csv_sep, + evsel_list->cpus->map[cpu], csv_sep, csv_output ? 0 : 18, "<not counted>", csv_sep, + csv_output ? 0 : -24, event_name(counter)); - fprintf(stderr, "\n"); + if (counter->cgrp) + fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name); + + fputc('\n', stderr); continue; } @@ -525,7 +546,7 @@ static void print_counter(struct perf_evsel *counter) 100.0 * run / ena); } } - fprintf(stderr, "\n"); + fputc('\n', stderr); } } @@ -555,10 +576,10 @@ static void print_stat(int argc, const char **argv) } if (no_aggr) { - list_for_each_entry(counter, &evsel_list, node) + list_for_each_entry(counter, &evsel_list->entries, node) print_counter(counter); } else { - list_for_each_entry(counter, &evsel_list, node) + list_for_each_entry(counter, &evsel_list->entries, node) print_counter_aggr(counter); } @@ -610,7 +631,7 @@ static int stat__set_big_num(const struct option *opt __used, } static const struct option options[] = { - OPT_CALLBACK('e', "event", NULL, "event", + OPT_CALLBACK('e', "event", &evsel_list, "event", "event selector. use 'perf list' to list available events", parse_events), OPT_BOOLEAN('i', "no-inherit", &no_inherit, @@ -638,6 +659,9 @@ static const struct option options[] = { "disable CPU count aggregation"), OPT_STRING('x', "field-separator", &csv_sep, "separator", "print counts with custom separator"), + OPT_CALLBACK('G', "cgroup", &evsel_list, "name", + "monitor event in cgroup name only", + parse_cgroups), OPT_END() }; @@ -648,6 +672,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) setlocale(LC_ALL, ""); + evsel_list = perf_evlist__new(NULL, NULL); + if (evsel_list == NULL) + return -ENOMEM; + argc = parse_options(argc, argv, options, stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -674,49 +702,50 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) if (run_count <= 0) usage_with_options(stat_usage, options); - /* no_aggr is for system-wide only */ - if (no_aggr && !system_wide) + /* no_aggr, cgroup are for system-wide only */ + if ((no_aggr || nr_cgroups) && !system_wide) { + fprintf(stderr, "both cgroup and no-aggregation " + "modes only available in system-wide mode\n"); + usage_with_options(stat_usage, options); + } /* Set attrs and nr_counters if no event is selected and !null_run */ - if (!null_run && !nr_counters) { + if (!null_run && !evsel_list->nr_entries) { size_t c; - nr_counters = ARRAY_SIZE(default_attrs); - for (c = 0; c < ARRAY_SIZE(default_attrs); ++c) { - pos = perf_evsel__new(&default_attrs[c], - nr_counters); + pos = perf_evsel__new(&default_attrs[c], c); if (pos == NULL) goto out; - list_add(&pos->node, &evsel_list); + perf_evlist__add(evsel_list, pos); } } if (target_pid != -1) target_tid = target_pid; - threads = thread_map__new(target_pid, target_tid); - if (threads == NULL) { + evsel_list->threads = thread_map__new(target_pid, target_tid); + if (evsel_list->threads == NULL) { pr_err("Problems finding threads of monitor\n"); usage_with_options(stat_usage, options); } if (system_wide) - cpus = cpu_map__new(cpu_list); + evsel_list->cpus = cpu_map__new(cpu_list); else - cpus = cpu_map__dummy_new(); + evsel_list->cpus = cpu_map__dummy_new(); - if (cpus == NULL) { + if (evsel_list->cpus == NULL) { perror("failed to parse CPUs map"); usage_with_options(stat_usage, options); return -1; } - list_for_each_entry(pos, &evsel_list, node) { + list_for_each_entry(pos, &evsel_list->entries, node) { if (perf_evsel__alloc_stat_priv(pos) < 0 || - perf_evsel__alloc_counts(pos, cpus->nr) < 0 || - perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0) + perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0 || + perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, evsel_list->threads->nr) < 0) goto out_free_fd; } @@ -741,11 +770,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) if (status != -1) print_stat(argc, argv); out_free_fd: - list_for_each_entry(pos, &evsel_list, node) + list_for_each_entry(pos, &evsel_list->entries, node) perf_evsel__free_stat_priv(pos); - perf_evsel_list__delete(); + perf_evlist__delete_maps(evsel_list); out: - thread_map__delete(threads); - threads = NULL; + perf_evlist__delete(evsel_list); return status; } diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 5dcdba6..1b2106c 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -7,10 +7,11 @@ #include "util/cache.h" #include "util/debug.h" +#include "util/evlist.h" #include "util/parse-options.h" -#include "util/session.h" +#include "util/parse-events.h" #include "util/symbol.h" -#include "util/thread.h" +#include "util/thread_map.h" static long page_size; @@ -238,14 +239,14 @@ out: #include "util/evsel.h" #include <sys/types.h> -static int trace_event__id(const char *event_name) +static int trace_event__id(const char *evname) { char *filename; int err = -1, fd; if (asprintf(&filename, "/sys/kernel/debug/tracing/events/syscalls/%s/id", - event_name) < 0) + evname) < 0) return -1; fd = open(filename, O_RDONLY); @@ -289,7 +290,7 @@ static int test__open_syscall_event(void) goto out_thread_map_delete; } - if (perf_evsel__open_per_thread(evsel, threads) < 0) { + if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", strerror(errno)); @@ -347,9 +348,9 @@ static int test__open_syscall_event_on_all_cpus(void) } cpus = cpu_map__new(NULL); - if (threads == NULL) { - pr_debug("thread_map__new\n"); - return -1; + if (cpus == NULL) { + pr_debug("cpu_map__new\n"); + goto out_thread_map_delete; } @@ -364,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void) goto out_thread_map_delete; } - if (perf_evsel__open(evsel, cpus, threads) < 0) { + if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) { pr_debug("failed to open counter: %s, " "tweak /proc/sys/kernel/perf_event_paranoid?\n", strerror(errno)); @@ -408,6 +409,8 @@ static int test__open_syscall_event_on_all_cpus(void) goto out_close_fd; } + err = 0; + for (cpu = 0; cpu < cpus->nr; ++cpu) { unsigned int expected; @@ -416,18 +419,18 @@ static int test__open_syscall_event_on_all_cpus(void) if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) { pr_debug("perf_evsel__open_read_on_cpu\n"); - goto out_close_fd; + err = -1; + break; } expected = nr_open_calls + cpu; if (evsel->counts->cpu[cpu].val != expected) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); - goto out_close_fd; + err = -1; } } - err = 0; out_close_fd: perf_evsel__close_fd(evsel, 1, threads->nr); out_evsel_delete: @@ -437,6 +440,159 @@ out_thread_map_delete: return err; } +/* + * This test will generate random numbers of calls to some getpid syscalls, + * then establish an mmap for a group of events that are created to monitor + * the syscalls. + * + * It will receive the events, using mmap, use its PERF_SAMPLE_ID generated + * sample.id field to map back to its respective perf_evsel instance. + * + * Then it checks if the number of syscalls reported as perf events by + * the kernel corresponds to the number of syscalls made. + */ +static int test__basic_mmap(void) +{ + int err = -1; + union perf_event *event; + struct thread_map *threads; + struct cpu_map *cpus; + struct perf_evlist *evlist; + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .read_format = PERF_FORMAT_ID, + .sample_type = PERF_SAMPLE_ID, + .watermark = 0, + }; + cpu_set_t cpu_set; + const char *syscall_names[] = { "getsid", "getppid", "getpgrp", + "getpgid", }; + pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp, + (void*)getpgid }; +#define nsyscalls ARRAY_SIZE(syscall_names) + int ids[nsyscalls]; + unsigned int nr_events[nsyscalls], + expected_nr_events[nsyscalls], i, j; + struct perf_evsel *evsels[nsyscalls], *evsel; + + for (i = 0; i < nsyscalls; ++i) { + char name[64]; + + snprintf(name, sizeof(name), "sys_enter_%s", syscall_names[i]); + ids[i] = trace_event__id(name); + if (ids[i] < 0) { + pr_debug("Is debugfs mounted on /sys/kernel/debug?\n"); + return -1; + } + nr_events[i] = 0; + expected_nr_events[i] = random() % 257; + } + + threads = thread_map__new(-1, getpid()); + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + cpus = cpu_map__new(NULL); + if (cpus == NULL) { + pr_debug("cpu_map__new\n"); + goto out_free_threads; + } + + CPU_ZERO(&cpu_set); + CPU_SET(cpus->map[0], &cpu_set); + sched_setaffinity(0, sizeof(cpu_set), &cpu_set); + if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) { + pr_debug("sched_setaffinity() failed on CPU %d: %s ", + cpus->map[0], strerror(errno)); + goto out_free_cpus; + } + + evlist = perf_evlist__new(cpus, threads); + if (evlist == NULL) { + pr_debug("perf_evlist__new\n"); + goto out_free_cpus; + } + + /* anonymous union fields, can't be initialized above */ + attr.wakeup_events = 1; + attr.sample_period = 1; + + for (i = 0; i < nsyscalls; ++i) { + attr.config = ids[i]; + evsels[i] = perf_evsel__new(&attr, i); + if (evsels[i] == NULL) { + pr_debug("perf_evsel__new\n"); + goto out_free_evlist; + } + + perf_evlist__add(evlist, evsels[i]); + + if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) { + pr_debug("failed to open counter: %s, " + "tweak /proc/sys/kernel/perf_event_paranoid?\n", + strerror(errno)); + goto out_close_fd; + } + } + + if (perf_evlist__mmap(evlist, 128, true) < 0) { + pr_debug("failed to mmap events: %d (%s)\n", errno, + strerror(errno)); + goto out_close_fd; + } + + for (i = 0; i < nsyscalls; ++i) + for (j = 0; j < expected_nr_events[i]; ++j) { + int foo = syscalls[i](); + ++foo; + } + + while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) { + struct perf_sample sample; + + if (event->header.type != PERF_RECORD_SAMPLE) { + pr_debug("unexpected %s event\n", + perf_event__name(event->header.type)); + goto out_munmap; + } + + perf_event__parse_sample(event, attr.sample_type, false, &sample); + evsel = perf_evlist__id2evsel(evlist, sample.id); + if (evsel == NULL) { + pr_debug("event with id %" PRIu64 + " doesn't map to an evsel\n", sample.id); + goto out_munmap; + } + nr_events[evsel->idx]++; + } + + list_for_each_entry(evsel, &evlist->entries, node) { + if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) { + pr_debug("expected %d %s events, got %d\n", + expected_nr_events[evsel->idx], + event_name(evsel), nr_events[evsel->idx]); + goto out_munmap; + } + } + + err = 0; +out_munmap: + perf_evlist__munmap(evlist); +out_close_fd: + for (i = 0; i < nsyscalls; ++i) + perf_evsel__close_fd(evsels[i], 1, threads->nr); +out_free_evlist: + perf_evlist__delete(evlist); +out_free_cpus: + cpu_map__delete(cpus); +out_free_threads: + thread_map__delete(threads); + return err; +#undef nsyscalls +} + static struct test { const char *desc; int (*func)(void); @@ -454,6 +610,10 @@ static struct test { .func = test__open_syscall_event_on_all_cpus, }, { + .desc = "read samples using the mmap interface", + .func = test__basic_mmap, + }, + { .func = NULL, }, }; diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 746cf03..67c0459 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -264,9 +264,6 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end) c->start_time = start; if (p->start_time == 0 || p->start_time > start) p->start_time = start; - - if (cpu > numcpus) - numcpus = cpu; } #define MAX_CPUS 4096 @@ -276,21 +273,24 @@ static int cpus_cstate_state[MAX_CPUS]; static u64 cpus_pstate_start_times[MAX_CPUS]; static u64 cpus_pstate_state[MAX_CPUS]; -static int process_comm_event(event_t *event, struct sample_data *sample __used, +static int process_comm_event(union perf_event *event, + struct perf_sample *sample __used, struct perf_session *session __used) { pid_set_comm(event->comm.tid, event->comm.comm); return 0; } -static int process_fork_event(event_t *event, struct sample_data *sample __used, +static int process_fork_event(union perf_event *event, + struct perf_sample *sample __used, struct perf_session *session __used) { pid_fork(event->fork.pid, event->fork.ppid, event->fork.time); return 0; } -static int process_exit_event(event_t *event, struct sample_data *sample __used, +static int process_exit_event(union perf_event *event, + struct perf_sample *sample __used, struct perf_session *session __used) { pid_exit(event->fork.pid, event->fork.time); @@ -486,8 +486,8 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te) } -static int process_sample_event(event_t *event __used, - struct sample_data *sample, +static int process_sample_event(union perf_event *event __used, + struct perf_sample *sample, struct perf_session *session) { struct trace_entry *te; @@ -511,6 +511,9 @@ static int process_sample_event(event_t *event __used, if (!event_str) return 0; + if (sample->cpu > numcpus) + numcpus = sample->cpu; + if (strcmp(event_str, "power:cpu_idle") == 0) { struct power_processor_entry *ppe = (void *)te; if (ppe->state == (u32)PWR_EVENT_EXIT) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b6998e0..80c9e06 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -20,11 +20,16 @@ #include "perf.h" +#include "util/annotate.h" +#include "util/cache.h" #include "util/color.h" +#include "util/evlist.h" #include "util/evsel.h" #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" +#include "util/thread_map.h" +#include "util/top.h" #include "util/util.h" #include <linux/rbtree.h> #include "util/parse-options.h" @@ -45,7 +50,6 @@ #include <errno.h> #include <time.h> #include <sched.h> -#include <pthread.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -60,85 +64,42 @@ #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +static struct perf_top top = { + .count_filter = 5, + .delay_secs = 2, + .display_weighted = -1, + .target_pid = -1, + .target_tid = -1, + .active_symbols = LIST_HEAD_INIT(top.active_symbols), + .active_symbols_lock = PTHREAD_MUTEX_INITIALIZER, + .active_symbols_cond = PTHREAD_COND_INITIALIZER, + .freq = 1000, /* 1 KHz */ +}; + static bool system_wide = false; -static int default_interval = 0; +static bool use_tui, use_stdio; -static int count_filter = 5; -static int print_entries; +static int default_interval = 0; -static int target_pid = -1; -static int target_tid = -1; -static struct thread_map *threads; static bool inherit = false; -static struct cpu_map *cpus; static int realtime_prio = 0; static bool group = false; static unsigned int page_size; -static unsigned int mmap_pages = 16; -static int freq = 1000; /* 1 KHz */ +static unsigned int mmap_pages = 128; -static int delay_secs = 2; -static bool zero = false; static bool dump_symtab = false; -static bool hide_kernel_symbols = false; -static bool hide_user_symbols = false; static struct winsize winsize; -/* - * Source - */ - -struct source_line { - u64 eip; - unsigned long count[MAX_COUNTERS]; - char *line; - struct source_line *next; -}; - static const char *sym_filter = NULL; -struct sym_entry *sym_filter_entry = NULL; struct sym_entry *sym_filter_entry_sched = NULL; static int sym_pcnt_filter = 5; -static int sym_counter = 0; -static struct perf_evsel *sym_evsel = NULL; -static int display_weighted = -1; -static const char *cpu_list; - -/* - * Symbols - */ - -struct sym_entry_source { - struct source_line *source; - struct source_line *lines; - struct source_line **lines_tail; - pthread_mutex_t lock; -}; - -struct sym_entry { - struct rb_node rb_node; - struct list_head node; - unsigned long snap_count; - double weight; - int skip; - u16 name_len; - u8 origin; - struct map *map; - struct sym_entry_source *src; - unsigned long count[0]; -}; /* * Source functions */ -static inline struct symbol *sym_entry__symbol(struct sym_entry *self) -{ - return ((void *)self) + symbol_conf.priv_size; -} - void get_term_dimensions(struct winsize *ws) { char *s = getenv("LINES"); @@ -163,10 +124,10 @@ void get_term_dimensions(struct winsize *ws) static void update_print_entries(struct winsize *ws) { - print_entries = ws->ws_row; + top.print_entries = ws->ws_row; - if (print_entries > 9) - print_entries -= 9; + if (top.print_entries > 9) + top.print_entries -= 9; } static void sig_winch_handler(int sig __used) @@ -178,12 +139,9 @@ static void sig_winch_handler(int sig __used) static int parse_source(struct sym_entry *syme) { struct symbol *sym; - struct sym_entry_source *source; + struct annotation *notes; struct map *map; - FILE *file; - char command[PATH_MAX*2]; - const char *path; - u64 len; + int err = -1; if (!syme) return -1; @@ -194,411 +152,137 @@ static int parse_source(struct sym_entry *syme) /* * We can't annotate with just /proc/kallsyms */ - if (map->dso->origin == DSO__ORIG_KERNEL) + if (map->dso->origin == DSO__ORIG_KERNEL) { + pr_err("Can't annotate %s: No vmlinux file was found in the " + "path\n", sym->name); + sleep(1); return -1; - - if (syme->src == NULL) { - syme->src = zalloc(sizeof(*source)); - if (syme->src == NULL) - return -1; - pthread_mutex_init(&syme->src->lock, NULL); } - source = syme->src; - - if (source->lines) { - pthread_mutex_lock(&source->lock); + notes = symbol__annotation(sym); + if (notes->src != NULL) { + pthread_mutex_lock(¬es->lock); goto out_assign; } - path = map->dso->long_name; - - len = sym->end - sym->start; - - sprintf(command, - "objdump --start-address=%#0*" PRIx64 " --stop-address=%#0*" PRIx64 " -dS %s", - BITS_PER_LONG / 4, map__rip_2objdump(map, sym->start), - BITS_PER_LONG / 4, map__rip_2objdump(map, sym->end), path); - - file = popen(command, "r"); - if (!file) - return -1; - - pthread_mutex_lock(&source->lock); - source->lines_tail = &source->lines; - while (!feof(file)) { - struct source_line *src; - size_t dummy = 0; - char *c, *sep; - src = malloc(sizeof(struct source_line)); - assert(src != NULL); - memset(src, 0, sizeof(struct source_line)); + pthread_mutex_lock(¬es->lock); - if (getline(&src->line, &dummy, file) < 0) - break; - if (!src->line) - break; - - c = strchr(src->line, '\n'); - if (c) - *c = 0; - - src->next = NULL; - *source->lines_tail = src; - source->lines_tail = &src->next; - - src->eip = strtoull(src->line, &sep, 16); - if (*sep == ':') - src->eip = map__objdump_2ip(map, src->eip); - else /* this line has no ip info (e.g. source line) */ - src->eip = 0; + if (symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) { + pthread_mutex_unlock(¬es->lock); + pr_err("Not enough memory for annotating '%s' symbol!\n", + sym->name); + sleep(1); + return err; } - pclose(file); + + err = symbol__annotate(sym, syme->map, 0); + if (err == 0) { out_assign: - sym_filter_entry = syme; - pthread_mutex_unlock(&source->lock); - return 0; + top.sym_filter_entry = syme; + } + + pthread_mutex_unlock(¬es->lock); + return err; } static void __zero_source_counters(struct sym_entry *syme) { - int i; - struct source_line *line; - - line = syme->src->lines; - while (line) { - for (i = 0; i < nr_counters; i++) - line->count[i] = 0; - line = line->next; - } + struct symbol *sym = sym_entry__symbol(syme); + symbol__annotate_zero_histograms(sym); } static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip) { - struct source_line *line; - - if (syme != sym_filter_entry) - return; + struct annotation *notes; + struct symbol *sym; - if (pthread_mutex_trylock(&syme->src->lock)) + if (syme != top.sym_filter_entry) return; - if (syme->src == NULL || syme->src->source == NULL) - goto out_unlock; - - for (line = syme->src->lines; line; line = line->next) { - /* skip lines without IP info */ - if (line->eip == 0) - continue; - if (line->eip == ip) { - line->count[counter]++; - break; - } - if (line->eip > ip) - break; - } -out_unlock: - pthread_mutex_unlock(&syme->src->lock); -} - -#define PATTERN_LEN (BITS_PER_LONG / 4 + 2) - -static void lookup_sym_source(struct sym_entry *syme) -{ - struct symbol *symbol = sym_entry__symbol(syme); - struct source_line *line; - char pattern[PATTERN_LEN + 1]; - - sprintf(pattern, "%0*" PRIx64 " <", BITS_PER_LONG / 4, - map__rip_2objdump(syme->map, symbol->start)); - - pthread_mutex_lock(&syme->src->lock); - for (line = syme->src->lines; line; line = line->next) { - if (memcmp(line->line, pattern, PATTERN_LEN) == 0) { - syme->src->source = line; - break; - } - } - pthread_mutex_unlock(&syme->src->lock); -} + sym = sym_entry__symbol(syme); + notes = symbol__annotation(sym); -static void show_lines(struct source_line *queue, int count, int total) -{ - int i; - struct source_line *line; + if (pthread_mutex_trylock(¬es->lock)) + return; - line = queue; - for (i = 0; i < count; i++) { - float pcnt = 100.0*(float)line->count[sym_counter]/(float)total; + ip = syme->map->map_ip(syme->map, ip); + symbol__inc_addr_samples(sym, syme->map, counter, ip); - printf("%8li %4.1f%%\t%s\n", line->count[sym_counter], pcnt, line->line); - line = line->next; - } + pthread_mutex_unlock(¬es->lock); } -#define TRACE_COUNT 3 - static void show_details(struct sym_entry *syme) { + struct annotation *notes; struct symbol *symbol; - struct source_line *line; - struct source_line *line_queue = NULL; - int displayed = 0; - int line_queue_count = 0, total = 0, more = 0; + int more; if (!syme) return; - if (!syme->src->source) - lookup_sym_source(syme); - - if (!syme->src->source) - return; - symbol = sym_entry__symbol(syme); - printf("Showing %s for %s\n", event_name(sym_evsel), symbol->name); - printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter); - - pthread_mutex_lock(&syme->src->lock); - line = syme->src->source; - while (line) { - total += line->count[sym_counter]; - line = line->next; - } - - line = syme->src->source; - while (line) { - float pcnt = 0.0; - - if (!line_queue_count) - line_queue = line; - line_queue_count++; - - if (line->count[sym_counter]) - pcnt = 100.0 * line->count[sym_counter] / (float)total; - if (pcnt >= (float)sym_pcnt_filter) { - if (displayed <= print_entries) - show_lines(line_queue, line_queue_count, total); - else more++; - displayed += line_queue_count; - line_queue_count = 0; - line_queue = NULL; - } else if (line_queue_count > TRACE_COUNT) { - line_queue = line_queue->next; - line_queue_count--; - } - - line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8; - line = line->next; - } - pthread_mutex_unlock(&syme->src->lock); - if (more) - printf("%d lines not displayed, maybe increase display entries [e]\n", more); -} + notes = symbol__annotation(symbol); -/* - * Symbols will be added here in event__process_sample and will get out - * after decayed. - */ -static LIST_HEAD(active_symbols); -static pthread_mutex_t active_symbols_lock = PTHREAD_MUTEX_INITIALIZER; - -/* - * Ordering weight: count-1 * count-2 * ... / count-n - */ -static double sym_weight(const struct sym_entry *sym) -{ - double weight = sym->snap_count; - int counter; - - if (!display_weighted) - return weight; + pthread_mutex_lock(¬es->lock); - for (counter = 1; counter < nr_counters-1; counter++) - weight *= sym->count[counter]; + if (notes->src == NULL) + goto out_unlock; - weight /= (sym->count[counter] + 1); + printf("Showing %s for %s\n", event_name(top.sym_evsel), symbol->name); + printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter); - return weight; + more = symbol__annotate_printf(symbol, syme->map, top.sym_evsel->idx, + 0, sym_pcnt_filter, top.print_entries, 4); + if (top.zero) + symbol__annotate_zero_histogram(symbol, top.sym_evsel->idx); + else + symbol__annotate_decay_histogram(symbol, top.sym_evsel->idx); + if (more != 0) + printf("%d lines not displayed, maybe increase display entries [e]\n", more); +out_unlock: + pthread_mutex_unlock(¬es->lock); } -static long samples; -static long kernel_samples, us_samples; -static long exact_samples; -static long guest_us_samples, guest_kernel_samples; static const char CONSOLE_CLEAR[] = "[H[2J"; static void __list_insert_active_sym(struct sym_entry *syme) { - list_add(&syme->node, &active_symbols); -} - -static void list_remove_active_sym(struct sym_entry *syme) -{ - pthread_mutex_lock(&active_symbols_lock); - list_del_init(&syme->node); - pthread_mutex_unlock(&active_symbols_lock); + list_add(&syme->node, &top.active_symbols); } -static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) +static void print_sym_table(struct perf_session *session) { - struct rb_node **p = &tree->rb_node; - struct rb_node *parent = NULL; - struct sym_entry *iter; - - while (*p != NULL) { - parent = *p; - iter = rb_entry(parent, struct sym_entry, rb_node); - - if (se->weight > iter->weight) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - - rb_link_node(&se->rb_node, parent, p); - rb_insert_color(&se->rb_node, tree); -} - -static void print_sym_table(void) -{ - int printed = 0, j; - struct perf_evsel *counter; - int snap = !display_weighted ? sym_counter : 0; - float samples_per_sec = samples/delay_secs; - float ksamples_per_sec = kernel_samples/delay_secs; - float us_samples_per_sec = (us_samples)/delay_secs; - float guest_kernel_samples_per_sec = (guest_kernel_samples)/delay_secs; - float guest_us_samples_per_sec = (guest_us_samples)/delay_secs; - float esamples_percent = (100.0*exact_samples)/samples; - float sum_ksamples = 0.0; - struct sym_entry *syme, *n; - struct rb_root tmp = RB_ROOT; + char bf[160]; + int printed = 0; struct rb_node *nd; - int sym_width = 0, dso_width = 0, dso_short_width = 0; + struct sym_entry *syme; + struct rb_root tmp = RB_ROOT; const int win_width = winsize.ws_col - 1; - - samples = us_samples = kernel_samples = exact_samples = 0; - guest_kernel_samples = guest_us_samples = 0; - - /* Sort the active symbols */ - pthread_mutex_lock(&active_symbols_lock); - syme = list_entry(active_symbols.next, struct sym_entry, node); - pthread_mutex_unlock(&active_symbols_lock); - - list_for_each_entry_safe_from(syme, n, &active_symbols, node) { - syme->snap_count = syme->count[snap]; - if (syme->snap_count != 0) { - - if ((hide_user_symbols && - syme->origin == PERF_RECORD_MISC_USER) || - (hide_kernel_symbols && - syme->origin == PERF_RECORD_MISC_KERNEL)) { - list_remove_active_sym(syme); - continue; - } - syme->weight = sym_weight(syme); - rb_insert_active_sym(&tmp, syme); - sum_ksamples += syme->snap_count; - - for (j = 0; j < nr_counters; j++) - syme->count[j] = zero ? 0 : syme->count[j] * 7 / 8; - } else - list_remove_active_sym(syme); - } + int sym_width, dso_width, dso_short_width; + float sum_ksamples = perf_top__decay_samples(&top, &tmp); puts(CONSOLE_CLEAR); - printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - if (!perf_guest) { - printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%%" - " exact: %4.1f%% [", - samples_per_sec, - 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) / - samples_per_sec)), - esamples_percent); - } else { - printf(" PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%" - " guest kernel:%4.1f%% guest us:%4.1f%%" - " exact: %4.1f%% [", - samples_per_sec, - 100.0 - (100.0 * ((samples_per_sec-ksamples_per_sec) / - samples_per_sec)), - 100.0 - (100.0 * ((samples_per_sec-us_samples_per_sec) / - samples_per_sec)), - 100.0 - (100.0 * ((samples_per_sec - - guest_kernel_samples_per_sec) / - samples_per_sec)), - 100.0 - (100.0 * ((samples_per_sec - - guest_us_samples_per_sec) / - samples_per_sec)), - esamples_percent); - } - - if (nr_counters == 1 || !display_weighted) { - struct perf_evsel *first; - first = list_entry(evsel_list.next, struct perf_evsel, node); - printf("%" PRIu64, (uint64_t)first->attr.sample_period); - if (freq) - printf("Hz "); - else - printf(" "); - } - - if (!display_weighted) - printf("%s", event_name(sym_evsel)); - else list_for_each_entry(counter, &evsel_list, node) { - if (counter->idx) - printf("/"); - - printf("%s", event_name(counter)); - } + perf_top__header_snprintf(&top, bf, sizeof(bf)); + printf("%s\n", bf); - printf( "], "); - - if (target_pid != -1) - printf(" (target_pid: %d", target_pid); - else if (target_tid != -1) - printf(" (target_tid: %d", target_tid); - else - printf(" (all"); - - if (cpu_list) - printf(", CPU%s: %s)\n", cpus->nr > 1 ? "s" : "", cpu_list); - else { - if (target_tid != -1) - printf(")\n"); - else - printf(", %d CPU%s)\n", cpus->nr, cpus->nr > 1 ? "s" : ""); - } + perf_top__reset_sample_counters(&top); printf("%-*.*s\n", win_width, win_width, graph_dotted_line); - if (sym_filter_entry) { - show_details(sym_filter_entry); - return; + if (session->hists.stats.total_lost != 0) { + color_fprintf(stdout, PERF_COLOR_RED, "WARNING:"); + printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n", + session->hists.stats.total_lost); } - /* - * Find the longest symbol name that will be displayed - */ - for (nd = rb_first(&tmp); nd; nd = rb_next(nd)) { - syme = rb_entry(nd, struct sym_entry, rb_node); - if (++printed > print_entries || - (int)syme->snap_count < count_filter) - continue; - - if (syme->map->dso->long_name_len > dso_width) - dso_width = syme->map->dso->long_name_len; - - if (syme->map->dso->short_name_len > dso_short_width) - dso_short_width = syme->map->dso->short_name_len; - - if (syme->name_len > sym_width) - sym_width = syme->name_len; + if (top.sym_filter_entry) { + show_details(top.sym_filter_entry); + return; } - printed = 0; + perf_top__find_widths(&top, &tmp, &dso_width, &dso_short_width, + &sym_width); if (sym_width + dso_width > winsize.ws_col - 29) { dso_width = dso_short_width; @@ -606,7 +290,7 @@ static void print_sym_table(void) sym_width = winsize.ws_col - dso_width - 29; } putchar('\n'); - if (nr_counters == 1) + if (top.evlist->nr_entries == 1) printf(" samples pcnt"); else printf(" weight samples pcnt"); @@ -615,7 +299,7 @@ static void print_sym_table(void) printf(" RIP "); printf(" %-*.*s DSO\n", sym_width, sym_width, "function"); printf(" %s _______ _____", - nr_counters == 1 ? " " : "______"); + top.evlist->nr_entries == 1 ? " " : "______"); if (verbose) printf(" ________________"); printf(" %-*.*s", sym_width, sym_width, graph_line); @@ -628,13 +312,14 @@ static void print_sym_table(void) syme = rb_entry(nd, struct sym_entry, rb_node); sym = sym_entry__symbol(syme); - if (++printed > print_entries || (int)syme->snap_count < count_filter) + if (++printed > top.print_entries || + (int)syme->snap_count < top.count_filter) continue; pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) / sum_ksamples)); - if (nr_counters == 1 || !display_weighted) + if (top.evlist->nr_entries == 1 || !top.display_weighted) printf("%20.2f ", syme->weight); else printf("%9.1f %10ld ", syme->weight, syme->snap_count); @@ -693,10 +378,8 @@ static void prompt_symbol(struct sym_entry **target, const char *msg) /* zero counters of active symbol */ if (syme) { - pthread_mutex_lock(&syme->src->lock); __zero_source_counters(syme); *target = NULL; - pthread_mutex_unlock(&syme->src->lock); } fprintf(stdout, "\n%s: ", msg); @@ -707,11 +390,11 @@ static void prompt_symbol(struct sym_entry **target, const char *msg) if (p) *p = 0; - pthread_mutex_lock(&active_symbols_lock); - syme = list_entry(active_symbols.next, struct sym_entry, node); - pthread_mutex_unlock(&active_symbols_lock); + pthread_mutex_lock(&top.active_symbols_lock); + syme = list_entry(top.active_symbols.next, struct sym_entry, node); + pthread_mutex_unlock(&top.active_symbols_lock); - list_for_each_entry_safe_from(syme, n, &active_symbols, node) { + list_for_each_entry_safe_from(syme, n, &top.active_symbols, node) { struct symbol *sym = sym_entry__symbol(syme); if (!strcmp(buf, sym->name)) { @@ -735,34 +418,34 @@ static void print_mapped_keys(void) { char *name = NULL; - if (sym_filter_entry) { - struct symbol *sym = sym_entry__symbol(sym_filter_entry); + if (top.sym_filter_entry) { + struct symbol *sym = sym_entry__symbol(top.sym_filter_entry); name = sym->name; } fprintf(stdout, "\nMapped keys:\n"); - fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", delay_secs); - fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", print_entries); + fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top.delay_secs); + fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top.print_entries); - if (nr_counters > 1) - fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(sym_evsel)); + if (top.evlist->nr_entries > 1) + fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top.sym_evsel)); - fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", count_filter); + fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top.count_filter); fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter); fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); fprintf(stdout, "\t[S] stop annotation.\n"); - if (nr_counters > 1) - fprintf(stdout, "\t[w] toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0); + if (top.evlist->nr_entries > 1) + fprintf(stdout, "\t[w] toggle display weighted/count[E]r. \t(%d)\n", top.display_weighted ? 1 : 0); fprintf(stdout, "\t[K] hide kernel_symbols symbols. \t(%s)\n", - hide_kernel_symbols ? "yes" : "no"); + top.hide_kernel_symbols ? "yes" : "no"); fprintf(stdout, "\t[U] hide user symbols. \t(%s)\n", - hide_user_symbols ? "yes" : "no"); - fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", zero ? 1 : 0); + top.hide_user_symbols ? "yes" : "no"); + fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", top.zero ? 1 : 0); fprintf(stdout, "\t[qQ] quit.\n"); } @@ -783,7 +466,7 @@ static int key_mapped(int c) return 1; case 'E': case 'w': - return nr_counters > 1 ? 1 : 0; + return top.evlist->nr_entries > 1 ? 1 : 0; default: break; } @@ -818,47 +501,47 @@ static void handle_keypress(struct perf_session *session, int c) switch (c) { case 'd': - prompt_integer(&delay_secs, "Enter display delay"); - if (delay_secs < 1) - delay_secs = 1; + prompt_integer(&top.delay_secs, "Enter display delay"); + if (top.delay_secs < 1) + top.delay_secs = 1; break; case 'e': - prompt_integer(&print_entries, "Enter display entries (lines)"); - if (print_entries == 0) { + prompt_integer(&top.print_entries, "Enter display entries (lines)"); + if (top.print_entries == 0) { sig_winch_handler(SIGWINCH); signal(SIGWINCH, sig_winch_handler); } else signal(SIGWINCH, SIG_DFL); break; case 'E': - if (nr_counters > 1) { + if (top.evlist->nr_entries > 1) { fprintf(stderr, "\nAvailable events:"); - list_for_each_entry(sym_evsel, &evsel_list, node) - fprintf(stderr, "\n\t%d %s", sym_evsel->idx, event_name(sym_evsel)); + list_for_each_entry(top.sym_evsel, &top.evlist->entries, node) + fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel)); - prompt_integer(&sym_counter, "Enter details event counter"); + prompt_integer(&top.sym_counter, "Enter details event counter"); - if (sym_counter >= nr_counters) { - sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node); - sym_counter = 0; - fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(sym_evsel)); + if (top.sym_counter >= top.evlist->nr_entries) { + top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node); + top.sym_counter = 0; + fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel)); sleep(1); break; } - list_for_each_entry(sym_evsel, &evsel_list, node) - if (sym_evsel->idx == sym_counter) + list_for_each_entry(top.sym_evsel, &top.evlist->entries, node) + if (top.sym_evsel->idx == top.sym_counter) break; - } else sym_counter = 0; + } else top.sym_counter = 0; break; case 'f': - prompt_integer(&count_filter, "Enter display event count filter"); + prompt_integer(&top.count_filter, "Enter display event count filter"); break; case 'F': prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)"); break; case 'K': - hide_kernel_symbols = !hide_kernel_symbols; + top.hide_kernel_symbols = !top.hide_kernel_symbols; break; case 'q': case 'Q': @@ -867,34 +550,50 @@ static void handle_keypress(struct perf_session *session, int c) perf_session__fprintf_dsos(session, stderr); exit(0); case 's': - prompt_symbol(&sym_filter_entry, "Enter details symbol"); + prompt_symbol(&top.sym_filter_entry, "Enter details symbol"); break; case 'S': - if (!sym_filter_entry) + if (!top.sym_filter_entry) break; else { - struct sym_entry *syme = sym_filter_entry; + struct sym_entry *syme = top.sym_filter_entry; - pthread_mutex_lock(&syme->src->lock); - sym_filter_entry = NULL; + top.sym_filter_entry = NULL; __zero_source_counters(syme); - pthread_mutex_unlock(&syme->src->lock); } break; case 'U': - hide_user_symbols = !hide_user_symbols; + top.hide_user_symbols = !top.hide_user_symbols; break; case 'w': - display_weighted = ~display_weighted; + top.display_weighted = ~top.display_weighted; break; case 'z': - zero = !zero; + top.zero = !top.zero; break; default: break; } } +static void *display_thread_tui(void *arg __used) +{ + int err = 0; + pthread_mutex_lock(&top.active_symbols_lock); + while (list_empty(&top.active_symbols)) { + err = pthread_cond_wait(&top.active_symbols_cond, + &top.active_symbols_lock); + if (err) + break; + } + pthread_mutex_unlock(&top.active_symbols_lock); + if (!err) + perf_top__tui_browser(&top); + exit_browser(0); + exit(0); + return NULL; +} + static void *display_thread(void *arg __used) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; @@ -909,13 +608,13 @@ static void *display_thread(void *arg __used) tc.c_cc[VTIME] = 0; repeat: - delay_msecs = delay_secs * 1000; + delay_msecs = top.delay_secs * 1000; tcsetattr(0, TCSANOW, &tc); /* trash return*/ getc(stdin); do { - print_sym_table(); + print_sym_table(session); } while (!poll(&stdin_poll, 1, delay_msecs) == 1); c = getc(stdin); @@ -930,6 +629,7 @@ repeat: /* Tag samples to be skipped. */ static const char *skip_symbols[] = { "default_idle", + "native_safe_halt", "cpu_idle", "enter_idle", "exit_idle", @@ -965,9 +665,9 @@ static int symbol_filter(struct map *map, struct symbol *sym) syme = symbol__priv(sym); syme->map = map; - syme->src = NULL; + symbol__annotate_init(map, sym); - if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) { + if (!top.sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) { /* schedule initial sym_filter_entry setup */ sym_filter_entry_sched = syme; sym_filter = NULL; @@ -980,44 +680,40 @@ static int symbol_filter(struct map *map, struct symbol *sym) } } - if (!syme->skip) - syme->name_len = strlen(sym->name); - return 0; } -static void event__process_sample(const event_t *self, - struct sample_data *sample, - struct perf_session *session, - struct perf_evsel *evsel) +static void perf_event__process_sample(const union perf_event *event, + struct perf_sample *sample, + struct perf_session *session) { - u64 ip = self->ip.ip; + u64 ip = event->ip.ip; struct sym_entry *syme; struct addr_location al; struct machine *machine; - u8 origin = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + u8 origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - ++samples; + ++top.samples; switch (origin) { case PERF_RECORD_MISC_USER: - ++us_samples; - if (hide_user_symbols) + ++top.us_samples; + if (top.hide_user_symbols) return; machine = perf_session__find_host_machine(session); break; case PERF_RECORD_MISC_KERNEL: - ++kernel_samples; - if (hide_kernel_symbols) + ++top.kernel_samples; + if (top.hide_kernel_symbols) return; machine = perf_session__find_host_machine(session); break; case PERF_RECORD_MISC_GUEST_KERNEL: - ++guest_kernel_samples; - machine = perf_session__find_machine(session, self->ip.pid); + ++top.guest_kernel_samples; + machine = perf_session__find_machine(session, event->ip.pid); break; case PERF_RECORD_MISC_GUEST_USER: - ++guest_us_samples; + ++top.guest_us_samples; /* * TODO: we don't process guest user from host side * except simple counting. @@ -1029,15 +725,15 @@ static void event__process_sample(const event_t *self, if (!machine && perf_guest) { pr_err("Can't find guest [%d]'s kernel information\n", - self->ip.pid); + event->ip.pid); return; } - if (self->header.misc & PERF_RECORD_MISC_EXACT_IP) - exact_samples++; + if (event->header.misc & PERF_RECORD_MISC_EXACT_IP) + top.exact_samples++; - if (event__preprocess_sample(self, session, &al, sample, - symbol_filter) < 0 || + if (perf_event__preprocess_sample(event, session, &al, sample, + symbol_filter) < 0 || al.filtered) return; @@ -1055,8 +751,9 @@ static void event__process_sample(const event_t *self, */ if (al.map == machine->vmlinux_maps[MAP__FUNCTION] && RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) { - pr_err("The %s file can't be used\n", - symbol_conf.vmlinux_name); + ui__warning("The %s file can't be used\n", + symbol_conf.vmlinux_name); + exit_browser(0); exit(1); } @@ -1065,13 +762,13 @@ static void event__process_sample(const event_t *self, /* let's see, whether we need to install initial sym_filter_entry */ if (sym_filter_entry_sched) { - sym_filter_entry = sym_filter_entry_sched; + top.sym_filter_entry = sym_filter_entry_sched; sym_filter_entry_sched = NULL; - if (parse_source(sym_filter_entry) < 0) { - struct symbol *sym = sym_entry__symbol(sym_filter_entry); + if (parse_source(top.sym_filter_entry) < 0) { + struct symbol *sym = sym_entry__symbol(top.sym_filter_entry); pr_err("Can't annotate %s", sym->name); - if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) { + if (top.sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) { pr_err(": No vmlinux file was found in the path:\n"); machine__fprintf_vmlinux_path(machine, stderr); } else @@ -1082,166 +779,73 @@ static void event__process_sample(const event_t *self, syme = symbol__priv(al.sym); if (!syme->skip) { - syme->count[evsel->idx]++; + struct perf_evsel *evsel; + syme->origin = origin; + evsel = perf_evlist__id2evsel(top.evlist, sample->id); + assert(evsel != NULL); + syme->count[evsel->idx]++; record_precise_ip(syme, evsel->idx, ip); - pthread_mutex_lock(&active_symbols_lock); - if (list_empty(&syme->node) || !syme->node.next) + pthread_mutex_lock(&top.active_symbols_lock); + if (list_empty(&syme->node) || !syme->node.next) { + static bool first = true; __list_insert_active_sym(syme); - pthread_mutex_unlock(&active_symbols_lock); + if (first) { + pthread_cond_broadcast(&top.active_symbols_cond); + first = false; + } + } + pthread_mutex_unlock(&top.active_symbols_lock); } } -struct mmap_data { - void *base; - int mask; - unsigned int prev; -}; - -static int perf_evsel__alloc_mmap_per_thread(struct perf_evsel *evsel, - int ncpus, int nthreads) -{ - evsel->priv = xyarray__new(ncpus, nthreads, sizeof(struct mmap_data)); - return evsel->priv != NULL ? 0 : -ENOMEM; -} - -static void perf_evsel__free_mmap(struct perf_evsel *evsel) -{ - xyarray__delete(evsel->priv); - evsel->priv = NULL; -} - -static unsigned int mmap_read_head(struct mmap_data *md) -{ - struct perf_event_mmap_page *pc = md->base; - int head; - - head = pc->data_head; - rmb(); - - return head; -} - -static void perf_session__mmap_read_counter(struct perf_session *self, - struct perf_evsel *evsel, - int cpu, int thread_idx) +static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu) { - struct xyarray *mmap_array = evsel->priv; - struct mmap_data *md = xyarray__entry(mmap_array, cpu, thread_idx); - unsigned int head = mmap_read_head(md); - unsigned int old = md->prev; - unsigned char *data = md->base + page_size; - struct sample_data sample; - int diff; - - /* - * If we're further behind than half the buffer, there's a chance - * the writer will bite our tail and mess up the samples under us. - * - * If we somehow ended up ahead of the head, we got messed up. - * - * In either case, truncate and restart at head. - */ - diff = head - old; - if (diff > md->mask / 2 || diff < 0) { - fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); - - /* - * head points to a known good entry, start there. - */ - old = head; - } - - for (; old != head;) { - event_t *event = (event_t *)&data[old & md->mask]; - - event_t event_copy; + struct perf_sample sample; + union perf_event *event; - size_t size = event->header.size; + while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) { + perf_session__parse_sample(self, event, &sample); - /* - * Event straddles the mmap boundary -- header should always - * be inside due to u64 alignment of output. - */ - if ((old & md->mask) + size != ((old + size) & md->mask)) { - unsigned int offset = old; - unsigned int len = min(sizeof(*event), size), cpy; - void *dst = &event_copy; - - do { - cpy = min(md->mask + 1 - (offset & md->mask), len); - memcpy(dst, &data[offset & md->mask], cpy); - offset += cpy; - dst += cpy; - len -= cpy; - } while (len); - - event = &event_copy; - } - - event__parse_sample(event, self, &sample); if (event->header.type == PERF_RECORD_SAMPLE) - event__process_sample(event, &sample, self, evsel); + perf_event__process_sample(event, &sample, self); else - event__process(event, &sample, self); - old += size; + perf_event__process(event, &sample, self); } - - md->prev = old; } -static struct pollfd *event_array; - static void perf_session__mmap_read(struct perf_session *self) { - struct perf_evsel *counter; - int i, thread_index; - - for (i = 0; i < cpus->nr; i++) { - list_for_each_entry(counter, &evsel_list, node) { - for (thread_index = 0; - thread_index < threads->nr; - thread_index++) { - perf_session__mmap_read_counter(self, - counter, i, thread_index); - } - } - } -} + int i; -int nr_poll; -int group_fd; + for (i = 0; i < top.evlist->cpus->nr; i++) + perf_session__mmap_read_cpu(self, i); +} -static void start_counter(int i, struct perf_evsel *evsel) +static void start_counters(struct perf_evlist *evlist) { - struct xyarray *mmap_array = evsel->priv; - struct mmap_data *mm; - struct perf_event_attr *attr; - int cpu = -1; - int thread_index; - - if (target_tid == -1) - cpu = cpus->map[i]; + struct perf_evsel *counter; - attr = &evsel->attr; + list_for_each_entry(counter, &evlist->entries, node) { + struct perf_event_attr *attr = &counter->attr; - attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; - if (freq) { - attr->sample_type |= PERF_SAMPLE_PERIOD; - attr->freq = 1; - attr->sample_freq = freq; - } + if (top.freq) { + attr->sample_type |= PERF_SAMPLE_PERIOD; + attr->freq = 1; + attr->sample_freq = top.freq; + } - attr->inherit = (cpu < 0) && inherit; - attr->mmap = 1; + if (evlist->nr_entries > 1) { + attr->sample_type |= PERF_SAMPLE_ID; + attr->read_format |= PERF_FORMAT_ID; + } - for (thread_index = 0; thread_index < threads->nr; thread_index++) { + attr->mmap = 1; try_again: - FD(evsel, i, thread_index) = sys_perf_event_open(attr, - threads->map[thread_index], cpu, group_fd, 0); - - if (FD(evsel, i, thread_index) < 0) { + if (perf_evsel__open(counter, top.evlist->cpus, + top.evlist->threads, group, inherit) < 0) { int err = errno; if (err == EPERM || err == EACCES) @@ -1253,8 +857,8 @@ try_again: * based cpu-clock-tick sw counter, which * is always available even if no PMU support: */ - if (attr->type == PERF_TYPE_HARDWARE - && attr->config == PERF_COUNT_HW_CPU_CYCLES) { + if (attr->type == PERF_TYPE_HARDWARE && + attr->config == PERF_COUNT_HW_CPU_CYCLES) { if (verbose) warning(" ... trying to fall back to cpu-clock-ticks\n"); @@ -1264,39 +868,22 @@ try_again: goto try_again; } printf("\n"); - error("sys_perf_event_open() syscall returned with %d (%s). /bin/dmesg may provide additional information.\n", - FD(evsel, i, thread_index), strerror(err)); + error("sys_perf_event_open() syscall returned with %d " + "(%s). /bin/dmesg may provide additional information.\n", + err, strerror(err)); die("No CONFIG_PERF_EVENTS=y kernel support configured?\n"); exit(-1); } - assert(FD(evsel, i, thread_index) >= 0); - fcntl(FD(evsel, i, thread_index), F_SETFL, O_NONBLOCK); - - /* - * First counter acts as the group leader: - */ - if (group && group_fd == -1) - group_fd = FD(evsel, i, thread_index); - - event_array[nr_poll].fd = FD(evsel, i, thread_index); - event_array[nr_poll].events = POLLIN; - nr_poll++; - - mm = xyarray__entry(mmap_array, i, thread_index); - mm->prev = 0; - mm->mask = mmap_pages*page_size - 1; - mm->base = mmap(NULL, (mmap_pages+1)*page_size, - PROT_READ, MAP_SHARED, FD(evsel, i, thread_index), 0); - if (mm->base == MAP_FAILED) - die("failed to mmap with %d (%s)\n", errno, strerror(errno)); } + + if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) + die("failed to mmap with %d (%s)\n", errno, strerror(errno)); } static int __cmd_top(void) { pthread_t thread; - struct perf_evsel *counter; - int i, ret; + int ret __used; /* * FIXME: perf_session__new should allow passing a O_MMAP, so that all this * mmap reading, etc is encapsulated in it. Use O_WRONLY for now. @@ -1305,23 +892,23 @@ static int __cmd_top(void) if (session == NULL) return -ENOMEM; - if (target_tid != -1) - event__synthesize_thread(target_tid, event__process, session); + if (top.target_tid != -1) + perf_event__synthesize_thread_map(top.evlist->threads, + perf_event__process, session); else - event__synthesize_threads(event__process, session); + perf_event__synthesize_threads(perf_event__process, session); - for (i = 0; i < cpus->nr; i++) { - group_fd = -1; - list_for_each_entry(counter, &evsel_list, node) - start_counter(i, counter); - } + start_counters(top.evlist); + session->evlist = top.evlist; + perf_session__update_sample_type(session); /* Wait for a minimal set of events before starting the snapshot */ - poll(&event_array[0], nr_poll, 100); + poll(top.evlist->pollfd, top.evlist->nr_fds, 100); perf_session__mmap_read(session); - if (pthread_create(&thread, NULL, display_thread, session)) { + if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui : + display_thread), session)) { printf("Could not create display thread.\n"); exit(-1); } @@ -1337,12 +924,12 @@ static int __cmd_top(void) } while (1) { - int hits = samples; + u64 hits = top.samples; perf_session__mmap_read(session); - if (hits == samples) - ret = poll(event_array, nr_poll, 100); + if (hits == top.samples) + ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100); } return 0; @@ -1354,31 +941,31 @@ static const char * const top_usage[] = { }; static const struct option options[] = { - OPT_CALLBACK('e', "event", NULL, "event", + OPT_CALLBACK('e', "event", &top.evlist, "event", "event selector. use 'perf list' to list available events", parse_events), OPT_INTEGER('c', "count", &default_interval, "event period to sample"), - OPT_INTEGER('p', "pid", &target_pid, + OPT_INTEGER('p', "pid", &top.target_pid, "profile events on existing process id"), - OPT_INTEGER('t', "tid", &target_tid, + OPT_INTEGER('t', "tid", &top.target_tid, "profile events on existing thread id"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), - OPT_STRING('C', "cpu", &cpu_list, "cpu", + OPT_STRING('C', "cpu", &top.cpu_list, "cpu", "list of cpus to monitor"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), - OPT_BOOLEAN('K', "hide_kernel_symbols", &hide_kernel_symbols, + OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols, "hide kernel symbols"), OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"), OPT_INTEGER('r', "realtime", &realtime_prio, "collect data with this RT SCHED_FIFO priority"), - OPT_INTEGER('d', "delay", &delay_secs, + OPT_INTEGER('d', "delay", &top.delay_secs, "number of seconds to delay between refreshes"), OPT_BOOLEAN('D', "dump-symtab", &dump_symtab, "dump the symbol table used for profiling"), - OPT_INTEGER('f', "count-filter", &count_filter, + OPT_INTEGER('f', "count-filter", &top.count_filter, "only display functions with more events than this"), OPT_BOOLEAN('g', "group", &group, "put the counters into a counter group"), @@ -1386,14 +973,16 @@ static const struct option options[] = { "child tasks inherit counters"), OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name", "symbol to annotate"), - OPT_BOOLEAN('z', "zero", &zero, + OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"), - OPT_INTEGER('F', "freq", &freq, + OPT_INTEGER('F', "freq", &top.freq, "profile at this frequency"), - OPT_INTEGER('E', "entries", &print_entries, + OPT_INTEGER('E', "entries", &top.print_entries, "display this many functions"), - OPT_BOOLEAN('U', "hide_user_symbols", &hide_user_symbols, + OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols, "hide user symbols"), + OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"), + OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_END() @@ -1404,64 +993,68 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) struct perf_evsel *pos; int status = -ENOMEM; + top.evlist = perf_evlist__new(NULL, NULL); + if (top.evlist == NULL) + return -ENOMEM; + page_size = sysconf(_SC_PAGE_SIZE); argc = parse_options(argc, argv, options, top_usage, 0); if (argc) usage_with_options(top_usage, options); - if (target_pid != -1) - target_tid = target_pid; + /* + * XXX For now start disabled, only using TUI if explicitely asked for. + * Change that when handle_keys equivalent gets written, live annotation + * done, etc. + */ + use_browser = 0; - threads = thread_map__new(target_pid, target_tid); - if (threads == NULL) { - pr_err("Problems finding threads of monitor\n"); - usage_with_options(top_usage, options); - } + if (use_stdio) + use_browser = 0; + else if (use_tui) + use_browser = 1; - event_array = malloc((sizeof(struct pollfd) * - MAX_NR_CPUS * MAX_COUNTERS * threads->nr)); - if (!event_array) - return -ENOMEM; + setup_browser(false); /* CPU and PID are mutually exclusive */ - if (target_tid > 0 && cpu_list) { + if (top.target_tid > 0 && top.cpu_list) { printf("WARNING: PID switch overriding CPU\n"); sleep(1); - cpu_list = NULL; + top.cpu_list = NULL; } - if (!nr_counters && perf_evsel_list__create_default() < 0) { + if (top.target_pid != -1) + top.target_tid = top.target_pid; + + if (perf_evlist__create_maps(top.evlist, top.target_pid, + top.target_tid, top.cpu_list) < 0) + usage_with_options(top_usage, options); + + if (!top.evlist->nr_entries && + perf_evlist__add_default(top.evlist) < 0) { pr_err("Not enough memory for event selector list\n"); return -ENOMEM; } - if (delay_secs < 1) - delay_secs = 1; + if (top.delay_secs < 1) + top.delay_secs = 1; /* * User specified count overrides default frequency. */ if (default_interval) - freq = 0; - else if (freq) { - default_interval = freq; + top.freq = 0; + else if (top.freq) { + default_interval = top.freq; } else { fprintf(stderr, "frequency and count are zero, aborting\n"); exit(EXIT_FAILURE); } - if (target_tid != -1) - cpus = cpu_map__dummy_new(); - else - cpus = cpu_map__new(cpu_list); - - if (cpus == NULL) - usage_with_options(top_usage, options); - - list_for_each_entry(pos, &evsel_list, node) { - if (perf_evsel__alloc_mmap_per_thread(pos, cpus->nr, threads->nr) < 0 || - perf_evsel__alloc_fd(pos, cpus->nr, threads->nr) < 0) + list_for_each_entry(pos, &top.evlist->entries, node) { + if (perf_evsel__alloc_fd(pos, top.evlist->cpus->nr, + top.evlist->threads->nr) < 0) goto out_free_fd; /* * Fill in the ones not specifically initialized via -c: @@ -1472,26 +1065,28 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) pos->attr.sample_period = default_interval; } - sym_evsel = list_entry(evsel_list.next, struct perf_evsel, node); + if (perf_evlist__alloc_pollfd(top.evlist) < 0 || + perf_evlist__alloc_mmap(top.evlist) < 0) + goto out_free_fd; + + top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node); - symbol_conf.priv_size = (sizeof(struct sym_entry) + - (nr_counters + 1) * sizeof(unsigned long)); + symbol_conf.priv_size = (sizeof(struct sym_entry) + sizeof(struct annotation) + + (top.evlist->nr_entries + 1) * sizeof(unsigned long)); symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); if (symbol__init() < 0) return -1; get_term_dimensions(&winsize); - if (print_entries == 0) { + if (top.print_entries == 0) { update_print_entries(&winsize); signal(SIGWINCH, sig_winch_handler); } status = __cmd_top(); out_free_fd: - list_for_each_entry(pos, &evsel_list, node) - perf_evsel__free_mmap(pos); - perf_evsel_list__delete(); + perf_evlist__delete(top.evlist); return status; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 95aaf56..a5fc660 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -94,6 +94,32 @@ void get_term_dimensions(struct winsize *ws); #include "util/types.h" #include <stdbool.h> +struct perf_mmap { + void *base; + int mask; + unsigned int prev; +}; + +static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm) +{ + struct perf_event_mmap_page *pc = mm->base; + int head = pc->data_head; + rmb(); + return head; +} + +static inline void perf_mmap__write_tail(struct perf_mmap *md, + unsigned long tail) +{ + struct perf_event_mmap_page *pc = md->base; + + /* + * ensure all reads are done before we write the tail out. + */ + /* mb(); */ + pc->data_tail = tail; +} + /* * prctl(PR_TASK_PERF_EVENTS_DISABLE) will (cheaply) disable all * counters in the current task. diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py new file mode 100755 index 0000000..df638c4 --- /dev/null +++ b/tools/perf/python/twatch.py @@ -0,0 +1,41 @@ +#! /usr/bin/python +# -*- python -*- +# -*- coding: utf-8 -*- +# twatch - Experimental use of the perf python interface +# Copyright (C) 2011 Arnaldo Carvalho de Melo <acme@redhat.com> +# +# This application is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# as published by the Free Software Foundation; version 2. +# +# This application is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# General Public License for more details. + +import perf + +def main(): + cpus = perf.cpu_map() + threads = perf.thread_map() + evsel = perf.evsel(task = 1, comm = 1, mmap = 0, + wakeup_events = 1, sample_period = 1, + sample_id_all = 1, + sample_type = perf.SAMPLE_PERIOD | perf.SAMPLE_TID | perf.SAMPLE_CPU | perf.SAMPLE_TID) + evsel.open(cpus = cpus, threads = threads); + evlist = perf.evlist(cpus, threads) + evlist.add(evsel) + evlist.mmap() + while True: + evlist.poll(timeout = -1) + for cpu in cpus: + event = evlist.read_on_cpu(cpu) + if not event: + continue + print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu, + event.sample_pid, + event.sample_tid), + print event + +if __name__ == '__main__': + main() diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c new file mode 100644 index 0000000..0d0830c --- /dev/null +++ b/tools/perf/util/annotate.c @@ -0,0 +1,605 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-annotate.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "util.h" +#include "build-id.h" +#include "color.h" +#include "cache.h" +#include "symbol.h" +#include "debug.h" +#include "annotate.h" +#include <pthread.h> + +int symbol__annotate_init(struct map *map __used, struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + pthread_mutex_init(¬es->lock, NULL); + return 0; +} + +int symbol__alloc_hist(struct symbol *sym, int nevents) +{ + struct annotation *notes = symbol__annotation(sym); + size_t sizeof_sym_hist = (sizeof(struct sym_hist) + + (sym->end - sym->start) * sizeof(u64)); + + notes->src = zalloc(sizeof(*notes->src) + nevents * sizeof_sym_hist); + if (notes->src == NULL) + return -1; + notes->src->sizeof_sym_hist = sizeof_sym_hist; + notes->src->nr_histograms = nevents; + INIT_LIST_HEAD(¬es->src->source); + return 0; +} + +void symbol__annotate_zero_histograms(struct symbol *sym) +{ + struct annotation *notes = symbol__annotation(sym); + + pthread_mutex_lock(¬es->lock); + if (notes->src != NULL) + memset(notes->src->histograms, 0, + notes->src->nr_histograms * notes->src->sizeof_sym_hist); + pthread_mutex_unlock(¬es->lock); +} + +int symbol__inc_addr_samples(struct symbol *sym, struct map *map, + int evidx, u64 addr) +{ + unsigned offset; + struct annotation *notes; + struct sym_hist *h; + + notes = symbol__annotation(sym); + if (notes->src == NULL) + return -ENOMEM; + + pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr)); + + if (addr >= sym->end) + return 0; + + offset = addr - sym->start; + h = annotation__histogram(notes, evidx); + h->sum++; + h->addr[offset]++; + + pr_debug3("%#" PRIx64 " %s: period++ [addr: %#" PRIx64 ", %#" PRIx64 + ", evidx=%d] => %" PRIu64 "\n", sym->start, sym->name, + addr, addr - sym->start, evidx, h->addr[offset]); + return 0; +} + +static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize) +{ + struct objdump_line *self = malloc(sizeof(*self) + privsize); + + if (self != NULL) { + self->offset = offset; + self->line = line; + } + + return self; +} + +void objdump_line__free(struct objdump_line *self) +{ + free(self->line); + free(self); +} + +static void objdump__add_line(struct list_head *head, struct objdump_line *line) +{ + list_add_tail(&line->node, head); +} + +struct objdump_line *objdump__get_next_ip_line(struct list_head *head, + struct objdump_line *pos) +{ + list_for_each_entry_continue(pos, head, node) + if (pos->offset >= 0) + return pos; + + return NULL; +} + +static int objdump_line__print(struct objdump_line *oline, struct symbol *sym, + int evidx, u64 len, int min_pcnt, + int printed, int max_lines, + struct objdump_line *queue) +{ + static const char *prev_line; + static const char *prev_color; + + if (oline->offset != -1) { + const char *path = NULL; + unsigned int hits = 0; + double percent = 0.0; + const char *color; + struct annotation *notes = symbol__annotation(sym); + struct source_line *src_line = notes->src->lines; + struct sym_hist *h = annotation__histogram(notes, evidx); + s64 offset = oline->offset; + struct objdump_line *next; + + next = objdump__get_next_ip_line(¬es->src->source, oline); + + while (offset < (s64)len && + (next == NULL || offset < next->offset)) { + if (src_line) { + if (path == NULL) + path = src_line[offset].path; + percent += src_line[offset].percent; + } else + hits += h->addr[offset]; + + ++offset; + } + + if (src_line == NULL && h->sum) + percent = 100.0 * hits / h->sum; + + if (percent < min_pcnt) + return -1; + + if (max_lines && printed >= max_lines) + return 1; + + if (queue != NULL) { + list_for_each_entry_from(queue, ¬es->src->source, node) { + if (queue == oline) + break; + objdump_line__print(queue, sym, evidx, len, + 0, 0, 1, NULL); + } + } + + color = get_percent_color(percent); + + /* + * Also color the filename and line if needed, with + * the same color than the percentage. Don't print it + * twice for close colored addr with the same filename:line + */ + if (path) { + if (!prev_line || strcmp(prev_line, path) + || color != prev_color) { + color_fprintf(stdout, color, " %s", path); + prev_line = path; + prev_color = color; + } + } + + color_fprintf(stdout, color, " %7.2f", percent); + printf(" : "); + color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", oline->line); + } else if (max_lines && printed >= max_lines) + return 1; + else { + if (queue) + return -1; + + if (!*oline->line) + printf(" :\n"); + else + printf(" : %s\n", oline->line); + } + + return 0; +} + +static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, + FILE *file, size_t privsize) +{ + struct annotation *notes = symbol__annotation(sym); + struct objdump_line *objdump_line; + char *line = NULL, *tmp, *tmp2, *c; + size_t line_len; + s64 line_ip, offset = -1; + + if (getline(&line, &line_len, file) < 0) + return -1; + + if (!line) + return -1; + + while (line_len != 0 && isspace(line[line_len - 1])) + line[--line_len] = '\0'; + + c = strchr(line, '\n'); + if (c) + *c = 0; + + line_ip = -1; + + /* + * Strip leading spaces: + */ + tmp = line; + while (*tmp) { + if (*tmp != ' ') + break; + tmp++; + } + + if (*tmp) { + /* + * Parse hexa addresses followed by ':' + */ + line_ip = strtoull(tmp, &tmp2, 16); + if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0') + line_ip = -1; + } + + if (line_ip != -1) { + u64 start = map__rip_2objdump(map, sym->start), + end = map__rip_2objdump(map, sym->end); + + offset = line_ip - start; + if (offset < 0 || (u64)line_ip > end) + offset = -1; + } + + objdump_line = objdump_line__new(offset, line, privsize); + if (objdump_line == NULL) { + free(line); + return -1; + } + objdump__add_line(¬es->src->source, objdump_line); + + return 0; +} + +int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize) +{ + struct dso *dso = map->dso; + char *filename = dso__build_id_filename(dso, NULL, 0); + bool free_filename = true; + char command[PATH_MAX * 2]; + FILE *file; + int err = 0; + char symfs_filename[PATH_MAX]; + + if (filename) { + snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", + symbol_conf.symfs, filename); + } + + if (filename == NULL) { + if (dso->has_build_id) { + pr_err("Can't annotate %s: not enough memory\n", + sym->name); + return -ENOMEM; + } + goto fallback; + } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || + strstr(command, "[kernel.kallsyms]") || + access(symfs_filename, R_OK)) { + free(filename); +fallback: + /* + * If we don't have build-ids or the build-id file isn't in the + * cache, or is just a kallsyms file, well, lets hope that this + * DSO is the same as when 'perf record' ran. + */ + filename = dso->long_name; + snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", + symbol_conf.symfs, filename); + free_filename = false; + } + + if (dso->origin == DSO__ORIG_KERNEL) { + char bf[BUILD_ID_SIZE * 2 + 16] = " with build id "; + char *build_id_msg = NULL; + + if (dso->annotate_warned) + goto out_free_filename; + + if (dso->has_build_id) { + build_id__sprintf(dso->build_id, + sizeof(dso->build_id), bf + 15); + build_id_msg = bf; + } + err = -ENOENT; + dso->annotate_warned = 1; + pr_err("Can't annotate %s: No vmlinux file%s was found in the " + "path.\nPlease use 'perf buildid-cache -av vmlinux' or " + "--vmlinux vmlinux.\n", + sym->name, build_id_msg ?: ""); + goto out_free_filename; + } + + pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, + filename, sym->name, map->unmap_ip(map, sym->start), + map->unmap_ip(map, sym->end)); + + pr_debug("annotating [%p] %30s : [%p] %30s\n", + dso, dso->long_name, sym, sym->name); + + snprintf(command, sizeof(command), + "objdump --start-address=0x%016" PRIx64 + " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand", + map__rip_2objdump(map, sym->start), + map__rip_2objdump(map, sym->end), + symfs_filename, filename); + + pr_debug("Executing: %s\n", command); + + file = popen(command, "r"); + if (!file) + goto out_free_filename; + + while (!feof(file)) + if (symbol__parse_objdump_line(sym, map, file, privsize) < 0) + break; + + pclose(file); +out_free_filename: + if (free_filename) + free(filename); + return err; +} + +static void insert_source_line(struct rb_root *root, struct source_line *src_line) +{ + struct source_line *iter; + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct source_line, node); + + if (src_line->percent > iter->percent) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&src_line->node, parent, p); + rb_insert_color(&src_line->node, root); +} + +static void symbol__free_source_line(struct symbol *sym, int len) +{ + struct annotation *notes = symbol__annotation(sym); + struct source_line *src_line = notes->src->lines; + int i; + + for (i = 0; i < len; i++) + free(src_line[i].path); + + free(src_line); + notes->src->lines = NULL; +} + +/* Get the filename:line for the colored entries */ +static int symbol__get_source_line(struct symbol *sym, struct map *map, + int evidx, struct rb_root *root, int len, + const char *filename) +{ + u64 start; + int i; + char cmd[PATH_MAX * 2]; + struct source_line *src_line; + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + + if (!h->sum) + return 0; + + src_line = notes->src->lines = calloc(len, sizeof(struct source_line)); + if (!notes->src->lines) + return -1; + + start = map->unmap_ip(map, sym->start); + + for (i = 0; i < len; i++) { + char *path = NULL; + size_t line_len; + u64 offset; + FILE *fp; + + src_line[i].percent = 100.0 * h->addr[i] / h->sum; + if (src_line[i].percent <= 0.5) + continue; + + offset = start + i; + sprintf(cmd, "addr2line -e %s %016" PRIx64, filename, offset); + fp = popen(cmd, "r"); + if (!fp) + continue; + + if (getline(&path, &line_len, fp) < 0 || !line_len) + goto next; + + src_line[i].path = malloc(sizeof(char) * line_len + 1); + if (!src_line[i].path) + goto next; + + strcpy(src_line[i].path, path); + insert_source_line(root, &src_line[i]); + + next: + pclose(fp); + } + + return 0; +} + +static void print_summary(struct rb_root *root, const char *filename) +{ + struct source_line *src_line; + struct rb_node *node; + + printf("\nSorted summary for file %s\n", filename); + printf("----------------------------------------------\n\n"); + + if (RB_EMPTY_ROOT(root)) { + printf(" Nothing higher than %1.1f%%\n", MIN_GREEN); + return; + } + + node = rb_first(root); + while (node) { + double percent; + const char *color; + char *path; + + src_line = rb_entry(node, struct source_line, node); + percent = src_line->percent; + color = get_percent_color(percent); + path = src_line->path; + + color_fprintf(stdout, color, " %7.2f %s", percent, path); + node = rb_next(node); + } +} + +static void symbol__annotate_hits(struct symbol *sym, int evidx) +{ + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + u64 len = sym->end - sym->start, offset; + + for (offset = 0; offset < len; ++offset) + if (h->addr[offset] != 0) + printf("%*" PRIx64 ": %" PRIu64 "\n", BITS_PER_LONG / 2, + sym->start + offset, h->addr[offset]); + printf("%*s: %" PRIu64 "\n", BITS_PER_LONG / 2, "h->sum", h->sum); +} + +int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, + bool full_paths, int min_pcnt, int max_lines, + int context) +{ + struct dso *dso = map->dso; + const char *filename = dso->long_name, *d_filename; + struct annotation *notes = symbol__annotation(sym); + struct objdump_line *pos, *queue = NULL; + int printed = 2, queue_len = 0; + int more = 0; + u64 len; + + if (full_paths) + d_filename = filename; + else + d_filename = basename(filename); + + len = sym->end - sym->start; + + printf(" Percent | Source code & Disassembly of %s\n", d_filename); + printf("------------------------------------------------\n"); + + if (verbose) + symbol__annotate_hits(sym, evidx); + + list_for_each_entry(pos, ¬es->src->source, node) { + if (context && queue == NULL) { + queue = pos; + queue_len = 0; + } + + switch (objdump_line__print(pos, sym, evidx, len, min_pcnt, + printed, max_lines, queue)) { + case 0: + ++printed; + if (context) { + printed += queue_len; + queue = NULL; + queue_len = 0; + } + break; + case 1: + /* filtered by max_lines */ + ++more; + break; + case -1: + default: + /* + * Filtered by min_pcnt or non IP lines when + * context != 0 + */ + if (!context) + break; + if (queue_len == context) + queue = list_entry(queue->node.next, typeof(*queue), node); + else + ++queue_len; + break; + } + } + + return more; +} + +void symbol__annotate_zero_histogram(struct symbol *sym, int evidx) +{ + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + + memset(h, 0, notes->src->sizeof_sym_hist); +} + +void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) +{ + struct annotation *notes = symbol__annotation(sym); + struct sym_hist *h = annotation__histogram(notes, evidx); + struct objdump_line *pos; + int len = sym->end - sym->start; + + h->sum = 0; + + list_for_each_entry(pos, ¬es->src->source, node) { + if (pos->offset != -1 && pos->offset < len) { + h->addr[pos->offset] = h->addr[pos->offset] * 7 / 8; + h->sum += h->addr[pos->offset]; + } + } +} + +void objdump_line_list__purge(struct list_head *head) +{ + struct objdump_line *pos, *n; + + list_for_each_entry_safe(pos, n, head, node) { + list_del(&pos->node); + objdump_line__free(pos); + } +} + +int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, + bool print_lines, bool full_paths, int min_pcnt, + int max_lines) +{ + struct dso *dso = map->dso; + const char *filename = dso->long_name; + struct rb_root source_line = RB_ROOT; + u64 len; + + if (symbol__annotate(sym, map, 0) < 0) + return -1; + + len = sym->end - sym->start; + + if (print_lines) { + symbol__get_source_line(sym, map, evidx, &source_line, + len, filename); + print_summary(&source_line, filename); + } + + symbol__annotate_printf(sym, map, evidx, full_paths, + min_pcnt, max_lines, 0); + if (print_lines) + symbol__free_source_line(sym, len); + + objdump_line_list__purge(&symbol__annotation(sym)->src->source); + + return 0; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h new file mode 100644 index 0000000..c2c2868 --- /dev/null +++ b/tools/perf/util/annotate.h @@ -0,0 +1,103 @@ +#ifndef __PERF_ANNOTATE_H +#define __PERF_ANNOTATE_H + +#include <stdbool.h> +#include "types.h" +#include "symbol.h" +#include <linux/list.h> +#include <linux/rbtree.h> + +struct objdump_line { + struct list_head node; + s64 offset; + char *line; +}; + +void objdump_line__free(struct objdump_line *self); +struct objdump_line *objdump__get_next_ip_line(struct list_head *head, + struct objdump_line *pos); + +struct sym_hist { + u64 sum; + u64 addr[0]; +}; + +struct source_line { + struct rb_node node; + double percent; + char *path; +}; + +/** struct annotated_source - symbols with hits have this attached as in sannotation + * + * @histogram: Array of addr hit histograms per event being monitored + * @lines: If 'print_lines' is specified, per source code line percentages + * @source: source parsed from objdump -dS + * + * lines is allocated, percentages calculated and all sorted by percentage + * when the annotation is about to be presented, so the percentages are for + * one of the entries in the histogram array, i.e. for the event/counter being + * presented. It is deallocated right after symbol__{tui,tty,etc}_annotate + * returns. + */ +struct annotated_source { + struct list_head source; + struct source_line *lines; + int nr_histograms; + int sizeof_sym_hist; + struct sym_hist histograms[0]; +}; + +struct annotation { + pthread_mutex_t lock; + struct annotated_source *src; +}; + +struct sannotation { + struct annotation annotation; + struct symbol symbol; +}; + +static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx) +{ + return (((void *)¬es->src->histograms) + + (notes->src->sizeof_sym_hist * idx)); +} + +static inline struct annotation *symbol__annotation(struct symbol *sym) +{ + struct sannotation *a = container_of(sym, struct sannotation, symbol); + return &a->annotation; +} + +int symbol__inc_addr_samples(struct symbol *sym, struct map *map, + int evidx, u64 addr); +int symbol__alloc_hist(struct symbol *sym, int nevents); +void symbol__annotate_zero_histograms(struct symbol *sym); + +int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize); +int symbol__annotate_init(struct map *map __used, struct symbol *sym); +int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, + bool full_paths, int min_pcnt, int max_lines, + int context); +void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); +void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); +void objdump_line_list__purge(struct list_head *head); + +int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, + bool print_lines, bool full_paths, int min_pcnt, + int max_lines); + +#ifdef NO_NEWT_SUPPORT +static inline int symbol__tui_annotate(struct symbol *sym __used, + struct map *map __used, + int evidx __used, int refresh __used) +{ + return 0; +} +#else +int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, + int refresh); +#endif + +#endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index deffb8c..31f934a 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -14,8 +14,8 @@ #include <linux/kernel.h> #include "debug.h" -static int build_id__mark_dso_hit(event_t *event, - struct sample_data *sample __used, +static int build_id__mark_dso_hit(union perf_event *event, + struct perf_sample *sample __used, struct perf_session *session) { struct addr_location al; @@ -37,13 +37,14 @@ static int build_id__mark_dso_hit(event_t *event, return 0; } -static int event__exit_del_thread(event_t *self, struct sample_data *sample __used, - struct perf_session *session) +static int perf_event__exit_del_thread(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { - struct thread *thread = perf_session__findnew(session, self->fork.tid); + struct thread *thread = perf_session__findnew(session, event->fork.tid); - dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, - self->fork.ppid, self->fork.ptid); + dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, + event->fork.ppid, event->fork.ptid); if (thread) { rb_erase(&thread->rb_node, &session->threads); @@ -56,9 +57,9 @@ static int event__exit_del_thread(event_t *self, struct sample_data *sample __us struct perf_event_ops build_id__mark_dso_hit_ops = { .sample = build_id__mark_dso_hit, - .mmap = event__process_mmap, - .fork = event__process_task, - .exit = event__exit_del_thread, + .mmap = perf_event__process_mmap, + .fork = perf_event__process_task, + .exit = perf_event__exit_del_thread, }; char *dso__build_id_filename(struct dso *self, char *bf, size_t size) diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index a772979..fc5e5a0 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -34,13 +34,14 @@ extern int pager_use_color; extern int use_browser; #ifdef NO_NEWT_SUPPORT -static inline void setup_browser(void) +static inline void setup_browser(bool fallback_to_pager) { - setup_pager(); + if (fallback_to_pager) + setup_pager(); } static inline void exit_browser(bool wait_for_ok __used) {} #else -void setup_browser(void); +void setup_browser(bool fallback_to_pager); void exit_browser(bool wait_for_ok); #endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index e12d539..9f7106a 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2010, Frederic Weisbecker <fweisbec@gmail.com> + * Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com> * * Handle the callchains from the stream in an ad-hoc radix tree and then * sort them in an rbtree. @@ -18,7 +18,8 @@ #include "util.h" #include "callchain.h" -bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event) +bool ip_callchain__valid(struct ip_callchain *chain, + const union perf_event *event) { unsigned int chain_size = event->header.size; chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event; @@ -26,10 +27,10 @@ bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event) } #define chain_for_each_child(child, parent) \ - list_for_each_entry(child, &parent->children, brothers) + list_for_each_entry(child, &parent->children, siblings) #define chain_for_each_child_safe(child, next, parent) \ - list_for_each_entry_safe(child, next, &parent->children, brothers) + list_for_each_entry_safe(child, next, &parent->children, siblings) static void rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, @@ -38,14 +39,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct callchain_node *rnode; - u64 chain_cumul = cumul_hits(chain); + u64 chain_cumul = callchain_cumul_hits(chain); while (*p) { u64 rnode_cumul; parent = *p; rnode = rb_entry(parent, struct callchain_node, rb_node); - rnode_cumul = cumul_hits(rnode); + rnode_cumul = callchain_cumul_hits(rnode); switch (mode) { case CHAIN_FLAT: @@ -104,7 +105,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node, chain_for_each_child(child, node) { __sort_chain_graph_abs(child, min_hit); - if (cumul_hits(child) >= min_hit) + if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, CHAIN_GRAPH_ABS); } @@ -129,7 +130,7 @@ static void __sort_chain_graph_rel(struct callchain_node *node, chain_for_each_child(child, node) { __sort_chain_graph_rel(child, min_percent); - if (cumul_hits(child) >= min_hit) + if (callchain_cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, CHAIN_GRAPH_REL); } @@ -143,7 +144,7 @@ sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root, rb_root->rb_node = chain_root->node.rb_root.rb_node; } -int register_callchain_param(struct callchain_param *param) +int callchain_register_param(struct callchain_param *param) { switch (param->mode) { case CHAIN_GRAPH_ABS: @@ -189,32 +190,27 @@ create_child(struct callchain_node *parent, bool inherit_children) chain_for_each_child(next, new) next->parent = new; } - list_add_tail(&new->brothers, &parent->children); + list_add_tail(&new->siblings, &parent->children); return new; } -struct resolved_ip { - u64 ip; - struct map_symbol ms; -}; - -struct resolved_chain { - u64 nr; - struct resolved_ip ips[0]; -}; - - /* * Fill the node with callchain values */ static void -fill_node(struct callchain_node *node, struct resolved_chain *chain, int start) +fill_node(struct callchain_node *node, struct callchain_cursor *cursor) { - unsigned int i; + struct callchain_cursor_node *cursor_node; + + node->val_nr = cursor->nr - cursor->pos; + if (!node->val_nr) + pr_warning("Warning: empty node in callchain tree\n"); - for (i = start; i < chain->nr; i++) { + cursor_node = callchain_cursor_current(cursor); + + while (cursor_node) { struct callchain_list *call; call = zalloc(sizeof(*call)); @@ -222,23 +218,25 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start) perror("not enough memory for the code path tree"); return; } - call->ip = chain->ips[i].ip; - call->ms = chain->ips[i].ms; + call->ip = cursor_node->ip; + call->ms.sym = cursor_node->sym; + call->ms.map = cursor_node->map; list_add_tail(&call->list, &node->val); + + callchain_cursor_advance(cursor); + cursor_node = callchain_cursor_current(cursor); } - node->val_nr = chain->nr - start; - if (!node->val_nr) - pr_warning("Warning: empty node in callchain tree\n"); } static void -add_child(struct callchain_node *parent, struct resolved_chain *chain, - int start, u64 period) +add_child(struct callchain_node *parent, + struct callchain_cursor *cursor, + u64 period) { struct callchain_node *new; new = create_child(parent, false); - fill_node(new, chain, start); + fill_node(new, cursor); new->children_hit = 0; new->hit = period; @@ -250,9 +248,10 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain, * Then create another child to host the given callchain of new branch */ static void -split_add_child(struct callchain_node *parent, struct resolved_chain *chain, - struct callchain_list *to_split, int idx_parents, int idx_local, - u64 period) +split_add_child(struct callchain_node *parent, + struct callchain_cursor *cursor, + struct callchain_list *to_split, + u64 idx_parents, u64 idx_local, u64 period) { struct callchain_node *new; struct list_head *old_tail; @@ -272,14 +271,14 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain, /* split the hits */ new->hit = parent->hit; new->children_hit = parent->children_hit; - parent->children_hit = cumul_hits(new); + parent->children_hit = callchain_cumul_hits(new); new->val_nr = parent->val_nr - idx_local; parent->val_nr = idx_local; /* create a new child for the new branch if any */ - if (idx_total < chain->nr) { + if (idx_total < cursor->nr) { parent->hit = 0; - add_child(parent, chain, idx_total, period); + add_child(parent, cursor, period); parent->children_hit += period; } else { parent->hit = period; @@ -287,36 +286,41 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain, } static int -append_chain(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start, u64 period); +append_chain(struct callchain_node *root, + struct callchain_cursor *cursor, + u64 period); static void -append_chain_children(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start, u64 period) +append_chain_children(struct callchain_node *root, + struct callchain_cursor *cursor, + u64 period) { struct callchain_node *rnode; /* lookup in childrens */ chain_for_each_child(rnode, root) { - unsigned int ret = append_chain(rnode, chain, start, period); + unsigned int ret = append_chain(rnode, cursor, period); if (!ret) goto inc_children_hit; } /* nothing in children, add to the current node */ - add_child(root, chain, start, period); + add_child(root, cursor, period); inc_children_hit: root->children_hit += period; } static int -append_chain(struct callchain_node *root, struct resolved_chain *chain, - unsigned int start, u64 period) +append_chain(struct callchain_node *root, + struct callchain_cursor *cursor, + u64 period) { + struct callchain_cursor_node *curr_snap = cursor->curr; struct callchain_list *cnode; - unsigned int i = start; + u64 start = cursor->pos; bool found = false; + u64 matches; /* * Lookup in the current node @@ -324,141 +328,134 @@ append_chain(struct callchain_node *root, struct resolved_chain *chain, * anywhere inside a function. */ list_for_each_entry(cnode, &root->val, list) { + struct callchain_cursor_node *node; struct symbol *sym; - if (i == chain->nr) + node = callchain_cursor_current(cursor); + if (!node) break; - sym = chain->ips[i].ms.sym; + sym = node->sym; if (cnode->ms.sym && sym) { if (cnode->ms.sym->start != sym->start) break; - } else if (cnode->ip != chain->ips[i].ip) + } else if (cnode->ip != node->ip) break; if (!found) found = true; - i++; + + callchain_cursor_advance(cursor); } /* matches not, relay on the parent */ - if (!found) + if (!found) { + cursor->curr = curr_snap; + cursor->pos = start; return -1; + } + + matches = cursor->pos - start; /* we match only a part of the node. Split it and add the new chain */ - if (i - start < root->val_nr) { - split_add_child(root, chain, cnode, start, i - start, period); + if (matches < root->val_nr) { + split_add_child(root, cursor, cnode, start, matches, period); return 0; } /* we match 100% of the path, increment the hit */ - if (i - start == root->val_nr && i == chain->nr) { + if (matches == root->val_nr && cursor->pos == cursor->nr) { root->hit += period; return 0; } /* We match the node and still have a part remaining */ - append_chain_children(root, chain, i, period); + append_chain_children(root, cursor, period); return 0; } -static void filter_context(struct ip_callchain *old, struct resolved_chain *new, - struct map_symbol *syms) -{ - int i, j = 0; - - for (i = 0; i < (int)old->nr; i++) { - if (old->ips[i] >= PERF_CONTEXT_MAX) - continue; - - new->ips[j].ip = old->ips[i]; - new->ips[j].ms = syms[i]; - j++; - } - - new->nr = j; -} - - -int callchain_append(struct callchain_root *root, struct ip_callchain *chain, - struct map_symbol *syms, u64 period) +int callchain_append(struct callchain_root *root, + struct callchain_cursor *cursor, + u64 period) { - struct resolved_chain *filtered; - - if (!chain->nr) + if (!cursor->nr) return 0; - filtered = zalloc(sizeof(*filtered) + - chain->nr * sizeof(struct resolved_ip)); - if (!filtered) - return -ENOMEM; - - filter_context(chain, filtered, syms); - - if (!filtered->nr) - goto end; + callchain_cursor_commit(cursor); - append_chain_children(&root->node, filtered, 0, period); + append_chain_children(&root->node, cursor, period); - if (filtered->nr > root->max_depth) - root->max_depth = filtered->nr; -end: - free(filtered); + if (cursor->nr > root->max_depth) + root->max_depth = cursor->nr; return 0; } static int -merge_chain_branch(struct callchain_node *dst, struct callchain_node *src, - struct resolved_chain *chain) +merge_chain_branch(struct callchain_cursor *cursor, + struct callchain_node *dst, struct callchain_node *src) { + struct callchain_cursor_node **old_last = cursor->last; struct callchain_node *child, *next_child; struct callchain_list *list, *next_list; - int old_pos = chain->nr; + int old_pos = cursor->nr; int err = 0; list_for_each_entry_safe(list, next_list, &src->val, list) { - chain->ips[chain->nr].ip = list->ip; - chain->ips[chain->nr].ms = list->ms; - chain->nr++; + callchain_cursor_append(cursor, list->ip, + list->ms.map, list->ms.sym); list_del(&list->list); free(list); } - if (src->hit) - append_chain_children(dst, chain, 0, src->hit); + if (src->hit) { + callchain_cursor_commit(cursor); + append_chain_children(dst, cursor, src->hit); + } chain_for_each_child_safe(child, next_child, src) { - err = merge_chain_branch(dst, child, chain); + err = merge_chain_branch(cursor, dst, child); if (err) break; - list_del(&child->brothers); + list_del(&child->siblings); free(child); } - chain->nr = old_pos; + cursor->nr = old_pos; + cursor->last = old_last; return err; } -int callchain_merge(struct callchain_root *dst, struct callchain_root *src) +int callchain_merge(struct callchain_cursor *cursor, + struct callchain_root *dst, struct callchain_root *src) +{ + return merge_chain_branch(cursor, &dst->node, &src->node); +} + +int callchain_cursor_append(struct callchain_cursor *cursor, + u64 ip, struct map *map, struct symbol *sym) { - struct resolved_chain *chain; - int err; + struct callchain_cursor_node *node = *cursor->last; - chain = malloc(sizeof(*chain) + - src->max_depth * sizeof(struct resolved_ip)); - if (!chain) - return -ENOMEM; + if (!node) { + node = calloc(sizeof(*node), 1); + if (!node) + return -ENOMEM; - chain->nr = 0; + *cursor->last = node; + } - err = merge_chain_branch(&dst->node, &src->node, chain); + node->ip = ip; + node->map = map; + node->sym = sym; - free(chain); + cursor->nr++; - return err; + cursor->last = &node->next; + + return 0; } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index c15fb8c..1a79df9 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -16,7 +16,7 @@ enum chain_mode { struct callchain_node { struct callchain_node *parent; - struct list_head brothers; + struct list_head siblings; struct list_head children; struct list_head val; struct rb_node rb_node; /* to sort nodes in an rbtree */ @@ -49,9 +49,30 @@ struct callchain_list { struct list_head list; }; +/* + * A callchain cursor is a single linked list that + * let one feed a callchain progressively. + * It keeps persitent allocated entries to minimize + * allocations. + */ +struct callchain_cursor_node { + u64 ip; + struct map *map; + struct symbol *sym; + struct callchain_cursor_node *next; +}; + +struct callchain_cursor { + u64 nr; + struct callchain_cursor_node *first; + struct callchain_cursor_node **last; + u64 pos; + struct callchain_cursor_node *curr; +}; + static inline void callchain_init(struct callchain_root *root) { - INIT_LIST_HEAD(&root->node.brothers); + INIT_LIST_HEAD(&root->node.siblings); INIT_LIST_HEAD(&root->node.children); INIT_LIST_HEAD(&root->node.val); @@ -61,15 +82,54 @@ static inline void callchain_init(struct callchain_root *root) root->max_depth = 0; } -static inline u64 cumul_hits(struct callchain_node *node) +static inline u64 callchain_cumul_hits(struct callchain_node *node) { return node->hit + node->children_hit; } -int register_callchain_param(struct callchain_param *param); -int callchain_append(struct callchain_root *root, struct ip_callchain *chain, - struct map_symbol *syms, u64 period); -int callchain_merge(struct callchain_root *dst, struct callchain_root *src); +int callchain_register_param(struct callchain_param *param); +int callchain_append(struct callchain_root *root, + struct callchain_cursor *cursor, + u64 period); + +int callchain_merge(struct callchain_cursor *cursor, + struct callchain_root *dst, struct callchain_root *src); + +bool ip_callchain__valid(struct ip_callchain *chain, + const union perf_event *event); +/* + * Initialize a cursor before adding entries inside, but keep + * the previously allocated entries as a cache. + */ +static inline void callchain_cursor_reset(struct callchain_cursor *cursor) +{ + cursor->nr = 0; + cursor->last = &cursor->first; +} + +int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip, + struct map *map, struct symbol *sym); -bool ip_callchain__valid(struct ip_callchain *chain, const event_t *event); +/* Close a cursor writing session. Initialize for the reader */ +static inline void callchain_cursor_commit(struct callchain_cursor *cursor) +{ + cursor->curr = cursor->first; + cursor->pos = 0; +} + +/* Cursor reading iteration helpers */ +static inline struct callchain_cursor_node * +callchain_cursor_current(struct callchain_cursor *cursor) +{ + if (cursor->pos == cursor->nr) + return NULL; + + return cursor->curr; +} + +static inline void callchain_cursor_advance(struct callchain_cursor *cursor) +{ + cursor->curr = cursor->curr->next; + cursor->pos++; +} #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c new file mode 100644 index 0000000..9fea755 --- /dev/null +++ b/tools/perf/util/cgroup.c @@ -0,0 +1,178 @@ +#include "util.h" +#include "../perf.h" +#include "parse-options.h" +#include "evsel.h" +#include "cgroup.h" +#include "debugfs.h" /* MAX_PATH, STR() */ +#include "evlist.h" + +int nr_cgroups; + +static int +cgroupfs_find_mountpoint(char *buf, size_t maxlen) +{ + FILE *fp; + char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1]; + char *token, *saved_ptr; + int found = 0; + + fp = fopen("/proc/mounts", "r"); + if (!fp) + return -1; + + /* + * in order to handle split hierarchy, we need to scan /proc/mounts + * and inspect every cgroupfs mount point to find one that has + * perf_event subsystem + */ + while (fscanf(fp, "%*s %"STR(MAX_PATH)"s %"STR(MAX_PATH)"s %" + STR(MAX_PATH)"s %*d %*d\n", + mountpoint, type, tokens) == 3) { + + if (!strcmp(type, "cgroup")) { + + token = strtok_r(tokens, ",", &saved_ptr); + + while (token != NULL) { + if (!strcmp(token, "perf_event")) { + found = 1; + break; + } + token = strtok_r(NULL, ",", &saved_ptr); + } + } + if (found) + break; + } + fclose(fp); + if (!found) + return -1; + + if (strlen(mountpoint) < maxlen) { + strcpy(buf, mountpoint); + return 0; + } + return -1; +} + +static int open_cgroup(char *name) +{ + char path[MAX_PATH+1]; + char mnt[MAX_PATH+1]; + int fd; + + + if (cgroupfs_find_mountpoint(mnt, MAX_PATH+1)) + return -1; + + snprintf(path, MAX_PATH, "%s/%s", mnt, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + fprintf(stderr, "no access to cgroup %s\n", path); + + return fd; +} + +static int add_cgroup(struct perf_evlist *evlist, char *str) +{ + struct perf_evsel *counter; + struct cgroup_sel *cgrp = NULL; + int n; + /* + * check if cgrp is already defined, if so we reuse it + */ + list_for_each_entry(counter, &evlist->entries, node) { + cgrp = counter->cgrp; + if (!cgrp) + continue; + if (!strcmp(cgrp->name, str)) + break; + + cgrp = NULL; + } + + if (!cgrp) { + cgrp = zalloc(sizeof(*cgrp)); + if (!cgrp) + return -1; + + cgrp->name = str; + + cgrp->fd = open_cgroup(str); + if (cgrp->fd == -1) { + free(cgrp); + return -1; + } + } + + /* + * find corresponding event + * if add cgroup N, then need to find event N + */ + n = 0; + list_for_each_entry(counter, &evlist->entries, node) { + if (n == nr_cgroups) + goto found; + n++; + } + if (cgrp->refcnt == 0) + free(cgrp); + + return -1; +found: + cgrp->refcnt++; + counter->cgrp = cgrp; + return 0; +} + +void close_cgroup(struct cgroup_sel *cgrp) +{ + if (!cgrp) + return; + + /* XXX: not reentrant */ + if (--cgrp->refcnt == 0) { + close(cgrp->fd); + free(cgrp->name); + free(cgrp); + } +} + +int parse_cgroups(const struct option *opt __used, const char *str, + int unset __used) +{ + struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; + const char *p, *e, *eos = str + strlen(str); + char *s; + int ret; + + if (list_empty(&evlist->entries)) { + fprintf(stderr, "must define events before cgroups\n"); + return -1; + } + + for (;;) { + p = strchr(str, ','); + e = p ? p : eos; + + /* allow empty cgroups, i.e., skip */ + if (e - str) { + /* termination added */ + s = strndup(str, e - str); + if (!s) + return -1; + ret = add_cgroup(evlist, s); + if (ret) { + free(s); + return -1; + } + } + /* nr_cgroups is increased een for empty cgroups */ + nr_cgroups++; + if (!p) + break; + str = p+1; + } + return 0; +} diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h new file mode 100644 index 0000000..89acd6d --- /dev/null +++ b/tools/perf/util/cgroup.h @@ -0,0 +1,17 @@ +#ifndef __CGROUP_H__ +#define __CGROUP_H__ + +struct option; + +struct cgroup_sel { + char *name; + int fd; + int refcnt; +}; + + +extern int nr_cgroups; /* number of explicit cgroups defined */ +extern void close_cgroup(struct cgroup_sel *cgrp); +extern int parse_cgroups(const struct option *opt, const char *str, int unset); + +#endif /* __CGROUP_H__ */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 3ccaa10..6893eec 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -177,3 +177,8 @@ struct cpu_map *cpu_map__dummy_new(void) return cpus; } + +void cpu_map__delete(struct cpu_map *map) +{ + free(map); +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index f7a4f42..072c0a3 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -8,6 +8,6 @@ struct cpu_map { struct cpu_map *cpu_map__new(const char *cpu_list); struct cpu_map *cpu_map__dummy_new(void); -void *cpu_map__delete(struct cpu_map *map); +void cpu_map__delete(struct cpu_map *map); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 01bbe8e..d4536a9 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -57,7 +57,7 @@ void ui__warning(const char *format, ...) } #endif -void trace_event(event_t *event) +void trace_event(union perf_event *event) { unsigned char *raw_event = (void *)event; const char *color = PERF_COLOR_BLUE; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index ca35fd6..93516cf4 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -9,7 +9,7 @@ extern int verbose; extern bool quiet, dump_trace; int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2))); -void trace_event(event_t *event); +void trace_event(union perf_event *event); struct ui_progress; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1478ab4..2b15c36 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -6,8 +6,9 @@ #include "string.h" #include "strlist.h" #include "thread.h" +#include "thread_map.h" -static const char *event__name[] = { +static const char *perf_event__names[] = { [0] = "TOTAL", [PERF_RECORD_MMAP] = "MMAP", [PERF_RECORD_LOST] = "LOST", @@ -25,16 +26,16 @@ static const char *event__name[] = { [PERF_RECORD_FINISHED_ROUND] = "FINISHED_ROUND", }; -const char *event__get_event_name(unsigned int id) +const char *perf_event__name(unsigned int id) { - if (id >= ARRAY_SIZE(event__name)) + if (id >= ARRAY_SIZE(perf_event__names)) return "INVALID"; - if (!event__name[id]) + if (!perf_event__names[id]) return "UNKNOWN"; - return event__name[id]; + return perf_event__names[id]; } -static struct sample_data synth_sample = { +static struct perf_sample synth_sample = { .pid = -1, .tid = -1, .time = -1, @@ -43,9 +44,9 @@ static struct sample_data synth_sample = { .period = 1, }; -static pid_t event__synthesize_comm(event_t *event, pid_t pid, int full, - event__handler_t process, - struct perf_session *session) +static pid_t perf_event__synthesize_comm(union perf_event *event, pid_t pid, + int full, perf_event__handler_t process, + struct perf_session *session) { char filename[PATH_MAX]; char bf[BUFSIZ]; @@ -126,9 +127,10 @@ out: return tgid; } -static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid, - event__handler_t process, - struct perf_session *session) +static int perf_event__synthesize_mmap_events(union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct perf_session *session) { char filename[PATH_MAX]; FILE *fp; @@ -199,14 +201,14 @@ static int event__synthesize_mmap_events(event_t *event, pid_t pid, pid_t tgid, return 0; } -int event__synthesize_modules(event__handler_t process, - struct perf_session *session, - struct machine *machine) +int perf_event__synthesize_modules(perf_event__handler_t process, + struct perf_session *session, + struct machine *machine) { struct rb_node *nd; struct map_groups *kmaps = &machine->kmaps; - event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size); - + union perf_event *event = zalloc((sizeof(event->mmap) + + session->id_hdr_size)); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -251,23 +253,25 @@ int event__synthesize_modules(event__handler_t process, return 0; } -static int __event__synthesize_thread(event_t *comm_event, event_t *mmap_event, - pid_t pid, event__handler_t process, +static int __event__synthesize_thread(union perf_event *comm_event, + union perf_event *mmap_event, + pid_t pid, perf_event__handler_t process, struct perf_session *session) { - pid_t tgid = event__synthesize_comm(comm_event, pid, 1, process, + pid_t tgid = perf_event__synthesize_comm(comm_event, pid, 1, process, session); if (tgid == -1) return -1; - return event__synthesize_mmap_events(mmap_event, pid, tgid, + return perf_event__synthesize_mmap_events(mmap_event, pid, tgid, process, session); } -int event__synthesize_thread(pid_t pid, event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_thread_map(struct thread_map *threads, + perf_event__handler_t process, + struct perf_session *session) { - event_t *comm_event, *mmap_event; - int err = -1; + union perf_event *comm_event, *mmap_event; + int err = -1, thread; comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size); if (comm_event == NULL) @@ -277,8 +281,15 @@ int event__synthesize_thread(pid_t pid, event__handler_t process, if (mmap_event == NULL) goto out_free_comm; - err = __event__synthesize_thread(comm_event, mmap_event, pid, - process, session); + err = 0; + for (thread = 0; thread < threads->nr; ++thread) { + if (__event__synthesize_thread(comm_event, mmap_event, + threads->map[thread], + process, session)) { + err = -1; + break; + } + } free(mmap_event); out_free_comm: free(comm_event); @@ -286,12 +297,12 @@ out: return err; } -int event__synthesize_threads(event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_threads(perf_event__handler_t process, + struct perf_session *session) { DIR *proc; struct dirent dirent, *next; - event_t *comm_event, *mmap_event; + union perf_event *comm_event, *mmap_event; int err = -1; comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size); @@ -349,10 +360,10 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } -int event__synthesize_kernel_mmap(event__handler_t process, - struct perf_session *session, - struct machine *machine, - const char *symbol_name) +int perf_event__synthesize_kernel_mmap(perf_event__handler_t process, + struct perf_session *session, + struct machine *machine, + const char *symbol_name) { size_t size; const char *filename, *mmap_name; @@ -366,8 +377,8 @@ int event__synthesize_kernel_mmap(event__handler_t process, * kernels. */ struct process_symbol_args args = { .name = symbol_name, }; - event_t *event = zalloc(sizeof(event->mmap) + session->id_hdr_size); - + union perf_event *event = zalloc((sizeof(event->mmap) + + session->id_hdr_size)); if (event == NULL) { pr_debug("Not enough memory synthesizing mmap event " "for kernel modules\n"); @@ -413,42 +424,15 @@ int event__synthesize_kernel_mmap(event__handler_t process, return err; } -static void thread__comm_adjust(struct thread *self, struct hists *hists) -{ - char *comm = self->comm; - - if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep && - (!symbol_conf.comm_list || - strlist__has_entry(symbol_conf.comm_list, comm))) { - u16 slen = strlen(comm); - - if (hists__new_col_len(hists, HISTC_COMM, slen)) - hists__set_col_len(hists, HISTC_THREAD, slen + 6); - } -} - -static int thread__set_comm_adjust(struct thread *self, const char *comm, - struct hists *hists) -{ - int ret = thread__set_comm(self, comm); - - if (ret) - return ret; - - thread__comm_adjust(self, hists); - - return 0; -} - -int event__process_comm(event_t *self, struct sample_data *sample __used, - struct perf_session *session) +int perf_event__process_comm(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { - struct thread *thread = perf_session__findnew(session, self->comm.tid); + struct thread *thread = perf_session__findnew(session, event->comm.tid); - dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid); + dump_printf(": %s:%d\n", event->comm.comm, event->comm.tid); - if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm, - &session->hists)) { + if (thread == NULL || thread__set_comm(thread, event->comm.comm)) { dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n"); return -1; } @@ -456,19 +440,21 @@ int event__process_comm(event_t *self, struct sample_data *sample __used, return 0; } -int event__process_lost(event_t *self, struct sample_data *sample __used, - struct perf_session *session) +int perf_event__process_lost(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n", - self->lost.id, self->lost.lost); - session->hists.stats.total_lost += self->lost.lost; + event->lost.id, event->lost.lost); + session->hists.stats.total_lost += event->lost.lost; return 0; } -static void event_set_kernel_mmap_len(struct map **maps, event_t *self) +static void perf_event__set_kernel_mmap_len(union perf_event *event, + struct map **maps) { - maps[MAP__FUNCTION]->start = self->mmap.start; - maps[MAP__FUNCTION]->end = self->mmap.start + self->mmap.len; + maps[MAP__FUNCTION]->start = event->mmap.start; + maps[MAP__FUNCTION]->end = event->mmap.start + event->mmap.len; /* * Be a bit paranoid here, some perf.data file came with * a zero sized synthesized MMAP event for the kernel. @@ -477,8 +463,8 @@ static void event_set_kernel_mmap_len(struct map **maps, event_t *self) maps[MAP__FUNCTION]->end = ~0ULL; } -static int event__process_kernel_mmap(event_t *self, - struct perf_session *session) +static int perf_event__process_kernel_mmap(union perf_event *event, + struct perf_session *session) { struct map *map; char kmmap_prefix[PATH_MAX]; @@ -486,9 +472,9 @@ static int event__process_kernel_mmap(event_t *self, enum dso_kernel_type kernel_type; bool is_kernel_mmap; - machine = perf_session__findnew_machine(session, self->mmap.pid); + machine = perf_session__findnew_machine(session, event->mmap.pid); if (!machine) { - pr_err("Can't find id %d's machine\n", self->mmap.pid); + pr_err("Can't find id %d's machine\n", event->mmap.pid); goto out_problem; } @@ -498,17 +484,17 @@ static int event__process_kernel_mmap(event_t *self, else kernel_type = DSO_TYPE_GUEST_KERNEL; - is_kernel_mmap = memcmp(self->mmap.filename, + is_kernel_mmap = memcmp(event->mmap.filename, kmmap_prefix, strlen(kmmap_prefix)) == 0; - if (self->mmap.filename[0] == '/' || - (!is_kernel_mmap && self->mmap.filename[0] == '[')) { + if (event->mmap.filename[0] == '/' || + (!is_kernel_mmap && event->mmap.filename[0] == '[')) { char short_module_name[1024]; char *name, *dot; - if (self->mmap.filename[0] == '/') { - name = strrchr(self->mmap.filename, '/'); + if (event->mmap.filename[0] == '/') { + name = strrchr(event->mmap.filename, '/'); if (name == NULL) goto out_problem; @@ -520,10 +506,10 @@ static int event__process_kernel_mmap(event_t *self, "[%.*s]", (int)(dot - name), name); strxfrchar(short_module_name, '-', '_'); } else - strcpy(short_module_name, self->mmap.filename); + strcpy(short_module_name, event->mmap.filename); - map = machine__new_module(machine, self->mmap.start, - self->mmap.filename); + map = machine__new_module(machine, event->mmap.start, + event->mmap.filename); if (map == NULL) goto out_problem; @@ -533,9 +519,9 @@ static int event__process_kernel_mmap(event_t *self, map->dso->short_name = name; map->dso->sname_alloc = 1; - map->end = map->start + self->mmap.len; + map->end = map->start + event->mmap.len; } else if (is_kernel_mmap) { - const char *symbol_name = (self->mmap.filename + + const char *symbol_name = (event->mmap.filename + strlen(kmmap_prefix)); /* * Should be there already, from the build-id table in @@ -550,10 +536,10 @@ static int event__process_kernel_mmap(event_t *self, if (__machine__create_kernel_maps(machine, kernel) < 0) goto out_problem; - event_set_kernel_mmap_len(machine->vmlinux_maps, self); + perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps); perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, symbol_name, - self->mmap.pgoff); + event->mmap.pgoff); if (machine__is_default_guest(machine)) { /* * preload dso of guest kernel and modules @@ -567,22 +553,23 @@ out_problem: return -1; } -int event__process_mmap(event_t *self, struct sample_data *sample __used, - struct perf_session *session) +int perf_event__process_mmap(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { struct machine *machine; struct thread *thread; struct map *map; - u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; int ret = 0; dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n", - self->mmap.pid, self->mmap.tid, self->mmap.start, - self->mmap.len, self->mmap.pgoff, self->mmap.filename); + event->mmap.pid, event->mmap.tid, event->mmap.start, + event->mmap.len, event->mmap.pgoff, event->mmap.filename); if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL || cpumode == PERF_RECORD_MISC_KERNEL) { - ret = event__process_kernel_mmap(self, session); + ret = perf_event__process_kernel_mmap(event, session); if (ret < 0) goto out_problem; return 0; @@ -591,12 +578,12 @@ int event__process_mmap(event_t *self, struct sample_data *sample __used, machine = perf_session__find_host_machine(session); if (machine == NULL) goto out_problem; - thread = perf_session__findnew(session, self->mmap.pid); + thread = perf_session__findnew(session, event->mmap.pid); if (thread == NULL) goto out_problem; - map = map__new(&machine->user_dsos, self->mmap.start, - self->mmap.len, self->mmap.pgoff, - self->mmap.pid, self->mmap.filename, + map = map__new(&machine->user_dsos, event->mmap.start, + event->mmap.len, event->mmap.pgoff, + event->mmap.pid, event->mmap.filename, MAP__FUNCTION); if (map == NULL) goto out_problem; @@ -609,16 +596,17 @@ out_problem: return 0; } -int event__process_task(event_t *self, struct sample_data *sample __used, - struct perf_session *session) +int perf_event__process_task(union perf_event *event, + struct perf_sample *sample __used, + struct perf_session *session) { - struct thread *thread = perf_session__findnew(session, self->fork.tid); - struct thread *parent = perf_session__findnew(session, self->fork.ptid); + struct thread *thread = perf_session__findnew(session, event->fork.tid); + struct thread *parent = perf_session__findnew(session, event->fork.ptid); - dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid, - self->fork.ppid, self->fork.ptid); + dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid, + event->fork.ppid, event->fork.ptid); - if (self->header.type == PERF_RECORD_EXIT) { + if (event->header.type == PERF_RECORD_EXIT) { perf_session__remove_thread(session, thread); return 0; } @@ -632,20 +620,22 @@ int event__process_task(event_t *self, struct sample_data *sample __used, return 0; } -int event__process(event_t *event, struct sample_data *sample, - struct perf_session *session) +int perf_event__process(union perf_event *event, struct perf_sample *sample, + struct perf_session *session) { switch (event->header.type) { case PERF_RECORD_COMM: - event__process_comm(event, sample, session); + perf_event__process_comm(event, sample, session); break; case PERF_RECORD_MMAP: - event__process_mmap(event, sample, session); + perf_event__process_mmap(event, sample, session); break; case PERF_RECORD_FORK: case PERF_RECORD_EXIT: - event__process_task(event, sample, session); + perf_event__process_task(event, sample, session); break; + case PERF_RECORD_LOST: + perf_event__process_lost(event, sample, session); default: break; } @@ -742,24 +732,14 @@ void thread__find_addr_location(struct thread *self, al->sym = NULL; } -static void dso__calc_col_width(struct dso *self, struct hists *hists) -{ - if (!symbol_conf.col_width_list_str && !symbol_conf.field_sep && - (!symbol_conf.dso_list || - strlist__has_entry(symbol_conf.dso_list, self->name))) { - u16 slen = dso__name_len(self); - hists__new_col_len(hists, HISTC_DSO, slen); - } - - self->slen_calculated = 1; -} - -int event__preprocess_sample(const event_t *self, struct perf_session *session, - struct addr_location *al, struct sample_data *data, - symbol_filter_t filter) +int perf_event__preprocess_sample(const union perf_event *event, + struct perf_session *session, + struct addr_location *al, + struct perf_sample *sample, + symbol_filter_t filter) { - u8 cpumode = self->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; - struct thread *thread = perf_session__findnew(session, self->ip.pid); + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct thread *thread = perf_session__findnew(session, event->ip.pid); if (thread == NULL) return -1; @@ -781,12 +761,12 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, machine__create_kernel_maps(&session->host_machine); thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION, - self->ip.pid, self->ip.ip, al); + event->ip.pid, event->ip.ip, al); dump_printf(" ...... dso: %s\n", al->map ? al->map->dso->long_name : al->level == 'H' ? "[hypervisor]" : "<not found>"); al->sym = NULL; - al->cpu = data->cpu; + al->cpu = sample->cpu; if (al->map) { if (symbol_conf.dso_list && @@ -797,23 +777,8 @@ int event__preprocess_sample(const event_t *self, struct perf_session *session, strlist__has_entry(symbol_conf.dso_list, al->map->dso->long_name))))) goto out_filtered; - /* - * We have to do this here as we may have a dso with no symbol - * hit that has a name longer than the ones with symbols - * sampled. - */ - if (!sort_dso.elide && !al->map->dso->slen_calculated) - dso__calc_col_width(al->map->dso, &session->hists); al->sym = map__find_symbol(al->map, al->addr, filter); - } else { - const unsigned int unresolved_col_width = BITS_PER_LONG / 4; - - if (hists__col_len(&session->hists, HISTC_DSO) < unresolved_col_width && - !symbol_conf.col_width_list_str && !symbol_conf.field_sep && - !symbol_conf.dso_list) - hists__set_col_len(&session->hists, HISTC_DSO, - unresolved_col_width); } if (symbol_conf.sym_list && al->sym && @@ -826,128 +791,3 @@ out_filtered: al->filtered = true; return 0; } - -static int event__parse_id_sample(const event_t *event, - struct perf_session *session, - struct sample_data *sample) -{ - const u64 *array; - u64 type; - - sample->cpu = sample->pid = sample->tid = -1; - sample->stream_id = sample->id = sample->time = -1ULL; - - if (!session->sample_id_all) - return 0; - - array = event->sample.array; - array += ((event->header.size - - sizeof(event->header)) / sizeof(u64)) - 1; - type = session->sample_type; - - if (type & PERF_SAMPLE_CPU) { - u32 *p = (u32 *)array; - sample->cpu = *p; - array--; - } - - if (type & PERF_SAMPLE_STREAM_ID) { - sample->stream_id = *array; - array--; - } - - if (type & PERF_SAMPLE_ID) { - sample->id = *array; - array--; - } - - if (type & PERF_SAMPLE_TIME) { - sample->time = *array; - array--; - } - - if (type & PERF_SAMPLE_TID) { - u32 *p = (u32 *)array; - sample->pid = p[0]; - sample->tid = p[1]; - } - - return 0; -} - -int event__parse_sample(const event_t *event, struct perf_session *session, - struct sample_data *data) -{ - const u64 *array; - u64 type; - - if (event->header.type != PERF_RECORD_SAMPLE) - return event__parse_id_sample(event, session, data); - - array = event->sample.array; - type = session->sample_type; - - if (type & PERF_SAMPLE_IP) { - data->ip = event->ip.ip; - array++; - } - - if (type & PERF_SAMPLE_TID) { - u32 *p = (u32 *)array; - data->pid = p[0]; - data->tid = p[1]; - array++; - } - - if (type & PERF_SAMPLE_TIME) { - data->time = *array; - array++; - } - - if (type & PERF_SAMPLE_ADDR) { - data->addr = *array; - array++; - } - - data->id = -1ULL; - if (type & PERF_SAMPLE_ID) { - data->id = *array; - array++; - } - - if (type & PERF_SAMPLE_STREAM_ID) { - data->stream_id = *array; - array++; - } - - if (type & PERF_SAMPLE_CPU) { - u32 *p = (u32 *)array; - data->cpu = *p; - array++; - } else - data->cpu = -1; - - if (type & PERF_SAMPLE_PERIOD) { - data->period = *array; - array++; - } - - if (type & PERF_SAMPLE_READ) { - pr_debug("PERF_SAMPLE_READ is unsuported for now\n"); - return -1; - } - - if (type & PERF_SAMPLE_CALLCHAIN) { - data->callchain = (struct ip_callchain *)array; - array += 1 + data->callchain->nr; - } - - if (type & PERF_SAMPLE_RAW) { - u32 *p = (u32 *)array; - data->raw_size = *p; - p++; - data->raw_data = p; - } - - return 0; -} diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 2b7e919..9c35170 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -61,7 +61,7 @@ struct sample_event { u64 array[]; }; -struct sample_data { +struct perf_sample { u64 ip; u32 pid, tid; u64 time; @@ -117,7 +117,7 @@ struct tracing_data_event { u32 size; }; -typedef union event_union { +union perf_event { struct perf_event_header header; struct ip_event ip; struct mmap_event mmap; @@ -130,48 +130,54 @@ typedef union event_union { struct event_type_event event_type; struct tracing_data_event tracing_data; struct build_id_event build_id; -} event_t; +}; -void event__print_totals(void); +void perf_event__print_totals(void); struct perf_session; +struct thread_map; -typedef int (*event__handler_synth_t)(event_t *event, +typedef int (*perf_event__handler_synth_t)(union perf_event *event, + struct perf_session *session); +typedef int (*perf_event__handler_t)(union perf_event *event, + struct perf_sample *sample, struct perf_session *session); -typedef int (*event__handler_t)(event_t *event, struct sample_data *sample, - struct perf_session *session); -int event__synthesize_thread(pid_t pid, event__handler_t process, +int perf_event__synthesize_thread_map(struct thread_map *threads, + perf_event__handler_t process, + struct perf_session *session); +int perf_event__synthesize_threads(perf_event__handler_t process, + struct perf_session *session); +int perf_event__synthesize_kernel_mmap(perf_event__handler_t process, + struct perf_session *session, + struct machine *machine, + const char *symbol_name); + +int perf_event__synthesize_modules(perf_event__handler_t process, + struct perf_session *session, + struct machine *machine); + +int perf_event__process_comm(union perf_event *event, struct perf_sample *sample, struct perf_session *session); -int event__synthesize_threads(event__handler_t process, - struct perf_session *session); -int event__synthesize_kernel_mmap(event__handler_t process, - struct perf_session *session, - struct machine *machine, - const char *symbol_name); - -int event__synthesize_modules(event__handler_t process, - struct perf_session *session, - struct machine *machine); - -int event__process_comm(event_t *self, struct sample_data *sample, - struct perf_session *session); -int event__process_lost(event_t *self, struct sample_data *sample, - struct perf_session *session); -int event__process_mmap(event_t *self, struct sample_data *sample, - struct perf_session *session); -int event__process_task(event_t *self, struct sample_data *sample, +int perf_event__process_lost(union perf_event *event, struct perf_sample *sample, + struct perf_session *session); +int perf_event__process_mmap(union perf_event *event, struct perf_sample *sample, + struct perf_session *session); +int perf_event__process_task(union perf_event *event, struct perf_sample *sample, + struct perf_session *session); +int perf_event__process(union perf_event *event, struct perf_sample *sample, struct perf_session *session); -int event__process(event_t *event, struct sample_data *sample, - struct perf_session *session); struct addr_location; -int event__preprocess_sample(const event_t *self, struct perf_session *session, - struct addr_location *al, struct sample_data *data, - symbol_filter_t filter); -int event__parse_sample(const event_t *event, struct perf_session *session, - struct sample_data *sample); +int perf_event__preprocess_sample(const union perf_event *self, + struct perf_session *session, + struct addr_location *al, + struct perf_sample *sample, + symbol_filter_t filter); + +const char *perf_event__name(unsigned int id); -const char *event__get_event_name(unsigned int id); +int perf_event__parse_sample(const union perf_event *event, u64 type, + bool sample_id_all, struct perf_sample *sample); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c new file mode 100644 index 0000000..d852cef --- /dev/null +++ b/tools/perf/util/evlist.c @@ -0,0 +1,394 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-{top,stat,record}.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include <poll.h> +#include "cpumap.h" +#include "thread_map.h" +#include "evlist.h" +#include "evsel.h" +#include "util.h" + +#include <sys/mman.h> + +#include <linux/bitops.h> +#include <linux/hash.h> + +#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) + +void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads) +{ + int i; + + for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) + INIT_HLIST_HEAD(&evlist->heads[i]); + INIT_LIST_HEAD(&evlist->entries); + perf_evlist__set_maps(evlist, cpus, threads); +} + +struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, + struct thread_map *threads) +{ + struct perf_evlist *evlist = zalloc(sizeof(*evlist)); + + if (evlist != NULL) + perf_evlist__init(evlist, cpus, threads); + + return evlist; +} + +static void perf_evlist__purge(struct perf_evlist *evlist) +{ + struct perf_evsel *pos, *n; + + list_for_each_entry_safe(pos, n, &evlist->entries, node) { + list_del_init(&pos->node); + perf_evsel__delete(pos); + } + + evlist->nr_entries = 0; +} + +void perf_evlist__exit(struct perf_evlist *evlist) +{ + free(evlist->mmap); + free(evlist->pollfd); + evlist->mmap = NULL; + evlist->pollfd = NULL; +} + +void perf_evlist__delete(struct perf_evlist *evlist) +{ + perf_evlist__purge(evlist); + perf_evlist__exit(evlist); + free(evlist); +} + +void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry) +{ + list_add_tail(&entry->node, &evlist->entries); + ++evlist->nr_entries; +} + +int perf_evlist__add_default(struct perf_evlist *evlist) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + struct perf_evsel *evsel = perf_evsel__new(&attr, 0); + + if (evsel == NULL) + return -ENOMEM; + + perf_evlist__add(evlist, evsel); + return 0; +} + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +{ + int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries; + evlist->pollfd = malloc(sizeof(struct pollfd) * nfds); + return evlist->pollfd != NULL ? 0 : -ENOMEM; +} + +void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd) +{ + fcntl(fd, F_SETFL, O_NONBLOCK); + evlist->pollfd[evlist->nr_fds].fd = fd; + evlist->pollfd[evlist->nr_fds].events = POLLIN; + evlist->nr_fds++; +} + +static void perf_evlist__id_hash(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + int hash; + struct perf_sample_id *sid = SID(evsel, cpu, thread); + + sid->id = id; + sid->evsel = evsel; + hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS); + hlist_add_head(&sid->node, &evlist->heads[hash]); +} + +void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + evsel->id[evsel->ids++] = id; +} + +static int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd) +{ + u64 read_data[4] = { 0, }; + int id_idx = 1; /* The first entry is the counter value */ + + if (!(evsel->attr.read_format & PERF_FORMAT_ID) || + read(fd, &read_data, sizeof(read_data)) == -1) + return -1; + + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + ++id_idx; + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + ++id_idx; + + perf_evlist__id_add(evlist, evsel, cpu, thread, read_data[id_idx]); + return 0; +} + +struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id) +{ + struct hlist_head *head; + struct hlist_node *pos; + struct perf_sample_id *sid; + int hash; + + if (evlist->nr_entries == 1) + return list_entry(evlist->entries.next, struct perf_evsel, node); + + hash = hash_64(id, PERF_EVLIST__HLIST_BITS); + head = &evlist->heads[hash]; + + hlist_for_each_entry(sid, pos, head, node) + if (sid->id == id) + return sid->evsel; + return NULL; +} + +union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu) +{ + /* XXX Move this to perf.c, making it generally available */ + unsigned int page_size = sysconf(_SC_PAGE_SIZE); + struct perf_mmap *md = &evlist->mmap[cpu]; + unsigned int head = perf_mmap__read_head(md); + unsigned int old = md->prev; + unsigned char *data = md->base + page_size; + union perf_event *event = NULL; + + if (evlist->overwrite) { + /* + * If we're further behind than half the buffer, there's a chance + * the writer will bite our tail and mess up the samples under us. + * + * If we somehow ended up ahead of the head, we got messed up. + * + * In either case, truncate and restart at head. + */ + int diff = head - old; + if (diff > md->mask / 2 || diff < 0) { + fprintf(stderr, "WARNING: failed to keep up with mmap data.\n"); + + /* + * head points to a known good entry, start there. + */ + old = head; + } + } + + if (old != head) { + size_t size; + + event = (union perf_event *)&data[old & md->mask]; + size = event->header.size; + + /* + * Event straddles the mmap boundary -- header should always + * be inside due to u64 alignment of output. + */ + if ((old & md->mask) + size != ((old + size) & md->mask)) { + unsigned int offset = old; + unsigned int len = min(sizeof(*event), size), cpy; + void *dst = &evlist->event_copy; + + do { + cpy = min(md->mask + 1 - (offset & md->mask), len); + memcpy(dst, &data[offset & md->mask], cpy); + offset += cpy; + dst += cpy; + len -= cpy; + } while (len); + + event = &evlist->event_copy; + } + + old += size; + } + + md->prev = old; + + if (!evlist->overwrite) + perf_mmap__write_tail(md, old); + + return event; +} + +void perf_evlist__munmap(struct perf_evlist *evlist) +{ + int cpu; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + if (evlist->mmap[cpu].base != NULL) { + munmap(evlist->mmap[cpu].base, evlist->mmap_len); + evlist->mmap[cpu].base = NULL; + } + } +} + +int perf_evlist__alloc_mmap(struct perf_evlist *evlist) +{ + evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap)); + return evlist->mmap != NULL ? 0 : -ENOMEM; +} + +static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot, + int mask, int fd) +{ + evlist->mmap[cpu].prev = 0; + evlist->mmap[cpu].mask = mask; + evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot, + MAP_SHARED, fd, 0); + if (evlist->mmap[cpu].base == MAP_FAILED) + return -1; + + perf_evlist__add_pollfd(evlist, fd); + return 0; +} + +/** perf_evlist__mmap - Create per cpu maps to receive events + * + * @evlist - list of events + * @pages - map length in pages + * @overwrite - overwrite older events? + * + * If overwrite is false the user needs to signal event consuption using: + * + * struct perf_mmap *m = &evlist->mmap[cpu]; + * unsigned int head = perf_mmap__read_head(m); + * + * perf_mmap__write_tail(m, head) + * + * Using perf_evlist__read_on_cpu does this automatically. + */ +int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite) +{ + unsigned int page_size = sysconf(_SC_PAGE_SIZE); + int mask = pages * page_size - 1, cpu; + struct perf_evsel *first_evsel, *evsel; + const struct cpu_map *cpus = evlist->cpus; + const struct thread_map *threads = evlist->threads; + int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE); + + if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0) + return -ENOMEM; + + if (evlist->pollfd == NULL && perf_evlist__alloc_pollfd(evlist) < 0) + return -ENOMEM; + + evlist->overwrite = overwrite; + evlist->mmap_len = (pages + 1) * page_size; + first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node); + + list_for_each_entry(evsel, &evlist->entries, node) { + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + evsel->sample_id == NULL && + perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0) + return -ENOMEM; + + for (cpu = 0; cpu < cpus->nr; cpu++) { + for (thread = 0; thread < threads->nr; thread++) { + int fd = FD(evsel, cpu, thread); + + if (evsel->idx || thread) { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, + FD(first_evsel, cpu, 0)) != 0) + goto out_unmap; + } else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0) + goto out_unmap; + + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0) + goto out_unmap; + } + } + } + + return 0; + +out_unmap: + for (cpu = 0; cpu < cpus->nr; cpu++) { + if (evlist->mmap[cpu].base != NULL) { + munmap(evlist->mmap[cpu].base, evlist->mmap_len); + evlist->mmap[cpu].base = NULL; + } + } + return -1; +} + +int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, + pid_t target_tid, const char *cpu_list) +{ + evlist->threads = thread_map__new(target_pid, target_tid); + + if (evlist->threads == NULL) + return -1; + + if (target_tid != -1) + evlist->cpus = cpu_map__dummy_new(); + else + evlist->cpus = cpu_map__new(cpu_list); + + if (evlist->cpus == NULL) + goto out_delete_threads; + + return 0; + +out_delete_threads: + thread_map__delete(evlist->threads); + return -1; +} + +void perf_evlist__delete_maps(struct perf_evlist *evlist) +{ + cpu_map__delete(evlist->cpus); + thread_map__delete(evlist->threads); + evlist->cpus = NULL; + evlist->threads = NULL; +} + +int perf_evlist__set_filters(struct perf_evlist *evlist) +{ + const struct thread_map *threads = evlist->threads; + const struct cpu_map *cpus = evlist->cpus; + struct perf_evsel *evsel; + char *filter; + int thread; + int cpu; + int err; + int fd; + + list_for_each_entry(evsel, &evlist->entries, node) { + filter = evsel->filter; + if (!filter) + continue; + for (cpu = 0; cpu < cpus->nr; cpu++) { + for (thread = 0; thread < threads->nr; thread++) { + fd = FD(evsel, cpu, thread); + err = ioctl(fd, PERF_EVENT_IOC_SET_FILTER, filter); + if (err) + return err; + } + } + } + + return 0; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h new file mode 100644 index 0000000..8b1cb7a --- /dev/null +++ b/tools/perf/util/evlist.h @@ -0,0 +1,68 @@ +#ifndef __PERF_EVLIST_H +#define __PERF_EVLIST_H 1 + +#include <linux/list.h> +#include "../perf.h" +#include "event.h" + +struct pollfd; +struct thread_map; +struct cpu_map; + +#define PERF_EVLIST__HLIST_BITS 8 +#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) + +struct perf_evlist { + struct list_head entries; + struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; + int nr_entries; + int nr_fds; + int mmap_len; + bool overwrite; + union perf_event event_copy; + struct perf_mmap *mmap; + struct pollfd *pollfd; + struct thread_map *threads; + struct cpu_map *cpus; +}; + +struct perf_evsel; + +struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, + struct thread_map *threads); +void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, + struct thread_map *threads); +void perf_evlist__exit(struct perf_evlist *evlist); +void perf_evlist__delete(struct perf_evlist *evlist); + +void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry); +int perf_evlist__add_default(struct perf_evlist *evlist); + +void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, + int cpu, int thread, u64 id); + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); +void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); + +struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id); + +union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu); + +int perf_evlist__alloc_mmap(struct perf_evlist *evlist); +int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite); +void perf_evlist__munmap(struct perf_evlist *evlist); + +static inline void perf_evlist__set_maps(struct perf_evlist *evlist, + struct cpu_map *cpus, + struct thread_map *threads) +{ + evlist->cpus = cpus; + evlist->threads = threads; +} + +int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid, + pid_t target_tid, const char *cpu_list); +void perf_evlist__delete_maps(struct perf_evlist *evlist); +int perf_evlist__set_filters(struct perf_evlist *evlist); + +#endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f5cfed6..662596a 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1,20 +1,34 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-{top,stat,record}.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + #include "evsel.h" -#include "../perf.h" +#include "evlist.h" #include "util.h" #include "cpumap.h" -#include "thread.h" +#include "thread_map.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) +void perf_evsel__init(struct perf_evsel *evsel, + struct perf_event_attr *attr, int idx) +{ + evsel->idx = idx; + evsel->attr = *attr; + INIT_LIST_HEAD(&evsel->node); +} + struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(sizeof(*evsel)); - if (evsel != NULL) { - evsel->idx = idx; - evsel->attr = *attr; - INIT_LIST_HEAD(&evsel->node); - } + if (evsel != NULL) + perf_evsel__init(evsel, attr, idx); return evsel; } @@ -25,6 +39,22 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) return evsel->fd != NULL ? 0 : -ENOMEM; } +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); + if (evsel->sample_id == NULL) + return -ENOMEM; + + evsel->id = zalloc(ncpus * nthreads * sizeof(u64)); + if (evsel->id == NULL) { + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + return -ENOMEM; + } + + return 0; +} + int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) { evsel->counts = zalloc((sizeof(*evsel->counts) + @@ -38,6 +68,14 @@ void perf_evsel__free_fd(struct perf_evsel *evsel) evsel->fd = NULL; } +void perf_evsel__free_id(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + free(evsel->id); + evsel->id = NULL; +} + void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { int cpu, thread; @@ -49,10 +87,19 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) } } -void perf_evsel__delete(struct perf_evsel *evsel) +void perf_evsel__exit(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); xyarray__delete(evsel->fd); + xyarray__delete(evsel->sample_id); + free(evsel->id); +} + +void perf_evsel__delete(struct perf_evsel *evsel) +{ + perf_evsel__exit(evsel); + close_cgroup(evsel->cgrp); + free(evsel->name); free(evsel); } @@ -90,7 +137,7 @@ int __perf_evsel__read(struct perf_evsel *evsel, int cpu, thread; struct perf_counts_values *aggr = &evsel->counts->aggr, count; - aggr->val = 0; + aggr->val = aggr->ena = aggr->run = 0; for (cpu = 0; cpu < ncpus; cpu++) { for (thread = 0; thread < nthreads; thread++) { @@ -128,21 +175,51 @@ int __perf_evsel__read(struct perf_evsel *evsel, } static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) + struct thread_map *threads, bool group, bool inherit) { int cpu, thread; + unsigned long flags = 0; + int pid = -1; if (evsel->fd == NULL && perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) return -1; + if (evsel->cgrp) { + flags = PERF_FLAG_PID_CGROUP; + pid = evsel->cgrp->fd; + } + for (cpu = 0; cpu < cpus->nr; cpu++) { + int group_fd = -1; + /* + * Don't allow mmap() of inherited per-task counters. This + * would create a performance issue due to all children writing + * to the same buffer. + * + * FIXME: + * Proper fix is not to pass 'inherit' to perf_evsel__open*, + * but a 'flags' parameter, with 'group' folded there as well, + * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if + * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is + * set. Lets go for the minimal fix first tho. + */ + evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit; + for (thread = 0; thread < threads->nr; thread++) { + + if (!evsel->cgrp) + pid = threads->map[thread]; + FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr, - threads->map[thread], - cpus->map[cpu], -1, 0); + pid, + cpus->map[cpu], + group_fd, flags); if (FD(evsel, cpu, thread) < 0) goto out_close; + + if (group && group_fd == -1) + group_fd = FD(evsel, cpu, thread); } } @@ -175,10 +252,9 @@ static struct { .threads = { -1, }, }; -int perf_evsel__open(struct perf_evsel *evsel, - struct cpu_map *cpus, struct thread_map *threads) +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads, bool group, bool inherit) { - if (cpus == NULL) { /* Work around old compiler warnings about strict aliasing */ cpus = &empty_cpu_map.map; @@ -187,15 +263,135 @@ int perf_evsel__open(struct perf_evsel *evsel, if (threads == NULL) threads = &empty_thread_map.map; - return __perf_evsel__open(evsel, cpus, threads); + return __perf_evsel__open(evsel, cpus, threads, group, inherit); } -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus) +int perf_evsel__open_per_cpu(struct perf_evsel *evsel, + struct cpu_map *cpus, bool group, bool inherit) { - return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); + return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit); +} + +int perf_evsel__open_per_thread(struct perf_evsel *evsel, + struct thread_map *threads, bool group, bool inherit) +{ + return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit); +} + +static int perf_event__parse_id_sample(const union perf_event *event, u64 type, + struct perf_sample *sample) +{ + const u64 *array = event->sample.array; + + array += ((event->header.size - + sizeof(event->header)) / sizeof(u64)) - 1; + + if (type & PERF_SAMPLE_CPU) { + u32 *p = (u32 *)array; + sample->cpu = *p; + array--; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + sample->stream_id = *array; + array--; + } + + if (type & PERF_SAMPLE_ID) { + sample->id = *array; + array--; + } + + if (type & PERF_SAMPLE_TIME) { + sample->time = *array; + array--; + } + + if (type & PERF_SAMPLE_TID) { + u32 *p = (u32 *)array; + sample->pid = p[0]; + sample->tid = p[1]; + } + + return 0; } -int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads) +int perf_event__parse_sample(const union perf_event *event, u64 type, + bool sample_id_all, struct perf_sample *data) { - return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); + const u64 *array; + + data->cpu = data->pid = data->tid = -1; + data->stream_id = data->id = data->time = -1ULL; + + if (event->header.type != PERF_RECORD_SAMPLE) { + if (!sample_id_all) + return 0; + return perf_event__parse_id_sample(event, type, data); + } + + array = event->sample.array; + + if (type & PERF_SAMPLE_IP) { + data->ip = event->ip.ip; + array++; + } + + if (type & PERF_SAMPLE_TID) { + u32 *p = (u32 *)array; + data->pid = p[0]; + data->tid = p[1]; + array++; + } + + if (type & PERF_SAMPLE_TIME) { + data->time = *array; + array++; + } + + if (type & PERF_SAMPLE_ADDR) { + data->addr = *array; + array++; + } + + data->id = -1ULL; + if (type & PERF_SAMPLE_ID) { + data->id = *array; + array++; + } + + if (type & PERF_SAMPLE_STREAM_ID) { + data->stream_id = *array; + array++; + } + + if (type & PERF_SAMPLE_CPU) { + u32 *p = (u32 *)array; + data->cpu = *p; + array++; + } + + if (type & PERF_SAMPLE_PERIOD) { + data->period = *array; + array++; + } + + if (type & PERF_SAMPLE_READ) { + fprintf(stderr, "PERF_SAMPLE_READ is unsuported for now\n"); + return -1; + } + + if (type & PERF_SAMPLE_CALLCHAIN) { + data->callchain = (struct ip_callchain *)array; + array += 1 + data->callchain->nr; + } + + if (type & PERF_SAMPLE_RAW) { + u32 *p = (u32 *)array; + data->raw_size = *p; + p++; + data->raw_data = p; + } + + return 0; } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index b2d755f..6710ab5 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -6,6 +6,8 @@ #include "../../../include/linux/perf_event.h" #include "types.h" #include "xyarray.h" +#include "cgroup.h" +#include "hist.h" struct perf_counts_values { union { @@ -24,31 +26,66 @@ struct perf_counts { struct perf_counts_values cpu[]; }; +struct perf_evsel; + +/* + * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are + * more than one entry in the evlist. + */ +struct perf_sample_id { + struct hlist_node node; + u64 id; + struct perf_evsel *evsel; +}; + +/** struct perf_evsel - event selector + * + * @name - Can be set to retain the original event name passed by the user, + * so that when showing results in tools such as 'perf stat', we + * show the name used, not some alias. + */ struct perf_evsel { struct list_head node; struct perf_event_attr attr; char *filter; struct xyarray *fd; + struct xyarray *sample_id; + u64 *id; struct perf_counts *counts; int idx; - void *priv; + int ids; + struct hists hists; + char *name; + union { + void *priv; + off_t id_offset; + }; + struct cgroup_sel *cgrp; }; struct cpu_map; struct thread_map; +struct perf_evlist; struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx); +void perf_evsel__init(struct perf_evsel *evsel, + struct perf_event_attr *attr, int idx); +void perf_evsel__exit(struct perf_evsel *evsel); void perf_evsel__delete(struct perf_evsel *evsel); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__free_fd(struct perf_evsel *evsel); +void perf_evsel__free_id(struct perf_evsel *evsel); void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); -int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus); -int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads); -int perf_evsel__open(struct perf_evsel *evsel, - struct cpu_map *cpus, struct thread_map *threads); +int perf_evsel__open_per_cpu(struct perf_evsel *evsel, + struct cpu_map *cpus, bool group, bool inherit); +int perf_evsel__open_per_thread(struct perf_evsel *evsel, + struct thread_map *threads, bool group, bool inherit); +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads, bool group, bool inherit); #define perf_evsel__match(evsel, t, c) \ (evsel->attr.type == PERF_TYPE_##t && \ diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c index 67eeff5..7adf4ad 100644 --- a/tools/perf/util/exec_cmd.c +++ b/tools/perf/util/exec_cmd.c @@ -11,31 +11,12 @@ static const char *argv0_path; const char *system_path(const char *path) { -#ifdef RUNTIME_PREFIX - static const char *prefix; -#else static const char *prefix = PREFIX; -#endif struct strbuf d = STRBUF_INIT; if (is_absolute_path(path)) return path; -#ifdef RUNTIME_PREFIX - assert(argv0_path); - assert(is_absolute_path(argv0_path)); - - if (!prefix && - !(prefix = strip_path_suffix(argv0_path, PERF_EXEC_PATH)) && - !(prefix = strip_path_suffix(argv0_path, BINDIR)) && - !(prefix = strip_path_suffix(argv0_path, "perf"))) { - prefix = PREFIX; - fprintf(stderr, "RUNTIME_PREFIX requested, " - "but prefix computation failed. " - "Using static fallback '%s'.\n", prefix); - } -#endif - strbuf_addf(&d, "%s/%s", prefix, path); path = strbuf_detach(&d, NULL); return path; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index f6a929e..e5230c0 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -8,6 +8,8 @@ #include <linux/list.h> #include <linux/kernel.h> +#include "evlist.h" +#include "evsel.h" #include "util.h" #include "header.h" #include "../perf.h" @@ -18,89 +20,6 @@ static bool no_buildid_cache = false; -/* - * Create new perf.data header attribute: - */ -struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr) -{ - struct perf_header_attr *self = malloc(sizeof(*self)); - - if (self != NULL) { - self->attr = *attr; - self->ids = 0; - self->size = 1; - self->id = malloc(sizeof(u64)); - if (self->id == NULL) { - free(self); - self = NULL; - } - } - - return self; -} - -void perf_header_attr__delete(struct perf_header_attr *self) -{ - free(self->id); - free(self); -} - -int perf_header_attr__add_id(struct perf_header_attr *self, u64 id) -{ - int pos = self->ids; - - self->ids++; - if (self->ids > self->size) { - int nsize = self->size * 2; - u64 *nid = realloc(self->id, nsize * sizeof(u64)); - - if (nid == NULL) - return -1; - - self->size = nsize; - self->id = nid; - } - self->id[pos] = id; - return 0; -} - -int perf_header__init(struct perf_header *self) -{ - self->size = 1; - self->attr = malloc(sizeof(void *)); - return self->attr == NULL ? -ENOMEM : 0; -} - -void perf_header__exit(struct perf_header *self) -{ - int i; - for (i = 0; i < self->attrs; ++i) - perf_header_attr__delete(self->attr[i]); - free(self->attr); -} - -int perf_header__add_attr(struct perf_header *self, - struct perf_header_attr *attr) -{ - if (self->frozen) - return -1; - - if (self->attrs == self->size) { - int nsize = self->size * 2; - struct perf_header_attr **nattr; - - nattr = realloc(self->attr, nsize * sizeof(void *)); - if (nattr == NULL) - return -1; - - self->size = nsize; - self->attr = nattr; - } - - self->attr[self->attrs++] = attr; - return 0; -} - static int event_count; static struct perf_trace_event_type *events; @@ -147,19 +66,19 @@ struct perf_file_attr { struct perf_file_section ids; }; -void perf_header__set_feat(struct perf_header *self, int feat) +void perf_header__set_feat(struct perf_header *header, int feat) { - set_bit(feat, self->adds_features); + set_bit(feat, header->adds_features); } -void perf_header__clear_feat(struct perf_header *self, int feat) +void perf_header__clear_feat(struct perf_header *header, int feat) { - clear_bit(feat, self->adds_features); + clear_bit(feat, header->adds_features); } -bool perf_header__has_feat(const struct perf_header *self, int feat) +bool perf_header__has_feat(const struct perf_header *header, int feat) { - return test_bit(feat, self->adds_features); + return test_bit(feat, header->adds_features); } static int do_write(int fd, const void *buf, size_t size) @@ -228,22 +147,22 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, return 0; } -static int machine__write_buildid_table(struct machine *self, int fd) +static int machine__write_buildid_table(struct machine *machine, int fd) { int err; u16 kmisc = PERF_RECORD_MISC_KERNEL, umisc = PERF_RECORD_MISC_USER; - if (!machine__is_host(self)) { + if (!machine__is_host(machine)) { kmisc = PERF_RECORD_MISC_GUEST_KERNEL; umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&self->kernel_dsos, self->pid, + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&self->user_dsos, - self->pid, umisc, fd); + err = __dsos__write_buildid_table(&machine->user_dsos, + machine->pid, umisc, fd); return err; } @@ -270,11 +189,15 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms) { const size_t size = PATH_MAX; - char *realname = realpath(name, NULL), - *filename = malloc(size), + char *realname, *filename = malloc(size), *linkname = malloc(size), *targetname; int len, err = -1; + if (is_kallsyms) + realname = (char *)name; + else + realname = realpath(name, NULL); + if (realname == NULL || filename == NULL || linkname == NULL) goto out_free; @@ -306,7 +229,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, if (symlink(targetname, linkname) == 0) err = 0; out_free: - free(realname); + if (!is_kallsyms) + free(realname); free(filename); free(linkname); return err; @@ -361,12 +285,12 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *self, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, const char *debugdir) { - bool is_kallsyms = self->kernel && self->long_name[0] != '/'; + bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; - return build_id_cache__add_b(self->build_id, sizeof(self->build_id), - self->long_name, debugdir, is_kallsyms); + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), + dso->long_name, debugdir, is_kallsyms); } static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) @@ -381,14 +305,14 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) return err; } -static int machine__cache_build_ids(struct machine *self, const char *debugdir) +static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&self->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&self->user_dsos, debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); return ret; } -static int perf_session__cache_build_ids(struct perf_session *self) +static int perf_session__cache_build_ids(struct perf_session *session) { struct rb_node *nd; int ret; @@ -399,28 +323,28 @@ static int perf_session__cache_build_ids(struct perf_session *self) if (mkdir(debugdir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&self->host_machine, debugdir); + ret = machine__cache_build_ids(&session->host_machine, debugdir); - for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__cache_build_ids(pos, debugdir); } return ret ? -1 : 0; } -static bool machine__read_build_ids(struct machine *self, bool with_hits) +static bool machine__read_build_ids(struct machine *machine, bool with_hits) { - bool ret = __dsos__read_build_ids(&self->kernel_dsos, with_hits); - ret |= __dsos__read_build_ids(&self->user_dsos, with_hits); + bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits); + ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits); return ret; } -static bool perf_session__read_build_ids(struct perf_session *self, bool with_hits) +static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits) { struct rb_node *nd; - bool ret = machine__read_build_ids(&self->host_machine, with_hits); + bool ret = machine__read_build_ids(&session->host_machine, with_hits); - for (nd = rb_first(&self->machines); nd; nd = rb_next(nd)) { + for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) { struct machine *pos = rb_entry(nd, struct machine, rb_node); ret |= machine__read_build_ids(pos, with_hits); } @@ -428,7 +352,8 @@ static bool perf_session__read_build_ids(struct perf_session *self, bool with_hi return ret; } -static int perf_header__adds_write(struct perf_header *self, int fd) +static int perf_header__adds_write(struct perf_header *header, + struct perf_evlist *evlist, int fd) { int nr_sections; struct perf_session *session; @@ -437,13 +362,13 @@ static int perf_header__adds_write(struct perf_header *self, int fd) u64 sec_start; int idx = 0, err; - session = container_of(self, struct perf_session, header); + session = container_of(header, struct perf_session, header); - if (perf_header__has_feat(self, HEADER_BUILD_ID && + if (perf_header__has_feat(header, HEADER_BUILD_ID && !perf_session__read_build_ids(session, true))) - perf_header__clear_feat(self, HEADER_BUILD_ID); + perf_header__clear_feat(header, HEADER_BUILD_ID); - nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; @@ -453,28 +378,28 @@ static int perf_header__adds_write(struct perf_header *self, int fd) sec_size = sizeof(*feat_sec) * nr_sections; - sec_start = self->data_offset + self->data_size; + sec_start = header->data_offset + header->data_size; lseek(fd, sec_start + sec_size, SEEK_SET); - if (perf_header__has_feat(self, HEADER_TRACE_INFO)) { + if (perf_header__has_feat(header, HEADER_TRACE_INFO)) { struct perf_file_section *trace_sec; trace_sec = &feat_sec[idx++]; /* Write trace info */ trace_sec->offset = lseek(fd, 0, SEEK_CUR); - read_tracing_data(fd, &evsel_list); + read_tracing_data(fd, &evlist->entries); trace_sec->size = lseek(fd, 0, SEEK_CUR) - trace_sec->offset; } - if (perf_header__has_feat(self, HEADER_BUILD_ID)) { + if (perf_header__has_feat(header, HEADER_BUILD_ID)) { struct perf_file_section *buildid_sec; buildid_sec = &feat_sec[idx++]; /* Write build-ids */ buildid_sec->offset = lseek(fd, 0, SEEK_CUR); - err = dsos__write_buildid_table(self, fd); + err = dsos__write_buildid_table(header, fd); if (err < 0) { pr_debug("failed to write buildid table\n"); goto out_free; @@ -513,32 +438,41 @@ int perf_header__write_pipe(int fd) return 0; } -int perf_header__write(struct perf_header *self, int fd, bool at_exit) +int perf_session__write_header(struct perf_session *session, + struct perf_evlist *evlist, + int fd, bool at_exit) { struct perf_file_header f_header; struct perf_file_attr f_attr; - struct perf_header_attr *attr; - int i, err; + struct perf_header *header = &session->header; + struct perf_evsel *attr, *pair = NULL; + int err; lseek(fd, sizeof(f_header), SEEK_SET); - for (i = 0; i < self->attrs; i++) { - attr = self->attr[i]; + if (session->evlist != evlist) + pair = list_entry(session->evlist->entries.next, struct perf_evsel, node); + list_for_each_entry(attr, &evlist->entries, node) { attr->id_offset = lseek(fd, 0, SEEK_CUR); err = do_write(fd, attr->id, attr->ids * sizeof(u64)); if (err < 0) { +out_err_write: pr_debug("failed to write perf header\n"); return err; } + if (session->evlist != evlist) { + err = do_write(fd, pair->id, pair->ids * sizeof(u64)); + if (err < 0) + goto out_err_write; + attr->ids += pair->ids; + pair = list_entry(pair->node.next, struct perf_evsel, node); + } } + header->attr_offset = lseek(fd, 0, SEEK_CUR); - self->attr_offset = lseek(fd, 0, SEEK_CUR); - - for (i = 0; i < self->attrs; i++) { - attr = self->attr[i]; - + list_for_each_entry(attr, &evlist->entries, node) { f_attr = (struct perf_file_attr){ .attr = attr->attr, .ids = { @@ -553,20 +487,20 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit) } } - self->event_offset = lseek(fd, 0, SEEK_CUR); - self->event_size = event_count * sizeof(struct perf_trace_event_type); + header->event_offset = lseek(fd, 0, SEEK_CUR); + header->event_size = event_count * sizeof(struct perf_trace_event_type); if (events) { - err = do_write(fd, events, self->event_size); + err = do_write(fd, events, header->event_size); if (err < 0) { pr_debug("failed to write perf header events\n"); return err; } } - self->data_offset = lseek(fd, 0, SEEK_CUR); + header->data_offset = lseek(fd, 0, SEEK_CUR); if (at_exit) { - err = perf_header__adds_write(self, fd); + err = perf_header__adds_write(header, evlist, fd); if (err < 0) return err; } @@ -576,20 +510,20 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit) .size = sizeof(f_header), .attr_size = sizeof(f_attr), .attrs = { - .offset = self->attr_offset, - .size = self->attrs * sizeof(f_attr), + .offset = header->attr_offset, + .size = evlist->nr_entries * sizeof(f_attr), }, .data = { - .offset = self->data_offset, - .size = self->data_size, + .offset = header->data_offset, + .size = header->data_size, }, .event_types = { - .offset = self->event_offset, - .size = self->event_size, + .offset = header->event_offset, + .size = header->event_size, }, }; - memcpy(&f_header.adds_features, &self->adds_features, sizeof(self->adds_features)); + memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features)); lseek(fd, 0, SEEK_SET); err = do_write(fd, &f_header, sizeof(f_header)); @@ -597,26 +531,26 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit) pr_debug("failed to write perf header\n"); return err; } - lseek(fd, self->data_offset + self->data_size, SEEK_SET); + lseek(fd, header->data_offset + header->data_size, SEEK_SET); - self->frozen = 1; + header->frozen = 1; return 0; } -static int perf_header__getbuffer64(struct perf_header *self, +static int perf_header__getbuffer64(struct perf_header *header, int fd, void *buf, size_t size) { if (readn(fd, buf, size) <= 0) return -1; - if (self->needs_swap) + if (header->needs_swap) mem_bswap_64(buf, size); return 0; } -int perf_header__process_sections(struct perf_header *self, int fd, - int (*process)(struct perf_file_section *self, +int perf_header__process_sections(struct perf_header *header, int fd, + int (*process)(struct perf_file_section *section, struct perf_header *ph, int feat, int fd)) { @@ -626,7 +560,7 @@ int perf_header__process_sections(struct perf_header *self, int fd, int idx = 0; int err = -1, feat = 1; - nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS); + nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; @@ -636,17 +570,17 @@ int perf_header__process_sections(struct perf_header *self, int fd, sec_size = sizeof(*feat_sec) * nr_sections; - lseek(fd, self->data_offset + self->data_size, SEEK_SET); + lseek(fd, header->data_offset + header->data_size, SEEK_SET); - if (perf_header__getbuffer64(self, fd, feat_sec, sec_size)) + if (perf_header__getbuffer64(header, fd, feat_sec, sec_size)) goto out_free; err = 0; while (idx < nr_sections && feat < HEADER_LAST_FEATURE) { - if (perf_header__has_feat(self, feat)) { + if (perf_header__has_feat(header, feat)) { struct perf_file_section *sec = &feat_sec[idx++]; - err = process(sec, self, feat, fd); + err = process(sec, header, feat, fd); if (err < 0) break; } @@ -657,35 +591,35 @@ out_free: return err; } -int perf_file_header__read(struct perf_file_header *self, +int perf_file_header__read(struct perf_file_header *header, struct perf_header *ph, int fd) { lseek(fd, 0, SEEK_SET); - if (readn(fd, self, sizeof(*self)) <= 0 || - memcmp(&self->magic, __perf_magic, sizeof(self->magic))) + if (readn(fd, header, sizeof(*header)) <= 0 || + memcmp(&header->magic, __perf_magic, sizeof(header->magic))) return -1; - if (self->attr_size != sizeof(struct perf_file_attr)) { - u64 attr_size = bswap_64(self->attr_size); + if (header->attr_size != sizeof(struct perf_file_attr)) { + u64 attr_size = bswap_64(header->attr_size); if (attr_size != sizeof(struct perf_file_attr)) return -1; - mem_bswap_64(self, offsetof(struct perf_file_header, + mem_bswap_64(header, offsetof(struct perf_file_header, adds_features)); ph->needs_swap = true; } - if (self->size != sizeof(*self)) { + if (header->size != sizeof(*header)) { /* Support the previous format */ - if (self->size == offsetof(typeof(*self), adds_features)) - bitmap_zero(self->adds_features, HEADER_FEAT_BITS); + if (header->size == offsetof(typeof(*header), adds_features)) + bitmap_zero(header->adds_features, HEADER_FEAT_BITS); else return -1; } - memcpy(&ph->adds_features, &self->adds_features, + memcpy(&ph->adds_features, &header->adds_features, sizeof(ph->adds_features)); /* * FIXME: hack that assumes that if we need swap the perf.data file @@ -699,10 +633,10 @@ int perf_file_header__read(struct perf_file_header *self, perf_header__set_feat(ph, HEADER_BUILD_ID); } - ph->event_offset = self->event_types.offset; - ph->event_size = self->event_types.size; - ph->data_offset = self->data.offset; - ph->data_size = self->data.size; + ph->event_offset = header->event_types.offset; + ph->event_size = header->event_types.size; + ph->data_offset = header->data.offset; + ph->data_size = header->data.size; return 0; } @@ -761,11 +695,10 @@ out: return err; } -static int perf_header__read_build_ids(struct perf_header *self, - int input, u64 offset, u64 size) +static int perf_header__read_build_ids(struct perf_header *header, + int input, u64 offset, u64 size) { - struct perf_session *session = container_of(self, - struct perf_session, header); + struct perf_session *session = container_of(header, struct perf_session, header); struct build_id_event bev; char filename[PATH_MAX]; u64 limit = offset + size; @@ -777,7 +710,7 @@ static int perf_header__read_build_ids(struct perf_header *self, if (read(input, &bev, sizeof(bev)) != sizeof(bev)) goto out; - if (self->needs_swap) + if (header->needs_swap) perf_event_header__bswap(&bev.header); len = bev.header.size - sizeof(bev); @@ -793,13 +726,13 @@ out: return err; } -static int perf_file_section__process(struct perf_file_section *self, +static int perf_file_section__process(struct perf_file_section *section, struct perf_header *ph, int feat, int fd) { - if (lseek(fd, self->offset, SEEK_SET) == (off_t)-1) { + if (lseek(fd, section->offset, SEEK_SET) == (off_t)-1) { pr_debug("Failed to lseek to %" PRIu64 " offset for feature " - "%d, continuing...\n", self->offset, feat); + "%d, continuing...\n", section->offset, feat); return 0; } @@ -809,7 +742,7 @@ static int perf_file_section__process(struct perf_file_section *self, break; case HEADER_BUILD_ID: - if (perf_header__read_build_ids(ph, fd, self->offset, self->size)) + if (perf_header__read_build_ids(ph, fd, section->offset, section->size)) pr_debug("Failed to read buildids, continuing...\n"); break; default: @@ -819,21 +752,21 @@ static int perf_file_section__process(struct perf_file_section *self, return 0; } -static int perf_file_header__read_pipe(struct perf_pipe_file_header *self, +static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, struct perf_header *ph, int fd, bool repipe) { - if (readn(fd, self, sizeof(*self)) <= 0 || - memcmp(&self->magic, __perf_magic, sizeof(self->magic))) + if (readn(fd, header, sizeof(*header)) <= 0 || + memcmp(&header->magic, __perf_magic, sizeof(header->magic))) return -1; - if (repipe && do_write(STDOUT_FILENO, self, sizeof(*self)) < 0) + if (repipe && do_write(STDOUT_FILENO, header, sizeof(*header)) < 0) return -1; - if (self->size != sizeof(*self)) { - u64 size = bswap_64(self->size); + if (header->size != sizeof(*header)) { + u64 size = bswap_64(header->size); - if (size != sizeof(*self)) + if (size != sizeof(*header)) return -1; ph->needs_swap = true; @@ -844,10 +777,10 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *self, static int perf_header__read_pipe(struct perf_session *session, int fd) { - struct perf_header *self = &session->header; + struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, self, fd, + if (perf_file_header__read_pipe(&f_header, header, fd, session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; @@ -858,18 +791,22 @@ static int perf_header__read_pipe(struct perf_session *session, int fd) return 0; } -int perf_header__read(struct perf_session *session, int fd) +int perf_session__read_header(struct perf_session *session, int fd) { - struct perf_header *self = &session->header; + struct perf_header *header = &session->header; struct perf_file_header f_header; struct perf_file_attr f_attr; u64 f_id; int nr_attrs, nr_ids, i, j; + session->evlist = perf_evlist__new(NULL, NULL); + if (session->evlist == NULL) + return -ENOMEM; + if (session->fd_pipe) return perf_header__read_pipe(session, fd); - if (perf_file_header__read(&f_header, self, fd) < 0) { + if (perf_file_header__read(&f_header, header, fd) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; } @@ -878,33 +815,39 @@ int perf_header__read(struct perf_session *session, int fd) lseek(fd, f_header.attrs.offset, SEEK_SET); for (i = 0; i < nr_attrs; i++) { - struct perf_header_attr *attr; + struct perf_evsel *evsel; off_t tmp; - if (perf_header__getbuffer64(self, fd, &f_attr, sizeof(f_attr))) + if (perf_header__getbuffer64(header, fd, &f_attr, sizeof(f_attr))) goto out_errno; tmp = lseek(fd, 0, SEEK_CUR); + evsel = perf_evsel__new(&f_attr.attr, i); - attr = perf_header_attr__new(&f_attr.attr); - if (attr == NULL) - return -ENOMEM; + if (evsel == NULL) + goto out_delete_evlist; + /* + * Do it before so that if perf_evsel__alloc_id fails, this + * entry gets purged too at perf_evlist__delete(). + */ + perf_evlist__add(session->evlist, evsel); nr_ids = f_attr.ids.size / sizeof(u64); + /* + * We don't have the cpu and thread maps on the header, so + * for allocating the perf_sample_id table we fake 1 cpu and + * hattr->ids threads. + */ + if (perf_evsel__alloc_id(evsel, 1, nr_ids)) + goto out_delete_evlist; + lseek(fd, f_attr.ids.offset, SEEK_SET); for (j = 0; j < nr_ids; j++) { - if (perf_header__getbuffer64(self, fd, &f_id, sizeof(f_id))) + if (perf_header__getbuffer64(header, fd, &f_id, sizeof(f_id))) goto out_errno; - if (perf_header_attr__add_id(attr, f_id) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; - } - } - if (perf_header__add_attr(self, attr) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; + perf_evlist__id_add(session->evlist, evsel, 0, j, f_id); } lseek(fd, tmp, SEEK_SET); @@ -915,93 +858,63 @@ int perf_header__read(struct perf_session *session, int fd) events = malloc(f_header.event_types.size); if (events == NULL) return -ENOMEM; - if (perf_header__getbuffer64(self, fd, events, + if (perf_header__getbuffer64(header, fd, events, f_header.event_types.size)) goto out_errno; event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type); } - perf_header__process_sections(self, fd, perf_file_section__process); + perf_header__process_sections(header, fd, perf_file_section__process); - lseek(fd, self->data_offset, SEEK_SET); + lseek(fd, header->data_offset, SEEK_SET); - self->frozen = 1; + header->frozen = 1; return 0; out_errno: return -errno; + +out_delete_evlist: + perf_evlist__delete(session->evlist); + session->evlist = NULL; + return -ENOMEM; } -u64 perf_header__sample_type(struct perf_header *header) +u64 perf_evlist__sample_type(struct perf_evlist *evlist) { + struct perf_evsel *pos; u64 type = 0; - int i; - - for (i = 0; i < header->attrs; i++) { - struct perf_header_attr *attr = header->attr[i]; + list_for_each_entry(pos, &evlist->entries, node) { if (!type) - type = attr->attr.sample_type; - else if (type != attr->attr.sample_type) + type = pos->attr.sample_type; + else if (type != pos->attr.sample_type) die("non matching sample_type"); } return type; } -bool perf_header__sample_id_all(const struct perf_header *header) +bool perf_evlist__sample_id_all(const struct perf_evlist *evlist) { bool value = false, first = true; - int i; - - for (i = 0; i < header->attrs; i++) { - struct perf_header_attr *attr = header->attr[i]; + struct perf_evsel *pos; + list_for_each_entry(pos, &evlist->entries, node) { if (first) { - value = attr->attr.sample_id_all; + value = pos->attr.sample_id_all; first = false; - } else if (value != attr->attr.sample_id_all) + } else if (value != pos->attr.sample_id_all) die("non matching sample_id_all"); } return value; } -struct perf_event_attr * -perf_header__find_attr(u64 id, struct perf_header *header) -{ - int i; - - /* - * We set id to -1 if the data file doesn't contain sample - * ids. This can happen when the data file contains one type - * of event and in that case, the header can still store the - * event attribute information. Check for this and avoid - * walking through the entire list of ids which may be large. - */ - if (id == -1ULL) { - if (header->attrs > 0) - return &header->attr[0]->attr; - return NULL; - } - - for (i = 0; i < header->attrs; i++) { - struct perf_header_attr *attr = header->attr[i]; - int j; - - for (j = 0; j < attr->ids; j++) { - if (attr->id[j] == id) - return &attr->attr; - } - } - - return NULL; -} - -int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, - event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, + perf_event__handler_t process, + struct perf_session *session) { - event_t *ev; + union perf_event *ev; size_t size; int err; @@ -1028,17 +941,15 @@ int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, return err; } -int event__synthesize_attrs(struct perf_header *self, event__handler_t process, - struct perf_session *session) +int perf_session__synthesize_attrs(struct perf_session *session, + perf_event__handler_t process) { - struct perf_header_attr *attr; - int i, err = 0; - - for (i = 0; i < self->attrs; i++) { - attr = self->attr[i]; + struct perf_evsel *attr; + int err = 0; - err = event__synthesize_attr(&attr->attr, attr->ids, attr->id, - process, session); + list_for_each_entry(attr, &session->evlist->entries, node) { + err = perf_event__synthesize_attr(&attr->attr, attr->ids, + attr->id, process, session); if (err) { pr_debug("failed to create perf header attribute\n"); return err; @@ -1048,29 +959,39 @@ int event__synthesize_attrs(struct perf_header *self, event__handler_t process, return err; } -int event__process_attr(event_t *self, struct perf_session *session) +int perf_event__process_attr(union perf_event *event, + struct perf_session *session) { - struct perf_header_attr *attr; unsigned int i, ids, n_ids; + struct perf_evsel *evsel; + + if (session->evlist == NULL) { + session->evlist = perf_evlist__new(NULL, NULL); + if (session->evlist == NULL) + return -ENOMEM; + } - attr = perf_header_attr__new(&self->attr.attr); - if (attr == NULL) + evsel = perf_evsel__new(&event->attr.attr, + session->evlist->nr_entries); + if (evsel == NULL) return -ENOMEM; - ids = self->header.size; - ids -= (void *)&self->attr.id - (void *)self; + perf_evlist__add(session->evlist, evsel); + + ids = event->header.size; + ids -= (void *)&event->attr.id - (void *)event; n_ids = ids / sizeof(u64); + /* + * We don't have the cpu and thread maps on the header, so + * for allocating the perf_sample_id table we fake 1 cpu and + * hattr->ids threads. + */ + if (perf_evsel__alloc_id(evsel, 1, n_ids)) + return -ENOMEM; for (i = 0; i < n_ids; i++) { - if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; - } - } - - if (perf_header__add_attr(&session->header, attr) < 0) { - perf_header_attr__delete(attr); - return -ENOMEM; + perf_evlist__id_add(session->evlist, evsel, 0, i, + event->attr.id[i]); } perf_session__update_sample_type(session); @@ -1078,11 +999,11 @@ int event__process_attr(event_t *self, struct perf_session *session) return 0; } -int event__synthesize_event_type(u64 event_id, char *name, - event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_event_type(u64 event_id, char *name, + perf_event__handler_t process, + struct perf_session *session) { - event_t ev; + union perf_event ev; size_t size = 0; int err = 0; @@ -1103,8 +1024,8 @@ int event__synthesize_event_type(u64 event_id, char *name, return err; } -int event__synthesize_event_types(event__handler_t process, - struct perf_session *session) +int perf_event__synthesize_event_types(perf_event__handler_t process, + struct perf_session *session) { struct perf_trace_event_type *type; int i, err = 0; @@ -1112,8 +1033,9 @@ int event__synthesize_event_types(event__handler_t process, for (i = 0; i < event_count; i++) { type = &events[i]; - err = event__synthesize_event_type(type->event_id, type->name, - process, session); + err = perf_event__synthesize_event_type(type->event_id, + type->name, process, + session); if (err) { pr_debug("failed to create perf header event type\n"); return err; @@ -1123,28 +1045,28 @@ int event__synthesize_event_types(event__handler_t process, return err; } -int event__process_event_type(event_t *self, - struct perf_session *session __unused) +int perf_event__process_event_type(union perf_event *event, + struct perf_session *session __unused) { - if (perf_header__push_event(self->event_type.event_type.event_id, - self->event_type.event_type.name) < 0) + if (perf_header__push_event(event->event_type.event_type.event_id, + event->event_type.event_type.name) < 0) return -ENOMEM; return 0; } -int event__synthesize_tracing_data(int fd, struct list_head *pattrs, - event__handler_t process, +int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist, + perf_event__handler_t process, struct perf_session *session __unused) { - event_t ev; + union perf_event ev; ssize_t size = 0, aligned_size = 0, padding; - int err = 0; + int err __used = 0; memset(&ev, 0, sizeof(ev)); ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA; - size = read_tracing_data_size(fd, pattrs); + size = read_tracing_data_size(fd, &evlist->entries); if (size <= 0) return size; aligned_size = ALIGN(size, sizeof(u64)); @@ -1154,16 +1076,16 @@ int event__synthesize_tracing_data(int fd, struct list_head *pattrs, process(&ev, NULL, session); - err = read_tracing_data(fd, pattrs); + err = read_tracing_data(fd, &evlist->entries); write_padded(fd, NULL, 0, padding); return aligned_size; } -int event__process_tracing_data(event_t *self, - struct perf_session *session) +int perf_event__process_tracing_data(union perf_event *event, + struct perf_session *session) { - ssize_t size_read, padding, size = self->tracing_data.size; + ssize_t size_read, padding, size = event->tracing_data.size; off_t offset = lseek(session->fd, 0, SEEK_CUR); char buf[BUFSIZ]; @@ -1189,12 +1111,12 @@ int event__process_tracing_data(event_t *self, return size_read + padding; } -int event__synthesize_build_id(struct dso *pos, u16 misc, - event__handler_t process, - struct machine *machine, - struct perf_session *session) +int perf_event__synthesize_build_id(struct dso *pos, u16 misc, + perf_event__handler_t process, + struct machine *machine, + struct perf_session *session) { - event_t ev; + union perf_event ev; size_t len; int err = 0; @@ -1217,11 +1139,11 @@ int event__synthesize_build_id(struct dso *pos, u16 misc, return err; } -int event__process_build_id(event_t *self, - struct perf_session *session) +int perf_event__process_build_id(union perf_event *event, + struct perf_session *session) { - __event_process_build_id(&self->build_id, - self->build_id.filename, + __event_process_build_id(&event->build_id, + event->build_id.filename, session); return 0; } diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 33f16be..456661d 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -9,13 +9,6 @@ #include <linux/bitmap.h> -struct perf_header_attr { - struct perf_event_attr attr; - int ids, size; - u64 *id; - off_t id_offset; -}; - enum { HEADER_TRACE_INFO = 1, HEADER_BUILD_ID, @@ -46,14 +39,12 @@ struct perf_pipe_file_header { struct perf_header; -int perf_file_header__read(struct perf_file_header *self, +int perf_file_header__read(struct perf_file_header *header, struct perf_header *ph, int fd); struct perf_header { int frozen; - int attrs, size; bool needs_swap; - struct perf_header_attr **attr; s64 attr_offset; u64 data_offset; u64 data_size; @@ -62,34 +53,25 @@ struct perf_header { DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS); }; -int perf_header__init(struct perf_header *self); -void perf_header__exit(struct perf_header *self); +struct perf_evlist; -int perf_header__read(struct perf_session *session, int fd); -int perf_header__write(struct perf_header *self, int fd, bool at_exit); +int perf_session__read_header(struct perf_session *session, int fd); +int perf_session__write_header(struct perf_session *session, + struct perf_evlist *evlist, + int fd, bool at_exit); int perf_header__write_pipe(int fd); -int perf_header__add_attr(struct perf_header *self, - struct perf_header_attr *attr); - int perf_header__push_event(u64 id, const char *name); char *perf_header__find_event(u64 id); -struct perf_header_attr *perf_header_attr__new(struct perf_event_attr *attr); -void perf_header_attr__delete(struct perf_header_attr *self); +u64 perf_evlist__sample_type(struct perf_evlist *evlist); +bool perf_evlist__sample_id_all(const struct perf_evlist *evlist); +void perf_header__set_feat(struct perf_header *header, int feat); +void perf_header__clear_feat(struct perf_header *header, int feat); +bool perf_header__has_feat(const struct perf_header *header, int feat); -int perf_header_attr__add_id(struct perf_header_attr *self, u64 id); - -u64 perf_header__sample_type(struct perf_header *header); -bool perf_header__sample_id_all(const struct perf_header *header); -struct perf_event_attr * -perf_header__find_attr(u64 id, struct perf_header *header); -void perf_header__set_feat(struct perf_header *self, int feat); -void perf_header__clear_feat(struct perf_header *self, int feat); -bool perf_header__has_feat(const struct perf_header *self, int feat); - -int perf_header__process_sections(struct perf_header *self, int fd, - int (*process)(struct perf_file_section *self, +int perf_header__process_sections(struct perf_header *header, int fd, + int (*process)(struct perf_file_section *section, struct perf_header *ph, int feat, int fd)); @@ -97,32 +79,31 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms); int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir); -int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, - event__handler_t process, - struct perf_session *session); -int event__synthesize_attrs(struct perf_header *self, - event__handler_t process, - struct perf_session *session); -int event__process_attr(event_t *self, struct perf_session *session); - -int event__synthesize_event_type(u64 event_id, char *name, - event__handler_t process, - struct perf_session *session); -int event__synthesize_event_types(event__handler_t process, - struct perf_session *session); -int event__process_event_type(event_t *self, - struct perf_session *session); - -int event__synthesize_tracing_data(int fd, struct list_head *pattrs, - event__handler_t process, - struct perf_session *session); -int event__process_tracing_data(event_t *self, +int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id, + perf_event__handler_t process, struct perf_session *session); +int perf_session__synthesize_attrs(struct perf_session *session, + perf_event__handler_t process); +int perf_event__process_attr(union perf_event *event, struct perf_session *session); + +int perf_event__synthesize_event_type(u64 event_id, char *name, + perf_event__handler_t process, + struct perf_session *session); +int perf_event__synthesize_event_types(perf_event__handler_t process, + struct perf_session *session); +int perf_event__process_event_type(union perf_event *event, + struct perf_session *session); -int event__synthesize_build_id(struct dso *pos, u16 misc, - event__handler_t process, - struct machine *machine, - struct perf_session *session); -int event__process_build_id(event_t *self, struct perf_session *session); - +int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist, + perf_event__handler_t process, + struct perf_session *session); +int perf_event__process_tracing_data(union perf_event *event, + struct perf_session *session); + +int perf_event__synthesize_build_id(struct dso *pos, u16 misc, + perf_event__handler_t process, + struct machine *machine, + struct perf_session *session); +int perf_event__process_build_id(union perf_event *event, + struct perf_session *session); #endif /* __PERF_HEADER_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 32f4f1f..627a02e 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1,3 +1,4 @@ +#include "annotate.h" #include "util.h" #include "build-id.h" #include "hist.h" @@ -49,6 +50,15 @@ static void hists__calc_col_len(struct hists *self, struct hist_entry *h) if (h->ms.sym) hists__new_col_len(self, HISTC_SYMBOL, h->ms.sym->namelen); + else { + const unsigned int unresolved_col_width = BITS_PER_LONG / 4; + + if (hists__col_len(self, HISTC_DSO) < unresolved_col_width && + !symbol_conf.col_width_list_str && !symbol_conf.field_sep && + !symbol_conf.dso_list) + hists__set_col_len(self, HISTC_DSO, + unresolved_col_width); + } len = thread__comm_len(h->thread); if (hists__new_col_len(self, HISTC_COMM, len)) @@ -211,7 +221,9 @@ void hist_entry__free(struct hist_entry *he) * collapse the histogram */ -static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he) +static bool hists__collapse_insert_entry(struct hists *self, + struct rb_root *root, + struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -226,8 +238,11 @@ static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he) if (!cmp) { iter->period += he->period; - if (symbol_conf.use_callchain) - callchain_merge(iter->callchain, he->callchain); + if (symbol_conf.use_callchain) { + callchain_cursor_reset(&self->callchain_cursor); + callchain_merge(&self->callchain_cursor, iter->callchain, + he->callchain); + } hist_entry__free(he); return false; } @@ -262,7 +277,7 @@ void hists__collapse_resort(struct hists *self) next = rb_next(&n->rb_node); rb_erase(&n->rb_node, &self->entries); - if (collapse__insert_entry(&tmp, n)) + if (hists__collapse_insert_entry(self, &tmp, n)) hists__inc_nr_entries(self, n); } @@ -425,7 +440,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self, u64 cumul; child = rb_entry(node, struct callchain_node, rb_node); - cumul = cumul_hits(child); + cumul = callchain_cumul_hits(child); remaining -= cumul; /* @@ -585,6 +600,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, { struct sort_entry *se; u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us; + u64 nr_events; const char *sep = symbol_conf.field_sep; int ret; @@ -593,6 +609,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, if (pair_hists) { period = self->pair ? self->pair->period : 0; + nr_events = self->pair ? self->pair->nr_events : 0; total = pair_hists->stats.total_period; period_sys = self->pair ? self->pair->period_sys : 0; period_us = self->pair ? self->pair->period_us : 0; @@ -600,6 +617,7 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, period_guest_us = self->pair ? self->pair->period_guest_us : 0; } else { period = self->period; + nr_events = self->nr_events; total = session_total; period_sys = self->period_sys; period_us = self->period_us; @@ -640,9 +658,9 @@ int hist_entry__snprintf(struct hist_entry *self, char *s, size_t size, if (symbol_conf.show_nr_samples) { if (sep) - ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period); + ret += snprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events); else - ret += snprintf(s + ret, size - ret, "%11" PRIu64, period); + ret += snprintf(s + ret, size - ret, "%11" PRIu64, nr_events); } if (pair_hists) { @@ -944,225 +962,14 @@ void hists__filter_by_thread(struct hists *self, const struct thread *thread) } } -static int symbol__alloc_hist(struct symbol *self) -{ - struct sym_priv *priv = symbol__priv(self); - const int size = (sizeof(*priv->hist) + - (self->end - self->start) * sizeof(u64)); - - priv->hist = zalloc(size); - return priv->hist == NULL ? -1 : 0; -} - -int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip) -{ - unsigned int sym_size, offset; - struct symbol *sym = self->ms.sym; - struct sym_priv *priv; - struct sym_hist *h; - - if (!sym || !self->ms.map) - return 0; - - priv = symbol__priv(sym); - if (priv->hist == NULL && symbol__alloc_hist(sym) < 0) - return -ENOMEM; - - sym_size = sym->end - sym->start; - offset = ip - sym->start; - - pr_debug3("%s: ip=%#" PRIx64 "\n", __func__, self->ms.map->unmap_ip(self->ms.map, ip)); - - if (offset >= sym_size) - return 0; - - h = priv->hist; - h->sum++; - h->ip[offset]++; - - pr_debug3("%#" PRIx64 " %s: period++ [ip: %#" PRIx64 ", %#" PRIx64 - "] => %" PRIu64 "\n", self->ms.sym->start, self->ms.sym->name, - ip, ip - self->ms.sym->start, h->ip[offset]); - return 0; -} - -static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize) -{ - struct objdump_line *self = malloc(sizeof(*self) + privsize); - - if (self != NULL) { - self->offset = offset; - self->line = line; - } - - return self; -} - -void objdump_line__free(struct objdump_line *self) -{ - free(self->line); - free(self); -} - -static void objdump__add_line(struct list_head *head, struct objdump_line *line) -{ - list_add_tail(&line->node, head); -} - -struct objdump_line *objdump__get_next_ip_line(struct list_head *head, - struct objdump_line *pos) -{ - list_for_each_entry_continue(pos, head, node) - if (pos->offset >= 0) - return pos; - - return NULL; -} - -static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file, - struct list_head *head, size_t privsize) +int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip) { - struct symbol *sym = self->ms.sym; - struct objdump_line *objdump_line; - char *line = NULL, *tmp, *tmp2, *c; - size_t line_len; - s64 line_ip, offset = -1; - - if (getline(&line, &line_len, file) < 0) - return -1; - - if (!line) - return -1; - - while (line_len != 0 && isspace(line[line_len - 1])) - line[--line_len] = '\0'; - - c = strchr(line, '\n'); - if (c) - *c = 0; - - line_ip = -1; - - /* - * Strip leading spaces: - */ - tmp = line; - while (*tmp) { - if (*tmp != ' ') - break; - tmp++; - } - - if (*tmp) { - /* - * Parse hexa addresses followed by ':' - */ - line_ip = strtoull(tmp, &tmp2, 16); - if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0') - line_ip = -1; - } - - if (line_ip != -1) { - u64 start = map__rip_2objdump(self->ms.map, sym->start), - end = map__rip_2objdump(self->ms.map, sym->end); - - offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) - offset = -1; - } - - objdump_line = objdump_line__new(offset, line, privsize); - if (objdump_line == NULL) { - free(line); - return -1; - } - objdump__add_line(head, objdump_line); - - return 0; + return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip); } -int hist_entry__annotate(struct hist_entry *self, struct list_head *head, - size_t privsize) +int hist_entry__annotate(struct hist_entry *he, size_t privsize) { - struct symbol *sym = self->ms.sym; - struct map *map = self->ms.map; - struct dso *dso = map->dso; - char *filename = dso__build_id_filename(dso, NULL, 0); - bool free_filename = true; - char command[PATH_MAX * 2]; - FILE *file; - int err = 0; - u64 len; - char symfs_filename[PATH_MAX]; - - if (filename) { - snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", - symbol_conf.symfs, filename); - } - - if (filename == NULL) { - if (dso->has_build_id) { - pr_err("Can't annotate %s: not enough memory\n", - sym->name); - return -ENOMEM; - } - goto fallback; - } else if (readlink(symfs_filename, command, sizeof(command)) < 0 || - strstr(command, "[kernel.kallsyms]") || - access(symfs_filename, R_OK)) { - free(filename); -fallback: - /* - * If we don't have build-ids or the build-id file isn't in the - * cache, or is just a kallsyms file, well, lets hope that this - * DSO is the same as when 'perf record' ran. - */ - filename = dso->long_name; - snprintf(symfs_filename, sizeof(symfs_filename), "%s%s", - symbol_conf.symfs, filename); - free_filename = false; - } - - if (dso->origin == DSO__ORIG_KERNEL) { - if (dso->annotate_warned) - goto out_free_filename; - err = -ENOENT; - dso->annotate_warned = 1; - pr_err("Can't annotate %s: No vmlinux file was found in the " - "path\n", sym->name); - goto out_free_filename; - } - - pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, - filename, sym->name, map->unmap_ip(map, sym->start), - map->unmap_ip(map, sym->end)); - - len = sym->end - sym->start; - - pr_debug("annotating [%p] %30s : [%p] %30s\n", - dso, dso->long_name, sym, sym->name); - - snprintf(command, sizeof(command), - "objdump --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 " -dS -C %s|grep -v %s|expand", - map__rip_2objdump(map, sym->start), - map__rip_2objdump(map, sym->end), - symfs_filename, filename); - - pr_debug("Executing: %s\n", command); - - file = popen(command, "r"); - if (!file) - goto out_free_filename; - - while (!feof(file)) - if (hist_entry__parse_objdump_line(self, file, head, privsize) < 0) - break; - - pclose(file); -out_free_filename: - if (free_filename) - free(filename); - return err; + return symbol__annotate(he->ms.sym, he->ms.map, privsize); } void hists__inc_nr_events(struct hists *self, u32 type) @@ -1177,8 +984,12 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp) size_t ret = 0; for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) { - const char *name = event__get_event_name(i); + const char *name; + + if (self->stats.nr_events[i] == 0) + continue; + name = perf_event__name(i); if (!strcmp(name, "UNKNOWN")) continue; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index ee78985..cb6858a 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -9,33 +9,6 @@ extern struct callchain_param callchain_param; struct hist_entry; struct addr_location; struct symbol; -struct rb_root; - -struct objdump_line { - struct list_head node; - s64 offset; - char *line; -}; - -void objdump_line__free(struct objdump_line *self); -struct objdump_line *objdump__get_next_ip_line(struct list_head *head, - struct objdump_line *pos); - -struct sym_hist { - u64 sum; - u64 ip[0]; -}; - -struct sym_ext { - struct rb_node node; - double percent; - char *path; -}; - -struct sym_priv { - struct sym_hist *hist; - struct sym_ext *ext; -}; /* * The kernel collects the number of events it couldn't send in a stretch and @@ -69,14 +42,13 @@ enum hist_column { }; struct hists { - struct rb_node rb_node; struct rb_root entries; u64 nr_entries; struct events_stats stats; - u64 config; u64 event_stream; - u32 type; u16 col_len[HISTC_NR_COLS]; + /* Best would be to reuse the session callchain cursor */ + struct callchain_cursor callchain_cursor; }; struct hist_entry *__hists__add_entry(struct hists *self, @@ -102,9 +74,8 @@ size_t hists__fprintf_nr_events(struct hists *self, FILE *fp); size_t hists__fprintf(struct hists *self, struct hists *pair, bool show_displacement, FILE *fp); -int hist_entry__inc_addr_samples(struct hist_entry *self, u64 ip); -int hist_entry__annotate(struct hist_entry *self, struct list_head *head, - size_t privsize); +int hist_entry__inc_addr_samples(struct hist_entry *self, int evidx, u64 addr); +int hist_entry__annotate(struct hist_entry *self, size_t privsize); void hists__filter_by_dso(struct hists *self, const struct dso *dso); void hists__filter_by_thread(struct hists *self, const struct thread *thread); @@ -113,21 +84,18 @@ u16 hists__col_len(struct hists *self, enum hist_column col); void hists__set_col_len(struct hists *self, enum hist_column col, u16 len); bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len); -#ifdef NO_NEWT_SUPPORT -static inline int hists__browse(struct hists *self __used, - const char *helpline __used, - const char *ev_name __used) -{ - return 0; -} +struct perf_evlist; -static inline int hists__tui_browse_tree(struct rb_root *self __used, - const char *help __used) +#ifdef NO_NEWT_SUPPORT +static inline +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __used, + const char *help __used) { return 0; } -static inline int hist_entry__tui_annotate(struct hist_entry *self __used) +static inline int hist_entry__tui_annotate(struct hist_entry *self __used, + int evidx __used) { return 0; } @@ -135,14 +103,12 @@ static inline int hist_entry__tui_annotate(struct hist_entry *self __used) #define KEY_RIGHT -2 #else #include <newt.h> -int hists__browse(struct hists *self, const char *helpline, - const char *ev_name); -int hist_entry__tui_annotate(struct hist_entry *self); +int hist_entry__tui_annotate(struct hist_entry *self, int evidx); #define KEY_LEFT NEWT_KEY_LEFT #define KEY_RIGHT NEWT_KEY_RIGHT -int hists__tui_browse_tree(struct rb_root *self, const char *help); +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help); #endif unsigned int hists__sort_list_width(struct hists *self); diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h index f5ca26e..356c7e4 100644 --- a/tools/perf/util/include/linux/list.h +++ b/tools/perf/util/include/linux/list.h @@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include "../../../../include/linux/list.h" #ifndef PERF_LIST_H diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 135f69b..54a7e26 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,6 +1,7 @@ #include "../../../include/linux/hw_breakpoint.h" #include "util.h" #include "../perf.h" +#include "evlist.h" #include "evsel.h" #include "parse-options.h" #include "parse-events.h" @@ -11,10 +12,6 @@ #include "header.h" #include "debugfs.h" -int nr_counters; - -LIST_HEAD(evsel_list); - struct event_symbol { u8 type; u64 config; @@ -271,6 +268,9 @@ const char *event_name(struct perf_evsel *evsel) u64 config = evsel->attr.config; int type = evsel->attr.type; + if (evsel->name) + return evsel->name; + return __event_name(type, config); } @@ -449,8 +449,8 @@ parse_single_tracepoint_event(char *sys_name, /* sys + ':' + event + ':' + flags*/ #define MAX_EVOPT_LEN (MAX_EVENT_LENGTH * 2 + 2 + 128) static enum event_result -parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp, - char *flags) +parse_multiple_tracepoint_event(const struct option *opt, char *sys_name, + const char *evt_exp, char *flags) { char evt_path[MAXPATHLEN]; struct dirent *evt_ent; @@ -483,15 +483,16 @@ parse_multiple_tracepoint_event(char *sys_name, const char *evt_exp, if (len < 0) return EVT_FAILED; - if (parse_events(NULL, event_opt, 0)) + if (parse_events(opt, event_opt, 0)) return EVT_FAILED; } return EVT_HANDLED_ALL; } -static enum event_result parse_tracepoint_event(const char **strp, - struct perf_event_attr *attr) +static enum event_result +parse_tracepoint_event(const struct option *opt, const char **strp, + struct perf_event_attr *attr) { const char *evt_name; char *flags = NULL, *comma_loc; @@ -530,7 +531,7 @@ static enum event_result parse_tracepoint_event(const char **strp, return EVT_FAILED; if (strpbrk(evt_name, "*?")) { *strp += strlen(sys_name) + evt_length + 1; /* 1 == the ':' */ - return parse_multiple_tracepoint_event(sys_name, evt_name, + return parse_multiple_tracepoint_event(opt, sys_name, evt_name, flags); } else { return parse_single_tracepoint_event(sys_name, evt_name, @@ -740,11 +741,12 @@ parse_event_modifier(const char **strp, struct perf_event_attr *attr) * Symbolic names are (almost) exactly matched. */ static enum event_result -parse_event_symbols(const char **str, struct perf_event_attr *attr) +parse_event_symbols(const struct option *opt, const char **str, + struct perf_event_attr *attr) { enum event_result ret; - ret = parse_tracepoint_event(str, attr); + ret = parse_tracepoint_event(opt, str, attr); if (ret != EVT_FAILED) goto modifier; @@ -778,14 +780,17 @@ modifier: return ret; } -int parse_events(const struct option *opt __used, const char *str, int unset __used) +int parse_events(const struct option *opt, const char *str, int unset __used) { + struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; struct perf_event_attr attr; enum event_result ret; + const char *ostr; for (;;) { + ostr = str; memset(&attr, 0, sizeof(attr)); - ret = parse_event_symbols(&str, &attr); + ret = parse_event_symbols(opt, &str, &attr); if (ret == EVT_FAILED) return -1; @@ -794,12 +799,15 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u if (ret != EVT_HANDLED_ALL) { struct perf_evsel *evsel; - evsel = perf_evsel__new(&attr, - nr_counters); + evsel = perf_evsel__new(&attr, evlist->nr_entries); if (evsel == NULL) return -1; - list_add_tail(&evsel->node, &evsel_list); - ++nr_counters; + perf_evlist__add(evlist, evsel); + + evsel->name = calloc(str - ostr + 1, 1); + if (!evsel->name) + return -1; + strncpy(evsel->name, ostr, str - ostr); } if (*str == 0) @@ -813,13 +821,14 @@ int parse_events(const struct option *opt __used, const char *str, int unset __u return 0; } -int parse_filter(const struct option *opt __used, const char *str, +int parse_filter(const struct option *opt, const char *str, int unset __used) { + struct perf_evlist *evlist = *(struct perf_evlist **)opt->value; struct perf_evsel *last = NULL; - if (!list_empty(&evsel_list)) - last = list_entry(evsel_list.prev, struct perf_evsel, node); + if (evlist->nr_entries > 0) + last = list_entry(evlist->entries.prev, struct perf_evsel, node); if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) { fprintf(stderr, @@ -849,7 +858,7 @@ static const char * const event_type_descriptors[] = { * Print the events from <debugfs_mount_point>/tracing/events */ -static void print_tracepoint_events(void) +void print_tracepoint_events(const char *subsys_glob, const char *event_glob) { DIR *sys_dir, *evt_dir; struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; @@ -864,6 +873,9 @@ static void print_tracepoint_events(void) return; for_each_subsystem(sys_dir, sys_dirent, sys_next) { + if (subsys_glob != NULL && + !strglobmatch(sys_dirent.d_name, subsys_glob)) + continue; snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path, sys_dirent.d_name); @@ -872,6 +884,10 @@ static void print_tracepoint_events(void) continue; for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + if (event_glob != NULL && + !strglobmatch(evt_dirent.d_name, event_glob)) + continue; + snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent.d_name, evt_dirent.d_name); printf(" %-42s [%s]\n", evt_path, @@ -923,13 +939,61 @@ int is_valid_tracepoint(const char *event_string) return 0; } +void print_events_type(u8 type) +{ + struct event_symbol *syms = event_symbols; + unsigned int i; + char name[64]; + + for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { + if (type != syms->type) + continue; + + if (strlen(syms->alias)) + snprintf(name, sizeof(name), "%s OR %s", + syms->symbol, syms->alias); + else + snprintf(name, sizeof(name), "%s", syms->symbol); + + printf(" %-42s [%s]\n", name, + event_type_descriptors[type]); + } +} + +int print_hwcache_events(const char *event_glob) +{ + unsigned int type, op, i, printed = 0; + + for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { + for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { + /* skip invalid cache type */ + if (!is_cache_op_valid(type, op)) + continue; + + for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { + char *name = event_cache_name(type, op, i); + + if (event_glob != NULL && + !strglobmatch(name, event_glob)) + continue; + + printf(" %-42s [%s]\n", name, + event_type_descriptors[PERF_TYPE_HW_CACHE]); + ++printed; + } + } + } + + return printed; +} + /* * Print the help text for the event symbols: */ -void print_events(void) +void print_events(const char *event_glob) { struct event_symbol *syms = event_symbols; - unsigned int i, type, op, prev_type = -1; + unsigned int i, type, prev_type = -1, printed = 0, ntypes_printed = 0; char name[40]; printf("\n"); @@ -938,8 +1002,16 @@ void print_events(void) for (i = 0; i < ARRAY_SIZE(event_symbols); i++, syms++) { type = syms->type; - if (type != prev_type) + if (type != prev_type && printed) { printf("\n"); + printed = 0; + ntypes_printed++; + } + + if (event_glob != NULL && + !(strglobmatch(syms->symbol, event_glob) || + (syms->alias && strglobmatch(syms->alias, event_glob)))) + continue; if (strlen(syms->alias)) sprintf(name, "%s OR %s", syms->symbol, syms->alias); @@ -949,22 +1021,17 @@ void print_events(void) event_type_descriptors[type]); prev_type = type; + ++printed; } - printf("\n"); - for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) { - for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) { - /* skip invalid cache type */ - if (!is_cache_op_valid(type, op)) - continue; - - for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) { - printf(" %-42s [%s]\n", - event_cache_name(type, op, i), - event_type_descriptors[PERF_TYPE_HW_CACHE]); - } - } + if (ntypes_printed) { + printed = 0; + printf("\n"); } + print_hwcache_events(event_glob); + + if (event_glob != NULL) + return; printf("\n"); printf(" %-42s [%s]\n", @@ -977,37 +1044,7 @@ void print_events(void) event_type_descriptors[PERF_TYPE_BREAKPOINT]); printf("\n"); - print_tracepoint_events(); + print_tracepoint_events(NULL, NULL); exit(129); } - -int perf_evsel_list__create_default(void) -{ - struct perf_evsel *evsel; - struct perf_event_attr attr; - - memset(&attr, 0, sizeof(attr)); - attr.type = PERF_TYPE_HARDWARE; - attr.config = PERF_COUNT_HW_CPU_CYCLES; - - evsel = perf_evsel__new(&attr, 0); - - if (evsel == NULL) - return -ENOMEM; - - list_add(&evsel->node, &evsel_list); - ++nr_counters; - return 0; -} - -void perf_evsel_list__delete(void) -{ - struct perf_evsel *pos, *n; - - list_for_each_entry_safe(pos, n, &evsel_list, node) { - list_del_init(&pos->node); - perf_evsel__delete(pos); - } - nr_counters = 0; -} diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 458e3ec..212f88e 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -9,11 +9,6 @@ struct list_head; struct perf_evsel; -extern struct list_head evsel_list; - -int perf_evsel_list__create_default(void); -void perf_evsel_list__delete(void); - struct option; struct tracepoint_path { @@ -25,8 +20,6 @@ struct tracepoint_path { extern struct tracepoint_path *tracepoint_id_to_path(u64 config); extern bool have_tracepoints(struct list_head *evlist); -extern int nr_counters; - const char *event_name(struct perf_evsel *event); extern const char *__event_name(int type, u64 config); @@ -35,7 +28,10 @@ extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) -extern void print_events(void); +void print_events(const char *event_glob); +void print_events_type(u8 type); +void print_tracepoint_events(const char *subsys_glob, const char *event_glob); +int print_hwcache_events(const char *event_glob); extern int is_valid_tracepoint(const char *event_string); extern char debugfs_path[]; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6e29d9c..5ddee66 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -31,6 +31,7 @@ #include <string.h> #include <stdarg.h> #include <limits.h> +#include <elf.h> #undef _GNU_SOURCE #include "util.h" @@ -111,7 +112,25 @@ static struct symbol *__find_kernel_function_by_name(const char *name, NULL); } -const char *kernel_get_module_path(const char *module) +static struct map *kernel_get_module_map(const char *module) +{ + struct rb_node *nd; + struct map_groups *grp = &machine.kmaps; + + if (!module) + module = "kernel"; + + for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) { + struct map *pos = rb_entry(nd, struct map, rb_node); + if (strncmp(pos->dso->short_name + 1, module, + pos->dso->short_name_len - 2) == 0) { + return pos; + } + } + return NULL; +} + +static struct dso *kernel_get_module_dso(const char *module) { struct dso *dso; struct map *map; @@ -141,7 +160,13 @@ const char *kernel_get_module_path(const char *module) } } found: - return dso->long_name; + return dso; +} + +const char *kernel_get_module_path(const char *module) +{ + struct dso *dso = kernel_get_module_dso(module); + return (dso) ? dso->long_name : NULL; } #ifdef DWARF_SUPPORT @@ -384,7 +409,7 @@ int show_line_range(struct line_range *lr, const char *module) setup_pager(); if (lr->function) - fprintf(stdout, "<%s:%d>\n", lr->function, + fprintf(stdout, "<%s@%s:%d>\n", lr->function, lr->path, lr->start - lr->offset); else fprintf(stdout, "<%s:%d>\n", lr->path, lr->start); @@ -426,12 +451,14 @@ end: } static int show_available_vars_at(int fd, struct perf_probe_event *pev, - int max_vls, bool externs) + int max_vls, struct strfilter *_filter, + bool externs) { char *buf; - int ret, i; + int ret, i, nvars; struct str_node *node; struct variable_list *vls = NULL, *vl; + const char *var; buf = synthesize_perf_probe_point(&pev->point); if (!buf) @@ -439,36 +466,45 @@ static int show_available_vars_at(int fd, struct perf_probe_event *pev, pr_debug("Searching variables at %s\n", buf); ret = find_available_vars_at(fd, pev, &vls, max_vls, externs); - if (ret > 0) { - /* Some variables were found */ - fprintf(stdout, "Available variables at %s\n", buf); - for (i = 0; i < ret; i++) { - vl = &vls[i]; - /* - * A probe point might be converted to - * several trace points. - */ - fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol, - vl->point.offset); - free(vl->point.symbol); - if (vl->vars) { - strlist__for_each(node, vl->vars) + if (ret <= 0) { + pr_err("Failed to find variables at %s (%d)\n", buf, ret); + goto end; + } + /* Some variables are found */ + fprintf(stdout, "Available variables at %s\n", buf); + for (i = 0; i < ret; i++) { + vl = &vls[i]; + /* + * A probe point might be converted to + * several trace points. + */ + fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol, + vl->point.offset); + free(vl->point.symbol); + nvars = 0; + if (vl->vars) { + strlist__for_each(node, vl->vars) { + var = strchr(node->s, '\t') + 1; + if (strfilter__compare(_filter, var)) { fprintf(stdout, "\t\t%s\n", node->s); - strlist__delete(vl->vars); - } else - fprintf(stdout, "(No variables)\n"); + nvars++; + } + } + strlist__delete(vl->vars); } - free(vls); - } else - pr_err("Failed to find variables at %s (%d)\n", buf, ret); - + if (nvars == 0) + fprintf(stdout, "\t\t(No matched variables)\n"); + } + free(vls); +end: free(buf); return ret; } /* Show available variables on given probe point */ int show_available_vars(struct perf_probe_event *pevs, int npevs, - int max_vls, const char *module, bool externs) + int max_vls, const char *module, + struct strfilter *_filter, bool externs) { int i, fd, ret = 0; @@ -485,7 +521,8 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs, setup_pager(); for (i = 0; i < npevs && ret >= 0; i++) - ret = show_available_vars_at(fd, &pevs[i], max_vls, externs); + ret = show_available_vars_at(fd, &pevs[i], max_vls, _filter, + externs); close(fd); return ret; @@ -531,7 +568,9 @@ int show_line_range(struct line_range *lr __unused, const char *module __unused) int show_available_vars(struct perf_probe_event *pevs __unused, int npevs __unused, int max_vls __unused, - const char *module __unused, bool externs __unused) + const char *module __unused, + struct strfilter *filter __unused, + bool externs __unused) { pr_warning("Debuginfo-analysis is not supported.\n"); return -ENOSYS; @@ -556,11 +595,11 @@ static int parse_line_num(char **ptr, int *val, const char *what) * The line range syntax is described by: * * SRC[:SLN[+NUM|-ELN]] - * FNC[:SLN[+NUM|-ELN]] + * FNC[@SRC][:SLN[+NUM|-ELN]] */ int parse_line_range_desc(const char *arg, struct line_range *lr) { - char *range, *name = strdup(arg); + char *range, *file, *name = strdup(arg); int err; if (!name) @@ -610,7 +649,16 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) } } - if (strchr(name, '.')) + file = strchr(name, '@'); + if (file) { + *file = '\0'; + lr->file = strdup(++file); + if (lr->file == NULL) { + err = -ENOMEM; + goto err; + } + lr->function = name; + } else if (strchr(name, '.')) lr->file = name; else lr->function = name; @@ -1784,9 +1832,12 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs, } /* Loop 2: add all events */ - for (i = 0; i < npevs && ret >= 0; i++) + for (i = 0; i < npevs; i++) { ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs, pkgs[i].ntevs, force_add); + if (ret < 0) + break; + } end: /* Loop 3: cleanup and free trace events */ for (i = 0; i < npevs; i++) { @@ -1912,4 +1963,46 @@ int del_perf_probe_events(struct strlist *dellist) return ret; } +/* TODO: don't use a global variable for filter ... */ +static struct strfilter *available_func_filter; + +/* + * If a symbol corresponds to a function with global binding and + * matches filter return 0. For all others return 1. + */ +static int filter_available_functions(struct map *map __unused, + struct symbol *sym) +{ + if (sym->binding == STB_GLOBAL && + strfilter__compare(available_func_filter, sym->name)) + return 0; + return 1; +} + +int show_available_funcs(const char *module, struct strfilter *_filter) +{ + struct map *map; + int ret; + + setup_pager(); + + ret = init_vmlinux(); + if (ret < 0) + return ret; + map = kernel_get_module_map(module); + if (!map) { + pr_err("Failed to find %s map.\n", (module) ? : "kernel"); + return -EINVAL; + } + available_func_filter = _filter; + if (map__load(map, filter_available_functions)) { + pr_err("Failed to load map.\n"); + return -EINVAL; + } + if (!dso__sorted_by_name(map->dso, map->type)) + dso__sort_by_name(map->dso, map->type); + + dso__fprintf_symbols_by_name(map->dso, map->type, stdout); + return 0; +} diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 5accbed..3434fc9 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -3,6 +3,7 @@ #include <stdbool.h> #include "strlist.h" +#include "strfilter.h" extern bool probe_event_dry_run; @@ -126,7 +127,8 @@ extern int show_perf_probe_events(void); extern int show_line_range(struct line_range *lr, const char *module); extern int show_available_vars(struct perf_probe_event *pevs, int npevs, int max_probe_points, const char *module, - bool externs); + struct strfilter *filter, bool externs); +extern int show_available_funcs(const char *module, struct strfilter *filter); /* Maximum index number of event-name postfix */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index ab83b6a..194f9e2 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -33,6 +33,7 @@ #include <ctype.h> #include <dwarf-regs.h> +#include <linux/bitops.h> #include "event.h" #include "debug.h" #include "util.h" @@ -280,6 +281,19 @@ static bool die_compare_name(Dwarf_Die *dw_die, const char *tname) return name ? (strcmp(tname, name) == 0) : false; } +/* Get callsite line number of inline-function instance */ +static int die_get_call_lineno(Dwarf_Die *in_die) +{ + Dwarf_Attribute attr; + Dwarf_Word ret; + + if (!dwarf_attr(in_die, DW_AT_call_line, &attr)) + return -ENOENT; + + dwarf_formudata(&attr, &ret); + return (int)ret; +} + /* Get type die */ static Dwarf_Die *die_get_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) { @@ -320,13 +334,23 @@ static Dwarf_Die *die_get_real_type(Dwarf_Die *vr_die, Dwarf_Die *die_mem) return vr_die; } -static bool die_is_signed_type(Dwarf_Die *tp_die) +static int die_get_attr_udata(Dwarf_Die *tp_die, unsigned int attr_name, + Dwarf_Word *result) { Dwarf_Attribute attr; + + if (dwarf_attr(tp_die, attr_name, &attr) == NULL || + dwarf_formudata(&attr, result) != 0) + return -ENOENT; + + return 0; +} + +static bool die_is_signed_type(Dwarf_Die *tp_die) +{ Dwarf_Word ret; - if (dwarf_attr(tp_die, DW_AT_encoding, &attr) == NULL || - dwarf_formudata(&attr, &ret) != 0) + if (die_get_attr_udata(tp_die, DW_AT_encoding, &ret)) return false; return (ret == DW_ATE_signed_char || ret == DW_ATE_signed || @@ -335,11 +359,29 @@ static bool die_is_signed_type(Dwarf_Die *tp_die) static int die_get_byte_size(Dwarf_Die *tp_die) { - Dwarf_Attribute attr; Dwarf_Word ret; - if (dwarf_attr(tp_die, DW_AT_byte_size, &attr) == NULL || - dwarf_formudata(&attr, &ret) != 0) + if (die_get_attr_udata(tp_die, DW_AT_byte_size, &ret)) + return 0; + + return (int)ret; +} + +static int die_get_bit_size(Dwarf_Die *tp_die) +{ + Dwarf_Word ret; + + if (die_get_attr_udata(tp_die, DW_AT_bit_size, &ret)) + return 0; + + return (int)ret; +} + +static int die_get_bit_offset(Dwarf_Die *tp_die) +{ + Dwarf_Word ret; + + if (die_get_attr_udata(tp_die, DW_AT_bit_offset, &ret)) return 0; return (int)ret; @@ -458,6 +500,151 @@ static Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr, return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem); } +/* Walker on lines (Note: line number will not be sorted) */ +typedef int (* line_walk_handler_t) (const char *fname, int lineno, + Dwarf_Addr addr, void *data); + +struct __line_walk_param { + const char *fname; + line_walk_handler_t handler; + void *data; + int retval; +}; + +static int __die_walk_funclines_cb(Dwarf_Die *in_die, void *data) +{ + struct __line_walk_param *lw = data; + Dwarf_Addr addr; + int lineno; + + if (dwarf_tag(in_die) == DW_TAG_inlined_subroutine) { + lineno = die_get_call_lineno(in_die); + if (lineno > 0 && dwarf_entrypc(in_die, &addr) == 0) { + lw->retval = lw->handler(lw->fname, lineno, addr, + lw->data); + if (lw->retval != 0) + return DIE_FIND_CB_FOUND; + } + } + return DIE_FIND_CB_SIBLING; +} + +/* Walk on lines of blocks included in given DIE */ +static int __die_walk_funclines(Dwarf_Die *sp_die, + line_walk_handler_t handler, void *data) +{ + struct __line_walk_param lw = { + .handler = handler, + .data = data, + .retval = 0, + }; + Dwarf_Die die_mem; + Dwarf_Addr addr; + int lineno; + + /* Handle function declaration line */ + lw.fname = dwarf_decl_file(sp_die); + if (lw.fname && dwarf_decl_line(sp_die, &lineno) == 0 && + dwarf_entrypc(sp_die, &addr) == 0) { + lw.retval = handler(lw.fname, lineno, addr, data); + if (lw.retval != 0) + goto done; + } + die_find_child(sp_die, __die_walk_funclines_cb, &lw, &die_mem); +done: + return lw.retval; +} + +static int __die_walk_culines_cb(Dwarf_Die *sp_die, void *data) +{ + struct __line_walk_param *lw = data; + + lw->retval = __die_walk_funclines(sp_die, lw->handler, lw->data); + if (lw->retval != 0) + return DWARF_CB_ABORT; + + return DWARF_CB_OK; +} + +/* + * Walk on lines inside given PDIE. If the PDIE is subprogram, walk only on + * the lines inside the subprogram, otherwise PDIE must be a CU DIE. + */ +static int die_walk_lines(Dwarf_Die *pdie, line_walk_handler_t handler, + void *data) +{ + Dwarf_Lines *lines; + Dwarf_Line *line; + Dwarf_Addr addr; + const char *fname; + int lineno, ret = 0; + Dwarf_Die die_mem, *cu_die; + size_t nlines, i; + + /* Get the CU die */ + if (dwarf_tag(pdie) == DW_TAG_subprogram) + cu_die = dwarf_diecu(pdie, &die_mem, NULL, NULL); + else + cu_die = pdie; + if (!cu_die) { + pr_debug2("Failed to get CU from subprogram\n"); + return -EINVAL; + } + + /* Get lines list in the CU */ + if (dwarf_getsrclines(cu_die, &lines, &nlines) != 0) { + pr_debug2("Failed to get source lines on this CU.\n"); + return -ENOENT; + } + pr_debug2("Get %zd lines from this CU\n", nlines); + + /* Walk on the lines on lines list */ + for (i = 0; i < nlines; i++) { + line = dwarf_onesrcline(lines, i); + if (line == NULL || + dwarf_lineno(line, &lineno) != 0 || + dwarf_lineaddr(line, &addr) != 0) { + pr_debug2("Failed to get line info. " + "Possible error in debuginfo.\n"); + continue; + } + /* Filter lines based on address */ + if (pdie != cu_die) + /* + * Address filtering + * The line is included in given function, and + * no inline block includes it. + */ + if (!dwarf_haspc(pdie, addr) || + die_find_inlinefunc(pdie, addr, &die_mem)) + continue; + /* Get source line */ + fname = dwarf_linesrc(line, NULL, NULL); + + ret = handler(fname, lineno, addr, data); + if (ret != 0) + return ret; + } + + /* + * Dwarf lines doesn't include function declarations and inlined + * subroutines. We have to check functions list or given function. + */ + if (pdie != cu_die) + ret = __die_walk_funclines(pdie, handler, data); + else { + struct __line_walk_param param = { + .handler = handler, + .data = data, + .retval = 0, + }; + dwarf_getfuncs(cu_die, __die_walk_culines_cb, ¶m, 0); + ret = param.retval; + } + + return ret; +} + struct __find_variable_param { const char *name; Dwarf_Addr addr; @@ -669,6 +856,8 @@ static_var: return 0; } +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_LONG / sizeof(long)) + static int convert_variable_type(Dwarf_Die *vr_die, struct probe_trace_arg *tvar, const char *cast) @@ -685,6 +874,14 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } + if (die_get_bit_size(vr_die) != 0) { + /* This is a bitfield */ + ret = snprintf(buf, 16, "b%d@%d/%zd", die_get_bit_size(vr_die), + die_get_bit_offset(vr_die), + BYTES_TO_BITS(die_get_byte_size(vr_die))); + goto formatted; + } + if (die_get_real_type(vr_die, &type) == NULL) { pr_warning("Failed to get a type information of %s.\n", dwarf_diename(vr_die)); @@ -729,29 +926,31 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } - ret = die_get_byte_size(&type) * 8; - if (ret) { - /* Check the bitwidth */ - if (ret > MAX_BASIC_TYPE_BITS) { - pr_info("%s exceeds max-bitwidth." - " Cut down to %d bits.\n", - dwarf_diename(&type), MAX_BASIC_TYPE_BITS); - ret = MAX_BASIC_TYPE_BITS; - } + ret = BYTES_TO_BITS(die_get_byte_size(&type)); + if (!ret) + /* No size ... try to use default type */ + return 0; - ret = snprintf(buf, 16, "%c%d", - die_is_signed_type(&type) ? 's' : 'u', ret); - if (ret < 0 || ret >= 16) { - if (ret >= 16) - ret = -E2BIG; - pr_warning("Failed to convert variable type: %s\n", - strerror(-ret)); - return ret; - } - tvar->type = strdup(buf); - if (tvar->type == NULL) - return -ENOMEM; + /* Check the bitwidth */ + if (ret > MAX_BASIC_TYPE_BITS) { + pr_info("%s exceeds max-bitwidth. Cut down to %d bits.\n", + dwarf_diename(&type), MAX_BASIC_TYPE_BITS); + ret = MAX_BASIC_TYPE_BITS; + } + ret = snprintf(buf, 16, "%c%d", + die_is_signed_type(&type) ? 's' : 'u', ret); + +formatted: + if (ret < 0 || ret >= 16) { + if (ret >= 16) + ret = -E2BIG; + pr_warning("Failed to convert variable type: %s\n", + strerror(-ret)); + return ret; } + tvar->type = strdup(buf); + if (tvar->type == NULL) + return -ENOMEM; return 0; } @@ -1050,157 +1249,102 @@ static int call_probe_finder(Dwarf_Die *sp_die, struct probe_finder *pf) return ret; } -/* Find probe point from its line number */ -static int find_probe_point_by_line(struct probe_finder *pf) +static int probe_point_line_walker(const char *fname, int lineno, + Dwarf_Addr addr, void *data) { - Dwarf_Lines *lines; - Dwarf_Line *line; - size_t nlines, i; - Dwarf_Addr addr; - int lineno; - int ret = 0; - - if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) { - pr_warning("No source lines found.\n"); - return -ENOENT; - } + struct probe_finder *pf = data; + int ret; - for (i = 0; i < nlines && ret == 0; i++) { - line = dwarf_onesrcline(lines, i); - if (dwarf_lineno(line, &lineno) != 0 || - lineno != pf->lno) - continue; + if (lineno != pf->lno || strtailcmp(fname, pf->fname) != 0) + return 0; - /* TODO: Get fileno from line, but how? */ - if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0) - continue; + pf->addr = addr; + ret = call_probe_finder(NULL, pf); - if (dwarf_lineaddr(line, &addr) != 0) { - pr_warning("Failed to get the address of the line.\n"); - return -ENOENT; - } - pr_debug("Probe line found: line[%d]:%d addr:0x%jx\n", - (int)i, lineno, (uintmax_t)addr); - pf->addr = addr; + /* Continue if no error, because the line will be in inline function */ + return ret < 0 ? ret : 0; +} - ret = call_probe_finder(NULL, pf); - /* Continuing, because target line might be inlined. */ - } - return ret; +/* Find probe point from its line number */ +static int find_probe_point_by_line(struct probe_finder *pf) +{ + return die_walk_lines(&pf->cu_die, probe_point_line_walker, pf); } /* Find lines which match lazy pattern */ static int find_lazy_match_lines(struct list_head *head, const char *fname, const char *pat) { - char *fbuf, *p1, *p2; - int fd, line, nlines = -1; - struct stat st; - - fd = open(fname, O_RDONLY); - if (fd < 0) { - pr_warning("Failed to open %s: %s\n", fname, strerror(-fd)); + FILE *fp; + char *line = NULL; + size_t line_len; + ssize_t len; + int count = 0, linenum = 1; + + fp = fopen(fname, "r"); + if (!fp) { + pr_warning("Failed to open %s: %s\n", fname, strerror(errno)); return -errno; } - if (fstat(fd, &st) < 0) { - pr_warning("Failed to get the size of %s: %s\n", - fname, strerror(errno)); - nlines = -errno; - goto out_close; - } - - nlines = -ENOMEM; - fbuf = malloc(st.st_size + 2); - if (fbuf == NULL) - goto out_close; - if (read(fd, fbuf, st.st_size) < 0) { - pr_warning("Failed to read %s: %s\n", fname, strerror(errno)); - nlines = -errno; - goto out_free_fbuf; - } - fbuf[st.st_size] = '\n'; /* Dummy line */ - fbuf[st.st_size + 1] = '\0'; - p1 = fbuf; - line = 1; - nlines = 0; - while ((p2 = strchr(p1, '\n')) != NULL) { - *p2 = '\0'; - if (strlazymatch(p1, pat)) { - line_list__add_line(head, line); - nlines++; + while ((len = getline(&line, &line_len, fp)) > 0) { + + if (line[len - 1] == '\n') + line[len - 1] = '\0'; + + if (strlazymatch(line, pat)) { + line_list__add_line(head, linenum); + count++; } - line++; - p1 = p2 + 1; + linenum++; } -out_free_fbuf: - free(fbuf); -out_close: - close(fd); - return nlines; + + if (ferror(fp)) + count = -errno; + free(line); + fclose(fp); + + if (count == 0) + pr_debug("No matched lines found in %s.\n", fname); + return count; +} + +static int probe_point_lazy_walker(const char *fname, int lineno, + Dwarf_Addr addr, void *data) +{ + struct probe_finder *pf = data; + int ret; + + if (!line_list__has_line(&pf->lcache, lineno) || + strtailcmp(fname, pf->fname) != 0) + return 0; + + pr_debug("Probe line found: line:%d addr:0x%llx\n", + lineno, (unsigned long long)addr); + pf->addr = addr; + ret = call_probe_finder(NULL, pf); + + /* + * Continue if no error, because the lazy pattern will match + * to other lines + */ + return ret < 0 ? ret : 0; } /* Find probe points from lazy pattern */ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf) { - Dwarf_Lines *lines; - Dwarf_Line *line; - size_t nlines, i; - Dwarf_Addr addr; - Dwarf_Die die_mem; - int lineno; int ret = 0; if (list_empty(&pf->lcache)) { /* Matching lazy line pattern */ ret = find_lazy_match_lines(&pf->lcache, pf->fname, pf->pev->point.lazy_line); - if (ret == 0) { - pr_debug("No matched lines found in %s.\n", pf->fname); - return 0; - } else if (ret < 0) + if (ret <= 0) return ret; } - if (dwarf_getsrclines(&pf->cu_die, &lines, &nlines) != 0) { - pr_warning("No source lines found.\n"); - return -ENOENT; - } - - for (i = 0; i < nlines && ret >= 0; i++) { - line = dwarf_onesrcline(lines, i); - - if (dwarf_lineno(line, &lineno) != 0 || - !line_list__has_line(&pf->lcache, lineno)) - continue; - - /* TODO: Get fileno from line, but how? */ - if (strtailcmp(dwarf_linesrc(line, NULL, NULL), pf->fname) != 0) - continue; - - if (dwarf_lineaddr(line, &addr) != 0) { - pr_debug("Failed to get the address of line %d.\n", - lineno); - continue; - } - if (sp_die) { - /* Address filtering 1: does sp_die include addr? */ - if (!dwarf_haspc(sp_die, addr)) - continue; - /* Address filtering 2: No child include addr? */ - if (die_find_inlinefunc(sp_die, addr, &die_mem)) - continue; - } - - pr_debug("Probe line found: line[%d]:%d addr:0x%llx\n", - (int)i, lineno, (unsigned long long)addr); - pf->addr = addr; - - ret = call_probe_finder(sp_die, pf); - /* Continuing, because target line might be inlined. */ - } - /* TODO: deallocate lines, but how? */ - return ret; + return die_walk_lines(sp_die, probe_point_lazy_walker, pf); } /* Callback parameter with return value */ @@ -1318,8 +1462,7 @@ static int find_probes(int fd, struct probe_finder *pf) off = 0; line_list__init(&pf->lcache); /* Loop on CUs (Compilation Unit) */ - while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL) && - ret >= 0) { + while (!dwarf_nextcu(dbg, off, &noff, &cuhl, NULL, NULL, NULL)) { /* Get the DIE(Debugging Information Entry) of this CU */ diep = dwarf_offdie(dbg, off + cuhl, &pf->cu_die); if (!diep) @@ -1340,6 +1483,8 @@ static int find_probes(int fd, struct probe_finder *pf) pf->lno = pp->line; ret = find_probe_point_by_line(pf); } + if (ret < 0) + break; } off = noff; } @@ -1644,91 +1789,28 @@ static int line_range_add_line(const char *src, unsigned int lineno, return line_list__add_line(&lr->line_list, lineno); } -/* Search function declaration lines */ -static int line_range_funcdecl_cb(Dwarf_Die *sp_die, void *data) +static int line_range_walk_cb(const char *fname, int lineno, + Dwarf_Addr addr __used, + void *data) { - struct dwarf_callback_param *param = data; - struct line_finder *lf = param->data; - const char *src; - int lineno; + struct line_finder *lf = data; - src = dwarf_decl_file(sp_die); - if (src && strtailcmp(src, lf->fname) != 0) - return DWARF_CB_OK; - - if (dwarf_decl_line(sp_die, &lineno) != 0 || + if ((strtailcmp(fname, lf->fname) != 0) || (lf->lno_s > lineno || lf->lno_e < lineno)) - return DWARF_CB_OK; + return 0; - param->retval = line_range_add_line(src, lineno, lf->lr); - if (param->retval < 0) - return DWARF_CB_ABORT; - return DWARF_CB_OK; -} + if (line_range_add_line(fname, lineno, lf->lr) < 0) + return -EINVAL; -static int find_line_range_func_decl_lines(struct line_finder *lf) -{ - struct dwarf_callback_param param = {.data = (void *)lf, .retval = 0}; - dwarf_getfuncs(&lf->cu_die, line_range_funcdecl_cb, ¶m, 0); - return param.retval; + return 0; } /* Find line range from its line number */ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf) { - Dwarf_Lines *lines; - Dwarf_Line *line; - size_t nlines, i; - Dwarf_Addr addr; - int lineno, ret = 0; - const char *src; - Dwarf_Die die_mem; - - line_list__init(&lf->lr->line_list); - if (dwarf_getsrclines(&lf->cu_die, &lines, &nlines) != 0) { - pr_warning("No source lines found.\n"); - return -ENOENT; - } - - /* Search probable lines on lines list */ - for (i = 0; i < nlines; i++) { - line = dwarf_onesrcline(lines, i); - if (dwarf_lineno(line, &lineno) != 0 || - (lf->lno_s > lineno || lf->lno_e < lineno)) - continue; - - if (sp_die) { - /* Address filtering 1: does sp_die include addr? */ - if (dwarf_lineaddr(line, &addr) != 0 || - !dwarf_haspc(sp_die, addr)) - continue; - - /* Address filtering 2: No child include addr? */ - if (die_find_inlinefunc(sp_die, addr, &die_mem)) - continue; - } - - /* TODO: Get fileno from line, but how? */ - src = dwarf_linesrc(line, NULL, NULL); - if (strtailcmp(src, lf->fname) != 0) - continue; - - ret = line_range_add_line(src, lineno, lf->lr); - if (ret < 0) - return ret; - } + int ret; - /* - * Dwarf lines doesn't include function declarations. We have to - * check functions list or given function. - */ - if (sp_die) { - src = dwarf_decl_file(sp_die); - if (src && dwarf_decl_line(sp_die, &lineno) == 0 && - (lf->lno_s <= lineno && lf->lno_e >= lineno)) - ret = line_range_add_line(src, lineno, lf->lr); - } else - ret = find_line_range_func_decl_lines(lf); + ret = die_walk_lines(sp_die ?: &lf->cu_die, line_range_walk_cb, lf); /* Update status */ if (ret >= 0) @@ -1758,9 +1840,6 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) struct line_finder *lf = param->data; struct line_range *lr = lf->lr; - pr_debug("find (%llx) %s\n", - (unsigned long long)dwarf_dieoffset(sp_die), - dwarf_diename(sp_die)); if (dwarf_tag(sp_die) == DW_TAG_subprogram && die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c new file mode 100644 index 0000000..a9f2d7e --- /dev/null +++ b/tools/perf/util/python.c @@ -0,0 +1,896 @@ +#include <Python.h> +#include <structmember.h> +#include <inttypes.h> +#include <poll.h> +#include "evlist.h" +#include "evsel.h" +#include "event.h" +#include "cpumap.h" +#include "thread_map.h" + +/* Define PyVarObject_HEAD_INIT for python 2.5 */ +#ifndef PyVarObject_HEAD_INIT +# define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, +#endif + +struct throttle_event { + struct perf_event_header header; + u64 time; + u64 id; + u64 stream_id; +}; + +PyMODINIT_FUNC initperf(void); + +#define member_def(type, member, ptype, help) \ + { #member, ptype, \ + offsetof(struct pyrf_event, event) + offsetof(struct type, member), \ + 0, help } + +#define sample_member_def(name, member, ptype, help) \ + { #name, ptype, \ + offsetof(struct pyrf_event, sample) + offsetof(struct perf_sample, member), \ + 0, help } + +struct pyrf_event { + PyObject_HEAD + struct perf_sample sample; + union perf_event event; +}; + +#define sample_members \ + sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"), \ + sample_member_def(sample_pid, pid, T_INT, "event pid"), \ + sample_member_def(sample_tid, tid, T_INT, "event tid"), \ + sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"), \ + sample_member_def(sample_addr, addr, T_ULONGLONG, "event addr"), \ + sample_member_def(sample_id, id, T_ULONGLONG, "event id"), \ + sample_member_def(sample_stream_id, stream_id, T_ULONGLONG, "event stream id"), \ + sample_member_def(sample_period, period, T_ULONGLONG, "event period"), \ + sample_member_def(sample_cpu, cpu, T_UINT, "event cpu"), + +static char pyrf_mmap_event__doc[] = PyDoc_STR("perf mmap event object."); + +static PyMemberDef pyrf_mmap_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(mmap_event, pid, T_UINT, "event pid"), + member_def(mmap_event, tid, T_UINT, "event tid"), + member_def(mmap_event, start, T_ULONGLONG, "start of the map"), + member_def(mmap_event, len, T_ULONGLONG, "map length"), + member_def(mmap_event, pgoff, T_ULONGLONG, "page offset"), + member_def(mmap_event, filename, T_STRING_INPLACE, "backing store"), + { .name = NULL, }, +}; + +static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent) +{ + PyObject *ret; + char *s; + + if (asprintf(&s, "{ type: mmap, pid: %u, tid: %u, start: %#" PRIx64 ", " + "length: %#" PRIx64 ", offset: %#" PRIx64 ", " + "filename: %s }", + pevent->event.mmap.pid, pevent->event.mmap.tid, + pevent->event.mmap.start, pevent->event.mmap.len, + pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) { + ret = PyErr_NoMemory(); + } else { + ret = PyString_FromString(s); + free(s); + } + return ret; +} + +static PyTypeObject pyrf_mmap_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.mmap_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_mmap_event__doc, + .tp_members = pyrf_mmap_event__members, + .tp_repr = (reprfunc)pyrf_mmap_event__repr, +}; + +static char pyrf_task_event__doc[] = PyDoc_STR("perf task (fork/exit) event object."); + +static PyMemberDef pyrf_task_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(fork_event, pid, T_UINT, "event pid"), + member_def(fork_event, ppid, T_UINT, "event ppid"), + member_def(fork_event, tid, T_UINT, "event tid"), + member_def(fork_event, ptid, T_UINT, "event ptid"), + member_def(fork_event, time, T_ULONGLONG, "timestamp"), + { .name = NULL, }, +}; + +static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent) +{ + return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, " + "ptid: %u, time: %" PRIu64 "}", + pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit", + pevent->event.fork.pid, + pevent->event.fork.ppid, + pevent->event.fork.tid, + pevent->event.fork.ptid, + pevent->event.fork.time); +} + +static PyTypeObject pyrf_task_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.task_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_task_event__doc, + .tp_members = pyrf_task_event__members, + .tp_repr = (reprfunc)pyrf_task_event__repr, +}; + +static char pyrf_comm_event__doc[] = PyDoc_STR("perf comm event object."); + +static PyMemberDef pyrf_comm_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(comm_event, pid, T_UINT, "event pid"), + member_def(comm_event, tid, T_UINT, "event tid"), + member_def(comm_event, comm, T_STRING_INPLACE, "process name"), + { .name = NULL, }, +}; + +static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent) +{ + return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }", + pevent->event.comm.pid, + pevent->event.comm.tid, + pevent->event.comm.comm); +} + +static PyTypeObject pyrf_comm_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.comm_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_comm_event__doc, + .tp_members = pyrf_comm_event__members, + .tp_repr = (reprfunc)pyrf_comm_event__repr, +}; + +static char pyrf_throttle_event__doc[] = PyDoc_STR("perf throttle event object."); + +static PyMemberDef pyrf_throttle_event__members[] = { + sample_members + member_def(perf_event_header, type, T_UINT, "event type"), + member_def(throttle_event, time, T_ULONGLONG, "timestamp"), + member_def(throttle_event, id, T_ULONGLONG, "event id"), + member_def(throttle_event, stream_id, T_ULONGLONG, "event stream id"), + { .name = NULL, }, +}; + +static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent) +{ + struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1); + + return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64 + ", stream_id: %" PRIu64 " }", + pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un", + te->time, te->id, te->stream_id); +} + +static PyTypeObject pyrf_throttle_event__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.throttle_event", + .tp_basicsize = sizeof(struct pyrf_event), + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_throttle_event__doc, + .tp_members = pyrf_throttle_event__members, + .tp_repr = (reprfunc)pyrf_throttle_event__repr, +}; + +static int pyrf_event__setup_types(void) +{ + int err; + pyrf_mmap_event__type.tp_new = + pyrf_task_event__type.tp_new = + pyrf_comm_event__type.tp_new = + pyrf_throttle_event__type.tp_new = PyType_GenericNew; + err = PyType_Ready(&pyrf_mmap_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_task_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_comm_event__type); + if (err < 0) + goto out; + err = PyType_Ready(&pyrf_throttle_event__type); + if (err < 0) + goto out; +out: + return err; +} + +static PyTypeObject *pyrf_event__type[] = { + [PERF_RECORD_MMAP] = &pyrf_mmap_event__type, + [PERF_RECORD_LOST] = &pyrf_mmap_event__type, + [PERF_RECORD_COMM] = &pyrf_comm_event__type, + [PERF_RECORD_EXIT] = &pyrf_task_event__type, + [PERF_RECORD_THROTTLE] = &pyrf_throttle_event__type, + [PERF_RECORD_UNTHROTTLE] = &pyrf_throttle_event__type, + [PERF_RECORD_FORK] = &pyrf_task_event__type, + [PERF_RECORD_READ] = &pyrf_mmap_event__type, + [PERF_RECORD_SAMPLE] = &pyrf_mmap_event__type, +}; + +static PyObject *pyrf_event__new(union perf_event *event) +{ + struct pyrf_event *pevent; + PyTypeObject *ptype; + + if (event->header.type < PERF_RECORD_MMAP || + event->header.type > PERF_RECORD_SAMPLE) + return NULL; + + ptype = pyrf_event__type[event->header.type]; + pevent = PyObject_New(struct pyrf_event, ptype); + if (pevent != NULL) + memcpy(&pevent->event, event, event->header.size); + return (PyObject *)pevent; +} + +struct pyrf_cpu_map { + PyObject_HEAD + + struct cpu_map *cpus; +}; + +static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus, + PyObject *args, PyObject *kwargs) +{ + static char *kwlist[] = { "cpustr", NULL, NULL, }; + char *cpustr = NULL; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|s", + kwlist, &cpustr)) + return -1; + + pcpus->cpus = cpu_map__new(cpustr); + if (pcpus->cpus == NULL) + return -1; + return 0; +} + +static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus) +{ + cpu_map__delete(pcpus->cpus); + pcpus->ob_type->tp_free((PyObject*)pcpus); +} + +static Py_ssize_t pyrf_cpu_map__length(PyObject *obj) +{ + struct pyrf_cpu_map *pcpus = (void *)obj; + + return pcpus->cpus->nr; +} + +static PyObject *pyrf_cpu_map__item(PyObject *obj, Py_ssize_t i) +{ + struct pyrf_cpu_map *pcpus = (void *)obj; + + if (i >= pcpus->cpus->nr) + return NULL; + + return Py_BuildValue("i", pcpus->cpus->map[i]); +} + +static PySequenceMethods pyrf_cpu_map__sequence_methods = { + .sq_length = pyrf_cpu_map__length, + .sq_item = pyrf_cpu_map__item, +}; + +static char pyrf_cpu_map__doc[] = PyDoc_STR("cpu map object."); + +static PyTypeObject pyrf_cpu_map__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.cpu_map", + .tp_basicsize = sizeof(struct pyrf_cpu_map), + .tp_dealloc = (destructor)pyrf_cpu_map__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_cpu_map__doc, + .tp_as_sequence = &pyrf_cpu_map__sequence_methods, + .tp_init = (initproc)pyrf_cpu_map__init, +}; + +static int pyrf_cpu_map__setup_types(void) +{ + pyrf_cpu_map__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_cpu_map__type); +} + +struct pyrf_thread_map { + PyObject_HEAD + + struct thread_map *threads; +}; + +static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads, + PyObject *args, PyObject *kwargs) +{ + static char *kwlist[] = { "pid", "tid", NULL, NULL, }; + int pid = -1, tid = -1; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", + kwlist, &pid, &tid)) + return -1; + + pthreads->threads = thread_map__new(pid, tid); + if (pthreads->threads == NULL) + return -1; + return 0; +} + +static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads) +{ + thread_map__delete(pthreads->threads); + pthreads->ob_type->tp_free((PyObject*)pthreads); +} + +static Py_ssize_t pyrf_thread_map__length(PyObject *obj) +{ + struct pyrf_thread_map *pthreads = (void *)obj; + + return pthreads->threads->nr; +} + +static PyObject *pyrf_thread_map__item(PyObject *obj, Py_ssize_t i) +{ + struct pyrf_thread_map *pthreads = (void *)obj; + + if (i >= pthreads->threads->nr) + return NULL; + + return Py_BuildValue("i", pthreads->threads->map[i]); +} + +static PySequenceMethods pyrf_thread_map__sequence_methods = { + .sq_length = pyrf_thread_map__length, + .sq_item = pyrf_thread_map__item, +}; + +static char pyrf_thread_map__doc[] = PyDoc_STR("thread map object."); + +static PyTypeObject pyrf_thread_map__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.thread_map", + .tp_basicsize = sizeof(struct pyrf_thread_map), + .tp_dealloc = (destructor)pyrf_thread_map__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_thread_map__doc, + .tp_as_sequence = &pyrf_thread_map__sequence_methods, + .tp_init = (initproc)pyrf_thread_map__init, +}; + +static int pyrf_thread_map__setup_types(void) +{ + pyrf_thread_map__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_thread_map__type); +} + +struct pyrf_evsel { + PyObject_HEAD + + struct perf_evsel evsel; +}; + +static int pyrf_evsel__init(struct pyrf_evsel *pevsel, + PyObject *args, PyObject *kwargs) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .sample_type = PERF_SAMPLE_PERIOD | PERF_SAMPLE_TID, + }; + static char *kwlist[] = { + "type", + "config", + "sample_freq", + "sample_period", + "sample_type", + "read_format", + "disabled", + "inherit", + "pinned", + "exclusive", + "exclude_user", + "exclude_kernel", + "exclude_hv", + "exclude_idle", + "mmap", + "comm", + "freq", + "inherit_stat", + "enable_on_exec", + "task", + "watermark", + "precise_ip", + "mmap_data", + "sample_id_all", + "wakeup_events", + "bp_type", + "bp_addr", + "bp_len", NULL, NULL, }; + u64 sample_period = 0; + u32 disabled = 0, + inherit = 0, + pinned = 0, + exclusive = 0, + exclude_user = 0, + exclude_kernel = 0, + exclude_hv = 0, + exclude_idle = 0, + mmap = 0, + comm = 0, + freq = 1, + inherit_stat = 0, + enable_on_exec = 0, + task = 0, + watermark = 0, + precise_ip = 0, + mmap_data = 0, + sample_id_all = 1; + int idx = 0; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, + "|iKiKKiiiiiiiiiiiiiiiiiiiiiKK", kwlist, + &attr.type, &attr.config, &attr.sample_freq, + &sample_period, &attr.sample_type, + &attr.read_format, &disabled, &inherit, + &pinned, &exclusive, &exclude_user, + &exclude_kernel, &exclude_hv, &exclude_idle, + &mmap, &comm, &freq, &inherit_stat, + &enable_on_exec, &task, &watermark, + &precise_ip, &mmap_data, &sample_id_all, + &attr.wakeup_events, &attr.bp_type, + &attr.bp_addr, &attr.bp_len, &idx)) + return -1; + + /* union... */ + if (sample_period != 0) { + if (attr.sample_freq != 0) + return -1; /* FIXME: throw right exception */ + attr.sample_period = sample_period; + } + + /* Bitfields */ + attr.disabled = disabled; + attr.inherit = inherit; + attr.pinned = pinned; + attr.exclusive = exclusive; + attr.exclude_user = exclude_user; + attr.exclude_kernel = exclude_kernel; + attr.exclude_hv = exclude_hv; + attr.exclude_idle = exclude_idle; + attr.mmap = mmap; + attr.comm = comm; + attr.freq = freq; + attr.inherit_stat = inherit_stat; + attr.enable_on_exec = enable_on_exec; + attr.task = task; + attr.watermark = watermark; + attr.precise_ip = precise_ip; + attr.mmap_data = mmap_data; + attr.sample_id_all = sample_id_all; + + perf_evsel__init(&pevsel->evsel, &attr, idx); + return 0; +} + +static void pyrf_evsel__delete(struct pyrf_evsel *pevsel) +{ + perf_evsel__exit(&pevsel->evsel); + pevsel->ob_type->tp_free((PyObject*)pevsel); +} + +static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel, + PyObject *args, PyObject *kwargs) +{ + struct perf_evsel *evsel = &pevsel->evsel; + struct cpu_map *cpus = NULL; + struct thread_map *threads = NULL; + PyObject *pcpus = NULL, *pthreads = NULL; + int group = 0, overwrite = 0; + static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL}; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, + &pcpus, &pthreads, &group, &overwrite)) + return NULL; + + if (pthreads != NULL) + threads = ((struct pyrf_thread_map *)pthreads)->threads; + + if (pcpus != NULL) + cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; + + if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyMethodDef pyrf_evsel__methods[] = { + { + .ml_name = "open", + .ml_meth = (PyCFunction)pyrf_evsel__open, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("open the event selector file descriptor table.") + }, + { .ml_name = NULL, } +}; + +static char pyrf_evsel__doc[] = PyDoc_STR("perf event selector list object."); + +static PyTypeObject pyrf_evsel__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.evsel", + .tp_basicsize = sizeof(struct pyrf_evsel), + .tp_dealloc = (destructor)pyrf_evsel__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_doc = pyrf_evsel__doc, + .tp_methods = pyrf_evsel__methods, + .tp_init = (initproc)pyrf_evsel__init, +}; + +static int pyrf_evsel__setup_types(void) +{ + pyrf_evsel__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_evsel__type); +} + +struct pyrf_evlist { + PyObject_HEAD + + struct perf_evlist evlist; +}; + +static int pyrf_evlist__init(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs __used) +{ + PyObject *pcpus = NULL, *pthreads = NULL; + struct cpu_map *cpus; + struct thread_map *threads; + + if (!PyArg_ParseTuple(args, "OO", &pcpus, &pthreads)) + return -1; + + threads = ((struct pyrf_thread_map *)pthreads)->threads; + cpus = ((struct pyrf_cpu_map *)pcpus)->cpus; + perf_evlist__init(&pevlist->evlist, cpus, threads); + return 0; +} + +static void pyrf_evlist__delete(struct pyrf_evlist *pevlist) +{ + perf_evlist__exit(&pevlist->evlist); + pevlist->ob_type->tp_free((PyObject*)pevlist); +} + +static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + static char *kwlist[] = {"pages", "overwrite", + NULL, NULL}; + int pages = 128, overwrite = false; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|ii", kwlist, + &pages, &overwrite)) + return NULL; + + if (perf_evlist__mmap(evlist, pages, overwrite) < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyObject *pyrf_evlist__poll(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + static char *kwlist[] = {"timeout", NULL, NULL}; + int timeout = -1, n; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|i", kwlist, &timeout)) + return NULL; + + n = poll(evlist->pollfd, evlist->nr_fds, timeout); + if (n < 0) { + PyErr_SetFromErrno(PyExc_OSError); + return NULL; + } + + return Py_BuildValue("i", n); +} + +static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist, + PyObject *args __used, PyObject *kwargs __used) +{ + struct perf_evlist *evlist = &pevlist->evlist; + PyObject *list = PyList_New(0); + int i; + + for (i = 0; i < evlist->nr_fds; ++i) { + PyObject *file; + FILE *fp = fdopen(evlist->pollfd[i].fd, "r"); + + if (fp == NULL) + goto free_list; + + file = PyFile_FromFile(fp, "perf", "r", NULL); + if (file == NULL) + goto free_list; + + if (PyList_Append(list, file) != 0) { + Py_DECREF(file); + goto free_list; + } + + Py_DECREF(file); + } + + return list; +free_list: + return PyErr_NoMemory(); +} + + +static PyObject *pyrf_evlist__add(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs __used) +{ + struct perf_evlist *evlist = &pevlist->evlist; + PyObject *pevsel; + struct perf_evsel *evsel; + + if (!PyArg_ParseTuple(args, "O", &pevsel)) + return NULL; + + Py_INCREF(pevsel); + evsel = &((struct pyrf_evsel *)pevsel)->evsel; + evsel->idx = evlist->nr_entries; + perf_evlist__add(evlist, evsel); + + return Py_BuildValue("i", evlist->nr_entries); +} + +static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, + PyObject *args, PyObject *kwargs) +{ + struct perf_evlist *evlist = &pevlist->evlist; + union perf_event *event; + int sample_id_all = 1, cpu; + static char *kwlist[] = {"sample_id_all", NULL, NULL}; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist, + &cpu, &sample_id_all)) + return NULL; + + event = perf_evlist__read_on_cpu(evlist, cpu); + if (event != NULL) { + struct perf_evsel *first; + PyObject *pyevent = pyrf_event__new(event); + struct pyrf_event *pevent = (struct pyrf_event *)pyevent; + + if (pyevent == NULL) + return PyErr_NoMemory(); + + first = list_entry(evlist->entries.next, struct perf_evsel, node); + perf_event__parse_sample(event, first->attr.sample_type, sample_id_all, + &pevent->sample); + return pyevent; + } + + Py_INCREF(Py_None); + return Py_None; +} + +static PyMethodDef pyrf_evlist__methods[] = { + { + .ml_name = "mmap", + .ml_meth = (PyCFunction)pyrf_evlist__mmap, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("mmap the file descriptor table.") + }, + { + .ml_name = "poll", + .ml_meth = (PyCFunction)pyrf_evlist__poll, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("poll the file descriptor table.") + }, + { + .ml_name = "get_pollfd", + .ml_meth = (PyCFunction)pyrf_evlist__get_pollfd, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("get the poll file descriptor table.") + }, + { + .ml_name = "add", + .ml_meth = (PyCFunction)pyrf_evlist__add, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("adds an event selector to the list.") + }, + { + .ml_name = "read_on_cpu", + .ml_meth = (PyCFunction)pyrf_evlist__read_on_cpu, + .ml_flags = METH_VARARGS | METH_KEYWORDS, + .ml_doc = PyDoc_STR("reads an event.") + }, + { .ml_name = NULL, } +}; + +static Py_ssize_t pyrf_evlist__length(PyObject *obj) +{ + struct pyrf_evlist *pevlist = (void *)obj; + + return pevlist->evlist.nr_entries; +} + +static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i) +{ + struct pyrf_evlist *pevlist = (void *)obj; + struct perf_evsel *pos; + + if (i >= pevlist->evlist.nr_entries) + return NULL; + + list_for_each_entry(pos, &pevlist->evlist.entries, node) + if (i-- == 0) + break; + + return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel)); +} + +static PySequenceMethods pyrf_evlist__sequence_methods = { + .sq_length = pyrf_evlist__length, + .sq_item = pyrf_evlist__item, +}; + +static char pyrf_evlist__doc[] = PyDoc_STR("perf event selector list object."); + +static PyTypeObject pyrf_evlist__type = { + PyVarObject_HEAD_INIT(NULL, 0) + .tp_name = "perf.evlist", + .tp_basicsize = sizeof(struct pyrf_evlist), + .tp_dealloc = (destructor)pyrf_evlist__delete, + .tp_flags = Py_TPFLAGS_DEFAULT|Py_TPFLAGS_BASETYPE, + .tp_as_sequence = &pyrf_evlist__sequence_methods, + .tp_doc = pyrf_evlist__doc, + .tp_methods = pyrf_evlist__methods, + .tp_init = (initproc)pyrf_evlist__init, +}; + +static int pyrf_evlist__setup_types(void) +{ + pyrf_evlist__type.tp_new = PyType_GenericNew; + return PyType_Ready(&pyrf_evlist__type); +} + +static struct { + const char *name; + int value; +} perf__constants[] = { + { "TYPE_HARDWARE", PERF_TYPE_HARDWARE }, + { "TYPE_SOFTWARE", PERF_TYPE_SOFTWARE }, + { "TYPE_TRACEPOINT", PERF_TYPE_TRACEPOINT }, + { "TYPE_HW_CACHE", PERF_TYPE_HW_CACHE }, + { "TYPE_RAW", PERF_TYPE_RAW }, + { "TYPE_BREAKPOINT", PERF_TYPE_BREAKPOINT }, + + { "COUNT_HW_CPU_CYCLES", PERF_COUNT_HW_CPU_CYCLES }, + { "COUNT_HW_INSTRUCTIONS", PERF_COUNT_HW_INSTRUCTIONS }, + { "COUNT_HW_CACHE_REFERENCES", PERF_COUNT_HW_CACHE_REFERENCES }, + { "COUNT_HW_CACHE_MISSES", PERF_COUNT_HW_CACHE_MISSES }, + { "COUNT_HW_BRANCH_INSTRUCTIONS", PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + { "COUNT_HW_BRANCH_MISSES", PERF_COUNT_HW_BRANCH_MISSES }, + { "COUNT_HW_BUS_CYCLES", PERF_COUNT_HW_BUS_CYCLES }, + { "COUNT_HW_CACHE_L1D", PERF_COUNT_HW_CACHE_L1D }, + { "COUNT_HW_CACHE_L1I", PERF_COUNT_HW_CACHE_L1I }, + { "COUNT_HW_CACHE_LL", PERF_COUNT_HW_CACHE_LL }, + { "COUNT_HW_CACHE_DTLB", PERF_COUNT_HW_CACHE_DTLB }, + { "COUNT_HW_CACHE_ITLB", PERF_COUNT_HW_CACHE_ITLB }, + { "COUNT_HW_CACHE_BPU", PERF_COUNT_HW_CACHE_BPU }, + { "COUNT_HW_CACHE_OP_READ", PERF_COUNT_HW_CACHE_OP_READ }, + { "COUNT_HW_CACHE_OP_WRITE", PERF_COUNT_HW_CACHE_OP_WRITE }, + { "COUNT_HW_CACHE_OP_PREFETCH", PERF_COUNT_HW_CACHE_OP_PREFETCH }, + { "COUNT_HW_CACHE_RESULT_ACCESS", PERF_COUNT_HW_CACHE_RESULT_ACCESS }, + { "COUNT_HW_CACHE_RESULT_MISS", PERF_COUNT_HW_CACHE_RESULT_MISS }, + + { "COUNT_SW_CPU_CLOCK", PERF_COUNT_SW_CPU_CLOCK }, + { "COUNT_SW_TASK_CLOCK", PERF_COUNT_SW_TASK_CLOCK }, + { "COUNT_SW_PAGE_FAULTS", PERF_COUNT_SW_PAGE_FAULTS }, + { "COUNT_SW_CONTEXT_SWITCHES", PERF_COUNT_SW_CONTEXT_SWITCHES }, + { "COUNT_SW_CPU_MIGRATIONS", PERF_COUNT_SW_CPU_MIGRATIONS }, + { "COUNT_SW_PAGE_FAULTS_MIN", PERF_COUNT_SW_PAGE_FAULTS_MIN }, + { "COUNT_SW_PAGE_FAULTS_MAJ", PERF_COUNT_SW_PAGE_FAULTS_MAJ }, + { "COUNT_SW_ALIGNMENT_FAULTS", PERF_COUNT_SW_ALIGNMENT_FAULTS }, + { "COUNT_SW_EMULATION_FAULTS", PERF_COUNT_SW_EMULATION_FAULTS }, + + { "SAMPLE_IP", PERF_SAMPLE_IP }, + { "SAMPLE_TID", PERF_SAMPLE_TID }, + { "SAMPLE_TIME", PERF_SAMPLE_TIME }, + { "SAMPLE_ADDR", PERF_SAMPLE_ADDR }, + { "SAMPLE_READ", PERF_SAMPLE_READ }, + { "SAMPLE_CALLCHAIN", PERF_SAMPLE_CALLCHAIN }, + { "SAMPLE_ID", PERF_SAMPLE_ID }, + { "SAMPLE_CPU", PERF_SAMPLE_CPU }, + { "SAMPLE_PERIOD", PERF_SAMPLE_PERIOD }, + { "SAMPLE_STREAM_ID", PERF_SAMPLE_STREAM_ID }, + { "SAMPLE_RAW", PERF_SAMPLE_RAW }, + + { "FORMAT_TOTAL_TIME_ENABLED", PERF_FORMAT_TOTAL_TIME_ENABLED }, + { "FORMAT_TOTAL_TIME_RUNNING", PERF_FORMAT_TOTAL_TIME_RUNNING }, + { "FORMAT_ID", PERF_FORMAT_ID }, + { "FORMAT_GROUP", PERF_FORMAT_GROUP }, + + { "RECORD_MMAP", PERF_RECORD_MMAP }, + { "RECORD_LOST", PERF_RECORD_LOST }, + { "RECORD_COMM", PERF_RECORD_COMM }, + { "RECORD_EXIT", PERF_RECORD_EXIT }, + { "RECORD_THROTTLE", PERF_RECORD_THROTTLE }, + { "RECORD_UNTHROTTLE", PERF_RECORD_UNTHROTTLE }, + { "RECORD_FORK", PERF_RECORD_FORK }, + { "RECORD_READ", PERF_RECORD_READ }, + { "RECORD_SAMPLE", PERF_RECORD_SAMPLE }, + { .name = NULL, }, +}; + +static PyMethodDef perf__methods[] = { + { .ml_name = NULL, } +}; + +PyMODINIT_FUNC initperf(void) +{ + PyObject *obj; + int i; + PyObject *dict, *module = Py_InitModule("perf", perf__methods); + + if (module == NULL || + pyrf_event__setup_types() < 0 || + pyrf_evlist__setup_types() < 0 || + pyrf_evsel__setup_types() < 0 || + pyrf_thread_map__setup_types() < 0 || + pyrf_cpu_map__setup_types() < 0) + return; + + Py_INCREF(&pyrf_evlist__type); + PyModule_AddObject(module, "evlist", (PyObject*)&pyrf_evlist__type); + + Py_INCREF(&pyrf_evsel__type); + PyModule_AddObject(module, "evsel", (PyObject*)&pyrf_evsel__type); + + Py_INCREF(&pyrf_thread_map__type); + PyModule_AddObject(module, "thread_map", (PyObject*)&pyrf_thread_map__type); + + Py_INCREF(&pyrf_cpu_map__type); + PyModule_AddObject(module, "cpu_map", (PyObject*)&pyrf_cpu_map__type); + + dict = PyModule_GetDict(module); + if (dict == NULL) + goto error; + + for (i = 0; perf__constants[i].name != NULL; i++) { + obj = PyInt_FromLong(perf__constants[i].value); + if (obj == NULL) + goto error; + PyDict_SetItemString(dict, perf__constants[i].name, obj); + Py_DECREF(obj); + } + +error: + if (PyErr_Occurred()) + PyErr_SetString(PyExc_ImportError, "perf: Init failed!"); +} diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index c6d9933..2040b85 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -248,8 +248,7 @@ static void python_process_event(int cpu, void *data, context = PyCObject_FromVoidPtr(scripting_context, NULL); PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); - PyTuple_SetItem(t, n++, - PyCObject_FromVoidPtr(scripting_context, NULL)); + PyTuple_SetItem(t, n++, context); if (handler) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 105f00b..f26639f 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -7,6 +7,8 @@ #include <sys/types.h> #include <sys/mman.h> +#include "evlist.h" +#include "evsel.h" #include "session.h" #include "sort.h" #include "util.h" @@ -19,7 +21,7 @@ static int perf_session__open(struct perf_session *self, bool force) self->fd_pipe = true; self->fd = STDIN_FILENO; - if (perf_header__read(self, self->fd) < 0) + if (perf_session__read_header(self, self->fd) < 0) pr_err("incompatible file format"); return 0; @@ -51,7 +53,7 @@ static int perf_session__open(struct perf_session *self, bool force) goto out_close; } - if (perf_header__read(self, self->fd) < 0) { + if (perf_session__read_header(self, self->fd) < 0) { pr_err("incompatible file format"); goto out_close; } @@ -67,7 +69,7 @@ out_close: static void perf_session__id_header_size(struct perf_session *session) { - struct sample_data *data; + struct perf_sample *data; u64 sample_type = session->sample_type; u16 size = 0; @@ -92,21 +94,10 @@ out: session->id_hdr_size = size; } -void perf_session__set_sample_id_all(struct perf_session *session, bool value) -{ - session->sample_id_all = value; - perf_session__id_header_size(session); -} - -void perf_session__set_sample_type(struct perf_session *session, u64 type) -{ - session->sample_type = type; -} - void perf_session__update_sample_type(struct perf_session *self) { - self->sample_type = perf_header__sample_type(&self->header); - self->sample_id_all = perf_header__sample_id_all(&self->header); + self->sample_type = perf_evlist__sample_type(self->evlist); + self->sample_id_all = perf_evlist__sample_id_all(self->evlist); perf_session__id_header_size(self); } @@ -135,13 +126,9 @@ struct perf_session *perf_session__new(const char *filename, int mode, if (self == NULL) goto out; - if (perf_header__init(&self->header) < 0) - goto out_free; - memcpy(self->filename, filename, len); self->threads = RB_ROOT; INIT_LIST_HEAD(&self->dead_threads); - self->hists_tree = RB_ROOT; self->last_match = NULL; /* * On 64bit we can mmap the data file in one go. No need for tiny mmap @@ -162,17 +149,16 @@ struct perf_session *perf_session__new(const char *filename, int mode, if (mode == O_RDONLY) { if (perf_session__open(self, force) < 0) goto out_delete; + perf_session__update_sample_type(self); } else if (mode == O_WRONLY) { /* * In O_RDONLY mode this will be performed when reading the - * kernel MMAP event, in event__process_mmap(). + * kernel MMAP event, in perf_event__process_mmap(). */ if (perf_session__create_kernel_maps(self) < 0) goto out_delete; } - perf_session__update_sample_type(self); - if (ops && ops->ordering_requires_timestamps && ops->ordered_samples && !self->sample_id_all) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); @@ -181,9 +167,6 @@ struct perf_session *perf_session__new(const char *filename, int mode, out: return self; -out_free: - free(self); - return NULL; out_delete: perf_session__delete(self); return NULL; @@ -214,7 +197,6 @@ static void perf_session__delete_threads(struct perf_session *self) void perf_session__delete(struct perf_session *self) { - perf_header__exit(&self->header); perf_session__destroy_kernel_maps(self); perf_session__delete_dead_threads(self); perf_session__delete_threads(self); @@ -242,17 +224,16 @@ static bool symbol__match_parent_regex(struct symbol *sym) return 0; } -struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent) +int perf_session__resolve_callchain(struct perf_session *self, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent) { u8 cpumode = PERF_RECORD_MISC_USER; unsigned int i; - struct map_symbol *syms = calloc(chain->nr, sizeof(*syms)); + int err; - if (!syms) - return NULL; + callchain_cursor_reset(&self->callchain_cursor); for (i = 0; i < chain->nr; i++) { u64 ip = chain->ips[i]; @@ -281,30 +262,33 @@ struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, *parent = al.sym; if (!symbol_conf.use_callchain) break; - syms[i].map = al.map; - syms[i].sym = al.sym; } + + err = callchain_cursor_append(&self->callchain_cursor, + ip, al.map, al.sym); + if (err) + return err; } - return syms; + return 0; } -static int process_event_synth_stub(event_t *event __used, +static int process_event_synth_stub(union perf_event *event __used, struct perf_session *session __used) { dump_printf(": unhandled!\n"); return 0; } -static int process_event_stub(event_t *event __used, - struct sample_data *sample __used, +static int process_event_stub(union perf_event *event __used, + struct perf_sample *sample __used, struct perf_session *session __used) { dump_printf(": unhandled!\n"); return 0; } -static int process_finished_round_stub(event_t *event __used, +static int process_finished_round_stub(union perf_event *event __used, struct perf_session *session __used, struct perf_event_ops *ops __used) { @@ -312,7 +296,7 @@ static int process_finished_round_stub(event_t *event __used, return 0; } -static int process_finished_round(event_t *event, +static int process_finished_round(union perf_event *event, struct perf_session *session, struct perf_event_ops *ops); @@ -329,7 +313,7 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler) if (handler->exit == NULL) handler->exit = process_event_stub; if (handler->lost == NULL) - handler->lost = event__process_lost; + handler->lost = perf_event__process_lost; if (handler->read == NULL) handler->read = process_event_stub; if (handler->throttle == NULL) @@ -363,98 +347,98 @@ void mem_bswap_64(void *src, int byte_size) } } -static void event__all64_swap(event_t *self) +static void perf_event__all64_swap(union perf_event *event) { - struct perf_event_header *hdr = &self->header; - mem_bswap_64(hdr + 1, self->header.size - sizeof(*hdr)); + struct perf_event_header *hdr = &event->header; + mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr)); } -static void event__comm_swap(event_t *self) +static void perf_event__comm_swap(union perf_event *event) { - self->comm.pid = bswap_32(self->comm.pid); - self->comm.tid = bswap_32(self->comm.tid); + event->comm.pid = bswap_32(event->comm.pid); + event->comm.tid = bswap_32(event->comm.tid); } -static void event__mmap_swap(event_t *self) +static void perf_event__mmap_swap(union perf_event *event) { - self->mmap.pid = bswap_32(self->mmap.pid); - self->mmap.tid = bswap_32(self->mmap.tid); - self->mmap.start = bswap_64(self->mmap.start); - self->mmap.len = bswap_64(self->mmap.len); - self->mmap.pgoff = bswap_64(self->mmap.pgoff); + event->mmap.pid = bswap_32(event->mmap.pid); + event->mmap.tid = bswap_32(event->mmap.tid); + event->mmap.start = bswap_64(event->mmap.start); + event->mmap.len = bswap_64(event->mmap.len); + event->mmap.pgoff = bswap_64(event->mmap.pgoff); } -static void event__task_swap(event_t *self) +static void perf_event__task_swap(union perf_event *event) { - self->fork.pid = bswap_32(self->fork.pid); - self->fork.tid = bswap_32(self->fork.tid); - self->fork.ppid = bswap_32(self->fork.ppid); - self->fork.ptid = bswap_32(self->fork.ptid); - self->fork.time = bswap_64(self->fork.time); + event->fork.pid = bswap_32(event->fork.pid); + event->fork.tid = bswap_32(event->fork.tid); + event->fork.ppid = bswap_32(event->fork.ppid); + event->fork.ptid = bswap_32(event->fork.ptid); + event->fork.time = bswap_64(event->fork.time); } -static void event__read_swap(event_t *self) +static void perf_event__read_swap(union perf_event *event) { - self->read.pid = bswap_32(self->read.pid); - self->read.tid = bswap_32(self->read.tid); - self->read.value = bswap_64(self->read.value); - self->read.time_enabled = bswap_64(self->read.time_enabled); - self->read.time_running = bswap_64(self->read.time_running); - self->read.id = bswap_64(self->read.id); + event->read.pid = bswap_32(event->read.pid); + event->read.tid = bswap_32(event->read.tid); + event->read.value = bswap_64(event->read.value); + event->read.time_enabled = bswap_64(event->read.time_enabled); + event->read.time_running = bswap_64(event->read.time_running); + event->read.id = bswap_64(event->read.id); } -static void event__attr_swap(event_t *self) +static void perf_event__attr_swap(union perf_event *event) { size_t size; - self->attr.attr.type = bswap_32(self->attr.attr.type); - self->attr.attr.size = bswap_32(self->attr.attr.size); - self->attr.attr.config = bswap_64(self->attr.attr.config); - self->attr.attr.sample_period = bswap_64(self->attr.attr.sample_period); - self->attr.attr.sample_type = bswap_64(self->attr.attr.sample_type); - self->attr.attr.read_format = bswap_64(self->attr.attr.read_format); - self->attr.attr.wakeup_events = bswap_32(self->attr.attr.wakeup_events); - self->attr.attr.bp_type = bswap_32(self->attr.attr.bp_type); - self->attr.attr.bp_addr = bswap_64(self->attr.attr.bp_addr); - self->attr.attr.bp_len = bswap_64(self->attr.attr.bp_len); - - size = self->header.size; - size -= (void *)&self->attr.id - (void *)self; - mem_bswap_64(self->attr.id, size); + event->attr.attr.type = bswap_32(event->attr.attr.type); + event->attr.attr.size = bswap_32(event->attr.attr.size); + event->attr.attr.config = bswap_64(event->attr.attr.config); + event->attr.attr.sample_period = bswap_64(event->attr.attr.sample_period); + event->attr.attr.sample_type = bswap_64(event->attr.attr.sample_type); + event->attr.attr.read_format = bswap_64(event->attr.attr.read_format); + event->attr.attr.wakeup_events = bswap_32(event->attr.attr.wakeup_events); + event->attr.attr.bp_type = bswap_32(event->attr.attr.bp_type); + event->attr.attr.bp_addr = bswap_64(event->attr.attr.bp_addr); + event->attr.attr.bp_len = bswap_64(event->attr.attr.bp_len); + + size = event->header.size; + size -= (void *)&event->attr.id - (void *)event; + mem_bswap_64(event->attr.id, size); } -static void event__event_type_swap(event_t *self) +static void perf_event__event_type_swap(union perf_event *event) { - self->event_type.event_type.event_id = - bswap_64(self->event_type.event_type.event_id); + event->event_type.event_type.event_id = + bswap_64(event->event_type.event_type.event_id); } -static void event__tracing_data_swap(event_t *self) +static void perf_event__tracing_data_swap(union perf_event *event) { - self->tracing_data.size = bswap_32(self->tracing_data.size); + event->tracing_data.size = bswap_32(event->tracing_data.size); } -typedef void (*event__swap_op)(event_t *self); - -static event__swap_op event__swap_ops[] = { - [PERF_RECORD_MMAP] = event__mmap_swap, - [PERF_RECORD_COMM] = event__comm_swap, - [PERF_RECORD_FORK] = event__task_swap, - [PERF_RECORD_EXIT] = event__task_swap, - [PERF_RECORD_LOST] = event__all64_swap, - [PERF_RECORD_READ] = event__read_swap, - [PERF_RECORD_SAMPLE] = event__all64_swap, - [PERF_RECORD_HEADER_ATTR] = event__attr_swap, - [PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap, - [PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap, - [PERF_RECORD_HEADER_BUILD_ID] = NULL, - [PERF_RECORD_HEADER_MAX] = NULL, +typedef void (*perf_event__swap_op)(union perf_event *event); + +static perf_event__swap_op perf_event__swap_ops[] = { + [PERF_RECORD_MMAP] = perf_event__mmap_swap, + [PERF_RECORD_COMM] = perf_event__comm_swap, + [PERF_RECORD_FORK] = perf_event__task_swap, + [PERF_RECORD_EXIT] = perf_event__task_swap, + [PERF_RECORD_LOST] = perf_event__all64_swap, + [PERF_RECORD_READ] = perf_event__read_swap, + [PERF_RECORD_SAMPLE] = perf_event__all64_swap, + [PERF_RECORD_HEADER_ATTR] = perf_event__attr_swap, + [PERF_RECORD_HEADER_EVENT_TYPE] = perf_event__event_type_swap, + [PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap, + [PERF_RECORD_HEADER_BUILD_ID] = NULL, + [PERF_RECORD_HEADER_MAX] = NULL, }; struct sample_queue { u64 timestamp; u64 file_offset; - event_t *event; + union perf_event *event; struct list_head list; }; @@ -472,8 +456,8 @@ static void perf_session_free_sample_buffers(struct perf_session *session) } static int perf_session_deliver_event(struct perf_session *session, - event_t *event, - struct sample_data *sample, + union perf_event *event, + struct perf_sample *sample, struct perf_event_ops *ops, u64 file_offset); @@ -483,7 +467,7 @@ static void flush_sample_queue(struct perf_session *s, struct ordered_samples *os = &s->ordered_samples; struct list_head *head = &os->samples; struct sample_queue *tmp, *iter; - struct sample_data sample; + struct perf_sample sample; u64 limit = os->next_flush; u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL; @@ -494,7 +478,7 @@ static void flush_sample_queue(struct perf_session *s, if (iter->timestamp > limit) break; - event__parse_sample(iter->event, s, &sample); + perf_session__parse_sample(s, iter->event, &sample); perf_session_deliver_event(s, iter->event, &sample, ops, iter->file_offset); @@ -550,7 +534,7 @@ static void flush_sample_queue(struct perf_session *s, * Flush every events below timestamp 7 * etc... */ -static int process_finished_round(event_t *event __used, +static int process_finished_round(union perf_event *event __used, struct perf_session *session, struct perf_event_ops *ops) { @@ -607,12 +591,12 @@ static void __queue_event(struct sample_queue *new, struct perf_session *s) #define MAX_SAMPLE_BUFFER (64 * 1024 / sizeof(struct sample_queue)) -static int perf_session_queue_event(struct perf_session *s, event_t *event, - struct sample_data *data, u64 file_offset) +static int perf_session_queue_event(struct perf_session *s, union perf_event *event, + struct perf_sample *sample, u64 file_offset) { struct ordered_samples *os = &s->ordered_samples; struct list_head *sc = &os->sample_cache; - u64 timestamp = data->time; + u64 timestamp = sample->time; struct sample_queue *new; if (!timestamp || timestamp == ~0ULL) @@ -648,7 +632,7 @@ static int perf_session_queue_event(struct perf_session *s, event_t *event, return 0; } -static void callchain__printf(struct sample_data *sample) +static void callchain__printf(struct perf_sample *sample) { unsigned int i; @@ -660,8 +644,8 @@ static void callchain__printf(struct sample_data *sample) } static void perf_session__print_tstamp(struct perf_session *session, - event_t *event, - struct sample_data *sample) + union perf_event *event, + struct perf_sample *sample) { if (event->header.type != PERF_RECORD_SAMPLE && !session->sample_id_all) { @@ -676,8 +660,8 @@ static void perf_session__print_tstamp(struct perf_session *session, printf("%" PRIu64 " ", sample->time); } -static void dump_event(struct perf_session *session, event_t *event, - u64 file_offset, struct sample_data *sample) +static void dump_event(struct perf_session *session, union perf_event *event, + u64 file_offset, struct perf_sample *sample) { if (!dump_trace) return; @@ -691,11 +675,11 @@ static void dump_event(struct perf_session *session, event_t *event, perf_session__print_tstamp(session, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, - event->header.size, event__get_event_name(event->header.type)); + event->header.size, perf_event__name(event->header.type)); } -static void dump_sample(struct perf_session *session, event_t *event, - struct sample_data *sample) +static void dump_sample(struct perf_session *session, union perf_event *event, + struct perf_sample *sample) { if (!dump_trace) return; @@ -709,8 +693,8 @@ static void dump_sample(struct perf_session *session, event_t *event, } static int perf_session_deliver_event(struct perf_session *session, - event_t *event, - struct sample_data *sample, + union perf_event *event, + struct perf_sample *sample, struct perf_event_ops *ops, u64 file_offset) { @@ -743,7 +727,7 @@ static int perf_session_deliver_event(struct perf_session *session, } static int perf_session__preprocess_sample(struct perf_session *session, - event_t *event, struct sample_data *sample) + union perf_event *event, struct perf_sample *sample) { if (event->header.type != PERF_RECORD_SAMPLE || !(session->sample_type & PERF_SAMPLE_CALLCHAIN)) @@ -758,7 +742,7 @@ static int perf_session__preprocess_sample(struct perf_session *session, return 0; } -static int perf_session__process_user_event(struct perf_session *session, event_t *event, +static int perf_session__process_user_event(struct perf_session *session, union perf_event *event, struct perf_event_ops *ops, u64 file_offset) { dump_event(session, event, file_offset, NULL); @@ -783,15 +767,16 @@ static int perf_session__process_user_event(struct perf_session *session, event_ } static int perf_session__process_event(struct perf_session *session, - event_t *event, + union perf_event *event, struct perf_event_ops *ops, u64 file_offset) { - struct sample_data sample; + struct perf_sample sample; int ret; - if (session->header.needs_swap && event__swap_ops[event->header.type]) - event__swap_ops[event->header.type](event); + if (session->header.needs_swap && + perf_event__swap_ops[event->header.type]) + perf_event__swap_ops[event->header.type](event); if (event->header.type >= PERF_RECORD_HEADER_MAX) return -EINVAL; @@ -804,7 +789,7 @@ static int perf_session__process_event(struct perf_session *session, /* * For all kernel events we get the sample data */ - event__parse_sample(event, session, &sample); + perf_session__parse_sample(session, event, &sample); /* Preprocess sample records - precheck callchains */ if (perf_session__preprocess_sample(session, event, &sample)) @@ -843,7 +828,7 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se static void perf_session__warn_about_errors(const struct perf_session *session, const struct perf_event_ops *ops) { - if (ops->lost == event__process_lost && + if (ops->lost == perf_event__process_lost && session->hists.stats.total_lost != 0) { ui__warning("Processed %" PRIu64 " events and LOST %" PRIu64 "!\n\nCheck IO/CPU overload!\n\n", @@ -875,7 +860,7 @@ volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *self, struct perf_event_ops *ops) { - event_t event; + union perf_event event; uint32_t size; int skip = 0; u64 head; @@ -956,7 +941,7 @@ int __perf_session__process_events(struct perf_session *session, struct ui_progress *progress; size_t page_size, mmap_size; char *buf, *mmaps[8]; - event_t *event; + union perf_event *event; uint32_t size; perf_event_ops__fill_defaults(ops); @@ -1001,7 +986,7 @@ remap: file_pos = file_offset + head; more: - event = (event_t *)(buf + head); + event = (union perf_event *)(buf + head); if (session->header.needs_swap) perf_event_header__bswap(&event->header); @@ -1134,3 +1119,18 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, size_t ret = machine__fprintf_dsos_buildid(&self->host_machine, fp, with_hits); return ret + machines__fprintf_dsos_buildid(&self->machines, fp, with_hits); } + +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp) +{ + struct perf_evsel *pos; + size_t ret = fprintf(fp, "Aggregated stats:\n"); + + ret += hists__fprintf_nr_events(&session->hists, fp); + + list_for_each_entry(pos, &session->evlist->entries, node) { + ret += fprintf(fp, "%s stats:\n", event_name(pos)); + ret += hists__fprintf_nr_events(&pos->hists, fp); + } + + return ret; +} diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index decd83f..b5b148b 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -34,12 +34,12 @@ struct perf_session { struct thread *last_match; struct machine host_machine; struct rb_root machines; - struct rb_root hists_tree; + struct perf_evlist *evlist; /* - * FIXME: should point to the first entry in hists_tree and - * be a hists instance. Right now its only 'report' - * that is using ->hists_tree while all the rest use - * ->hists. + * FIXME: Need to split this up further, we need global + * stats + per event stats. 'perf diff' also needs + * to properly support multiple events in a single + * perf.data file. */ struct hists hists; u64 sample_type; @@ -51,15 +51,17 @@ struct perf_session { int cwdlen; char *cwd; struct ordered_samples ordered_samples; - char filename[0]; + struct callchain_cursor callchain_cursor; + char filename[0]; }; struct perf_event_ops; -typedef int (*event_op)(event_t *self, struct sample_data *sample, +typedef int (*event_op)(union perf_event *self, struct perf_sample *sample, struct perf_session *session); -typedef int (*event_synth_op)(event_t *self, struct perf_session *session); -typedef int (*event_op2)(event_t *self, struct perf_session *session, +typedef int (*event_synth_op)(union perf_event *self, + struct perf_session *session); +typedef int (*event_op2)(union perf_event *self, struct perf_session *session, struct perf_event_ops *ops); struct perf_event_ops { @@ -94,10 +96,10 @@ int __perf_session__process_events(struct perf_session *self, int perf_session__process_events(struct perf_session *self, struct perf_event_ops *event_ops); -struct map_symbol *perf_session__resolve_callchain(struct perf_session *self, - struct thread *thread, - struct ip_callchain *chain, - struct symbol **parent); +int perf_session__resolve_callchain(struct perf_session *self, + struct thread *thread, + struct ip_callchain *chain, + struct symbol **parent); bool perf_session__has_traces(struct perf_session *self, const char *msg); @@ -110,8 +112,6 @@ void mem_bswap_64(void *src, int byte_size); int perf_session__create_kernel_maps(struct perf_session *self); void perf_session__update_sample_type(struct perf_session *self); -void perf_session__set_sample_id_all(struct perf_session *session, bool value); -void perf_session__set_sample_type(struct perf_session *session, u64 type); void perf_session__remove_thread(struct perf_session *self, struct thread *th); static inline @@ -149,9 +149,14 @@ size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp); size_t perf_session__fprintf_dsos_buildid(struct perf_session *self, FILE *fp, bool with_hits); -static inline -size_t perf_session__fprintf_nr_events(struct perf_session *self, FILE *fp) +size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); + +static inline int perf_session__parse_sample(struct perf_session *session, + const union perf_event *event, + struct perf_sample *sample) { - return hists__fprintf_nr_events(&self->hists, fp); + return perf_event__parse_sample(event, session->sample_type, + session->sample_id_all, sample); } + #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py new file mode 100644 index 0000000..e24ffad --- /dev/null +++ b/tools/perf/util/setup.py @@ -0,0 +1,19 @@ +#!/usr/bin/python2 + +from distutils.core import setup, Extension + +perf = Extension('perf', + sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c', + 'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c', + 'util/util.c', 'util/xyarray.c', 'util/cgroup.c'], + include_dirs = ['util/include'], + extra_compile_args = ['-fno-strict-aliasing', '-Wno-write-strings']) + +setup(name='perf', + version='0.1', + description='Interface with the Linux profiling infrastructure', + author='Arnaldo Carvalho de Melo', + author_email='acme@redhat.com', + license='GPLv2', + url='http://perf.wiki.kernel.org', + ext_modules=[perf]) diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c new file mode 100644 index 0000000..834c8eb --- /dev/null +++ b/tools/perf/util/strfilter.c @@ -0,0 +1,199 @@ +#include "util.h" +#include "string.h" +#include "strfilter.h" + +/* Operators */ +static const char *OP_and = "&"; /* Logical AND */ +static const char *OP_or = "|"; /* Logical OR */ +static const char *OP_not = "!"; /* Logical NOT */ + +#define is_operator(c) ((c) == '|' || (c) == '&' || (c) == '!') +#define is_separator(c) (is_operator(c) || (c) == '(' || (c) == ')') + +static void strfilter_node__delete(struct strfilter_node *self) +{ + if (self) { + if (self->p && !is_operator(*self->p)) + free((char *)self->p); + strfilter_node__delete(self->l); + strfilter_node__delete(self->r); + free(self); + } +} + +void strfilter__delete(struct strfilter *self) +{ + if (self) { + strfilter_node__delete(self->root); + free(self); + } +} + +static const char *get_token(const char *s, const char **e) +{ + const char *p; + + while (isspace(*s)) /* Skip spaces */ + s++; + + if (*s == '\0') { + p = s; + goto end; + } + + p = s + 1; + if (!is_separator(*s)) { + /* End search */ +retry: + while (*p && !is_separator(*p) && !isspace(*p)) + p++; + /* Escape and special case: '!' is also used in glob pattern */ + if (*(p - 1) == '\\' || (*p == '!' && *(p - 1) == '[')) { + p++; + goto retry; + } + } +end: + *e = p; + return s; +} + +static struct strfilter_node *strfilter_node__alloc(const char *op, + struct strfilter_node *l, + struct strfilter_node *r) +{ + struct strfilter_node *ret = zalloc(sizeof(struct strfilter_node)); + + if (ret) { + ret->p = op; + ret->l = l; + ret->r = r; + } + + return ret; +} + +static struct strfilter_node *strfilter_node__new(const char *s, + const char **ep) +{ + struct strfilter_node root, *cur, *last_op; + const char *e; + + if (!s) + return NULL; + + memset(&root, 0, sizeof(root)); + last_op = cur = &root; + + s = get_token(s, &e); + while (*s != '\0' && *s != ')') { + switch (*s) { + case '&': /* Exchg last OP->r with AND */ + if (!cur->r || !last_op->r) + goto error; + cur = strfilter_node__alloc(OP_and, last_op->r, NULL); + if (!cur) + goto nomem; + last_op->r = cur; + last_op = cur; + break; + case '|': /* Exchg the root with OR */ + if (!cur->r || !root.r) + goto error; + cur = strfilter_node__alloc(OP_or, root.r, NULL); + if (!cur) + goto nomem; + root.r = cur; + last_op = cur; + break; + case '!': /* Add NOT as a leaf node */ + if (cur->r) + goto error; + cur->r = strfilter_node__alloc(OP_not, NULL, NULL); + if (!cur->r) + goto nomem; + cur = cur->r; + break; + case '(': /* Recursively parses inside the parenthesis */ + if (cur->r) + goto error; + cur->r = strfilter_node__new(s + 1, &s); + if (!s) + goto nomem; + if (!cur->r || *s != ')') + goto error; + e = s + 1; + break; + default: + if (cur->r) + goto error; + cur->r = strfilter_node__alloc(NULL, NULL, NULL); + if (!cur->r) + goto nomem; + cur->r->p = strndup(s, e - s); + if (!cur->r->p) + goto nomem; + } + s = get_token(e, &e); + } + if (!cur->r) + goto error; + *ep = s; + return root.r; +nomem: + s = NULL; +error: + *ep = s; + strfilter_node__delete(root.r); + return NULL; +} + +/* + * Parse filter rule and return new strfilter. + * Return NULL if fail, and *ep == NULL if memory allocation failed. + */ +struct strfilter *strfilter__new(const char *rules, const char **err) +{ + struct strfilter *ret = zalloc(sizeof(struct strfilter)); + const char *ep = NULL; + + if (ret) + ret->root = strfilter_node__new(rules, &ep); + + if (!ret || !ret->root || *ep != '\0') { + if (err) + *err = ep; + strfilter__delete(ret); + ret = NULL; + } + + return ret; +} + +static bool strfilter_node__compare(struct strfilter_node *self, + const char *str) +{ + if (!self || !self->p) + return false; + + switch (*self->p) { + case '|': /* OR */ + return strfilter_node__compare(self->l, str) || + strfilter_node__compare(self->r, str); + case '&': /* AND */ + return strfilter_node__compare(self->l, str) && + strfilter_node__compare(self->r, str); + case '!': /* NOT */ + return !strfilter_node__compare(self->r, str); + default: + return strglobmatch(str, self->p); + } +} + +/* Return true if STR matches the filter rules */ +bool strfilter__compare(struct strfilter *self, const char *str) +{ + if (!self) + return false; + return strfilter_node__compare(self->root, str); +} diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h new file mode 100644 index 0000000..00f58a7 --- /dev/null +++ b/tools/perf/util/strfilter.h @@ -0,0 +1,48 @@ +#ifndef __PERF_STRFILTER_H +#define __PERF_STRFILTER_H +/* General purpose glob matching filter */ + +#include <linux/list.h> +#include <stdbool.h> + +/* A node of string filter */ +struct strfilter_node { + struct strfilter_node *l; /* Tree left branche (for &,|) */ + struct strfilter_node *r; /* Tree right branche (for !,&,|) */ + const char *p; /* Operator or rule */ +}; + +/* String filter */ +struct strfilter { + struct strfilter_node *root; +}; + +/** + * strfilter__new - Create a new string filter + * @rules: Filter rule, which is a combination of glob expressions. + * @err: Pointer which points an error detected on @rules + * + * Parse @rules and return new strfilter. Return NULL if an error detected. + * In that case, *@err will indicate where it is detected, and *@err is NULL + * if a memory allocation is failed. + */ +struct strfilter *strfilter__new(const char *rules, const char **err); + +/** + * strfilter__compare - compare given string and a string filter + * @self: String filter + * @str: target string + * + * Compare @str and @self. Return true if the str match the rule + */ +bool strfilter__compare(struct strfilter *self, const char *str); + +/** + * strfilter__delete - delete a string filter + * @self: String filter to delete + * + * Delete @self. + */ +void strfilter__delete(struct strfilter *self); + +#endif diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index fb737fe..96c8660 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -456,9 +456,9 @@ void svg_legenda(void) return; svg_legenda_box(0, "Running", "sample"); - svg_legenda_box(100, "Idle","rect.c1"); - svg_legenda_box(200, "Deeper Idle", "rect.c3"); - svg_legenda_box(350, "Deepest Idle", "rect.c6"); + svg_legenda_box(100, "Idle","c1"); + svg_legenda_box(200, "Deeper Idle", "c3"); + svg_legenda_box(350, "Deepest Idle", "c6"); svg_legenda_box(550, "Sleeping", "process2"); svg_legenda_box(650, "Waiting for cpu", "waiting"); svg_legenda_box(800, "Blocked on IO", "blocked"); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 7821d0e..00014e3 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -207,7 +207,6 @@ struct dso *dso__new(const char *name) dso__set_short_name(self, self->name); for (i = 0; i < MAP__NR_TYPES; ++i) self->symbols[i] = self->symbol_names[i] = RB_ROOT; - self->slen_calculated = 0; self->origin = DSO__ORIG_NOT_FOUND; self->loaded = 0; self->sorted_by_name = 0; @@ -1525,8 +1524,8 @@ int dso__load(struct dso *self, struct map *map, symbol_filter_t filter) symbol_conf.symfs, self->long_name); break; case DSO__ORIG_GUEST_KMODULE: - if (map->groups && map->groups->machine) - root_dir = map->groups->machine->root_dir; + if (map->groups && machine) + root_dir = machine->root_dir; else root_dir = ""; snprintf(name, size, "%s%s%s", symbol_conf.symfs, @@ -1836,7 +1835,7 @@ int dso__load_vmlinux(struct dso *self, struct map *map, int err = -1, fd; char symfs_vmlinux[PATH_MAX]; - snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s/%s", + snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s", symbol_conf.symfs, vmlinux); fd = open(symfs_vmlinux, O_RDONLY); if (fd < 0) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 670cd1c..4d7ed09 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -132,7 +132,6 @@ struct dso { struct rb_root symbol_names[MAP__NR_TYPES]; enum dso_kernel_type kernel; u8 adjust_symbols:1; - u8 slen_calculated:1; u8 has_build_id:1; u8 hit:1; u8 annotate_warned:1; diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 00f4ead..d5d3b22 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -7,61 +7,6 @@ #include "util.h" #include "debug.h" -/* Skip "." and ".." directories */ -static int filter(const struct dirent *dir) -{ - if (dir->d_name[0] == '.') - return 0; - else - return 1; -} - -struct thread_map *thread_map__new_by_pid(pid_t pid) -{ - struct thread_map *threads; - char name[256]; - int items; - struct dirent **namelist = NULL; - int i; - - sprintf(name, "/proc/%d/task", pid); - items = scandir(name, &namelist, filter, NULL); - if (items <= 0) - return NULL; - - threads = malloc(sizeof(*threads) + sizeof(pid_t) * items); - if (threads != NULL) { - for (i = 0; i < items; i++) - threads->map[i] = atoi(namelist[i]->d_name); - threads->nr = items; - } - - for (i=0; i<items; i++) - free(namelist[i]); - free(namelist); - - return threads; -} - -struct thread_map *thread_map__new_by_tid(pid_t tid) -{ - struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t)); - - if (threads != NULL) { - threads->map[0] = tid; - threads->nr = 1; - } - - return threads; -} - -struct thread_map *thread_map__new(pid_t pid, pid_t tid) -{ - if (pid != -1) - return thread_map__new_by_pid(pid); - return thread_map__new_by_tid(tid); -} - static struct thread *thread__new(pid_t pid) { struct thread *self = zalloc(sizeof(*self)); diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index d757410..e5f2401 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -18,24 +18,10 @@ struct thread { int comm_len; }; -struct thread_map { - int nr; - int map[]; -}; - struct perf_session; void thread__delete(struct thread *self); -struct thread_map *thread_map__new_by_pid(pid_t pid); -struct thread_map *thread_map__new_by_tid(pid_t tid); -struct thread_map *thread_map__new(pid_t pid, pid_t tid); - -static inline void thread_map__delete(struct thread_map *threads) -{ - free(threads); -} - int thread__set_comm(struct thread *self, const char *comm); int thread__comm_len(struct thread *self); struct thread *perf_session__findnew(struct perf_session *self, pid_t pid); diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c new file mode 100644 index 0000000..a5df131 --- /dev/null +++ b/tools/perf/util/thread_map.c @@ -0,0 +1,64 @@ +#include <dirent.h> +#include <stdlib.h> +#include <stdio.h> +#include "thread_map.h" + +/* Skip "." and ".." directories */ +static int filter(const struct dirent *dir) +{ + if (dir->d_name[0] == '.') + return 0; + else + return 1; +} + +struct thread_map *thread_map__new_by_pid(pid_t pid) +{ + struct thread_map *threads; + char name[256]; + int items; + struct dirent **namelist = NULL; + int i; + + sprintf(name, "/proc/%d/task", pid); + items = scandir(name, &namelist, filter, NULL); + if (items <= 0) + return NULL; + + threads = malloc(sizeof(*threads) + sizeof(pid_t) * items); + if (threads != NULL) { + for (i = 0; i < items; i++) + threads->map[i] = atoi(namelist[i]->d_name); + threads->nr = items; + } + + for (i=0; i<items; i++) + free(namelist[i]); + free(namelist); + + return threads; +} + +struct thread_map *thread_map__new_by_tid(pid_t tid) +{ + struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t)); + + if (threads != NULL) { + threads->map[0] = tid; + threads->nr = 1; + } + + return threads; +} + +struct thread_map *thread_map__new(pid_t pid, pid_t tid) +{ + if (pid != -1) + return thread_map__new_by_pid(pid); + return thread_map__new_by_tid(tid); +} + +void thread_map__delete(struct thread_map *threads) +{ + free(threads); +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h new file mode 100644 index 0000000..3cb9073 --- /dev/null +++ b/tools/perf/util/thread_map.h @@ -0,0 +1,15 @@ +#ifndef __PERF_THREAD_MAP_H +#define __PERF_THREAD_MAP_H + +#include <sys/types.h> + +struct thread_map { + int nr; + int map[]; +}; + +struct thread_map *thread_map__new_by_pid(pid_t pid); +struct thread_map *thread_map__new_by_tid(pid_t tid); +struct thread_map *thread_map__new(pid_t pid, pid_t tid); +void thread_map__delete(struct thread_map *threads); +#endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c new file mode 100644 index 0000000..75cfe4d --- /dev/null +++ b/tools/perf/util/top.c @@ -0,0 +1,238 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Refactored from builtin-top.c, see that files for further copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "cpumap.h" +#include "event.h" +#include "evlist.h" +#include "evsel.h" +#include "parse-events.h" +#include "symbol.h" +#include "top.h" +#include <inttypes.h> + +/* + * Ordering weight: count-1 * count-2 * ... / count-n + */ +static double sym_weight(const struct sym_entry *sym, struct perf_top *top) +{ + double weight = sym->snap_count; + int counter; + + if (!top->display_weighted) + return weight; + + for (counter = 1; counter < top->evlist->nr_entries - 1; counter++) + weight *= sym->count[counter]; + + weight /= (sym->count[counter] + 1); + + return weight; +} + +static void perf_top__remove_active_sym(struct perf_top *top, struct sym_entry *syme) +{ + pthread_mutex_lock(&top->active_symbols_lock); + list_del_init(&syme->node); + pthread_mutex_unlock(&top->active_symbols_lock); +} + +static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) +{ + struct rb_node **p = &tree->rb_node; + struct rb_node *parent = NULL; + struct sym_entry *iter; + + while (*p != NULL) { + parent = *p; + iter = rb_entry(parent, struct sym_entry, rb_node); + + if (se->weight > iter->weight) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&se->rb_node, parent, p); + rb_insert_color(&se->rb_node, tree); +} + +#define SNPRINTF(buf, size, fmt, args...) \ +({ \ + size_t r = snprintf(buf, size, fmt, ## args); \ + r > size ? size : r; \ +}) + +size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) +{ + struct perf_evsel *counter; + float samples_per_sec = top->samples / top->delay_secs; + float ksamples_per_sec = top->kernel_samples / top->delay_secs; + float esamples_percent = (100.0 * top->exact_samples) / top->samples; + size_t ret = 0; + + if (!perf_guest) { + ret = SNPRINTF(bf, size, + " PerfTop:%8.0f irqs/sec kernel:%4.1f%%" + " exact: %4.1f%% [", samples_per_sec, + 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) / + samples_per_sec)), + esamples_percent); + } else { + float us_samples_per_sec = top->us_samples / top->delay_secs; + float guest_kernel_samples_per_sec = top->guest_kernel_samples / top->delay_secs; + float guest_us_samples_per_sec = top->guest_us_samples / top->delay_secs; + + ret = SNPRINTF(bf, size, + " PerfTop:%8.0f irqs/sec kernel:%4.1f%% us:%4.1f%%" + " guest kernel:%4.1f%% guest us:%4.1f%%" + " exact: %4.1f%% [", samples_per_sec, + 100.0 - (100.0 * ((samples_per_sec - ksamples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - us_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_kernel_samples_per_sec) / + samples_per_sec)), + 100.0 - (100.0 * ((samples_per_sec - + guest_us_samples_per_sec) / + samples_per_sec)), + esamples_percent); + } + + if (top->evlist->nr_entries == 1 || !top->display_weighted) { + struct perf_evsel *first; + first = list_entry(top->evlist->entries.next, struct perf_evsel, node); + ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ", + (uint64_t)first->attr.sample_period, + top->freq ? "Hz" : ""); + } + + if (!top->display_weighted) { + ret += SNPRINTF(bf + ret, size - ret, "%s", + event_name(top->sym_evsel)); + } else { + /* + * Don't let events eat all the space. Leaving 30 bytes + * for the rest should be enough. + */ + size_t last_pos = size - 30; + + list_for_each_entry(counter, &top->evlist->entries, node) { + ret += SNPRINTF(bf + ret, size - ret, "%s%s", + counter->idx ? "/" : "", + event_name(counter)); + if (ret > last_pos) { + sprintf(bf + last_pos - 3, ".."); + ret = last_pos - 1; + break; + } + } + } + + ret += SNPRINTF(bf + ret, size - ret, "], "); + + if (top->target_pid != -1) + ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %d", + top->target_pid); + else if (top->target_tid != -1) + ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %d", + top->target_tid); + else + ret += SNPRINTF(bf + ret, size - ret, " (all"); + + if (top->cpu_list) + ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", + top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list); + else { + if (top->target_tid != -1) + ret += SNPRINTF(bf + ret, size - ret, ")"); + else + ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", + top->evlist->cpus->nr, + top->evlist->cpus->nr > 1 ? "s" : ""); + } + + return ret; +} + +void perf_top__reset_sample_counters(struct perf_top *top) +{ + top->samples = top->us_samples = top->kernel_samples = + top->exact_samples = top->guest_kernel_samples = + top->guest_us_samples = 0; +} + +float perf_top__decay_samples(struct perf_top *top, struct rb_root *root) +{ + struct sym_entry *syme, *n; + float sum_ksamples = 0.0; + int snap = !top->display_weighted ? top->sym_counter : 0, j; + + /* Sort the active symbols */ + pthread_mutex_lock(&top->active_symbols_lock); + syme = list_entry(top->active_symbols.next, struct sym_entry, node); + pthread_mutex_unlock(&top->active_symbols_lock); + + top->rb_entries = 0; + list_for_each_entry_safe_from(syme, n, &top->active_symbols, node) { + syme->snap_count = syme->count[snap]; + if (syme->snap_count != 0) { + + if ((top->hide_user_symbols && + syme->origin == PERF_RECORD_MISC_USER) || + (top->hide_kernel_symbols && + syme->origin == PERF_RECORD_MISC_KERNEL)) { + perf_top__remove_active_sym(top, syme); + continue; + } + syme->weight = sym_weight(syme, top); + + if ((int)syme->snap_count >= top->count_filter) { + rb_insert_active_sym(root, syme); + ++top->rb_entries; + } + sum_ksamples += syme->snap_count; + + for (j = 0; j < top->evlist->nr_entries; j++) + syme->count[j] = top->zero ? 0 : syme->count[j] * 7 / 8; + } else + perf_top__remove_active_sym(top, syme); + } + + return sum_ksamples; +} + +/* + * Find the longest symbol name that will be displayed + */ +void perf_top__find_widths(struct perf_top *top, struct rb_root *root, + int *dso_width, int *dso_short_width, int *sym_width) +{ + struct rb_node *nd; + int printed = 0; + + *sym_width = *dso_width = *dso_short_width = 0; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct sym_entry *syme = rb_entry(nd, struct sym_entry, rb_node); + struct symbol *sym = sym_entry__symbol(syme); + + if (++printed > top->print_entries || + (int)syme->snap_count < top->count_filter) + continue; + + if (syme->map->dso->long_name_len > *dso_width) + *dso_width = syme->map->dso->long_name_len; + + if (syme->map->dso->short_name_len > *dso_short_width) + *dso_short_width = syme->map->dso->short_name_len; + + if (sym->namelen > *sym_width) + *sym_width = sym->namelen; + } +} diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h new file mode 100644 index 0000000..96d1cb7 --- /dev/null +++ b/tools/perf/util/top.h @@ -0,0 +1,66 @@ +#ifndef __PERF_TOP_H +#define __PERF_TOP_H 1 + +#include "types.h" +#include "../perf.h" +#include <stddef.h> +#include <pthread.h> +#include <linux/list.h> +#include <linux/rbtree.h> + +struct perf_evlist; +struct perf_evsel; + +struct sym_entry { + struct rb_node rb_node; + struct list_head node; + unsigned long snap_count; + double weight; + int skip; + u8 origin; + struct map *map; + unsigned long count[0]; +}; + +static inline struct symbol *sym_entry__symbol(struct sym_entry *self) +{ + return ((void *)self) + symbol_conf.priv_size; +} + +struct perf_top { + struct perf_evlist *evlist; + /* + * Symbols will be added here in perf_event__process_sample and will + * get out after decayed. + */ + struct list_head active_symbols; + pthread_mutex_t active_symbols_lock; + pthread_cond_t active_symbols_cond; + u64 samples; + u64 kernel_samples, us_samples; + u64 exact_samples; + u64 guest_us_samples, guest_kernel_samples; + int print_entries, count_filter, delay_secs; + int display_weighted, freq, rb_entries, sym_counter; + pid_t target_pid, target_tid; + bool hide_kernel_symbols, hide_user_symbols, zero; + const char *cpu_list; + struct sym_entry *sym_filter_entry; + struct perf_evsel *sym_evsel; +}; + +size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size); +void perf_top__reset_sample_counters(struct perf_top *top); +float perf_top__decay_samples(struct perf_top *top, struct rb_root *root); +void perf_top__find_widths(struct perf_top *top, struct rb_root *root, + int *dso_width, int *dso_short_width, int *sym_width); + +#ifdef NO_NEWT_SUPPORT +static inline int perf_top__tui_browser(struct perf_top *top __used) +{ + return 0; +} +#else +int perf_top__tui_browser(struct perf_top *top); +#endif +#endif /* __PERF_TOP_H */ diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 73a0222..d8e622d 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -153,7 +153,7 @@ void parse_proc_kallsyms(char *file, unsigned int size __unused) char *next = NULL; char *addr_str; char ch; - int ret; + int ret __used; int i; line = strtok_r(file, "\n", &next); diff --git a/tools/perf/util/ui/browser.c b/tools/perf/util/ui/browser.c index 8bc010e..611219f 100644 --- a/tools/perf/util/ui/browser.c +++ b/tools/perf/util/ui/browser.c @@ -1,4 +1,5 @@ #include "libslang.h" +#include "ui.h" #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -156,6 +157,20 @@ void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]) } } +void __ui_browser__show_title(struct ui_browser *browser, const char *title) +{ + SLsmg_gotorc(0, 0); + ui_browser__set_color(browser, NEWT_COLORSET_ROOT); + slsmg_write_nstring(title, browser->width); +} + +void ui_browser__show_title(struct ui_browser *browser, const char *title) +{ + pthread_mutex_lock(&ui__lock); + __ui_browser__show_title(browser, title); + pthread_mutex_unlock(&ui__lock); +} + int ui_browser__show(struct ui_browser *self, const char *title, const char *helpline, ...) { @@ -178,9 +193,8 @@ int ui_browser__show(struct ui_browser *self, const char *title, if (self->sb == NULL) return -1; - SLsmg_gotorc(0, 0); - ui_browser__set_color(self, NEWT_COLORSET_ROOT); - slsmg_write_nstring(title, self->width); + pthread_mutex_lock(&ui__lock); + __ui_browser__show_title(self, title); ui_browser__add_exit_keys(self, keys); newtFormAddComponent(self->form, self->sb); @@ -188,25 +202,30 @@ int ui_browser__show(struct ui_browser *self, const char *title, va_start(ap, helpline); ui_helpline__vpush(helpline, ap); va_end(ap); + pthread_mutex_unlock(&ui__lock); return 0; } void ui_browser__hide(struct ui_browser *self) { + pthread_mutex_lock(&ui__lock); newtFormDestroy(self->form); self->form = NULL; ui_helpline__pop(); + pthread_mutex_unlock(&ui__lock); } int ui_browser__refresh(struct ui_browser *self) { int row; + pthread_mutex_lock(&ui__lock); newtScrollbarSet(self->sb, self->index, self->nr_entries - 1); row = self->refresh(self); ui_browser__set_color(self, HE_COLORSET_NORMAL); SLsmg_fill_region(self->y + row, self->x, self->height - row, self->width, ' '); + pthread_mutex_unlock(&ui__lock); return 0; } diff --git a/tools/perf/util/ui/browser.h b/tools/perf/util/ui/browser.h index 0dc7e4d..fc63dda 100644 --- a/tools/perf/util/ui/browser.h +++ b/tools/perf/util/ui/browser.h @@ -24,7 +24,6 @@ struct ui_browser { u32 nr_entries; }; - void ui_browser__set_color(struct ui_browser *self, int color); void ui_browser__set_percent_color(struct ui_browser *self, double percent, bool current); @@ -35,6 +34,8 @@ void ui_browser__reset_index(struct ui_browser *self); void ui_browser__gotorc(struct ui_browser *self, int y, int x); void ui_browser__add_exit_key(struct ui_browser *self, int key); void ui_browser__add_exit_keys(struct ui_browser *self, int keys[]); +void __ui_browser__show_title(struct ui_browser *browser, const char *title); +void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *self, const char *title, const char *helpline, ...); void ui_browser__hide(struct ui_browser *self); diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c index 82b78f9..8c17a87 100644 --- a/tools/perf/util/ui/browsers/annotate.c +++ b/tools/perf/util/ui/browsers/annotate.c @@ -1,9 +1,12 @@ #include "../browser.h" #include "../helpline.h" #include "../libslang.h" +#include "../../annotate.h" #include "../../hist.h" #include "../../sort.h" #include "../../symbol.h" +#include "../../annotate.h" +#include <pthread.h> static void ui__error_window(const char *fmt, ...) { @@ -42,8 +45,6 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro struct objdump_line_rb_node *olrb = objdump_line__rb(ol); ui_browser__set_percent_color(self, olrb->percent, current_entry); slsmg_printf(" %7.2f ", olrb->percent); - if (!current_entry) - ui_browser__set_color(self, HE_COLORSET_CODE); } else { ui_browser__set_percent_color(self, 0, current_entry); slsmg_write_nstring(" ", 9); @@ -55,35 +56,40 @@ static void annotate_browser__write(struct ui_browser *self, void *entry, int ro slsmg_write_nstring(" ", width - 18); else slsmg_write_nstring(ol->line, width - 18); + + if (!current_entry) + ui_browser__set_color(self, HE_COLORSET_CODE); } static double objdump_line__calc_percent(struct objdump_line *self, - struct list_head *head, - struct symbol *sym) + struct symbol *sym, int evidx) { double percent = 0.0; if (self->offset != -1) { int len = sym->end - sym->start; unsigned int hits = 0; - struct sym_priv *priv = symbol__priv(sym); - struct sym_ext *sym_ext = priv->ext; - struct sym_hist *h = priv->hist; + struct annotation *notes = symbol__annotation(sym); + struct source_line *src_line = notes->src->lines; + struct sym_hist *h = annotation__histogram(notes, evidx); s64 offset = self->offset; - struct objdump_line *next = objdump__get_next_ip_line(head, self); - + struct objdump_line *next; + next = objdump__get_next_ip_line(¬es->src->source, self); while (offset < (s64)len && (next == NULL || offset < next->offset)) { - if (sym_ext) { - percent += sym_ext[offset].percent; + if (src_line) { + percent += src_line[offset].percent; } else - hits += h->ip[offset]; + hits += h->addr[offset]; ++offset; } - - if (sym_ext == NULL && h->sum) + /* + * If the percentage wasn't already calculated in + * symbol__get_source_line, do it now: + */ + if (src_line == NULL && h->sum) percent = 100.0 * hits / h->sum; } @@ -133,103 +139,161 @@ static void annotate_browser__set_top(struct annotate_browser *self, self->curr_hot = nd; } -static int annotate_browser__run(struct annotate_browser *self) +static void annotate_browser__calc_percent(struct annotate_browser *browser, + int evidx) { - struct rb_node *nd; - struct hist_entry *he = self->b.priv; - int key; + struct symbol *sym = browser->b.priv; + struct annotation *notes = symbol__annotation(sym); + struct objdump_line *pos; - if (ui_browser__show(&self->b, he->ms.sym->name, - "<-, -> or ESC: exit, TAB/shift+TAB: cycle thru samples") < 0) - return -1; + browser->entries = RB_ROOT; + + pthread_mutex_lock(¬es->lock); + + list_for_each_entry(pos, ¬es->src->source, node) { + struct objdump_line_rb_node *rbpos = objdump_line__rb(pos); + rbpos->percent = objdump_line__calc_percent(pos, sym, evidx); + if (rbpos->percent < 0.01) { + RB_CLEAR_NODE(&rbpos->rb_node); + continue; + } + objdump__insert_line(&browser->entries, rbpos); + } + pthread_mutex_unlock(¬es->lock); + + browser->curr_hot = rb_last(&browser->entries); +} + +static int annotate_browser__run(struct annotate_browser *self, int evidx, + int refresh) +{ + struct rb_node *nd = NULL; + struct symbol *sym = self->b.priv; /* - * To allow builtin-annotate to cycle thru multiple symbols by + * RIGHT To allow builtin-annotate to cycle thru multiple symbols by * examining the exit key for this function. */ - ui_browser__add_exit_key(&self->b, NEWT_KEY_RIGHT); + int exit_keys[] = { 'H', NEWT_KEY_TAB, NEWT_KEY_UNTAB, + NEWT_KEY_RIGHT, 0 }; + int key; + + if (ui_browser__show(&self->b, sym->name, + "<-, -> or ESC: exit, TAB/shift+TAB: " + "cycle hottest lines, H: Hottest") < 0) + return -1; + + ui_browser__add_exit_keys(&self->b, exit_keys); + annotate_browser__calc_percent(self, evidx); + + if (self->curr_hot) + annotate_browser__set_top(self, self->curr_hot); nd = self->curr_hot; - if (nd) { - int tabs[] = { NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0 }; - ui_browser__add_exit_keys(&self->b, tabs); - } + + if (refresh != 0) + newtFormSetTimer(self->b.form, refresh); while (1) { key = ui_browser__run(&self->b); + if (refresh != 0) { + annotate_browser__calc_percent(self, evidx); + /* + * Current line focus got out of the list of most active + * lines, NULL it so that if TAB|UNTAB is pressed, we + * move to curr_hot (current hottest line). + */ + if (nd != NULL && RB_EMPTY_NODE(nd)) + nd = NULL; + } + switch (key) { + case -1: + /* + * FIXME we need to check if it was + * es.reason == NEWT_EXIT_TIMER + */ + if (refresh != 0) + symbol__annotate_decay_histogram(sym, evidx); + continue; case NEWT_KEY_TAB: - nd = rb_prev(nd); - if (nd == NULL) - nd = rb_last(&self->entries); - annotate_browser__set_top(self, nd); + if (nd != NULL) { + nd = rb_prev(nd); + if (nd == NULL) + nd = rb_last(&self->entries); + } else + nd = self->curr_hot; break; case NEWT_KEY_UNTAB: - nd = rb_next(nd); - if (nd == NULL) - nd = rb_first(&self->entries); - annotate_browser__set_top(self, nd); + if (nd != NULL) + nd = rb_next(nd); + if (nd == NULL) + nd = rb_first(&self->entries); + else + nd = self->curr_hot; + break; + case 'H': + nd = self->curr_hot; break; default: goto out; } + + if (nd != NULL) + annotate_browser__set_top(self, nd); } out: ui_browser__hide(&self->b); return key; } -int hist_entry__tui_annotate(struct hist_entry *self) +int hist_entry__tui_annotate(struct hist_entry *he, int evidx) +{ + return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, 0); +} + +int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, + int refresh) { struct objdump_line *pos, *n; - struct objdump_line_rb_node *rbpos; - LIST_HEAD(head); + struct annotation *notes = symbol__annotation(sym); struct annotate_browser browser = { .b = { - .entries = &head, + .entries = ¬es->src->source, .refresh = ui_browser__list_head_refresh, .seek = ui_browser__list_head_seek, .write = annotate_browser__write, - .priv = self, + .priv = sym, }, }; int ret; - if (self->ms.sym == NULL) + if (sym == NULL) return -1; - if (self->ms.map->dso->annotate_warned) + if (map->dso->annotate_warned) return -1; - if (hist_entry__annotate(self, &head, sizeof(*rbpos)) < 0) { + if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) { ui__error_window(ui_helpline__last_msg); return -1; } ui_helpline__push("Press <- or ESC to exit"); - list_for_each_entry(pos, &head, node) { + list_for_each_entry(pos, ¬es->src->source, node) { + struct objdump_line_rb_node *rbpos; size_t line_len = strlen(pos->line); + if (browser.b.width < line_len) browser.b.width = line_len; rbpos = objdump_line__rb(pos); rbpos->idx = browser.b.nr_entries++; - rbpos->percent = objdump_line__calc_percent(pos, &head, self->ms.sym); - if (rbpos->percent < 0.01) - continue; - objdump__insert_line(&browser.entries, rbpos); } - /* - * Position the browser at the hottest line. - */ - browser.curr_hot = rb_last(&browser.entries); - if (browser.curr_hot) - annotate_browser__set_top(&browser, browser.curr_hot); - browser.b.width += 18; /* Percentage */ - ret = annotate_browser__run(&browser); - list_for_each_entry_safe(pos, n, &head, node) { + ret = annotate_browser__run(&browser, evidx, refresh); + list_for_each_entry_safe(pos, n, ¬es->src->source, node) { list_del(&pos->node); objdump_line__free(pos); } diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c index 60c463c..798efdc 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/util/ui/browsers/hists.c @@ -7,6 +7,8 @@ #include <newt.h> #include <linux/rbtree.h> +#include "../../evsel.h" +#include "../../evlist.h" #include "../../hist.h" #include "../../pstack.h" #include "../../sort.h" @@ -292,7 +294,8 @@ static int hist_browser__run(struct hist_browser *self, const char *title) { int key; int exit_keys[] = { 'a', '?', 'h', 'C', 'd', 'D', 'E', 't', - NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, 0, }; + NEWT_KEY_ENTER, NEWT_KEY_RIGHT, NEWT_KEY_LEFT, + NEWT_KEY_TAB, NEWT_KEY_UNTAB, 0, }; self->b.entries = &self->hists->entries; self->b.nr_entries = self->hists->nr_entries; @@ -377,7 +380,7 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *self, while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); struct rb_node *next = rb_next(node); - u64 cumul = cumul_hits(child); + u64 cumul = callchain_cumul_hits(child); struct callchain_list *chain; char folded_sign = ' '; int first = true; @@ -638,6 +641,9 @@ static void ui_browser__hists_seek(struct ui_browser *self, struct rb_node *nd; bool first = true; + if (self->nr_entries == 0) + return; + switch (whence) { case SEEK_SET: nd = hists__filter_entries(rb_first(self->entries)); @@ -797,8 +803,11 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, return printed; } -int hists__browse(struct hists *self, const char *helpline, const char *ev_name) +static int perf_evsel__hists_browse(struct perf_evsel *evsel, + const char *helpline, const char *ev_name, + bool left_exits) { + struct hists *self = &evsel->hists; struct hist_browser *browser = hist_browser__new(self); struct pstack *fstack; const struct thread *thread_filter = NULL; @@ -818,8 +827,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) hists__browser_title(self, msg, sizeof(msg), ev_name, dso_filter, thread_filter); while (1) { - const struct thread *thread; - const struct dso *dso; + const struct thread *thread = NULL; + const struct dso *dso = NULL; char *options[16]; int nr_options = 0, choice = 0, i, annotate = -2, zoom_dso = -2, zoom_thread = -2, @@ -827,8 +836,10 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) key = hist_browser__run(browser, msg); - thread = hist_browser__selected_thread(browser); - dso = browser->selection->map ? browser->selection->map->dso : NULL; + if (browser->he_selection != NULL) { + thread = hist_browser__selected_thread(browser); + dso = browser->selection->map ? browser->selection->map->dso : NULL; + } switch (key) { case NEWT_KEY_TAB: @@ -839,7 +850,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) */ goto out_free_stack; case 'a': - if (browser->selection->map == NULL && + if (browser->selection == NULL || + browser->selection->map == NULL || browser->selection->map->dso->annotate_warned) continue; goto do_annotate; @@ -858,6 +870,7 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) "E Expand all callchains\n" "d Zoom into current DSO\n" "t Zoom into current Thread\n" + "TAB/UNTAB Switch events\n" "q/CTRL+C Exit browser"); continue; case NEWT_KEY_ENTER: @@ -867,8 +880,14 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) case NEWT_KEY_LEFT: { const void *top; - if (pstack__empty(fstack)) + if (pstack__empty(fstack)) { + /* + * Go back to the perf_evsel_menu__run or other user + */ + if (left_exits) + goto out_free_stack; continue; + } top = pstack__pop(fstack); if (top == &dso_filter) goto zoom_out_dso; @@ -877,14 +896,16 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) continue; } case NEWT_KEY_ESCAPE: - if (!ui__dialog_yesno("Do you really want to exit?")) + if (!left_exits && + !ui__dialog_yesno("Do you really want to exit?")) continue; /* Fall thru */ default: goto out_free_stack; } - if (browser->selection->sym != NULL && + if (browser->selection != NULL && + browser->selection->sym != NULL && !browser->selection->map->dso->annotate_warned && asprintf(&options[nr_options], "Annotate %s", browser->selection->sym->name) > 0) @@ -903,7 +924,8 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) (dso->kernel ? "the Kernel" : dso->short_name)) > 0) zoom_dso = nr_options++; - if (browser->selection->map != NULL && + if (browser->selection != NULL && + browser->selection->map != NULL && asprintf(&options[nr_options], "Browse map details") > 0) browse_map = nr_options++; @@ -923,19 +945,11 @@ int hists__browse(struct hists *self, const char *helpline, const char *ev_name) if (choice == annotate) { struct hist_entry *he; do_annotate: - if (browser->selection->map->dso->origin == DSO__ORIG_KERNEL) { - browser->selection->map->dso->annotate_warned = 1; - ui_helpline__puts("No vmlinux file found, can't " - "annotate with just a " - "kallsyms file"); - continue; - } - he = hist_browser__selected_entry(browser); if (he == NULL) continue; - hist_entry__tui_annotate(he); + hist_entry__tui_annotate(he, evsel->idx); } else if (choice == browse_map) map__browse(browser->selection->map); else if (choice == zoom_dso) { @@ -984,30 +998,141 @@ out: return key; } -int hists__tui_browse_tree(struct rb_root *self, const char *help) +struct perf_evsel_menu { + struct ui_browser b; + struct perf_evsel *selection; +}; + +static void perf_evsel_menu__write(struct ui_browser *browser, + void *entry, int row) +{ + struct perf_evsel_menu *menu = container_of(browser, + struct perf_evsel_menu, b); + struct perf_evsel *evsel = list_entry(entry, struct perf_evsel, node); + bool current_entry = ui_browser__is_current_entry(browser, row); + unsigned long nr_events = evsel->hists.stats.nr_events[PERF_RECORD_SAMPLE]; + const char *ev_name = event_name(evsel); + char bf[256], unit; + + ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED : + HE_COLORSET_NORMAL); + + nr_events = convert_unit(nr_events, &unit); + snprintf(bf, sizeof(bf), "%lu%c%s%s", nr_events, + unit, unit == ' ' ? "" : " ", ev_name); + slsmg_write_nstring(bf, browser->width); + + if (current_entry) + menu->selection = evsel; +} + +static int perf_evsel_menu__run(struct perf_evsel_menu *menu, const char *help) { - struct rb_node *first = rb_first(self), *nd = first, *next; - int key = 0; + int exit_keys[] = { NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, }; + struct perf_evlist *evlist = menu->b.priv; + struct perf_evsel *pos; + const char *ev_name, *title = "Available samples"; + int key; + + if (ui_browser__show(&menu->b, title, + "ESC: exit, ENTER|->: Browse histograms") < 0) + return -1; + + ui_browser__add_exit_keys(&menu->b, exit_keys); - while (nd) { - struct hists *hists = rb_entry(nd, struct hists, rb_node); - const char *ev_name = __event_name(hists->type, hists->config); + while (1) { + key = ui_browser__run(&menu->b); - key = hists__browse(hists, help, ev_name); switch (key) { - case NEWT_KEY_TAB: - next = rb_next(nd); - if (next) - nd = next; + case NEWT_KEY_RIGHT: + case NEWT_KEY_ENTER: + if (!menu->selection) + continue; + pos = menu->selection; +browse_hists: + ev_name = event_name(pos); + key = perf_evsel__hists_browse(pos, help, ev_name, true); + ui_browser__show_title(&menu->b, title); break; - case NEWT_KEY_UNTAB: - if (nd == first) + case NEWT_KEY_LEFT: + continue; + case NEWT_KEY_ESCAPE: + if (!ui__dialog_yesno("Do you really want to exit?")) continue; - nd = rb_prev(nd); + /* Fall thru */ + default: + goto out; + } + + switch (key) { + case NEWT_KEY_TAB: + if (pos->node.next == &evlist->entries) + pos = list_entry(evlist->entries.next, struct perf_evsel, node); + else + pos = list_entry(pos->node.next, struct perf_evsel, node); + goto browse_hists; + case NEWT_KEY_UNTAB: + if (pos->node.prev == &evlist->entries) + pos = list_entry(evlist->entries.prev, struct perf_evsel, node); + else + pos = list_entry(pos->node.prev, struct perf_evsel, node); + goto browse_hists; + case 'q': + case CTRL('c'): + goto out; default: - return key; + break; } } +out: + ui_browser__hide(&menu->b); return key; } + +static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist, + const char *help) +{ + struct perf_evsel *pos; + struct perf_evsel_menu menu = { + .b = { + .entries = &evlist->entries, + .refresh = ui_browser__list_head_refresh, + .seek = ui_browser__list_head_seek, + .write = perf_evsel_menu__write, + .nr_entries = evlist->nr_entries, + .priv = evlist, + }, + }; + + ui_helpline__push("Press ESC to exit"); + + list_for_each_entry(pos, &evlist->entries, node) { + const char *ev_name = event_name(pos); + size_t line_len = strlen(ev_name) + 7; + + if (menu.b.width < line_len) + menu.b.width = line_len; + /* + * Cache the evsel name, tracepoints have a _high_ cost per + * event_name() call. + */ + if (pos->name == NULL) + pos->name = strdup(ev_name); + } + + return perf_evsel_menu__run(&menu, help); +} + +int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help) +{ + + if (evlist->nr_entries == 1) { + struct perf_evsel *first = list_entry(evlist->entries.next, + struct perf_evsel, node); + const char *ev_name = event_name(first); + return perf_evsel__hists_browse(first, help, ev_name, false); + } + + return __perf_evlist__tui_browse_hists(evlist, help); +} diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/util/ui/browsers/map.c index e515836..8462bff 100644 --- a/tools/perf/util/ui/browsers/map.c +++ b/tools/perf/util/ui/browsers/map.c @@ -41,7 +41,7 @@ static int ui_entry__read(const char *title, char *bf, size_t size, int width) out_free_form: newtPopWindow(); newtFormDestroy(form); - return 0; + return err; } struct map_browser { diff --git a/tools/perf/util/ui/browsers/top.c b/tools/perf/util/ui/browsers/top.c new file mode 100644 index 0000000..5a06538 --- /dev/null +++ b/tools/perf/util/ui/browsers/top.c @@ -0,0 +1,213 @@ +/* + * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Parts came from builtin-{top,stat,record}.c, see those files for further + * copyright notes. + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include "../browser.h" +#include "../../annotate.h" +#include "../helpline.h" +#include "../libslang.h" +#include "../util.h" +#include "../../evlist.h" +#include "../../hist.h" +#include "../../sort.h" +#include "../../symbol.h" +#include "../../top.h" + +struct perf_top_browser { + struct ui_browser b; + struct rb_root root; + struct sym_entry *selection; + float sum_ksamples; + int dso_width; + int dso_short_width; + int sym_width; +}; + +static void perf_top_browser__write(struct ui_browser *browser, void *entry, int row) +{ + struct perf_top_browser *top_browser = container_of(browser, struct perf_top_browser, b); + struct sym_entry *syme = rb_entry(entry, struct sym_entry, rb_node); + bool current_entry = ui_browser__is_current_entry(browser, row); + struct symbol *symbol = sym_entry__symbol(syme); + struct perf_top *top = browser->priv; + int width = browser->width; + double pcnt; + + pcnt = 100.0 - (100.0 * ((top_browser->sum_ksamples - syme->snap_count) / + top_browser->sum_ksamples)); + ui_browser__set_percent_color(browser, pcnt, current_entry); + + if (top->evlist->nr_entries == 1 || !top->display_weighted) { + slsmg_printf("%20.2f ", syme->weight); + width -= 24; + } else { + slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count); + width -= 23; + } + + slsmg_printf("%4.1f%%", pcnt); + width -= 7; + + if (verbose) { + slsmg_printf(" %016" PRIx64, symbol->start); + width -= 17; + } + + slsmg_printf(" %-*.*s ", top_browser->sym_width, top_browser->sym_width, + symbol->name); + width -= top_browser->sym_width; + slsmg_write_nstring(width >= syme->map->dso->long_name_len ? + syme->map->dso->long_name : + syme->map->dso->short_name, width); + + if (current_entry) + top_browser->selection = syme; +} + +static void perf_top_browser__update_rb_tree(struct perf_top_browser *browser) +{ + struct perf_top *top = browser->b.priv; + u64 top_idx = browser->b.top_idx; + + browser->root = RB_ROOT; + browser->b.top = NULL; + browser->sum_ksamples = perf_top__decay_samples(top, &browser->root); + /* + * No active symbols + */ + if (top->rb_entries == 0) + return; + + perf_top__find_widths(top, &browser->root, &browser->dso_width, + &browser->dso_short_width, + &browser->sym_width); + if (browser->sym_width + browser->dso_width > browser->b.width - 29) { + browser->dso_width = browser->dso_short_width; + if (browser->sym_width + browser->dso_width > browser->b.width - 29) + browser->sym_width = browser->b.width - browser->dso_width - 29; + } + + /* + * Adjust the ui_browser indexes since the entries in the browser->root + * rb_tree may have changed, then seek it from start, so that we get a + * possible new top of the screen. + */ + browser->b.nr_entries = top->rb_entries; + + if (top_idx >= browser->b.nr_entries) { + if (browser->b.height >= browser->b.nr_entries) + top_idx = browser->b.nr_entries - browser->b.height; + else + top_idx = 0; + } + + if (browser->b.index >= top_idx + browser->b.height) + browser->b.index = top_idx + browser->b.index - browser->b.top_idx; + + if (browser->b.index >= browser->b.nr_entries) + browser->b.index = browser->b.nr_entries - 1; + + browser->b.top_idx = top_idx; + browser->b.seek(&browser->b, top_idx, SEEK_SET); +} + +static void perf_top_browser__annotate(struct perf_top_browser *browser) +{ + struct sym_entry *syme = browser->selection; + struct symbol *sym = sym_entry__symbol(syme); + struct annotation *notes = symbol__annotation(sym); + struct perf_top *top = browser->b.priv; + + if (notes->src != NULL) + goto do_annotation; + + pthread_mutex_lock(¬es->lock); + + top->sym_filter_entry = NULL; + + if (symbol__alloc_hist(sym, top->evlist->nr_entries) < 0) { + pr_err("Not enough memory for annotating '%s' symbol!\n", + sym->name); + pthread_mutex_unlock(¬es->lock); + return; + } + + top->sym_filter_entry = syme; + + pthread_mutex_unlock(¬es->lock); +do_annotation: + symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000); +} + +static int perf_top_browser__run(struct perf_top_browser *browser) +{ + int key; + char title[160]; + struct perf_top *top = browser->b.priv; + int delay_msecs = top->delay_secs * 1000; + int exit_keys[] = { 'a', NEWT_KEY_ENTER, NEWT_KEY_RIGHT, 0, }; + + perf_top_browser__update_rb_tree(browser); + perf_top__header_snprintf(top, title, sizeof(title)); + perf_top__reset_sample_counters(top); + + if (ui_browser__show(&browser->b, title, + "ESC: exit, ENTER|->|a: Live Annotate") < 0) + return -1; + + newtFormSetTimer(browser->b.form, delay_msecs); + ui_browser__add_exit_keys(&browser->b, exit_keys); + + while (1) { + key = ui_browser__run(&browser->b); + + switch (key) { + case -1: + /* FIXME we need to check if it was es.reason == NEWT_EXIT_TIMER */ + perf_top_browser__update_rb_tree(browser); + perf_top__header_snprintf(top, title, sizeof(title)); + perf_top__reset_sample_counters(top); + ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT); + SLsmg_gotorc(0, 0); + slsmg_write_nstring(title, browser->b.width); + break; + case 'a': + case NEWT_KEY_RIGHT: + case NEWT_KEY_ENTER: + if (browser->selection) + perf_top_browser__annotate(browser); + break; + case NEWT_KEY_LEFT: + continue; + case NEWT_KEY_ESCAPE: + if (!ui__dialog_yesno("Do you really want to exit?")) + continue; + /* Fall thru */ + default: + goto out; + } + } +out: + ui_browser__hide(&browser->b); + return key; +} + +int perf_top__tui_browser(struct perf_top *top) +{ + struct perf_top_browser browser = { + .b = { + .entries = &browser.root, + .refresh = ui_browser__rb_tree_refresh, + .seek = ui_browser__rb_tree_seek, + .write = perf_top_browser__write, + .priv = top, + }, + }; + + ui_helpline__push("Press <- or ESC to exit"); + return perf_top_browser__run(&browser); +} diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/util/ui/helpline.c index 8d79daa..f36d2ff5 100644 --- a/tools/perf/util/ui/helpline.c +++ b/tools/perf/util/ui/helpline.c @@ -5,6 +5,7 @@ #include "../debug.h" #include "helpline.h" +#include "ui.h" void ui_helpline__pop(void) { @@ -55,7 +56,8 @@ int ui_helpline__show_help(const char *format, va_list ap) int ret; static int backlog; - ret = vsnprintf(ui_helpline__last_msg + backlog, + pthread_mutex_lock(&ui__lock); + ret = vsnprintf(ui_helpline__last_msg + backlog, sizeof(ui_helpline__last_msg) - backlog, format, ap); backlog += ret; @@ -64,6 +66,7 @@ int ui_helpline__show_help(const char *format, va_list ap) newtRefresh(); backlog = 0; } + pthread_mutex_unlock(&ui__lock); return ret; } diff --git a/tools/perf/util/ui/libslang.h b/tools/perf/util/ui/libslang.h index 5623da8..2b63e1c 100644 --- a/tools/perf/util/ui/libslang.h +++ b/tools/perf/util/ui/libslang.h @@ -13,11 +13,11 @@ #if SLANG_VERSION < 20104 #define slsmg_printf(msg, args...) \ - SLsmg_printf((char *)msg, ##args) + SLsmg_printf((char *)(msg), ##args) #define slsmg_write_nstring(msg, len) \ - SLsmg_write_nstring((char *)msg, len) + SLsmg_write_nstring((char *)(msg), len) #define sltt_set_color(obj, name, fg, bg) \ - SLtt_set_color(obj,(char *)name, (char *)fg, (char *)bg) + SLtt_set_color(obj,(char *)(name), (char *)(fg), (char *)(bg)) #else #define slsmg_printf SLsmg_printf #define slsmg_write_nstring SLsmg_write_nstring diff --git a/tools/perf/util/ui/setup.c b/tools/perf/util/ui/setup.c index 6620850..ee46d67 100644 --- a/tools/perf/util/ui/setup.c +++ b/tools/perf/util/ui/setup.c @@ -6,6 +6,9 @@ #include "../debug.h" #include "browser.h" #include "helpline.h" +#include "ui.h" + +pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; static void newt_suspend(void *d __used) { @@ -14,11 +17,12 @@ static void newt_suspend(void *d __used) newtResume(); } -void setup_browser(void) +void setup_browser(bool fallback_to_pager) { if (!isatty(1) || !use_browser || dump_trace) { use_browser = 0; - setup_pager(); + if (fallback_to_pager) + setup_pager(); return; } diff --git a/tools/perf/util/ui/ui.h b/tools/perf/util/ui/ui.h new file mode 100644 index 0000000..d264e05 --- /dev/null +++ b/tools/perf/util/ui/ui.h @@ -0,0 +1,8 @@ +#ifndef _PERF_UI_H_ +#define _PERF_UI_H_ 1 + +#include <pthread.h> + +extern pthread_mutex_t ui__lock; + +#endif /* _PERF_UI_H_ */ diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c index 7b5a892..fdf1fc8 100644 --- a/tools/perf/util/ui/util.c +++ b/tools/perf/util/ui/util.c @@ -9,6 +9,7 @@ #include "../debug.h" #include "browser.h" #include "helpline.h" +#include "ui.h" #include "util.h" static void newt_form__set_exit_keys(newtComponent self) @@ -118,10 +119,12 @@ void ui__warning(const char *format, ...) va_list args; va_start(args, format); - if (use_browser > 0) + if (use_browser > 0) { + pthread_mutex_lock(&ui__lock); newtWinMessagev((char *)warning_str, (char *)ok, (char *)format, args); - else + pthread_mutex_unlock(&ui__lock); + } else vfprintf(stderr, format, args); va_end(args); } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index e833f26..fc78428 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -70,9 +70,7 @@ #include <sys/poll.h> #include <sys/socket.h> #include <sys/ioctl.h> -#ifndef NO_SYS_SELECT_H #include <sys/select.h> -#endif #include <netinet/in.h> #include <netinet/tcp.h> #include <arpa/inet.h> @@ -83,10 +81,6 @@ #include "types.h" #include <sys/ttydefaults.h> -#ifndef NO_ICONV -#include <iconv.h> -#endif - extern const char *graph_line; extern const char *graph_dotted_line; extern char buildid_dir[]; @@ -236,26 +230,6 @@ static inline int sane_case(int x, int high) return x; } -#ifndef DIR_HAS_BSD_GROUP_SEMANTICS -# define FORCE_DIR_SET_GID S_ISGID -#else -# define FORCE_DIR_SET_GID 0 -#endif - -#ifdef NO_NSEC -#undef USE_NSEC -#define ST_CTIME_NSEC(st) 0 -#define ST_MTIME_NSEC(st) 0 -#else -#ifdef USE_ST_TIMESPEC -#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctimespec.tv_nsec)) -#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtimespec.tv_nsec)) -#else -#define ST_CTIME_NSEC(st) ((unsigned int)((st).st_ctim.tv_nsec)) -#define ST_MTIME_NSEC(st) ((unsigned int)((st).st_mtim.tv_nsec)) -#endif -#endif - int mkdir_p(char *path, mode_t mode); int copyfile(const char *from, const char *to); diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 4c6983d..362a0cb 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -72,7 +72,7 @@ int need_reinitialize; int num_cpus; -typedef struct per_cpu_counters { +struct counters { unsigned long long tsc; /* per thread */ unsigned long long aperf; /* per thread */ unsigned long long mperf; /* per thread */ @@ -88,13 +88,13 @@ typedef struct per_cpu_counters { int pkg; int core; int cpu; - struct per_cpu_counters *next; -} PCC; + struct counters *next; +}; -PCC *pcc_even; -PCC *pcc_odd; -PCC *pcc_delta; -PCC *pcc_average; +struct counters *cnt_even; +struct counters *cnt_odd; +struct counters *cnt_delta; +struct counters *cnt_average; struct timeval tv_even; struct timeval tv_odd; struct timeval tv_delta; @@ -125,7 +125,7 @@ unsigned long long get_msr(int cpu, off_t offset) return msr; } -void print_header() +void print_header(void) { if (show_pkg) fprintf(stderr, "pkg "); @@ -160,39 +160,39 @@ void print_header() putc('\n', stderr); } -void dump_pcc(PCC *pcc) +void dump_cnt(struct counters *cnt) { - fprintf(stderr, "package: %d ", pcc->pkg); - fprintf(stderr, "core:: %d ", pcc->core); - fprintf(stderr, "CPU: %d ", pcc->cpu); - fprintf(stderr, "TSC: %016llX\n", pcc->tsc); - fprintf(stderr, "c3: %016llX\n", pcc->c3); - fprintf(stderr, "c6: %016llX\n", pcc->c6); - fprintf(stderr, "c7: %016llX\n", pcc->c7); - fprintf(stderr, "aperf: %016llX\n", pcc->aperf); - fprintf(stderr, "pc2: %016llX\n", pcc->pc2); - fprintf(stderr, "pc3: %016llX\n", pcc->pc3); - fprintf(stderr, "pc6: %016llX\n", pcc->pc6); - fprintf(stderr, "pc7: %016llX\n", pcc->pc7); - fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, pcc->extra_msr); + fprintf(stderr, "package: %d ", cnt->pkg); + fprintf(stderr, "core:: %d ", cnt->core); + fprintf(stderr, "CPU: %d ", cnt->cpu); + fprintf(stderr, "TSC: %016llX\n", cnt->tsc); + fprintf(stderr, "c3: %016llX\n", cnt->c3); + fprintf(stderr, "c6: %016llX\n", cnt->c6); + fprintf(stderr, "c7: %016llX\n", cnt->c7); + fprintf(stderr, "aperf: %016llX\n", cnt->aperf); + fprintf(stderr, "pc2: %016llX\n", cnt->pc2); + fprintf(stderr, "pc3: %016llX\n", cnt->pc3); + fprintf(stderr, "pc6: %016llX\n", cnt->pc6); + fprintf(stderr, "pc7: %016llX\n", cnt->pc7); + fprintf(stderr, "msr0x%x: %016llX\n", extra_msr_offset, cnt->extra_msr); } -void dump_list(PCC *pcc) +void dump_list(struct counters *cnt) { - printf("dump_list 0x%p\n", pcc); + printf("dump_list 0x%p\n", cnt); - for (; pcc; pcc = pcc->next) - dump_pcc(pcc); + for (; cnt; cnt = cnt->next) + dump_cnt(cnt); } -void print_pcc(PCC *p) +void print_cnt(struct counters *p) { double interval_float; interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; /* topology columns, print blanks on 1st (average) line */ - if (p == pcc_average) { + if (p == cnt_average) { if (show_pkg) fprintf(stderr, " "); if (show_core) @@ -262,24 +262,24 @@ void print_pcc(PCC *p) putc('\n', stderr); } -void print_counters(PCC *cnt) +void print_counters(struct counters *counters) { - PCC *pcc; + struct counters *cnt; print_header(); if (num_cpus > 1) - print_pcc(pcc_average); + print_cnt(cnt_average); - for (pcc = cnt; pcc != NULL; pcc = pcc->next) - print_pcc(pcc); + for (cnt = counters; cnt != NULL; cnt = cnt->next) + print_cnt(cnt); } #define SUBTRACT_COUNTER(after, before, delta) (delta = (after - before), (before > after)) - -int compute_delta(PCC *after, PCC *before, PCC *delta) +int compute_delta(struct counters *after, + struct counters *before, struct counters *delta) { int errors = 0; int perf_err = 0; @@ -391,20 +391,20 @@ int compute_delta(PCC *after, PCC *before, PCC *delta) delta->extra_msr = after->extra_msr; if (errors) { fprintf(stderr, "ERROR cpu%d before:\n", before->cpu); - dump_pcc(before); + dump_cnt(before); fprintf(stderr, "ERROR cpu%d after:\n", before->cpu); - dump_pcc(after); + dump_cnt(after); errors = 0; } } return 0; } -void compute_average(PCC *delta, PCC *avg) +void compute_average(struct counters *delta, struct counters *avg) { - PCC *sum; + struct counters *sum; - sum = calloc(1, sizeof(PCC)); + sum = calloc(1, sizeof(struct counters)); if (sum == NULL) { perror("calloc sum"); exit(1); @@ -438,35 +438,34 @@ void compute_average(PCC *delta, PCC *avg) free(sum); } -void get_counters(PCC *pcc) +void get_counters(struct counters *cnt) { - for ( ; pcc; pcc = pcc->next) { - pcc->tsc = get_msr(pcc->cpu, MSR_TSC); + for ( ; cnt; cnt = cnt->next) { + cnt->tsc = get_msr(cnt->cpu, MSR_TSC); if (do_nhm_cstates) - pcc->c3 = get_msr(pcc->cpu, MSR_CORE_C3_RESIDENCY); + cnt->c3 = get_msr(cnt->cpu, MSR_CORE_C3_RESIDENCY); if (do_nhm_cstates) - pcc->c6 = get_msr(pcc->cpu, MSR_CORE_C6_RESIDENCY); + cnt->c6 = get_msr(cnt->cpu, MSR_CORE_C6_RESIDENCY); if (do_snb_cstates) - pcc->c7 = get_msr(pcc->cpu, MSR_CORE_C7_RESIDENCY); + cnt->c7 = get_msr(cnt->cpu, MSR_CORE_C7_RESIDENCY); if (has_aperf) - pcc->aperf = get_msr(pcc->cpu, MSR_APERF); + cnt->aperf = get_msr(cnt->cpu, MSR_APERF); if (has_aperf) - pcc->mperf = get_msr(pcc->cpu, MSR_MPERF); + cnt->mperf = get_msr(cnt->cpu, MSR_MPERF); if (do_snb_cstates) - pcc->pc2 = get_msr(pcc->cpu, MSR_PKG_C2_RESIDENCY); + cnt->pc2 = get_msr(cnt->cpu, MSR_PKG_C2_RESIDENCY); if (do_nhm_cstates) - pcc->pc3 = get_msr(pcc->cpu, MSR_PKG_C3_RESIDENCY); + cnt->pc3 = get_msr(cnt->cpu, MSR_PKG_C3_RESIDENCY); if (do_nhm_cstates) - pcc->pc6 = get_msr(pcc->cpu, MSR_PKG_C6_RESIDENCY); + cnt->pc6 = get_msr(cnt->cpu, MSR_PKG_C6_RESIDENCY); if (do_snb_cstates) - pcc->pc7 = get_msr(pcc->cpu, MSR_PKG_C7_RESIDENCY); + cnt->pc7 = get_msr(cnt->cpu, MSR_PKG_C7_RESIDENCY); if (extra_msr_offset) - pcc->extra_msr = get_msr(pcc->cpu, extra_msr_offset); + cnt->extra_msr = get_msr(cnt->cpu, extra_msr_offset); } } - -void print_nehalem_info() +void print_nehalem_info(void) { unsigned long long msr; unsigned int ratio; @@ -514,38 +513,38 @@ void print_nehalem_info() } -void free_counter_list(PCC *list) +void free_counter_list(struct counters *list) { - PCC *p; + struct counters *p; for (p = list; p; ) { - PCC *free_me; + struct counters *free_me; free_me = p; p = p->next; free(free_me); } - return; } void free_all_counters(void) { - free_counter_list(pcc_even); - pcc_even = NULL; + free_counter_list(cnt_even); + cnt_even = NULL; - free_counter_list(pcc_odd); - pcc_odd = NULL; + free_counter_list(cnt_odd); + cnt_odd = NULL; - free_counter_list(pcc_delta); - pcc_delta = NULL; + free_counter_list(cnt_delta); + cnt_delta = NULL; - free_counter_list(pcc_average); - pcc_average = NULL; + free_counter_list(cnt_average); + cnt_average = NULL; } -void insert_cpu_counters(PCC **list, PCC *new) +void insert_counters(struct counters **list, + struct counters *new) { - PCC *prev; + struct counters *prev; /* * list was empty @@ -594,18 +593,16 @@ void insert_cpu_counters(PCC **list, PCC *new) */ new->next = prev->next; prev->next = new; - - return; } -void alloc_new_cpu_counters(int pkg, int core, int cpu) +void alloc_new_counters(int pkg, int core, int cpu) { - PCC *new; + struct counters *new; if (verbose > 1) printf("pkg%d core%d, cpu%d\n", pkg, core, cpu); - new = (PCC *)calloc(1, sizeof(PCC)); + new = (struct counters *)calloc(1, sizeof(struct counters)); if (new == NULL) { perror("calloc"); exit(1); @@ -613,9 +610,10 @@ void alloc_new_cpu_counters(int pkg, int core, int cpu) new->pkg = pkg; new->core = core; new->cpu = cpu; - insert_cpu_counters(&pcc_odd, new); + insert_counters(&cnt_odd, new); - new = (PCC *)calloc(1, sizeof(PCC)); + new = (struct counters *)calloc(1, + sizeof(struct counters)); if (new == NULL) { perror("calloc"); exit(1); @@ -623,9 +621,9 @@ void alloc_new_cpu_counters(int pkg, int core, int cpu) new->pkg = pkg; new->core = core; new->cpu = cpu; - insert_cpu_counters(&pcc_even, new); + insert_counters(&cnt_even, new); - new = (PCC *)calloc(1, sizeof(PCC)); + new = (struct counters *)calloc(1, sizeof(struct counters)); if (new == NULL) { perror("calloc"); exit(1); @@ -633,9 +631,9 @@ void alloc_new_cpu_counters(int pkg, int core, int cpu) new->pkg = pkg; new->core = core; new->cpu = cpu; - insert_cpu_counters(&pcc_delta, new); + insert_counters(&cnt_delta, new); - new = (PCC *)calloc(1, sizeof(PCC)); + new = (struct counters *)calloc(1, sizeof(struct counters)); if (new == NULL) { perror("calloc"); exit(1); @@ -643,7 +641,7 @@ void alloc_new_cpu_counters(int pkg, int core, int cpu) new->pkg = pkg; new->core = core; new->cpu = cpu; - pcc_average = new; + cnt_average = new; } int get_physical_package_id(int cpu) @@ -719,7 +717,7 @@ void re_initialize(void) { printf("turbostat: topology changed, re-initializing.\n"); free_all_counters(); - num_cpus = for_all_cpus(alloc_new_cpu_counters); + num_cpus = for_all_cpus(alloc_new_counters); need_reinitialize = 0; printf("num_cpus is now %d\n", num_cpus); } @@ -728,7 +726,7 @@ void dummy(int pkg, int core, int cpu) { return; } /* * check to see if a cpu came on-line */ -void verify_num_cpus() +void verify_num_cpus(void) { int new_num_cpus; @@ -740,14 +738,12 @@ void verify_num_cpus() num_cpus, new_num_cpus); need_reinitialize = 1; } - - return; } void turbostat_loop() { restart: - get_counters(pcc_even); + get_counters(cnt_even); gettimeofday(&tv_even, (struct timezone *)NULL); while (1) { @@ -757,24 +753,24 @@ restart: goto restart; } sleep(interval_sec); - get_counters(pcc_odd); + get_counters(cnt_odd); gettimeofday(&tv_odd, (struct timezone *)NULL); - compute_delta(pcc_odd, pcc_even, pcc_delta); + compute_delta(cnt_odd, cnt_even, cnt_delta); timersub(&tv_odd, &tv_even, &tv_delta); - compute_average(pcc_delta, pcc_average); - print_counters(pcc_delta); + compute_average(cnt_delta, cnt_average); + print_counters(cnt_delta); if (need_reinitialize) { re_initialize(); goto restart; } sleep(interval_sec); - get_counters(pcc_even); + get_counters(cnt_even); gettimeofday(&tv_even, (struct timezone *)NULL); - compute_delta(pcc_even, pcc_odd, pcc_delta); + compute_delta(cnt_even, cnt_odd, cnt_delta); timersub(&tv_even, &tv_odd, &tv_delta); - compute_average(pcc_delta, pcc_average); - print_counters(pcc_delta); + compute_average(cnt_delta, cnt_average); + print_counters(cnt_delta); } } @@ -892,7 +888,7 @@ void check_cpuid() * this check is valid for both Intel and AMD */ asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007)); - has_invariant_tsc = edx && (1 << 8); + has_invariant_tsc = edx & (1 << 8); if (!has_invariant_tsc) { fprintf(stderr, "No invariant TSC\n"); @@ -905,7 +901,7 @@ void check_cpuid() */ asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6)); - has_aperf = ecx && (1 << 0); + has_aperf = ecx & (1 << 0); if (!has_aperf) { fprintf(stderr, "No APERF MSR\n"); exit(1); @@ -952,7 +948,7 @@ void turbostat_init() check_dev_msr(); check_super_user(); - num_cpus = for_all_cpus(alloc_new_cpu_counters); + num_cpus = for_all_cpus(alloc_new_counters); if (verbose) print_nehalem_info(); @@ -962,7 +958,7 @@ int fork_it(char **argv) { int retval; pid_t child_pid; - get_counters(pcc_even); + get_counters(cnt_even); gettimeofday(&tv_even, (struct timezone *)NULL); child_pid = fork(); @@ -985,14 +981,14 @@ int fork_it(char **argv) exit(1); } } - get_counters(pcc_odd); + get_counters(cnt_odd); gettimeofday(&tv_odd, (struct timezone *)NULL); - retval = compute_delta(pcc_odd, pcc_even, pcc_delta); + retval = compute_delta(cnt_odd, cnt_even, cnt_delta); timersub(&tv_odd, &tv_even, &tv_delta); - compute_average(pcc_delta, pcc_average); + compute_average(cnt_delta, cnt_average); if (!retval) - print_counters(pcc_delta); + print_counters(cnt_delta); fprintf(stderr, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec/1000000.0);; diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index e1c62ee..ba7c63a 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1,6 +1,6 @@ #!/usr/bin/perl -w # -# Copywrite 2010 - Steven Rostedt <srostedt@redhat.com>, Red Hat Inc. +# Copyright 2010 - Steven Rostedt <srostedt@redhat.com>, Red Hat Inc. # Licensed under the terms of the GNU GPL License version 2 # |
