diff options
| author | David S. Miller <davem@davemloft.net> | 2016-08-30 00:54:02 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2016-08-30 00:54:02 -0400 |
| commit | 6abdd5f5935fff978f950561f3c5175eb34dad73 (patch) | |
| tree | 6f3ed3a4f4af9e74436ec9355ebf8201357f1c40 | |
| parent | 0b498a52778368ff501557d68c7b50878ab1701e (diff) | |
| parent | e4e98c460ad38c78498622a164fd5ef09a2dc9cb (diff) | |
| download | op-kernel-dev-6abdd5f5935fff978f950561f3c5175eb34dad73.zip op-kernel-dev-6abdd5f5935fff978f950561f3c5175eb34dad73.tar.gz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
All three conflicts were cases of simple overlapping
changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
468 files changed, 5386 insertions, 2127 deletions
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index c55df29..cd9c9f6 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a min_vecs argument set to this limit, and the PCI core will return -ENOSPC if it can't meet the minimum number of vectors. -The flags argument should normally be set to 0, but can be used to pass the -PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support -MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in -case the device does not support legacy interrupt lines. - -By default this function will spread the interrupts around the available -CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY -flag. +The flags argument is used to specify which type of interrupt can be used +by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX). +A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for +any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set, +pci_alloc_irq_vectors() will spread the interrupts around the available CPUs. To get the Linux IRQ numbers passed to request_irq() and free_irq() and the vectors, use the following function: @@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be capped to the supported limit, so there is no need to query the number of vectors supported beforehand: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES) if (nvec < 0) goto out_err; @@ -140,7 +137,7 @@ interrupts it can request a particular number of interrupts by passing that number to pci_alloc_irq_vectors() function as both 'min_vecs' and 'max_vecs' parameters: - ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0); + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; @@ -148,15 +145,14 @@ The most notorious example of the request type described above is enabling the single MSI mode for a device. It could be done by passing two 1s as 'min_vecs' and 'max_vecs': - ret = pci_alloc_irq_vectors(pdev, 1, 1, 0); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; Some devices might not support using legacy line interrupts, in which case -the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform -can't provide MSI or MSI-X interrupts: +the driver can specify that only MSI or MSI-X is acceptable: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nvec < 0) goto out_err; diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 4da60b4..ccc6032 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -53,6 +53,7 @@ stable kernels. | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | | ARM | Cortex-A57 | #852523 | N/A | | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| ARM | Cortex-A72 | #853709 | N/A | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/Documentation/conf.py b/Documentation/conf.py index 96b7aa6..106ae9c 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -131,7 +131,7 @@ pygments_style = 'sphinx' todo_include_todos = False primary_domain = 'C' -highlight_language = 'C' +highlight_language = 'guess' # -- Options for HTML output ---------------------------------------------- diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt index 6f6c2f8..0741dff 100644 --- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt +++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt @@ -8,8 +8,6 @@ Required properties: - interrupts: Interrupt number for McPDM - interrupt-parent: The parent interrupt controller - ti,hwmods: Name of the hwmod associated to the McPDM -- clocks: phandle for the pdmclk provider, likely <&twl6040> -- clock-names: Must be "pdmclk" Example: @@ -21,11 +19,3 @@ mcpdm: mcpdm@40132000 { interrupt-parent = <&gic>; ti,hwmods = "mcpdm"; }; - -In board DTS file the pdmclk needs to be added: - -&mcpdm { - clocks = <&twl6040>; - clock-names = "pdmclk"; - status = "okay"; -}; diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt index 41b817f..88b6ea1 100644 --- a/Documentation/devicetree/bindings/thermal/thermal.txt +++ b/Documentation/devicetree/bindings/thermal/thermal.txt @@ -62,7 +62,7 @@ For more examples of cooling devices, refer to the example sections below. Required properties: - #cooling-cells: Used to provide cooling device specific information Type: unsigned while referring to it. Must be at least 2, in order - Size: one cell to specify minimum and maximum cooling state used + Size: one cell to specify minimum and maximum cooling state used in the reference. The first cell is the minimum cooling state requested and the second cell is the maximum cooling state requested in the reference. @@ -119,7 +119,7 @@ Required properties: Optional property: - contribution: The cooling contribution to the thermal zone of the Type: unsigned referred cooling device at the referred trip point. - Size: one cell The contribution is a ratio of the sum + Size: one cell The contribution is a ratio of the sum of all cooling contributions within a thermal zone. Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle @@ -145,7 +145,7 @@ Required properties: Size: one cell - thermal-sensors: A list of thermal sensor phandles and sensor specifier - Type: list of used while monitoring the thermal zone. + Type: list of used while monitoring the thermal zone. phandles + sensor specifier @@ -473,7 +473,7 @@ thermal-zones { <&adc>; /* pcb north */ /* hotspot = 100 * bandgap - 120 * adc + 484 */ - coefficients = <100 -120 484>; + coefficients = <100 -120 484>; trips { ... @@ -502,7 +502,7 @@ from the ADC sensor. The binding would be then: thermal-sensors = <&adc>; /* hotspot = 1 * adc + 6000 */ - coefficients = <1 6000>; + coefficients = <1 6000>; (d) - Board thermal diff --git a/Documentation/hwmon/ftsteutates b/Documentation/hwmon/ftsteutates index 2a1bf69..8c10a91 100644 --- a/Documentation/hwmon/ftsteutates +++ b/Documentation/hwmon/ftsteutates @@ -19,5 +19,5 @@ enhancements. It can monitor up to 4 voltages, 16 temperatures and implemented in this driver. Specification of the chip can be found here: -ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf -ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf +ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf +ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf diff --git a/Documentation/kernel-documentation.rst b/Documentation/kernel-documentation.rst index c4eb504..391decc 100644 --- a/Documentation/kernel-documentation.rst +++ b/Documentation/kernel-documentation.rst @@ -366,8 +366,6 @@ Domain`_ references. Cross-referencing from reStructuredText ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -.. highlight:: none - To cross-reference the functions and types defined in the kernel-doc comments from reStructuredText documents, please use the `Sphinx C Domain`_ references. For example:: @@ -390,8 +388,6 @@ For further details, please refer to the `Sphinx C Domain`_ documentation. Function documentation ---------------------- -.. highlight:: c - The general format of a function and function-like macro kernel-doc comment is:: /** @@ -572,8 +568,6 @@ DocBook XML [DEPRECATED] Converting DocBook to Sphinx ---------------------------- -.. highlight:: none - Over time, we expect all of the documents under ``Documentation/DocBook`` to be converted to Sphinx and reStructuredText. For most DocBook XML documents, a good enough solution is to use the simple ``Documentation/sphinx/tmplcvt`` script, diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 46c030a..a4f4d69 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3032,6 +3032,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. PAGE_SIZE is used as alignment. PCI-PCI bridge can be specified, if resource windows need to be expanded. + To specify the alignment for several + instances of a device, the PCI vendor, + device, subvendor, and subdevice may be + specified, e.g., 4096@pci:8086:9c22:103c:198f ecrc= Enable/disable PCIe ECRC (transaction layer end-to-end CRC checking). bios: Use BIOS/firmware settings. This is the diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 44ed453..a4e55c7 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -587,26 +587,6 @@ of DSA, would be the its port-based VLAN, used by the associated bridge device. TODO ==== -The platform device problem ---------------------------- -DSA is currently implemented as a platform device driver which is far from ideal -as was discussed in this thread: - -http://permalink.gmane.org/gmane.linux.network/329848 - -This basically prevents the device driver model to be properly used and applied, -and support non-MDIO, non-MMIO Ethernet connected switches. - -Another problem with the platform device driver approach is that it prevents the -use of a modular switch drivers build due to a circular dependency, illustrated -here: - -http://comments.gmane.org/gmane.linux.network/345803 - -Attempts of reworking this has been done here: - -https://lwn.net/Articles/643149/ - Making SWITCHDEV and DSA converge towards an unified codebase ------------------------------------------------------------- diff --git a/Documentation/power/basic-pm-debugging.txt b/Documentation/power/basic-pm-debugging.txt index b96098c..708f87f 100644 --- a/Documentation/power/basic-pm-debugging.txt +++ b/Documentation/power/basic-pm-debugging.txt @@ -164,7 +164,32 @@ load n/2 modules more and try again. Again, if you find the offending module(s), it(they) must be unloaded every time before hibernation, and please report the problem with it(them). -c) Advanced debugging +c) Using the "test_resume" hibernation option + +/sys/power/disk generally tells the kernel what to do after creating a +hibernation image. One of the available options is "test_resume" which +causes the just created image to be used for immediate restoration. Namely, +after doing: + +# echo test_resume > /sys/power/disk +# echo disk > /sys/power/state + +a hibernation image will be created and a resume from it will be triggered +immediately without involving the platform firmware in any way. + +That test can be used to check if failures to resume from hibernation are +related to bad interactions with the platform firmware. That is, if the above +works every time, but resume from actual hibernation does not work or is +unreliable, the platform firmware may be responsible for the failures. + +On architectures and platforms that support using different kernels to restore +hibernation images (that is, the kernel used to read the image from storage and +load it into memory is different from the one included in the image) or support +kernel address space randomization, it also can be used to check if failures +to resume may be related to the differences between the restore and image +kernels. + +d) Advanced debugging In case that hibernation does not work on your system even in the minimal configuration and compiling more drivers as modules is not practical or some diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt index f1f0f59a..974916f 100644 --- a/Documentation/power/interface.txt +++ b/Documentation/power/interface.txt @@ -1,75 +1,76 @@ -Power Management Interface - - -The power management subsystem provides a unified sysfs interface to -userspace, regardless of what architecture or platform one is -running. The interface exists in /sys/power/ directory (assuming sysfs -is mounted at /sys). - -/sys/power/state controls system power state. Reading from this file -returns what states are supported, which is hard-coded to 'freeze', -'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk' -(Suspend-to-Disk). - -Writing to this file one of those strings causes the system to -transition into that state. Please see the file -Documentation/power/states.txt for a description of each of those -states. - - -/sys/power/disk controls the operating mode of the suspend-to-disk -mechanism. Suspend-to-disk can be handled in several ways. We have a -few options for putting the system to sleep - using the platform driver -(e.g. ACPI or other suspend_ops), powering off the system or rebooting the -system (for testing). - -Additionally, /sys/power/disk can be used to turn on one of the two testing -modes of the suspend-to-disk mechanism: 'testproc' or 'test'. If the -suspend-to-disk mechanism is in the 'testproc' mode, writing 'disk' to -/sys/power/state will cause the kernel to disable nonboot CPUs and freeze -tasks, wait for 5 seconds, unfreeze tasks and enable nonboot CPUs. If it is -in the 'test' mode, writing 'disk' to /sys/power/state will cause the kernel -to disable nonboot CPUs and freeze tasks, shrink memory, suspend devices, wait -for 5 seconds, resume devices, unfreeze tasks and enable nonboot CPUs. Then, -we are able to look in the log messages and work out, for example, which code -is being slow and which device drivers are misbehaving. - -Reading from this file will display all supported modes and the currently -selected one in brackets, for example - - [shutdown] reboot test testproc - -Writing to this file will accept one of - - 'platform' (only if the platform supports it) - 'shutdown' - 'reboot' - 'testproc' - 'test' - -/sys/power/image_size controls the size of the image created by -the suspend-to-disk mechanism. It can be written a string -representing a non-negative integer that will be used as an upper -limit of the image size, in bytes. The suspend-to-disk mechanism will -do its best to ensure the image size will not exceed that number. However, -if this turns out to be impossible, it will try to suspend anyway using the -smallest image possible. In particular, if "0" is written to this file, the -suspend image will be as small as possible. - -Reading from this file will display the current image size limit, which -is set to 2/5 of available RAM by default. - -/sys/power/pm_trace controls the code which saves the last PM event point in -the RTC across reboots, so that you can debug a machine that just hangs -during suspend (or more commonly, during resume). Namely, the RTC is only -used to save the last PM event point if this file contains '1'. Initially it -contains '0' which may be changed to '1' by writing a string representing a -nonzero integer into it. - -To use this debugging feature you should attempt to suspend the machine, then -reboot it and run - - dmesg -s 1000000 | grep 'hash matches' - -CAUTION: Using it will cause your machine's real-time (CMOS) clock to be -set to a random invalid time after a resume. +Power Management Interface for System Sleep + +Copyright (c) 2016 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com> + +The power management subsystem provides userspace with a unified sysfs interface +for system sleep regardless of the underlying system architecture or platform. +The interface is located in the /sys/power/ directory (assuming that sysfs is +mounted at /sys). + +/sys/power/state is the system sleep state control file. + +Reading from it returns a list of supported sleep states, encoded as: + +'freeze' (Suspend-to-Idle) +'standby' (Power-On Suspend) +'mem' (Suspend-to-RAM) +'disk' (Suspend-to-Disk) + +Suspend-to-Idle is always supported. Suspend-to-Disk is always supported +too as long the kernel has been configured to support hibernation at all +(ie. CONFIG_HIBERNATION is set in the kernel configuration file). Support +for Suspend-to-RAM and Power-On Suspend depends on the capabilities of the +platform. + +If one of the strings listed in /sys/power/state is written to it, the system +will attempt to transition into the corresponding sleep state. Refer to +Documentation/power/states.txt for a description of each of those states. + +/sys/power/disk controls the operating mode of hibernation (Suspend-to-Disk). +Specifically, it tells the kernel what to do after creating a hibernation image. + +Reading from it returns a list of supported options encoded as: + +'platform' (put the system into sleep using a platform-provided method) +'shutdown' (shut the system down) +'reboot' (reboot the system) +'suspend' (trigger a Suspend-to-RAM transition) +'test_resume' (resume-after-hibernation test mode) + +The currently selected option is printed in square brackets. + +The 'platform' option is only available if the platform provides a special +mechanism to put the system to sleep after creating a hibernation image (ACPI +does that, for example). The 'suspend' option is available if Suspend-to-RAM +is supported. Refer to Documentation/power/basic_pm_debugging.txt for the +description of the 'test_resume' option. + +To select an option, write the string representing it to /sys/power/disk. + +/sys/power/image_size controls the size of hibernation images. + +It can be written a string representing a non-negative integer that will be +used as a best-effort upper limit of the image size, in bytes. The hibernation +core will do its best to ensure that the image size will not exceed that number. +However, if that turns out to be impossible to achieve, a hibernation image will +still be created and its size will be as small as possible. In particular, +writing '0' to this file will enforce hibernation images to be as small as +possible. + +Reading from this file returns the current image size limit, which is set to +around 2/5 of available RAM by default. + +/sys/power/pm_trace controls the PM trace mechanism saving the last suspend +or resume event point in the RTC across reboots. + +It helps to debug hard lockups or reboots due to device driver failures that +occur during system suspend or resume (which is more common) more effectively. + +If /sys/power/pm_trace contains '1', the fingerprint of each suspend/resume +event point in turn will be stored in the RTC memory (overwriting the actual +RTC information), so it will survive a system crash if one occurs right after +storing it and it can be used later to identify the driver that caused the crash +to happen (see Documentation/power/s2ram.txt for more information). + +Initially it contains '0' which may be changed to '1' by writing a string +representing a nonzero integer into it. diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt index ba0a2a4..e32fdbb 100644 --- a/Documentation/powerpc/transactional_memory.txt +++ b/Documentation/powerpc/transactional_memory.txt @@ -167,6 +167,8 @@ signal will be rolled back anyway. For signals taken in non-TM or suspended mode, we use the normal/non-checkpointed stack pointer. +Any transaction initiated inside a sighandler and suspended on return +from the sighandler to the kernel will get reclaimed and discarded. Failure cause codes used by kernel ================================== diff --git a/Documentation/sphinx-static/theme_overrides.css b/Documentation/sphinx-static/theme_overrides.css index 3a2ac4b..e88461c 100644 --- a/Documentation/sphinx-static/theme_overrides.css +++ b/Documentation/sphinx-static/theme_overrides.css @@ -42,11 +42,12 @@ caption a.headerlink { opacity: 0; } caption a.headerlink:hover { opacity: 1; } - /* inline literal: drop the borderbox and red color */ + /* inline literal: drop the borderbox, padding and red color */ code, .rst-content tt, .rst-content code { color: inherit; border: none; + padding: unset; background: inherit; font-size: 85%; } diff --git a/MAINTAINERS b/MAINTAINERS index 99f9527..58b5029 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -890,6 +890,15 @@ S: Supported F: drivers/gpu/drm/arc/ F: Documentation/devicetree/bindings/display/snps,arcpgu.txt +ARM ARCHITECTED TIMER DRIVER +M: Mark Rutland <mark.rutland@arm.com> +M: Marc Zyngier <marc.zyngier@arm.com> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/include/asm/arch_timer.h +F: arch/arm64/include/asm/arch_timer.h +F: drivers/clocksource/arm_arch_timer.c + ARM HDLCD DRM DRIVER M: Liviu Dudau <liviu.dudau@arm.com> S: Supported @@ -4534,6 +4543,12 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/sb_edac.c +EDAC-SKYLAKE +M: Tony Luck <tony.luck@intel.com> +L: linux-edac@vger.kernel.org +S: Maintained +F: drivers/edac/skx_edac.c + EDAC-XGENE APPLIED MICRO (APM) X-GENE SOC EDAC M: Loc Ho <lho@apm.com> @@ -7664,7 +7679,7 @@ L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home Q: http://patchwork.kernel.org/project/linux-rdma/list/ -F: drivers/infiniband/hw/rxe/ +F: drivers/infiniband/sw/rxe/ F: include/uapi/rdma/rdma_user_rxe.h MEMBARRIER SUPPORT @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc4 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index ad7860c..51597f3 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -142,7 +142,7 @@ #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it with rest of callee_regs - ld.as r12, [r12, PT_user_r25] + ld r12, [r12, PT_user_r25] PUSH r12 #else PUSH r25 @@ -198,7 +198,7 @@ ; SP is back to start of pt_regs #ifdef CONFIG_ARC_CURR_IN_REG - st.as r12, [sp, PT_user_r25] + st r12, [sp, PT_user_r25] #endif .endm diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index c1d3645..4c6eed8 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void) .endm .macro IRQ_ENABLE scratch + TRACE_ASM_IRQ_ENABLE lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch - TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 0f92d97..89eeb37 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h index 0f99ac8..0037a58 100644 --- a/arch/arc/include/uapi/asm/elf.h +++ b/arch/arc/include/uapi/asm/elf.h @@ -13,8 +13,15 @@ /* Machine specific ELF Hdr flags */ #define EF_ARC_OSABI_MSK 0x00000f00 -#define EF_ARC_OSABI_ORIG 0x00000000 /* MUST be zero for back-compat */ -#define EF_ARC_OSABI_CURRENT 0x00000300 /* v3 (no legacy syscalls) */ + +#define EF_ARC_OSABI_V3 0x00000300 /* v3 (no legacy syscalls) */ +#define EF_ARC_OSABI_V4 0x00000400 /* v4 (64bit data any reg align) */ + +#if __GNUC__ < 6 +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V3 +#else +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V4 +#endif typedef unsigned long elf_greg_t; typedef unsigned long elf_fpregset_t; diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c index 4d9e777..000dd04 100644 --- a/arch/arc/kernel/arcksyms.c +++ b/arch/arc/kernel/arcksyms.c @@ -28,6 +28,7 @@ extern void __muldf3(void); extern void __divdf3(void); extern void __floatunsidf(void); extern void __floatunsisf(void); +extern void __udivdi3(void); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); @@ -45,6 +46,7 @@ EXPORT_SYMBOL(__muldf3); EXPORT_SYMBOL(__divdf3); EXPORT_SYMBOL(__floatunsidf); EXPORT_SYMBOL(__floatunsisf); +EXPORT_SYMBOL(__udivdi3); /* ARC optimised assembler routines */ EXPORT_SYMBOL(memset); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index b5db9e7..be1972b 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -199,7 +199,7 @@ int elf_check_arch(const struct elf32_hdr *x) } eflags = x->e_flags; - if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) { + if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) { pr_err("ABI mismatch - you need newer toolchain\n"); force_sigsegv(SIGSEGV, current); return 0; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a946400..f52a0d0d 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -291,8 +291,10 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) cpu->dccm.base_addr, TO_KB(cpu->dccm.sz), cpu->iccm.base_addr, TO_KB(cpu->iccm.sz)); - n += scnprintf(buf + n, len - n, - "OS ABI [v3]\t: no-legacy-syscalls\n"); + n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n", + EF_ARC_OSABI_CURRENT >> 8, + EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ? + "no-legacy-syscalls" : "64-bit data any register aligned"); return buf; } diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 5a294b2..0b10efe 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -921,6 +921,15 @@ void arc_cache_init(void) printk(arc_cache_mumbojumbo(0, str, sizeof(str))); + /* + * Only master CPU needs to execute rest of function: + * - Assume SMP so all cores will have same cache config so + * any geomtry checks will be same for all + * - IOC setup / dma callbacks only need to be setup once + */ + if (cpu) + return; + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 04f8332..77ff64a 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -61,6 +61,7 @@ void *kmap(struct page *page) return kmap_high(page); } +EXPORT_SYMBOL(kmap); void *kmap_atomic(struct page *page) { diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index bc5f507..9f157e7 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -295,6 +295,7 @@ __und_svc_fault: bl __und_fault __und_svc_finish: + get_thread_info tsk ldr r5, [sp, #S_PSR] @ Get SVC cpsr svc_exit r5 @ return from exception UNWIND(.fnend ) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index bda27b6..29d0b23 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1309,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, smp_rmb(); pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); - if (is_error_pfn(pfn)) + if (is_error_noslot_pfn(pfn)) return -EFAULT; if (kvm_is_device_pfn(pfn)) { diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index fd87205..0df062d 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -271,6 +271,12 @@ static int __init imx_gpc_init(struct device_node *node, for (i = 0; i < IMR_NUM; i++) writel_relaxed(~0, gpc_base + GPC_IMR1 + i * 4); + /* + * Clear the OF_POPULATED flag set in of_irq_init so that + * later the GPC power domain driver will not be skipped. + */ + of_node_clear_flag(node, OF_POPULATED); + return 0; } IRQCHIP_DECLARE(imx_gpc, "fsl,imx6q-gpc", imx_gpc_init); diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c index c410d84..66070ac 100644 --- a/arch/arm/mach-pxa/idp.c +++ b/arch/arm/mach-pxa/idp.c @@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_USE_DMA | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c index 3f06cd9..056369e 100644 --- a/arch/arm/mach-pxa/xcep.c +++ b/arch/arm/mach-pxa/xcep.c @@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata xcep_smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT | SMC91X_USE_DMA, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index baf1745..a0ead0a 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -93,7 +93,8 @@ static struct smsc911x_platform_config smsc911x_config = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, }; static struct platform_device realview_eth_device = { diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c index 1525d7b..88149f8 100644 --- a/arch/arm/mach-sa1100/pleb.c +++ b/arch/arm/mach-sa1100/pleb.c @@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 62f4d01..6344913 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -728,7 +728,8 @@ static void *__init late_alloc(unsigned long sz) { void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz)); - BUG_ON(!ptr); + if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) + BUG(); return ptr; } @@ -1155,10 +1156,19 @@ void __init sanity_check_meminfo(void) { phys_addr_t memblock_limit = 0; int highmem = 0; - phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; + u64 vmalloc_limit; struct memblock_region *reg; bool should_use_highmem = false; + /* + * Let's use our own (unoptimized) equivalent of __pa() that is + * not affected by wrap-arounds when sizeof(phys_addr_t) == 4. + * The result is used as the upper bound on physical memory address + * and may itself be outside the valid range for which phys_addr_t + * and therefore __pa() is defined. + */ + vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET; + for_each_memblock(memory, reg) { phys_addr_t block_start = reg->base; phys_addr_t block_end = reg->base + reg->size; @@ -1183,10 +1193,11 @@ void __init sanity_check_meminfo(void) if (reg->size > size_limit) { phys_addr_t overlap_size = reg->size - size_limit; - pr_notice("Truncating RAM at %pa-%pa to -%pa", - &block_start, &block_end, &vmalloc_limit); - memblock_remove(vmalloc_limit, overlap_size); + pr_notice("Truncating RAM at %pa-%pa", + &block_start, &block_end); block_end = vmalloc_limit; + pr_cont(" to -%pa", &block_end); + memblock_remove(vmalloc_limit, overlap_size); should_use_highmem = true; } } diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index b0b82f5..3d2cef6 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); static struct vcpu_info __percpu *xen_vcpu_info; /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); /* These are unused until we support booting "pre-ballooned" */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b77f583..3e7b050 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -757,6 +757,9 @@ ENTRY(__enable_mmu) isb bl __create_page_tables // recreate kernel mapping + tlbi vmalle1 // Remove any stale TLB entries + dsb nsh + msr sctlr_el1, x19 // re-enable the MMU isb ic iallu // flush instructions fetched diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 9a3aec9..ccf79d8 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -101,12 +101,20 @@ ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly /* enable the MMU early - so we can access sleep_save_stash by va */ adr_l lr, __enable_mmu /* __cpu_setup will return here */ - ldr x27, =_cpu_resume /* __enable_mmu will branch here */ + adr_l x27, _resume_switched /* __enable_mmu will branch here */ adrp x25, idmap_pg_dir adrp x26, swapper_pg_dir b __cpu_setup ENDPROC(cpu_resume) + .pushsection ".idmap.text", "ax" +_resume_switched: + ldr x8, =_cpu_resume + br x8 +ENDPROC(_resume_switched) + .ltorg + .popsection + ENTRY(_cpu_resume) mrs x1, mpidr_el1 adrp x8, mpidr_hash diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index ae7855f..5a84b45 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -256,7 +256,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) /* * We must restore the 32-bit state before the sysregs, thanks - * to Cortex-A57 erratum #852523. + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_guest_state(guest_ctxt); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b0b225c..e51367d 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -823,14 +823,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 * - * We could trap ID_DFR0 and tell the guest we don't support performance - * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was - * NAKed, so it will read the PMCR anyway. - * - * Therefore we tell the guest we have 0 counters. Unfortunately, we - * must always support PMCCNTR (the cycle counter): we just RAZ/WI for - * all PM registers, which doesn't crash the guest kernel at least. - * * Debug handling: We do trap most, if not all debug related system * registers. The implementation is good enough to ensure that a guest * can use these with minimal performance degradation. The drawback is @@ -1360,7 +1352,7 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, /* ICC_SRE */ - { Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi }, + { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre }, { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index f94b80e..9c3e75d 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -242,7 +242,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) { - pte_t *pte = pte_offset_kernel(pmd, 0); + pte_t *pte = pte_offset_kernel(pmd, 0UL); unsigned long addr; unsigned i; @@ -254,7 +254,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) { - pmd_t *pmd = pmd_offset(pud, 0); + pmd_t *pmd = pmd_offset(pud, 0UL); unsigned long addr; unsigned i; @@ -271,7 +271,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) { - pud_t *pud = pud_offset(pgd, 0); + pud_t *pud = pud_offset(pgd, 0UL); unsigned long addr; unsigned i; diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index c7fe3ec..5bb15ea 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -23,6 +23,8 @@ #include <linux/module.h> #include <linux/of.h> +#include <asm/acpi.h> + struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); nodemask_t numa_nodes_parsed __initdata; diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index c6db52b..10c5777 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = { #include <linux/smc91x.h> static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index f35525b..57d1c43 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = { #include <linux/smc91x.h> static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ea0cd97..5f98759 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -164,7 +164,7 @@ typedef struct { unsigned long pgprot; } pgprot_t; */ static inline unsigned long ___pa(unsigned long x) { - if (config_enabled(CONFIG_64BIT)) { + if (IS_ENABLED(CONFIG_64BIT)) { /* * For MIPS64 the virtual address may either be in one of * the compatibility segements ckseg0 or ckseg1, or it may @@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x) return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x); } - if (!config_enabled(CONFIG_EVA)) { + if (!IS_ENABLED(CONFIG_EVA)) { /* * We're using the standard MIPS32 legacy memory map, ie. * the address x is going to be in kseg0 or kseg1. We can diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 6cfdcf5..121008c 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -40,7 +40,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) srcu_idx = srcu_read_lock(&kvm->srcu); pfn = gfn_to_pfn(kvm, gfn); - if (is_error_pfn(pfn)) { + if (is_error_noslot_pfn(pfn)) { kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn); err = -EFAULT; goto out; diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index c0ae625..274d5bc 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -97,10 +97,10 @@ #define ENOTCONN 235 /* Transport endpoint is not connected */ #define ESHUTDOWN 236 /* Cannot send after transport endpoint shutdown */ #define ETOOMANYREFS 237 /* Too many references: cannot splice */ -#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ #define ETIMEDOUT 238 /* Connection timed out */ #define ECONNREFUSED 239 /* Connection refused */ -#define EREMOTERELEASE 240 /* Remote peer released connection */ +#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ +#define EREMOTERELEASE 240 /* Remote peer released connection */ #define EHOSTDOWN 241 /* Host is down */ #define EHOSTUNREACH 242 /* No route to host */ diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 5adc339..0c2a94a 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -51,8 +51,6 @@ EXPORT_SYMBOL(_parisc_requires_coherency); DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data); -extern int update_cr16_clocksource(void); /* from time.c */ - /* ** PARISC CPU driver - claim "device" and initialize CPU data structures. ** @@ -228,12 +226,6 @@ static int processor_probe(struct parisc_device *dev) } #endif - /* If we've registered more than one cpu, - * we'll use the jiffies clocksource since cr16 - * is not synchronized between CPUs. - */ - update_cr16_clocksource(); - return 0; } diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 505cf1a..4b0b963 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -221,18 +221,6 @@ static struct clocksource clocksource_cr16 = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -int update_cr16_clocksource(void) -{ - /* since the cr16 cycle counters are not synchronized across CPUs, - we'll check if we should switch to a safe clocksource: */ - if (clocksource_cr16.rating != 0 && num_online_cpus() > 1) { - clocksource_change_rating(&clocksource_cr16, 0); - return 1; - } - - return 0; -} - void __init start_cpu_itimer(void) { unsigned int cpu = smp_processor_id(); diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index 666bef4e..9377bdf 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -3,6 +3,7 @@ #ifndef __ASSEMBLY__ #include <linux/cpumask.h> +#include <asm/cpu_has_feature.h> /* * Mapping of threads to cores diff --git a/arch/powerpc/include/asm/hmi.h b/arch/powerpc/include/asm/hmi.h index 88b4901..85b7a1a 100644 --- a/arch/powerpc/include/asm/hmi.h +++ b/arch/powerpc/include/asm/hmi.h @@ -21,7 +21,7 @@ #ifndef __ASM_PPC64_HMI_H__ #define __ASM_PPC64_HMI_H__ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #define CORE_TB_RESYNC_REQ_BIT 63 #define MAX_SUBCORE_PER_CORE 4 diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 148303e7..6a6792b 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -183,11 +183,6 @@ struct paca_struct { */ u16 in_mce; u8 hmi_event_available; /* HMI event is available */ - /* - * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for - * more details - */ - struct sibling_subcore_state *sibling_subcore_state; #endif /* Stuff for accurate time accounting */ @@ -202,6 +197,13 @@ struct paca_struct { struct kvmppc_book3s_shadow_vcpu shadow_vcpu; #endif struct kvmppc_host_state kvm_hstate; +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for + * more details + */ + struct sibling_subcore_state *sibling_subcore_state; +#endif #endif }; diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b5e88e4..c0309c5 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -301,6 +301,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose, /* Allocate & free a PCI host bridge structure */ extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev); extern void pcibios_free_controller(struct pci_controller *phb); +extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge); #ifdef CONFIG_PCI extern int pcibios_vaddr_is_ioport(void __iomem *address); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b2027a5..fe4c075 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -41,7 +41,7 @@ obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o -obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o +obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC64) += vdso64/ obj-$(CONFIG_ALTIVEC) += vecemu.o diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 6b8bc0d..5afd03e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -368,13 +368,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) tabort_syscall: /* Firstly we need to enable TM in the kernel */ mfmsr r10 - li r13, 1 - rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG + li r9, 1 + rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG mtmsrd r10, 0 /* tabort, this dooms the transaction, nothing else */ - li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R13) + li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) + TABORT(R9) /* * Return directly to userspace. We have corrupted user register state, @@ -382,8 +382,8 @@ tabort_syscall: * resume after the tbegin of the aborted transaction with the * checkpointed register state. */ - li r13, MSR_RI - andc r10, r10, r13 + li r9, MSR_RI + andc r10, r10, r9 mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index df6d45e..bffec73 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -485,7 +485,23 @@ machine_check_fwnmi: EXCEPTION_PROLOG_0(PACA_EXMC) machine_check_pSeries_0: EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200) - EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD) + /* + * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the + * difference that MSR_RI is not enabled, because PACA_EXMC is being + * used, so nested machine check corrupts it. machine_check_common + * enables MSR_RI. + */ + ld r12,PACAKBASE(r13) + ld r10,PACAKMSR(r13) + xori r10,r10,MSR_RI + mfspr r11,SPRN_SRR0 + LOAD_HANDLER(r12, machine_check_common) + mtspr SPRN_SRR0,r12 + mfspr r12,SPRN_SRR1 + mtspr SPRN_SRR1,r10 + rfid + b . /* prevent speculative execution */ + KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200) KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300) KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380) @@ -969,14 +985,17 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) machine_check_common: mfspr r10,SPRN_DAR - std r10,PACA_EXGEN+EX_DAR(r13) + std r10,PACA_EXMC+EX_DAR(r13) mfspr r10,SPRN_DSISR - stw r10,PACA_EXGEN+EX_DSISR(r13) + stw r10,PACA_EXMC+EX_DSISR(r13) EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC) FINISH_NAP RECONCILE_IRQ_STATE(r10, r11) - ld r3,PACA_EXGEN+EX_DAR(r13) - lwz r4,PACA_EXGEN+EX_DSISR(r13) + ld r3,PACA_EXMC+EX_DAR(r13) + lwz r4,PACA_EXMC+EX_DSISR(r13) + /* Enable MSR_RI when finished with PACA_EXMC */ + li r10,MSR_RI + mtmsrd r10,1 std r3,_DAR(r1) std r4,_DSISR(r1) bl save_nvgprs diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 3ed8ec09..e785cc9 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -29,7 +29,7 @@ #include <linux/kprobes.h> #include <linux/ptrace.h> #include <linux/preempt.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kdebug.h> #include <linux/slab.h> #include <asm/code-patching.h> diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 7fdf324..e589080 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -154,6 +154,42 @@ void pcibios_free_controller(struct pci_controller *phb) EXPORT_SYMBOL_GPL(pcibios_free_controller); /* + * This function is used to call pcibios_free_controller() + * in a deferred manner: a callback from the PCI subsystem. + * + * _*DO NOT*_ call pcibios_free_controller() explicitly if + * this is used (or it may access an invalid *phb pointer). + * + * The callback occurs when all references to the root bus + * are dropped (e.g., child buses/devices and their users). + * + * It's called as .release_fn() of 'struct pci_host_bridge' + * which is associated with the 'struct pci_controller.bus' + * (root bus) - it expects .release_data to hold a pointer + * to 'struct pci_controller'. + * + * In order to use it, register .release_fn()/release_data + * like this: + * + * pci_set_host_bridge_release(bridge, + * pcibios_free_controller_deferred + * (void *) phb); + * + * e.g. in the pcibios_root_bridge_prepare() callback from + * pci_create_root_bus(). + */ +void pcibios_free_controller_deferred(struct pci_host_bridge *bridge) +{ + struct pci_controller *phb = (struct pci_controller *) + bridge->release_data; + + pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic); + + pcibios_free_controller(phb); +} +EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred); + +/* * The function is used to return the minimal alignment * for memory or I/O windows of the associated P2P bridge. * By default, 4KiB alignment for I/O windows and 1MiB for diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 4e74fc5..d3eff99 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -695,7 +695,7 @@ unsigned char ibm_architecture_vec[] = { OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */ /* option vector 5: PAPR/OF options */ - VECTOR_LENGTH(18), /* length */ + VECTOR_LENGTH(21), /* length */ 0, /* don't ignore, don't halt */ OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) | OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) | @@ -726,8 +726,11 @@ unsigned char ibm_architecture_vec[] = { 0, 0, OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) | - OV5_FEAT(OV5_PFO_HW_842), - OV5_FEAT(OV5_SUB_PROCESSORS), + OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */ + 0, /* Byte 18 */ + 0, /* Byte 19 */ + 0, /* Byte 20 */ + OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */ /* option vector 6: IBM PAPR hints */ VECTOR_LENGTH(3), /* length */ diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b6aa378..a7daf74 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1226,7 +1226,21 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, (regs->gpr[1] + __SIGNAL_FRAMESIZE + 16); if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf))) goto bad; + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(tmp, &rt_sf->uc.uc_link)) goto bad; uc_transact = (struct ucontext __user *)(uintptr_t)tmp; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 7e49984..70409bb 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -676,7 +676,21 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5, if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set))) goto badframe; set_current_blocked(&set); + #ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * If there is a transactional state then throw it away. + * The purpose of a sigreturn is to destroy all traces of the + * signal frame, this includes any transactional state created + * within in. We only check for suspended as we can never be + * active in the kernel, we are active, there is nothing better to + * do than go ahead and Bad Thing later. + * The cause is not important as there will never be a + * recheckpoint so it's not user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); + if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR])) goto badframe; if (MSR_TM_ACTIVE(msr)) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 25a3905..9c6f3fd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -830,7 +830,7 @@ int __cpu_disable(void) /* Update sibling maps */ base = cpu_first_thread_sibling(cpu); - for (i = 0; i < threads_per_core; i++) { + for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) { cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); cpumask_clear_cpu(cpu, cpu_core_mask(base + i)); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 2cb5892..62859eb 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -25,7 +25,8 @@ #include <linux/user.h> #include <linux/interrupt.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/extable.h> +#include <linux/module.h> /* print_modules */ #include <linux/prctl.h> #include <linux/delay.h> #include <linux/kprobes.h> diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 1f9e552..855d4b9 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -78,6 +78,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \ ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \ + book3s_hv_hmi.o \ book3s_hv_rmhandlers.o \ book3s_hv_rm_mmu.o \ book3s_hv_ras.o \ diff --git a/arch/powerpc/kernel/hmi.c b/arch/powerpc/kvm/book3s_hv_hmi.c index e3f738e..e3f738e 100644 --- a/arch/powerpc/kernel/hmi.c +++ b/arch/powerpc/kvm/book3s_hv_hmi.c diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index a4db22f..bb1ffc5 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -26,7 +26,7 @@ #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/highmem.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/perf_event.h> diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c index 8eb82b0..d93dd4a 100644 --- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c +++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c @@ -528,7 +528,6 @@ static struct platform_driver mpc512x_lpbfifo_driver = { .remove = mpc512x_lpbfifo_remove, .driver = { .name = DRV_NAME, - .owner = THIS_MODULE, .of_match_table = mpc512x_lpbfifo_match, }, }; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index dbcd030..63c5ab64 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -222,7 +222,6 @@ static const struct of_device_id mcu_of_match_table[] = { static struct i2c_driver mcu_driver = { .driver = { .name = "mcu-mpc8349emitx", - .owner = THIS_MODULE, .of_match_table = mcu_of_match_table, }, .probe = mcu_probe, diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index dafba10..dfd3100 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -26,7 +26,7 @@ #include <linux/tty.h> #include <linux/serial_core.h> #include <linux/of_platform.h> -#include <linux/module.h> +#include <linux/extable.h> #include <asm/time.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 80804f9..f97bab8 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -23,7 +23,7 @@ #include <linux/pci.h> #include <linux/kdev_t.h> #include <linux/console.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/delay.h> #include <linux/irq.h> #include <linux/seq_file.h> diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 2ee9643..4c82782 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -370,6 +370,7 @@ static irqreturn_t process_dump(int irq, void *data) uint32_t dump_id, dump_size, dump_type; struct dump_obj *dump; char name[22]; + struct kobject *kobj; rc = dump_read_info(&dump_id, &dump_size, &dump_type); if (rc != OPAL_SUCCESS) @@ -381,8 +382,12 @@ static irqreturn_t process_dump(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(dump_kset, name)) + kobj = kset_find_obj(dump_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return 0; + } dump = create_dump_obj(dump_id, dump_size, dump_type); if (!dump) diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 37f959b..f2344cb 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -247,6 +247,7 @@ static irqreturn_t elog_event(int irq, void *data) uint64_t elog_type; int rc; char name[2+16+1]; + struct kobject *kobj; rc = opal_get_elog_size(&id, &size, &type); if (rc != OPAL_SUCCESS) { @@ -269,8 +270,12 @@ static irqreturn_t elog_event(int irq, void *data) * that gracefully and not create two conflicting * entries. */ - if (kset_find_obj(elog_kset, name)) + kobj = kset_find_obj(elog_kset, name); + if (kobj) { + /* Drop reference added by kset_find_obj() */ + kobject_put(kobj); return IRQ_HANDLED; + } create_elog_obj(log_id, elog_size, elog_type); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index fd9444f..1321826 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -149,7 +149,7 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no) static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb) { - unsigned long pe = phb->ioda.total_pe_num - 1; + long pe; for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) { if (!test_and_set_bit(pe, phb->ioda.pe_alloc)) diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index fe16a50..09eba5a 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -119,6 +119,10 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) bus = bridge->bus; + /* Rely on the pcibios_free_controller_deferred() callback. */ + pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred, + (void *) pci_bus_to_host(bus)); + dn = pcibios_get_phb_of_node(bus); if (!dn) return 0; diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 906dbaa..547fd13 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -106,8 +106,11 @@ int remove_phb_dynamic(struct pci_controller *phb) release_resource(res); } - /* Free pci_controller data structure */ - pcibios_free_controller(phb); + /* + * The pci_controller data structure is freed by + * the pcibios_free_controller_deferred() callback; + * see pseries_root_bridge_prepare(). + */ return 0; } diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 6c11099..81d4947 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -534,7 +534,8 @@ struct cpm1_gpio16_chip { static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = + container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc); struct cpm_ioport16 __iomem *iop = mm_gc->regs; cpm1_gc->cpdata = in_be16(&iop->dat); @@ -649,7 +650,8 @@ struct cpm1_gpio32_chip { static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio32_chip *cpm1_gc = + container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc); struct cpm_ioport32b __iomem *iop = mm_gc->regs; cpm1_gc->cpdata = in_be32(&iop->dat); diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c index 911456d..947f420 100644 --- a/arch/powerpc/sysdev/cpm_common.c +++ b/arch/powerpc/sysdev/cpm_common.c @@ -94,7 +94,8 @@ struct cpm2_gpio32_chip { static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) { - struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm2_gpio32_chip *cpm2_gc = + container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc); struct cpm2_ioports __iomem *iop = mm_gc->regs; cpm2_gc->cpdata = in_be32(&iop->dat); diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 68e7c0d..3cc7cac 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -23,7 +23,7 @@ */ #include <linux/init.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/types.h> #include <linux/dma-mapping.h> #include <linux/interrupt.h> diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ba5f456..7f7ba5f2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -204,11 +204,9 @@ static void __init conmode_default(void) #endif } } else if (MACHINE_IS_KVM) { - if (sclp.has_vt220 && - config_enabled(CONFIG_SCLP_VT220_CONSOLE)) + if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE)) SET_CONSOLE_VT220; - else if (sclp.has_linemode && - config_enabled(CONFIG_SCLP_CONSOLE)) + else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE)) SET_CONSOLE_SCLP; else SET_CONSOLE_HVC; diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 1dd5bd8..1330553 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -81,7 +81,7 @@ .altinstr_replacement : { *(.altinstr_replacement) } /* .exit.text is discard at runtime, not link time, to deal with references from .altinstructions and .eh_frame */ - .exit.text : { *(.exit.text) } + .exit.text : { EXIT_TEXT } .exit.data : { *(.exit.data) } .preinit_array : { diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c index 89fa85e..6f97fb3 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb.c +++ b/arch/x86/crypto/sha256-mb/sha256_mb.c @@ -485,10 +485,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index b691da9..a78a069 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -265,13 +265,14 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0 - movl _args_digest+4*32(state, idx, 4), tmp2_w + vmovd _args_digest(state , idx, 4) , %xmm0 vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1 - vmovdqu %xmm0, _result_digest(job_rax) - movl tmp2_w, _result_digest+1*16(job_rax) + vmovdqu %xmm0, _result_digest(job_rax) + offset = (_result_digest + 1*16) + vmovdqu %xmm1, offset(job_rax) pop %rbx diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index f4cf5b7..d210174 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -497,10 +497,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index cea4fc1..50c95af 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1623,6 +1623,9 @@ void __init enable_IR_x2apic(void) unsigned long flags; int ret, ir_stat; + if (skip_ioapic_setup) + return; + ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 27a0228..b816971 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -355,6 +355,7 @@ void load_ucode_amd_ap(void) unsigned int cpu = smp_processor_id(); struct equiv_cpu_entry *eq; struct microcode_amd *mc; + u8 *cont = container; u32 rev, eax; u16 eq_id; @@ -371,8 +372,11 @@ void load_ucode_amd_ap(void) if (check_current_patch_level(&rev, false)) return; + /* Add CONFIG_RANDOMIZE_MEMORY offset. */ + cont += PAGE_OFFSET - __PAGE_OFFSET_BASE; + eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); + eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ); eq_id = find_equiv_id(eq, eax); if (!eq_id) @@ -434,6 +438,9 @@ int __init save_microcode_in_initrd_amd(void) else container = cont_va; + /* Add CONFIG_RANDOMIZE_MEMORY offset. */ + container += PAGE_OFFSET - __PAGE_OFFSET_BASE; + eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2a6e84a..4296beb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -100,10 +100,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); /* Logical package management. We might want to allocate that dynamically */ static int *physical_to_logical_pkg __read_mostly; static unsigned long *physical_package_map __read_mostly;; -static unsigned long *logical_package_map __read_mostly; static unsigned int max_physical_pkg_id __read_mostly; unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); +static unsigned int logical_packages __read_mostly; +static bool logical_packages_frozen __read_mostly; /* Maximum number of SMT threads on any online core */ int __max_smt_threads __read_mostly; @@ -277,14 +278,14 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu) if (test_and_set_bit(pkg, physical_package_map)) goto found; - new = find_first_zero_bit(logical_package_map, __max_logical_packages); - if (new >= __max_logical_packages) { + if (logical_packages_frozen) { physical_to_logical_pkg[pkg] = -1; - pr_warn("APIC(%x) Package %u exceeds logical package map\n", + pr_warn("APIC(%x) Package %u exceeds logical package max\n", apicid, pkg); return -ENOSPC; } - set_bit(new, logical_package_map); + + new = logical_packages++; pr_info("APIC(%x) Converting physical %u to logical package %u\n", apicid, pkg, new); physical_to_logical_pkg[pkg] = new; @@ -341,6 +342,7 @@ static void __init smp_init_package_map(void) } __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); + logical_packages = 0; /* * Possibly larger than what we need as the number of apic ids per @@ -352,10 +354,6 @@ static void __init smp_init_package_map(void) memset(physical_to_logical_pkg, 0xff, size); size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); physical_package_map = kzalloc(size, GFP_KERNEL); - size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long); - logical_package_map = kzalloc(size, GFP_KERNEL); - - pr_info("Max logical packages: %u\n", __max_logical_packages); for_each_present_cpu(cpu) { unsigned int apicid = apic->cpu_present_to_apicid(cpu); @@ -369,6 +367,15 @@ static void __init smp_init_package_map(void) set_cpu_possible(cpu, false); set_cpu_present(cpu, false); } + + if (logical_packages > __max_logical_packages) { + pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n", + logical_packages, __max_logical_packages); + logical_packages_frozen = true; + __max_logical_packages = logical_packages; + } + + pr_info("Max logical packages: %u\n", __max_logical_packages); } void __init smp_store_boot_cpu_info(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a45d858..5cede40 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -422,6 +422,7 @@ struct nested_vmx { struct list_head vmcs02_pool; int vmcs02_num; u64 vmcs01_tsc_offset; + bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; /* @@ -435,6 +436,8 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; + unsigned long *msr_bitmap; + struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -924,7 +927,6 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; -static unsigned long *vmx_msr_bitmap_nested; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -2198,6 +2200,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.control) != old.control); } +static void decache_tsc_multiplier(struct vcpu_vmx *vmx) +{ + vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -2256,10 +2264,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Setup TSC multiplier */ if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { - vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; - vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); - } + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) + decache_tsc_multiplier(vmx); vmx_vcpu_pi_load(vcpu, cpu); vmx->host_pkru = read_pkru(); @@ -2508,7 +2514,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) unsigned long *msr_bitmap; if (is_guest_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_nested; + msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; else if (cpu_has_secondary_exec_ctrls() && (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { @@ -6363,13 +6369,6 @@ static __init int hardware_setup(void) if (!vmx_msr_bitmap_longmode_x2apic) goto out4; - if (nested) { - vmx_msr_bitmap_nested = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_nested) - goto out5; - } - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) goto out6; @@ -6392,8 +6391,6 @@ static __init int hardware_setup(void) memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (nested) - memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE); if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; @@ -6529,9 +6526,6 @@ out8: out7: free_page((unsigned long)vmx_vmread_bitmap); out6: - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); -out5: free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); out4: free_page((unsigned long)vmx_msr_bitmap_longmode); @@ -6557,8 +6551,6 @@ static __exit void hardware_unsetup(void) free_page((unsigned long)vmx_io_bitmap_a); free_page((unsigned long)vmx_vmwrite_bitmap); free_page((unsigned long)vmx_vmread_bitmap); - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); free_kvm_area(); } @@ -6995,16 +6987,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) - return -ENOMEM; + goto out_cached_vmcs12; if (enable_shadow_vmcs) { shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) { - kfree(vmx->nested.cached_vmcs12); - return -ENOMEM; - } + if (!shadow_vmcs) + goto out_shadow_vmcs; /* mark vmcs as shadow */ shadow_vmcs->revision_id |= (1u << 31); /* init shadow vmcs */ @@ -7024,6 +7021,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; } /* @@ -7098,6 +7104,10 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); + if (vmx->nested.msr_bitmap) { + free_page((unsigned long)vmx->nested.msr_bitmap); + vmx->nested.msr_bitmap = NULL; + } if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); kfree(vmx->nested.cached_vmcs12); @@ -8419,6 +8429,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) { u32 sec_exec_control; + /* Postpone execution until vmcs01 is the current VMCS. */ + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + return; + } + /* * There is not point to enable virtualize x2apic without enable * apicv @@ -9472,8 +9488,10 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, { int msr; struct page *page; - unsigned long *msr_bitmap; + unsigned long *msr_bitmap_l1; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + /* This shortcut is ok because we support only x2APIC MSRs so far. */ if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) return false; @@ -9482,63 +9500,37 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, WARN_ON(1); return false; } - msr_bitmap = (unsigned long *)kmap(page); - if (!msr_bitmap) { + msr_bitmap_l1 = (unsigned long *)kmap(page); + if (!msr_bitmap_l1) { nested_release_page_clean(page); WARN_ON(1); return false; } + memset(msr_bitmap_l0, 0xff, PAGE_SIZE); + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { if (nested_cpu_has_apic_reg_virt(vmcs12)) for (msr = 0x800; msr <= 0x8ff; msr++) nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, msr, MSR_TYPE_R); - /* TPR is allowed */ - nested_vmx_disable_intercept_for_msr(msr_bitmap, - vmx_msr_bitmap_nested, + + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_TASKPRI >> 4), MSR_TYPE_R | MSR_TYPE_W); + if (nested_cpu_has_vid(vmcs12)) { - /* EOI and self-IPI are allowed */ nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_EOI >> 4), MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_SELF_IPI >> 4), MSR_TYPE_W); } - } else { - /* - * Enable reading intercept of all the x2apic - * MSRs. We should not rely on vmcs12 to do any - * optimizations here, it may have been modified - * by L1. - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - msr, - MSR_TYPE_R); - - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); } kunmap(page); nested_release_page_clean(page); @@ -9957,10 +9949,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS) { - nested_vmx_merge_msr_bitmap(vcpu, vmcs12); - /* MSR_BITMAP will be set by following vmx_set_efer. */ - } else + exec_control & CPU_BASED_USE_MSR_BITMAPS && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; /* MSR_BITMAP will be set by following vmx_set_efer. */ + else exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; /* @@ -10011,6 +10003,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); else vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); if (enable_vpid) { /* @@ -10767,6 +10761,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, else vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); + + if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { + vmx->nested.change_vmcs01_virtual_x2apic_mode = false; + vmx_set_virtual_x2apic_mode(vcpu, + vcpu->arch.apic_base & X2APIC_ENABLE); + } /* This is needed for same reason as it was needed in prepare_vmcs02 */ vmx->host_rsp = 0; diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index ec8654f..bda8d5e 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -77,7 +77,7 @@ static inline unsigned long get_padding(struct kaslr_memory_region *region) */ static inline bool kaslr_memory_enabled(void) { - return kaslr_enabled() && !config_enabled(CONFIG_KASAN); + return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN); } /* Initialize base and padding for each memory region randomized with KASLR */ diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index b814ca6..7948be3 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -41,6 +41,7 @@ static DEFINE_RAW_SPINLOCK(list_lock); * @node: list item for parent traversal. * @rcu: RCU callback item for freeing. * @irq: back pointer to parent. + * @enabled: true if driver enabled IRQ * @virq: the virtual IRQ value provided to the requesting driver. * * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to @@ -50,6 +51,7 @@ struct vmd_irq { struct list_head node; struct rcu_head rcu; struct vmd_irq_list *irq; + bool enabled; unsigned int virq; }; @@ -122,7 +124,9 @@ static void vmd_irq_enable(struct irq_data *data) unsigned long flags; raw_spin_lock_irqsave(&list_lock, flags); + WARN_ON(vmdirq->enabled); list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + vmdirq->enabled = true; raw_spin_unlock_irqrestore(&list_lock, flags); data->chip->irq_unmask(data); @@ -136,8 +140,10 @@ static void vmd_irq_disable(struct irq_data *data) data->chip->irq_mask(data); raw_spin_lock_irqsave(&list_lock, flags); - list_del_rcu(&vmdirq->node); - INIT_LIST_HEAD_RCU(&vmdirq->node); + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } raw_spin_unlock_irqrestore(&list_lock, flags); } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index a3e3ccc..9634557 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -113,7 +113,7 @@ static int set_up_temporary_mappings(void) return result; } - temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET; + temp_level4_pgt = __pa(pgd); return 0; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 8ffb089..b86ebb1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -118,7 +118,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); enum xen_domain_type xen_domain_type = XEN_NATIVE; diff --git a/block/bio.c b/block/bio.c index f394775..aa73540 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-core.c b/block/blk-core.c index 999442e..36c7ac3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end); void blk_set_queue_dying(struct request_queue *q) { - queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); if (q->mq_ops) blk_mq_wake_waiters(q); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a..2642e5f 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,9 +94,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is the + * bio_clone() in bio bounce. + * + * If bio is splitted by this reason, we should have + * allowed to continue bios merging, but don't do + * that now for making the change simple. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs++ >= BIO_MAX_PAGES) + goto split; + + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ @@ -172,12 +194,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +241,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +413,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +423,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/blk-mq.c b/block/blk-mq.c index e931a0e..13f5a6c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -793,11 +793,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) struct list_head *dptr; int queued; - WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)); - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; + WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && + cpu_online(hctx->next_cpu)); + hctx->run++; /* @@ -1036,10 +1037,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) EXPORT_SYMBOL(blk_mq_delay_queue); static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, struct request *rq, bool at_head) { + struct blk_mq_ctx *ctx = rq->mq_ctx; + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1053,20 +1055,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, at_head); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, - bool async) + bool async) { + struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - if (!cpu_online(ctx->cpu)) - rq->mq_ctx = ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1076,8 +1074,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, if (run_queue) blk_mq_run_hw_queue(hctx, async); - - blk_mq_put_ctx(current_ctx); } static void blk_mq_insert_requests(struct request_queue *q, @@ -1088,14 +1084,9 @@ static void blk_mq_insert_requests(struct request_queue *q, { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *current_ctx; trace_block_unplug(q, depth, !from_schedule); - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) - ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); /* @@ -1107,15 +1098,14 @@ static void blk_mq_insert_requests(struct request_queue *q, struct request *rq; rq = list_first_entry(list, struct request, queuelist); + BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); - rq->mq_ctx = ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, false); + __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); - blk_mq_put_ctx(current_ctx); } static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1630,16 +1620,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node) return 0; } +/* + * 'cpu' is going away. splice any existing rq_list entries from this + * software queue to the hw queue dispatch list, and ensure that it + * gets run. + */ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) { - struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); - /* - * Move ctx entries to new CPU, if this one is going away. - */ - ctx = __blk_mq_get_ctx(q, cpu); + ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { @@ -1651,24 +1642,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) if (list_empty(&tmp)) return NOTIFY_OK; - ctx = blk_mq_get_ctx(q); - spin_lock(&ctx->lock); - - while (!list_empty(&tmp)) { - struct request *rq; - - rq = list_first_entry(&tmp, struct request, queuelist); - rq->mq_ctx = ctx; - list_move_tail(&rq->queuelist, &ctx->rq_list); - } - - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_hctx_mark_pending(hctx, ctx); - - spin_unlock(&ctx->lock); + spin_lock(&hctx->lock); + list_splice_tail_init(&tmp, &hctx->dispatch); + spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); - blk_mq_put_ctx(ctx); return NOTIFY_OK; } diff --git a/block/elevator.c b/block/elevator.c index 7096c22..f7d973a 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b71a9c7..e3d8e4c 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3706,22 +3706,21 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - if (mode & (FMODE_READ|FMODE_WRITE)) { - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + if (!(mode & FMODE_NDELAY)) { + if (mode & (FMODE_READ|FMODE_WRITE)) { + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; + } + res = -EROFS; + if ((mode & FMODE_WRITE) && + !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) goto out; } - - res = -EROFS; - - if ((mode & FMODE_WRITE) && - !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) - goto out; - mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); return 0; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index be4fea6..88ef6d4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -189,6 +189,8 @@ struct blkfront_info struct mutex mutex; struct xenbus_device *xbdev; struct gendisk *gd; + u16 sector_size; + unsigned int physical_sector_size; int vdevice; blkif_vdev_t handle; enum blkif_state connected; @@ -910,9 +912,45 @@ static struct blk_mq_ops blkfront_mq_ops = { .map_queue = blk_mq_map_queue, }; +static void blkif_set_queue_limits(struct blkfront_info *info) +{ + struct request_queue *rq = info->rq; + struct gendisk *gd = info->gd; + unsigned int segments = info->max_indirect_segments ? : + BLKIF_MAX_SEGMENTS_PER_REQUEST; + + queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); + + if (info->feature_discard) { + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); + blk_queue_max_discard_sectors(rq, get_capacity(gd)); + rq->limits.discard_granularity = info->discard_granularity; + rq->limits.discard_alignment = info->discard_alignment; + if (info->feature_secdiscard) + queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); + } + + /* Hard sector size and max sectors impersonate the equiv. hardware. */ + blk_queue_logical_block_size(rq, info->sector_size); + blk_queue_physical_block_size(rq, info->physical_sector_size); + blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); + + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(rq, PAGE_SIZE - 1); + blk_queue_max_segment_size(rq, PAGE_SIZE); + + /* Ensure a merged request will fit in a single I/O ring slot. */ + blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); + + /* Make sure buffer addresses are sector-aligned. */ + blk_queue_dma_alignment(rq, 511); + + /* Make sure we don't use bounce buffers. */ + blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); +} + static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, - unsigned int physical_sector_size, - unsigned int segments) + unsigned int physical_sector_size) { struct request_queue *rq; struct blkfront_info *info = gd->private_data; @@ -944,36 +982,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, } rq->queuedata = info; - queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); - - if (info->feature_discard) { - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); - blk_queue_max_discard_sectors(rq, get_capacity(gd)); - rq->limits.discard_granularity = info->discard_granularity; - rq->limits.discard_alignment = info->discard_alignment; - if (info->feature_secdiscard) - queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); - } - - /* Hard sector size and max sectors impersonate the equiv. hardware. */ - blk_queue_logical_block_size(rq, sector_size); - blk_queue_physical_block_size(rq, physical_sector_size); - blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); - - /* Each segment in a request is up to an aligned page in size. */ - blk_queue_segment_boundary(rq, PAGE_SIZE - 1); - blk_queue_max_segment_size(rq, PAGE_SIZE); - - /* Ensure a merged request will fit in a single I/O ring slot. */ - blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); - - /* Make sure buffer addresses are sector-aligned. */ - blk_queue_dma_alignment(rq, 511); - - /* Make sure we don't use bounce buffers. */ - blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); - - gd->queue = rq; + info->rq = gd->queue = rq; + info->gd = gd; + info->sector_size = sector_size; + info->physical_sector_size = physical_sector_size; + blkif_set_queue_limits(info); return 0; } @@ -1136,16 +1149,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, gd->private_data = info; set_capacity(gd, capacity); - if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size, - info->max_indirect_segments ? : - BLKIF_MAX_SEGMENTS_PER_REQUEST)) { + if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) { del_gendisk(gd); goto release; } - info->rq = gd->queue; - info->gd = gd; - xlvbd_flush(info); if (vdisk_info & VDISK_READONLY) @@ -1315,7 +1323,7 @@ free_shadow: rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE)); + free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); rinfo->ring.sring = NULL; if (rinfo->irq) @@ -2007,8 +2015,10 @@ static int blkif_recover(struct blkfront_info *info) struct split_bio *split_bio; blkfront_gather_backend_features(info); + /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ + blkif_set_queue_limits(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; - blk_queue_max_segments(info->rq, segs); + blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); for (r_index = 0; r_index < info->nr_rings; r_index++) { struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; @@ -2432,7 +2442,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", info->xbdev->otherend); - return; + goto fail; } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2445,6 +2455,11 @@ static void blkfront_connect(struct blkfront_info *info) device_add_disk(&info->xbdev->dev, info->gd); info->is_ready = 1; + return; + +fail: + blkif_free(info, 0); + return; } /** diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c index 7e3fd37..92f6e4d 100644 --- a/drivers/clocksource/bcm_kona_timer.c +++ b/drivers/clocksource/bcm_kona_timer.c @@ -66,10 +66,10 @@ static void kona_timer_disable_and_clear(void __iomem *base) } -static void +static int kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw) { - int loop_limit = 4; + int loop_limit = 3; /* * Read 64-bit free running counter @@ -83,18 +83,19 @@ kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw) * if new hi-word is equal to previously read hi-word then stop. */ - while (--loop_limit) { + do { *msw = readl(timer_base + KONA_GPTIMER_STCHI_OFFSET); *lsw = readl(timer_base + KONA_GPTIMER_STCLO_OFFSET); if (*msw == readl(timer_base + KONA_GPTIMER_STCHI_OFFSET)) break; - } + } while (--loop_limit); if (!loop_limit) { pr_err("bcm_kona_timer: getting counter failed.\n"); pr_err(" Timer will be impacted\n"); + return -ETIMEDOUT; } - return; + return 0; } static int kona_timer_set_next_event(unsigned long clc, @@ -112,8 +113,11 @@ static int kona_timer_set_next_event(unsigned long clc, uint32_t lsw, msw; uint32_t reg; + int ret; - kona_timer_get_counter(timers.tmr_regs, &msw, &lsw); + ret = kona_timer_get_counter(timers.tmr_regs, &msw, &lsw); + if (ret) + return ret; /* Load the "next" event tick value */ writel(lsw + clc, timers.tmr_regs + KONA_GPTIMER_STCM0_OFFSET); diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index d91e872..b4b3ab5 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -164,7 +164,7 @@ void __init gic_clocksource_init(unsigned int frequency) gic_start_count(); } -static void __init gic_clocksource_of_init(struct device_node *node) +static int __init gic_clocksource_of_init(struct device_node *node) { struct clk *clk; int ret; diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c index 937e10b..3e1cb51 100644 --- a/drivers/clocksource/pxa_timer.c +++ b/drivers/clocksource/pxa_timer.c @@ -21,6 +21,8 @@ #include <linux/of_irq.h> #include <linux/sched_clock.h> +#include <clocksource/pxa.h> + #include <asm/div64.h> #define OSMR0 0x00 /* OS Timer 0 Match Register */ diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index 97669ee..c83452c 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -123,12 +123,16 @@ static struct clock_event_device sun4i_clockevent = { .set_next_event = sun4i_clkevt_next_event, }; +static void sun4i_timer_clear_interrupt(void) +{ + writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG); +} static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id) { struct clock_event_device *evt = (struct clock_event_device *)dev_id; - writel(0x1, timer_base + TIMER_IRQ_ST_REG); + sun4i_timer_clear_interrupt(); evt->event_handler(evt); return IRQ_HANDLED; @@ -208,6 +212,9 @@ static int __init sun4i_timer_init(struct device_node *node) /* Make sure timer is stopped before playing with interrupts */ sun4i_clkevt_time_stop(0); + /* clear timer0 interrupt */ + sun4i_timer_clear_interrupt(); + sun4i_clockevent.cpumask = cpu_possible_mask; sun4i_clockevent.irq = irq; diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c index 719b478..3c39e6f 100644 --- a/drivers/clocksource/time-armada-370-xp.c +++ b/drivers/clocksource/time-armada-370-xp.c @@ -338,7 +338,6 @@ static int __init armada_xp_timer_init(struct device_node *np) struct clk *clk = of_clk_get_by_name(np, "fixed"); int ret; - clk = of_clk_get(np, 0); if (IS_ERR(clk)) { pr_err("Failed to get clock"); return PTR_ERR(clk); diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c index a7d9a08..a8e6c7d 100644 --- a/drivers/clocksource/time-pistachio.c +++ b/drivers/clocksource/time-pistachio.c @@ -202,10 +202,10 @@ static int __init pistachio_clksrc_of_init(struct device_node *node) rate = clk_get_rate(fast_clk); /* Disable irq's for clocksource usage */ - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 0); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 1); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 2); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 3); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 0); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 1); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 2); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 3); /* Enable timer block */ writel(TIMER_ME_GLOBAL, pcs_gpt.base); diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index 1ffac0c..3494bc5 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -261,6 +261,12 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) return PTR_ERR(data->mck); } + ret = clk_prepare_enable(data->mck); + if (ret) { + pr_err("Unable to enable mck\n"); + return ret; + } + /* Get the interrupts property */ data->irq = irq_of_parse_and_map(node, 0); if (!data->irq) { diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index dfb1685..1f01e98 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -116,6 +116,9 @@ static int dax_pmem_probe(struct device *dev) if (rc) return rc; + /* adjust the dax_region resource to the start of data */ + res.start += le64_to_cpu(pfn_sb->dataoff); + nd_region = to_nd_region(dev->parent); dax_region = alloc_dax_region(dev, nd_region->id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index d0c1dab..dff1a4a 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -251,6 +251,14 @@ config EDAC_SBRIDGE Support for error detection and correction the Intel Sandy Bridge, Ivy Bridge and Haswell Integrated Memory Controllers. +config EDAC_SKX + tristate "Intel Skylake server Integrated MC" + depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL + depends on PCI_MMCONFIG + help + Support for error detection and correction the Intel + Skylake server Integrated Memory Controllers. + config EDAC_MPC85XX tristate "Freescale MPC83xx / MPC85xx" depends on EDAC_MM_EDAC && FSL_SOC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index f9e4a3e..9860499 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_EDAC_I5400) += i5400_edac.o obj-$(CONFIG_EDAC_I7300) += i7300_edac.o obj-$(CONFIG_EDAC_I7CORE) += i7core_edac.o obj-$(CONFIG_EDAC_SBRIDGE) += sb_edac.o +obj-$(CONFIG_EDAC_SKX) += skx_edac.o obj-$(CONFIG_EDAC_E7XXX) += e7xxx_edac.o obj-$(CONFIG_EDAC_E752X) += e752x_edac.o obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c new file mode 100644 index 0000000..0ff4878 --- /dev/null +++ b/drivers/edac/skx_edac.c @@ -0,0 +1,1121 @@ +/* + * EDAC driver for Intel(R) Xeon(R) Skylake processors + * Copyright (c) 2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/edac.h> +#include <linux/mmzone.h> +#include <linux/smp.h> +#include <linux/bitmap.h> +#include <linux/math64.h> +#include <linux/mod_devicetable.h> +#include <asm/cpu_device_id.h> +#include <asm/processor.h> +#include <asm/mce.h> + +#include "edac_core.h" + +#define SKX_REVISION " Ver: 1.0 " + +/* + * Debug macros + */ +#define skx_printk(level, fmt, arg...) \ + edac_printk(level, "skx", fmt, ##arg) + +#define skx_mc_printk(mci, level, fmt, arg...) \ + edac_mc_chipset_printk(mci, level, "skx", fmt, ##arg) + +/* + * Get a bit field at register value <v>, from bit <lo> to bit <hi> + */ +#define GET_BITFIELD(v, lo, hi) \ + (((v) & GENMASK_ULL((hi), (lo))) >> (lo)) + +static LIST_HEAD(skx_edac_list); + +static u64 skx_tolm, skx_tohm; + +#define NUM_IMC 2 /* memory controllers per socket */ +#define NUM_CHANNELS 3 /* channels per memory controller */ +#define NUM_DIMMS 2 /* Max DIMMS per channel */ + +#define MASK26 0x3FFFFFF /* Mask for 2^26 */ +#define MASK29 0x1FFFFFFF /* Mask for 2^29 */ + +/* + * Each cpu socket contains some pci devices that provide global + * information, and also some that are local to each of the two + * memory controllers on the die. + */ +struct skx_dev { + struct list_head list; + u8 bus[4]; + struct pci_dev *sad_all; + struct pci_dev *util_all; + u32 mcroute; + struct skx_imc { + struct mem_ctl_info *mci; + u8 mc; /* system wide mc# */ + u8 lmc; /* socket relative mc# */ + u8 src_id, node_id; + struct skx_channel { + struct pci_dev *cdev; + struct skx_dimm { + u8 close_pg; + u8 bank_xor_enable; + u8 fine_grain_bank; + u8 rowbits; + u8 colbits; + } dimms[NUM_DIMMS]; + } chan[NUM_CHANNELS]; + } imc[NUM_IMC]; +}; +static int skx_num_sockets; + +struct skx_pvt { + struct skx_imc *imc; +}; + +struct decoded_addr { + struct skx_dev *dev; + u64 addr; + int socket; + int imc; + int channel; + u64 chan_addr; + int sktways; + int chanways; + int dimm; + int rank; + int channel_rank; + u64 rank_address; + int row; + int column; + int bank_address; + int bank_group; +}; + +static struct skx_dev *get_skx_dev(u8 bus, u8 idx) +{ + struct skx_dev *d; + + list_for_each_entry(d, &skx_edac_list, list) { + if (d->bus[idx] == bus) + return d; + } + + return NULL; +} + +enum munittype { + CHAN0, CHAN1, CHAN2, SAD_ALL, UTIL_ALL, SAD +}; + +struct munit { + u16 did; + u16 devfn[NUM_IMC]; + u8 busidx; + u8 per_socket; + enum munittype mtype; +}; + +/* + * List of PCI device ids that we need together with some device + * number and function numbers to tell which memory controller the + * device belongs to. + */ +static const struct munit skx_all_munits[] = { + { 0x2054, { }, 1, 1, SAD_ALL }, + { 0x2055, { }, 1, 1, UTIL_ALL }, + { 0x2040, { PCI_DEVFN(10, 0), PCI_DEVFN(12, 0) }, 2, 2, CHAN0 }, + { 0x2044, { PCI_DEVFN(10, 4), PCI_DEVFN(12, 4) }, 2, 2, CHAN1 }, + { 0x2048, { PCI_DEVFN(11, 0), PCI_DEVFN(13, 0) }, 2, 2, CHAN2 }, + { 0x208e, { }, 1, 0, SAD }, + { } +}; + +/* + * We use the per-socket device 0x2016 to count how many sockets are present, + * and to detemine which PCI buses are associated with each socket. Allocate + * and build the full list of all the skx_dev structures that we need here. + */ +static int get_all_bus_mappings(void) +{ + struct pci_dev *pdev, *prev; + struct skx_dev *d; + u32 reg; + int ndev = 0; + + prev = NULL; + for (;;) { + pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2016, prev); + if (!pdev) + break; + ndev++; + d = kzalloc(sizeof(*d), GFP_KERNEL); + if (!d) { + pci_dev_put(pdev); + return -ENOMEM; + } + pci_read_config_dword(pdev, 0xCC, ®); + d->bus[0] = GET_BITFIELD(reg, 0, 7); + d->bus[1] = GET_BITFIELD(reg, 8, 15); + d->bus[2] = GET_BITFIELD(reg, 16, 23); + d->bus[3] = GET_BITFIELD(reg, 24, 31); + edac_dbg(2, "busses: %x, %x, %x, %x\n", + d->bus[0], d->bus[1], d->bus[2], d->bus[3]); + list_add_tail(&d->list, &skx_edac_list); + skx_num_sockets++; + prev = pdev; + } + + return ndev; +} + +static int get_all_munits(const struct munit *m) +{ + struct pci_dev *pdev, *prev; + struct skx_dev *d; + u32 reg; + int i = 0, ndev = 0; + + prev = NULL; + for (;;) { + pdev = pci_get_device(PCI_VENDOR_ID_INTEL, m->did, prev); + if (!pdev) + break; + ndev++; + if (m->per_socket == NUM_IMC) { + for (i = 0; i < NUM_IMC; i++) + if (m->devfn[i] == pdev->devfn) + break; + if (i == NUM_IMC) + goto fail; + } + d = get_skx_dev(pdev->bus->number, m->busidx); + if (!d) + goto fail; + + /* Be sure that the device is enabled */ + if (unlikely(pci_enable_device(pdev) < 0)) { + skx_printk(KERN_ERR, + "Couldn't enable %04x:%04x\n", PCI_VENDOR_ID_INTEL, m->did); + goto fail; + } + + switch (m->mtype) { + case CHAN0: case CHAN1: case CHAN2: + pci_dev_get(pdev); + d->imc[i].chan[m->mtype].cdev = pdev; + break; + case SAD_ALL: + pci_dev_get(pdev); + d->sad_all = pdev; + break; + case UTIL_ALL: + pci_dev_get(pdev); + d->util_all = pdev; + break; + case SAD: + /* + * one of these devices per core, including cores + * that don't exist on this SKU. Ignore any that + * read a route table of zero, make sure all the + * non-zero values match. + */ + pci_read_config_dword(pdev, 0xB4, ®); + if (reg != 0) { + if (d->mcroute == 0) + d->mcroute = reg; + else if (d->mcroute != reg) { + skx_printk(KERN_ERR, + "mcroute mismatch\n"); + goto fail; + } + } + ndev--; + break; + } + + prev = pdev; + } + + return ndev; +fail: + pci_dev_put(pdev); + return -ENODEV; +} + +const struct x86_cpu_id skx_cpuids[] = { + { X86_VENDOR_INTEL, 6, 0x55, 0, 0 }, /* Skylake */ + { } +}; +MODULE_DEVICE_TABLE(x86cpu, skx_cpuids); + +static u8 get_src_id(struct skx_dev *d) +{ + u32 reg; + + pci_read_config_dword(d->util_all, 0xF0, ®); + + return GET_BITFIELD(reg, 12, 14); +} + +static u8 skx_get_node_id(struct skx_dev *d) +{ + u32 reg; + + pci_read_config_dword(d->util_all, 0xF4, ®); + + return GET_BITFIELD(reg, 0, 2); +} + +static int get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, + int maxval, char *name) +{ + u32 val = GET_BITFIELD(reg, lobit, hibit); + + if (val < minval || val > maxval) { + edac_dbg(2, "bad %s = %d (raw=%x)\n", name, val, reg); + return -EINVAL; + } + return val + add; +} + +#define IS_DIMM_PRESENT(mtr) GET_BITFIELD((mtr), 15, 15) + +#define numrank(reg) get_dimm_attr((reg), 12, 13, 0, 1, 2, "ranks") +#define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows") +#define numcol(reg) get_dimm_attr((reg), 0, 1, 10, 0, 2, "cols") + +static int get_width(u32 mtr) +{ + switch (GET_BITFIELD(mtr, 8, 9)) { + case 0: + return DEV_X4; + case 1: + return DEV_X8; + case 2: + return DEV_X16; + } + return DEV_UNKNOWN; +} + +static int skx_get_hi_lo(void) +{ + struct pci_dev *pdev; + u32 reg; + + pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2034, NULL); + if (!pdev) { + edac_dbg(0, "Can't get tolm/tohm\n"); + return -ENODEV; + } + + pci_read_config_dword(pdev, 0xD0, ®); + skx_tolm = reg; + pci_read_config_dword(pdev, 0xD4, ®); + skx_tohm = reg; + pci_read_config_dword(pdev, 0xD8, ®); + skx_tohm |= (u64)reg << 32; + + pci_dev_put(pdev); + edac_dbg(2, "tolm=%llx tohm=%llx\n", skx_tolm, skx_tohm); + + return 0; +} + +static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, + struct skx_imc *imc, int chan, int dimmno) +{ + int banks = 16, ranks, rows, cols, npages; + u64 size; + + if (!IS_DIMM_PRESENT(mtr)) + return 0; + ranks = numrank(mtr); + rows = numrow(mtr); + cols = numcol(mtr); + + /* + * Compute size in 8-byte (2^3) words, then shift to MiB (2^20) + */ + size = ((1ull << (rows + cols + ranks)) * banks) >> (20 - 3); + npages = MiB_TO_PAGES(size); + + edac_dbg(0, "mc#%d: channel %d, dimm %d, %lld Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n", + imc->mc, chan, dimmno, size, npages, + banks, ranks, rows, cols); + + imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mtr, 0, 0); + imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mtr, 9, 9); + imc->chan[chan].dimms[dimmno].fine_grain_bank = GET_BITFIELD(amap, 0, 0); + imc->chan[chan].dimms[dimmno].rowbits = rows; + imc->chan[chan].dimms[dimmno].colbits = cols; + + dimm->nr_pages = npages; + dimm->grain = 32; + dimm->dtype = get_width(mtr); + dimm->mtype = MEM_DDR4; + dimm->edac_mode = EDAC_SECDED; /* likely better than this */ + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", + imc->src_id, imc->lmc, chan, dimmno); + + return 1; +} + +#define SKX_GET_MTMTR(dev, reg) \ + pci_read_config_dword((dev), 0x87c, ®) + +static bool skx_check_ecc(struct pci_dev *pdev) +{ + u32 mtmtr; + + SKX_GET_MTMTR(pdev, mtmtr); + + return !!GET_BITFIELD(mtmtr, 2, 2); +} + +static int skx_get_dimm_config(struct mem_ctl_info *mci) +{ + struct skx_pvt *pvt = mci->pvt_info; + struct skx_imc *imc = pvt->imc; + struct dimm_info *dimm; + int i, j; + u32 mtr, amap; + int ndimms; + + for (i = 0; i < NUM_CHANNELS; i++) { + ndimms = 0; + pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap); + for (j = 0; j < NUM_DIMMS; j++) { + dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, + mci->n_layers, i, j, 0); + pci_read_config_dword(imc->chan[i].cdev, + 0x80 + 4*j, &mtr); + ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + } + if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) { + skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc); + return -ENODEV; + } + } + + return 0; +} + +static void skx_unregister_mci(struct skx_imc *imc) +{ + struct mem_ctl_info *mci = imc->mci; + + if (!mci) + return; + + edac_dbg(0, "MC%d: mci = %p\n", imc->mc, mci); + + /* Remove MC sysfs nodes */ + edac_mc_del_mc(mci->pdev); + + edac_dbg(1, "%s: free mci struct\n", mci->ctl_name); + kfree(mci->ctl_name); + edac_mc_free(mci); +} + +static int skx_register_mci(struct skx_imc *imc) +{ + struct mem_ctl_info *mci; + struct edac_mc_layer layers[2]; + struct pci_dev *pdev = imc->chan[0].cdev; + struct skx_pvt *pvt; + int rc; + + /* allocate a new MC control structure */ + layers[0].type = EDAC_MC_LAYER_CHANNEL; + layers[0].size = NUM_CHANNELS; + layers[0].is_virt_csrow = false; + layers[1].type = EDAC_MC_LAYER_SLOT; + layers[1].size = NUM_DIMMS; + layers[1].is_virt_csrow = true; + mci = edac_mc_alloc(imc->mc, ARRAY_SIZE(layers), layers, + sizeof(struct skx_pvt)); + + if (unlikely(!mci)) + return -ENOMEM; + + edac_dbg(0, "MC#%d: mci = %p\n", imc->mc, mci); + + /* Associate skx_dev and mci for future usage */ + imc->mci = mci; + pvt = mci->pvt_info; + pvt->imc = imc; + + mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", + imc->node_id, imc->lmc); + mci->mtype_cap = MEM_FLAG_DDR4; + mci->edac_ctl_cap = EDAC_FLAG_NONE; + mci->edac_cap = EDAC_FLAG_NONE; + mci->mod_name = "skx_edac.c"; + mci->dev_name = pci_name(imc->chan[0].cdev); + mci->mod_ver = SKX_REVISION; + mci->ctl_page_to_phys = NULL; + + rc = skx_get_dimm_config(mci); + if (rc < 0) + goto fail; + + /* record ptr to the generic device */ + mci->pdev = &pdev->dev; + + /* add this new MC control structure to EDAC's list of MCs */ + if (unlikely(edac_mc_add_mc(mci))) { + edac_dbg(0, "MC: failed edac_mc_add_mc()\n"); + rc = -EINVAL; + goto fail; + } + + return 0; + +fail: + kfree(mci->ctl_name); + edac_mc_free(mci); + imc->mci = NULL; + return rc; +} + +#define SKX_MAX_SAD 24 + +#define SKX_GET_SAD(d, i, reg) \ + pci_read_config_dword((d)->sad_all, 0x60 + 8 * (i), ®) +#define SKX_GET_ILV(d, i, reg) \ + pci_read_config_dword((d)->sad_all, 0x64 + 8 * (i), ®) + +#define SKX_SAD_MOD3MODE(sad) GET_BITFIELD((sad), 30, 31) +#define SKX_SAD_MOD3(sad) GET_BITFIELD((sad), 27, 27) +#define SKX_SAD_LIMIT(sad) (((u64)GET_BITFIELD((sad), 7, 26) << 26) | MASK26) +#define SKX_SAD_MOD3ASMOD2(sad) GET_BITFIELD((sad), 5, 6) +#define SKX_SAD_ATTR(sad) GET_BITFIELD((sad), 3, 4) +#define SKX_SAD_INTERLEAVE(sad) GET_BITFIELD((sad), 1, 2) +#define SKX_SAD_ENABLE(sad) GET_BITFIELD((sad), 0, 0) + +#define SKX_ILV_REMOTE(tgt) (((tgt) & 8) == 0) +#define SKX_ILV_TARGET(tgt) ((tgt) & 7) + +static bool skx_sad_decode(struct decoded_addr *res) +{ + struct skx_dev *d = list_first_entry(&skx_edac_list, typeof(*d), list); + u64 addr = res->addr; + int i, idx, tgt, lchan, shift; + u32 sad, ilv; + u64 limit, prev_limit; + int remote = 0; + + /* Simple sanity check for I/O space or out of range */ + if (addr >= skx_tohm || (addr >= skx_tolm && addr < BIT_ULL(32))) { + edac_dbg(0, "Address %llx out of range\n", addr); + return false; + } + +restart: + prev_limit = 0; + for (i = 0; i < SKX_MAX_SAD; i++) { + SKX_GET_SAD(d, i, sad); + limit = SKX_SAD_LIMIT(sad); + if (SKX_SAD_ENABLE(sad)) { + if (addr >= prev_limit && addr <= limit) + goto sad_found; + } + prev_limit = limit + 1; + } + edac_dbg(0, "No SAD entry for %llx\n", addr); + return false; + +sad_found: + SKX_GET_ILV(d, i, ilv); + + switch (SKX_SAD_INTERLEAVE(sad)) { + case 0: + idx = GET_BITFIELD(addr, 6, 8); + break; + case 1: + idx = GET_BITFIELD(addr, 8, 10); + break; + case 2: + idx = GET_BITFIELD(addr, 12, 14); + break; + case 3: + idx = GET_BITFIELD(addr, 30, 32); + break; + } + + tgt = GET_BITFIELD(ilv, 4 * idx, 4 * idx + 3); + + /* If point to another node, find it and start over */ + if (SKX_ILV_REMOTE(tgt)) { + if (remote) { + edac_dbg(0, "Double remote!\n"); + return false; + } + remote = 1; + list_for_each_entry(d, &skx_edac_list, list) { + if (d->imc[0].src_id == SKX_ILV_TARGET(tgt)) + goto restart; + } + edac_dbg(0, "Can't find node %d\n", SKX_ILV_TARGET(tgt)); + return false; + } + + if (SKX_SAD_MOD3(sad) == 0) + lchan = SKX_ILV_TARGET(tgt); + else { + switch (SKX_SAD_MOD3MODE(sad)) { + case 0: + shift = 6; + break; + case 1: + shift = 8; + break; + case 2: + shift = 12; + break; + default: + edac_dbg(0, "illegal mod3mode\n"); + return false; + } + switch (SKX_SAD_MOD3ASMOD2(sad)) { + case 0: + lchan = (addr >> shift) % 3; + break; + case 1: + lchan = (addr >> shift) % 2; + break; + case 2: + lchan = (addr >> shift) % 2; + lchan = (lchan << 1) | ~lchan; + break; + case 3: + lchan = ((addr >> shift) % 2) << 1; + break; + } + lchan = (lchan << 1) | (SKX_ILV_TARGET(tgt) & 1); + } + + res->dev = d; + res->socket = d->imc[0].src_id; + res->imc = GET_BITFIELD(d->mcroute, lchan * 3, lchan * 3 + 2); + res->channel = GET_BITFIELD(d->mcroute, lchan * 2 + 18, lchan * 2 + 19); + + edac_dbg(2, "%llx: socket=%d imc=%d channel=%d\n", + res->addr, res->socket, res->imc, res->channel); + return true; +} + +#define SKX_MAX_TAD 8 + +#define SKX_GET_TADBASE(d, mc, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[0].cdev, 0x850 + 4 * (i), ®) +#define SKX_GET_TADWAYNESS(d, mc, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[0].cdev, 0x880 + 4 * (i), ®) +#define SKX_GET_TADCHNILVOFFSET(d, mc, ch, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[ch].cdev, 0x90 + 4 * (i), ®) + +#define SKX_TAD_BASE(b) ((u64)GET_BITFIELD((b), 12, 31) << 26) +#define SKX_TAD_SKT_GRAN(b) GET_BITFIELD((b), 4, 5) +#define SKX_TAD_CHN_GRAN(b) GET_BITFIELD((b), 6, 7) +#define SKX_TAD_LIMIT(b) (((u64)GET_BITFIELD((b), 12, 31) << 26) | MASK26) +#define SKX_TAD_OFFSET(b) ((u64)GET_BITFIELD((b), 4, 23) << 26) +#define SKX_TAD_SKTWAYS(b) (1 << GET_BITFIELD((b), 10, 11)) +#define SKX_TAD_CHNWAYS(b) (GET_BITFIELD((b), 8, 9) + 1) + +/* which bit used for both socket and channel interleave */ +static int skx_granularity[] = { 6, 8, 12, 30 }; + +static u64 skx_do_interleave(u64 addr, int shift, int ways, u64 lowbits) +{ + addr >>= shift; + addr /= ways; + addr <<= shift; + + return addr | (lowbits & ((1ull << shift) - 1)); +} + +static bool skx_tad_decode(struct decoded_addr *res) +{ + int i; + u32 base, wayness, chnilvoffset; + int skt_interleave_bit, chn_interleave_bit; + u64 channel_addr; + + for (i = 0; i < SKX_MAX_TAD; i++) { + SKX_GET_TADBASE(res->dev, res->imc, i, base); + SKX_GET_TADWAYNESS(res->dev, res->imc, i, wayness); + if (SKX_TAD_BASE(base) <= res->addr && res->addr <= SKX_TAD_LIMIT(wayness)) + goto tad_found; + } + edac_dbg(0, "No TAD entry for %llx\n", res->addr); + return false; + +tad_found: + res->sktways = SKX_TAD_SKTWAYS(wayness); + res->chanways = SKX_TAD_CHNWAYS(wayness); + skt_interleave_bit = skx_granularity[SKX_TAD_SKT_GRAN(base)]; + chn_interleave_bit = skx_granularity[SKX_TAD_CHN_GRAN(base)]; + + SKX_GET_TADCHNILVOFFSET(res->dev, res->imc, res->channel, i, chnilvoffset); + channel_addr = res->addr - SKX_TAD_OFFSET(chnilvoffset); + + if (res->chanways == 3 && skt_interleave_bit > chn_interleave_bit) { + /* Must handle channel first, then socket */ + channel_addr = skx_do_interleave(channel_addr, chn_interleave_bit, + res->chanways, channel_addr); + channel_addr = skx_do_interleave(channel_addr, skt_interleave_bit, + res->sktways, channel_addr); + } else { + /* Handle socket then channel. Preserve low bits from original address */ + channel_addr = skx_do_interleave(channel_addr, skt_interleave_bit, + res->sktways, res->addr); + channel_addr = skx_do_interleave(channel_addr, chn_interleave_bit, + res->chanways, res->addr); + } + + res->chan_addr = channel_addr; + + edac_dbg(2, "%llx: chan_addr=%llx sktways=%d chanways=%d\n", + res->addr, res->chan_addr, res->sktways, res->chanways); + return true; +} + +#define SKX_MAX_RIR 4 + +#define SKX_GET_RIRWAYNESS(d, mc, ch, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[ch].cdev, \ + 0x108 + 4 * (i), ®) +#define SKX_GET_RIRILV(d, mc, ch, idx, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[ch].cdev, \ + 0x120 + 16 * idx + 4 * (i), ®) + +#define SKX_RIR_VALID(b) GET_BITFIELD((b), 31, 31) +#define SKX_RIR_LIMIT(b) (((u64)GET_BITFIELD((b), 1, 11) << 29) | MASK29) +#define SKX_RIR_WAYS(b) (1 << GET_BITFIELD((b), 28, 29)) +#define SKX_RIR_CHAN_RANK(b) GET_BITFIELD((b), 16, 19) +#define SKX_RIR_OFFSET(b) ((u64)(GET_BITFIELD((b), 2, 15) << 26)) + +static bool skx_rir_decode(struct decoded_addr *res) +{ + int i, idx, chan_rank; + int shift; + u32 rirway, rirlv; + u64 rank_addr, prev_limit = 0, limit; + + if (res->dev->imc[res->imc].chan[res->channel].dimms[0].close_pg) + shift = 6; + else + shift = 13; + + for (i = 0; i < SKX_MAX_RIR; i++) { + SKX_GET_RIRWAYNESS(res->dev, res->imc, res->channel, i, rirway); + limit = SKX_RIR_LIMIT(rirway); + if (SKX_RIR_VALID(rirway)) { + if (prev_limit <= res->chan_addr && + res->chan_addr <= limit) + goto rir_found; + } + prev_limit = limit; + } + edac_dbg(0, "No RIR entry for %llx\n", res->addr); + return false; + +rir_found: + rank_addr = res->chan_addr >> shift; + rank_addr /= SKX_RIR_WAYS(rirway); + rank_addr <<= shift; + rank_addr |= res->chan_addr & GENMASK_ULL(shift - 1, 0); + + res->rank_address = rank_addr; + idx = (res->chan_addr >> shift) % SKX_RIR_WAYS(rirway); + + SKX_GET_RIRILV(res->dev, res->imc, res->channel, idx, i, rirlv); + res->rank_address = rank_addr - SKX_RIR_OFFSET(rirlv); + chan_rank = SKX_RIR_CHAN_RANK(rirlv); + res->channel_rank = chan_rank; + res->dimm = chan_rank / 4; + res->rank = chan_rank % 4; + + edac_dbg(2, "%llx: dimm=%d rank=%d chan_rank=%d rank_addr=%llx\n", + res->addr, res->dimm, res->rank, + res->channel_rank, res->rank_address); + return true; +} + +static u8 skx_close_row[] = { + 15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33 +}; +static u8 skx_close_column[] = { + 3, 4, 5, 14, 19, 23, 24, 25, 26, 27 +}; +static u8 skx_open_row[] = { + 14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33 +}; +static u8 skx_open_column[] = { + 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 +}; +static u8 skx_open_fine_column[] = { + 3, 4, 5, 7, 8, 9, 10, 11, 12, 13 +}; + +static int skx_bits(u64 addr, int nbits, u8 *bits) +{ + int i, res = 0; + + for (i = 0; i < nbits; i++) + res |= ((addr >> bits[i]) & 1) << i; + return res; +} + +static int skx_bank_bits(u64 addr, int b0, int b1, int do_xor, int x0, int x1) +{ + int ret = GET_BITFIELD(addr, b0, b0) | (GET_BITFIELD(addr, b1, b1) << 1); + + if (do_xor) + ret ^= GET_BITFIELD(addr, x0, x0) | (GET_BITFIELD(addr, x1, x1) << 1); + + return ret; +} + +static bool skx_mad_decode(struct decoded_addr *r) +{ + struct skx_dimm *dimm = &r->dev->imc[r->imc].chan[r->channel].dimms[r->dimm]; + int bg0 = dimm->fine_grain_bank ? 6 : 13; + + if (dimm->close_pg) { + r->row = skx_bits(r->rank_address, dimm->rowbits, skx_close_row); + r->column = skx_bits(r->rank_address, dimm->colbits, skx_close_column); + r->column |= 0x400; /* C10 is autoprecharge, always set */ + r->bank_address = skx_bank_bits(r->rank_address, 8, 9, dimm->bank_xor_enable, 22, 28); + r->bank_group = skx_bank_bits(r->rank_address, 6, 7, dimm->bank_xor_enable, 20, 21); + } else { + r->row = skx_bits(r->rank_address, dimm->rowbits, skx_open_row); + if (dimm->fine_grain_bank) + r->column = skx_bits(r->rank_address, dimm->colbits, skx_open_fine_column); + else + r->column = skx_bits(r->rank_address, dimm->colbits, skx_open_column); + r->bank_address = skx_bank_bits(r->rank_address, 18, 19, dimm->bank_xor_enable, 22, 23); + r->bank_group = skx_bank_bits(r->rank_address, bg0, 17, dimm->bank_xor_enable, 20, 21); + } + r->row &= (1u << dimm->rowbits) - 1; + + edac_dbg(2, "%llx: row=%x col=%x bank_addr=%d bank_group=%d\n", + r->addr, r->row, r->column, r->bank_address, + r->bank_group); + return true; +} + +static bool skx_decode(struct decoded_addr *res) +{ + + return skx_sad_decode(res) && skx_tad_decode(res) && + skx_rir_decode(res) && skx_mad_decode(res); +} + +#ifdef CONFIG_EDAC_DEBUG +/* + * Debug feature. Make /sys/kernel/debug/skx_edac_test/addr. + * Write an address to this file to exercise the address decode + * logic in this driver. + */ +static struct dentry *skx_test; +static u64 skx_fake_addr; + +static int debugfs_u64_set(void *data, u64 val) +{ + struct decoded_addr res; + + res.addr = val; + skx_decode(&res); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); + +static struct dentry *mydebugfs_create(const char *name, umode_t mode, + struct dentry *parent, u64 *value) +{ + return debugfs_create_file(name, mode, parent, value, &fops_u64_wo); +} + +static void setup_skx_debug(void) +{ + skx_test = debugfs_create_dir("skx_edac_test", NULL); + mydebugfs_create("addr", S_IWUSR, skx_test, &skx_fake_addr); +} + +static void teardown_skx_debug(void) +{ + debugfs_remove_recursive(skx_test); +} +#else +static void setup_skx_debug(void) +{ +} + +static void teardown_skx_debug(void) +{ +} +#endif /*CONFIG_EDAC_DEBUG*/ + +static void skx_mce_output_error(struct mem_ctl_info *mci, + const struct mce *m, + struct decoded_addr *res) +{ + enum hw_event_mc_err_type tp_event; + char *type, *optype, msg[256]; + bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0); + bool overflow = GET_BITFIELD(m->status, 62, 62); + bool uncorrected_error = GET_BITFIELD(m->status, 61, 61); + bool recoverable; + u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52); + u32 mscod = GET_BITFIELD(m->status, 16, 31); + u32 errcode = GET_BITFIELD(m->status, 0, 15); + u32 optypenum = GET_BITFIELD(m->status, 4, 6); + + recoverable = GET_BITFIELD(m->status, 56, 56); + + if (uncorrected_error) { + if (ripv) { + type = "FATAL"; + tp_event = HW_EVENT_ERR_FATAL; + } else { + type = "NON_FATAL"; + tp_event = HW_EVENT_ERR_UNCORRECTED; + } + } else { + type = "CORRECTED"; + tp_event = HW_EVENT_ERR_CORRECTED; + } + + /* + * According with Table 15-9 of the Intel Architecture spec vol 3A, + * memory errors should fit in this mask: + * 000f 0000 1mmm cccc (binary) + * where: + * f = Correction Report Filtering Bit. If 1, subsequent errors + * won't be shown + * mmm = error type + * cccc = channel + * If the mask doesn't match, report an error to the parsing logic + */ + if (!((errcode & 0xef80) == 0x80)) { + optype = "Can't parse: it is not a mem"; + } else { + switch (optypenum) { + case 0: + optype = "generic undef request error"; + break; + case 1: + optype = "memory read error"; + break; + case 2: + optype = "memory write error"; + break; + case 3: + optype = "addr/cmd error"; + break; + case 4: + optype = "memory scrubbing error"; + break; + default: + optype = "reserved"; + break; + } + } + + snprintf(msg, sizeof(msg), + "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x", + overflow ? " OVERFLOW" : "", + (uncorrected_error && recoverable) ? " recoverable" : "", + mscod, errcode, + res->socket, res->imc, res->rank, + res->bank_group, res->bank_address, res->row, res->column); + + edac_dbg(0, "%s\n", msg); + + /* Call the helper to output message */ + edac_mc_handle_error(tp_event, mci, core_err_cnt, + m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, + res->channel, res->dimm, -1, + optype, msg); +} + +static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + struct decoded_addr res; + struct mem_ctl_info *mci; + char *type; + + if (get_edac_report_status() == EDAC_REPORTING_DISABLED) + return NOTIFY_DONE; + + /* ignore unless this is memory related with an address */ + if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV)) + return NOTIFY_DONE; + + res.addr = mce->addr; + if (!skx_decode(&res)) + return NOTIFY_DONE; + mci = res.dev->imc[res.imc].mci; + + if (mce->mcgstatus & MCG_STATUS_MCIP) + type = "Exception"; + else + type = "Event"; + + skx_mc_printk(mci, KERN_DEBUG, "HANDLING MCE MEMORY ERROR\n"); + + skx_mc_printk(mci, KERN_DEBUG, "CPU %d: Machine Check %s: %Lx " + "Bank %d: %016Lx\n", mce->extcpu, type, + mce->mcgstatus, mce->bank, mce->status); + skx_mc_printk(mci, KERN_DEBUG, "TSC %llx ", mce->tsc); + skx_mc_printk(mci, KERN_DEBUG, "ADDR %llx ", mce->addr); + skx_mc_printk(mci, KERN_DEBUG, "MISC %llx ", mce->misc); + + skx_mc_printk(mci, KERN_DEBUG, "PROCESSOR %u:%x TIME %llu SOCKET " + "%u APIC %x\n", mce->cpuvendor, mce->cpuid, + mce->time, mce->socketid, mce->apicid); + + skx_mce_output_error(mci, mce, &res); + + return NOTIFY_DONE; +} + +static struct notifier_block skx_mce_dec = { + .notifier_call = skx_mce_check_error, +}; + +static void skx_remove(void) +{ + int i, j; + struct skx_dev *d, *tmp; + + edac_dbg(0, "\n"); + + list_for_each_entry_safe(d, tmp, &skx_edac_list, list) { + list_del(&d->list); + for (i = 0; i < NUM_IMC; i++) { + skx_unregister_mci(&d->imc[i]); + for (j = 0; j < NUM_CHANNELS; j++) + pci_dev_put(d->imc[i].chan[j].cdev); + } + pci_dev_put(d->util_all); + pci_dev_put(d->sad_all); + + kfree(d); + } +} + +/* + * skx_init: + * make sure we are running on the correct cpu model + * search for all the devices we need + * check which DIMMs are present. + */ +int __init skx_init(void) +{ + const struct x86_cpu_id *id; + const struct munit *m; + int rc = 0, i; + u8 mc = 0, src_id, node_id; + struct skx_dev *d; + + edac_dbg(2, "\n"); + + id = x86_match_cpu(skx_cpuids); + if (!id) + return -ENODEV; + + rc = skx_get_hi_lo(); + if (rc) + return rc; + + rc = get_all_bus_mappings(); + if (rc < 0) + goto fail; + if (rc == 0) { + edac_dbg(2, "No memory controllers found\n"); + return -ENODEV; + } + + for (m = skx_all_munits; m->did; m++) { + rc = get_all_munits(m); + if (rc < 0) + goto fail; + if (rc != m->per_socket * skx_num_sockets) { + edac_dbg(2, "Expected %d, got %d of %x\n", + m->per_socket * skx_num_sockets, rc, m->did); + rc = -ENODEV; + goto fail; + } + } + + list_for_each_entry(d, &skx_edac_list, list) { + src_id = get_src_id(d); + node_id = skx_get_node_id(d); + edac_dbg(2, "src_id=%d node_id=%d\n", src_id, node_id); + for (i = 0; i < NUM_IMC; i++) { + d->imc[i].mc = mc++; + d->imc[i].lmc = i; + d->imc[i].src_id = src_id; + d->imc[i].node_id = node_id; + rc = skx_register_mci(&d->imc[i]); + if (rc < 0) + goto fail; + } + } + + /* Ensure that the OPSTATE is set correctly for POLL or NMI */ + opstate_init(); + + setup_skx_debug(); + + mce_register_decode_chain(&skx_mce_dec); + + return 0; +fail: + skx_remove(); + return rc; +} + +static void __exit skx_exit(void) +{ + edac_dbg(2, "\n"); + mce_unregister_decode_chain(&skx_mce_dec); + skx_remove(); + teardown_skx_debug(); +} + +module_init(skx_init); +module_exit(skx_exit); + +module_param(edac_op_state, int, 0444); +MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI"); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tony Luck"); +MODULE_DESCRIPTION("MC Driver for Intel Skylake server processors"); diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 98dd47a..66a9410 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -50,6 +50,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y depends on OF + depends on HAS_IOMEM config GPIO_ACPI def_bool y @@ -188,7 +189,7 @@ config GPIO_EP93XX config GPIO_ETRAXFS bool "Axis ETRAX FS General I/O" depends on CRIS || COMPILE_TEST - depends on OF + depends on OF_GPIO select GPIO_GENERIC select GPIOLIB_IRQCHIP help @@ -214,7 +215,7 @@ config GPIO_GENERIC_PLATFORM config GPIO_GRGPIO tristate "Aeroflex Gaisler GRGPIO support" - depends on OF + depends on OF_GPIO select GPIO_GENERIC select IRQ_DOMAIN help @@ -312,7 +313,7 @@ config GPIO_MPC8XXX config GPIO_MVEBU def_bool y depends on PLAT_ORION - depends on OF + depends on OF_GPIO select GENERIC_IRQ_CHIP config GPIO_MXC @@ -405,7 +406,7 @@ config GPIO_TEGRA bool "NVIDIA Tegra GPIO support" default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST - depends on OF + depends on OF_GPIO help Say yes here to support GPIO pins on NVIDIA Tegra SoCs. @@ -1099,7 +1100,7 @@ menu "SPI GPIO expanders" config GPIO_74X164 tristate "74x164 serial-in/parallel-out 8-bits shift register" - depends on OF + depends on OF_GPIO help Driver for 74x164 compatible serial-in/parallel-out 8-outputs shift registers. This driver can be used to provide access diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index 0880736..946d091 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -192,6 +192,10 @@ int __max730x_probe(struct max7301 *ts) ts->chip.parent = dev; ts->chip.owner = THIS_MODULE; + ret = gpiochip_add_data(&ts->chip, ts); + if (ret) + goto exit_destroy; + /* * initialize pullups according to platform data and cache the * register values for later use. @@ -213,10 +217,6 @@ int __max730x_probe(struct max7301 *ts) } } - ret = gpiochip_add_data(&ts->chip, ts); - if (ret) - goto exit_destroy; - return ret; exit_destroy: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 8ebc5f1..700c56b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -426,6 +426,8 @@ struct amdgpu_mman { /* custom LRU management */ struct amdgpu_mman_lru log2_size[AMDGPU_TTM_LRU_SIZE]; + /* guard for log2_size array, don't add anything in between */ + struct amdgpu_mman_lru guard; }; int amdgpu_copy_buffer(struct amdgpu_ring *ring, @@ -646,9 +648,9 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev); void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev); int amdgpu_gart_init(struct amdgpu_device *adev); void amdgpu_gart_fini(struct amdgpu_device *adev); -void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, +void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset, int pages); -int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset, +int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, int pages, struct page **pagelist, dma_addr_t *dma_addr, uint32_t flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 9831753..fe872b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -321,6 +321,19 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * (le16_to_cpu(path->usConnObjectId) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; + /* Skip TV/CV support */ + if ((le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_TV1_SUPPORT) || + (le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_CV_SUPPORT)) + continue; + + if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) { + DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n", + con_obj_id, le16_to_cpu(path->usDeviceTag)); + continue; + } + connector_type = object_connector_convert[con_obj_id]; connector_object_id = con_obj_id; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 49de926..10b5ddf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -200,16 +200,7 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { printk("ATPX Hybrid Graphics\n"); -#if 1 - /* This is a temporary hack until the D3 cold support - * makes it upstream. The ATPX power_control method seems - * to still work on even if the system should be using - * the new standardized hybrid D3 cold ACPI interface. - */ - atpx->functions.power_cntl = true; -#else atpx->functions.power_cntl = false; -#endif atpx->is_hybrid = true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 921bce2..0feea34 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -221,7 +221,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev) * Unbinds the requested pages from the gart page table and * replaces them with the dummy page (all asics). */ -void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, +void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset, int pages) { unsigned t; @@ -268,7 +268,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, * (all asics). * Returns 0 for success, -EINVAL for failure. */ -int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset, +int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, int pages, struct page **pagelist, dma_addr_t *dma_addr, uint32_t flags) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 9b61c8b..716f2af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -251,8 +251,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, adev = amdgpu_get_adev(bo->bdev); ring = adev->mman.buffer_funcs_ring; - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: @@ -950,6 +950,8 @@ static struct list_head *amdgpu_ttm_lru_tail(struct ttm_buffer_object *tbo) struct list_head *res = lru->lru[tbo->mem.mem_type]; lru->lru[tbo->mem.mem_type] = &tbo->lru; + while ((++lru)->lru[tbo->mem.mem_type] == res) + lru->lru[tbo->mem.mem_type] = &tbo->lru; return res; } @@ -960,6 +962,8 @@ static struct list_head *amdgpu_ttm_swap_lru_tail(struct ttm_buffer_object *tbo) struct list_head *res = lru->swap_lru; lru->swap_lru = &tbo->swap; + while ((++lru)->swap_lru == res) + lru->swap_lru = &tbo->swap; return res; } @@ -1011,6 +1015,10 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) lru->swap_lru = &adev->mman.bdev.glob->swap_lru; } + for (j = 0; j < TTM_NUM_MEM_TYPES; ++j) + adev->mman.guard.lru[j] = NULL; + adev->mman.guard.swap_lru = NULL; + adev->mman.initialized = true; r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM, adev->mc.real_vram_size >> PAGE_SHIFT); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index b11f4e8..4aa993d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1187,7 +1187,8 @@ int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = 0; } -error: fence_put(fence); + +error: return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8e642fc..80120fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1535,7 +1535,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) r = amd_sched_entity_init(&ring->sched, &vm->entity, rq, amdgpu_sched_jobs); if (r) - return r; + goto err; vm->page_directory_fence = NULL; @@ -1565,6 +1565,9 @@ error_free_page_directory: error_free_sched_entity: amd_sched_entity_fini(&ring->sched, &vm->entity); +err: + drm_free_large(vm->page_tables); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 1351c7e..a64715d 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -714,7 +714,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) DRM_ERROR("amdgpu: IB test timed out\n"); r = -ETIMEDOUT; goto err1; - } else if (r) { + } else if (r < 0) { DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err1; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index e621eba..a7d3cb3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -184,7 +184,7 @@ u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd, sizeof(u32)) + inx; pr_debug("kfd: get kernel queue doorbell\n" - " doorbell offset == 0x%08d\n" + " doorbell offset == 0x%08X\n" " kernel address == 0x%08lX\n", *doorbell_off, (uintptr_t)(kfd->doorbell_kernel_ptr + inx)); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index ef312bb..963a24d 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -405,7 +405,7 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) spin_lock(&sched->job_list_lock); s_job = list_first_entry_or_null(&sched->ring_mirror_list, struct amd_sched_job, node); - if (s_job) + if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT) schedule_delayed_work(&s_job->work_tdr, sched->timeout); list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index fa39307..2a3ded4 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -475,7 +475,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, -1, &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (property == config->ctm_property) { ret = drm_atomic_replace_property_blob_from_id(crtc, @@ -483,7 +483,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, sizeof(struct drm_color_ctm), &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (property == config->gamma_lut_property) { ret = drm_atomic_replace_property_blob_from_id(crtc, @@ -491,7 +491,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, -1, &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (crtc->funcs->atomic_set_property) return crtc->funcs->atomic_set_property(crtc, state, property, val); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index b1dbb60..ddebe54 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -5404,6 +5404,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, struct drm_pending_vblank_event *e = NULL; int ret = -EINVAL; + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return -EINVAL; + if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS || page_flip->reserved != 0) return -EINVAL; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index ce54e98..0a06f91 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -464,7 +464,7 @@ static bool drm_fb_helper_is_bound(struct drm_fb_helper *fb_helper) /* Sometimes user space wants everything disabled, so don't steal the * display if there's a master. */ - if (lockless_dereference(dev->master)) + if (READ_ONCE(dev->master)) return false; drm_for_each_crtc(crtc, dev) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 87ef341..b382cf5 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1333,8 +1333,6 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, if (ret < 0) return ret; - mutex_lock(&gpu->lock); - /* * TODO * @@ -1348,16 +1346,18 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, if (unlikely(event == ~0U)) { DRM_ERROR("no free event\n"); ret = -EBUSY; - goto out_unlock; + goto out_pm_put; } fence = etnaviv_gpu_fence_alloc(gpu); if (!fence) { event_free(gpu, event); ret = -ENOMEM; - goto out_unlock; + goto out_pm_put; } + mutex_lock(&gpu->lock); + gpu->event[event].fence = fence; submit->fence = fence->seqno; gpu->active_fence = submit->fence; @@ -1395,9 +1395,9 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, hangcheck_timer_reset(gpu); ret = 0; -out_unlock: mutex_unlock(&gpu->lock); +out_pm_put: etnaviv_gpu_pm_put(gpu); return ret; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 21f9390..f68c789 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -882,11 +882,12 @@ struct i915_gem_context { struct i915_ctx_hang_stats hang_stats; - /* Unique identifier for this context, used by the hw for tracking */ unsigned long flags; #define CONTEXT_NO_ZEROMAP BIT(0) #define CONTEXT_NO_ERROR_CAPTURE BIT(1) - unsigned hw_id; + + /* Unique identifier for this context, used by the hw for tracking */ + unsigned int hw_id; u32 user_handle; u32 ggtt_alignment; @@ -1854,6 +1855,7 @@ struct drm_i915_private { enum modeset_restore modeset_restore; struct mutex modeset_restore_lock; struct drm_atomic_state *modeset_restore_state; + struct drm_modeset_acquire_ctx reset_ctx; struct list_head vm_list; /* Global list of all address spaces */ struct i915_ggtt ggtt; /* VM representing the global address space */ @@ -1962,6 +1964,13 @@ struct drm_i915_private { struct i915_suspend_saved_registers regfile; struct vlv_s0ix_state vlv_s0ix_state; + enum { + I915_SKL_SAGV_UNKNOWN = 0, + I915_SKL_SAGV_DISABLED, + I915_SKL_SAGV_ENABLED, + I915_SKL_SAGV_NOT_CONTROLLED + } skl_sagv_status; + struct { /* * Raw watermark latency values: @@ -3590,6 +3599,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); /* belongs in i915_gem_gtt.h */ static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv) { + wmb(); if (INTEL_GEN(dev_priv) < 6) intel_gtt_chipset_flush(); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 1168150..a77ce99 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -879,9 +879,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, ret = i915_gem_shmem_pread(dev, obj, args, file); /* pread for non shmem backed objects */ - if (ret == -EFAULT || ret == -ENODEV) + if (ret == -EFAULT || ret == -ENODEV) { + intel_runtime_pm_get(to_i915(dev)); ret = i915_gem_gtt_pread(dev, obj, args->size, args->offset, args->data_ptr); + intel_runtime_pm_put(to_i915(dev)); + } out: drm_gem_object_unreference(&obj->base); @@ -1306,7 +1309,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, * textures). Fallback to the shmem path in that case. */ } - if (ret == -EFAULT) { + if (ret == -EFAULT || ret == -ENOSPC) { if (obj->phys_handle) ret = i915_gem_phys_pwrite(obj, args, file); else if (i915_gem_object_has_struct_page(obj)) @@ -3169,6 +3172,8 @@ static void i915_gem_reset_engine_cleanup(struct intel_engine_cs *engine) } intel_ring_init_seqno(engine, engine->last_submitted_seqno); + + engine->i915->gt.active_engines &= ~intel_engine_flag(engine); } void i915_gem_reset(struct drm_device *dev) @@ -3186,6 +3191,7 @@ void i915_gem_reset(struct drm_device *dev) for_each_engine(engine, dev_priv) i915_gem_reset_engine_cleanup(engine); + mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0); i915_gem_context_reset(dev); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 1978633..b35e5b6 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -943,8 +943,6 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, { const unsigned other_rings = ~intel_engine_flag(req->engine); struct i915_vma *vma; - uint32_t flush_domains = 0; - bool flush_chipset = false; int ret; list_for_each_entry(vma, vmas, exec_list) { @@ -957,16 +955,11 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, } if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) - flush_chipset |= i915_gem_clflush_object(obj, false); - - flush_domains |= obj->base.write_domain; + i915_gem_clflush_object(obj, false); } - if (flush_chipset) - i915_gem_chipset_flush(req->engine->i915); - - if (flush_domains & I915_GEM_DOMAIN_GTT) - wmb(); + /* Unconditionally flush any chipset caches (for streaming writes). */ + i915_gem_chipset_flush(req->engine->i915); /* Unconditionally invalidate gpu caches and ensure that we do flush * any residual writes from the previous batch. diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 10f1e32..7a30af7 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2873,6 +2873,7 @@ void i915_ggtt_cleanup_hw(struct drm_device *dev) struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; ppgtt->base.cleanup(&ppgtt->base); + kfree(ppgtt); } i915_gem_cleanup_stolen(dev); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index ce14fe0..bf2cad3 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1536,6 +1536,7 @@ enum skl_disp_power_wells { #define BALANCE_LEG_MASK(port) (7<<(8+3*(port))) /* Balance leg disable bits */ #define BALANCE_LEG_DISABLE_SHIFT 23 +#define BALANCE_LEG_DISABLE(port) (1 << (23 + (port))) /* * Fence registers @@ -7144,6 +7145,15 @@ enum { #define GEN6_PCODE_MAILBOX _MMIO(0x138124) #define GEN6_PCODE_READY (1<<31) +#define GEN6_PCODE_ERROR_MASK 0xFF +#define GEN6_PCODE_SUCCESS 0x0 +#define GEN6_PCODE_ILLEGAL_CMD 0x1 +#define GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2 +#define GEN6_PCODE_TIMEOUT 0x3 +#define GEN6_PCODE_UNIMPLEMENTED_CMD 0xFF +#define GEN7_PCODE_TIMEOUT 0x2 +#define GEN7_PCODE_ILLEGAL_DATA 0x3 +#define GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10 #define GEN6_PCODE_WRITE_RC6VIDS 0x4 #define GEN6_PCODE_READ_RC6VIDS 0x5 #define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5) @@ -7165,6 +7175,10 @@ enum { #define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17 #define DISPLAY_IPS_CONTROL 0x19 #define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A +#define GEN9_PCODE_SAGV_CONTROL 0x21 +#define GEN9_SAGV_DISABLE 0x0 +#define GEN9_SAGV_IS_DISABLED 0x1 +#define GEN9_SAGV_ENABLE 0x3 #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 6700a7b..d32f586 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -600,6 +600,8 @@ static void i915_audio_component_codec_wake_override(struct device *dev, if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv)) return; + i915_audio_component_get_power(dev); + /* * Enable/disable generating the codec wake signal, overriding the * internal logic to generate the codec wake to controller. @@ -615,6 +617,8 @@ static void i915_audio_component_codec_wake_override(struct device *dev, I915_WRITE(HSW_AUD_CHICKENBIT, tmp); usleep_range(1000, 1500); } + + i915_audio_component_put_power(dev); } /* Get CDCLK in kHz */ @@ -648,6 +652,7 @@ static int i915_audio_component_sync_audio_rate(struct device *dev, !IS_HASWELL(dev_priv)) return 0; + i915_audio_component_get_power(dev); mutex_lock(&dev_priv->av_mutex); /* 1. get the pipe */ intel_encoder = dev_priv->dig_port_map[port]; @@ -698,6 +703,7 @@ static int i915_audio_component_sync_audio_rate(struct device *dev, unlock: mutex_unlock(&dev_priv->av_mutex); + i915_audio_component_put_power(dev); return err; } diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 3edb958..c3b33a1 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -41,15 +41,15 @@ * be moved to FW_FAILED. */ -#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" +#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin" MODULE_FIRMWARE(I915_CSR_KBL); #define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) -#define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin" MODULE_FIRMWARE(I915_CSR_SKL); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 26) -#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin" MODULE_FIRMWARE(I915_CSR_BXT); #define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index dd1d6fe..1a7efac 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -145,7 +145,7 @@ static const struct ddi_buf_trans skl_ddi_translations_dp[] = { static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = { { 0x0000201B, 0x000000A2, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x80007011, 0x000000CD, 0x0 }, + { 0x80007011, 0x000000CD, 0x1 }, { 0x80009010, 0x000000C0, 0x1 }, { 0x0000201B, 0x0000009D, 0x0 }, { 0x80005012, 0x000000C0, 0x1 }, @@ -158,7 +158,7 @@ static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = { static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = { { 0x00000018, 0x000000A2, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x80007011, 0x000000CD, 0x0 }, + { 0x80007011, 0x000000CD, 0x3 }, { 0x80009010, 0x000000C0, 0x3 }, { 0x00000018, 0x0000009D, 0x0 }, { 0x80005012, 0x000000C0, 0x3 }, @@ -388,6 +388,40 @@ skl_get_buf_trans_hdmi(struct drm_i915_private *dev_priv, int *n_entries) } } +static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) +{ + int n_hdmi_entries; + int hdmi_level; + int hdmi_default_entry; + + hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; + + if (IS_BROXTON(dev_priv)) + return hdmi_level; + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries); + hdmi_default_entry = 8; + } else if (IS_BROADWELL(dev_priv)) { + n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); + hdmi_default_entry = 7; + } else if (IS_HASWELL(dev_priv)) { + n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi); + hdmi_default_entry = 6; + } else { + WARN(1, "ddi translation table missing\n"); + n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); + hdmi_default_entry = 7; + } + + /* Choose a good default if VBT is badly populated */ + if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN || + hdmi_level >= n_hdmi_entries) + hdmi_level = hdmi_default_entry; + + return hdmi_level; +} + /* * Starting with Haswell, DDI port buffers must be programmed with correct * values in advance. The buffer values are different for FDI and DP modes, @@ -399,7 +433,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); u32 iboost_bit = 0; - int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry, + int i, n_hdmi_entries, n_dp_entries, n_edp_entries, size; int hdmi_level; enum port port; @@ -410,7 +444,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) const struct ddi_buf_trans *ddi_translations; port = intel_ddi_get_encoder_port(encoder); - hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; + hdmi_level = intel_ddi_hdmi_level(dev_priv, port); if (IS_BROXTON(dev_priv)) { if (encoder->type != INTEL_OUTPUT_HDMI) @@ -430,7 +464,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) skl_get_buf_trans_edp(dev_priv, &n_edp_entries); ddi_translations_hdmi = skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries); - hdmi_default_entry = 8; /* If we're boosting the current, set bit 31 of trans1 */ if (dev_priv->vbt.ddi_port_info[port].hdmi_boost_level || dev_priv->vbt.ddi_port_info[port].dp_boost_level) @@ -456,7 +489,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); - hdmi_default_entry = 7; } else if (IS_HASWELL(dev_priv)) { ddi_translations_fdi = hsw_ddi_translations_fdi; ddi_translations_dp = hsw_ddi_translations_dp; @@ -464,7 +496,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) ddi_translations_hdmi = hsw_ddi_translations_hdmi; n_dp_entries = n_edp_entries = ARRAY_SIZE(hsw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi); - hdmi_default_entry = 6; } else { WARN(1, "ddi translation table missing\n"); ddi_translations_edp = bdw_ddi_translations_dp; @@ -474,7 +505,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); - hdmi_default_entry = 7; } switch (encoder->type) { @@ -505,11 +535,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) if (encoder->type != INTEL_OUTPUT_HDMI) return; - /* Choose a good default if VBT is badly populated */ - if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN || - hdmi_level >= n_hdmi_entries) - hdmi_level = hdmi_default_entry; - /* Entry 9 is for HDMI: */ I915_WRITE(DDI_BUF_TRANS_LO(port, i), ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit); @@ -1379,14 +1404,30 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc) TRANS_CLK_SEL_DISABLED); } -static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv, - u32 level, enum port port, int type) +static void _skl_ddi_set_iboost(struct drm_i915_private *dev_priv, + enum port port, uint8_t iboost) { + u32 tmp; + + tmp = I915_READ(DISPIO_CR_TX_BMU_CR0); + tmp &= ~(BALANCE_LEG_MASK(port) | BALANCE_LEG_DISABLE(port)); + if (iboost) + tmp |= iboost << BALANCE_LEG_SHIFT(port); + else + tmp |= BALANCE_LEG_DISABLE(port); + I915_WRITE(DISPIO_CR_TX_BMU_CR0, tmp); +} + +static void skl_ddi_set_iboost(struct intel_encoder *encoder, u32 level) +{ + struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base); + struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev); + enum port port = intel_dig_port->port; + int type = encoder->type; const struct ddi_buf_trans *ddi_translations; uint8_t iboost; uint8_t dp_iboost, hdmi_iboost; int n_entries; - u32 reg; /* VBT may override standard boost values */ dp_iboost = dev_priv->vbt.ddi_port_info[port].dp_boost_level; @@ -1428,16 +1469,10 @@ static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv, return; } - reg = I915_READ(DISPIO_CR_TX_BMU_CR0); - reg &= ~BALANCE_LEG_MASK(port); - reg &= ~(1 << (BALANCE_LEG_DISABLE_SHIFT + port)); - - if (iboost) - reg |= iboost << BALANCE_LEG_SHIFT(port); - else - reg |= 1 << (BALANCE_LEG_DISABLE_SHIFT + port); + _skl_ddi_set_iboost(dev_priv, port, iboost); - I915_WRITE(DISPIO_CR_TX_BMU_CR0, reg); + if (port == PORT_A && intel_dig_port->max_lanes == 4) + _skl_ddi_set_iboost(dev_priv, PORT_E, iboost); } static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv, @@ -1568,7 +1603,7 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp) level = translate_signal_level(signal_levels); if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) - skl_ddi_set_iboost(dev_priv, level, port, encoder->type); + skl_ddi_set_iboost(encoder, level); else if (IS_BROXTON(dev_priv)) bxt_ddi_vswing_sequence(dev_priv, level, port, encoder->type); @@ -1637,6 +1672,10 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) intel_dp_stop_link_train(intel_dp); } else if (type == INTEL_OUTPUT_HDMI) { struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + int level = intel_ddi_hdmi_level(dev_priv, port); + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + skl_ddi_set_iboost(intel_encoder, level); intel_hdmi->set_infoframes(encoder, crtc->config->has_hdmi_sink, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index dcf93b3..175595f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3093,40 +3093,110 @@ static void intel_update_primary_planes(struct drm_device *dev) for_each_crtc(dev, crtc) { struct intel_plane *plane = to_intel_plane(crtc->primary); - struct intel_plane_state *plane_state; - - drm_modeset_lock_crtc(crtc, &plane->base); - plane_state = to_intel_plane_state(plane->base.state); + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); if (plane_state->visible) plane->update_plane(&plane->base, to_intel_crtc_state(crtc->state), plane_state); + } +} + +static int +__intel_display_resume(struct drm_device *dev, + struct drm_atomic_state *state) +{ + struct drm_crtc_state *crtc_state; + struct drm_crtc *crtc; + int i, ret; + + intel_modeset_setup_hw_state(dev); + i915_redisable_vga(dev); - drm_modeset_unlock_crtc(crtc); + if (!state) + return 0; + + for_each_crtc_in_state(state, crtc, crtc_state, i) { + /* + * Force recalculation even if we restore + * current state. With fast modeset this may not result + * in a modeset when the state is compatible. + */ + crtc_state->mode_changed = true; } + + /* ignore any reset values/BIOS leftovers in the WM registers */ + to_intel_atomic_state(state)->skip_intermediate_wm = true; + + ret = drm_atomic_commit(state); + + WARN_ON(ret == -EDEADLK); + return ret; } void intel_prepare_reset(struct drm_i915_private *dev_priv) { + struct drm_device *dev = &dev_priv->drm; + struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx; + struct drm_atomic_state *state; + int ret; + /* no reset support for gen2 */ if (IS_GEN2(dev_priv)) return; - /* reset doesn't touch the display */ + /* + * Need mode_config.mutex so that we don't + * trample ongoing ->detect() and whatnot. + */ + mutex_lock(&dev->mode_config.mutex); + drm_modeset_acquire_init(ctx, 0); + while (1) { + ret = drm_modeset_lock_all_ctx(dev, ctx); + if (ret != -EDEADLK) + break; + + drm_modeset_backoff(ctx); + } + + /* reset doesn't touch the display, but flips might get nuked anyway, */ if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) return; - drm_modeset_lock_all(&dev_priv->drm); /* * Disabling the crtcs gracefully seems nicer. Also the * g33 docs say we should at least disable all the planes. */ - intel_display_suspend(&dev_priv->drm); + state = drm_atomic_helper_duplicate_state(dev, ctx); + if (IS_ERR(state)) { + ret = PTR_ERR(state); + state = NULL; + DRM_ERROR("Duplicating state failed with %i\n", ret); + goto err; + } + + ret = drm_atomic_helper_disable_all(dev, ctx); + if (ret) { + DRM_ERROR("Suspending crtc's failed with %i\n", ret); + goto err; + } + + dev_priv->modeset_restore_state = state; + state->acquire_ctx = ctx; + return; + +err: + drm_atomic_state_free(state); } void intel_finish_reset(struct drm_i915_private *dev_priv) { + struct drm_device *dev = &dev_priv->drm; + struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx; + struct drm_atomic_state *state = dev_priv->modeset_restore_state; + int ret; + /* * Flips in the rings will be nuked by the reset, * so complete all pending flips so that user space @@ -3138,6 +3208,8 @@ void intel_finish_reset(struct drm_i915_private *dev_priv) if (IS_GEN2(dev_priv)) return; + dev_priv->modeset_restore_state = NULL; + /* reset doesn't touch the display */ if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { /* @@ -3149,29 +3221,32 @@ void intel_finish_reset(struct drm_i915_private *dev_priv) * FIXME: Atomic will make this obsolete since we won't schedule * CS-based flips (which might get lost in gpu resets) any more. */ - intel_update_primary_planes(&dev_priv->drm); - return; - } - - /* - * The display has been reset as well, - * so need a full re-initialization. - */ - intel_runtime_pm_disable_interrupts(dev_priv); - intel_runtime_pm_enable_interrupts(dev_priv); + intel_update_primary_planes(dev); + } else { + /* + * The display has been reset as well, + * so need a full re-initialization. + */ + intel_runtime_pm_disable_interrupts(dev_priv); + intel_runtime_pm_enable_interrupts(dev_priv); - intel_modeset_init_hw(&dev_priv->drm); + intel_modeset_init_hw(dev); - spin_lock_irq(&dev_priv->irq_lock); - if (dev_priv->display.hpd_irq_setup) - dev_priv->display.hpd_irq_setup(dev_priv); - spin_unlock_irq(&dev_priv->irq_lock); + spin_lock_irq(&dev_priv->irq_lock); + if (dev_priv->display.hpd_irq_setup) + dev_priv->display.hpd_irq_setup(dev_priv); + spin_unlock_irq(&dev_priv->irq_lock); - intel_display_resume(&dev_priv->drm); + ret = __intel_display_resume(dev, state); + if (ret) + DRM_ERROR("Restoring old state failed with %i\n", ret); - intel_hpd_init(dev_priv); + intel_hpd_init(dev_priv); + } - drm_modeset_unlock_all(&dev_priv->drm); + drm_modeset_drop_locks(ctx); + drm_modeset_acquire_fini(ctx); + mutex_unlock(&dev->mode_config.mutex); } static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc) @@ -13684,6 +13759,13 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco)) dev_priv->display.modeset_commit_cdclk(state); + /* + * SKL workaround: bspec recommends we disable the SAGV when we + * have more then one pipe enabled + */ + if (IS_SKYLAKE(dev_priv) && !skl_can_enable_sagv(state)) + skl_disable_sagv(dev_priv); + intel_modeset_verify_disabled(dev); } @@ -13757,6 +13839,10 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state); } + if (IS_SKYLAKE(dev_priv) && intel_state->modeset && + skl_can_enable_sagv(state)) + skl_enable_sagv(dev_priv); + drm_atomic_helper_commit_hw_done(state); if (intel_state->modeset) @@ -16156,9 +16242,10 @@ void intel_display_resume(struct drm_device *dev) struct drm_atomic_state *state = dev_priv->modeset_restore_state; struct drm_modeset_acquire_ctx ctx; int ret; - bool setup = false; dev_priv->modeset_restore_state = NULL; + if (state) + state->acquire_ctx = &ctx; /* * This is a cludge because with real atomic modeset mode_config.mutex @@ -16169,43 +16256,17 @@ void intel_display_resume(struct drm_device *dev) mutex_lock(&dev->mode_config.mutex); drm_modeset_acquire_init(&ctx, 0); -retry: - ret = drm_modeset_lock_all_ctx(dev, &ctx); - - if (ret == 0 && !setup) { - setup = true; - - intel_modeset_setup_hw_state(dev); - i915_redisable_vga(dev); - } - - if (ret == 0 && state) { - struct drm_crtc_state *crtc_state; - struct drm_crtc *crtc; - int i; - - state->acquire_ctx = &ctx; - - /* ignore any reset values/BIOS leftovers in the WM registers */ - to_intel_atomic_state(state)->skip_intermediate_wm = true; - - for_each_crtc_in_state(state, crtc, crtc_state, i) { - /* - * Force recalculation even if we restore - * current state. With fast modeset this may not result - * in a modeset when the state is compatible. - */ - crtc_state->mode_changed = true; - } - - ret = drm_atomic_commit(state); - } + while (1) { + ret = drm_modeset_lock_all_ctx(dev, &ctx); + if (ret != -EDEADLK) + break; - if (ret == -EDEADLK) { drm_modeset_backoff(&ctx); - goto retry; } + if (!ret) + ret = __intel_display_resume(dev, state); + drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); mutex_unlock(&dev->mode_config.mutex); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index cc937a1..ff399b9 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1716,6 +1716,9 @@ void ilk_wm_get_hw_state(struct drm_device *dev); void skl_wm_get_hw_state(struct drm_device *dev); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); +bool skl_can_enable_sagv(struct drm_atomic_state *state); +int skl_enable_sagv(struct drm_i915_private *dev_priv); +int skl_disable_sagv(struct drm_i915_private *dev_priv); uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config); bool ilk_disable_lp_wm(struct drm_device *dev); int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6); diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 6a7ad3e..3836a1c 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -1230,12 +1230,29 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) if (i915.enable_fbc >= 0) return !!i915.enable_fbc; + if (!HAS_FBC(dev_priv)) + return 0; + if (IS_BROADWELL(dev_priv)) return 1; return 0; } +static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv) +{ +#ifdef CONFIG_INTEL_IOMMU + /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */ + if (intel_iommu_gfx_mapped && + (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) { + DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n"); + return true; + } +#endif + + return false; +} + /** * intel_fbc_init - Initialize FBC * @dev_priv: the i915 device @@ -1253,6 +1270,9 @@ void intel_fbc_init(struct drm_i915_private *dev_priv) fbc->active = false; fbc->work.scheduled = false; + if (need_fbc_vtd_wa(dev_priv)) + mkwrite_device_info(dev_priv)->has_fbc = false; + i915.enable_fbc = intel_sanitize_fbc_option(dev_priv); DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", i915.enable_fbc); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 97ba6c8..53e13c1 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2852,6 +2852,7 @@ bool ilk_disable_lp_wm(struct drm_device *dev) #define SKL_DDB_SIZE 896 /* in blocks */ #define BXT_DDB_SIZE 512 +#define SKL_SAGV_BLOCK_TIME 30 /* µs */ /* * Return the index of a plane in the SKL DDB and wm result arrays. Primary @@ -2875,6 +2876,153 @@ skl_wm_plane_id(const struct intel_plane *plane) } } +/* + * SAGV dynamically adjusts the system agent voltage and clock frequencies + * depending on power and performance requirements. The display engine access + * to system memory is blocked during the adjustment time. Because of the + * blocking time, having this enabled can cause full system hangs and/or pipe + * underruns if we don't meet all of the following requirements: + * + * - <= 1 pipe enabled + * - All planes can enable watermarks for latencies >= SAGV engine block time + * - We're not using an interlaced display configuration + */ +int +skl_enable_sagv(struct drm_i915_private *dev_priv) +{ + int ret; + + if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED || + dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED) + return 0; + + DRM_DEBUG_KMS("Enabling the SAGV\n"); + mutex_lock(&dev_priv->rps.hw_lock); + + ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL, + GEN9_SAGV_ENABLE); + + /* We don't need to wait for the SAGV when enabling */ + mutex_unlock(&dev_priv->rps.hw_lock); + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have an SAGV. + */ + if (ret == -ENXIO) { + DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n"); + dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED; + return 0; + } else if (ret < 0) { + DRM_ERROR("Failed to enable the SAGV\n"); + return ret; + } + + dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED; + return 0; +} + +static int +skl_do_sagv_disable(struct drm_i915_private *dev_priv) +{ + int ret; + uint32_t temp = GEN9_SAGV_DISABLE; + + ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL, + &temp); + if (ret) + return ret; + else + return temp & GEN9_SAGV_IS_DISABLED; +} + +int +skl_disable_sagv(struct drm_i915_private *dev_priv) +{ + int ret, result; + + if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED || + dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED) + return 0; + + DRM_DEBUG_KMS("Disabling the SAGV\n"); + mutex_lock(&dev_priv->rps.hw_lock); + + /* bspec says to keep retrying for at least 1 ms */ + ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1); + mutex_unlock(&dev_priv->rps.hw_lock); + + if (ret == -ETIMEDOUT) { + DRM_ERROR("Request to disable SAGV timed out\n"); + return -ETIMEDOUT; + } + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have an SAGV. + */ + if (result == -ENXIO) { + DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n"); + dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED; + return 0; + } else if (result < 0) { + DRM_ERROR("Failed to disable the SAGV\n"); + return result; + } + + dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED; + return 0; +} + +bool skl_can_enable_sagv(struct drm_atomic_state *state) +{ + struct drm_device *dev = state->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct drm_crtc *crtc; + enum pipe pipe; + int level, plane; + + /* + * SKL workaround: bspec recommends we disable the SAGV when we have + * more then one pipe enabled + * + * If there are no active CRTCs, no additional checks need be performed + */ + if (hweight32(intel_state->active_crtcs) == 0) + return true; + else if (hweight32(intel_state->active_crtcs) > 1) + return false; + + /* Since we're now guaranteed to only have one active CRTC... */ + pipe = ffs(intel_state->active_crtcs) - 1; + crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + + if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE) + return false; + + for_each_plane(dev_priv, pipe, plane) { + /* Skip this plane if it's not enabled */ + if (intel_state->wm_results.plane[pipe][plane][0] == 0) + continue; + + /* Find the highest enabled wm level for this plane */ + for (level = ilk_wm_max_level(dev); + intel_state->wm_results.plane[pipe][plane][level] == 0; --level) + { } + + /* + * If any of the planes on this pipe don't enable wm levels + * that incur memory latencies higher then 30µs we can't enable + * the SAGV + */ + if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME) + return false; + } + + return true; +} + static void skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, const struct intel_crtc_state *cstate, @@ -3107,8 +3255,6 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate) total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id]; } - WARN_ON(cstate->plane_mask && total_data_rate == 0); - return total_data_rate; } @@ -3344,6 +3490,8 @@ static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, plane_bytes_per_line *= 4; plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512); plane_blocks_per_line /= 4; + } else if (tiling == DRM_FORMAT_MOD_NONE) { + plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1; } else { plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512); } @@ -3910,9 +4058,24 @@ skl_compute_ddb(struct drm_atomic_state *state) * pretend that all pipes switched active status so that we'll * ensure a full DDB recompute. */ - if (dev_priv->wm.distrust_bios_wm) + if (dev_priv->wm.distrust_bios_wm) { + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, + state->acquire_ctx); + if (ret) + return ret; + intel_state->active_pipe_changes = ~0; + /* + * We usually only initialize intel_state->active_crtcs if we + * we're doing a modeset; make sure this field is always + * initialized during the sanitization process that happens + * on the first commit too. + */ + if (!intel_state->modeset) + intel_state->active_crtcs = dev_priv->active_crtcs; + } + /* * If the modeset changes which CRTC's are active, we need to * recompute the DDB allocation for *all* active pipes, even @@ -3941,11 +4104,33 @@ skl_compute_ddb(struct drm_atomic_state *state) ret = skl_allocate_pipe_ddb(cstate, ddb); if (ret) return ret; + + ret = drm_atomic_add_affected_planes(state, &intel_crtc->base); + if (ret) + return ret; } return 0; } +static void +skl_copy_wm_for_pipe(struct skl_wm_values *dst, + struct skl_wm_values *src, + enum pipe pipe) +{ + dst->wm_linetime[pipe] = src->wm_linetime[pipe]; + memcpy(dst->plane[pipe], src->plane[pipe], + sizeof(dst->plane[pipe])); + memcpy(dst->plane_trans[pipe], src->plane_trans[pipe], + sizeof(dst->plane_trans[pipe])); + + dst->ddb.pipe[pipe] = src->ddb.pipe[pipe]; + memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe], + sizeof(dst->ddb.y_plane[pipe])); + memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe], + sizeof(dst->ddb.plane[pipe])); +} + static int skl_compute_wm(struct drm_atomic_state *state) { @@ -4018,8 +4203,10 @@ static void skl_update_wm(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct skl_wm_values *results = &dev_priv->wm.skl_results; + struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw; struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal; + int pipe; if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0) return; @@ -4031,8 +4218,12 @@ static void skl_update_wm(struct drm_crtc *crtc) skl_write_wm_values(dev_priv, results); skl_flush_wm_values(dev_priv, results); - /* store the new configuration */ - dev_priv->wm.skl_hw = *results; + /* + * Store the new configuration (but only for the pipes that have + * changed; the other values weren't recomputed). + */ + for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes) + skl_copy_wm_for_pipe(hw_vals, results, pipe); mutex_unlock(&dev_priv->wm.wm_mutex); } @@ -6574,9 +6765,7 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv) { - if (IS_CHERRYVIEW(dev_priv)) - return; - else if (IS_VALLEYVIEW(dev_priv)) + if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); if (!i915.enable_rc6) @@ -7658,8 +7847,53 @@ void intel_init_pm(struct drm_device *dev) } } +static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv) +{ + uint32_t flags = + I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK; + + switch (flags) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_UNIMPLEMENTED_CMD: + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + case GEN6_PCODE_TIMEOUT: + return -ETIMEDOUT; + default: + MISSING_CASE(flags) + return 0; + } +} + +static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv) +{ + uint32_t flags = + I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK; + + switch (flags) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN7_PCODE_TIMEOUT: + return -ETIMEDOUT; + case GEN7_PCODE_ILLEGAL_DATA: + return -EINVAL; + case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + default: + MISSING_CASE(flags); + return 0; + } +} + int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val) { + int status; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); /* GEN6_PCODE_* are outside of the forcewake domain, we can @@ -7686,12 +7920,25 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val *val = I915_READ_FW(GEN6_PCODE_DATA); I915_WRITE_FW(GEN6_PCODE_DATA, 0); + if (INTEL_GEN(dev_priv) > 6) + status = gen7_check_mailbox_status(dev_priv); + else + status = gen6_check_mailbox_status(dev_priv); + + if (status) { + DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n", + status); + return status; + } + return 0; } int sandybridge_pcode_write(struct drm_i915_private *dev_priv, - u32 mbox, u32 val) + u32 mbox, u32 val) { + int status; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); /* GEN6_PCODE_* are outside of the forcewake domain, we can @@ -7716,6 +7963,17 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, I915_WRITE_FW(GEN6_PCODE_DATA, 0); + if (INTEL_GEN(dev_priv) > 6) + status = gen7_check_mailbox_status(dev_priv); + else + status = gen6_check_mailbox_status(dev_priv); + + if (status) { + DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n", + status); + return status; + } + return 0; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index cca7792..1d3161b 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1178,8 +1178,8 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2)); - /* WaInsertDummyPushConstPs:bxt */ - if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + /* WaToEnableHwFixForPushConstHWBug:bxt */ + if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); @@ -1222,8 +1222,8 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_RO_PERF_DIS); - /* WaInsertDummyPushConstPs:kbl */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + /* WaToEnableHwFixForPushConstHWBug:kbl */ + if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index 23ac804..294de45 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -2,6 +2,9 @@ config DRM_MEDIATEK tristate "DRM Support for Mediatek SoCs" depends on DRM depends on ARCH_MEDIATEK || (ARM && COMPILE_TEST) + depends on COMMON_CLK + depends on HAVE_ARM_SMCCC + depends on OF select DRM_GEM_CMA_HELPER select DRM_KMS_HELPER select DRM_MIPI_DSI diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index df26570..28c1423 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -73,10 +73,12 @@ static void qxl_fb_image_init(struct qxl_fb_image *qxl_fb_image, } } +#ifdef CONFIG_DRM_FBDEV_EMULATION static struct fb_deferred_io qxl_defio = { .delay = QXL_DIRTY_DELAY, .deferred_io = drm_fb_helper_deferred_io, }; +#endif static struct fb_ops qxlfb_ops = { .owner = THIS_MODULE, @@ -313,8 +315,10 @@ static int qxlfb_create(struct qxl_fbdev *qfbdev, goto out_destroy_fbi; } +#ifdef CONFIG_DRM_FBDEV_EMULATION info->fbdefio = &qxl_defio; fb_deferred_io_init(info); +#endif qdev->fbdev_info = info; qdev->fbdev_qfb = &qfbdev->qfb; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index a97abc8..1dcf390 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -627,7 +627,9 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, if (radeon_crtc->ss.refdiv) { radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV; radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv; - if (rdev->family >= CHIP_RV770) + if (ASIC_IS_AVIVO(rdev) && + rdev->family != CHIP_RS780 && + rdev->family != CHIP_RS880) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; } } diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 6de3428..ddef0d4 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -198,16 +198,7 @@ static int radeon_atpx_validate(struct radeon_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { printk("ATPX Hybrid Graphics\n"); -#if 1 - /* This is a temporary hack until the D3 cold support - * makes it upstream. The ATPX power_control method seems - * to still work on even if the system should be using - * the new standardized hybrid D3 cold ACPI interface. - */ - atpx->functions.power_cntl = true; -#else atpx->functions.power_cntl = false; -#endif atpx->is_hybrid = true; } diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 0c00e19..c2e0a1c 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -263,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, rdev = radeon_get_rdev(bo->bdev); ridx = radeon_copy_ring_index(rdev); - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 3d228ad..3dea121 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -840,6 +840,21 @@ static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = { .destroy = tegra_output_encoder_destroy, }; +static void tegra_dsi_unprepare(struct tegra_dsi *dsi) +{ + int err; + + if (dsi->slave) + tegra_dsi_unprepare(dsi->slave); + + err = tegra_mipi_disable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n", + err); + + pm_runtime_put(dsi->dev); +} + static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) { struct tegra_output *output = encoder_to_output(encoder); @@ -876,7 +891,26 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) tegra_dsi_disable(dsi); - pm_runtime_put(dsi->dev); + tegra_dsi_unprepare(dsi); +} + +static void tegra_dsi_prepare(struct tegra_dsi *dsi) +{ + int err; + + pm_runtime_get_sync(dsi->dev); + + err = tegra_mipi_enable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n", + err); + + err = tegra_dsi_pad_calibrate(dsi); + if (err < 0) + dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + + if (dsi->slave) + tegra_dsi_prepare(dsi->slave); } static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) @@ -887,13 +921,8 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) struct tegra_dsi *dsi = to_dsi(output); struct tegra_dsi_state *state; u32 value; - int err; - - pm_runtime_get_sync(dsi->dev); - err = tegra_dsi_pad_calibrate(dsi); - if (err < 0) - dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + tegra_dsi_prepare(dsi); state = tegra_dsi_get_state(dsi); diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index d5df555..9688bfa 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -203,6 +203,7 @@ static int udl_fb_open(struct fb_info *info, int user) ufbdev->fb_count++; +#ifdef CONFIG_DRM_FBDEV_EMULATION if (fb_defio && (info->fbdefio == NULL)) { /* enable defio at last moment if not disabled by client */ @@ -218,6 +219,7 @@ static int udl_fb_open(struct fb_info *info, int user) info->fbdefio = fbdefio; fb_deferred_io_init(info); } +#endif pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n", info->node, user, info, ufbdev->fb_count); @@ -235,12 +237,14 @@ static int udl_fb_release(struct fb_info *info, int user) ufbdev->fb_count--; +#ifdef CONFIG_DRM_FBDEV_EMULATION if ((ufbdev->fb_count == 0) && (info->fbdefio)) { fb_deferred_io_cleanup(info); kfree(info->fbdefio); info->fbdefio = NULL; info->fbops->fb_mmap = udl_fb_mmap; } +#endif pr_warn("released /dev/fb%d user=%d count=%d\n", info->node, user, ufbdev->fb_count); diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c index 52a6fd2..e00809d 100644 --- a/drivers/gpu/host1x/mipi.c +++ b/drivers/gpu/host1x/mipi.c @@ -242,20 +242,6 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device) dev->pads = args.args[0]; dev->device = device; - mutex_lock(&dev->mipi->lock); - - if (dev->mipi->usage_count++ == 0) { - err = tegra_mipi_power_up(dev->mipi); - if (err < 0) { - dev_err(dev->mipi->dev, - "failed to power up MIPI bricks: %d\n", - err); - return ERR_PTR(err); - } - } - - mutex_unlock(&dev->mipi->lock); - return dev; put: @@ -270,29 +256,42 @@ EXPORT_SYMBOL(tegra_mipi_request); void tegra_mipi_free(struct tegra_mipi_device *device) { - int err; + platform_device_put(device->pdev); + kfree(device); +} +EXPORT_SYMBOL(tegra_mipi_free); - mutex_lock(&device->mipi->lock); +int tegra_mipi_enable(struct tegra_mipi_device *dev) +{ + int err = 0; - if (--device->mipi->usage_count == 0) { - err = tegra_mipi_power_down(device->mipi); - if (err < 0) { - /* - * Not much that can be done here, so an error message - * will have to do. - */ - dev_err(device->mipi->dev, - "failed to power down MIPI bricks: %d\n", - err); - } - } + mutex_lock(&dev->mipi->lock); - mutex_unlock(&device->mipi->lock); + if (dev->mipi->usage_count++ == 0) + err = tegra_mipi_power_up(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; - platform_device_put(device->pdev); - kfree(device); } -EXPORT_SYMBOL(tegra_mipi_free); +EXPORT_SYMBOL(tegra_mipi_enable); + +int tegra_mipi_disable(struct tegra_mipi_device *dev) +{ + int err = 0; + + mutex_lock(&dev->mipi->lock); + + if (--dev->mipi->usage_count == 0) + err = tegra_mipi_power_down(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; + +} +EXPORT_SYMBOL(tegra_mipi_disable); static int tegra_mipi_wait(struct tegra_mipi *mipi) { diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index 730d840..4667012 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -491,7 +491,7 @@ struct it87_sio_data { struct it87_data { const struct attribute_group *groups[7]; enum chips type; - u16 features; + u32 features; u8 peci_mask; u8 old_peci_mask; @@ -2015,6 +2015,7 @@ static struct attribute *it87_attributes_in[] = { &sensor_dev_attr_in10_input.dev_attr.attr, /* 41 */ &sensor_dev_attr_in11_input.dev_attr.attr, /* 41 */ &sensor_dev_attr_in12_input.dev_attr.attr, /* 41 */ + NULL }; static const struct attribute_group it87_group_in = { diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c index f233726..1bb97f6 100644 --- a/drivers/i2c/busses/i2c-at91.c +++ b/drivers/i2c/busses/i2c-at91.c @@ -38,6 +38,7 @@ #define AT91_I2C_TIMEOUT msecs_to_jiffies(100) /* transfer timeout */ #define AT91_I2C_DMA_THRESHOLD 8 /* enable DMA if transfer size is bigger than this threshold */ #define AUTOSUSPEND_TIMEOUT 2000 +#define AT91_I2C_MAX_ALT_CMD_DATA_SIZE 256 /* AT91 TWI register definitions */ #define AT91_TWI_CR 0x0000 /* Control Register */ @@ -141,6 +142,7 @@ struct at91_twi_dev { unsigned twi_cwgr_reg; struct at91_twi_pdata *pdata; bool use_dma; + bool use_alt_cmd; bool recv_len_abort; u32 fifo_size; struct at91_twi_dma dma; @@ -269,7 +271,7 @@ static void at91_twi_write_next_byte(struct at91_twi_dev *dev) /* send stop when last byte has been written */ if (--dev->buf_len == 0) - if (!dev->pdata->has_alt_cmd) + if (!dev->use_alt_cmd) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); dev_dbg(dev->dev, "wrote 0x%x, to go %d\n", *dev->buf, dev->buf_len); @@ -292,7 +294,7 @@ static void at91_twi_write_data_dma_callback(void *data) * we just have to enable TXCOMP one. */ at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP); - if (!dev->pdata->has_alt_cmd) + if (!dev->use_alt_cmd) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); } @@ -410,7 +412,7 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev) } /* send stop if second but last byte has been read */ - if (!dev->pdata->has_alt_cmd && dev->buf_len == 1) + if (!dev->use_alt_cmd && dev->buf_len == 1) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); dev_dbg(dev->dev, "read 0x%x, to go %d\n", *dev->buf, dev->buf_len); @@ -426,7 +428,7 @@ static void at91_twi_read_data_dma_callback(void *data) dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg[0]), dev->buf_len, DMA_FROM_DEVICE); - if (!dev->pdata->has_alt_cmd) { + if (!dev->use_alt_cmd) { /* The last two bytes have to be read without using dma */ dev->buf += dev->buf_len - 2; dev->buf_len = 2; @@ -443,7 +445,7 @@ static void at91_twi_read_data_dma(struct at91_twi_dev *dev) struct dma_chan *chan_rx = dma->chan_rx; size_t buf_len; - buf_len = (dev->pdata->has_alt_cmd) ? dev->buf_len : dev->buf_len - 2; + buf_len = (dev->use_alt_cmd) ? dev->buf_len : dev->buf_len - 2; dma->direction = DMA_FROM_DEVICE; /* Keep in mind that we won't use dma to read the last two bytes */ @@ -651,7 +653,7 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) unsigned start_flags = AT91_TWI_START; /* if only one byte is to be read, immediately stop transfer */ - if (!has_alt_cmd && dev->buf_len <= 1 && + if (!dev->use_alt_cmd && dev->buf_len <= 1 && !(dev->msg->flags & I2C_M_RECV_LEN)) start_flags |= AT91_TWI_STOP; at91_twi_write(dev, AT91_TWI_CR, start_flags); @@ -745,7 +747,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) int ret; unsigned int_addr_flag = 0; struct i2c_msg *m_start = msg; - bool is_read, use_alt_cmd = false; + bool is_read; dev_dbg(&adap->dev, "at91_xfer: processing %d messages:\n", num); @@ -768,14 +770,16 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) at91_twi_write(dev, AT91_TWI_IADR, internal_address); } + dev->use_alt_cmd = false; is_read = (m_start->flags & I2C_M_RD); if (dev->pdata->has_alt_cmd) { - if (m_start->len > 0) { + if (m_start->len > 0 && + m_start->len < AT91_I2C_MAX_ALT_CMD_DATA_SIZE) { at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_ACMEN); at91_twi_write(dev, AT91_TWI_ACR, AT91_TWI_ACR_DATAL(m_start->len) | ((is_read) ? AT91_TWI_ACR_DIR : 0)); - use_alt_cmd = true; + dev->use_alt_cmd = true; } else { at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_ACMDIS); } @@ -784,7 +788,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) at91_twi_write(dev, AT91_TWI_MMR, (m_start->addr << 16) | int_addr_flag | - ((!use_alt_cmd && is_read) ? AT91_TWI_MREAD : 0)); + ((!dev->use_alt_cmd && is_read) ? AT91_TWI_MREAD : 0)); dev->buf_len = m_start->len; dev->buf = m_start->buf; diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 19c8438..95f7cac 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -158,7 +158,7 @@ static irqreturn_t bcm_iproc_i2c_isr(int irq, void *data) if (status & BIT(IS_M_START_BUSY_SHIFT)) { iproc_i2c->xfer_is_done = 1; - complete_all(&iproc_i2c->done); + complete(&iproc_i2c->done); } writel(status, iproc_i2c->base + IS_OFFSET); diff --git a/drivers/i2c/busses/i2c-bcm-kona.c b/drivers/i2c/busses/i2c-bcm-kona.c index ac9f476..f987432 100644 --- a/drivers/i2c/busses/i2c-bcm-kona.c +++ b/drivers/i2c/busses/i2c-bcm-kona.c @@ -229,7 +229,7 @@ static irqreturn_t bcm_kona_i2c_isr(int irq, void *devid) dev->base + TXFCR_OFFSET); writel(status & ~ISR_RESERVED_MASK, dev->base + ISR_OFFSET); - complete_all(&dev->done); + complete(&dev->done); return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 3f5a4d7..385b57b 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -228,7 +228,7 @@ static irqreturn_t brcmstb_i2c_isr(int irq, void *devid) return IRQ_NONE; brcmstb_i2c_enable_disable_irq(dev, INT_DISABLE); - complete_all(&dev->done); + complete(&dev->done); dev_dbg(dev->device, "isr handled"); return IRQ_HANDLED; diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c index a0d95ff..2d5ff863 100644 --- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c +++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c @@ -215,7 +215,7 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[], msg->outsize = request_len; msg->insize = response_len; - result = cros_ec_cmd_xfer(bus->ec, msg); + result = cros_ec_cmd_xfer_status(bus->ec, msg); if (result < 0) { dev_err(dev, "Error transferring EC i2c message %d\n", result); goto exit; diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c index 71d3929..76e2898 100644 --- a/drivers/i2c/busses/i2c-meson.c +++ b/drivers/i2c/busses/i2c-meson.c @@ -211,7 +211,7 @@ static void meson_i2c_stop(struct meson_i2c *i2c) meson_i2c_add_token(i2c, TOKEN_STOP); } else { i2c->state = STATE_IDLE; - complete_all(&i2c->done); + complete(&i2c->done); } } @@ -238,7 +238,7 @@ static irqreturn_t meson_i2c_irq(int irqno, void *dev_id) dev_dbg(i2c->dev, "error bit set\n"); i2c->error = -ENXIO; i2c->state = STATE_IDLE; - complete_all(&i2c->done); + complete(&i2c->done); goto out; } @@ -269,7 +269,7 @@ static irqreturn_t meson_i2c_irq(int irqno, void *dev_id) break; case STATE_STOP: i2c->state = STATE_IDLE; - complete_all(&i2c->done); + complete(&i2c->done); break; case STATE_IDLE: break; diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index dfa7a4b..ac88a52 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -379,6 +379,7 @@ static int ocores_i2c_of_probe(struct platform_device *pdev, if (!clock_frequency_present) { dev_err(&pdev->dev, "Missing required parameter 'opencores,ip-clock-frequency'\n"); + clk_disable_unprepare(i2c->clk); return -ENODEV; } i2c->ip_clock_khz = clock_frequency / 1000; @@ -467,20 +468,21 @@ static int ocores_i2c_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported I/O width (%d)\n", i2c->reg_io_width); - return -EINVAL; + ret = -EINVAL; + goto err_clk; } } ret = ocores_init(&pdev->dev, i2c); if (ret) - return ret; + goto err_clk; init_waitqueue_head(&i2c->wait); ret = devm_request_irq(&pdev->dev, irq, ocores_isr, 0, pdev->name, i2c); if (ret) { dev_err(&pdev->dev, "Cannot claim IRQ\n"); - return ret; + goto err_clk; } /* hook up driver to tree */ @@ -494,7 +496,7 @@ static int ocores_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(&i2c->adap); if (ret) { dev_err(&pdev->dev, "Failed to add adapter\n"); - return ret; + goto err_clk; } /* add in known devices to the bus */ @@ -504,6 +506,10 @@ static int ocores_i2c_probe(struct platform_device *pdev) } return 0; + +err_clk: + clk_disable_unprepare(i2c->clk); + return ret; } static int ocores_i2c_remove(struct platform_device *pdev) diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index 8de073a..215ac87 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -68,7 +68,7 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne adap = of_find_i2c_adapter_by_node(priv->chan[new_chan].parent_np); if (!adap) { ret = -ENODEV; - goto err; + goto err_with_revert; } p = devm_pinctrl_get_select(adap->dev.parent, priv->bus_name); @@ -103,6 +103,8 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne err_with_put: i2c_put_adapter(adap); + err_with_revert: + of_changeset_revert(&priv->chan[new_chan].chgset); err: dev_err(priv->dev, "failed to setup demux-adapter %d (%d)\n", new_chan, ret); return ret; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e6dfa1b..5f65a78 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2462,18 +2462,24 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) if (addr->dev_addr.bound_dev_if) { ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } if (ndev->flags & IFF_LOOPBACK) { dev_put(ndev); - if (!id_priv->id.device->get_netdev) - return -EOPNOTSUPP; + if (!id_priv->id.device->get_netdev) { + ret = -EOPNOTSUPP; + goto err2; + } ndev = id_priv->id.device->get_netdev(id_priv->id.device, id_priv->id.port_num); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } } route->path_rec->net = &init_net; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 3aca7f6..b6a953a 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1827,8 +1827,12 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) (ep->mpa_pkt + sizeof(*mpa)); ep->ird = ntohs(mpa_v2_params->ird) & MPA_V2_IRD_ORD_MASK; + ep->ird = min_t(u32, ep->ird, + cur_max_read_depth(ep->com.dev)); ep->ord = ntohs(mpa_v2_params->ord) & MPA_V2_IRD_ORD_MASK; + ep->ord = min_t(u32, ep->ord, + cur_max_read_depth(ep->com.dev)); PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird, ep->ord); if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL) @@ -3136,7 +3140,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { if (conn_param->ord > ep->ird) { if (RELAXED_IRD_NEGOTIATION) { - ep->ord = ep->ird; + conn_param->ord = ep->ird; } else { ep->ird = conn_param->ird; ep->ord = conn_param->ord; diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 812ab72..ac926c9 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -1016,15 +1016,15 @@ int c4iw_resize_cq(struct ib_cq *cq, int cqe, struct ib_udata *udata) int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { struct c4iw_cq *chp; - int ret; + int ret = 0; unsigned long flag; chp = to_c4iw_cq(ibcq); spin_lock_irqsave(&chp->lock, flag); - ret = t4_arm_cq(&chp->cq, - (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + t4_arm_cq(&chp->cq, + (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + if (flags & IB_CQ_REPORT_MISSED_EVENTS) + ret = t4_cq_notempty(&chp->cq); spin_unlock_irqrestore(&chp->lock, flag); - if (ret && !(flags & IB_CQ_REPORT_MISSED_EVENTS)) - ret = 0; return ret; } diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index 6126bbe..02173f4 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -634,6 +634,11 @@ static inline int t4_valid_cqe(struct t4_cq *cq, struct t4_cqe *cqe) return (CQE_GENBIT(cqe) == cq->gen); } +static inline int t4_cq_notempty(struct t4_cq *cq) +{ + return cq->sw_in_use || t4_valid_cqe(cq, &cq->queue[cq->cidx]); +} + static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe) { int ret; diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 79575ee..0566393 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -47,7 +47,6 @@ #include <linux/topology.h> #include <linux/cpumask.h> #include <linux/module.h> -#include <linux/cpumask.h> #include "hfi.h" #include "affinity.h" @@ -682,7 +681,7 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, size_t count) { struct hfi1_affinity_node *entry; - struct cpumask mask; + cpumask_var_t mask; int ret, i; spin_lock(&node_affinity.lock); @@ -692,19 +691,24 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (!entry) return -EINVAL; - ret = cpulist_parse(buf, &mask); + ret = zalloc_cpumask_var(&mask, GFP_KERNEL); + if (!ret) + return -ENOMEM; + + ret = cpulist_parse(buf, mask); if (ret) - return ret; + goto out; - if (!cpumask_subset(&mask, cpu_online_mask) || cpumask_empty(&mask)) { + if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) { dd_dev_warn(dd, "Invalid CPU mask\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } mutex_lock(&sdma_affinity_mutex); /* reset the SDMA interrupt affinity details */ init_cpu_mask_set(&entry->def_intr); - cpumask_copy(&entry->def_intr.mask, &mask); + cpumask_copy(&entry->def_intr.mask, mask); /* * Reassign the affinity for each SDMA interrupt. */ @@ -720,8 +724,9 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (ret) break; } - mutex_unlock(&sdma_affinity_mutex); +out: + free_cpumask_var(mask); return ret ? ret : strnlen(buf, PAGE_SIZE); } diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index dbab9d9..a49cc88 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -223,28 +223,32 @@ DEBUGFS_SEQ_FILE_OPEN(ctx_stats) DEBUGFS_FILE_OPS(ctx_stats); static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) -__acquires(RCU) + __acquires(RCU) { struct qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qp_iter *iter = iter_ptr; @@ -259,7 +263,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) -__releases(RCU) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 8246dc7..303f105 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -888,14 +888,15 @@ void set_all_slowpath(struct hfi1_devdata *dd) } static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd, - struct hfi1_packet packet, + struct hfi1_packet *packet, struct hfi1_devdata *dd) { struct work_struct *lsaw = &rcd->ppd->linkstate_active_work; - struct hfi1_message_header *hdr = hfi1_get_msgheader(packet.rcd->dd, - packet.rhf_addr); + struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd, + packet->rhf_addr); + u8 etype = rhf_rcv_type(packet->rhf); - if (hdr2sc(hdr, packet.rhf) != 0xf) { + if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) { int hwstate = read_logical_state(dd); if (hwstate != LSTATE_ACTIVE) { @@ -979,7 +980,7 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread) /* Auto activate link on non-SC15 packet receive */ if (unlikely(rcd->ppd->host_link_state == HLS_UP_ARMED) && - set_armed_to_active(rcd, packet, dd)) + set_armed_to_active(rcd, &packet, dd)) goto bail; last = process_rcv_packet(&packet, thread); } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 1ecbec1..7e03ccd 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) if (fd) { fd->rec_cpu_num = -1; /* no cpu affinity by default */ fd->mm = current->mm; + atomic_inc(&fd->mm->mm_count); } fp->private_data = fd; @@ -222,7 +223,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, ret = assign_ctxt(fp, &uinfo); if (ret < 0) return ret; - setup_ctxt(fp); + ret = setup_ctxt(fp); if (ret) return ret; ret = user_init(fp); @@ -779,6 +780,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) mutex_unlock(&hfi1_mutex); hfi1_free_ctxtdata(dd, uctxt); done: + mmdrop(fdata->mm); kobject_put(&dd->kobj); kfree(fdata); return 0; diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1000e0f..a021e66 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1272,9 +1272,26 @@ static inline int hdr2sc(struct hfi1_message_header *hdr, u64 rhf) ((!!(rhf_dc_info(rhf))) << 4); } +#define HFI1_JKEY_WIDTH 16 +#define HFI1_JKEY_MASK (BIT(16) - 1) +#define HFI1_ADMIN_JKEY_RANGE 32 + +/* + * J_KEYs are split and allocated in the following groups: + * 0 - 31 - users with administrator privileges + * 32 - 63 - kernel protocols using KDETH packets + * 64 - 65535 - all other users using KDETH packets + */ static inline u16 generate_jkey(kuid_t uid) { - return from_kuid(current_user_ns(), uid) & 0xffff; + u16 jkey = from_kuid(current_user_ns(), uid) & HFI1_JKEY_MASK; + + if (capable(CAP_SYS_ADMIN)) + jkey &= HFI1_ADMIN_JKEY_RANGE - 1; + else if (jkey < 64) + jkey |= BIT(HFI1_JKEY_WIDTH - 1); + + return jkey; } /* @@ -1656,7 +1673,6 @@ struct cc_state *get_cc_state_protected(struct hfi1_pportdata *ppd) struct hfi1_devdata *hfi1_init_dd(struct pci_dev *, const struct pci_device_id *); void hfi1_free_devdata(struct hfi1_devdata *); -void cc_state_reclaim(struct rcu_head *rcu); struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra); /* LED beaconing functions */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index a358d23..b793545 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1333,7 +1333,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) spin_unlock(&ppd->cc_state_lock); if (cc_state) - call_rcu(&cc_state->rcu, cc_state_reclaim); + kfree_rcu(cc_state, rcu); } free_credit_return(dd); diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 1263abe..39e42c3 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -1819,6 +1819,11 @@ static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data, u32 len = OPA_AM_CI_LEN(am) + 1; int ret; + if (dd->pport->port_type != PORT_TYPE_QSFP) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + #define __CI_PAGE_SIZE BIT(7) /* 128 bytes */ #define __CI_PAGE_MASK ~(__CI_PAGE_SIZE - 1) #define __CI_PAGE_NUM(a) ((a) & __CI_PAGE_MASK) @@ -3398,7 +3403,7 @@ static void apply_cc_state(struct hfi1_pportdata *ppd) spin_unlock(&ppd->cc_state_lock); - call_rcu(&old_cc_state->rcu, cc_state_reclaim); + kfree_rcu(old_cc_state, rcu); } static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, @@ -3553,13 +3558,6 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, return reply((struct ib_mad_hdr *)smp); } -void cc_state_reclaim(struct rcu_head *rcu) -{ - struct cc_state *cc_state = container_of(rcu, struct cc_state, rcu); - - kfree(cc_state); -} - static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, u32 *resp_len) diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index a5aa351..4e4d831 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -656,10 +656,6 @@ struct qp_iter *qp_iter_init(struct hfi1_ibdev *dev) iter->dev = dev; iter->specials = dev->rdi.ibdev.phys_port_cnt * 2; - if (qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c index a207717..4e95ad8 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.c +++ b/drivers/infiniband/hw/hfi1/qsfp.c @@ -706,8 +706,8 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, u8 *data) { struct hfi1_pportdata *ppd; - u32 excess_len = 0; - int ret = 0; + u32 excess_len = len; + int ret = 0, offset = 0; if (port_num > dd->num_pports || port_num < 1) { dd_dev_info(dd, "%s: Invalid port number %d\n", @@ -740,6 +740,34 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, } memcpy(data, &ppd->qsfp_info.cache[addr], len); + + if (addr <= QSFP_MONITOR_VAL_END && + (addr + len) >= QSFP_MONITOR_VAL_START) { + /* Overlap with the dynamic channel monitor range */ + if (addr < QSFP_MONITOR_VAL_START) { + if (addr + len <= QSFP_MONITOR_VAL_END) + len = addr + len - QSFP_MONITOR_VAL_START; + else + len = QSFP_MONITOR_RANGE; + offset = QSFP_MONITOR_VAL_START - addr; + addr = QSFP_MONITOR_VAL_START; + } else if (addr == QSFP_MONITOR_VAL_START) { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_RANGE; + } else { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_VAL_END - addr + 1; + } + /* Refresh the values of the dynamic monitors from the cable */ + ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len); + if (ret != len) { + ret = -EAGAIN; + goto set_zeroes; + } + } + return 0; set_zeroes: diff --git a/drivers/infiniband/hw/hfi1/qsfp.h b/drivers/infiniband/hw/hfi1/qsfp.h index 69275eb..36cf523 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.h +++ b/drivers/infiniband/hw/hfi1/qsfp.h @@ -74,6 +74,9 @@ /* Defined fields that Intel requires of qualified cables */ /* Byte 0 is Identifier, not checked */ /* Byte 1 is reserved "status MSB" */ +#define QSFP_MONITOR_VAL_START 22 +#define QSFP_MONITOR_VAL_END 81 +#define QSFP_MONITOR_RANGE (QSFP_MONITOR_VAL_END - QSFP_MONITOR_VAL_START + 1) #define QSFP_TX_CTRL_BYTE_OFFS 86 #define QSFP_PWR_CTRL_BYTE_OFFS 93 #define QSFP_CDR_CTRL_BYTE_OFFS 98 diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index b738acd..8ec09e4 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -232,7 +232,7 @@ struct i40iw_device { struct i40e_client *client; struct i40iw_hw hw; struct i40iw_cm_core cm_core; - unsigned long *mem_resources; + u8 *mem_resources; unsigned long *allocated_qps; unsigned long *allocated_cqs; unsigned long *allocated_mrs; @@ -435,8 +435,8 @@ static inline int i40iw_alloc_resource(struct i40iw_device *iwdev, *next = resource_num + 1; if (*next == max_resources) *next = 0; - spin_unlock_irqrestore(&iwdev->resource_lock, flags); *req_resource_num = resource_num; + spin_unlock_irqrestore(&iwdev->resource_lock, flags); return 0; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 5026dc7..7ca0638 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -535,8 +535,8 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node, buf += hdr_len; } - if (pd_len) - memcpy(buf, pdata->addr, pd_len); + if (pdata && pdata->addr) + memcpy(buf, pdata->addr, pdata->size); atomic_set(&sqbuf->refcount, 1); @@ -3347,26 +3347,6 @@ int i40iw_cm_disconn(struct i40iw_qp *iwqp) } /** - * i40iw_loopback_nop - Send a nop - * @qp: associated hw qp - */ -static void i40iw_loopback_nop(struct i40iw_sc_qp *qp) -{ - u64 *wqe; - u64 header; - - wqe = qp->qp_uk.sq_base->elem; - set_64bit_val(wqe, 0, 0); - set_64bit_val(wqe, 8, 0); - set_64bit_val(wqe, 16, 0); - - header = LS_64(I40IWQP_OP_NOP, I40IWQPSQ_OPCODE) | - LS_64(0, I40IWQPSQ_SIGCOMPL) | - LS_64(qp->qp_uk.swqe_polarity, I40IWQPSQ_VALID); - set_64bit_val(wqe, 24, header); -} - -/** * i40iw_qp_disconnect - free qp and close cm * @iwqp: associate qp for the connection */ @@ -3638,7 +3618,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) } else { if (iwqp->page) iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page); - i40iw_loopback_nop(&iwqp->sc_qp); + dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp, NULL, 0, 0); } if (iwqp->page) diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 6e90813..0cbbe40 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1558,6 +1558,10 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client) enum i40iw_status_code status; struct i40iw_handler *hdl; + hdl = i40iw_find_netdev(ldev->netdev); + if (hdl) + return 0; + hdl = kzalloc(sizeof(*hdl), GFP_KERNEL); if (!hdl) return -ENOMEM; diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 0e8db0a..6fd043b 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -673,8 +673,11 @@ enum i40iw_status_code i40iw_free_virt_mem(struct i40iw_hw *hw, { if (!mem) return I40IW_ERR_PARAM; + /* + * mem->va points to the parent of mem, so both mem and mem->va + * can not be touched once mem->va is freed + */ kfree(mem->va); - mem->va = NULL; return 0; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 2360338..6329c97 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -794,7 +794,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, return &iwqp->ibqp; error: i40iw_free_qp_resources(iwdev, iwqp, qp_num); - kfree(mem); return ERR_PTR(err_code); } @@ -1926,8 +1925,7 @@ static int i40iw_dereg_mr(struct ib_mr *ib_mr) } if (iwpbl->pbl_allocated) i40iw_free_pble(iwdev->pble_rsrc, palloc); - kfree(iwpbl->iwmr); - iwpbl->iwmr = NULL; + kfree(iwmr); return 0; } diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index d6fc8a6..006db64 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -576,8 +576,8 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum) checksum == cpu_to_be16(0xffff); } -static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, - unsigned tail, struct mlx4_cqe *cqe, int is_eth) +static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, + unsigned tail, struct mlx4_cqe *cqe, int is_eth) { struct mlx4_ib_proxy_sqp_hdr *hdr; @@ -600,8 +600,6 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32); wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12); } - - return 0; } static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries, @@ -692,7 +690,7 @@ repoll: if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP && is_send)) { pr_warn("Completion for NOP opcode detected!\n"); - return -EINVAL; + return -EAGAIN; } /* Resize CQ in progress */ @@ -723,7 +721,7 @@ repoll: if (unlikely(!mqp)) { pr_warn("CQ %06x with entry for unknown QPN %06x\n", cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK); - return -EINVAL; + return -EAGAIN; } *cur_qp = to_mibqp(mqp); @@ -741,7 +739,7 @@ repoll: if (unlikely(!msrq)) { pr_warn("CQ %06x with entry for unknown SRQN %06x\n", cq->mcq.cqn, srq_num); - return -EINVAL; + return -EAGAIN; } } @@ -852,9 +850,11 @@ repoll: if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) { if ((*cur_qp)->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER | - MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) - return use_tunnel_data(*cur_qp, cq, wc, tail, - cqe, is_eth); + MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) { + use_tunnel_data(*cur_qp, cq, wc, tail, cqe, + is_eth); + return 0; + } } wc->slid = be16_to_cpu(cqe->rlid); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index f02a975..8db6fdf 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -37,7 +37,6 @@ #include <linux/pci.h> #include <linux/dma-mapping.h> #include <linux/slab.h> -#include <linux/io-mapping.h> #if defined(CONFIG_X86) #include <asm/pat.h> #endif diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 16740dc..67fc0b6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1156,18 +1156,18 @@ static void ocrdma_get_attr(struct ocrdma_dev *dev, attr->max_srq = (rsp->max_srq_rpir_qps & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_OFFSET; - attr->max_send_sge = ((rsp->max_write_send_sge & + attr->max_send_sge = ((rsp->max_recv_send_sge & OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT); - attr->max_recv_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT; + attr->max_recv_sge = (rsp->max_recv_send_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT; attr->max_srq_sge = (rsp->max_srq_rqe_sge & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET; - attr->max_rdma_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT; + attr->max_rdma_sge = (rsp->max_wr_rd_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT; attr->max_ord_per_qp = (rsp->max_ird_ord_per_qp & OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 0efc966..37df448 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -554,9 +554,9 @@ enum { OCRDMA_MBX_QUERY_CFG_L3_TYPE_MASK = 0x18, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK = 0xFFFF, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT = 16, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK = 0xFFFF << - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT = 16, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK = 0xFFFF << + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK = 0xFFFF, @@ -612,6 +612,8 @@ enum { OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET = 0, OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK = 0xFFFF << OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT = 0, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK = 0xFFFF, }; struct ocrdma_mbx_query_config { @@ -619,7 +621,7 @@ struct ocrdma_mbx_query_config { struct ocrdma_mbx_rsp rsp; u32 qp_srq_cq_ird_ord; u32 max_pd_ca_ack_delay; - u32 max_write_send_sge; + u32 max_recv_send_sge; u32 max_ird_ord_per_qp; u32 max_shared_ird_ord; u32 max_mr; @@ -639,6 +641,8 @@ struct ocrdma_mbx_query_config { u32 max_wqes_rqes_per_q; u32 max_cq_cqes_per_cq; u32 max_srq_rqe_sge; + u32 max_wr_rd_sge; + u32 ird_pgsz_num_pages; }; struct ocrdma_fw_ver_rsp { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index b1a3d91..0aa8547 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr, IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_LOCAL_DMA_LKEY | IB_DEVICE_MEM_MGT_EXTENSIONS; - attr->max_sge = dev->attr.max_send_sge; - attr->max_sge_rd = attr->max_sge; + attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_recv_sge); + attr->max_sge_rd = dev->attr.max_rdma_sge; attr->max_cq = dev->attr.max_cq; attr->max_cqe = dev->attr.max_cqe; attr->max_mr = dev->attr.max_mr; diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 5e75b43..5bad8e3 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -189,27 +189,32 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v) DEBUGFS_FILE(ctx_stats) static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) + __acquires(RCU) { struct qib_qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qib_qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qib_qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qib_qp_iter *iter = iter_ptr; @@ -224,6 +229,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index fcdf3791..c3edc03 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -328,26 +328,12 @@ static ssize_t flash_write(struct file *file, const char __user *buf, pos = *ppos; - if (pos != 0) { - ret = -EINVAL; - goto bail; - } - - if (count != sizeof(struct qib_flash)) { - ret = -EINVAL; - goto bail; - } - - tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) { - ret = -ENOMEM; - goto bail; - } + if (pos != 0 || count != sizeof(struct qib_flash)) + return -EINVAL; - if (copy_from_user(tmp, buf, count)) { - ret = -EFAULT; - goto bail_tmp; - } + tmp = memdup_user(buf, count); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); dd = private2dd(file); if (qib_eeprom_write(dd, pos, tmp, count)) { @@ -361,8 +347,6 @@ static ssize_t flash_write(struct file *file, const char __user *buf, bail_tmp: kfree(tmp); - -bail: return ret; } diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 9cc0aae..f9b8cd2 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -573,10 +573,6 @@ struct qib_qp_iter *qib_qp_iter_init(struct qib_ibdev *dev) return NULL; iter->dev = dev; - if (qib_qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c229b9f..0a89a95 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -664,7 +664,8 @@ static int __init usnic_ib_init(void) return err; } - if (pci_register_driver(&usnic_ib_pci_driver)) { + err = pci_register_driver(&usnic_ib_pci_driver); + if (err) { usnic_err("Unable to register with PCI\n"); goto out_umem_fini; } diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index bdb540f..870b4f2 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -873,7 +873,8 @@ bail_qpn: free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: - vfree(qp->r_rq.wq); + if (!qp->ip) + vfree(qp->r_rq.wq); bail_driver_priv: rdi->driver_f.qp_priv_free(rdi, qp); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index ba6be06..7914c14 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -448,7 +448,7 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { - isert_err("Unable to allocate isert_conn->login_rspbuf\n"); + ret = -ENOMEM; goto out_unmap_login_req_buf; } diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index dfa23b0..883bbfe 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -522,6 +522,11 @@ static int srpt_refresh_port(struct srpt_port *sport) if (ret) goto err_query_port; + snprintf(sport->port_guid, sizeof(sport->port_guid), + "0x%016llx%016llx", + be64_to_cpu(sport->gid.global.subnet_prefix), + be64_to_cpu(sport->gid.global.interface_id)); + if (!sport->mad_agent) { memset(®_req, 0, sizeof(reg_req)); reg_req.mgmt_class = IB_MGMT_CLASS_DEVICE_MGMT; @@ -2548,10 +2553,6 @@ static void srpt_add_one(struct ib_device *device) sdev->device->name, i); goto err_ring; } - snprintf(sport->port_guid, sizeof(sport->port_guid), - "0x%016llx%016llx", - be64_to_cpu(sport->gid.global.subnet_prefix), - be64_to_cpu(sport->gid.global.interface_id)); } spin_lock(&srpt_dev_lock); diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c index 7d61439..0c07e10 100644 --- a/drivers/input/keyboard/tegra-kbc.c +++ b/drivers/input/keyboard/tegra-kbc.c @@ -376,7 +376,7 @@ static int tegra_kbc_start(struct tegra_kbc *kbc) /* Reset the KBC controller to clear all previous status.*/ reset_control_assert(kbc->rst); udelay(100); - reset_control_assert(kbc->rst); + reset_control_deassert(kbc->rst); udelay(100); tegra_kbc_config_pins(kbc); diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index faa295e..c83bce8 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -553,7 +553,6 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, goto free_struct_buff; reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS); - map_offset = 0; for (i = 0; i < rdesc->num_registers; i++) { struct rmi_register_desc_item *item = &rdesc->registers[i]; int reg_size = struct_buf[offset]; @@ -576,6 +575,8 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, item->reg = reg; item->reg_size = reg_size; + map_offset = 0; + do { for (b = 0; b < 7; b++) { if (struct_buf[offset] & (0x1 << b)) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index b4d3408..405252a 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1305,6 +1305,7 @@ static int __init i8042_create_aux_port(int idx) serio->write = i8042_aux_write; serio->start = i8042_start; serio->stop = i8042_stop; + serio->ps2_cmd_mutex = &i8042_mutex; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; if (idx < 0) { diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index a61b215..1ce3ecb 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1473,7 +1473,6 @@ static int ads7846_remove(struct spi_device *spi) ads784x_hwmon_unregister(spi, ts); - regulator_disable(ts->reg); regulator_put(ts->reg); if (!ts->get_pendown_state) { diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 7379fe1..b2744a6 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -464,7 +464,7 @@ static int silead_ts_probe(struct i2c_client *client, return -ENODEV; /* Power GPIO pin */ - data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); + data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); if (IS_ERR(data->gpio_power)) { if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER) dev_err(dev, "Shutdown GPIO request failed\n"); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index ce80117..641e887 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -879,7 +879,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) * We may have concurrent producers, so we need to be careful * not to touch any of the shadow cmdq state. */ - queue_read(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_read(cmd, Q_ENT(q, cons), q->ent_dwords); dev_err(smmu->dev, "skipping command in error state:\n"); for (i = 0; i < ARRAY_SIZE(cmd); ++i) dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]); @@ -890,7 +890,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) return; } - queue_write(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_write(Q_ENT(q, cons), cmd, q->ent_dwords); } static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu, @@ -1034,6 +1034,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, case STRTAB_STE_0_CFG_S2_TRANS: ste_live = true; break; + case STRTAB_STE_0_CFG_ABORT: + if (disable_bypass) + break; default: BUG(); /* STE corruption */ } diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 4f49fe2..2db74eb 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -686,8 +686,7 @@ static struct iommu_gather_ops arm_smmu_gather_ops = { static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { - int flags, ret; - u32 fsr, fsynr, resume; + u32 fsr, fsynr; unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -701,34 +700,15 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) if (!(fsr & FSR_FAULT)) return IRQ_NONE; - if (fsr & FSR_IGN) - dev_err_ratelimited(smmu->dev, - "Unexpected context fault (fsr 0x%x)\n", - fsr); - fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); - flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; - iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); - if (!report_iommu_fault(domain, smmu->dev, iova, flags)) { - ret = IRQ_HANDLED; - resume = RESUME_RETRY; - } else { - dev_err_ratelimited(smmu->dev, - "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n", - iova, fsynr, cfg->cbndx); - ret = IRQ_NONE; - resume = RESUME_TERMINATE; - } - - /* Clear the faulting FSR */ - writel(fsr, cb_base + ARM_SMMU_CB_FSR); - /* Retry or terminate any stalled transactions */ - if (fsr & FSR_SS) - writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME); + dev_err_ratelimited(smmu->dev, + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n", + fsr, iova, fsynr, cfg->cbndx); - return ret; + writel(fsr, cb_base + ARM_SMMU_CB_FSR); + return IRQ_HANDLED; } static irqreturn_t arm_smmu_global_fault(int irq, void *dev) @@ -837,7 +817,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, } /* SCTLR */ - reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; + reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; if (stage1) reg |= SCTLR_S1_ASIDPNE; #ifdef __BIG_ENDIAN diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 8c61399..def8ca1 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -286,12 +286,14 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl) int prot = IOMMU_READ; arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl); - if (attr & ARM_V7S_PTE_AP_RDONLY) + if (!(attr & ARM_V7S_PTE_AP_RDONLY)) prot |= IOMMU_WRITE; if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0) prot |= IOMMU_MMIO; else if (pte & ARM_V7S_ATTR_C) prot |= IOMMU_CACHE; + if (pte & ARM_V7S_ATTR_XN(lvl)) + prot |= IOMMU_NOEXEC; return prot; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7ceaba8..36b9c28 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1545,7 +1545,12 @@ static int its_force_quiescent(void __iomem *base) u32 val; val = readl_relaxed(base + GITS_CTLR); - if (val & GITS_CTLR_QUIESCENT) + /* + * GIC architecture specification requires the ITS to be both + * disabled and quiescent for writes to GITS_BASER<n> or + * GITS_CBASER to not have UNPREDICTABLE results. + */ + if ((val & GITS_CTLR_QUIESCENT) && !(val & GITS_CTLR_ENABLE)) return 0; /* Disable the generation of all interrupts to this ITS */ diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6fc56c3..ede5672 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -667,13 +667,20 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, #endif #ifdef CONFIG_CPU_PM +/* Check whether it's single security state view */ +static bool gic_dist_security_disabled(void) +{ + return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS; +} + static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { if (cmd == CPU_PM_EXIT) { - gic_enable_redist(true); + if (gic_dist_security_disabled()) + gic_enable_redist(true); gic_cpu_sys_reg_init(); - } else if (cmd == CPU_PM_ENTER) { + } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) { gic_write_grpen1(0); gic_enable_redist(false); } diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index c2cab57..390fac5 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -769,6 +769,13 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) int cpu; unsigned long flags, map = 0; + if (unlikely(nr_cpu_ids == 1)) { + /* Only one CPU? let's do a self-IPI... */ + writel_relaxed(2 << 24 | irq, + gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT); + return; + } + raw_spin_lock_irqsave(&irq_controller_lock, flags); /* Convert our logical CPU mask into a physical one. */ diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index c5f33c3..83f4983 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -713,9 +713,6 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, unsigned long flags; int i; - irq_set_chip_and_handler(virq, &gic_level_irq_controller, - handle_level_irq); - spin_lock_irqsave(&gic_lock, flags); gic_map_to_pin(intr, gic_cpu_pin); gic_map_to_vpe(intr, mips_cm_vp_id(vpe)); @@ -732,6 +729,10 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, { if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS) return gic_local_irq_domain_map(d, virq, hw); + + irq_set_chip_and_handler(virq, &gic_level_irq_controller, + handle_level_irq); + return gic_shared_irq_domain_map(d, virq, hw, 0); } @@ -771,11 +772,13 @@ static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq, hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i); ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq, - &gic_edge_irq_controller, + &gic_level_irq_controller, NULL); if (ret) goto error; + irq_set_handler(virq + i, handle_level_irq); + ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu); if (ret) goto error; @@ -890,10 +893,17 @@ void gic_dev_domain_free(struct irq_domain *d, unsigned int virq, return; } +static void gic_dev_domain_activate(struct irq_domain *domain, + struct irq_data *d) +{ + gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0); +} + static struct irq_domain_ops gic_dev_domain_ops = { .xlate = gic_dev_domain_xlate, .alloc = gic_dev_domain_alloc, .free = gic_dev_domain_free, + .activate = gic_dev_domain_activate, }; static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, diff --git a/drivers/macintosh/ams/ams-i2c.c b/drivers/macintosh/ams/ams-i2c.c index 978eda8..8a3ba56 100644 --- a/drivers/macintosh/ams/ams-i2c.c +++ b/drivers/macintosh/ams/ams-i2c.c @@ -73,7 +73,6 @@ MODULE_DEVICE_TABLE(i2c, ams_id); static struct i2c_driver ams_i2c_driver = { .driver = { .name = "ams", - .owner = THIS_MODULE, }, .probe = ams_i2c_probe, .remove = ams_i2c_remove, diff --git a/drivers/macintosh/windfarm_pm112.c b/drivers/macintosh/windfarm_pm112.c index 3024685..96d16fc 100644 --- a/drivers/macintosh/windfarm_pm112.c +++ b/drivers/macintosh/windfarm_pm112.c @@ -668,7 +668,6 @@ static struct platform_driver wf_pm112_driver = { .remove = wf_pm112_remove, .driver = { .name = "windfarm", - .owner = THIS_MODULE, }, }; diff --git a/drivers/macintosh/windfarm_pm72.c b/drivers/macintosh/windfarm_pm72.c index 2f506b9..e88cfb3 100644 --- a/drivers/macintosh/windfarm_pm72.c +++ b/drivers/macintosh/windfarm_pm72.c @@ -789,7 +789,6 @@ static struct platform_driver wf_pm72_driver = { .remove = wf_pm72_remove, .driver = { .name = "windfarm", - .owner = THIS_MODULE, }, }; diff --git a/drivers/macintosh/windfarm_rm31.c b/drivers/macintosh/windfarm_rm31.c index 82fc86a..bdfcb8a 100644 --- a/drivers/macintosh/windfarm_rm31.c +++ b/drivers/macintosh/windfarm_rm31.c @@ -682,7 +682,6 @@ static struct platform_driver wf_rm31_driver = { .remove = wf_rm31_remove, .driver = { .name = "windfarm", - .owner = THIS_MODULE, }, }; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 95a4ca6..849ad44 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -760,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, if (!d->nr_stripes || d->nr_stripes > INT_MAX || d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) { - pr_err("nr_stripes too large"); + pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)", + (unsigned)d->nr_stripes); return -ENOMEM; } @@ -1820,7 +1821,7 @@ static int cache_alloc(struct cache *ca) free = roundup_pow_of_two(ca->sb.nbuckets) >> 10; if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) || - !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || + !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) || !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) || @@ -1844,7 +1845,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, struct block_device *bdev, struct cache *ca) { char name[BDEVNAME_SIZE]; - const char *err = NULL; + const char *err = NULL; /* must be set for any error case */ int ret = 0; memcpy(&ca->sb, sb, sizeof(struct cache_sb)); @@ -1861,8 +1862,13 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); - if (ret != 0) + if (ret != 0) { + if (ret == -ENOMEM) + err = "cache_alloc(): -ENOMEM"; + else + err = "cache_alloc(): unknown error"; goto err; + } if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) { err = "error calling kobject_add"; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 4e9784b..eedba67 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -181,7 +181,7 @@ struct crypt_config { u8 key[0]; }; -#define MIN_IOS 16 +#define MIN_IOS 64 static void clone_init(struct dm_crypt_io *, struct bio *); static void kcryptd_queue_crypt(struct dm_crypt_io *io); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 97e446d..6a2e8dd 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -289,15 +289,13 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) pb->bio_submitted = true; /* - * Map reads as normal only if corrupt_bio_byte set. + * Error reads if neither corrupt_bio_byte or drop_writes are set. + * Otherwise, flakey_end_io() will decide if the reads should be modified. */ if (bio_data_dir(bio) == READ) { - /* If flags were specified, only corrupt those that match. */ - if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && - all_corrupt_bio_flags_match(bio, fc)) - goto map_bio; - else + if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags)) return -EIO; + goto map_bio; } /* @@ -334,14 +332,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - /* - * Corrupt successful READs while in down state. - */ if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { - if (fc->corrupt_bio_byte) + if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && + all_corrupt_bio_flags_match(bio, fc)) { + /* + * Corrupt successful matching READs while in down state. + */ corrupt_bio_data(bio, fc); - else + + } else if (!test_bit(DROP_WRITES, &fc->flags)) { + /* + * Error read during the down_interval if drop_writes + * wasn't configured. + */ return -EIO; + } } return error; diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 4ca2d1d..07fc1ad 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -291,9 +291,10 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis core->nr_regions = le64_to_cpu(disk->nr_regions); } -static int rw_header(struct log_c *lc, int rw) +static int rw_header(struct log_c *lc, int op) { - lc->io_req.bi_op = rw; + lc->io_req.bi_op = op; + lc->io_req.bi_op_flags = 0; return dm_io(&lc->io_req, 1, &lc->header_location, NULL); } @@ -316,7 +317,7 @@ static int read_header(struct log_c *log) { int r; - r = rw_header(log, READ); + r = rw_header(log, REQ_OP_READ); if (r) return r; @@ -630,7 +631,7 @@ static int disk_resume(struct dm_dirty_log *log) header_to_disk(&lc->header, lc->disk_header); /* write the new header */ - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (!r) { r = flush_header(lc); if (r) @@ -698,7 +699,7 @@ static int disk_flush(struct dm_dirty_log *log) log_clear_bit(lc, lc->clean_bits, i); } - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (r) fail_log_device(lc); else { diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 1b9795d..8abde6b 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -191,7 +191,6 @@ struct raid_dev { #define RT_FLAG_RS_BITMAP_LOADED 2 #define RT_FLAG_UPDATE_SBS 3 #define RT_FLAG_RESHAPE_RS 4 -#define RT_FLAG_KEEP_RS_FROZEN 5 /* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) @@ -861,6 +860,9 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) { unsigned long min_region_size = rs->ti->len / (1 << 21); + if (rs_is_raid0(rs)) + return 0; + if (!region_size) { /* * Choose a reasonable default. All figures in sectors. @@ -930,6 +932,8 @@ static int validate_raid_redundancy(struct raid_set *rs) rebuild_cnt++; switch (rs->raid_type->level) { + case 0: + break; case 1: if (rebuild_cnt >= rs->md.raid_disks) goto too_many; @@ -2335,6 +2339,13 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) case 0: break; default: + /* + * We have to keep any raid0 data/metadata device pairs or + * the MD raid0 personality will fail to start the array. + */ + if (rs_is_raid0(rs)) + continue; + dev = container_of(rdev, struct raid_dev, rdev); if (dev->meta_dev) dm_put_device(ti, dev->meta_dev); @@ -2579,7 +2590,6 @@ static int rs_prepare_reshape(struct raid_set *rs) } else { /* Process raid1 without delta_disks */ mddev->raid_disks = rs->raid_disks; - set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags); reshape = false; } } else { @@ -2590,7 +2600,6 @@ static int rs_prepare_reshape(struct raid_set *rs) if (reshape) { set_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags); set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags); } else if (mddev->raid_disks < rs->raid_disks) /* Create new superblocks and bitmaps, if any new disks */ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); @@ -2902,7 +2911,6 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags); /* Takeover ain't recovery, so disable recovery */ rs_setup_recovery(rs, MaxSector); rs_set_new(rs); @@ -3386,21 +3394,28 @@ static void raid_postsuspend(struct dm_target *ti) { struct raid_set *rs = ti->private; - if (test_and_clear_bit(RT_FLAG_RS_RESUMED, &rs->runtime_flags)) { - if (!rs->md.suspended) - mddev_suspend(&rs->md); - rs->md.ro = 1; - } + if (!rs->md.suspended) + mddev_suspend(&rs->md); + + rs->md.ro = 1; } static void attempt_restore_of_faulty_devices(struct raid_set *rs) { int i; - uint64_t failed_devices, cleared_failed_devices = 0; + uint64_t cleared_failed_devices[DISKS_ARRAY_ELEMS]; unsigned long flags; + bool cleared = false; struct dm_raid_superblock *sb; + struct mddev *mddev = &rs->md; struct md_rdev *r; + /* RAID personalities have to provide hot add/remove methods or we need to bail out. */ + if (!mddev->pers || !mddev->pers->hot_add_disk || !mddev->pers->hot_remove_disk) + return; + + memset(cleared_failed_devices, 0, sizeof(cleared_failed_devices)); + for (i = 0; i < rs->md.raid_disks; i++) { r = &rs->dev[i].rdev; if (test_bit(Faulty, &r->flags) && r->sb_page && @@ -3420,7 +3435,7 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs) * ourselves. */ if ((r->raid_disk >= 0) && - (r->mddev->pers->hot_remove_disk(r->mddev, r) != 0)) + (mddev->pers->hot_remove_disk(mddev, r) != 0)) /* Failed to revive this device, try next */ continue; @@ -3430,22 +3445,30 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs) clear_bit(Faulty, &r->flags); clear_bit(WriteErrorSeen, &r->flags); clear_bit(In_sync, &r->flags); - if (r->mddev->pers->hot_add_disk(r->mddev, r)) { + if (mddev->pers->hot_add_disk(mddev, r)) { r->raid_disk = -1; r->saved_raid_disk = -1; r->flags = flags; } else { r->recovery_offset = 0; - cleared_failed_devices |= 1 << i; + set_bit(i, (void *) cleared_failed_devices); + cleared = true; } } } - if (cleared_failed_devices) { + + /* If any failed devices could be cleared, update all sbs failed_devices bits */ + if (cleared) { + uint64_t failed_devices[DISKS_ARRAY_ELEMS]; + rdev_for_each(r, &rs->md) { sb = page_address(r->sb_page); - failed_devices = le64_to_cpu(sb->failed_devices); - failed_devices &= ~cleared_failed_devices; - sb->failed_devices = cpu_to_le64(failed_devices); + sb_retrieve_failed_devices(sb, failed_devices); + + for (i = 0; i < DISKS_ARRAY_ELEMS; i++) + failed_devices[i] &= ~cleared_failed_devices[i]; + + sb_update_failed_devices(sb, failed_devices); } } } @@ -3610,26 +3633,15 @@ static void raid_resume(struct dm_target *ti) * devices are reachable again. */ attempt_restore_of_faulty_devices(rs); - } else { - mddev->ro = 0; - mddev->in_sync = 0; + } - /* - * When passing in flags to the ctr, we expect userspace - * to reset them because they made it to the superblocks - * and reload the mapping anyway. - * - * -> only unfreeze recovery in case of a table reload or - * we'll have a bogus recovery/reshape position - * retrieved from the superblock by the ctr because - * the ongoing recovery/reshape will change it after read. - */ - if (!test_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags)) - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + mddev->ro = 0; + mddev->in_sync = 0; - if (mddev->suspended) - mddev_resume(mddev); - } + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + + if (mddev->suspended) + mddev_resume(mddev); } static struct target_type raid_target = { diff --git a/drivers/md/dm-round-robin.c b/drivers/md/dm-round-robin.c index 4ace1da..6c25213 100644 --- a/drivers/md/dm-round-robin.c +++ b/drivers/md/dm-round-robin.c @@ -210,14 +210,17 @@ static struct dm_path *rr_select_path(struct path_selector *ps, size_t nr_bytes) struct path_info *pi = NULL; struct dm_path *current_path = NULL; + local_irq_save(flags); current_path = *this_cpu_ptr(s->current_path); if (current_path) { percpu_counter_dec(&s->repeat_count); - if (percpu_counter_read_positive(&s->repeat_count) > 0) + if (percpu_counter_read_positive(&s->repeat_count) > 0) { + local_irq_restore(flags); return current_path; + } } - spin_lock_irqsave(&s->lock, flags); + spin_lock(&s->lock); if (!list_empty(&s->valid_paths)) { pi = list_entry(s->valid_paths.next, struct path_info, list); list_move_tail(&pi->list, &s->valid_paths); diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index 7ada5f1..3519ace 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -230,6 +230,11 @@ int cxl_pci_vphb_add(struct cxl_afu *afu) if (phb->bus == NULL) return -ENXIO; + /* Set release hook on root bus */ + pci_set_host_bridge_release(to_pci_host_bridge(phb->bus->bridge), + pcibios_free_controller_deferred, + (void *) phb); + /* Claim resources. This might need some rework as well depending * whether we are doing probe-only or not, like assigning unassigned * resources etc... @@ -256,7 +261,10 @@ void cxl_pci_vphb_remove(struct cxl_afu *afu) afu->phb = NULL; pci_remove_root_bus(phb->bus); - pcibios_free_controller(phb); + /* + * We don't free phb here - that's handled by + * pcibios_free_controller_deferred() + */ } static bool _cxl_pci_is_vphb_device(struct pci_controller *phb) diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 48a5dd7..2206d44 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) break; if (req_op(next) == REQ_OP_DISCARD || + req_op(next) == REQ_OP_SECURE_ERASE || req_op(next) == REQ_OP_FLUSH) break; @@ -2150,6 +2151,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) struct mmc_card *card = md->queue.card; struct mmc_host *host = card->host; unsigned long flags; + bool req_is_special = mmc_req_is_special(req); if (req && !mq->mqrq_prev->req) /* claim host only for the first request */ @@ -2190,8 +2192,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) } out: - if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || - mmc_req_is_special(req)) + if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special) /* * Release host when there are no more requests * and after special request(discard, flush) is done. diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index bf14642..7080572 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests and discards. */ - if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) { + if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD && + req_op(req) != REQ_OP_SECURE_ERASE) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } @@ -64,6 +65,8 @@ static int mmc_queue_thread(void *d) spin_unlock_irq(q->queue_lock); if (req || mq->mqrq_prev->req) { + bool req_is_special = mmc_req_is_special(req); + set_current_state(TASK_RUNNING); mq->issue_fn(mq, req); cond_resched(); @@ -79,7 +82,7 @@ static int mmc_queue_thread(void *d) * has been finished. Do not assign it to previous * request. */ - if (mmc_req_is_special(req)) + if (req_is_special) mq->mqrq_cur->req = NULL; mq->mqrq_prev->brq.mrq.data = NULL; diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index d625311..fee5e12 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,7 +4,9 @@ static inline bool mmc_req_is_special(struct request *req) { return req && - (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD); + (req_op(req) == REQ_OP_FLUSH || + req_op(req) == REQ_OP_DISCARD || + req_op(req) == REQ_OP_SECURE_ERASE); } struct request; diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index c4c12d9..afe5668 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -145,8 +145,8 @@ static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val, \ static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \ u32 mask) \ { \ - intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \ priv->irq##which##_mask &= ~(mask); \ + intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \ } \ static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \ u32 mask) \ diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 750d01d..4e697ee 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2646,15 +2646,19 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return ret; } + /* Rate Control: disable ingress rate limiting. */ if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) || mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) || - mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) || mv88e6xxx_6320_family(chip)) { - /* Rate Control: disable ingress rate limiting. */ ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), PORT_RATE_CONTROL, 0x0001); if (ret) return ret; + } else if (mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip)) { + ret = _mv88e6xxx_reg_write(chip, REG_PORT(port), + PORT_RATE_CONTROL, 0x0000); + if (ret) + return ret; } /* Port Control 1: disable trunking, disable sending diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index c4d0026..d29a4f3 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1612,6 +1612,8 @@ static const struct pci_device_id alx_pci_tbl[] = { .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400), .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, + { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2500), + .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162), .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG }, { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) }, diff --git a/drivers/net/ethernet/atheros/alx/reg.h b/drivers/net/ethernet/atheros/alx/reg.h index 0959e68..1fc2d85 100644 --- a/drivers/net/ethernet/atheros/alx/reg.h +++ b/drivers/net/ethernet/atheros/alx/reg.h @@ -38,6 +38,7 @@ #define ALX_DEV_ID_AR8161 0x1091 #define ALX_DEV_ID_E2200 0xe091 #define ALX_DEV_ID_E2400 0xe0a1 +#define ALX_DEV_ID_E2500 0xe0b1 #define ALX_DEV_ID_AR8162 0x1090 #define ALX_DEV_ID_AR8171 0x10A1 #define ALX_DEV_ID_AR8172 0x10A0 diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 3bc0a04..c16ec3a 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -161,7 +161,7 @@ static int bgmac_probe(struct bcma_device *core) if (!bgmac_is_bcm4707_family(core) && !(ci->id == BCMA_CHIP_ID_BCM53573 && core->core_unit == 1)) { mii_bus = bcma_mdio_mii_register(core, bgmac->phyaddr); - if (!IS_ERR(mii_bus)) { + if (IS_ERR(mii_bus)) { err = PTR_ERR(mii_bus); goto err; } diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index db9c632..edf779f 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -185,7 +185,6 @@ #define NIC_QSET_SQ_0_7_DOOR (0x010838) #define NIC_QSET_SQ_0_7_STATUS (0x010840) #define NIC_QSET_SQ_0_7_DEBUG (0x010848) -#define NIC_QSET_SQ_0_7_CNM_CHG (0x010860) #define NIC_QSET_SQ_0_7_STAT_0_1 (0x010900) #define NIC_QSET_RBDR_0_1_CFG (0x010C00) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index d2d8ef2..ad4fddb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -382,7 +382,10 @@ static void nicvf_get_regs(struct net_device *dev, p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q); p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q); p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q); - p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q); + /* Padding, was NIC_QSET_SQ_0_7_CNM_CHG, which + * produces bus errors when read + */ + p[i++] = 0; p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q); reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3); p[i++] = nicvf_queue_reg_read(nic, reg_offset, q); diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index d20935d..4b4f5bc 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2922,17 +2922,25 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus, { unsigned int size = lstatus & BD_LENGTH_MASK; struct page *page = rxb->page; + bool last = !!(lstatus & BD_LFLAG(RXBD_LAST)); /* Remove the FCS from the packet length */ - if (likely(lstatus & BD_LFLAG(RXBD_LAST))) + if (last) size -= ETH_FCS_LEN; - if (likely(first)) + if (likely(first)) { skb_put(skb, size); - else - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - rxb->page_offset + RXBUF_ALIGNMENT, - size, GFAR_RXB_TRUESIZE); + } else { + /* the last fragments' length contains the full frame length */ + if (last) + size -= skb->len; + + /* in case the last fragment consisted only of the FCS */ + if (size > 0) + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rxb->page_offset + RXBUF_ALIGNMENT, + size, GFAR_RXB_TRUESIZE); + } /* try reuse page */ if (unlikely(page_count(page) != 1)) diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 373fd09..6e8a9c8 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -100,7 +100,8 @@ extern const char gfar_driver_version[]; #define DEFAULT_RX_LFC_THR 16 #define DEFAULT_LFC_PTVVAL 4 -#define GFAR_RXB_SIZE 1536 +/* prevent fragmenation by HW in DSA environments */ +#define GFAR_RXB_SIZE roundup(1536 + 8, 64) #define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define GFAR_RXB_TRUESIZE 2048 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index ff8b6a4..6ea8722 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -328,9 +328,10 @@ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb) static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb) { u32 port; - struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev; if (ppe_cb->ppe_common_cb) { + struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev; + port = ppe_cb->index; dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 5404b32..250db0b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -209,6 +209,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi) { struct i40e_client_instance *cdev; + int ret = 0; if (!vsi) return; @@ -221,7 +222,14 @@ void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi) "Cannot locate client instance open routine\n"); continue; } - cdev->client->ops->open(&cdev->lan_info, cdev->client); + if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state))) { + ret = cdev->client->ops->open(&cdev->lan_info, + cdev->client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state); + } } } mutex_unlock(&i40e_client_instance_mutex); @@ -432,12 +440,14 @@ struct i40e_vsi *i40e_vsi_lookup(struct i40e_pf *pf, * i40e_client_add_instance - add a client instance struct to the instance list * @pf: pointer to the board struct * @client: pointer to a client struct in the client list. + * @existing: if there was already an existing instance * - * Returns cdev ptr on success, NULL on failure + * Returns cdev ptr on success or if already exists, NULL on failure **/ static struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, - struct i40e_client *client) + struct i40e_client *client, + bool *existing) { struct i40e_client_instance *cdev; struct netdev_hw_addr *mac = NULL; @@ -446,7 +456,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, mutex_lock(&i40e_client_instance_mutex); list_for_each_entry(cdev, &i40e_client_instances, list) { if ((cdev->lan_info.pf == pf) && (cdev->client == client)) { - cdev = NULL; + *existing = true; goto out; } } @@ -530,6 +540,7 @@ void i40e_client_subtask(struct i40e_pf *pf) { struct i40e_client_instance *cdev; struct i40e_client *client; + bool existing = false; int ret = 0; if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED)) @@ -553,18 +564,25 @@ void i40e_client_subtask(struct i40e_pf *pf) /* check if L2 VSI is up, if not we are not ready */ if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state)) continue; + } else { + dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n", + client->name); } /* Add the client instance to the instance list */ - cdev = i40e_client_add_instance(pf, client); + cdev = i40e_client_add_instance(pf, client, &existing); if (!cdev) continue; - /* Also up the ref_cnt of no. of instances of this client */ - atomic_inc(&client->ref_cnt); - dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n", - client->name, pf->hw.pf_id, - pf->hw.bus.device, pf->hw.bus.func); + if (!existing) { + /* Also up the ref_cnt for no. of instances of this + * client. + */ + atomic_inc(&client->ref_cnt); + dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n", + client->name, pf->hw.pf_id, + pf->hw.bus.device, pf->hw.bus.func); + } mutex_lock(&i40e_client_instance_mutex); /* Send an Open request to the client */ @@ -616,7 +634,8 @@ int i40e_lan_add_device(struct i40e_pf *pf) pf->hw.pf_id, pf->hw.bus.device, pf->hw.bus.func); /* Since in some cases register may have happened before a device gets - * added, we can schedule a subtask to go initiate the clients. + * added, we can schedule a subtask to go initiate the clients if + * they can be launched at probe time. */ pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; i40e_service_event_schedule(pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f355c04..fcdea29 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5430,7 +5430,6 @@ int i40e_open(struct net_device *netdev) wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16); udp_tunnel_get_rx_info(netdev); - i40e_notify_client_of_netdev_open(vsi); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 3095c24..77d3039 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -2959,8 +2959,10 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) } /* was that the last pool using this rar? */ - if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0) + if (mpsar_lo == 0 && mpsar_hi == 0 && + rar != 0 && rar != hw->mac.san_mac_rar_index) hw->mac.ops.clear_rar(hw, rar); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index bb89f04..1e639f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -143,13 +143,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) return cmd->cmd_buf + (idx << cmd->log_stride); } -static u8 xor8_buf(void *buf, int len) +static u8 xor8_buf(void *buf, size_t offset, int len) { u8 *ptr = buf; u8 sum = 0; int i; + int end = len + offset; - for (i = 0; i < len; i++) + for (i = offset; i < end; i++) sum ^= ptr[i]; return sum; @@ -157,41 +158,49 @@ static u8 xor8_buf(void *buf, int len) static int verify_block_sig(struct mlx5_cmd_prot_block *block) { - if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff) + size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0); + int xor_len = sizeof(*block) - sizeof(block->data) - 1; + + if (xor8_buf(block, rsvd0_off, xor_len) != 0xff) return -EINVAL; - if (xor8_buf(block, sizeof(*block)) != 0xff) + if (xor8_buf(block, 0, sizeof(*block)) != 0xff) return -EINVAL; return 0; } -static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token, - int csum) +static void calc_block_sig(struct mlx5_cmd_prot_block *block) { - block->token = token; - if (csum) { - block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) - - sizeof(block->data) - 2); - block->sig = ~xor8_buf(block, sizeof(*block) - 1); - } + int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2; + size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0); + + block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len); + block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1); } -static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum) +static void calc_chain_sig(struct mlx5_cmd_msg *msg) { struct mlx5_cmd_mailbox *next = msg->next; - - while (next) { - calc_block_sig(next->buf, token, csum); + int size = msg->len; + int blen = size - min_t(int, sizeof(msg->first.data), size); + int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) + / MLX5_CMD_DATA_BLOCK_SIZE; + int i = 0; + + for (i = 0; i < n && next; i++) { + calc_block_sig(next->buf); next = next->next; } } static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) { - ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay)); - calc_chain_sig(ent->in, ent->token, csum); - calc_chain_sig(ent->out, ent->token, csum); + ent->lay->sig = ~xor8_buf(ent->lay, 0, sizeof(*ent->lay)); + if (csum) { + calc_chain_sig(ent->in); + calc_chain_sig(ent->out); + } } static void poll_timeout(struct mlx5_cmd_work_ent *ent) @@ -222,12 +231,17 @@ static int verify_signature(struct mlx5_cmd_work_ent *ent) struct mlx5_cmd_mailbox *next = ent->out->next; int err; u8 sig; + int size = ent->out->len; + int blen = size - min_t(int, sizeof(ent->out->first.data), size); + int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) + / MLX5_CMD_DATA_BLOCK_SIZE; + int i = 0; - sig = xor8_buf(ent->lay, sizeof(*ent->lay)); + sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay)); if (sig != 0xff) return -EINVAL; - while (next) { + for (i = 0; i < n && next; i++) { err = verify_block_sig(next->buf); if (err) return err; @@ -783,7 +797,6 @@ static void cmd_work_handler(struct work_struct *work) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - ent->token = alloc_token(cmd); cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; @@ -883,7 +896,8 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, struct mlx5_cmd_msg *out, void *uout, int uout_size, mlx5_cmd_cbk_t callback, - void *context, int page_queue, u8 *status) + void *context, int page_queue, u8 *status, + u8 token) { struct mlx5_cmd *cmd = &dev->cmd; struct mlx5_cmd_work_ent *ent; @@ -900,6 +914,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (IS_ERR(ent)) return PTR_ERR(ent); + ent->token = token; + if (!callback) init_completion(&ent->done); @@ -971,7 +987,8 @@ static const struct file_operations fops = { .write = dbg_write, }; -static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size) +static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size, + u8 token) { struct mlx5_cmd_prot_block *block; struct mlx5_cmd_mailbox *next; @@ -997,6 +1014,7 @@ static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size) memcpy(block->data, from, copy); from += copy; size -= copy; + block->token = token; next = next->next; } @@ -1066,7 +1084,8 @@ static void free_cmd_box(struct mlx5_core_dev *dev, } static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, - gfp_t flags, int size) + gfp_t flags, int size, + u8 token) { struct mlx5_cmd_mailbox *tmp, *head = NULL; struct mlx5_cmd_prot_block *block; @@ -1095,6 +1114,7 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, tmp->next = head; block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0); block->block_num = cpu_to_be32(n - i - 1); + block->token = token; head = tmp; } msg->next = head; @@ -1463,7 +1483,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size, } if (IS_ERR(msg)) - msg = mlx5_alloc_cmd_msg(dev, gfp, in_size); + msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0); return msg; } @@ -1483,6 +1503,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int err; u8 status = 0; u32 drv_synd; + u8 token; if (pci_channel_offline(dev->pdev) || dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { @@ -1503,20 +1524,22 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, return err; } - err = mlx5_copy_to_msg(inb, in, in_size); + token = alloc_token(&dev->cmd); + + err = mlx5_copy_to_msg(inb, in, in_size, token); if (err) { mlx5_core_warn(dev, "err %d\n", err); goto out_in; } - outb = mlx5_alloc_cmd_msg(dev, gfp, out_size); + outb = mlx5_alloc_cmd_msg(dev, gfp, out_size, token); if (IS_ERR(outb)) { err = PTR_ERR(outb); goto out_in; } err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context, - pages_queue, &status); + pages_queue, &status, token); if (err) goto out_out; @@ -1587,7 +1610,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev) INIT_LIST_HEAD(&cmd->cache.med.head); for (i = 0; i < NUM_LONG_LISTS; i++) { - msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE); + msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0); if (IS_ERR(msg)) { err = PTR_ERR(msg); goto ex_err; @@ -1597,7 +1620,7 @@ static int create_msg_cache(struct mlx5_core_dev *dev) } for (i = 0; i < NUM_MED_LISTS; i++) { - msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE); + msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0); if (IS_ERR(msg)) { err = PTR_ERR(msg); goto ex_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 61902b1..9699560 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -73,8 +73,12 @@ #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) #define MLX5_MPWRQ_STRIDES_PER_PAGE (MLX5_MPWRQ_NUM_STRIDES >> \ MLX5_MPWRQ_WQE_PAGE_ORDER) -#define MLX5_CHANNEL_MAX_NUM_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8) * \ - BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW)) + +#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) +#define MLX5E_REQUIRED_MTTS(rqs, wqes)\ + (rqs * wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) +#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX) + #define MLX5_UMR_ALIGN (2048) #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128) @@ -219,9 +223,8 @@ struct mlx5e_tstamp { }; enum { - MLX5E_RQ_STATE_POST_WQES_ENABLE, + MLX5E_RQ_STATE_FLUSH, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, - MLX5E_RQ_STATE_FLUSH_TIMEOUT, MLX5E_RQ_STATE_AM, }; @@ -304,6 +307,7 @@ struct mlx5e_rq { unsigned long state; int ix; + u32 mpwqe_mtt_offset; struct mlx5e_rx_am am; /* Adaptive Moderation */ @@ -365,9 +369,8 @@ struct mlx5e_sq_dma { }; enum { - MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, + MLX5E_SQ_STATE_FLUSH, MLX5E_SQ_STATE_BF_ENABLE, - MLX5E_SQ_STATE_TX_TIMEOUT, }; struct mlx5e_ico_wqe_info { @@ -664,7 +667,6 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget); bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); void mlx5e_free_tx_descs(struct mlx5e_sq *sq); -void mlx5e_free_rx_descs(struct mlx5e_rq *rq); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); @@ -780,11 +782,6 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) MLX5E_MAX_NUM_CHANNELS); } -static inline int mlx5e_get_mtt_octw(int npages) -{ - return ALIGN(npages, 8) / 2; -} - extern const struct ethtool_ops mlx5e_ethtool_ops; #ifdef CONFIG_MLX5_CORE_EN_DCB extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 3247c3c..029e856 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -142,7 +142,7 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev) struct mlx5e_tir *tir; void *in; int inlen; - int err; + int err = 0; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = mlx5_vzalloc(inlen); @@ -154,10 +154,11 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev) list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen); if (err) - return err; + goto out; } +out: kvfree(in); - return 0; + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index caa9a3c..762af16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -127,29 +127,40 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) return mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw); } -static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets) +static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, + struct ieee_ets *ets) { int bw_sum = 0; int i; /* Validate Priority */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) + if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) { + netdev_err(netdev, + "Failed to validate ETS: priority value greater than max(%d)\n", + MLX5E_MAX_PRIORITY); return -EINVAL; + } } /* Validate Bandwidth Sum */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { - if (!ets->tc_tx_bw[i]) + if (!ets->tc_tx_bw[i]) { + netdev_err(netdev, + "Failed to validate ETS: BW 0 is illegal\n"); return -EINVAL; + } bw_sum += ets->tc_tx_bw[i]; } } - if (bw_sum != 0 && bw_sum != 100) + if (bw_sum != 0 && bw_sum != 100) { + netdev_err(netdev, + "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; + } return 0; } @@ -159,7 +170,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); int err; - err = mlx5e_dbcnl_validate_ets(ets); + err = mlx5e_dbcnl_validate_ets(netdev, ets); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 9561fca..d1cd156 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -352,15 +352,61 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, sq_stats_desc, j); } +static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type, + int num_wqe) +{ + int packets_per_wqe; + int stride_size; + int num_strides; + int wqe_size; + + if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + return num_wqe; + + stride_size = 1 << priv->params.mpwqe_log_stride_sz; + num_strides = 1 << priv->params.mpwqe_log_num_strides; + wqe_size = stride_size * num_strides; + + packets_per_wqe = wqe_size / + ALIGN(ETH_DATA_LEN, stride_size); + return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1)); +} + +static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type, + int num_packets) +{ + int packets_per_wqe; + int stride_size; + int num_strides; + int wqe_size; + int num_wqes; + + if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + return num_packets; + + stride_size = 1 << priv->params.mpwqe_log_stride_sz; + num_strides = 1 << priv->params.mpwqe_log_num_strides; + wqe_size = stride_size * num_strides; + + num_packets = (1 << order_base_2(num_packets)); + + packets_per_wqe = wqe_size / + ALIGN(ETH_DATA_LEN, stride_size); + num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe); + return 1 << (order_base_2(num_wqes)); +} + static void mlx5e_get_ringparam(struct net_device *dev, struct ethtool_ringparam *param) { struct mlx5e_priv *priv = netdev_priv(dev); int rq_wq_type = priv->params.rq_wq_type; - param->rx_max_pending = 1 << mlx5_max_log_rq_size(rq_wq_type); + param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << mlx5_max_log_rq_size(rq_wq_type)); param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE; - param->rx_pending = 1 << priv->params.log_rq_size; + param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << priv->params.log_rq_size); param->tx_pending = 1 << priv->params.log_sq_size; } @@ -370,9 +416,13 @@ static int mlx5e_set_ringparam(struct net_device *dev, struct mlx5e_priv *priv = netdev_priv(dev); bool was_opened; int rq_wq_type = priv->params.rq_wq_type; + u32 rx_pending_wqes; + u32 min_rq_size; + u32 max_rq_size; u16 min_rx_wqes; u8 log_rq_size; u8 log_sq_size; + u32 num_mtts; int err = 0; if (param->rx_jumbo_pending) { @@ -385,18 +435,36 @@ static int mlx5e_set_ringparam(struct net_device *dev, __func__); return -EINVAL; } - if (param->rx_pending < (1 << mlx5_min_log_rq_size(rq_wq_type))) { + + min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << mlx5_min_log_rq_size(rq_wq_type)); + max_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type, + 1 << mlx5_max_log_rq_size(rq_wq_type)); + rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type, + param->rx_pending); + + if (param->rx_pending < min_rq_size) { netdev_info(dev, "%s: rx_pending (%d) < min (%d)\n", __func__, param->rx_pending, - 1 << mlx5_min_log_rq_size(rq_wq_type)); + min_rq_size); return -EINVAL; } - if (param->rx_pending > (1 << mlx5_max_log_rq_size(rq_wq_type))) { + if (param->rx_pending > max_rq_size) { netdev_info(dev, "%s: rx_pending (%d) > max (%d)\n", __func__, param->rx_pending, - 1 << mlx5_max_log_rq_size(rq_wq_type)); + max_rq_size); return -EINVAL; } + + num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels, + rx_pending_wqes); + if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && + !MLX5E_VALID_NUM_MTTS(num_mtts)) { + netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n", + __func__, param->rx_pending); + return -EINVAL; + } + if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) { netdev_info(dev, "%s: tx_pending (%d) < min (%d)\n", __func__, param->tx_pending, @@ -410,9 +478,9 @@ static int mlx5e_set_ringparam(struct net_device *dev, return -EINVAL; } - log_rq_size = order_base_2(param->rx_pending); + log_rq_size = order_base_2(rx_pending_wqes); log_sq_size = order_base_2(param->tx_pending); - min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, param->rx_pending); + min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes); if (log_rq_size == priv->params.log_rq_size && log_sq_size == priv->params.log_sq_size && @@ -454,6 +522,7 @@ static int mlx5e_set_channels(struct net_device *dev, unsigned int count = ch->combined_count; bool arfs_enabled; bool was_opened; + u32 num_mtts; int err = 0; if (!count) { @@ -472,6 +541,14 @@ static int mlx5e_set_channels(struct net_device *dev, return -EINVAL; } + num_mtts = MLX5E_REQUIRED_MTTS(count, BIT(priv->params.log_rq_size)); + if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && + !MLX5E_VALID_NUM_MTTS(num_mtts)) { + netdev_info(dev, "%s: rx count (%d) request can't be satisfied, try to reduce.\n", + __func__, count); + return -EINVAL; + } + if (priv->params.num_channels == count) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index fa40414..03586ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -39,13 +39,6 @@ #include "eswitch.h" #include "vxlan.h" -enum { - MLX5_EN_QP_FLUSH_TIMEOUT_MS = 5000, - MLX5_EN_QP_FLUSH_MSLEEP_QUANT = 20, - MLX5_EN_QP_FLUSH_MAX_ITER = MLX5_EN_QP_FLUSH_TIMEOUT_MS / - MLX5_EN_QP_FLUSH_MSLEEP_QUANT, -}; - struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; struct mlx5_wq_param wq; @@ -162,6 +155,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->tx_queue_stopped += sq_stats->stopped; s->tx_queue_wake += sq_stats->wake; s->tx_queue_dropped += sq_stats->dropped; + s->tx_xmit_more += sq_stats->xmit_more; s->tx_csum_partial_inner += sq_stats->csum_partial_inner; tx_offload_none += sq_stats->csum_none; } @@ -337,6 +331,9 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, rq->alloc_wqe = mlx5e_alloc_rx_mpwqe; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; + rq->mpwqe_mtt_offset = c->ix * + MLX5E_REQUIRED_MTTS(1, BIT(priv->params.log_rq_size)); + rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz); rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides); rq->wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides; @@ -425,7 +422,6 @@ static int mlx5e_enable_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); - MLX5_SET(rqc, rqc, flush_in_error_en, 1); MLX5_SET(rqc, rqc, vsd, priv->params.vlan_strip_disable); MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); @@ -523,6 +519,27 @@ static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq) return -ETIMEDOUT; } +static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) +{ + struct mlx5_wq_ll *wq = &rq->wq; + struct mlx5e_rx_wqe *wqe; + __be16 wqe_ix_be; + u16 wqe_ix; + + /* UMR WQE (if in progress) is always at wq->head */ + if (test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) + mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]); + + while (!mlx5_wq_ll_is_empty(wq)) { + wqe_ix_be = *wq->tail_next; + wqe_ix = be16_to_cpu(wqe_ix_be); + wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix); + rq->dealloc_wqe(rq, wqe_ix); + mlx5_wq_ll_pop(&rq->wq, wqe_ix_be, + &wqe->next.next_wqe_index); + } +} + static int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_rq_param *param, struct mlx5e_rq *rq) @@ -546,8 +563,6 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (param->am_enabled) set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); - set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); - sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_NOP; sq->ico_wqe_info[pi].num_wqebbs = 1; mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */ @@ -564,23 +579,8 @@ err_destroy_rq: static void mlx5e_close_rq(struct mlx5e_rq *rq) { - int tout = 0; - int err; - - clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state); + set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ - - err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR); - while (!mlx5_wq_ll_is_empty(&rq->wq) && !err && - tout++ < MLX5_EN_QP_FLUSH_MAX_ITER) - msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT); - - if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER) - set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state); - - /* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */ - napi_synchronize(&rq->channel->napi); - cancel_work_sync(&rq->am.work); mlx5e_disable_rq(rq); @@ -819,7 +819,6 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, goto err_disable_sq; if (sq->txq) { - set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); netdev_tx_reset_queue(sq->txq); netif_tx_start_queue(sq->txq); } @@ -843,38 +842,20 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_close_sq(struct mlx5e_sq *sq) { - int tout = 0; - int err; + set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + /* prevent netif_tx_wake_queue */ + napi_synchronize(&sq->channel->napi); if (sq->txq) { - clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state); - /* prevent netif_tx_wake_queue */ - napi_synchronize(&sq->channel->napi); netif_tx_disable_queue(sq->txq); - /* ensure hw is notified of all pending wqes */ + /* last doorbell out, godspeed .. */ if (mlx5e_sq_has_room_for(sq, 1)) mlx5e_send_nop(sq, true); - - err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, - MLX5_SQC_STATE_ERR, false, 0); - if (err) - set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); - } - - /* wait till sq is empty, unless a TX timeout occurred on this SQ */ - while (sq->cc != sq->pc && - !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) { - msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT); - if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER) - set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); } - /* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */ - napi_synchronize(&sq->channel->napi); - - mlx5e_free_tx_descs(sq); mlx5e_disable_sq(sq); + mlx5e_free_tx_descs(sq); mlx5e_destroy_sq(sq); } @@ -1824,10 +1805,6 @@ int mlx5e_open_locked(struct net_device *netdev) netif_set_real_num_tx_queues(netdev, num_txqs); netif_set_real_num_rx_queues(netdev, priv->params.num_channels); - err = mlx5e_set_dev_port_mtu(netdev); - if (err) - goto err_clear_state_opened_flag; - err = mlx5e_open_channels(priv); if (err) { netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n", @@ -2572,6 +2549,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) u16 max_mtu; u16 min_mtu; int err = 0; + bool reset; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); @@ -2587,13 +2565,18 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) mutex_lock(&priv->state_lock); + reset = !priv->params.lro_en && + (priv->params.rq_wq_type != + MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ); + was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state); - if (was_opened) + if (was_opened && reset) mlx5e_close_locked(netdev); netdev->mtu = new_mtu; + mlx5e_set_dev_port_mtu(netdev); - if (was_opened) + if (was_opened && reset) err = mlx5e_open_locked(netdev); mutex_unlock(&priv->state_lock); @@ -2793,7 +2776,7 @@ static void mlx5e_tx_timeout(struct net_device *dev) if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) continue; sched_work = true; - set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state); + set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n", i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc); } @@ -3227,7 +3210,8 @@ static void mlx5e_destroy_q_counter(struct mlx5e_priv *priv) static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - u64 npages = priv->profile->max_nch(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS; + u64 npages = MLX5E_REQUIRED_MTTS(priv->profile->max_nch(mdev), + BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW)); int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; u32 *in; @@ -3239,6 +3223,8 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv) mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + npages = min_t(u32, ALIGN(U16_MAX, 4) * 2, npages); + MLX5_SET(mkc, mkc, free, 1); MLX5_SET(mkc, mkc, umr_en, 1); MLX5_SET(mkc, mkc, lw, 1); @@ -3249,7 +3235,7 @@ static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv) MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn); MLX5_SET64(mkc, mkc, len, npages << PAGE_SHIFT); MLX5_SET(mkc, mkc, translations_octword_size, - mlx5e_get_mtt_octw(npages)); + MLX5_MTT_OCTW(npages)); MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT); err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen); @@ -3385,6 +3371,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); if (MLX5_CAP_GEN(mdev, vport_group_manager)) { + mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id); rep.load = mlx5e_nic_rep_load; rep.unload = mlx5e_nic_rep_unload; rep.vport = 0; @@ -3464,6 +3451,8 @@ void *mlx5e_create_netdev(struct mlx5_core_dev *mdev, mlx5e_init_l2_addr(priv); + mlx5e_set_dev_port_mtu(netdev); + err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); @@ -3502,16 +3491,20 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev) struct mlx5_eswitch *esw = mdev->priv.eswitch; int total_vfs = MLX5_TOTAL_VPORTS(mdev); int vport; + u8 mac[ETH_ALEN]; if (!MLX5_CAP_GEN(mdev, vport_group_manager)) return; + mlx5_query_nic_vport_mac_address(mdev, 0, mac); + for (vport = 1; vport < total_vfs; vport++) { struct mlx5_eswitch_rep rep; rep.load = mlx5e_vport_rep_load; rep.unload = mlx5e_vport_rep_unload; rep.vport = vport; + ether_addr_copy(rep.hw_id, mac); mlx5_eswitch_register_vport_rep(esw, &rep); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 681c12c..29db473 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -135,17 +135,16 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = { int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr) { struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_eswitch_rep *rep = priv->ppriv; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - u8 mac[ETH_ALEN]; if (esw->mode == SRIOV_NONE) return -EOPNOTSUPP; switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - mlx5_query_nic_vport_mac_address(priv->mdev, 0, mac); attr->u.ppid.id_len = ETH_ALEN; - memcpy(&attr->u.ppid.id, &mac, ETH_ALEN); + ether_addr_copy(attr->u.ppid.id, rep->hw_id); break; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 9f2a16a..b6f8ebb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -324,9 +324,9 @@ mlx5e_copy_skb_header_fragmented_mpwqe(struct device *pdev, } } -static u16 mlx5e_get_wqe_mtt_offset(u16 rq_ix, u16 wqe_ix) +static u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix) { - return rq_ix * MLX5_CHANNEL_MAX_NUM_MTTS + + return rq->mpwqe_mtt_offset + wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8); } @@ -340,7 +340,7 @@ static void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, struct mlx5_wqe_data_seg *dseg = &wqe->data; struct mlx5e_mpw_info *wi = &rq->wqe_info[ix]; u8 ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS); - u16 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix); + u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix); memset(wqe, 0, sizeof(*wqe)); cseg->opmod_idx_opcode = @@ -353,9 +353,9 @@ static void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN; ucseg->klm_octowords = - cpu_to_be16(mlx5e_get_mtt_octw(MLX5_MPWRQ_PAGES_PER_WQE)); + cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE)); ucseg->bsf_octowords = - cpu_to_be16(mlx5e_get_mtt_octw(umr_wqe_mtt_offset)); + cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset)); ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); dseg->lkey = sq->mkey_be; @@ -423,7 +423,7 @@ static int mlx5e_alloc_rx_fragmented_mpwqe(struct mlx5e_rq *rq, { struct mlx5e_mpw_info *wi = &rq->wqe_info[ix]; int mtt_sz = mlx5e_get_wqe_mtt_sz(); - u32 dma_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix) << PAGE_SHIFT; + u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT; int i; wi->umr.dma_info = kmalloc(sizeof(*wi->umr.dma_info) * @@ -506,6 +506,12 @@ void mlx5e_post_rx_fragmented_mpwqe(struct mlx5e_rq *rq) struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); + + if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) { + mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]); + return; + } + mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index)); rq->stats.mpwqe_frag++; @@ -595,26 +601,9 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) wi->free_wqe(rq, wi); } -void mlx5e_free_rx_descs(struct mlx5e_rq *rq) -{ - struct mlx5_wq_ll *wq = &rq->wq; - struct mlx5e_rx_wqe *wqe; - __be16 wqe_ix_be; - u16 wqe_ix; - - while (!mlx5_wq_ll_is_empty(wq)) { - wqe_ix_be = *wq->tail_next; - wqe_ix = be16_to_cpu(wqe_ix_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix); - rq->dealloc_wqe(rq, wqe_ix); - mlx5_wq_ll_pop(&rq->wq, wqe_ix_be, - &wqe->next.next_wqe_index); - } -} - #define RQ_CANNOT_POST(rq) \ - (!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \ - test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) + (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \ + test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) { @@ -916,7 +905,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); int work_done = 0; - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state))) + if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) return 0; if (cq->decmprs_left) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 7b9d8a9..499487c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -70,6 +70,7 @@ struct mlx5e_sw_stats { u64 tx_queue_stopped; u64 tx_queue_wake; u64 tx_queue_dropped; + u64 tx_xmit_more; u64 rx_wqe_err; u64 rx_mpwqe_filler; u64 rx_mpwqe_frag; @@ -101,6 +102,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_frag) }, @@ -298,6 +300,7 @@ struct mlx5e_sq_stats { /* commonly accessed in data path */ u64 packets; u64 bytes; + u64 xmit_more; u64 tso_packets; u64 tso_bytes; u64 tso_inner_packets; @@ -324,6 +327,7 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) }, }; #define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dc8b1cb..22cfc4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -170,7 +170,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_dissector_key_control *key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, + FLOW_DISSECTOR_KEY_CONTROL, f->key); addr_type = key->addr_type; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index e073bf59..988eca9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -375,6 +375,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) sq->stats.packets++; sq->stats.bytes += num_bytes; + sq->stats.xmit_more += skb->xmit_more; return NETDEV_TX_OK; dma_unmap_wqe_err: @@ -394,35 +395,6 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) return mlx5e_sq_xmit(sq, skb); } -void mlx5e_free_tx_descs(struct mlx5e_sq *sq) -{ - struct mlx5e_tx_wqe_info *wi; - struct sk_buff *skb; - u16 ci; - int i; - - while (sq->cc != sq->pc) { - ci = sq->cc & sq->wq.sz_m1; - skb = sq->skb[ci]; - wi = &sq->wqe_info[ci]; - - if (!skb) { /* nop */ - sq->cc++; - continue; - } - - for (i = 0; i < wi->num_dma; i++) { - struct mlx5e_sq_dma *dma = - mlx5e_dma_get(sq, sq->dma_fifo_cc++); - - mlx5e_tx_dma_unmap(sq->pdev, dma); - } - - dev_kfree_skb_any(skb); - sq->cc += wi->num_wqebbs; - } -} - bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq *sq; @@ -434,7 +406,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state))) + if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) return false; npkts = 0; @@ -512,11 +484,39 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) netdev_tx_completed_queue(sq->txq, npkts, nbytes); if (netif_tx_queue_stopped(sq->txq) && - mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM) && - likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) { - netif_tx_wake_queue(sq->txq); - sq->stats.wake++; + mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) { + netif_tx_wake_queue(sq->txq); + sq->stats.wake++; } return (i == MLX5E_TX_CQ_POLL_BUDGET); } + +void mlx5e_free_tx_descs(struct mlx5e_sq *sq) +{ + struct mlx5e_tx_wqe_info *wi; + struct sk_buff *skb; + u16 ci; + int i; + + while (sq->cc != sq->pc) { + ci = sq->cc & sq->wq.sz_m1; + skb = sq->skb[ci]; + wi = &sq->wqe_info[ci]; + + if (!skb) { /* nop */ + sq->cc++; + continue; + } + + for (i = 0; i < wi->num_dma; i++) { + struct mlx5e_sq_dma *dma = + mlx5e_dma_get(sq, sq->dma_fifo_cc++); + + mlx5e_tx_dma_unmap(sq->pdev, dma); + } + + dev_kfree_skb_any(skb); + sq->cc += wi->num_wqebbs; + } +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 64ae2e8..9bf33bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -51,16 +51,18 @@ struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq) static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) { + struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq); struct mlx5_wq_cyc *wq; struct mlx5_cqe64 *cqe; - struct mlx5e_sq *sq; u16 sqcc; + if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + return; + cqe = mlx5e_get_cqe(cq); if (likely(!cqe)) return; - sq = container_of(cq, struct mlx5e_sq, cq); wq = &sq->wq; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 7c49359..1014305 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1421,7 +1421,8 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num); - if (vport_num) { /* Only VFs need ACLs for VST and spoofchk filtering */ + /* Only VFs need ACLs for VST and spoofchk filtering */ + if (vport_num && esw->mode == SRIOV_LEGACY) { esw_vport_ingress_config(esw, vport); esw_vport_egress_config(esw, vport); } @@ -1472,7 +1473,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) */ esw_vport_change_handle_locked(vport); vport->enabled_events = 0; - if (vport_num) { + if (vport_num && esw->mode == SRIOV_LEGACY) { esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); } @@ -1737,7 +1738,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, vport, err); mutex_lock(&esw->state_lock); - if (evport->enabled) + if (evport->enabled && esw->mode == SRIOV_LEGACY) err = esw_vport_ingress_config(esw, evport); mutex_unlock(&esw->state_lock); return err; @@ -1809,7 +1810,7 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); evport->vlan = vlan; evport->qos = qos; - if (evport->enabled) { + if (evport->enabled && esw->mode == SRIOV_LEGACY) { err = esw_vport_ingress_config(esw, evport); if (err) goto out; @@ -1838,10 +1839,11 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); pschk = evport->spoofchk; evport->spoofchk = spoofchk; - if (evport->enabled) + if (evport->enabled && esw->mode == SRIOV_LEGACY) { err = esw_vport_ingress_config(esw, evport); - if (err) - evport->spoofchk = pschk; + if (err) + evport->spoofchk = pschk; + } mutex_unlock(&esw->state_lock); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index c0b0560..a961409 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -174,6 +174,7 @@ struct mlx5_eswitch_rep { void *priv_data; struct list_head vport_sqs_list; bool valid; + u8 hw_id[ETH_ALEN]; }; struct mlx5_esw_offload { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index a357e8e..3dc83a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -113,7 +113,7 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport_num = vport; - flow_rule = mlx5_add_flow_rule(esw->fdb_table.fdb, spec, + flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, 0, &dest); if (IS_ERR(flow_rule)) @@ -535,7 +535,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports) esw_destroy_offloads_fdb_table(esw); } -static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) +static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) { switch (mode) { case DEVLINK_ESWITCH_MODE_LEGACY: @@ -551,6 +551,22 @@ static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) return 0; } +static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode) +{ + switch (mlx5_mode) { + case SRIOV_LEGACY: + *mode = DEVLINK_ESWITCH_MODE_LEGACY; + break; + case SRIOV_OFFLOADS: + *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; + break; + default: + return -EINVAL; + } + + return 0; +} + int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) { struct mlx5_core_dev *dev; @@ -566,7 +582,7 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) if (cur_mlx5_mode == SRIOV_NONE) return -EOPNOTSUPP; - if (mlx5_esw_mode_from_devlink(mode, &mlx5_mode)) + if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; if (cur_mlx5_mode == mlx5_mode) @@ -592,9 +608,7 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) if (dev->priv.eswitch->mode == SRIOV_NONE) return -EOPNOTSUPP; - *mode = dev->priv.eswitch->mode; - - return 0; + return esw_mode_to_devlink(dev->priv.eswitch->mode, mode); } void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f5571a5..5da2cc8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -80,7 +80,7 @@ LEFTOVERS_NUM_PRIOS) #define ETHTOOL_PRIO_NUM_LEVELS 1 -#define ETHTOOL_NUM_PRIOS 10 +#define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) /* Vlan, mac, ttc, aRFS */ #define KERNEL_NIC_PRIO_NUM_LEVELS 4 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index c2877e9..3a9195b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -126,12 +126,21 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, for (node = &first->node; node; node = rb_next(node)) { struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node); struct mlx5_fc_cache *c = &counter->cache; + u64 packets; + u64 bytes; if (counter->id > last_id) break; mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &c->packets, &c->bytes); + counter->id, &packets, &bytes); + + if (c->packets == packets) + continue; + + c->packets = packets; + c->bytes = bytes; + c->lastuse = jiffies; } out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 28e3ce6..c132ef1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1417,36 +1417,12 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, dev_info(&pdev->dev, "%s was called\n", __func__); mlx5_enter_error_state(dev); mlx5_unload_one(dev, priv); + pci_save_state(pdev); mlx5_pci_disable_device(dev); return state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; } -static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) -{ - struct mlx5_core_dev *dev = pci_get_drvdata(pdev); - int err = 0; - - dev_info(&pdev->dev, "%s was called\n", __func__); - - err = mlx5_pci_enable_device(dev); - if (err) { - dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n" - , __func__, err); - return PCI_ERS_RESULT_DISCONNECT; - } - pci_set_master(pdev); - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; -} - -void mlx5_disable_device(struct mlx5_core_dev *dev) -{ - mlx5_pci_err_detected(dev->pdev, 0); -} - /* wait for the device to show vital signs by waiting * for the health counter to start counting. */ @@ -1474,21 +1450,44 @@ static int wait_vital(struct pci_dev *pdev) return -ETIMEDOUT; } -static void mlx5_pci_resume(struct pci_dev *pdev) +static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); - struct mlx5_priv *priv = &dev->priv; int err; dev_info(&pdev->dev, "%s was called\n", __func__); - pci_save_state(pdev); - err = wait_vital(pdev); + err = mlx5_pci_enable_device(dev); if (err) { + dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n" + , __func__, err); + return PCI_ERS_RESULT_DISCONNECT; + } + + pci_set_master(pdev); + pci_restore_state(pdev); + + if (wait_vital(pdev)) { dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__); - return; + return PCI_ERS_RESULT_DISCONNECT; } + return PCI_ERS_RESULT_RECOVERED; +} + +void mlx5_disable_device(struct mlx5_core_dev *dev) +{ + mlx5_pci_err_detected(dev->pdev, 0); +} + +static void mlx5_pci_resume(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; + int err; + + dev_info(&pdev->dev, "%s was called\n", __func__); + err = mlx5_load_one(dev, priv); if (err) dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n" diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h index f33b997..af371a8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/port.h +++ b/drivers/net/ethernet/mellanox/mlxsw/port.h @@ -56,6 +56,7 @@ #define MLXSW_PORT_PHY_BITS_MASK (MLXSW_PORT_MAX_PHY_PORTS - 1) #define MLXSW_PORT_CPU_PORT 0x0 +#define MLXSW_PORT_ROUTER_PORT (MLXSW_PORT_MAX_PHY_PORTS + 2) #define MLXSW_PORT_DONT_CARE (MLXSW_PORT_MAX_PORTS) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 8c9c124..6c6b726 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3248,6 +3248,39 @@ static struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fid_find(mlxsw_sp, fid); } +static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID : + MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST; +} + +static u16 mlxsw_sp_flood_table_index_get(u16 fid) +{ + return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid; +} + +static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid, + bool set) +{ + enum mlxsw_flood_table_type table_type; + char *sftr_pl; + u16 index; + int err; + + sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); + if (!sftr_pl) + return -ENOMEM; + + table_type = mlxsw_sp_flood_table_type_get(fid); + index = mlxsw_sp_flood_table_index_get(fid); + mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, index, table_type, + 1, MLXSW_PORT_ROUTER_PORT, set); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl); + + kfree(sftr_pl); + return err; +} + static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid) { if (mlxsw_sp_fid_is_vfid(fid)) @@ -3284,10 +3317,14 @@ static int mlxsw_sp_rif_bridge_create(struct mlxsw_sp *mlxsw_sp, if (rif == MLXSW_SP_RIF_MAX) return -ERANGE; - err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true); if (err) return err; + err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true); + if (err) + goto err_rif_bridge_op; + err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true); if (err) goto err_rif_fdb_op; @@ -3309,6 +3346,8 @@ err_rif_alloc: mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false); err_rif_fdb_op: mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); +err_rif_bridge_op: + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); return err; } @@ -3328,6 +3367,8 @@ void mlxsw_sp_rif_bridge_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false); + mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false); + netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 237418a..953b214 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -717,22 +717,18 @@ int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port, u8 local_port = mlxsw_sp_port->local_port; u8 pg_buff = tc_index; enum mlxsw_reg_sbxx_dir dir = pool_type; - u8 pool = pool_index; + u8 pool = pool_get(pool_index); u32 max_buff; int err; + if (dir != dir_get(pool_index)) + return -EINVAL; + err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir, threshold, &max_buff); if (err) return err; - if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS) { - if (pool < MLXSW_SP_SB_POOL_COUNT) - return -EINVAL; - pool -= MLXSW_SP_SB_POOL_COUNT; - } else if (pool >= MLXSW_SP_SB_POOL_COUNT) { - return -EINVAL; - } return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, dir, 0, max_buff, pool); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 90bb93b..917ddd1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -657,7 +657,7 @@ int mlxsw_sp_router_neigh_construct(struct net_device *dev, return 0; } - r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); if (WARN_ON(!r)) return -EINVAL; diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 4d4ecba..8e13ec8 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -475,14 +475,6 @@ static void __lpc_get_mac(struct netdata_local *pldat, u8 *mac) mac[5] = tmp >> 8; } -static void __lpc_eth_clock_enable(struct netdata_local *pldat, bool enable) -{ - if (enable) - clk_prepare_enable(pldat->clk); - else - clk_disable_unprepare(pldat->clk); -} - static void __lpc_params_setup(struct netdata_local *pldat) { u32 tmp; @@ -1056,7 +1048,7 @@ static int lpc_eth_close(struct net_device *ndev) writel(0, LPC_ENET_MAC2(pldat->net_base)); spin_unlock_irqrestore(&pldat->lock, flags); - __lpc_eth_clock_enable(pldat, false); + clk_disable_unprepare(pldat->clk); return 0; } @@ -1197,11 +1189,14 @@ static int lpc_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) static int lpc_eth_open(struct net_device *ndev) { struct netdata_local *pldat = netdev_priv(ndev); + int ret; if (netif_msg_ifup(pldat)) dev_dbg(&pldat->pdev->dev, "enabling %s\n", ndev->name); - __lpc_eth_clock_enable(pldat, true); + ret = clk_prepare_enable(pldat->clk); + if (ret) + return ret; /* Suspended PHY makes LPC ethernet core block, so resume now */ phy_resume(ndev->phydev); @@ -1320,7 +1315,9 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) } /* Enable network clock */ - __lpc_eth_clock_enable(pldat, true); + ret = clk_prepare_enable(pldat->clk); + if (ret) + goto err_out_clk_put; /* Map IO space */ pldat->net_base = ioremap(res->start, resource_size(res)); @@ -1454,6 +1451,7 @@ err_out_iounmap: iounmap(pldat->net_base); err_out_disable_clocks: clk_disable_unprepare(pldat->clk); +err_out_clk_put: clk_put(pldat->clk); err_out_free_dev: free_netdev(ndev); diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 9ba7a7e..2d67469 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -563,9 +563,18 @@ struct qed_dev { static inline u8 qed_concrete_to_sw_fid(struct qed_dev *cdev, u32 concrete_fid) { + u8 vfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_VFID); u8 pfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_PFID); + u8 vf_valid = GET_FIELD(concrete_fid, + PXP_CONCRETE_FID_VFVALID); + u8 sw_fid; - return pfid; + if (vf_valid) + sw_fid = vfid + MAX_NUM_PFS; + else + sw_fid = pfid; + + return sw_fid; } #define PURE_LB_TC 8 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 4056219..b4a56e6 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -722,11 +722,14 @@ static netdev_tx_t qede_start_xmit(struct sk_buff *skb, txq->tx_db.data.bd_prod = cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl)); - if (!skb->xmit_more || netif_tx_queue_stopped(netdev_txq)) + if (!skb->xmit_more || netif_xmit_stopped(netdev_txq)) qede_update_tx_producer(txq); if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl) < (MAX_SKB_FRAGS + 1))) { + if (skb->xmit_more) + qede_update_tx_producer(txq); + netif_tx_stop_queue(netdev_txq); txq->stopped_cnt++; DP_VERBOSE(edev, NETIF_MSG_TX_QUEUED, diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index deae10d..5297bf7 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -467,8 +467,8 @@ static int cp_rx_poll(struct napi_struct *napi, int budget) unsigned int rx_tail = cp->rx_tail; int rx; -rx_status_loop: rx = 0; +rx_status_loop: cpw16(IntrStatus, cp_rx_intr_mask); while (rx < budget) { diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 6fe1d0b..00279da 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1616,13 +1616,14 @@ static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask) } #if BITS_PER_LONG == 64 + BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 2); mask[0] = raw_mask[0]; mask[1] = raw_mask[1]; #else + BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 3); mask[0] = raw_mask[0] & 0xffffffff; mask[1] = raw_mask[0] >> 32; mask[2] = raw_mask[1] & 0xffffffff; - mask[3] = raw_mask[1] >> 32; #endif } diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 726b80f..503a3b6 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2275,6 +2275,13 @@ static int smc_drv_probe(struct platform_device *pdev) if (pd) { memcpy(&lp->cfg, pd, sizeof(lp->cfg)); lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags); + + if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) { + dev_err(&pdev->dev, + "at least one of 8-bit or 16-bit access support is required.\n"); + ret = -ENXIO; + goto out_free_netdev; + } } #if IS_BUILTIN(CONFIG_OF) diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 1a55c79..e17671c 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -37,6 +37,27 @@ #include <linux/smc91x.h> /* + * Any 16-bit access is performed with two 8-bit accesses if the hardware + * can't do it directly. Most registers are 16-bit so those are mandatory. + */ +#define SMC_outw_b(x, a, r) \ + do { \ + unsigned int __val16 = (x); \ + unsigned int __reg = (r); \ + SMC_outb(__val16, a, __reg); \ + SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT)); \ + } while (0) + +#define SMC_inw_b(a, r) \ + ({ \ + unsigned int __val16; \ + unsigned int __reg = r; \ + __val16 = SMC_inb(a, __reg); \ + __val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \ + __val16; \ + }) + +/* * Define your architecture specific bus configuration parameters here. */ @@ -55,10 +76,30 @@ #define SMC_IO_SHIFT (lp->io_shift) #define SMC_inb(a, r) readb((a) + (r)) -#define SMC_inw(a, r) readw((a) + (r)) +#define SMC_inw(a, r) \ + ({ \ + unsigned int __smc_r = r; \ + SMC_16BIT(lp) ? readw((a) + __smc_r) : \ + SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) : \ + ({ BUG(); 0; }); \ + }) + #define SMC_inl(a, r) readl((a) + (r)) #define SMC_outb(v, a, r) writeb(v, (a) + (r)) +#define SMC_outw(v, a, r) \ + do { \ + unsigned int __v = v, __smc_r = r; \ + if (SMC_16BIT(lp)) \ + __SMC_outw(__v, a, __smc_r); \ + else if (SMC_8BIT(lp)) \ + SMC_outw_b(__v, a, __smc_r); \ + else \ + BUG(); \ + } while (0) + #define SMC_outl(v, a, r) writel(v, (a) + (r)) +#define SMC_insb(a, r, p, l) readsb((a) + (r), p, l) +#define SMC_outsb(a, r, p, l) writesb((a) + (r), p, l) #define SMC_insw(a, r, p, l) readsw((a) + (r), p, l) #define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l) #define SMC_insl(a, r, p, l) readsl((a) + (r), p, l) @@ -66,7 +107,7 @@ #define SMC_IRQ_FLAGS (-1) /* from resource */ /* We actually can't write halfwords properly if not word aligned */ -static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg) +static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg) { if ((machine_is_mainstone() || machine_is_stargate2() || machine_is_pxa_idp()) && reg & 2) { @@ -416,24 +457,8 @@ smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, #if ! SMC_CAN_USE_16BIT -/* - * Any 16-bit access is performed with two 8-bit accesses if the hardware - * can't do it directly. Most registers are 16-bit so those are mandatory. - */ -#define SMC_outw(x, ioaddr, reg) \ - do { \ - unsigned int __val16 = (x); \ - SMC_outb( __val16, ioaddr, reg ); \ - SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\ - } while (0) -#define SMC_inw(ioaddr, reg) \ - ({ \ - unsigned int __val16; \ - __val16 = SMC_inb( ioaddr, reg ); \ - __val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \ - __val16; \ - }) - +#define SMC_outw(x, ioaddr, reg) SMC_outw_b(x, ioaddr, reg) +#define SMC_inw(ioaddr, reg) SMC_inw_b(ioaddr, reg) #define SMC_insw(a, r, p, l) BUG() #define SMC_outsw(a, r, p, l) BUG() diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 9f159a7..5a3941b 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -1622,13 +1622,7 @@ static void dwceqos_init_hw(struct net_local *lp) DWCEQOS_MMC_CTRL_RSTONRD); dwceqos_enable_mmc_interrupt(lp); - /* Enable Interrupts */ - dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, - DWCEQOS_DMA_CH0_IE_NIE | - DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE | - DWCEQOS_DMA_CH0_IE_AIE | - DWCEQOS_DMA_CH0_IE_FBEE); - + dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, 0); dwceqos_write(lp, REG_DWCEQOS_MAC_IE, 0); dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, DWCEQOS_MAC_CFG_IPC | @@ -1905,6 +1899,15 @@ static int dwceqos_open(struct net_device *ndev) netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); + /* Enable Interrupts -- do this only after we enable NAPI and the + * tasklet. + */ + dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, + DWCEQOS_DMA_CH0_IE_NIE | + DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE | + DWCEQOS_DMA_CH0_IE_AIE | + DWCEQOS_DMA_CH0_IE_FBEE); + return 0; } diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 7452b5f..7108c68 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1987,7 +1987,7 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if ((readl(nic->regs + FPGA_VER) & 0xFFF) >= 378) { err = pci_enable_msi(pdev); if (err) - pr_err("Can't eneble msi. error is %d\n", err); + pr_err("Can't enable msi. error is %d\n", err); else nic->irq_type = IRQ_MSI; } else diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 3cee84a..93dc10b 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1131,11 +1131,13 @@ static int xemaclite_of_probe(struct platform_device *ofdev) lp->rx_ping_pong = get_bool(ofdev, "xlnx,rx-ping-pong"); mac_address = of_get_mac_address(ofdev->dev.of_node); - if (mac_address) + if (mac_address) { /* Set the MAC address. */ memcpy(ndev->dev_addr, mac_address, ETH_ALEN); - else - dev_warn(dev, "No MAC address found\n"); + } else { + dev_warn(dev, "No MAC address found, using random\n"); + eth_hw_addr_random(ndev); + } /* Clear the Tx CSR's in case this is a restart */ __raw_writel(0, lp->base_addr + XEL_TSR_OFFSET); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 053e879..885ac9c 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -964,7 +964,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8873MLL, .phy_id_mask = MICREL_PHY_ID_MASK, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index c5dc2c36..c6f6683 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -722,8 +722,10 @@ phy_err: int phy_start_interrupts(struct phy_device *phydev) { atomic_set(&phydev->irq_disable, 0); - if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt", - phydev) < 0) { + if (request_irq(phydev->irq, phy_interrupt, + IRQF_SHARED, + "phy_interrupt", + phydev) < 0) { pr_warn("%s: Can't get IRQ %d (PHY)\n", phydev->mdio.bus->name, phydev->irq); phydev->irq = PHY_POLL; diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c index cdb19b3..b228bea 100644 --- a/drivers/net/team/team_mode_loadbalance.c +++ b/drivers/net/team/team_mode_loadbalance.c @@ -14,9 +14,23 @@ #include <linux/init.h> #include <linux/errno.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/filter.h> #include <linux/if_team.h> +static rx_handler_result_t lb_receive(struct team *team, struct team_port *port, + struct sk_buff *skb) +{ + if (unlikely(skb->protocol == htons(ETH_P_SLOW))) { + /* LACPDU packets should go to exact delivery */ + const unsigned char *dest = eth_hdr(skb)->h_dest; + + if (is_link_local_ether_addr(dest) && dest[5] == 0x02) + return RX_HANDLER_EXACT; + } + return RX_HANDLER_ANOTHER; +} + struct lb_priv; typedef struct team_port *lb_select_tx_port_func_t(struct team *, @@ -652,6 +666,7 @@ static const struct team_mode_ops lb_mode_ops = { .port_enter = lb_port_enter, .port_leave = lb_port_leave, .port_disabled = lb_port_disabled, + .receive = lb_receive, .transmit = lb_transmit, }; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index e249428..8093e39 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -888,11 +888,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; - if (skb->sk && sk_fullsock(skb->sk)) { - sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags, - &skb_shinfo(skb)->tx_flags); - sw_tx_timestamp(skb); - } + skb_tx_timestamp(skb); /* Orphan the skb - required as we might hang on to it * for indefinite time. diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c index 770212b..528b9c9 100644 --- a/drivers/net/usb/kaweth.c +++ b/drivers/net/usb/kaweth.c @@ -1009,6 +1009,7 @@ static int kaweth_probe( struct net_device *netdev; const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; int result = 0; + int rv = -EIO; dev_dbg(dev, "Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n", @@ -1029,6 +1030,7 @@ static int kaweth_probe( kaweth = netdev_priv(netdev); kaweth->dev = udev; kaweth->net = netdev; + kaweth->intf = intf; spin_lock_init(&kaweth->device_lock); init_waitqueue_head(&kaweth->term_wait); @@ -1048,6 +1050,10 @@ static int kaweth_probe( /* Download the firmware */ dev_info(dev, "Downloading firmware...\n"); kaweth->firmware_buf = (__u8 *)__get_free_page(GFP_KERNEL); + if (!kaweth->firmware_buf) { + rv = -ENOMEM; + goto err_free_netdev; + } if ((result = kaweth_download_firmware(kaweth, "kaweth/new_code.bin", 100, @@ -1139,8 +1145,6 @@ err_fw: dev_dbg(dev, "Initializing net device.\n"); - kaweth->intf = intf; - kaweth->tx_urb = usb_alloc_urb(0, GFP_KERNEL); if (!kaweth->tx_urb) goto err_free_netdev; @@ -1204,7 +1208,7 @@ err_only_tx: err_free_netdev: free_netdev(netdev); - return -EIO; + return rv; } /**************************************************************** diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index fc68dd4..2fd93b4 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -914,7 +914,9 @@ vmxnet3_copy_hdr(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, { struct Vmxnet3_TxDataDesc *tdd; - tdd = tq->data_ring.base + tq->tx_ring.next2fill; + tdd = (struct Vmxnet3_TxDataDesc *)((u8 *)tq->data_ring.base + + tq->tx_ring.next2fill * + tq->txdata_desc_size); memcpy(tdd->data, skb->data, ctx->copy_size); netdev_dbg(adapter->netdev, diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 74fc030..7dc37a0 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.9.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.a.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040900 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040a00 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7ff2e82..2feacc7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -81,10 +81,12 @@ EXPORT_SYMBOL_GPL(nvme_cancel_request); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { - enum nvme_ctrl_state old_state = ctrl->state; + enum nvme_ctrl_state old_state; bool changed = false; spin_lock_irq(&ctrl->lock); + + old_state = ctrl->state; switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { @@ -140,11 +142,12 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, default: break; } - spin_unlock_irq(&ctrl->lock); if (changed) ctrl->state = new_state; + spin_unlock_irq(&ctrl->lock); + return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); @@ -608,7 +611,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } @@ -628,7 +631,7 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } diff --git a/drivers/of/base.c b/drivers/of/base.c index 7792266..3ce6953 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1631,8 +1631,7 @@ static int __of_parse_phandle_with_args(const struct device_node *np, */ err: - if (it.node) - of_node_put(it.node); + of_node_put(it.node); return rc; } @@ -2343,20 +2342,13 @@ struct device_node *of_graph_get_endpoint_by_regs( const struct device_node *parent, int port_reg, int reg) { struct of_endpoint endpoint; - struct device_node *node, *prev_node = NULL; - - while (1) { - node = of_graph_get_next_endpoint(parent, prev_node); - of_node_put(prev_node); - if (!node) - break; + struct device_node *node = NULL; + for_each_endpoint_of_node(parent, node) { of_graph_parse_endpoint(node, &endpoint); if (((port_reg == -1) || (endpoint.port == port_reg)) && ((reg == -1) || (endpoint.id == reg))) return node; - - prev_node = node; } return NULL; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 55f1b83..085c638 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -517,7 +517,7 @@ static void *__unflatten_device_tree(const void *blob, pr_warning("End of tree marker overwritten: %08x\n", be32_to_cpup(mem + size)); - if (detached) { + if (detached && mynodes) { of_node_set_flag(*mynodes, OF_DETACHED); pr_debug("unflattened tree is detached\n"); } diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 89a71c6..a2e68f7 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -544,12 +544,15 @@ void __init of_irq_init(const struct of_device_id *matches) list_del(&desc->list); + of_node_set_flag(desc->dev, OF_POPULATED); + pr_debug("of_irq_init: init %s (%p), parent %p\n", desc->dev->full_name, desc->dev, desc->interrupt_parent); ret = desc->irq_init_cb(desc->dev, desc->interrupt_parent); if (ret) { + of_node_clear_flag(desc->dev, OF_POPULATED); kfree(desc); continue; } @@ -559,8 +562,6 @@ void __init of_irq_init(const struct of_device_id *matches) * its children can get processed in a subsequent pass. */ list_add_tail(&desc->list, &intc_parent_list); - - of_node_set_flag(desc->dev, OF_POPULATED); } /* Get the next pending parent that might have children */ diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 8aa1976..f39ccd5 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -497,6 +497,7 @@ int of_platform_default_populate(struct device_node *root, } EXPORT_SYMBOL_GPL(of_platform_default_populate); +#ifndef CONFIG_PPC static int __init of_platform_default_populate_init(void) { struct device_node *node; @@ -521,6 +522,7 @@ static int __init of_platform_default_populate_init(void) return 0; } arch_initcall_sync(of_platform_default_populate_init); +#endif static int of_platform_device_destroy(struct device *dev, void *data) { diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c index 5f4a2e0..add6623 100644 --- a/drivers/pci/host-bridge.c +++ b/drivers/pci/host-bridge.c @@ -44,6 +44,7 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge, bridge->release_fn = release_fn; bridge->release_data = release_data; } +EXPORT_SYMBOL_GPL(pci_set_host_bridge_release); void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region, struct resource *res) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index eafa613..98f1222 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1069,7 +1069,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, nvec = maxvec; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1105,7 +1105,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, **/ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { - return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY); + return __pci_enable_msi_range(dev, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msi_range); @@ -1120,7 +1120,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, return -ERANGE; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1160,8 +1160,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { - return __pci_enable_msix_range(dev, entries, minvec, maxvec, - PCI_IRQ_NOAFFINITY); + return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msix_range); @@ -1187,22 +1186,25 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { int vecs = -ENOSPC; - if (!(flags & PCI_IRQ_NOMSIX)) { + if (flags & PCI_IRQ_MSIX) { vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } - if (!(flags & PCI_IRQ_NOMSI)) { + if (flags & PCI_IRQ_MSI) { vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } /* use legacy irq if allowed */ - if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1) + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) { + pci_intx(dev, 1); return 1; + } + return vecs; } EXPORT_SYMBOL(pci_alloc_irq_vectors); diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c index f99b183..374a802 100644 --- a/drivers/platform/olpc/olpc-ec.c +++ b/drivers/platform/olpc/olpc-ec.c @@ -1,6 +1,8 @@ /* * Generic driver for the OLPC Embedded Controller. * + * Author: Andres Salomon <dilinger@queued.net> + * * Copyright (C) 2011-2012 One Laptop per Child Foundation. * * Licensed under the GPL v2 or later. @@ -12,7 +14,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/workqueue.h> -#include <linux/module.h> +#include <linux/init.h> #include <linux/list.h> #include <linux/olpc-ec.h> #include <asm/olpc.h> @@ -326,8 +328,4 @@ static int __init olpc_ec_init_module(void) { return platform_driver_register(&olpc_ec_plat_driver); } - arch_initcall(olpc_ec_init_module); - -MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c index 63b371d..91ae585 100644 --- a/drivers/platform/x86/intel_pmic_gpio.c +++ b/drivers/platform/x86/intel_pmic_gpio.c @@ -1,6 +1,8 @@ /* Moorestown PMIC GPIO (access through IPC) driver * Copyright (c) 2008 - 2009, Intel Corporation. * + * Author: Alek Du <alek.du@intel.com> + * * 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. @@ -21,7 +23,6 @@ #define pr_fmt(fmt) "%s: " fmt, __func__ -#include <linux/module.h> #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/delay.h> @@ -322,9 +323,4 @@ static int __init platform_pmic_gpio_init(void) { return platform_driver_register(&platform_pmic_gpio_driver); } - subsys_initcall(platform_pmic_gpio_init); - -MODULE_AUTHOR("Alek Du <alek.du@intel.com>"); -MODULE_DESCRIPTION("Intel Moorestown PMIC GPIO driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c index b381b371..5648b71 100644 --- a/drivers/scsi/aacraid/commctrl.c +++ b/drivers/scsi/aacraid/commctrl.c @@ -63,7 +63,7 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg) struct fib *fibptr; struct hw_fib * hw_fib = (struct hw_fib *)0; dma_addr_t hw_fib_pa = (dma_addr_t)0LL; - unsigned size; + unsigned int size, osize; int retval; if (dev->in_reset) { @@ -87,7 +87,8 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg) * will not overrun the buffer when we copy the memory. Return * an error if we would. */ - size = le16_to_cpu(kfib->header.Size) + sizeof(struct aac_fibhdr); + osize = size = le16_to_cpu(kfib->header.Size) + + sizeof(struct aac_fibhdr); if (size < le16_to_cpu(kfib->header.SenderSize)) size = le16_to_cpu(kfib->header.SenderSize); if (size > dev->max_fib_size) { @@ -118,6 +119,14 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg) goto cleanup; } + /* Sanity check the second copy */ + if ((osize != le16_to_cpu(kfib->header.Size) + + sizeof(struct aac_fibhdr)) + || (size < le16_to_cpu(kfib->header.SenderSize))) { + retval = -EINVAL; + goto cleanup; + } + if (kfib->header.Command == cpu_to_le16(TakeABreakPt)) { aac_adapter_interrupt(dev); /* diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index a569c65..dcf3653 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -2923,7 +2923,7 @@ static int fcoe_ctlr_vlan_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) mutex_unlock(&fip->ctlr_mutex); drop: - kfree(skb); + kfree_skb(skb); return rc; } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 2dab3dc..c1ed25a 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -5037,7 +5037,7 @@ static int megasas_init_fw(struct megasas_instance *instance) /* Find first memory bar */ bar_list = pci_select_bars(instance->pdev, IORESOURCE_MEM); instance->bar = find_first_bit(&bar_list, sizeof(unsigned long)); - if (pci_request_selected_regions(instance->pdev, instance->bar, + if (pci_request_selected_regions(instance->pdev, 1<<instance->bar, "megasas: LSI")) { dev_printk(KERN_DEBUG, &instance->pdev->dev, "IO memory region busy!\n"); return -EBUSY; @@ -5339,7 +5339,7 @@ fail_ready_state: iounmap(instance->reg_set); fail_ioremap: - pci_release_selected_regions(instance->pdev, instance->bar); + pci_release_selected_regions(instance->pdev, 1<<instance->bar); return -EINVAL; } @@ -5360,7 +5360,7 @@ static void megasas_release_mfi(struct megasas_instance *instance) iounmap(instance->reg_set); - pci_release_selected_regions(instance->pdev, instance->bar); + pci_release_selected_regions(instance->pdev, 1<<instance->bar); } /** diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index ec83754..52d8bbf 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -2603,7 +2603,7 @@ megasas_release_fusion(struct megasas_instance *instance) iounmap(instance->reg_set); - pci_release_selected_regions(instance->pdev, instance->bar); + pci_release_selected_regions(instance->pdev, 1<<instance->bar); } /** diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 751f13e..750f82c 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2188,6 +2188,17 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc) } else ioc->msix96_vector = 0; + if (ioc->is_warpdrive) { + ioc->reply_post_host_index[0] = (resource_size_t __iomem *) + &ioc->chip->ReplyPostHostIndex; + + for (i = 1; i < ioc->cpu_msix_table_sz; i++) + ioc->reply_post_host_index[i] = + (resource_size_t __iomem *) + ((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1) + * 4))); + } + list_for_each_entry(reply_q, &ioc->reply_queue_list, list) pr_info(MPT3SAS_FMT "%s: IRQ %d\n", reply_q->name, ((ioc->msix_enable) ? "PCI-MSI-X enabled" : @@ -5280,17 +5291,6 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) if (r) goto out_free_resources; - if (ioc->is_warpdrive) { - ioc->reply_post_host_index[0] = (resource_size_t __iomem *) - &ioc->chip->ReplyPostHostIndex; - - for (i = 1; i < ioc->cpu_msix_table_sz; i++) - ioc->reply_post_host_index[i] = - (resource_size_t __iomem *) - ((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1) - * 4))); - } - pci_set_drvdata(ioc->pdev, ioc->shost); r = _base_get_ioc_facts(ioc, CAN_SLEEP); if (r) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 53ef1cb..0e8601a 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -778,6 +778,8 @@ static void ses_intf_remove_enclosure(struct scsi_device *sdev) if (!edev) return; + enclosure_unregister(edev); + ses_dev = edev->scratch; edev->scratch = NULL; @@ -789,7 +791,6 @@ static void ses_intf_remove_enclosure(struct scsi_device *sdev) kfree(edev->component[0].scratch); put_device(&edev->edev); - enclosure_unregister(edev); } static void ses_intf_remove(struct device *cdev, diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 3788ed7..a32b417 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -740,12 +740,22 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, } /* Bind cpufreq callbacks to thermal cooling device ops */ + static struct thermal_cooling_device_ops cpufreq_cooling_ops = { .get_max_state = cpufreq_get_max_state, .get_cur_state = cpufreq_get_cur_state, .set_cur_state = cpufreq_set_cur_state, }; +static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = { + .get_max_state = cpufreq_get_max_state, + .get_cur_state = cpufreq_get_cur_state, + .set_cur_state = cpufreq_set_cur_state, + .get_requested_power = cpufreq_get_requested_power, + .state2power = cpufreq_state2power, + .power2state = cpufreq_power2state, +}; + /* Notifier for cpufreq policy change */ static struct notifier_block thermal_cpufreq_notifier_block = { .notifier_call = cpufreq_thermal_notifier, @@ -795,6 +805,7 @@ __cpufreq_cooling_register(struct device_node *np, struct cpumask temp_mask; unsigned int freq, i, num_cpus; int ret; + struct thermal_cooling_device_ops *cooling_ops; cpumask_and(&temp_mask, clip_cpus, cpu_online_mask); policy = cpufreq_cpu_get(cpumask_first(&temp_mask)); @@ -850,10 +861,6 @@ __cpufreq_cooling_register(struct device_node *np, cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus); if (capacitance) { - cpufreq_cooling_ops.get_requested_power = - cpufreq_get_requested_power; - cpufreq_cooling_ops.state2power = cpufreq_state2power; - cpufreq_cooling_ops.power2state = cpufreq_power2state; cpufreq_dev->plat_get_static_power = plat_static_func; ret = build_dyn_power_table(cpufreq_dev, capacitance); @@ -861,6 +868,10 @@ __cpufreq_cooling_register(struct device_node *np, cool_dev = ERR_PTR(ret); goto free_table; } + + cooling_ops = &cpufreq_power_cooling_ops; + } else { + cooling_ops = &cpufreq_cooling_ops; } ret = get_idr(&cpufreq_idr, &cpufreq_dev->id); @@ -885,7 +896,7 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_dev->id); cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev, - &cpufreq_cooling_ops); + cooling_ops); if (IS_ERR(cool_dev)) goto remove_idr; diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index c5547bd..e473548 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -471,8 +471,6 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match); static int imx_thermal_probe(struct platform_device *pdev) { - const struct of_device_id *of_id = - of_match_device(of_imx_thermal_match, &pdev->dev); struct imx_thermal_data *data; struct regmap *map; int measure_freq; @@ -490,7 +488,7 @@ static int imx_thermal_probe(struct platform_device *pdev) } data->tempmon = map; - data->socdata = of_id->data; + data->socdata = of_device_get_match_data(&pdev->dev); /* make sure the IRQ flag is clear before enabling irq on i.MX6SX */ if (data->socdata->version == TEMPMON_IMX6SX) { diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c index a578cd2..1891f34 100644 --- a/drivers/thermal/int340x_thermal/int3406_thermal.c +++ b/drivers/thermal/int340x_thermal/int3406_thermal.c @@ -225,7 +225,6 @@ static struct platform_driver int3406_thermal_driver = { .remove = int3406_thermal_remove, .driver = { .name = "int3406 thermal", - .owner = THIS_MODULE, .acpi_match_table = int3406_thermal_match, }, }; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 7191230..0f3f62e 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1354,7 +1354,6 @@ made_compressed_probe: spin_lock_init(&acm->write_lock); spin_lock_init(&acm->read_lock); mutex_init(&acm->mutex); - acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress); acm->is_int_ep = usb_endpoint_xfer_int(epread); if (acm->is_int_ep) acm->bInterval = epread->bInterval; @@ -1394,14 +1393,14 @@ made_compressed_probe: urb->transfer_dma = rb->dma; if (acm->is_int_ep) { usb_fill_int_urb(urb, acm->dev, - acm->rx_endpoint, + usb_rcvintpipe(usb_dev, epread->bEndpointAddress), rb->base, acm->readsize, acm_read_bulk_callback, rb, acm->bInterval); } else { usb_fill_bulk_urb(urb, acm->dev, - acm->rx_endpoint, + usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress), rb->base, acm->readsize, acm_read_bulk_callback, rb); diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 05ce308..1f1eabf 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -96,7 +96,6 @@ struct acm { struct acm_rb read_buffers[ACM_NR]; struct acm_wb *putbuffer; /* for acm_tty_put_char() */ int rx_buflimit; - int rx_endpoint; spinlock_t read_lock; int write_used; /* number of non-empty write buffers */ int transmitting; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 31ccdcc..0511631 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -171,6 +171,31 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno, ep, buffer, size); } +static const unsigned short low_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 8, + [USB_ENDPOINT_XFER_ISOC] = 0, + [USB_ENDPOINT_XFER_BULK] = 0, + [USB_ENDPOINT_XFER_INT] = 8, +}; +static const unsigned short full_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 64, + [USB_ENDPOINT_XFER_ISOC] = 1023, + [USB_ENDPOINT_XFER_BULK] = 64, + [USB_ENDPOINT_XFER_INT] = 64, +}; +static const unsigned short high_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 64, + [USB_ENDPOINT_XFER_ISOC] = 1024, + [USB_ENDPOINT_XFER_BULK] = 512, + [USB_ENDPOINT_XFER_INT] = 1023, +}; +static const unsigned short super_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 512, + [USB_ENDPOINT_XFER_ISOC] = 1024, + [USB_ENDPOINT_XFER_BULK] = 1024, + [USB_ENDPOINT_XFER_INT] = 1024, +}; + static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_interface *ifp, int num_ep, unsigned char *buffer, int size) @@ -179,6 +204,8 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, struct usb_endpoint_descriptor *d; struct usb_host_endpoint *endpoint; int n, i, j, retval; + unsigned int maxp; + const unsigned short *maxpacket_maxes; d = (struct usb_endpoint_descriptor *) buffer; buffer += d->bLength; @@ -286,6 +313,42 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, endpoint->desc.wMaxPacketSize = cpu_to_le16(8); } + /* Validate the wMaxPacketSize field */ + maxp = usb_endpoint_maxp(&endpoint->desc); + + /* Find the highest legal maxpacket size for this endpoint */ + i = 0; /* additional transactions per microframe */ + switch (to_usb_device(ddev)->speed) { + case USB_SPEED_LOW: + maxpacket_maxes = low_speed_maxpacket_maxes; + break; + case USB_SPEED_FULL: + maxpacket_maxes = full_speed_maxpacket_maxes; + break; + case USB_SPEED_HIGH: + /* Bits 12..11 are allowed only for HS periodic endpoints */ + if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) { + i = maxp & (BIT(12) | BIT(11)); + maxp &= ~i; + } + /* fallthrough */ + default: + maxpacket_maxes = high_speed_maxpacket_maxes; + break; + case USB_SPEED_SUPER: + case USB_SPEED_SUPER_PLUS: + maxpacket_maxes = super_speed_maxpacket_maxes; + break; + } + j = maxpacket_maxes[usb_endpoint_type(&endpoint->desc)]; + + if (maxp > j) { + dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid maxpacket %d, setting to %d\n", + cfgno, inum, asnum, d->bEndpointAddress, maxp, j); + maxp = j; + endpoint->desc.wMaxPacketSize = cpu_to_le16(i | maxp); + } + /* * Some buggy high speed devices have bulk endpoints using * maxpacket sizes other than 512. High speed HCDs may not @@ -293,9 +356,6 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, */ if (to_usb_device(ddev)->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) { - unsigned maxp; - - maxp = usb_endpoint_maxp(&endpoint->desc) & 0x07ff; if (maxp != 512) dev_warn(ddev, "config %d interface %d altsetting %d " "bulk endpoint 0x%X has invalid maxpacket %d\n", diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e9f5043..e6a6d67 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -241,7 +241,8 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) goto error_decrease_mem; } - mem = usb_alloc_coherent(ps->dev, size, GFP_USER, &dma_handle); + mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN, + &dma_handle); if (!mem) { ret = -ENOMEM; goto error_free_usbm; @@ -2582,7 +2583,9 @@ static unsigned int usbdev_poll(struct file *file, if (file->f_mode & FMODE_WRITE && !list_empty(&ps->async_completed)) mask |= POLLOUT | POLLWRNORM; if (!connected(ps)) - mask |= POLLERR | POLLHUP; + mask |= POLLHUP; + if (list_empty(&ps->list)) + mask |= POLLERR; return mask; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index bee1351..1d5fc32 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1052,14 +1052,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Continue a partial initialization */ if (type == HUB_INIT2 || type == HUB_INIT3) { - device_lock(hub->intfdev); + device_lock(&hdev->dev); /* Was the hub disconnected while we were waiting? */ - if (hub->disconnected) { - device_unlock(hub->intfdev); - kref_put(&hub->kref, hub_release); - return; - } + if (hub->disconnected) + goto disconnected; if (type == HUB_INIT2) goto init2; goto init3; @@ -1262,7 +1259,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) queue_delayed_work(system_power_efficient_wq, &hub->init_work, msecs_to_jiffies(delay)); - device_unlock(hub->intfdev); + device_unlock(&hdev->dev); return; /* Continues at init3: below */ } else { msleep(delay); @@ -1281,12 +1278,12 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Scan all ports that need attention */ kick_hub_wq(hub); - /* Allow autosuspend if it was suppressed */ - if (type <= HUB_INIT3) + if (type == HUB_INIT2 || type == HUB_INIT3) { + /* Allow autosuspend if it was suppressed */ + disconnected: usb_autopm_put_interface_async(to_usb_interface(hub->intfdev)); - - if (type == HUB_INIT2 || type == HUB_INIT3) - device_unlock(hub->intfdev); + device_unlock(&hdev->dev); + } kref_put(&hub->kref, hub_release); } @@ -1315,8 +1312,6 @@ static void hub_quiesce(struct usb_hub *hub, enum hub_quiescing_type type) struct usb_device *hdev = hub->hdev; int i; - cancel_delayed_work_sync(&hub->init_work); - /* hub_wq and related activity won't re-trigger */ hub->quiescing = 1; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 9743353..e56d59b 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -61,6 +61,7 @@ static int dwc3_of_simple_probe(struct platform_device *pdev) if (!simple->clks) return -ENOMEM; + platform_set_drvdata(pdev, simple); simple->dev = dev; for (i = 0; i < simple->num_clocks; i++) { diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 45f5a23..2eb84d6 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -37,6 +37,7 @@ #define PCI_DEVICE_ID_INTEL_BXT 0x0aaa #define PCI_DEVICE_ID_INTEL_BXT_M 0x1aaa #define PCI_DEVICE_ID_INTEL_APL 0x5aaa +#define PCI_DEVICE_ID_INTEL_KBP 0xa2b0 static const struct acpi_gpio_params reset_gpios = { 0, 0, false }; static const struct acpi_gpio_params cs_gpios = { 1, 0, false }; @@ -227,6 +228,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT), }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT_M), }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), }, { } /* Terminating Entry */ }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 8f8c215..1f5597e 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -829,7 +829,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, if (!req->request.no_interrupt && !chain) trb->ctrl |= DWC3_TRB_CTRL_IOC | DWC3_TRB_CTRL_ISP_IMI; - if (last) + if (last && !usb_endpoint_xfer_isoc(dep->endpoint.desc)) trb->ctrl |= DWC3_TRB_CTRL_LST; if (chain) @@ -1955,7 +1955,8 @@ static void dwc3_gadget_free_endpoints(struct dwc3 *dwc) static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, struct dwc3_request *req, struct dwc3_trb *trb, - const struct dwc3_event_depevt *event, int status) + const struct dwc3_event_depevt *event, int status, + int chain) { unsigned int count; unsigned int s_pkt = 0; @@ -1964,17 +1965,22 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, dep->queued_requests--; trace_dwc3_complete_trb(dep, trb); + /* + * If we're in the middle of series of chained TRBs and we + * receive a short transfer along the way, DWC3 will skip + * through all TRBs including the last TRB in the chain (the + * where CHN bit is zero. DWC3 will also avoid clearing HWO + * bit and SW has to do it manually. + * + * We're going to do that here to avoid problems of HW trying + * to use bogus TRBs for transfers. + */ + if (chain && (trb->ctrl & DWC3_TRB_CTRL_HWO)) + trb->ctrl &= ~DWC3_TRB_CTRL_HWO; + if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN) - /* - * We continue despite the error. There is not much we - * can do. If we don't clean it up we loop forever. If - * we skip the TRB then it gets overwritten after a - * while since we use them in a ring buffer. A BUG() - * would help. Lets hope that if this occurs, someone - * fixes the root cause instead of looking away :) - */ - dev_err(dwc->dev, "%s's TRB (%p) still owned by HW\n", - dep->name, trb); + return 1; + count = trb->size & DWC3_TRB_SIZE_MASK; if (dep->direction) { @@ -2013,15 +2019,7 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, s_pkt = 1; } - /* - * We assume here we will always receive the entire data block - * which we should receive. Meaning, if we program RX to - * receive 4K but we receive only 2K, we assume that's all we - * should receive and we simply bounce the request back to the - * gadget driver for further processing. - */ - req->request.actual += req->request.length - count; - if (s_pkt) + if (s_pkt && !chain) return 1; if ((event->status & DEPEVT_STATUS_LST) && (trb->ctrl & (DWC3_TRB_CTRL_LST | @@ -2040,13 +2038,17 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep, struct dwc3_trb *trb; unsigned int slot; unsigned int i; + int count = 0; int ret; do { + int chain; + req = next_request(&dep->started_list); if (WARN_ON_ONCE(!req)) return 1; + chain = req->request.num_mapped_sgs > 0; i = 0; do { slot = req->first_trb_index + i; @@ -2054,13 +2056,22 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep, slot++; slot %= DWC3_TRB_NUM; trb = &dep->trb_pool[slot]; + count += trb->size & DWC3_TRB_SIZE_MASK; ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb, - event, status); + event, status, chain); if (ret) break; } while (++i < req->request.num_mapped_sgs); + /* + * We assume here we will always receive the entire data block + * which we should receive. Meaning, if we program RX to + * receive 4K but we receive only 2K, we assume that's all we + * should receive and we simply bounce the request back to the + * gadget driver for further processing. + */ + req->request.actual += req->request.length - count; dwc3_gadget_giveback(dep, req, status); if (ret) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index eb64848..5ebe6af7 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1913,6 +1913,8 @@ unknown: break; case USB_RECIP_ENDPOINT: + if (!cdev->config) + break; endp = ((w_index & 0x80) >> 3) | (w_index & 0x0f); list_for_each_entry(f, &cdev->config->functions, list) { if (test_bit(endp, f->endpoints)) @@ -2124,14 +2126,14 @@ int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, cdev->os_desc_req = usb_ep_alloc_request(ep0, GFP_KERNEL); if (!cdev->os_desc_req) { - ret = PTR_ERR(cdev->os_desc_req); + ret = -ENOMEM; goto end; } /* OS feature descriptor length <= 4kB */ cdev->os_desc_req->buf = kmalloc(4096, GFP_KERNEL); if (!cdev->os_desc_req->buf) { - ret = PTR_ERR(cdev->os_desc_req->buf); + ret = -ENOMEM; kfree(cdev->os_desc_req); goto end; } diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 70cf347..f9237fe 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1490,7 +1490,9 @@ void unregister_gadget_item(struct config_item *item) { struct gadget_info *gi = to_gadget_info(item); + mutex_lock(&gi->lock); unregister_gadget(gi); + mutex_unlock(&gi->lock); } EXPORT_SYMBOL_GPL(unregister_gadget_item); diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 943c21a..ab6ac1b 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -680,6 +680,12 @@ static int rndis_reset_response(struct rndis_params *params, { rndis_reset_cmplt_type *resp; rndis_resp_t *r; + u8 *xbuf; + u32 length; + + /* drain the response queue */ + while ((xbuf = rndis_get_next_response(params, &length))) + rndis_free_response(params, xbuf); r = rndis_add_response(params, sizeof(rndis_reset_cmplt_type)); if (!r) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index a3f7e7c..5f562c1 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -556,7 +556,8 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb, /* Multi frame CDC protocols may store the frame for * later which is not a dropped frame. */ - if (dev->port_usb->supports_multi_frame) + if (dev->port_usb && + dev->port_usb->supports_multi_frame) goto multiframe; goto drop; } diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 66753ba..31125a4 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -2023,7 +2023,7 @@ static int uvcg_streaming_class_allow_link(struct config_item *src, if (!data) { kfree(*class_array); *class_array = NULL; - ret = PTR_ERR(data); + ret = -ENOMEM; goto unlock; } cl_arr = *class_array; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index aa3707b..16104b5e 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -542,7 +542,7 @@ static ssize_t ep_aio(struct kiocb *iocb, */ spin_lock_irq(&epdata->dev->lock); value = -ENODEV; - if (unlikely(epdata->ep)) + if (unlikely(epdata->ep == NULL)) goto fail; req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); @@ -606,7 +606,7 @@ ep_read_iter(struct kiocb *iocb, struct iov_iter *to) } if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); - if (value >= 0 && copy_to_iter(buf, value, to)) + if (value >= 0 && (copy_to_iter(buf, value, to) != value)) value = -EFAULT; } else { struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index ff8685e..934f838 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1145,7 +1145,7 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, if (ret != -EPROBE_DEFER) list_del(&driver->pending); if (ret) - goto err4; + goto err5; break; } } @@ -1154,6 +1154,9 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, return 0; +err5: + device_del(&udc->dev); + err4: list_del(&udc->list); mutex_unlock(&udc_lock); diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 93d28cb..cf8819a 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2053,7 +2053,7 @@ static void setup_received_handle(struct qe_udc *udc, struct qe_ep *ep; if (wValue != 0 || wLength != 0 - || pipe > USB_MAX_ENDPOINTS) + || pipe >= USB_MAX_ENDPOINTS) break; ep = &udc->eps[pipe]; diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index a962b89..1e5f529 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -332,11 +332,11 @@ static void ehci_turn_off_all_ports(struct ehci_hcd *ehci) int port = HCS_N_PORTS(ehci->hcs_params); while (port--) { - ehci_writel(ehci, PORT_RWC_BITS, - &ehci->regs->port_status[port]); spin_unlock_irq(&ehci->lock); ehci_port_power(ehci, port, false); spin_lock_irq(&ehci->lock); + ehci_writel(ehci, PORT_RWC_BITS, + &ehci->regs->port_status[port]); } } diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index c369c29..2f76900 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -1675,7 +1675,7 @@ max3421_gpout_set_value(struct usb_hcd *hcd, u8 pin_number, u8 value) if (pin_number > 7) return; - mask = 1u << pin_number; + mask = 1u << (pin_number % 4); idx = pin_number / 4; if (value) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index d61fcc4..730b9fd 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -386,6 +386,9 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) ret = 0; virt_dev = xhci->devs[slot_id]; + if (!virt_dev) + return -ENODEV; + cmd = xhci_alloc_command(xhci, false, true, GFP_NOIO); if (!cmd) { xhci_dbg(xhci, "Couldn't allocate command structure.\n"); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 4fd041b..d7b0f97 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -314,11 +314,12 @@ static void xhci_pci_remove(struct pci_dev *dev) usb_remove_hcd(xhci->shared_hcd); usb_put_hcd(xhci->shared_hcd); } - usb_hcd_pci_remove(dev); /* Workaround for spurious wakeups at shutdown with HSW */ if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) pci_set_power_state(dev, PCI_D3hot); + + usb_hcd_pci_remove(dev); } #ifdef CONFIG_PM diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 918e0c7..fd9fd12 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1334,12 +1334,6 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, cmd = list_entry(xhci->cmd_list.next, struct xhci_command, cmd_list); - if (cmd->command_trb != xhci->cmd_ring->dequeue) { - xhci_err(xhci, - "Command completion event does not match command\n"); - return; - } - del_timer(&xhci->cmd_timer); trace_xhci_cmd_completion(cmd_trb, (struct xhci_generic_trb *) event); @@ -1351,6 +1345,13 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, xhci_handle_stopped_cmd_ring(xhci, cmd); return; } + + if (cmd->command_trb != xhci->cmd_ring->dequeue) { + xhci_err(xhci, + "Command completion event does not match command\n"); + return; + } + /* * Host aborted the command ring, check if the current command was * supposed to be aborted, otherwise continue normally. @@ -3243,7 +3244,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, send_addr = addr; /* Queue the TRBs, even if they are zero-length */ - for (enqd_len = 0; enqd_len < full_len; enqd_len += trb_buff_len) { + for (enqd_len = 0; first_trb || enqd_len < full_len; + enqd_len += trb_buff_len) { field = TRB_TYPE(TRB_NORMAL); /* TRB buffer should not cross 64KB boundaries */ diff --git a/drivers/usb/misc/ftdi-elan.c b/drivers/usb/misc/ftdi-elan.c index 52c27ca..9b5b3b2 100644 --- a/drivers/usb/misc/ftdi-elan.c +++ b/drivers/usb/misc/ftdi-elan.c @@ -665,7 +665,7 @@ static ssize_t ftdi_elan_read(struct file *file, char __user *buffer, { char data[30 *3 + 4]; char *d = data; - int m = (sizeof(data) - 1) / 3; + int m = (sizeof(data) - 1) / 3 - 1; int bytes_read = 0; int retry_on_empty = 10; int retry_on_timeout = 5; @@ -1684,7 +1684,7 @@ wait:if (ftdi->disconnected > 0) { int i = 0; char data[30 *3 + 4]; char *d = data; - int m = (sizeof(data) - 1) / 3; + int m = (sizeof(data) - 1) / 3 - 1; int l = 0; struct u132_target *target = &ftdi->target[ed]; struct u132_command *command = &ftdi->command[ @@ -1876,7 +1876,7 @@ more:{ if (packet_bytes > 2) { char diag[30 *3 + 4]; char *d = diag; - int m = (sizeof(diag) - 1) / 3; + int m = (sizeof(diag) - 1) / 3 - 1; char *b = ftdi->bulk_in_buffer; int bytes_read = 0; diag[0] = 0; @@ -2053,7 +2053,7 @@ static int ftdi_elan_synchronize(struct usb_ftdi *ftdi) if (packet_bytes > 2) { char diag[30 *3 + 4]; char *d = diag; - int m = (sizeof(diag) - 1) / 3; + int m = (sizeof(diag) - 1) / 3 - 1; char *b = ftdi->bulk_in_buffer; int bytes_read = 0; unsigned char c = 0; @@ -2155,7 +2155,7 @@ more:{ if (packet_bytes > 2) { char diag[30 *3 + 4]; char *d = diag; - int m = (sizeof(diag) - 1) / 3; + int m = (sizeof(diag) - 1) / 3 - 1; char *b = ftdi->bulk_in_buffer; int bytes_read = 0; diag[0] = 0; diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index 6b978f0..5c8210d 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -585,7 +585,6 @@ static void sg_timeout(unsigned long _req) { struct usb_sg_request *req = (struct usb_sg_request *) _req; - req->status = -ETIMEDOUT; usb_sg_cancel(req); } @@ -616,8 +615,10 @@ static int perform_sglist( mod_timer(&sg_timer, jiffies + msecs_to_jiffies(SIMPLE_IO_TIMEOUT)); usb_sg_wait(req); - del_timer_sync(&sg_timer); - retval = req->status; + if (!del_timer_sync(&sg_timer)) + retval = -ETIMEDOUT; + else + retval = req->status; /* FIXME check resulting data pattern */ @@ -2602,7 +2603,7 @@ usbtest_ioctl(struct usb_interface *intf, unsigned int code, void *buf) ktime_get_ts64(&start); retval = usbtest_do_ioctl(intf, param_32); - if (retval) + if (retval < 0) goto free_mutex; ktime_get_ts64(&end); diff --git a/drivers/usb/phy/phy-omap-otg.c b/drivers/usb/phy/phy-omap-otg.c index 6f6d2a7..6523af4 100644 --- a/drivers/usb/phy/phy-omap-otg.c +++ b/drivers/usb/phy/phy-omap-otg.c @@ -140,6 +140,8 @@ static int omap_otg_probe(struct platform_device *pdev) (rev >> 4) & 0xf, rev & 0xf, config->extcon, otg_dev->id, otg_dev->vbus); + platform_set_drvdata(pdev, otg_dev); + return 0; } diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index 8fbbc2d..ac67bab 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -514,7 +514,8 @@ static struct renesas_usbhs_platform_info *usbhs_parse_dt(struct device *dev) if (gpio > 0) dparam->enable_gpio = gpio; - if (dparam->type == USBHS_TYPE_RCAR_GEN2) + if (dparam->type == USBHS_TYPE_RCAR_GEN2 || + dparam->type == USBHS_TYPE_RCAR_GEN3) dparam->has_usb_dmac = 1; return info; diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 280ed5f..857e783 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -871,7 +871,7 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done) /* use PIO if packet is less than pio_dma_border or pipe is DCP */ if ((len < usbhs_get_dparam(priv, pio_dma_border)) || - usbhs_pipe_is_dcp(pipe)) + usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC)) goto usbhsf_pio_prepare_push; /* check data length if this driver don't use USB-DMAC */ @@ -976,7 +976,7 @@ static int usbhsf_dma_prepare_pop_with_usb_dmac(struct usbhs_pkt *pkt, /* use PIO if packet is less than pio_dma_border or pipe is DCP */ if ((pkt->length < usbhs_get_dparam(priv, pio_dma_border)) || - usbhs_pipe_is_dcp(pipe)) + usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC)) goto usbhsf_pio_prepare_pop; fifo = usbhsf_get_dma_fifo(priv, pkt); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 50f3363..92bc83b 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -617,10 +617,13 @@ static int usbhsg_ep_enable(struct usb_ep *ep, * use dmaengine if possible. * It will use pio handler if impossible. */ - if (usb_endpoint_dir_in(desc)) + if (usb_endpoint_dir_in(desc)) { pipe->handler = &usbhs_fifo_dma_push_handler; - else + } else { pipe->handler = &usbhs_fifo_dma_pop_handler; + usbhs_xxxsts_clear(priv, BRDYSTS, + usbhs_pipe_number(pipe)); + } ret = 0; } diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 0082080..b2d767e 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -648,6 +648,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_ELV_TFD128_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_FM3RX_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_WS777_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_PALMSENS_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_IVIUM_XSTAT_PID) }, { USB_DEVICE(FTDI_VID, LINX_SDMUSBQSS_PID) }, { USB_DEVICE(FTDI_VID, LINX_MASTERDEVEL2_PID) }, { USB_DEVICE(FTDI_VID, LINX_FUTURE_0_PID) }, @@ -1008,6 +1010,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) }, + { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index c5d6c1e..f87a938 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -406,6 +406,12 @@ #define FTDI_4N_GALAXY_DE_3_PID 0xF3C2 /* + * Ivium Technologies product IDs + */ +#define FTDI_PALMSENS_PID 0xf440 +#define FTDI_IVIUM_XSTAT_PID 0xf441 + +/* * Linx Technologies product ids */ #define LINX_SDMUSBQSS_PID 0xF448 /* Linx SDM-USB-QS-S */ @@ -673,6 +679,12 @@ #define INTREPID_NEOVI_PID 0x0701 /* + * WICED USB UART + */ +#define WICED_VID 0x0A5C +#define WICED_USB20706V2_PID 0x6422 + +/* * Definitions for ID TECH (www.idt-net.com) devices */ #define IDTECH_VID 0x0ACD /* ID TECH Vendor ID */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8e07536..bc47258 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -274,6 +274,12 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 #define TELIT_PRODUCT_LE910_USBCFG4 0x1206 +#define TELIT_PRODUCT_LE920A4_1207 0x1207 +#define TELIT_PRODUCT_LE920A4_1208 0x1208 +#define TELIT_PRODUCT_LE920A4_1211 0x1211 +#define TELIT_PRODUCT_LE920A4_1212 0x1212 +#define TELIT_PRODUCT_LE920A4_1213 0x1213 +#define TELIT_PRODUCT_LE920A4_1214 0x1214 /* ZTE PRODUCTS */ #define ZTE_VENDOR_ID 0x19d2 @@ -628,6 +634,11 @@ static const struct option_blacklist_info telit_le920_blacklist = { .reserved = BIT(1) | BIT(5), }; +static const struct option_blacklist_info telit_le920a4_blacklist_1 = { + .sendsetup = BIT(0), + .reserved = BIT(1), +}; + static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = { .sendsetup = BIT(2), .reserved = BIT(0) | BIT(1) | BIT(3), @@ -1203,6 +1214,16 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), .driver_info = (kernel_ulong_t)&telit_le920_blacklist }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1207) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1208), + .driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1211), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1212), + .driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&net_intf1_blacklist }, @@ -1966,6 +1987,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index b1b9bac..d213cf4 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1433,7 +1433,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[] rc = usb_register(udriver); if (rc) - return rc; + goto failed_usb_register; for (sd = serial_drivers; *sd; ++sd) { (*sd)->usb_driver = udriver; @@ -1451,6 +1451,8 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[] while (sd-- > serial_drivers) usb_serial_deregister(*sd); usb_deregister(udriver); +failed_usb_register: + kfree(udriver); return rc; } EXPORT_SYMBOL_GPL(usb_serial_register_drivers); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 9d6320e..6e29d05 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -88,7 +88,7 @@ struct vhost_scsi_cmd { struct scatterlist *tvc_prot_sgl; struct page **tvc_upages; /* Pointer to response header iovec */ - struct iovec *tvc_resp_iov; + struct iovec tvc_resp_iov; /* Pointer to vhost_scsi for our device */ struct vhost_scsi *tvc_vhost; /* Pointer to vhost_virtqueue for the cmd */ @@ -547,7 +547,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) memcpy(v_rsp.sense, cmd->tvc_sense_buf, se_cmd->scsi_sense_length); - iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov, + iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov, cmd->tvc_in_iovs, sizeof(v_rsp)); ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter); if (likely(ret == sizeof(v_rsp))) { @@ -1044,7 +1044,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = &vq->iov[out]; + cmd->tvc_resp_iov = vq->iov[out]; cmd->tvc_in_iovs = in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 7487971..c1010f01 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,7 +316,7 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } - } else { + } else if (msg_type == XS_TRANSACTION_END) { list_for_each_entry(trans, &u->transactions, list) if (trans->handle.id == u->u.msg.tx_id) break; diff --git a/fs/block_dev.c b/fs/block_dev.c index c3cdde8..08ae993 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -249,7 +249,8 @@ struct super_block *freeze_bdev(struct block_device *bdev) * thaw_bdev drops it. */ sb = get_super(bdev); - drop_super(sb); + if (sb) + drop_super(sb); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } @@ -646,7 +647,7 @@ static struct dentry *bd_mount(struct file_system_type *fs_type, { struct dentry *dent; dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC); - if (dent) + if (!IS_ERR(dent)) dent->d_sb->s_iflags |= SB_I_CGROUPWB; return dent; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2b88439..455a6b2 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -589,6 +589,7 @@ static void __merge_refs(struct list_head *head, int mode) list_del(&ref2->list); kmem_cache_free(btrfs_prelim_ref_cache, ref2); + cond_resched(); } } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2fe8f89..eff3993 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1028,6 +1028,7 @@ struct btrfs_fs_info { struct btrfs_workqueue *qgroup_rescan_workers; struct completion qgroup_rescan_completion; struct btrfs_work qgroup_rescan_work; + bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */ /* filesystem state */ unsigned long fs_state; @@ -1079,6 +1080,8 @@ struct btrfs_fs_info { struct list_head pinned_chunks; int creating_free_space_tree; + /* Used to record internally whether fs has been frozen */ + int fs_frozen; }; struct btrfs_subvolume_writers { @@ -2578,7 +2581,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, u64 offset, struct btrfs_key *ins); -int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index d9ddcfc..ac02e04 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -541,7 +541,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_qgroup_extent_record *qexisting; int count_mod = 1; int must_insert_reserved = 0; @@ -606,10 +605,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, qrecord->num_bytes = num_bytes; qrecord->old_roots = NULL; - qexisting = btrfs_qgroup_insert_dirty_extent(fs_info, - delayed_refs, - qrecord); - if (qexisting) + if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info, + delayed_refs, qrecord)) kfree(qrecord); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59febfb..54bc8c7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -559,8 +559,29 @@ static noinline int check_leaf(struct btrfs_root *root, u32 nritems = btrfs_header_nritems(leaf); int slot; - if (nritems == 0) + if (nritems == 0) { + struct btrfs_root *check_root; + + key.objectid = btrfs_header_owner(leaf); + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + + check_root = btrfs_get_fs_root(root->fs_info, &key, false); + /* + * The only reason we also check NULL here is that during + * open_ctree() some roots has not yet been set up. + */ + if (!IS_ERR_OR_NULL(check_root)) { + /* if leaf is the root, then it's fine */ + if (leaf->start != + btrfs_root_bytenr(&check_root->root_item)) { + CORRUPT("non-root leaf's nritems is 0", + leaf, root, 0); + return -EIO; + } + } return 0; + } /* Check the 0 item */ if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != @@ -612,6 +633,19 @@ static noinline int check_leaf(struct btrfs_root *root, return 0; } +static int check_node(struct btrfs_root *root, struct extent_buffer *node) +{ + unsigned long nr = btrfs_header_nritems(node); + + if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) { + btrfs_crit(root->fs_info, + "corrupt node: block %llu root %llu nritems %lu", + node->start, root->objectid, nr); + return -EIO; + } + return 0; +} + static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, u64 phy_offset, struct page *page, u64 start, u64 end, int mirror) @@ -682,6 +716,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; } + if (found_level > 0 && check_node(root, eb)) + ret = -EIO; + if (!ret) set_extent_buffer_uptodate(eb); err: @@ -1618,8 +1655,8 @@ fail: return ret; } -static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; @@ -2298,6 +2335,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; fs_info->qgroup_ulist = NULL; + fs_info->qgroup_rescan_running = false; mutex_init(&fs_info->qgroup_rescan_lock); } @@ -2624,6 +2662,7 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic64_set(&fs_info->tree_mod_seq, 0); + fs_info->fs_frozen = 0; fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; @@ -3739,8 +3778,15 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { btrfs_free_log(NULL, root); + if (root->reloc_root) { + free_extent_buffer(root->reloc_root->node); + free_extent_buffer(root->reloc_root->commit_root); + btrfs_put_fs_root(root->reloc_root); + root->reloc_root = NULL; + } + } if (root->free_ino_pinned) __btrfs_remove_free_space_cache(root->free_ino_pinned); @@ -3851,7 +3897,7 @@ void close_ctree(struct btrfs_root *root) smp_mb(); /* wait for the qgroup rescan worker to stop */ - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index b3207a0e..f19a982 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -68,6 +68,8 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, struct btrfs_key *location); int btrfs_init_fs_root(struct btrfs_root *root); +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id); int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 61b494e..0450dc4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -60,21 +60,6 @@ enum { CHUNK_ALLOC_FORCE = 2, }; -/* - * Control how reservations are dealt with. - * - * RESERVE_FREE - freeing a reservation. - * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for - * ENOSPC accounting - * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update - * bytes_may_use as the ENOSPC accounting is done elsewhere - */ -enum { - RESERVE_FREE = 0, - RESERVE_ALLOC = 1, - RESERVE_ALLOC_NO_ACCOUNT = 2, -}; - static int update_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, int alloc); @@ -104,9 +89,10 @@ static int find_next_key(struct btrfs_path *path, int level, struct btrfs_key *key); static void dump_space_info(struct btrfs_space_info *info, u64 bytes, int dump_block_groups); -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, - int delalloc); +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 ram_bytes, u64 num_bytes, int delalloc); +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); int btrfs_pin_extent(struct btrfs_root *root, @@ -3501,7 +3487,6 @@ again: dcs = BTRFS_DC_SETUP; else if (ret == -ENOSPC) set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags); - btrfs_free_reserved_data_space(inode, 0, num_pages); out_put: iput(inode); @@ -4472,6 +4457,15 @@ void check_system_chunk(struct btrfs_trans_handle *trans, } } +/* + * If force is CHUNK_ALLOC_FORCE: + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + * If force is NOT CHUNK_ALLOC_FORCE: + * - return 0 if it doesn't need to allocate a new chunk, + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + */ static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 flags, int force) { @@ -4882,7 +4876,7 @@ static int flush_space(struct btrfs_root *root, btrfs_get_alloc_profile(root, 0), CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans, root); - if (ret == -ENOSPC) + if (ret > 0 || ret == -ENOSPC) ret = 0; break; case COMMIT_TRANS: @@ -6497,19 +6491,15 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) } /** - * btrfs_update_reserved_bytes - update the block_group and space info counters + * btrfs_add_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating + * @ram_bytes: The number of bytes of file content, and will be same to + * @num_bytes except for the compress path. * @num_bytes: The number of bytes in question - * @reserve: One of the reservation enums * @delalloc: The blocks are allocated for the delalloc write * - * This is called by the allocator when it reserves space, or by somebody who is - * freeing space that was never actually used on disk. For example if you - * reserve some space for a new leaf in transaction A and before transaction A - * commits you free that leaf, you call this with reserve set to 0 in order to - * clear the reservation. - * - * Metadata reservations should be called with RESERVE_ALLOC so we do the proper + * This is called by the allocator when it reserves space. Metadata + * reservations should be called with RESERVE_ALLOC so we do the proper * ENOSPC accounting. For data we handle the reservation through clearing the * delalloc bits in the io_tree. We have to do this since we could end up * allocating less disk space for the amount of data we have reserved in the @@ -6519,44 +6509,63 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) * make the reservation and return -EAGAIN, otherwise this function always * succeeds. */ -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int delalloc) +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 ram_bytes, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; int ret = 0; spin_lock(&space_info->lock); spin_lock(&cache->lock); - if (reserve != RESERVE_FREE) { - if (cache->ro) { - ret = -EAGAIN; - } else { - cache->reserved += num_bytes; - space_info->bytes_reserved += num_bytes; - if (reserve == RESERVE_ALLOC) { - trace_btrfs_space_reservation(cache->fs_info, - "space_info", space_info->flags, - num_bytes, 0); - space_info->bytes_may_use -= num_bytes; - } - - if (delalloc) - cache->delalloc_bytes += num_bytes; - } + if (cache->ro) { + ret = -EAGAIN; } else { - if (cache->ro) - space_info->bytes_readonly += num_bytes; - cache->reserved -= num_bytes; - space_info->bytes_reserved -= num_bytes; + cache->reserved += num_bytes; + space_info->bytes_reserved += num_bytes; + trace_btrfs_space_reservation(cache->fs_info, + "space_info", space_info->flags, + ram_bytes, 0); + space_info->bytes_may_use -= ram_bytes; if (delalloc) - cache->delalloc_bytes -= num_bytes; + cache->delalloc_bytes += num_bytes; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); return ret; } +/** + * btrfs_free_reserved_bytes - update the block_group and space info counters + * @cache: The cache we are manipulating + * @num_bytes: The number of bytes in question + * @delalloc: The blocks are allocated for the delalloc write + * + * This is called by somebody who is freeing space that was never actually used + * on disk. For example if you reserve some space for a new leaf in transaction + * A and before transaction A commits you free that leaf, you call this with + * reserve set to 0 in order to clear the reservation. + */ + +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc) +{ + struct btrfs_space_info *space_info = cache->space_info; + int ret = 0; + + spin_lock(&space_info->lock); + spin_lock(&cache->lock); + if (cache->ro) + space_info->bytes_readonly += num_bytes; + cache->reserved -= num_bytes; + space_info->bytes_reserved -= num_bytes; + + if (delalloc) + cache->delalloc_bytes -= num_bytes; + spin_unlock(&cache->lock); + spin_unlock(&space_info->lock); + return ret; +} void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -7191,7 +7200,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); - btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0); + btrfs_free_reserved_bytes(cache, buf->len, 0); btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(root, buf->start, buf->len); pin = 0; @@ -7416,9 +7425,9 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache, * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, - u64 num_bytes, u64 empty_size, - u64 hint_byte, struct btrfs_key *ins, - u64 flags, int delalloc) + u64 ram_bytes, u64 num_bytes, u64 empty_size, + u64 hint_byte, struct btrfs_key *ins, + u64 flags, int delalloc) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -7430,8 +7439,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_space_info *space_info; int loop = 0; int index = __get_raid_index(flags); - int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ? - RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC; bool failed_cluster_refill = false; bool failed_alloc = false; bool use_cluster = true; @@ -7763,8 +7770,8 @@ checks: search_start - offset); BUG_ON(offset > search_start); - ret = btrfs_update_reserved_bytes(block_group, num_bytes, - alloc_type, delalloc); + ret = btrfs_add_reserved_bytes(block_group, ram_bytes, + num_bytes, delalloc); if (ret == -EAGAIN) { btrfs_add_free_space(block_group, offset, num_bytes); goto loop; @@ -7936,7 +7943,7 @@ again: up_read(&info->groups_sem); } -int btrfs_reserve_extent(struct btrfs_root *root, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc) @@ -7948,8 +7955,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, flags = btrfs_get_alloc_profile(root, is_data); again: WARN_ON(num_bytes < root->sectorsize); - ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, - flags, delalloc); + ret = find_free_extent(root, ram_bytes, num_bytes, empty_size, + hint_byte, ins, flags, delalloc); if (!ret && !is_data) { btrfs_dec_block_group_reservations(root->fs_info, ins->objectid); @@ -7958,6 +7965,7 @@ again: num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); + ram_bytes = num_bytes; if (num_bytes == min_alloc_size) final_tried = true; goto again; @@ -7995,7 +8003,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, if (btrfs_test_opt(root->fs_info, DISCARD)) ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); - btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); + btrfs_free_reserved_bytes(cache, len, delalloc); trace_btrfs_reserved_extent_free(root, start, len); } @@ -8223,8 +8231,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, if (!block_group) return -EINVAL; - ret = btrfs_update_reserved_bytes(block_group, ins->offset, - RESERVE_ALLOC_NO_ACCOUNT, 0); + ret = btrfs_add_reserved_bytes(block_group, ins->offset, + ins->offset, 0); BUG_ON(ret); /* logic error */ ret = alloc_reserved_file_extent(trans, root, 0, root_objectid, 0, owner, offset, ins, 1); @@ -8368,7 +8376,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, if (IS_ERR(block_rsv)) return ERR_CAST(block_rsv); - ret = btrfs_reserve_extent(root, blocksize, blocksize, + ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize, empty_size, hint, &ins, 0, 0); if (ret) goto out_unuse; @@ -8521,35 +8529,6 @@ reada: wc->reada_slot = slot; } -/* - * These may not be seen by the usual inc/dec ref code so we have to - * add them here. - */ -static int record_one_subtree_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 bytenr, - u64 num_bytes) -{ - struct btrfs_qgroup_extent_record *qrecord; - struct btrfs_delayed_ref_root *delayed_refs; - - qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS); - if (!qrecord) - return -ENOMEM; - - qrecord->bytenr = bytenr; - qrecord->num_bytes = num_bytes; - qrecord->old_roots = NULL; - - delayed_refs = &trans->transaction->delayed_refs; - spin_lock(&delayed_refs->lock); - if (btrfs_qgroup_insert_dirty_extent(trans->fs_info, - delayed_refs, qrecord)) - kfree(qrecord); - spin_unlock(&delayed_refs->lock); - - return 0; -} - static int account_leaf_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb) @@ -8583,7 +8562,8 @@ static int account_leaf_items(struct btrfs_trans_handle *trans, num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); - ret = record_one_subtree_extent(trans, root, bytenr, num_bytes); + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + bytenr, num_bytes, GFP_NOFS); if (ret) return ret; } @@ -8732,8 +8712,9 @@ walk_down: btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); path->locks[level] = BTRFS_READ_LOCK_BLOCKING; - ret = record_one_subtree_extent(trans, root, child_bytenr, - root->nodesize); + ret = btrfs_qgroup_insert_dirty_extent(trans, + root->fs_info, child_bytenr, + root->nodesize, GFP_NOFS); if (ret) goto out; } @@ -9906,6 +9887,7 @@ static int find_first_block_group(struct btrfs_root *root, } else { ret = 0; } + free_extent_map(em); goto out; } path->slots[0]++; @@ -9942,6 +9924,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) block_group->iref = 0; block_group->inode = NULL; spin_unlock(&block_group->lock); + ASSERT(block_group->io_ctl.inode == NULL); iput(inode); last = block_group->key.objectid + block_group->key.offset; btrfs_put_block_group(block_group); @@ -9999,6 +9982,10 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) free_excluded_extents(info->extent_root, block_group); btrfs_remove_free_space_cache(block_group); + ASSERT(list_empty(&block_group->dirty_list)); + ASSERT(list_empty(&block_group->io_list)); + ASSERT(list_empty(&block_group->bg_list)); + ASSERT(atomic_read(&block_group->count) == 1); btrfs_put_block_group(block_group); spin_lock(&info->block_group_cache_lock); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index bc2729a..28cd88f 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -20,6 +20,7 @@ #define EXTENT_DAMAGED (1U << 14) #define EXTENT_NORESERVE (1U << 15) #define EXTENT_QGROUP_RESERVED (1U << 16) +#define EXTENT_CLEAR_DATA_RESV (1U << 17) #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5842423..fea31a4 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2070,7 +2070,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } trans->sync = true; - btrfs_init_log_ctx(&ctx); + btrfs_init_log_ctx(&ctx, inode); ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx); if (ret < 0) { @@ -2675,6 +2675,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); + cur_offset = alloc_start; /* Make sure we aren't being give some crap mode */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) @@ -2767,7 +2768,6 @@ static long btrfs_fallocate(struct file *file, int mode, /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); - cur_offset = alloc_start; while (1) { em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); @@ -2794,6 +2794,14 @@ static long btrfs_fallocate(struct file *file, int mode, last_byte - cur_offset); if (ret < 0) break; + } else { + /* + * Do not need to reserve unwritten extent for this + * range, free reserved data space first, otherwise + * it'll result in false ENOSPC error. + */ + btrfs_free_reserved_data_space(inode, cur_offset, + last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -2811,6 +2819,9 @@ static long btrfs_fallocate(struct file *file, int mode, range->start, range->len, 1 << inode->i_blkbits, offset + len, &alloc_hint); + else + btrfs_free_reserved_data_space(inode, range->start, + range->len); list_del(&range->list); kfree(range); } @@ -2845,18 +2856,11 @@ out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state, GFP_KERNEL); out: - /* - * As we waited the extent range, the data_rsv_map must be empty - * in the range, as written data range will be released from it. - * And for prealloacted extent, it will also be released when - * its metadata is written. - * So this is completely used as cleanup. - */ - btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start); inode_unlock(inode); /* Let go of our reservation. */ - btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - alloc_start); + if (ret != 0) + btrfs_free_reserved_data_space(inode, alloc_start, + alloc_end - cur_offset); return ret; } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index aa6faba..359ee86 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -495,10 +495,9 @@ again: ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_space(inode, 0, prealloc); + btrfs_delalloc_release_metadata(inode, prealloc); goto out_put; } - btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 08dfc57..e6811c42 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -566,6 +566,8 @@ cont: PAGE_SET_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); goto free_pages_out; } } @@ -742,7 +744,7 @@ retry: lock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); - ret = btrfs_reserve_extent(root, + ret = btrfs_reserve_extent(root, async_extent->ram_size, async_extent->compressed_size, async_extent->compressed_size, 0, alloc_hint, &ins, 1, 1); @@ -969,7 +971,8 @@ static noinline int cow_file_range(struct inode *inode, EXTENT_DEFRAG, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); - + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -989,7 +992,7 @@ static noinline int cow_file_range(struct inode *inode, unsigned long op; cur_alloc_size = disk_num_bytes; - ret = btrfs_reserve_extent(root, cur_alloc_size, + ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret < 0) @@ -1489,8 +1492,10 @@ out_check: extent_clear_unlock_delalloc(inode, cur_offset, cur_offset + num_bytes - 1, locked_page, EXTENT_LOCKED | - EXTENT_DELALLOC, PAGE_UNLOCK | - PAGE_SET_PRIVATE2); + EXTENT_DELALLOC | + EXTENT_CLEAR_DATA_RESV, + PAGE_UNLOCK | PAGE_SET_PRIVATE2); + if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); cur_offset = extent_end; @@ -1807,7 +1812,9 @@ static void btrfs_clear_bit_hook(struct inode *inode, return; if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID - && do_list && !(state->state & EXTENT_NORESERVE)) + && do_list && !(state->state & EXTENT_NORESERVE) + && (*bits & (EXTENT_DO_ACCOUNTING | + EXTENT_CLEAR_DATA_RESV))) btrfs_free_reserved_data_space_noquota(inode, state->start, len); @@ -7251,7 +7258,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, int ret; alloc_hint = get_extent_allocation_hint(inode, start, len); - ret = btrfs_reserve_extent(root, len, root->sectorsize, 0, + ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret) return ERR_PTR(ret); @@ -7751,6 +7758,13 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ret = PTR_ERR(em2); goto unlock_err; } + /* + * For inode marked NODATACOW or extent marked PREALLOC, + * use the existing or preallocated extent, so does not + * need to adjust btrfs_space_info's bytes_may_use. + */ + btrfs_free_reserved_data_space_noquota(inode, + start, len); goto unlock; } } @@ -7785,7 +7799,6 @@ unlock: i_size_write(inode, start + len); adjust_dio_outstanding_extents(inode, dio_data, len); - btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; dio_data->unsubmitted_oe_range_end = start + len; @@ -10306,6 +10319,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, u64 last_alloc = (u64)-1; int ret = 0; bool own_trans = true; + u64 end = start + num_bytes - 1; if (trans) own_trans = false; @@ -10327,8 +10341,8 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, * sized chunks. */ cur_bytes = min(cur_bytes, last_alloc); - ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, - *alloc_hint, &ins, 1, 0); + ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes, + min_size, 0, *alloc_hint, &ins, 1, 0); if (ret) { if (own_trans) btrfs_end_transaction(trans, root); @@ -10414,6 +10428,9 @@ next: if (own_trans) btrfs_end_transaction(trans, root); } + if (cur_offset < end) + btrfs_free_reserved_data_space(inode, cur_offset, + end - cur_offset + 1); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 14ed1e9..b2a2da5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5084,7 +5084,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - return btrfs_qgroup_wait_for_completion(root->fs_info); + return btrfs_qgroup_wait_for_completion(root->fs_info, true); } static long _btrfs_ioctl_set_received_subvol(struct file *file, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 93ee1c1..8db2e29 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, goto out; fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; @@ -1453,10 +1453,9 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, return ret; } -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record) +int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record) { struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node; struct rb_node *parent_node = NULL; @@ -1475,12 +1474,42 @@ btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, else if (bytenr > entry->bytenr) p = &(*p)->rb_right; else - return entry; + return 1; } rb_link_node(&record->node, parent_node, p); rb_insert_color(&record->node, &delayed_refs->dirty_extent_root); - return NULL; + return 0; +} + +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag) +{ + struct btrfs_qgroup_extent_record *record; + struct btrfs_delayed_ref_root *delayed_refs; + int ret; + + if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0) + return 0; + if (WARN_ON(trans == NULL)) + return -EINVAL; + record = kmalloc(sizeof(*record), gfp_flag); + if (!record) + return -ENOMEM; + + delayed_refs = &trans->transaction->delayed_refs; + record->bytenr = bytenr; + record->num_bytes = num_bytes; + record->old_roots = NULL; + + spin_lock(&delayed_refs->lock); + ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs, + record); + spin_unlock(&delayed_refs->lock); + if (ret > 0) + kfree(record); + return 0; } #define UPDATE_NEW 0 @@ -2303,6 +2332,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) int err = -ENOMEM; int ret = 0; + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = true; + mutex_unlock(&fs_info->qgroup_rescan_lock); + path = btrfs_alloc_path(); if (!path) goto out; @@ -2369,6 +2402,9 @@ out: } done: + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = false; + mutex_unlock(&fs_info->qgroup_rescan_lock); complete_all(&fs_info->qgroup_rescan_completion); } @@ -2487,20 +2523,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible) { int running; int ret = 0; mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN; + running = fs_info->qgroup_rescan_running; spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - if (running) + if (!running) + return 0; + + if (interruptible) ret = wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion); + else + wait_for_completion(&fs_info->qgroup_rescan_completion); return ret; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 710887c..1bc64c8 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info); +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible); int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst); int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, @@ -63,10 +64,35 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record); +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * No lock version, caller must acquire delayed ref lock and allocate memory. + * + * Return 0 for success insert + * Return >0 for existing record, caller can free @record safely. + * Error is not possible + */ +int btrfs_qgroup_insert_dirty_extent_nolock( + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record); + +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * Better encapsulated version. + * + * Return 0 if the operation is done. + * Return <0 for error, like memory allocation failure or invalid parameter + * (NULL trans) + */ +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag); + int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b26a5ae..8a2c2a0 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -31,6 +31,7 @@ #include "async-thread.h" #include "free-space-cache.h" #include "inode-map.h" +#include "qgroup.h" /* * backref_node, mapping_node and tree_block start with this @@ -3037,15 +3038,19 @@ int prealloc_file_extent_cluster(struct inode *inode, u64 num_bytes; int nr = 0; int ret = 0; + u64 prealloc_start = cluster->start - offset; + u64 prealloc_end = cluster->end - offset; + u64 cur_offset; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); - ret = btrfs_check_data_free_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + ret = btrfs_check_data_free_space(inode, prealloc_start, + prealloc_end + 1 - prealloc_start); if (ret) goto out; + cur_offset = prealloc_start; while (nr < cluster->nr) { start = cluster->boundary[nr] - offset; if (nr + 1 < cluster->nr) @@ -3055,16 +3060,21 @@ int prealloc_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, start, end); num_bytes = end + 1 - start; + if (cur_offset < start) + btrfs_free_reserved_data_space(inode, cur_offset, + start - cur_offset); ret = btrfs_prealloc_file_range(inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); + cur_offset = end + 1; unlock_extent(&BTRFS_I(inode)->io_tree, start, end); if (ret) break; nr++; } - btrfs_free_reserved_data_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + if (cur_offset < prealloc_end) + btrfs_free_reserved_data_space(inode, cur_offset, + prealloc_end + 1 - cur_offset); out: inode_unlock(inode); return ret; @@ -3916,6 +3926,90 @@ int prepare_to_relocate(struct reloc_control *rc) return 0; } +/* + * Qgroup fixer for data chunk relocation. + * The data relocation is done in the following steps + * 1) Copy data extents into data reloc tree + * 2) Create tree reloc tree(special snapshot) for related subvolumes + * 3) Modify file extents in tree reloc tree + * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks + * + * The problem is, data and tree reloc tree are not accounted to qgroup, + * and 4) will only info qgroup to track tree blocks change, not file extents + * in the tree blocks. + * + * The good news is, related data extents are all in data reloc tree, so we + * only need to info qgroup to track all file extents in data reloc tree + * before commit trans. + */ +static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans, + struct reloc_control *rc) +{ + struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; + struct inode *inode = rc->data_inode; + struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root; + struct btrfs_path *path; + struct btrfs_key key; + int ret = 0; + + if (!fs_info->quota_enabled) + return 0; + + /* + * Only for stage where we update data pointers the qgroup fix is + * valid. + * For MOVING_DATA stage, we will miss the timing of swapping tree + * blocks, and won't fix it. + */ + if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found)) + return 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + key.objectid = btrfs_ino(inode); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0); + if (ret < 0) + goto out; + + lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1); + while (1) { + struct btrfs_file_extent_item *fi; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid > btrfs_ino(inode)) + break; + if (key.type != BTRFS_EXTENT_DATA_KEY) + goto next; + fi = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + if (btrfs_file_extent_type(path->nodes[0], fi) != + BTRFS_FILE_EXTENT_REG) + goto next; + ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info, + btrfs_file_extent_disk_bytenr(path->nodes[0], fi), + btrfs_file_extent_disk_num_bytes(path->nodes[0], fi), + GFP_NOFS); + if (ret < 0) + break; +next: + ret = btrfs_next_item(data_reloc_root, path); + if (ret < 0) + break; + if (ret > 0) { + ret = 0; + break; + } + } + unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1); +out: + btrfs_free_path(path); + return ret; +} + static noinline_for_stack int relocate_block_group(struct reloc_control *rc) { struct rb_root blocks = RB_ROOT; @@ -4102,10 +4196,16 @@ restart: /* get rid of pinned extents */ trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + btrfs_commit_transaction(trans, rc->extent_root); out_free: btrfs_free_block_rsv(rc->extent_root, rc->block_rsv); btrfs_free_path(path); @@ -4468,10 +4568,16 @@ int btrfs_recover_relocation(struct btrfs_root *root) unset_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - err = btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + err = btrfs_commit_transaction(trans, rc->extent_root); out_free: kfree(rc); out: diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7fd7e18..0912960 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -272,6 +272,23 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid = key.offset; key.offset++; + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + root = btrfs_lookup_fs_root(tree_root->fs_info, + root_key.objectid); + if (root) { + WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, + &root->state)); + if (btrfs_root_refs(&root->root_item) == 0) + btrfs_add_dead_root(root); + continue; + } + root = btrfs_read_fs_root(tree_root, &root_key); err = PTR_ERR_OR_ZERO(root); if (err && err != -ENOENT) { @@ -310,16 +327,8 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); - /* - * The root might have been inserted already, as before we look - * for orphan roots, log replay might have happened, which - * triggers a transaction commit and qgroup accounting, which - * in turn reads and inserts fs roots while doing backref - * walking. - */ - if (err == -EEXIST) - err = 0; if (err) { + BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 864ce33..4071fe2 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2241,6 +2241,13 @@ static int btrfs_freeze(struct super_block *sb) struct btrfs_trans_handle *trans; struct btrfs_root *root = btrfs_sb(sb)->tree_root; + root->fs_info->fs_frozen = 1; + /* + * We don't need a barrier here, we'll wait for any transaction that + * could be in progress on other threads (and do delayed iputs that + * we want to avoid on a frozen filesystem), or do the commit + * ourselves. + */ trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { /* no transaction, don't bother */ @@ -2251,6 +2258,14 @@ static int btrfs_freeze(struct super_block *sb) return btrfs_commit_transaction(trans, root); } +static int btrfs_unfreeze(struct super_block *sb) +{ + struct btrfs_root *root = btrfs_sb(sb)->tree_root; + + root->fs_info->fs_frozen = 0; + return 0; +} + static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); @@ -2299,6 +2314,7 @@ static const struct super_operations btrfs_super_ops = { .statfs = btrfs_statfs, .remount_fs = btrfs_remount, .freeze_fs = btrfs_freeze, + .unfreeze_fs = btrfs_unfreeze, }; static const struct file_operations btrfs_ctl_fops = { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9cca0a7..95d4191 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2278,8 +2278,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); + /* + * If fs has been frozen, we can not handle delayed iputs, otherwise + * it'll result in deadlock about SB_FREEZE_FS. + */ if (current != root->fs_info->transaction_kthread && - current != root->fs_info->cleaner_kthread) + current != root->fs_info->cleaner_kthread && + !root->fs_info->fs_frozen) btrfs_run_delayed_iputs(root); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fff3f3e..e935035 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -27,6 +27,7 @@ #include "backref.h" #include "hash.h" #include "compression.h" +#include "qgroup.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); + /* + * Manually record dirty extent, as here we did a shallow + * file extent item copy and skip normal backref update, + * but modifying extent tree all by ourselves. + * So need to manually record dirty extent for qgroup, + * as the owner of the file extent changed from log tree + * (doesn't affect qgroup) to fs/file tree(affects qgroup) + */ + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + btrfs_file_extent_disk_bytenr(eb, item), + btrfs_file_extent_disk_num_bytes(eb, item), + GFP_NOFS); + if (ret < 0) + goto out; + if (ins.objectid > 0) { u64 csum_start; u64 csum_end; @@ -2807,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ mutex_unlock(&root->log_mutex); - btrfs_init_log_ctx(&root_log_ctx); + btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); atomic_inc(&log_root_tree->log_batch); @@ -4741,7 +4757,8 @@ again: if (ret < 0) { err = ret; goto out_unlock; - } else if (ret > 0) { + } else if (ret > 0 && ctx && + other_ino != btrfs_ino(ctx->inode)) { struct btrfs_key inode_key; struct inode *other_inode; diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index a9f1b75..ab858e3 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -30,15 +30,18 @@ struct btrfs_log_ctx { int log_transid; int io_err; bool log_new_dentries; + struct inode *inode; struct list_head list; }; -static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx) +static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, + struct inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->io_err = 0; ctx->log_new_dentries = false; + ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 51f1255..035efce 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -834,10 +834,6 @@ static void __free_device(struct work_struct *work) struct btrfs_device *device; device = container_of(work, struct btrfs_device, rcu_work); - - if (device->bdev) - blkdev_put(device->bdev, device->mode); - rcu_string_free(device->name); kfree(device); } @@ -852,6 +848,17 @@ static void free_device(struct rcu_head *head) schedule_work(&device->rcu_work); } +static void btrfs_close_bdev(struct btrfs_device *device) +{ + if (device->bdev && device->writeable) { + sync_blockdev(device->bdev); + invalidate_bdev(device->bdev); + } + + if (device->bdev) + blkdev_put(device->bdev, device->mode); +} + static void btrfs_close_one_device(struct btrfs_device *device) { struct btrfs_fs_devices *fs_devices = device->fs_devices; @@ -870,10 +877,7 @@ static void btrfs_close_one_device(struct btrfs_device *device) if (device->missing) fs_devices->missing_devices--; - if (device->bdev && device->writeable) { - sync_blockdev(device->bdev); - invalidate_bdev(device->bdev); - } + btrfs_close_bdev(device); new_device = btrfs_alloc_device(NULL, &device->devid, device->uuid); @@ -1932,6 +1936,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid) btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device); } + btrfs_close_bdev(device); + call_rcu(&device->rcu, free_device); num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1; @@ -2025,6 +2031,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, /* zero out the old super if it is writable */ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); } + + btrfs_close_bdev(srcdev); + call_rcu(&srcdev->rcu, free_device); /* @@ -2080,6 +2089,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, * the device_list_mutex lock. */ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); + + btrfs_close_bdev(tgtdev); call_rcu(&tgtdev->rcu, free_device); } diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index eea6491..466f7d6 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -607,20 +607,54 @@ static const struct file_operations format2_fops; static const struct file_operations format3_fops; static const struct file_operations format4_fops; -static int table_open(struct inode *inode, struct file *file) +static int table_open1(struct inode *inode, struct file *file) { struct seq_file *seq; - int ret = -1; + int ret; - if (file->f_op == &format1_fops) - ret = seq_open(file, &format1_seq_ops); - else if (file->f_op == &format2_fops) - ret = seq_open(file, &format2_seq_ops); - else if (file->f_op == &format3_fops) - ret = seq_open(file, &format3_seq_ops); - else if (file->f_op == &format4_fops) - ret = seq_open(file, &format4_seq_ops); + ret = seq_open(file, &format1_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open2(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format2_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open3(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format3_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open4(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + ret = seq_open(file, &format4_seq_ops); if (ret) return ret; @@ -631,7 +665,7 @@ static int table_open(struct inode *inode, struct file *file) static const struct file_operations format1_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open1, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -639,7 +673,7 @@ static const struct file_operations format1_fops = { static const struct file_operations format2_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open2, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -647,7 +681,7 @@ static const struct file_operations format2_fops = { static const struct file_operations format3_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open3, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -655,7 +689,7 @@ static const struct file_operations format3_fops = { static const struct file_operations format4_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open4, .read = seq_read, .llseek = seq_lseek, .release = seq_release diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3131747..c6ea25a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5466,8 +5466,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) sbi->s_want_extra_isize, iloc, handle); if (ret) { - ext4_set_inode_state(inode, - EXT4_STATE_NO_EXPAND); if (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count)) { ext4_warning(inode->i_sb, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1c593aa..3ec8708 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2211,6 +2211,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, + ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -2241,6 +2242,11 @@ static int ext4_check_descriptors(struct super_block *sb, grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); + if (block_bitmap == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Block bitmap for group %u overlaps " + "superblock", i); + } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " @@ -2248,6 +2254,11 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); + if (inode_bitmap == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode bitmap for group %u overlaps " + "superblock", i); + } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " @@ -2255,6 +2266,11 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } inode_table = ext4_inode_table(sb, gdp); + if (inode_table == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode table for group %u overlaps " + "superblock", i); + } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " @@ -3757,7 +3773,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - if (!ext4_check_descriptors(sb, &first_not_zeroed)) { + if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 39e9cfb..2eb935c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1353,15 +1353,19 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, size_t min_offs, free; int total_ino; void *base, *start, *end; - int extra_isize = 0, error = 0, tried_min_extra_isize = 0; + int error = 0, tried_min_extra_isize = 0; int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize); + int isize_diff; /* How much do we need to grow i_extra_isize */ down_write(&EXT4_I(inode)->xattr_sem); + /* + * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty + */ + ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND); retry: - if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) { - up_write(&EXT4_I(inode)->xattr_sem); - return 0; - } + isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; + if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) + goto out; header = IHDR(inode, raw_inode); entry = IFIRST(header); @@ -1382,7 +1386,7 @@ retry: goto cleanup; free = ext4_xattr_free_space(last, &min_offs, base, &total_ino); - if (free >= new_extra_isize) { + if (free >= isize_diff) { entry = IFIRST(header); ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize - new_extra_isize, (void *)raw_inode + @@ -1390,8 +1394,7 @@ retry: (void *)header, total_ino, inode->i_sb->s_blocksize); EXT4_I(inode)->i_extra_isize = new_extra_isize; - error = 0; - goto cleanup; + goto out; } /* @@ -1414,7 +1417,7 @@ retry: end = bh->b_data + bh->b_size; min_offs = end - base; free = ext4_xattr_free_space(first, &min_offs, base, NULL); - if (free < new_extra_isize) { + if (free < isize_diff) { if (!tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; @@ -1428,7 +1431,7 @@ retry: free = inode->i_sb->s_blocksize; } - while (new_extra_isize > 0) { + while (isize_diff > 0) { size_t offs, size, entry_size; struct ext4_xattr_entry *small_entry = NULL; struct ext4_xattr_info i = { @@ -1459,7 +1462,7 @@ retry: EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) + EXT4_XATTR_LEN(last->e_name_len); if (total_size <= free && total_size < min_total_size) { - if (total_size < new_extra_isize) { + if (total_size < isize_diff) { small_entry = last; } else { entry = last; @@ -1514,22 +1517,22 @@ retry: error = ext4_xattr_ibody_set(handle, inode, &i, is); if (error) goto cleanup; + total_ino -= entry_size; entry = IFIRST(header); - if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize) - shift_bytes = new_extra_isize; + if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff) + shift_bytes = isize_diff; else - shift_bytes = entry_size + size; + shift_bytes = entry_size + EXT4_XATTR_SIZE(size); /* Adjust the offsets and shift the remaining entries ahead */ - ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize - - shift_bytes, (void *)raw_inode + - EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes, - (void *)header, total_ino - entry_size, - inode->i_sb->s_blocksize); + ext4_xattr_shift_entries(entry, -shift_bytes, + (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + + EXT4_I(inode)->i_extra_isize + shift_bytes, + (void *)header, total_ino, inode->i_sb->s_blocksize); - extra_isize += shift_bytes; - new_extra_isize -= shift_bytes; - EXT4_I(inode)->i_extra_isize = extra_isize; + isize_diff -= shift_bytes; + EXT4_I(inode)->i_extra_isize += shift_bytes; + header = IHDR(inode, raw_inode); i.name = b_entry_name; i.value = buffer; @@ -1551,6 +1554,8 @@ retry: kfree(bs); } brelse(bh); +out: + ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND); up_write(&EXT4_I(inode)->xattr_sem); return 0; @@ -1562,6 +1567,10 @@ cleanup: kfree(is); kfree(bs); brelse(bh); + /* + * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode + * size expansion failed. + */ up_write(&EXT4_I(inode)->xattr_sem); return error; } diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 69dd3e6..a92e783 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -24,6 +24,7 @@ #define EXT4_XATTR_INDEX_SYSTEM 7 #define EXT4_XATTR_INDEX_RICHACL 8 #define EXT4_XATTR_INDEX_ENCRYPTION 9 +#define EXT4_XATTR_INDEX_HURD 10 /* Reserved for Hurd */ struct ext4_xattr_header { __le32 h_magic; /* magic number for identification */ diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index d64d2a5..ccb401e 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1699,11 +1699,11 @@ static int f2fs_write_end(struct file *file, trace_f2fs_write_end(inode, pos, len, copied); set_page_dirty(page); - f2fs_put_page(page, 1); if (pos + copied > i_size_read(inode)) f2fs_i_size_write(inode, pos + copied); + f2fs_put_page(page, 1); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 675fa79..14f5fe2 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -538,7 +538,7 @@ struct f2fs_nm_info { /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ struct radix_tree_root nat_set_root;/* root of the nat set cache */ - struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ + struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ unsigned int nat_cnt; /* the # of cached nat entries */ unsigned int dirty_nat_cnt; /* total num of nat entries in set */ @@ -787,7 +787,7 @@ struct f2fs_sb_info { struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ struct inode *meta_inode; /* cache meta blocks */ struct mutex cp_mutex; /* checkpoint procedure lock */ - struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */ + struct rw_semaphore cp_rwsem; /* blocking FS operations */ struct rw_semaphore node_write; /* locking node writes */ wait_queue_head_t cp_wait; unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ @@ -1074,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) { - percpu_down_read(&sbi->cp_rwsem); + down_read(&sbi->cp_rwsem); } static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) { - percpu_up_read(&sbi->cp_rwsem); + up_read(&sbi->cp_rwsem); } static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { - percpu_down_write(&sbi->cp_rwsem); + down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) { - percpu_up_write(&sbi->cp_rwsem); + up_write(&sbi->cp_rwsem); } static inline int __get_cp_reason(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0e493f6..47abb96 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2086,15 +2086,19 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (unlikely(f2fs_readonly(src->i_sb))) return -EROFS; - if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode)) - return -EISDIR; + if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) + return -EINVAL; if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) return -EOPNOTSUPP; inode_lock(src); - if (src != dst) - inode_lock(dst); + if (src != dst) { + if (!inode_trylock(dst)) { + ret = -EBUSY; + goto out; + } + } ret = -EINVAL; if (pos_in + len > src->i_size || pos_in + len < pos_in) @@ -2152,6 +2156,7 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, out_unlock: if (src != dst) inode_unlock(dst); +out: inode_unlock(src); return ret; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b2fa4b6..f75d197 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -206,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool need = false; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { if (!get_nat_flag(e, IS_CHECKPOINTED) && !get_nat_flag(e, HAS_FSYNCED_INODE)) need = true; } - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need; } @@ -223,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool is_cp = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return is_cp; } @@ -237,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool need_update = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need_update; } @@ -284,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { e = grab_nat_entry(nm_i, ni->nid); @@ -334,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) @@ -342,7 +342,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; - percpu_down_write(&nm_i->nat_tree_lock); + if (!down_write_trylock(&nm_i->nat_tree_lock)) + return 0; while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; @@ -351,7 +352,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) __del_from_nat_cache(nm_i, ne); nr_shrink--; } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } @@ -373,13 +374,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->nid = nid; /* Check nat cache */ - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return; } @@ -403,11 +404,11 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); /* cache nat entry */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } /* @@ -1788,7 +1789,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1820,7 +1821,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } up_read(&curseg->journal_rwsem); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -2209,7 +2210,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!nm_i->dirty_nat_cnt) return; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); /* * if there are no enough space in journal to store dirty nat @@ -2232,7 +2233,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); } @@ -2268,8 +2269,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->free_nid_list_lock); - if (percpu_init_rwsem(&nm_i->nat_tree_lock)) - return -ENOMEM; + init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -2326,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) spin_unlock(&nm_i->free_nid_list_lock); /* destroy nat cache */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; @@ -2351,9 +2351,8 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) kmem_cache_free(nat_entry_set_slab, setvec[idx]); } } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); - percpu_free_rwsem(&nm_i->nat_tree_lock); kfree(nm_i->nat_bitmap); sbi->nm_info = NULL; kfree(nm_i); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1b86d3f..7f863a6 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -706,8 +706,6 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi) percpu_counter_destroy(&sbi->nr_pages[i]); percpu_counter_destroy(&sbi->alloc_valid_block_count); percpu_counter_destroy(&sbi->total_valid_inode_count); - - percpu_free_rwsem(&sbi->cp_rwsem); } static void f2fs_put_super(struct super_block *sb) @@ -1483,9 +1481,6 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) { int i, err; - if (percpu_init_rwsem(&sbi->cp_rwsem)) - return -ENOMEM; - for (i = 0; i < NR_COUNT_TYPE; i++) { err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL); if (err) @@ -1686,6 +1681,7 @@ try_onemore: sbi->write_io[i].bio = NULL; } + init_rwsem(&sbi->cp_rwsem); init_waitqueue_head(&sbi->cp_wait); init_sb_info(sbi); @@ -84,8 +84,11 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, * Now the data has been copied, commit the range we've copied. This * should not fail unless the filesystem has had a fatal error. */ - ret = ops->iomap_end(inode, pos, length, written > 0 ? written : 0, - flags, &iomap); + if (ops->iomap_end) { + ret = ops->iomap_end(inode, pos, length, + written > 0 ? written : 0, + flags, &iomap); + } return written ? written : ret; } @@ -194,12 +197,9 @@ again: if (mapping_writably_mapped(inode->i_mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); status = iomap_write_end(inode, pos, bytes, copied, page); if (unlikely(status < 0)) @@ -470,13 +470,18 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, if (ret) return ret; - ret = filemap_write_and_wait(inode->i_mapping); - if (ret) - return ret; + if (fi->fi_flags & FIEMAP_FLAG_SYNC) { + ret = filemap_write_and_wait(inode->i_mapping); + if (ret) + return ret; + } while (len > 0) { ret = iomap_apply(inode, start, len, 0, ops, &ctx, iomap_fiemap_actor); + /* inode with no (attribute) mapping will give ENOENT */ + if (ret == -ENOENT) + break; if (ret < 0) return ret; if (ret == 0) diff --git a/fs/seq_file.c b/fs/seq_file.c index 19f532e..6dc4296 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -223,8 +223,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) size -= n; buf += n; copied += n; - if (!m->count) + if (!m->count) { + m->from = 0; m->index++; + } if (!size) goto Done; } diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index b45345d..51157da 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) p = c->gap_lebs; do { - ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs); + ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs); written = layout_leb_in_gaps(c, p); if (written < 0) { err = written; diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e237811..11a0041 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -575,7 +575,8 @@ static int ubifs_xattr_get(const struct xattr_handler *handler, dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name, inode->i_ino, dentry, size); - return __ubifs_getxattr(inode, name, buffer, size); + name = xattr_full_name(handler, name); + return __ubifs_getxattr(inode, name, buffer, size); } static int ubifs_xattr_set(const struct xattr_handler *handler, @@ -586,6 +587,8 @@ static int ubifs_xattr_set(const struct xattr_handler *handler, dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", name, inode->i_ino, dentry, size); + name = xattr_full_name(handler, name); + if (value) return __ubifs_setxattr(inode, name, value, size, flags); else diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 776ae2f..3dd8f1d 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1582,6 +1582,7 @@ xfs_alloc_ag_vextent_small( xfs_extlen_t *flenp, /* result length */ int *stat) /* status: 0-freelist, 1-normal/none */ { + struct xfs_owner_info oinfo; int error; xfs_agblock_t fbno; xfs_extlen_t flen; @@ -1624,6 +1625,18 @@ xfs_alloc_ag_vextent_small( error0); args->wasfromfl = 1; trace_xfs_alloc_small_freelist(args); + + /* + * If we're feeding an AGFL block to something that + * doesn't live in the free space, we need to clear + * out the OWN_AG rmap. + */ + xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG); + error = xfs_rmap_free(args->tp, args->agbp, args->agno, + fbno, 1, &oinfo); + if (error) + goto error0; + *stat = 0; return 0; } @@ -2264,6 +2277,7 @@ xfs_alloc_log_agf( offsetof(xfs_agf_t, agf_longest), offsetof(xfs_agf_t, agf_btreeblks), offsetof(xfs_agf_t, agf_uuid), + offsetof(xfs_agf_t, agf_rmap_blocks), sizeof(xfs_agf_t) }; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index f814d42..e6a8bea 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -640,12 +640,15 @@ typedef struct xfs_agf { __be32 agf_btreeblks; /* # of blocks held in AGF btrees */ uuid_t agf_uuid; /* uuid of filesystem */ + __be32 agf_rmap_blocks; /* rmapbt blocks used */ + __be32 agf_padding; /* padding */ + /* * reserve some contiguous space for future logged fields before we add * the unlogged fields. This makes the range logging via flags and * structure offsets much simpler. */ - __be64 agf_spare64[16]; + __be64 agf_spare64[15]; /* unlogged fields, written during buffer writeback. */ __be64 agf_lsn; /* last write sequence */ @@ -670,7 +673,8 @@ typedef struct xfs_agf { #define XFS_AGF_LONGEST 0x00000400 #define XFS_AGF_BTREEBLKS 0x00000800 #define XFS_AGF_UUID 0x00001000 -#define XFS_AGF_NUM_BITS 13 +#define XFS_AGF_RMAP_BLOCKS 0x00002000 +#define XFS_AGF_NUM_BITS 14 #define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1) #define XFS_AGF_FLAGS \ @@ -686,7 +690,8 @@ typedef struct xfs_agf { { XFS_AGF_FREEBLKS, "FREEBLKS" }, \ { XFS_AGF_LONGEST, "LONGEST" }, \ { XFS_AGF_BTREEBLKS, "BTREEBLKS" }, \ - { XFS_AGF_UUID, "UUID" } + { XFS_AGF_UUID, "UUID" }, \ + { XFS_AGF_RMAP_BLOCKS, "RMAP_BLOCKS" } /* disk block (xfs_daddr_t) in the AG */ #define XFS_AGF_DADDR(mp) ((xfs_daddr_t)(1 << (mp)->m_sectbb_log)) diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index bc1faeb..17b8eeb 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -98,6 +98,8 @@ xfs_rmapbt_alloc_block( union xfs_btree_ptr *new, int *stat) { + struct xfs_buf *agbp = cur->bc_private.a.agbp; + struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp); int error; xfs_agblock_t bno; @@ -124,6 +126,8 @@ xfs_rmapbt_alloc_block( xfs_trans_agbtree_delta(cur->bc_tp, 1); new->s = cpu_to_be32(bno); + be32_add_cpu(&agf->agf_rmap_blocks, 1); + xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); *stat = 1; @@ -143,6 +147,8 @@ xfs_rmapbt_free_block( bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp)); trace_xfs_rmapbt_free_block(cur->bc_mp, cur->bc_private.a.agno, bno, 1); + be32_add_cpu(&agf->agf_rmap_blocks, -1); + xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1); if (error) return error; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 47a318c..607cc29 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -115,7 +115,6 @@ xfs_buf_ioacct_dec( if (!(bp->b_flags & _XBF_IN_FLIGHT)) return; - ASSERT(bp->b_flags & XBF_ASYNC); bp->b_flags &= ~_XBF_IN_FLIGHT; percpu_counter_dec(&bp->b_target->bt_io_count); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ed95e5b..e612a02 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -741,9 +741,20 @@ xfs_file_dax_write( * page is inserted into the pagecache when we have to serve a write * fault on a hole. It should never be dirtied and can simply be * dropped from the pagecache once we get real data for the page. + * + * XXX: This is racy against mmap, and there's nothing we can do about + * it. dax_do_io() should really do this invalidation internally as + * it will know if we've allocated over a holei for this specific IO and + * if so it needs to update the mapping tree and invalidate existing + * PTEs over the newly allocated range. Remove this invalidation when + * dax_do_io() is fixed up. */ if (mapping->nrpages) { - ret = invalidate_inode_pages2(mapping); + loff_t end = iocb->ki_pos + iov_iter_count(from) - 1; + + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, + end >> PAGE_SHIFT); WARN_ON_ONCE(ret); } diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 0f96847..0b7f986 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -248,6 +248,7 @@ xfs_growfs_data_private( agf->agf_roots[XFS_BTNUM_RMAPi] = cpu_to_be32(XFS_RMAP_BLOCK(mp)); agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1); + agf->agf_rmap_blocks = cpu_to_be32(1); } agf->agf_flfirst = cpu_to_be32(1); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 2114d53..2af0dda 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -715,12 +715,16 @@ xfs_iomap_write_allocate( * is in the delayed allocation extent on which we sit * but before our buffer starts. */ - nimaps = 0; while (nimaps == 0) { nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); - - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, nres, + /* + * We have already reserved space for the extent and any + * indirect blocks when creating the delalloc extent, + * there is no need to reserve space in this transaction + * again. + */ + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; @@ -1037,20 +1041,14 @@ xfs_file_iomap_begin( return error; trace_xfs_iomap_alloc(ip, offset, length, 0, &imap); - xfs_bmbt_to_iomap(ip, iomap, &imap); - } else if (nimaps) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - trace_xfs_iomap_found(ip, offset, length, 0, &imap); - xfs_bmbt_to_iomap(ip, iomap, &imap); } else { + ASSERT(nimaps); + xfs_iunlock(ip, XFS_ILOCK_EXCL); - trace_xfs_iomap_not_found(ip, offset, length, 0, &imap); - iomap->blkno = IOMAP_NULL_BLOCK; - iomap->type = IOMAP_HOLE; - iomap->offset = offset; - iomap->length = length; + trace_xfs_iomap_found(ip, offset, length, 0, &imap); } + xfs_bmbt_to_iomap(ip, iomap, &imap); return 0; } @@ -1112,3 +1110,48 @@ struct iomap_ops xfs_iomap_ops = { .iomap_begin = xfs_file_iomap_begin, .iomap_end = xfs_file_iomap_end, }; + +static int +xfs_xattr_iomap_begin( + struct inode *inode, + loff_t offset, + loff_t length, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length); + struct xfs_bmbt_irec imap; + int nimaps = 1, error = 0; + unsigned lockmode; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + lockmode = xfs_ilock_data_map_shared(ip); + + /* if there are no attribute fork or extents, return ENOENT */ + if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) { + error = -ENOENT; + goto out_unlock; + } + + ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL); + error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, + &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK); +out_unlock: + xfs_iunlock(ip, lockmode); + + if (!error) { + ASSERT(nimaps); + xfs_bmbt_to_iomap(ip, iomap, &imap); + } + + return error; +} + +struct iomap_ops xfs_xattr_iomap_ops = { + .iomap_begin = xfs_xattr_iomap_begin, +}; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index e066d04..fb8aca3 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -35,5 +35,6 @@ void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); extern struct iomap_ops xfs_iomap_ops; +extern struct iomap_ops xfs_xattr_iomap_ops; #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index ab820f8..b24c310 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1009,7 +1009,14 @@ xfs_vn_fiemap( int error; xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED); - error = iomap_fiemap(inode, fieinfo, start, length, &xfs_iomap_ops); + if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { + fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; + error = iomap_fiemap(inode, fieinfo, start, length, + &xfs_xattr_iomap_ops); + } else { + error = iomap_fiemap(inode, fieinfo, start, length, + &xfs_iomap_ops); + } xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED); return error; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 551b7e2..7e88bec 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1298,7 +1298,6 @@ DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc); DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct); DEFINE_IOMAP_EVENT(xfs_iomap_alloc); DEFINE_IOMAP_EVENT(xfs_iomap_found); -DEFINE_IOMAP_EVENT(xfs_iomap_not_found); DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), diff --git a/include/linux/bio.h b/include/linux/bio.h index 59ffaa6..23ddf4b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -71,7 +71,8 @@ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && - bio_op(bio) != REQ_OP_DISCARD) + bio_op(bio) != REQ_OP_DISCARD && + bio_op(bio) != REQ_OP_SECURE_ERASE) return true; return false; @@ -79,7 +80,9 @@ static inline bool bio_has_data(struct bio *bio) static inline bool bio_no_advance_iter(struct bio *bio) { - return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME; + return bio_op(bio) == REQ_OP_DISCARD || + bio_op(bio) == REQ_OP_SECURE_ERASE || + bio_op(bio) == REQ_OP_WRITE_SAME; } static inline bool bio_is_rw(struct bio *bio) @@ -199,6 +202,9 @@ static inline unsigned bio_segments(struct bio *bio) if (bio_op(bio) == REQ_OP_DISCARD) return 1; + if (bio_op(bio) == REQ_OP_SECURE_ERASE) + return 1; + if (bio_op(bio) == REQ_OP_WRITE_SAME) return 1; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c210b6..e79055c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -882,7 +882,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { - if (unlikely(op == REQ_OP_DISCARD)) + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(op == REQ_OP_WRITE_SAME)) @@ -913,7 +913,9 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset), diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e294939..8dbc892 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -242,7 +242,11 @@ */ #define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +/* + * sparse (__CHECKER__) pretends to be gcc, but can't do constant + * folding in __builtin_bswap*() (yet), so don't set these for it. + */ +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -250,7 +254,7 @@ #if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 1bb9548..436aa4e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -527,13 +527,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. * - * The seemingly unused void * variable is to validate @p is indeed a pointer - * type. All pointer types silently cast to void *. + * The seemingly unused size_t variable is to validate @p is indeed a pointer + * type by making sure it can be dereferenced. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ - __maybe_unused const void * const _________p2 = _________p1; \ + size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) diff --git a/include/linux/host1x.h b/include/linux/host1x.h index d2ba7d3..1ffbf2a 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -304,6 +304,8 @@ struct tegra_mipi_device; struct tegra_mipi_device *tegra_mipi_request(struct device *device); void tegra_mipi_free(struct tegra_mipi_device *device); +int tegra_mipi_enable(struct tegra_mipi_device *device); +int tegra_mipi_disable(struct tegra_mipi_device *device); int tegra_mipi_calibrate(struct tegra_mipi_device *device); #endif diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 56b0b7e..99ac022 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,6 +337,7 @@ */ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 #define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109 +#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307 #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 #define E_ITS_MAPD_DEVICE_OOR 0x010801 #define E_ITS_MAPC_PROCNUM_OOR 0x010902 diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h index 80ca889..664da00 100644 --- a/include/linux/netfilter/nfnetlink_acct.h +++ b/include/linux/netfilter/nfnetlink_acct.h @@ -15,6 +15,6 @@ struct nf_acct; struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); -extern int nfnl_acct_overquota(const struct sk_buff *skb, - struct nf_acct *nfacct); +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct); #endif /* _NFNL_ACCT_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 2599a98..fbc1fa6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1251,10 +1251,12 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); -#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ -#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ -#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ -#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */ +#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */ +#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */ +#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */ +#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */ +#define PCI_IRQ_ALL_TYPES \ + (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) /* kmem_cache style wrapper around pci_alloc_consistent() */ diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h index 76199b7..e302c44 100644 --- a/include/linux/smc91x.h +++ b/include/linux/smc91x.h @@ -1,6 +1,16 @@ #ifndef __SMC91X_H__ #define __SMC91X_H__ +/* + * These bits define which access sizes a platform can support, rather + * than the maximal access size. So, if your platform can do 16-bit + * and 32-bit accesses to the SMC91x device, but not 8-bit, set both + * SMC91X_USE_16BIT and SMC91X_USE_32BIT. + * + * The SMC91x driver requires at least one of SMC91X_USE_8BIT or + * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is + * an invalid configuration. + */ #define SMC91X_USE_8BIT (1 << 0) #define SMC91X_USE_16BIT (1 << 1) #define SMC91X_USE_32BIT (1 << 2) diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index d82cb60..ecc3e07 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -43,6 +43,8 @@ extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_jiffies(struct ctl_table *, int, diff --git a/include/net/tcp.h b/include/net/tcp.h index dd99679..d6ae365 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1521,6 +1521,8 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli { if (sk->sk_send_head == skb_unlinked) sk->sk_send_head = NULL; + if (tcp_sk(sk)->highest_sack == skb_unlinked) + tcp_sk(sk)->highest_sack = NULL; } static inline void tcp_init_send_head(struct sock *sk) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8e90dd2..e1f9673 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2115,22 +2115,17 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t len) { const void __user *p = udata->inbuf + offset; - bool ret = false; + bool ret; u8 *buf; if (len > USHRT_MAX) return false; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) + buf = memdup_user(p, len); + if (IS_ERR(buf)) return false; - if (copy_from_user(buf, p, len)) - goto free; - ret = !memchr_inv(buf, 0, len); - -free: kfree(buf); return ret; } diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 9c9c6ad..5cd4d4d 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -14,6 +14,7 @@ #include <linux/atmapi.h> #include <linux/atmioc.h> +#include <linux/time.h> #define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) /* get pool statistics */ diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h index 163e8ad..4bd1f55 100644 --- a/include/uapi/linux/if_pppol2tp.h +++ b/include/uapi/linux/if_pppol2tp.h @@ -16,7 +16,8 @@ #define _UAPI__LINUX_IF_PPPOL2TP_H #include <linux/types.h> - +#include <linux/in.h> +#include <linux/in6.h> /* Structure used to connect() the socket to a particular tunnel UDP * socket over IPv4. diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h index e128769..d37bbb1 100644 --- a/include/uapi/linux/if_pppox.h +++ b/include/uapi/linux/if_pppox.h @@ -21,8 +21,11 @@ #include <asm/byteorder.h> #include <linux/socket.h> +#include <linux/if.h> #include <linux/if_ether.h> #include <linux/if_pppol2tp.h> +#include <linux/in.h> +#include <linux/in6.h> /* For user-space programs to pick up these definitions * which they wouldn't get otherwise without defining __KERNEL__ diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 361b9f0..9865c8c 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -2,6 +2,9 @@ #define _UAPI_IF_TUNNEL_H_ #include <linux/types.h> +#include <linux/if.h> +#include <linux/ip.h> +#include <linux/in6.h> #include <asm/byteorder.h> diff --git a/include/uapi/linux/ipx.h b/include/uapi/linux/ipx.h index 3d48014..30f031d 100644 --- a/include/uapi/linux/ipx.h +++ b/include/uapi/linux/ipx.h @@ -1,11 +1,13 @@ #ifndef _IPX_H_ #define _IPX_H_ +#include <linux/libc-compat.h> /* for compatibility with glibc netipx/ipx.h */ #include <linux/types.h> #include <linux/sockios.h> #include <linux/socket.h> #define IPX_NODE_LEN 6 #define IPX_MTU 576 +#if __UAPI_DEF_SOCKADDR_IPX struct sockaddr_ipx { __kernel_sa_family_t sipx_family; __be16 sipx_port; @@ -14,6 +16,7 @@ struct sockaddr_ipx { __u8 sipx_type; unsigned char sipx_zero; /* 16 byte fill */ }; +#endif /* __UAPI_DEF_SOCKADDR_IPX */ /* * So we can fit the extra info for SIOCSIFADDR into the address nicely @@ -23,12 +26,15 @@ struct sockaddr_ipx { #define IPX_DLTITF 0 #define IPX_CRTITF 1 +#if __UAPI_DEF_IPX_ROUTE_DEFINITION struct ipx_route_definition { __be32 ipx_network; __be32 ipx_router_network; unsigned char ipx_router_node[IPX_NODE_LEN]; }; +#endif /* __UAPI_DEF_IPX_ROUTE_DEFINITION */ +#if __UAPI_DEF_IPX_INTERFACE_DEFINITION struct ipx_interface_definition { __be32 ipx_network; unsigned char ipx_device[16]; @@ -45,16 +51,20 @@ struct ipx_interface_definition { #define IPX_INTERNAL 2 unsigned char ipx_node[IPX_NODE_LEN]; }; - +#endif /* __UAPI_DEF_IPX_INTERFACE_DEFINITION */ + +#if __UAPI_DEF_IPX_CONFIG_DATA struct ipx_config_data { unsigned char ipxcfg_auto_select_primary; unsigned char ipxcfg_auto_create_interfaces; }; +#endif /* __UAPI_DEF_IPX_CONFIG_DATA */ /* * OLD Route Definition for backward compatibility. */ +#if __UAPI_DEF_IPX_ROUTE_DEF struct ipx_route_def { __be32 ipx_network; __be32 ipx_router_network; @@ -67,6 +77,7 @@ struct ipx_route_def { #define IPX_RT_BLUEBOOK 2 #define IPX_RT_ROUTED 1 }; +#endif /* __UAPI_DEF_IPX_ROUTE_DEF */ #define SIOCAIPXITFCRT (SIOCPROTOPRIVATE) #define SIOCAIPXPRISLT (SIOCPROTOPRIVATE + 1) diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index e4f048e..44b8a6b 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -139,6 +139,25 @@ #endif /* _NETINET_IN_H */ +/* Coordinate with glibc netipx/ipx.h header. */ +#if defined(__NETIPX_IPX_H) + +#define __UAPI_DEF_SOCKADDR_IPX 0 +#define __UAPI_DEF_IPX_ROUTE_DEFINITION 0 +#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 0 +#define __UAPI_DEF_IPX_CONFIG_DATA 0 +#define __UAPI_DEF_IPX_ROUTE_DEF 0 + +#else /* defined(__NETIPX_IPX_H) */ + +#define __UAPI_DEF_SOCKADDR_IPX 1 +#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1 +#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1 +#define __UAPI_DEF_IPX_CONFIG_DATA 1 +#define __UAPI_DEF_IPX_ROUTE_DEF 1 + +#endif /* defined(__NETIPX_IPX_H) */ + /* Definitions for xattr.h */ #if defined(_SYS_XATTR_H) #define __UAPI_DEF_XATTR 0 @@ -179,6 +198,13 @@ #define __UAPI_DEF_IN6_PKTINFO 1 #define __UAPI_DEF_IP6_MTUINFO 1 +/* Definitions for ipx.h */ +#define __UAPI_DEF_SOCKADDR_IPX 1 +#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1 +#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1 +#define __UAPI_DEF_IPX_CONFIG_DATA 1 +#define __UAPI_DEF_IPX_ROUTE_DEF 1 + /* Definitions for xattr.h */ #define __UAPI_DEF_XATTR 1 diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index d95a301..54c3b4f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -583,7 +583,7 @@ enum ovs_userspace_attr { #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1) struct ovs_action_trunc { - uint32_t max_len; /* Max packet size in bytes. */ + __u32 max_len; /* Max packet size in bytes. */ }; /** @@ -632,8 +632,8 @@ enum ovs_hash_alg { * @hash_basis: basis used for computing hash. */ struct ovs_action_hash { - uint32_t hash_alg; /* One of ovs_hash_alg. */ - uint32_t hash_basis; + __u32 hash_alg; /* One of ovs_hash_alg. */ + __u32 hash_basis; }; /** diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 9a37c541..b5486e6 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -9,8 +9,8 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); -DECLARE_PER_CPU(int, xen_vcpu_id); -static inline int xen_vcpu_nr(int cpu) +DECLARE_PER_CPU(uint32_t, xen_vcpu_id); +static inline uint32_t xen_vcpu_nr(int cpu) { return per_cpu(xen_vcpu_id, cpu); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 1903b8f..3cfabdf 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -242,18 +242,6 @@ unlock: return ret; } -static void event_function_local(struct perf_event *event, event_f func, void *data) -{ - struct event_function_struct efs = { - .event = event, - .func = func, - .data = data, - }; - - int ret = event_function(&efs); - WARN_ON_ONCE(ret); -} - static void event_function_call(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; @@ -303,6 +291,54 @@ again: raw_spin_unlock_irq(&ctx->lock); } +/* + * Similar to event_function_call() + event_function(), but hard assumes IRQs + * are already disabled and we're on the right CPU. + */ +static void event_function_local(struct perf_event *event, event_f func, void *data) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct task_struct *task = READ_ONCE(ctx->task); + struct perf_event_context *task_ctx = NULL; + + WARN_ON_ONCE(!irqs_disabled()); + + if (task) { + if (task == TASK_TOMBSTONE) + return; + + task_ctx = ctx; + } + + perf_ctx_lock(cpuctx, task_ctx); + + task = ctx->task; + if (task == TASK_TOMBSTONE) + goto unlock; + + if (task) { + /* + * We must be either inactive or active and the right task, + * otherwise we're screwed, since we cannot IPI to somewhere + * else. + */ + if (ctx->is_active) { + if (WARN_ON_ONCE(task != current)) + goto unlock; + + if (WARN_ON_ONCE(cpuctx->task_ctx != ctx)) + goto unlock; + } + } else { + WARN_ON_ONCE(&cpuctx->ctx != ctx); + } + + func(event, cpuctx, ctx, data); +unlock: + perf_ctx_unlock(cpuctx, task_ctx); +} + #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -3513,9 +3549,10 @@ static int perf_event_read(struct perf_event *event, bool group) .group = group, .ret = 0, }; - smp_call_function_single(event->oncpu, - __perf_event_read, &data, 1); - ret = data.ret; + ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1); + /* The event must have been read from an online CPU: */ + WARN_ON_ONCE(ret); + ret = ret ? : data.ret; } else if (event->state == PERF_EVENT_STATE_INACTIVE) { struct perf_event_context *ctx = event->ctx; unsigned long flags; @@ -6129,7 +6166,7 @@ static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; struct pmu *pmu = event->pmu; - struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, }; @@ -6584,15 +6621,6 @@ got_name: } /* - * Whether this @filter depends on a dynamic object which is not loaded - * yet or its load addresses are not known. - */ -static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter) -{ - return filter->filter && filter->inode; -} - -/* * Check whether inode and address range match filter criteria. */ static bool perf_addr_filter_match(struct perf_addr_filter *filter, @@ -6653,6 +6681,13 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma) struct perf_event_context *ctx; int ctxn; + /* + * Data tracing isn't supported yet and as such there is no need + * to keep track of anything that isn't related to executable code: + */ + if (!(vma->vm_flags & VM_EXEC)) + return; + rcu_read_lock(); for_each_task_context_nr(ctxn) { ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); @@ -7805,7 +7840,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event) list_for_each_entry(filter, &ifh->list, entry) { event->addr_filters_offs[count] = 0; - if (perf_addr_filter_needs_mmap(filter)) + /* + * Adjust base offset if the filter is associated to a binary + * that needs to be mapped: + */ + if (filter->inode) event->addr_filters_offs[count] = perf_addr_filter_apply(filter, mm); @@ -7936,8 +7975,10 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, goto fail; } - if (token == IF_SRC_FILE) { - filename = match_strdup(&args[2]); + if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) { + int fpos = filter->range ? 2 : 1; + + filename = match_strdup(&args[fpos]); if (!filename) { ret = -ENOMEM; goto fail; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index b7a525a..8c50276 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); err = -EAGAIN; ptep = page_check_address(page, mm, addr, &ptl, 0); - if (!ptep) + if (!ptep) { + mem_cgroup_cancel_charge(kpage, memcg, false); goto unlock; + } get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr, false); @@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = 0; unlock: - mem_cgroup_cancel_charge(kpage, memcg, false); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(page); return err; diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f689593..32f6cfc 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -39,6 +39,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) return NULL; } + get_online_cpus(); if (max_vecs >= num_online_cpus()) { cpumask_copy(affinity_mask, cpu_online_mask); *nr_vecs = num_online_cpus(); @@ -56,6 +57,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) } *nr_vecs = vecs; } + put_online_cpus(); return affinity_mask; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b4c1bc7..6373890 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -820,6 +820,17 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, desc->name = name; if (handle != handle_bad_irq && is_chained) { + /* + * We're about to start this interrupt immediately, + * hence the need to set the trigger configuration. + * But the .set_type callback may have overridden the + * flow handler, ignoring that we're dealing with a + * chained interrupt. Reset it immediately because we + * do know better. + */ + __irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data)); + desc->handle_irq = handle; + irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 73a2b78..9530fcd 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1681,8 +1681,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) + if (retval < 0) { + kfree(action); return retval; + } chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); @@ -1985,8 +1987,10 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, action->percpu_dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) + if (retval < 0) { + kfree(action); return retval; + } chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 9a0178c..b022284 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -835,9 +835,9 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) */ static bool rtree_next_node(struct memory_bitmap *bm) { - bm->cur.node = list_entry(bm->cur.node->list.next, - struct rtree_node, list); - if (&bm->cur.node->list != &bm->cur.zone->leaves) { + if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) { + bm->cur.node = list_entry(bm->cur.node->list.next, + struct rtree_node, list); bm->cur.node_pfn += BM_BITS_PER_BLOCK; bm->cur.node_bit = 0; touch_softlockup_watchdog(); @@ -845,9 +845,9 @@ static bool rtree_next_node(struct memory_bitmap *bm) } /* No more nodes, goto next zone */ - bm->cur.zone = list_entry(bm->cur.zone->list.next, + if (!list_is_last(&bm->cur.zone->list, &bm->zones)) { + bm->cur.zone = list_entry(bm->cur.zone->list.next, struct mem_zone_bm_rtree, list); - if (&bm->cur.zone->list != &bm->zones) { bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c index 276762f..d5760c4 100644 --- a/kernel/printk/braille.c +++ b/kernel/printk/braille.c @@ -9,10 +9,10 @@ char *_braille_console_setup(char **str, char **brl_options) { - if (!memcmp(*str, "brl,", 4)) { + if (!strncmp(*str, "brl,", 4)) { *brl_options = ""; *str += 4; - } else if (!memcmp(str, "brl=", 4)) { + } else if (!strncmp(*str, "brl=", 4)) { *brl_options = *str + 4; *str = strchr(*brl_options, ','); if (!*str) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 9858266..a846cf8 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime) cpustat[CPUTIME_IDLE] += (__force u64) cputime; } +/* + * When a guest is interrupted for a longer amount of time, missed clock + * ticks are not redelivered later. Due to that, this function may on + * occasion account more time than the calling functions think elapsed. + */ static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) { #ifdef CONFIG_PARAVIRT @@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, * idle, or potentially user or system time. Due to rounding, * other time can exceed ticks occasionally. */ - other = account_other_time(cputime); + other = account_other_time(ULONG_MAX); if (other >= cputime) return; cputime -= other; @@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick) } cputime = cputime_one_jiffy; - steal = steal_account_process_time(cputime); + steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) return; @@ -516,7 +521,7 @@ void account_idle_ticks(unsigned long ticks) } cputime = jiffies_to_cputime(ticks); - steal = steal_account_process_time(cputime); + steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) return; @@ -614,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr, stime = curr->stime; utime = curr->utime; - if (utime == 0) { - stime = rtime; + /* + * If either stime or both stime and utime are 0, assume all runtime is + * userspace. Once a task gets some ticks, the monotonicy code at + * 'update' will ensure things converge to the observed ratio. + */ + if (stime == 0) { + utime = rtime; goto update; } - if (stime == 0) { - utime = rtime; + if (utime == 0) { + stime = rtime; goto update; } stime = scale_stime((__force u64)stime, (__force u64)rtime, (__force u64)(stime + utime)); +update: /* * Make sure stime doesn't go backwards; this preserves monotonicity * for utime because rtime is monotonic. @@ -649,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr, stime = rtime - utime; } -update: prev->stime = stime; prev->utime = utime; out: @@ -694,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) unsigned long now = READ_ONCE(jiffies); cputime_t delta, other; + /* + * Unlike tick based timing, vtime based timing never has lost + * ticks, and no need for steal time accounting to make up for + * lost ticks. Vtime accounts a rounded version of actual + * elapsed time. Limit account_other_time to prevent rounding + * errors from causing elapsed vtime to go negative. + */ delta = jiffies_to_cputime(now - tsk->vtime_snap); other = account_other_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b43d0b2..a13bbda 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } +static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*negp) + return -EINVAL; + *valp = *lvalp; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long)val; + } + return 0; +} + static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, @@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write, int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,buffer,lenp,ppos, - NULL,NULL); + return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); +} + +/** + * proc_douintvec - read a vector of unsigned integers + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* @@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, * exception granted :-) */ EXPORT_SYMBOL(proc_dointvec); +EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3b65746..e07fb09 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -401,7 +401,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); - now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); + now = ktime_to_ns(tkr->base); + + now += clocksource_delta(tkr->read(tkr->clock), + tkr->cycle_last, tkr->mask); } while (read_seqcount_retry(&tkf->seq, seq)); return now; diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index f6bd652..107310a 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -23,7 +23,9 @@ #include "timekeeping_internal.h" -static unsigned int sleep_time_bin[32] = {0}; +#define NUM_BINS 32 + +static unsigned int sleep_time_bin[NUM_BINS] = {0}; static int tk_debug_show_sleep_time(struct seq_file *s, void *data) { @@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init); void tk_debug_account_sleep_time(struct timespec64 *t) { - sleep_time_bin[fls(t->tv_sec)]++; + /* Cap bin index so we don't overflow the array */ + int bin = min(fls(t->tv_sec), NUM_BINS-1); + + sleep_time_bin[bin]++; } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7598e6c..dbafc5d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); - if (op == REQ_OP_DISCARD) + if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 97e3cf0..4320b92 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -77,17 +77,18 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, size = min_t(unsigned int, size, tbl->size >> 1); if (sizeof(spinlock_t) != 0) { + tbl->locks = NULL; #ifdef CONFIG_NUMA if (size * sizeof(spinlock_t) > PAGE_SIZE && gfp == GFP_KERNEL) tbl->locks = vmalloc(size * sizeof(spinlock_t)); - else #endif if (gfp != GFP_KERNEL) gfp |= __GFP_NOWARN | __GFP_NORETRY; - tbl->locks = kmalloc_array(size, sizeof(spinlock_t), - gfp); + if (!tbl->locks) + tbl->locks = kmalloc_array(size, sizeof(spinlock_t), + gfp); if (!tbl->locks) return -ENOMEM; for (i = 0; i < size; i++) @@ -262,7 +262,14 @@ config COMPACTION select MIGRATION depends on MMU help - Allows the compaction of memory for the allocation of huge pages. + Compaction is the only memory management component to form + high order (larger physically contiguous) memory blocks + reliably. The page allocator relies on compaction heavily and + the lack of the feature can lead to unexpected OOM killer + invocations for high order memory requests. You shouldn't + disable this option unless there really is a strong reason for + it and then we would be really interested to hear about that at + linux-mm@kvack.org. # # support for page migration diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2373f0a..2db2112 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1512,7 +1512,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, struct page *page; pgtable_t pgtable; pmd_t _pmd; - bool young, write, dirty; + bool young, write, dirty, soft_dirty; unsigned long addr; int i; @@ -1546,6 +1546,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, write = pmd_write(*pmd); young = pmd_young(*pmd); dirty = pmd_dirty(*pmd); + soft_dirty = pmd_soft_dirty(*pmd); pmdp_huge_split_prepare(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); @@ -1562,6 +1563,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t swp_entry; swp_entry = make_migration_entry(page + i, write); entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); } else { entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(entry, vma); @@ -1569,6 +1572,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); + if (soft_dirty) + entry = pte_mksoft_dirty(entry); } if (dirty) SetPageDirty(page + i); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2ff0289..9a6a51a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4082,24 +4082,6 @@ static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) atomic_add(n, &memcg->id.ref); } -static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) -{ - while (!atomic_inc_not_zero(&memcg->id.ref)) { - /* - * The root cgroup cannot be destroyed, so it's refcount must - * always be >= 1. - */ - if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { - VM_BUG_ON(1); - break; - } - memcg = parent_mem_cgroup(memcg); - if (!memcg) - memcg = root_mem_cgroup; - } - return memcg; -} - static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { if (atomic_sub_and_test(n, &memcg->id.ref)) { @@ -5821,6 +5803,24 @@ static int __init mem_cgroup_init(void) subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + /** * mem_cgroup_swapout - transfer a memsw charge to swap * @page: page whose memsw charge to transfer diff --git a/mm/readahead.c b/mm/readahead.c index 65ec288..c8a955b 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,6 +8,7 @@ */ #include <linux/kernel.h> +#include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/blkdev.h> @@ -544,6 +545,14 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops) return -EINVAL; + /* + * Readahead doesn't make sense for DAX inodes, but we don't want it + * to report a failure either. Instead, we just return success and + * don't do any work. + */ + if (dax_mapping(mapping)) + return 0; + return force_page_cache_readahead(mapping, filp, index, nr); } diff --git a/mm/usercopy.c b/mm/usercopy.c index 8ebae91..a3cc305 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -83,7 +83,7 @@ static bool overlaps(const void *ptr, unsigned long n, unsigned long low, unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ - if (check_low >= high || check_high < low) + if (check_low >= high || check_high <= low) return false; return true; @@ -124,7 +124,7 @@ static inline const char *check_kernel_text_object(const void *ptr, static inline const char *check_bogus_address(const void *ptr, unsigned long n) { /* Reject if object wraps past end of memory. */ - if (ptr + n < ptr) + if ((unsigned long)ptr + n < (unsigned long)ptr) return "<wrapped address>"; /* Reject if NULL or ZERO-allocation. */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ece45e0..0b5f729 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -250,7 +250,7 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index c045b3c..b0e23df 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -262,6 +262,8 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, break; } + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; hdev->req_status = hdev->req_result = 0; BT_DBG("%s end: err %d", hdev->name, err); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 6ef8a01..96f04b7 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1091,7 +1091,7 @@ static int hci_sock_recvmsg(struct socket *sock, struct msghdr *msg, skb_free_datagram(sk, skb); - if (msg->msg_flags & MSG_TRUNC) + if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 54ceb1f..d4cad29b0 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -32,6 +32,7 @@ #include <linux/debugfs.h> #include <linux/crc16.h> +#include <linux/filter.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -5835,6 +5836,9 @@ static int l2cap_reassemble_sdu(struct l2cap_chan *chan, struct sk_buff *skb, if (chan->sdu) break; + if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE)) + break; + chan->sdu_len = get_unaligned_le16(skb->data); skb_pull(skb, L2CAP_SDULEN_SIZE); @@ -6610,6 +6614,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } + if ((chan->mode == L2CAP_MODE_ERTM || + chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) + goto drop; + if (!control->sframe) { int err; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1842141..a8ba752 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1019,7 +1019,7 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg, goto done; if (pi->rx_busy_skb) { - if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb)) + if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb)) pi->rx_busy_skb = NULL; else goto done; @@ -1270,7 +1270,17 @@ static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) goto done; } - err = sock_queue_rcv_skb(sk, skb); + if (chan->mode != L2CAP_MODE_ERTM && + chan->mode != L2CAP_MODE_STREAMING) { + /* Even if no filter is attached, we could potentially + * get errors from security modules, etc. + */ + err = sk_filter(sk, skb); + if (err) + goto done; + } + + err = __sock_queue_rcv_skb(sk, skb); /* For ERTM, handle one skb that doesn't fit into the recv * buffer. This is important to do because the data frames diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index febca0f..e2ffc2a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -249,7 +249,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * - * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits + * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest @@ -258,7 +258,7 @@ static inline unsigned long get_index(t_key key, struct key_vector *kv) * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * - * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown + * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 9d847c3..0f227db 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -73,9 +73,11 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - if (skb_iif && proto == IPPROTO_UDP) { - /* Arrived from an ingress interface and got udp encapuslated. - * The encapsulated network segment length may exceed dst mtu. + if (skb_iif && !(df & htons(IP_DF))) { + /* Arrived from an ingress interface, got encapsulated, with + * fragmentation of encapulating frames allowed. + * If skb is gso, the resulting encapsulated network segments + * may exceed dst mtu. * Allow IP Fragmentation of segments. */ IPCB(skb)->flags |= IPSKB_FRAG_SEGS; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 60a4388..77311a9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3182,7 +3182,6 @@ int tcp_abort(struct sock *sk, int err) local_bh_enable(); return 0; } - sock_gen_put(sk); return -EOPNOTSUPP; } @@ -3211,7 +3210,6 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); release_sock(sk); - sock_put(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4d61093..a748c74 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -54,11 +54,16 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, { struct net *net = sock_net(in_skb->sk); struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req); + int err; if (IS_ERR(sk)) return PTR_ERR(sk); - return sock_diag_destroy(sk, ECONNABORTED); + err = sock_diag_destroy(sk, ECONNABORTED); + + sock_gen_put(sk); + + return err; } #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 53e80cd..a75bf48 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -814,8 +814,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v4_send_ack(sock_net(sk), skb, seq, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, 0, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f0ebb0b..058c312 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1183,13 +1183,13 @@ out: * @sk: socket * * Drops all bad checksum frames, until a valid one is found. - * Returns the length of found skb, or 0 if none is found. + * Returns the length of found skb, or -1 if none is found. */ -static unsigned int first_packet_length(struct sock *sk) +static int first_packet_length(struct sock *sk) { struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; struct sk_buff *skb; - unsigned int res; + int res; __skb_queue_head_init(&list_kill); @@ -1204,7 +1204,7 @@ static unsigned int first_packet_length(struct sock *sk) __skb_unlink(skb, rcvq); __skb_queue_tail(&list_kill, skb); } - res = skb ? skb->len : 0; + res = skb ? skb->len : -1; spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { @@ -1233,7 +1233,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) case SIOCINQ: { - unsigned int amount = first_packet_length(sk); + int amount = max_t(int, 0, first_packet_length(sk)); return put_user(amount, (int __user *)arg); } @@ -2185,7 +2185,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Check for false positives due to checksum errors */ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && - !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) + !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(POLLIN | POLLRDNORM); return mask; @@ -2231,7 +2231,6 @@ struct proto udp_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 67fc9d9..af81715 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -55,7 +55,6 @@ struct proto udplite_prot = { .unhash = udp_lib_unhash, .get_port = udp_v4_get_port, .obj_size = sizeof(struct udp_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index df8425f..f418d2e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1872,7 +1872,6 @@ static int addrconf_dad_end(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct inet6_ifaddr *ifp) { - struct in6_addr addr; struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(ifp->idev->dev); @@ -1934,18 +1933,6 @@ void addrconf_dad_failure(struct inet6_ifaddr *ifp) in6_ifa_put(ifp2); lock_errdad: spin_lock_bh(&ifp->lock); - } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { - addr.s6_addr32[0] = htonl(0xfe800000); - addr.s6_addr32[1] = 0; - - if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && - ipv6_addr_equal(&ifp->addr, &addr)) { - /* DAD failed for link-local based on MAC address */ - idev->cnf.disable_ipv6 = 1; - - pr_info("%s: IPv6 being disabled!\n", - ifp->idev->dev->name); - } } errdad: @@ -3821,6 +3808,7 @@ static void addrconf_dad_work(struct work_struct *w) dad_work); struct inet6_dev *idev = ifp->idev; struct in6_addr mcaddr; + bool disable_ipv6 = false; enum { DAD_PROCESS, @@ -3837,6 +3825,24 @@ static void addrconf_dad_work(struct work_struct *w) } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; + + if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 && + !(ifp->flags & IFA_F_STABLE_PRIVACY)) { + struct in6_addr addr; + + addr.s6_addr32[0] = htonl(0xfe800000); + addr.s6_addr32[1] = 0; + + if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && + ipv6_addr_equal(&ifp->addr, &addr)) { + /* DAD failed for link-local based on MAC */ + idev->cnf.disable_ipv6 = 1; + + pr_info("%s: IPv6 being disabled!\n", + ifp->idev->dev->name); + disable_ipv6 = true; + } + } } spin_unlock_bh(&ifp->lock); @@ -3845,6 +3851,8 @@ static void addrconf_dad_work(struct work_struct *w) goto out; } else if (action == DAD_ABORT) { addrconf_dad_stop(ifp, 1); + if (disable_ipv6) + addrconf_ifdown(idev->dev, 0); goto out; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5bf460b..04529a3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -945,9 +945,15 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ + /* RFC 7323 2.3 + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits: + */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, - tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, + tcp_rsk(req)->rcv_nxt, + req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9efe740..9aa7c1c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1449,7 +1449,6 @@ struct proto udpv6_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 5cf0099..47d0d2b 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -50,7 +50,6 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .obj_size = sizeof(struct udp6_sock), - .slab_flags = SLAB_DESTROY_BY_RCU, .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 254ee66..34eff77 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -854,7 +854,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = -ENOTCONN; if (sk == NULL) goto end; - if (sk->sk_state != PPPOX_CONNECTED) + if (!(sk->sk_state & PPPOX_CONNECTED)) goto end; error = -EBADF; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 958a145..9f267c3 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -205,6 +205,7 @@ static int ct_seq_show(struct seq_file *s, void *v) struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l3proto *l3proto; const struct nf_conntrack_l4proto *l4proto; + struct net *net = seq_file_net(s); int ret = 0; NF_CT_ASSERT(ct); @@ -215,6 +216,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (NF_CT_DIRECTION(hash)) goto release; + if (!net_eq(nf_ct_net(ct), net)) + goto release; + l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct)); NF_CT_ASSERT(l3proto); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 1b4de4b..70eb2f6a 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -326,14 +326,14 @@ static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; - /* we want to avoid races with nfnl_acct_find_get. */ - if (atomic_dec_and_test(&cur->refcnt)) { + /* We want to avoid races with nfnl_acct_put. So only when the current + * refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&cur->refcnt); ret = -EBUSY; } return ret; @@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); -static void nfnl_overquota_report(struct nf_acct *nfacct) +static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; @@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } -int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct) { u64 now; u64 *quota; @@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { - nfnl_overquota_report(nfacct); + nfnl_overquota_report(net, nfacct); } return ret; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 4cdcd96..68216cd 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -330,16 +330,16 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) { int ret = 0; - /* we want to avoid races with nf_ct_timeout_find_get. */ - if (atomic_dec_and_test(&timeout->refcnt)) { + /* We want to avoid races with ctnl_timeout_put. So only when the + * current refcnt is 1, we decrease it to 0. + */ + if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); nf_ct_l4proto_put(timeout->l4proto); ctnl_untimeout(net, timeout); kfree_rcu(timeout, rcu_head); } else { - /* still in use, restore reference counter. */ - atomic_inc(&timeout->refcnt); ret = -EBUSY; } return ret; @@ -543,7 +543,9 @@ err: static void ctnl_timeout_put(struct ctnl_timeout *timeout) { - atomic_dec(&timeout->refcnt); + if (atomic_dec_and_test(&timeout->refcnt)) + kfree_rcu(timeout, rcu_head); + module_put(THIS_MODULE); } #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ @@ -591,7 +593,9 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); nf_ct_l4proto_put(cur->l4proto); - kfree_rcu(cur, rcu_head); + + if (atomic_dec_and_test(&cur->refcnt)) + kfree_rcu(cur, rcu_head); } } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index cbcfdfb..6577db5 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1147,6 +1147,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); +MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 7f4414d..663c4c3 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,6 +127,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound @@ -195,6 +197,8 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); + if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in * xt_socket, since xt_TPROXY needs 0 bound diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 3048a7e..cf32759 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) nfnl_acct_update(skb, info->nfacct); - overquota = nfnl_acct_overquota(skb, info->nfacct); + overquota = nfnl_acct_overquota(par->net, skb, info->nfacct); return overquota == NFACCT_UNDERQUOTA ? false : true; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 141a06e..e87cd81 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -53,7 +53,7 @@ int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval) u32 *tlv = (u32 *)(skbdata); u16 totlen = nla_total_size(dlen); /*alignment + hdr */ char *dptr = (char *)tlv + NLA_HDRLEN; - u32 htlv = attrtype << 16 | totlen; + u32 htlv = attrtype << 16 | dlen; *tlv = htonl(htlv); memset(dptr, 0, totlen - NLA_HDRLEN); @@ -135,7 +135,7 @@ EXPORT_SYMBOL_GPL(ife_release_meta_gen); int ife_validate_meta_u32(void *val, int len) { - if (len == 4) + if (len == sizeof(u32)) return 0; return -EINVAL; @@ -144,8 +144,8 @@ EXPORT_SYMBOL_GPL(ife_validate_meta_u32); int ife_validate_meta_u16(void *val, int len) { - /* length will include padding */ - if (len == NLA_ALIGN(2)) + /* length will not include padding */ + if (len == sizeof(u16)) return 0; return -EINVAL; @@ -652,12 +652,14 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlvdata = (u8 *)tlv; u16 mtype = tlv->type; u16 mlen = tlv->len; + u16 alen; mtype = ntohs(mtype); mlen = ntohs(mlen); + alen = NLA_ALIGN(mlen); - if (find_decode_metaid(skb, ife, mtype, (mlen - 4), - (void *)(tlvdata + 4))) { + if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN), + (void *)(tlvdata + NLA_HDRLEN))) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -666,8 +668,8 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, ife->tcf_qstats.overlimits++; } - tlvdata += mlen; - ifehdrln -= mlen; + tlvdata += alen; + ifehdrln -= alen; tlv = (struct meta_tlvhdr *)tlvdata; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 18faecc..0d21b56 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -641,18 +641,19 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc *sch; if (!try_module_get(ops->owner)) - goto errout; + return NULL; sch = qdisc_alloc(dev_queue, ops); - if (IS_ERR(sch)) - goto errout; + if (IS_ERR(sch)) { + module_put(ops->owner); + return NULL; + } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL) == 0) return sch; qdisc_destroy(sch); -errout: return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); diff --git a/net/sctp/input.c b/net/sctp/input.c index c182db7..69444d3 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -119,7 +119,13 @@ int sctp_rcv(struct sk_buff *skb) skb_transport_offset(skb)) goto discard_it; - if (!pskb_may_pull(skb, sizeof(struct sctphdr))) + /* If the packet is fragmented and we need to do crc checking, + * it's better to just linearize it otherwise crc computing + * takes longer. + */ + if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + skb_linearize(skb)) || + !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; /* Pull up the IP header. */ @@ -1177,9 +1183,6 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) return NULL; - if (skb_linearize(skb)) - return NULL; - ch = (sctp_chunkhdr_t *) skb->data; /* The code below will attempt to walk the chunk and extract diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index c30ddb0..6437aa9 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,19 +170,6 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - /* Linearize if it's not GSO */ - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP && - skb_is_nonlinear(chunk->skb)) { - if (skb_linearize(chunk->skb)) { - __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); - sctp_chunk_free(chunk); - goto next_chunk; - } - - /* Update sctp_hdr as it probably changed */ - chunk->sctp_hdr = sctp_hdr(chunk->skb); - } - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { /* GSO-marked skbs but without frags, handle * them normally diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index bb69153..f3508aa 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -424,11 +424,13 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, paddr.v4.sin_family = AF_INET; } else { laddr.v6.sin6_port = req->id.idiag_sport; - memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64); + memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, + sizeof(laddr.v6.sin6_addr)); laddr.v6.sin6_family = AF_INET6; paddr.v6.sin6_port = req->id.idiag_dport; - memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64); + memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, + sizeof(paddr.v6.sin6_addr)); paddr.v6.sin6_family = AF_INET6; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 245e9a2..dd27468 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -732,6 +732,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, return 0; err: + if (ub->ubsock) + udp_tunnel_sock_release(ub->ubsock); kfree(ub); return err; } diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 49a00d5..aed4511 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -2136,9 +2136,11 @@ sub vcs_file_exists { my $cmd = $VCS_cmds{"file_exists_cmd"}; $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd - + $cmd .= " 2>&1"; $exists = &{$VCS_cmds{"execute_cmd"}}($cmd); + return 0 if ($? != 0); + return $exists; } diff --git a/security/Kconfig b/security/Kconfig index df28f2b..da10d9b 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -136,6 +136,7 @@ config HAVE_ARCH_HARDENED_USERCOPY config HARDENED_USERCOPY bool "Harden memory copies between kernel and userspace" depends on HAVE_ARCH_HARDENED_USERCOPY + depends on HAVE_HARDENED_USERCOPY_ALLOCATOR select BUG help This option checks for obviously wrong memory regions when diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 574b1b4..7100f05 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4828,7 +4828,7 @@ enum { ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_FIXUP_TPT440_DOCK, ALC292_FIXUP_TPT440, - ALC283_FIXUP_BXBT2807_MIC, + ALC283_FIXUP_HEADSET_MIC, ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, ALC282_FIXUP_ASPIRE_V5_PINS, ALC280_FIXUP_HP_GPIO4, @@ -5321,7 +5321,7 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC292_FIXUP_TPT440_DOCK, }, - [ALC283_FIXUP_BXBT2807_MIC] = { + [ALC283_FIXUP_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x04a110f0 }, @@ -5651,7 +5651,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), - SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC), + SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 54c09ac..16e459a 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -299,8 +299,9 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream, clk_enable(ssc_p->ssc->clk); ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk); - /* Reset the SSC to keep it at a clean status */ - ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); + /* Reset the SSC unless initialized to keep it in a clean state */ + if (!ssc_p->initialized) + ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { dir = 0; diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index e5527bc..bcf1834 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -1247,8 +1247,8 @@ static int da7213_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) return -EINVAL; } - /* By default only 32 BCLK per WCLK is supported */ - dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_32; + /* By default only 64 BCLK per WCLK is supported */ + dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_64; snd_soc_write(codec, DA7213_DAI_CLK_MODE, dai_clk_mode); snd_soc_update_bits(codec, DA7213_DAI_CTRL, DA7213_DAI_FORMAT_MASK, diff --git a/sound/soc/codecs/max98371.c b/sound/soc/codecs/max98371.c index cf0a39b..02352ed 100644 --- a/sound/soc/codecs/max98371.c +++ b/sound/soc/codecs/max98371.c @@ -412,6 +412,7 @@ static int max98371_i2c_remove(struct i2c_client *client) static const struct i2c_device_id max98371_i2c_id[] = { { "max98371", 0 }, + { } }; MODULE_DEVICE_TABLE(i2c, max98371_i2c_id); diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 5c9707a..2e59a85 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -212,31 +212,6 @@ static const unsigned short logtable[256] = { 0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47 }; -static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825) -{ - struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm); - struct snd_soc_component *component = &codec->component; - struct snd_soc_dai *codec_dai, *_dai; - - list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) { - if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI, - strlen(NUVOTON_CODEC_DAI))) - return codec_dai; - } - return NULL; -} - -static bool nau8825_dai_is_active(struct nau8825 *nau8825) -{ - struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825); - - if (codec_dai) { - if (codec_dai->playback_active || codec_dai->capture_active) - return true; - } - return false; -} - /** * nau8825_sema_acquire - acquire the semaphore of nau88l25 * @nau8825: component to register the codec private data with @@ -250,19 +225,26 @@ static bool nau8825_dai_is_active(struct nau8825 *nau8825) * Acquires the semaphore without jiffies. If no more tasks are allowed * to acquire the semaphore, calling this function will put the task to * sleep until the semaphore is released. - * It returns if the semaphore was acquired. + * If the semaphore is not released within the specified number of jiffies, + * this function returns -ETIME. + * If the sleep is interrupted by a signal, this function will return -EINTR. + * It returns 0 if the semaphore was acquired successfully. */ -static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) +static int nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) { int ret; - if (timeout) + if (timeout) { ret = down_timeout(&nau8825->xtalk_sem, timeout); - else + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone timeout\n"); + } else { ret = down_interruptible(&nau8825->xtalk_sem); + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + } - if (ret < 0) - dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + return ret; } /** @@ -1205,6 +1187,8 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int val_len = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (params_width(params)) { case 16: val_len |= NAU8825_I2S_DL_16; @@ -1225,6 +1209,9 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1, NAU8825_I2S_DL_MASK, val_len); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1234,6 +1221,8 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int ctrl1_val = 0, ctrl2_val = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBM_CFM: ctrl2_val |= NAU8825_I2S_MS_MASTER; @@ -1282,6 +1271,9 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, NAU8825_I2S_MS_MASK, ctrl2_val); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1611,8 +1603,11 @@ static irqreturn_t nau8825_interrupt(int irq, void *data) * cess and restore changes if process * is ongoing when ejection. */ + int ret; nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; } /* Startup cross talk detection process */ nau8825->xtalk_state = NAU8825_XTALK_PREPARE; @@ -2238,23 +2233,14 @@ static int __maybe_unused nau8825_suspend(struct snd_soc_codec *codec) static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec) { struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + int ret; regcache_cache_only(nau8825->regmap, false); regcache_sync(nau8825->regmap); - if (nau8825_is_jack_inserted(nau8825->regmap)) { - /* If the jack is inserted, we need to check whether the play- - * back is active before suspend. If active, the driver has to - * raise the protection for cross talk function to avoid the - * playback recovers before cross talk process finish. Other- - * wise, the playback will be interfered by cross talk func- - * tion. It is better to apply hardware related parameters - * before starting playback or record. - */ - if (nau8825_dai_is_active(nau8825)) { - nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); - } - } + nau8825->xtalk_protect = true; + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; enable_irq(nau8825->irq); return 0; diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index a67ea10..f266439 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -581,7 +581,7 @@ static int wm2000_anc_transition(struct wm2000_priv *wm2000, if (anc_transitions[i].dest == ANC_OFF) clk_disable_unprepare(wm2000->mclk); - return ret; + return 0; } static int wm2000_anc_set_mode(struct wm2000_priv *wm2000) diff --git a/sound/soc/generic/Makefile b/sound/soc/generic/Makefile index 45602ca..2d53c8d 100644 --- a/sound/soc/generic/Makefile +++ b/sound/soc/generic/Makefile @@ -1,5 +1,5 @@ -obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o - +snd-soc-simple-card-utils-objs := simple-card-utils.o snd-soc-simple-card-objs := simple-card.o -obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o +obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) += snd-soc-simple-card-utils.o +obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index d89a9a1..9599de6 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/module.h> #include <linux/of.h> #include <sound/simple_card_utils.h> @@ -95,3 +96,8 @@ int asoc_simple_card_parse_card_name(struct snd_soc_card *card, return 0; } EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name); + +/* Module information */ +MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>"); +MODULE_DESCRIPTION("ALSA SoC Simple Card Utils"); +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/intel/skylake/skl-sst-utils.c b/sound/soc/intel/skylake/skl-sst-utils.c index 25fcb79..ddcb52a 100644 --- a/sound/soc/intel/skylake/skl-sst-utils.c +++ b/sound/soc/intel/skylake/skl-sst-utils.c @@ -123,6 +123,11 @@ int snd_skl_get_module_info(struct skl_sst *ctx, u8 *uuid, uuid_mod = (uuid_le *)uuid; + if (list_empty(&ctx->uuid_list)) { + dev_err(ctx->dev, "Module list is empty\n"); + return -EINVAL; + } + list_for_each_entry(module, &ctx->uuid_list, list) { if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) { dfw_config->module_id = module->id; diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index cd59536..e3e7641 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -672,8 +672,10 @@ static int skl_probe(struct pci_dev *pci, skl->nhlt = skl_nhlt_init(bus->dev); - if (skl->nhlt == NULL) + if (skl->nhlt == NULL) { + err = -ENODEV; goto out_free; + } skl_nhlt_update_topology_bin(skl); diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c index 0843a68..f61b3b5 100644 --- a/sound/soc/omap/omap-abe-twl6040.c +++ b/sound/soc/omap/omap-abe-twl6040.c @@ -38,10 +38,10 @@ struct abe_twl6040 { int jack_detection; /* board can detect jack events */ int mclk_freq; /* MCLK frequency speed for twl6040 */ - - struct platform_device *dmic_codec_dev; }; +struct platform_device *dmic_codec_dev; + static int omap_abe_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { @@ -258,8 +258,6 @@ static int omap_abe_probe(struct platform_device *pdev) if (priv == NULL) return -ENOMEM; - priv->dmic_codec_dev = ERR_PTR(-EINVAL); - if (snd_soc_of_parse_card_name(card, "ti,model")) { dev_err(&pdev->dev, "Card name is not provided\n"); return -ENODEV; @@ -284,13 +282,6 @@ static int omap_abe_probe(struct platform_device *pdev) num_links = 2; abe_twl6040_dai_links[1].cpu_of_node = dai_node; abe_twl6040_dai_links[1].platform_of_node = dai_node; - - priv->dmic_codec_dev = platform_device_register_simple( - "dmic-codec", -1, NULL, 0); - if (IS_ERR(priv->dmic_codec_dev)) { - dev_err(&pdev->dev, "Can't instantiate dmic-codec\n"); - return PTR_ERR(priv->dmic_codec_dev); - } } else { num_links = 1; } @@ -299,16 +290,14 @@ static int omap_abe_probe(struct platform_device *pdev) of_property_read_u32(node, "ti,mclk-freq", &priv->mclk_freq); if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency not provided\n"); - ret = -EINVAL; - goto err_unregister; + return -EINVAL; } card->fully_routed = 1; if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency missing\n"); - ret = -ENODEV; - goto err_unregister; + return -ENODEV; } card->dai_link = abe_twl6040_dai_links; @@ -317,17 +306,9 @@ static int omap_abe_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(card, priv); ret = snd_soc_register_card(card); - if (ret) { + if (ret) dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret); - goto err_unregister; - } - - return 0; - -err_unregister: - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); return ret; } @@ -335,13 +316,9 @@ err_unregister: static int omap_abe_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - struct abe_twl6040 *priv = snd_soc_card_get_drvdata(card); snd_soc_unregister_card(card); - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); - return 0; } @@ -361,7 +338,33 @@ static struct platform_driver omap_abe_driver = { .remove = omap_abe_remove, }; -module_platform_driver(omap_abe_driver); +static int __init omap_abe_init(void) +{ + int ret; + + dmic_codec_dev = platform_device_register_simple("dmic-codec", -1, NULL, + 0); + if (IS_ERR(dmic_codec_dev)) { + pr_err("%s: dmic-codec device registration failed\n", __func__); + return PTR_ERR(dmic_codec_dev); + } + + ret = platform_driver_register(&omap_abe_driver); + if (ret) { + pr_err("%s: platform driver registration failed\n", __func__); + platform_device_unregister(dmic_codec_dev); + } + + return ret; +} +module_init(omap_abe_init); + +static void __exit omap_abe_exit(void) +{ + platform_driver_unregister(&omap_abe_driver); + platform_device_unregister(dmic_codec_dev); +} +module_exit(omap_abe_exit); MODULE_AUTHOR("Misael Lopez Cruz <misael.lopez@ti.com>"); MODULE_DESCRIPTION("ALSA SoC for OMAP boards with ABE and twl6040 codec"); diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index e7cdc51..64609c7 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -31,7 +31,6 @@ #include <linux/err.h> #include <linux/io.h> #include <linux/irq.h> -#include <linux/clk.h> #include <linux/slab.h> #include <linux/pm_runtime.h> #include <linux/of_device.h> @@ -55,7 +54,6 @@ struct omap_mcpdm { unsigned long phys_base; void __iomem *io_base; int irq; - struct clk *pdmclk; struct mutex mutex; @@ -390,15 +388,14 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai) struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); int ret; - clk_prepare_enable(mcpdm->pdmclk); pm_runtime_enable(mcpdm->dev); /* Disable lines while request is ongoing */ pm_runtime_get_sync(mcpdm->dev); omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00); - ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler, - 0, "McPDM", (void *)mcpdm); + ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM", + (void *)mcpdm); pm_runtime_put_sync(mcpdm->dev); @@ -423,9 +420,9 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + free_irq(mcpdm->irq, (void *)mcpdm); pm_runtime_disable(mcpdm->dev); - clk_disable_unprepare(mcpdm->pdmclk); return 0; } @@ -445,8 +442,6 @@ static int omap_mcpdm_suspend(struct snd_soc_dai *dai) mcpdm->pm_active_count++; } - clk_disable_unprepare(mcpdm->pdmclk); - return 0; } @@ -454,8 +449,6 @@ static int omap_mcpdm_resume(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); - clk_prepare_enable(mcpdm->pdmclk); - if (mcpdm->pm_active_count) { while (mcpdm->pm_active_count--) pm_runtime_get_sync(mcpdm->dev); @@ -549,15 +542,6 @@ static int asoc_mcpdm_probe(struct platform_device *pdev) mcpdm->dev = &pdev->dev; - mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk"); - if (IS_ERR(mcpdm->pdmclk)) { - if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n", - PTR_ERR(mcpdm->pdmclk)); - mcpdm->pdmclk = NULL; - } - ret = devm_snd_soc_register_component(&pdev->dev, &omap_mcpdm_component, &omap_mcpdm_dai, 1); diff --git a/sound/soc/samsung/s3c24xx_uda134x.c b/sound/soc/samsung/s3c24xx_uda134x.c index 50849e1..92e88bc 100644 --- a/sound/soc/samsung/s3c24xx_uda134x.c +++ b/sound/soc/samsung/s3c24xx_uda134x.c @@ -58,10 +58,12 @@ static struct platform_device *s3c24xx_uda134x_snd_device; static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) { - int ret = 0; + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *cpu_dai = rtd->cpu_dai; #ifdef ENFORCE_RATES struct snd_pcm_runtime *runtime = substream->runtime; #endif + int ret = 0; mutex_lock(&clk_lock); pr_debug("%s %d\n", __func__, clk_users); @@ -71,8 +73,7 @@ static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) printk(KERN_ERR "%s cannot get xtal\n", __func__); ret = PTR_ERR(xtal); } else { - pclk = clk_get(&s3c24xx_uda134x_snd_device->dev, - "pclk"); + pclk = clk_get(cpu_dai->dev, "iis"); if (IS_ERR(pclk)) { printk(KERN_ERR "%s cannot get pclk\n", __func__); diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index e39f916..969a516 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -226,8 +226,12 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, ifscr = 0; fsrate = 0; if (fin != fout) { + u64 n; + ifscr = 1; - fsrate = 0x0400000 / fout * fin; + n = (u64)0x0400000 * fin; + do_div(n, fout); + fsrate = n; } /* diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index d2df46c..bf7b52f 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -121,7 +121,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) dpcm_be_disconnect(fe, stream); fe->dpcm[stream].runtime = NULL; - goto fe_err; + goto path_err; } dpcm_clear_pending_state(fe, stream); @@ -136,6 +136,8 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) return 0; +path_err: + dpcm_path_put(&list); fe_err: if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown) fe->dai_link->compr_ops->shutdown(cstream); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 16369ca..4afa8db 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1056,7 +1056,7 @@ static int soc_bind_dai_link(struct snd_soc_card *card, if (!rtd->platform) { dev_err(card->dev, "ASoC: platform %s not registered\n", dai_link->platform_name); - return -EPROBE_DEFER; + goto _err_defer; } soc_add_pcm_runtime(card, rtd); @@ -2083,14 +2083,13 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) /* remove auxiliary devices */ soc_remove_aux_devices(card); + snd_soc_dapm_free(&card->dapm); soc_cleanup_card_debugfs(card); /* remove the card */ if (card->remove) card->remove(card); - snd_soc_dapm_free(&card->dapm); - snd_card_free(card->snd_card); return 0; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 8698c26..d908ff8 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3493,6 +3493,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, const struct snd_soc_pcm_stream *config = w->params + w->params_select; struct snd_pcm_substream substream; struct snd_pcm_hw_params *params = NULL; + struct snd_pcm_runtime *runtime = NULL; u64 fmt; int ret; @@ -3541,6 +3542,14 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, memset(&substream, 0, sizeof(substream)); + /* Allocate a dummy snd_pcm_runtime for startup() and other ops() */ + runtime = kzalloc(sizeof(*runtime), GFP_KERNEL); + if (!runtime) { + ret = -ENOMEM; + goto out; + } + substream.runtime = runtime; + switch (event) { case SND_SOC_DAPM_PRE_PMU: substream.stream = SNDRV_PCM_STREAM_CAPTURE; @@ -3606,6 +3615,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, } out: + kfree(runtime); kfree(params); return ret; } diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c index 204cc07..41aa335 100644 --- a/sound/usb/line6/pcm.c +++ b/sound/usb/line6/pcm.c @@ -55,7 +55,6 @@ static int snd_line6_impulse_volume_put(struct snd_kcontrol *kcontrol, err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE); if (err < 0) { line6pcm->impulse_volume = 0; - line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE); return err; } } else { @@ -211,7 +210,9 @@ static void line6_stream_stop(struct snd_line6_pcm *line6pcm, int direction, spin_lock_irqsave(&pstr->lock, flags); clear_bit(type, &pstr->running); if (!pstr->running) { + spin_unlock_irqrestore(&pstr->lock, flags); line6_unlink_audio_urbs(line6pcm, pstr); + spin_lock_irqsave(&pstr->lock, flags); if (direction == SNDRV_PCM_STREAM_CAPTURE) { line6pcm->prev_fbuf = NULL; line6pcm->prev_fsize = 0; diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c index daf81d16..45dd348 100644 --- a/sound/usb/line6/pod.c +++ b/sound/usb/line6/pod.c @@ -244,8 +244,8 @@ static int pod_set_system_param_int(struct usb_line6_pod *pod, int value, static ssize_t serial_number_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%u\n", pod->serial_number); } @@ -256,8 +256,8 @@ static ssize_t serial_number_show(struct device *dev, static ssize_t firmware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100, pod->firmware_version % 100); @@ -269,8 +269,8 @@ static ssize_t firmware_version_show(struct device *dev, static ssize_t device_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d\n", pod->device_id); } diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f209ea1..3051f86 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -87,9 +87,11 @@ struct kvm_regs { /* Supported VGICv3 address types */ #define KVM_VGIC_V3_ADDR_TYPE_DIST 2 #define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 +#define KVM_VGIC_ITS_ADDR_TYPE 4 #define KVM_VGIC_V3_DIST_SIZE SZ_64K #define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) +#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 3b8e99e..a2ffec4 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine { __u64 fac_list[256]; }; +#define KVM_S390_VM_CPU_PROCESSOR_FEAT 2 +#define KVM_S390_VM_CPU_MACHINE_FEAT 3 + +#define KVM_S390_VM_CPU_FEAT_NR_BITS 1024 +#define KVM_S390_VM_CPU_FEAT_ESOP 0 +#define KVM_S390_VM_CPU_FEAT_SIEF2 1 +#define KVM_S390_VM_CPU_FEAT_64BSCAO 2 +#define KVM_S390_VM_CPU_FEAT_SIIF 3 +#define KVM_S390_VM_CPU_FEAT_GPERE 4 +#define KVM_S390_VM_CPU_FEAT_GSLS 5 +#define KVM_S390_VM_CPU_FEAT_IB 6 +#define KVM_S390_VM_CPU_FEAT_CEI 7 +#define KVM_S390_VM_CPU_FEAT_IBS 8 +#define KVM_S390_VM_CPU_FEAT_SKEY 9 +#define KVM_S390_VM_CPU_FEAT_CMMA 10 +#define KVM_S390_VM_CPU_FEAT_PFMFI 11 +#define KVM_S390_VM_CPU_FEAT_SIGPIF 12 +struct kvm_s390_vm_cpu_feat { + __u64 feat[16]; +}; + +#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC 4 +#define KVM_S390_VM_CPU_MACHINE_SUBFUNC 5 +/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */ +struct kvm_s390_vm_cpu_subfunc { + __u8 plo[32]; /* always */ + __u8 ptff[16]; /* with TOD-clock steering */ + __u8 kmac[16]; /* with MSA */ + __u8 kmc[16]; /* with MSA */ + __u8 km[16]; /* with MSA */ + __u8 kimd[16]; /* with MSA */ + __u8 klmd[16]; /* with MSA */ + __u8 pckmo[16]; /* with MSA3 */ + __u8 kmctr[16]; /* with MSA4 */ + __u8 kmf[16]; /* with MSA4 */ + __u8 kmo[16]; /* with MSA4 */ + __u8 pcc[16]; /* with MSA4 */ + __u8 ppno[16]; /* with MSA5 */ + __u8 reserved[1824]; +}; + /* kvm attributes for crypto */ #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW 0 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1 diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h index 8fb5d4a..3ac6343 100644 --- a/tools/arch/s390/include/uapi/asm/sie.h +++ b/tools/arch/s390/include/uapi/asm/sie.h @@ -140,6 +140,7 @@ exit_code_ipa0(0xB2, 0x4c, "TAR"), \ exit_code_ipa0(0xB2, 0x50, "CSP"), \ exit_code_ipa0(0xB2, 0x54, "MVPG"), \ + exit_code_ipa0(0xB2, 0x56, "STHYI"), \ exit_code_ipa0(0xB2, 0x58, "BSG"), \ exit_code_ipa0(0xB2, 0x5a, "BSA"), \ exit_code_ipa0(0xB2, 0x5f, "CHSC"), \ diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 448ed96..1c14c25 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -1,5 +1,5 @@ /* - * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * gpio-event-mon - monitor GPIO line events from userspace * * Copyright (C) 2016 Linus Walleij * diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index b968794..f436d24 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len); int strtobool(const char *s, bool *res); -#ifdef __GLIBC__ +/* + * glibc based builds needs the extern while uClibc doesn't. + * However uClibc headers also define __GLIBC__ hence the hack below + */ +#if defined(__GLIBC__) && !defined(__UCLIBC__) extern size_t strlcpy(char *dest, const char *src, size_t size); #endif diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 8d4dc97..35745a7 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -97,6 +97,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, } } +#ifdef HAVE_LIBELF_SUPPORT void arch__post_process_probe_trace_events(struct perf_probe_event *pev, int ntevs) { @@ -118,5 +119,6 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev, } } } +#endif /* HAVE_LIBELF_SUPPORT */ #endif diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index fb51457..a2412e9 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; - bool have_timing_info; + bool have_timing_info, need_immediate = false; struct perf_evsel *evsel, *intel_pt_evsel = NULL; const struct cpu_map *cpus = evlist->cpus; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; @@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, ptr->have_sched_switch = 3; } else { opts->record_switch_events = true; + need_immediate = true; if (cpu_wide) ptr->have_sched_switch = 3; else @@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel->attr.freq = 0; tracking_evsel->attr.sample_period = 1; + if (need_immediate) + tracking_evsel->immediate = true; + /* In per-cpu case, always need the time of mmap events etc */ if (!cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(tracking_evsel, TIME); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index d608a2c..d1ce29b 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) if (mem->operation & MEM_OPERATION_LOAD) perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + if (mem->operation & MEM_OPERATION_STORE) + perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) rec_argv[i++] = "-W"; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9c640a8..c859e59 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session) if (!no_callchain) { bool use_callchain = false; + bool not_pipe = false; evlist__for_each_entry(session->evlist, evsel) { + not_pipe = true; if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { use_callchain = true; break; } } - if (!use_callchain) + if (not_pipe && !use_callchain) symbol_conf.use_callchain = false; } @@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused, snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); - if (!scripts_dir) - return -1; + if (!scripts_dir) { + fprintf(stdout, + "open(%s) failed.\n" + "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n", + scripts_path); + exit(-1); + } for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d9b80ef..21fd573 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -507,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) u8 op, result, type = (config >> 0) & 0xff; const char *err = "unknown-ext-hardware-cache-type"; - if (type > PERF_COUNT_HW_CACHE_MAX) + if (type >= PERF_COUNT_HW_CACHE_MAX) goto out_err; op = (config >> 8) & 0xff; err = "unknown-ext-hardware-cache-op"; - if (op > PERF_COUNT_HW_CACHE_OP_MAX) + if (op >= PERF_COUNT_HW_CACHE_OP_MAX) goto out_err; result = (config >> 16) & 0xff; err = "unknown-ext-hardware-cache-result"; - if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX) goto out_err; err = "invalid-cache"; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 9c8f15d..8ff6c6a 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -123,8 +123,6 @@ struct intel_pt_decoder { bool have_calc_cyc_to_tsc; int exec_mode; unsigned int insn_bytes; - uint64_t sign_bit; - uint64_t sign_bits; uint64_t period; enum intel_pt_period_type period_type; uint64_t tot_insn_cnt; @@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->data = params->data; decoder->return_compression = params->return_compression; - decoder->sign_bit = (uint64_t)1 << 47; - decoder->sign_bits = ~(((uint64_t)1 << 48) - 1); - decoder->period = params->period; decoder->period_type = params->period_type; @@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen) return 0; } -static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, - const struct intel_pt_pkt *packet, +static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, uint64_t last_ip) { uint64_t ip; switch (packet->count) { - case 2: + case 1: ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) | packet->payload; break; - case 4: + case 2: ip = (last_ip & (uint64_t)0xffffffff00000000ULL) | packet->payload; break; + case 3: + ip = packet->payload; + /* Sign-extend 6-byte ip */ + if (ip & (uint64_t)0x800000000000ULL) + ip |= (uint64_t)0xffff000000000000ULL; + break; + case 4: + ip = (last_ip & (uint64_t)0xffff000000000000ULL) | + packet->payload; + break; case 6: ip = packet->payload; break; @@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, return 0; } - if (ip & decoder->sign_bit) - return ip | decoder->sign_bits; - return ip; } static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { - decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet, - decoder->last_ip); + decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -1657,6 +1657,12 @@ next: } } +static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) +{ + return decoder->last_ip || decoder->packet.count == 0 || + decoder->packet.count == 3 || decoder->packet.count == 6; +} + /* Walk PSB+ packets to get in sync. */ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) { @@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) { + if (intel_pt_have_ip(decoder)) { uint64_t current_ip = decoder->ip; intel_pt_set_ip(decoder); @@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; @@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: if (decoder->overflow) { - if (decoder->last_ip || - decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index b1257c8..4f7b320 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte, const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { - switch (byte >> 5) { + int ip_len; + + packet->count = byte >> 5; + + switch (packet->count) { case 0: - packet->count = 0; + ip_len = 0; break; case 1: if (len < 3) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 2; + ip_len = 2; packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); break; case 2: if (len < 5) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 4; + ip_len = 4; packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1)); break; case 3: - case 6: + case 4: if (len < 7) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 6; + ip_len = 6; memcpy_le64(&packet->payload, buf + 1, 6); break; + case 6: + if (len < 9) + return INTEL_PT_NEED_MORE_BYTES; + ip_len = 8; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1)); + break; default: return INTEL_PT_BAD_PACKET; } packet->type = type; - return packet->count + 1; + return ip_len + 1; } static int intel_pt_get_mode(const unsigned char *buf, size_t len, diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 9f3305f..95f0884 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -1,3 +1,4 @@ +#include <sys/sysmacros.h> #include <sys/types.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 9aed9c3..9c3b9ed 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag) /* Get raw string list of current kprobe_events or uprobe_events */ struct strlist *probe_file__get_rawlist(int fd) { - int ret, idx; + int ret, idx, fddup; FILE *fp; char buf[MAX_CMDLEN]; char *p; @@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd) return NULL; sl = strlist__new(NULL, NULL); + if (sl == NULL) + return NULL; + + fddup = dup(fd); + if (fddup < 0) + goto out_free_sl; + + fp = fdopen(fddup, "r"); + if (!fp) + goto out_close_fddup; - fp = fdopen(dup(fd), "r"); while (!feof(fp)) { p = fgets(buf, MAX_CMDLEN, fp); if (!p) @@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd) ret = strlist__add(sl, buf); if (ret < 0) { pr_debug("strlist__add failed (%d)\n", ret); - strlist__delete(sl); - return NULL; + goto out_close_fp; } } fclose(fp); return sl; + +out_close_fp: + fclose(fp); + goto out_free_sl; +out_close_fddup: + close(fddup); +out_free_sl: + strlist__delete(sl); + return NULL; } static struct strlist *__probe_file__get_namelist(int fd, bool include_group) @@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache) { struct probe_cache_entry *entry = NULL; char buf[MAX_CMDLEN], *p; - int ret = 0; + int ret = 0, fddup; FILE *fp; - fp = fdopen(dup(pcache->fd), "r"); - if (!fp) + fddup = dup(pcache->fd); + if (fddup < 0) + return -errno; + fp = fdopen(fddup, "r"); + if (!fp) { + close(fddup); return -EINVAL; + } while (!feof(fp)) { if (!fgets(buf, MAX_CMDLEN, fp)) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a34321e..a811c13 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map, sec = syms_ss->symtab; shdr = syms_ss->symshdr; - if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL)) + if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr, + ".text", NULL)) dso->text_offset = tshdr.sh_addr - tshdr.sh_offset; if (runtime_ss->opdsec) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index cf5e250..783a53f 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = ip; + e->ip = al.addr; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 97c0f8f..20c2e57 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread, thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); - e.ip = ip; + e.ip = al.addr; e.map = al.map; e.sym = al.sym; diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 4fde8c7..77e6ccf 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -33,6 +33,7 @@ static struct timecounter *timecounter; static struct workqueue_struct *wqueue; static unsigned int host_vtimer_irq; +static u32 host_vtimer_irq_flags; void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { @@ -365,7 +366,7 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) static void kvm_timer_init_interrupt(void *info) { - enable_percpu_irq(host_vtimer_irq, 0); + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -432,6 +433,14 @@ int kvm_timer_hyp_init(void) } host_vtimer_irq = info->virtual_irq; + host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); + if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && + host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for IRQ%d, assuming level low\n", + host_vtimer_irq); + host_vtimer_irq_flags = IRQF_TRIGGER_LOW; + } + err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, "kvm guest timer", kvm_get_running_vcpus()); if (err) { diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 07411cf..4660a7d 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -51,7 +51,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid) irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL); if (!irq) - return NULL; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&irq->lpi_list); INIT_LIST_HEAD(&irq->ap_list); @@ -441,39 +441,63 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. + * Returns 0 on success, a positive error value for any ITS mapping + * related errors and negative error values for generic errors. */ -static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid) +static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid) { + struct kvm_vcpu *vcpu; struct its_itte *itte; if (!its->enabled) - return; + return -EBUSY; itte = find_itte(its, devid, eventid); - /* Triggering an unmapped IRQ gets silently dropped. */ - if (itte && its_is_collection_mapped(itte->collection)) { - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); - if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) { - spin_lock(&itte->irq->irq_lock); - itte->irq->pending = true; - vgic_queue_irq_unlock(kvm, itte->irq); - } - } + if (!itte || !its_is_collection_mapped(itte->collection)) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); + if (!vcpu) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + if (!vcpu->arch.vgic_cpu.lpis_enabled) + return -EBUSY; + + spin_lock(&itte->irq->irq_lock); + itte->irq->pending = true; + vgic_queue_irq_unlock(kvm, itte->irq); + + return 0; +} + +static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev) +{ + struct vgic_io_device *iodev; + + if (dev->ops != &kvm_io_gic_ops) + return NULL; + + iodev = container_of(dev, struct vgic_io_device, dev); + + if (iodev->iodev_type != IODEV_ITS) + return NULL; + + return iodev; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. + * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { u64 address; struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; + int ret; if (!vgic_has_its(kvm)) return -ENODEV; @@ -485,15 +509,28 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address); if (!kvm_io_dev) - return -ENODEV; + return -EINVAL; - iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); + iodev = vgic_get_its_iodev(kvm_io_dev); + if (!iodev) + return -EINVAL; mutex_lock(&iodev->its->its_lock); - vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); + ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); mutex_unlock(&iodev->its->its_lock); - return 0; + if (ret < 0) + return ret; + + /* + * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 + * if the guest has blocked the MSI. So we map any LPI mapping + * related error to that. + */ + if (ret) + return 0; + else + return 1; } /* Requires the its_lock to be held. */ @@ -502,7 +539,8 @@ static void its_free_itte(struct kvm *kvm, struct its_itte *itte) list_del(&itte->itte_list); /* This put matches the get in vgic_add_lpi. */ - vgic_put_irq(kvm, itte->irq); + if (itte->irq) + vgic_put_irq(kvm, itte->irq); kfree(itte); } @@ -697,6 +735,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, struct its_device *device; struct its_collection *collection, *new_coll = NULL; int lpi_nr; + struct vgic_irq *irq; device = find_its_device(its, device_id); if (!device) @@ -710,6 +749,10 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; + /* If there is an existing mapping, behavior is UNPREDICTABLE. */ + if (find_itte(its, device_id, event_id)) + return 0; + collection = find_collection(its, coll_id); if (!collection) { int ret = vgic_its_alloc_collection(its, &collection, coll_id); @@ -718,22 +761,28 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, new_coll = collection; } - itte = find_itte(its, device_id, event_id); + itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); if (!itte) { - itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); - if (!itte) { - if (new_coll) - vgic_its_free_collection(its, coll_id); - return -ENOMEM; - } - - itte->event_id = event_id; - list_add_tail(&itte->itte_list, &device->itt_head); + if (new_coll) + vgic_its_free_collection(its, coll_id); + return -ENOMEM; } + itte->event_id = event_id; + list_add_tail(&itte->itte_list, &device->itt_head); + itte->collection = collection; itte->lpi = lpi_nr; - itte->irq = vgic_add_lpi(kvm, lpi_nr); + + irq = vgic_add_lpi(kvm, lpi_nr); + if (IS_ERR(irq)) { + if (new_coll) + vgic_its_free_collection(its, coll_id); + its_free_itte(kvm, itte); + return PTR_ERR(irq); + } + itte->irq = irq; + update_affinity_itte(kvm, itte); /* @@ -981,9 +1030,7 @@ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); - vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); - - return 0; + return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* @@ -1288,13 +1335,13 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu) its_sync_lpi_pending_table(vcpu); } -static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) +static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its) { struct vgic_io_device *iodev = &its->iodev; int ret; - if (its->initialized) - return 0; + if (!its->initialized) + return -EBUSY; if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) return -ENXIO; @@ -1311,9 +1358,6 @@ static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) KVM_VGIC_V3_ITS_SIZE, &iodev->dev); mutex_unlock(&kvm->slots_lock); - if (!ret) - its->initialized = true; - return ret; } @@ -1435,9 +1479,6 @@ static int vgic_its_set_attr(struct kvm_device *dev, if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; - if (its->initialized) - return -EBUSY; - if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; @@ -1453,7 +1494,9 @@ static int vgic_its_set_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: - return vgic_its_init_its(dev->kvm, its); + its->initialized = true; + + return 0; } break; } @@ -1498,3 +1541,30 @@ int kvm_vgic_register_its_device(void) return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } + +/* + * Registers all ITSes with the kvm_io_bus framework. + * To follow the existing VGIC initialization sequence, this has to be + * done as late as possible, just before the first VCPU runs. + */ +int vgic_register_its_iodevs(struct kvm *kvm) +{ + struct kvm_device *dev; + int ret = 0; + + list_for_each_entry(dev, &kvm->devices, vm_node) { + if (dev->ops != &kvm_arm_vgic_its_ops) + continue; + + ret = vgic_register_its_iodev(kvm, dev->private); + if (ret) + return ret; + /* + * We don't need to care about tearing down previously + * registered ITSes, as the kvm_io_bus framework removes + * them for us if the VM gets destroyed. + */ + } + + return ret; +} diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index ff668e0..90d8181 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -306,16 +306,19 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 propbaser = dist->propbaser; + u64 old_propbaser, propbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - propbaser = update_64bit_reg(propbaser, addr & 4, len, val); - propbaser = vgic_sanitise_propbaser(propbaser); - - dist->propbaser = propbaser; + do { + old_propbaser = dist->propbaser; + propbaser = old_propbaser; + propbaser = update_64bit_reg(propbaser, addr & 4, len, val); + propbaser = vgic_sanitise_propbaser(propbaser); + } while (cmpxchg64(&dist->propbaser, old_propbaser, + propbaser) != old_propbaser); } static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, @@ -331,16 +334,19 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 pendbaser = vgic_cpu->pendbaser; + u64 old_pendbaser, pendbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); - pendbaser = vgic_sanitise_pendbaser(pendbaser); - - vgic_cpu->pendbaser = pendbaser; + do { + old_pendbaser = vgic_cpu->pendbaser; + pendbaser = old_pendbaser; + pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); + pendbaser = vgic_sanitise_pendbaser(pendbaser); + } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, + pendbaser) != old_pendbaser); } /* diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 0506543..9f0dae3 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -289,6 +289,14 @@ int vgic_v3_map_resources(struct kvm *kvm) goto out; } + if (vgic_has_its(kvm)) { + ret = vgic_register_its_iodevs(kvm); + if (ret) { + kvm_err("Unable to register VGIC ITS MMIO regions\n"); + goto out; + } + } + dist->ready = true; out: diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index e7aeac7..e83b7fe 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -117,17 +117,17 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { - struct vgic_dist *dist; + struct vgic_dist *dist = &kvm->arch.vgic; if (irq->intid < VGIC_MIN_LPI) return; - if (!kref_put(&irq->refcount, vgic_irq_release)) + spin_lock(&dist->lpi_list_lock); + if (!kref_put(&irq->refcount, vgic_irq_release)) { + spin_unlock(&dist->lpi_list_lock); return; + }; - dist = &kvm->arch.vgic; - - spin_lock(&dist->lpi_list_lock); list_del(&irq->lpi_list); dist->lpi_list_count--; spin_unlock(&dist->lpi_list_lock); diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 1d8e21d..6c4625c 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -84,6 +84,7 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu); int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address); +int vgic_register_its_iodevs(struct kvm *kvm); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); void vgic_enable_lpis(struct kvm_vcpu *vcpu); @@ -140,6 +141,11 @@ static inline int vgic_register_redist_iodevs(struct kvm *kvm, return -ENODEV; } +static inline int vgic_register_its_iodevs(struct kvm *kvm) +{ + return -ENODEV; +} + static inline bool vgic_has_its(struct kvm *kvm) { return false; |
