diff options
433 files changed, 5188 insertions, 2358 deletions
@@ -2808,8 +2808,7 @@ S: Ottawa, Ontario S: Canada K2P 0X8 N: Mikael Pettersson -E: mikpe@it.uu.se -W: http://user.it.uu.se/~mikpe/linux/ +E: mikpelinux@gmail.com D: Miscellaneous fixes N: Reed H. Petty diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX index d18ecd8..929d990 100644 --- a/Documentation/block/00-INDEX +++ b/Documentation/block/00-INDEX @@ -6,6 +6,8 @@ capability.txt - Generic Block Device Capability (/sys/block/<device>/capability) cfq-iosched.txt - CFQ IO scheduler tunables +cmdline-partition.txt + - how to specify block device partitions on kernel command line data-integrity.txt - Block data integrity deadline-iosched.txt diff --git a/Documentation/block/cmdline-partition.txt b/Documentation/block/cmdline-partition.txt index 2bbf4cc..525b9f6 100644 --- a/Documentation/block/cmdline-partition.txt +++ b/Documentation/block/cmdline-partition.txt @@ -1,9 +1,9 @@ -Embedded device command line partition +Embedded device command line partition parsing ===================================================================== -Read block device partition table from command line. -The partition used for fixed block device (eMMC) embedded device. -It is no MBR, save storage space. Bootloader can be easily accessed +Support for reading the block device partition table from the command line. +It is typically used for fixed block (eMMC) embedded devices. +It has no MBR, so saves storage space. Bootloader can be easily accessed by absolute address of data on the block device. Users can easily change the partition. diff --git a/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt index 6d1c098..c67b975 100644 --- a/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt +++ b/Documentation/devicetree/bindings/mmc/exynos-dw-mshc.txt @@ -1,11 +1,11 @@ -* Samsung Exynos specific extensions to the Synopsis Designware Mobile +* Samsung Exynos specific extensions to the Synopsys Designware Mobile Storage Host Controller -The Synopsis designware mobile storage host controller is used to interface +The Synopsys designware mobile storage host controller is used to interface a SoC with storage medium such as eMMC or SD/MMC cards. This file documents -differences between the core Synopsis dw mshc controller properties described -by synopsis-dw-mshc.txt and the properties used by the Samsung Exynos specific -extensions to the Synopsis Designware Mobile Storage Host Controller. +differences between the core Synopsys dw mshc controller properties described +by synopsys-dw-mshc.txt and the properties used by the Samsung Exynos specific +extensions to the Synopsys Designware Mobile Storage Host Controller. Required Properties: diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt index 8a3d91d..c559f3f 100644 --- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt +++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt @@ -1,11 +1,11 @@ -* Rockchip specific extensions to the Synopsis Designware Mobile +* Rockchip specific extensions to the Synopsys Designware Mobile Storage Host Controller -The Synopsis designware mobile storage host controller is used to interface +The Synopsys designware mobile storage host controller is used to interface a SoC with storage medium such as eMMC or SD/MMC cards. This file documents -differences between the core Synopsis dw mshc controller properties described -by synopsis-dw-mshc.txt and the properties used by the Rockchip specific -extensions to the Synopsis Designware Mobile Storage Host Controller. +differences between the core Synopsys dw mshc controller properties described +by synopsys-dw-mshc.txt and the properties used by the Rockchip specific +extensions to the Synopsys Designware Mobile Storage Host Controller. Required Properties: diff --git a/Documentation/devicetree/bindings/mmc/synopsis-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt index cdcebea..066a78b 100644 --- a/Documentation/devicetree/bindings/mmc/synopsis-dw-mshc.txt +++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt @@ -1,14 +1,14 @@ -* Synopsis Designware Mobile Storage Host Controller +* Synopsys Designware Mobile Storage Host Controller -The Synopsis designware mobile storage host controller is used to interface +The Synopsys designware mobile storage host controller is used to interface a SoC with storage medium such as eMMC or SD/MMC cards. This file documents differences between the core mmc properties described by mmc.txt and the -properties used by the Synopsis Designware Mobile Storage Host Controller. +properties used by the Synopsys Designware Mobile Storage Host Controller. Required Properties: * compatible: should be - - snps,dw-mshc: for controllers compliant with synopsis dw-mshc. + - snps,dw-mshc: for controllers compliant with synopsys dw-mshc. * #address-cells: should be 1. * #size-cells: should be 0. diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt index eabcb4b..e216af3 100644 --- a/Documentation/devicetree/bindings/pci/designware-pcie.txt +++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt @@ -1,4 +1,4 @@ -* Synopsis Designware PCIe interface +* Synopsys Designware PCIe interface Required properties: - compatible: should contain "snps,dw-pcie" to identify the diff --git a/Documentation/devicetree/bindings/tty/serial/qca,ar9330-uart.txt b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt index c5e032c..c5e032c 100644 --- a/Documentation/devicetree/bindings/tty/serial/qca,ar9330-uart.txt +++ b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 1a036cd9..fcbb736 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -480,6 +480,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Format: <io>,<irq>,<mode> See header of drivers/net/hamradio/baycom_ser_hdx.c. + blkdevparts= Manual partition parsing of block device(s) for + embedded devices based on command line input. + See Documentation/block/cmdline-partition.txt + boot_delay= Milliseconds to delay each printk during boot. Values larger than 10 seconds (10000) are changed to no delay (0). @@ -1357,7 +1361,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. pages. In the event, a node is too small to have both kernelcore and Movable pages, kernelcore pages will take priority and other nodes will have a larger number - of kernelcore pages. The Movable zone is used for the + of Movable pages. The Movable zone is used for the allocation of pages that may be reclaimed or moved by the page migration subsystem. This means that HugeTLB pages may not be allocated from this zone. @@ -3485,6 +3489,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. the unplug protocol never -- do not unplug even if version check succeeds + xen_nopvspin [X86,XEN] + Disables the ticketlock slowpath using Xen PV + optimizations. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt index a46ddb8..f911e36 100644 --- a/Documentation/sound/alsa/HD-Audio-Models.txt +++ b/Documentation/sound/alsa/HD-Audio-Models.txt @@ -296,6 +296,12 @@ Cirrus Logic CS4206/4207 imac27 IMac 27 Inch auto BIOS setup (default) +Cirrus Logic CS4208 +=================== + mba6 MacBook Air 6,1 and 6,2 + gpio0 Enable GPIO 0 amp + auto BIOS setup (default) + VIA VT17xx/VT18xx/VT20xx ======================== auto BIOS setup (default) diff --git a/MAINTAINERS b/MAINTAINERS index e61c2e8..d2d2f45 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1812,7 +1812,8 @@ S: Supported F: drivers/net/ethernet/broadcom/bnx2x/ BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE -M: Christian Daudt <csd@broadcom.com> +M: Christian Daudt <bcm@fixthebug.org> +L: bcm-kernel-feedback-list@broadcom.com T: git git://git.github.com/broadcom/bcm11351 S: Maintained F: arch/arm/mach-bcm/ @@ -2639,6 +2640,18 @@ F: include/linux/device-mapper.h F: include/linux/dm-*.h F: include/uapi/linux/dm-*.h +DIGI NEO AND CLASSIC PCI PRODUCTS +M: Lidza Louina <lidza.louina@gmail.com> +L: driverdev-devel@linuxdriverproject.org +S: Maintained +F: drivers/staging/dgnc/ + +DIGI EPCA PCI PRODUCTS +M: Lidza Louina <lidza.louina@gmail.com> +L: driverdev-devel@linuxdriverproject.org +S: Maintained +F: drivers/staging/dgap/ + DIOLAN U2C-12 I2C DRIVER M: Guenter Roeck <linux@roeck-us.net> L: linux-i2c@vger.kernel.org @@ -6595,7 +6608,7 @@ S: Obsolete F: drivers/net/wireless/prism54/ PROMISE SATA TX2/TX4 CONTROLLER LIBATA DRIVER -M: Mikael Pettersson <mikpe@it.uu.se> +M: Mikael Pettersson <mikpelinux@gmail.com> L: linux-ide@vger.kernel.org S: Maintained F: drivers/ata/sata_promise.* @@ -7258,9 +7271,9 @@ F: include/linux/sched.h F: include/uapi/linux/sched.h SCORE ARCHITECTURE -M: Chen Liqin <liqin.chen@sunplusct.com> +M: Chen Liqin <liqin.linux@gmail.com> M: Lennox Wu <lennox.wu@gmail.com> -W: http://www.sunplusct.com +W: http://www.sunplus.com S: Supported F: arch/score/ @@ -8724,9 +8737,8 @@ F: Documentation/hid/hiddev.txt F: drivers/hid/usbhid/ USB/IP DRIVERS -M: Matt Mooney <mfm@muteddisk.com> L: linux-usb@vger.kernel.org -S: Maintained +S: Orphan F: drivers/staging/usbip/ USB ISP116X DRIVER @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = One Giant Leap for Frogkind # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 1feb169..af2cc6e 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -286,9 +286,6 @@ config HAVE_PERF_USER_STACK_DUMP config HAVE_ARCH_JUMP_LABEL bool -config HAVE_ARCH_MUTEX_CPU_RELAX - bool - config HAVE_RCU_TABLE_FREE bool diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index f158197..b6a8c2d 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -45,7 +45,14 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) static inline void arch_spin_unlock(arch_spinlock_t *lock) { - lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; + unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__; + + __asm__ __volatile__( + " ex %0, [%1] \n" + : "+r" (tmp) + : "r"(&(lock->slock)) + : "memory"); + smp_mb(); } diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index 3242082..30c9baf 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -43,7 +43,7 @@ * Because it essentially checks if buffer end is within limit and @len is * non-ngeative, which implies that buffer start will be within limit too. * - * The reason for rewriting being, for majorit yof cases, @len is generally + * The reason for rewriting being, for majority of cases, @len is generally * compile time constant, causing first sub-expression to be compile time * subsumed. * @@ -53,7 +53,7 @@ * */ #define __user_ok(addr, sz) (((sz) <= TASK_SIZE) && \ - (((addr)+(sz)) <= get_fs())) + ((addr) <= (get_fs() - (sz)))) #define __access_ok(addr, sz) (unlikely(__kernel_ok) || \ likely(__user_ok((addr), (sz)))) diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 0e51e69..3fde7de 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -227,12 +227,9 @@ void __attribute__((weak)) arc_local_timer_setup(unsigned int cpu) { struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu); - clockevents_calc_mult_shift(clk, arc_get_core_freq(), 5); - - clk->max_delta_ns = clockevent_delta2ns(ARC_TIMER_MAX, clk); clk->cpumask = cpumask_of(cpu); - - clockevents_register_device(clk); + clockevents_config_and_register(clk, arc_get_core_freq(), + 0, ARC_TIMER_MAX); /* * setup the per-cpu timer IRQ handler - for all cpus diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 28d1700..7ff5b5c 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -245,6 +245,12 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; + + /* handle zero-overhead-loop */ + if ((regs->ret == regs->lp_end) && (regs->lp_count)) { + regs->ret = regs->lp_start; + regs->lp_count--; + } } return 0; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3f7714d..1ad6fb6 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2217,8 +2217,7 @@ config NEON config KERNEL_MODE_NEON bool "Support for NEON in kernel mode" - default n - depends on NEON + depends on NEON && AEABI help Say Y to include support for NEON in kernel mode. diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S index 19d6cd6..3a14ea8 100644 --- a/arch/arm/crypto/aes-armv4.S +++ b/arch/arm/crypto/aes-armv4.S @@ -148,7 +148,7 @@ AES_Te: @ const AES_KEY *key) { .align 5 ENTRY(AES_encrypt) - sub r3,pc,#8 @ AES_encrypt + adr r3,AES_encrypt stmdb sp!,{r1,r4-r12,lr} mov r12,r0 @ inp mov r11,r2 @@ -381,7 +381,7 @@ _armv4_AES_encrypt: .align 5 ENTRY(private_AES_set_encrypt_key) _armv4_AES_set_encrypt_key: - sub r3,pc,#8 @ AES_set_encrypt_key + adr r3,_armv4_AES_set_encrypt_key teq r0,#0 moveq r0,#-1 beq .Labrt @@ -843,7 +843,7 @@ AES_Td: @ const AES_KEY *key) { .align 5 ENTRY(AES_decrypt) - sub r3,pc,#8 @ AES_decrypt + adr r3,AES_decrypt stmdb sp!,{r1,r4-r12,lr} mov r12,r0 @ inp mov r11,r2 diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 7e1f760..72abdc5 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -19,6 +19,13 @@ #include <asm/unified.h> #include <asm/compiler.h> +#if __LINUX_ARM_ARCH__ < 6 +#include <asm-generic/uaccess-unaligned.h> +#else +#define __get_user_unaligned __get_user +#define __put_user_unaligned __put_user +#endif + #define VERIFY_READ 0 #define VERIFY_WRITE 1 diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 74ad15d1..bc6bd96 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -442,10 +442,10 @@ local_restart: ldrcc pc, [tbl, scno, lsl #2] @ call sys_* routine add r1, sp, #S_OFF - cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) +2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back bcs arm_syscall -2: mov why, #0 @ no longer a real syscall + mov why, #0 @ no longer a real syscall b sys_ni_syscall @ not private func #if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI) diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S index de23a9b..39f89fb 100644 --- a/arch/arm/kernel/entry-header.S +++ b/arch/arm/kernel/entry-header.S @@ -329,10 +329,10 @@ #ifdef CONFIG_CONTEXT_TRACKING .if \save stmdb sp!, {r0-r3, ip, lr} - bl user_exit + bl context_tracking_user_exit ldmia sp!, {r0-r3, ip, lr} .else - bl user_exit + bl context_tracking_user_exit .endif #endif .endm @@ -341,10 +341,10 @@ #ifdef CONFIG_CONTEXT_TRACKING .if \save stmdb sp!, {r0-r3, ip, lr} - bl user_enter + bl context_tracking_user_enter ldmia sp!, {r0-r3, ip, lr} .else - bl user_enter + bl context_tracking_user_enter .endif #endif .endm diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index d22af85..fd79807 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -1,5 +1,19 @@ generic-y += clkdev.h +generic-y += cputime.h +generic-y += delay.h +generic-y += device.h +generic-y += div64.h +generic-y += emergency-restart.h generic-y += exec.h -generic-y += trace_clock.h +generic-y += futex.h +generic-y += irq_regs.h generic-y += param.h +generic-y += local.h +generic-y += local64.h +generic-y += percpu.h +generic-y += scatterlist.h +generic-y += sections.h +generic-y += topology.h +generic-y += trace_clock.h +generic-y += xor.h diff --git a/arch/avr32/include/asm/cputime.h b/arch/avr32/include/asm/cputime.h deleted file mode 100644 index e87e0f8..0000000 --- a/arch/avr32/include/asm/cputime.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_CPUTIME_H -#define __ASM_AVR32_CPUTIME_H - -#include <asm-generic/cputime.h> - -#endif /* __ASM_AVR32_CPUTIME_H */ diff --git a/arch/avr32/include/asm/delay.h b/arch/avr32/include/asm/delay.h deleted file mode 100644 index 9670e12..0000000 --- a/arch/avr32/include/asm/delay.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/delay.h> diff --git a/arch/avr32/include/asm/device.h b/arch/avr32/include/asm/device.h deleted file mode 100644 index d8f9872..0000000 --- a/arch/avr32/include/asm/device.h +++ /dev/null @@ -1,7 +0,0 @@ -/* - * Arch specific extensions to struct device - * - * This file is released under the GPLv2 - */ -#include <asm-generic/device.h> - diff --git a/arch/avr32/include/asm/div64.h b/arch/avr32/include/asm/div64.h deleted file mode 100644 index d7ddd4f..0000000 --- a/arch/avr32/include/asm/div64.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_DIV64_H -#define __ASM_AVR32_DIV64_H - -#include <asm-generic/div64.h> - -#endif /* __ASM_AVR32_DIV64_H */ diff --git a/arch/avr32/include/asm/emergency-restart.h b/arch/avr32/include/asm/emergency-restart.h deleted file mode 100644 index 3e7e014..0000000 --- a/arch/avr32/include/asm/emergency-restart.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_EMERGENCY_RESTART_H -#define __ASM_AVR32_EMERGENCY_RESTART_H - -#include <asm-generic/emergency-restart.h> - -#endif /* __ASM_AVR32_EMERGENCY_RESTART_H */ diff --git a/arch/avr32/include/asm/futex.h b/arch/avr32/include/asm/futex.h deleted file mode 100644 index 10419f1..0000000 --- a/arch/avr32/include/asm/futex.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_FUTEX_H -#define __ASM_AVR32_FUTEX_H - -#include <asm-generic/futex.h> - -#endif /* __ASM_AVR32_FUTEX_H */ diff --git a/arch/avr32/include/asm/irq_regs.h b/arch/avr32/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b..0000000 --- a/arch/avr32/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/irq_regs.h> diff --git a/arch/avr32/include/asm/local.h b/arch/avr32/include/asm/local.h deleted file mode 100644 index 1c16196..0000000 --- a/arch/avr32/include/asm/local.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_LOCAL_H -#define __ASM_AVR32_LOCAL_H - -#include <asm-generic/local.h> - -#endif /* __ASM_AVR32_LOCAL_H */ diff --git a/arch/avr32/include/asm/local64.h b/arch/avr32/include/asm/local64.h deleted file mode 100644 index 36c93b5..0000000 --- a/arch/avr32/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/avr32/include/asm/percpu.h b/arch/avr32/include/asm/percpu.h deleted file mode 100644 index 69227b4..0000000 --- a/arch/avr32/include/asm/percpu.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_PERCPU_H -#define __ASM_AVR32_PERCPU_H - -#include <asm-generic/percpu.h> - -#endif /* __ASM_AVR32_PERCPU_H */ diff --git a/arch/avr32/include/asm/scatterlist.h b/arch/avr32/include/asm/scatterlist.h deleted file mode 100644 index a5902d98..0000000 --- a/arch/avr32/include/asm/scatterlist.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_SCATTERLIST_H -#define __ASM_AVR32_SCATTERLIST_H - -#include <asm-generic/scatterlist.h> - -#endif /* __ASM_AVR32_SCATTERLIST_H */ diff --git a/arch/avr32/include/asm/sections.h b/arch/avr32/include/asm/sections.h deleted file mode 100644 index aa14252..0000000 --- a/arch/avr32/include/asm/sections.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_SECTIONS_H -#define __ASM_AVR32_SECTIONS_H - -#include <asm-generic/sections.h> - -#endif /* __ASM_AVR32_SECTIONS_H */ diff --git a/arch/avr32/include/asm/topology.h b/arch/avr32/include/asm/topology.h deleted file mode 100644 index 5b766cb..0000000 --- a/arch/avr32/include/asm/topology.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef __ASM_AVR32_TOPOLOGY_H -#define __ASM_AVR32_TOPOLOGY_H - -#include <asm-generic/topology.h> - -#endif /* __ASM_AVR32_TOPOLOGY_H */ diff --git a/arch/avr32/include/asm/xor.h b/arch/avr32/include/asm/xor.h deleted file mode 100644 index 99c87aa..0000000 --- a/arch/avr32/include/asm/xor.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_XOR_H -#define _ASM_XOR_H - -#include <asm-generic/xor.h> - -#endif diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index c273100..42a53e74 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -289,7 +289,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, memset(childregs, 0, sizeof(struct pt_regs)); p->thread.cpu_context.r0 = arg; p->thread.cpu_context.r1 = usp; /* fn */ - p->thread.cpu_context.r2 = syscall_return; + p->thread.cpu_context.r2 = (unsigned long)syscall_return; p->thread.cpu_context.pc = (unsigned long)ret_from_kernel_thread; childregs->sr = MODE_SUPERVISOR; } else { diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c index 869a1c6..12f828a 100644 --- a/arch/avr32/kernel/time.c +++ b/arch/avr32/kernel/time.c @@ -98,7 +98,14 @@ static void comparator_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_SHUTDOWN: sysreg_write(COMPARE, 0); pr_debug("%s: stop\n", evdev->name); - cpu_idle_poll_ctrl(false); + if (evdev->mode == CLOCK_EVT_MODE_ONESHOT || + evdev->mode == CLOCK_EVT_MODE_RESUME) { + /* + * Only disable idle poll if we have forced that + * in a previous call. + */ + cpu_idle_poll_ctrl(false); + } break; default: BUG(); diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index 51680d1..d445d06 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -187,7 +187,7 @@ /* * MIPS32, MIPS64, VR5500, IDT32332, IDT32334 and maybe a few other - * pre-MIPS32/MIPS53 processors have CLO, CLZ. The IDT RC64574 is 64-bit and + * pre-MIPS32/MIPS64 processors have CLO, CLZ. The IDT RC64574 is 64-bit and * has CLO and CLZ but not DCLO nor DCLZ. For 64-bit kernels * cpu_has_clo_clz also indicates the availability of DCLO and DCLZ. */ diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index f25a7e9..5f8b955 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -308,12 +308,10 @@ static void mips_dma_sync_sg_for_cpu(struct device *dev, { int i; - /* Make sure that gcc doesn't leave the empty loop body. */ - for (i = 0; i < nelems; i++, sg++) { - if (cpu_needs_post_dma_flush(dev)) + if (cpu_needs_post_dma_flush(dev)) + for (i = 0; i < nelems; i++, sg++) __dma_sync(sg_page(sg), sg->offset, sg->length, direction); - } } static void mips_dma_sync_sg_for_device(struct device *dev, @@ -321,12 +319,10 @@ static void mips_dma_sync_sg_for_device(struct device *dev, { int i; - /* Make sure that gcc doesn't leave the empty loop body. */ - for (i = 0; i < nelems; i++, sg++) { - if (!plat_device_is_coherent(dev)) + if (!plat_device_is_coherent(dev)) + for (i = 0; i < nelems; i++, sg++) __dma_sync(sg_page(sg), sg->offset, sg->length, direction); - } } int mips_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h index eb59bfe..93c9980 100644 --- a/arch/openrisc/include/asm/prom.h +++ b/arch/openrisc/include/asm/prom.h @@ -14,53 +14,9 @@ * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ - -#include <linux/of.h> /* linux/of.h gets to determine #include ordering */ - #ifndef _ASM_OPENRISC_PROM_H #define _ASM_OPENRISC_PROM_H -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ -#include <linux/types.h> -#include <asm/irq.h> -#include <linux/irqdomain.h> -#include <linux/atomic.h> -#include <linux/of_irq.h> -#include <linux/of_fdt.h> -#include <linux/of_address.h> -#include <linux/proc_fs.h> -#include <linux/platform_device.h> #define HAVE_ARCH_DEVTREE_FIXUPS -/* Other Prototypes */ -extern int early_uartlite_console(void); - -/* Parse the ibm,dma-window property of an OF node into the busno, phys and - * size parameters. - */ -void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, - unsigned long *busno, unsigned long *phys, unsigned long *size); - -extern void kdump_move_device_tree(void); - -/* Get the MAC address */ -extern const void *of_get_mac_address(struct device_node *np); - -/** - * of_irq_map_pci - Resolve the interrupt for a PCI device - * @pdev: the device whose interrupt is to be resolved - * @out_irq: structure of_irq filled by this function - * - * This function resolves the PCI interrupt for a given PCI device. If a - * device-node exists for a given pci_dev, it will use normal OF tree - * walking. If not, it will implement standard swizzling and walk up the - * PCI tree until an device-node is found, at which point it will finish - * resolving using the OF tree walking. - */ -struct pci_dev; -extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq); - -#endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ #endif /* _ASM_OPENRISC_PROM_H */ diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index d10d27a..00c0ed3 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -182,6 +182,9 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + acc_type = parisc_acctyp(code, regs->iir); + if (acc_type & VM_WRITE) flags |= FAULT_FLAG_WRITE; retry: @@ -196,8 +199,6 @@ retry: good_area: - acc_type = parisc_acctyp(code,regs->iir); - if ((vma->vm_flags & acc_type) != acc_type) goto bad_area; diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6a15c96..15ca225 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -74,7 +74,7 @@ src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c -src-plat-y := of.c +src-plat-y := of.c epapr.c src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \ treeboot-walnut.c cuboot-acadia.c \ cuboot-kilauea.c simpleboot.c \ @@ -97,7 +97,7 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \ prpmc2800.c src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c -src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c +src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c src-wlib := $(sort $(src-wlib-y)) src-plat := $(sort $(src-plat-y)) diff --git a/arch/powerpc/boot/epapr-wrapper.c b/arch/powerpc/boot/epapr-wrapper.c new file mode 100644 index 0000000..c101910 --- /dev/null +++ b/arch/powerpc/boot/epapr-wrapper.c @@ -0,0 +1,9 @@ +extern void epapr_platform_init(unsigned long r3, unsigned long r4, + unsigned long r5, unsigned long r6, + unsigned long r7); + +void platform_init(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7) +{ + epapr_platform_init(r3, r4, r5, r6, r7); +} diff --git a/arch/powerpc/boot/epapr.c b/arch/powerpc/boot/epapr.c index 06c1961..02e91aa 100644 --- a/arch/powerpc/boot/epapr.c +++ b/arch/powerpc/boot/epapr.c @@ -48,8 +48,8 @@ static void platform_fixups(void) fdt_addr, fdt_totalsize((void *)fdt_addr), ima_size); } -void platform_init(unsigned long r3, unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7) +void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7) { epapr_magic = r6; ima_size = r7; diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c index 61d9899..62e2f43 100644 --- a/arch/powerpc/boot/of.c +++ b/arch/powerpc/boot/of.c @@ -26,6 +26,9 @@ static unsigned long claim_base; +void epapr_platform_init(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7); + static void *of_try_claim(unsigned long size) { unsigned long addr = 0; @@ -61,7 +64,7 @@ static void of_image_hdr(const void *hdr) } } -void platform_init(unsigned long a1, unsigned long a2, void *promptr) +static void of_platform_init(unsigned long a1, unsigned long a2, void *promptr) { platform_ops.image_hdr = of_image_hdr; platform_ops.malloc = of_try_claim; @@ -81,3 +84,14 @@ void platform_init(unsigned long a1, unsigned long a2, void *promptr) loader_info.initrd_size = a2; } } + +void platform_init(unsigned long r3, unsigned long r4, unsigned long r5, + unsigned long r6, unsigned long r7) +{ + /* Detect OF vs. ePAPR boot */ + if (r5) + of_platform_init(r3, r4, (void *)r5); + else + epapr_platform_init(r3, r4, r5, r6, r7); +} + diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index 6761c74..cd7af84 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -148,18 +148,18 @@ make_space=y case "$platform" in pseries) - platformo=$object/of.o + platformo="$object/of.o $object/epapr.o" link_address='0x4000000' ;; maple) - platformo=$object/of.o + platformo="$object/of.o $object/epapr.o" link_address='0x400000' ;; pmac|chrp) - platformo=$object/of.o + platformo="$object/of.o $object/epapr.o" ;; coff) - platformo="$object/crt0.o $object/of.o" + platformo="$object/crt0.o $object/of.o $object/epapr.o" lds=$object/zImage.coff.lds link_address='0x500000' pie= @@ -253,6 +253,7 @@ treeboot-iss4xx-mpic) platformo="$object/treeboot-iss4xx.o" ;; epapr) + platformo="$object/epapr.o $object/epapr-wrapper.o" link_address='0x20000000' pie=-pie ;; diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 0e40843..41f13ce 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -69,9 +69,9 @@ extern struct thread_info *softirq_ctx[NR_CPUS]; extern void irq_ctx_init(void); extern void call_do_softirq(struct thread_info *tp); -extern int call_handle_irq(int irq, void *p1, - struct thread_info *tp, void *func); +extern void call_do_irq(struct pt_regs *regs, struct thread_info *tp); extern void do_IRQ(struct pt_regs *regs); +extern void __do_irq(struct pt_regs *regs); int irq_choose_cpu(const struct cpumask *mask); diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index e378ccc..ce4de5a 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -149,8 +149,6 @@ typedef struct { struct thread_struct { unsigned long ksp; /* Kernel stack pointer */ - unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */ - #ifdef CONFIG_PPC64 unsigned long ksp_vsid; #endif @@ -162,6 +160,7 @@ struct thread_struct { #endif #ifdef CONFIG_PPC32 void *pgdir; /* root of page-table tree */ + unsigned long ksp_limit; /* if ksp <= ksp_limit stack overflow */ #endif #ifdef CONFIG_PPC_ADV_DEBUG_REGS /* @@ -321,7 +320,6 @@ struct thread_struct { #else #define INIT_THREAD { \ .ksp = INIT_SP, \ - .ksp_limit = INIT_SP_LIMIT, \ .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \ .fs = KERNEL_DS, \ .fpr = {{0}}, \ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index d8958be..502c7a4 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -80,10 +80,11 @@ int main(void) DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr)); #else DEFINE(THREAD_INFO, offsetof(struct task_struct, stack)); + DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16)); + DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit)); #endif /* CONFIG_PPC64 */ DEFINE(KSP, offsetof(struct thread_struct, ksp)); - DEFINE(KSP_LIMIT, offsetof(struct thread_struct, ksp_limit)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); #ifdef CONFIG_BOOKE DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0])); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c69440c..57d286a 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -441,50 +441,6 @@ void migrate_irqs(void) } #endif -static inline void handle_one_irq(unsigned int irq) -{ - struct thread_info *curtp, *irqtp; - unsigned long saved_sp_limit; - struct irq_desc *desc; - - desc = irq_to_desc(irq); - if (!desc) - return; - - /* Switch to the irq stack to handle this */ - curtp = current_thread_info(); - irqtp = hardirq_ctx[smp_processor_id()]; - - if (curtp == irqtp) { - /* We're already on the irq stack, just handle it */ - desc->handle_irq(irq, desc); - return; - } - - saved_sp_limit = current->thread.ksp_limit; - - irqtp->task = curtp->task; - irqtp->flags = 0; - - /* Copy the softirq bits in preempt_count so that the - * softirq checks work in the hardirq context. */ - irqtp->preempt_count = (irqtp->preempt_count & ~SOFTIRQ_MASK) | - (curtp->preempt_count & SOFTIRQ_MASK); - - current->thread.ksp_limit = (unsigned long)irqtp + - _ALIGN_UP(sizeof(struct thread_info), 16); - - call_handle_irq(irq, desc, irqtp, desc->handle_irq); - current->thread.ksp_limit = saved_sp_limit; - irqtp->task = NULL; - - /* Set any flag that may have been set on the - * alternate stack - */ - if (irqtp->flags) - set_bits(irqtp->flags, &curtp->flags); -} - static inline void check_stack_overflow(void) { #ifdef CONFIG_DEBUG_STACKOVERFLOW @@ -501,9 +457,9 @@ static inline void check_stack_overflow(void) #endif } -void do_IRQ(struct pt_regs *regs) +void __do_irq(struct pt_regs *regs) { - struct pt_regs *old_regs = set_irq_regs(regs); + struct irq_desc *desc; unsigned int irq; irq_enter(); @@ -519,18 +475,56 @@ void do_IRQ(struct pt_regs *regs) */ irq = ppc_md.get_irq(); - /* We can hard enable interrupts now */ + /* We can hard enable interrupts now to allow perf interrupts */ may_hard_irq_enable(); /* And finally process it */ - if (irq != NO_IRQ) - handle_one_irq(irq); - else + if (unlikely(irq == NO_IRQ)) __get_cpu_var(irq_stat).spurious_irqs++; + else { + desc = irq_to_desc(irq); + if (likely(desc)) + desc->handle_irq(irq, desc); + } trace_irq_exit(regs); irq_exit(); +} + +void do_IRQ(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + struct thread_info *curtp, *irqtp; + + /* Switch to the irq stack to handle this */ + curtp = current_thread_info(); + irqtp = hardirq_ctx[raw_smp_processor_id()]; + + /* Already there ? */ + if (unlikely(curtp == irqtp)) { + __do_irq(regs); + set_irq_regs(old_regs); + return; + } + + /* Prepare the thread_info in the irq stack */ + irqtp->task = curtp->task; + irqtp->flags = 0; + + /* Copy the preempt_count so that the [soft]irq checks work. */ + irqtp->preempt_count = curtp->preempt_count; + + /* Switch stack and call */ + call_do_irq(regs, irqtp); + + /* Restore stack limit */ + irqtp->task = NULL; + + /* Copy back updates to the thread_info */ + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); + set_irq_regs(old_regs); } @@ -592,28 +586,22 @@ void irq_ctx_init(void) memset((void *)softirq_ctx[i], 0, THREAD_SIZE); tp = softirq_ctx[i]; tp->cpu = i; - tp->preempt_count = 0; memset((void *)hardirq_ctx[i], 0, THREAD_SIZE); tp = hardirq_ctx[i]; tp->cpu = i; - tp->preempt_count = HARDIRQ_OFFSET; } } static inline void do_softirq_onstack(void) { struct thread_info *curtp, *irqtp; - unsigned long saved_sp_limit = current->thread.ksp_limit; curtp = current_thread_info(); irqtp = softirq_ctx[smp_processor_id()]; irqtp->task = curtp->task; irqtp->flags = 0; - current->thread.ksp_limit = (unsigned long)irqtp + - _ALIGN_UP(sizeof(struct thread_info), 16); call_do_softirq(irqtp); - current->thread.ksp_limit = saved_sp_limit; irqtp->task = NULL; /* Set any flag that may have been set on the diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 777d999..2b0ad98 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -36,26 +36,41 @@ .text +/* + * We store the saved ksp_limit in the unused part + * of the STACK_FRAME_OVERHEAD + */ _GLOBAL(call_do_softirq) mflr r0 stw r0,4(r1) + lwz r10,THREAD+KSP_LIMIT(r2) + addi r11,r3,THREAD_INFO_GAP stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3) mr r1,r3 + stw r10,8(r1) + stw r11,THREAD+KSP_LIMIT(r2) bl __do_softirq + lwz r10,8(r1) lwz r1,0(r1) lwz r0,4(r1) + stw r10,THREAD+KSP_LIMIT(r2) mtlr r0 blr -_GLOBAL(call_handle_irq) +_GLOBAL(call_do_irq) mflr r0 stw r0,4(r1) - mtctr r6 - stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5) - mr r1,r5 - bctrl + lwz r10,THREAD+KSP_LIMIT(r2) + addi r11,r3,THREAD_INFO_GAP + stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) + mr r1,r4 + stw r10,8(r1) + stw r11,THREAD+KSP_LIMIT(r2) + bl __do_irq + lwz r10,8(r1) lwz r1,0(r1) lwz r0,4(r1) + stw r10,THREAD+KSP_LIMIT(r2) mtlr r0 blr diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 971d7e7..e59caf8 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -40,14 +40,12 @@ _GLOBAL(call_do_softirq) mtlr r0 blr -_GLOBAL(call_handle_irq) - ld r8,0(r6) +_GLOBAL(call_do_irq) mflr r0 std r0,16(r1) - mtctr r8 - stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r5) - mr r1,r5 - bctrl + stdu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) + mr r1,r4 + bl .__do_irq ld r1,0(r1) ld r0,16(r1) mtlr r0 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 6f428da..96d2fdf 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1000,9 +1000,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, kregs = (struct pt_regs *) sp; sp -= STACK_FRAME_OVERHEAD; p->thread.ksp = sp; +#ifdef CONFIG_PPC32 p->thread.ksp_limit = (unsigned long)task_stack_page(p) + _ALIGN_UP(sizeof(struct thread_info), 16); - +#endif #ifdef CONFIG_HAVE_HW_BREAKPOINT p->thread.ptrace_bps[0] = NULL; #endif diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 12e656f..5fe2842 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -196,6 +196,8 @@ static int __initdata mem_reserve_cnt; static cell_t __initdata regbuf[1024]; +static bool rtas_has_query_cpu_stopped; + /* * Error results ... some OF calls will return "-1" on error, some @@ -1574,6 +1576,11 @@ static void __init prom_instantiate_rtas(void) prom_setprop(rtas_node, "/rtas", "linux,rtas-entry", &val, sizeof(val)); + /* Check if it supports "query-cpu-stopped-state" */ + if (prom_getprop(rtas_node, "query-cpu-stopped-state", + &val, sizeof(val)) != PROM_ERROR) + rtas_has_query_cpu_stopped = true; + #if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__) /* PowerVN takeover hack */ prom_rtas_data = base; @@ -1815,6 +1822,18 @@ static void __init prom_hold_cpus(void) = (void *) LOW_ADDR(__secondary_hold_acknowledge); unsigned long secondary_hold = LOW_ADDR(__secondary_hold); + /* + * On pseries, if RTAS supports "query-cpu-stopped-state", + * we skip this stage, the CPUs will be started by the + * kernel using RTAS. + */ + if ((of_platform == PLATFORM_PSERIES || + of_platform == PLATFORM_PSERIES_LPAR) && + rtas_has_query_cpu_stopped) { + prom_printf("prom_hold_cpus: skipped\n"); + return; + } + prom_debug("prom_hold_cpus: start...\n"); prom_debug(" 1) spinloop = 0x%x\n", (unsigned long)spinloop); prom_debug(" 1) *spinloop = 0x%x\n", *spinloop); @@ -3011,6 +3030,8 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, * On non-powermacs, put all CPUs in spin-loops. * * PowerMacs use a different mechanism to spin CPUs + * + * (This must be done after instanciating RTAS) */ if (of_platform != PLATFORM_POWERMAC && of_platform != PLATFORM_OPAL) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index a7ee978..b1faa15 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1505,6 +1505,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) */ if ((ra == 1) && !(regs->msr & MSR_PR) \ && (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) { +#ifdef CONFIG_PPC32 /* * Check if we will touch kernel sack overflow */ @@ -1513,7 +1514,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) err = -EINVAL; break; } - +#endif /* CONFIG_PPC32 */ /* * Check if we already set since that means we'll * lose the previous value. diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 1c1771a..24f58cb 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -233,18 +233,24 @@ static void __init smp_init_pseries(void) alloc_bootmem_cpumask_var(&of_spin_mask); - /* Mark threads which are still spinning in hold loops. */ - if (cpu_has_feature(CPU_FTR_SMT)) { - for_each_present_cpu(i) { - if (cpu_thread_in_core(i) == 0) - cpumask_set_cpu(i, of_spin_mask); - } - } else { - cpumask_copy(of_spin_mask, cpu_present_mask); + /* + * Mark threads which are still spinning in hold loops + * + * We know prom_init will not have started them if RTAS supports + * query-cpu-stopped-state. + */ + if (rtas_token("query-cpu-stopped-state") == RTAS_UNKNOWN_SERVICE) { + if (cpu_has_feature(CPU_FTR_SMT)) { + for_each_present_cpu(i) { + if (cpu_thread_in_core(i) == 0) + cpumask_set_cpu(i, of_spin_mask); + } + } else + cpumask_copy(of_spin_mask, cpu_present_mask); + + cpumask_clear_cpu(boot_cpuid, of_spin_mask); } - cpumask_clear_cpu(boot_cpuid, of_spin_mask); - /* Non-lpar has additional take/give timebase */ if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) { smp_ops->give_timebase = rtas_give_timebase; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index dcc6ac2..7143793 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -93,6 +93,7 @@ config S390 select ARCH_INLINE_WRITE_UNLOCK_IRQ select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS2 @@ -102,7 +103,6 @@ config S390 select GENERIC_TIME_VSYSCALL_OLD select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 - select HAVE_ARCH_MUTEX_CPU_RELAX select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h index 688271f..458c1f7 100644 --- a/arch/s390/include/asm/mutex.h +++ b/arch/s390/include/asm/mutex.h @@ -7,5 +7,3 @@ */ #include <asm-generic/mutex-dec.h> - -#define arch_mutex_cpu_relax() barrier() diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 0eb3750..ca7821f 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -198,6 +198,8 @@ static inline void cpu_relax(void) barrier(); } +#define arch_mutex_cpu_relax() barrier() + static inline void psw_set_key(unsigned int key) { asm volatile("spka 0(%0)" : : "d" (key)); diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 701fe8c..83e5d216 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -44,6 +44,11 @@ extern void arch_spin_lock_wait_flags(arch_spinlock_t *, unsigned long flags); extern int arch_spin_trylock_retry(arch_spinlock_t *); extern void arch_spin_relax(arch_spinlock_t *lock); +static inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.owner_cpu == 0; +} + static inline void arch_spin_lock(arch_spinlock_t *lp) { int old; diff --git a/arch/score/Kconfig b/arch/score/Kconfig index a1be70d..305f7ee 100644 --- a/arch/score/Kconfig +++ b/arch/score/Kconfig @@ -2,6 +2,7 @@ menu "Machine selection" config SCORE def_bool y + select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_SHOW select GENERIC_IOMAP select GENERIC_ATOMIC64 @@ -110,3 +111,6 @@ source "security/Kconfig" source "crypto/Kconfig" source "lib/Kconfig" + +config NO_IOMEM + def_bool y diff --git a/arch/score/Makefile b/arch/score/Makefile index 974aefe..9e3e060 100644 --- a/arch/score/Makefile +++ b/arch/score/Makefile @@ -20,8 +20,8 @@ cflags-y += -G0 -pipe -mel -mnhwloop -D__SCOREEL__ \ # KBUILD_AFLAGS += $(cflags-y) KBUILD_CFLAGS += $(cflags-y) -KBUILD_AFLAGS_MODULE += -mlong-calls -KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_AFLAGS_MODULE += +KBUILD_CFLAGS_MODULE += LDFLAGS += --oformat elf32-littlescore LDFLAGS_vmlinux += -G0 -static -nostdlib diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h index f909ac3..961bd64 100644 --- a/arch/score/include/asm/checksum.h +++ b/arch/score/include/asm/checksum.h @@ -184,48 +184,57 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, __wsum sum) { __asm__ __volatile__( - ".set\tnoreorder\t\t\t# csum_ipv6_magic\n\t" - ".set\tnoat\n\t" - "addu\t%0, %5\t\t\t# proto (long in network byte order)\n\t" - "sltu\t$1, %0, %5\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %6\t\t\t# csum\n\t" - "sltu\t$1, %0, %6\n\t" - "lw\t%1, 0(%2)\t\t\t# four words source address\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 4(%2)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 8(%2)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 12(%2)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 0(%3)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 4(%3)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 8(%3)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "lw\t%1, 12(%3)\n\t" - "addu\t%0, $1\n\t" - "addu\t%0, %1\n\t" - "sltu\t$1, %0, %1\n\t" - "addu\t%0, $1\t\t\t# Add final carry\n\t" - ".set\tnoat\n\t" - ".set\tnoreorder" + ".set\tvolatile\t\t\t# csum_ipv6_magic\n\t" + "add\t%0, %0, %5\t\t\t# proto (long in network byte order)\n\t" + "cmp.c\t%5, %0\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %6\t\t\t# csum\n\t" + "cmp.c\t%6, %0\n\t" + "lw\t%1, [%2, 0]\t\t\t# four words source address\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "1:lw\t%1, [%2, 4]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "lw\t%1, [%2,8]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "lw\t%1, [%2, 12]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0,%1\n\t" + "cmp.c\t%1, %0\n\t" + "lw\t%1, [%3, 0]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "lw\t%1, [%3, 4]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "lw\t%1, [%3, 8]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "lw\t%1, [%3, 12]\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:add\t%0, %0, %1\n\t" + "cmp.c\t%1, %0\n\t" + "bleu 1f\n\t" + "addi\t%0, 0x1\n\t" + "1:\n\t" + ".set\toptimize" : "=r" (sum), "=r" (proto) : "r" (saddr), "r" (daddr), "0" (htonl(len)), "1" (htonl(proto)), "r" (sum)); diff --git a/arch/score/include/asm/io.h b/arch/score/include/asm/io.h index fbbfd71..574c8827 100644 --- a/arch/score/include/asm/io.h +++ b/arch/score/include/asm/io.h @@ -5,5 +5,4 @@ #define virt_to_bus virt_to_phys #define bus_to_virt phys_to_virt - #endif /* _ASM_SCORE_IO_H */ diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h index 059a61b..716b3fd 100644 --- a/arch/score/include/asm/pgalloc.h +++ b/arch/score/include/asm/pgalloc.h @@ -2,7 +2,7 @@ #define _ASM_SCORE_PGALLOC_H #include <linux/mm.h> - +#include <linux/highmem.h> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) { diff --git a/arch/score/kernel/entry.S b/arch/score/kernel/entry.S index 7234ed0..befb87d 100644 --- a/arch/score/kernel/entry.S +++ b/arch/score/kernel/entry.S @@ -264,7 +264,7 @@ resume_kernel: disable_irq lw r8, [r28, TI_PRE_COUNT] cmpz.c r8 - bne r8, restore_all + bne restore_all need_resched: lw r8, [r28, TI_FLAGS] andri.c r9, r8, _TIF_NEED_RESCHED @@ -415,7 +415,7 @@ ENTRY(handle_sys) sw r9, [r0, PT_EPC] cmpi.c r27, __NR_syscalls # check syscall number - bgeu illegal_syscall + bcs illegal_syscall slli r8, r27, 2 # get syscall routine la r11, sys_call_table diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index f4c6d02..a1519ad3 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -78,8 +78,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.reg0 = (unsigned long) childregs; if (unlikely(p->flags & PF_KTHREAD)) { memset(childregs, 0, sizeof(struct pt_regs)); - p->thread->reg12 = usp; - p->thread->reg13 = arg; + p->thread.reg12 = usp; + p->thread.reg13 = arg; p->thread.reg3 = (unsigned long) ret_from_kernel_thread; } else { *childregs = *current_pt_regs(); diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 6aef9fb..b913915 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn) return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY; } -static inline unsigned long mfn_to_pfn(unsigned long mfn) +static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn) { unsigned long pfn; - int ret = 0; + int ret; if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely(mfn >= machine_to_phys_nr)) { - pfn = ~0; - goto try_override; - } - pfn = 0; + if (unlikely(mfn >= machine_to_phys_nr)) + return ~0; + /* * The array access can fail (e.g., device space beyond end of RAM). * In such cases it doesn't matter what we return (we return garbage), * but we must handle the fault without crashing! */ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); -try_override: - /* ret might be < 0 if there are no entries in the m2p for mfn */ if (ret < 0) - pfn = ~0; - else if (get_phys_to_machine(pfn) != mfn) + return ~0; + + return pfn; +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return mfn; + + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) != mfn) { /* * If this appears to be a foreign mfn (because the pfn * doesn't map back to the mfn), then check the local override @@ -111,6 +119,7 @@ try_override: * m2p_find_override_pfn returns ~0 if it doesn't find anything. */ pfn = m2p_find_override_pfn(mfn, ~0); + } /* * pfn is ~0 if there are no entries in the m2p for mfn or if the diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 8355c84..897783b 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return 0; + err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); @@ -1883,9 +1883,9 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { - userpg->cap_usr_time = 0; - userpg->cap_usr_time_zero = 0; - userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -1894,13 +1894,13 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) return; - userpg->cap_usr_time = 1; + userpg->cap_user_time = 1; userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; if (sched_clock_stable && !check_tsc_disabled()) { - userpg->cap_usr_time_zero = 1; + userpg->cap_user_time_zero = 1; userpg->time_zero = this_cpu_read(cyc2ns_offset); } } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9db76c3..f31a165 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2325,6 +2325,7 @@ __init int intel_pmu_init(void) break; case 55: /* Atom 22nm "Silvermont" */ + case 77: /* Avoton "Silvermont" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 8ed4458..4118f9f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2706,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) { struct intel_uncore_box *box; int i, size; size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; @@ -3031,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu, struct intel_uncore_box *fake_box; int ret = -EINVAL, n; - fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); if (!fake_box) return -ENOMEM; @@ -3294,7 +3294,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id } type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; - box = uncore_alloc_box(type, 0); + box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3499,7 +3499,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id) if (pmu->func_id < 0) pmu->func_id = j; - box = uncore_alloc_box(type, cpu); + box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7123b5d..af99f71 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; + uci->cpu_sig.rev = rev; return 0; } diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 563ed91..e643e74 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -352,12 +352,28 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, { /* Handle problems with rebooting on the Precision M6600. */ .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + .ident = "Dell Precision M6600", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), }, }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Some C6100 machines were shipped with vendor being 'Dell'. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, { } }; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 90f6ed1..c7e22ab 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -912,10 +912,13 @@ void __init efi_enter_virtual_mode(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; + if (!(md->attribute & EFI_MEMORY_RUNTIME)) { +#ifdef CONFIG_X86_64 + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) +#endif + continue; + } size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 8b901e8..a61c7d5 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -879,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; - int ret = 0; pfn = page_to_pfn(page); if (!PageHighMem(page)) { @@ -926,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page, * frontend pages while they are being shared with the backend, * because mfn_to_pfn (that ends up being called by GUPF) will * return the backend pfn rather than the frontend pfn. */ - ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); - if (ret == 0 && get_phys_to_machine(pfn) == mfn) + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) == mfn) set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); return 0; @@ -942,7 +941,6 @@ int m2p_remove_override(struct page *page, unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; - int ret = 0; pfn = page_to_pfn(page); mfn = get_phys_to_machine(pfn); @@ -1029,8 +1027,8 @@ int m2p_remove_override(struct page *page, * the original pfn causes mfn_to_pfn(mfn) to return the frontend * pfn again. */ mfn &= ~FOREIGN_FRAME_BIT; - ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); - if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && m2p_find_override(mfn) == NULL) set_phys_to_machine(pfn, mfn); diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 253f63f..be6b860 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -259,6 +259,14 @@ void xen_uninit_lock_cpu(int cpu) } +/* + * Our init of PV spinlocks is split in two init functions due to us + * using paravirt patching and jump labels patching and having to do + * all of this before SMP code is invoked. + * + * The paravirt patching needs to be done _before_ the alternative asm code + * is started, otherwise we would not patch the core kernel code. + */ void __init xen_init_spinlocks(void) { @@ -267,12 +275,26 @@ void __init xen_init_spinlocks(void) return; } - static_key_slow_inc(¶virt_ticketlocks_enabled); - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; } +/* + * While the jump_label init code needs to happend _after_ the jump labels are + * enabled and before SMP is started. Hence we use pre-SMP initcall level + * init. We cannot do it in xen_init_spinlocks as that is done before + * jump labels are activated. + */ +static __init int xen_init_spinlocks_jump(void) +{ + if (!xen_pvspin) + return 0; + + static_key_slow_inc(¶virt_ticketlocks_enabled); + return 0; +} +early_initcall(xen_init_spinlocks_jump); + static __init int xen_parse_nopvspin(char *arg) { xen_pvspin = false; diff --git a/block/Kconfig b/block/Kconfig index 7f38e40..2429515 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -99,11 +99,16 @@ config BLK_DEV_THROTTLING See Documentation/cgroups/blkio-controller.txt for more information. -config CMDLINE_PARSER +config BLK_CMDLINE_PARSER bool "Block device command line partition parser" default n ---help--- - Parsing command line, get the partitions information. + Enabling this option allows you to specify the partition layout from + the kernel boot args. This is typically of use for embedded devices + which don't otherwise have any standardized method for listing the + partitions on a block device. + + See Documentation/block/cmdline-partition.txt for more information. menu "Partition Types" diff --git a/block/Makefile b/block/Makefile index 4fa4be5..671a83d 100644 --- a/block/Makefile +++ b/block/Makefile @@ -18,4 +18,4 @@ obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o obj-$(CONFIG_BLK_DEV_INTEGRITY) += blk-integrity.o -obj-$(CONFIG_CMDLINE_PARSER) += cmdline-parser.o +obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e90c7c1..4e491d9 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -235,8 +235,13 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg->online = true; spin_unlock(&blkcg->lock); - if (!ret) + if (!ret) { + if (blkcg == &blkcg_root) { + q->root_blkg = blkg; + q->root_rl.blkg = blkg; + } return blkg; + } /* @blkg failed fully initialized, use the usual release path */ blkg_put(blkg); @@ -335,6 +340,15 @@ static void blkg_destroy(struct blkcg_gq *blkg) rcu_assign_pointer(blkcg->blkg_hint, NULL); /* + * If root blkg is destroyed. Just clear the pointer since root_rl + * does not take reference on root blkg. + */ + if (blkcg == &blkcg_root) { + blkg->q->root_blkg = NULL; + blkg->q->root_rl.blkg = NULL; + } + + /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ @@ -360,13 +374,6 @@ static void blkg_destroy_all(struct request_queue *q) blkg_destroy(blkg); spin_unlock(&blkcg->lock); } - - /* - * root blkg is destroyed. Just clear the pointer since - * root_rl does not take reference on root blkg. - */ - q->root_blkg = NULL; - q->root_rl.blkg = NULL; } /* @@ -970,8 +977,6 @@ int blkcg_activate_policy(struct request_queue *q, ret = PTR_ERR(blkg); goto out_unlock; } - q->root_blkg = blkg; - q->root_rl.blkg = blkg; list_for_each_entry(blkg, &q->blkg_list, q_node) cnt++; diff --git a/block/blk-core.c b/block/blk-core.c index c045053..0a00e4e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1549,11 +1549,9 @@ get_rq: if (plug) { /* * If this is the first request added after a plug, fire - * of a plug trace. If others have been added before, check - * if we have multiple devices in this plug. If so, make a - * note to sort the list before dispatch. + * of a plug trace. */ - if (list_empty(&plug->list)) + if (!request_count) trace_block_plug(q); else { if (request_count >= BLK_MAX_REQUEST_COUNT) { diff --git a/block/blk-exec.c b/block/blk-exec.c index e706213..ae4f27d 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -68,9 +68,9 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, spin_lock_irq(q->queue_lock); if (unlikely(blk_queue_dying(q))) { + rq->cmd_flags |= REQ_QUIET; rq->errors = -ENXIO; - if (rq->end_io) - rq->end_io(rq, rq->errors); + __blk_end_request_all(rq, rq->errors); spin_unlock_irq(q->queue_lock); return; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index dabb9d0..434944c 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1803,7 +1803,7 @@ static u64 cfqg_prfill_avg_queue_size(struct seq_file *sf, if (samples) { v = blkg_stat_read(&cfqg->stats.avg_queue_size_sum); - do_div(v, samples); + v = div64_u64(v, samples); } __blkg_prfill_u64(sf, pd, v); return 0; @@ -4358,7 +4358,7 @@ static int cfq_init_queue(struct request_queue *q, struct elevator_type *e) if (!eq) return -ENOMEM; - cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); + cfqd = kzalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node); if (!cfqd) { kobject_put(&eq->kobj); return -ENOMEM; diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index 20614a3..9ef6640 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -346,7 +346,7 @@ static int deadline_init_queue(struct request_queue *q, struct elevator_type *e) if (!eq) return -ENOMEM; - dd = kmalloc_node(sizeof(*dd), GFP_KERNEL | __GFP_ZERO, q->node); + dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); if (!dd) { kobject_put(&eq->kobj); return -ENOMEM; diff --git a/block/elevator.c b/block/elevator.c index 668394d..2bcbd8c 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -155,7 +155,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q, { struct elevator_queue *eq; - eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node); + eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node); if (unlikely(!eq)) goto err; diff --git a/block/genhd.c b/block/genhd.c index dadf42b..791f419 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1252,8 +1252,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id) { struct gendisk *disk; - disk = kmalloc_node(sizeof(struct gendisk), - GFP_KERNEL | __GFP_ZERO, node_id); + disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (disk) { if (!init_part_stats(&disk->part0)) { kfree(disk); diff --git a/block/partitions/Kconfig b/block/partitions/Kconfig index 87a3208..9b29a99 100644 --- a/block/partitions/Kconfig +++ b/block/partitions/Kconfig @@ -263,7 +263,7 @@ config SYSV68_PARTITION config CMDLINE_PARTITION bool "Command line partition support" if PARTITION_ADVANCED - select CMDLINE_PARSER + select BLK_CMDLINE_PARSER help - Say Y here if you would read the partitions table from bootargs. + Say Y here if you want to read the partition table from bootargs. The format for the command line is just like mtdparts. diff --git a/block/partitions/cmdline.c b/block/partitions/cmdline.c index 56cf4ff..5141b56 100644 --- a/block/partitions/cmdline.c +++ b/block/partitions/cmdline.c @@ -2,15 +2,15 @@ * Copyright (C) 2013 HUAWEI * Author: Cai Zhiyong <caizhiyong@huawei.com> * - * Read block device partition table from command line. - * The partition used for fixed block device (eMMC) embedded device. - * It is no MBR, save storage space. Bootloader can be easily accessed + * Read block device partition table from the command line. + * Typically used for fixed block (eMMC) embedded devices. + * It has no MBR, so saves storage space. Bootloader can be easily accessed * by absolute address of data on the block device. * Users can easily change the partition. * * The format for the command line is just like mtdparts. * - * Verbose config please reference "Documentation/block/cmdline-partition.txt" + * For further information, see "Documentation/block/cmdline-partition.txt" * */ diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c index f40acef..a6977e1 100644 --- a/drivers/acpi/acpi_ipmi.c +++ b/drivers/acpi/acpi_ipmi.c @@ -39,6 +39,7 @@ #include <linux/ipmi.h> #include <linux/device.h> #include <linux/pnp.h> +#include <linux/spinlock.h> MODULE_AUTHOR("Zhao Yakui"); MODULE_DESCRIPTION("ACPI IPMI Opregion driver"); @@ -57,7 +58,7 @@ struct acpi_ipmi_device { struct list_head head; /* the IPMI request message list */ struct list_head tx_msg_list; - struct mutex tx_msg_lock; + spinlock_t tx_msg_lock; acpi_handle handle; struct pnp_dev *pnp_dev; ipmi_user_t user_interface; @@ -147,6 +148,7 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg, struct kernel_ipmi_msg *msg; struct acpi_ipmi_buffer *buffer; struct acpi_ipmi_device *device; + unsigned long flags; msg = &tx_msg->tx_message; /* @@ -177,10 +179,10 @@ static void acpi_format_ipmi_msg(struct acpi_ipmi_msg *tx_msg, /* Get the msgid */ device = tx_msg->device; - mutex_lock(&device->tx_msg_lock); + spin_lock_irqsave(&device->tx_msg_lock, flags); device->curr_msgid++; tx_msg->tx_msgid = device->curr_msgid; - mutex_unlock(&device->tx_msg_lock); + spin_unlock_irqrestore(&device->tx_msg_lock, flags); } static void acpi_format_ipmi_response(struct acpi_ipmi_msg *msg, @@ -242,6 +244,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data) int msg_found = 0; struct acpi_ipmi_msg *tx_msg; struct pnp_dev *pnp_dev = ipmi_device->pnp_dev; + unsigned long flags; if (msg->user != ipmi_device->user_interface) { dev_warn(&pnp_dev->dev, "Unexpected response is returned. " @@ -250,7 +253,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data) ipmi_free_recv_msg(msg); return; } - mutex_lock(&ipmi_device->tx_msg_lock); + spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags); list_for_each_entry(tx_msg, &ipmi_device->tx_msg_list, head) { if (msg->msgid == tx_msg->tx_msgid) { msg_found = 1; @@ -258,7 +261,7 @@ static void ipmi_msg_handler(struct ipmi_recv_msg *msg, void *user_msg_data) } } - mutex_unlock(&ipmi_device->tx_msg_lock); + spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags); if (!msg_found) { dev_warn(&pnp_dev->dev, "Unexpected response (msg id %ld) is " "returned.\n", msg->msgid); @@ -378,6 +381,7 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address, struct acpi_ipmi_device *ipmi_device = handler_context; int err, rem_time; acpi_status status; + unsigned long flags; /* * IPMI opregion message. * IPMI message is firstly written to the BMC and system software @@ -395,9 +399,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address, return AE_NO_MEMORY; acpi_format_ipmi_msg(tx_msg, address, value); - mutex_lock(&ipmi_device->tx_msg_lock); + spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags); list_add_tail(&tx_msg->head, &ipmi_device->tx_msg_list); - mutex_unlock(&ipmi_device->tx_msg_lock); + spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags); err = ipmi_request_settime(ipmi_device->user_interface, &tx_msg->addr, tx_msg->tx_msgid, @@ -413,9 +417,9 @@ acpi_ipmi_space_handler(u32 function, acpi_physical_address address, status = AE_OK; end_label: - mutex_lock(&ipmi_device->tx_msg_lock); + spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags); list_del(&tx_msg->head); - mutex_unlock(&ipmi_device->tx_msg_lock); + spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags); kfree(tx_msg); return status; } @@ -457,7 +461,7 @@ static void acpi_add_ipmi_device(struct acpi_ipmi_device *ipmi_device) INIT_LIST_HEAD(&ipmi_device->head); - mutex_init(&ipmi_device->tx_msg_lock); + spin_lock_init(&ipmi_device->tx_msg_lock); INIT_LIST_HEAD(&ipmi_device->tx_msg_list); ipmi_install_space_handler(ipmi_device); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index fbdb82e..611ce90 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1121,7 +1121,7 @@ int acpi_bus_register_driver(struct acpi_driver *driver) EXPORT_SYMBOL(acpi_bus_register_driver); /** - * acpi_bus_unregister_driver - unregisters a driver with the APIC bus + * acpi_bus_unregister_driver - unregisters a driver with the ACPI bus * @driver: driver to unregister * * Unregisters a driver with the ACPI bus. Searches the namespace for all diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c index 958ba2a..97f4acb 100644 --- a/drivers/ata/sata_promise.c +++ b/drivers/ata/sata_promise.c @@ -2,7 +2,7 @@ * sata_promise.c - Promise SATA * * Maintained by: Tejun Heo <tj@kernel.org> - * Mikael Pettersson <mikpe@it.uu.se> + * Mikael Pettersson * Please ALWAYS copy linux-ide@vger.kernel.org * on emails. * diff --git a/drivers/base/core.c b/drivers/base/core.c index c7cfadc..34abf4d 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2017,7 +2017,7 @@ EXPORT_SYMBOL_GPL(device_move); */ void device_shutdown(void) { - struct device *dev; + struct device *dev, *parent; spin_lock(&devices_kset->list_lock); /* @@ -2034,7 +2034,7 @@ void device_shutdown(void) * prevent it from being freed because parent's * lock is to be held */ - get_device(dev->parent); + parent = get_device(dev->parent); get_device(dev); /* * Make sure the device is off the kset list, in the @@ -2044,8 +2044,8 @@ void device_shutdown(void) spin_unlock(&devices_kset->list_lock); /* hold lock to avoid race with probe/release */ - if (dev->parent) - device_lock(dev->parent); + if (parent) + device_lock(parent); device_lock(dev); /* Don't allow any more runtime suspends */ @@ -2063,11 +2063,11 @@ void device_shutdown(void) } device_unlock(dev); - if (dev->parent) - device_unlock(dev->parent); + if (parent) + device_unlock(parent); put_device(dev); - put_device(dev->parent); + put_device(parent); spin_lock(&devices_kset->list_lock); } diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index d2d95ff..edfa251 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -1189,6 +1189,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode, int err; u32 cp; + memset(&arg64, 0, sizeof(arg64)); err = 0; err |= copy_from_user(&arg64.LUN_info, &arg32->LUN_info, diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c index 639d26b..2b94403 100644 --- a/drivers/block/cpqarray.c +++ b/drivers/block/cpqarray.c @@ -1193,6 +1193,7 @@ out_passthru: ida_pci_info_struct pciinfo; if (!arg) return -EINVAL; + memset(&pciinfo, 0, sizeof(pciinfo)); pciinfo.bus = host->pci_dev->bus->number; pciinfo.dev_fn = host->pci_dev->devfn; pciinfo.board_id = host->board_id; diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c index 7a7929b..06189e5 100644 --- a/drivers/char/tpm/xen-tpmfront.c +++ b/drivers/char/tpm/xen-tpmfront.c @@ -142,32 +142,6 @@ static int vtpm_recv(struct tpm_chip *chip, u8 *buf, size_t count) return length; } -ssize_t tpm_show_locality(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct tpm_chip *chip = dev_get_drvdata(dev); - struct tpm_private *priv = TPM_VPRIV(chip); - u8 locality = priv->shr->locality; - - return sprintf(buf, "%d\n", locality); -} - -ssize_t tpm_store_locality(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len) -{ - struct tpm_chip *chip = dev_get_drvdata(dev); - struct tpm_private *priv = TPM_VPRIV(chip); - u8 val; - - int rv = kstrtou8(buf, 0, &val); - if (rv) - return rv; - - priv->shr->locality = val; - - return len; -} - static const struct file_operations vtpm_ops = { .owner = THIS_MODULE, .llseek = no_llseek, @@ -188,8 +162,6 @@ static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps, NULL); static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel); static DEVICE_ATTR(durations, S_IRUGO, tpm_show_durations, NULL); static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL); -static DEVICE_ATTR(locality, S_IRUGO | S_IWUSR, tpm_show_locality, - tpm_store_locality); static struct attribute *vtpm_attrs[] = { &dev_attr_pubek.attr, @@ -202,7 +174,6 @@ static struct attribute *vtpm_attrs[] = { &dev_attr_cancel.attr, &dev_attr_durations.attr, &dev_attr_timeouts.attr, - &dev_attr_locality.attr, NULL, }; @@ -210,8 +181,6 @@ static struct attribute_group vtpm_attr_grp = { .attrs = vtpm_attrs, }; -#define TPM_LONG_TIMEOUT (10 * 60 * HZ) - static const struct tpm_vendor_specific tpm_vtpm = { .status = vtpm_status, .recv = vtpm_recv, @@ -224,11 +193,6 @@ static const struct tpm_vendor_specific tpm_vtpm = { .miscdev = { .fops = &vtpm_ops, }, - .duration = { - TPM_LONG_TIMEOUT, - TPM_LONG_TIMEOUT, - TPM_LONG_TIMEOUT, - }, }; static irqreturn_t tpmif_interrupt(int dummy, void *dev_id) diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 41c6946..971d796 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -26,6 +26,7 @@ config DW_APB_TIMER_OF config ARMADA_370_XP_TIMER bool + select CLKSRC_OF config ORION_TIMER select CLKSRC_OF diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c index 37f5325..b9ddd9e 100644 --- a/drivers/clocksource/clksrc-of.c +++ b/drivers/clocksource/clksrc-of.c @@ -30,6 +30,9 @@ void __init clocksource_of_init(void) clocksource_of_init_fn init_func; for_each_matching_node_and_match(np, __clksrc_of_table, &match) { + if (!of_device_is_available(np)) + continue; + init_func = match->data; init_func(np); } diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c index b9c81b7..3a5909c 100644 --- a/drivers/clocksource/em_sti.c +++ b/drivers/clocksource/em_sti.c @@ -301,7 +301,7 @@ static void em_sti_register_clockevent(struct em_sti_priv *p) ced->name = dev_name(&p->pdev->dev); ced->features = CLOCK_EVT_FEAT_ONESHOT; ced->rating = 200; - ced->cpumask = cpumask_of(0); + ced->cpumask = cpu_possible_mask; ced->set_next_event = em_sti_clock_event_next; ced->set_mode = em_sti_clock_event_mode; diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index 5b34768..62b0de6 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -428,7 +428,6 @@ static int exynos4_local_timer_setup(struct clock_event_device *evt) evt->irq); return -EIO; } - irq_set_affinity(evt->irq, cpumask_of(cpu)); } else { enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0); } @@ -449,6 +448,7 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { struct mct_clock_event_device *mevt; + unsigned int cpu; /* * Grab cpu pointer in each case to avoid spurious @@ -459,6 +459,12 @@ static int exynos4_mct_cpu_notify(struct notifier_block *self, mevt = this_cpu_ptr(&percpu_mct_tick); exynos4_local_timer_setup(&mevt->evt); break; + case CPU_ONLINE: + cpu = (unsigned long)hcpu; + if (mct_int_type == MCT_INT_SPI) + irq_set_affinity(mct_irqs[MCT_L0_IRQ + cpu], + cpumask_of(cpu)); + break; case CPU_DYING: mevt = this_cpu_ptr(&percpu_mct_tick); exynos4_local_timer_stop(&mevt->evt); @@ -500,6 +506,8 @@ static void __init exynos4_timer_resources(struct device_node *np, void __iomem &percpu_mct_tick); WARN(err, "MCT: can't request IRQ %d (%d)\n", mct_irqs[MCT_L0_IRQ], err); + } else { + irq_set_affinity(mct_irqs[MCT_L0_IRQ], cpumask_of(0)); } err = register_cpu_notifier(&exynos4_mct_cpu_nb); diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index a1260b4..d2c3253 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -986,6 +986,10 @@ static int __init acpi_cpufreq_init(void) { int ret; + /* don't keep reloading if cpufreq_driver exists */ + if (cpufreq_get_current_driver()) + return 0; + if (acpi_disabled) return 0; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 89b3c52..04548f7 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1460,6 +1460,9 @@ unsigned int cpufreq_get(unsigned int cpu) { unsigned int ret_freq = 0; + if (cpufreq_disabled() || !cpufreq_driver) + return -ENOENT; + if (!down_read_trylock(&cpufreq_rwsem)) return 0; diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c index d514c15..be5380e 100644 --- a/drivers/cpufreq/exynos5440-cpufreq.c +++ b/drivers/cpufreq/exynos5440-cpufreq.c @@ -457,7 +457,7 @@ err_free_table: opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table); err_put_node: of_node_put(np); - dev_err(dvfs_info->dev, "%s: failed initialization\n", __func__); + dev_err(&pdev->dev, "%s: failed initialization\n", __func__); return ret; } diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c index b4fb86d..224ff96 100644 --- a/drivers/gpu/drm/drm_context.c +++ b/drivers/gpu/drm/drm_context.c @@ -42,6 +42,10 @@ #include <drm/drmP.h> +/******************************************************************/ +/** \name Context bitmap support */ +/*@{*/ + /** * Free a handle from the context bitmap. * @@ -52,48 +56,13 @@ * in drm_device::ctx_idr, while holding the drm_device::struct_mutex * lock. */ -static void drm_ctxbitmap_free(struct drm_device * dev, int ctx_handle) +void drm_ctxbitmap_free(struct drm_device * dev, int ctx_handle) { - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return; - mutex_lock(&dev->struct_mutex); idr_remove(&dev->ctx_idr, ctx_handle); mutex_unlock(&dev->struct_mutex); } -/******************************************************************/ -/** \name Context bitmap support */ -/*@{*/ - -void drm_legacy_ctxbitmap_release(struct drm_device *dev, - struct drm_file *file_priv) -{ - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return; - - mutex_lock(&dev->ctxlist_mutex); - if (!list_empty(&dev->ctxlist)) { - struct drm_ctx_list *pos, *n; - - list_for_each_entry_safe(pos, n, &dev->ctxlist, head) { - if (pos->tag == file_priv && - pos->handle != DRM_KERNEL_CONTEXT) { - if (dev->driver->context_dtor) - dev->driver->context_dtor(dev, - pos->handle); - - drm_ctxbitmap_free(dev, pos->handle); - - list_del(&pos->head); - kfree(pos); - --dev->ctx_count; - } - } - } - mutex_unlock(&dev->ctxlist_mutex); -} - /** * Context bitmap allocation. * @@ -121,12 +90,10 @@ static int drm_ctxbitmap_next(struct drm_device * dev) * * Initialise the drm_device::ctx_idr */ -void drm_legacy_ctxbitmap_init(struct drm_device * dev) +int drm_ctxbitmap_init(struct drm_device * dev) { - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return; - idr_init(&dev->ctx_idr); + return 0; } /** @@ -137,7 +104,7 @@ void drm_legacy_ctxbitmap_init(struct drm_device * dev) * Free all idr members using drm_ctx_sarea_free helper function * while holding the drm_device::struct_mutex lock. */ -void drm_legacy_ctxbitmap_cleanup(struct drm_device * dev) +void drm_ctxbitmap_cleanup(struct drm_device * dev) { mutex_lock(&dev->struct_mutex); idr_destroy(&dev->ctx_idr); @@ -169,9 +136,6 @@ int drm_getsareactx(struct drm_device *dev, void *data, struct drm_local_map *map; struct drm_map_list *_entry; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - mutex_lock(&dev->struct_mutex); map = idr_find(&dev->ctx_idr, request->ctx_id); @@ -216,9 +180,6 @@ int drm_setsareactx(struct drm_device *dev, void *data, struct drm_local_map *map = NULL; struct drm_map_list *r_list = NULL; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - mutex_lock(&dev->struct_mutex); list_for_each_entry(r_list, &dev->maplist, head) { if (r_list->map @@ -319,9 +280,6 @@ int drm_resctx(struct drm_device *dev, void *data, struct drm_ctx ctx; int i; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - if (res->count >= DRM_RESERVED_CONTEXTS) { memset(&ctx, 0, sizeof(ctx)); for (i = 0; i < DRM_RESERVED_CONTEXTS; i++) { @@ -352,9 +310,6 @@ int drm_addctx(struct drm_device *dev, void *data, struct drm_ctx_list *ctx_entry; struct drm_ctx *ctx = data; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - ctx->handle = drm_ctxbitmap_next(dev); if (ctx->handle == DRM_KERNEL_CONTEXT) { /* Skip kernel's context and get a new one. */ @@ -398,9 +353,6 @@ int drm_getctx(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_ctx *ctx = data; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - /* This is 0, because we don't handle any context flags */ ctx->flags = 0; @@ -423,9 +375,6 @@ int drm_switchctx(struct drm_device *dev, void *data, { struct drm_ctx *ctx = data; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - DRM_DEBUG("%d\n", ctx->handle); return drm_context_switch(dev, dev->last_context, ctx->handle); } @@ -446,9 +395,6 @@ int drm_newctx(struct drm_device *dev, void *data, { struct drm_ctx *ctx = data; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - DRM_DEBUG("%d\n", ctx->handle); drm_context_switch_complete(dev, file_priv, ctx->handle); @@ -471,9 +417,6 @@ int drm_rmctx(struct drm_device *dev, void *data, { struct drm_ctx *ctx = data; - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return -EINVAL; - DRM_DEBUG("%d\n", ctx->handle); if (ctx->handle != DRM_KERNEL_CONTEXT) { if (dev->driver->context_dtor) diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c index 4be8e09..3f84277 100644 --- a/drivers/gpu/drm/drm_fops.c +++ b/drivers/gpu/drm/drm_fops.c @@ -439,7 +439,26 @@ int drm_release(struct inode *inode, struct file *filp) if (dev->driver->driver_features & DRIVER_GEM) drm_gem_release(dev, file_priv); - drm_legacy_ctxbitmap_release(dev, file_priv); + mutex_lock(&dev->ctxlist_mutex); + if (!list_empty(&dev->ctxlist)) { + struct drm_ctx_list *pos, *n; + + list_for_each_entry_safe(pos, n, &dev->ctxlist, head) { + if (pos->tag == file_priv && + pos->handle != DRM_KERNEL_CONTEXT) { + if (dev->driver->context_dtor) + dev->driver->context_dtor(dev, + pos->handle); + + drm_ctxbitmap_free(dev, pos->handle); + + list_del(&pos->head); + kfree(pos); + --dev->ctx_count; + } + } + } + mutex_unlock(&dev->ctxlist_mutex); mutex_lock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index e7eb027..39d8645 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -292,7 +292,13 @@ int drm_fill_in_dev(struct drm_device *dev, goto error_out_unreg; } - drm_legacy_ctxbitmap_init(dev); + + + retcode = drm_ctxbitmap_init(dev); + if (retcode) { + DRM_ERROR("Cannot allocate memory for context bitmap.\n"); + goto error_out_unreg; + } if (driver->driver_features & DRIVER_GEM) { retcode = drm_gem_init(dev); @@ -446,7 +452,7 @@ void drm_put_dev(struct drm_device *dev) drm_rmmap(dev, r_list->map); drm_ht_remove(&dev->map_hash); - drm_legacy_ctxbitmap_cleanup(dev); + drm_ctxbitmap_cleanup(dev); if (drm_core_check_feature(dev, DRIVER_MODESET)) drm_put_minor(&dev->control); diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 4752f22..45b6ef5 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -56,7 +56,7 @@ config DRM_EXYNOS_IPP config DRM_EXYNOS_FIMC bool "Exynos DRM FIMC" - depends on DRM_EXYNOS_IPP && MFD_SYSCON && OF + depends on DRM_EXYNOS_IPP && MFD_SYSCON help Choose this option if you want to use Exynos FIMC for DRM. diff --git a/drivers/gpu/drm/exynos/exynos_drm_buf.c b/drivers/gpu/drm/exynos/exynos_drm_buf.c index 3445a0f..9c80884 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_buf.c +++ b/drivers/gpu/drm/exynos/exynos_drm_buf.c @@ -63,7 +63,8 @@ static int lowlevel_buffer_allocate(struct drm_device *dev, return -ENOMEM; } - buf->kvaddr = dma_alloc_attrs(dev->dev, buf->size, + buf->kvaddr = (void __iomem *)dma_alloc_attrs(dev->dev, + buf->size, &buf->dma_addr, GFP_KERNEL, &buf->dma_attrs); if (!buf->kvaddr) { @@ -90,9 +91,9 @@ static int lowlevel_buffer_allocate(struct drm_device *dev, } buf->sgt = drm_prime_pages_to_sg(buf->pages, nr_pages); - if (!buf->sgt) { + if (IS_ERR(buf->sgt)) { DRM_ERROR("failed to get sg table.\n"); - ret = -ENOMEM; + ret = PTR_ERR(buf->sgt); goto err_free_attrs; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 78e868b..e7c2f2d 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -99,12 +99,13 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper, if (is_drm_iommu_supported(dev)) { unsigned int nr_pages = buffer->size >> PAGE_SHIFT; - buffer->kvaddr = vmap(buffer->pages, nr_pages, VM_MAP, + buffer->kvaddr = (void __iomem *) vmap(buffer->pages, + nr_pages, VM_MAP, pgprot_writecombine(PAGE_KERNEL)); } else { phys_addr_t dma_addr = buffer->dma_addr; if (dma_addr) - buffer->kvaddr = phys_to_virt(dma_addr); + buffer->kvaddr = (void __iomem *)phys_to_virt(dma_addr); else buffer->kvaddr = (void __iomem *)NULL; } diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index b1f8fc6..60e8404 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -707,8 +707,7 @@ tda998x_encoder_dpms(struct drm_encoder *encoder, int mode) reg_write(encoder, REG_VIP_CNTRL_2, priv->vip_cntrl_2); break; case DRM_MODE_DPMS_OFF: - /* disable audio and video ports */ - reg_write(encoder, REG_ENA_AP, 0x00); + /* disable video ports */ reg_write(encoder, REG_ENA_VP_0, 0x00); reg_write(encoder, REG_ENA_VP_1, 0x00); reg_write(encoder, REG_ENA_VP_2, 0x00); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 8507c6d..cdfb9da 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1392,14 +1392,11 @@ out: if (i915_terminally_wedged(&dev_priv->gpu_error)) return VM_FAULT_SIGBUS; case -EAGAIN: - /* Give the error handler a chance to run and move the - * objects off the GPU active list. Next time we service the - * fault, we should be able to transition the page into the - * GTT without touching the GPU (and so avoid further - * EIO/EGAIN). If the GPU is wedged, then there is no issue - * with coherency, just lost writes. + /* + * EAGAIN means the gpu is hung and we'll wait for the error + * handler to reset everything when re-faulting in + * i915_mutex_lock_interruptible. */ - set_need_resched(); case 0: case -ERESTARTSYS: case -EINTR: @@ -4803,10 +4800,10 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc) if (!mutex_trylock(&dev->struct_mutex)) { if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return SHRINK_STOP; + return 0; if (dev_priv->mm.shrinker_no_lock_stealing) - return SHRINK_STOP; + return 0; unlock = false; } @@ -4904,10 +4901,10 @@ i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc) if (!mutex_trylock(&dev->struct_mutex)) { if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return 0; + return SHRINK_STOP; if (dev_priv->mm.shrinker_no_lock_stealing) - return 0; + return SHRINK_STOP; unlock = false; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index aba9d74..dae364f 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -143,8 +143,10 @@ static void i915_error_vprintf(struct drm_i915_error_state_buf *e, /* Seek the first printf which is hits start position */ if (e->pos < e->start) { - len = vsnprintf(NULL, 0, f, args); - if (!__i915_error_seek(e, len)) + va_list tmp; + + va_copy(tmp, args); + if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp))) return; } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 83cce0c..4b91228 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1469,6 +1469,34 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg) return ret; } +static void i915_error_wake_up(struct drm_i915_private *dev_priv, + bool reset_completed) +{ + struct intel_ring_buffer *ring; + int i; + + /* + * Notify all waiters for GPU completion events that reset state has + * been changed, and that they need to restart their wait after + * checking for potential errors (and bail out to drop locks if there is + * a gpu reset pending so that i915_error_work_func can acquire them). + */ + + /* Wake up __wait_seqno, potentially holding dev->struct_mutex. */ + for_each_ring(ring, dev_priv, i) + wake_up_all(&ring->irq_queue); + + /* Wake up intel_crtc_wait_for_pending_flips, holding crtc->mutex. */ + wake_up_all(&dev_priv->pending_flip_queue); + + /* + * Signal tasks blocked in i915_gem_wait_for_error that the pending + * reset state is cleared. + */ + if (reset_completed) + wake_up_all(&dev_priv->gpu_error.reset_queue); +} + /** * i915_error_work_func - do process context error handling work * @work: work struct @@ -1483,11 +1511,10 @@ static void i915_error_work_func(struct work_struct *work) drm_i915_private_t *dev_priv = container_of(error, drm_i915_private_t, gpu_error); struct drm_device *dev = dev_priv->dev; - struct intel_ring_buffer *ring; char *error_event[] = { I915_ERROR_UEVENT "=1", NULL }; char *reset_event[] = { I915_RESET_UEVENT "=1", NULL }; char *reset_done_event[] = { I915_ERROR_UEVENT "=0", NULL }; - int i, ret; + int ret; kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event); @@ -1506,8 +1533,16 @@ static void i915_error_work_func(struct work_struct *work) kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, reset_event); + /* + * All state reset _must_ be completed before we update the + * reset counter, for otherwise waiters might miss the reset + * pending state and not properly drop locks, resulting in + * deadlocks with the reset work. + */ ret = i915_reset(dev); + intel_display_handle_reset(dev); + if (ret == 0) { /* * After all the gem state is reset, increment the reset @@ -1528,12 +1563,11 @@ static void i915_error_work_func(struct work_struct *work) atomic_set(&error->reset_counter, I915_WEDGED); } - for_each_ring(ring, dev_priv, i) - wake_up_all(&ring->irq_queue); - - intel_display_handle_reset(dev); - - wake_up_all(&dev_priv->gpu_error.reset_queue); + /* + * Note: The wake_up also serves as a memory barrier so that + * waiters see the update value of the reset counter atomic_t. + */ + i915_error_wake_up(dev_priv, true); } } @@ -1642,8 +1676,6 @@ static void i915_report_and_clear_eir(struct drm_device *dev) void i915_handle_error(struct drm_device *dev, bool wedged) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; - int i; i915_capture_error_state(dev); i915_report_and_clear_eir(dev); @@ -1653,11 +1685,19 @@ void i915_handle_error(struct drm_device *dev, bool wedged) &dev_priv->gpu_error.reset_counter); /* - * Wakeup waiting processes so that the reset work item - * doesn't deadlock trying to grab various locks. + * Wakeup waiting processes so that the reset work function + * i915_error_work_func doesn't deadlock trying to grab various + * locks. By bumping the reset counter first, the woken + * processes will see a reset in progress and back off, + * releasing their locks and then wait for the reset completion. + * We must do this for _all_ gpu waiters that might hold locks + * that the reset work needs to acquire. + * + * Note: The wake_up serves as the required memory barrier to + * ensure that the waiters see the updated value of the reset + * counter atomic_t. */ - for_each_ring(ring, dev_priv, i) - wake_up_all(&ring->irq_queue); + i915_error_wake_up(dev_priv, false); } /* diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 63aca49..63de270 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -778,7 +778,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc) /* Can only use the always-on power well for eDP when * not using the panel fitter, and when not using motion * blur mitigation (which we don't support). */ - if (intel_crtc->config.pch_pfit.size) + if (intel_crtc->config.pch_pfit.enabled) temp |= TRANS_DDI_EDP_INPUT_A_ONOFF; else temp |= TRANS_DDI_EDP_INPUT_A_ON; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2489d0b..e5822e7 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2249,7 +2249,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, I915_WRITE(PIPESRC(intel_crtc->pipe), ((crtc->mode.hdisplay - 1) << 16) | (crtc->mode.vdisplay - 1)); - if (!intel_crtc->config.pch_pfit.size && + if (!intel_crtc->config.pch_pfit.enabled && (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) || intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) { I915_WRITE(PF_CTL(intel_crtc->pipe), 0); @@ -3203,7 +3203,7 @@ static void ironlake_pfit_enable(struct intel_crtc *crtc) struct drm_i915_private *dev_priv = dev->dev_private; int pipe = crtc->pipe; - if (crtc->config.pch_pfit.size) { + if (crtc->config.pch_pfit.enabled) { /* Force use of hard-coded filter coefficients * as some pre-programmed values are broken, * e.g. x201. @@ -3428,7 +3428,7 @@ static void ironlake_pfit_disable(struct intel_crtc *crtc) /* To avoid upsetting the power well on haswell only disable the pfit if * it's in use. The hw state code will make sure we get this right. */ - if (crtc->config.pch_pfit.size) { + if (crtc->config.pch_pfit.enabled) { I915_WRITE(PF_CTL(pipe), 0); I915_WRITE(PF_WIN_POS(pipe), 0); I915_WRITE(PF_WIN_SZ(pipe), 0); @@ -4775,6 +4775,10 @@ static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc) pipeconf = 0; + if (dev_priv->quirks & QUIRK_PIPEA_FORCE && + I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE) + pipeconf |= PIPECONF_ENABLE; + if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) { /* Enable pixel doubling when the dot clock is > 90% of the (display) * core speed. @@ -4877,9 +4881,6 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, return -EINVAL; } - /* Ensure that the cursor is valid for the new mode before changing... */ - intel_crtc_update_cursor(crtc, true); - if (is_lvds && dev_priv->lvds_downclock_avail) { /* * Ensure we match the reduced clock's P to the target clock. @@ -5768,9 +5769,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, intel_crtc->config.dpll.p2 = clock.p2; } - /* Ensure that the cursor is valid for the new mode before changing... */ - intel_crtc_update_cursor(crtc, true); - /* CPU eDP is the only output that doesn't need a PCH PLL of its own. */ if (intel_crtc->config.has_pch_encoder) { fp = i9xx_dpll_compute_fp(&intel_crtc->config.dpll); @@ -5859,6 +5857,7 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc, tmp = I915_READ(PF_CTL(crtc->pipe)); if (tmp & PF_ENABLE) { + pipe_config->pch_pfit.enabled = true; pipe_config->pch_pfit.pos = I915_READ(PF_WIN_POS(crtc->pipe)); pipe_config->pch_pfit.size = I915_READ(PF_WIN_SZ(crtc->pipe)); @@ -6236,7 +6235,7 @@ static void haswell_modeset_global_resources(struct drm_device *dev) if (!crtc->base.enabled) continue; - if (crtc->pipe != PIPE_A || crtc->config.pch_pfit.size || + if (crtc->pipe != PIPE_A || crtc->config.pch_pfit.enabled || crtc->config.cpu_transcoder != TRANSCODER_EDP) enable = true; } @@ -6259,9 +6258,6 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc, if (!intel_ddi_pll_mode_set(crtc)) return -EINVAL; - /* Ensure that the cursor is valid for the new mode before changing... */ - intel_crtc_update_cursor(crtc, true); - if (intel_crtc->config.has_dp_encoder) intel_dp_set_m_n(intel_crtc); @@ -6494,15 +6490,15 @@ static void haswell_write_eld(struct drm_connector *connector, /* Set ELD valid state */ tmp = I915_READ(aud_cntrl_st2); - DRM_DEBUG_DRIVER("HDMI audio: pin eld vld status=0x%8x\n", tmp); + DRM_DEBUG_DRIVER("HDMI audio: pin eld vld status=0x%08x\n", tmp); tmp |= (AUDIO_ELD_VALID_A << (pipe * 4)); I915_WRITE(aud_cntrl_st2, tmp); tmp = I915_READ(aud_cntrl_st2); - DRM_DEBUG_DRIVER("HDMI audio: eld vld status=0x%8x\n", tmp); + DRM_DEBUG_DRIVER("HDMI audio: eld vld status=0x%08x\n", tmp); /* Enable HDMI mode */ tmp = I915_READ(aud_config); - DRM_DEBUG_DRIVER("HDMI audio: audio conf: 0x%8x\n", tmp); + DRM_DEBUG_DRIVER("HDMI audio: audio conf: 0x%08x\n", tmp); /* clear N_programing_enable and N_value_index */ tmp &= ~(AUD_CONFIG_N_VALUE_INDEX | AUD_CONFIG_N_PROG_ENABLE); I915_WRITE(aud_config, tmp); @@ -6937,7 +6933,8 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc, intel_crtc->cursor_width = width; intel_crtc->cursor_height = height; - intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL); + if (intel_crtc->active) + intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL); return 0; fail_unpin: @@ -6956,7 +6953,8 @@ static int intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) intel_crtc->cursor_x = x; intel_crtc->cursor_y = y; - intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL); + if (intel_crtc->active) + intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL); return 0; } @@ -8205,9 +8203,10 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc, pipe_config->gmch_pfit.control, pipe_config->gmch_pfit.pgm_ratios, pipe_config->gmch_pfit.lvds_border_bits); - DRM_DEBUG_KMS("pch pfit: pos: 0x%08x, size: 0x%08x\n", + DRM_DEBUG_KMS("pch pfit: pos: 0x%08x, size: 0x%08x, %s\n", pipe_config->pch_pfit.pos, - pipe_config->pch_pfit.size); + pipe_config->pch_pfit.size, + pipe_config->pch_pfit.enabled ? "enabled" : "disabled"); DRM_DEBUG_KMS("ips: %i\n", pipe_config->ips_enabled); } @@ -8603,8 +8602,11 @@ intel_pipe_config_compare(struct drm_device *dev, if (INTEL_INFO(dev)->gen < 4) PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios); PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits); - PIPE_CONF_CHECK_I(pch_pfit.pos); - PIPE_CONF_CHECK_I(pch_pfit.size); + PIPE_CONF_CHECK_I(pch_pfit.enabled); + if (current_config->pch_pfit.enabled) { + PIPE_CONF_CHECK_I(pch_pfit.pos); + PIPE_CONF_CHECK_I(pch_pfit.size); + } PIPE_CONF_CHECK_I(ips_enabled); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 2151d13..79c14e2 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -588,7 +588,18 @@ intel_dp_i2c_aux_ch(struct i2c_adapter *adapter, int mode, DRM_DEBUG_KMS("aux_ch native nack\n"); return -EREMOTEIO; case AUX_NATIVE_REPLY_DEFER: - udelay(100); + /* + * For now, just give more slack to branch devices. We + * could check the DPCD for I2C bit rate capabilities, + * and if available, adjust the interval. We could also + * be more careful with DP-to-Legacy adapters where a + * long legacy cable may force very low I2C bit rates. + */ + if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & + DP_DWN_STRM_PORT_PRESENT) + usleep_range(500, 600); + else + usleep_range(300, 400); continue; default: DRM_ERROR("aux_ch invalid native reply 0x%02x\n", diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index a47799e..28cae80 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -280,6 +280,7 @@ struct intel_crtc_config { struct { u32 pos; u32 size; + bool enabled; } pch_pfit; /* FDI configuration, only valid if has_pch_encoder is set. */ diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 406303b..7fa7df5 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -263,6 +263,8 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder, C(vtotal); C(clock); #undef C + + drm_mode_set_crtcinfo(adjusted_mode, 0); } if (intel_dvo->dev.dev_ops->mode_fixup) diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 42114ec..293564a 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -112,6 +112,7 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc, done: pipe_config->pch_pfit.pos = (x << 16) | y; pipe_config->pch_pfit.size = (width << 16) | height; + pipe_config->pch_pfit.enabled = pipe_config->pch_pfit.size != 0; } static void diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 0c115cc..dd176b7 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2096,16 +2096,16 @@ static uint32_t ilk_pipe_pixel_rate(struct drm_device *dev, struct drm_crtc *crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - uint32_t pixel_rate, pfit_size; + uint32_t pixel_rate; pixel_rate = intel_crtc->config.adjusted_mode.clock; /* We only use IF-ID interlacing. If we ever use PF-ID we'll need to * adjust the pixel_rate here. */ - pfit_size = intel_crtc->config.pch_pfit.size; - if (pfit_size) { + if (intel_crtc->config.pch_pfit.enabled) { uint64_t pipe_w, pipe_h, pfit_w, pfit_h; + uint32_t pfit_size = intel_crtc->config.pch_pfit.size; pipe_w = intel_crtc->config.requested_mode.hdisplay; pipe_h = intel_crtc->config.requested_mode.vdisplay; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 85037b9..49482fd 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -788,6 +788,8 @@ static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd, uint16_t h_sync_offset, v_sync_offset; int mode_clock; + memset(dtd, 0, sizeof(*dtd)); + width = mode->hdisplay; height = mode->vdisplay; @@ -830,44 +832,51 @@ static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd, if (mode->flags & DRM_MODE_FLAG_PVSYNC) dtd->part2.dtd_flags |= DTD_FLAG_VSYNC_POSITIVE; - dtd->part2.sdvo_flags = 0; dtd->part2.v_sync_off_high = v_sync_offset & 0xc0; - dtd->part2.reserved = 0; } -static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode * mode, +static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode *pmode, const struct intel_sdvo_dtd *dtd) { - mode->hdisplay = dtd->part1.h_active; - mode->hdisplay += ((dtd->part1.h_high >> 4) & 0x0f) << 8; - mode->hsync_start = mode->hdisplay + dtd->part2.h_sync_off; - mode->hsync_start += (dtd->part2.sync_off_width_high & 0xc0) << 2; - mode->hsync_end = mode->hsync_start + dtd->part2.h_sync_width; - mode->hsync_end += (dtd->part2.sync_off_width_high & 0x30) << 4; - mode->htotal = mode->hdisplay + dtd->part1.h_blank; - mode->htotal += (dtd->part1.h_high & 0xf) << 8; - - mode->vdisplay = dtd->part1.v_active; - mode->vdisplay += ((dtd->part1.v_high >> 4) & 0x0f) << 8; - mode->vsync_start = mode->vdisplay; - mode->vsync_start += (dtd->part2.v_sync_off_width >> 4) & 0xf; - mode->vsync_start += (dtd->part2.sync_off_width_high & 0x0c) << 2; - mode->vsync_start += dtd->part2.v_sync_off_high & 0xc0; - mode->vsync_end = mode->vsync_start + + struct drm_display_mode mode = {}; + + mode.hdisplay = dtd->part1.h_active; + mode.hdisplay += ((dtd->part1.h_high >> 4) & 0x0f) << 8; + mode.hsync_start = mode.hdisplay + dtd->part2.h_sync_off; + mode.hsync_start += (dtd->part2.sync_off_width_high & 0xc0) << 2; + mode.hsync_end = mode.hsync_start + dtd->part2.h_sync_width; + mode.hsync_end += (dtd->part2.sync_off_width_high & 0x30) << 4; + mode.htotal = mode.hdisplay + dtd->part1.h_blank; + mode.htotal += (dtd->part1.h_high & 0xf) << 8; + + mode.vdisplay = dtd->part1.v_active; + mode.vdisplay += ((dtd->part1.v_high >> 4) & 0x0f) << 8; + mode.vsync_start = mode.vdisplay; + mode.vsync_start += (dtd->part2.v_sync_off_width >> 4) & 0xf; + mode.vsync_start += (dtd->part2.sync_off_width_high & 0x0c) << 2; + mode.vsync_start += dtd->part2.v_sync_off_high & 0xc0; + mode.vsync_end = mode.vsync_start + (dtd->part2.v_sync_off_width & 0xf); - mode->vsync_end += (dtd->part2.sync_off_width_high & 0x3) << 4; - mode->vtotal = mode->vdisplay + dtd->part1.v_blank; - mode->vtotal += (dtd->part1.v_high & 0xf) << 8; + mode.vsync_end += (dtd->part2.sync_off_width_high & 0x3) << 4; + mode.vtotal = mode.vdisplay + dtd->part1.v_blank; + mode.vtotal += (dtd->part1.v_high & 0xf) << 8; - mode->clock = dtd->part1.clock * 10; + mode.clock = dtd->part1.clock * 10; - mode->flags &= ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC); if (dtd->part2.dtd_flags & DTD_FLAG_INTERLACE) - mode->flags |= DRM_MODE_FLAG_INTERLACE; + mode.flags |= DRM_MODE_FLAG_INTERLACE; if (dtd->part2.dtd_flags & DTD_FLAG_HSYNC_POSITIVE) - mode->flags |= DRM_MODE_FLAG_PHSYNC; + mode.flags |= DRM_MODE_FLAG_PHSYNC; + else + mode.flags |= DRM_MODE_FLAG_NHSYNC; if (dtd->part2.dtd_flags & DTD_FLAG_VSYNC_POSITIVE) - mode->flags |= DRM_MODE_FLAG_PVSYNC; + mode.flags |= DRM_MODE_FLAG_PVSYNC; + else + mode.flags |= DRM_MODE_FLAG_NVSYNC; + + drm_mode_set_crtcinfo(&mode, 0); + + drm_mode_copy(pmode, &mode); } static bool intel_sdvo_check_supp_encode(struct intel_sdvo *intel_sdvo) diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index f2c6d79..dd6f84b 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -916,6 +916,14 @@ intel_tv_compute_config(struct intel_encoder *encoder, DRM_DEBUG_KMS("forcing bpc to 8 for TV\n"); pipe_config->pipe_bpp = 8*3; + /* TV has it's own notion of sync and other mode flags, so clear them. */ + pipe_config->adjusted_mode.flags = 0; + + /* + * FIXME: We don't check whether the input mode is actually what we want + * or whether userspace is doing something stupid. + */ + return true; } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index a605847..a0b9d8a 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -124,6 +124,8 @@ void adreno_recover(struct msm_gpu *gpu) /* reset completed fence seqno, just discard anything pending: */ adreno_gpu->memptrs->fence = gpu->submitted_fence; + adreno_gpu->memptrs->rptr = 0; + adreno_gpu->memptrs->wptr = 0; gpu->funcs->pm_resume(gpu); ret = gpu->funcs->hw_init(gpu); @@ -229,7 +231,7 @@ void adreno_idle(struct msm_gpu *gpu) return; } while(time_before(jiffies, t)); - DRM_ERROR("timeout waiting for %s to drain ringbuffer!\n", gpu->name); + DRM_ERROR("%s: timeout waiting to drain ringbuffer!\n", gpu->name); /* TODO maybe we need to reset GPU here to recover from hang? */ } @@ -256,11 +258,17 @@ void adreno_wait_ring(struct msm_gpu *gpu, uint32_t ndwords) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); uint32_t freedwords; + unsigned long t = jiffies + ADRENO_IDLE_TIMEOUT; do { uint32_t size = gpu->rb->size / 4; uint32_t wptr = get_wptr(gpu->rb); uint32_t rptr = adreno_gpu->memptrs->rptr; freedwords = (rptr + (size - 1) - wptr) % size; + + if (time_after(jiffies, t)) { + DRM_ERROR("%s: timeout waiting for ringbuffer space\n", gpu->name); + break; + } } while(freedwords < ndwords); } diff --git a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c index 5db5bba..bc7fd11 100644 --- a/drivers/gpu/drm/msm/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/mdp4/mdp4_kms.c @@ -19,8 +19,6 @@ #include "msm_drv.h" #include "mdp4_kms.h" -#include <mach/iommu.h> - static struct mdp4_platform_config *mdp4_get_config(struct platform_device *dev); static int mdp4_hw_init(struct msm_kms *kms) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 864c977..b3a2f16 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -18,8 +18,6 @@ #include "msm_drv.h" #include "msm_gpu.h" -#include <mach/iommu.h> - static void msm_fb_output_poll_changed(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; @@ -62,6 +60,8 @@ int msm_iommu_attach(struct drm_device *dev, struct iommu_domain *iommu, int i, ret; for (i = 0; i < cnt; i++) { + /* TODO maybe some day msm iommu won't require this hack: */ + struct device *msm_iommu_get_ctx(const char *ctx_name); struct device *ctx = msm_iommu_get_ctx(names[i]); if (!ctx) continue; @@ -199,7 +199,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags) * imx drm driver on iMX5 */ dev_err(dev->dev, "failed to load kms\n"); - ret = PTR_ERR(priv->kms); + ret = PTR_ERR(kms); goto fail; } @@ -499,25 +499,41 @@ int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence, struct timespec *timeout) { struct msm_drm_private *priv = dev->dev_private; - unsigned long timeout_jiffies = timespec_to_jiffies(timeout); - unsigned long start_jiffies = jiffies; - unsigned long remaining_jiffies; int ret; - if (time_after(start_jiffies, timeout_jiffies)) - remaining_jiffies = 0; - else - remaining_jiffies = timeout_jiffies - start_jiffies; - - ret = wait_event_interruptible_timeout(priv->fence_event, - priv->completed_fence >= fence, - remaining_jiffies); - if (ret == 0) { - DBG("timeout waiting for fence: %u (completed: %u)", - fence, priv->completed_fence); - ret = -ETIMEDOUT; - } else if (ret != -ERESTARTSYS) { - ret = 0; + if (!priv->gpu) + return 0; + + if (fence > priv->gpu->submitted_fence) { + DRM_ERROR("waiting on invalid fence: %u (of %u)\n", + fence, priv->gpu->submitted_fence); + return -EINVAL; + } + + if (!timeout) { + /* no-wait: */ + ret = fence_completed(dev, fence) ? 0 : -EBUSY; + } else { + unsigned long timeout_jiffies = timespec_to_jiffies(timeout); + unsigned long start_jiffies = jiffies; + unsigned long remaining_jiffies; + + if (time_after(start_jiffies, timeout_jiffies)) + remaining_jiffies = 0; + else + remaining_jiffies = timeout_jiffies - start_jiffies; + + ret = wait_event_interruptible_timeout(priv->fence_event, + fence_completed(dev, fence), + remaining_jiffies); + + if (ret == 0) { + DBG("timeout waiting for fence: %u (completed: %u)", + fence, priv->completed_fence); + ret = -ETIMEDOUT; + } else if (ret != -ERESTARTSYS) { + ret = 0; + } } return ret; @@ -681,7 +697,7 @@ static struct drm_driver msm_driver = { .gem_vm_ops = &vm_ops, .dumb_create = msm_gem_dumb_create, .dumb_map_offset = msm_gem_dumb_map_offset, - .dumb_destroy = msm_gem_dumb_destroy, + .dumb_destroy = drm_gem_dumb_destroy, #ifdef CONFIG_DEBUG_FS .debugfs_init = msm_debugfs_init, .debugfs_cleanup = msm_debugfs_cleanup, diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 80d7509..df8f1d0 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -153,7 +153,7 @@ void *msm_gem_vaddr(struct drm_gem_object *obj); int msm_gem_queue_inactive_work(struct drm_gem_object *obj, struct work_struct *work); void msm_gem_move_to_active(struct drm_gem_object *obj, - struct msm_gpu *gpu, uint32_t fence); + struct msm_gpu *gpu, bool write, uint32_t fence); void msm_gem_move_to_inactive(struct drm_gem_object *obj); int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, struct timespec *timeout); @@ -191,6 +191,12 @@ u32 msm_readl(const void __iomem *addr); #define DBG(fmt, ...) DRM_DEBUG(fmt"\n", ##__VA_ARGS__) #define VERB(fmt, ...) if (0) DRM_DEBUG(fmt"\n", ##__VA_ARGS__) +static inline bool fence_completed(struct drm_device *dev, uint32_t fence) +{ + struct msm_drm_private *priv = dev->dev_private; + return priv->completed_fence >= fence; +} + static inline int align_pitch(int width, int bpp) { int bytespp = (bpp + 7) / 8; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 6b5a6c8..2bae46c 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -40,9 +40,9 @@ static struct page **get_pages(struct drm_gem_object *obj) } msm_obj->sgt = drm_prime_pages_to_sg(p, npages); - if (!msm_obj->sgt) { + if (IS_ERR(msm_obj->sgt)) { dev_err(dev->dev, "failed to allocate sgt\n"); - return ERR_PTR(-ENOMEM); + return ERR_CAST(msm_obj->sgt); } msm_obj->pages = p; @@ -159,7 +159,6 @@ out_unlock: out: switch (ret) { case -EAGAIN: - set_need_resched(); case 0: case -ERESTARTSYS: case -EINTR: @@ -320,13 +319,6 @@ int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev, MSM_BO_SCANOUT | MSM_BO_WC, &args->handle); } -int msm_gem_dumb_destroy(struct drm_file *file, struct drm_device *dev, - uint32_t handle) -{ - /* No special work needed, drop the reference and see what falls out */ - return drm_gem_handle_delete(file, handle); -} - int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, uint32_t handle, uint64_t *offset) { @@ -393,11 +385,14 @@ int msm_gem_queue_inactive_work(struct drm_gem_object *obj, } void msm_gem_move_to_active(struct drm_gem_object *obj, - struct msm_gpu *gpu, uint32_t fence) + struct msm_gpu *gpu, bool write, uint32_t fence) { struct msm_gem_object *msm_obj = to_msm_bo(obj); msm_obj->gpu = gpu; - msm_obj->fence = fence; + if (write) + msm_obj->write_fence = fence; + else + msm_obj->read_fence = fence; list_del_init(&msm_obj->mm_list); list_add_tail(&msm_obj->mm_list, &gpu->active_list); } @@ -411,7 +406,8 @@ void msm_gem_move_to_inactive(struct drm_gem_object *obj) WARN_ON(!mutex_is_locked(&dev->struct_mutex)); msm_obj->gpu = NULL; - msm_obj->fence = 0; + msm_obj->read_fence = 0; + msm_obj->write_fence = 0; list_del_init(&msm_obj->mm_list); list_add_tail(&msm_obj->mm_list, &priv->inactive_list); @@ -433,8 +429,18 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, struct msm_gem_object *msm_obj = to_msm_bo(obj); int ret = 0; - if (is_active(msm_obj) && !(op & MSM_PREP_NOSYNC)) - ret = msm_wait_fence_interruptable(dev, msm_obj->fence, timeout); + if (is_active(msm_obj)) { + uint32_t fence = 0; + + if (op & MSM_PREP_READ) + fence = msm_obj->write_fence; + if (op & MSM_PREP_WRITE) + fence = max(fence, msm_obj->read_fence); + if (op & MSM_PREP_NOSYNC) + timeout = NULL; + + ret = msm_wait_fence_interruptable(dev, fence, timeout); + } /* TODO cache maintenance */ @@ -455,9 +461,10 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m) uint64_t off = drm_vma_node_start(&obj->vma_node); WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - seq_printf(m, "%08x: %c(%d) %2d (%2d) %08llx %p %d\n", + seq_printf(m, "%08x: %c(r=%u,w=%u) %2d (%2d) %08llx %p %d\n", msm_obj->flags, is_active(msm_obj) ? 'A' : 'I', - msm_obj->fence, obj->name, obj->refcount.refcount.counter, + msm_obj->read_fence, msm_obj->write_fence, + obj->name, obj->refcount.refcount.counter, off, msm_obj->vaddr, obj->size); } diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index d746f13..0676f32 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -36,7 +36,7 @@ struct msm_gem_object { */ struct list_head mm_list; struct msm_gpu *gpu; /* non-null if active */ - uint32_t fence; + uint32_t read_fence, write_fence; /* Transiently in the process of submit ioctl, objects associated * with the submit are on submit->bo_list.. this only lasts for diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3e1ef3a..5281d4b 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -78,7 +78,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, } if (submit_bo.flags & BO_INVALID_FLAGS) { - DBG("invalid flags: %x", submit_bo.flags); + DRM_ERROR("invalid flags: %x\n", submit_bo.flags); ret = -EINVAL; goto out_unlock; } @@ -92,7 +92,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, */ obj = idr_find(&file->object_idr, submit_bo.handle); if (!obj) { - DBG("invalid handle %u at index %u", submit_bo.handle, i); + DRM_ERROR("invalid handle %u at index %u\n", submit_bo.handle, i); ret = -EINVAL; goto out_unlock; } @@ -100,7 +100,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, msm_obj = to_msm_bo(obj); if (!list_empty(&msm_obj->submit_entry)) { - DBG("handle %u at index %u already on submit list", + DRM_ERROR("handle %u at index %u already on submit list\n", submit_bo.handle, i); ret = -EINVAL; goto out_unlock; @@ -216,8 +216,9 @@ static int submit_bo(struct msm_gem_submit *submit, uint32_t idx, struct msm_gem_object **obj, uint32_t *iova, bool *valid) { if (idx >= submit->nr_bos) { - DBG("invalid buffer index: %u (out of %u)", idx, submit->nr_bos); - return EINVAL; + DRM_ERROR("invalid buffer index: %u (out of %u)\n", + idx, submit->nr_bos); + return -EINVAL; } if (obj) @@ -239,7 +240,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob int ret; if (offset % 4) { - DBG("non-aligned cmdstream buffer: %u", offset); + DRM_ERROR("non-aligned cmdstream buffer: %u\n", offset); return -EINVAL; } @@ -266,7 +267,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob return -EFAULT; if (submit_reloc.submit_offset % 4) { - DBG("non-aligned reloc offset: %u", + DRM_ERROR("non-aligned reloc offset: %u\n", submit_reloc.submit_offset); return -EINVAL; } @@ -276,7 +277,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob if ((off >= (obj->base.size / 4)) || (off < last_offset)) { - DBG("invalid offset %u at reloc %u", off, i); + DRM_ERROR("invalid offset %u at reloc %u\n", off, i); return -EINVAL; } @@ -374,14 +375,15 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, goto out; if (submit_cmd.size % 4) { - DBG("non-aligned cmdstream buffer size: %u", + DRM_ERROR("non-aligned cmdstream buffer size: %u\n", submit_cmd.size); ret = -EINVAL; goto out; } - if (submit_cmd.size >= msm_obj->base.size) { - DBG("invalid cmdstream size: %u", submit_cmd.size); + if ((submit_cmd.size + submit_cmd.submit_offset) >= + msm_obj->base.size) { + DRM_ERROR("invalid cmdstream size: %u\n", submit_cmd.size); ret = -EINVAL; goto out; } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index e1e1ec9..3bab937 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -29,13 +29,14 @@ static void bs_init(struct msm_gpu *gpu, struct platform_device *pdev) { struct drm_device *dev = gpu->dev; - struct kgsl_device_platform_data *pdata = pdev->dev.platform_data; + struct kgsl_device_platform_data *pdata; if (!pdev) { dev_err(dev->dev, "could not find dtv pdata\n"); return; } + pdata = pdev->dev.platform_data; if (pdata->bus_scale_table) { gpu->bsc = msm_bus_scale_register_client(pdata->bus_scale_table); DBG("bus scale client: %08x", gpu->bsc); @@ -230,6 +231,8 @@ static void hangcheck_timer_reset(struct msm_gpu *gpu) static void hangcheck_handler(unsigned long data) { struct msm_gpu *gpu = (struct msm_gpu *)data; + struct drm_device *dev = gpu->dev; + struct msm_drm_private *priv = dev->dev_private; uint32_t fence = gpu->funcs->last_fence(gpu); if (fence != gpu->hangcheck_fence) { @@ -237,14 +240,22 @@ static void hangcheck_handler(unsigned long data) gpu->hangcheck_fence = fence; } else if (fence < gpu->submitted_fence) { /* no progress and not done.. hung! */ - struct msm_drm_private *priv = gpu->dev->dev_private; gpu->hangcheck_fence = fence; + dev_err(dev->dev, "%s: hangcheck detected gpu lockup!\n", + gpu->name); + dev_err(dev->dev, "%s: completed fence: %u\n", + gpu->name, fence); + dev_err(dev->dev, "%s: submitted fence: %u\n", + gpu->name, gpu->submitted_fence); queue_work(priv->wq, &gpu->recover_work); } /* if still more pending work, reset the hangcheck timer: */ if (gpu->submitted_fence > gpu->hangcheck_fence) hangcheck_timer_reset(gpu); + + /* workaround for missing irq: */ + queue_work(priv->wq, &gpu->retire_work); } /* @@ -265,7 +276,8 @@ static void retire_worker(struct work_struct *work) obj = list_first_entry(&gpu->active_list, struct msm_gem_object, mm_list); - if (obj->fence <= fence) { + if ((obj->read_fence <= fence) && + (obj->write_fence <= fence)) { /* move to inactive: */ msm_gem_move_to_inactive(&obj->base); msm_gem_put_iova(&obj->base, gpu->id); @@ -321,7 +333,11 @@ int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, submit->gpu->id, &iova); } - msm_gem_move_to_active(&msm_obj->base, gpu, submit->fence); + if (submit->bos[i].flags & MSM_SUBMIT_BO_READ) + msm_gem_move_to_active(&msm_obj->base, gpu, false, submit->fence); + + if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE) + msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence); } hangcheck_timer_reset(gpu); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c index 05ff315..b162e98 100644 --- a/drivers/gpu/drm/radeon/btc_dpm.c +++ b/drivers/gpu/drm/radeon/btc_dpm.c @@ -1168,6 +1168,23 @@ static const struct radeon_blacklist_clocks btc_blacklist_clocks[] = { 25000, 30000, RADEON_SCLK_UP } }; +void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table, + u32 *max_clock) +{ + u32 i, clock = 0; + + if ((table == NULL) || (table->count == 0)) { + *max_clock = clock; + return; + } + + for (i = 0; i < table->count; i++) { + if (clock < table->entries[i].clk) + clock = table->entries[i].clk; + } + *max_clock = clock; +} + void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table, u32 clock, u16 max_voltage, u16 *voltage) { @@ -2080,6 +2097,7 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev, bool disable_mclk_switching; u32 mclk, sclk; u16 vddc, vddci; + u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; if ((rdev->pm.dpm.new_active_crtc_count > 1) || btc_dpm_vblank_too_short(rdev)) @@ -2121,6 +2139,39 @@ static void btc_apply_state_adjust_rules(struct radeon_device *rdev, ps->low.vddci = max_limits->vddci; } + /* limit clocks to max supported clocks based on voltage dependency tables */ + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk, + &max_sclk_vddc); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk, + &max_mclk_vddci); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk, + &max_mclk_vddc); + + if (max_sclk_vddc) { + if (ps->low.sclk > max_sclk_vddc) + ps->low.sclk = max_sclk_vddc; + if (ps->medium.sclk > max_sclk_vddc) + ps->medium.sclk = max_sclk_vddc; + if (ps->high.sclk > max_sclk_vddc) + ps->high.sclk = max_sclk_vddc; + } + if (max_mclk_vddci) { + if (ps->low.mclk > max_mclk_vddci) + ps->low.mclk = max_mclk_vddci; + if (ps->medium.mclk > max_mclk_vddci) + ps->medium.mclk = max_mclk_vddci; + if (ps->high.mclk > max_mclk_vddci) + ps->high.mclk = max_mclk_vddci; + } + if (max_mclk_vddc) { + if (ps->low.mclk > max_mclk_vddc) + ps->low.mclk = max_mclk_vddc; + if (ps->medium.mclk > max_mclk_vddc) + ps->medium.mclk = max_mclk_vddc; + if (ps->high.mclk > max_mclk_vddc) + ps->high.mclk = max_mclk_vddc; + } + /* XXX validate the min clocks required for display */ if (disable_mclk_switching) { diff --git a/drivers/gpu/drm/radeon/btc_dpm.h b/drivers/gpu/drm/radeon/btc_dpm.h index 1a15e0e..3b6f12b 100644 --- a/drivers/gpu/drm/radeon/btc_dpm.h +++ b/drivers/gpu/drm/radeon/btc_dpm.h @@ -46,6 +46,8 @@ void btc_adjust_clock_combinations(struct radeon_device *rdev, struct rv7xx_pl *pl); void btc_apply_voltage_dependency_rules(struct radeon_clock_voltage_dependency_table *table, u32 clock, u16 max_voltage, u16 *voltage); +void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table, + u32 *max_clock); void btc_apply_voltage_delta_rules(struct radeon_device *rdev, u16 max_vddc, u16 max_vddci, u16 *vddc, u16 *vddci); diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 8996274..51e947a 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -146,6 +146,8 @@ static const struct ci_pt_config_reg didt_config_ci[] = }; extern u8 rv770_get_memory_module_index(struct radeon_device *rdev); +extern void btc_get_max_clock_from_voltage_dependency_table(struct radeon_clock_voltage_dependency_table *table, + u32 *max_clock); extern int ni_copy_and_switch_arb_sets(struct radeon_device *rdev, u32 arb_freq_src, u32 arb_freq_dest); extern u8 si_get_ddr3_mclk_frequency_ratio(u32 memory_clock); @@ -712,6 +714,7 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev, struct radeon_clock_and_voltage_limits *max_limits; bool disable_mclk_switching; u32 sclk, mclk; + u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; int i; if ((rdev->pm.dpm.new_active_crtc_count > 1) || @@ -739,6 +742,29 @@ static void ci_apply_state_adjust_rules(struct radeon_device *rdev, } } + /* limit clocks to max supported clocks based on voltage dependency tables */ + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk, + &max_sclk_vddc); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk, + &max_mclk_vddci); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk, + &max_mclk_vddc); + + for (i = 0; i < ps->performance_level_count; i++) { + if (max_sclk_vddc) { + if (ps->performance_levels[i].sclk > max_sclk_vddc) + ps->performance_levels[i].sclk = max_sclk_vddc; + } + if (max_mclk_vddci) { + if (ps->performance_levels[i].mclk > max_mclk_vddci) + ps->performance_levels[i].mclk = max_mclk_vddci; + } + if (max_mclk_vddc) { + if (ps->performance_levels[i].mclk > max_mclk_vddc) + ps->performance_levels[i].mclk = max_mclk_vddc; + } + } + /* XXX validate the min clocks required for display */ if (disable_mclk_switching) { diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index adbdb65..d02fd1c 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -2845,10 +2845,8 @@ static void cik_gpu_init(struct radeon_device *rdev) rdev->config.cik.tile_config |= (3 << 0); break; } - if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) - rdev->config.cik.tile_config |= 1 << 4; - else - rdev->config.cik.tile_config |= 0 << 4; + rdev->config.cik.tile_config |= + ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4; rdev->config.cik.tile_config |= ((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8; rdev->config.cik.tile_config |= @@ -4456,8 +4454,8 @@ static int cik_mc_init(struct radeon_device *rdev) rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0); rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0); /* size in MB on si */ - rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024; - rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024 * 1024; + rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL; + rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL; rdev->mc.visible_vram_size = rdev->mc.aper_size; si_vram_gtt_location(rdev, &rdev->mc); radeon_update_bandwidth_info(rdev); @@ -4735,12 +4733,13 @@ static void cik_vm_decode_fault(struct radeon_device *rdev, u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT; u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT; u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT; - char *block = (char *)&mc_client; + char block[5] = { mc_client >> 24, (mc_client >> 16) & 0xff, + (mc_client >> 8) & 0xff, mc_client & 0xff, 0 }; - printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n", + printk("VM fault (0x%02x, vmid %d) at page %u, %s from '%s' (0x%08x) (%d)\n", protections, vmid, addr, (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read", - block, mc_id); + block, mc_client, mc_id); } /** diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index 6c398a4..f263390 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -787,6 +787,7 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev, bool disable_mclk_switching; u32 mclk, sclk; u16 vddc, vddci; + u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; int i; if ((rdev->pm.dpm.new_active_crtc_count > 1) || @@ -813,6 +814,29 @@ static void ni_apply_state_adjust_rules(struct radeon_device *rdev, } } + /* limit clocks to max supported clocks based on voltage dependency tables */ + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk, + &max_sclk_vddc); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk, + &max_mclk_vddci); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk, + &max_mclk_vddc); + + for (i = 0; i < ps->performance_level_count; i++) { + if (max_sclk_vddc) { + if (ps->performance_levels[i].sclk > max_sclk_vddc) + ps->performance_levels[i].sclk = max_sclk_vddc; + } + if (max_mclk_vddci) { + if (ps->performance_levels[i].mclk > max_mclk_vddci) + ps->performance_levels[i].mclk = max_mclk_vddci; + } + if (max_mclk_vddc) { + if (ps->performance_levels[i].mclk > max_mclk_vddc) + ps->performance_levels[i].mclk = max_mclk_vddc; + } + } + /* XXX validate the min clocks required for display */ if (disable_mclk_switching) { diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 2417571..d713330 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -2933,9 +2933,11 @@ static int r100_debugfs_cp_ring_info(struct seq_file *m, void *data) seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp); seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw); seq_printf(m, "%u dwords in ring\n", count); - for (j = 0; j <= count; j++) { - i = (rdp + j) & ring->ptr_mask; - seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]); + if (ring->ready) { + for (j = 0; j <= count; j++) { + i = (rdp + j) & ring->ptr_mask; + seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]); + } } return 0; } diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c index e65f211..5513d8f 100644 --- a/drivers/gpu/drm/radeon/r600_dpm.c +++ b/drivers/gpu/drm/radeon/r600_dpm.c @@ -1084,7 +1084,7 @@ int r600_parse_extended_power_table(struct radeon_device *rdev) rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].dclk = le16_to_cpu(uvd_clk->usDClkLow) | (uvd_clk->ucDClkHigh << 16); rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table.entries[i].v = - le16_to_cpu(limits->entries[i].usVoltage); + le16_to_cpu(entry->usVoltage); entry = (ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record *) ((u8 *)entry + sizeof(ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record)); } diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index f443010..b0fa600 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -257,10 +257,7 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock) * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ - if (ASIC_IS_DCE3(rdev)) { - /* according to the reg specs, this should DCE3.2 only, but in - * practice it seems to cover DCE3.0 as well. - */ + if (ASIC_IS_DCE32(rdev)) { if (dig->dig_encoder == 0) { dto_cntl = RREG32(DCCG_AUDIO_DTO0_CNTL) & ~DCCG_AUDIO_DTO_WALLCLOCK_RATIO_MASK; dto_cntl |= DCCG_AUDIO_DTO_WALLCLOCK_RATIO(wallclock_ratio); @@ -276,8 +273,21 @@ void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock) WREG32(DCCG_AUDIO_DTO1_MODULE, dto_modulo); WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */ } + } else if (ASIC_IS_DCE3(rdev)) { + /* according to the reg specs, this should DCE3.2 only, but in + * practice it seems to cover DCE3.0/3.1 as well. + */ + if (dig->dig_encoder == 0) { + WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100); + WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100); + WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */ + } else { + WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100); + WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100); + WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */ + } } else { - /* according to the reg specs, this should be DCE2.0 and DCE3.0 */ + /* according to the reg specs, this should be DCE2.0 and DCE3.0/3.1 */ WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) | AUDIO_DTO_MODULE(clock / 10)); } diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 5003385..8f7e045 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -1004,6 +1004,8 @@ static struct radeon_asic rv6xx_asic = { .wait_for_vblank = &avivo_wait_for_vblank, .set_backlight_level = &atombios_set_backlight_level, .get_backlight_level = &atombios_get_backlight_level, + .hdmi_enable = &r600_hdmi_enable, + .hdmi_setmode = &r600_hdmi_setmode, }, .copy = { .blit = &r600_copy_cpdma, diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 404e25d..f79ee18 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -1367,6 +1367,7 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev, int index = GetIndexIntoMasterTable(DATA, PPLL_SS_Info); uint16_t data_offset, size; struct _ATOM_SPREAD_SPECTRUM_INFO *ss_info; + struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT *ss_assign; uint8_t frev, crev; int i, num_indices; @@ -1378,18 +1379,21 @@ bool radeon_atombios_get_ppll_ss_info(struct radeon_device *rdev, num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) / sizeof(ATOM_SPREAD_SPECTRUM_ASSIGNMENT); - + ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*) + ((u8 *)&ss_info->asSS_Info[0]); for (i = 0; i < num_indices; i++) { - if (ss_info->asSS_Info[i].ucSS_Id == id) { + if (ss_assign->ucSS_Id == id) { ss->percentage = - le16_to_cpu(ss_info->asSS_Info[i].usSpreadSpectrumPercentage); - ss->type = ss_info->asSS_Info[i].ucSpreadSpectrumType; - ss->step = ss_info->asSS_Info[i].ucSS_Step; - ss->delay = ss_info->asSS_Info[i].ucSS_Delay; - ss->range = ss_info->asSS_Info[i].ucSS_Range; - ss->refdiv = ss_info->asSS_Info[i].ucRecommendedRef_Div; + le16_to_cpu(ss_assign->usSpreadSpectrumPercentage); + ss->type = ss_assign->ucSpreadSpectrumType; + ss->step = ss_assign->ucSS_Step; + ss->delay = ss_assign->ucSS_Delay; + ss->range = ss_assign->ucSS_Range; + ss->refdiv = ss_assign->ucRecommendedRef_Div; return true; } + ss_assign = (struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT*) + ((u8 *)ss_assign + sizeof(struct _ATOM_SPREAD_SPECTRUM_ASSIGNMENT)); } } return false; @@ -1477,6 +1481,12 @@ union asic_ss_info { struct _ATOM_ASIC_INTERNAL_SS_INFO_V3 info_3; }; +union asic_ss_assignment { + struct _ATOM_ASIC_SS_ASSIGNMENT v1; + struct _ATOM_ASIC_SS_ASSIGNMENT_V2 v2; + struct _ATOM_ASIC_SS_ASSIGNMENT_V3 v3; +}; + bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, struct radeon_atom_ss *ss, int id, u32 clock) @@ -1485,6 +1495,7 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, int index = GetIndexIntoMasterTable(DATA, ASIC_InternalSS_Info); uint16_t data_offset, size; union asic_ss_info *ss_info; + union asic_ss_assignment *ss_assign; uint8_t frev, crev; int i, num_indices; @@ -1509,45 +1520,52 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) / sizeof(ATOM_ASIC_SS_ASSIGNMENT); + ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info.asSpreadSpectrum[0]); for (i = 0; i < num_indices; i++) { - if ((ss_info->info.asSpreadSpectrum[i].ucClockIndication == id) && - (clock <= le32_to_cpu(ss_info->info.asSpreadSpectrum[i].ulTargetClockRange))) { + if ((ss_assign->v1.ucClockIndication == id) && + (clock <= le32_to_cpu(ss_assign->v1.ulTargetClockRange))) { ss->percentage = - le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadSpectrumPercentage); - ss->type = ss_info->info.asSpreadSpectrum[i].ucSpreadSpectrumMode; - ss->rate = le16_to_cpu(ss_info->info.asSpreadSpectrum[i].usSpreadRateInKhz); + le16_to_cpu(ss_assign->v1.usSpreadSpectrumPercentage); + ss->type = ss_assign->v1.ucSpreadSpectrumMode; + ss->rate = le16_to_cpu(ss_assign->v1.usSpreadRateInKhz); return true; } + ss_assign = (union asic_ss_assignment *) + ((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT)); } break; case 2: num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) / sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2); + ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_2.asSpreadSpectrum[0]); for (i = 0; i < num_indices; i++) { - if ((ss_info->info_2.asSpreadSpectrum[i].ucClockIndication == id) && - (clock <= le32_to_cpu(ss_info->info_2.asSpreadSpectrum[i].ulTargetClockRange))) { + if ((ss_assign->v2.ucClockIndication == id) && + (clock <= le32_to_cpu(ss_assign->v2.ulTargetClockRange))) { ss->percentage = - le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadSpectrumPercentage); - ss->type = ss_info->info_2.asSpreadSpectrum[i].ucSpreadSpectrumMode; - ss->rate = le16_to_cpu(ss_info->info_2.asSpreadSpectrum[i].usSpreadRateIn10Hz); + le16_to_cpu(ss_assign->v2.usSpreadSpectrumPercentage); + ss->type = ss_assign->v2.ucSpreadSpectrumMode; + ss->rate = le16_to_cpu(ss_assign->v2.usSpreadRateIn10Hz); if ((crev == 2) && ((id == ASIC_INTERNAL_ENGINE_SS) || (id == ASIC_INTERNAL_MEMORY_SS))) ss->rate /= 100; return true; } + ss_assign = (union asic_ss_assignment *) + ((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V2)); } break; case 3: num_indices = (size - sizeof(ATOM_COMMON_TABLE_HEADER)) / sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3); + ss_assign = (union asic_ss_assignment *)((u8 *)&ss_info->info_3.asSpreadSpectrum[0]); for (i = 0; i < num_indices; i++) { - if ((ss_info->info_3.asSpreadSpectrum[i].ucClockIndication == id) && - (clock <= le32_to_cpu(ss_info->info_3.asSpreadSpectrum[i].ulTargetClockRange))) { + if ((ss_assign->v3.ucClockIndication == id) && + (clock <= le32_to_cpu(ss_assign->v3.ulTargetClockRange))) { ss->percentage = - le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadSpectrumPercentage); - ss->type = ss_info->info_3.asSpreadSpectrum[i].ucSpreadSpectrumMode; - ss->rate = le16_to_cpu(ss_info->info_3.asSpreadSpectrum[i].usSpreadRateIn10Hz); + le16_to_cpu(ss_assign->v3.usSpreadSpectrumPercentage); + ss->type = ss_assign->v3.ucSpreadSpectrumMode; + ss->rate = le16_to_cpu(ss_assign->v3.usSpreadRateIn10Hz); if ((id == ASIC_INTERNAL_ENGINE_SS) || (id == ASIC_INTERNAL_MEMORY_SS)) ss->rate /= 100; @@ -1555,6 +1573,8 @@ bool radeon_atombios_get_asic_ss_info(struct radeon_device *rdev, radeon_atombios_get_igp_ss_overrides(rdev, ss, id); return true; } + ss_assign = (union asic_ss_assignment *) + ((u8 *)ss_assign + sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3)); } break; default: diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index ac6ece6..66c2228 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -85,8 +85,9 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) VRAM, also but everything into VRAM on AGP cards to avoid image corruptions */ if (p->ring == R600_RING_TYPE_UVD_INDEX && - (i == 0 || p->rdev->flags & RADEON_IS_AGP)) { - /* TODO: is this still needed for NI+ ? */ + p->rdev->family < CHIP_PALM && + (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) { + p->relocs[i].lobj.domain = RADEON_GEM_DOMAIN_VRAM; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index e29faa7..841d0e0 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1320,13 +1320,22 @@ int radeon_device_init(struct radeon_device *rdev, return r; } if ((radeon_testing & 1)) { - radeon_test_moves(rdev); + if (rdev->accel_working) + radeon_test_moves(rdev); + else + DRM_INFO("radeon: acceleration disabled, skipping move tests\n"); } if ((radeon_testing & 2)) { - radeon_test_syncing(rdev); + if (rdev->accel_working) + radeon_test_syncing(rdev); + else + DRM_INFO("radeon: acceleration disabled, skipping sync tests\n"); } if (radeon_benchmarking) { - radeon_benchmark(rdev, radeon_benchmarking); + if (rdev->accel_working) + radeon_benchmark(rdev, radeon_benchmarking); + else + DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n"); } return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 87e1d69..ac07ad1 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1002,7 +1002,7 @@ static void radeon_pm_resume_old(struct radeon_device *rdev) { /* set up the default clocks if the MC ucode is loaded */ if ((rdev->family >= CHIP_BARTS) && - (rdev->family <= CHIP_HAINAN) && + (rdev->family <= CHIP_CAYMAN) && rdev->mc_fw) { if (rdev->pm.default_vddc) radeon_atom_set_voltage(rdev, rdev->pm.default_vddc, @@ -1046,7 +1046,7 @@ static void radeon_pm_resume_dpm(struct radeon_device *rdev) if (ret) { DRM_ERROR("radeon: dpm resume failed\n"); if ((rdev->family >= CHIP_BARTS) && - (rdev->family <= CHIP_HAINAN) && + (rdev->family <= CHIP_CAYMAN) && rdev->mc_fw) { if (rdev->pm.default_vddc) radeon_atom_set_voltage(rdev, rdev->pm.default_vddc, @@ -1097,7 +1097,7 @@ static int radeon_pm_init_old(struct radeon_device *rdev) radeon_pm_init_profile(rdev); /* set up the default clocks if the MC ucode is loaded */ if ((rdev->family >= CHIP_BARTS) && - (rdev->family <= CHIP_HAINAN) && + (rdev->family <= CHIP_CAYMAN) && rdev->mc_fw) { if (rdev->pm.default_vddc) radeon_atom_set_voltage(rdev, rdev->pm.default_vddc, @@ -1183,7 +1183,7 @@ static int radeon_pm_init_dpm(struct radeon_device *rdev) if (ret) { rdev->pm.dpm_enabled = false; if ((rdev->family >= CHIP_BARTS) && - (rdev->family <= CHIP_HAINAN) && + (rdev->family <= CHIP_CAYMAN) && rdev->mc_fw) { if (rdev->pm.default_vddc) radeon_atom_set_voltage(rdev, rdev->pm.default_vddc, diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 46a25f0..18254e1 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -839,9 +839,11 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data) * packet that is the root issue */ i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask; - for (j = 0; j <= (count + 32); j++) { - seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]); - i = (i + 1) & ring->ptr_mask; + if (ring->ready) { + for (j = 0; j <= (count + 32); j++) { + seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]); + i = (i + 1) & ring->ptr_mask; + } } return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 1a01bbf..a0f1185 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -476,8 +476,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, return -EINVAL; } - /* TODO: is this still necessary on NI+ ? */ - if ((cmd == 0 || cmd == 0x3) && + if (p->rdev->family < CHIP_PALM && (cmd == 0 || cmd == 0x3) && (start >> 28) != (p->rdev->uvd.gpu_addr >> 28)) { DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n", start, end); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index cfe5d4d..9ace287 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2910,6 +2910,7 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, bool disable_sclk_switching = false; u32 mclk, sclk; u16 vddc, vddci; + u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc; int i; if ((rdev->pm.dpm.new_active_crtc_count > 1) || @@ -2943,6 +2944,29 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, } } + /* limit clocks to max supported clocks based on voltage dependency tables */ + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk, + &max_sclk_vddc); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddci_dependency_on_mclk, + &max_mclk_vddci); + btc_get_max_clock_from_voltage_dependency_table(&rdev->pm.dpm.dyn_state.vddc_dependency_on_mclk, + &max_mclk_vddc); + + for (i = 0; i < ps->performance_level_count; i++) { + if (max_sclk_vddc) { + if (ps->performance_levels[i].sclk > max_sclk_vddc) + ps->performance_levels[i].sclk = max_sclk_vddc; + } + if (max_mclk_vddci) { + if (ps->performance_levels[i].mclk > max_mclk_vddci) + ps->performance_levels[i].mclk = max_mclk_vddci; + } + if (max_mclk_vddc) { + if (ps->performance_levels[i].mclk > max_mclk_vddc) + ps->performance_levels[i].mclk = max_mclk_vddc; + } + } + /* XXX validate the min clocks required for display */ if (disable_mclk_switching) { diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index 7266805..3100fa9 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -212,8 +212,8 @@ int uvd_v1_0_start(struct radeon_device *rdev) /* enable VCPU clock */ WREG32(UVD_VCPU_CNTL, 1 << 9); - /* enable UMC */ - WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8)); + /* enable UMC and NC0 */ + WREG32_P(UVD_LMI_CTRL2, 1 << 13, ~((1 << 8) | (1 << 13))); /* boot up the VCPU */ WREG32(UVD_SOFT_RESET, 0); diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 8f4743a..936093e 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -195,7 +195,7 @@ int vmbus_connect(void) do { ret = vmbus_negotiate_version(msginfo, version); - if (ret) + if (ret == -ETIMEDOUT) goto cleanup; if (vmbus_connection.conn_state == CONNECTED) diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index 28b0332..09988b2 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -32,13 +32,17 @@ /* * Pre win8 version numbers used in ws2008 and ws 2008 r2 (win7) */ +#define WS2008_SRV_MAJOR 1 +#define WS2008_SRV_MINOR 0 +#define WS2008_SRV_VERSION (WS2008_SRV_MAJOR << 16 | WS2008_SRV_MINOR) + #define WIN7_SRV_MAJOR 3 #define WIN7_SRV_MINOR 0 -#define WIN7_SRV_MAJOR_MINOR (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR) +#define WIN7_SRV_VERSION (WIN7_SRV_MAJOR << 16 | WIN7_SRV_MINOR) #define WIN8_SRV_MAJOR 4 #define WIN8_SRV_MINOR 0 -#define WIN8_SRV_MAJOR_MINOR (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) +#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) /* * Global state maintained for transaction that is being processed. @@ -587,6 +591,8 @@ void hv_kvp_onchannelcallback(void *context) struct icmsg_hdr *icmsghdrp; struct icmsg_negotiate *negop = NULL; + int util_fw_version; + int kvp_srv_version; if (kvp_transaction.active) { /* @@ -606,17 +612,26 @@ void hv_kvp_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { /* - * We start with win8 version and if the host cannot - * support that we use the previous version. + * Based on the host, select appropriate + * framework and service versions we will + * negotiate. */ - if (vmbus_prep_negotiate_resp(icmsghdrp, negop, - recv_buffer, UTIL_FW_MAJOR_MINOR, - WIN8_SRV_MAJOR_MINOR)) - goto done; - + switch (vmbus_proto_version) { + case (VERSION_WS2008): + util_fw_version = UTIL_WS2K8_FW_VERSION; + kvp_srv_version = WS2008_SRV_VERSION; + break; + case (VERSION_WIN7): + util_fw_version = UTIL_FW_VERSION; + kvp_srv_version = WIN7_SRV_VERSION; + break; + default: + util_fw_version = UTIL_FW_VERSION; + kvp_srv_version = WIN8_SRV_VERSION; + } vmbus_prep_negotiate_resp(icmsghdrp, negop, - recv_buffer, UTIL_FW_MAJOR_MINOR, - WIN7_SRV_MAJOR_MINOR); + recv_buffer, util_fw_version, + kvp_srv_version); } else { kvp_msg = (struct hv_kvp_msg *)&recv_buffer[ @@ -649,7 +664,6 @@ void hv_kvp_onchannelcallback(void *context) return; } -done: icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index e4572f3..0c35462 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -26,7 +26,7 @@ #define VSS_MAJOR 5 #define VSS_MINOR 0 -#define VSS_MAJOR_MINOR (VSS_MAJOR << 16 | VSS_MINOR) +#define VSS_VERSION (VSS_MAJOR << 16 | VSS_MINOR) @@ -190,8 +190,8 @@ void hv_vss_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { vmbus_prep_negotiate_resp(icmsghdrp, negop, - recv_buffer, UTIL_FW_MAJOR_MINOR, - VSS_MAJOR_MINOR); + recv_buffer, UTIL_FW_VERSION, + VSS_VERSION); } else { vss_msg = (struct hv_vss_msg *)&recv_buffer[ sizeof(struct vmbuspipe_hdr) + diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index cb82233..273e3dd 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -28,17 +28,32 @@ #include <linux/reboot.h> #include <linux/hyperv.h> -#define SHUTDOWN_MAJOR 3 -#define SHUTDOWN_MINOR 0 -#define SHUTDOWN_MAJOR_MINOR (SHUTDOWN_MAJOR << 16 | SHUTDOWN_MINOR) -#define TIMESYNCH_MAJOR 3 -#define TIMESYNCH_MINOR 0 -#define TIMESYNCH_MAJOR_MINOR (TIMESYNCH_MAJOR << 16 | TIMESYNCH_MINOR) +#define SD_MAJOR 3 +#define SD_MINOR 0 +#define SD_VERSION (SD_MAJOR << 16 | SD_MINOR) -#define HEARTBEAT_MAJOR 3 -#define HEARTBEAT_MINOR 0 -#define HEARTBEAT_MAJOR_MINOR (HEARTBEAT_MAJOR << 16 | HEARTBEAT_MINOR) +#define SD_WS2008_MAJOR 1 +#define SD_WS2008_VERSION (SD_WS2008_MAJOR << 16 | SD_MINOR) + +#define TS_MAJOR 3 +#define TS_MINOR 0 +#define TS_VERSION (TS_MAJOR << 16 | TS_MINOR) + +#define TS_WS2008_MAJOR 1 +#define TS_WS2008_VERSION (TS_WS2008_MAJOR << 16 | TS_MINOR) + +#define HB_MAJOR 3 +#define HB_MINOR 0 +#define HB_VERSION (HB_MAJOR << 16 | HB_MINOR) + +#define HB_WS2008_MAJOR 1 +#define HB_WS2008_VERSION (HB_WS2008_MAJOR << 16 | HB_MINOR) + +static int sd_srv_version; +static int ts_srv_version; +static int hb_srv_version; +static int util_fw_version; static void shutdown_onchannelcallback(void *context); static struct hv_util_service util_shutdown = { @@ -99,8 +114,8 @@ static void shutdown_onchannelcallback(void *context) if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { vmbus_prep_negotiate_resp(icmsghdrp, negop, - shut_txf_buf, UTIL_FW_MAJOR_MINOR, - SHUTDOWN_MAJOR_MINOR); + shut_txf_buf, util_fw_version, + sd_srv_version); } else { shutdown_msg = (struct shutdown_msg_data *)&shut_txf_buf[ @@ -216,6 +231,7 @@ static void timesync_onchannelcallback(void *context) struct icmsg_hdr *icmsghdrp; struct ictimesync_data *timedatap; u8 *time_txf_buf = util_timesynch.recv_buffer; + struct icmsg_negotiate *negop = NULL; vmbus_recvpacket(channel, time_txf_buf, PAGE_SIZE, &recvlen, &requestid); @@ -225,9 +241,10 @@ static void timesync_onchannelcallback(void *context) sizeof(struct vmbuspipe_hdr)]; if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { - vmbus_prep_negotiate_resp(icmsghdrp, NULL, time_txf_buf, - UTIL_FW_MAJOR_MINOR, - TIMESYNCH_MAJOR_MINOR); + vmbus_prep_negotiate_resp(icmsghdrp, negop, + time_txf_buf, + util_fw_version, + ts_srv_version); } else { timedatap = (struct ictimesync_data *)&time_txf_buf[ sizeof(struct vmbuspipe_hdr) + @@ -257,6 +274,7 @@ static void heartbeat_onchannelcallback(void *context) struct icmsg_hdr *icmsghdrp; struct heartbeat_msg_data *heartbeat_msg; u8 *hbeat_txf_buf = util_heartbeat.recv_buffer; + struct icmsg_negotiate *negop = NULL; vmbus_recvpacket(channel, hbeat_txf_buf, PAGE_SIZE, &recvlen, &requestid); @@ -266,9 +284,9 @@ static void heartbeat_onchannelcallback(void *context) sizeof(struct vmbuspipe_hdr)]; if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) { - vmbus_prep_negotiate_resp(icmsghdrp, NULL, - hbeat_txf_buf, UTIL_FW_MAJOR_MINOR, - HEARTBEAT_MAJOR_MINOR); + vmbus_prep_negotiate_resp(icmsghdrp, negop, + hbeat_txf_buf, util_fw_version, + hb_srv_version); } else { heartbeat_msg = (struct heartbeat_msg_data *)&hbeat_txf_buf[ @@ -321,6 +339,25 @@ static int util_probe(struct hv_device *dev, goto error; hv_set_drvdata(dev, srv); + /* + * Based on the host; initialize the framework and + * service version numbers we will negotiate. + */ + switch (vmbus_proto_version) { + case (VERSION_WS2008): + util_fw_version = UTIL_WS2K8_FW_VERSION; + sd_srv_version = SD_WS2008_VERSION; + ts_srv_version = TS_WS2008_VERSION; + hb_srv_version = HB_WS2008_VERSION; + break; + + default: + util_fw_version = UTIL_FW_VERSION; + sd_srv_version = SD_VERSION; + ts_srv_version = TS_VERSION; + hb_srv_version = HB_VERSION; + } + return 0; error: diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index 62c2e32..98814d1 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -525,16 +525,25 @@ static int applesmc_init_smcreg_try(void) { struct applesmc_registers *s = &smcreg; bool left_light_sensor, right_light_sensor; + unsigned int count; u8 tmp[1]; int ret; if (s->init_complete) return 0; - ret = read_register_count(&s->key_count); + ret = read_register_count(&count); if (ret) return ret; + if (s->cache && s->key_count != count) { + pr_warn("key count changed from %d to %d\n", + s->key_count, count); + kfree(s->cache); + s->cache = NULL; + } + s->key_count = count; + if (!s->cache) s->cache = kcalloc(s->key_count, sizeof(*s->cache), GFP_KERNEL); if (!s->cache) diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index dbecf08..5888fee 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -98,6 +98,8 @@ #define DW_IC_ERR_TX_ABRT 0x1 +#define DW_IC_TAR_10BITADDR_MASTER BIT(12) + /* * status codes */ @@ -388,22 +390,34 @@ static int i2c_dw_wait_bus_not_busy(struct dw_i2c_dev *dev) static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) { struct i2c_msg *msgs = dev->msgs; - u32 ic_con; + u32 ic_con, ic_tar = 0; /* Disable the adapter */ __i2c_dw_enable(dev, false); - /* set the slave (target) address */ - dw_writel(dev, msgs[dev->msg_write_idx].addr, DW_IC_TAR); - /* if the slave address is ten bit address, enable 10BITADDR */ ic_con = dw_readl(dev, DW_IC_CON); - if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) + if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) { ic_con |= DW_IC_CON_10BITADDR_MASTER; - else + /* + * If I2C_DYNAMIC_TAR_UPDATE is set, the 10-bit addressing + * mode has to be enabled via bit 12 of IC_TAR register. + * We set it always as I2C_DYNAMIC_TAR_UPDATE can't be + * detected from registers. + */ + ic_tar = DW_IC_TAR_10BITADDR_MASTER; + } else { ic_con &= ~DW_IC_CON_10BITADDR_MASTER; + } + dw_writel(dev, ic_con, DW_IC_CON); + /* + * Set the slave (target) address and enable 10-bit addressing mode + * if applicable. + */ + dw_writel(dev, msgs[dev->msg_write_idx].addr | ic_tar, DW_IC_TAR); + /* Enable the adapter */ __i2c_dw_enable(dev, true); diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 8ed79a0..1672eff 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -393,6 +393,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, desc = &priv->hw[priv->head]; + /* Initialize the DMA buffer */ + memset(priv->dma_buffer, 0, sizeof(priv->dma_buffer)); + /* Initialize the descriptor */ memset(desc, 0, sizeof(struct ismt_desc)); desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index 7f3a474..d3e9cc3 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -234,9 +234,9 @@ static int mv64xxx_i2c_offload_msg(struct mv64xxx_i2c_data *drv_data) ctrl_reg |= MV64XXX_I2C_BRIDGE_CONTROL_WR | (msg->len - 1) << MV64XXX_I2C_BRIDGE_CONTROL_TX_SIZE_SHIFT; - writel_relaxed(data_reg_lo, + writel(data_reg_lo, drv_data->reg_base + MV64XXX_I2C_REG_TX_DATA_LO); - writel_relaxed(data_reg_hi, + writel(data_reg_hi, drv_data->reg_base + MV64XXX_I2C_REG_TX_DATA_HI); } else { @@ -697,6 +697,7 @@ static const struct of_device_id mv64xxx_i2c_of_match_table[] = { MODULE_DEVICE_TABLE(of, mv64xxx_i2c_of_match_table); #ifdef CONFIG_OF +#ifdef CONFIG_HAVE_CLK static int mv64xxx_calc_freq(const int tclk, const int n, const int m) { @@ -726,16 +727,12 @@ mv64xxx_find_baud_factors(const u32 req_freq, const u32 tclk, u32 *best_n, return false; return true; } +#endif /* CONFIG_HAVE_CLK */ static int mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, struct device *dev) { - const struct of_device_id *device; - struct device_node *np = dev->of_node; - u32 bus_freq, tclk; - int rc = 0; - /* CLK is mandatory when using DT to describe the i2c bus. We * need to know tclk in order to calculate bus clock * factors. @@ -744,6 +741,11 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, /* Have OF but no CLK */ return -ENODEV; #else + const struct of_device_id *device; + struct device_node *np = dev->of_node; + u32 bus_freq, tclk; + int rc = 0; + if (IS_ERR(drv_data->clk)) { rc = -ENODEV; goto out; diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 3535f3c..3747b9b 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -1178,8 +1178,6 @@ static int s3c24xx_i2c_remove(struct platform_device *pdev) i2c_del_adapter(&i2c->adap); - clk_disable_unprepare(i2c->clk); - if (pdev->dev.of_node && IS_ERR(i2c->pctrl)) s3c24xx_i2c_dt_gpio_free(i2c); diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index 12e32e6..81e3dc2 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -620,7 +620,7 @@ static int bma180_remove(struct i2c_client *client) #ifdef CONFIG_PM_SLEEP static int bma180_suspend(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev)); struct bma180_data *data = iio_priv(indio_dev); int ret; @@ -633,7 +633,7 @@ static int bma180_suspend(struct device *dev) static int bma180_resume(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); + struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev)); struct bma180_data *data = iio_priv(indio_dev); int ret; diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 84be63b..0f16b55 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -556,7 +556,7 @@ static const struct iio_info at91_adc_info = { static int at91_adc_probe(struct platform_device *pdev) { - unsigned int prsc, mstrclk, ticks, adc_clk, shtim; + unsigned int prsc, mstrclk, ticks, adc_clk, adc_clk_khz, shtim; int ret; struct iio_dev *idev; struct at91_adc_state *st; @@ -649,6 +649,7 @@ static int at91_adc_probe(struct platform_device *pdev) */ mstrclk = clk_get_rate(st->clk); adc_clk = clk_get_rate(st->adc_clk); + adc_clk_khz = adc_clk / 1000; prsc = (mstrclk / (2 * adc_clk)) - 1; if (!st->startup_time) { @@ -662,15 +663,15 @@ static int at91_adc_probe(struct platform_device *pdev) * defined in the electrical characteristics of the board, divided by 8. * The formula thus is : Startup Time = (ticks + 1) * 8 / ADC Clock */ - ticks = round_up((st->startup_time * adc_clk / - 1000000) - 1, 8) / 8; + ticks = round_up((st->startup_time * adc_clk_khz / + 1000) - 1, 8) / 8; /* * a minimal Sample and Hold Time is necessary for the ADC to guarantee * the best converted final value between two channels selection * The formula thus is : Sample and Hold Time = (shtim + 1) / ADCClock */ - shtim = round_up((st->sample_hold_time * adc_clk / - 1000000) - 1, 1); + shtim = round_up((st->sample_hold_time * adc_clk_khz / + 1000) - 1, 1); reg = AT91_ADC_PRESCAL_(prsc) & st->registers->mr_prescal_mask; reg |= AT91_ADC_STARTUP_(ticks) & st->registers->mr_startup_mask; diff --git a/drivers/iio/buffer_cb.c b/drivers/iio/buffer_cb.c index 9d19ba7..415f3c6 100644 --- a/drivers/iio/buffer_cb.c +++ b/drivers/iio/buffer_cb.c @@ -41,6 +41,8 @@ struct iio_cb_buffer *iio_channel_get_all_cb(struct device *dev, goto error_ret; } + iio_buffer_init(&cb_buff->buffer); + cb_buff->private = private; cb_buff->cb = cb; cb_buff->buffer.access = &iio_cb_access; diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 1f4a48e..1397b6e 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -37,21 +37,21 @@ struct mcp4725_data { static int mcp4725_suspend(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct mcp4725_data *data = iio_priv(indio_dev); + struct mcp4725_data *data = iio_priv(i2c_get_clientdata( + to_i2c_client(dev))); u8 outbuf[2]; outbuf[0] = (data->powerdown_mode + 1) << 4; outbuf[1] = 0; data->powerdown = true; - return i2c_master_send(to_i2c_client(dev), outbuf, 2); + return i2c_master_send(data->client, outbuf, 2); } static int mcp4725_resume(struct device *dev) { - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct mcp4725_data *data = iio_priv(indio_dev); + struct mcp4725_data *data = iio_priv(i2c_get_clientdata( + to_i2c_client(dev))); u8 outbuf[2]; /* restore previous DAC value */ @@ -59,7 +59,7 @@ static int mcp4725_resume(struct device *dev) outbuf[1] = data->dac_value & 0xff; data->powerdown = false; - return i2c_master_send(to_i2c_client(dev), outbuf, 2); + return i2c_master_send(data->client, outbuf, 2); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/iio/iio_core.h b/drivers/iio/iio_core.h index 05c1b74..9b32253 100644 --- a/drivers/iio/iio_core.h +++ b/drivers/iio/iio_core.h @@ -49,11 +49,15 @@ ssize_t iio_buffer_read_first_n_outer(struct file *filp, char __user *buf, #define iio_buffer_poll_addr (&iio_buffer_poll) #define iio_buffer_read_first_n_outer_addr (&iio_buffer_read_first_n_outer) +void iio_disable_all_buffers(struct iio_dev *indio_dev); + #else #define iio_buffer_poll_addr NULL #define iio_buffer_read_first_n_outer_addr NULL +static inline void iio_disable_all_buffers(struct iio_dev *indio_dev) {} + #endif int iio_device_register_eventset(struct iio_dev *indio_dev); diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index e73033f..2710f72 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -460,6 +460,25 @@ static int iio_compute_scan_bytes(struct iio_dev *indio_dev, const long *mask, return bytes; } +void iio_disable_all_buffers(struct iio_dev *indio_dev) +{ + struct iio_buffer *buffer, *_buffer; + + if (list_empty(&indio_dev->buffer_list)) + return; + + if (indio_dev->setup_ops->predisable) + indio_dev->setup_ops->predisable(indio_dev); + + list_for_each_entry_safe(buffer, _buffer, + &indio_dev->buffer_list, buffer_list) + list_del_init(&buffer->buffer_list); + + indio_dev->currentmode = INDIO_DIRECT_MODE; + if (indio_dev->setup_ops->postdisable) + indio_dev->setup_ops->postdisable(indio_dev); +} + int iio_update_buffers(struct iio_dev *indio_dev, struct iio_buffer *insert_buffer, struct iio_buffer *remove_buffer) @@ -528,8 +547,15 @@ int iio_update_buffers(struct iio_dev *indio_dev, * Note can only occur when adding a buffer. */ list_del(&insert_buffer->buffer_list); - indio_dev->active_scan_mask = old_mask; - success = -EINVAL; + if (old_mask) { + indio_dev->active_scan_mask = old_mask; + success = -EINVAL; + } + else { + kfree(compound_mask); + ret = -EINVAL; + goto error_ret; + } } } else { indio_dev->active_scan_mask = compound_mask; diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 97f0297..8e84cd5 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -848,8 +848,6 @@ static void iio_device_unregister_sysfs(struct iio_dev *indio_dev) static void iio_dev_release(struct device *device) { struct iio_dev *indio_dev = dev_to_iio_dev(device); - if (indio_dev->chrdev.dev) - cdev_del(&indio_dev->chrdev); if (indio_dev->modes & INDIO_BUFFER_TRIGGERED) iio_device_unregister_trigger_consumer(indio_dev); iio_device_unregister_eventset(indio_dev); @@ -970,6 +968,8 @@ static int iio_chrdev_open(struct inode *inode, struct file *filp) if (test_and_set_bit(IIO_BUSY_BIT_POS, &indio_dev->flags)) return -EBUSY; + iio_device_get(indio_dev); + filp->private_data = indio_dev; return 0; @@ -983,6 +983,8 @@ static int iio_chrdev_release(struct inode *inode, struct file *filp) struct iio_dev *indio_dev = container_of(inode->i_cdev, struct iio_dev, chrdev); clear_bit(IIO_BUSY_BIT_POS, &indio_dev->flags); + iio_device_put(indio_dev); + return 0; } @@ -1052,18 +1054,20 @@ int iio_device_register(struct iio_dev *indio_dev) indio_dev->setup_ops == NULL) indio_dev->setup_ops = &noop_ring_setup_ops; - ret = device_add(&indio_dev->dev); - if (ret < 0) - goto error_unreg_eventset; cdev_init(&indio_dev->chrdev, &iio_buffer_fileops); indio_dev->chrdev.owner = indio_dev->info->driver_module; + indio_dev->chrdev.kobj.parent = &indio_dev->dev.kobj; ret = cdev_add(&indio_dev->chrdev, indio_dev->dev.devt, 1); if (ret < 0) - goto error_del_device; - return 0; + goto error_unreg_eventset; -error_del_device: - device_del(&indio_dev->dev); + ret = device_add(&indio_dev->dev); + if (ret < 0) + goto error_cdev_del; + + return 0; +error_cdev_del: + cdev_del(&indio_dev->chrdev); error_unreg_eventset: iio_device_unregister_eventset(indio_dev); error_free_sysfs: @@ -1078,9 +1082,16 @@ EXPORT_SYMBOL(iio_device_register); void iio_device_unregister(struct iio_dev *indio_dev) { mutex_lock(&indio_dev->info_exist_lock); + + device_del(&indio_dev->dev); + + if (indio_dev->chrdev.dev) + cdev_del(&indio_dev->chrdev); + + iio_disable_all_buffers(indio_dev); + indio_dev->info = NULL; mutex_unlock(&indio_dev->info_exist_lock); - device_del(&indio_dev->dev); } EXPORT_SYMBOL(iio_device_unregister); subsys_initcall(iio_init); diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index 10aa9ef..6be65ef 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -72,7 +72,8 @@ EXPORT_SYMBOL(iio_push_event); static unsigned int iio_event_poll(struct file *filep, struct poll_table_struct *wait) { - struct iio_event_interface *ev_int = filep->private_data; + struct iio_dev *indio_dev = filep->private_data; + struct iio_event_interface *ev_int = indio_dev->event_interface; unsigned int events = 0; poll_wait(filep, &ev_int->wait, wait); @@ -90,7 +91,8 @@ static ssize_t iio_event_chrdev_read(struct file *filep, size_t count, loff_t *f_ps) { - struct iio_event_interface *ev_int = filep->private_data; + struct iio_dev *indio_dev = filep->private_data; + struct iio_event_interface *ev_int = indio_dev->event_interface; unsigned int copied; int ret; @@ -121,7 +123,8 @@ error_unlock: static int iio_event_chrdev_release(struct inode *inode, struct file *filep) { - struct iio_event_interface *ev_int = filep->private_data; + struct iio_dev *indio_dev = filep->private_data; + struct iio_event_interface *ev_int = indio_dev->event_interface; spin_lock_irq(&ev_int->wait.lock); __clear_bit(IIO_BUSY_BIT_POS, &ev_int->flags); @@ -133,6 +136,8 @@ static int iio_event_chrdev_release(struct inode *inode, struct file *filep) kfifo_reset_out(&ev_int->det_events); spin_unlock_irq(&ev_int->wait.lock); + iio_device_put(indio_dev); + return 0; } @@ -158,12 +163,15 @@ int iio_event_getfd(struct iio_dev *indio_dev) return -EBUSY; } spin_unlock_irq(&ev_int->wait.lock); - fd = anon_inode_getfd("iio:event", - &iio_event_chrdev_fileops, ev_int, O_RDONLY); + iio_device_get(indio_dev); + + fd = anon_inode_getfd("iio:event", &iio_event_chrdev_fileops, + indio_dev, O_RDONLY); if (fd < 0) { spin_lock_irq(&ev_int->wait.lock); __clear_bit(IIO_BUSY_BIT_POS, &ev_int->flags); spin_unlock_irq(&ev_int->wait.lock); + iio_device_put(indio_dev); } return fd; } @@ -276,7 +284,7 @@ static int iio_device_add_event_sysfs(struct iio_dev *indio_dev, goto error_ret; } if (chan->modified) - mask = IIO_MOD_EVENT_CODE(chan->type, 0, chan->channel, + mask = IIO_MOD_EVENT_CODE(chan->type, 0, chan->channel2, i/IIO_EV_DIR_MAX, i%IIO_EV_DIR_MAX); else if (chan->differential) diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c index 64ccde3..6d63883 100644 --- a/drivers/iio/temperature/tmp006.c +++ b/drivers/iio/temperature/tmp006.c @@ -255,12 +255,14 @@ static int tmp006_remove(struct i2c_client *client) #ifdef CONFIG_PM_SLEEP static int tmp006_suspend(struct device *dev) { - return tmp006_powerdown(iio_priv(dev_to_iio_dev(dev))); + struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev)); + return tmp006_powerdown(iio_priv(indio_dev)); } static int tmp006_resume(struct device *dev) { - struct tmp006_data *data = iio_priv(dev_to_iio_dev(dev)); + struct tmp006_data *data = iio_priv(i2c_get_clientdata( + to_i2c_client(dev))); return i2c_smbus_write_word_swapped(data->client, TMP006_CONFIG, data->config | TMP006_CONFIG_MOD_MASK); } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index b39f6f0..0f12382 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -498,7 +498,7 @@ struct cached_dev { */ atomic_t has_dirty; - struct ratelimit writeback_rate; + struct bch_ratelimit writeback_rate; struct delayed_work writeback_rate_update; /* @@ -507,10 +507,9 @@ struct cached_dev { */ sector_t last_read; - /* Number of writeback bios in flight */ - atomic_t in_flight; + /* Limit number of writeback bios in flight */ + struct semaphore in_flight; struct closure_with_timer writeback; - struct closure_waitlist writeback_wait; struct keybuf writeback_keys; diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 8010eed..22d1ae7 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -926,28 +926,45 @@ struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search) /* Mergesort */ +static void sort_key_next(struct btree_iter *iter, + struct btree_iter_set *i) +{ + i->k = bkey_next(i->k); + + if (i->k == i->end) + *i = iter->data[--iter->used]; +} + static void btree_sort_fixup(struct btree_iter *iter) { while (iter->used > 1) { struct btree_iter_set *top = iter->data, *i = top + 1; - struct bkey *k; if (iter->used > 2 && btree_iter_cmp(i[0], i[1])) i++; - for (k = i->k; - k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0; - k = bkey_next(k)) - if (top->k > i->k) - __bch_cut_front(top->k, k); - else if (KEY_SIZE(k)) - bch_cut_back(&START_KEY(k), top->k); - - if (top->k < i->k || k == i->k) + if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0) break; - heap_sift(iter, i - top, btree_iter_cmp); + if (!KEY_SIZE(i->k)) { + sort_key_next(iter, i); + heap_sift(iter, i - top, btree_iter_cmp); + continue; + } + + if (top->k > i->k) { + if (bkey_cmp(top->k, i->k) >= 0) + sort_key_next(iter, i); + else + bch_cut_front(top->k, i->k); + + heap_sift(iter, i - top, btree_iter_cmp); + } else { + /* can't happen because of comparison func */ + BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k))); + bch_cut_back(&START_KEY(i->k), top->k); + } } } diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index f9764e6..f42fc7e 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -255,7 +255,7 @@ void bch_btree_node_read(struct btree *b) return; err: - bch_cache_set_error(b->c, "io error reading bucket %lu", + bch_cache_set_error(b->c, "io error reading bucket %zu", PTR_BUCKET_NR(b->c, &b->key, 0)); } @@ -612,7 +612,7 @@ static unsigned long bch_mca_scan(struct shrinker *shrink, return SHRINK_STOP; /* Return -1 if we can't do anything right now */ - if (sc->gfp_mask & __GFP_WAIT) + if (sc->gfp_mask & __GFP_IO) mutex_lock(&c->bucket_lock); else if (!mutex_trylock(&c->bucket_lock)) return -1; diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index ba95ab8..8435f81 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -153,7 +153,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list, bitmap_zero(bitmap, SB_JOURNAL_BUCKETS); pr_debug("%u journal buckets", ca->sb.njournal_buckets); - /* Read journal buckets ordered by golden ratio hash to quickly + /* + * Read journal buckets ordered by golden ratio hash to quickly * find a sequence of buckets with valid journal entries */ for (i = 0; i < ca->sb.njournal_buckets; i++) { @@ -166,18 +167,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list, goto bsearch; } - /* If that fails, check all the buckets we haven't checked + /* + * If that fails, check all the buckets we haven't checked * already */ pr_debug("falling back to linear search"); - for (l = 0; l < ca->sb.njournal_buckets; l++) { - if (test_bit(l, bitmap)) - continue; - + for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets); + l < ca->sb.njournal_buckets; + l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1)) if (read_bucket(l)) goto bsearch; - } + + if (list_empty(list)) + continue; bsearch: /* Binary search */ m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1); @@ -197,10 +200,12 @@ bsearch: r = m; } - /* Read buckets in reverse order until we stop finding more + /* + * Read buckets in reverse order until we stop finding more * journal entries */ - pr_debug("finishing up"); + pr_debug("finishing up: m %u njournal_buckets %u", + m, ca->sb.njournal_buckets); l = m; while (1) { @@ -228,9 +233,10 @@ bsearch: } } - c->journal.seq = list_entry(list->prev, - struct journal_replay, - list)->j.seq; + if (!list_empty(list)) + c->journal.seq = list_entry(list->prev, + struct journal_replay, + list)->j.seq; return 0; #undef read_bucket @@ -428,7 +434,7 @@ static void do_journal_discard(struct cache *ca) return; } - switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) { + switch (atomic_read(&ja->discard_in_flight)) { case DISCARD_IN_FLIGHT: return; @@ -689,6 +695,7 @@ void bch_journal_meta(struct cache_set *c, struct closure *cl) if (cl) BUG_ON(!closure_wait(&w->wait, cl)); + closure_flush(&c->journal.io); __journal_try_write(c, true); } } diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 786a1a4..71eb233 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -997,14 +997,17 @@ static void request_write(struct cached_dev *dc, struct search *s) } else { bch_writeback_add(dc); - if (s->op.flush_journal) { + if (bio->bi_rw & REQ_FLUSH) { /* Also need to send a flush to the backing device */ - s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO, - dc->disk.bio_split); + struct bio *flush = bio_alloc_bioset(0, GFP_NOIO, + dc->disk.bio_split); - bio->bi_size = 0; - bio->bi_vcnt = 0; - closure_bio_submit(bio, cl, s->d); + flush->bi_rw = WRITE_FLUSH; + flush->bi_bdev = bio->bi_bdev; + flush->bi_end_io = request_endio; + flush->bi_private = cl; + + closure_bio_submit(flush, cl, s->d); } else { s->op.cache_bio = bio; } diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 4fe6ab2..924dcfd 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -223,8 +223,13 @@ STORE(__cached_dev) } if (attr == &sysfs_label) { - /* note: endlines are preserved */ - memcpy(dc->sb.label, buf, SB_LABEL_SIZE); + if (size > SB_LABEL_SIZE) + return -EINVAL; + memcpy(dc->sb.label, buf, size); + if (size < SB_LABEL_SIZE) + dc->sb.label[size] = '\0'; + if (size && dc->sb.label[size - 1] == '\n') + dc->sb.label[size - 1] = '\0'; bch_write_bdev_super(dc, NULL); if (dc->disk.c) { memcpy(dc->disk.c->uuids[dc->disk.id].label, diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 98eb811..420dad5 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -190,7 +190,16 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time) stats->last = now ?: 1; } -unsigned bch_next_delay(struct ratelimit *d, uint64_t done) +/** + * bch_next_delay() - increment @d by the amount of work done, and return how + * long to delay until the next time to do some work. + * + * @d - the struct bch_ratelimit to update + * @done - the amount of work done, in arbitrary units + * + * Returns the amount of time to delay by, in jiffies + */ +uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) { uint64_t now = local_clock(); diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 1ae2a73..ea345c6 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -450,17 +450,23 @@ read_attribute(name ## _last_ ## frequency_units) (ewma) >> factor; \ }) -struct ratelimit { +struct bch_ratelimit { + /* Next time we want to do some work, in nanoseconds */ uint64_t next; + + /* + * Rate at which we want to do work, in units per nanosecond + * The units here correspond to the units passed to bch_next_delay() + */ unsigned rate; }; -static inline void ratelimit_reset(struct ratelimit *d) +static inline void bch_ratelimit_reset(struct bch_ratelimit *d) { d->next = local_clock(); } -unsigned bch_next_delay(struct ratelimit *d, uint64_t done); +uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done); #define __DIV_SAFE(n, d, zero) \ ({ \ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 22cbff5..ba3ee48 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -94,11 +94,15 @@ static void update_writeback_rate(struct work_struct *work) static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors) { + uint64_t ret; + if (atomic_read(&dc->disk.detaching) || !dc->writeback_percent) return 0; - return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); + ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); + + return min_t(uint64_t, ret, HZ); } /* Background writeback */ @@ -208,7 +212,7 @@ normal_refill: up_write(&dc->writeback_lock); - ratelimit_reset(&dc->writeback_rate); + bch_ratelimit_reset(&dc->writeback_rate); /* Punt to workqueue only so we don't recurse and blow the stack */ continue_at(cl, read_dirty, dirty_wq); @@ -318,9 +322,7 @@ static void write_dirty_finish(struct closure *cl) } bch_keybuf_del(&dc->writeback_keys, w); - atomic_dec_bug(&dc->in_flight); - - closure_wake_up(&dc->writeback_wait); + up(&dc->in_flight); closure_return_with_destructor(cl, dirty_io_destructor); } @@ -349,7 +351,7 @@ static void write_dirty(struct closure *cl) closure_bio_submit(&io->bio, cl, &io->dc->disk); - continue_at(cl, write_dirty_finish, dirty_wq); + continue_at(cl, write_dirty_finish, system_wq); } static void read_dirty_endio(struct bio *bio, int error) @@ -369,7 +371,7 @@ static void read_dirty_submit(struct closure *cl) closure_bio_submit(&io->bio, cl, &io->dc->disk); - continue_at(cl, write_dirty, dirty_wq); + continue_at(cl, write_dirty, system_wq); } static void read_dirty(struct closure *cl) @@ -394,12 +396,8 @@ static void read_dirty(struct closure *cl) if (delay > 0 && (KEY_START(&w->key) != dc->last_read || - jiffies_to_msecs(delay) > 50)) { - w->private = NULL; - - closure_delay(&dc->writeback, delay); - continue_at(cl, read_dirty, dirty_wq); - } + jiffies_to_msecs(delay) > 50)) + delay = schedule_timeout_uninterruptible(delay); dc->last_read = KEY_OFFSET(&w->key); @@ -424,15 +422,10 @@ static void read_dirty(struct closure *cl) trace_bcache_writeback(&w->key); - closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl); + down(&dc->in_flight); + closure_call(&io->cl, read_dirty_submit, NULL, cl); delay = writeback_delay(dc, KEY_SIZE(&w->key)); - - atomic_inc(&dc->in_flight); - - if (!closure_wait_event(&dc->writeback_wait, cl, - atomic_read(&dc->in_flight) < 64)) - continue_at(cl, read_dirty, dirty_wq); } if (0) { @@ -442,7 +435,11 @@ err: bch_keybuf_del(&dc->writeback_keys, w); } - refill_dirty(cl); + /* + * Wait for outstanding writeback IOs to finish (and keybuf slots to be + * freed) before refilling again + */ + continue_at(cl, refill_dirty, dirty_wq); } /* Init */ @@ -484,6 +481,7 @@ void bch_sectors_dirty_init(struct cached_dev *dc) void bch_cached_dev_writeback_init(struct cached_dev *dc) { + sema_init(&dc->in_flight, 64); closure_init_unlocked(&dc->writeback); init_rwsem(&dc->writeback_lock); @@ -513,7 +511,7 @@ void bch_writeback_exit(void) int __init bch_writeback_init(void) { - dirty_wq = create_singlethread_workqueue("bcache_writeback"); + dirty_wq = create_workqueue("bcache_writeback"); if (!dirty_wq) return -ENOMEM; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index ea49834..2a20986 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -19,8 +19,6 @@ #define DM_MSG_PREFIX "io" #define DM_IO_MAX_REGIONS BITS_PER_LONG -#define MIN_IOS 16 -#define MIN_BIOS 16 struct dm_io_client { mempool_t *pool; @@ -50,16 +48,17 @@ static struct kmem_cache *_dm_io_cache; struct dm_io_client *dm_io_client_create(void) { struct dm_io_client *client; + unsigned min_ios = dm_get_reserved_bio_based_ios(); client = kmalloc(sizeof(*client), GFP_KERNEL); if (!client) return ERR_PTR(-ENOMEM); - client->pool = mempool_create_slab_pool(MIN_IOS, _dm_io_cache); + client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache); if (!client->pool) goto bad; - client->bios = bioset_create(MIN_BIOS, 0); + client->bios = bioset_create(min_ios, 0); if (!client->bios) goto bad; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index b759a12..de570a5 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -7,6 +7,7 @@ #include <linux/device-mapper.h> +#include "dm.h" #include "dm-path-selector.h" #include "dm-uevent.h" @@ -116,8 +117,6 @@ struct dm_mpath_io { typedef int (*action_fn) (struct pgpath *pgpath); -#define MIN_IOS 256 /* Mempool size */ - static struct kmem_cache *_mpio_cache; static struct workqueue_struct *kmultipathd, *kmpath_handlerd; @@ -190,6 +189,7 @@ static void free_priority_group(struct priority_group *pg, static struct multipath *alloc_multipath(struct dm_target *ti) { struct multipath *m; + unsigned min_ios = dm_get_reserved_rq_based_ios(); m = kzalloc(sizeof(*m), GFP_KERNEL); if (m) { @@ -202,7 +202,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti) INIT_WORK(&m->trigger_event, trigger_event); init_waitqueue_head(&m->pg_init_wait); mutex_init(&m->work_mutex); - m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache); + m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache); if (!m->mpio_pool) { kfree(m); return NULL; @@ -1268,6 +1268,7 @@ static int noretry_error(int error) case -EREMOTEIO: case -EILSEQ: case -ENODATA: + case -ENOSPC: return 1; } @@ -1298,8 +1299,17 @@ static int do_end_io(struct multipath *m, struct request *clone, if (!error && !clone->errors) return 0; /* I/O complete */ - if (noretry_error(error)) + if (noretry_error(error)) { + if ((clone->cmd_flags & REQ_WRITE_SAME) && + !clone->q->limits.max_write_same_sectors) { + struct queue_limits *limits; + + /* device doesn't really support WRITE SAME, disable it */ + limits = dm_get_queue_limits(dm_table_get_md(m->ti->table)); + limits->max_write_same_sectors = 0; + } return error; + } if (mpio->pgpath) fail_path(mpio->pgpath); diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 3ac4156..4caa8e6 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw, */ INIT_WORK_ONSTACK(&req.work, do_metadata); queue_work(ps->metadata_wq, &req.work); - flush_work(&req.work); + flush_workqueue(ps->metadata_wq); return req.result; } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index c434e5a..aec57d7 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -725,17 +725,16 @@ static int calc_max_buckets(void) */ static int init_hash_tables(struct dm_snapshot *s) { - sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets; + sector_t hash_size, cow_dev_size, max_buckets; /* * Calculate based on the size of the original volume or * the COW volume... */ cow_dev_size = get_dev_size(s->cow->bdev); - origin_dev_size = get_dev_size(s->origin->bdev); max_buckets = calc_max_buckets(); - hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift; + hash_size = cow_dev_size >> s->store->chunk_shift; hash_size = min(hash_size, max_buckets); if (hash_size < 64) diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 8ae31e8..3d404c1 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -451,19 +451,26 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry, struct dm_stat_percpu *p; /* - * For strict correctness we should use local_irq_disable/enable + * For strict correctness we should use local_irq_save/restore * instead of preempt_disable/enable. * - * This is racy if the driver finishes bios from non-interrupt - * context as well as from interrupt context or from more different - * interrupts. + * preempt_disable/enable is racy if the driver finishes bios + * from non-interrupt context as well as from interrupt context + * or from more different interrupts. * - * However, the race only results in not counting some events, - * so it is acceptable. + * On 64-bit architectures the race only results in not counting some + * events, so it is acceptable. On 32-bit architectures the race could + * cause the counter going off by 2^32, so we need to do proper locking + * there. * * part_stat_lock()/part_stat_unlock() have this race too. */ +#if BITS_PER_LONG == 32 + unsigned long flags; + local_irq_save(flags); +#else preempt_disable(); +#endif p = &s->stat_percpu[smp_processor_id()][entry]; if (!end) { @@ -478,7 +485,11 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry, p->ticks[idx] += duration; } +#if BITS_PER_LONG == 32 + local_irq_restore(flags); +#else preempt_enable(); +#endif } static void __dm_stat_bio(struct dm_stat *s, unsigned long bi_rw, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ed06342..2c0cf51 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2095,6 +2095,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) * them down to the data device. The thin device's discard * processing will cause mappings to be removed from the btree. */ + ti->discard_zeroes_data_unsupported = true; if (pf.discard_enabled && pf.discard_passdown) { ti->num_discard_bios = 1; @@ -2104,7 +2105,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) * thin devices' discard limits consistent). */ ti->discards_supported = true; - ti->discard_zeroes_data_unsupported = true; } ti->private = pt; @@ -2689,8 +2689,16 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) * They get transferred to the live pool in bind_control_target() * called from pool_preresume(). */ - if (!pt->adjusted_pf.discard_enabled) + if (!pt->adjusted_pf.discard_enabled) { + /* + * Must explicitly disallow stacking discard limits otherwise the + * block layer will stack them if pool's data device has support. + * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the + * user to see that, so make sure to set all discard limits to 0. + */ + limits->discard_granularity = 0; return; + } disable_passdown_if_not_supported(pt); @@ -2826,10 +2834,10 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->per_bio_data_size = sizeof(struct dm_thin_endio_hook); /* In case the pool supports discards, pass them on. */ + ti->discard_zeroes_data_unsupported = true; if (tc->pool->pf.discard_enabled) { ti->discards_supported = true; ti->num_discard_bios = 1; - ti->discard_zeroes_data_unsupported = true; /* Discard bios must be split on a block boundary */ ti->split_discard_bios = true; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 6a5e9ed..b3e26c7 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -211,10 +211,55 @@ struct dm_md_mempools { struct bio_set *bs; }; -#define MIN_IOS 256 +#define RESERVED_BIO_BASED_IOS 16 +#define RESERVED_REQUEST_BASED_IOS 256 +#define RESERVED_MAX_IOS 1024 static struct kmem_cache *_io_cache; static struct kmem_cache *_rq_tio_cache; +/* + * Bio-based DM's mempools' reserved IOs set by the user. + */ +static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS; + +/* + * Request-based DM's mempools' reserved IOs set by the user. + */ +static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; + +static unsigned __dm_get_reserved_ios(unsigned *reserved_ios, + unsigned def, unsigned max) +{ + unsigned ios = ACCESS_ONCE(*reserved_ios); + unsigned modified_ios = 0; + + if (!ios) + modified_ios = def; + else if (ios > max) + modified_ios = max; + + if (modified_ios) { + (void)cmpxchg(reserved_ios, ios, modified_ios); + ios = modified_ios; + } + + return ios; +} + +unsigned dm_get_reserved_bio_based_ios(void) +{ + return __dm_get_reserved_ios(&reserved_bio_based_ios, + RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS); +} +EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios); + +unsigned dm_get_reserved_rq_based_ios(void) +{ + return __dm_get_reserved_ios(&reserved_rq_based_ios, + RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS); +} +EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios); + static int __init local_init(void) { int r = -ENOMEM; @@ -2278,6 +2323,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md) } /* + * The queue_limits are only valid as long as you have a reference + * count on 'md'. + */ +struct queue_limits *dm_get_queue_limits(struct mapped_device *md) +{ + BUG_ON(!atomic_read(&md->holders)); + return &md->queue->limits; +} +EXPORT_SYMBOL_GPL(dm_get_queue_limits); + +/* * Fully initialize a request-based queue (->elevator, ->request_fn, etc). */ static int dm_init_request_based_queue(struct mapped_device *md) @@ -2862,18 +2918,18 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u if (type == DM_TYPE_BIO_BASED) { cachep = _io_cache; - pool_size = 16; + pool_size = dm_get_reserved_bio_based_ios(); front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone); } else if (type == DM_TYPE_REQUEST_BASED) { cachep = _rq_tio_cache; - pool_size = MIN_IOS; + pool_size = dm_get_reserved_rq_based_ios(); front_pad = offsetof(struct dm_rq_clone_bio_info, clone); /* per_bio_data_size is not used. See __bind_mempools(). */ WARN_ON(per_bio_data_size != 0); } else goto out; - pools->io_pool = mempool_create_slab_pool(MIN_IOS, cachep); + pools->io_pool = mempool_create_slab_pool(pool_size, cachep); if (!pools->io_pool) goto out; @@ -2924,6 +2980,13 @@ module_exit(dm_exit); module_param(major, uint, 0); MODULE_PARM_DESC(major, "The major number of the device mapper"); + +module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools"); + +module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools"); + MODULE_DESCRIPTION(DM_NAME " driver"); MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 5e604cc..1d1ad7b 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -184,6 +184,9 @@ void dm_free_md_mempools(struct dm_md_mempools *pools); /* * Helpers that are used by DM core */ +unsigned dm_get_reserved_bio_based_ios(void); +unsigned dm_get_reserved_rq_based_ios(void); + static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen) { return !maxlen || strlen(result) + 1 >= maxlen; diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c index d0fdc13..f6ff711 100644 --- a/drivers/misc/mei/amthif.c +++ b/drivers/misc/mei/amthif.c @@ -57,6 +57,7 @@ void mei_amthif_reset_params(struct mei_device *dev) dev->iamthif_ioctl = false; dev->iamthif_state = MEI_IAMTHIF_IDLE; dev->iamthif_timer = 0; + dev->iamthif_stall_timer = 0; } /** diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 6d0282c..cd2033c 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -297,10 +297,13 @@ int __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length) if (cl->reading_state != MEI_READ_COMPLETE && !waitqueue_active(&cl->rx_wait)) { + mutex_unlock(&dev->device_lock); if (wait_event_interruptible(cl->rx_wait, - (MEI_READ_COMPLETE == cl->reading_state))) { + cl->reading_state == MEI_READ_COMPLETE || + mei_cl_is_transitioning(cl))) { + if (signal_pending(current)) return -EINTR; return -ERESTARTSYS; diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 9eb031e..892cc42 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -90,6 +90,12 @@ static inline bool mei_cl_is_connected(struct mei_cl *cl) cl->dev->dev_state == MEI_DEV_ENABLED && cl->state == MEI_FILE_CONNECTED); } +static inline bool mei_cl_is_transitioning(struct mei_cl *cl) +{ + return (MEI_FILE_INITIALIZING == cl->state || + MEI_FILE_DISCONNECTED == cl->state || + MEI_FILE_DISCONNECTING == cl->state); +} bool mei_cl_is_other_connecting(struct mei_cl *cl); int mei_cl_disconnect(struct mei_cl *cl); diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 6127ab6..0a044832 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -35,11 +35,15 @@ static void mei_hbm_me_cl_allocate(struct mei_device *dev) struct mei_me_client *clients; int b; + dev->me_clients_num = 0; + dev->me_client_presentation_num = 0; + dev->me_client_index = 0; + /* count how many ME clients we have */ for_each_set_bit(b, dev->me_clients_map, MEI_CLIENTS_MAX) dev->me_clients_num++; - if (dev->me_clients_num <= 0) + if (dev->me_clients_num == 0) return; kfree(dev->me_clients); @@ -221,7 +225,7 @@ static int mei_hbm_prop_req(struct mei_device *dev) struct hbm_props_request *prop_req; const size_t len = sizeof(struct hbm_props_request); unsigned long next_client_index; - u8 client_num; + unsigned long client_num; client_num = dev->me_client_presentation_num; @@ -677,8 +681,6 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) if (dev->dev_state == MEI_DEV_INIT_CLIENTS && dev->hbm_state == MEI_HBM_ENUM_CLIENTS) { dev->init_clients_timer = 0; - dev->me_client_presentation_num = 0; - dev->me_client_index = 0; mei_hbm_me_cl_allocate(dev); dev->hbm_state = MEI_HBM_CLIENT_PROPERTIES; diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index 92c7311..6197018 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -175,6 +175,9 @@ void mei_reset(struct mei_device *dev, int interrupts_enabled) memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg)); } + /* we're already in reset, cancel the init timer */ + dev->init_clients_timer = 0; + dev->me_clients_num = 0; dev->rd_msg_hdr = 0; dev->wd_pending = false; diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 173ff09..cabeddd 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -249,19 +249,16 @@ static ssize_t mei_read(struct file *file, char __user *ubuf, mutex_unlock(&dev->device_lock); if (wait_event_interruptible(cl->rx_wait, - (MEI_READ_COMPLETE == cl->reading_state || - MEI_FILE_INITIALIZING == cl->state || - MEI_FILE_DISCONNECTED == cl->state || - MEI_FILE_DISCONNECTING == cl->state))) { + MEI_READ_COMPLETE == cl->reading_state || + mei_cl_is_transitioning(cl))) { + if (signal_pending(current)) return -EINTR; return -ERESTARTSYS; } mutex_lock(&dev->device_lock); - if (MEI_FILE_INITIALIZING == cl->state || - MEI_FILE_DISCONNECTED == cl->state || - MEI_FILE_DISCONNECTING == cl->state) { + if (mei_cl_is_transitioning(cl)) { rets = -EBUSY; goto out; } diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 7b918b2..456b322 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -396,9 +396,9 @@ struct mei_device { struct mei_me_client *me_clients; /* Note: memory has to be allocated */ DECLARE_BITMAP(me_clients_map, MEI_CLIENTS_MAX); DECLARE_BITMAP(host_clients_map, MEI_CLIENTS_MAX); - u8 me_clients_num; - u8 me_client_presentation_num; - u8 me_client_index; + unsigned long me_clients_num; + unsigned long me_client_presentation_num; + unsigned long me_client_index; struct mei_cl wd_cl; enum mei_wd_states wd_state; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e8ccf6c..bdd64b1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1155,8 +1155,14 @@ static void pci_enable_bridge(struct pci_dev *dev) pci_enable_bridge(dev->bus->self); - if (pci_is_enabled(dev)) + if (pci_is_enabled(dev)) { + if (!dev->is_busmaster) { + dev_warn(&dev->dev, "driver skip pci_set_master, fix it!\n"); + pci_set_master(dev); + } return; + } + retval = pci_enable_device(dev); if (retval) dev_err(&dev->dev, "Error enabling bridge (%d), continuing\n", diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index 1a78163..b9f2653 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -709,7 +709,7 @@ static struct da9063_regulators_pdata *da9063_parse_regulators_dt( struct of_regulator_match **da9063_reg_matches) { da9063_reg_matches = NULL; - return PTR_ERR(-ENODEV); + return ERR_PTR(-ENODEV); } #endif diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c index 488dfe7..7e2b165 100644 --- a/drivers/regulator/palmas-regulator.c +++ b/drivers/regulator/palmas-regulator.c @@ -201,13 +201,7 @@ static unsigned int palmas_smps_ramp_delay[4] = {0, 10000, 5000, 2500}; #define SMPS_CTRL_MODE_ECO 0x02 #define SMPS_CTRL_MODE_PWM 0x03 -/* These values are derived from the data sheet. And are the number of steps - * where there is a voltage change, the ranges at beginning and end of register - * max/min values where there are no change are ommitted. - * - * So they are basically (maxV-minV)/stepV - */ -#define PALMAS_SMPS_NUM_VOLTAGES 117 +#define PALMAS_SMPS_NUM_VOLTAGES 122 #define PALMAS_SMPS10_NUM_VOLTAGES 2 #define PALMAS_LDO_NUM_VOLTAGES 50 @@ -979,6 +973,7 @@ static int palmas_regulators_probe(struct platform_device *pdev) pmic->desc[id].min_uV = 900000; pmic->desc[id].uV_step = 50000; pmic->desc[id].linear_min_sel = 1; + pmic->desc[id].enable_time = 500; pmic->desc[id].vsel_reg = PALMAS_BASE_TO_REG(PALMAS_LDO_BASE, palmas_regs_info[id].vsel_addr); @@ -997,6 +992,11 @@ static int palmas_regulators_probe(struct platform_device *pdev) pmic->desc[id].min_uV = 450000; pmic->desc[id].uV_step = 25000; } + + /* LOD6 in vibrator mode will have enable time 2000us */ + if (pdata && pdata->ldo6_vibrator && + (id == PALMAS_REG_LDO6)) + pmic->desc[id].enable_time = 2000; } else { pmic->desc[id].n_voltages = 1; pmic->desc[id].ops = &palmas_ops_extreg; diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c index d8e3e12..20c271d 100644 --- a/drivers/regulator/ti-abb-regulator.c +++ b/drivers/regulator/ti-abb-regulator.c @@ -279,8 +279,12 @@ static int ti_abb_set_opp(struct regulator_dev *rdev, struct ti_abb *abb, ti_abb_rmw(regs->opp_sel_mask, info->opp_sel, regs->control_reg, abb->base); - /* program LDO VBB vset override if needed */ - if (abb->ldo_base) + /* + * program LDO VBB vset override if needed for !bypass mode + * XXX: Do not switch sequence - for !bypass, LDO override reset *must* + * be performed *before* switch to bias mode else VBB glitches. + */ + if (abb->ldo_base && info->opp_sel != TI_ABB_NOMINAL_OPP) ti_abb_program_ldovbb(dev, abb, info); /* Initiate ABB ldo change */ @@ -295,6 +299,14 @@ static int ti_abb_set_opp(struct regulator_dev *rdev, struct ti_abb *abb, if (ret) goto out; + /* + * Reset LDO VBB vset override bypass mode + * XXX: Do not switch sequence - for bypass, LDO override reset *must* + * be performed *after* switch to bypass else VBB glitches. + */ + if (abb->ldo_base && info->opp_sel == TI_ABB_NOMINAL_OPP) + ti_abb_program_ldovbb(dev, abb, info); + out: return ret; } diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c index 1432b26..2205fbc 100644 --- a/drivers/regulator/wm831x-ldo.c +++ b/drivers/regulator/wm831x-ldo.c @@ -63,7 +63,7 @@ static irqreturn_t wm831x_ldo_uv_irq(int irq, void *data) */ static const struct regulator_linear_range wm831x_gp_ldo_ranges[] = { - { .min_uV = 900000, .max_uV = 1650000, .min_sel = 0, .max_sel = 14, + { .min_uV = 900000, .max_uV = 1600000, .min_sel = 0, .max_sel = 14, .uV_step = 50000 }, { .min_uV = 1700000, .max_uV = 3300000, .min_sel = 15, .max_sel = 31, .uV_step = 100000 }, @@ -332,7 +332,7 @@ static struct platform_driver wm831x_gp_ldo_driver = { */ static const struct regulator_linear_range wm831x_aldo_ranges[] = { - { .min_uV = 1000000, .max_uV = 1650000, .min_sel = 0, .max_sel = 12, + { .min_uV = 1000000, .max_uV = 1600000, .min_sel = 0, .max_sel = 12, .uV_step = 50000 }, { .min_uV = 1700000, .max_uV = 3500000, .min_sel = 13, .max_sel = 31, .uV_step = 100000 }, diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c index 835b5f0..61ca929 100644 --- a/drivers/regulator/wm8350-regulator.c +++ b/drivers/regulator/wm8350-regulator.c @@ -543,7 +543,7 @@ static int wm8350_dcdc_set_suspend_mode(struct regulator_dev *rdev, } static const struct regulator_linear_range wm8350_ldo_ranges[] = { - { .min_uV = 900000, .max_uV = 1750000, .min_sel = 0, .max_sel = 15, + { .min_uV = 900000, .max_uV = 1650000, .min_sel = 0, .max_sel = 15, .uV_step = 50000 }, { .min_uV = 1800000, .max_uV = 3300000, .min_sel = 16, .max_sel = 31, .uV_step = 100000 }, diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig index a84aab4..f73287e 100644 --- a/drivers/staging/comedi/Kconfig +++ b/drivers/staging/comedi/Kconfig @@ -96,6 +96,15 @@ config COMEDI_SKEL To compile this driver as a module, choose M here: the module will be called skel. +config COMEDI_SSV_DNP + tristate "SSV Embedded Systems DIL/Net-PC support" + depends on X86_32 || COMPILE_TEST + ---help--- + Enable support for SSV Embedded Systems DIL/Net-PC + + To compile this driver as a module, choose M here: the module will be + called ssv_dnp. + endif # COMEDI_MISC_DRIVERS menuconfig COMEDI_ISA_DRIVERS @@ -386,6 +395,14 @@ config COMEDI_DMM32AT To compile this driver as a module, choose M here: the module will be called dmm32at. +config COMEDI_UNIOXX5 + tristate "Fastwel UNIOxx-5 analog and digital io board support" + ---help--- + Enable support for Fastwel UNIOxx-5 (analog and digital i/o) boards + + To compile this driver as a module, choose M here: the module will be + called unioxx5. + config COMEDI_FL512 tristate "FL512 ISA card support" ---help--- @@ -855,14 +872,6 @@ config COMEDI_DYNA_PCI10XX To compile this driver as a module, choose M here: the module will be called dyna_pci10xx. -config COMEDI_UNIOXX5 - tristate "Fastwel UNIOxx-5 analog and digital io board support" - ---help--- - Enable support for Fastwel UNIOxx-5 (analog and digital i/o) boards - - To compile this driver as a module, choose M here: the module will be - called unioxx5. - config COMEDI_GSC_HPDI tristate "General Standards PCI-HPDI32 / PMC-HPDI32 support" select COMEDI_FC @@ -1085,14 +1094,6 @@ config COMEDI_S626 To compile this driver as a module, choose M here: the module will be called s626. -config COMEDI_SSV_DNP - tristate "SSV Embedded Systems DIL/Net-PC support" - ---help--- - Enable support for SSV Embedded Systems DIL/Net-PC - - To compile this driver as a module, choose M here: the module will be - called ssv_dnp. - config COMEDI_MITE depends on HAS_DMA tristate diff --git a/drivers/staging/dgap/dgap_driver.c b/drivers/staging/dgap/dgap_driver.c index 724a685..40ef785 100644 --- a/drivers/staging/dgap/dgap_driver.c +++ b/drivers/staging/dgap/dgap_driver.c @@ -474,7 +474,7 @@ static void dgap_cleanup_board(struct board_t *brd) DGAP_LOCK(dgap_global_lock, flags); brd->msgbuf = NULL; - printk(brd->msgbuf_head); + printk("%s", brd->msgbuf_head); kfree(brd->msgbuf_head); brd->msgbuf_head = NULL; DGAP_UNLOCK(dgap_global_lock, flags); @@ -628,7 +628,7 @@ static int dgap_found_board(struct pci_dev *pdev, int id) DPR_INIT(("dgap_scan(%d) - printing out the msgbuf\n", i)); DGAP_LOCK(dgap_global_lock, flags); brd->msgbuf = NULL; - printk(brd->msgbuf_head); + printk("%s", brd->msgbuf_head); kfree(brd->msgbuf_head); brd->msgbuf_head = NULL; DGAP_UNLOCK(dgap_global_lock, flags); @@ -955,25 +955,28 @@ static void dgap_mbuf(struct board_t *brd, const char *fmt, ...) { char buf[1024]; int i; unsigned long flags; + size_t length; DGAP_LOCK(dgap_global_lock, flags); /* Format buf using fmt and arguments contained in ap. */ va_start(ap, fmt); - i = vsprintf(buf, fmt, ap); + i = vsnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); DPR((buf)); if (!brd || !brd->msgbuf) { - printk(buf); + printk("%s", buf); DGAP_UNLOCK(dgap_global_lock, flags); return; } - memcpy(brd->msgbuf, buf, strlen(buf)); - brd->msgbuf += strlen(buf); - *brd->msgbuf = 0; + length = strlen(buf) + 1; + if (brd->msgbuf - brd->msgbuf_head < length) + length = brd->msgbuf - brd->msgbuf_head; + memcpy(brd->msgbuf, buf, length); + brd->msgbuf += length; DGAP_UNLOCK(dgap_global_lock, flags); } diff --git a/drivers/staging/dgnc/dgnc_driver.c b/drivers/staging/dgnc/dgnc_driver.c index f8c1e22..71d2b83 100644 --- a/drivers/staging/dgnc/dgnc_driver.c +++ b/drivers/staging/dgnc/dgnc_driver.c @@ -454,7 +454,7 @@ static void dgnc_cleanup_board(struct board_t *brd) DGNC_LOCK(dgnc_global_lock, flags); brd->msgbuf = NULL; - printk(brd->msgbuf_head); + printk("%s", brd->msgbuf_head); kfree(brd->msgbuf_head); brd->msgbuf_head = NULL; DGNC_UNLOCK(dgnc_global_lock, flags); @@ -710,7 +710,7 @@ static int dgnc_found_board(struct pci_dev *pdev, int id) DPR_INIT(("dgnc_scan(%d) - printing out the msgbuf\n", i)); DGNC_LOCK(dgnc_global_lock, flags); brd->msgbuf = NULL; - printk(brd->msgbuf_head); + printk("%s", brd->msgbuf_head); kfree(brd->msgbuf_head); brd->msgbuf_head = NULL; DGNC_UNLOCK(dgnc_global_lock, flags); diff --git a/drivers/staging/iio/Kconfig b/drivers/staging/iio/Kconfig index db4d6dc..b36feb0 100644 --- a/drivers/staging/iio/Kconfig +++ b/drivers/staging/iio/Kconfig @@ -37,7 +37,7 @@ config IIO_SIMPLE_DUMMY_EVENTS config IIO_SIMPLE_DUMMY_BUFFER boolean "Buffered capture support" - depends on IIO_KFIFO_BUF + select IIO_KFIFO_BUF help Add buffered data capture to the simple dummy driver. diff --git a/drivers/staging/iio/light/isl29018.c b/drivers/staging/iio/light/isl29018.c index 351936c..e4998e4 100644 --- a/drivers/staging/iio/light/isl29018.c +++ b/drivers/staging/iio/light/isl29018.c @@ -563,6 +563,7 @@ static int isl29018_probe(struct i2c_client *client, mutex_init(&chip->lock); chip->lux_scale = 1; + chip->lux_uscale = 0; chip->range = 1000; chip->adc_bit = 16; chip->suspended = false; diff --git a/drivers/staging/iio/magnetometer/hmc5843.c b/drivers/staging/iio/magnetometer/hmc5843.c index d2748c3..c3f3f53 100644 --- a/drivers/staging/iio/magnetometer/hmc5843.c +++ b/drivers/staging/iio/magnetometer/hmc5843.c @@ -229,7 +229,7 @@ static int hmc5843_read_measurement(struct iio_dev *indio_dev, if (result < 0) return -EINVAL; - *val = result; + *val = sign_extend32(result, 15); return IIO_VAL_INT; } diff --git a/drivers/staging/iio/meter/ade7854-spi.c b/drivers/staging/iio/meter/ade7854-spi.c index a802cf2..4c6d204 100644 --- a/drivers/staging/iio/meter/ade7854-spi.c +++ b/drivers/staging/iio/meter/ade7854-spi.c @@ -299,7 +299,7 @@ static int ade7854_spi_probe(struct spi_device *spi) if (ret) iio_device_free(indio_dev); - return 0; + return ret; } static int ade7854_spi_remove(struct spi_device *spi) diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c index 47c58884..a2e52a0 100644 --- a/drivers/staging/imx-drm/imx-drm-core.c +++ b/drivers/staging/imx-drm/imx-drm-core.c @@ -41,7 +41,6 @@ struct imx_drm_device { struct list_head encoder_list; struct list_head connector_list; struct mutex mutex; - int references; int pipes; struct drm_fbdev_cma *fbhelper; }; @@ -241,8 +240,6 @@ struct drm_device *imx_drm_device_get(void) } } - imxdrm->references++; - return imxdrm->drm; unwind_crtc: @@ -280,8 +277,6 @@ void imx_drm_device_put(void) list_for_each_entry(enc, &imxdrm->encoder_list, list) module_put(enc->owner); - imxdrm->references--; - mutex_unlock(&imxdrm->mutex); } EXPORT_SYMBOL_GPL(imx_drm_device_put); @@ -485,7 +480,7 @@ int imx_drm_add_crtc(struct drm_crtc *crtc, mutex_lock(&imxdrm->mutex); - if (imxdrm->references) { + if (imxdrm->drm->open_count) { ret = -EBUSY; goto err_busy; } @@ -564,7 +559,7 @@ int imx_drm_add_encoder(struct drm_encoder *encoder, mutex_lock(&imxdrm->mutex); - if (imxdrm->references) { + if (imxdrm->drm->open_count) { ret = -EBUSY; goto err_busy; } @@ -709,7 +704,7 @@ int imx_drm_add_connector(struct drm_connector *connector, mutex_lock(&imxdrm->mutex); - if (imxdrm->references) { + if (imxdrm->drm->open_count) { ret = -EBUSY; goto err_busy; } diff --git a/drivers/staging/line6/toneport.c b/drivers/staging/line6/toneport.c index 2f44d56..776d363 100644 --- a/drivers/staging/line6/toneport.c +++ b/drivers/staging/line6/toneport.c @@ -244,13 +244,17 @@ static int snd_toneport_source_put(struct snd_kcontrol *kcontrol, struct snd_line6_pcm *line6pcm = snd_kcontrol_chip(kcontrol); struct usb_line6_toneport *toneport = (struct usb_line6_toneport *)line6pcm->line6; + unsigned int source; - if (ucontrol->value.enumerated.item[0] == toneport->source) + source = ucontrol->value.enumerated.item[0]; + if (source >= ARRAY_SIZE(toneport_source_info)) + return -EINVAL; + if (source == toneport->source) return 0; - toneport->source = ucontrol->value.enumerated.item[0]; + toneport->source = source; toneport_send_cmd(toneport->line6.usbdev, - toneport_source_info[toneport->source].code, 0x0000); + toneport_source_info[source].code, 0x0000); return 1; } diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c index 086ca3d..26b49a2 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -1802,7 +1802,7 @@ kiblnd_recv (lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg, int delayed, int kiblnd_thread_start(int (*fn)(void *arg), void *arg, char *name) { - struct task_struct *task = kthread_run(fn, arg, name); + struct task_struct *task = kthread_run(fn, arg, "%s", name); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c index 2c581b7..68a4f52 100644 --- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c @@ -1005,7 +1005,7 @@ ksocknal_send(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg) int ksocknal_thread_start(int (*fn)(void *arg), void *arg, char *name) { - struct task_struct *task = kthread_run(fn, arg, name); + struct task_struct *task = kthread_run(fn, arg, "%s", name); if (IS_ERR(task)) return PTR_ERR(task); diff --git a/drivers/staging/lustre/lustre/Kconfig b/drivers/staging/lustre/lustre/Kconfig index 4e898e4..2156a44 100644 --- a/drivers/staging/lustre/lustre/Kconfig +++ b/drivers/staging/lustre/lustre/Kconfig @@ -1,6 +1,6 @@ config LUSTRE_FS tristate "Lustre file system client support" - depends on INET && m + depends on INET && m && !MIPS && !XTENSA && !SUPERH select LNET select CRYPTO select CRYPTO_CRC32 @@ -52,7 +52,7 @@ config LUSTRE_DEBUG_EXPENSIVE_CHECK config LUSTRE_TRANSLATE_ERRNOS bool depends on LUSTRE_FS && !X86 - default true + default y config LUSTRE_LLITE_LLOOP bool "Lustre virtual block device" diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c b/drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c index 3916bda..a100a0b 100644 --- a/drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c +++ b/drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c @@ -800,9 +800,9 @@ static int ldlm_bl_thread_start(struct ldlm_bl_pool *blp) init_completion(&bltd.bltd_comp); bltd.bltd_num = atomic_read(&blp->blp_num_threads); - snprintf(bltd.bltd_name, sizeof(bltd.bltd_name) - 1, + snprintf(bltd.bltd_name, sizeof(bltd.bltd_name), "ldlm_bl_%02d", bltd.bltd_num); - task = kthread_run(ldlm_bl_thread_main, &bltd, bltd.bltd_name); + task = kthread_run(ldlm_bl_thread_main, &bltd, "%s", bltd.bltd_name); if (IS_ERR(task)) { CERROR("cannot start LDLM thread ldlm_bl_%02d: rc %ld\n", atomic_read(&blp->blp_num_threads), PTR_ERR(task)); diff --git a/drivers/staging/lustre/lustre/libcfs/workitem.c b/drivers/staging/lustre/lustre/libcfs/workitem.c index 462172d..1a55c81 100644 --- a/drivers/staging/lustre/lustre/libcfs/workitem.c +++ b/drivers/staging/lustre/lustre/libcfs/workitem.c @@ -397,7 +397,7 @@ cfs_wi_sched_create(char *name, struct cfs_cpt_table *cptab, sched->ws_name, sched->ws_nthreads); } - task = kthread_run(cfs_wi_scheduler, sched, name); + task = kthread_run(cfs_wi_scheduler, sched, "%s", name); if (!IS_ERR(task)) { nthrs--; continue; diff --git a/drivers/staging/lustre/lustre/obdecho/echo_client.c b/drivers/staging/lustre/lustre/obdecho/echo_client.c index 2644edf..c8b4344 100644 --- a/drivers/staging/lustre/lustre/obdecho/echo_client.c +++ b/drivers/staging/lustre/lustre/obdecho/echo_client.c @@ -1387,7 +1387,7 @@ echo_copyout_lsm (struct lov_stripe_md *lsm, void *_ulsm, int ulsm_nob) if (nob > ulsm_nob) return (-EINVAL); - if (copy_to_user (ulsm, lsm, sizeof(ulsm))) + if (copy_to_user (ulsm, lsm, sizeof(*ulsm))) return (-EFAULT); for (i = 0; i < lsm->lsm_stripe_count; i++) { diff --git a/drivers/staging/lustre/lustre/ptlrpc/pinger.c b/drivers/staging/lustre/lustre/ptlrpc/pinger.c index 227a0ae..5dec771 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/pinger.c +++ b/drivers/staging/lustre/lustre/ptlrpc/pinger.c @@ -383,8 +383,8 @@ int ptlrpc_start_pinger(void) /* CLONE_VM and CLONE_FILES just avoid a needless copy, because we * just drop the VM and FILES in cfs_daemonize_ctxt() right away. */ - rc = PTR_ERR(kthread_run(ptlrpc_pinger_main, - &pinger_thread, pinger_thread.t_name)); + rc = PTR_ERR(kthread_run(ptlrpc_pinger_main, &pinger_thread, + "%s", pinger_thread.t_name)); if (IS_ERR_VALUE(rc)) { CERROR("cannot start thread: %d\n", rc); return rc; diff --git a/drivers/staging/lustre/lustre/ptlrpc/ptlrpcd.c b/drivers/staging/lustre/lustre/ptlrpc/ptlrpcd.c index fbdeff6..89c9be9 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/ptlrpcd.c +++ b/drivers/staging/lustre/lustre/ptlrpc/ptlrpcd.c @@ -615,7 +615,7 @@ int ptlrpcd_start(int index, int max, const char *name, struct ptlrpcd_ctl *pc) init_completion(&pc->pc_starting); init_completion(&pc->pc_finishing); spin_lock_init(&pc->pc_lock); - strncpy(pc->pc_name, name, sizeof(pc->pc_name) - 1); + strlcpy(pc->pc_name, name, sizeof(pc->pc_name)); pc->pc_set = ptlrpc_prep_set(); if (pc->pc_set == NULL) GOTO(out, rc = -ENOMEM); @@ -638,7 +638,7 @@ int ptlrpcd_start(int index, int max, const char *name, struct ptlrpcd_ctl *pc) GOTO(out, rc); } - task = kthread_run(ptlrpcd, pc, pc->pc_name); + task = kthread_run(ptlrpcd, pc, "%s", pc->pc_name); if (IS_ERR(task)) GOTO(out, rc = PTR_ERR(task)); @@ -745,7 +745,7 @@ static int ptlrpcd_init(void) if (ptlrpcds == NULL) GOTO(out, rc = -ENOMEM); - snprintf(name, 15, "ptlrpcd_rcv"); + snprintf(name, sizeof(name), "ptlrpcd_rcv"); set_bit(LIOD_RECOVERY, &ptlrpcds->pd_thread_rcv.pc_flags); rc = ptlrpcd_start(-1, nthreads, name, &ptlrpcds->pd_thread_rcv); if (rc < 0) @@ -764,7 +764,7 @@ static int ptlrpcd_init(void) * unnecessary dependency. But how to distribute async RPCs load * among all the ptlrpc daemons becomes another trouble. */ for (i = 0; i < nthreads; i++) { - snprintf(name, 15, "ptlrpcd_%d", i); + snprintf(name, sizeof(name), "ptlrpcd_%d", i); rc = ptlrpcd_start(i, nthreads, name, &ptlrpcds->pd_threads[i]); if (rc < 0) GOTO(out, rc); diff --git a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c index e90c8fb..6547f46 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c +++ b/drivers/staging/lustre/lustre/ptlrpc/sec_bulk.c @@ -59,8 +59,8 @@ ****************************************/ -#define PTRS_PER_PAGE (PAGE_CACHE_SIZE / sizeof(void *)) -#define PAGES_PER_POOL (PTRS_PER_PAGE) +#define POINTERS_PER_PAGE (PAGE_CACHE_SIZE / sizeof(void *)) +#define PAGES_PER_POOL (POINTERS_PER_PAGE) #define IDLE_IDX_MAX (100) #define IDLE_IDX_WEIGHT (3) diff --git a/drivers/staging/lustre/lustre/ptlrpc/service.c b/drivers/staging/lustre/lustre/ptlrpc/service.c index ac8b5fd..acf75f3 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/service.c +++ b/drivers/staging/lustre/lustre/ptlrpc/service.c @@ -2718,15 +2718,15 @@ int ptlrpc_start_thread(struct ptlrpc_service_part *svcpt, int wait) spin_unlock(&svcpt->scp_lock); if (svcpt->scp_cpt >= 0) { - snprintf(thread->t_name, PTLRPC_THR_NAME_LEN, "%s%02d_%03d", + snprintf(thread->t_name, sizeof(thread->t_name), "%s%02d_%03d", svc->srv_thread_name, svcpt->scp_cpt, thread->t_id); } else { - snprintf(thread->t_name, PTLRPC_THR_NAME_LEN, "%s_%04d", + snprintf(thread->t_name, sizeof(thread->t_name), "%s_%04d", svc->srv_thread_name, thread->t_id); } CDEBUG(D_RPCTRACE, "starting thread '%s'\n", thread->t_name); - rc = PTR_ERR(kthread_run(ptlrpc_main, thread, thread->t_name)); + rc = PTR_ERR(kthread_run(ptlrpc_main, thread, "%s", thread->t_name)); if (IS_ERR_VALUE(rc)) { CERROR("cannot start thread '%s': rc %d\n", thread->t_name, rc); diff --git a/drivers/staging/octeon-usb/cvmx-usb.c b/drivers/staging/octeon-usb/cvmx-usb.c index d7b3c82..45dfe94 100644 --- a/drivers/staging/octeon-usb/cvmx-usb.c +++ b/drivers/staging/octeon-usb/cvmx-usb.c @@ -604,7 +604,7 @@ int cvmx_usb_initialize(struct cvmx_usb_state *state, int usb_port_number, } } - memset(usb, 0, sizeof(usb)); + memset(usb, 0, sizeof(*usb)); usb->init_flags = flags; /* Initialize the USB state structure */ diff --git a/drivers/staging/rtl8188eu/core/rtw_ieee80211.c b/drivers/staging/rtl8188eu/core/rtw_ieee80211.c index 3605c5d..6fc7742 100644 --- a/drivers/staging/rtl8188eu/core/rtw_ieee80211.c +++ b/drivers/staging/rtl8188eu/core/rtw_ieee80211.c @@ -157,8 +157,8 @@ _func_enter_; *frlen = *frlen + (len + 2); - return pbuf + len + 2; _func_exit_; + return pbuf + len + 2; } inline u8 *rtw_set_ie_ch_switch (u8 *buf, u32 *buf_len, u8 ch_switch_mode, diff --git a/drivers/staging/rtl8188eu/core/rtw_mlme_ext.c b/drivers/staging/rtl8188eu/core/rtw_mlme_ext.c index 8b2ba26..4b2eb8e 100644 --- a/drivers/staging/rtl8188eu/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8188eu/core/rtw_mlme_ext.c @@ -1827,13 +1827,13 @@ unsigned int OnAction_back(struct adapter *padapter, union recv_frame *precv_fra #ifdef CONFIG_88EU_P2P -static int get_reg_classes_full_count(struct p2p_channels channel_list) +static int get_reg_classes_full_count(struct p2p_channels *channel_list) { int cnt = 0; int i; - for (i = 0; i < channel_list.reg_classes; i++) { - cnt += channel_list.reg_class[i].channels; + for (i = 0; i < channel_list->reg_classes; i++) { + cnt += channel_list->reg_class[i].channels; } return cnt; @@ -2065,7 +2065,7 @@ void issue_p2p_GO_request(struct adapter *padapter, u8 *raddr) /* + number of channels in all classes */ len_channellist_attr = 3 + (1 + 1) * (u16)(pmlmeext->channel_list.reg_classes) - + get_reg_classes_full_count(pmlmeext->channel_list); + + get_reg_classes_full_count(&pmlmeext->channel_list); *(__le16 *)(p2pie + p2pielen) = cpu_to_le16(len_channellist_attr); p2pielen += 2; @@ -2437,7 +2437,7 @@ static void issue_p2p_GO_response(struct adapter *padapter, u8 *raddr, u8 *frame /* + number of channels in all classes */ len_channellist_attr = 3 + (1 + 1) * (u16)pmlmeext->channel_list.reg_classes - + get_reg_classes_full_count(pmlmeext->channel_list); + + get_reg_classes_full_count(&pmlmeext->channel_list); *(__le16 *)(p2pie + p2pielen) = cpu_to_le16(len_channellist_attr); @@ -2859,7 +2859,7 @@ void issue_p2p_invitation_request(struct adapter *padapter, u8 *raddr) /* + number of channels in all classes */ len_channellist_attr = 3 + (1 + 1) * (u16)pmlmeext->channel_list.reg_classes - + get_reg_classes_full_count(pmlmeext->channel_list); + + get_reg_classes_full_count(&pmlmeext->channel_list); *(__le16 *)(p2pie + p2pielen) = cpu_to_le16(len_channellist_attr); @@ -3120,7 +3120,7 @@ void issue_p2p_invitation_response(struct adapter *padapter, u8 *raddr, u8 dialo /* + number of channels in all classes */ len_channellist_attr = 3 + (1 + 1) * (u16)pmlmeext->channel_list.reg_classes - + get_reg_classes_full_count(pmlmeext->channel_list); + + get_reg_classes_full_count(&pmlmeext->channel_list); *(__le16 *)(p2pie + p2pielen) = cpu_to_le16(len_channellist_attr); p2pielen += 2; diff --git a/drivers/staging/rtl8188eu/core/rtw_mp.c b/drivers/staging/rtl8188eu/core/rtw_mp.c index c7ff2e4..9832dcb 100644 --- a/drivers/staging/rtl8188eu/core/rtw_mp.c +++ b/drivers/staging/rtl8188eu/core/rtw_mp.c @@ -907,7 +907,7 @@ u32 mp_query_psd(struct adapter *pAdapter, u8 *data) sscanf(data, "pts =%d, start =%d, stop =%d", &psd_pts, &psd_start, &psd_stop); } - _rtw_memset(data, '\0', sizeof(data)); + _rtw_memset(data, '\0', sizeof(*data)); i = psd_start; while (i < psd_stop) { diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c index 013ea48..8018edd 100644 --- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c @@ -631,7 +631,7 @@ void WMMOnAssocRsp(struct adapter *padapter) inx[0] = 0; inx[1] = 1; inx[2] = 2; inx[3] = 3; if (pregpriv->wifi_spec == 1) { - u32 j, tmp, change_inx; + u32 j, tmp, change_inx = false; /* entry indx: 0->vo, 1->vi, 2->be, 3->bk. */ for (i = 0; i < 4; i++) { diff --git a/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c b/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c index 9c2e7a2..ec0028d 100644 --- a/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c +++ b/drivers/staging/rtl8188eu/hal/rtl8188e_dm.c @@ -57,7 +57,7 @@ static void Init_ODM_ComInfo_88E(struct adapter *Adapter) u8 cut_ver, fab_ver; /* Init Value */ - _rtw_memset(dm_odm, 0, sizeof(dm_odm)); + _rtw_memset(dm_odm, 0, sizeof(*dm_odm)); dm_odm->Adapter = Adapter; diff --git a/drivers/staging/rtl8188eu/include/odm.h b/drivers/staging/rtl8188eu/include/odm.h index 2bfe728..4787bac 100644 --- a/drivers/staging/rtl8188eu/include/odm.h +++ b/drivers/staging/rtl8188eu/include/odm.h @@ -1010,7 +1010,7 @@ enum dm_dig_op { #define DM_false_ALARM_THRESH_LOW 400 #define DM_false_ALARM_THRESH_HIGH 1000 -#define DM_DIG_MAX_NIC 0x3e +#define DM_DIG_MAX_NIC 0x4e #define DM_DIG_MIN_NIC 0x1e /* 0x22/0x1c */ #define DM_DIG_MAX_AP 0x32 diff --git a/drivers/staging/rtl8188eu/include/rtl8188e_hal.h b/drivers/staging/rtl8188eu/include/rtl8188e_hal.h index 52b2801..555c801 100644 --- a/drivers/staging/rtl8188eu/include/rtl8188e_hal.h +++ b/drivers/staging/rtl8188eu/include/rtl8188e_hal.h @@ -188,7 +188,7 @@ enum ChannelPlan { struct txpowerinfo24g { u8 IndexCCK_Base[MAX_RF_PATH][MAX_CHNL_GROUP_24G]; - u8 IndexBW40_Base[MAX_RF_PATH][MAX_CHNL_GROUP_24G-1]; + u8 IndexBW40_Base[MAX_RF_PATH][MAX_CHNL_GROUP_24G]; /* If only one tx, only BW20 and OFDM are used. */ s8 CCK_Diff[MAX_RF_PATH][MAX_TX_COUNT]; s8 OFDM_Diff[MAX_RF_PATH][MAX_TX_COUNT]; diff --git a/drivers/staging/rtl8188eu/include/rtw_mlme_ext.h b/drivers/staging/rtl8188eu/include/rtw_mlme_ext.h index a96b018..853ab80 100644 --- a/drivers/staging/rtl8188eu/include/rtw_mlme_ext.h +++ b/drivers/staging/rtl8188eu/include/rtw_mlme_ext.h @@ -870,6 +870,7 @@ static struct fwevent wlanevents[] = { {0, NULL}, {0, NULL}, {0, &rtw_cpwm_event_callback}, + {0, NULL}, }; #endif/* _RTL_MLME_EXT_C_ */ diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c index cd4100f..95953eb 100644 --- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c @@ -6973,7 +6973,7 @@ static int rtw_mp_ctx(struct net_device *dev, stop = strncmp(extra, "stop", 4); sscanf(extra, "count =%d, pkt", &count); - _rtw_memset(extra, '\0', sizeof(extra)); + _rtw_memset(extra, '\0', sizeof(*extra)); if (stop == 0) { bStartTest = 0; /* To set Stop */ diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index d3078d2..9ca3180 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -54,6 +54,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = { /*=== Customer ID ===*/ /****** 8188EUS ********/ {USB_DEVICE(0x8179, 0x07B8)}, /* Abocom - Abocom */ + {USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/rtl8192u/r819xU_cmdpkt.c b/drivers/staging/rtl8192u/r819xU_cmdpkt.c index 5bc361b..5614401 100644 --- a/drivers/staging/rtl8192u/r819xU_cmdpkt.c +++ b/drivers/staging/rtl8192u/r819xU_cmdpkt.c @@ -37,6 +37,8 @@ rt_status SendTxCommandPacket(struct net_device *dev, void *pData, u32 DataLen) /* Get TCB and local buffer from common pool. (It is shared by CmdQ, MgntQ, and USB coalesce DataQ) */ skb = dev_alloc_skb(USB_HWDESC_HEADER_LEN + DataLen + 4); + if (!skb) + return RT_STATUS_FAILURE; memcpy((unsigned char *)(skb->cb), &dev, sizeof(dev)); tcb_desc = (cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE); tcb_desc->queue_index = TXCMD_QUEUE; diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c index dbf11ec..19d3cf4 100644 --- a/drivers/staging/vt6656/card.c +++ b/drivers/staging/vt6656/card.c @@ -172,8 +172,8 @@ static u16 swGetOFDMControlRate(struct vnt_private *pDevice, u16 wRateIdx) if (!CARDbIsOFDMinBasicRate(pDevice)) { DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "swGetOFDMControlRate:(NO OFDM) %d\n", wRateIdx); - if (wRateIdx > RATE_24M) - wRateIdx = RATE_24M; + if (wRateIdx > RATE_24M) + wRateIdx = RATE_24M; return wRateIdx; } diff --git a/drivers/staging/vt6656/iwctl.c b/drivers/staging/vt6656/iwctl.c index d0cf7d8..8872e0f 100644 --- a/drivers/staging/vt6656/iwctl.c +++ b/drivers/staging/vt6656/iwctl.c @@ -1634,6 +1634,9 @@ int iwctl_siwencodeext(struct net_device *dev, struct iw_request_info *info, if (pMgmt == NULL) return -EFAULT; + if (!(pDevice->flags & DEVICE_FLAGS_OPENED)) + return -ENODEV; + buf = kzalloc(sizeof(struct viawget_wpa_param), GFP_KERNEL); if (buf == NULL) return -ENOMEM; diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c index 5369717..6f9d281 100644 --- a/drivers/staging/vt6656/main_usb.c +++ b/drivers/staging/vt6656/main_usb.c @@ -1098,6 +1098,8 @@ static int device_close(struct net_device *dev) memset(pMgmt->abyCurrBSSID, 0, 6); pMgmt->eCurrState = WMAC_STATE_IDLE; + pDevice->flags &= ~DEVICE_FLAGS_OPENED; + device_free_tx_bufs(pDevice); device_free_rx_bufs(pDevice); device_free_int_bufs(pDevice); @@ -1109,7 +1111,6 @@ static int device_close(struct net_device *dev) usb_free_urb(pDevice->pInterruptURB); BSSvClearNodeDBTable(pDevice, 0); - pDevice->flags &=(~DEVICE_FLAGS_OPENED); DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "device_close2 \n"); diff --git a/drivers/staging/vt6656/rxtx.c b/drivers/staging/vt6656/rxtx.c index fb743a8..14f3e85 100644 --- a/drivers/staging/vt6656/rxtx.c +++ b/drivers/staging/vt6656/rxtx.c @@ -148,6 +148,8 @@ static void *s_vGetFreeContext(struct vnt_private *pDevice) DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO"GetFreeContext()\n"); for (ii = 0; ii < pDevice->cbTD; ii++) { + if (!pDevice->apTD[ii]) + return NULL; pContext = pDevice->apTD[ii]; if (pContext->bBoolInUse == false) { pContext->bBoolInUse = true; diff --git a/drivers/staging/xillybus/xillybus_core.c b/drivers/staging/xillybus/xillybus_core.c index efc5698..7db6f03 100644 --- a/drivers/staging/xillybus/xillybus_core.c +++ b/drivers/staging/xillybus/xillybus_core.c @@ -2054,7 +2054,7 @@ static int xillybus_init_chrdev(struct xilly_endpoint *endpoint, NULL, MKDEV(major, i), NULL, - devname); + "%s", devname); if (IS_ERR(device)) { pr_warn("xillybus: Failed to create %s " diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c index 91d94b5..2c4ed52 100644 --- a/drivers/staging/zram/zram_drv.c +++ b/drivers/staging/zram/zram_drv.c @@ -981,4 +981,3 @@ MODULE_PARM_DESC(num_devices, "Number of zram devices"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>"); MODULE_DESCRIPTION("Compressed RAM Block Device"); -MODULE_ALIAS("devname:zram"); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index c9a9ddd..01bf5eb 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1758,8 +1758,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) canon_change = (old->c_lflag ^ tty->termios.c_lflag) & ICANON; if (canon_change) { bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE); - ldata->line_start = 0; - ldata->canon_head = ldata->read_tail; + ldata->line_start = ldata->canon_head = ldata->read_tail; ldata->erasing = 0; ldata->lnext = 0; } diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 52379e5..44077c0 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -667,30 +667,21 @@ static int pop_tx_x(struct eg20t_port *priv, unsigned char *buf) static int dma_push_rx(struct eg20t_port *priv, int size) { - struct tty_struct *tty; int room; struct uart_port *port = &priv->port; struct tty_port *tport = &port->state->port; - port = &priv->port; - tty = tty_port_tty_get(tport); - if (!tty) { - dev_dbg(priv->port.dev, "%s:tty is busy now", __func__); - return 0; - } - room = tty_buffer_request_room(tport, size); if (room < size) dev_warn(port->dev, "Rx overrun: dropping %u bytes\n", size - room); if (!room) - return room; + return 0; tty_insert_flip_string(tport, sg_virt(&priv->sg_rx), size); port->icount.rx += room; - tty_kref_put(tty); return room; } @@ -1098,6 +1089,8 @@ static void pch_uart_err_ir(struct eg20t_port *priv, unsigned int lsr) if (tty == NULL) { for (i = 0; error_msg[i] != NULL; i++) dev_err(&priv->pdev->dev, error_msg[i]); + } else { + tty_kref_put(tty); } } diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index d0d972f..0489a2b 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -732,7 +732,7 @@ static irqreturn_t tegra_uart_isr(int irq, void *data) static void tegra_uart_stop_rx(struct uart_port *u) { struct tegra_uart_port *tup = to_tegra_uport(u); - struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port); + struct tty_struct *tty; struct tty_port *port = &u->state->port; struct dma_tx_state state; unsigned long ier; @@ -744,6 +744,8 @@ static void tegra_uart_stop_rx(struct uart_port *u) if (!tup->rx_in_progress) return; + tty = tty_port_tty_get(&tup->uport.state->port); + tegra_uart_wait_sym_time(tup, 1); /* wait a character interval */ ier = tup->ier_shadow; diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 03ba081..6fd60fe 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -1201,6 +1201,9 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, } return 0; case TCFLSH: + retval = tty_check_change(tty); + if (retval) + return retval; return __tty_perform_flush(tty, arg); default: /* Try the mode commands */ diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig index 4a851e1..77b47d8 100644 --- a/drivers/usb/chipidea/Kconfig +++ b/drivers/usb/chipidea/Kconfig @@ -1,6 +1,6 @@ config USB_CHIPIDEA tristate "ChipIdea Highspeed Dual Role Controller" - depends on (USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET) + depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA help Say Y here if your system has a dual role high speed USB controller based on ChipIdea silicon IP. Currently, only the diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 74d998d..be822a2 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -131,7 +131,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "usbmisc init failed, ret=%d\n", ret); - goto err_clk; + goto err_phy; } } @@ -143,7 +143,7 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Can't register ci_hdrc platform device, err=%d\n", ret); - goto err_clk; + goto err_phy; } if (data->usbmisc_data) { @@ -164,6 +164,9 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) disable_device: ci_hdrc_remove_device(data->ci_pdev); +err_phy: + if (data->phy) + usb_phy_shutdown(data->phy); err_clk: clk_disable_unprepare(data->clk); return ret; diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 9462640..23763dc 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -605,6 +605,7 @@ static int ci_hdrc_remove(struct platform_device *pdev) dbg_remove_files(ci); free_irq(ci->irq, ci); ci_role_destroy(ci); + kfree(ci->hw_bank.regmap); return 0; } diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 6b4c2f2..9333083 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -1600,6 +1600,8 @@ static void destroy_eps(struct ci_hdrc *ci) for (i = 0; i < ci->hw_ep_max; i++) { struct ci_hw_ep *hwep = &ci->ci_hw_ep[i]; + if (hwep->pending_td) + free_pending_td(hwep); dma_pool_free(ci->qh_pool, hwep->qh.ptr, hwep->qh.dma); } } @@ -1667,13 +1669,13 @@ static int ci_udc_stop(struct usb_gadget *gadget, if (ci->platdata->notify_event) ci->platdata->notify_event(ci, CI_HDRC_CONTROLLER_STOPPED_EVENT); - ci->driver = NULL; spin_unlock_irqrestore(&ci->lock, flags); _gadget_stop_activity(&ci->gadget); spin_lock_irqsave(&ci->lock, flags); pm_runtime_put(&ci->gadget.dev); } + ci->driver = NULL; spin_unlock_irqrestore(&ci->lock, flags); return 0; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 737e3c1..71dc5d7 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -742,6 +742,22 @@ static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype, if ((index & ~USB_DIR_IN) == 0) return 0; ret = findintfep(ps->dev, index); + if (ret < 0) { + /* + * Some not fully compliant Win apps seem to get + * index wrong and have the endpoint number here + * rather than the endpoint address (with the + * correct direction). Win does let this through, + * so we'll not reject it here but leave it to + * the device to not break KVM. But we warn. + */ + ret = findintfep(ps->dev, index ^ 0x80); + if (ret >= 0) + dev_info(&ps->dev->dev, + "%s: process %i (%s) requesting ep %02x but needs %02x\n", + __func__, task_pid_nr(current), + current->comm, index, index ^ 0x80); + } if (ret >= 0) ret = checkintf(ps, ret); break; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index dde4c83..e6b682c 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3426,6 +3426,9 @@ static int usb_req_set_sel(struct usb_device *udev, enum usb3_link_state state) unsigned long long u2_pel; int ret; + if (udev->state != USB_STATE_CONFIGURED) + return 0; + /* Convert SEL and PEL stored in ns to us */ u1_sel = DIV_ROUND_UP(udev->u1_params.sel, 1000); u1_pel = DIV_ROUND_UP(udev->u1_params.pel, 1000); diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index b870872..70fc430 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -1,7 +1,6 @@ config USB_DWC3 tristate "DesignWare USB3 DRD Core Support" depends on (USB || USB_GADGET) && HAS_DMA - depends on EXTCON select USB_XHCI_PLATFORM if USB_SUPPORT && USB_XHCI_HCD help Say Y or M here if your system has a Dual Role SuperSpeed diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 9b13812..2e252aa 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -28,6 +28,8 @@ /* FIXME define these in <linux/pci_ids.h> */ #define PCI_VENDOR_ID_SYNOPSYS 0x16c3 #define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3 0xabcd +#define PCI_DEVICE_ID_INTEL_BYT 0x0f37 +#define PCI_DEVICE_ID_INTEL_MRFLD 0x119e struct dwc3_pci { struct device *dev; @@ -187,6 +189,8 @@ static DEFINE_PCI_DEVICE_TABLE(dwc3_pci_id_table) = { PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS, PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3), }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BYT), }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MRFLD), }, { } /* Terminating Entry */ }; MODULE_DEVICE_TABLE(pci, dwc3_pci_id_table); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index f168eae..5452c0f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2611,15 +2611,13 @@ int dwc3_gadget_init(struct dwc3 *dwc) ret = usb_add_gadget_udc(dwc->dev, &dwc->gadget); if (ret) { dev_err(dwc->dev, "failed to register udc\n"); - goto err5; + goto err4; } return 0; -err5: - dwc3_gadget_free_endpoints(dwc); - err4: + dwc3_gadget_free_endpoints(dwc); dma_free_coherent(dwc->dev, DWC3_EP0_BOUNCE_SIZE, dwc->ep0_bounce, dwc->ep0_bounce_addr); diff --git a/drivers/usb/gadget/cdc2.c b/drivers/usb/gadget/cdc2.c index 5a5acf2..e126b6b 100644 --- a/drivers/usb/gadget/cdc2.c +++ b/drivers/usb/gadget/cdc2.c @@ -113,12 +113,6 @@ static int __init cdc_do_config(struct usb_configuration *c) c->bmAttributes |= USB_CONFIG_ATT_WAKEUP; } - fi_ecm = usb_get_function_instance("ecm"); - if (IS_ERR(fi_ecm)) { - status = PTR_ERR(fi_ecm); - goto err_func_ecm; - } - f_ecm = usb_get_function(fi_ecm); if (IS_ERR(f_ecm)) { status = PTR_ERR(f_ecm); @@ -129,35 +123,24 @@ static int __init cdc_do_config(struct usb_configuration *c) if (status) goto err_add_ecm; - fi_serial = usb_get_function_instance("acm"); - if (IS_ERR(fi_serial)) { - status = PTR_ERR(fi_serial); - goto err_get_acm; - } - f_acm = usb_get_function(fi_serial); if (IS_ERR(f_acm)) { status = PTR_ERR(f_acm); - goto err_func_acm; + goto err_get_acm; } status = usb_add_function(c, f_acm); if (status) goto err_add_acm; - return 0; err_add_acm: usb_put_function(f_acm); -err_func_acm: - usb_put_function_instance(fi_serial); err_get_acm: usb_remove_function(c, f_ecm); err_add_ecm: usb_put_function(f_ecm); err_get_ecm: - usb_put_function_instance(fi_ecm); -err_func_ecm: return status; } diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c index 06ecd08..b8a2376 100644 --- a/drivers/usb/gadget/dummy_hcd.c +++ b/drivers/usb/gadget/dummy_hcd.c @@ -923,8 +923,9 @@ static int dummy_udc_stop(struct usb_gadget *g, struct dummy_hcd *dum_hcd = gadget_to_dummy_hcd(g); struct dummy *dum = dum_hcd->dum; - dev_dbg(udc_dev(dum), "unregister gadget driver '%s'\n", - driver->driver.name); + if (driver) + dev_dbg(udc_dev(dum), "unregister gadget driver '%s'\n", + driver->driver.name); dum->driver = NULL; @@ -1000,8 +1001,8 @@ static int dummy_udc_remove(struct platform_device *pdev) { struct dummy *dum = platform_get_drvdata(pdev); - usb_del_gadget_udc(&dum->gadget); device_remove_file(&dum->gadget.dev, &dev_attr_function); + usb_del_gadget_udc(&dum->gadget); return 0; } diff --git a/drivers/usb/gadget/f_ecm.c b/drivers/usb/gadget/f_ecm.c index edab45d..8d9e6f7 100644 --- a/drivers/usb/gadget/f_ecm.c +++ b/drivers/usb/gadget/f_ecm.c @@ -995,7 +995,7 @@ static void ecm_unbind(struct usb_configuration *c, struct usb_function *f) usb_ep_free_request(ecm->notify, ecm->notify_req); } -struct usb_function *ecm_alloc(struct usb_function_instance *fi) +static struct usb_function *ecm_alloc(struct usb_function_instance *fi) { struct f_ecm *ecm; struct f_ecm_opts *opts; diff --git a/drivers/usb/gadget/f_eem.c b/drivers/usb/gadget/f_eem.c index d00392d..d61c11d 100644 --- a/drivers/usb/gadget/f_eem.c +++ b/drivers/usb/gadget/f_eem.c @@ -624,7 +624,7 @@ static void eem_unbind(struct usb_configuration *c, struct usb_function *f) usb_free_all_descriptors(f); } -struct usb_function *eem_alloc(struct usb_function_instance *fi) +static struct usb_function *eem_alloc(struct usb_function_instance *fi) { struct f_eem *eem; struct f_eem_opts *opts; diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index 1a66c5b..0658908 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -1034,37 +1034,19 @@ struct ffs_sb_fill_data { struct ffs_file_perms perms; umode_t root_mode; const char *dev_name; - union { - /* set by ffs_fs_mount(), read by ffs_sb_fill() */ - void *private_data; - /* set by ffs_sb_fill(), read by ffs_fs_mount */ - struct ffs_data *ffs_data; - }; + struct ffs_data *ffs_data; }; static int ffs_sb_fill(struct super_block *sb, void *_data, int silent) { struct ffs_sb_fill_data *data = _data; struct inode *inode; - struct ffs_data *ffs; + struct ffs_data *ffs = data->ffs_data; ENTER(); - /* Initialise data */ - ffs = ffs_data_new(); - if (unlikely(!ffs)) - goto Enomem; - ffs->sb = sb; - ffs->dev_name = kstrdup(data->dev_name, GFP_KERNEL); - if (unlikely(!ffs->dev_name)) - goto Enomem; - ffs->file_perms = data->perms; - ffs->private_data = data->private_data; - - /* used by the caller of this function */ - data->ffs_data = ffs; - + data->ffs_data = NULL; sb->s_fs_info = ffs; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; @@ -1080,17 +1062,14 @@ static int ffs_sb_fill(struct super_block *sb, void *_data, int silent) &data->perms); sb->s_root = d_make_root(inode); if (unlikely(!sb->s_root)) - goto Enomem; + return -ENOMEM; /* EP0 file */ if (unlikely(!ffs_sb_create_file(sb, "ep0", ffs, &ffs_ep0_operations, NULL))) - goto Enomem; + return -ENOMEM; return 0; - -Enomem: - return -ENOMEM; } static int ffs_fs_parse_opts(struct ffs_sb_fill_data *data, char *opts) @@ -1193,6 +1172,7 @@ ffs_fs_mount(struct file_system_type *t, int flags, struct dentry *rv; int ret; void *ffs_dev; + struct ffs_data *ffs; ENTER(); @@ -1200,18 +1180,30 @@ ffs_fs_mount(struct file_system_type *t, int flags, if (unlikely(ret < 0)) return ERR_PTR(ret); + ffs = ffs_data_new(); + if (unlikely(!ffs)) + return ERR_PTR(-ENOMEM); + ffs->file_perms = data.perms; + + ffs->dev_name = kstrdup(dev_name, GFP_KERNEL); + if (unlikely(!ffs->dev_name)) { + ffs_data_put(ffs); + return ERR_PTR(-ENOMEM); + } + ffs_dev = functionfs_acquire_dev_callback(dev_name); - if (IS_ERR(ffs_dev)) - return ffs_dev; + if (IS_ERR(ffs_dev)) { + ffs_data_put(ffs); + return ERR_CAST(ffs_dev); + } + ffs->private_data = ffs_dev; + data.ffs_data = ffs; - data.dev_name = dev_name; - data.private_data = ffs_dev; rv = mount_nodev(t, flags, &data, ffs_sb_fill); - - /* data.ffs_data is set by ffs_sb_fill */ - if (IS_ERR(rv)) + if (IS_ERR(rv) && data.ffs_data) { functionfs_release_dev_callback(data.ffs_data); - + ffs_data_put(data.ffs_data); + } return rv; } diff --git a/drivers/usb/gadget/f_mass_storage.c b/drivers/usb/gadget/f_mass_storage.c index 313b835..a01d7d3 100644 --- a/drivers/usb/gadget/f_mass_storage.c +++ b/drivers/usb/gadget/f_mass_storage.c @@ -2260,10 +2260,12 @@ reset: /* Disable the endpoints */ if (fsg->bulk_in_enabled) { usb_ep_disable(fsg->bulk_in); + fsg->bulk_in->driver_data = NULL; fsg->bulk_in_enabled = 0; } if (fsg->bulk_out_enabled) { usb_ep_disable(fsg->bulk_out); + fsg->bulk_out->driver_data = NULL; fsg->bulk_out_enabled = 0; } diff --git a/drivers/usb/gadget/fotg210-udc.c b/drivers/usb/gadget/fotg210-udc.c index 32db2ee..bbbfd19 100644 --- a/drivers/usb/gadget/fotg210-udc.c +++ b/drivers/usb/gadget/fotg210-udc.c @@ -1214,6 +1214,6 @@ static struct platform_driver fotg210_driver = { module_platform_driver(fotg210_driver); -MODULE_AUTHOR("Yuan-Hsin Chen <yhchen@faraday-tech.com>"); +MODULE_AUTHOR("Yuan-Hsin Chen, Feng-Hsin Chiang <john453@faraday-tech.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION(DRIVER_DESC); diff --git a/drivers/usb/gadget/fusb300_udc.c b/drivers/usb/gadget/fusb300_udc.c index f1dd6da..b278abe 100644 --- a/drivers/usb/gadget/fusb300_udc.c +++ b/drivers/usb/gadget/fusb300_udc.c @@ -22,7 +22,7 @@ MODULE_DESCRIPTION("FUSB300 USB gadget driver"); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Yuan Hsin Chen <yhchen@faraday-tech.com>"); +MODULE_AUTHOR("Yuan-Hsin Chen, Feng-Hsin Chiang <john453@faraday-tech.com>"); MODULE_ALIAS("platform:fusb300_udc"); #define DRIVER_VERSION "20 October 2010" diff --git a/drivers/usb/gadget/multi.c b/drivers/usb/gadget/multi.c index 2a1ebef..2339325 100644 --- a/drivers/usb/gadget/multi.c +++ b/drivers/usb/gadget/multi.c @@ -179,7 +179,7 @@ err_conf: return ret; } -static int rndis_config_register(struct usb_composite_dev *cdev) +static __ref int rndis_config_register(struct usb_composite_dev *cdev) { static struct usb_configuration config = { .bConfigurationValue = MULTI_RNDIS_CONFIG_NUM, @@ -194,7 +194,7 @@ static int rndis_config_register(struct usb_composite_dev *cdev) #else -static int rndis_config_register(struct usb_composite_dev *cdev) +static __ref int rndis_config_register(struct usb_composite_dev *cdev) { return 0; } @@ -241,7 +241,7 @@ err_conf: return ret; } -static int cdc_config_register(struct usb_composite_dev *cdev) +static __ref int cdc_config_register(struct usb_composite_dev *cdev) { static struct usb_configuration config = { .bConfigurationValue = MULTI_CDC_CONFIG_NUM, @@ -256,7 +256,7 @@ static int cdc_config_register(struct usb_composite_dev *cdev) #else -static int cdc_config_register(struct usb_composite_dev *cdev) +static __ref int cdc_config_register(struct usb_composite_dev *cdev) { return 0; } diff --git a/drivers/usb/gadget/mv_u3d_core.c b/drivers/usb/gadget/mv_u3d_core.c index bbb6e98..561b30e 100644 --- a/drivers/usb/gadget/mv_u3d_core.c +++ b/drivers/usb/gadget/mv_u3d_core.c @@ -645,6 +645,7 @@ static int mv_u3d_ep_disable(struct usb_ep *_ep) struct mv_u3d_ep *ep; struct mv_u3d_ep_context *ep_context; u32 epxcr, direction; + unsigned long flags; if (!_ep) return -EINVAL; @@ -661,7 +662,9 @@ static int mv_u3d_ep_disable(struct usb_ep *_ep) direction = mv_u3d_ep_dir(ep); /* nuke all pending requests (does flush) */ + spin_lock_irqsave(&u3d->lock, flags); mv_u3d_nuke(ep, -ESHUTDOWN); + spin_unlock_irqrestore(&u3d->lock, flags); /* Disable the endpoint for Rx or Tx and reset the endpoint type */ if (direction == MV_U3D_EP_DIR_OUT) { diff --git a/drivers/usb/gadget/s3c-hsotg.c b/drivers/usb/gadget/s3c-hsotg.c index d69b36a..6bddf1a 100644 --- a/drivers/usb/gadget/s3c-hsotg.c +++ b/drivers/usb/gadget/s3c-hsotg.c @@ -2475,8 +2475,6 @@ irq_retry: if (gintsts & GINTSTS_ErlySusp) { dev_dbg(hsotg->dev, "GINTSTS_ErlySusp\n"); writel(GINTSTS_ErlySusp, hsotg->regs + GINTSTS); - - s3c_hsotg_disconnect(hsotg); } /* @@ -2962,9 +2960,6 @@ static int s3c_hsotg_udc_stop(struct usb_gadget *gadget, if (!hsotg) return -ENODEV; - if (!driver || driver != hsotg->driver || !driver->unbind) - return -EINVAL; - /* all endpoints should be shutdown */ for (ep = 0; ep < hsotg->num_of_eps; ep++) s3c_hsotg_ep_disable(&hsotg->eps[ep].ep); @@ -2972,15 +2967,15 @@ static int s3c_hsotg_udc_stop(struct usb_gadget *gadget, spin_lock_irqsave(&hsotg->lock, flags); s3c_hsotg_phy_disable(hsotg); - regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); - hsotg->driver = NULL; + if (!driver) + hsotg->driver = NULL; + hsotg->gadget.speed = USB_SPEED_UNKNOWN; spin_unlock_irqrestore(&hsotg->lock, flags); - dev_info(hsotg->dev, "unregistered gadget driver '%s'\n", - driver->driver.name); + regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); return 0; } diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 947b009..f2407b2 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -130,7 +130,7 @@ static int usb_hcd_fsl_probe(const struct hc_driver *driver, } /* Enable USB controller, 83xx or 8536 */ - if (pdata->have_sysif_regs) + if (pdata->have_sysif_regs && pdata->controller_ver < FSL_USB_VER_1_6) setbits32(hcd->regs + FSL_SOC_USB_CTRL, 0x4); /* Don't need to set host mode here. It will be done by tdi_reset() */ @@ -232,15 +232,9 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd, case FSL_USB2_PHY_ULPI: if (pdata->have_sysif_regs && pdata->controller_ver) { /* controller version 1.6 or above */ + clrbits32(non_ehci + FSL_SOC_USB_CTRL, UTMI_PHY_EN); setbits32(non_ehci + FSL_SOC_USB_CTRL, - ULPI_PHY_CLK_SEL); - /* - * Due to controller issue of PHY_CLK_VALID in ULPI - * mode, we set USB_CTRL_USB_EN before checking - * PHY_CLK_VALID, otherwise PHY_CLK_VALID doesn't work. - */ - clrsetbits_be32(non_ehci + FSL_SOC_USB_CTRL, - UTMI_PHY_EN, USB_CTRL_USB_EN); + ULPI_PHY_CLK_SEL | USB_CTRL_USB_EN); } portsc |= PORT_PTS_ULPI; break; @@ -270,8 +264,9 @@ static int ehci_fsl_setup_phy(struct usb_hcd *hcd, if (pdata->have_sysif_regs && pdata->controller_ver && (phy_mode == FSL_USB2_PHY_ULPI)) { /* check PHY_CLK_VALID to get phy clk valid */ - if (!spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) & - PHY_CLK_VALID, FSL_USB_PHY_CLK_TIMEOUT, 0)) { + if (!(spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) & + PHY_CLK_VALID, FSL_USB_PHY_CLK_TIMEOUT, 0) || + in_be32(non_ehci + FSL_SOC_USB_PRICTRL))) { printk(KERN_WARNING "fsl-ehci: USB PHY clock invalid\n"); return -EINVAL; } @@ -669,7 +664,7 @@ static const struct hc_driver ehci_fsl_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_USB2 | HCD_MEMORY | HCD_BH, + .flags = HCD_USB2 | HCD_MEMORY, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-grlib.c b/drivers/usb/host/ehci-grlib.c index b52a66c..83ab51a 100644 --- a/drivers/usb/host/ehci-grlib.c +++ b/drivers/usb/host/ehci-grlib.c @@ -43,7 +43,7 @@ static const struct hc_driver ehci_grlib_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 5d6022f..86ab9fd 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -1158,7 +1158,7 @@ static const struct hc_driver ehci_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-mv.c b/drivers/usb/host/ehci-mv.c index 417c10d..35cdbd8 100644 --- a/drivers/usb/host/ehci-mv.c +++ b/drivers/usb/host/ehci-mv.c @@ -96,7 +96,7 @@ static const struct hc_driver mv_ehci_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-octeon.c b/drivers/usb/host/ehci-octeon.c index ab0397e..45cc001 100644 --- a/drivers/usb/host/ehci-octeon.c +++ b/drivers/usb/host/ehci-octeon.c @@ -51,7 +51,7 @@ static const struct hc_driver ehci_octeon_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c index 6bd299e..854c2ec 100644 --- a/drivers/usb/host/ehci-pci.c +++ b/drivers/usb/host/ehci-pci.c @@ -361,7 +361,7 @@ static struct pci_driver ehci_pci_driver = { .remove = usb_hcd_pci_remove, .shutdown = usb_hcd_pci_shutdown, -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM .driver = { .pm = &usb_hcd_pci_pm_ops }, diff --git a/drivers/usb/host/ehci-pmcmsp.c b/drivers/usb/host/ehci-pmcmsp.c index 893b707..601e208 100644 --- a/drivers/usb/host/ehci-pmcmsp.c +++ b/drivers/usb/host/ehci-pmcmsp.c @@ -286,7 +286,7 @@ static const struct hc_driver ehci_msp_hc_driver = { #else .irq = ehci_irq, #endif - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-ppc-of.c b/drivers/usb/host/ehci-ppc-of.c index 6cc5567..932293f 100644 --- a/drivers/usb/host/ehci-ppc-of.c +++ b/drivers/usb/host/ehci-ppc-of.c @@ -28,7 +28,7 @@ static const struct hc_driver ehci_ppc_of_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-ps3.c b/drivers/usb/host/ehci-ps3.c index 8188542..fd98377 100644 --- a/drivers/usb/host/ehci-ps3.c +++ b/drivers/usb/host/ehci-ps3.c @@ -71,7 +71,7 @@ static const struct hc_driver ps3_ehci_hc_driver = { .product_desc = "PS3 EHCI Host Controller", .hcd_priv_size = sizeof(struct ehci_hcd), .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, .reset = ps3_ehci_hc_reset, .start = ehci_run, .stop = ehci_stop, diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index e321804..a7f776a 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -247,6 +247,8 @@ static int qtd_copy_status ( static void ehci_urb_done(struct ehci_hcd *ehci, struct urb *urb, int status) +__releases(ehci->lock) +__acquires(ehci->lock) { if (usb_pipetype(urb->pipe) == PIPE_INTERRUPT) { /* ... update hc-wide periodic stats */ @@ -272,8 +274,11 @@ ehci_urb_done(struct ehci_hcd *ehci, struct urb *urb, int status) urb->actual_length, urb->transfer_buffer_length); #endif + /* complete() can reenter this HCD */ usb_hcd_unlink_urb_from_ep(ehci_to_hcd(ehci), urb); + spin_unlock (&ehci->lock); usb_hcd_giveback_urb(ehci_to_hcd(ehci), urb, status); + spin_lock (&ehci->lock); } static int qh_schedule (struct ehci_hcd *ehci, struct ehci_qh *qh); diff --git a/drivers/usb/host/ehci-sead3.c b/drivers/usb/host/ehci-sead3.c index 8a73449..b2de52d 100644 --- a/drivers/usb/host/ehci-sead3.c +++ b/drivers/usb/host/ehci-sead3.c @@ -55,7 +55,7 @@ const struct hc_driver ehci_sead3_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-sh.c b/drivers/usb/host/ehci-sh.c index dc899eb..93e59a1 100644 --- a/drivers/usb/host/ehci-sh.c +++ b/drivers/usb/host/ehci-sh.c @@ -36,7 +36,7 @@ static const struct hc_driver ehci_sh_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_USB2 | HCD_MEMORY | HCD_BH, + .flags = HCD_USB2 | HCD_MEMORY, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-tilegx.c b/drivers/usb/host/ehci-tilegx.c index 67026ff..cca4be9 100644 --- a/drivers/usb/host/ehci-tilegx.c +++ b/drivers/usb/host/ehci-tilegx.c @@ -61,7 +61,7 @@ static const struct hc_driver ehci_tilegx_hc_driver = { * Generic hardware linkage. */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * Basic lifecycle operations. diff --git a/drivers/usb/host/ehci-w90x900.c b/drivers/usb/host/ehci-w90x900.c index 1c370df..59e0e24 100644 --- a/drivers/usb/host/ehci-w90x900.c +++ b/drivers/usb/host/ehci-w90x900.c @@ -108,7 +108,7 @@ static const struct hc_driver ehci_w90x900_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_USB2|HCD_MEMORY|HCD_BH, + .flags = HCD_USB2|HCD_MEMORY, /* * basic lifecycle operations diff --git a/drivers/usb/host/ehci-xilinx-of.c b/drivers/usb/host/ehci-xilinx-of.c index 95979f9..eba962e 100644 --- a/drivers/usb/host/ehci-xilinx-of.c +++ b/drivers/usb/host/ehci-xilinx-of.c @@ -79,7 +79,7 @@ static const struct hc_driver ehci_xilinx_of_hc_driver = { * generic hardware linkage */ .irq = ehci_irq, - .flags = HCD_MEMORY | HCD_USB2 | HCD_BH, + .flags = HCD_MEMORY | HCD_USB2, /* * basic lifecycle operations diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index 9e0020d..abd5050 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -24,7 +24,7 @@ struct fsl_usb2_dev_data { enum fsl_usb2_operating_modes op_mode; /* operating mode */ }; -struct fsl_usb2_dev_data dr_mode_data[] = { +static struct fsl_usb2_dev_data dr_mode_data[] = { { .dr_mode = "host", .drivers = { "fsl-ehci", NULL, NULL, }, @@ -42,7 +42,7 @@ struct fsl_usb2_dev_data dr_mode_data[] = { }, }; -struct fsl_usb2_dev_data *get_dr_mode_data(struct device_node *np) +static struct fsl_usb2_dev_data *get_dr_mode_data(struct device_node *np) { const unsigned char *prop; int i; @@ -75,7 +75,7 @@ static enum fsl_usb2_phy_modes determine_usb_phy(const char *phy_type) return FSL_USB2_PHY_NONE; } -struct platform_device *fsl_usb2_device_register( +static struct platform_device *fsl_usb2_device_register( struct platform_device *ofdev, struct fsl_usb2_platform_data *pdata, const char *name, int id) diff --git a/drivers/usb/host/imx21-hcd.c b/drivers/usb/host/imx21-hcd.c index 60a5de5..adb01d9 100644 --- a/drivers/usb/host/imx21-hcd.c +++ b/drivers/usb/host/imx21-hcd.c @@ -824,13 +824,13 @@ static int imx21_hc_urb_enqueue_isoc(struct usb_hcd *hcd, i = DIV_ROUND_UP(wrap_frame( cur_frame - urb->start_frame), urb->interval); - if (urb->transfer_flags & URB_ISO_ASAP) { + + /* Treat underruns as if URB_ISO_ASAP was set */ + if ((urb->transfer_flags & URB_ISO_ASAP) || + i >= urb->number_of_packets) { urb->start_frame = wrap_frame(urb->start_frame + i * urb->interval); i = 0; - } else if (i >= urb->number_of_packets) { - ret = -EXDEV; - goto alloc_dmem_failed; } } } diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 8f6b695..604cad1 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -216,31 +216,26 @@ static int ohci_urb_enqueue ( frame &= ~(ed->interval - 1); frame |= ed->branch; urb->start_frame = frame; + ed->last_iso = frame + ed->interval * (size - 1); } } else if (ed->type == PIPE_ISOCHRONOUS) { u16 next = ohci_frame_no(ohci) + 1; u16 frame = ed->last_iso + ed->interval; + u16 length = ed->interval * (size - 1); /* Behind the scheduling threshold? */ if (unlikely(tick_before(frame, next))) { - /* USB_ISO_ASAP: Round up to the first available slot */ + /* URB_ISO_ASAP: Round up to the first available slot */ if (urb->transfer_flags & URB_ISO_ASAP) { frame += (next - frame + ed->interval - 1) & -ed->interval; /* - * Not ASAP: Use the next slot in the stream. If - * the entire URB falls before the threshold, fail. + * Not ASAP: Use the next slot in the stream, + * no matter what. */ } else { - if (tick_before(frame + ed->interval * - (urb->number_of_packets - 1), next)) { - retval = -EXDEV; - usb_hcd_unlink_urb_from_ep(hcd, urb); - goto fail; - } - /* * Some OHCI hardware doesn't handle late TDs * correctly. After retiring them it proceeds @@ -251,9 +246,16 @@ static int ohci_urb_enqueue ( urb_priv->td_cnt = DIV_ROUND_UP( (u16) (next - frame), ed->interval); + if (urb_priv->td_cnt >= urb_priv->length) { + ++urb_priv->td_cnt; /* Mark it */ + ohci_dbg(ohci, "iso underrun %p (%u+%u < %u)\n", + urb, frame, length, + next); + } } } urb->start_frame = frame; + ed->last_iso = frame + length; } /* fill the TDs and link them to the ed; and diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index df4a670..e7f577e 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -41,9 +41,13 @@ finish_urb(struct ohci_hcd *ohci, struct urb *urb, int status) __releases(ohci->lock) __acquires(ohci->lock) { - struct device *dev = ohci_to_hcd(ohci)->self.controller; + struct device *dev = ohci_to_hcd(ohci)->self.controller; + struct usb_host_endpoint *ep = urb->ep; + struct urb_priv *urb_priv; + // ASSERT (urb->hcpriv != 0); + restart: urb_free_priv (ohci, urb->hcpriv); urb->hcpriv = NULL; if (likely(status == -EINPROGRESS)) @@ -80,6 +84,21 @@ __acquires(ohci->lock) ohci->hc_control &= ~(OHCI_CTRL_PLE|OHCI_CTRL_IE); ohci_writel (ohci, ohci->hc_control, &ohci->regs->control); } + + /* + * An isochronous URB that is sumitted too late won't have any TDs + * (marked by the fact that the td_cnt value is larger than the + * actual number of TDs). If the next URB on this endpoint is like + * that, give it back now. + */ + if (!list_empty(&ep->urb_list)) { + urb = list_first_entry(&ep->urb_list, struct urb, urb_list); + urb_priv = urb->hcpriv; + if (urb_priv->td_cnt > urb_priv->length) { + status = 0; + goto restart; + } + } } @@ -546,7 +565,6 @@ td_fill (struct ohci_hcd *ohci, u32 info, td->hwCBP = cpu_to_hc32 (ohci, data & 0xFFFFF000); *ohci_hwPSWp(ohci, td, 0) = cpu_to_hc16 (ohci, (data & 0x0FFF) | 0xE000); - td->ed->last_iso = info & 0xffff; } else { td->hwCBP = cpu_to_hc32 (ohci, data); } @@ -996,7 +1014,7 @@ rescan_this: urb_priv->td_cnt++; /* if URB is done, clean up */ - if (urb_priv->td_cnt == urb_priv->length) { + if (urb_priv->td_cnt >= urb_priv->length) { modified = completed = 1; finish_urb(ohci, urb, 0); } @@ -1086,7 +1104,7 @@ static void takeback_td(struct ohci_hcd *ohci, struct td *td) urb_priv->td_cnt++; /* If all this urb's TDs are done, call complete() */ - if (urb_priv->td_cnt == urb_priv->length) + if (urb_priv->td_cnt >= urb_priv->length) finish_urb(ohci, urb, status); /* clean schedule: unlink EDs that are no longer busy */ diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index c300bd2f7..0f228c4 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -293,7 +293,7 @@ static struct pci_driver uhci_pci_driver = { .remove = usb_hcd_pci_remove, .shutdown = uhci_shutdown, -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM .driver = { .pm = &usb_hcd_pci_pm_ops }, diff --git a/drivers/usb/host/uhci-q.c b/drivers/usb/host/uhci-q.c index 041c6dd..da6f56d 100644 --- a/drivers/usb/host/uhci-q.c +++ b/drivers/usb/host/uhci-q.c @@ -1303,7 +1303,7 @@ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb, } /* Fell behind? */ - if (uhci_frame_before_eq(frame, next)) { + if (!uhci_frame_before_eq(next, frame)) { /* USB_ISO_ASAP: Round up to the first available slot */ if (urb->transfer_flags & URB_ISO_ASAP) @@ -1311,13 +1311,17 @@ static int uhci_submit_isochronous(struct uhci_hcd *uhci, struct urb *urb, -qh->period; /* - * Not ASAP: Use the next slot in the stream. If - * the entire URB falls before the threshold, fail. + * Not ASAP: Use the next slot in the stream, + * no matter what. */ else if (!uhci_frame_before_eq(next, frame + (urb->number_of_packets - 1) * qh->period)) - return -EXDEV; + dev_dbg(uhci_dev(uhci), "iso underrun %p (%u+%u < %u)\n", + urb, frame, + (urb->number_of_packets - 1) * + qh->period, + next); } } diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index fae697e..773a6b2 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -287,7 +287,7 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue) xhci_queue_stop_endpoint(xhci, slot_id, i, suspend); } - cmd->command_trb = xhci->cmd_ring->enqueue; + cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring); list_add_tail(&cmd->cmd_list, &virt_dev->cmd_list); xhci_queue_stop_endpoint(xhci, slot_id, 0, suspend); xhci_ring_cmd_db(xhci); @@ -552,11 +552,15 @@ void xhci_del_comp_mod_timer(struct xhci_hcd *xhci, u32 status, u16 wIndex) * - Mark a port as being done with device resume, * and ring the endpoint doorbells. * - Stop the Synopsys redriver Compliance Mode polling. + * - Drop and reacquire the xHCI lock, in order to wait for port resume. */ static u32 xhci_get_port_status(struct usb_hcd *hcd, struct xhci_bus_state *bus_state, __le32 __iomem **port_array, - u16 wIndex, u32 raw_port_status) + u16 wIndex, u32 raw_port_status, + unsigned long flags) + __releases(&xhci->lock) + __acquires(&xhci->lock) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); u32 status = 0; @@ -591,21 +595,42 @@ static u32 xhci_get_port_status(struct usb_hcd *hcd, return 0xffffffff; if (time_after_eq(jiffies, bus_state->resume_done[wIndex])) { + int time_left; + xhci_dbg(xhci, "Resume USB2 port %d\n", wIndex + 1); bus_state->resume_done[wIndex] = 0; clear_bit(wIndex, &bus_state->resuming_ports); + + set_bit(wIndex, &bus_state->rexit_ports); xhci_set_link_state(xhci, port_array, wIndex, XDEV_U0); - xhci_dbg(xhci, "set port %d resume\n", - wIndex + 1); - slot_id = xhci_find_slot_id_by_port(hcd, xhci, - wIndex + 1); - if (!slot_id) { - xhci_dbg(xhci, "slot_id is zero\n"); - return 0xffffffff; + + spin_unlock_irqrestore(&xhci->lock, flags); + time_left = wait_for_completion_timeout( + &bus_state->rexit_done[wIndex], + msecs_to_jiffies( + XHCI_MAX_REXIT_TIMEOUT)); + spin_lock_irqsave(&xhci->lock, flags); + + if (time_left) { + slot_id = xhci_find_slot_id_by_port(hcd, + xhci, wIndex + 1); + if (!slot_id) { + xhci_dbg(xhci, "slot_id is zero\n"); + return 0xffffffff; + } + xhci_ring_device(xhci, slot_id); + } else { + int port_status = xhci_readl(xhci, + port_array[wIndex]); + xhci_warn(xhci, "Port resume took longer than %i msec, port status = 0x%x\n", + XHCI_MAX_REXIT_TIMEOUT, + port_status); + status |= USB_PORT_STAT_SUSPEND; + clear_bit(wIndex, &bus_state->rexit_ports); } - xhci_ring_device(xhci, slot_id); + bus_state->port_c_suspend |= 1 << wIndex; bus_state->suspended_ports &= ~(1 << wIndex); } else { @@ -728,7 +753,7 @@ int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, break; } status = xhci_get_port_status(hcd, bus_state, port_array, - wIndex, temp); + wIndex, temp, flags); if (status == 0xffffffff) goto error; diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 53b972c..83bcd13 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2428,6 +2428,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) for (i = 0; i < USB_MAXCHILDREN; ++i) { xhci->bus_state[0].resume_done[i] = 0; xhci->bus_state[1].resume_done[i] = 0; + /* Only the USB 2.0 completions will ever be used. */ + init_completion(&xhci->bus_state[1].rexit_done[i]); } if (scratchpad_alloc(xhci, flags)) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c2d4950..236c3aa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -351,7 +351,7 @@ static struct pci_driver xhci_pci_driver = { /* suspend and resume implemented later */ .shutdown = usb_hcd_pci_shutdown, -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM .driver = { .pm = &usb_hcd_pci_pm_ops }, diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 411da1f..6bfbd80 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -123,6 +123,16 @@ static int enqueue_is_link_trb(struct xhci_ring *ring) return TRB_TYPE_LINK_LE32(link->control); } +union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring) +{ + /* Enqueue pointer can be left pointing to the link TRB, + * we must handle that + */ + if (TRB_TYPE_LINK_LE32(ring->enqueue->link.control)) + return ring->enq_seg->next->trbs; + return ring->enqueue; +} + /* Updates trb to point to the next TRB in the ring, and updates seg if the next * TRB is in a new segment. This does not skip over link TRBs, and it does not * effect the ring dequeue or enqueue pointers. @@ -859,8 +869,12 @@ remove_finished_td: /* Otherwise ring the doorbell(s) to restart queued transfers */ ring_doorbell_for_active_rings(xhci, slot_id, ep_index); } - ep->stopped_td = NULL; - ep->stopped_trb = NULL; + + /* Clear stopped_td and stopped_trb if endpoint is not halted */ + if (!(ep->ep_state & EP_HALTED)) { + ep->stopped_td = NULL; + ep->stopped_trb = NULL; + } /* * Drop the lock and complete the URBs in the cancelled TD list. @@ -1414,6 +1428,12 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, inc_deq(xhci, xhci->cmd_ring); return; } + /* There is no command to handle if we get a stop event when the + * command ring is empty, event->cmd_trb points to the next + * unset command + */ + if (xhci->cmd_ring->dequeue == xhci->cmd_ring->enqueue) + return; } switch (le32_to_cpu(xhci->cmd_ring->dequeue->generic.field[3]) @@ -1743,6 +1763,19 @@ static void handle_port_status(struct xhci_hcd *xhci, } } + /* + * Check to see if xhci-hub.c is waiting on RExit to U0 transition (or + * RExit to a disconnect state). If so, let the the driver know it's + * out of the RExit state. + */ + if (!DEV_SUPERSPEED(temp) && + test_and_clear_bit(faked_port_index, + &bus_state->rexit_ports)) { + complete(&bus_state->rexit_done[faked_port_index]); + bogus_port_status = true; + goto cleanup; + } + if (hcd->speed != HCD_USB3) xhci_test_and_clear_bit(xhci, port_array, faked_port_index, PORT_PLC); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 49b6edb..1e36dbb 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2598,15 +2598,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, if (command) { cmd_completion = command->completion; cmd_status = &command->status; - command->command_trb = xhci->cmd_ring->enqueue; - - /* Enqueue pointer can be left pointing to the link TRB, - * we must handle that - */ - if (TRB_TYPE_LINK_LE32(command->command_trb->link.control)) - command->command_trb = - xhci->cmd_ring->enq_seg->next->trbs; - + command->command_trb = xhci_find_next_enqueue(xhci->cmd_ring); list_add_tail(&command->cmd_list, &virt_dev->cmd_list); } else { cmd_completion = &virt_dev->cmd_completion; @@ -2614,7 +2606,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci, } init_completion(cmd_completion); - cmd_trb = xhci->cmd_ring->dequeue; + cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring); if (!ctx_change) ret = xhci_queue_configure_endpoint(xhci, in_ctx->dma, udev->slot_id, must_succeed); @@ -3439,14 +3431,7 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev) /* Attempt to submit the Reset Device command to the command ring */ spin_lock_irqsave(&xhci->lock, flags); - reset_device_cmd->command_trb = xhci->cmd_ring->enqueue; - - /* Enqueue pointer can be left pointing to the link TRB, - * we must handle that - */ - if (TRB_TYPE_LINK_LE32(reset_device_cmd->command_trb->link.control)) - reset_device_cmd->command_trb = - xhci->cmd_ring->enq_seg->next->trbs; + reset_device_cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring); list_add_tail(&reset_device_cmd->cmd_list, &virt_dev->cmd_list); ret = xhci_queue_reset_device(xhci, slot_id); @@ -3650,7 +3635,7 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev) union xhci_trb *cmd_trb; spin_lock_irqsave(&xhci->lock, flags); - cmd_trb = xhci->cmd_ring->dequeue; + cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring); ret = xhci_queue_slot_control(xhci, TRB_ENABLE_SLOT, 0); if (ret) { spin_unlock_irqrestore(&xhci->lock, flags); @@ -3785,7 +3770,7 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev) slot_ctx->dev_info >> 27); spin_lock_irqsave(&xhci->lock, flags); - cmd_trb = xhci->cmd_ring->dequeue; + cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring); ret = xhci_queue_address_device(xhci, virt_dev->in_ctx->dma, udev->slot_id); if (ret) { diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 46aa148..289fbfb 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1412,8 +1412,18 @@ struct xhci_bus_state { unsigned long resume_done[USB_MAXCHILDREN]; /* which ports have started to resume */ unsigned long resuming_ports; + /* Which ports are waiting on RExit to U0 transition. */ + unsigned long rexit_ports; + struct completion rexit_done[USB_MAXCHILDREN]; }; + +/* + * It can take up to 20 ms to transition from RExit to U0 on the + * Intel Lynx Point LP xHCI host. + */ +#define XHCI_MAX_REXIT_TIMEOUT (20 * 1000) + static inline unsigned int hcd_index(struct usb_hcd *hcd) { if (hcd->speed == HCD_USB3) @@ -1840,6 +1850,7 @@ int xhci_cancel_cmd(struct xhci_hcd *xhci, struct xhci_command *command, union xhci_trb *cmd_trb); void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id, unsigned int ep_index, unsigned int stream_id); +union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring); /* xHCI roothub code */ void xhci_set_link_state(struct xhci_hcd *xhci, __le32 __iomem **port_array, diff --git a/drivers/usb/phy/phy-omap-usb3.c b/drivers/usb/phy/phy-omap-usb3.c index fc15694..4e8a040 100644 --- a/drivers/usb/phy/phy-omap-usb3.c +++ b/drivers/usb/phy/phy-omap-usb3.c @@ -79,7 +79,7 @@ static struct usb_dpll_params *omap_usb3_get_dpll_params(unsigned long rate) return &dpll_map[i].params; } - return 0; + return NULL; } static int omap_usb3_suspend(struct usb_phy *x, int suspend) diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig index c454bfa..ddb9c51 100644 --- a/drivers/usb/serial/Kconfig +++ b/drivers/usb/serial/Kconfig @@ -60,7 +60,7 @@ config USB_SERIAL_SIMPLE - Suunto ANT+ USB device. - Fundamental Software dongle. - HP4x calculators - - a number of Motoroloa phones + - a number of Motorola phones - Siemens USB/MPI adapter. - ViVOtech ViVOpay USB device. - Infineon Modem Flashloader USB interface diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index e7a84f0..bedf8e4 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -139,6 +139,7 @@ enum pl2303_type { HX_TA, /* HX(A) / X(A) / TA version */ /* TODO: improve */ HXD_EA_RA_SA, /* HXD / EA / RA / SA version */ /* TODO: improve */ TB, /* TB version */ + HX_CLONE, /* Cheap and less functional clone of the HX chip */ }; /* * NOTE: don't know the difference between type 0 and type 1, @@ -206,8 +207,23 @@ static int pl2303_startup(struct usb_serial *serial) * the device descriptors of the X/HX, HXD, EA, RA, SA, TA, TB */ if (le16_to_cpu(serial->dev->descriptor.bcdDevice) == 0x300) { - type = HX_TA; - type_str = "X/HX/TA"; + /* Check if the device is a clone */ + pl2303_vendor_read(0x9494, 0, serial, buf); + /* + * NOTE: Not sure if this read is really needed. + * The HX returns 0x00, the clone 0x02, but the Windows + * driver seems to ignore the value and continues. + */ + pl2303_vendor_write(0x0606, 0xaa, serial); + pl2303_vendor_read(0x8686, 0, serial, buf); + if (buf[0] != 0xaa) { + type = HX_CLONE; + type_str = "X/HX clone (limited functionality)"; + } else { + type = HX_TA; + type_str = "X/HX/TA"; + } + pl2303_vendor_write(0x0606, 0x00, serial); } else if (le16_to_cpu(serial->dev->descriptor.bcdDevice) == 0x400) { type = HXD_EA_RA_SA; @@ -305,8 +321,9 @@ static int pl2303_baudrate_encode_direct(int baud, enum pl2303_type type, { /* * NOTE: Only the values defined in baud_sup are supported ! - * => if unsupported values are set, the PL2303 seems to - * use 9600 baud (at least my PL2303X always does) + * => if unsupported values are set, the PL2303 uses 9600 baud instead + * => HX clones just don't work at unsupported baud rates < 115200 baud, + * for baud rates > 115200 they run at 115200 baud */ const int baud_sup[] = { 75, 150, 300, 600, 1200, 1800, 2400, 3600, 4800, 7200, 9600, 14400, 19200, 28800, 38400, @@ -316,14 +333,14 @@ static int pl2303_baudrate_encode_direct(int baud, enum pl2303_type type, * NOTE: With the exception of type_0/1 devices, the following * additional baud rates are supported (tested with HX rev. 3A only): * 110*, 56000*, 128000, 134400, 161280, 201600, 256000*, 268800, - * 403200, 806400. (*: not HX) + * 403200, 806400. (*: not HX and HX clones) * * Maximum values: HXD, TB: 12000000; HX, TA: 6000000; - * type_0+1: 1228800; RA: 921600; SA: 115200 + * type_0+1: 1228800; RA: 921600; HX clones, SA: 115200 * * As long as we are not using this encoding method for anything else - * than the type_0+1 and HX chips, there is no point in complicating - * the code to support them. + * than the type_0+1, HX and HX clone chips, there is no point in + * complicating the code to support them. */ int i; @@ -347,6 +364,8 @@ static int pl2303_baudrate_encode_direct(int baud, enum pl2303_type type, baud = min_t(int, baud, 6000000); else if (type == type_0 || type == type_1) baud = min_t(int, baud, 1228800); + else if (type == HX_CLONE) + baud = min_t(int, baud, 115200); /* Direct (standard) baud rate encoding method */ put_unaligned_le32(baud, buf); @@ -359,7 +378,8 @@ static int pl2303_baudrate_encode_divisor(int baud, enum pl2303_type type, /* * Divisor based baud rate encoding method * - * NOTE: it's not clear if the type_0/1 chips support this method + * NOTE: HX clones do NOT support this method. + * It's not clear if the type_0/1 chips support it. * * divisor = 12MHz * 32 / baudrate = 2^A * B * @@ -452,7 +472,7 @@ static void pl2303_encode_baudrate(struct tty_struct *tty, * 1) Direct method: encodes the baud rate value directly * => supported by all chip types * 2) Divisor based method: encodes a divisor to a base value (12MHz*32) - * => supported by HX chips (and likely not by type_0/1 chips) + * => not supported by HX clones (and likely type_0/1 chips) * * NOTE: Although the divisor based baud rate encoding method is much * more flexible, some of the standard baud rate values can not be @@ -460,7 +480,7 @@ static void pl2303_encode_baudrate(struct tty_struct *tty, * the device likely uses the same baud rate generator for both methods * so that there is likley no difference. */ - if (type == type_0 || type == type_1) + if (type == type_0 || type == type_1 || type == HX_CLONE) baud = pl2303_baudrate_encode_direct(baud, type, buf); else baud = pl2303_baudrate_encode_divisor(baud, type, buf); @@ -813,6 +833,7 @@ static void pl2303_break_ctl(struct tty_struct *tty, int break_state) result = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), BREAK_REQUEST, BREAK_REQUEST_TYPE, state, 0, NULL, 0, 100); + /* NOTE: HX clones don't support sending breaks, -EPIPE is returned */ if (result) dev_err(&port->dev, "error sending break = %d\n", result); } diff --git a/drivers/video/mmp/hw/mmp_ctrl.c b/drivers/video/mmp/hw/mmp_ctrl.c index 75dca19..6ac7552 100644 --- a/drivers/video/mmp/hw/mmp_ctrl.c +++ b/drivers/video/mmp/hw/mmp_ctrl.c @@ -514,7 +514,7 @@ static int mmphw_probe(struct platform_device *pdev) if (IS_ERR(ctrl->clk)) { dev_err(ctrl->dev, "unable to get clk %s\n", mi->clk_name); ret = -ENOENT; - goto failed_get_clk; + goto failed; } clk_prepare_enable(ctrl->clk); @@ -551,21 +551,8 @@ failed_path_init: path_deinit(path_plat); } - if (ctrl->clk) { - devm_clk_put(ctrl->dev, ctrl->clk); - clk_disable_unprepare(ctrl->clk); - } -failed_get_clk: - devm_free_irq(ctrl->dev, ctrl->irq, ctrl); + clk_disable_unprepare(ctrl->clk); failed: - if (ctrl) { - if (ctrl->reg_base) - devm_iounmap(ctrl->dev, ctrl->reg_base); - devm_release_mem_region(ctrl->dev, res->start, - resource_size(res)); - devm_kfree(ctrl->dev, ctrl); - } - dev_err(&pdev->dev, "device init failed\n"); return ret; diff --git a/drivers/video/mxsfb.c b/drivers/video/mxsfb.c index d250ed0..27197a8 100644 --- a/drivers/video/mxsfb.c +++ b/drivers/video/mxsfb.c @@ -620,6 +620,7 @@ static int mxsfb_restore_mode(struct mxsfb_info *host) break; case 3: bits_per_pixel = 32; + break; case 1: default: return -EINVAL; diff --git a/drivers/video/neofb.c b/drivers/video/neofb.c index 7ef079c..c172a52 100644 --- a/drivers/video/neofb.c +++ b/drivers/video/neofb.c @@ -2075,6 +2075,7 @@ static int neofb_probe(struct pci_dev *dev, const struct pci_device_id *id) if (!fb_find_mode(&info->var, info, mode_option, NULL, 0, info->monspecs.modedb, 16)) { printk(KERN_ERR "neofb: Unable to find usable video mode.\n"); + err = -EINVAL; goto err_map_video; } @@ -2097,7 +2098,8 @@ static int neofb_probe(struct pci_dev *dev, const struct pci_device_id *id) info->fix.smem_len >> 10, info->var.xres, info->var.yres, h_sync / 1000, h_sync % 1000, v_sync); - if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) + err = fb_alloc_cmap(&info->cmap, 256, 0); + if (err < 0) goto err_map_video; err = register_framebuffer(info); diff --git a/drivers/video/of_display_timing.c b/drivers/video/of_display_timing.c index 171821d..ba5b40f 100644 --- a/drivers/video/of_display_timing.c +++ b/drivers/video/of_display_timing.c @@ -120,7 +120,7 @@ int of_get_display_timing(struct device_node *np, const char *name, return -EINVAL; } - timing_np = of_find_node_by_name(np, name); + timing_np = of_get_child_by_name(np, name); if (!timing_np) { pr_err("%s: could not find node '%s'\n", of_node_full_name(np), name); @@ -143,11 +143,11 @@ struct display_timings *of_get_display_timings(struct device_node *np) struct display_timings *disp; if (!np) { - pr_err("%s: no devicenode given\n", of_node_full_name(np)); + pr_err("%s: no device node given\n", of_node_full_name(np)); return NULL; } - timings_np = of_find_node_by_name(np, "display-timings"); + timings_np = of_get_child_by_name(np, "display-timings"); if (!timings_np) { pr_err("%s: could not find display-timings node\n", of_node_full_name(np)); diff --git a/drivers/video/omap2/displays-new/Kconfig b/drivers/video/omap2/displays-new/Kconfig index 6c90885..10b25e7 100644 --- a/drivers/video/omap2/displays-new/Kconfig +++ b/drivers/video/omap2/displays-new/Kconfig @@ -35,6 +35,7 @@ config DISPLAY_PANEL_DPI config DISPLAY_PANEL_DSI_CM tristate "Generic DSI Command Mode Panel" + depends on BACKLIGHT_CLASS_DEVICE help Driver for generic DSI command mode panels. diff --git a/drivers/video/omap2/displays-new/connector-analog-tv.c b/drivers/video/omap2/displays-new/connector-analog-tv.c index 1b60698..ccd9073 100644 --- a/drivers/video/omap2/displays-new/connector-analog-tv.c +++ b/drivers/video/omap2/displays-new/connector-analog-tv.c @@ -191,7 +191,7 @@ static int tvc_probe_pdata(struct platform_device *pdev) in = omap_dss_find_output(pdata->source); if (in == NULL) { dev_err(&pdev->dev, "Failed to find video source\n"); - return -ENODEV; + return -EPROBE_DEFER; } ddata->in = in; diff --git a/drivers/video/omap2/displays-new/connector-dvi.c b/drivers/video/omap2/displays-new/connector-dvi.c index bc5f8ce..63d88ee 100644 --- a/drivers/video/omap2/displays-new/connector-dvi.c +++ b/drivers/video/omap2/displays-new/connector-dvi.c @@ -263,7 +263,7 @@ static int dvic_probe_pdata(struct platform_device *pdev) in = omap_dss_find_output(pdata->source); if (in == NULL) { dev_err(&pdev->dev, "Failed to find video source\n"); - return -ENODEV; + return -EPROBE_DEFER; } ddata->in = in; diff --git a/drivers/video/omap2/displays-new/connector-hdmi.c b/drivers/video/omap2/displays-new/connector-hdmi.c index c582671..9abe2c0 100644 --- a/drivers/video/omap2/displays-new/connector-hdmi.c +++ b/drivers/video/omap2/displays-new/connector-hdmi.c @@ -290,7 +290,7 @@ static int hdmic_probe_pdata(struct platform_device *pdev) in = omap_dss_find_output(pdata->source); if (in == NULL) { dev_err(&pdev->dev, "Failed to find video source\n"); - return -ENODEV; + return -EPROBE_DEFER; } ddata->in = in; diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c index 02a7340..4779750 100644 --- a/drivers/video/omap2/dss/dispc.c +++ b/drivers/video/omap2/dss/dispc.c @@ -3691,6 +3691,7 @@ static int __init omap_dispchw_probe(struct platform_device *pdev) } pm_runtime_enable(&pdev->dev); + pm_runtime_irq_safe(&pdev->dev); r = dispc_runtime_get(); if (r) diff --git a/drivers/video/s3fb.c b/drivers/video/s3fb.c index 47ca86c..d838ba8 100644 --- a/drivers/video/s3fb.c +++ b/drivers/video/s3fb.c @@ -1336,14 +1336,7 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) (info->var.bits_per_pixel * info->var.xres_virtual); if (info->var.yres_virtual < info->var.yres) { dev_err(info->device, "virtual vertical size smaller than real\n"); - goto err_find_mode; - } - - /* maximize virtual vertical size for fast scrolling */ - info->var.yres_virtual = info->fix.smem_len * 8 / - (info->var.bits_per_pixel * info->var.xres_virtual); - if (info->var.yres_virtual < info->var.yres) { - dev_err(info->device, "virtual vertical size smaller than real\n"); + rc = -EINVAL; goto err_find_mode; } diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index a50c6e3..b232908 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -398,8 +398,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) if (nr_pages > ARRAY_SIZE(frame_list)) nr_pages = ARRAY_SIZE(frame_list); - scratch_page = get_balloon_scratch_page(); - for (i = 0; i < nr_pages; i++) { page = alloc_page(gfp); if (page == NULL) { @@ -413,6 +411,12 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) scrub_page(page); + /* + * Ballooned out frames are effectively replaced with + * a scratch frame. Ensure direct mappings and the + * p2m are consistent. + */ + scratch_page = get_balloon_scratch_page(); #ifdef CONFIG_XEN_HAVE_PVMMU if (xen_pv_domain() && !PageHighMem(page)) { ret = HYPERVISOR_update_va_mapping( @@ -422,24 +426,19 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) BUG_ON(ret); } #endif - } - - /* Ensure that ballooned highmem pages don't have kmaps. */ - kmap_flush_unused(); - flush_tlb_all(); - - /* No more mappings: invalidate P2M and add to balloon. */ - for (i = 0; i < nr_pages; i++) { - pfn = mfn_to_pfn(frame_list[i]); if (!xen_feature(XENFEAT_auto_translated_physmap)) { unsigned long p; p = page_to_pfn(scratch_page); __set_phys_to_machine(pfn, pfn_to_mfn(p)); } + put_balloon_scratch_page(); + balloon_append(pfn_to_page(pfn)); } - put_balloon_scratch_page(); + /* Ensure that ballooned highmem pages don't have kmaps. */ + kmap_flush_unused(); + flush_tlb_all(); set_xen_guest_handle(reservation.extent_start, frame_list); reservation.nr_extents = nr_pages; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 646337d..5293003 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -600,9 +600,6 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) /* lock down the parent dentry so we can peer at it */ parent = dget_parent(dentry); - if (!parent->d_inode) - goto out_bad; - dir = AFS_FS_I(parent->d_inode); /* validate the parent directory */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 100edcc..4c94a79 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1413,7 +1413,7 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata, * long file_ofs * followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL... */ -static void fill_files_note(struct memelfnote *note) +static int fill_files_note(struct memelfnote *note) { struct vm_area_struct *vma; unsigned count, size, names_ofs, remaining, n; @@ -1428,11 +1428,11 @@ static void fill_files_note(struct memelfnote *note) names_ofs = (2 + 3 * count) * sizeof(data[0]); alloc: if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */ - goto err; + return -EINVAL; size = round_up(size, PAGE_SIZE); data = vmalloc(size); if (!data) - goto err; + return -ENOMEM; start_end_ofs = data + 2; name_base = name_curpos = ((char *)data) + names_ofs; @@ -1485,7 +1485,7 @@ static void fill_files_note(struct memelfnote *note) size = name_curpos - (char *)data; fill_note(note, "CORE", NT_FILE, size, data); - err: ; + return 0; } #ifdef CORE_DUMP_USE_REGSET @@ -1686,8 +1686,8 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, fill_auxv_note(&info->auxv, current->mm); info->size += notesize(&info->auxv); - fill_files_note(&info->files); - info->size += notesize(&info->files); + if (fill_files_note(&info->files) == 0) + info->size += notesize(&info->files); return 1; } @@ -1719,7 +1719,8 @@ static int write_note_info(struct elf_note_info *info, return 0; if (first && !writenote(&info->auxv, file, foffset)) return 0; - if (first && !writenote(&info->files, file, foffset)) + if (first && info->files.data && + !writenote(&info->files, file, foffset)) return 0; for (i = 1; i < info->thread_notes; ++i) @@ -1806,6 +1807,7 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) struct elf_note_info { struct memelfnote *notes; + struct memelfnote *notes_files; struct elf_prstatus *prstatus; /* NT_PRSTATUS */ struct elf_prpsinfo *psinfo; /* NT_PRPSINFO */ struct list_head thread_list; @@ -1896,9 +1898,12 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, fill_siginfo_note(info->notes + 2, &info->csigdata, siginfo); fill_auxv_note(info->notes + 3, current->mm); - fill_files_note(info->notes + 4); + info->numnote = 4; - info->numnote = 5; + if (fill_files_note(info->notes + info->numnote) == 0) { + info->notes_files = info->notes + info->numnote; + info->numnote++; + } /* Try to dump the FPU. */ info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs, @@ -1960,8 +1965,9 @@ static void free_note_info(struct elf_note_info *info) kfree(list_entry(tmp, struct elf_thread_status, list)); } - /* Free data allocated by fill_files_note(): */ - vfree(info->notes[4].data); + /* Free data possibly allocated by fill_files_note(): */ + if (info->notes_files) + vfree(info->notes_files->data); kfree(info->prstatus); kfree(info->psinfo); @@ -2044,7 +2050,7 @@ static int elf_core_dump(struct coredump_params *cprm) struct vm_area_struct *vma, *gate_vma; struct elfhdr *elf = NULL; loff_t offset = 0, dataoff, foffset; - struct elf_note_info info; + struct elf_note_info info = { }; struct elf_phdr *phdr4note = NULL; struct elf_shdr *shdr4extnum = NULL; Elf_Half e_phnum; diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 6025084..fc60b31 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -735,7 +735,7 @@ void bioset_integrity_free(struct bio_set *bs) mempool_destroy(bs->bio_integrity_pool); if (bs->bvec_integrity_pool) - mempool_destroy(bs->bio_integrity_pool); + mempool_destroy(bs->bvec_integrity_pool); } EXPORT_SYMBOL(bioset_integrity_free); @@ -917,8 +917,8 @@ void bio_copy_data(struct bio *dst, struct bio *src) src_p = kmap_atomic(src_bv->bv_page); dst_p = kmap_atomic(dst_bv->bv_page); - memcpy(dst_p + dst_bv->bv_offset, - src_p + src_bv->bv_offset, + memcpy(dst_p + dst_offset, + src_p + src_offset, bytes); kunmap_atomic(dst_p); diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index d0ae226..71f074e 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -213,7 +213,10 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode) static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) { if (BTRFS_I(inode)->logged_trans == generation && - BTRFS_I(inode)->last_sub_trans <= BTRFS_I(inode)->last_log_commit) + BTRFS_I(inode)->last_sub_trans <= + BTRFS_I(inode)->last_log_commit && + BTRFS_I(inode)->last_sub_trans <= + BTRFS_I(inode)->root->last_log_commit) return 1; return 0; } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 6434672..61b5bcd 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1005,8 +1005,11 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } - if (root->ref_cows) - btrfs_reloc_cow_block(trans, root, buf, cow); + if (root->ref_cows) { + ret = btrfs_reloc_cow_block(trans, root, buf, cow); + if (ret) + return ret; + } if (buf == root->node) { WARN_ON(parent && parent != buf); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3c1da6f..0506f40 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1118,15 +1118,6 @@ struct btrfs_space_info { */ struct percpu_counter total_bytes_pinned; - /* - * we bump reservation progress every time we decrement - * bytes_reserved. This way people waiting for reservations - * know something good has happened and they can check - * for progress. The number here isn't to be trusted, it - * just shows reclaim activity - */ - unsigned long reservation_progress; - unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ @@ -3135,7 +3126,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root, unsigned num_items) { return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) * - 3 * num_items; + 2 * num_items; } /* @@ -3939,9 +3930,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_recover_relocation(struct btrfs_root *root); int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len); -void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf, - struct extent_buffer *cow); +int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf, + struct extent_buffer *cow); void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans, struct btrfs_pending_snapshot *pending, u64 *bytes_to_reserve); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index a644353..7068168 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -400,7 +400,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; btrfs_dev_replace_unlock(dev_replace); - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); /* force writing the updated state information to disk */ trans = btrfs_start_transaction(root, 0); @@ -475,7 +475,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4cbb00a..4ae17ed 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -157,6 +157,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, + { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, { .id = 0, .name_stem = "tree" }, }; @@ -3415,6 +3416,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) if (total_errors > max_errors) { printk(KERN_ERR "btrfs: %d errors while writing supers\n", total_errors); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ btrfs_error(root->fs_info, -EIO, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index cfb3cf7..d58bef1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3925,7 +3925,6 @@ static int can_overcommit(struct btrfs_root *root, u64 space_size; u64 avail; u64 used; - u64 to_add; used = space_info->bytes_used + space_info->bytes_reserved + space_info->bytes_pinned + space_info->bytes_readonly; @@ -3959,25 +3958,17 @@ static int can_overcommit(struct btrfs_root *root, BTRFS_BLOCK_GROUP_RAID10)) avail >>= 1; - to_add = space_info->total_bytes; - /* * If we aren't flushing all things, let us overcommit up to * 1/2th of the space. If we can flush, don't let us overcommit * too much, let it overcommit up to 1/8 of the space. */ if (flush == BTRFS_RESERVE_FLUSH_ALL) - to_add >>= 3; + avail >>= 3; else - to_add >>= 1; - - /* - * Limit the overcommit to the amount of free space we could possibly - * allocate for chunks. - */ - to_add = min(avail, to_add); + avail >>= 1; - if (used + bytes < space_info->total_bytes + to_add) + if (used + bytes < space_info->total_bytes + avail) return 1; return 0; } @@ -4000,7 +3991,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root, */ btrfs_start_all_delalloc_inodes(root->fs_info, 0); if (!current->journal_info) - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); } } @@ -4030,7 +4021,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, if (delalloc_bytes == 0) { if (trans) return; - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); return; } @@ -4058,7 +4049,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, loops++; if (wait_ordered && !trans) { - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); } else { time_left = schedule_timeout_killable(1); if (time_left) @@ -4465,7 +4456,6 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info, space_info->bytes_may_use -= num_bytes; trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, num_bytes, 0); - space_info->reservation_progress++; spin_unlock(&space_info->lock); } } @@ -4666,7 +4656,6 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) sinfo->bytes_may_use -= num_bytes; trace_btrfs_space_reservation(fs_info, "space_info", sinfo->flags, num_bytes, 0); - sinfo->reservation_progress++; block_rsv->reserved = block_rsv->size; block_rsv->full = 1; } @@ -5446,7 +5435,6 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, space_info->bytes_readonly += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; - space_info->reservation_progress++; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); @@ -6117,10 +6105,13 @@ enum btrfs_loop_type { /* * walks the btree of allocated extents and find a hole of a given size. * The key ins is changed to record the hole: - * ins->objectid == block start + * ins->objectid == start position * ins->flags = BTRFS_EXTENT_ITEM_KEY - * ins->offset == number of blocks + * ins->offset == the size of the hole. * Any available blocks before search_start are skipped. + * + * If there is no suitable free space, we will record the max size of + * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, u64 num_bytes, u64 empty_size, @@ -6133,6 +6124,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_block_group_cache *block_group = NULL; struct btrfs_block_group_cache *used_block_group; u64 search_start = 0; + u64 max_extent_size = 0; int empty_cluster = 2 * 1024 * 1024; struct btrfs_space_info *space_info; int loop = 0; @@ -6292,7 +6284,10 @@ have_block_group: btrfs_get_block_group(used_block_group); offset = btrfs_alloc_from_cluster(used_block_group, - last_ptr, num_bytes, used_block_group->key.objectid); + last_ptr, + num_bytes, + used_block_group->key.objectid, + &max_extent_size); if (offset) { /* we have a block, we're done */ spin_unlock(&last_ptr->refill_lock); @@ -6355,8 +6350,10 @@ refill_cluster: * cluster */ offset = btrfs_alloc_from_cluster(block_group, - last_ptr, num_bytes, - search_start); + last_ptr, + num_bytes, + search_start, + &max_extent_size); if (offset) { /* we found one, proceed */ spin_unlock(&last_ptr->refill_lock); @@ -6391,13 +6388,18 @@ unclustered_alloc: if (cached && block_group->free_space_ctl->free_space < num_bytes + empty_cluster + empty_size) { + if (block_group->free_space_ctl->free_space > + max_extent_size) + max_extent_size = + block_group->free_space_ctl->free_space; spin_unlock(&block_group->free_space_ctl->tree_lock); goto loop; } spin_unlock(&block_group->free_space_ctl->tree_lock); offset = btrfs_find_space_for_alloc(block_group, search_start, - num_bytes, empty_size); + num_bytes, empty_size, + &max_extent_size); /* * If we didn't find a chunk, and we haven't failed on this * block group before, and this block group is in the middle of @@ -6515,7 +6517,8 @@ loop: ret = 0; } out: - + if (ret == -ENOSPC) + ins->offset = max_extent_size; return ret; } @@ -6573,8 +6576,8 @@ again: flags); if (ret == -ENOSPC) { - if (!final_tried) { - num_bytes = num_bytes >> 1; + if (!final_tried && ins->offset) { + num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); if (num_bytes == min_alloc_size) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 09582b8..c09a40d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1481,10 +1481,12 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree, *end = state->end; cur_start = state->end + 1; node = rb_next(node); - if (!node) - break; total_bytes += state->end - state->start + 1; - if (total_bytes >= max_bytes) + if (total_bytes >= max_bytes) { + *end = *start + max_bytes - 1; + break; + } + if (!node) break; } out: diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index bc5072b..72da4df 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1859,8 +1859,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = btrfs_log_dentry_safe(trans, root, dentry); if (ret < 0) { - mutex_unlock(&inode->i_mutex); - goto out; + /* Fallthrough and commit/free transaction. */ + ret = 1; } /* we've logged all the items and now have a consistent diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 3f0ddfc..b4f9904 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1431,13 +1431,19 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl, ctl->free_space += bytes; } +/* + * If we can not find suitable extent, we will use bytes to record + * the size of the max extent. + */ static int search_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes) { unsigned long found_bits = 0; + unsigned long max_bits = 0; unsigned long bits, i; unsigned long next_zero; + unsigned long extent_bits; i = offset_to_bit(bitmap_info->offset, ctl->unit, max_t(u64, *offset, bitmap_info->offset)); @@ -1446,9 +1452,12 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) { next_zero = find_next_zero_bit(bitmap_info->bitmap, BITS_PER_BITMAP, i); - if ((next_zero - i) >= bits) { - found_bits = next_zero - i; + extent_bits = next_zero - i; + if (extent_bits >= bits) { + found_bits = extent_bits; break; + } else if (extent_bits > max_bits) { + max_bits = extent_bits; } i = next_zero; } @@ -1459,38 +1468,41 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, return 0; } + *bytes = (u64)(max_bits) * ctl->unit; return -1; } +/* Cache the size of the max extent in bytes */ static struct btrfs_free_space * find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, - unsigned long align) + unsigned long align, u64 *max_extent_size) { struct btrfs_free_space *entry; struct rb_node *node; - u64 ctl_off; u64 tmp; u64 align_off; int ret; if (!ctl->free_space_offset.rb_node) - return NULL; + goto out; entry = tree_search_offset(ctl, offset_to_bitmap(ctl, *offset), 0, 1); if (!entry) - return NULL; + goto out; for (node = &entry->offset_index; node; node = rb_next(node)) { entry = rb_entry(node, struct btrfs_free_space, offset_index); - if (entry->bytes < *bytes) + if (entry->bytes < *bytes) { + if (entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; continue; + } /* make sure the space returned is big enough * to match our requested alignment */ if (*bytes >= align) { - ctl_off = entry->offset - ctl->start; - tmp = ctl_off + align - 1;; + tmp = entry->offset - ctl->start + align - 1; do_div(tmp, align); tmp = tmp * align + ctl->start; align_off = tmp - entry->offset; @@ -1499,14 +1511,22 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, tmp = entry->offset; } - if (entry->bytes < *bytes + align_off) + if (entry->bytes < *bytes + align_off) { + if (entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; continue; + } if (entry->bitmap) { - ret = search_bitmap(ctl, entry, &tmp, bytes); + u64 size = *bytes; + + ret = search_bitmap(ctl, entry, &tmp, &size); if (!ret) { *offset = tmp; + *bytes = size; return entry; + } else if (size > *max_extent_size) { + *max_extent_size = size; } continue; } @@ -1515,7 +1535,7 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, *bytes = entry->bytes - align_off; return entry; } - +out: return NULL; } @@ -2116,7 +2136,8 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) } u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes, u64 empty_size) + u64 offset, u64 bytes, u64 empty_size, + u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; @@ -2127,7 +2148,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, - block_group->full_stripe_len); + block_group->full_stripe_len, max_extent_size); if (!entry) goto out; @@ -2137,7 +2158,6 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, if (!entry->bytes) free_bitmap(ctl, entry); } else { - unlink_free_space(ctl, entry); align_gap_len = offset - entry->offset; align_gap = entry->offset; @@ -2151,7 +2171,6 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, else link_free_space(ctl, entry); } - out: spin_unlock(&ctl->tree_lock); @@ -2206,7 +2225,8 @@ int btrfs_return_cluster_to_free_space( static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, struct btrfs_free_space *entry, - u64 bytes, u64 min_start) + u64 bytes, u64 min_start, + u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; int err; @@ -2218,8 +2238,11 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, search_bytes = bytes; err = search_bitmap(ctl, entry, &search_start, &search_bytes); - if (err) + if (err) { + if (search_bytes > *max_extent_size) + *max_extent_size = search_bytes; return 0; + } ret = search_start; __bitmap_clear_bits(ctl, entry, ret, bytes); @@ -2234,7 +2257,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, */ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 bytes, - u64 min_start) + u64 min_start, u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; @@ -2254,6 +2277,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, entry = rb_entry(node, struct btrfs_free_space, offset_index); while(1) { + if (entry->bytes < bytes && entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; + if (entry->bytes < bytes || (!entry->bitmap && entry->offset < min_start)) { node = rb_next(&entry->offset_index); @@ -2267,7 +2293,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, if (entry->bitmap) { ret = btrfs_alloc_from_bitmap(block_group, cluster, entry, bytes, - cluster->window_start); + cluster->window_start, + max_extent_size); if (ret == 0) { node = rb_next(&entry->offset_index); if (!node) diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index c749041..e737f92 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -94,7 +94,8 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl); void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group); u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes, u64 empty_size); + u64 offset, u64 bytes, u64 empty_size, + u64 *max_extent_size); u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, u64 bytes); @@ -105,7 +106,7 @@ int btrfs_find_space_cluster(struct btrfs_root *root, void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 bytes, - u64 min_start); + u64 min_start, u64 *max_extent_size); int btrfs_return_cluster_to_free_space( struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f338c56..22ebc13 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4688,11 +4688,11 @@ static void inode_tree_add(struct inode *inode) struct btrfs_inode *entry; struct rb_node **p; struct rb_node *parent; + struct rb_node *new = &BTRFS_I(inode)->rb_node; u64 ino = btrfs_ino(inode); if (inode_unhashed(inode)) return; -again: parent = NULL; spin_lock(&root->inode_lock); p = &root->inode_tree.rb_node; @@ -4707,14 +4707,14 @@ again: else { WARN_ON(!(entry->vfs_inode.i_state & (I_WILL_FREE | I_FREEING))); - rb_erase(parent, &root->inode_tree); + rb_replace_node(parent, new, &root->inode_tree); RB_CLEAR_NODE(parent); spin_unlock(&root->inode_lock); - goto again; + return; } } - rb_link_node(&BTRFS_I(inode)->rb_node, parent, p); - rb_insert_color(&BTRFS_I(inode)->rb_node, &root->inode_tree); + rb_link_node(new, parent, p); + rb_insert_color(new, &root->inode_tree); spin_unlock(&root->inode_lock); } @@ -8216,6 +8216,10 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput) work = btrfs_alloc_delalloc_work(inode, 0, delay_iput); if (unlikely(!work)) { + if (delay_iput) + btrfs_add_delayed_iput(inode); + else + iput(inode); ret = -ENOMEM; goto out; } @@ -8613,11 +8617,13 @@ static const struct inode_operations btrfs_dir_inode_operations = { .removexattr = btrfs_removexattr, .permission = btrfs_permission, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct inode_operations btrfs_dir_ro_inode_operations = { .lookup = btrfs_lookup, .permission = btrfs_permission, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct file_operations btrfs_dir_file_operations = { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1a5b946..9d46f60 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -574,7 +574,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) return ret; - btrfs_wait_ordered_extents(root, 0); + btrfs_wait_ordered_extents(root); pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS); if (!pending_snapshot) @@ -2696,9 +2696,9 @@ out_unlock: static long btrfs_ioctl_file_extent_same(struct file *file, void __user *argp) { - struct btrfs_ioctl_same_args *args = argp; - struct btrfs_ioctl_same_args same; - struct btrfs_ioctl_same_extent_info info; + struct btrfs_ioctl_same_args tmp; + struct btrfs_ioctl_same_args *same; + struct btrfs_ioctl_same_extent_info *info; struct inode *src = file->f_dentry->d_inode; struct file *dst_file = NULL; struct inode *dst; @@ -2706,6 +2706,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, u64 len; int i; int ret; + unsigned long size; u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; bool is_admin = capable(CAP_SYS_ADMIN); @@ -2716,15 +2717,30 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (ret) return ret; - if (copy_from_user(&same, + if (copy_from_user(&tmp, (struct btrfs_ioctl_same_args __user *)argp, - sizeof(same))) { + sizeof(tmp))) { ret = -EFAULT; goto out; } - off = same.logical_offset; - len = same.length; + size = sizeof(tmp) + + tmp.dest_count * sizeof(struct btrfs_ioctl_same_extent_info); + + same = kmalloc(size, GFP_NOFS); + if (!same) { + ret = -EFAULT; + goto out; + } + + if (copy_from_user(same, + (struct btrfs_ioctl_same_args __user *)argp, size)) { + ret = -EFAULT; + goto out; + } + + off = same->logical_offset; + len = same->length; /* * Limit the total length we will dedupe for each operation. @@ -2752,27 +2768,28 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (!S_ISREG(src->i_mode)) goto out; - ret = 0; - for (i = 0; i < same.dest_count; i++) { - if (copy_from_user(&info, &args->info[i], sizeof(info))) { - ret = -EFAULT; - goto out; - } + /* pre-format output fields to sane values */ + for (i = 0; i < same->dest_count; i++) { + same->info[i].bytes_deduped = 0ULL; + same->info[i].status = 0; + } - info.bytes_deduped = 0; + ret = 0; + for (i = 0; i < same->dest_count; i++) { + info = &same->info[i]; - dst_file = fget(info.fd); + dst_file = fget(info->fd); if (!dst_file) { - info.status = -EBADF; + info->status = -EBADF; goto next; } if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { - info.status = -EINVAL; + info->status = -EINVAL; goto next; } - info.status = -EXDEV; + info->status = -EXDEV; if (file->f_path.mnt != dst_file->f_path.mnt) goto next; @@ -2781,32 +2798,29 @@ static long btrfs_ioctl_file_extent_same(struct file *file, goto next; if (S_ISDIR(dst->i_mode)) { - info.status = -EISDIR; + info->status = -EISDIR; goto next; } if (!S_ISREG(dst->i_mode)) { - info.status = -EACCES; + info->status = -EACCES; goto next; } - info.status = btrfs_extent_same(src, off, len, dst, - info.logical_offset); - if (info.status == 0) - info.bytes_deduped += len; + info->status = btrfs_extent_same(src, off, len, dst, + info->logical_offset); + if (info->status == 0) + info->bytes_deduped += len; next: if (dst_file) fput(dst_file); - - if (__put_user_unaligned(info.status, &args->info[i].status) || - __put_user_unaligned(info.bytes_deduped, - &args->info[i].bytes_deduped)) { - ret = -EFAULT; - goto out; - } } + ret = copy_to_user(argp, same, size); + if (ret) + ret = -EFAULT; + out: mnt_drop_write_file(file); return ret; @@ -3310,7 +3324,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) } if (!objectid) - objectid = root->root_key.objectid; + objectid = BTRFS_FS_TREE_OBJECTID; location.objectid = objectid; location.type = BTRFS_ROOT_ITEM_KEY; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 966b413..c702cb6 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -563,11 +563,10 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work) * wait for all the ordered extents in a root. This is done when balancing * space between drives. */ -void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) +void btrfs_wait_ordered_extents(struct btrfs_root *root) { struct list_head splice, works; struct btrfs_ordered_extent *ordered, *next; - struct inode *inode; INIT_LIST_HEAD(&splice); INIT_LIST_HEAD(&works); @@ -580,15 +579,6 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) root_extent_list); list_move_tail(&ordered->root_extent_list, &root->ordered_extents); - /* - * the inode may be getting freed (in sys_unlink path). - */ - inode = igrab(ordered->inode); - if (!inode) { - cond_resched_lock(&root->ordered_extent_lock); - continue; - } - atomic_inc(&ordered->refs); spin_unlock(&root->ordered_extent_lock); @@ -605,21 +595,13 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) list_for_each_entry_safe(ordered, next, &works, work_list) { list_del_init(&ordered->work_list); wait_for_completion(&ordered->completion); - - inode = ordered->inode; btrfs_put_ordered_extent(ordered); - if (delay_iput) - btrfs_add_delayed_iput(inode); - else - iput(inode); - cond_resched(); } mutex_unlock(&root->fs_info->ordered_operations_mutex); } -void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, - int delay_iput) +void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; struct list_head splice; @@ -637,7 +619,7 @@ void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); - btrfs_wait_ordered_extents(root, delay_iput); + btrfs_wait_ordered_extents(root); btrfs_put_fs_root(root); spin_lock(&fs_info->ordered_root_lock); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index d9a5aa0..0c0b356 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -195,9 +195,8 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans, void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); -void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput); -void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, - int delay_iput); +void btrfs_wait_ordered_extents(struct btrfs_root *root); +void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info); void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode); void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid); void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index aacc212..a5a2632 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1548,7 +1548,7 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr, btrfs_file_extent_other_encoding(leaf, fi)); if (num_bytes != btrfs_file_extent_disk_num_bytes(leaf, fi)) { - ret = 1; + ret = -EINVAL; goto out; } @@ -1579,7 +1579,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, u64 end; u32 nritems; u32 i; - int ret; + int ret = 0; int first = 1; int dirty = 0; @@ -1642,11 +1642,13 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = get_new_location(rc->data_inode, &new_bytenr, bytenr, num_bytes); - if (ret > 0) { - WARN_ON(1); - continue; + if (ret) { + /* + * Don't have to abort since we've not changed anything + * in the file extent yet. + */ + break; } - BUG_ON(ret < 0); btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr); dirty = 1; @@ -1656,18 +1658,24 @@ int replace_file_extents(struct btrfs_trans_handle *trans, num_bytes, parent, btrfs_header_owner(leaf), key.objectid, key.offset, 1); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + break; + } ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), key.objectid, key.offset, 1); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + break; + } } if (dirty) btrfs_mark_buffer_dirty(leaf); if (inode) btrfs_add_delayed_iput(inode); - return 0; + return ret; } static noinline_for_stack @@ -4238,7 +4246,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) err = ret; goto out; } - btrfs_wait_all_ordered_extents(fs_info, 0); + btrfs_wait_all_ordered_extents(fs_info); while (1) { mutex_lock(&fs_info->cleaner_mutex); @@ -4499,19 +4507,19 @@ out: return ret; } -void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf, - struct extent_buffer *cow) +int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf, + struct extent_buffer *cow) { struct reloc_control *rc; struct backref_node *node; int first_cow = 0; int level; - int ret; + int ret = 0; rc = root->fs_info->reloc_ctl; if (!rc) - return; + return 0; BUG_ON(rc->stage == UPDATE_DATA_PTRS && root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID); @@ -4547,10 +4555,9 @@ void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, rc->nodes_relocated += buf->len; } - if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS) { + if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS) ret = replace_file_extents(trans, rc, root, cow); - BUG_ON(ret); - } + return ret; } /* diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0afcd45..a18e0e2 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -158,12 +158,20 @@ struct scrub_fixup_nodatasum { int mirror_num; }; +struct scrub_nocow_inode { + u64 inum; + u64 offset; + u64 root; + struct list_head list; +}; + struct scrub_copy_nocow_ctx { struct scrub_ctx *sctx; u64 logical; u64 len; int mirror_num; u64 physical_for_dev_replace; + struct list_head inodes; struct btrfs_work work; }; @@ -245,7 +253,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work); static int write_page_nocow(struct scrub_ctx *sctx, u64 physical_for_dev_replace, struct page *page); static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, - void *ctx); + struct scrub_copy_nocow_ctx *ctx); static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, int mirror_num, u64 physical_for_dev_replace); static void copy_nocow_pages_worker(struct btrfs_work *work); @@ -3126,12 +3134,30 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, nocow_ctx->mirror_num = mirror_num; nocow_ctx->physical_for_dev_replace = physical_for_dev_replace; nocow_ctx->work.func = copy_nocow_pages_worker; + INIT_LIST_HEAD(&nocow_ctx->inodes); btrfs_queue_worker(&fs_info->scrub_nocow_workers, &nocow_ctx->work); return 0; } +static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx) +{ + struct scrub_copy_nocow_ctx *nocow_ctx = ctx; + struct scrub_nocow_inode *nocow_inode; + + nocow_inode = kzalloc(sizeof(*nocow_inode), GFP_NOFS); + if (!nocow_inode) + return -ENOMEM; + nocow_inode->inum = inum; + nocow_inode->offset = offset; + nocow_inode->root = root; + list_add_tail(&nocow_inode->list, &nocow_ctx->inodes); + return 0; +} + +#define COPY_COMPLETE 1 + static void copy_nocow_pages_worker(struct btrfs_work *work) { struct scrub_copy_nocow_ctx *nocow_ctx = @@ -3167,8 +3193,7 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) } ret = iterate_inodes_from_logical(logical, fs_info, path, - copy_nocow_pages_for_inode, - nocow_ctx); + record_inode_for_nocow, nocow_ctx); if (ret != 0 && ret != -ENOENT) { pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n", logical, physical_for_dev_replace, len, mirror_num, @@ -3177,7 +3202,33 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) goto out; } + btrfs_end_transaction(trans, root); + trans = NULL; + while (!list_empty(&nocow_ctx->inodes)) { + struct scrub_nocow_inode *entry; + entry = list_first_entry(&nocow_ctx->inodes, + struct scrub_nocow_inode, + list); + list_del_init(&entry->list); + ret = copy_nocow_pages_for_inode(entry->inum, entry->offset, + entry->root, nocow_ctx); + kfree(entry); + if (ret == COPY_COMPLETE) { + ret = 0; + break; + } else if (ret) { + break; + } + } out: + while (!list_empty(&nocow_ctx->inodes)) { + struct scrub_nocow_inode *entry; + entry = list_first_entry(&nocow_ctx->inodes, + struct scrub_nocow_inode, + list); + list_del_init(&entry->list); + kfree(entry); + } if (trans && !IS_ERR(trans)) btrfs_end_transaction(trans, root); if (not_written) @@ -3190,20 +3241,25 @@ out: scrub_pending_trans_workers_dec(sctx); } -static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) +static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, + struct scrub_copy_nocow_ctx *nocow_ctx) { - struct scrub_copy_nocow_ctx *nocow_ctx = ctx; struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info; struct btrfs_key key; struct inode *inode; struct page *page; struct btrfs_root *local_root; + struct btrfs_ordered_extent *ordered; + struct extent_map *em; + struct extent_state *cached_state = NULL; + struct extent_io_tree *io_tree; u64 physical_for_dev_replace; - u64 len; + u64 len = nocow_ctx->len; + u64 lockstart = offset, lockend = offset + len - 1; unsigned long index; int srcu_index; - int ret; - int err; + int ret = 0; + int err = 0; key.objectid = root; key.type = BTRFS_ROOT_ITEM_KEY; @@ -3229,9 +3285,33 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) mutex_lock(&inode->i_mutex); inode_dio_wait(inode); - ret = 0; physical_for_dev_replace = nocow_ctx->physical_for_dev_replace; - len = nocow_ctx->len; + io_tree = &BTRFS_I(inode)->io_tree; + + lock_extent_bits(io_tree, lockstart, lockend, 0, &cached_state); + ordered = btrfs_lookup_ordered_range(inode, lockstart, len); + if (ordered) { + btrfs_put_ordered_extent(ordered); + goto out_unlock; + } + + em = btrfs_get_extent(inode, NULL, 0, lockstart, len, 0); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out_unlock; + } + + /* + * This extent does not actually cover the logical extent anymore, + * move on to the next inode. + */ + if (em->block_start > nocow_ctx->logical || + em->block_start + em->block_len < nocow_ctx->logical + len) { + free_extent_map(em); + goto out_unlock; + } + free_extent_map(em); + while (len >= PAGE_CACHE_SIZE) { index = offset >> PAGE_CACHE_SHIFT; again: @@ -3247,10 +3327,9 @@ again: goto next_page; } else { ClearPageError(page); - err = extent_read_full_page(&BTRFS_I(inode)-> - io_tree, - page, btrfs_get_extent, - nocow_ctx->mirror_num); + err = extent_read_full_page_nolock(io_tree, page, + btrfs_get_extent, + nocow_ctx->mirror_num); if (err) { ret = err; goto next_page; @@ -3264,6 +3343,7 @@ again: * page in the page cache. */ if (page->mapping != inode->i_mapping) { + unlock_page(page); page_cache_release(page); goto again; } @@ -3287,6 +3367,10 @@ next_page: physical_for_dev_replace += PAGE_CACHE_SIZE; len -= PAGE_CACHE_SIZE; } + ret = COPY_COMPLETE; +out_unlock: + unlock_extent_cached(io_tree, lockstart, lockend, &cached_state, + GFP_NOFS); out: mutex_unlock(&inode->i_mutex); iput(inode); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3aab10c..e913328 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -921,7 +921,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_wait_all_ordered_extents(fs_info, 1); + btrfs_wait_all_ordered_extents(fs_info); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { @@ -1340,6 +1340,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; } else { + if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) { + btrfs_err(fs_info, + "Remounting read-write after error is not allowed\n"); + ret = -EINVAL; + goto restore; + } if (fs_info->fs_devices->rw_devices == 0) { ret = -EACCES; goto restore; @@ -1377,6 +1383,16 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) pr_warn("btrfs: failed to resume dev_replace\n"); goto restore; } + + if (!fs_info->uuid_root) { + pr_info("btrfs: creating UUID tree\n"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + pr_warn("btrfs: failed to create the uuid tree" + "%d\n", ret); + goto restore; + } + } sb->s_flags &= ~MS_RDONLY; } out: @@ -1762,6 +1778,9 @@ static void btrfs_print_info(void) #ifdef CONFIG_BTRFS_DEBUG ", debug=on" #endif +#ifdef CONFIG_BTRFS_ASSERT + ", assert=on" +#endif #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY ", integrity-checker=on" #endif diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index cac4a3f..e7a9535 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1603,7 +1603,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT)) - btrfs_wait_all_ordered_extents(fs_info, 1); + btrfs_wait_all_ordered_extents(fs_info); } int btrfs_commit_transaction(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 0d9613c..79f057c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -93,7 +93,8 @@ */ #define LOG_WALK_PIN_ONLY 0 #define LOG_WALK_REPLAY_INODES 1 -#define LOG_WALK_REPLAY_ALL 2 +#define LOG_WALK_REPLAY_DIR_INDEX 2 +#define LOG_WALK_REPLAY_ALL 3 static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, @@ -393,6 +394,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, if (inode_item) { struct btrfs_inode_item *item; u64 nbytes; + u32 mode; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); @@ -400,9 +402,19 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, nbytes); + + /* + * If this is a directory we need to reset the i_size to + * 0 so that we can set it up properly when replaying + * the rest of the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } } else if (inode_item) { struct btrfs_inode_item *item; + u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out @@ -410,6 +422,15 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, */ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, 0); + + /* + * If this is a directory we need to reset the i_size to 0 so + * that we can set it up properly when replaying the rest of + * the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } insert: btrfs_release_path(path); @@ -1496,6 +1517,7 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, iput(inode); return -EIO; } + ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index); /* FIXME, put inode into FIXUP list */ @@ -1534,6 +1556,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, u8 log_type; int exists; int ret = 0; + bool update_size = (key->type == BTRFS_DIR_INDEX_KEY); dir = read_one_inode(root, key->objectid); if (!dir) @@ -1604,6 +1627,10 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto insert; out: btrfs_release_path(path); + if (!ret && update_size) { + btrfs_i_size_write(dir, dir->i_size + name_len * 2); + ret = btrfs_update_inode(trans, root, dir); + } kfree(name); iput(dir); return ret; @@ -1614,6 +1641,7 @@ insert: name, name_len, log_type, &log_key); if (ret && ret != -ENOENT) goto out; + update_size = false; ret = 0; goto out; } @@ -2027,6 +2055,15 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, if (ret) break; } + + if (key.type == BTRFS_DIR_INDEX_KEY && + wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { + ret = replay_one_dir_item(wc->trans, root, path, + eb, i, &key); + if (ret) + break; + } + if (wc->stage < LOG_WALK_REPLAY_ALL) continue; @@ -2048,8 +2085,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, eb, i, &key); if (ret) break; - } else if (key.type == BTRFS_DIR_ITEM_KEY || - key.type == BTRFS_DIR_INDEX_KEY) { + } else if (key.type == BTRFS_DIR_ITEM_KEY) { ret = replay_one_dir_item(wc->trans, root, path, eb, i, &key); if (ret) @@ -3805,6 +3841,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, int ret = 0; struct btrfs_root *root; struct dentry *old_parent = NULL; + struct inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -3824,7 +3861,14 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, } while (1) { - BTRFS_I(inode)->logged_trans = trans->transid; + /* + * If we are logging a directory then we start with our inode, + * not our parents inode, so we need to skipp setting the + * logged_trans so that further down in the log code we don't + * think this inode has already been logged. + */ + if (inode != orig_inode) + BTRFS_I(inode)->logged_trans = trans->transid; smp_mb(); if (BTRFS_I(inode)->last_unlink_trans > last_committed) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0052ca8..a106458 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -796,7 +796,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fs_devices->rotating = 1; fs_devices->open_devices++; - if (device->writeable && !device->is_tgtdev_for_dev_replace) { + if (device->writeable && + device->devid != BTRFS_DEV_REPLACE_DEVID) { fs_devices->rw_devices++; list_add(&device->dev_alloc_list, &fs_devices->alloc_list); @@ -911,9 +912,9 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, if (disk_super->label[0]) { if (disk_super->label[BTRFS_LABEL_SIZE - 1]) disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0'; - printk(KERN_INFO "device label %s ", disk_super->label); + printk(KERN_INFO "btrfs: device label %s ", disk_super->label); } else { - printk(KERN_INFO "device fsid %pU ", disk_super->fsid); + printk(KERN_INFO "btrfs: device fsid %pU ", disk_super->fsid); } printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path); diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index b5e80b0..38c1768 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -140,6 +140,17 @@ config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN If the NFS client is unchanged from the upstream kernel, this option should be set to the default "kernel.org". +config NFS_V4_1_MIGRATION + bool "NFSv4.1 client support for migration" + depends on NFS_V4_1 + default n + help + This option makes the NFS client advertise to NFSv4.1 servers that + it can support NFSv4 migration. + + The NFSv4.1 pieces of the Linux NFSv4 migration implementation are + still experimental. If you are not an NFSv4 developer, say N here. + config NFS_V4_SECURITY_LABEL bool depends on NFS_V4_2 && SECURITY diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 67cd732..073b4cf 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -164,8 +164,7 @@ nfs41_callback_up(struct svc_serv *serv) svc_xprt_put(serv->sv_bc_xprt); serv->sv_bc_xprt = NULL; } - dprintk("--> %s return %ld\n", __func__, - IS_ERR(rqstp) ? PTR_ERR(rqstp) : 0); + dprintk("--> %s return %d\n", __func__, PTR_ERR_OR_ZERO(rqstp)); return rqstp; } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 2dceee4..1d09289 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -590,6 +590,8 @@ int nfs_create_rpc_client(struct nfs_client *clp, if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_DISCRTRY; + if (test_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags)) + args.flags |= RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT; if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags)) @@ -784,8 +786,10 @@ static int nfs_init_server(struct nfs_server *server, goto error; server->port = data->nfs_server.port; + server->auth_info = data->auth_info; - error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]); + error = nfs_init_server_rpcclient(server, &timeparms, + data->selected_flavor); if (error < 0) goto error; @@ -926,6 +930,7 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour target->acdirmax = source->acdirmax; target->caps = source->caps; target->options = source->options; + target->auth_info = source->auth_info; } EXPORT_SYMBOL_GPL(nfs_server_copy_userdata); @@ -943,7 +948,7 @@ void nfs_server_insert_lists(struct nfs_server *server) } EXPORT_SYMBOL_GPL(nfs_server_insert_lists); -static void nfs_server_remove_lists(struct nfs_server *server) +void nfs_server_remove_lists(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; struct nfs_net *nn; @@ -960,6 +965,7 @@ static void nfs_server_remove_lists(struct nfs_server *server) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nfs_server_remove_lists); /* * Allocate and initialise a server record diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 4c5edcc..9a8676f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1139,7 +1139,13 @@ out_zap_parent: if (inode && S_ISDIR(inode->i_mode)) { /* Purge readdir caches. */ nfs_zap_caches(inode); - if (dentry->d_flags & DCACHE_DISCONNECTED) + /* + * We can't d_drop the root of a disconnected tree: + * its d_hash is on the s_anon list and d_drop() would hide + * it from shrink_dcache_for_unmount(), leading to busy + * inodes on unmount and further oopses. + */ + if (IS_ROOT(dentry)) goto out_valid; } /* If we have submounts, don't unhash ! */ @@ -1458,7 +1464,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, trace_nfs_atomic_open_enter(dir, ctx, open_flags); nfs_block_sillyrename(dentry->d_parent); - inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); + inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened); nfs_unblock_sillyrename(dentry->d_parent); if (IS_ERR(inode)) { err = PTR_ERR(inode); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bb90bff..471ba59 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1209,6 +1209,7 @@ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) * not on the result */ return nfs_fhandle_hash(fh); } +EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); /* * _nfs_display_fhandle - display an NFS file handle on the console @@ -1253,6 +1254,7 @@ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) } } } +EXPORT_SYMBOL_GPL(_nfs_display_fhandle); #endif /** diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 38da8c2..bca6a3e 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -88,8 +88,8 @@ struct nfs_parsed_mount_data { unsigned int namlen; unsigned int options; unsigned int bsize; - unsigned int auth_flavor_len; - rpc_authflavor_t auth_flavors[1]; + struct nfs_auth_info auth_info; + rpc_authflavor_t selected_flavor; char *client_address; unsigned int version; unsigned int minorversion; @@ -154,6 +154,7 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *, rpc_authflavor_t); int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); void nfs_server_insert_lists(struct nfs_server *); +void nfs_server_remove_lists(struct nfs_server *); void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int); int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, rpc_authflavor_t); @@ -174,6 +175,8 @@ extern struct nfs_server *nfs4_create_server( struct nfs_subversion *); extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, struct nfs_fh *); +extern int nfs4_update_server(struct nfs_server *server, const char *hostname, + struct sockaddr *sap, size_t salen); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, @@ -323,6 +326,7 @@ extern struct file_system_type nfs_xdev_fs_type; extern struct file_system_type nfs4_xdev_fs_type; extern struct file_system_type nfs4_referral_fs_type; #endif +bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *); void nfs_initialise_sb(struct super_block *); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 28842ab..3ce79b0 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -29,6 +29,8 @@ enum nfs4_client_state { NFS4CLNT_SERVER_SCOPE_MISMATCH, NFS4CLNT_PURGE_STATE, NFS4CLNT_BIND_CONN_TO_SESSION, + NFS4CLNT_MOVED, + NFS4CLNT_LEASE_MOVED, }; #define NFS4_RENEW_TIMEOUT 0x01 @@ -50,6 +52,7 @@ struct nfs4_minor_version_ops { const struct nfs4_state_recovery_ops *reboot_recovery_ops; const struct nfs4_state_recovery_ops *nograce_recovery_ops; const struct nfs4_state_maintenance_ops *state_renewal_ops; + const struct nfs4_mig_recovery_ops *mig_recovery_ops; }; #define NFS_SEQID_CONFIRMED 1 @@ -203,6 +206,12 @@ struct nfs4_state_maintenance_ops { int (*renew_lease)(struct nfs_client *, struct rpc_cred *); }; +struct nfs4_mig_recovery_ops { + int (*get_locations)(struct inode *, struct nfs4_fs_locations *, + struct page *, struct rpc_cred *); + int (*fsid_present)(struct inode *, struct rpc_cred *); +}; + extern const struct dentry_operations nfs4_dentry_operations; /* dir.c */ @@ -213,10 +222,11 @@ int nfs_atomic_open(struct inode *, struct dentry *, struct file *, extern struct file_system_type nfs4_fs_type; /* nfs4namespace.c */ -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); +int nfs4_replace_transport(struct nfs_server *server, + const struct nfs4_fs_locations *locations); /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); @@ -231,6 +241,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); +extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, + struct page *page, struct rpc_cred *); +extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *, struct nfs_fh *, struct nfs_fattr *); extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); @@ -411,6 +424,8 @@ extern int nfs4_client_recover_expired_lease(struct nfs_client *clp); extern void nfs4_schedule_state_manager(struct nfs_client *); extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp); extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *); +extern int nfs4_schedule_migration_recovery(const struct nfs_server *); +extern void nfs4_schedule_lease_moved_recovery(struct nfs_client *); extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_server_scope(struct nfs_client *, struct nfs41_server_scope **); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index a860ab5..b4a160a 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -197,6 +197,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; + clp->cl_mig_gen = 1; return clp; error: @@ -368,6 +369,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (clp->cl_minorversion != 0) __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags); __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags); error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I); if (error == -EINVAL) error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); @@ -924,7 +926,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, dprintk("Server FSID: %llx:%llx\n", (unsigned long long) server->fsid.major, (unsigned long long) server->fsid.minor); - dprintk("Mount FH: %d\n", mntfh->size); + nfs_display_fhandle(mntfh, "Pseudo-fs root FH"); nfs4_session_set_rwsize(server); @@ -947,9 +949,8 @@ out: * Create a version 4 volume record */ static int nfs4_init_server(struct nfs_server *server, - const struct nfs_parsed_mount_data *data) + struct nfs_parsed_mount_data *data) { - rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; struct rpc_timeout timeparms; int error; @@ -961,9 +962,15 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; server->options = data->options; + server->auth_info = data->auth_info; - if (data->auth_flavor_len >= 1) - pseudoflavor = data->auth_flavors[0]; + /* Use the first specified auth flavor. If this flavor isn't + * allowed by the server, use the SECINFO path to try the + * other specified flavors */ + if (data->auth_info.flavor_len >= 1) + data->selected_flavor = data->auth_info.flavors[0]; + else + data->selected_flavor = RPC_AUTH_UNIX; /* Get a client record */ error = nfs4_set_client(server, @@ -971,7 +978,7 @@ static int nfs4_init_server(struct nfs_server *server, (const struct sockaddr *)&data->nfs_server.address, data->nfs_server.addrlen, data->client_address, - pseudoflavor, + data->selected_flavor, data->nfs_server.protocol, &timeparms, data->minorversion, @@ -991,7 +998,8 @@ static int nfs4_init_server(struct nfs_server *server, server->port = data->nfs_server.port; - error = nfs_init_server_rpcclient(server, &timeparms, pseudoflavor); + error = nfs_init_server_rpcclient(server, &timeparms, + data->selected_flavor); error: /* Done */ @@ -1018,7 +1026,7 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, if (!server) return ERR_PTR(-ENOMEM); - auth_probe = mount_info->parsed->auth_flavor_len < 1; + auth_probe = mount_info->parsed->auth_info.flavor_len < 1; /* set up the general RPC client */ error = nfs4_init_server(server, mount_info->parsed); @@ -1046,6 +1054,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, { struct nfs_client *parent_client; struct nfs_server *server, *parent_server; + bool auth_probe; int error; dprintk("--> nfs4_create_referral_server()\n"); @@ -1078,8 +1087,9 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, if (error < 0) goto error; - error = nfs4_server_common_setup(server, mntfh, - !(parent_server->flags & NFS_MOUNT_SECFLAVOUR)); + auth_probe = parent_server->auth_info.flavor_len < 1; + + error = nfs4_server_common_setup(server, mntfh, auth_probe); if (error < 0) goto error; @@ -1091,3 +1101,111 @@ error: dprintk("<-- nfs4_create_referral_server() = error %d\n", error); return ERR_PTR(error); } + +/* + * Grab the destination's particulars, including lease expiry time. + * + * Returns zero if probe succeeded and retrieved FSID matches the FSID + * we have cached. + */ +static int nfs_probe_destination(struct nfs_server *server) +{ + struct inode *inode = server->super->s_root->d_inode; + struct nfs_fattr *fattr; + int error; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + return -ENOMEM; + + /* Sanity: the probe won't work if the destination server + * does not recognize the migrated FH. */ + error = nfs_probe_fsinfo(server, NFS_FH(inode), fattr); + + nfs_free_fattr(fattr); + return error; +} + +/** + * nfs4_update_server - Move an nfs_server to a different nfs_client + * + * @server: represents FSID to be moved + * @hostname: new end-point's hostname + * @sap: new end-point's socket address + * @salen: size of "sap" + * + * The nfs_server must be quiescent before this function is invoked. + * Either its session is drained (NFSv4.1+), or its transport is + * plugged and drained (NFSv4.0). + * + * Returns zero on success, or a negative errno value. + */ +int nfs4_update_server(struct nfs_server *server, const char *hostname, + struct sockaddr *sap, size_t salen) +{ + struct nfs_client *clp = server->nfs_client; + struct rpc_clnt *clnt = server->client; + struct xprt_create xargs = { + .ident = clp->cl_proto, + .net = &init_net, + .dstaddr = sap, + .addrlen = salen, + .servername = hostname, + }; + char buf[INET6_ADDRSTRLEN + 1]; + struct sockaddr_storage address; + struct sockaddr *localaddr = (struct sockaddr *)&address; + int error; + + dprintk("--> %s: move FSID %llx:%llx to \"%s\")\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + hostname); + + error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout); + if (error != 0) { + dprintk("<-- %s(): rpc_switch_client_transport returned %d\n", + __func__, error); + goto out; + } + + error = rpc_localaddr(clnt, localaddr, sizeof(address)); + if (error != 0) { + dprintk("<-- %s(): rpc_localaddr returned %d\n", + __func__, error); + goto out; + } + + error = -EAFNOSUPPORT; + if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0) { + dprintk("<-- %s(): rpc_ntop returned %d\n", + __func__, error); + goto out; + } + + nfs_server_remove_lists(server); + error = nfs4_set_client(server, hostname, sap, salen, buf, + clp->cl_rpcclient->cl_auth->au_flavor, + clp->cl_proto, clnt->cl_timeout, + clp->cl_minorversion, clp->cl_net); + nfs_put_client(clp); + if (error != 0) { + nfs_server_insert_lists(server); + dprintk("<-- %s(): nfs4_set_client returned %d\n", + __func__, error); + goto out; + } + + if (server->nfs_client->cl_hostname == NULL) + server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + nfs_server_insert_lists(server); + + error = nfs_probe_destination(server); + if (error < 0) + goto out; + + dprintk("<-- %s() succeeded\n", __func__); + +out: + return error; +} diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 5b8a618..1f01b55 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -19,6 +19,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct inode *dir; unsigned openflags = filp->f_flags; struct iattr attr; + int opened = 0; int err; /* @@ -55,7 +56,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) nfs_wb_all(inode); } - inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, &opened); if (IS_ERR(inode)) { err = PTR_ERR(inode); switch (err) { diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index 95604f6..c7c295e5 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -185,6 +185,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds) if (status) goto out_put; + smp_wmb(); ds->ds_clp = clp; dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr); out: @@ -801,34 +802,35 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr; struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx]; struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); - - if (filelayout_test_devid_unavailable(devid)) - return NULL; + struct nfs4_pnfs_ds *ret = ds; if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", __func__, ds_idx); filelayout_mark_devid_invalid(devid); - return NULL; + goto out; } + smp_rmb(); if (ds->ds_clp) - return ds; + goto out_test_devid; if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) { struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); int err; err = nfs4_ds_connect(s, ds); - if (err) { + if (err) nfs4_mark_deviceid_unavailable(devid); - ds = NULL; - } nfs4_clear_ds_conn_bit(ds); } else { /* Either ds is connected, or ds is NULL */ nfs4_wait_ds_connect(ds); } - return ds; +out_test_devid: + if (filelayout_test_devid_unavailable(devid)) + ret = NULL; +out: + return ret; } module_param(dataserver_retrans, uint, 0644); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 2288cd3..c08cbf4 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -137,6 +137,7 @@ static size_t nfs_parse_server_name(char *string, size_t len, /** * nfs_find_best_sec - Find a security mechanism supported locally + * @server: NFS server struct * @flavors: List of security tuples returned by SECINFO procedure * * Return the pseudoflavor of the first security mechanism in @@ -145,7 +146,8 @@ static size_t nfs_parse_server_name(char *string, size_t len, * is searched in the order returned from the server, per RFC 3530 * recommendation. */ -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) +static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server, + struct nfs4_secinfo_flavors *flavors) { rpc_authflavor_t pseudoflavor; struct nfs4_secinfo4 *secinfo; @@ -160,12 +162,19 @@ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) case RPC_AUTH_GSS: pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor, &secinfo->flavor_info); - if (pseudoflavor != RPC_AUTH_MAXFLAVOR) + /* make sure pseudoflavor matches sec= mount opt */ + if (pseudoflavor != RPC_AUTH_MAXFLAVOR && + nfs_auth_info_match(&server->auth_info, + pseudoflavor)) return pseudoflavor; break; } } + /* if there were any sec= options then nothing matched */ + if (server->auth_info.flavor_len > 0) + return -EPERM; + return RPC_AUTH_UNIX; } @@ -187,7 +196,7 @@ static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr goto out; } - flavor = nfs_find_best_sec(flavors); + flavor = nfs_find_best_sec(NFS_SERVER(inode), flavors); out: put_page(page); @@ -390,7 +399,7 @@ struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, if (client->cl_auth->au_flavor != flavor) flavor = client->cl_auth->au_flavor; - else if (!(server->flags & NFS_MOUNT_SECFLAVOUR)) { + else { rpc_authflavor_t new = nfs4_negotiate_security(dir, name); if ((int)new >= 0) flavor = new; @@ -400,3 +409,104 @@ out: rpc_shutdown_client(client); return mnt; } + +/* + * Try one location from the fs_locations array. + * + * Returns zero on success, or a negative errno value. + */ +static int nfs4_try_replacing_one_location(struct nfs_server *server, + char *page, char *page2, + const struct nfs4_fs_location *location) +{ + const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct sockaddr *sap; + unsigned int s; + size_t salen; + int error; + + sap = kmalloc(addr_bufsize, GFP_KERNEL); + if (sap == NULL) + return -ENOMEM; + + error = -ENOENT; + for (s = 0; s < location->nservers; s++) { + const struct nfs4_string *buf = &location->servers[s]; + char *hostname; + + if (buf->len <= 0 || buf->len > PAGE_SIZE) + continue; + + if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len) != NULL) + continue; + + salen = nfs_parse_server_name(buf->data, buf->len, + sap, addr_bufsize, server); + if (salen == 0) + continue; + rpc_set_port(sap, NFS_PORT); + + error = -ENOMEM; + hostname = kstrndup(buf->data, buf->len, GFP_KERNEL); + if (hostname == NULL) + break; + + error = nfs4_update_server(server, hostname, sap, salen); + kfree(hostname); + if (error == 0) + break; + } + + kfree(sap); + return error; +} + +/** + * nfs4_replace_transport - set up transport to destination server + * + * @server: export being migrated + * @locations: fs_locations array + * + * Returns zero on success, or a negative errno value. + * + * The client tries all the entries in the "locations" array, in the + * order returned by the server, until one works or the end of the + * array is reached. + */ +int nfs4_replace_transport(struct nfs_server *server, + const struct nfs4_fs_locations *locations) +{ + char *page = NULL, *page2 = NULL; + int loc, error; + + error = -ENOENT; + if (locations == NULL || locations->nlocations <= 0) + goto out; + + error = -ENOMEM; + page = (char *) __get_free_page(GFP_USER); + if (!page) + goto out; + page2 = (char *) __get_free_page(GFP_USER); + if (!page2) + goto out; + + for (loc = 0; loc < locations->nlocations; loc++) { + const struct nfs4_fs_location *location = + &locations->locations[loc]; + + if (location == NULL || location->nservers <= 0 || + location->rootpath.ncomponents == 0) + continue; + + error = nfs4_try_replacing_one_location(server, page, + page2, location); + if (error == 0) + break; + } + +out: + free_page((unsigned long)page); + free_page((unsigned long)page2); + return error; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 989bb9d..b02c4cc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -384,6 +384,14 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc case -NFS4ERR_STALE_CLIENTID: nfs4_schedule_lease_recovery(clp); goto wait_on_recovery; + case -NFS4ERR_MOVED: + ret = nfs4_schedule_migration_recovery(server); + if (ret < 0) + break; + goto wait_on_recovery; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + goto wait_on_recovery; #if defined(CONFIG_NFS_V4_1) case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -431,6 +439,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc return nfs4_map_errors(ret); wait_on_recovery: ret = nfs4_wait_clnt_recover(clp); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -EIO; if (ret == 0) exception->retry = 1; return ret; @@ -912,6 +922,7 @@ struct nfs4_opendata { struct iattr attrs; unsigned long timestamp; unsigned int rpc_done : 1; + unsigned int file_created : 1; unsigned int is_recover : 1; int rpc_status; int cancelled; @@ -1317,31 +1328,24 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) int ret; if (!data->rpc_done) { - ret = data->rpc_status; - goto err; + if (data->rpc_status) { + ret = data->rpc_status; + goto err; + } + /* cached opens have already been processed */ + goto update; } - ret = -ESTALE; - if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) || - !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) || - !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE)) - goto err; - - ret = -ENOMEM; - state = nfs4_get_open_state(inode, data->owner); - if (state == NULL) - goto err; - ret = nfs_refresh_inode(inode, &data->f_attr); if (ret) goto err; - nfs_setsecurity(inode, &data->f_attr, data->f_label); - if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); +update: update_open_stateid(state, &data->o_res.stateid, NULL, data->o_arg.fmode); + atomic_inc(&state->count); return state; err: @@ -1574,6 +1578,12 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct /* Don't recall a delegation if it was lost */ nfs4_schedule_lease_recovery(server->nfs_client); return -EAGAIN; + case -NFS4ERR_MOVED: + nfs4_schedule_migration_recovery(server); + return -EAGAIN; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(server->nfs_client); + return -EAGAIN; case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: @@ -1946,8 +1956,13 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(server, &data->f_attr); - if (o_arg->open_flags & O_CREAT) + if (o_arg->open_flags & O_CREAT) { update_changeattr(dir, &o_res->cinfo); + if (o_arg->open_flags & O_EXCL) + data->file_created = 1; + else if (o_res->cinfo.before != o_res->cinfo.after) + data->file_created = 1; + } if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) server->caps &= ~NFS_CAP_POSIX_LOCK; if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { @@ -2191,7 +2206,8 @@ static int _nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, struct iattr *sattr, - struct nfs4_label *label) + struct nfs4_label *label, + int *opened) { struct nfs4_state_owner *sp; struct nfs4_state *state = NULL; @@ -2261,6 +2277,8 @@ static int _nfs4_do_open(struct inode *dir, nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel); } } + if (opendata->file_created) + *opened |= FILE_CREATED; if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) *ctx_th = opendata->f_attr.mdsthreshold; @@ -2289,7 +2307,8 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct nfs_open_context *ctx, int flags, struct iattr *sattr, - struct nfs4_label *label) + struct nfs4_label *label, + int *opened) { struct nfs_server *server = NFS_SERVER(dir); struct nfs4_exception exception = { }; @@ -2297,7 +2316,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, int status; do { - status = _nfs4_do_open(dir, ctx, flags, sattr, label); + status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened); res = ctx->state; trace_nfs4_open_file(ctx, flags, status); if (status == 0) @@ -2659,7 +2678,8 @@ out: } static struct inode * -nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags, struct iattr *attr) +nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, + int open_flags, struct iattr *attr, int *opened) { struct nfs4_state *state; struct nfs4_label l = {0, 0, 0, NULL}, *label = NULL; @@ -2667,7 +2687,7 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags label = nfs4_label_init_security(dir, ctx->dentry, attr, &l); /* Protect against concurrent sillydeletes */ - state = nfs4_do_open(dir, ctx, open_flags, attr, label); + state = nfs4_do_open(dir, ctx, open_flags, attr, label, opened); nfs4_label_release_security(label); @@ -2853,11 +2873,24 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, int status = -EPERM; size_t i; - for (i = 0; i < ARRAY_SIZE(flav_array); i++) { - status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]); - if (status == -NFS4ERR_WRONGSEC || status == -EACCES) - continue; - break; + if (server->auth_info.flavor_len > 0) { + /* try each flavor specified by user */ + for (i = 0; i < server->auth_info.flavor_len; i++) { + status = nfs4_lookup_root_sec(server, fhandle, info, + server->auth_info.flavors[i]); + if (status == -NFS4ERR_WRONGSEC || status == -EACCES) + continue; + break; + } + } else { + /* no flavors specified by user, try default list */ + for (i = 0; i < ARRAY_SIZE(flav_array); i++) { + status = nfs4_lookup_root_sec(server, fhandle, info, + flav_array[i]); + if (status == -NFS4ERR_WRONGSEC || status == -EACCES) + continue; + break; + } } /* @@ -2899,9 +2932,6 @@ int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle, status = nfs4_lookup_root(server, fhandle, info); if (status != -NFS4ERR_WRONGSEC) break; - /* Did user force a 'sec=' mount option? */ - if (server->flags & NFS_MOUNT_SECFLAVOUR) - break; default: status = nfs4_do_find_root_sec(server, fhandle, info); } @@ -2970,11 +3000,16 @@ static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, status = nfs4_proc_fs_locations(client, dir, name, locations, page); if (status != 0) goto out; - /* Make sure server returned a different fsid for the referral */ + + /* + * If the fsid didn't change, this is a migration event, not a + * referral. Cause us to drop into the exception handler, which + * will kick off migration recovery. + */ if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) { dprintk("%s: server did not return a different fsid for" " a referral at %s\n", __func__, name->name); - status = -EIO; + status = -NFS4ERR_MOVED; goto out; } /* Fixup attributes for the nfs_lookup() call to nfs_fhget() */ @@ -3154,9 +3189,6 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, err = -EPERM; if (client != *clnt) goto out; - /* No security negotiation if the user specified 'sec=' */ - if (NFS_SERVER(dir)->flags & NFS_MOUNT_SECFLAVOUR) - goto out; client = nfs4_create_sec_client(client, dir, name); if (IS_ERR(client)) return PTR_ERR(client); @@ -3332,6 +3364,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, struct nfs4_label l, *ilabel = NULL; struct nfs_open_context *ctx; struct nfs4_state *state; + int opened = 0; int status = 0; ctx = alloc_nfs_open_context(dentry, FMODE_READ); @@ -3341,7 +3374,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, ilabel = nfs4_label_init_security(dir, dentry, sattr, &l); sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, ctx, flags, sattr, ilabel); + state = nfs4_do_open(dir, ctx, flags, sattr, ilabel, &opened); if (IS_ERR(state)) { status = PTR_ERR(state); goto out; @@ -4209,7 +4242,13 @@ static void nfs4_renew_done(struct rpc_task *task, void *calldata) unsigned long timestamp = data->timestamp; trace_nfs4_renew_async(clp, task->tk_status); - if (task->tk_status < 0) { + switch (task->tk_status) { + case 0: + break; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + break; + default: /* Unless we're shutting down, schedule state recovery! */ if (test_bit(NFS_CS_RENEWD, &clp->cl_res_state) == 0) return; @@ -4723,17 +4762,24 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, if (state == NULL) break; if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto stateid_invalid; + goto recovery_failed; goto wait_on_recovery; case -NFS4ERR_EXPIRED: if (state != NULL) { if (nfs4_schedule_stateid_recovery(server, state) < 0) - goto stateid_invalid; + goto recovery_failed; } case -NFS4ERR_STALE_STATEID: case -NFS4ERR_STALE_CLIENTID: nfs4_schedule_lease_recovery(clp); goto wait_on_recovery; + case -NFS4ERR_MOVED: + if (nfs4_schedule_migration_recovery(server) < 0) + goto recovery_failed; + goto wait_on_recovery; + case -NFS4ERR_LEASE_MOVED: + nfs4_schedule_lease_moved_recovery(clp); + goto wait_on_recovery; #if defined(CONFIG_NFS_V4_1) case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -4745,29 +4791,28 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, dprintk("%s ERROR %d, Reset session\n", __func__, task->tk_status); nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); - task->tk_status = 0; - return -EAGAIN; + goto restart_call; #endif /* CONFIG_NFS_V4_1 */ case -NFS4ERR_DELAY: nfs_inc_server_stats(server, NFSIOS_DELAY); case -NFS4ERR_GRACE: rpc_delay(task, NFS4_POLL_RETRY_MAX); - task->tk_status = 0; - return -EAGAIN; case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_OLD_STATEID: - task->tk_status = 0; - return -EAGAIN; + goto restart_call; } task->tk_status = nfs4_map_errors(task->tk_status); return 0; -stateid_invalid: +recovery_failed: task->tk_status = -EIO; return 0; wait_on_recovery: rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL); if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0) rpc_wake_up_queued_task(&clp->cl_rpcwaitq, task); + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + goto recovery_failed; +restart_call: task->tk_status = 0; return -EAGAIN; } @@ -5094,6 +5139,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock status = 0; } request->fl_ops->fl_release_private(request); + request->fl_ops = NULL; out: return status; } @@ -5767,6 +5813,7 @@ struct nfs_release_lockowner_data { struct nfs_release_lockowner_args args; struct nfs4_sequence_args seq_args; struct nfs4_sequence_res seq_res; + unsigned long timestamp; }; static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata) @@ -5774,12 +5821,27 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata struct nfs_release_lockowner_data *data = calldata; nfs40_setup_sequence(data->server, &data->seq_args, &data->seq_res, task); + data->timestamp = jiffies; } static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata) { struct nfs_release_lockowner_data *data = calldata; + struct nfs_server *server = data->server; + nfs40_sequence_done(task, &data->seq_res); + + switch (task->tk_status) { + case 0: + renew_lease(server, data->timestamp); + break; + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_EXPIRED: + case -NFS4ERR_LEASE_MOVED: + case -NFS4ERR_DELAY: + if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) + rpc_restart_call_prepare(task); + } } static void nfs4_release_lockowner_release(void *calldata) @@ -5978,6 +6040,283 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, return err; } +/* + * This operation also signals the server that this client is + * performing migration recovery. The server can stop returning + * NFS4ERR_LEASE_MOVED to this client. A RENEW operation is + * appended to this compound to identify the client ID which is + * performing recovery. + */ +static int _nfs40_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .clientid = server->nfs_client->cl_clientid, + .fh = NFS_FH(inode), + .page = page, + .bitmask = bitmask, + .migration = 1, /* skip LOOKUP */ + .renew = 1, /* append RENEW */ + }; + struct nfs4_fs_locations_res res = { + .fs_locations = locations, + .migration = 1, + .renew = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + nfs_fattr_init(&locations->fattr); + locations->server = server; + locations->nlocations = 0; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + if (status) + return status; + + renew_lease(server, now); + return 0; +} + +#ifdef CONFIG_NFS_V4_1 + +/* + * This operation also signals the server that this client is + * performing migration recovery. The server can stop asserting + * SEQ4_STATUS_LEASE_MOVED for this client. The client ID + * performing this operation is identified in the SEQUENCE + * operation in this compound. + * + * When the client supports GETATTR(fs_locations_info), it can + * be plumbed in here. + */ +static int _nfs41_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + }; + struct nfs4_fs_locations_arg args = { + .fh = NFS_FH(inode), + .page = page, + .bitmask = bitmask, + .migration = 1, /* skip LOOKUP */ + }; + struct nfs4_fs_locations_res res = { + .fs_locations = locations, + .migration = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + nfs_fattr_init(&locations->fattr); + locations->server = server; + locations->nlocations = 0; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + if (status == NFS4_OK && + res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) + status = -NFS4ERR_LEASE_MOVED; + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_proc_get_locations - discover locations for a migrated FSID + * @inode: inode on FSID that is migrating + * @locations: result of query + * @page: buffer + * @cred: credential to use for this operation + * + * Returns NFS4_OK on success, a negative NFS4ERR status code if the + * operation failed, or a negative errno if a local error occurred. + * + * On success, "locations" is filled in, but if the server has + * no locations information, NFS_ATTR_FATTR_V4_LOCATIONS is not + * asserted. + * + * -NFS4ERR_LEASE_MOVED is returned if the server still has leases + * from this client that require migration recovery. + */ +int nfs4_proc_get_locations(struct inode *inode, + struct nfs4_fs_locations *locations, + struct page *page, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + const struct nfs4_mig_recovery_ops *ops = + clp->cl_mvops->mig_recovery_ops; + struct nfs4_exception exception = { }; + int status; + + dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + nfs_display_fhandle(NFS_FH(inode), __func__); + + do { + status = ops->get_locations(inode, locations, page, cred); + if (status != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, status, &exception); + } while (exception.retry); + return status; +} + +/* + * This operation also signals the server that this client is + * performing "lease moved" recovery. The server can stop + * returning NFS4ERR_LEASE_MOVED to this client. A RENEW operation + * is appended to this compound to identify the client ID which is + * performing recovery. + */ +static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; + struct rpc_clnt *clnt = server->client; + struct nfs4_fsid_present_arg args = { + .fh = NFS_FH(inode), + .clientid = clp->cl_clientid, + .renew = 1, /* append RENEW */ + }; + struct nfs4_fsid_present_res res = { + .renew = 1, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + unsigned long now = jiffies; + int status; + + res.fh = nfs_alloc_fhandle(); + if (res.fh == NULL) + return -ENOMEM; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + nfs_free_fhandle(res.fh); + if (status) + return status; + + do_renew_lease(clp, now); + return 0; +} + +#ifdef CONFIG_NFS_V4_1 + +/* + * This operation also signals the server that this client is + * performing "lease moved" recovery. The server can stop asserting + * SEQ4_STATUS_LEASE_MOVED for this client. The client ID performing + * this operation is identified in the SEQUENCE operation in this + * compound. + */ +static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct rpc_clnt *clnt = server->client; + struct nfs4_fsid_present_arg args = { + .fh = NFS_FH(inode), + }; + struct nfs4_fsid_present_res res = { + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FSID_PRESENT], + .rpc_argp = &args, + .rpc_resp = &res, + .rpc_cred = cred, + }; + int status; + + res.fh = nfs_alloc_fhandle(); + if (res.fh == NULL) + return -ENOMEM; + + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0); + nfs4_set_sequence_privileged(&args.seq_args); + status = nfs4_call_sync_sequence(clnt, server, &msg, + &args.seq_args, &res.seq_res); + nfs_free_fhandle(res.fh); + if (status == NFS4_OK && + res.seq_res.sr_status_flags & SEQ4_STATUS_LEASE_MOVED) + status = -NFS4ERR_LEASE_MOVED; + return status; +} + +#endif /* CONFIG_NFS_V4_1 */ + +/** + * nfs4_proc_fsid_present - Is this FSID present or absent on server? + * @inode: inode on FSID to check + * @cred: credential to use for this operation + * + * Server indicates whether the FSID is present, moved, or not + * recognized. This operation is necessary to clear a LEASE_MOVED + * condition for this client ID. + * + * Returns NFS4_OK if the FSID is present on this server, + * -NFS4ERR_MOVED if the FSID is no longer present, a negative + * NFS4ERR code if some error occurred on the server, or a + * negative errno if a local failure occurred. + */ +int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + struct nfs_client *clp = server->nfs_client; + const struct nfs4_mig_recovery_ops *ops = + clp->cl_mvops->mig_recovery_ops; + struct nfs4_exception exception = { }; + int status; + + dprintk("%s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + nfs_display_fhandle(NFS_FH(inode), __func__); + + do { + status = ops->fsid_present(inode, cred); + if (status != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, status, &exception); + } while (exception.retry); + return status; +} + /** * If 'use_integrity' is true and the state managment nfs_client * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient @@ -6264,8 +6603,14 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, struct nfs41_exchange_id_args args = { .verifier = &verifier, .client = clp, +#ifdef CONFIG_NFS_V4_1_MIGRATION .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | - EXCHGID4_FLAG_BIND_PRINC_STATEID, + EXCHGID4_FLAG_BIND_PRINC_STATEID | + EXCHGID4_FLAG_SUPP_MOVED_MIGR, +#else + .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | + EXCHGID4_FLAG_BIND_PRINC_STATEID, +#endif }; struct nfs41_exchange_id_res res = { 0 @@ -7564,8 +7909,10 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, { int err; struct page *page; - rpc_authflavor_t flavor; + rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; struct nfs4_secinfo_flavors *flavors; + struct nfs4_secinfo4 *secinfo; + int i; page = alloc_page(GFP_KERNEL); if (!page) { @@ -7587,9 +7934,34 @@ nfs41_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, if (err) goto out_freepage; - flavor = nfs_find_best_sec(flavors); - if (err == 0) - err = nfs4_lookup_root_sec(server, fhandle, info, flavor); + for (i = 0; i < flavors->num_flavors; i++) { + secinfo = &flavors->flavors[i]; + + switch (secinfo->flavor) { + case RPC_AUTH_NULL: + case RPC_AUTH_UNIX: + case RPC_AUTH_GSS: + flavor = rpcauth_get_pseudoflavor(secinfo->flavor, + &secinfo->flavor_info); + break; + default: + flavor = RPC_AUTH_MAXFLAVOR; + break; + } + + if (!nfs_auth_info_match(&server->auth_info, flavor)) + flavor = RPC_AUTH_MAXFLAVOR; + + if (flavor != RPC_AUTH_MAXFLAVOR) { + err = nfs4_lookup_root_sec(server, fhandle, + info, flavor); + if (!err) + break; + } + } + + if (flavor == RPC_AUTH_MAXFLAVOR) + err = -EPERM; out_freepage: put_page(page); @@ -7851,6 +8223,18 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = { }; #endif +static const struct nfs4_mig_recovery_ops nfs40_mig_recovery_ops = { + .get_locations = _nfs40_proc_get_locations, + .fsid_present = _nfs40_proc_fsid_present, +}; + +#if defined(CONFIG_NFS_V4_1) +static const struct nfs4_mig_recovery_ops nfs41_mig_recovery_ops = { + .get_locations = _nfs41_proc_get_locations, + .fsid_present = _nfs41_proc_fsid_present, +}; +#endif /* CONFIG_NFS_V4_1 */ + static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, .init_caps = NFS_CAP_READDIRPLUS @@ -7866,6 +8250,7 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .reboot_recovery_ops = &nfs40_reboot_recovery_ops, .nograce_recovery_ops = &nfs40_nograce_recovery_ops, .state_renewal_ops = &nfs40_state_renewal_ops, + .mig_recovery_ops = &nfs40_mig_recovery_ops, }; #if defined(CONFIG_NFS_V4_1) @@ -7886,6 +8271,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .reboot_recovery_ops = &nfs41_reboot_recovery_ops, .nograce_recovery_ops = &nfs41_nograce_recovery_ops, .state_renewal_ops = &nfs41_state_renewal_ops, + .mig_recovery_ops = &nfs41_mig_recovery_ops, }; #endif diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index cc14cbb..452f4c8 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -239,8 +239,6 @@ static void nfs4_end_drain_session(struct nfs_client *clp) } } -#if defined(CONFIG_NFS_V4_1) - static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl) { set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state); @@ -270,6 +268,8 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) return nfs4_drain_slot_tbl(&ses->fc_slot_table); } +#if defined(CONFIG_NFS_V4_1) + static int nfs41_setup_state_renewal(struct nfs_client *clp) { int status; @@ -1197,20 +1197,74 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp) } EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery); +/** + * nfs4_schedule_migration_recovery - trigger migration recovery + * + * @server: FSID that is migrating + * + * Returns zero if recovery has started, otherwise a negative NFS4ERR + * value is returned. + */ +int nfs4_schedule_migration_recovery(const struct nfs_server *server) +{ + struct nfs_client *clp = server->nfs_client; + + if (server->fh_expire_type != NFS4_FH_PERSISTENT) { + pr_err("NFS: volatile file handles not supported (server %s)\n", + clp->cl_hostname); + return -NFS4ERR_IO; + } + + if (test_bit(NFS_MIG_FAILED, &server->mig_status)) + return -NFS4ERR_IO; + + dprintk("%s: scheduling migration recovery for (%llx:%llx) on %s\n", + __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + + set_bit(NFS_MIG_IN_TRANSITION, + &((struct nfs_server *)server)->mig_status); + set_bit(NFS4CLNT_MOVED, &clp->cl_state); + + nfs4_schedule_state_manager(clp); + return 0; +} +EXPORT_SYMBOL_GPL(nfs4_schedule_migration_recovery); + +/** + * nfs4_schedule_lease_moved_recovery - start lease-moved recovery + * + * @clp: server to check for moved leases + * + */ +void nfs4_schedule_lease_moved_recovery(struct nfs_client *clp) +{ + dprintk("%s: scheduling lease-moved recovery for client ID %llx on %s\n", + __func__, clp->cl_clientid, clp->cl_hostname); + + set_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state); + nfs4_schedule_state_manager(clp); +} +EXPORT_SYMBOL_GPL(nfs4_schedule_lease_moved_recovery); + int nfs4_wait_clnt_recover(struct nfs_client *clp) { int res; might_sleep(); + atomic_inc(&clp->cl_count); res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, nfs_wait_bit_killable, TASK_KILLABLE); if (res) - return res; - + goto out; if (clp->cl_cons_state < 0) - return clp->cl_cons_state; - return 0; + res = clp->cl_cons_state; +out: + nfs_put_client(clp); + return res; } int nfs4_client_recover_expired_lease(struct nfs_client *clp) @@ -1375,8 +1429,8 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: goto out; default: - printk(KERN_ERR "NFS: %s: unhandled error %d. " - "Zeroing state\n", __func__, status); + printk(KERN_ERR "NFS: %s: unhandled error %d\n", + __func__, status); case -ENOMEM: case -NFS4ERR_DENIED: case -NFS4ERR_RECLAIM_BAD: @@ -1439,15 +1493,12 @@ restart: } switch (status) { default: - printk(KERN_ERR "NFS: %s: unhandled error %d. " - "Zeroing state\n", __func__, status); + printk(KERN_ERR "NFS: %s: unhandled error %d\n", + __func__, status); case -ENOENT: case -ENOMEM: case -ESTALE: - /* - * Open state on this file cannot be recovered - * All we can do is revert to using the zero stateid. - */ + /* Open state on this file cannot be recovered */ nfs4_state_mark_recovery_failed(state, status); break; case -EAGAIN: @@ -1628,7 +1679,6 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) nfs4_state_end_reclaim_reboot(clp); break; case -NFS4ERR_STALE_CLIENTID: - case -NFS4ERR_LEASE_MOVED: set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); @@ -1829,6 +1879,168 @@ static int nfs4_purge_lease(struct nfs_client *clp) return 0; } +/* + * Try remote migration of one FSID from a source server to a + * destination server. The source server provides a list of + * potential destinations. + * + * Returns zero or a negative NFS4ERR status code. + */ +static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred) +{ + struct nfs_client *clp = server->nfs_client; + struct nfs4_fs_locations *locations = NULL; + struct inode *inode; + struct page *page; + int status, result; + + dprintk("--> %s: FSID %llx:%llx on \"%s\"\n", __func__, + (unsigned long long)server->fsid.major, + (unsigned long long)server->fsid.minor, + clp->cl_hostname); + + result = 0; + page = alloc_page(GFP_KERNEL); + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (page == NULL || locations == NULL) { + dprintk("<-- %s: no memory\n", __func__); + goto out; + } + + inode = server->super->s_root->d_inode; + result = nfs4_proc_get_locations(inode, locations, page, cred); + if (result) { + dprintk("<-- %s: failed to retrieve fs_locations: %d\n", + __func__, result); + goto out; + } + + result = -NFS4ERR_NXIO; + if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { + dprintk("<-- %s: No fs_locations data, migration skipped\n", + __func__); + goto out; + } + + nfs4_begin_drain_session(clp); + + status = nfs4_replace_transport(server, locations); + if (status != 0) { + dprintk("<-- %s: failed to replace transport: %d\n", + __func__, status); + goto out; + } + + result = 0; + dprintk("<-- %s: migration succeeded\n", __func__); + +out: + if (page != NULL) + __free_page(page); + kfree(locations); + if (result) { + pr_err("NFS: migration recovery failed (server %s)\n", + clp->cl_hostname); + set_bit(NFS_MIG_FAILED, &server->mig_status); + } + return result; +} + +/* + * Returns zero or a negative NFS4ERR status code. + */ +static int nfs4_handle_migration(struct nfs_client *clp) +{ + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + struct nfs_server *server; + struct rpc_cred *cred; + + dprintk("%s: migration reported on \"%s\"\n", __func__, + clp->cl_hostname); + + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) + return -NFS4ERR_NOENT; + + clp->cl_mig_gen++; +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + int status; + + if (server->mig_gen == clp->cl_mig_gen) + continue; + server->mig_gen = clp->cl_mig_gen; + + if (!test_and_clear_bit(NFS_MIG_IN_TRANSITION, + &server->mig_status)) + continue; + + rcu_read_unlock(); + status = nfs4_try_migration(server, cred); + if (status < 0) { + put_rpccred(cred); + return status; + } + goto restart; + } + rcu_read_unlock(); + put_rpccred(cred); + return 0; +} + +/* + * Test each nfs_server on the clp's cl_superblocks list to see + * if it's moved to another server. Stop when the server no longer + * returns NFS4ERR_LEASE_MOVED. + */ +static int nfs4_handle_lease_moved(struct nfs_client *clp) +{ + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + struct nfs_server *server; + struct rpc_cred *cred; + + dprintk("%s: lease moved reported on \"%s\"\n", __func__, + clp->cl_hostname); + + spin_lock(&clp->cl_lock); + cred = ops->get_state_renewal_cred_locked(clp); + spin_unlock(&clp->cl_lock); + if (cred == NULL) + return -NFS4ERR_NOENT; + + clp->cl_mig_gen++; +restart: + rcu_read_lock(); + list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { + struct inode *inode; + int status; + + if (server->mig_gen == clp->cl_mig_gen) + continue; + server->mig_gen = clp->cl_mig_gen; + + rcu_read_unlock(); + + inode = server->super->s_root->d_inode; + status = nfs4_proc_fsid_present(inode, cred); + if (status != -NFS4ERR_MOVED) + goto restart; /* wasn't this one */ + if (nfs4_try_migration(server, cred) == -NFS4ERR_LEASE_MOVED) + goto restart; /* there are more */ + goto out; + } + rcu_read_unlock(); + +out: + put_rpccred(cred); + return 0; +} + /** * nfs4_discover_server_trunking - Detect server IP address trunking * @@ -2017,9 +2229,10 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) nfs41_handle_server_reboot(clp); if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | - SEQ4_STATUS_ADMIN_STATE_REVOKED | - SEQ4_STATUS_LEASE_MOVED)) + SEQ4_STATUS_ADMIN_STATE_REVOKED)) nfs41_handle_state_revoked(clp); + if (flags & SEQ4_STATUS_LEASE_MOVED) + nfs4_schedule_lease_moved_recovery(clp); if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) nfs41_handle_recallable_state_revoked(clp); if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT) @@ -2157,7 +2370,20 @@ static void nfs4_state_manager(struct nfs_client *clp) status = nfs4_check_lease(clp); if (status < 0) goto out_error; - continue; + } + + if (test_and_clear_bit(NFS4CLNT_MOVED, &clp->cl_state)) { + section = "migration"; + status = nfs4_handle_migration(clp); + if (status < 0) + goto out_error; + } + + if (test_and_clear_bit(NFS4CLNT_LEASE_MOVED, &clp->cl_state)) { + section = "lease moved"; + status = nfs4_handle_lease_moved(clp); + if (status < 0) + goto out_error; } /* First recover reboot state... */ diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index e26acdd..65ab0a0 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -261,9 +261,9 @@ struct dentry *nfs4_try_mount(int flags, const char *dev_name, res = nfs_follow_remote_path(root_mnt, export_path); - dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n", - IS_ERR(res) ? PTR_ERR(res) : 0, - IS_ERR(res) ? " [error]" : ""); + dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", + PTR_ERR_OR_ZERO(res), + IS_ERR(res) ? " [error]" : ""); return res; } @@ -319,9 +319,9 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, data->mnt_path = export_path; res = nfs_follow_remote_path(root_mnt, export_path); - dprintk("<-- nfs4_referral_mount() = %ld%s\n", - IS_ERR(res) ? PTR_ERR(res) : 0, - IS_ERR(res) ? " [error]" : ""); + dprintk("<-- nfs4_referral_mount() = %d%s\n", + PTR_ERR_OR_ZERO(res), + IS_ERR(res) ? " [error]" : ""); return res; } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 79210d2..f903389 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -595,11 +595,13 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_getattr_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_getattr_maxsz) + encode_getattr_maxsz + \ + encode_renew_maxsz) #define NFS4_dec_getattr_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_getattr_maxsz) + decode_getattr_maxsz + \ + decode_renew_maxsz) #define NFS4_enc_lookup_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -736,13 +738,15 @@ static int nfs4_stat_to_errno(int); encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_lookup_maxsz + \ - encode_fs_locations_maxsz) + encode_fs_locations_maxsz + \ + encode_renew_maxsz) #define NFS4_dec_fs_locations_sz \ (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_lookup_maxsz + \ - decode_fs_locations_maxsz) + decode_fs_locations_maxsz + \ + decode_renew_maxsz) #define NFS4_enc_secinfo_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ @@ -751,6 +755,18 @@ static int nfs4_stat_to_errno(int); decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_secinfo_maxsz) +#define NFS4_enc_fsid_present_sz \ + (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_getfh_maxsz + \ + encode_renew_maxsz) +#define NFS4_dec_fsid_present_sz \ + (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_getfh_maxsz + \ + decode_renew_maxsz) #if defined(CONFIG_NFS_V4_1) #define NFS4_enc_bind_conn_to_session_sz \ (compound_encode_hdr_maxsz + \ @@ -2687,11 +2703,20 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); - encode_putfh(xdr, args->dir_fh, &hdr); - encode_lookup(xdr, args->name, &hdr); - replen = hdr.replen; /* get the attribute into args->page */ - encode_fs_locations(xdr, args->bitmask, &hdr); + if (args->migration) { + encode_putfh(xdr, args->fh, &hdr); + replen = hdr.replen; + encode_fs_locations(xdr, args->bitmask, &hdr); + if (args->renew) + encode_renew(xdr, args->clientid, &hdr); + } else { + encode_putfh(xdr, args->dir_fh, &hdr); + encode_lookup(xdr, args->name, &hdr); + replen = hdr.replen; + encode_fs_locations(xdr, args->bitmask, &hdr); + } + /* Set up reply kvec to capture returned fs_locations array. */ xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page, 0, PAGE_SIZE); encode_nops(&hdr); @@ -2715,6 +2740,26 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, encode_nops(&hdr); } +/* + * Encode FSID_PRESENT request + */ +static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs4_fsid_present_arg *args) +{ + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_getfh(xdr, &hdr); + if (args->renew) + encode_renew(xdr, args->clientid, &hdr); + encode_nops(&hdr); +} + #if defined(CONFIG_NFS_V4_1) /* * BIND_CONN_TO_SESSION request @@ -6824,13 +6869,26 @@ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, status = decode_putfh(xdr); if (status) goto out; - status = decode_lookup(xdr); - if (status) - goto out; - xdr_enter_page(xdr, PAGE_SIZE); - status = decode_getfattr_generic(xdr, &res->fs_locations->fattr, + if (res->migration) { + xdr_enter_page(xdr, PAGE_SIZE); + status = decode_getfattr_generic(xdr, + &res->fs_locations->fattr, NULL, res->fs_locations, NULL, res->fs_locations->server); + if (status) + goto out; + if (res->renew) + status = decode_renew(xdr); + } else { + status = decode_lookup(xdr); + if (status) + goto out; + xdr_enter_page(xdr, PAGE_SIZE); + status = decode_getfattr_generic(xdr, + &res->fs_locations->fattr, + NULL, res->fs_locations, + NULL, res->fs_locations->server); + } out: return status; } @@ -6859,6 +6917,34 @@ out: return status; } +/* + * Decode FSID_PRESENT response + */ +static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + struct nfs4_fsid_present_res *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + if (res->renew) + status = decode_renew(xdr); +out: + return status; +} + #if defined(CONFIG_NFS_V4_1) /* * Decode BIND_CONN_TO_SESSION response @@ -7373,6 +7459,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(FS_LOCATIONS, enc_fs_locations, dec_fs_locations), PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner), PROC(SECINFO, enc_secinfo, dec_secinfo), + PROC(FSID_PRESENT, enc_fsid_present, dec_fsid_present), #if defined(CONFIG_NFS_V4_1) PROC(EXCHANGE_ID, enc_exchange_id, dec_exchange_id), PROC(CREATE_SESSION, enc_create_session, dec_create_session), diff --git a/fs/nfs/super.c b/fs/nfs/super.c index a03b9c6..317d6fc 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -497,7 +497,8 @@ static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour) static const struct { rpc_authflavor_t flavour; const char *str; - } sec_flavours[] = { + } sec_flavours[NFS_AUTH_INFO_MAX_FLAVORS] = { + /* update NFS_AUTH_INFO_MAX_FLAVORS when this list changes! */ { RPC_AUTH_NULL, "null" }, { RPC_AUTH_UNIX, "sys" }, { RPC_AUTH_GSS_KRB5, "krb5" }, @@ -923,8 +924,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) data->mount_server.port = NFS_UNSPEC_PORT; data->nfs_server.port = NFS_UNSPEC_PORT; data->nfs_server.protocol = XPRT_TRANSPORT_TCP; - data->auth_flavors[0] = RPC_AUTH_MAXFLAVOR; - data->auth_flavor_len = 0; + data->selected_flavor = RPC_AUTH_MAXFLAVOR; data->minorversion = 0; data->need_mount = true; data->net = current->nsproxy->net_ns; @@ -1019,12 +1019,51 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt) } } -static void nfs_set_auth_parsed_mount_data(struct nfs_parsed_mount_data *data, - rpc_authflavor_t pseudoflavor) +/* + * Add 'flavor' to 'auth_info' if not already present. + * Returns true if 'flavor' ends up in the list, false otherwise + */ +static bool nfs_auth_info_add(struct nfs_auth_info *auth_info, + rpc_authflavor_t flavor) +{ + unsigned int i; + unsigned int max_flavor_len = (sizeof(auth_info->flavors) / + sizeof(auth_info->flavors[0])); + + /* make sure this flavor isn't already in the list */ + for (i = 0; i < auth_info->flavor_len; i++) { + if (flavor == auth_info->flavors[i]) + return true; + } + + if (auth_info->flavor_len + 1 >= max_flavor_len) { + dfprintk(MOUNT, "NFS: too many sec= flavors\n"); + return false; + } + + auth_info->flavors[auth_info->flavor_len++] = flavor; + return true; +} + +/* + * Return true if 'match' is in auth_info or auth_info is empty. + * Return false otherwise. + */ +bool nfs_auth_info_match(const struct nfs_auth_info *auth_info, + rpc_authflavor_t match) { - data->auth_flavors[0] = pseudoflavor; - data->auth_flavor_len = 1; + int i; + + if (!auth_info->flavor_len) + return true; + + for (i = 0; i < auth_info->flavor_len; i++) { + if (auth_info->flavors[i] == match) + return true; + } + return false; } +EXPORT_SYMBOL_GPL(nfs_auth_info_match); /* * Parse the value of the 'sec=' option. @@ -1034,49 +1073,55 @@ static int nfs_parse_security_flavors(char *value, { substring_t args[MAX_OPT_ARGS]; rpc_authflavor_t pseudoflavor; + char *p; dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value); - switch (match_token(value, nfs_secflavor_tokens, args)) { - case Opt_sec_none: - pseudoflavor = RPC_AUTH_NULL; - break; - case Opt_sec_sys: - pseudoflavor = RPC_AUTH_UNIX; - break; - case Opt_sec_krb5: - pseudoflavor = RPC_AUTH_GSS_KRB5; - break; - case Opt_sec_krb5i: - pseudoflavor = RPC_AUTH_GSS_KRB5I; - break; - case Opt_sec_krb5p: - pseudoflavor = RPC_AUTH_GSS_KRB5P; - break; - case Opt_sec_lkey: - pseudoflavor = RPC_AUTH_GSS_LKEY; - break; - case Opt_sec_lkeyi: - pseudoflavor = RPC_AUTH_GSS_LKEYI; - break; - case Opt_sec_lkeyp: - pseudoflavor = RPC_AUTH_GSS_LKEYP; - break; - case Opt_sec_spkm: - pseudoflavor = RPC_AUTH_GSS_SPKM; - break; - case Opt_sec_spkmi: - pseudoflavor = RPC_AUTH_GSS_SPKMI; - break; - case Opt_sec_spkmp: - pseudoflavor = RPC_AUTH_GSS_SPKMP; - break; - default: - return 0; + while ((p = strsep(&value, ":")) != NULL) { + switch (match_token(p, nfs_secflavor_tokens, args)) { + case Opt_sec_none: + pseudoflavor = RPC_AUTH_NULL; + break; + case Opt_sec_sys: + pseudoflavor = RPC_AUTH_UNIX; + break; + case Opt_sec_krb5: + pseudoflavor = RPC_AUTH_GSS_KRB5; + break; + case Opt_sec_krb5i: + pseudoflavor = RPC_AUTH_GSS_KRB5I; + break; + case Opt_sec_krb5p: + pseudoflavor = RPC_AUTH_GSS_KRB5P; + break; + case Opt_sec_lkey: + pseudoflavor = RPC_AUTH_GSS_LKEY; + break; + case Opt_sec_lkeyi: + pseudoflavor = RPC_AUTH_GSS_LKEYI; + break; + case Opt_sec_lkeyp: + pseudoflavor = RPC_AUTH_GSS_LKEYP; + break; + case Opt_sec_spkm: + pseudoflavor = RPC_AUTH_GSS_SPKM; + break; + case Opt_sec_spkmi: + pseudoflavor = RPC_AUTH_GSS_SPKMI; + break; + case Opt_sec_spkmp: + pseudoflavor = RPC_AUTH_GSS_SPKMP; + break; + default: + dfprintk(MOUNT, + "NFS: sec= option '%s' not recognized\n", p); + return 0; + } + + if (!nfs_auth_info_add(&mnt->auth_info, pseudoflavor)) + return 0; } - mnt->flags |= NFS_MOUNT_SECFLAVOUR; - nfs_set_auth_parsed_mount_data(mnt, pseudoflavor); return 1; } @@ -1623,12 +1668,14 @@ out_security_failure: } /* - * Ensure that the specified authtype in args->auth_flavors[0] is supported by - * the server. Returns 0 if it's ok, and -EACCES if not. + * Ensure that a specified authtype in args->auth_info is supported by + * the server. Returns 0 and sets args->selected_flavor if it's ok, and + * -EACCES if not. */ -static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args, +static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, rpc_authflavor_t *server_authlist, unsigned int count) { + rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; unsigned int i; /* @@ -1640,17 +1687,20 @@ static int nfs_verify_authflavor(struct nfs_parsed_mount_data *args, * can be used. */ for (i = 0; i < count; i++) { - if (args->auth_flavors[0] == server_authlist[i] || - server_authlist[i] == RPC_AUTH_NULL) + flavor = server_authlist[i]; + + if (nfs_auth_info_match(&args->auth_info, flavor) || + flavor == RPC_AUTH_NULL) goto out; } - dfprintk(MOUNT, "NFS: auth flavor %u not supported by server\n", - args->auth_flavors[0]); + dfprintk(MOUNT, + "NFS: specified auth flavors not supported by server\n"); return -EACCES; out: - dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]); + args->selected_flavor = flavor; + dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->selected_flavor); return 0; } @@ -1738,9 +1788,10 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf * Was a sec= authflavor specified in the options? First, verify * whether the server supports it, and then just try to use it if so. */ - if (args->auth_flavor_len > 0) { - status = nfs_verify_authflavor(args, authlist, authlist_len); - dfprintk(MOUNT, "NFS: using auth flavor %u\n", args->auth_flavors[0]); + if (args->auth_info.flavor_len > 0) { + status = nfs_verify_authflavors(args, authlist, authlist_len); + dfprintk(MOUNT, "NFS: using auth flavor %u\n", + args->selected_flavor); if (status) return ERR_PTR(status); return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); @@ -1769,7 +1820,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Fallthrough */ } dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor); - nfs_set_auth_parsed_mount_data(args, flavor); + args->selected_flavor = flavor; server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); if (!IS_ERR(server)) return server; @@ -1785,7 +1836,7 @@ static struct nfs_server *nfs_try_mount_request(struct nfs_mount_info *mount_inf /* Last chance! Try AUTH_UNIX */ dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", RPC_AUTH_UNIX); - nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; return nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); } @@ -1972,9 +2023,9 @@ static int nfs23_validate_mount_data(void *options, args->bsize = data->bsize; if (data->flags & NFS_MOUNT_SECFLAVOUR) - nfs_set_auth_parsed_mount_data(args, data->pseudoflavor); + args->selected_flavor = data->pseudoflavor; else - nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; if (!args->nfs_server.hostname) goto out_nomem; @@ -2108,9 +2159,6 @@ static int nfs_validate_text_mount_data(void *options, nfs_set_port(sap, &args->nfs_server.port, port); - if (args->auth_flavor_len > 1) - goto out_bad_auth; - return nfs_parse_devname(dev_name, &args->nfs_server.hostname, max_namelen, @@ -2130,10 +2178,6 @@ out_invalid_transport_udp: out_no_address: dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); return -EINVAL; - -out_bad_auth: - dfprintk(MOUNT, "NFS: Too many RPC auth flavours specified\n"); - return -EINVAL; } static int @@ -2143,8 +2187,10 @@ nfs_compare_remount_data(struct nfs_server *nfss, if (data->flags != nfss->flags || data->rsize != nfss->rsize || data->wsize != nfss->wsize || + data->version != nfss->nfs_client->rpc_ops->version || + data->minorversion != nfss->nfs_client->cl_minorversion || data->retrans != nfss->client->cl_timeout->to_retries || - data->auth_flavors[0] != nfss->client->cl_auth->au_flavor || + data->selected_flavor != nfss->client->cl_auth->au_flavor || data->acregmin != nfss->acregmin / HZ || data->acregmax != nfss->acregmax / HZ || data->acdirmin != nfss->acdirmin / HZ || @@ -2189,7 +2235,8 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->rsize = nfss->rsize; data->wsize = nfss->wsize; data->retrans = nfss->client->cl_timeout->to_retries; - nfs_set_auth_parsed_mount_data(data, nfss->client->cl_auth->au_flavor); + data->selected_flavor = nfss->client->cl_auth->au_flavor; + data->auth_info = nfss->auth_info; data->acregmin = nfss->acregmin / HZ; data->acregmax = nfss->acregmax / HZ; data->acdirmin = nfss->acdirmin / HZ; @@ -2197,12 +2244,14 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ; data->nfs_server.port = nfss->port; data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen; + data->version = nfsvers; + data->minorversion = nfss->nfs_client->cl_minorversion; memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr, data->nfs_server.addrlen); /* overwrite those values with any that were specified */ - error = nfs_parse_mount_options((char *)options, data); - if (error < 0) + error = -EINVAL; + if (!nfs_parse_mount_options((char *)options, data)) goto out; /* @@ -2332,7 +2381,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->acdirmax != b->acdirmax) goto Ebusy; - if (b->flags & NFS_MOUNT_SECFLAVOUR && + if (b->auth_info.flavor_len > 0 && clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) goto Ebusy; return 1; @@ -2530,6 +2579,7 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, mntroot = ERR_PTR(error); goto error_splat_bdi; } + server->super = s; } if (!s->s_root) { @@ -2713,9 +2763,9 @@ static int nfs4_validate_mount_data(void *options, data->auth_flavours, sizeof(pseudoflavor))) return -EFAULT; - nfs_set_auth_parsed_mount_data(args, pseudoflavor); + args->selected_flavor = pseudoflavor; } else - nfs_set_auth_parsed_mount_data(args, RPC_AUTH_UNIX); + args->selected_flavor = RPC_AUTH_UNIX; c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN); if (IS_ERR(c)) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index bb939ed..0c29b1b 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -493,7 +493,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) unsigned long long fileid; struct dentry *sdentry; struct rpc_task *task; - int error = -EIO; + int error = -EBUSY; dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n", dentry->d_parent->d_name.name, dentry->d_name.name, @@ -503,7 +503,6 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) /* * We don't allow a dentry to be silly-renamed twice. */ - error = -EBUSY; if (dentry->d_flags & DCACHE_NFSFS_RENAMED) goto out; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 0ba6798..da27664 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -94,6 +94,7 @@ void nilfs_forget_buffer(struct buffer_head *bh) clear_buffer_nilfs_volatile(bh); clear_buffer_nilfs_checked(bh); clear_buffer_nilfs_redirected(bh); + clear_buffer_async_write(bh); clear_buffer_dirty(bh); if (nilfs_page_buffers_clean(page)) __nilfs_clear_page_dirty(page); @@ -429,6 +430,7 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) "discard block %llu, size %zu", (u64)bh->b_blocknr, bh->b_size); } + clear_buffer_async_write(bh); clear_buffer_dirty(bh); clear_buffer_nilfs_volatile(bh); clear_buffer_nilfs_checked(bh); diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index bd88a74..9f6b486 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -665,7 +665,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, bh = head = page_buffers(page); do { - if (!buffer_dirty(bh)) + if (!buffer_dirty(bh) || buffer_async_write(bh)) continue; get_bh(bh); list_add_tail(&bh->b_assoc_buffers, listp); @@ -699,7 +699,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); do { - if (buffer_dirty(bh)) { + if (buffer_dirty(bh) && + !buffer_async_write(bh)) { get_bh(bh); list_add_tail(&bh->b_assoc_buffers, listp); @@ -1579,6 +1580,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + set_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) { lock_page(bd_page); @@ -1592,6 +1594,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { + set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1677,6 +1680,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1686,6 +1690,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { + clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { end_page_writeback(bd_page); @@ -1755,6 +1760,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) b_assoc_buffers) { set_buffer_uptodate(bh); clear_buffer_dirty(bh); + clear_buffer_async_write(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1776,6 +1782,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) b_assoc_buffers) { set_buffer_uptodate(bh); clear_buffer_dirty(bh); + clear_buffer_async_write(bh); clear_buffer_delay(bh); clear_buffer_nilfs_volatile(bh); clear_buffer_nilfs_redirected(bh); diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index ef99972..0d3a97d 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -70,9 +70,10 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) */ if (inode == NULL) { unsigned long gen = (unsigned long) dentry->d_fsdata; - unsigned long pgen = - OCFS2_I(dentry->d_parent->d_inode)->ip_dir_lock_gen; - + unsigned long pgen; + spin_lock(&dentry->d_lock); + pgen = OCFS2_I(dentry->d_parent->d_inode)->ip_dir_lock_gen; + spin_unlock(&dentry->d_lock); trace_ocfs2_dentry_revalidate_negative(dentry->d_name.len, dentry->d_name.name, pgen, gen); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 121da2d..d4e81e4 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1924,7 +1924,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) { int tmp, hangup_needed = 0; struct ocfs2_super *osb = NULL; - char nodestr[8]; + char nodestr[12]; trace_ocfs2_dismount_volume(sb); diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 73feacc4..fd77703 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1163,21 +1163,6 @@ static struct reiserfs_journal_list *find_newer_jl_for_cn(struct return NULL; } -static int newer_jl_done(struct reiserfs_journal_cnode *cn) -{ - struct super_block *sb = cn->sb; - b_blocknr_t blocknr = cn->blocknr; - - cn = cn->hprev; - while (cn) { - if (cn->sb == sb && cn->blocknr == blocknr && cn->jlist && - atomic_read(&cn->jlist->j_commit_left) != 0) - return 0; - cn = cn->hprev; - } - return 1; -} - static void remove_journal_hash(struct super_block *, struct reiserfs_journal_cnode **, struct reiserfs_journal_list *, unsigned long, @@ -1353,7 +1338,6 @@ static int flush_journal_list(struct super_block *s, reiserfs_warning(s, "clm-2048", "called with wcount %d", atomic_read(&journal->j_wcount)); } - BUG_ON(jl->j_trans_id == 0); /* if flushall == 0, the lock is already held */ if (flushall) { @@ -1593,31 +1577,6 @@ static int flush_journal_list(struct super_block *s, return err; } -static int test_transaction(struct super_block *s, - struct reiserfs_journal_list *jl) -{ - struct reiserfs_journal_cnode *cn; - - if (jl->j_len == 0 || atomic_read(&jl->j_nonzerolen) == 0) - return 1; - - cn = jl->j_realblock; - while (cn) { - /* if the blocknr == 0, this has been cleared from the hash, - ** skip it - */ - if (cn->blocknr == 0) { - goto next; - } - if (cn->bh && !newer_jl_done(cn)) - return 0; - next: - cn = cn->next; - cond_resched(); - } - return 0; -} - static int write_one_transaction(struct super_block *s, struct reiserfs_journal_list *jl, struct buffer_chunk *chunk) @@ -1805,6 +1764,8 @@ static int flush_used_journal_lists(struct super_block *s, break; tjl = JOURNAL_LIST_ENTRY(tjl->j_list.next); } + get_journal_list(jl); + get_journal_list(flush_jl); /* try to find a group of blocks we can flush across all the ** transactions, but only bother if we've actually spanned ** across multiple lists @@ -1813,6 +1774,8 @@ static int flush_used_journal_lists(struct super_block *s, ret = kupdate_transactions(s, jl, &tjl, &trans_id, len, i); } flush_journal_list(s, flush_jl, 1); + put_journal_list(s, flush_jl); + put_journal_list(s, jl); return 0; } @@ -3868,27 +3831,6 @@ int reiserfs_prepare_for_journal(struct super_block *sb, return 1; } -static void flush_old_journal_lists(struct super_block *s) -{ - struct reiserfs_journal *journal = SB_JOURNAL(s); - struct reiserfs_journal_list *jl; - struct list_head *entry; - time_t now = get_seconds(); - - while (!list_empty(&journal->j_journal_list)) { - entry = journal->j_journal_list.next; - jl = JOURNAL_LIST_ENTRY(entry); - /* this check should always be run, to send old lists to disk */ - if (jl->j_timestamp < (now - (JOURNAL_MAX_TRANS_AGE * 4)) && - atomic_read(&jl->j_commit_left) == 0 && - test_transaction(s, jl)) { - flush_used_journal_lists(s, jl); - } else { - break; - } - } -} - /* ** long and ugly. If flush, will not return until all commit ** blocks and all real buffers in the trans are on disk. @@ -4232,7 +4174,6 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, } } } - flush_old_journal_lists(sb); journal->j_current_jl->j_list_bitmap = get_list_bitmap(sb, journal->j_current_jl); diff --git a/fs/sysv/super.c b/fs/sysv/super.c index d0c6a00..eda1095 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -487,6 +487,7 @@ static int v7_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sb = sb; sbi->s_block_base = 0; sbi->s_type = FSTYPE_V7; + mutex_init(&sbi->s_lock); sb->s_fs_info = sbi; sb_set_blocksize(sb, 512); diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index 7e5aae4..6eaf5ed 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -30,18 +30,17 @@ void udf_free_inode(struct inode *inode) { struct super_block *sb = inode->i_sb; struct udf_sb_info *sbi = UDF_SB(sb); + struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); - mutex_lock(&sbi->s_alloc_mutex); - if (sbi->s_lvid_bh) { - struct logicalVolIntegrityDescImpUse *lvidiu = - udf_sb_lvidiu(sbi); + if (lvidiu) { + mutex_lock(&sbi->s_alloc_mutex); if (S_ISDIR(inode->i_mode)) le32_add_cpu(&lvidiu->numDirs, -1); else le32_add_cpu(&lvidiu->numFiles, -1); udf_updated_lvid(sb); + mutex_unlock(&sbi->s_alloc_mutex); } - mutex_unlock(&sbi->s_alloc_mutex); udf_free_blocks(sb, NULL, &UDF_I(inode)->i_location, 0, 1); } @@ -55,6 +54,7 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err) uint32_t start = UDF_I(dir)->i_location.logicalBlockNum; struct udf_inode_info *iinfo; struct udf_inode_info *dinfo = UDF_I(dir); + struct logicalVolIntegrityDescImpUse *lvidiu; inode = new_inode(sb); @@ -92,12 +92,10 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err) return NULL; } - if (sbi->s_lvid_bh) { - struct logicalVolIntegrityDescImpUse *lvidiu; - + lvidiu = udf_sb_lvidiu(sb); + if (lvidiu) { iinfo->i_unique = lvid_get_unique_id(sb); mutex_lock(&sbi->s_alloc_mutex); - lvidiu = udf_sb_lvidiu(sbi); if (S_ISDIR(mode)) le32_add_cpu(&lvidiu->numDirs, 1); else diff --git a/fs/udf/super.c b/fs/udf/super.c index 839a2ba..9121938 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -94,13 +94,25 @@ static unsigned int udf_count_free(struct super_block *); static int udf_statfs(struct dentry *, struct kstatfs *); static int udf_show_options(struct seq_file *, struct dentry *); -struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi) +struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb) { - struct logicalVolIntegrityDesc *lvid = - (struct logicalVolIntegrityDesc *)sbi->s_lvid_bh->b_data; - __u32 number_of_partitions = le32_to_cpu(lvid->numOfPartitions); - __u32 offset = number_of_partitions * 2 * - sizeof(uint32_t)/sizeof(uint8_t); + struct logicalVolIntegrityDesc *lvid; + unsigned int partnum; + unsigned int offset; + + if (!UDF_SB(sb)->s_lvid_bh) + return NULL; + lvid = (struct logicalVolIntegrityDesc *)UDF_SB(sb)->s_lvid_bh->b_data; + partnum = le32_to_cpu(lvid->numOfPartitions); + if ((sb->s_blocksize - sizeof(struct logicalVolIntegrityDescImpUse) - + offsetof(struct logicalVolIntegrityDesc, impUse)) / + (2 * sizeof(uint32_t)) < partnum) { + udf_err(sb, "Logical volume integrity descriptor corrupted " + "(numOfPartitions = %u)!\n", partnum); + return NULL; + } + /* The offset is to skip freeSpaceTable and sizeTable arrays */ + offset = partnum * 2 * sizeof(uint32_t); return (struct logicalVolIntegrityDescImpUse *)&(lvid->impUse[offset]); } @@ -629,9 +641,10 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) struct udf_options uopt; struct udf_sb_info *sbi = UDF_SB(sb); int error = 0; + struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); - if (sbi->s_lvid_bh) { - int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev); + if (lvidiu) { + int write_rev = le16_to_cpu(lvidiu->minUDFWriteRev); if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY)) return -EACCES; } @@ -1905,11 +1918,12 @@ static void udf_open_lvid(struct super_block *sb) if (!bh) return; - - mutex_lock(&sbi->s_alloc_mutex); lvid = (struct logicalVolIntegrityDesc *)bh->b_data; - lvidiu = udf_sb_lvidiu(sbi); + lvidiu = udf_sb_lvidiu(sb); + if (!lvidiu) + return; + mutex_lock(&sbi->s_alloc_mutex); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; udf_time_to_disk_stamp(&lvid->recordingDateAndTime, @@ -1937,10 +1951,12 @@ static void udf_close_lvid(struct super_block *sb) if (!bh) return; + lvid = (struct logicalVolIntegrityDesc *)bh->b_data; + lvidiu = udf_sb_lvidiu(sb); + if (!lvidiu) + return; mutex_lock(&sbi->s_alloc_mutex); - lvid = (struct logicalVolIntegrityDesc *)bh->b_data; - lvidiu = udf_sb_lvidiu(sbi); lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; udf_time_to_disk_stamp(&lvid->recordingDateAndTime, CURRENT_TIME); @@ -2093,15 +2109,19 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (sbi->s_lvid_bh) { struct logicalVolIntegrityDescImpUse *lvidiu = - udf_sb_lvidiu(sbi); - uint16_t minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev); - uint16_t minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev); - /* uint16_t maxUDFWriteRev = - le16_to_cpu(lvidiu->maxUDFWriteRev); */ + udf_sb_lvidiu(sb); + uint16_t minUDFReadRev; + uint16_t minUDFWriteRev; + if (!lvidiu) { + ret = -EINVAL; + goto error_out; + } + minUDFReadRev = le16_to_cpu(lvidiu->minUDFReadRev); + minUDFWriteRev = le16_to_cpu(lvidiu->minUDFWriteRev); if (minUDFReadRev > UDF_MAX_READ_VERSION) { udf_err(sb, "minUDFReadRev=%x (max is %x)\n", - le16_to_cpu(lvidiu->minUDFReadRev), + minUDFReadRev, UDF_MAX_READ_VERSION); ret = -EINVAL; goto error_out; @@ -2265,11 +2285,7 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf) struct logicalVolIntegrityDescImpUse *lvidiu; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); - if (sbi->s_lvid_bh != NULL) - lvidiu = udf_sb_lvidiu(sbi); - else - lvidiu = NULL; - + lvidiu = udf_sb_lvidiu(sb); buf->f_type = UDF_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = sbi->s_partmaps[sbi->s_partition].s_partition_len; diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index ed401e9..1f32c7b 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -162,7 +162,7 @@ static inline struct udf_sb_info *UDF_SB(struct super_block *sb) return sb->s_fs_info; } -struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi); +struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct super_block *sb); int udf_compute_nr_groups(struct super_block *sb, u32 partition); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 88c5ea7..f1d85cf 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -628,6 +628,7 @@ xfs_buf_item_unlock( else if (aborted) { ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); if (lip->li_flags & XFS_LI_IN_AIL) { + spin_lock(&lip->li_ailp->xa_lock); xfs_trans_ail_delete(lip->li_ailp, lip, SHUTDOWN_LOG_IO_ERROR); } diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 069537c..20bf8e8 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -1224,6 +1224,7 @@ xfs_da3_node_toosmall( /* start with smaller blk num */ forward = nodehdr.forw < nodehdr.back; for (i = 0; i < 2; forward = !forward, i++) { + struct xfs_da3_icnode_hdr thdr; if (forward) blkno = nodehdr.forw; else @@ -1236,10 +1237,10 @@ xfs_da3_node_toosmall( return(error); node = bp->b_addr; - xfs_da3_node_hdr_from_disk(&nodehdr, node); + xfs_da3_node_hdr_from_disk(&thdr, node); xfs_trans_brelse(state->args->trans, bp); - if (count - nodehdr.count >= 0) + if (count - thdr.count >= 0) break; /* fits with at least 25% to spare */ } if (i >= 2) { diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index 1edb5cc..18272c7 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -515,7 +515,7 @@ typedef struct xfs_swapext /* XFS_IOC_GETBIOSIZE ---- deprecated 47 */ #define XFS_IOC_GETBMAPX _IOWR('X', 56, struct getbmap) #define XFS_IOC_ZERO_RANGE _IOW ('X', 57, struct xfs_flock64) -#define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_eofblocks) +#define XFS_IOC_FREE_EOFBLOCKS _IOR ('X', 58, struct xfs_fs_eofblocks) /* * ioctl commands that replace IRIX syssgi()'s diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 193206b..474807a 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -119,11 +119,6 @@ xfs_inode_free( ip->i_itemp = NULL; } - /* asserts to verify all state is correct here */ - ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!spin_is_locked(&ip->i_flags_lock)); - ASSERT(!xfs_isiflocked(ip)); - /* * Because we use RCU freeing we need to ensure the inode always * appears to be reclaimed with an invalid inode number when in the @@ -135,6 +130,10 @@ xfs_inode_free( ip->i_ino = 0; spin_unlock(&ip->i_flags_lock); + /* asserts to verify all state is correct here */ + ASSERT(atomic_read(&ip->i_pincount) == 0); + ASSERT(!xfs_isiflocked(ip)); + call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index dabda95..cc17987 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1970,6 +1970,13 @@ xlog_recover_do_inode_buffer( * magic number. If we don't recognise the magic number in the buffer, then * return a LSN of -1 so that the caller knows it was an unrecognised block and * so can recover the buffer. + * + * Note: we cannot rely solely on magic number matches to determine that the + * buffer has a valid LSN - we also need to verify that it belongs to this + * filesystem, so we need to extract the object's LSN and compare it to that + * which we read from the superblock. If the UUIDs don't match, then we've got a + * stale metadata block from an old filesystem instance that we need to recover + * over the top of. */ static xfs_lsn_t xlog_recover_get_buf_lsn( @@ -1980,6 +1987,8 @@ xlog_recover_get_buf_lsn( __uint16_t magic16; __uint16_t magicda; void *blk = bp->b_addr; + uuid_t *uuid; + xfs_lsn_t lsn = -1; /* v4 filesystems always recover immediately */ if (!xfs_sb_version_hascrc(&mp->m_sb)) @@ -1992,43 +2001,79 @@ xlog_recover_get_buf_lsn( case XFS_ABTB_MAGIC: case XFS_ABTC_MAGIC: case XFS_IBT_CRC_MAGIC: - case XFS_IBT_MAGIC: - return be64_to_cpu( - ((struct xfs_btree_block *)blk)->bb_u.s.bb_lsn); + case XFS_IBT_MAGIC: { + struct xfs_btree_block *btb = blk; + + lsn = be64_to_cpu(btb->bb_u.s.bb_lsn); + uuid = &btb->bb_u.s.bb_uuid; + break; + } case XFS_BMAP_CRC_MAGIC: - case XFS_BMAP_MAGIC: - return be64_to_cpu( - ((struct xfs_btree_block *)blk)->bb_u.l.bb_lsn); + case XFS_BMAP_MAGIC: { + struct xfs_btree_block *btb = blk; + + lsn = be64_to_cpu(btb->bb_u.l.bb_lsn); + uuid = &btb->bb_u.l.bb_uuid; + break; + } case XFS_AGF_MAGIC: - return be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn); + lsn = be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn); + uuid = &((struct xfs_agf *)blk)->agf_uuid; + break; case XFS_AGFL_MAGIC: - return be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn); + lsn = be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn); + uuid = &((struct xfs_agfl *)blk)->agfl_uuid; + break; case XFS_AGI_MAGIC: - return be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn); + lsn = be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn); + uuid = &((struct xfs_agi *)blk)->agi_uuid; + break; case XFS_SYMLINK_MAGIC: - return be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn); + lsn = be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn); + uuid = &((struct xfs_dsymlink_hdr *)blk)->sl_uuid; + break; case XFS_DIR3_BLOCK_MAGIC: case XFS_DIR3_DATA_MAGIC: case XFS_DIR3_FREE_MAGIC: - return be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn); + lsn = be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn); + uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid; + break; case XFS_ATTR3_RMT_MAGIC: - return be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn); + lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn); + uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid; + break; case XFS_SB_MAGIC: - return be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn); + lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn); + uuid = &((struct xfs_dsb *)blk)->sb_uuid; + break; default: break; } + if (lsn != (xfs_lsn_t)-1) { + if (!uuid_equal(&mp->m_sb.sb_uuid, uuid)) + goto recover_immediately; + return lsn; + } + magicda = be16_to_cpu(((struct xfs_da_blkinfo *)blk)->magic); switch (magicda) { case XFS_DIR3_LEAF1_MAGIC: case XFS_DIR3_LEAFN_MAGIC: case XFS_DA3_NODE_MAGIC: - return be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn); + lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn); + uuid = &((struct xfs_da3_blkinfo *)blk)->uuid; + break; default: break; } + if (lsn != (xfs_lsn_t)-1) { + if (!uuid_equal(&mp->m_sb.sb_uuid, uuid)) + goto recover_immediately; + return lsn; + } + /* * We do individual object checks on dquot and inode buffers as they * have their own individual LSN records. Also, we could have a stale diff --git a/include/asm-generic/vtime.h b/include/asm-generic/vtime.h index e69de29..b1a4967 100644 --- a/include/asm-generic/vtime.h +++ b/include/asm-generic/vtime.h @@ -0,0 +1 @@ +/* no content, but patch(1) dislikes empty files */ diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 2907341..b46fb45 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1322,10 +1322,9 @@ extern int drm_newctx(struct drm_device *dev, void *data, extern int drm_rmctx(struct drm_device *dev, void *data, struct drm_file *file_priv); -extern void drm_legacy_ctxbitmap_init(struct drm_device *dev); -extern void drm_legacy_ctxbitmap_cleanup(struct drm_device *dev); -extern void drm_legacy_ctxbitmap_release(struct drm_device *dev, - struct drm_file *file_priv); +extern int drm_ctxbitmap_init(struct drm_device *dev); +extern void drm_ctxbitmap_cleanup(struct drm_device *dev); +extern void drm_ctxbitmap_free(struct drm_device *dev, int ctx_handle); extern int drm_setsareactx(struct drm_device *dev, void *data, struct drm_file *file_priv); diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index f7f1d71..089743a 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -159,6 +159,26 @@ static inline bool balloon_page_movable(struct page *page) } /* + * isolated_balloon_page - identify an isolated balloon page on private + * compaction/migration page lists. + * + * After a compaction thread isolates a balloon page for migration, it raises + * the page refcount to prevent concurrent compaction threads from re-isolating + * the same page. For that reason putback_movable_pages(), or other routines + * that need to identify isolated balloon pages on private pagelists, cannot + * rely on balloon_page_movable() to accomplish the task. + */ +static inline bool isolated_balloon_page(struct page *page) +{ + /* Already isolated balloon pages, by default, have a raised refcount */ + if (page_flags_cleared(page) && !page_mapped(page) && + page_count(page) >= 2) + return __is_movable_balloon_page(page); + + return false; +} + +/* * balloon_page_insert - insert a page into the balloon's page list and make * the page->mapping assignment accordingly. * @page : page to be assigned as a 'balloon page' @@ -243,6 +263,11 @@ static inline bool balloon_page_movable(struct page *page) return false; } +static inline bool isolated_balloon_page(struct page *page) +{ + return false; +} + static inline bool balloon_page_isolate(struct page *page) { return false; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2fdb4a4..0e6f765 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -862,6 +862,17 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) return blk_queue_get_max_sectors(q, rq->cmd_flags); } +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + /* * Request issue related functions. */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 653073d..ed419c6 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -406,13 +406,14 @@ int dm_noflush_suspending(struct dm_target *ti); union map_info *dm_get_mapinfo(struct bio *bio); union map_info *dm_get_rq_mapinfo(struct request *rq); +struct queue_limits *dm_get_queue_limits(struct mapped_device *md); + /* * Geometry functions. */ int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo); int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); - /*----------------------------------------------------------------- * Functions for manipulating device-mapper tables. *---------------------------------------------------------------*/ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a3b8b2e..d98503b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -30,10 +30,13 @@ /* * Framework version for util services. */ +#define UTIL_FW_MINOR 0 + +#define UTIL_WS2K8_FW_MAJOR 1 +#define UTIL_WS2K8_FW_VERSION (UTIL_WS2K8_FW_MAJOR << 16 | UTIL_FW_MINOR) #define UTIL_FW_MAJOR 3 -#define UTIL_FW_MINOR 0 -#define UTIL_FW_MAJOR_MINOR (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) +#define UTIL_FW_VERSION (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR) /* diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 60e9587..ecc82b3 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -53,23 +53,6 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; -enum mem_cgroup_filter_t { - VISIT, /* visit current node */ - SKIP, /* skip the current node and continue traversal */ - SKIP_TREE, /* skip the whole subtree and continue traversal */ -}; - -/* - * mem_cgroup_filter_t predicate might instruct mem_cgroup_iter_cond how to - * iterate through the hierarchy tree. Each tree element is checked by the - * predicate before it is returned by the iterator. If a filter returns - * SKIP or SKIP_TREE then the iterator code continues traversal (with the - * next node down the hierarchy or the next node that doesn't belong under the - * memcg's subtree). - */ -typedef enum mem_cgroup_filter_t -(*mem_cgroup_iter_filter)(struct mem_cgroup *memcg, struct mem_cgroup *root); - #ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or @@ -137,18 +120,9 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); -struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond); - -static inline struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim) -{ - return mem_cgroup_iter_cond(root, prev, reclaim, NULL); -} - +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); /* @@ -260,9 +234,9 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root); +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, @@ -376,15 +350,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok) { } -static inline struct mem_cgroup * -mem_cgroup_iter_cond(struct mem_cgroup *root, - struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond) -{ - /* first call must return non-NULL, second return NULL */ - return (struct mem_cgroup *)(unsigned long)!prev; -} static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, @@ -471,11 +436,11 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root) +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) { - return VISIT; + return 0; } static inline void mem_cgroup_split_huge_fixup(struct page *head) diff --git a/include/linux/mutex.h b/include/linux/mutex.h index ccd4260..bab49da 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -15,8 +15,8 @@ #include <linux/spinlock_types.h> #include <linux/linkage.h> #include <linux/lockdep.h> - #include <linux/atomic.h> +#include <asm/processor.h> /* * Simple, straightforward mutexes with strict semantics: @@ -175,8 +175,8 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); -#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX -#define arch_mutex_cpu_relax() cpu_relax() +#ifndef arch_mutex_cpu_relax +# define arch_mutex_cpu_relax() cpu_relax() #endif #endif diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e36dee5..c56fa8f 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -460,6 +460,7 @@ enum { NFSPROC4_CLNT_FS_LOCATIONS, NFSPROC4_CLNT_RELEASE_LOCKOWNER, NFSPROC4_CLNT_SECINFO, + NFSPROC4_CLNT_FSID_PRESENT, /* nfs41 */ NFSPROC4_CLNT_EXCHANGE_ID, diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index b8cedce..1150ea4 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -41,6 +41,7 @@ struct nfs_client { #define NFS_CS_DISCRTRY 1 /* - disconnect on RPC retry */ #define NFS_CS_MIGRATION 2 /* - transparent state migr */ #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ +#define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -78,6 +79,7 @@ struct nfs_client { char cl_ipaddr[48]; u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; + unsigned long cl_mig_gen; /* NFSv4.0 transport blocking */ struct nfs4_slot_table *cl_slot_tbl; @@ -147,7 +149,9 @@ struct nfs_server { __u64 maxfilesize; /* maximum file size */ struct timespec time_delta; /* smallest time granularity */ unsigned long mount_time; /* when this fs was mounted */ + struct super_block *super; /* VFS super block */ dev_t s_dev; /* superblock dev numbers */ + struct nfs_auth_info auth_info; /* parsed auth flavors */ #ifdef CONFIG_NFS_FSCACHE struct nfs_fscache_key *fscache_key; /* unique key for superblock */ @@ -187,6 +191,12 @@ struct nfs_server { struct list_head state_owners_lru; struct list_head layouts; struct list_head delegations; + + unsigned long mig_gen; + unsigned long mig_status; +#define NFS_MIG_IN_TRANSITION (1) +#define NFS_MIG_FAILED (2) + void (*destroy)(struct nfs_server *); atomic_t active; /* Keep trace of any activity to this server */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 01fd84b..3ccfcec 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -591,6 +591,13 @@ struct nfs_renameres { struct nfs_fattr *new_fattr; }; +/* parsed sec= options */ +#define NFS_AUTH_INFO_MAX_FLAVORS 12 /* see fs/nfs/super.c */ +struct nfs_auth_info { + unsigned int flavor_len; + rpc_authflavor_t flavors[NFS_AUTH_INFO_MAX_FLAVORS]; +}; + /* * Argument struct for decode_entry function */ @@ -1053,14 +1060,18 @@ struct nfs4_fs_locations { struct nfs4_fs_locations_arg { struct nfs4_sequence_args seq_args; const struct nfs_fh *dir_fh; + const struct nfs_fh *fh; const struct qstr *name; struct page *page; const u32 *bitmask; + clientid4 clientid; + unsigned char migration:1, renew:1; }; struct nfs4_fs_locations_res { struct nfs4_sequence_res seq_res; struct nfs4_fs_locations *fs_locations; + unsigned char migration:1, renew:1; }; struct nfs4_secinfo4 { @@ -1084,6 +1095,19 @@ struct nfs4_secinfo_res { struct nfs4_secinfo_flavors *flavors; }; +struct nfs4_fsid_present_arg { + struct nfs4_sequence_args seq_args; + const struct nfs_fh *fh; + clientid4 clientid; + unsigned char renew:1; +}; + +struct nfs4_fsid_present_res { + struct nfs4_sequence_res seq_res; + struct nfs_fh *fh; + unsigned char renew:1; +}; + #endif /* CONFIG_NFS_V4 */ struct nfstime4 { @@ -1455,7 +1479,8 @@ struct nfs_rpc_ops { struct inode * (*open_context) (struct inode *dir, struct nfs_open_context *ctx, int open_flags, - struct iattr *iattr); + struct iattr *iattr, + int *); int (*have_delegation)(struct inode *, fmode_t); int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 535cecf..fcd63ba 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -1,8 +1,6 @@ #ifndef __OF_IRQ_H #define __OF_IRQ_H -#if defined(CONFIG_OF) -struct of_irq; #include <linux/types.h> #include <linux/errno.h> #include <linux/irq.h> @@ -10,14 +8,6 @@ struct of_irq; #include <linux/ioport.h> #include <linux/of.h> -/* - * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC - * implements it differently. However, the prototype is the same for all, - * so declare it here regardless of the CONFIG_OF_IRQ setting. - */ -extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); - -#if defined(CONFIG_OF_IRQ) /** * of_irq - container for device_node/irq_specifier pair for an irq controller * @controller: pointer to interrupt controller device tree node @@ -71,11 +61,17 @@ extern int of_irq_to_resource(struct device_node *dev, int index, extern int of_irq_count(struct device_node *dev); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); -extern struct device_node *of_irq_find_parent(struct device_node *child); extern void of_irq_init(const struct of_device_id *matches); -#endif /* CONFIG_OF_IRQ */ +#if defined(CONFIG_OF) +/* + * irq_of_parse_and_map() is used by all OF enabled platforms; but SPARC + * implements it differently. However, the prototype is the same for all, + * so declare it here regardless of the CONFIG_OF_IRQ setting. + */ +extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); +extern struct device_node *of_irq_find_parent(struct device_node *child); #else /* !CONFIG_OF */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 67e13aa..9bdad43 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -40,6 +40,8 @@ enum regulator_status { }; /** + * struct regulator_linear_range - specify linear voltage ranges + * * Specify a range of voltages for regulator_map_linar_range() and * regulator_list_linear_range(). * diff --git a/include/linux/smp.h b/include/linux/smp.h index cfb7ca0..731f523 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -155,6 +155,12 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } +static inline void __smp_call_function_single(int cpuid, + struct call_single_data *data, int wait) +{ + on_each_cpu(data->func, data->info, wait); +} + #endif /* !SMP */ /* diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6740801..8af2804 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -49,6 +49,7 @@ struct rpc_clnt { unsigned int cl_softrtry : 1,/* soft timeouts */ cl_discrtry : 1,/* disconnect before retry */ + cl_noretranstimeo: 1,/* No retransmit timeouts */ cl_autobind : 1,/* use getport() */ cl_chatty : 1;/* be verbose */ @@ -126,6 +127,7 @@ struct rpc_create_args { #define RPC_CLNT_CREATE_QUIET (1UL << 6) #define RPC_CLNT_CREATE_INFINITE_SLOTS (1UL << 7) #define RPC_CLNT_CREATE_NO_IDLE_TIMEOUT (1UL << 8) +#define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, @@ -134,6 +136,10 @@ void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt); struct rpc_clnt *rpc_clone_client(struct rpc_clnt *); struct rpc_clnt *rpc_clone_client_set_auth(struct rpc_clnt *, rpc_authflavor_t); +int rpc_switch_client_transport(struct rpc_clnt *, + struct xprt_create *, + const struct rpc_timeout *); + void rpc_shutdown_client(struct rpc_clnt *); void rpc_release_client(struct rpc_clnt *); void rpc_task_release_client(struct rpc_task *); diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 096ee58..3a847de 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -122,6 +122,7 @@ struct rpc_task_setup { #define RPC_TASK_SENT 0x0800 /* message was sent */ #define RPC_TASK_TIMEOUT 0x1000 /* fail with ETIMEDOUT on timeout */ #define RPC_TASK_NOCONNECT 0x2000 /* return ENOTCONN if not connected */ +#define RPC_TASK_NO_RETRANS_TIMEOUT 0x4000 /* wait forever for a reply */ #define RPC_IS_ASYNC(t) ((t)->tk_flags & RPC_TASK_ASYNC) #define RPC_IS_SWAPPER(t) ((t)->tk_flags & RPC_TASK_SWAPPER) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index cec7b9b..8097b9d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -288,7 +288,7 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); -int xprt_prepare_transmit(struct rpc_task *task); +bool xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 60ae7c3..4c2301d 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -618,6 +618,7 @@ TRACE_EVENT(block_rq_remap, __field( unsigned int, nr_sector ) __field( dev_t, old_dev ) __field( sector_t, old_sector ) + __field( unsigned int, nr_bios ) __array( char, rwbs, RWBS_LEN) ), @@ -627,15 +628,16 @@ TRACE_EVENT(block_rq_remap, __entry->nr_sector = blk_rq_sectors(rq); __entry->old_dev = dev; __entry->old_sector = from; + __entry->nr_bios = blk_rq_count_bios(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); ), - TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", + TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, MAJOR(__entry->old_dev), MINOR(__entry->old_dev), - (unsigned long long)__entry->old_sector) + (unsigned long long)__entry->old_sector, __entry->nr_bios) ); #endif /* _TRACE_BLOCK_H */ diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 45702c3..f18b3b7 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -42,6 +42,7 @@ struct extent_buffer; { BTRFS_TREE_LOG_OBJECTID, "TREE_LOG" }, \ { BTRFS_QUOTA_TREE_OBJECTID, "QUOTA_TREE" }, \ { BTRFS_TREE_RELOC_OBJECTID, "TREE_RELOC" }, \ + { BTRFS_UUID_TREE_OBJECTID, "UUID_RELOC" }, \ { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }) #define show_root_type(obj) \ diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h index fa8b3ad..46d41e8 100644 --- a/include/uapi/drm/radeon_drm.h +++ b/include/uapi/drm/radeon_drm.h @@ -1007,4 +1007,6 @@ struct drm_radeon_info { #define SI_TILE_MODE_DEPTH_STENCIL_2D_4AA 3 #define SI_TILE_MODE_DEPTH_STENCIL_2D_8AA 2 +#define CIK_TILE_MODE_DEPTH_STENCIL_1D 5 + #endif diff --git a/include/uapi/linux/nfs_mount.h b/include/uapi/linux/nfs_mount.h index 576bddd..64b0f22 100644 --- a/include/uapi/linux/nfs_mount.h +++ b/include/uapi/linux/nfs_mount.h @@ -60,7 +60,7 @@ struct nfs_mount_data { #define NFS_MOUNT_BROKEN_SUID 0x0400 /* 4 */ #define NFS_MOUNT_NOACL 0x0800 /* 4 */ #define NFS_MOUNT_STRICTLOCK 0x1000 /* reserved for NFSv4 */ -#define NFS_MOUNT_SECFLAVOUR 0x2000 /* 5 */ +#define NFS_MOUNT_SECFLAVOUR 0x2000 /* 5 non-text parsed mount data only */ #define NFS_MOUNT_NORDIRPLUS 0x4000 /* 5 */ #define NFS_MOUNT_UNSHARED 0x8000 /* 5 */ #define NFS_MOUNT_FLAGMASK 0xFFFF diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 40a1fb8..009a655 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -380,10 +380,13 @@ struct perf_event_mmap_page { union { __u64 capabilities; struct { - __u64 cap_usr_time : 1, - cap_usr_rdpmc : 1, - cap_usr_time_zero : 1, - cap_____res : 61; + __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */ + cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ + + cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ + cap_user_time : 1, /* The time_* fields are used */ + cap_user_time_zero : 1, /* The time_zero field is used */ + cap_____res : 59; }; }; @@ -442,12 +445,13 @@ struct perf_event_mmap_page { * ((rem * time_mult) >> time_shift); */ __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ /* * Hole for extension of the self monitor capabilities */ - __u64 __reserved[119]; /* align to 1k */ + __u8 __reserved[118*8+4]; /* align to 1k. */ /* * Control data for the mmap() data buffer. @@ -528,6 +532,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, @@ -165,6 +165,15 @@ static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) ipc_rmid(&msg_ids(ns), &s->q_perm); } +static void msg_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct msg_queue *msq = ipc_rcu_to_struct(p); + + security_msg_queue_free(msq); + ipc_rcu_free(head); +} + /** * newque - Create a new msg queue * @ns: namespace @@ -189,15 +198,14 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(msq); if (retval) { - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, ipc_rcu_free); return retval; } /* ipc_addid() locks msq upon success. */ id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); if (id < 0) { - security_msg_queue_free(msq); - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, msg_rcu_free); return id; } @@ -276,8 +284,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) free_msg(msg); } atomic_sub(msq->q_cbytes, &ns->msg_bytes); - security_msg_queue_free(msq); - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, msg_rcu_free); } /* @@ -688,6 +695,12 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, if (ipcperms(ns, &msq->q_perm, S_IWUGO)) goto out_unlock0; + /* raced with RMID? */ + if (msq->q_perm.deleted) { + err = -EIDRM; + goto out_unlock0; + } + err = security_msg_queue_msgsnd(msq, msg, msgflg); if (err) goto out_unlock0; @@ -717,7 +730,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, rcu_read_lock(); ipc_lock_object(&msq->q_perm); - ipc_rcu_putref(msq); + ipc_rcu_putref(msq, ipc_rcu_free); if (msq->q_perm.deleted) { err = -EIDRM; goto out_unlock0; @@ -894,6 +907,13 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl goto out_unlock1; ipc_lock_object(&msq->q_perm); + + /* raced with RMID? */ + if (msq->q_perm.deleted) { + msg = ERR_PTR(-EIDRM); + goto out_unlock0; + } + msg = find_msg(msq, &msgtyp, mode); if (!IS_ERR(msg)) { /* @@ -243,71 +243,122 @@ static void merge_queues(struct sem_array *sma) } } +static void sem_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct sem_array *sma = ipc_rcu_to_struct(p); + + security_sem_free(sma); + ipc_rcu_free(head); +} + +/* + * Wait until all currently ongoing simple ops have completed. + * Caller must own sem_perm.lock. + * New simple ops cannot start, because simple ops first check + * that sem_perm.lock is free. + * that a) sem_perm.lock is free and b) complex_count is 0. + */ +static void sem_wait_array(struct sem_array *sma) +{ + int i; + struct sem *sem; + + if (sma->complex_count) { + /* The thread that increased sma->complex_count waited on + * all sem->lock locks. Thus we don't need to wait again. + */ + return; + } + + for (i = 0; i < sma->sem_nsems; i++) { + sem = sma->sem_base + i; + spin_unlock_wait(&sem->lock); + } +} + /* * If the request contains only one semaphore operation, and there are * no complex transactions pending, lock only the semaphore involved. * Otherwise, lock the entire semaphore array, since we either have * multiple semaphores in our own semops, or we need to look at * semaphores from other pending complex operations. - * - * Carefully guard against sma->complex_count changing between zero - * and non-zero while we are spinning for the lock. The value of - * sma->complex_count cannot change while we are holding the lock, - * so sem_unlock should be fine. - * - * The global lock path checks that all the local locks have been released, - * checking each local lock once. This means that the local lock paths - * cannot start their critical sections while the global lock is held. */ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, int nsops) { - int locknum; - again: - if (nsops == 1 && !sma->complex_count) { - struct sem *sem = sma->sem_base + sops->sem_num; + struct sem *sem; - /* Lock just the semaphore we are interested in. */ - spin_lock(&sem->lock); + if (nsops != 1) { + /* Complex operation - acquire a full lock */ + ipc_lock_object(&sma->sem_perm); - /* - * If sma->complex_count was set while we were spinning, - * we may need to look at things we did not lock here. + /* And wait until all simple ops that are processed + * right now have dropped their locks. */ - if (unlikely(sma->complex_count)) { - spin_unlock(&sem->lock); - goto lock_array; - } + sem_wait_array(sma); + return -1; + } + + /* + * Only one semaphore affected - try to optimize locking. + * The rules are: + * - optimized locking is possible if no complex operation + * is either enqueued or processed right now. + * - The test for enqueued complex ops is simple: + * sma->complex_count != 0 + * - Testing for complex ops that are processed right now is + * a bit more difficult. Complex ops acquire the full lock + * and first wait that the running simple ops have completed. + * (see above) + * Thus: If we own a simple lock and the global lock is free + * and complex_count is now 0, then it will stay 0 and + * thus just locking sem->lock is sufficient. + */ + sem = sma->sem_base + sops->sem_num; + if (sma->complex_count == 0) { /* - * Another process is holding the global lock on the - * sem_array; we cannot enter our critical section, - * but have to wait for the global lock to be released. + * It appears that no complex operation is around. + * Acquire the per-semaphore lock. */ - if (unlikely(spin_is_locked(&sma->sem_perm.lock))) { - spin_unlock(&sem->lock); - spin_unlock_wait(&sma->sem_perm.lock); - goto again; + spin_lock(&sem->lock); + + /* Then check that the global lock is free */ + if (!spin_is_locked(&sma->sem_perm.lock)) { + /* spin_is_locked() is not a memory barrier */ + smp_mb(); + + /* Now repeat the test of complex_count: + * It can't change anymore until we drop sem->lock. + * Thus: if is now 0, then it will stay 0. + */ + if (sma->complex_count == 0) { + /* fast path successful! */ + return sops->sem_num; + } } + spin_unlock(&sem->lock); + } - locknum = sops->sem_num; + /* slow path: acquire the full lock */ + ipc_lock_object(&sma->sem_perm); + + if (sma->complex_count == 0) { + /* False alarm: + * There is no complex operation, thus we can switch + * back to the fast path. + */ + spin_lock(&sem->lock); + ipc_unlock_object(&sma->sem_perm); + return sops->sem_num; } else { - int i; - /* - * Lock the semaphore array, and wait for all of the - * individual semaphore locks to go away. The code - * above ensures no new single-lock holders will enter - * their critical section while the array lock is held. + /* Not a false alarm, thus complete the sequence for a + * full lock. */ - lock_array: - ipc_lock_object(&sma->sem_perm); - for (i = 0; i < sma->sem_nsems; i++) { - struct sem *sem = sma->sem_base + i; - spin_unlock_wait(&sem->lock); - } - locknum = -1; + sem_wait_array(sma); + return -1; } - return locknum; } static inline void sem_unlock(struct sem_array *sma, int locknum) @@ -374,12 +425,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); - ipc_rcu_putref(sma); -} - -static inline void sem_putref(struct sem_array *sma) -{ - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) @@ -458,14 +504,13 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) sma->sem_perm.security = NULL; retval = security_sem_alloc(sma); if (retval) { - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return retval; } id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if (id < 0) { - security_sem_free(sma); - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, sem_rcu_free); return id; } ns->used_sems += nsems; @@ -873,6 +918,24 @@ again: } /** + * set_semotime(sma, sops) - set sem_otime + * @sma: semaphore array + * @sops: operations that modified the array, may be NULL + * + * sem_otime is replicated to avoid cache line trashing. + * This function sets one instance to the current time. + */ +static void set_semotime(struct sem_array *sma, struct sembuf *sops) +{ + if (sops == NULL) { + sma->sem_base[0].sem_otime = get_seconds(); + } else { + sma->sem_base[sops[0].sem_num].sem_otime = + get_seconds(); + } +} + +/** * do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue * @sma: semaphore array * @sops: operations that were performed @@ -922,17 +985,10 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop } } } - if (otime) { - if (sops == NULL) { - sma->sem_base[0].sem_otime = get_seconds(); - } else { - sma->sem_base[sops[0].sem_num].sem_otime = - get_seconds(); - } - } + if (otime) + set_semotime(sma, sops); } - /* The following counts are associated to each semaphore: * semncnt number of tasks waiting on semval being nonzero * semzcnt number of tasks waiting on semval being zero @@ -1047,8 +1103,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) wake_up_sem_queue_do(&tasks); ns->used_sems -= sma->sem_nsems; - security_sem_free(sma); - ipc_rcu_putref(sma); + ipc_rcu_putref(sma, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) @@ -1292,7 +1347,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_unlock(); sem_io = ipc_alloc(sizeof(ushort)*nsems); if(sem_io == NULL) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return -ENOMEM; } @@ -1328,20 +1383,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, if(nsems > SEMMSL_FAST) { sem_io = ipc_alloc(sizeof(ushort)*nsems); if(sem_io == NULL) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return -ENOMEM; } } if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); err = -ERANGE; goto out_free; } @@ -1629,7 +1684,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) /* step 2: allocate new undo structure */ new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); if (!new) { - sem_putref(sma); + ipc_rcu_putref(sma, ipc_rcu_free); return ERR_PTR(-ENOMEM); } @@ -1795,12 +1850,17 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, error = perform_atomic_semop(sma, sops, nsops, un, task_tgid_vnr(current)); - if (error <= 0) { - if (alter && error == 0) + if (error == 0) { + /* If the operation was successful, then do + * the required updates. + */ + if (alter) do_smart_update(sma, sops, nsops, 1, &tasks); - - goto out_unlock_free; + else + set_semotime(sma, sops); } + if (error <= 0) + goto out_unlock_free; /* We need to sleep on this operation, so we put the current * task into the pending queue and go to sleep. @@ -2059,6 +2119,14 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) struct sem_array *sma = it; time_t sem_otime; + /* + * The proc interface isn't aware of sem_lock(), it calls + * ipc_lock_object() directly (in sysvipc_find_ipc). + * In order to stay compatible with sem_lock(), we must wait until + * all simple semop() calls have left their critical regions. + */ + sem_wait_array(sma); + sem_otime = get_semotime(sma); return seq_printf(s, @@ -167,6 +167,15 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) ipc_lock_object(&ipcp->shm_perm); } +static void shm_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + struct shmid_kernel *shp = ipc_rcu_to_struct(p); + + security_shm_free(shp); + ipc_rcu_free(head); +} + static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) { ipc_rmid(&shm_ids(ns), &s->shm_perm); @@ -208,8 +217,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) user_shm_unlock(file_inode(shp->shm_file)->i_size, shp->mlock_user); fput (shp->shm_file); - security_shm_free(shp); - ipc_rcu_putref(shp); + ipc_rcu_putref(shp, shm_rcu_free); } /* @@ -497,7 +505,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(shp); if (error) { - ipc_rcu_putref(shp); + ipc_rcu_putref(shp, ipc_rcu_free); return error; } @@ -566,8 +574,7 @@ no_id: user_shm_unlock(size, shp->mlock_user); fput(file); no_file: - security_shm_free(shp); - ipc_rcu_putref(shp); + ipc_rcu_putref(shp, shm_rcu_free); return error; } @@ -474,11 +474,6 @@ void ipc_free(void* ptr, int size) kfree(ptr); } -struct ipc_rcu { - struct rcu_head rcu; - atomic_t refcount; -} ____cacheline_aligned_in_smp; - /** * ipc_rcu_alloc - allocate ipc and rcu space * @size: size desired @@ -505,27 +500,24 @@ int ipc_rcu_getref(void *ptr) return atomic_inc_not_zero(&p->refcount); } -/** - * ipc_schedule_free - free ipc + rcu space - * @head: RCU callback structure for queued work - */ -static void ipc_schedule_free(struct rcu_head *head) -{ - vfree(container_of(head, struct ipc_rcu, rcu)); -} - -void ipc_rcu_putref(void *ptr) +void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)) { struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1; if (!atomic_dec_and_test(&p->refcount)) return; - if (is_vmalloc_addr(ptr)) { - call_rcu(&p->rcu, ipc_schedule_free); - } else { - kfree_rcu(p, rcu); - } + call_rcu(&p->rcu, func); +} + +void ipc_rcu_free(struct rcu_head *head) +{ + struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu); + + if (is_vmalloc_addr(p)) + vfree(p); + else + kfree(p); } /** @@ -47,6 +47,13 @@ static inline void msg_exit_ns(struct ipc_namespace *ns) { } static inline void shm_exit_ns(struct ipc_namespace *ns) { } #endif +struct ipc_rcu { + struct rcu_head rcu; + atomic_t refcount; +} ____cacheline_aligned_in_smp; + +#define ipc_rcu_to_struct(p) ((void *)(p+1)) + /* * Structure that holds the parameters needed by the ipc operations * (see after) @@ -120,7 +127,8 @@ void ipc_free(void* ptr, int size); */ void* ipc_rcu_alloc(int size); int ipc_rcu_getref(void *ptr); -void ipc_rcu_putref(void *ptr); +void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head)); +void ipc_rcu_free(struct rcu_head *head); struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int); struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id); diff --git a/kernel/audit.c b/kernel/audit.c index 91e53d0..7b0e23a 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1117,9 +1117,10 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, sleep_time = timeout_start + audit_backlog_wait_time - jiffies; - if ((long)sleep_time > 0) + if ((long)sleep_time > 0) { wait_for_auditd(sleep_time); - continue; + continue; + } } if (audit_rate_check() && printk_ratelimit()) printk(KERN_WARNING diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 247091b..859c8df 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -51,6 +51,15 @@ void context_tracking_user_enter(void) unsigned long flags; /* + * Repeat the user_enter() check here because some archs may be calling + * this from asm and if no CPU needs context tracking, they shouldn't + * go further. Repeat the check here until they support the static key + * check. + */ + if (!static_key_false(&context_tracking_enabled)) + return; + + /* * Some contexts may involve an exception occuring in an irq, * leading to that nesting: * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() @@ -151,6 +160,9 @@ void context_tracking_user_exit(void) { unsigned long flags; + if (!static_key_false(&context_tracking_enabled)) + return; + if (in_interrupt()) return; diff --git a/kernel/events/core.c b/kernel/events/core.c index dd236b6..cb4238e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3660,6 +3660,26 @@ static void calc_timer_values(struct perf_event *event, *running = ctx_time - event->tstamp_running; } +static void perf_event_init_userpage(struct perf_event *event) +{ + struct perf_event_mmap_page *userpg; + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb) + goto unlock; + + userpg = rb->user_page; + + /* Allow new userspace to detect that bit 0 is deprecated */ + userpg->cap_bit0_is_deprecated = 1; + userpg->size = offsetof(struct perf_event_mmap_page, __reserved); + +unlock: + rcu_read_unlock(); +} + void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { } @@ -4044,6 +4064,7 @@ again: ring_buffer_attach(event, rb); rcu_assign_pointer(event->rb, rb); + perf_event_init_userpage(event); perf_event_update_userpage(event); unlock: diff --git a/kernel/kmod.c b/kernel/kmod.c index fb32636..b086006 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -571,6 +571,10 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) DECLARE_COMPLETION_ONSTACK(done); int retval = 0; + if (!sub_info->path) { + call_usermodehelper_freeinfo(sub_info); + return -EINVAL; + } helper_lock(); if (!khelper_wq || usermodehelper_disabled) { retval = -EBUSY; diff --git a/kernel/params.c b/kernel/params.c index 81c4e78..c00d5b5 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -254,11 +254,11 @@ int parse_args(const char *doing, STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", unsigned long, kstrtoul); -STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtoul); +STANDARD_PARAM_DEF(short, short, "%hi", long, kstrtol); STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", unsigned long, kstrtoul); -STANDARD_PARAM_DEF(int, int, "%i", long, kstrtoul); +STANDARD_PARAM_DEF(int, int, "%i", long, kstrtol); STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, kstrtoul); -STANDARD_PARAM_DEF(long, long, "%li", long, kstrtoul); +STANDARD_PARAM_DEF(long, long, "%li", long, kstrtol); STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, kstrtoul); int param_set_charp(const char *val, const struct kernel_param *kp) diff --git a/kernel/pid.c b/kernel/pid.c index ebe5e80..9b9a266 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -273,6 +273,11 @@ void free_pid(struct pid *pid) */ wake_up_process(ns->child_reaper); break; + case PIDNS_HASH_ADDING: + /* Handle a fork failure of the first process */ + WARN_ON(ns->child_reaper); + ns->nr_hashed = 0; + /* fall through */ case 0: schedule_work(&ns->proc_work); break; diff --git a/kernel/reboot.c b/kernel/reboot.c index 269ed93..f813b34 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -32,7 +32,14 @@ EXPORT_SYMBOL(cad_pid); #endif enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE; -int reboot_default; +/* + * This variable is used privately to keep track of whether or not + * reboot_type is still set to its default value (i.e., reboot= hasn't + * been set on the command line). This is needed so that we can + * suppress DMI scanning for reboot quirks. Without it, it's + * impossible to override a faulty reboot quirk without recompiling. + */ +int reboot_default = 1; int reboot_cpu; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 11cd136..7c70201 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4242,7 +4242,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) } if (!se) { - cfs_rq->h_load = rq->avg.load_avg_contrib; + cfs_rq->h_load = cfs_rq->runnable_load_avg; cfs_rq->last_h_load_update = now; } @@ -4823,8 +4823,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) (busiest->load_per_task * SCHED_POWER_SCALE) / busiest->group_power; - if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >= - (scaled_busy_load_per_task * imbn)) { + if (busiest->avg_load + scaled_busy_load_per_task >= + local->avg_load + (scaled_busy_load_per_task * imbn)) { env->imbalance = busiest->load_per_task; return; } @@ -4896,7 +4896,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * max load less than avg load(as we skip the groups at or below * its cpu_power, while calculating max_load..) */ - if (busiest->avg_load < sds->avg_load) { + if (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load) { env->imbalance = 0; return fix_small_imbalance(env, sds); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 51c4f34..4431610 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -486,7 +486,52 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -static int watchdog_enable_all_cpus(void) +static void restart_watchdog_hrtimer(void *info) +{ + struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); + int ret; + + /* + * No need to cancel and restart hrtimer if it is currently executing + * because it will reprogram itself with the new period now. + * We should never see it unqueued here because we are running per-cpu + * with interrupts disabled. + */ + ret = hrtimer_try_to_cancel(hrtimer); + if (ret == 1) + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); +} + +static void update_timers(int cpu) +{ + struct call_single_data data = {.func = restart_watchdog_hrtimer}; + /* + * Make sure that perf event counter will adopt to a new + * sampling period. Updating the sampling period directly would + * be much nicer but we do not have an API for that now so + * let's use a big hammer. + * Hrtimer will adopt the new period on the next tick but this + * might be late already so we have to restart the timer as well. + */ + watchdog_nmi_disable(cpu); + __smp_call_function_single(cpu, &data, 1); + watchdog_nmi_enable(cpu); +} + +static void update_timers_all_cpus(void) +{ + int cpu; + + get_online_cpus(); + preempt_disable(); + for_each_online_cpu(cpu) + update_timers(cpu); + preempt_enable(); + put_online_cpus(); +} + +static int watchdog_enable_all_cpus(bool sample_period_changed) { int err = 0; @@ -496,6 +541,8 @@ static int watchdog_enable_all_cpus(void) pr_err("Failed to create watchdog threads, disabled\n"); else watchdog_running = 1; + } else if (sample_period_changed) { + update_timers_all_cpus(); } return err; @@ -520,13 +567,15 @@ int proc_dowatchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int err, old_thresh, old_enabled; + static DEFINE_MUTEX(watchdog_proc_mutex); + mutex_lock(&watchdog_proc_mutex); old_thresh = ACCESS_ONCE(watchdog_thresh); old_enabled = ACCESS_ONCE(watchdog_user_enabled); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (err || !write) - return err; + goto out; set_sample_period(); /* @@ -535,7 +584,7 @@ int proc_dowatchdog(struct ctl_table *table, int write, * watchdog_*_all_cpus() function takes care of this. */ if (watchdog_user_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); + err = watchdog_enable_all_cpus(old_thresh != watchdog_thresh); else watchdog_disable_all_cpus(); @@ -544,7 +593,8 @@ int proc_dowatchdog(struct ctl_table *table, int write, watchdog_thresh = old_thresh; watchdog_user_enabled = old_enabled; } - +out: + mutex_unlock(&watchdog_proc_mutex); return err; } #endif /* CONFIG_SYSCTL */ @@ -554,5 +604,5 @@ void __init lockup_detector_init(void) set_sample_period(); if (watchdog_user_enabled) - watchdog_enable_all_cpus(); + watchdog_enable_all_cpus(false); } diff --git a/lib/kobject.c b/lib/kobject.c index 9621751..669bf19 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -933,10 +933,7 @@ const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj) bool kobj_ns_current_may_mount(enum kobj_ns_type type) { - bool may_mount = false; - - if (type == KOBJ_NS_TYPE_NONE) - return true; + bool may_mount = true; spin_lock(&kobj_ns_type_lock); if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) && diff --git a/lib/lockref.c b/lib/lockref.c index 677d036c..6f9d434 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -4,6 +4,22 @@ #ifdef CONFIG_CMPXCHG_LOCKREF /* + * Allow weakly-ordered memory architectures to provide barrier-less + * cmpxchg semantics for lockref updates. + */ +#ifndef cmpxchg64_relaxed +# define cmpxchg64_relaxed cmpxchg64 +#endif + +/* + * Allow architectures to override the default cpu_relax() within CMPXCHG_LOOP. + * This is useful for architectures with an expensive cpu_relax(). + */ +#ifndef arch_mutex_cpu_relax +# define arch_mutex_cpu_relax() cpu_relax() +#endif + +/* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ @@ -14,12 +30,13 @@ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old, prev = old; \ CODE \ - old.lock_count = cmpxchg64(&lockref->lock_count, \ - old.lock_count, new.lock_count); \ + old.lock_count = cmpxchg64_relaxed(&lockref->lock_count, \ + old.lock_count, \ + new.lock_count); \ if (likely(old.lock_count == prev.lock_count)) { \ SUCCESS; \ } \ - cpu_relax(); \ + arch_mutex_cpu_relax(); \ } \ } while (0) diff --git a/mm/bounce.c b/mm/bounce.c index c9f0a43..5a7d58f 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -204,6 +204,8 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, struct bio_vec *to, *from; unsigned i; + if (force) + goto bounce; bio_for_each_segment(from, *bio_orig, i) if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q)) goto bounce; diff --git a/mm/compaction.c b/mm/compaction.c index c437893..b5326b1 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -677,6 +677,13 @@ static void isolate_freepages(struct zone *zone, pfn -= pageblock_nr_pages) { unsigned long isolated; + /* + * This can iterate a massively long zone without finding any + * suitable migration targets, so periodically check if we need + * to schedule. + */ + cond_resched(); + if (!pfn_valid(pfn)) continue; diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index afc2daa..4c84678 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -20,8 +20,6 @@ static int hwpoison_inject(void *data, u64 val) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!hwpoison_filter_enable) - goto inject; if (!pfn_valid(pfn)) return -ENXIO; @@ -33,6 +31,9 @@ static int hwpoison_inject(void *data, u64 val) if (!get_page_unless_zero(hpage)) return 0; + if (!hwpoison_filter_enable) + goto inject; + if (!PageLRU(p) && !PageHuge(p)) shake_page(p, 0); /* diff --git a/mm/madvise.c b/mm/madvise.c index 6975bc8..539eeb9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -343,10 +343,11 @@ static long madvise_remove(struct vm_area_struct *vma, */ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end) { + struct page *p; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - for (; start < end; start += PAGE_SIZE) { - struct page *p; + for (; start < end; start += PAGE_SIZE << + compound_order(compound_head(p))) { int ret; ret = get_user_pages_fast(start, 1, 0, &p); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d5ff3ce..1c52ddb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -39,6 +39,7 @@ #include <linux/limits.h> #include <linux/export.h> #include <linux/mutex.h> +#include <linux/rbtree.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -160,6 +161,10 @@ struct mem_cgroup_per_zone { struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1]; + struct rb_node tree_node; /* RB tree node */ + unsigned long long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -168,6 +173,26 @@ struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; }; +/* + * Cgroups above their limits are maintained in a RB-Tree, independent of + * their hierarchy representation + */ + +struct mem_cgroup_tree_per_zone { + struct rb_root rb_root; + spinlock_t lock; +}; + +struct mem_cgroup_tree_per_node { + struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; +}; + +struct mem_cgroup_tree { + struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; +}; + +static struct mem_cgroup_tree soft_limit_tree __read_mostly; + struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; u64 threshold; @@ -303,22 +328,6 @@ struct mem_cgroup { atomic_t numainfo_events; atomic_t numainfo_updating; #endif - /* - * Protects soft_contributed transitions. - * See mem_cgroup_update_soft_limit - */ - spinlock_t soft_lock; - - /* - * If true then this group has increased parents' children_in_excess - * when it got over the soft limit. - * When a group falls bellow the soft limit, parents' children_in_excess - * is decreased and soft_contributed changed to false. - */ - bool soft_contributed; - - /* Number of children that are in soft limit excess */ - atomic_t children_in_excess; struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ @@ -422,6 +431,7 @@ static bool move_file(void) * limit reclaim to prevent infinite loops, if they ever occur. */ #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 +#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, @@ -648,6 +658,164 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page) return mem_cgroup_zoneinfo(memcg, nid, zid); } +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_node_zone(int nid, int zid) +{ + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static struct mem_cgroup_tree_per_zone * +soft_limit_tree_from_page(struct page *page) +{ + int nid = page_to_nid(page); + int zid = page_zonenum(page); + + return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; +} + +static void +__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz, + unsigned long long new_usage_in_excess) +{ + struct rb_node **p = &mctz->rb_root.rb_node; + struct rb_node *parent = NULL; + struct mem_cgroup_per_zone *mz_node; + + if (mz->on_tree) + return; + + mz->usage_in_excess = new_usage_in_excess; + if (!mz->usage_in_excess) + return; + while (*p) { + parent = *p; + mz_node = rb_entry(parent, struct mem_cgroup_per_zone, + tree_node); + if (mz->usage_in_excess < mz_node->usage_in_excess) + p = &(*p)->rb_left; + /* + * We can't avoid mem cgroups that are over their soft + * limit by the same amount + */ + else if (mz->usage_in_excess >= mz_node->usage_in_excess) + p = &(*p)->rb_right; + } + rb_link_node(&mz->tree_node, parent, p); + rb_insert_color(&mz->tree_node, &mctz->rb_root); + mz->on_tree = true; +} + +static void +__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + if (!mz->on_tree) + return; + rb_erase(&mz->tree_node, &mctz->rb_root); + mz->on_tree = false; +} + +static void +mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, + struct mem_cgroup_per_zone *mz, + struct mem_cgroup_tree_per_zone *mctz) +{ + spin_lock(&mctz->lock); + __mem_cgroup_remove_exceeded(memcg, mz, mctz); + spin_unlock(&mctz->lock); +} + + +static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) +{ + unsigned long long excess; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + int nid = page_to_nid(page); + int zid = page_zonenum(page); + mctz = soft_limit_tree_from_page(page); + + /* + * Necessary to update all ancestors when hierarchy is used. + * because their event counter is not touched. + */ + for (; memcg; memcg = parent_mem_cgroup(memcg)) { + mz = mem_cgroup_zoneinfo(memcg, nid, zid); + excess = res_counter_soft_limit_excess(&memcg->res); + /* + * We have to update the tree if mz is on RB-tree or + * mem is over its softlimit. + */ + if (excess || mz->on_tree) { + spin_lock(&mctz->lock); + /* if on-tree, remove it */ + if (mz->on_tree) + __mem_cgroup_remove_exceeded(memcg, mz, mctz); + /* + * Insert again. mz->usage_in_excess will be updated. + * If excess is 0, no tree ops. + */ + __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); + spin_unlock(&mctz->lock); + } + } +} + +static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) +{ + int node, zone; + struct mem_cgroup_per_zone *mz; + struct mem_cgroup_tree_per_zone *mctz; + + for_each_node(node) { + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + mz = mem_cgroup_zoneinfo(memcg, node, zone); + mctz = soft_limit_tree_node_zone(node, zone); + mem_cgroup_remove_exceeded(memcg, mz, mctz); + } + } +} + +static struct mem_cgroup_per_zone * +__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct rb_node *rightmost = NULL; + struct mem_cgroup_per_zone *mz; + +retry: + mz = NULL; + rightmost = rb_last(&mctz->rb_root); + if (!rightmost) + goto done; /* Nothing to reclaim from */ + + mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); + /* + * Remove the node now but someone else can add it back, + * we will to add it back at the end of reclaim to its correct + * position in the tree. + */ + __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + if (!res_counter_soft_limit_excess(&mz->memcg->res) || + !css_tryget(&mz->memcg->css)) + goto retry; +done: + return mz; +} + +static struct mem_cgroup_per_zone * +mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) +{ + struct mem_cgroup_per_zone *mz; + + spin_lock(&mctz->lock); + mz = __mem_cgroup_largest_soft_limit_node(mctz); + spin_unlock(&mctz->lock); + return mz; +} + /* * Implementation Note: reading percpu statistics for memcg. * @@ -822,48 +990,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, } /* - * Called from rate-limited memcg_check_events when enough - * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure - * that all the parents up the hierarchy will be notified that this group - * is in excess or that it is not in excess anymore. mmecg->soft_contributed - * makes the transition a single action whenever the state flips from one to - * the other. - */ -static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg) -{ - unsigned long long excess = res_counter_soft_limit_excess(&memcg->res); - struct mem_cgroup *parent = memcg; - int delta = 0; - - spin_lock(&memcg->soft_lock); - if (excess) { - if (!memcg->soft_contributed) { - delta = 1; - memcg->soft_contributed = true; - } - } else { - if (memcg->soft_contributed) { - delta = -1; - memcg->soft_contributed = false; - } - } - - /* - * Necessary to update all ancestors when hierarchy is used - * because their event counter is not touched. - * We track children even outside the hierarchy for the root - * cgroup because tree walk starting at root should visit - * all cgroups and we want to prevent from pointless tree - * walk if no children is below the limit. - */ - while (delta && (parent = parent_mem_cgroup(parent))) - atomic_add(delta, &parent->children_in_excess); - if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy) - atomic_add(delta, &root_mem_cgroup->children_in_excess); - spin_unlock(&memcg->soft_lock); -} - -/* * Check events in order. * */ @@ -886,7 +1012,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) - mem_cgroup_update_soft_limit(memcg); + mem_cgroup_update_tree(memcg, page); #if MAX_NUMNODES > 1 if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); @@ -929,15 +1055,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) return memcg; } -static enum mem_cgroup_filter_t -mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root, - mem_cgroup_iter_filter cond) -{ - if (!cond) - return VISIT; - return cond(memcg, root); -} - /* * Returns a next (in a pre-order walk) alive memcg (with elevated css * ref. count) or NULL if the whole root's subtree has been visited. @@ -945,7 +1062,7 @@ mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root, * helper function to be used by mem_cgroup_iter */ static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, - struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond) + struct mem_cgroup *last_visited) { struct cgroup_subsys_state *prev_css, *next_css; @@ -963,31 +1080,11 @@ skip_node: if (next_css) { struct mem_cgroup *mem = mem_cgroup_from_css(next_css); - switch (mem_cgroup_filter(mem, root, cond)) { - case SKIP: + if (css_tryget(&mem->css)) + return mem; + else { prev_css = next_css; goto skip_node; - case SKIP_TREE: - if (mem == root) - return NULL; - /* - * css_rightmost_descendant is not an optimal way to - * skip through a subtree (especially for imbalanced - * trees leaning to right) but that's what we have right - * now. More effective solution would be traversing - * right-up for first non-NULL without calling - * css_next_descendant_pre afterwards. - */ - prev_css = css_rightmost_descendant(next_css); - goto skip_node; - case VISIT: - if (css_tryget(&mem->css)) - return mem; - else { - prev_css = next_css; - goto skip_node; - } - break; } } @@ -1051,7 +1148,6 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, * @root: hierarchy root * @prev: previously returned memcg, NULL on first invocation * @reclaim: cookie for shared reclaim walks, NULL for full walks - * @cond: filter for visited nodes, NULL for no filter * * Returns references to children of the hierarchy below @root, or * @root itself, or %NULL after a full round-trip. @@ -1064,18 +1160,15 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter, * divide up the memcgs in the hierarchy among all concurrent * reclaimers operating on the same zone and priority. */ -struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, - struct mem_cgroup_reclaim_cookie *reclaim, - mem_cgroup_iter_filter cond) + struct mem_cgroup_reclaim_cookie *reclaim) { struct mem_cgroup *memcg = NULL; struct mem_cgroup *last_visited = NULL; - if (mem_cgroup_disabled()) { - /* first call must return non-NULL, second return NULL */ - return (struct mem_cgroup *)(unsigned long)!prev; - } + if (mem_cgroup_disabled()) + return NULL; if (!root) root = root_mem_cgroup; @@ -1086,9 +1179,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, if (!root->use_hierarchy && root != root_mem_cgroup) { if (prev) goto out_css_put; - if (mem_cgroup_filter(root, root, cond) == VISIT) - return root; - return NULL; + return root; } rcu_read_lock(); @@ -1111,7 +1202,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, last_visited = mem_cgroup_iter_load(iter, root, &seq); } - memcg = __mem_cgroup_iter_next(root, last_visited, cond); + memcg = __mem_cgroup_iter_next(root, last_visited); if (reclaim) { mem_cgroup_iter_update(iter, last_visited, memcg, seq); @@ -1122,11 +1213,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root, reclaim->generation = iter->generation; } - /* - * We have finished the whole tree walk or no group has been - * visited because filter told us to skip the root node. - */ - if (!memcg && (prev || (cond && !last_visited))) + if (prev && !memcg) goto out_unlock; } out_unlock: @@ -1767,7 +1854,6 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg, return total; } -#if MAX_NUMNODES > 1 /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg @@ -1790,6 +1876,7 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg, return false; } +#if MAX_NUMNODES > 1 /* * Always updating the nodemask is not very good - even if we have an empty @@ -1857,50 +1944,104 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) return node; } +/* + * Check all nodes whether it contains reclaimable pages or not. + * For quick scan, we make use of scan_nodes. This will allow us to skip + * unused nodes. But scan_nodes is lazily updated and may not cotain + * enough new information. We need to do double check. + */ +static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) +{ + int nid; + + /* + * quick check...making use of scan_node. + * We can skip unused nodes. + */ + if (!nodes_empty(memcg->scan_nodes)) { + for (nid = first_node(memcg->scan_nodes); + nid < MAX_NUMNODES; + nid = next_node(nid, memcg->scan_nodes)) { + + if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) + return true; + } + } + /* + * Check rest of nodes. + */ + for_each_node_state(nid, N_MEMORY) { + if (node_isset(nid, memcg->scan_nodes)) + continue; + if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) + return true; + } + return false; +} + #else int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { return 0; } -#endif - -/* - * A group is eligible for the soft limit reclaim under the given root - * hierarchy if - * a) it is over its soft limit - * b) any parent up the hierarchy is over its soft limit - * - * If the given group doesn't have any children over the limit then it - * doesn't make any sense to iterate its subtree. - */ -enum mem_cgroup_filter_t -mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg, - struct mem_cgroup *root) +static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) { - struct mem_cgroup *parent; - - if (!memcg) - memcg = root_mem_cgroup; - parent = memcg; - - if (res_counter_soft_limit_excess(&memcg->res)) - return VISIT; + return test_mem_cgroup_node_reclaimable(memcg, 0, noswap); +} +#endif - /* - * If any parent up to the root in the hierarchy is over its soft limit - * then we have to obey and reclaim from this group as well. - */ - while ((parent = parent_mem_cgroup(parent))) { - if (res_counter_soft_limit_excess(&parent->res)) - return VISIT; - if (parent == root) +static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, + struct zone *zone, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + struct mem_cgroup *victim = NULL; + int total = 0; + int loop = 0; + unsigned long excess; + unsigned long nr_scanned; + struct mem_cgroup_reclaim_cookie reclaim = { + .zone = zone, + .priority = 0, + }; + + excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT; + + while (1) { + victim = mem_cgroup_iter(root_memcg, victim, &reclaim); + if (!victim) { + loop++; + if (loop >= 2) { + /* + * If we have not been able to reclaim + * anything, it might because there are + * no reclaimable pages under this hierarchy + */ + if (!total) + break; + /* + * We want to do more targeted reclaim. + * excess >> 2 is not to excessive so as to + * reclaim too much, nor too less that we keep + * coming back to reclaim from this cgroup + */ + if (total >= (excess >> 2) || + (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) + break; + } + continue; + } + if (!mem_cgroup_reclaimable(victim, false)) + continue; + total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false, + zone, &nr_scanned); + *total_scanned += nr_scanned; + if (!res_counter_soft_limit_excess(&root_memcg->res)) break; } - - if (!atomic_read(&memcg->children_in_excess)) - return SKIP_TREE; - return SKIP; + mem_cgroup_iter_break(root_memcg, victim); + return total; } static DEFINE_SPINLOCK(memcg_oom_lock); @@ -2812,7 +2953,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, unlock_page_cgroup(pc); /* - * "charge_statistics" updated event counter. + * "charge_statistics" updated event counter. Then, check it. + * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. + * if they exceeds softlimit. */ memcg_check_events(memcg, page); } @@ -4647,6 +4790,98 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg, return ret; } +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + unsigned long nr_reclaimed = 0; + struct mem_cgroup_per_zone *mz, *next_mz = NULL; + unsigned long reclaimed; + int loop = 0; + struct mem_cgroup_tree_per_zone *mctz; + unsigned long long excess; + unsigned long nr_scanned; + + if (order > 0) + return 0; + + mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone)); + /* + * This loop can run a while, specially if mem_cgroup's continuously + * keep exceeding their soft limit and putting the system under + * pressure + */ + do { + if (next_mz) + mz = next_mz; + else + mz = mem_cgroup_largest_soft_limit_node(mctz); + if (!mz) + break; + + nr_scanned = 0; + reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone, + gfp_mask, &nr_scanned); + nr_reclaimed += reclaimed; + *total_scanned += nr_scanned; + spin_lock(&mctz->lock); + + /* + * If we failed to reclaim anything from this memory cgroup + * it is time to move on to the next cgroup + */ + next_mz = NULL; + if (!reclaimed) { + do { + /* + * Loop until we find yet another one. + * + * By the time we get the soft_limit lock + * again, someone might have aded the + * group back on the RB tree. Iterate to + * make sure we get a different mem. + * mem_cgroup_largest_soft_limit_node returns + * NULL if no other cgroup is present on + * the tree + */ + next_mz = + __mem_cgroup_largest_soft_limit_node(mctz); + if (next_mz == mz) + css_put(&next_mz->memcg->css); + else /* next_mz == NULL or other memcg */ + break; + } while (1); + } + __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + excess = res_counter_soft_limit_excess(&mz->memcg->res); + /* + * One school of thought says that we should not add + * back the node to the tree if reclaim returns 0. + * But our reclaim could return 0, simply because due + * to priority we are exposing a smaller subset of + * memory to reclaim from. Consider this as a longer + * term TODO. + */ + /* If excess == 0, no tree ops */ + __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); + spin_unlock(&mctz->lock); + css_put(&mz->memcg->css); + loop++; + /* + * Could not reclaim anything and there are no more + * mem cgroups to try or we seem to be looping without + * reclaiming anything. + */ + if (!nr_reclaimed && + (next_mz == NULL || + loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS)) + break; + } while (!nr_reclaimed); + if (next_mz) + css_put(&next_mz->memcg->css); + return nr_reclaimed; +} + /** * mem_cgroup_force_empty_list - clears LRU of a group * @memcg: group to clear @@ -5911,6 +6146,8 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; lruvec_init(&mz->lruvec); + mz->usage_in_excess = 0; + mz->on_tree = false; mz->memcg = memcg; } memcg->nodeinfo[node] = pn; @@ -5966,6 +6203,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) int node; size_t size = memcg_size(); + mem_cgroup_remove_from_trees(memcg); free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node(node) @@ -6002,6 +6240,29 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); +static void __init mem_cgroup_soft_limit_tree_init(void) +{ + struct mem_cgroup_tree_per_node *rtpn; + struct mem_cgroup_tree_per_zone *rtpz; + int tmp, node, zone; + + for_each_node(node) { + tmp = node; + if (!node_state(node, N_NORMAL_MEMORY)) + tmp = -1; + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); + BUG_ON(!rtpn); + + soft_limit_tree.rb_tree_per_node[node] = rtpn; + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + rtpz = &rtpn->rb_tree_per_zone[zone]; + rtpz->rb_root = RB_ROOT; + spin_lock_init(&rtpz->lock); + } + } +} + static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -6031,7 +6292,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); vmpressure_init(&memcg->vmpressure); - spin_lock_init(&memcg->soft_lock); return &memcg->css; @@ -6109,13 +6369,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) mem_cgroup_invalidate_reclaim_iterators(memcg); mem_cgroup_reparent_charges(memcg); - if (memcg->soft_contributed) { - while ((memcg = parent_mem_cgroup(memcg))) - atomic_dec(&memcg->children_in_excess); - - if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy) - atomic_dec(&root_mem_cgroup->children_in_excess); - } mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } @@ -6790,6 +7043,7 @@ static int __init mem_cgroup_init(void) { hotcpu_notifier(memcg_cpu_hotplug_callback, 0); enable_swap_cgroup(); + mem_cgroup_soft_limit_tree_init(); memcg_stock_init(); return 0; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 947ed54..bf3351b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1114,8 +1114,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags) * shake_page could have turned it free. */ if (is_free_buddy_page(p)) { - action_result(pfn, "free buddy, 2nd try", - DELAYED); + if (flags & MF_COUNT_INCREASED) + action_result(pfn, "free buddy", DELAYED); + else + action_result(pfn, "free buddy, 2nd try", DELAYED); return 0; } action_result(pfn, "non LRU", IGNORED); @@ -1349,7 +1351,7 @@ int unpoison_memory(unsigned long pfn) * worked by memory_failure() and the page lock is not held yet. * In such case, we yield to memory_failure() and make unpoison fail. */ - if (PageTransHuge(page)) { + if (!PageHuge(page) && PageTransHuge(page)) { pr_info("MCE: Memory failure is now running on %#lx\n", pfn); return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index 9c8d5f5..a26bccd 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -107,7 +107,7 @@ void putback_movable_pages(struct list_head *l) list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (unlikely(balloon_page_movable(page))) + if (unlikely(isolated_balloon_page(page))) balloon_page_putback(page); else putback_lru_page(page); @@ -379,10 +379,14 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, /* * Initialize pte walk starting at the already pinned page where we - * are sure that there is a pte. + * are sure that there is a pte, as it was pinned under the same + * mmap_sem write op. */ pte = get_locked_pte(vma->vm_mm, start, &ptl); - end = min(end, pmd_addr_end(start, end)); + /* Make sure we do not cross the page table boundary */ + end = pgd_addr_end(start, end); + end = pud_addr_end(start, end); + end = pmd_addr_end(start, end); /* The page next to the pinned page is the first we will try to get */ start += PAGE_SIZE; @@ -736,6 +740,7 @@ static int do_mlockall(int flags) /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); + cond_resched(); } out: return 0; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0ee638f..dd886fa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6366,10 +6366,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) list_del(&page->lru); rmv_page_order(page); zone->free_area[order].nr_free--; -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages -= 1 << order; -#endif for (i = 0; i < (1 << order); i++) SetPageReserved((page+i)); pfn += (1 << order); diff --git a/mm/vmscan.c b/mm/vmscan.c index 8ed1b77..53f2f82 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -48,6 +48,7 @@ #include <asm/div64.h> #include <linux/swapops.h> +#include <linux/balloon_compaction.h> #include "internal.h" @@ -139,23 +140,11 @@ static bool global_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup; } - -static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc) -{ - struct mem_cgroup *root = sc->target_mem_cgroup; - return !mem_cgroup_disabled() && - mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE; -} #else static bool global_reclaim(struct scan_control *sc) { return true; } - -static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc) -{ - return false; -} #endif unsigned long zone_reclaimable_pages(struct zone *zone) @@ -1125,7 +1114,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { - if (page_is_file_cache(page) && !PageDirty(page)) { + if (page_is_file_cache(page) && !PageDirty(page) && + !isolated_balloon_page(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } @@ -2176,11 +2166,9 @@ static inline bool should_continue_reclaim(struct zone *zone, } } -static int -__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) +static void shrink_zone(struct zone *zone, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned; - int groups_scanned = 0; do { struct mem_cgroup *root = sc->target_mem_cgroup; @@ -2188,17 +2176,15 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) .zone = zone, .priority = sc->priority, }; - struct mem_cgroup *memcg = NULL; - mem_cgroup_iter_filter filter = (soft_reclaim) ? - mem_cgroup_soft_reclaim_eligible : NULL; + struct mem_cgroup *memcg; nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; - while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) { + memcg = mem_cgroup_iter(root, NULL, &reclaim); + do { struct lruvec *lruvec; - groups_scanned++; lruvec = mem_cgroup_zone_lruvec(zone, memcg); shrink_lruvec(lruvec, sc); @@ -2218,7 +2204,8 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) mem_cgroup_iter_break(root, memcg); break; } - } + memcg = mem_cgroup_iter(root, memcg, &reclaim); + } while (memcg); vmpressure(sc->gfp_mask, sc->target_mem_cgroup, sc->nr_scanned - nr_scanned, @@ -2226,37 +2213,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim) } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); - - return groups_scanned; -} - - -static void shrink_zone(struct zone *zone, struct scan_control *sc) -{ - bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc); - unsigned long nr_scanned = sc->nr_scanned; - int scanned_groups; - - scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim); - /* - * memcg iterator might race with other reclaimer or start from - * a incomplete tree walk so the tree walk in __shrink_zone - * might have missed groups that are above the soft limit. Try - * another loop to catch up with others. Do it just once to - * prevent from reclaim latencies when other reclaimers always - * preempt this one. - */ - if (do_soft_reclaim && !scanned_groups) - __shrink_zone(zone, sc, do_soft_reclaim); - - /* - * No group is over the soft limit or those that are do not have - * pages in the zone we are reclaiming so we have to reclaim everybody - */ - if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) { - __shrink_zone(zone, sc, false); - return; - } } /* Returns true if compaction should go ahead for a high-order request */ @@ -2320,6 +2276,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; + unsigned long nr_soft_reclaimed; + unsigned long nr_soft_scanned; bool aborted_reclaim = false; /* @@ -2359,6 +2317,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; } } + /* + * This steals pages from memory cgroups over softlimit + * and returns the number of reclaimed pages and + * scanned pages. This works for global memory pressure + * and balancing, not for a memcg's limit. + */ + nr_soft_scanned = 0; + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + sc->order, sc->gfp_mask, + &nr_soft_scanned); + sc->nr_reclaimed += nr_soft_reclaimed; + sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } @@ -2952,6 +2922,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, { int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ + unsigned long nr_soft_reclaimed; + unsigned long nr_soft_scanned; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, @@ -3066,6 +3038,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, sc.nr_scanned = 0; + nr_soft_scanned = 0; + /* + * Call soft limit reclaim before calling shrink_zone. + */ + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + order, sc.gfp_mask, + &nr_soft_scanned); + sc.nr_reclaimed += nr_soft_reclaimed; + /* * There should be no need to raise the scanning * priority if enough pages are already being scanned diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index fcac5d1..97912b4 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -420,41 +420,53 @@ static void gss_encode_v0_msg(struct gss_upcall_msg *gss_msg) memcpy(gss_msg->databuf, &uid, sizeof(uid)); gss_msg->msg.data = gss_msg->databuf; gss_msg->msg.len = sizeof(uid); - BUG_ON(sizeof(uid) > UPCALL_BUF_LEN); + + BUILD_BUG_ON(sizeof(uid) > sizeof(gss_msg->databuf)); } -static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, +static int gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, const char *service_name, const char *target_name) { struct gss_api_mech *mech = gss_msg->auth->mech; char *p = gss_msg->databuf; - int len = 0; - - gss_msg->msg.len = sprintf(gss_msg->databuf, "mech=%s uid=%d ", - mech->gm_name, - from_kuid(&init_user_ns, gss_msg->uid)); - p += gss_msg->msg.len; + size_t buflen = sizeof(gss_msg->databuf); + int len; + + len = scnprintf(p, buflen, "mech=%s uid=%d ", mech->gm_name, + from_kuid(&init_user_ns, gss_msg->uid)); + buflen -= len; + p += len; + gss_msg->msg.len = len; if (target_name) { - len = sprintf(p, "target=%s ", target_name); + len = scnprintf(p, buflen, "target=%s ", target_name); + buflen -= len; p += len; gss_msg->msg.len += len; } if (service_name != NULL) { - len = sprintf(p, "service=%s ", service_name); + len = scnprintf(p, buflen, "service=%s ", service_name); + buflen -= len; p += len; gss_msg->msg.len += len; } if (mech->gm_upcall_enctypes) { - len = sprintf(p, "enctypes=%s ", mech->gm_upcall_enctypes); + len = scnprintf(p, buflen, "enctypes=%s ", + mech->gm_upcall_enctypes); + buflen -= len; p += len; gss_msg->msg.len += len; } - len = sprintf(p, "\n"); + len = scnprintf(p, buflen, "\n"); + if (len == 0) + goto out_overflow; gss_msg->msg.len += len; gss_msg->msg.data = gss_msg->databuf; - BUG_ON(gss_msg->msg.len > UPCALL_BUF_LEN); + return 0; +out_overflow: + WARN_ON_ONCE(1); + return -ENOMEM; } static struct gss_upcall_msg * @@ -463,15 +475,15 @@ gss_alloc_msg(struct gss_auth *gss_auth, { struct gss_upcall_msg *gss_msg; int vers; + int err = -ENOMEM; gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS); if (gss_msg == NULL) - return ERR_PTR(-ENOMEM); + goto err; vers = get_pipe_version(gss_auth->net); - if (vers < 0) { - kfree(gss_msg); - return ERR_PTR(vers); - } + err = vers; + if (err < 0) + goto err_free_msg; gss_msg->pipe = gss_auth->gss_pipe[vers]->pipe; INIT_LIST_HEAD(&gss_msg->list); rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq"); @@ -482,10 +494,17 @@ gss_alloc_msg(struct gss_auth *gss_auth, switch (vers) { case 0: gss_encode_v0_msg(gss_msg); + break; default: - gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); + err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); + if (err) + goto err_free_msg; }; return gss_msg; +err_free_msg: + kfree(gss_msg); +err: + return ERR_PTR(err); } static struct gss_upcall_msg * @@ -1075,6 +1094,15 @@ gss_destroy(struct rpc_auth *auth) kref_put(&gss_auth->kref, gss_free_callback); } +/* + * Auths may be shared between rpc clients that were cloned from a + * common client with the same xprt, if they also share the flavor and + * target_name. + * + * The auth is looked up from the oldest parent sharing the same + * cl_xprt, and the auth itself references only that common parent + * (which is guaranteed to last as long as any of its descendants). + */ static struct gss_auth * gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, struct rpc_clnt *clnt, @@ -1088,6 +1116,8 @@ gss_auth_find_or_add_hashed(struct rpc_auth_create_args *args, gss_auth, hash, hashval) { + if (gss_auth->client != clnt) + continue; if (gss_auth->rpc_auth.au_flavor != args->pseudoflavor) continue; if (gss_auth->target_name != args->target_name) { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 7747960..759b78b 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -25,6 +25,7 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/slab.h> +#include <linux/rcupdate.h> #include <linux/utsname.h> #include <linux/workqueue.h> #include <linux/in.h> @@ -264,6 +265,26 @@ void rpc_clients_notifier_unregister(void) return rpc_pipefs_notifier_unregister(&rpc_clients_block); } +static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + const struct rpc_timeout *timeout) +{ + struct rpc_xprt *old; + + spin_lock(&clnt->cl_lock); + old = rcu_dereference_protected(clnt->cl_xprt, + lockdep_is_held(&clnt->cl_lock)); + + if (!xprt_bound(xprt)) + clnt->cl_autobind = 1; + + clnt->cl_timeout = timeout; + rcu_assign_pointer(clnt->cl_xprt, xprt); + spin_unlock(&clnt->cl_lock); + + return old; +} + static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) { clnt->cl_nodelen = strlen(nodename); @@ -272,12 +293,13 @@ static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) memcpy(clnt->cl_nodename, nodename, clnt->cl_nodelen); } -static int rpc_client_register(const struct rpc_create_args *args, - struct rpc_clnt *clnt) +static int rpc_client_register(struct rpc_clnt *clnt, + rpc_authflavor_t pseudoflavor, + const char *client_name) { struct rpc_auth_create_args auth_args = { - .pseudoflavor = args->authflavor, - .target_name = args->client_name, + .pseudoflavor = pseudoflavor, + .target_name = client_name, }; struct rpc_auth *auth; struct net *net = rpc_net_ns(clnt); @@ -298,7 +320,7 @@ static int rpc_client_register(const struct rpc_create_args *args, auth = rpcauth_create(&auth_args, clnt); if (IS_ERR(auth)) { dprintk("RPC: Couldn't create auth handle (flavor %u)\n", - args->authflavor); + pseudoflavor); err = PTR_ERR(auth); goto err_auth; } @@ -337,7 +359,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, { const struct rpc_program *program = args->program; const struct rpc_version *version; - struct rpc_clnt *clnt = NULL; + struct rpc_clnt *clnt = NULL; + const struct rpc_timeout *timeout; int err; /* sanity check the name before trying to print it */ @@ -365,7 +388,6 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (err) goto out_no_clid; - rcu_assign_pointer(clnt->cl_xprt, xprt); clnt->cl_procinfo = version->procs; clnt->cl_maxproc = version->nrprocs; clnt->cl_prog = args->prognumber ? : program->number; @@ -380,16 +402,15 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, INIT_LIST_HEAD(&clnt->cl_tasks); spin_lock_init(&clnt->cl_lock); - if (!xprt_bound(xprt)) - clnt->cl_autobind = 1; - - clnt->cl_timeout = xprt->timeout; + timeout = xprt->timeout; if (args->timeout != NULL) { memcpy(&clnt->cl_timeout_default, args->timeout, sizeof(clnt->cl_timeout_default)); - clnt->cl_timeout = &clnt->cl_timeout_default; + timeout = &clnt->cl_timeout_default; } + rpc_clnt_set_transport(clnt, xprt, timeout); + clnt->cl_rtt = &clnt->cl_rtt_default; rpc_init_rtt(&clnt->cl_rtt_default, clnt->cl_timeout->to_initval); @@ -398,7 +419,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, /* save the nodename */ rpc_clnt_set_nodename(clnt, utsname()->nodename); - err = rpc_client_register(args, clnt); + err = rpc_client_register(clnt, args->authflavor, args->client_name); if (err) goto out_no_path; if (parent) @@ -600,6 +621,80 @@ rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor) } EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth); +/** + * rpc_switch_client_transport: switch the RPC transport on the fly + * @clnt: pointer to a struct rpc_clnt + * @args: pointer to the new transport arguments + * @timeout: pointer to the new timeout parameters + * + * This function allows the caller to switch the RPC transport for the + * rpc_clnt structure 'clnt' to allow it to connect to a mirrored NFS + * server, for instance. It assumes that the caller has ensured that + * there are no active RPC tasks by using some form of locking. + * + * Returns zero if "clnt" is now using the new xprt. Otherwise a + * negative errno is returned, and "clnt" continues to use the old + * xprt. + */ +int rpc_switch_client_transport(struct rpc_clnt *clnt, + struct xprt_create *args, + const struct rpc_timeout *timeout) +{ + const struct rpc_timeout *old_timeo; + rpc_authflavor_t pseudoflavor; + struct rpc_xprt *xprt, *old; + struct rpc_clnt *parent; + int err; + + xprt = xprt_create_transport(args); + if (IS_ERR(xprt)) { + dprintk("RPC: failed to create new xprt for clnt %p\n", + clnt); + return PTR_ERR(xprt); + } + + pseudoflavor = clnt->cl_auth->au_flavor; + + old_timeo = clnt->cl_timeout; + old = rpc_clnt_set_transport(clnt, xprt, timeout); + + rpc_unregister_client(clnt); + __rpc_clnt_remove_pipedir(clnt); + + /* + * A new transport was created. "clnt" therefore + * becomes the root of a new cl_parent tree. clnt's + * children, if it has any, still point to the old xprt. + */ + parent = clnt->cl_parent; + clnt->cl_parent = clnt; + + /* + * The old rpc_auth cache cannot be re-used. GSS + * contexts in particular are between a single + * client and server. + */ + err = rpc_client_register(clnt, pseudoflavor, NULL); + if (err) + goto out_revert; + + synchronize_rcu(); + if (parent != clnt) + rpc_release_client(parent); + xprt_put(old); + dprintk("RPC: replaced xprt for clnt %p\n", clnt); + return 0; + +out_revert: + rpc_clnt_set_transport(clnt, old, old_timeo); + clnt->cl_parent = parent; + rpc_client_register(clnt, pseudoflavor, NULL); + xprt_put(xprt); + dprintk("RPC: failed to switch xprt for clnt %p\n", clnt); + return err; +} +EXPORT_SYMBOL_GPL(rpc_switch_client_transport); + /* * Kill all tasks for the given client. * XXX: kill their descendants as well? @@ -772,6 +867,8 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt) atomic_inc(&clnt->cl_count); if (clnt->cl_softrtry) task->tk_flags |= RPC_TASK_SOFT; + if (clnt->cl_noretranstimeo) + task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT; if (sk_memalloc_socks()) { struct rpc_xprt *xprt; @@ -1690,6 +1787,7 @@ call_connect_status(struct rpc_task *task) dprint_status(task); trace_rpc_connect_status(task, status); + task->tk_status = 0; switch (status) { /* if soft mounted, test if we've timed out */ case -ETIMEDOUT: @@ -1698,12 +1796,14 @@ call_connect_status(struct rpc_task *task) case -ECONNREFUSED: case -ECONNRESET: case -ENETUNREACH: + /* retry with existing socket, after a delay */ + rpc_delay(task, 3*HZ); if (RPC_IS_SOFTCONN(task)) break; - /* retry with existing socket, after a delay */ - case 0: case -EAGAIN: - task->tk_status = 0; + task->tk_action = call_bind; + return; + case 0: clnt->cl_stats->netreconn++; task->tk_action = call_transmit; return; @@ -1717,13 +1817,14 @@ call_connect_status(struct rpc_task *task) static void call_transmit(struct rpc_task *task) { + int is_retrans = RPC_WAS_SENT(task); + dprint_status(task); task->tk_action = call_status; if (task->tk_status < 0) return; - task->tk_status = xprt_prepare_transmit(task); - if (task->tk_status != 0) + if (!xprt_prepare_transmit(task)) return; task->tk_action = call_transmit_status; /* Encode here so that rpcsec_gss can use correct sequence number. */ @@ -1742,6 +1843,8 @@ call_transmit(struct rpc_task *task) xprt_transmit(task); if (task->tk_status < 0) return; + if (is_retrans) + task->tk_client->cl_stats->rpcretrans++; /* * On success, ensure that we call xprt_end_transmit() before sleeping * in order to allow access to the socket to other RPC requests. @@ -1811,8 +1914,7 @@ call_bc_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; - task->tk_status = xprt_prepare_transmit(task); - if (task->tk_status == -EAGAIN) { + if (!xprt_prepare_transmit(task)) { /* * Could not reserve the transport. Try again after the * transport is released. @@ -1900,7 +2002,8 @@ call_status(struct rpc_task *task) rpc_delay(task, 3*HZ); case -ETIMEDOUT: task->tk_action = call_timeout; - if (task->tk_client->cl_discrtry) + if (!(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) + && task->tk_client->cl_discrtry) xprt_conditional_disconnect(req->rq_xprt, req->rq_connect_cookie); break; @@ -1982,7 +2085,6 @@ call_timeout(struct rpc_task *task) rpcauth_invalcred(task); retry: - clnt->cl_stats->rpcretrans++; task->tk_action = call_bind; task->tk_status = 0; } @@ -2025,7 +2127,6 @@ call_decode(struct rpc_task *task) if (req->rq_rcv_buf.len < 12) { if (!RPC_IS_SOFT(task)) { task->tk_action = call_bind; - clnt->cl_stats->rpcretrans++; goto out_retry; } dprintk("RPC: %s: too small RPC reply size (%d bytes)\n", diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 095363e..04199bc 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -205,10 +205,8 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) goto out_sleep; } xprt->snd_task = task; - if (req != NULL) { - req->rq_bytes_sent = 0; + if (req != NULL) req->rq_ntrans++; - } return 1; @@ -263,7 +261,6 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) } if (__xprt_get_cong(xprt, task)) { xprt->snd_task = task; - req->rq_bytes_sent = 0; req->rq_ntrans++; return 1; } @@ -300,10 +297,8 @@ static bool __xprt_lock_write_func(struct rpc_task *task, void *data) req = task->tk_rqstp; xprt->snd_task = task; - if (req) { - req->rq_bytes_sent = 0; + if (req) req->rq_ntrans++; - } return true; } @@ -329,7 +324,6 @@ static bool __xprt_lock_write_cong_func(struct rpc_task *task, void *data) } if (__xprt_get_cong(xprt, task)) { xprt->snd_task = task; - req->rq_bytes_sent = 0; req->rq_ntrans++; return true; } @@ -358,6 +352,11 @@ out_unlock: void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) { if (xprt->snd_task == task) { + if (task != NULL) { + struct rpc_rqst *req = task->tk_rqstp; + if (req != NULL) + req->rq_bytes_sent = 0; + } xprt_clear_locked(xprt); __xprt_lock_write_next(xprt); } @@ -375,6 +374,11 @@ EXPORT_SYMBOL_GPL(xprt_release_xprt); void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) { if (xprt->snd_task == task) { + if (task != NULL) { + struct rpc_rqst *req = task->tk_rqstp; + if (req != NULL) + req->rq_bytes_sent = 0; + } xprt_clear_locked(xprt); __xprt_lock_write_next_cong(xprt); } @@ -854,24 +858,36 @@ static inline int xprt_has_timer(struct rpc_xprt *xprt) * @task: RPC task about to send a request * */ -int xprt_prepare_transmit(struct rpc_task *task) +bool xprt_prepare_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - int err = 0; + bool ret = false; dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid); spin_lock_bh(&xprt->transport_lock); - if (req->rq_reply_bytes_recvd && !req->rq_bytes_sent) { - err = req->rq_reply_bytes_recvd; + if (!req->rq_bytes_sent) { + if (req->rq_reply_bytes_recvd) { + task->tk_status = req->rq_reply_bytes_recvd; + goto out_unlock; + } + if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) + && xprt_connected(xprt) + && req->rq_connect_cookie == xprt->connect_cookie) { + xprt->ops->set_retrans_timeout(task); + rpc_sleep_on(&xprt->pending, task, xprt_timer); + goto out_unlock; + } + } + if (!xprt->ops->reserve_xprt(xprt, task)) { + task->tk_status = -EAGAIN; goto out_unlock; } - if (!xprt->ops->reserve_xprt(xprt, task)) - err = -EAGAIN; + ret = true; out_unlock: spin_unlock_bh(&xprt->transport_lock); - return err; + return ret; } void xprt_end_transmit(struct rpc_task *task) @@ -912,7 +928,6 @@ void xprt_transmit(struct rpc_task *task) } else if (!req->rq_bytes_sent) return; - req->rq_connect_cookie = xprt->connect_cookie; req->rq_xtime = ktime_get(); status = xprt->ops->send_request(task); if (status != 0) { @@ -938,12 +953,14 @@ void xprt_transmit(struct rpc_task *task) /* Don't race with disconnect */ if (!xprt_connected(xprt)) task->tk_status = -ENOTCONN; - else if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) { + else { /* * Sleep on the pending queue since * we're expecting a reply. */ - rpc_sleep_on(&xprt->pending, task, xprt_timer); + if (!req->rq_reply_bytes_recvd && rpc_reply_expected(task)) + rpc_sleep_on(&xprt->pending, task, xprt_timer); + req->rq_connect_cookie = xprt->connect_cookie; } spin_unlock_bh(&xprt->transport_lock); } @@ -1087,11 +1104,9 @@ struct rpc_xprt *xprt_alloc(struct net *net, size_t size, for (i = 0; i < num_prealloc; i++) { req = kzalloc(sizeof(struct rpc_rqst), GFP_KERNEL); if (!req) - break; + goto out_free; list_add(&req->rq_list, &xprt->free); } - if (i < num_prealloc) - goto out_free; if (max_alloc > num_prealloc) xprt->max_reqs = max_alloc; else @@ -1186,6 +1201,12 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) req->rq_xprt = xprt; req->rq_buffer = NULL; req->rq_xid = xprt_alloc_xid(xprt); + req->rq_connect_cookie = xprt->connect_cookie - 1; + req->rq_bytes_sent = 0; + req->rq_snd_buf.len = 0; + req->rq_snd_buf.buflen = 0; + req->rq_rcv_buf.len = 0; + req->rq_rcv_buf.buflen = 0; req->rq_release_snd_buf = NULL; xprt_reset_majortimeo(req); dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ee03d35..9deed17 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1511,6 +1511,7 @@ static void xs_tcp_state_change(struct sock *sk) transport->tcp_copied = 0; transport->tcp_flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; + xprt->connect_cookie++; xprt_wake_pending_tasks(xprt, -EAGAIN); } @@ -2112,6 +2113,19 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) if (!transport->inet) { struct sock *sk = sock->sk; + unsigned int keepidle = xprt->timeout->to_initval / HZ; + unsigned int keepcnt = xprt->timeout->to_retries + 1; + unsigned int opt_on = 1; + + /* TCP Keepalive options */ + kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, + (char *)&opt_on, sizeof(opt_on)); + kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE, + (char *)&keepidle, sizeof(keepidle)); + kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL, + (char *)&keepidle, sizeof(keepidle)); + kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, + (char *)&keepcnt, sizeof(keepcnt)); write_lock_bh(&sk->sk_callback_lock); @@ -2151,7 +2165,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) case 0: case -EINPROGRESS: /* SYN_SENT! */ - xprt->connect_cookie++; if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; } @@ -2859,8 +2872,8 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args) if (args->bc_xprt->xpt_bc_xprt) { /* * This server connection already has a backchannel - * export; we can't create a new one, as we wouldn't be - * able to match replies based on xid any more. So, + * transport; we can't create a new one, as we wouldn't + * be able to match replies based on xid any more. So, * reuse the already-existing one: */ return args->bc_xprt->xpt_bc_xprt; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 47016c3..66cad50 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3975,8 +3975,8 @@ sub string_find_replace { # check for new externs in .h files. if ($realfile =~ /\.h$/ && $line =~ /^\+\s*(extern\s+)$Type\s*$Ident\s*\(/s) { - if (WARN("AVOID_EXTERNS", - "extern prototypes should be avoided in .h files\n" . $herecurr) && + if (CHK("AVOID_EXTERNS", + "extern prototypes should be avoided in .h files\n" . $herecurr) && $fix) { $fixed[$linenr - 1] =~ s/(.*)\bextern\b\s*(.*)/$1$2/; } diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c index d6222ba..532471d 100644 --- a/security/apparmor/crypto.c +++ b/security/apparmor/crypto.c @@ -15,14 +15,14 @@ * it should be. */ -#include <linux/crypto.h> +#include <crypto/hash.h> #include "include/apparmor.h" #include "include/crypto.h" static unsigned int apparmor_hash_size; -static struct crypto_hash *apparmor_tfm; +static struct crypto_shash *apparmor_tfm; unsigned int aa_hash_size(void) { @@ -32,35 +32,33 @@ unsigned int aa_hash_size(void) int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start, size_t len) { - struct scatterlist sg[2]; - struct hash_desc desc = { - .tfm = apparmor_tfm, - .flags = 0 - }; + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(apparmor_tfm)]; + } desc; int error = -ENOMEM; u32 le32_version = cpu_to_le32(version); if (!apparmor_tfm) return 0; - sg_init_table(sg, 2); - sg_set_buf(&sg[0], &le32_version, 4); - sg_set_buf(&sg[1], (u8 *) start, len); - profile->hash = kzalloc(apparmor_hash_size, GFP_KERNEL); if (!profile->hash) goto fail; - error = crypto_hash_init(&desc); + desc.shash.tfm = apparmor_tfm; + desc.shash.flags = 0; + + error = crypto_shash_init(&desc.shash); if (error) goto fail; - error = crypto_hash_update(&desc, &sg[0], 4); + error = crypto_shash_update(&desc.shash, (u8 *) &le32_version, 4); if (error) goto fail; - error = crypto_hash_update(&desc, &sg[1], len); + error = crypto_shash_update(&desc.shash, (u8 *) start, len); if (error) goto fail; - error = crypto_hash_final(&desc, profile->hash); + error = crypto_shash_final(&desc.shash, profile->hash); if (error) goto fail; @@ -75,19 +73,19 @@ fail: static int __init init_profile_hash(void) { - struct crypto_hash *tfm; + struct crypto_shash *tfm; if (!apparmor_initialized) return 0; - tfm = crypto_alloc_hash("sha1", 0, CRYPTO_ALG_ASYNC); + tfm = crypto_alloc_shash("sha1", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) { int error = PTR_ERR(tfm); AA_ERROR("failed to setup profile sha1 hashing: %d\n", error); return error; } apparmor_tfm = tfm; - apparmor_hash_size = crypto_hash_digestsize(apparmor_tfm); + apparmor_hash_size = crypto_shash_digestsize(apparmor_tfm); aa_info_message("AppArmor sha1 policy hashing enabled"); diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index f2d4b63..c28b0f2 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -360,7 +360,9 @@ static inline void aa_put_replacedby(struct aa_replacedby *p) static inline void __aa_update_replacedby(struct aa_profile *orig, struct aa_profile *new) { - struct aa_profile *tmp = rcu_dereference(orig->replacedby->profile); + struct aa_profile *tmp; + tmp = rcu_dereference_protected(orig->replacedby->profile, + mutex_is_locked(&orig->ns->lock)); rcu_assign_pointer(orig->replacedby->profile, aa_get_profile(new)); orig->flags |= PFLAG_INVALID; aa_put_profile(tmp); diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 6172509..345bec0 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -563,7 +563,8 @@ void __init aa_free_root_ns(void) static void free_replacedby(struct aa_replacedby *r) { if (r) { - aa_put_profile(rcu_dereference(r->profile)); + /* r->profile will not be updated any more as r is dead */ + aa_put_profile(rcu_dereference_protected(r->profile, true)); kzfree(r); } } diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 9896954..bea523a 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -139,6 +139,18 @@ static int snd_compr_open(struct inode *inode, struct file *f) static int snd_compr_free(struct inode *inode, struct file *f) { struct snd_compr_file *data = f->private_data; + struct snd_compr_runtime *runtime = data->stream.runtime; + + switch (runtime->state) { + case SNDRV_PCM_STATE_RUNNING: + case SNDRV_PCM_STATE_DRAINING: + case SNDRV_PCM_STATE_PAUSED: + data->stream.ops->trigger(&data->stream, SNDRV_PCM_TRIGGER_STOP); + break; + default: + break; + } + data->stream.ops->free(&data->stream); kfree(data->stream.runtime->buffer); kfree(data->stream.runtime); @@ -837,7 +849,8 @@ static int snd_compress_dev_disconnect(struct snd_device *device) struct snd_compr *compr; compr = device->device_data; - snd_unregister_device(compr->direction, compr->card, compr->device); + snd_unregister_device(SNDRV_DEVICE_TYPE_COMPRESS, compr->card, + compr->device); return 0; } diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index b524f89..18d9725 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -111,6 +111,9 @@ enum { /* 0x0009 - 0x0014 -> 12 test regs */ /* 0x0015 - visibility reg */ +/* Cirrus Logic CS4208 */ +#define CS4208_VENDOR_NID 0x24 + /* * Cirrus Logic CS4210 * @@ -223,6 +226,16 @@ static const struct hda_verb cs_coef_init_verbs[] = { {} /* terminator */ }; +static const struct hda_verb cs4208_coef_init_verbs[] = { + {0x01, AC_VERB_SET_POWER_STATE, 0x00}, /* AFG: D0 */ + {0x24, AC_VERB_SET_PROC_STATE, 0x01}, /* VPW: processing on */ + {0x24, AC_VERB_SET_COEF_INDEX, 0x0033}, + {0x24, AC_VERB_SET_PROC_COEF, 0x0001}, /* A1 ICS */ + {0x24, AC_VERB_SET_COEF_INDEX, 0x0034}, + {0x24, AC_VERB_SET_PROC_COEF, 0x1C01}, /* A1 Enable, A Thresh = 300mV */ + {} /* terminator */ +}; + /* Errata: CS4207 rev C0/C1/C2 Silicon * * http://www.cirrus.com/en/pubs/errata/ER880C3.pdf @@ -295,6 +308,8 @@ static int cs_init(struct hda_codec *codec) /* init_verb sequence for C0/C1/C2 errata*/ snd_hda_sequence_write(codec, cs_errata_init_verbs); snd_hda_sequence_write(codec, cs_coef_init_verbs); + } else if (spec->vendor_nid == CS4208_VENDOR_NID) { + snd_hda_sequence_write(codec, cs4208_coef_init_verbs); } snd_hda_gen_init(codec); @@ -434,6 +449,29 @@ static const struct hda_pintbl mba42_pincfgs[] = { {} /* terminator */ }; +static const struct hda_pintbl mba6_pincfgs[] = { + { 0x10, 0x032120f0 }, /* HP */ + { 0x11, 0x500000f0 }, + { 0x12, 0x90100010 }, /* Speaker */ + { 0x13, 0x500000f0 }, + { 0x14, 0x500000f0 }, + { 0x15, 0x770000f0 }, + { 0x16, 0x770000f0 }, + { 0x17, 0x430000f0 }, + { 0x18, 0x43ab9030 }, /* Mic */ + { 0x19, 0x770000f0 }, + { 0x1a, 0x770000f0 }, + { 0x1b, 0x770000f0 }, + { 0x1c, 0x90a00090 }, + { 0x1d, 0x500000f0 }, + { 0x1e, 0x500000f0 }, + { 0x1f, 0x500000f0 }, + { 0x20, 0x500000f0 }, + { 0x21, 0x430000f0 }, + { 0x22, 0x430000f0 }, + {} /* terminator */ +}; + static void cs420x_fixup_gpio_13(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -556,22 +594,23 @@ static int patch_cs420x(struct hda_codec *codec) /* * CS4208 support: - * Its layout is no longer compatible with CS4206/CS4207, and the generic - * parser seems working fairly well, except for trivial fixups. + * Its layout is no longer compatible with CS4206/CS4207 */ enum { + CS4208_MBA6, CS4208_GPIO0, }; static const struct hda_model_fixup cs4208_models[] = { { .id = CS4208_GPIO0, .name = "gpio0" }, + { .id = CS4208_MBA6, .name = "mba6" }, {} }; static const struct snd_pci_quirk cs4208_fixup_tbl[] = { /* codec SSID */ - SND_PCI_QUIRK(0x106b, 0x7100, "MacBookPro 6,1", CS4208_GPIO0), - SND_PCI_QUIRK(0x106b, 0x7200, "MacBookPro 6,2", CS4208_GPIO0), + SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6), + SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6), {} /* terminator */ }; @@ -588,18 +627,35 @@ static void cs4208_fixup_gpio0(struct hda_codec *codec, } static const struct hda_fixup cs4208_fixups[] = { + [CS4208_MBA6] = { + .type = HDA_FIXUP_PINS, + .v.pins = mba6_pincfgs, + .chained = true, + .chain_id = CS4208_GPIO0, + }, [CS4208_GPIO0] = { .type = HDA_FIXUP_FUNC, .v.func = cs4208_fixup_gpio0, }, }; +/* correct the 0dB offset of input pins */ +static void cs4208_fix_amp_caps(struct hda_codec *codec, hda_nid_t adc) +{ + unsigned int caps; + + caps = query_amp_caps(codec, adc, HDA_INPUT); + caps &= ~(AC_AMPCAP_OFFSET); + caps |= 0x02; + snd_hda_override_amp_caps(codec, adc, HDA_INPUT, caps); +} + static int patch_cs4208(struct hda_codec *codec) { struct cs_spec *spec; int err; - spec = cs_alloc_spec(codec, 0); /* no specific w/a */ + spec = cs_alloc_spec(codec, CS4208_VENDOR_NID); if (!spec) return -ENOMEM; @@ -609,6 +665,12 @@ static int patch_cs4208(struct hda_codec *codec) cs4208_fixups); snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE); + snd_hda_override_wcaps(codec, 0x18, + get_wcaps(codec, 0x18) | AC_WCAP_STEREO); + cs4208_fix_amp_caps(codec, 0x18); + cs4208_fix_amp_caps(codec, 0x1b); + cs4208_fix_amp_caps(codec, 0x1c); + err = cs_parse_auto_config(codec); if (err < 0) goto error; diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 3d8cd044..7ea0245 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1149,32 +1149,43 @@ static int hdmi_choose_cvt(struct hda_codec *codec, } static void haswell_config_cvts(struct hda_codec *codec, - int pin_id, int mux_id) + hda_nid_t pin_nid, int mux_idx) { struct hdmi_spec *spec = codec->spec; - struct hdmi_spec_per_pin *per_pin; - int pin_idx, mux_idx; - int curr; - int err; + hda_nid_t nid, end_nid; + int cvt_idx, curr; + struct hdmi_spec_per_cvt *per_cvt; - for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) { - per_pin = get_pin(spec, pin_idx); + /* configure all pins, including "no physical connection" ones */ + end_nid = codec->start_nid + codec->num_nodes; + for (nid = codec->start_nid; nid < end_nid; nid++) { + unsigned int wid_caps = get_wcaps(codec, nid); + unsigned int wid_type = get_wcaps_type(wid_caps); - if (pin_idx == pin_id) + if (wid_type != AC_WID_PIN) continue; - curr = snd_hda_codec_read(codec, per_pin->pin_nid, 0, + if (nid == pin_nid) + continue; + + curr = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONNECT_SEL, 0); + if (curr != mux_idx) + continue; - /* Choose another unused converter */ - if (curr == mux_id) { - err = hdmi_choose_cvt(codec, pin_idx, NULL, &mux_idx); - if (err < 0) - return; - snd_printdd("HDMI: choose converter %d for pin %d\n", mux_idx, pin_idx); - snd_hda_codec_write_cache(codec, per_pin->pin_nid, 0, + /* choose an unassigned converter. The conveters in the + * connection list are in the same order as in the codec. + */ + for (cvt_idx = 0; cvt_idx < spec->num_cvts; cvt_idx++) { + per_cvt = get_cvt(spec, cvt_idx); + if (!per_cvt->assigned) { + snd_printdd("choose cvt %d for pin nid %d\n", + cvt_idx, nid); + snd_hda_codec_write_cache(codec, nid, 0, AC_VERB_SET_CONNECT_SEL, - mux_idx); + cvt_idx); + break; + } } } } @@ -1216,7 +1227,7 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo, /* configure unused pins to choose other converters */ if (is_haswell(codec)) - haswell_config_cvts(codec, pin_idx, mux_idx); + haswell_config_cvts(codec, per_pin->pin_nid, mux_idx); snd_hda_spdif_ctls_assign(codec, pin_idx, per_cvt->cvt_nid); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bc07d36..0e303b9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3439,6 +3439,9 @@ static void alc283_fixup_chromebook(struct hda_codec *codec, /* Set to manual mode */ val = alc_read_coef_idx(codec, 0x06); alc_write_coef_idx(codec, 0x06, val & ~0x000c); + /* Enable Line1 input control by verb */ + val = alc_read_coef_idx(codec, 0x1a); + alc_write_coef_idx(codec, 0x1a, val | (1 << 4)); break; } } @@ -3531,6 +3534,7 @@ enum { ALC269VB_FIXUP_ORDISSIMO_EVE2, ALC283_FIXUP_CHROME_BOOK, ALC282_FIXUP_ASUS_TX300, + ALC283_FIXUP_INT_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -3790,6 +3794,16 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc282_fixup_asus_tx300, }, + [ALC283_FIXUP_INT_MIC] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + {0x20, AC_VERB_SET_COEF_INDEX, 0x1a}, + {0x20, AC_VERB_SET_PROC_COEF, 0x0011}, + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -3874,7 +3888,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), - SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c index 099e7cd..7c43479 100644 --- a/tools/lib/lk/debugfs.c +++ b/tools/lib/lk/debugfs.c @@ -5,7 +5,6 @@ #include <stdbool.h> #include <sys/vfs.h> #include <sys/mount.h> -#include <linux/magic.h> #include <linux/kernel.h> #include "debugfs.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 9570c2b..b2519e4 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -32,7 +32,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc) int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) { - bool cap_usr_time_zero; + bool cap_user_time_zero; u32 seq; int i = 0; @@ -42,7 +42,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, tc->time_mult = pc->time_mult; tc->time_shift = pc->time_shift; tc->time_zero = pc->time_zero; - cap_usr_time_zero = pc->cap_usr_time_zero; + cap_user_time_zero = pc->cap_user_time_zero; rmb(); if (pc->lock == seq && !(seq & 1)) break; @@ -52,7 +52,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, } } - if (!cap_usr_time_zero) + if (!cap_user_time_zero) return -EOPNOTSUPP; return 0; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 423875c99..afe377b 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -321,8 +321,6 @@ found: return perf_event__repipe(tool, event_sw, &sample_sw, machine); } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index c2dff9c..9b5f077 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -101,7 +101,7 @@ static int setup_cpunode_map(void) dir1 = opendir(PATH_SYS_NODE); if (!dir1) - return -1; + return 0; while ((dent1 = readdir(dir1)) != NULL) { if (dent1->d_type != DT_DIR || diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8e50d8d..72eae74 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -401,8 +401,6 @@ static int perf_report__setup_sample_type(struct perf_report *rep) return 0; } -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; @@ -568,6 +566,9 @@ static int __cmd_report(struct perf_report *rep) } } + if (session_done()) + return 0; + if (nr_samples == 0) { ui__error("The %s file has no samples!\n", session->filename); return 0; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7f31a3d..9c333ff 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -553,8 +553,6 @@ static struct perf_tool perf_script = { .ordering_requires_timestamps = true, }; -extern volatile int session_done; - static void sig_handler(int sig __maybe_unused) { session_done = 1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f5aa637..71aa3e3 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -16,6 +16,23 @@ #include <sys/mman.h> #include <linux/futex.h> +/* For older distros: */ +#ifndef MAP_STACK +# define MAP_STACK 0x20000 +#endif + +#ifndef MADV_HWPOISON +# define MADV_HWPOISON 100 +#endif + +#ifndef MADV_MERGEABLE +# define MADV_MERGEABLE 12 +#endif + +#ifndef MADV_UNMERGEABLE +# define MADV_UNMERGEABLE 13 +#endif + static size_t syscall_arg__scnprintf_hex(char *bf, size_t size, unsigned long arg, u8 arg_idx __maybe_unused, @@ -1038,6 +1055,7 @@ static int trace__replay(struct trace *trace) trace->tool.sample = trace__process_sample; trace->tool.mmap = perf_event__process_mmap; + trace->tool.mmap2 = perf_event__process_mmap2; trace->tool.comm = perf_event__process_comm; trace->tool.exit = perf_event__process_exit; trace->tool.fork = perf_event__process_fork; diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 214e17e..5f6f9b3 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -87,7 +87,7 @@ CFLAGS += -Wall CFLAGS += -Wextra CFLAGS += -std=gnu99 -EXTLIBS = -lelf -lpthread -lrt -lm +EXTLIBS = -lelf -lpthread -lrt -lm -ldl ifeq ($(call try-cc,$(SOURCE_HELLO),$(CFLAGS) -Werror -fstack-protector-all,-fstack-protector-all),y) CFLAGS += -fstack-protector-all @@ -180,6 +180,9 @@ FLAGS_LIBELF=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) CFLAGS += -DLIBELF_MMAP endif +ifeq ($(call try-cc,$(SOURCE_ELF_GETPHDRNUM),$(FLAGS_LIBELF),-DHAVE_ELF_GETPHDRNUM),y) + CFLAGS += -DHAVE_ELF_GETPHDRNUM +endif # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index 708fb8e..d5a8dd4 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -61,6 +61,15 @@ int main(void) } endef +define SOURCE_ELF_GETPHDRNUM +#include <libelf.h> +int main(void) +{ + size_t dst; + return elf_getphdrnum(0, &dst); +} +endef + ifndef NO_SLANG define SOURCE_SLANG #include <slang.h> @@ -210,6 +219,7 @@ define SOURCE_LIBAUDIT int main(void) { + printf(\"error message: %s\n\", audit_errno_to_name(0)); return audit_open(); } endef diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index bfc5a27..7eae548 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -809,7 +809,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, end = map__rip_2objdump(map, sym->end); offset = line_ip - start; - if (offset < 0 || (u64)line_ip > end) + if ((u64)line_ip < start || (u64)line_ip > end) offset = -1; else parsed_line = tmp2 + 1; diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 3e5f543..e23bde1 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -263,6 +263,21 @@ bool die_is_signed_type(Dwarf_Die *tp_die) } /** + * die_is_func_def - Ensure that this DIE is a subprogram and definition + * @dw_die: a DIE + * + * Ensure that this DIE is a subprogram and NOT a declaration. This + * returns true if @dw_die is a function definition. + **/ +bool die_is_func_def(Dwarf_Die *dw_die) +{ + Dwarf_Attribute attr; + + return (dwarf_tag(dw_die) == DW_TAG_subprogram && + dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL); +} + +/** * die_get_data_member_location - Get the data-member offset * @mb_die: a DIE of a member of a data structure * @offs: The offset of the member in the data structure @@ -392,6 +407,10 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data) { struct __addr_die_search_param *ad = data; + /* + * Since a declaration entry doesn't has given pc, this always returns + * function definition entry. + */ if (dwarf_tag(fn_die) == DW_TAG_subprogram && dwarf_haspc(fn_die, ad->addr)) { memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die)); diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 6ce1717..8658d41 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -38,6 +38,9 @@ extern int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr, extern int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr, int (*callback)(Dwarf_Die *, void *), void *data); +/* Ensure that this DIE is a subprogram and definition (not declaration) */ +extern bool die_is_func_def(Dwarf_Die *dw_die); + /* Compare diename and tname */ extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 26441d0..ce69901 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -199,9 +199,11 @@ static int write_buildid(char *name, size_t name_len, u8 *build_id, return write_padded(fd, name, name_len + 1, len); } -static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, - u16 misc, int fd) +static int __dsos__write_buildid_table(struct list_head *head, + struct machine *machine, + pid_t pid, u16 misc, int fd) { + char nm[PATH_MAX]; struct dso *pos; dsos__for_each_with_build_id(pos, head) { @@ -215,6 +217,10 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid, if (is_vdso_map(pos->short_name)) { name = (char *) VDSO__MAP_NAME; name_len = sizeof(VDSO__MAP_NAME) + 1; + } else if (dso__is_kcore(pos)) { + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + name_len = strlen(nm) + 1; } else { name = pos->long_name; name_len = pos->long_name_len + 1; @@ -240,10 +246,10 @@ static int machine__write_buildid_table(struct machine *machine, int fd) umisc = PERF_RECORD_MISC_GUEST_USER; } - err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid, - kmisc, fd); + err = __dsos__write_buildid_table(&machine->kernel_dsos, machine, + machine->pid, kmisc, fd); if (err == 0) - err = __dsos__write_buildid_table(&machine->user_dsos, + err = __dsos__write_buildid_table(&machine->user_dsos, machine, machine->pid, umisc, fd); return err; } @@ -375,23 +381,31 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, const char *debugdir) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + const char *debugdir) { bool is_kallsyms = dso->kernel && dso->long_name[0] != '/'; bool is_vdso = is_vdso_map(dso->short_name); + char *name = dso->long_name; + char nm[PATH_MAX]; - return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), - dso->long_name, debugdir, - is_kallsyms, is_vdso); + if (dso__is_kcore(dso)) { + is_kallsyms = true; + machine__mmap_name(machine, nm, sizeof(nm)); + name = nm; + } + return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name, + debugdir, is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) +static int __dsos__cache_build_ids(struct list_head *head, + struct machine *machine, const char *debugdir) { struct dso *pos; int err = 0; dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, debugdir)) + if (dso__cache_build_id(pos, machine, debugdir)) err = -1; return err; @@ -399,8 +413,9 @@ static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir) static int machine__cache_build_ids(struct machine *machine, const char *debugdir) { - int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir); - ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir); + int ret = __dsos__cache_build_ids(&machine->kernel_dsos, machine, + debugdir); + ret |= __dsos__cache_build_ids(&machine->user_dsos, machine, debugdir); return ret; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 46a0d35..9ff6cf3 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -611,6 +611,8 @@ void hists__collapse_resort(struct hists *hists) next = rb_first(root); while (next) { + if (session_done()) + break; n = rb_entry(next, struct hist_entry, rb_node_in); next = rb_next(&n->rb_node_in); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 933d14f..6188d28 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -792,7 +792,7 @@ static int machine__create_modules(struct machine *machine) modules = path; } - if (symbol__restricted_filename(path, "/proc/modules")) + if (symbol__restricted_filename(modules, "/proc/modules")) return -1; file = fopen(modules, "r"); diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index be03293..371476c 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -118,7 +118,6 @@ static const Dwfl_Callbacks offline_callbacks = { static int debuginfo__init_offline_dwarf(struct debuginfo *self, const char *path) { - Dwfl_Module *mod; int fd; fd = open(path, O_RDONLY); @@ -129,11 +128,11 @@ static int debuginfo__init_offline_dwarf(struct debuginfo *self, if (!self->dwfl) goto error; - mod = dwfl_report_offline(self->dwfl, "", "", fd); - if (!mod) + self->mod = dwfl_report_offline(self->dwfl, "", "", fd); + if (!self->mod) goto error; - self->dbg = dwfl_module_getdwarf(mod, &self->bias); + self->dbg = dwfl_module_getdwarf(self->mod, &self->bias); if (!self->dbg) goto error; @@ -676,37 +675,42 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) } /* Convert subprogram DIE to trace point */ -static int convert_to_trace_point(Dwarf_Die *sp_die, Dwarf_Addr paddr, - bool retprobe, struct probe_trace_point *tp) +static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, + Dwarf_Addr paddr, bool retprobe, + struct probe_trace_point *tp) { Dwarf_Addr eaddr, highaddr; - const char *name; - - /* Copy the name of probe point */ - name = dwarf_diename(sp_die); - if (name) { - if (dwarf_entrypc(sp_die, &eaddr) != 0) { - pr_warning("Failed to get entry address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (dwarf_highpc(sp_die, &highaddr) != 0) { - pr_warning("Failed to get end address of %s\n", - dwarf_diename(sp_die)); - return -ENOENT; - } - if (paddr > highaddr) { - pr_warning("Offset specified is greater than size of %s\n", - dwarf_diename(sp_die)); - return -EINVAL; - } - tp->symbol = strdup(name); - if (tp->symbol == NULL) - return -ENOMEM; - tp->offset = (unsigned long)(paddr - eaddr); - } else - /* This function has no name. */ - tp->offset = (unsigned long)paddr; + GElf_Sym sym; + const char *symbol; + + /* Verify the address is correct */ + if (dwarf_entrypc(sp_die, &eaddr) != 0) { + pr_warning("Failed to get entry address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (dwarf_highpc(sp_die, &highaddr) != 0) { + pr_warning("Failed to get end address of %s\n", + dwarf_diename(sp_die)); + return -ENOENT; + } + if (paddr > highaddr) { + pr_warning("Offset specified is greater than size of %s\n", + dwarf_diename(sp_die)); + return -EINVAL; + } + + /* Get an appropriate symbol from symtab */ + symbol = dwfl_module_addrsym(mod, paddr, &sym, NULL); + if (!symbol) { + pr_warning("Failed to find symbol at 0x%lx\n", + (unsigned long)paddr); + return -ENOENT; + } + tp->offset = (unsigned long)(paddr - sym.st_value); + tp->symbol = strdup(symbol); + if (!tp->symbol) + return -ENOMEM; /* Return probe must be on the head of a subprogram */ if (retprobe) { @@ -734,7 +738,7 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) } /* If not a real subprogram, find a real one */ - if (dwarf_tag(sc_die) != DW_TAG_subprogram) { + if (!die_is_func_def(sc_die)) { if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) { pr_warning("Failed to find probe point in any " "functions.\n"); @@ -980,12 +984,10 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data) struct dwarf_callback_param *param = data; struct probe_finder *pf = param->data; struct perf_probe_point *pp = &pf->pev->point; - Dwarf_Attribute attr; /* Check tag and diename */ - if (dwarf_tag(sp_die) != DW_TAG_subprogram || - !die_compare_name(sp_die, pp->function) || - dwarf_attr(sp_die, DW_AT_declaration, &attr)) + if (!die_is_func_def(sp_die) || + !die_compare_name(sp_die, pp->function)) return DWARF_CB_OK; /* Check declared file */ @@ -1151,7 +1153,7 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf) tev = &tf->tevs[tf->ntevs++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, tf->mod, pf->addr, pf->pev->point.retprobe, &tev->point); if (ret < 0) return ret; @@ -1183,7 +1185,7 @@ int debuginfo__find_trace_events(struct debuginfo *self, { struct trace_event_finder tf = { .pf = {.pev = pev, .callback = add_probe_trace_event}, - .max_tevs = max_tevs}; + .mod = self->mod, .max_tevs = max_tevs}; int ret; /* Allocate result tevs array */ @@ -1252,7 +1254,7 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf) vl = &af->vls[af->nvls++]; /* Trace point should be converted from subprogram DIE */ - ret = convert_to_trace_point(&pf->sp_die, pf->addr, + ret = convert_to_trace_point(&pf->sp_die, af->mod, pf->addr, pf->pev->point.retprobe, &vl->point); if (ret < 0) return ret; @@ -1291,6 +1293,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *self, { struct available_var_finder af = { .pf = {.pev = pev, .callback = add_available_vars}, + .mod = self->mod, .max_vls = max_vls, .externs = externs}; int ret; @@ -1474,7 +1477,7 @@ static int line_range_inline_cb(Dwarf_Die *in_die, void *data) return 0; } -/* Search function from function name */ +/* Search function definition from function name */ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) { struct dwarf_callback_param *param = data; @@ -1485,7 +1488,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data) if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die))) return DWARF_CB_OK; - if (dwarf_tag(sp_die) == DW_TAG_subprogram && + if (die_is_func_def(sp_die) && die_compare_name(sp_die, lr->function)) { lf->fname = dwarf_decl_file(sp_die); dwarf_decl_line(sp_die, &lr->offset); diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 17e94d0..3b7d630 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -23,6 +23,7 @@ static inline int is_c_varname(const char *name) /* debug information structure */ struct debuginfo { Dwarf *dbg; + Dwfl_Module *mod; Dwfl *dwfl; Dwarf_Addr bias; }; @@ -77,6 +78,7 @@ struct probe_finder { struct trace_event_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct probe_trace_event *tevs; /* Found trace events */ int ntevs; /* Number of trace events */ int max_tevs; /* Max number of trace events */ @@ -84,6 +86,7 @@ struct trace_event_finder { struct available_var_finder { struct probe_finder pf; + Dwfl_Module *mod; /* For solving symbols */ struct variable_list *vls; /* Found variable lists */ int nvls; /* Number of variable lists */ int max_vls; /* Max no. of variable lists */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 51f5edf..70ffa41 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -531,6 +531,9 @@ static int flush_sample_queue(struct perf_session *s, return 0; list_for_each_entry_safe(iter, tmp, head, list) { + if (session_done()) + return 0; + if (iter->timestamp > limit) break; @@ -1160,7 +1163,6 @@ static void perf_session__warn_about_errors(const struct perf_session *session, } } -#define session_done() (*(volatile int *)(&session_done)) volatile int session_done; static int __perf_session__process_pipe_events(struct perf_session *self, @@ -1372,10 +1374,13 @@ more: "Processing events..."); } + err = 0; + if (session_done()) + goto out_err; + if (file_pos < file_size) goto more; - err = 0; /* do the final flush for ordered samples */ session->ordered_samples.next_flush = ULLONG_MAX; err = flush_sample_queue(session, tool); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3aa75fb..04bf737 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -124,4 +124,8 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session, #define perf_session__set_tracepoints_handlers(session, array) \ __perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array)) + +extern volatile int session_done; + +#define session_done() (*(volatile int *)(&session_done)) #endif /* __PERF_SESSION_H */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a7b9ab5..a9c829b 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -8,6 +8,22 @@ #include "symbol.h" #include "debug.h" +#ifndef HAVE_ELF_GETPHDRNUM +static int elf_getphdrnum(Elf *elf, size_t *dst) +{ + GElf_Ehdr gehdr; + GElf_Ehdr *ehdr; + + ehdr = gelf_getehdr(elf, &gehdr); + if (!ehdr) + return -1; + + *dst = ehdr->e_phnum; + + return 0; +} +#endif + #ifndef NT_GNU_BUILD_ID #define NT_GNU_BUILD_ID 3 #endif diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index fe7a27d..e9e1c03 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -186,7 +186,7 @@ void parse_proc_kallsyms(struct pevent *pevent, char *next = NULL; char *addr_str; char *mod; - char *fmt; + char *fmt = NULL; line = strtok_r(file, "\n", &next); while (line) { |
