diff options
260 files changed, 2644 insertions, 1817 deletions
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index f4817802406..db3b1aba32a 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -843,6 +843,7 @@ Provides counts of softirq handlers serviced since boot time, for each cpu. TASKLET: 0 0 0 290 SCHED: 27035 26983 26971 26746 HRTIMER: 0 0 0 0 + RCU: 1678 1769 2178 2250 1.3 IDE devices in /proc/ide diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index 88880839ece..64565aac6e4 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -520,59 +520,20 @@ Support for power domains is provided through the pwr_domain field of struct device. This field is a pointer to an object of type struct dev_power_domain, defined in include/linux/pm.h, providing a set of power management callbacks analogous to the subsystem-level and device driver callbacks that are executed -for the given device during all power transitions, in addition to the respective -subsystem-level callbacks. Specifically, the power domain "suspend" callbacks -(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are -executed after the analogous subsystem-level callbacks, while the power domain -"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore, -etc.) are executed before the analogous subsystem-level callbacks. Error codes -returned by the "suspend" and "resume" power domain callbacks are ignored. - -Power domain ->runtime_idle() callback is executed before the subsystem-level -->runtime_idle() callback and the result returned by it is not ignored. Namely, -if it returns error code, the subsystem-level ->runtime_idle() callback will not -be called and the helper function rpm_idle() executing it will return error -code. This mechanism is intended to help platforms where saving device state -is a time consuming operation and should only be carried out if all devices -in the power domain are idle, before turning off the shared power resource(s). -Namely, the power domain ->runtime_idle() callback may return error code until -the pm_runtime_idle() helper (or its asychronous version) has been called for -all devices in the power domain (it is recommended that the returned error code -be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle() -callback from being run prematurely. - -The support for device power domains is only relevant to platforms needing to -use the same subsystem-level (e.g. platform bus type) and device driver power -management callbacks in many different power domain configurations and wanting -to avoid incorporating the support for power domains into the subsystem-level -callbacks. The other platforms need not implement it or take it into account -in any way. - - -System Devices --------------- -System devices (sysdevs) follow a slightly different API, which can be found in - - include/linux/sysdev.h - drivers/base/sys.c - -System devices will be suspended with interrupts disabled, and after all other -devices have been suspended. On resume, they will be resumed before any other -devices, and also with interrupts disabled. These things occur in special -"sysdev_driver" phases, which affect only system devices. - -Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when -the non-boot CPUs are all offline and IRQs are disabled on the remaining online -CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a -sleep state (or a system image is created). During resume (or after the image -has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs -are enabled on the only online CPU, the non-boot CPUs are enabled, and the -resume_noirq (or thaw_noirq or restore_noirq) phase begins. - -Code to actually enter and exit the system-wide low power state sometimes -involves hardware details that are only known to the boot firmware, and -may leave a CPU running software (from SRAM or flash memory) that monitors -the system and manages its wakeup sequence. +for the given device during all power transitions, instead of the respective +subsystem-level callbacks. Specifically, if a device's pm_domain pointer is +not NULL, the ->suspend() callback from the object pointed to by it will be +executed instead of its subsystem's (e.g. bus type's) ->suspend() callback and +anlogously for all of the remaining callbacks. In other words, power management +domain callbacks, if defined for the given device, always take precedence over +the callbacks provided by the device's subsystem (e.g. bus type). + +The support for device power management domains is only relevant to platforms +needing to use the same device driver power management callbacks in many +different power domain configurations and wanting to avoid incorporating the +support for power domains into subsystem-level callbacks, for example by +modifying the platform bus type. Other platforms need not implement it or take +it into account in any way. Device Low Power (suspend) States diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 654097b130b..22accb3eb40 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -566,11 +566,6 @@ to do this is: pm_runtime_set_active(dev); pm_runtime_enable(dev); -The PM core always increments the run-time usage counter before calling the -->prepare() callback and decrements it after calling the ->complete() callback. -Hence disabling run-time PM temporarily like this will not cause any run-time -suspend callbacks to be lost. - 7. Generic subsystem callbacks Subsystems may wish to conserve code space by using the set of generic power diff --git a/MAINTAINERS b/MAINTAINERS index 502f2dd761e..f0358cd91de 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2291,8 +2291,7 @@ F: drivers/scsi/eata_pio.* EBTABLES M: Bart De Schuymer <bart.de.schuymer@pandora.be> -L: ebtables-user@lists.sourceforge.net -L: ebtables-devel@lists.sourceforge.net +L: netfilter-devel@vger.kernel.org W: http://ebtables.sourceforge.net/ S: Maintained F: include/linux/netfilter_bridge/ebt_*.h @@ -7007,6 +7006,13 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86. S: Maintained F: drivers/platform/x86 +X86 MCE INFRASTRUCTURE +M: Tony Luck <tony.luck@intel.com> +M: Borislav Petkov <bp@amd64.org> +L: linux-edac@vger.kernel.org +S: Maintained +F: arch/x86/kernel/cpu/mcheck/* + XEN HYPERVISOR INTERFACE M: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Sneaky Weasel # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h index 8af56ce346a..445dc42e033 100644 --- a/arch/alpha/include/asm/mmzone.h +++ b/arch/alpha/include/asm/mmzone.h @@ -56,7 +56,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n) * Given a kernel address, find the home node of the underlying memory. */ #define kvaddr_to_nid(kaddr) pa_to_nid(__pa(kaddr)) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) /* * Given a kaddr, LOCAL_BASE_ADDR finds the owning node of the memory diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 942fad97e44..940b2017810 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -597,6 +597,8 @@ __common_mmu_cache_on: sub pc, lr, r0, lsr #32 @ properly flush pipeline #endif +#define PROC_ENTRY_SIZE (4*5) + /* * Here follow the relocatable cache support functions for the * various processors. This is a generic hook for locating an @@ -624,7 +626,7 @@ call_cache_fn: adr r12, proc_types ARM( addeq pc, r12, r3 ) @ call cache function THUMB( addeq r12, r3 ) THUMB( moveq pc, r12 ) @ call cache function - add r12, r12, #4*5 + add r12, r12, #PROC_ENTRY_SIZE b 1b /* @@ -794,6 +796,16 @@ proc_types: .size proc_types, . - proc_types + /* + * If you get a "non-constant expression in ".if" statement" + * error from the assembler on this line, check that you have + * not accidentally written a "b" instruction where you should + * have written W(b). + */ + .if (. - proc_types) % PROC_ENTRY_SIZE != 0 + .error "The size of one or more proc_types entries is wrong." + .endif + /* * Turn off the Cache and MMU. ARMv3 does not support * reading the control register, but ARMv4 does. diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index bc2d2d75f70..65c3f2474f5 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -13,6 +13,9 @@ * Do not include any C declarations in this file - it is included by * assembler source. */ +#ifndef __ASM_ASSEMBLER_H__ +#define __ASM_ASSEMBLER_H__ + #ifndef __ASSEMBLY__ #error "Only include this from assembly code" #endif @@ -290,3 +293,4 @@ .macro ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f usracc ldr, \reg, \ptr, \inc, \cond, \rept, \abort .endm +#endif /* __ASM_ASSEMBLER_H__ */ diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S index ec0bbf79c71..2da8547de6d 100644 --- a/arch/arm/include/asm/entry-macro-multi.S +++ b/arch/arm/include/asm/entry-macro-multi.S @@ -1,3 +1,5 @@ +#include <asm/assembler.h> + /* * Interrupt handling. Preserves r7, r8, r9 */ diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index fee7c36349e..016d6a0830a 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -193,8 +193,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, offset -= 0x02000000; offset += sym->st_value - loc; - /* only Thumb addresses allowed (no interworking) */ - if (!(offset & 1) || + /* + * For function symbols, only Thumb addresses are + * allowed (no interworking). + * + * For non-function symbols, the destination + * has no specific ARM/Thumb disposition, so + * the branch is resolved under the assumption + * that interworking is not required. + */ + if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC && + !(offset & 1)) || offset <= (s32)0xff000000 || offset >= (s32)0x01000000) { pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n", diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 344e52b16c8..e7f92a4321f 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -318,9 +318,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void) smp_store_cpu_info(cpu); /* - * OK, now it's safe to let the boot CPU continue + * OK, now it's safe to let the boot CPU continue. Wait for + * the CPU migration code to notice that the CPU is online + * before we continue. */ set_cpu_online(cpu, true); + while (!cpu_active(cpu)) + cpu_relax(); /* * OK, it's off to the idle thread for us diff --git a/arch/arm/mach-h720x/Kconfig b/arch/arm/mach-h720x/Kconfig index 9b6982efbd2..abf356c0234 100644 --- a/arch/arm/mach-h720x/Kconfig +++ b/arch/arm/mach-h720x/Kconfig @@ -6,12 +6,14 @@ config ARCH_H7201 bool "gms30c7201" depends on ARCH_H720X select CPU_H7201 + select ZONE_DMA help Say Y here if you are using the Hynix GMS30C7201 Reference Board config ARCH_H7202 bool "hms30c7202" select CPU_H7202 + select ZONE_DMA depends on ARCH_H720X help Say Y here if you are using the Hynix HMS30C7202 Reference Board diff --git a/arch/arm/mach-msm/timer.c b/arch/arm/mach-msm/timer.c index 38b95e949d1..63621f152c9 100644 --- a/arch/arm/mach-msm/timer.c +++ b/arch/arm/mach-msm/timer.c @@ -23,6 +23,8 @@ #include <linux/io.h> #include <asm/mach/time.h> +#include <asm/hardware/gic.h> + #include <mach/msm_iomap.h> #include <mach/cpu.h> @@ -55,10 +57,12 @@ enum timer_location { #if defined(CONFIG_ARCH_QSD8X50) #define DGT_HZ (19200000 / 4) /* 19.2 MHz / 4 by default */ #define MSM_DGT_SHIFT (0) -#elif defined(CONFIG_ARCH_MSM7X30) || defined(CONFIG_ARCH_MSM8X60) || \ - defined(CONFIG_ARCH_MSM8960) +#elif defined(CONFIG_ARCH_MSM7X30) #define DGT_HZ (24576000 / 4) /* 24.576 MHz (LPXO) / 4 by default */ #define MSM_DGT_SHIFT (0) +#elif defined(CONFIG_ARCH_MSM8X60) || defined(CONFIG_ARCH_MSM8960) +#define DGT_HZ (27000000 / 4) /* 27 MHz (PXO) / 4 by default */ +#define MSM_DGT_SHIFT (0) #else #define DGT_HZ 19200000 /* 19.2 MHz or 600 KHz after shift */ #define MSM_DGT_SHIFT (5) @@ -100,7 +104,11 @@ static cycle_t msm_read_timer_count(struct clocksource *cs) { struct msm_clock *clk = container_of(cs, struct msm_clock, clocksource); - return readl(clk->global_counter); + /* + * Shift timer count down by a constant due to unreliable lower bits + * on some targets. + */ + return readl(clk->global_counter) >> clk->shift; } static struct msm_clock *clockevent_to_clock(struct clock_event_device *evt) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3c3867850a3..089c0b5e454 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -210,19 +210,21 @@ cpu_v7_name: /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size -.equ cpu_v7_suspend_size, 4 * 8 +.equ cpu_v7_suspend_size, 4 * 9 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_v7_do_suspend) stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID mrc p15, 0, r5, c13, c0, 1 @ Context ID + mrc p15, 0, r6, c13, c0, 3 @ User r/o thread ID + stmia r0!, {r4 - r6} mrc p15, 0, r6, c3, c0, 0 @ Domain ID mrc p15, 0, r7, c2, c0, 0 @ TTB 0 mrc p15, 0, r8, c2, c0, 1 @ TTB 1 mrc p15, 0, r9, c1, c0, 0 @ Control register mrc p15, 0, r10, c1, c0, 1 @ Auxiliary control register mrc p15, 0, r11, c1, c0, 2 @ Co-processor access control - stmia r0, {r4 - r11} + stmia r0, {r6 - r11} ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_v7_do_suspend) @@ -230,9 +232,11 @@ ENTRY(cpu_v7_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache - ldmia r0, {r4 - r11} + ldmia r0!, {r4 - r6} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID mcr p15, 0, r5, c13, c0, 1 @ Context ID + mcr p15, 0, r6, c13, c0, 3 @ User r/o thread ID + ldmia r0, {r6 - r11} mcr p15, 0, r6, c3, c0, 0 @ Domain ID mcr p15, 0, r7, c2, c0, 0 @ TTB 0 mcr p15, 0, r8, c2, c0, 1 @ TTB 1 @@ -418,9 +422,9 @@ ENTRY(v7_processor_functions) .word cpu_v7_dcache_clean_area .word cpu_v7_switch_mm .word cpu_v7_set_pte_ext - .word 0 - .word 0 - .word 0 + .word cpu_v7_suspend_size + .word cpu_v7_do_suspend + .word cpu_v7_do_resume .size v7_processor_functions, . - v7_processor_functions .section ".rodata" diff --git a/arch/arm/plat-iop/cp6.c b/arch/arm/plat-iop/cp6.c index 9612a87e2a8..bab73e2c79d 100644 --- a/arch/arm/plat-iop/cp6.c +++ b/arch/arm/plat-iop/cp6.c @@ -18,6 +18,7 @@ */ #include <linux/init.h> #include <asm/traps.h> +#include <asm/ptrace.h> static int cp6_trap(struct pt_regs *regs, unsigned int instr) { diff --git a/arch/m32r/include/asm/mmzone.h b/arch/m32r/include/asm/mmzone.h index 9f3b5accda8..115ced33feb 100644 --- a/arch/m32r/include/asm/mmzone.h +++ b/arch/m32r/include/asm/mmzone.h @@ -14,12 +14,6 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) #define node_localnr(pfn, nid) ((pfn) - NODE_DATA(nid)->node_start_pfn) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages - 1; \ -}) #define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) /* @@ -44,7 +38,7 @@ static __inline__ int pfn_to_nid(unsigned long pfn) int node; for (node = 0 ; node < MAX_NUMNODES ; node++) - if (pfn >= node_start_pfn(node) && pfn <= node_end_pfn(node)) + if (pfn >= node_start_pfn(node) && pfn < node_end_pfn(node)) break; return node; diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h index 3d6e60dad9d..780560b330d 100644 --- a/arch/mn10300/include/asm/uaccess.h +++ b/arch/mn10300/include/asm/uaccess.h @@ -15,6 +15,7 @@ * User space memory access functions */ #include <linux/thread_info.h> +#include <linux/kernel.h> #include <asm/page.h> #include <asm/errno.h> diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h index 9608d2cf214..e67eb9c3d1b 100644 --- a/arch/parisc/include/asm/mmzone.h +++ b/arch/parisc/include/asm/mmzone.h @@ -14,13 +14,6 @@ extern struct node_map_data node_data[]; #define NODE_DATA(nid) (&node_data[nid].pg_data) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - /* We have these possible memory map layouts: * Astro: 0-3.75, 67.75-68, 4-64 * zx1: 0-1, 257-260, 4-256 diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index fd3fd58bad8..7b589178be4 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -38,13 +38,6 @@ u64 memory_hotplug_max(void); #define memory_hotplug_max() memblock_end_of_DRAM() #endif -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) - #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 90d77bd078f..c03fef7a9c2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -579,6 +579,7 @@ config S390_GUEST def_bool y prompt "s390 guest support for KVM (EXPERIMENTAL)" depends on 64BIT && EXPERIMENTAL + select VIRTUALIZATION select VIRTIO select VIRTIO_RING select VIRTIO_CONSOLE diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 52420d2785b..1d55c95f617 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -262,7 +262,7 @@ void smp_ctl_set_bit(int cr, int bit) memset(&parms.orvals, 0, sizeof(parms.orvals)); memset(&parms.andvals, 0xff, sizeof(parms.andvals)); - parms.orvals[cr] = 1 << bit; + parms.orvals[cr] = 1UL << bit; on_each_cpu(smp_ctl_bit_callback, &parms, 1); } EXPORT_SYMBOL(smp_ctl_set_bit); @@ -276,7 +276,7 @@ void smp_ctl_clear_bit(int cr, int bit) memset(&parms.orvals, 0, sizeof(parms.orvals)); memset(&parms.andvals, 0xff, sizeof(parms.andvals)); - parms.andvals[cr] = ~(1L << bit); + parms.andvals[cr] = ~(1UL << bit); on_each_cpu(smp_ctl_bit_callback, &parms, 1); } EXPORT_SYMBOL(smp_ctl_clear_bit); diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 5995e9bc72d..0e358c2cffe 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -25,7 +25,7 @@ extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth); #include "hwsampler.h" -#define DEFAULT_INTERVAL 4096 +#define DEFAULT_INTERVAL 4127518 #define DEFAULT_SDBT_BLOCKS 1 #define DEFAULT_SDB_BLOCKS 511 @@ -151,6 +151,12 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops) if (oprofile_max_interval == 0) return -ENODEV; + /* The initial value should be sane */ + if (oprofile_hw_interval < oprofile_min_interval) + oprofile_hw_interval = oprofile_min_interval; + if (oprofile_hw_interval > oprofile_max_interval) + oprofile_hw_interval = oprofile_max_interval; + if (oprofile_timer_init(ops)) return -ENODEV; diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h index 8887baff5ef..15a8496960e 100644 --- a/arch/sh/include/asm/mmzone.h +++ b/arch/sh/include/asm/mmzone.h @@ -9,10 +9,6 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ - NODE_DATA(nid)->node_spanned_pages) - static inline int pfn_to_nid(unsigned long pfn) { int nid; diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h index e8c648741ed..99d9b9f577b 100644 --- a/arch/sparc/include/asm/mmzone.h +++ b/arch/sparc/include/asm/mmzone.h @@ -8,8 +8,6 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) extern int numa_cpu_lookup_table[]; extern cpumask_t numa_cpumask_lookup_table[]; diff --git a/arch/tile/include/asm/mmzone.h b/arch/tile/include/asm/mmzone.h index c6344c4f32a..9d3dbce8f95 100644 --- a/arch/tile/include/asm/mmzone.h +++ b/arch/tile/include/asm/mmzone.h @@ -40,17 +40,6 @@ static inline int pfn_to_nid(unsigned long pfn) return highbits_to_node[__pfn_to_highbits(pfn)]; } -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - #define kern_addr_valid(kaddr) virt_addr_valid((void *)kaddr) static inline int pfn_valid(int pfn) diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h index 19ae14ba697..0cd3800f33b 100644 --- a/arch/x86/include/asm/memblock.h +++ b/arch/x86/include/asm/memblock.h @@ -4,7 +4,6 @@ #define ARCH_DISCARD_MEMBLOCK u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); -void memblock_x86_to_bootmem(u64 start, u64 end); void memblock_x86_reserve_range(u64 start, u64 end, char *name); void memblock_x86_free_range(u64 start, u64 end); @@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end); u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); u64 memblock_x86_memory_in_range(u64 addr, u64 limit); +bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); #endif diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 5e83a416eca..224e8c5eb30 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn) #endif } -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - static inline int pfn_valid(int pfn) { int nid = pfn_to_nid(pfn); diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index b3f88d7867c..129d9aa3ceb 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -13,8 +13,5 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ - NODE_DATA(nid)->node_spanned_pages) #endif #endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 31d84acc151..a518c0a4504 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) u64 product; #ifdef __i386__ u32 tmp1, tmp2; +#else + ulong tmp; #endif if (shift < 0) @@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); #elif defined(__x86_64__) __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); + "mul %[mul_frac] ; shrd $32, %[hi], %[lo]" + : [lo]"=a"(product), + [hi]"=d"(tmp) + : "0"(delta), + [mul_frac]"rm"((u64)mul_frac)); #else #error implement me! #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index bd14bb4c859..aee38623b76 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) { - return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); + return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); } static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c4dc010c4c..9d03ad4dd5e 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gva_t addr, u32 access) { pt_element_t pte; - pt_element_t __user *ptep_user; + pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4c3fa0f6746..d48ec60ea42 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, unsigned long cr0, struct kvm_vcpu *vcpu) { - vmx_decache_cr3(vcpu); + if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + vmx_decache_cr3(vcpu); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c index aa1169392b8..992da5ec5a6 100644 --- a/arch/x86/mm/memblock.c +++ b/arch/x86/mm/memblock.c @@ -8,7 +8,7 @@ #include <linux/range.h> /* Check for already reserved areas */ -static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align) +bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align) { struct memblock_region *r; u64 addr = *addrp, last; @@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align) if (addr >= ei_last) continue; *sizep = ei_last - addr; - while (check_with_memblock_reserved_size(&addr, sizep, align)) + while (memblock_x86_check_reserved_size(&addr, sizep, align)) ; if (*sizep) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0972315c386..68c3c139520 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point) return false; } -static void coalesce_windows(struct pci_root_info *info, int type) +static void coalesce_windows(struct pci_root_info *info, unsigned long type) { int i, j; struct resource *res1, *res2; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 0d3a4fa3456..474356b98ed 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -310,14 +310,31 @@ void __init efi_reserve_boot_services(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; - unsigned long long start = md->phys_addr; - unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + u64 start = md->phys_addr; + u64 size = md->num_pages << EFI_PAGE_SHIFT; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - - memblock_x86_reserve_range(start, start + size, "EFI Boot"); + /* Only reserve where possible: + * - Not within any already allocated areas + * - Not over any memory area (really needed, if above?) + * - Not within any part of the kernel + * - Not the bios reserved area + */ + if ((start+size >= virt_to_phys(_text) + && start <= virt_to_phys(_end)) || + !e820_all_mapped(start, start+size, E820_RAM) || + memblock_x86_check_reserved_size(&start, &size, + 1<<EFI_PAGE_SHIFT)) { + /* Could not reserve, skip it */ + md->num_pages = 0; + memblock_dbg(PFX "Could not reserve boot range " + "[0x%010llx-0x%010llx]\n", + start, start+size-1); + } else + memblock_x86_reserve_range(start, start+size, + "EFI Boot"); } } @@ -334,6 +351,10 @@ static void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; + /* Could not reserve boot area */ + if (!size) + continue; + free_bootmem_late(start, size); } } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index dd7b88f2ec7..5525163a039 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1033,6 +1033,13 @@ static void xen_machine_halt(void) xen_reboot(SHUTDOWN_poweroff); } +static void xen_machine_power_off(void) +{ + if (pm_power_off) + pm_power_off(); + xen_reboot(SHUTDOWN_poweroff); +} + static void xen_crash_shutdown(struct pt_regs *regs) { xen_reboot(SHUTDOWN_crash); @@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void) static const struct machine_ops xen_machine_ops __initconst = { .restart = xen_restart, .halt = xen_machine_halt, - .power_off = xen_machine_halt, + .power_off = xen_machine_power_off, .shutdown = xen_machine_halt, .crash_shutdown = xen_crash_shutdown, .emergency_restart = xen_emergency_restart, diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index dc708dcc62f..673e968df3c 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -59,6 +59,7 @@ #include <asm/page.h> #include <asm/init.h> #include <asm/pat.h> +#include <asm/smp.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -1231,7 +1232,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; - DECLARE_BITMAP(mask, NR_CPUS); + DECLARE_BITMAP(mask, num_processors); } *args; struct multicall_space mcs; @@ -1599,6 +1600,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; +#ifdef CONFIG_X86_32 + if (pfn > max_pfn_mapped) + max_pfn_mapped = pfn; +#endif + if (!pte_none(pte_page[pteidx])) continue; @@ -1766,7 +1772,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index be1a464f6d6..60aeeb56948 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -227,11 +227,7 @@ char * __init xen_memory_setup(void) memcpy(map_raw, map, sizeof(map)); e820.nr_map = 0; -#ifdef CONFIG_X86_32 xen_extra_mem_start = mem_end; -#else - xen_extra_mem_start = max((1ULL << 32), mem_end); -#endif for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end; @@ -266,6 +262,12 @@ char * __init xen_memory_setup(void) if (map[i].size > 0) e820_add_region(map[i].addr, map[i].size, map[i].type); } + /* Align the balloon area so that max_low_pfn does not get set + * to be at the _end_ of the PCI gap at the far end (fee01000). + * Note that xen_extra_mem_start gets set in the loop above to be + * past the last E820 region. */ + if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) + xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 41038c01de4..b4533a86d7e 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void) static void __init xen_smp_prepare_cpus(unsigned int max_cpus) { unsigned cpu; + unsigned int i; xen_init_lock_cpu(0); smp_store_cpu_info(0); cpu_data(0).x86_max_cores = 1; + + for_each_possible_cpu(i) { + zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); + } set_cpu_sibling_map(0); if (xen_smp_intr_init(0)) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a62be8d0dc1..3689f833afd 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -927,7 +927,7 @@ static int throtl_dispatch(struct request_queue *q) bio_list_init(&bio_list_on_stack); - throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u", + throtl_log(td, "dispatch nr_queued=%d read=%u write=%u", total_nr_queued(td), td->nr_queued[READ], td->nr_queued[WRITE]); @@ -1204,7 +1204,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop) } queue_bio: - throtl_log_tg(td, tg, "[%c] bio. bdisp=%u sz=%u bps=%llu" + throtl_log_tg(td, tg, "[%c] bio. bdisp=%llu sz=%u bps=%llu" " iodisp=%u iops=%u queued=%d/%d", rw == READ ? 'R' : 'W', tg->bytes_disp[rw], bio->bi_size, tg->bps[rw], diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 3c7b537bf90..f3799432676 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -988,9 +988,10 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, st->min_vdisktime); - cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u" - " sect=%u", used_sl, cfqq->slice_dispatch, charge, - iops_mode(cfqd), cfqq->nr_sectors); + cfq_log_cfqq(cfqq->cfqd, cfqq, + "sl_used=%u disp=%u charge=%u iops=%u sect=%lu", + used_sl, cfqq->slice_dispatch, charge, + iops_mode(cfqd), cfqq->nr_sectors); cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl, unaccounted_sl); cfq_blkiocg_set_start_empty_time(&cfqg->blkg); @@ -2023,8 +2024,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) */ if (sample_valid(cic->ttime_samples) && (cfqq->slice_end - jiffies < cic->ttime_mean)) { - cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d", - cic->ttime_mean); + cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu", + cic->ttime_mean); return; } @@ -2772,8 +2773,11 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, smp_wmb(); cic->key = cfqd_dead_key(cfqd); - if (ioc->ioc_data == cic) + if (rcu_dereference(ioc->ioc_data) == cic) { + spin_lock(&ioc->lock); rcu_assign_pointer(ioc->ioc_data, NULL); + spin_unlock(&ioc->lock); + } if (cic->cfqq[BLK_RW_ASYNC]) { cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]); diff --git a/block/genhd.c b/block/genhd.c index 95822ae25cf..3608289c8ec 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1371,6 +1371,7 @@ struct disk_events { struct gendisk *disk; /* the associated disk */ spinlock_t lock; + struct mutex block_mutex; /* protects blocking */ int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ @@ -1414,22 +1415,44 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk) return msecs_to_jiffies(intv_msecs); } -static void __disk_block_events(struct gendisk *disk, bool sync) +/** + * disk_block_events - block and flush disk event checking + * @disk: disk to block events for + * + * On return from this function, it is guaranteed that event checking + * isn't in progress and won't happen until unblocked by + * disk_unblock_events(). Events blocking is counted and the actual + * unblocking happens after the matching number of unblocks are done. + * + * Note that this intentionally does not block event checking from + * disk_clear_events(). + * + * CONTEXT: + * Might sleep. + */ +void disk_block_events(struct gendisk *disk) { struct disk_events *ev = disk->ev; unsigned long flags; bool cancel; + if (!ev) + return; + + /* + * Outer mutex ensures that the first blocker completes canceling + * the event work before further blockers are allowed to finish. + */ + mutex_lock(&ev->block_mutex); + spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); - if (cancel) { - if (sync) - cancel_delayed_work_sync(&disk->ev->dwork); - else - cancel_delayed_work(&disk->ev->dwork); - } + if (cancel) + cancel_delayed_work_sync(&disk->ev->dwork); + + mutex_unlock(&ev->block_mutex); } static void __disk_unblock_events(struct gendisk *disk, bool check_now) @@ -1461,27 +1484,6 @@ out_unlock: } /** - * disk_block_events - block and flush disk event checking - * @disk: disk to block events for - * - * On return from this function, it is guaranteed that event checking - * isn't in progress and won't happen until unblocked by - * disk_unblock_events(). Events blocking is counted and the actual - * unblocking happens after the matching number of unblocks are done. - * - * Note that this intentionally does not block event checking from - * disk_clear_events(). - * - * CONTEXT: - * Might sleep. - */ -void disk_block_events(struct gendisk *disk) -{ - if (disk->ev) - __disk_block_events(disk, true); -} - -/** * disk_unblock_events - unblock disk event checking * @disk: disk to unblock events for * @@ -1508,10 +1510,18 @@ void disk_unblock_events(struct gendisk *disk) */ void disk_check_events(struct gendisk *disk) { - if (disk->ev) { - __disk_block_events(disk, false); - __disk_unblock_events(disk, true); + struct disk_events *ev = disk->ev; + unsigned long flags; + + if (!ev) + return; + + spin_lock_irqsave(&ev->lock, flags); + if (!ev->block) { + cancel_delayed_work(&ev->dwork); + queue_delayed_work(system_nrt_wq, &ev->dwork, 0); } + spin_unlock_irqrestore(&ev->lock, flags); } EXPORT_SYMBOL_GPL(disk_check_events); @@ -1546,7 +1556,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) spin_unlock_irq(&ev->lock); /* uncondtionally schedule event check and wait for it to finish */ - __disk_block_events(disk, true); + disk_block_events(disk); queue_delayed_work(system_nrt_wq, &ev->dwork, 0); flush_delayed_work(&ev->dwork); __disk_unblock_events(disk, false); @@ -1664,7 +1674,7 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev, if (intv < 0 && intv != -1) return -EINVAL; - __disk_block_events(disk, true); + disk_block_events(disk); disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); @@ -1750,6 +1760,7 @@ static void disk_add_events(struct gendisk *disk) INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); + mutex_init(&ev->block_mutex); ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); @@ -1770,7 +1781,7 @@ static void disk_del_events(struct gendisk *disk) if (!disk->ev) return; - __disk_block_events(disk, true); + disk_block_events(disk); mutex_lock(&disk_events_mutex); list_del_init(&disk->ev->node); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 736bee5dafe..000d03ae665 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4143,9 +4143,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { * Devices which choke on SETXFER. Applies only if both the * device and controller are SATA. */ - { "PIONEER DVD-RW DVRTD08", "1.00", ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-212D", "1.28", ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-216D", "1.08", ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVRTD08", NULL, ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* End Marker */ { } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d51f9795c06..927f968e99d 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3797,6 +3797,12 @@ EXPORT_SYMBOL_GPL(ata_sas_port_alloc); */ int ata_sas_port_start(struct ata_port *ap) { + /* + * the port is marked as frozen at allocation time, but if we don't + * have new eh, we won't thaw it + */ + if (!ap->ops->error_handler) + ap->pflags &= ~ATA_PFLAG_FROZEN; return 0; } EXPORT_SYMBOL_GPL(ata_sas_port_start); diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c index 75a6a0c0094..5d7f58a7e34 100644 --- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -161,6 +161,9 @@ static const struct pci_device_id marvell_pci_tbl[] = { { PCI_DEVICE(0x11AB, 0x6121), }, { PCI_DEVICE(0x11AB, 0x6123), }, { PCI_DEVICE(0x11AB, 0x6145), }, + { PCI_DEVICE(0x1B4B, 0x91A0), }, + { PCI_DEVICE(0x1B4B, 0x91A4), }, + { } /* terminate list */ }; diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 1c4b3aa4c7c..dc88a39e7db 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -389,7 +389,7 @@ static void sata_dwc_tf_dump(struct ata_taskfile *tf) /* * Function: get_burst_length_encode * arguments: datalength: length in bytes of data - * returns value to be programmed in register corrresponding to data length + * returns value to be programmed in register corresponding to data length * This value is effectively the log(base 2) of the length */ static int get_burst_length_encode(int datalength) diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index eaa8a854af0..ad367c4139b 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -387,7 +387,7 @@ static int pm_runtime_clk_notify(struct notifier_block *nb, clknb = container_of(nb, struct pm_clk_notifier_block, nb); switch (action) { - case BUS_NOTIFY_ADD_DEVICE: + case BUS_NOTIFY_BIND_DRIVER: if (clknb->con_ids[0]) { for (con_id = clknb->con_ids; *con_id; con_id++) enable_clock(dev, *con_id); @@ -395,7 +395,7 @@ static int pm_runtime_clk_notify(struct notifier_block *nb, enable_clock(dev, NULL); } break; - case BUS_NOTIFY_DEL_DEVICE: + case BUS_NOTIFY_UNBOUND_DRIVER: if (clknb->con_ids[0]) { for (con_id = clknb->con_ids; *con_id; con_id++) disable_clock(dev, *con_id); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index aa632020774..06f09bf89cb 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -57,7 +57,8 @@ static int async_error; */ void device_pm_init(struct device *dev) { - dev->power.in_suspend = false; + dev->power.is_prepared = false; + dev->power.is_suspended = false; init_completion(&dev->power.completion); complete_all(&dev->power.completion); dev->power.wakeup = NULL; @@ -91,7 +92,7 @@ void device_pm_add(struct device *dev) pr_debug("PM: Adding info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); mutex_lock(&dpm_list_mtx); - if (dev->parent && dev->parent->power.in_suspend) + if (dev->parent && dev->parent->power.is_prepared) dev_warn(dev, "parent %s should not be sleeping\n", dev_name(dev->parent)); list_add_tail(&dev->power.entry, &dpm_list); @@ -511,7 +512,14 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) dpm_wait(dev->parent, async); device_lock(dev); - dev->power.in_suspend = false; + /* + * This is a fib. But we'll allow new children to be added below + * a resumed device, even if the device hasn't been completed yet. + */ + dev->power.is_prepared = false; + + if (!dev->power.is_suspended) + goto Unlock; if (dev->pwr_domain) { pm_dev_dbg(dev, state, "power domain "); @@ -548,6 +556,9 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) } End: + dev->power.is_suspended = false; + + Unlock: device_unlock(dev); complete_all(&dev->power.completion); @@ -670,7 +681,7 @@ void dpm_complete(pm_message_t state) struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); - dev->power.in_suspend = false; + dev->power.is_prepared = false; list_move(&dev->power.entry, &list); mutex_unlock(&dpm_list_mtx); @@ -835,11 +846,11 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) device_lock(dev); if (async_error) - goto End; + goto Unlock; if (pm_wakeup_pending()) { async_error = -EBUSY; - goto End; + goto Unlock; } if (dev->pwr_domain) { @@ -877,6 +888,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) } End: + dev->power.is_suspended = !error; + + Unlock: device_unlock(dev); complete_all(&dev->power.completion); @@ -1042,7 +1056,7 @@ int dpm_prepare(pm_message_t state) put_device(dev); break; } - dev->power.in_suspend = true; + dev->power.is_prepared = true; if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); put_device(dev); diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index fd6305bf953..8ecf4c6c287 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -64,6 +64,8 @@ static ssize_t btmrvl_hscfgcmd_write(struct file *file, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.hscfgcmd = result; @@ -108,6 +110,8 @@ static ssize_t btmrvl_psmode_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.psmode = result; @@ -147,6 +151,8 @@ static ssize_t btmrvl_pscmd_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.pscmd = result; @@ -191,6 +197,8 @@ static ssize_t btmrvl_gpiogap_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 16, &result); + if (ret) + return ret; priv->btmrvl_dev.gpio_gap = result; @@ -230,6 +238,8 @@ static ssize_t btmrvl_hscmd_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.hscmd = result; if (priv->btmrvl_dev.hscmd) { @@ -272,6 +282,8 @@ static ssize_t btmrvl_hsmode_write(struct file *file, const char __user *ubuf, return -EFAULT; ret = strict_strtol(buf, 10, &result); + if (ret) + return ret; priv->btmrvl_dev.hsmode = result; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 94c84d74410..c6389de5316 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1219,11 +1219,11 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ret = i915_gem_object_bind_to_gtt(obj, 0, true); if (ret) goto unlock; - } - ret = i915_gem_object_set_to_gtt_domain(obj, write); - if (ret) - goto unlock; + ret = i915_gem_object_set_to_gtt_domain(obj, write); + if (ret) + goto unlock; + } if (obj->tiling_mode == I915_TILING_NONE) ret = i915_gem_object_put_fence(obj); @@ -2926,8 +2926,6 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj) */ wmb(); - i915_gem_release_mmap(obj); - old_write_domain = obj->base.write_domain; obj->base.write_domain = 0; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 20a4cc5b818..4934cf84c32 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -187,10 +187,6 @@ i915_gem_object_set_to_gpu_domain(struct drm_i915_gem_object *obj, if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_CPU) i915_gem_clflush_object(obj); - /* blow away mappings if mapped through GTT */ - if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_GTT) - i915_gem_release_mmap(obj); - if (obj->base.pending_write_domain) cd->flips |= atomic_read(&obj->pending_flip); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9e34a1abeb6..ae2b49969b9 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1749,6 +1749,7 @@ void ironlake_irq_preinstall(struct drm_device *dev) * happens. */ I915_WRITE(GEN6_BLITTER_HWSTAM, ~GEN6_BLITTER_USER_INTERRUPT); + I915_WRITE(GEN6_BSD_HWSTAM, ~GEN6_BSD_USER_INTERRUPT); } /* XXX hotplug from PCH */ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2f967af8e62..5d5def756c9 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -531,6 +531,7 @@ #define GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_ENABLE 0 #define GEN6_BSD_SLEEP_PSMI_CONTROL_IDLE_INDICATOR (1 << 3) +#define GEN6_BSD_HWSTAM 0x12098 #define GEN6_BSD_IMR 0x120a8 #define GEN6_BSD_USER_INTERRUPT (1 << 12) diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 60a94d2b526..e8152d23d5b 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -678,6 +678,7 @@ void i915_save_display(struct drm_device *dev) } /* VGA state */ + mutex_lock(&dev->struct_mutex); dev_priv->saveVGA0 = I915_READ(VGA0); dev_priv->saveVGA1 = I915_READ(VGA1); dev_priv->saveVGA_PD = I915_READ(VGA_PD); @@ -687,6 +688,7 @@ void i915_save_display(struct drm_device *dev) dev_priv->saveVGACNTRL = I915_READ(VGACNTRL); i915_save_vga(dev); + mutex_unlock(&dev->struct_mutex); } void i915_restore_display(struct drm_device *dev) @@ -780,6 +782,8 @@ void i915_restore_display(struct drm_device *dev) I915_WRITE(CPU_VGACNTRL, dev_priv->saveVGACNTRL); else I915_WRITE(VGACNTRL, dev_priv->saveVGACNTRL); + + mutex_lock(&dev->struct_mutex); I915_WRITE(VGA0, dev_priv->saveVGA0); I915_WRITE(VGA1, dev_priv->saveVGA1); I915_WRITE(VGA_PD, dev_priv->saveVGA_PD); @@ -787,6 +791,7 @@ void i915_restore_display(struct drm_device *dev) udelay(150); i915_restore_vga(dev); + mutex_unlock(&dev->struct_mutex); } int i915_save_state(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 81a9059b6a9..aa43e7be605 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4687,6 +4687,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(DSPCNTR(plane), dspcntr); POSTING_READ(DSPCNTR(plane)); + intel_enable_plane(dev_priv, plane, pipe); ret = intel_pipe_set_base(crtc, x, y, old_fb); @@ -5217,8 +5218,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(DSPCNTR(plane), dspcntr); POSTING_READ(DSPCNTR(plane)); - if (!HAS_PCH_SPLIT(dev)) - intel_enable_plane(dev_priv, plane, pipe); ret = intel_pipe_set_base(crtc, x, y, old_fb); diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index f0d459bb46e..525744d593c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -262,7 +262,6 @@ static bool nouveau_dsm_detect(void) vga_count++; retval = nouveau_dsm_pci_probe(pdev); - printk("ret val is %d\n", retval); if (retval & NOUVEAU_DSM_HAS_MUX) has_dsm |= 1; if (retval & NOUVEAU_DSM_HAS_OPT) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 4b9f4493c9f..7347075ca5b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -339,11 +339,12 @@ semaphore_acquire(struct nouveau_channel *chan, struct nouveau_semaphore *sema) int ret; if (dev_priv->chipset < 0x84) { - ret = RING_SPACE(chan, 3); + ret = RING_SPACE(chan, 4); if (ret) return ret; - BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 2); + BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 3); + OUT_RING (chan, NvSema); OUT_RING (chan, sema->mem->start); OUT_RING (chan, 1); } else @@ -351,10 +352,12 @@ semaphore_acquire(struct nouveau_channel *chan, struct nouveau_semaphore *sema) struct nouveau_vma *vma = &dev_priv->fence.bo->vma; u64 offset = vma->offset + sema->mem->start; - ret = RING_SPACE(chan, 5); + ret = RING_SPACE(chan, 7); if (ret) return ret; + BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); + OUT_RING (chan, chan->vram_handle); BEGIN_RING(chan, NvSubSw, 0x0010, 4); OUT_RING (chan, upper_32_bits(offset)); OUT_RING (chan, lower_32_bits(offset)); @@ -394,11 +397,12 @@ semaphore_release(struct nouveau_channel *chan, struct nouveau_semaphore *sema) int ret; if (dev_priv->chipset < 0x84) { - ret = RING_SPACE(chan, 4); + ret = RING_SPACE(chan, 5); if (ret) return ret; - BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_OFFSET, 1); + BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 2); + OUT_RING (chan, NvSema); OUT_RING (chan, sema->mem->start); BEGIN_RING(chan, NvSubSw, NV_SW_SEMAPHORE_RELEASE, 1); OUT_RING (chan, 1); @@ -407,10 +411,12 @@ semaphore_release(struct nouveau_channel *chan, struct nouveau_semaphore *sema) struct nouveau_vma *vma = &dev_priv->fence.bo->vma; u64 offset = vma->offset + sema->mem->start; - ret = RING_SPACE(chan, 5); + ret = RING_SPACE(chan, 7); if (ret) return ret; + BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); + OUT_RING (chan, chan->vram_handle); BEGIN_RING(chan, NvSubSw, 0x0010, 4); OUT_RING (chan, upper_32_bits(offset)); OUT_RING (chan, lower_32_bits(offset)); @@ -504,22 +510,22 @@ nouveau_fence_channel_init(struct nouveau_channel *chan) struct nouveau_gpuobj *obj = NULL; int ret; - if (dev_priv->card_type >= NV_C0) - goto out_initialised; + if (dev_priv->card_type < NV_C0) { + /* Create an NV_SW object for various sync purposes */ + ret = nouveau_gpuobj_gr_new(chan, NvSw, NV_SW); + if (ret) + return ret; - /* Create an NV_SW object for various sync purposes */ - ret = nouveau_gpuobj_gr_new(chan, NvSw, NV_SW); - if (ret) - return ret; + ret = RING_SPACE(chan, 2); + if (ret) + return ret; - /* we leave subchannel empty for nvc0 */ - ret = RING_SPACE(chan, 2); - if (ret) - return ret; - BEGIN_RING(chan, NvSubSw, 0, 1); - OUT_RING(chan, NvSw); + BEGIN_RING(chan, NvSubSw, 0, 1); + OUT_RING (chan, NvSw); + FIRE_RING (chan); + } - /* Create a DMA object for the shared cross-channel sync area. */ + /* Setup area of memory shared between all channels for x-chan sync */ if (USE_SEMA(dev) && dev_priv->chipset < 0x84) { struct ttm_mem_reg *mem = &dev_priv->fence.bo->bo.mem; @@ -534,23 +540,8 @@ nouveau_fence_channel_init(struct nouveau_channel *chan) nouveau_gpuobj_ref(NULL, &obj); if (ret) return ret; - - ret = RING_SPACE(chan, 2); - if (ret) - return ret; - BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); - OUT_RING(chan, NvSema); - } else { - ret = RING_SPACE(chan, 2); - if (ret) - return ret; - BEGIN_RING(chan, NvSubSw, NV_SW_DMA_SEMAPHORE, 1); - OUT_RING (chan, chan->vram_handle); /* whole VM */ } - FIRE_RING(chan); - -out_initialised: INIT_LIST_HEAD(&chan->fence.pending); spin_lock_init(&chan->fence.lock); atomic_set(&chan->fence.last_sequence_irq, 0); diff --git a/drivers/gpu/drm/nouveau/nouveau_perf.c b/drivers/gpu/drm/nouveau/nouveau_perf.c index 922fb6b664e..ef9dec0e6f8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_perf.c +++ b/drivers/gpu/drm/nouveau/nouveau_perf.c @@ -182,6 +182,11 @@ nouveau_perf_init(struct drm_device *dev) entries = perf[2]; } + if (entries > NOUVEAU_PM_MAX_LEVEL) { + NV_DEBUG(dev, "perf table has too many entries - buggy vbios?\n"); + entries = NOUVEAU_PM_MAX_LEVEL; + } + entry = perf + headerlen; for (i = 0; i < entries; i++) { struct nouveau_pm_level *perflvl = &pm->perflvl[pm->nr_perflvl]; diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c index 80218887e0a..144f79a350a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_state.c +++ b/drivers/gpu/drm/nouveau/nouveau_state.c @@ -881,8 +881,8 @@ int nouveau_load(struct drm_device *dev, unsigned long flags) #ifdef __BIG_ENDIAN /* Put the card in BE mode if it's not */ - if (nv_rd32(dev, NV03_PMC_BOOT_1)) - nv_wr32(dev, NV03_PMC_BOOT_1, 0x00000001); + if (nv_rd32(dev, NV03_PMC_BOOT_1) != 0x01000001) + nv_wr32(dev, NV03_PMC_BOOT_1, 0x01000001); DRM_MEMORYBARRIER(); #endif diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 74a3f687270..08da478ba54 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -409,7 +409,7 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct nouveau_channel *evo = dispc->sync; int ret; - ret = RING_SPACE(evo, 24); + ret = RING_SPACE(evo, chan ? 25 : 27); if (unlikely(ret)) return ret; @@ -458,8 +458,19 @@ nv50_display_flip_next(struct drm_crtc *crtc, struct drm_framebuffer *fb, /* queue the flip on the crtc's "display sync" channel */ BEGIN_RING(evo, 0, 0x0100, 1); OUT_RING (evo, 0xfffe0000); - BEGIN_RING(evo, 0, 0x0084, 5); - OUT_RING (evo, chan ? 0x00000100 : 0x00000010); + if (chan) { + BEGIN_RING(evo, 0, 0x0084, 1); + OUT_RING (evo, 0x00000100); + } else { + BEGIN_RING(evo, 0, 0x0084, 1); + OUT_RING (evo, 0x00000010); + /* allows gamma somehow, PDISP will bitch at you if + * you don't wait for vblank before changing this.. + */ + BEGIN_RING(evo, 0, 0x00e0, 1); + OUT_RING (evo, 0x40000000); + } + BEGIN_RING(evo, 0, 0x0088, 4); OUT_RING (evo, dispc->sem.offset); OUT_RING (evo, 0xf00d0000 | dispc->sem.value); OUT_RING (evo, 0x74b1e000); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 7e3d96e7ac0..12d2fdc5241 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -140,11 +140,17 @@ void evergreen_pm_misc(struct radeon_device *rdev) struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage; if (voltage->type == VOLTAGE_SW) { + /* 0xff01 is a flag rather then an actual voltage */ + if (voltage->voltage == 0xff01) + return; if (voltage->voltage && (voltage->voltage != rdev->pm.current_vddc)) { radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC); rdev->pm.current_vddc = voltage->voltage; DRM_DEBUG("Setting: vddc: %d\n", voltage->voltage); } + /* 0xff01 is a flag rather then an actual voltage */ + if (voltage->vddci == 0xff01) + return; if (voltage->vddci && (voltage->vddci != rdev->pm.current_vddci)) { radeon_atom_set_voltage(rdev, voltage->vddci, SET_VOLTAGE_TYPE_ASIC_VDDCI); rdev->pm.current_vddci = voltage->vddci; @@ -2007,9 +2013,9 @@ static void evergreen_gpu_init(struct radeon_device *rdev) rdev->config.evergreen.tile_config |= (3 << 0); break; } - /* num banks is 8 on all fusion asics */ + /* num banks is 8 on all fusion asics. 0 = 4, 1 = 8, 2 = 16 */ if (rdev->flags & RADEON_IS_IGP) - rdev->config.evergreen.tile_config |= 8 << 4; + rdev->config.evergreen.tile_config |= 1 << 4; else rdev->config.evergreen.tile_config |= ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4; @@ -2695,28 +2701,25 @@ static inline u32 evergreen_get_ih_wptr(struct radeon_device *rdev) int evergreen_irq_process(struct radeon_device *rdev) { - u32 wptr = evergreen_get_ih_wptr(rdev); - u32 rptr = rdev->ih.rptr; + u32 wptr; + u32 rptr; u32 src_id, src_data; u32 ring_index; unsigned long flags; bool queue_hotplug = false; - DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr); - if (!rdev->ih.enabled) + if (!rdev->ih.enabled || rdev->shutdown) return IRQ_NONE; - spin_lock_irqsave(&rdev->ih.lock, flags); + wptr = evergreen_get_ih_wptr(rdev); + rptr = rdev->ih.rptr; + DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr); + spin_lock_irqsave(&rdev->ih.lock, flags); if (rptr == wptr) { spin_unlock_irqrestore(&rdev->ih.lock, flags); return IRQ_NONE; } - if (rdev->shutdown) { - spin_unlock_irqrestore(&rdev->ih.lock, flags); - return IRQ_NONE; - } - restart_ih: /* display interrupts */ evergreen_irq_ack(rdev); diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 7dd45ca64e2..f79d2ccb675 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -590,6 +590,9 @@ void r600_pm_misc(struct radeon_device *rdev) struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage; if ((voltage->type == VOLTAGE_SW) && voltage->voltage) { + /* 0xff01 is a flag rather then an actual voltage */ + if (voltage->voltage == 0xff01) + return; if (voltage->voltage != rdev->pm.current_vddc) { radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC); rdev->pm.current_vddc = voltage->voltage; @@ -3294,27 +3297,26 @@ static inline u32 r600_get_ih_wptr(struct radeon_device *rdev) int r600_irq_process(struct radeon_device *rdev) { - u32 wptr = r600_get_ih_wptr(rdev); - u32 rptr = rdev->ih.rptr; + u32 wptr; + u32 rptr; u32 src_id, src_data; u32 ring_index; unsigned long flags; bool queue_hotplug = false; - DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr); - if (!rdev->ih.enabled) + if (!rdev->ih.enabled || rdev->shutdown) return IRQ_NONE; + wptr = r600_get_ih_wptr(rdev); + rptr = rdev->ih.rptr; + DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr); + spin_lock_irqsave(&rdev->ih.lock, flags); if (rptr == wptr) { spin_unlock_irqrestore(&rdev->ih.lock, flags); return IRQ_NONE; } - if (rdev->shutdown) { - spin_unlock_irqrestore(&rdev->ih.lock, flags); - return IRQ_NONE; - } restart_ih: /* display interrupts */ diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 27f45579e64..ef0e0e01691 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -179,6 +179,7 @@ void radeon_pm_resume(struct radeon_device *rdev); void radeon_combios_get_power_modes(struct radeon_device *rdev); void radeon_atombios_get_power_modes(struct radeon_device *rdev); void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type); +int radeon_atom_get_max_vddc(struct radeon_device *rdev, u16 *voltage); void rs690_pm_info(struct radeon_device *rdev); extern int rv6xx_get_temp(struct radeon_device *rdev); extern int rv770_get_temp(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index fa62a503ae7..bf2b61584cd 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -2320,6 +2320,14 @@ static bool radeon_atombios_parse_pplib_clock_info(struct radeon_device *rdev, le16_to_cpu(clock_info->r600.usVDDC); } + /* patch up vddc if necessary */ + if (rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage == 0xff01) { + u16 vddc; + + if (radeon_atom_get_max_vddc(rdev, &vddc) == 0) + rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage = vddc; + } + if (rdev->flags & RADEON_IS_IGP) { /* skip invalid modes */ if (rdev->pm.power_state[state_index].clock_info[mode_index].sclk == 0) @@ -2607,6 +2615,10 @@ void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 v if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) return; + /* 0xff01 is a flag rather then an actual voltage */ + if (voltage_level == 0xff01) + return; + switch (crev) { case 1: args.v1.ucVoltageType = voltage_type; @@ -2626,7 +2638,35 @@ void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 v atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } +int radeon_atom_get_max_vddc(struct radeon_device *rdev, + u16 *voltage) +{ + union set_voltage args; + int index = GetIndexIntoMasterTable(COMMAND, SetVoltage); + u8 frev, crev; + + if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) + return -EINVAL; + + switch (crev) { + case 1: + return -EINVAL; + case 2: + args.v2.ucVoltageType = SET_VOLTAGE_GET_MAX_VOLTAGE; + args.v2.ucVoltageMode = 0; + args.v2.usVoltageLevel = 0; + + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + *voltage = le16_to_cpu(args.v2.usVoltageLevel); + break; + default: + DRM_ERROR("Unknown table version %d, %d\n", frev, crev); + return -EINVAL; + } + + return 0; +} void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev) { diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index f55b64cb59d..b293487e5aa 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -1090,9 +1090,10 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t break; } - if (is_dp) + if (is_dp) { args.v2.acConfig.fCoherentMode = 1; - else if (radeon_encoder->devices & (ATOM_DEVICE_DFP_SUPPORT)) { + args.v2.acConfig.fDPConnector = 1; + } else if (radeon_encoder->devices & (ATOM_DEVICE_DFP_SUPPORT)) { if (dig->coherent_mode) args.v2.acConfig.fCoherentMode = 1; if (radeon_encoder->pixel_clock > 165000) @@ -1431,7 +1432,11 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode) if (is_dig) { switch (mode) { case DRM_MODE_DPMS_ON: - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); + /* some early dce3.2 boards have a bug in their transmitter control table */ + if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730)) + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); + else + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_DP) { struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index ef8a5babe9f..6f508ffd103 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -105,6 +105,9 @@ void rv770_pm_misc(struct radeon_device *rdev) struct radeon_voltage *voltage = &ps->clock_info[req_cm_idx].voltage; if ((voltage->type == VOLTAGE_SW) && voltage->voltage) { + /* 0xff01 is a flag rather then an actual voltage */ + if (voltage->voltage == 0xff01) + return; if (voltage->voltage != rdev->pm.current_vddc) { radeon_atom_set_voltage(rdev, voltage->voltage, SET_VOLTAGE_TYPE_ASIC_VDDC); rdev->pm.current_vddc = voltage->voltage; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index f7440e8ce3e..6f3289a5788 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1423,6 +1423,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACETRAVELLER) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACENAVIGATOR) }, { HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH_DUAL) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICOLCD) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICOLCD_BOOTLOADER) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_SIDEWINDER_GV) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index aecb5a4b8d6..a756ee6c7df 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -449,6 +449,7 @@ #define USB_VENDOR_ID_LUMIO 0x202e #define USB_DEVICE_ID_CRYSTALTOUCH 0x0006 +#define USB_DEVICE_ID_CRYSTALTOUCH_DUAL 0x0007 #define USB_VENDOR_ID_MCC 0x09db #define USB_DEVICE_ID_MCC_PMD1024LS 0x0076 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 0b2dcd0ee59..62cac4dc3b6 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -271,6 +271,8 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi, } return 1; case HID_DG_CONTACTID: + if (!td->maxcontacts) + td->maxcontacts = MT_DEFAULT_MAXCONTACT; input_mt_init_slots(hi->input, td->maxcontacts); td->last_slot_field = usage->hid; td->last_field_index = field->index; @@ -547,9 +549,6 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) goto fail; - if (!td->maxcontacts) - td->maxcontacts = MT_DEFAULT_MAXCONTACT; - td->slots = kzalloc(td->maxcontacts * sizeof(struct mt_slot), GFP_KERNEL); if (!td->slots) { @@ -677,6 +676,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH) }, + { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, + HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, + USB_DEVICE_ID_CRYSTALTOUCH_DUAL) }, /* MosArt panels */ { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, @@ -707,10 +709,10 @@ static const struct hid_device_id mt_devices[] = { HID_USB_DEVICE(USB_VENDOR_ID_STANTUM, USB_DEVICE_ID_MTP)}, { .driver_data = MT_CLS_CONFIDENCE, - HID_USB_DEVICE(USB_VENDOR_ID_STANTUM, + HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_STM, USB_DEVICE_ID_MTP_STM)}, { .driver_data = MT_CLS_CONFIDENCE, - HID_USB_DEVICE(USB_VENDOR_ID_STANTUM, + HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_SITRONIX, USB_DEVICE_ID_MTP_SITRONIX)}, /* Touch International panels */ diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index b5e892017e0..dcb78a7a804 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -268,6 +268,7 @@ static struct device_attribute atk_name_attr = static void atk_init_attribute(struct device_attribute *attr, char *name, sysfs_show_func show) { + sysfs_attr_init(&attr->attr); attr->attr.name = name; attr->attr.mode = 0444; attr->show = show; @@ -1188,19 +1189,15 @@ static int atk_create_files(struct atk_data *data) int err; list_for_each_entry(s, &data->sensor_list, list) { - sysfs_attr_init(&s->input_attr.attr); err = device_create_file(data->hwmon_dev, &s->input_attr); if (err) return err; - sysfs_attr_init(&s->label_attr.attr); err = device_create_file(data->hwmon_dev, &s->label_attr); if (err) return err; - sysfs_attr_init(&s->limit1_attr.attr); err = device_create_file(data->hwmon_dev, &s->limit1_attr); if (err) return err; - sysfs_attr_init(&s->limit2_attr.attr); err = device_create_file(data->hwmon_dev, &s->limit2_attr); if (err) return err; diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 85e937984ff..0070d5476dd 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -97,9 +97,7 @@ struct platform_data { struct pdev_entry { struct list_head list; struct platform_device *pdev; - unsigned int cpu; u16 phys_proc_id; - u16 cpu_core_id; }; static LIST_HEAD(pdev_list); @@ -653,9 +651,7 @@ static int __cpuinit coretemp_device_add(unsigned int cpu) } pdev_entry->pdev = pdev; - pdev_entry->cpu = cpu; pdev_entry->phys_proc_id = TO_PHYS_ID(cpu); - pdev_entry->cpu_core_id = TO_CORE_ID(cpu); list_add_tail(&pdev_entry->list, &pdev_list); mutex_unlock(&pdev_list_mutex); diff --git a/drivers/hwmon/ibmaem.c b/drivers/hwmon/ibmaem.c index 537409d07ee..1a409c5bc9b 100644 --- a/drivers/hwmon/ibmaem.c +++ b/drivers/hwmon/ibmaem.c @@ -947,6 +947,7 @@ static int aem_register_sensors(struct aem_data *data, /* Set up read-only sensors */ while (ro->label) { + sysfs_attr_init(&sensors->dev_attr.attr); sensors->dev_attr.attr.name = ro->label; sensors->dev_attr.attr.mode = S_IRUGO; sensors->dev_attr.show = ro->show; @@ -963,6 +964,7 @@ static int aem_register_sensors(struct aem_data *data, /* Set up read-write sensors */ while (rw->label) { + sysfs_attr_init(&sensors->dev_attr.attr); sensors->dev_attr.attr.name = rw->label; sensors->dev_attr.attr.mode = S_IRUGO | S_IWUSR; sensors->dev_attr.show = rw->show; diff --git a/drivers/hwmon/ibmpex.c b/drivers/hwmon/ibmpex.c index 06d4eafcf76..41dbf8161ed 100644 --- a/drivers/hwmon/ibmpex.c +++ b/drivers/hwmon/ibmpex.c @@ -358,6 +358,7 @@ static int create_sensor(struct ibmpex_bmc_data *data, int type, else if (type == POWER_SENSOR) sprintf(n, power_sensor_name_templates[func], "power", counter); + sysfs_attr_init(&data->sensors[sensor].attr[func].dev_attr.attr); data->sensors[sensor].attr[func].dev_attr.attr.name = n; data->sensors[sensor].attr[func].dev_attr.attr.mode = S_IRUGO; data->sensors[sensor].attr[func].dev_attr.show = ibmpex_show_sensor; diff --git a/drivers/hwmon/s3c-hwmon.c b/drivers/hwmon/s3c-hwmon.c index 92b42db43bc..b39f52e2752 100644 --- a/drivers/hwmon/s3c-hwmon.c +++ b/drivers/hwmon/s3c-hwmon.c @@ -232,6 +232,7 @@ static int s3c_hwmon_create_attr(struct device *dev, attr = &attrs->in; attr->index = channel; + sysfs_attr_init(&attr->dev_attr.attr); attr->dev_attr.attr.name = attrs->in_name; attr->dev_attr.attr.mode = S_IRUGO; attr->dev_attr.show = s3c_hwmon_ch_show; @@ -249,6 +250,7 @@ static int s3c_hwmon_create_attr(struct device *dev, attr = &attrs->label; attr->index = channel; + sysfs_attr_init(&attr->dev_attr.attr); attr->dev_attr.attr.name = attrs->label_name; attr->dev_attr.attr.mode = S_IRUGO; attr->dev_attr.show = s3c_hwmon_label_show; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index f660cd04ec2..31fb44085c9 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1463,9 +1463,9 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) struct c4iw_qp_attributes attrs; int disconnect = 1; int release = 0; - int abort = 0; struct tid_info *t = dev->rdev.lldi.tids; unsigned int tid = GET_TID(hdr); + int ret; ep = lookup_tid(t, tid); PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid); @@ -1501,10 +1501,12 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) start_ep_timer(ep); __state_set(&ep->com, CLOSING); attrs.next_state = C4IW_QP_STATE_CLOSING; - abort = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, + ret = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); - peer_close_upcall(ep); - disconnect = 1; + if (ret != -ECONNRESET) { + peer_close_upcall(ep); + disconnect = 1; + } break; case ABORTING: disconnect = 0; @@ -2109,15 +2111,16 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp) break; } - mutex_unlock(&ep->com.mutex); if (close) { - if (abrupt) - ret = abort_connection(ep, NULL, gfp); - else + if (abrupt) { + close_complete_upcall(ep); + ret = send_abort(ep, NULL, gfp); + } else ret = send_halfclose(ep, gfp); if (ret) fatal = 1; } + mutex_unlock(&ep->com.mutex); if (fatal) release_ep_resources(ep); return ret; @@ -2301,6 +2304,31 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb) return 0; } +static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb) +{ + struct cpl_abort_req_rss *req = cplhdr(skb); + struct c4iw_ep *ep; + struct tid_info *t = dev->rdev.lldi.tids; + unsigned int tid = GET_TID(req); + + ep = lookup_tid(t, tid); + if (is_neg_adv_abort(req->status)) { + PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep, + ep->hwtid); + kfree_skb(skb); + return 0; + } + PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid, + ep->com.state); + + /* + * Wake up any threads in rdma_init() or rdma_fini(). + */ + c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + sched(dev, skb); + return 0; +} + /* * Most upcalls from the T4 Core go to sched() to * schedule the processing on a work queue. @@ -2317,7 +2345,7 @@ c4iw_handler_func c4iw_handlers[NUM_CPL_CMDS] = { [CPL_PASS_ESTABLISH] = sched, [CPL_PEER_CLOSE] = sched, [CPL_CLOSE_CON_RPL] = sched, - [CPL_ABORT_REQ_RSS] = sched, + [CPL_ABORT_REQ_RSS] = peer_abort_intr, [CPL_RDMA_TERMINATE] = sched, [CPL_FW4_ACK] = sched, [CPL_SET_TCB_RPL] = set_tcb_rpl, diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 8d8f8add6fc..1720dc790d1 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -801,6 +801,10 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries, if (ucontext) { memsize = roundup(memsize, PAGE_SIZE); hwentries = memsize / sizeof *chp->cq.queue; + while (hwentries > T4_MAX_IQ_SIZE) { + memsize -= PAGE_SIZE; + hwentries = memsize / sizeof *chp->cq.queue; + } } chp->cq.size = hwentries; chp->cq.memsize = memsize; diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 273ffe49525..0347eed4a16 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -625,7 +625,7 @@ pbl_done: mhp->attr.perms = c4iw_ib_to_tpt_access(acc); mhp->attr.va_fbo = virt; mhp->attr.page_size = shift - 12; - mhp->attr.len = (u32) length; + mhp->attr.len = length; err = register_mem(rhp, php, mhp, shift); if (err) diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 3b773b05a89..a41578e48c7 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1207,11 +1207,8 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, c4iw_get_ep(&qhp->ep->com); } ret = rdma_fini(rhp, qhp, ep); - if (ret) { - if (internal) - c4iw_get_ep(&qhp->ep->com); + if (ret) goto err; - } break; case C4IW_QP_STATE_TERMINATE: set_state(qhp, C4IW_QP_STATE_TERMINATE); diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 9f53e68a096..8ec5237031a 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -469,6 +469,8 @@ static u8 ib_rate_to_delay[IB_RATE_120_GBPS + 1] = { #define IB_7322_LT_STATE_RECOVERIDLE 0x0f #define IB_7322_LT_STATE_CFGENH 0x10 #define IB_7322_LT_STATE_CFGTEST 0x11 +#define IB_7322_LT_STATE_CFGWAITRMTTEST 0x12 +#define IB_7322_LT_STATE_CFGWAITENH 0x13 /* link state machine states from IBC */ #define IB_7322_L_STATE_DOWN 0x0 @@ -498,8 +500,10 @@ static const u8 qib_7322_physportstate[0x20] = { IB_PHYSPORTSTATE_LINK_ERR_RECOVER, [IB_7322_LT_STATE_CFGENH] = IB_PHYSPORTSTATE_CFG_ENH, [IB_7322_LT_STATE_CFGTEST] = IB_PHYSPORTSTATE_CFG_TRAIN, - [0x12] = IB_PHYSPORTSTATE_CFG_TRAIN, - [0x13] = IB_PHYSPORTSTATE_CFG_WAIT_ENH, + [IB_7322_LT_STATE_CFGWAITRMTTEST] = + IB_PHYSPORTSTATE_CFG_TRAIN, + [IB_7322_LT_STATE_CFGWAITENH] = + IB_PHYSPORTSTATE_CFG_WAIT_ENH, [0x14] = IB_PHYSPORTSTATE_CFG_TRAIN, [0x15] = IB_PHYSPORTSTATE_CFG_TRAIN, [0x16] = IB_PHYSPORTSTATE_CFG_TRAIN, @@ -1692,7 +1696,9 @@ static void handle_serdes_issues(struct qib_pportdata *ppd, u64 ibcst) break; } - if (ibclt == IB_7322_LT_STATE_CFGTEST && + if (((ibclt >= IB_7322_LT_STATE_CFGTEST && + ibclt <= IB_7322_LT_STATE_CFGWAITENH) || + ibclt == IB_7322_LT_STATE_LINKUP) && (ibcst & SYM_MASK(IBCStatusA_0, LinkSpeedQDR))) { force_h1(ppd); ppd->cpspec->qdr_reforce = 1; @@ -7301,12 +7307,17 @@ static void ibsd_wr_allchans(struct qib_pportdata *ppd, int addr, unsigned data, static void serdes_7322_los_enable(struct qib_pportdata *ppd, int enable) { u64 data = qib_read_kreg_port(ppd, krp_serdesctrl); - printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS %s\n", - ppd->dd->unit, ppd->port, (enable ? "on" : "off")); - if (enable) + u8 state = SYM_FIELD(data, IBSerdesCtrl_0, RXLOSEN); + + if (enable && !state) { + printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS on\n", + ppd->dd->unit, ppd->port); data |= SYM_MASK(IBSerdesCtrl_0, RXLOSEN); - else + } else if (!enable && state) { + printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS off\n", + ppd->dd->unit, ppd->port); data &= ~SYM_MASK(IBSerdesCtrl_0, RXLOSEN); + } qib_write_kreg_port(ppd, krp_serdesctrl, data); } diff --git a/drivers/infiniband/hw/qib/qib_intr.c b/drivers/infiniband/hw/qib/qib_intr.c index a693c56ec8a..6ae57d23004 100644 --- a/drivers/infiniband/hw/qib/qib_intr.c +++ b/drivers/infiniband/hw/qib/qib_intr.c @@ -96,8 +96,12 @@ void qib_handle_e_ibstatuschanged(struct qib_pportdata *ppd, u64 ibcs) * states, or if it transitions from any of the up (INIT or better) * states into any of the down states (except link recovery), then * call the chip-specific code to take appropriate actions. + * + * ppd->lflags could be 0 if this is the first time the interrupt + * handlers has been called but the link is already up. */ - if (lstate >= IB_PORT_INIT && (ppd->lflags & QIBL_LINKDOWN) && + if (lstate >= IB_PORT_INIT && + (!ppd->lflags || (ppd->lflags & QIBL_LINKDOWN)) && ltstate == IB_PHYSPORTSTATE_LINKUP) { /* transitioned to UP */ if (dd->f_ib_updown(ppd, 1, ibcs)) diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index be0921ef6b5..4cf25347b01 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -111,7 +111,8 @@ static void evdev_event(struct input_handle *handle, rcu_read_unlock(); - wake_up_interruptible(&evdev->wait); + if (type == EV_SYN && code == SYN_REPORT) + wake_up_interruptible(&evdev->wait); } static int evdev_fasync(int fd, struct file *file, int on) diff --git a/drivers/input/input.c b/drivers/input/input.c index 75e11c7b70f..da38d97a51b 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1756,7 +1756,7 @@ static unsigned int input_estimate_events_per_packet(struct input_dev *dev) } else if (test_bit(ABS_MT_TRACKING_ID, dev->absbit)) { mt_slots = dev->absinfo[ABS_MT_TRACKING_ID].maximum - dev->absinfo[ABS_MT_TRACKING_ID].minimum + 1, - clamp(mt_slots, 2, 32); + mt_slots = clamp(mt_slots, 2, 32); } else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) { mt_slots = 2; } else { diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c index f23a743817d..33d0bdc837c 100644 --- a/drivers/input/keyboard/omap-keypad.c +++ b/drivers/input/keyboard/omap-keypad.c @@ -209,6 +209,7 @@ static void omap_kp_tasklet(unsigned long data) #endif } } + input_sync(omap_kp_data->input); memcpy(keypad_state, new_state, sizeof(keypad_state)); if (key_down) { diff --git a/drivers/input/keyboard/sh_keysc.c b/drivers/input/keyboard/sh_keysc.c index 834cf98e7ef..6876700a446 100644 --- a/drivers/input/keyboard/sh_keysc.c +++ b/drivers/input/keyboard/sh_keysc.c @@ -32,7 +32,7 @@ static const struct { [SH_KEYSC_MODE_3] = { 2, 4, 7 }, [SH_KEYSC_MODE_4] = { 3, 6, 6 }, [SH_KEYSC_MODE_5] = { 4, 6, 7 }, - [SH_KEYSC_MODE_6] = { 5, 7, 7 }, + [SH_KEYSC_MODE_6] = { 5, 8, 8 }, }; struct sh_keysc_priv { diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 257e033986e..0110b5a3a16 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -187,7 +187,7 @@ static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev, if (size == 0) size = xres ? : 1; - clamp(value, min, max); + value = clamp(value, min, max); mousedev->packet.x = ((value - min) * xres) / size; mousedev->packet.abs_event = 1; @@ -201,7 +201,7 @@ static void mousedev_abs_event(struct input_dev *dev, struct mousedev *mousedev, if (size == 0) size = yres ? : 1; - clamp(value, min, max); + value = clamp(value, min, max); mousedev->packet.y = yres - ((value - min) * yres) / size; mousedev->packet.abs_event = 1; diff --git a/drivers/isdn/gigaset/interface.c b/drivers/isdn/gigaset/interface.c index 59de638225f..e35058bcd7b 100644 --- a/drivers/isdn/gigaset/interface.c +++ b/drivers/isdn/gigaset/interface.c @@ -156,8 +156,10 @@ static int if_open(struct tty_struct *tty, struct file *filp) if (!cs || !try_module_get(cs->driver->owner)) return -ENODEV; - if (mutex_lock_interruptible(&cs->mutex)) + if (mutex_lock_interruptible(&cs->mutex)) { + module_put(cs->driver->owner); return -ERESTARTSYS; + } tty->driver_data = cs; ++cs->open_count; diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c index ee5109a3cd9..42f067347bc 100644 --- a/drivers/misc/sgi-xp/xpnet.c +++ b/drivers/misc/sgi-xp/xpnet.c @@ -495,14 +495,14 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) } } + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + if (atomic_dec_return(&queued_msg->use_count) == 0) { dev_kfree_skb(skb); kfree(queued_msg); } - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - return NETDEV_TX_OK; } diff --git a/drivers/net/3c503.c b/drivers/net/3c503.c index d84f6e8903a..5b732988d49 100644 --- a/drivers/net/3c503.c +++ b/drivers/net/3c503.c @@ -412,7 +412,7 @@ el2_open(struct net_device *dev) outb_p(0x04 << ((*irqp == 9) ? 2 : *irqp), E33G_IDCFR); outb_p(0x00, E33G_IDCFR); msleep(1); - free_irq(*irqp, el2_probe_interrupt); + free_irq(*irqp, &seen); if (!seen) continue; @@ -422,6 +422,7 @@ el2_open(struct net_device *dev) continue; if (retval < 0) goto err_disable; + break; } while (*++irqp); if (*irqp == 0) { diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c index 68d45ba2d9b..6c019e14854 100644 --- a/drivers/net/bfin_mac.c +++ b/drivers/net/bfin_mac.c @@ -52,13 +52,13 @@ MODULE_DESCRIPTION(DRV_DESC); MODULE_ALIAS("platform:bfin_mac"); #if defined(CONFIG_BFIN_MAC_USE_L1) -# define bfin_mac_alloc(dma_handle, size) l1_data_sram_zalloc(size) -# define bfin_mac_free(dma_handle, ptr) l1_data_sram_free(ptr) +# define bfin_mac_alloc(dma_handle, size, num) l1_data_sram_zalloc(size*num) +# define bfin_mac_free(dma_handle, ptr, num) l1_data_sram_free(ptr) #else -# define bfin_mac_alloc(dma_handle, size) \ - dma_alloc_coherent(NULL, size, dma_handle, GFP_KERNEL) -# define bfin_mac_free(dma_handle, ptr) \ - dma_free_coherent(NULL, sizeof(*ptr), ptr, dma_handle) +# define bfin_mac_alloc(dma_handle, size, num) \ + dma_alloc_coherent(NULL, size*num, dma_handle, GFP_KERNEL) +# define bfin_mac_free(dma_handle, ptr, num) \ + dma_free_coherent(NULL, sizeof(*ptr)*num, ptr, dma_handle) #endif #define PKT_BUF_SZ 1580 @@ -95,7 +95,7 @@ static void desc_list_free(void) t = t->next; } } - bfin_mac_free(dma_handle, tx_desc); + bfin_mac_free(dma_handle, tx_desc, CONFIG_BFIN_TX_DESC_NUM); } if (rx_desc) { @@ -109,7 +109,7 @@ static void desc_list_free(void) r = r->next; } } - bfin_mac_free(dma_handle, rx_desc); + bfin_mac_free(dma_handle, rx_desc, CONFIG_BFIN_RX_DESC_NUM); } } @@ -126,13 +126,13 @@ static int desc_list_init(void) #endif tx_desc = bfin_mac_alloc(&dma_handle, - sizeof(struct net_dma_desc_tx) * + sizeof(struct net_dma_desc_tx), CONFIG_BFIN_TX_DESC_NUM); if (tx_desc == NULL) goto init_error; rx_desc = bfin_mac_alloc(&dma_handle, - sizeof(struct net_dma_desc_rx) * + sizeof(struct net_dma_desc_rx), CONFIG_BFIN_RX_DESC_NUM); if (rx_desc == NULL) goto init_error; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 652b30e525d..eafe44a528a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1297,6 +1297,7 @@ static inline int slave_enable_netpoll(struct slave *slave) goto out; np->dev = slave->dev; + strlcpy(np->dev_name, slave->dev->name, IFNAMSIZ); err = __netpoll_setup(np); if (err) { kfree(np); diff --git a/drivers/net/fs_enet/mac-fcc.c b/drivers/net/fs_enet/mac-fcc.c index 7a84e45487e..7583a9572bc 100644 --- a/drivers/net/fs_enet/mac-fcc.c +++ b/drivers/net/fs_enet/mac-fcc.c @@ -105,7 +105,7 @@ static int do_pd_setup(struct fs_enet_private *fep) goto out_ep; fep->fcc.mem = (void __iomem *)cpm2_immr; - fpi->dpram_offset = cpm_dpalloc(128, 8); + fpi->dpram_offset = cpm_dpalloc(128, 32); if (IS_ERR_VALUE(fpi->dpram_offset)) { ret = fpi->dpram_offset; goto out_fcccp; diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c index 8e10d2f6a5a..c3ecb118c1d 100644 --- a/drivers/net/hp100.c +++ b/drivers/net/hp100.c @@ -1580,12 +1580,12 @@ static netdev_tx_t hp100_start_xmit_bm(struct sk_buff *skb, hp100_outl(ringptr->pdl_paddr, TX_PDA_L); /* Low Prio. Queue */ lp->txrcommit++; - spin_unlock_irqrestore(&lp->lock, flags); - /* Update statistics */ dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + spin_unlock_irqrestore(&lp->lock, flags); + return NETDEV_TX_OK; drop: diff --git a/drivers/net/hplance.c b/drivers/net/hplance.c index b6060f7538d..a900d5bf294 100644 --- a/drivers/net/hplance.c +++ b/drivers/net/hplance.c @@ -135,7 +135,7 @@ static void __devexit hplance_remove_one(struct dio_dev *d) } /* Initialise a single lance board at the given DIO device */ -static void __init hplance_init(struct net_device *dev, struct dio_dev *d) +static void __devinit hplance_init(struct net_device *dev, struct dio_dev *d) { unsigned long va = (d->resource.start + DIO_VIRADDRBASE); struct hplance_private *lp; diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index b644383017f..c0788a31ff0 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -1965,11 +1965,11 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) netxen_tso_check(netdev, tx_ring, first_desc, skb); - netxen_nic_update_cmd_producer(adapter, tx_ring); - adapter->stats.txbytes += skb->len; adapter->stats.xmitcalled++; + netxen_nic_update_cmd_producer(adapter, tx_ring); + return NETDEV_TX_OK; drop_packet: diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 392a6c4b72e..a70244306c9 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -58,6 +58,7 @@ config BROADCOM_PHY config BCM63XX_PHY tristate "Drivers for Broadcom 63xx SOCs internal PHY" + depends on BCM63XX ---help--- Currently supports the 6348 and 6358 PHYs. diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index b0c9522bb53..2cd8dc5847b 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -543,11 +543,20 @@ static void recalibrate(struct dp83640_clock *clock) /* time stamping methods */ -static void decode_evnt(struct dp83640_private *dp83640, - struct phy_txts *phy_txts, u16 ests) +static int decode_evnt(struct dp83640_private *dp83640, + void *data, u16 ests) { + struct phy_txts *phy_txts; struct ptp_clock_event event; int words = (ests >> EVNT_TS_LEN_SHIFT) & EVNT_TS_LEN_MASK; + u16 ext_status = 0; + + if (ests & MULT_EVNT) { + ext_status = *(u16 *) data; + data += sizeof(ext_status); + } + + phy_txts = data; switch (words) { /* fall through in every case */ case 3: @@ -565,6 +574,9 @@ static void decode_evnt(struct dp83640_private *dp83640, event.timestamp = phy2txts(&dp83640->edata); ptp_clock_event(dp83640->clock->ptp_clock, &event); + + words = ext_status ? words + 2 : words + 1; + return words * sizeof(u16); } static void decode_rxts(struct dp83640_private *dp83640, @@ -643,9 +655,7 @@ static void decode_status_frame(struct dp83640_private *dp83640, } else if (PSF_EVNT == type && len >= sizeof(*phy_txts)) { - phy_txts = (struct phy_txts *) ptr; - decode_evnt(dp83640, phy_txts, ests); - size = sizeof(*phy_txts); + size = decode_evnt(dp83640, ptr, ests); } else { size = 0; @@ -1034,8 +1044,8 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, if (is_status_frame(skb, type)) { decode_status_frame(dp83640, skb); - /* Let the stack drop this frame. */ - return false; + kfree_skb(skb); + return true; } SKB_PTP_TYPE(skb) = type; diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c index a1b82c9c67d..c554a397e55 100644 --- a/drivers/net/ppp_async.c +++ b/drivers/net/ppp_async.c @@ -523,7 +523,7 @@ static void ppp_async_process(unsigned long arg) #define PUT_BYTE(ap, buf, c, islcp) do { \ if ((islcp && c < 0x20) || (ap->xaccm[c >> 5] & (1 << (c & 0x1f)))) {\ *buf++ = PPP_ESCAPE; \ - *buf++ = c ^ 0x20; \ + *buf++ = c ^ PPP_TRANS; \ } else \ *buf++ = c; \ } while (0) @@ -896,7 +896,7 @@ ppp_async_input(struct asyncppp *ap, const unsigned char *buf, sp = skb_put(skb, n); memcpy(sp, buf, n); if (ap->state & SC_ESCAPE) { - sp[0] ^= 0x20; + sp[0] ^= PPP_TRANS; ap->state &= ~SC_ESCAPE; } } diff --git a/drivers/net/pxa168_eth.c b/drivers/net/pxa168_eth.c index 89f7540d90f..5f597ca592b 100644 --- a/drivers/net/pxa168_eth.c +++ b/drivers/net/pxa168_eth.c @@ -1273,7 +1273,7 @@ static int pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) wmb(); wrl(pep, SDMA_CMD, SDMA_CMD_TXDH | SDMA_CMD_ERD); - stats->tx_bytes += skb->len; + stats->tx_bytes += length; stats->tx_packets++; dev->trans_start = jiffies; if (pep->tx_ring_size - pep->tx_desc_count <= 1) { diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index ef1ce2ebeb4..05d81780d1f 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -1621,7 +1621,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, * * (RTL_R32(TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec */ - static const struct { + static const struct rtl_mac_info { u32 mask; u32 val; int mac_version; @@ -1689,7 +1689,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, /* Catch-all */ { 0x00000000, 0x00000000, RTL_GIGA_MAC_NONE } - }, *p = mac_info; + }; + const struct rtl_mac_info *p = mac_info; u32 reg; reg = RTL_R32(TxConfig); @@ -3681,7 +3682,7 @@ static void rtl_set_rx_max_size(void __iomem *ioaddr, unsigned int rx_buf_sz) static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) { - static const struct { + static const struct rtl_cfg2_info { u32 mac_version; u32 clk; u32 val; @@ -3690,7 +3691,8 @@ static void rtl8169_set_magic_reg(void __iomem *ioaddr, unsigned mac_version) { RTL_GIGA_MAC_VER_05, PCI_Clock_66MHz, 0x000fffff }, { RTL_GIGA_MAC_VER_06, PCI_Clock_33MHz, 0x00ffff00 }, // 8110SCe { RTL_GIGA_MAC_VER_06, PCI_Clock_66MHz, 0x00ffffff } - }, *p = cfg2_info; + }; + const struct rtl_cfg2_info *p = cfg2_info; unsigned int i; u32 clk; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 74e94054ab1..5235f48be1b 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -460,7 +460,23 @@ static u32 tun_net_fix_features(struct net_device *dev, u32 features) return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); } - +#ifdef CONFIG_NET_POLL_CONTROLLER +static void tun_poll_controller(struct net_device *dev) +{ + /* + * Tun only receives frames when: + * 1) the char device endpoint gets data from user space + * 2) the tun socket gets a sendmsg call from user space + * Since both of those are syncronous operations, we are guaranteed + * never to have pending data when we poll for it + * so theres nothing to do here but return. + * We need this though so netpoll recognizes us as an interface that + * supports polling, which enables bridge devices in virt setups to + * still use netconsole + */ + return; +} +#endif static const struct net_device_ops tun_netdev_ops = { .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, @@ -468,6 +484,9 @@ static const struct net_device_ops tun_netdev_ops = { .ndo_start_xmit = tun_net_xmit, .ndo_change_mtu = tun_net_change_mtu, .ndo_fix_features = tun_net_fix_features, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tun_poll_controller, +#endif }; static const struct net_device_ops tap_netdev_ops = { @@ -480,6 +499,9 @@ static const struct net_device_ops tap_netdev_ops = { .ndo_set_multicast_list = tun_net_mclist, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tun_poll_controller, +#endif }; /* Initialize net device. */ diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 9d4f9117260..84d4608153c 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -385,6 +385,16 @@ config USB_NET_CX82310_ETH router with USB ethernet port. This driver is for routers only, it will not work with ADSL modems (use cxacru driver instead). +config USB_NET_KALMIA + tristate "Samsung Kalmia based LTE USB modem" + depends on USB_USBNET + help + Choose this option if you have a Samsung Kalmia based USB modem + as Samsung GT-B3730. + + To compile this driver as a module, choose M here: the + module will be called kalmia. + config USB_HSO tristate "Option USB High Speed Mobile Devices" depends on USB && RFKILL diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index c7ec8a5f0a9..c203fa21f6b 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_USB_NET_MCS7830) += mcs7830.o obj-$(CONFIG_USB_USBNET) += usbnet.o obj-$(CONFIG_USB_NET_INT51X1) += int51x1.o obj-$(CONFIG_USB_CDC_PHONET) += cdc-phonet.o +obj-$(CONFIG_USB_NET_KALMIA) += kalmia.o obj-$(CONFIG_USB_IPHETH) += ipheth.o obj-$(CONFIG_USB_SIERRA_NET) += sierra_net.o obj-$(CONFIG_USB_NET_CX82310_ETH) += cx82310_eth.o diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c new file mode 100644 index 00000000000..d965fb1e013 --- /dev/null +++ b/drivers/net/usb/kalmia.c @@ -0,0 +1,384 @@ +/* + * USB network interface driver for Samsung Kalmia based LTE USB modem like the + * Samsung GT-B3730 and GT-B3710. + * + * Copyright (C) 2011 Marius Bjoernstad Kotsbak <marius@kotsbak.com> + * + * Sponsored by Quicklink Video Distribution Services Ltd. + * + * Based on the cdc_eem module. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/ctype.h> +#include <linux/ethtool.h> +#include <linux/workqueue.h> +#include <linux/mii.h> +#include <linux/usb.h> +#include <linux/crc32.h> +#include <linux/usb/cdc.h> +#include <linux/usb/usbnet.h> +#include <linux/gfp.h> + +/* + * The Samsung Kalmia based LTE USB modems have a CDC ACM port for modem control + * handled by the "option" module and an ethernet data port handled by this + * module. + * + * The stick must first be switched into modem mode by usb_modeswitch + * or similar tool. Then the modem gets sent two initialization packets by + * this module, which gives the MAC address of the device. User space can then + * connect the modem using AT commands through the ACM port and then use + * DHCP on the network interface exposed by this module. Network packets are + * sent to and from the modem in a proprietary format discovered after watching + * the behavior of the windows driver for the modem. + * + * More information about the use of the modem is available in usb_modeswitch + * forum and the project page: + * + * http://www.draisberghof.de/usb_modeswitch/bb/viewtopic.php?t=465 + * https://github.com/mkotsbak/Samsung-GT-B3730-linux-driver + */ + +/* #define DEBUG */ +/* #define VERBOSE */ + +#define KALMIA_HEADER_LENGTH 6 +#define KALMIA_ALIGN_SIZE 4 +#define KALMIA_USB_TIMEOUT 10000 + +/*-------------------------------------------------------------------------*/ + +static int +kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, + u8 *buffer, u8 expected_len) +{ + int act_len; + int status; + + netdev_dbg(dev->net, "Sending init packet"); + + status = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 0x02), + init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT); + if (status != 0) { + netdev_err(dev->net, + "Error sending init packet. Status %i, length %i\n", + status, act_len); + return status; + } + else if (act_len != init_msg_len) { + netdev_err(dev->net, + "Did not send all of init packet. Bytes sent: %i", + act_len); + } + else { + netdev_dbg(dev->net, "Successfully sent init packet."); + } + + status = usb_bulk_msg(dev->udev, usb_rcvbulkpipe(dev->udev, 0x81), + buffer, expected_len, &act_len, KALMIA_USB_TIMEOUT); + + if (status != 0) + netdev_err(dev->net, + "Error receiving init result. Status %i, length %i\n", + status, act_len); + else if (act_len != expected_len) + netdev_err(dev->net, "Unexpected init result length: %i\n", + act_len); + + return status; +} + +static int +kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) +{ + char init_msg_1[] = + { 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00, + 0x00, 0x00 }; + char init_msg_2[] = + { 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0xf4, + 0x00, 0x00 }; + char receive_buf[28]; + int status; + + status = kalmia_send_init_packet(dev, init_msg_1, sizeof(init_msg_1) + / sizeof(init_msg_1[0]), receive_buf, 24); + if (status != 0) + return status; + + status = kalmia_send_init_packet(dev, init_msg_2, sizeof(init_msg_2) + / sizeof(init_msg_2[0]), receive_buf, 28); + if (status != 0) + return status; + + memcpy(ethernet_addr, receive_buf + 10, ETH_ALEN); + + return status; +} + +static int +kalmia_bind(struct usbnet *dev, struct usb_interface *intf) +{ + u8 status; + u8 ethernet_addr[ETH_ALEN]; + + /* Don't bind to AT command interface */ + if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC) + return -EINVAL; + + dev->in = usb_rcvbulkpipe(dev->udev, 0x81 & USB_ENDPOINT_NUMBER_MASK); + dev->out = usb_sndbulkpipe(dev->udev, 0x02 & USB_ENDPOINT_NUMBER_MASK); + dev->status = NULL; + + dev->net->hard_header_len += KALMIA_HEADER_LENGTH; + dev->hard_mtu = 1400; + dev->rx_urb_size = dev->hard_mtu * 10; // Found as optimal after testing + + status = kalmia_init_and_get_ethernet_addr(dev, ethernet_addr); + + if (status < 0) { + usb_set_intfdata(intf, NULL); + usb_driver_release_interface(driver_of(intf), intf); + return status; + } + + memcpy(dev->net->dev_addr, ethernet_addr, ETH_ALEN); + memcpy(dev->net->perm_addr, ethernet_addr, ETH_ALEN); + + return status; +} + +static struct sk_buff * +kalmia_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) +{ + struct sk_buff *skb2 = NULL; + u16 content_len; + unsigned char *header_start; + unsigned char ether_type_1, ether_type_2; + u8 remainder, padlen = 0; + + if (!skb_cloned(skb)) { + int headroom = skb_headroom(skb); + int tailroom = skb_tailroom(skb); + + if ((tailroom >= KALMIA_ALIGN_SIZE) && (headroom + >= KALMIA_HEADER_LENGTH)) + goto done; + + if ((headroom + tailroom) > (KALMIA_HEADER_LENGTH + + KALMIA_ALIGN_SIZE)) { + skb->data = memmove(skb->head + KALMIA_HEADER_LENGTH, + skb->data, skb->len); + skb_set_tail_pointer(skb, skb->len); + goto done; + } + } + + skb2 = skb_copy_expand(skb, KALMIA_HEADER_LENGTH, + KALMIA_ALIGN_SIZE, flags); + if (!skb2) + return NULL; + + dev_kfree_skb_any(skb); + skb = skb2; + + done: header_start = skb_push(skb, KALMIA_HEADER_LENGTH); + ether_type_1 = header_start[KALMIA_HEADER_LENGTH + 12]; + ether_type_2 = header_start[KALMIA_HEADER_LENGTH + 13]; + + netdev_dbg(dev->net, "Sending etherType: %02x%02x", ether_type_1, + ether_type_2); + + /* According to empiric data for data packages */ + header_start[0] = 0x57; + header_start[1] = 0x44; + content_len = skb->len - KALMIA_HEADER_LENGTH; + header_start[2] = (content_len & 0xff); /* low byte */ + header_start[3] = (content_len >> 8); /* high byte */ + + header_start[4] = ether_type_1; + header_start[5] = ether_type_2; + + /* Align to 4 bytes by padding with zeros */ + remainder = skb->len % KALMIA_ALIGN_SIZE; + if (remainder > 0) { + padlen = KALMIA_ALIGN_SIZE - remainder; + memset(skb_put(skb, padlen), 0, padlen); + } + + netdev_dbg( + dev->net, + "Sending package with length %i and padding %i. Header: %02x:%02x:%02x:%02x:%02x:%02x.", + content_len, padlen, header_start[0], header_start[1], + header_start[2], header_start[3], header_start[4], + header_start[5]); + + return skb; +} + +static int +kalmia_rx_fixup(struct usbnet *dev, struct sk_buff *skb) +{ + /* + * Our task here is to strip off framing, leaving skb with one + * data frame for the usbnet framework code to process. + */ + const u8 HEADER_END_OF_USB_PACKET[] = + { 0x57, 0x5a, 0x00, 0x00, 0x08, 0x00 }; + const u8 EXPECTED_UNKNOWN_HEADER_1[] = + { 0x57, 0x43, 0x1e, 0x00, 0x15, 0x02 }; + const u8 EXPECTED_UNKNOWN_HEADER_2[] = + { 0x57, 0x50, 0x0e, 0x00, 0x00, 0x00 }; + u8 i = 0; + + /* incomplete header? */ + if (skb->len < KALMIA_HEADER_LENGTH) + return 0; + + do { + struct sk_buff *skb2 = NULL; + u8 *header_start; + u16 usb_packet_length, ether_packet_length; + int is_last; + + header_start = skb->data; + + if (unlikely(header_start[0] != 0x57 || header_start[1] != 0x44)) { + if (!memcmp(header_start, EXPECTED_UNKNOWN_HEADER_1, + sizeof(EXPECTED_UNKNOWN_HEADER_1)) || !memcmp( + header_start, EXPECTED_UNKNOWN_HEADER_2, + sizeof(EXPECTED_UNKNOWN_HEADER_2))) { + netdev_dbg( + dev->net, + "Received expected unknown frame header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], + header_start[2], header_start[3], + header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + } + else { + netdev_err( + dev->net, + "Received unknown frame header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], + header_start[2], header_start[3], + header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + return 0; + } + } + else + netdev_dbg( + dev->net, + "Received header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], header_start[2], + header_start[3], header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + + /* subtract start header and end header */ + usb_packet_length = skb->len - (2 * KALMIA_HEADER_LENGTH); + ether_packet_length = header_start[2] + (header_start[3] << 8); + skb_pull(skb, KALMIA_HEADER_LENGTH); + + /* Some small packets misses end marker */ + if (usb_packet_length < ether_packet_length) { + ether_packet_length = usb_packet_length + + KALMIA_HEADER_LENGTH; + is_last = true; + } + else { + netdev_dbg(dev->net, "Correct package length #%i", i + + 1); + + is_last = (memcmp(skb->data + ether_packet_length, + HEADER_END_OF_USB_PACKET, + sizeof(HEADER_END_OF_USB_PACKET)) == 0); + if (!is_last) { + header_start = skb->data + ether_packet_length; + netdev_dbg( + dev->net, + "End header: %02x:%02x:%02x:%02x:%02x:%02x. Package length: %i\n", + header_start[0], header_start[1], + header_start[2], header_start[3], + header_start[4], header_start[5], + skb->len - KALMIA_HEADER_LENGTH); + } + } + + if (is_last) { + skb2 = skb; + } + else { + skb2 = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!skb2)) + return 0; + } + + skb_trim(skb2, ether_packet_length); + + if (is_last) { + return 1; + } + else { + usbnet_skb_return(dev, skb2); + skb_pull(skb, ether_packet_length); + } + + i++; + } + while (skb->len); + + return 1; +} + +static const struct driver_info kalmia_info = { + .description = "Samsung Kalmia LTE USB dongle", + .flags = FLAG_WWAN, + .bind = kalmia_bind, + .rx_fixup = kalmia_rx_fixup, + .tx_fixup = kalmia_tx_fixup +}; + +/*-------------------------------------------------------------------------*/ + +static const struct usb_device_id products[] = { + /* The unswitched USB ID, to get the module auto loaded: */ + { USB_DEVICE(0x04e8, 0x689a) }, + /* The stick swithed into modem (by e.g. usb_modeswitch): */ + { USB_DEVICE(0x04e8, 0x6889), + .driver_info = (unsigned long) &kalmia_info, }, + { /* EMPTY == end of list */} }; +MODULE_DEVICE_TABLE( usb, products); + +static struct usb_driver kalmia_driver = { + .name = "kalmia", + .id_table = products, + .probe = usbnet_probe, + .disconnect = usbnet_disconnect, + .suspend = usbnet_suspend, + .resume = usbnet_resume +}; + +static int __init kalmia_init(void) +{ + return usb_register(&kalmia_driver); +} +module_init( kalmia_init); + +static void __exit kalmia_exit(void) +{ + usb_deregister(&kalmia_driver); +} +module_exit( kalmia_exit); + +MODULE_AUTHOR("Marius Bjoernstad Kotsbak <marius@kotsbak.com>"); +MODULE_DESCRIPTION("Samsung Kalmia USB network driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index e050bd65e03..777d1a4e81b 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -2203,8 +2203,10 @@ fst_open(struct net_device *dev) if (port->mode != FST_RAW) { err = hdlc_open(dev); - if (err) + if (err) { + module_put(THIS_MODULE); return err; + } } fst_openport(port); diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index 660831ce293..687c1f22349 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -1288,6 +1288,8 @@ int mwifiex_register_cfg80211(struct net_device *dev, u8 *mac, *(unsigned long *) wdev_priv = (unsigned long) priv; + set_wiphy_dev(wdev->wiphy, (struct device *) priv->adapter->dev); + ret = wiphy_register(wdev->wiphy); if (ret < 0) { dev_err(priv->adapter->dev, "%s: registering cfg80211 device\n", diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 32261189bce..aeac3cc4dbe 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -2474,6 +2474,7 @@ struct mwl8k_cmd_set_hw_spec { * faster client. */ #define MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY 0x00000400 +#define MWL8K_SET_HW_SPEC_FLAG_GENERATE_CCMP_HDR 0x00000200 #define MWL8K_SET_HW_SPEC_FLAG_HOST_DECR_MGMT 0x00000080 #define MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_PROBERESP 0x00000020 #define MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_BEACON 0x00000010 @@ -2510,7 +2511,8 @@ static int mwl8k_cmd_set_hw_spec(struct ieee80211_hw *hw) cmd->flags = cpu_to_le32(MWL8K_SET_HW_SPEC_FLAG_HOST_DECR_MGMT | MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_PROBERESP | MWL8K_SET_HW_SPEC_FLAG_HOSTFORM_BEACON | - MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY); + MWL8K_SET_HW_SPEC_FLAG_ENABLE_LIFE_TIME_EXPIRY | + MWL8K_SET_HW_SPEC_FLAG_GENERATE_CCMP_HDR); cmd->num_tx_desc_per_queue = cpu_to_le32(MWL8K_TX_DESCS); cmd->total_rxd = cpu_to_le32(MWL8K_RX_DESCS); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 135df164a4c..46767c53917 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -624,7 +624,7 @@ static int pci_pm_prepare(struct device *dev) * system from the sleep state, we'll have to prevent it from signaling * wake-up. */ - pm_runtime_resume(dev); + pm_runtime_get_sync(dev); if (drv && drv->pm && drv->pm->prepare) error = drv->pm->prepare(dev); @@ -638,6 +638,8 @@ static void pci_pm_complete(struct device *dev) if (drv && drv->pm && drv->pm->complete) drv->pm->complete(dev); + + pm_runtime_put_sync(dev); } #else /* !CONFIG_PM_SLEEP */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 5f10c23dff9..2c5b9b99127 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3284,7 +3284,7 @@ static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode, * @dev: the PCI device * @decode: true = enable decoding, false = disable decoding * @command_bits: PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY - * @change_bridge_flags: traverse ancestors and change bridges + * @flags: traverse ancestors and change bridges * CHANGE_BRIDGE_ONLY / CHANGE_BRIDGE */ int pci_set_vga_state(struct pci_dev *dev, bool decode, diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 48849ffdd67..bafb3c3d4a8 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -168,7 +168,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->flags |= pci_calc_resource_flags(l) | IORESOURCE_SIZEALIGN; if (type == pci_bar_io) { l &= PCI_BASE_ADDRESS_IO_MASK; - mask = PCI_BASE_ADDRESS_IO_MASK & IO_SPACE_LIMIT; + mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT; } else { l &= PCI_BASE_ADDRESS_MEM_MASK; mask = (u32)PCI_BASE_ADDRESS_MEM_MASK; diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c index b8bc862903a..efd6066b5cd 100644 --- a/drivers/rtc/rtc-vt8500.c +++ b/drivers/rtc/rtc-vt8500.c @@ -78,7 +78,6 @@ struct vt8500_rtc { void __iomem *regbase; struct resource *res; int irq_alarm; - int irq_hz; struct rtc_device *rtc; spinlock_t lock; /* Protects this structure */ }; @@ -100,10 +99,6 @@ static irqreturn_t vt8500_rtc_irq(int irq, void *dev_id) if (isr & 1) events |= RTC_AF | RTC_IRQF; - /* Only second/minute interrupts are supported */ - if (isr & 2) - events |= RTC_UF | RTC_IRQF; - rtc_update_irq(vt8500_rtc->rtc, 1, events); return IRQ_HANDLED; @@ -199,27 +194,12 @@ static int vt8500_alarm_irq_enable(struct device *dev, unsigned int enabled) return 0; } -static int vt8500_update_irq_enable(struct device *dev, unsigned int enabled) -{ - struct vt8500_rtc *vt8500_rtc = dev_get_drvdata(dev); - unsigned long tmp = readl(vt8500_rtc->regbase + VT8500_RTC_CR); - - if (enabled) - tmp |= VT8500_RTC_CR_SM_SEC | VT8500_RTC_CR_SM_ENABLE; - else - tmp &= ~VT8500_RTC_CR_SM_ENABLE; - - writel(tmp, vt8500_rtc->regbase + VT8500_RTC_CR); - return 0; -} - static const struct rtc_class_ops vt8500_rtc_ops = { .read_time = vt8500_rtc_read_time, .set_time = vt8500_rtc_set_time, .read_alarm = vt8500_rtc_read_alarm, .set_alarm = vt8500_rtc_set_alarm, .alarm_irq_enable = vt8500_alarm_irq_enable, - .update_irq_enable = vt8500_update_irq_enable, }; static int __devinit vt8500_rtc_probe(struct platform_device *pdev) @@ -248,13 +228,6 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev) goto err_free; } - vt8500_rtc->irq_hz = platform_get_irq(pdev, 1); - if (vt8500_rtc->irq_hz < 0) { - dev_err(&pdev->dev, "No 1Hz IRQ resource defined\n"); - ret = -ENXIO; - goto err_free; - } - vt8500_rtc->res = request_mem_region(vt8500_rtc->res->start, resource_size(vt8500_rtc->res), "vt8500-rtc"); @@ -272,9 +245,8 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev) goto err_release; } - /* Enable the second/minute interrupt generation and enable RTC */ - writel(VT8500_RTC_CR_ENABLE | VT8500_RTC_CR_24H - | VT8500_RTC_CR_SM_ENABLE | VT8500_RTC_CR_SM_SEC, + /* Enable RTC and set it to 24-hour mode */ + writel(VT8500_RTC_CR_ENABLE | VT8500_RTC_CR_24H, vt8500_rtc->regbase + VT8500_RTC_CR); vt8500_rtc->rtc = rtc_device_register("vt8500-rtc", &pdev->dev, @@ -286,26 +258,16 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev) goto err_unmap; } - ret = request_irq(vt8500_rtc->irq_hz, vt8500_rtc_irq, 0, - "rtc 1Hz", vt8500_rtc); - if (ret < 0) { - dev_err(&pdev->dev, "can't get irq %i, err %d\n", - vt8500_rtc->irq_hz, ret); - goto err_unreg; - } - ret = request_irq(vt8500_rtc->irq_alarm, vt8500_rtc_irq, 0, "rtc alarm", vt8500_rtc); if (ret < 0) { dev_err(&pdev->dev, "can't get irq %i, err %d\n", vt8500_rtc->irq_alarm, ret); - goto err_free_hz; + goto err_unreg; } return 0; -err_free_hz: - free_irq(vt8500_rtc->irq_hz, vt8500_rtc); err_unreg: rtc_device_unregister(vt8500_rtc->rtc); err_unmap: @@ -323,7 +285,6 @@ static int __devexit vt8500_rtc_remove(struct platform_device *pdev) struct vt8500_rtc *vt8500_rtc = platform_get_drvdata(pdev); free_irq(vt8500_rtc->irq_alarm, vt8500_rtc); - free_irq(vt8500_rtc->irq_hz, vt8500_rtc); rtc_device_unregister(vt8500_rtc->rtc); diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index dee2a2c909f..70c2e7fa666 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -386,7 +386,7 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc) */ se_cmd->se_tmr_req = core_tmr_alloc_req(se_cmd, (void *)tl_tmr, TMR_LUN_RESET); - if (!se_cmd->se_tmr_req) + if (IS_ERR(se_cmd->se_tmr_req)) goto release; /* * Locate the underlying TCM struct se_lun from sc->device->lun @@ -1017,6 +1017,7 @@ static int tcm_loop_make_nexus( struct se_portal_group *se_tpg; struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba; struct tcm_loop_nexus *tl_nexus; + int ret = -ENOMEM; if (tl_tpg->tl_hba->tl_nexus) { printk(KERN_INFO "tl_tpg->tl_hba->tl_nexus already exists\n"); @@ -1033,8 +1034,10 @@ static int tcm_loop_make_nexus( * Initialize the struct se_session pointer */ tl_nexus->se_sess = transport_init_session(); - if (!tl_nexus->se_sess) + if (IS_ERR(tl_nexus->se_sess)) { + ret = PTR_ERR(tl_nexus->se_sess); goto out; + } /* * Since we are running in 'demo mode' this call with generate a * struct se_node_acl for the tcm_loop struct se_portal_group with the SCSI @@ -1060,7 +1063,7 @@ static int tcm_loop_make_nexus( out: kfree(tl_nexus); - return -ENOMEM; + return ret; } static int tcm_loop_drop_nexus( @@ -1140,7 +1143,7 @@ static ssize_t tcm_loop_tpg_store_nexus( * the fabric protocol_id set in tcm_loop_make_scsi_hba(), and call * tcm_loop_make_nexus() */ - if (strlen(page) > TL_WWN_ADDR_LEN) { + if (strlen(page) >= TL_WWN_ADDR_LEN) { printk(KERN_ERR "Emulated NAA Sas Address: %s, exceeds" " max: %d\n", page, TL_WWN_ADDR_LEN); return -EINVAL; @@ -1321,7 +1324,7 @@ struct se_wwn *tcm_loop_make_scsi_hba( return ERR_PTR(-EINVAL); check_len: - if (strlen(name) > TL_WWN_ADDR_LEN) { + if (strlen(name) >= TL_WWN_ADDR_LEN) { printk(KERN_ERR "Emulated NAA %s Address: %s, exceeds" " max: %d\n", name, tcm_loop_dump_proto_id(tl_hba), TL_WWN_ADDR_LEN); diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index ee6fad979b5..25c1f49a7d8 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -304,7 +304,7 @@ struct target_fabric_configfs *target_fabric_configfs_init( printk(KERN_ERR "Unable to locate passed fabric name\n"); return NULL; } - if (strlen(name) > TARGET_FABRIC_NAME_SIZE) { + if (strlen(name) >= TARGET_FABRIC_NAME_SIZE) { printk(KERN_ERR "Passed name: %s exceeds TARGET_FABRIC" "_NAME_SIZE\n", name); return NULL; @@ -312,7 +312,7 @@ struct target_fabric_configfs *target_fabric_configfs_init( tf = kzalloc(sizeof(struct target_fabric_configfs), GFP_KERNEL); if (!(tf)) - return ERR_PTR(-ENOMEM); + return NULL; INIT_LIST_HEAD(&tf->tf_list); atomic_set(&tf->tf_access_cnt, 0); @@ -851,7 +851,7 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial( return -EOPNOTSUPP; } - if ((strlen(page) + 1) > INQUIRY_VPD_SERIAL_LEN) { + if (strlen(page) >= INQUIRY_VPD_SERIAL_LEN) { printk(KERN_ERR "Emulated VPD Unit Serial exceeds" " INQUIRY_VPD_SERIAL_LEN: %d\n", INQUIRY_VPD_SERIAL_LEN); return -EOVERFLOW; @@ -917,7 +917,7 @@ static ssize_t target_core_dev_wwn_show_attr_vpd_protocol_identifier( transport_dump_vpd_proto_id(vpd, buf, VPD_TMP_BUF_SIZE); - if ((len + strlen(buf) > PAGE_SIZE)) + if ((len + strlen(buf) >= PAGE_SIZE)) break; len += sprintf(page+len, "%s", buf); @@ -962,19 +962,19 @@ static ssize_t target_core_dev_wwn_show_attr_##_name( \ \ memset(buf, 0, VPD_TMP_BUF_SIZE); \ transport_dump_vpd_assoc(vpd, buf, VPD_TMP_BUF_SIZE); \ - if ((len + strlen(buf) > PAGE_SIZE)) \ + if ((len + strlen(buf) >= PAGE_SIZE)) \ break; \ len += sprintf(page+len, "%s", buf); \ \ memset(buf, 0, VPD_TMP_BUF_SIZE); \ transport_dump_vpd_ident_type(vpd, buf, VPD_TMP_BUF_SIZE); \ - if ((len + strlen(buf) > PAGE_SIZE)) \ + if ((len + strlen(buf) >= PAGE_SIZE)) \ break; \ len += sprintf(page+len, "%s", buf); \ \ memset(buf, 0, VPD_TMP_BUF_SIZE); \ transport_dump_vpd_ident(vpd, buf, VPD_TMP_BUF_SIZE); \ - if ((len + strlen(buf) > PAGE_SIZE)) \ + if ((len + strlen(buf) >= PAGE_SIZE)) \ break; \ len += sprintf(page+len, "%s", buf); \ } \ @@ -1299,7 +1299,7 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts( &i_buf[0] : "", pr_reg->pr_res_key, pr_reg->pr_res_generation); - if ((len + strlen(buf) > PAGE_SIZE)) + if ((len + strlen(buf) >= PAGE_SIZE)) break; len += sprintf(page+len, "%s", buf); @@ -1496,7 +1496,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( ret = -ENOMEM; goto out; } - if (strlen(i_port) > PR_APTPL_MAX_IPORT_LEN) { + if (strlen(i_port) >= PR_APTPL_MAX_IPORT_LEN) { printk(KERN_ERR "APTPL metadata initiator_node=" " exceeds PR_APTPL_MAX_IPORT_LEN: %d\n", PR_APTPL_MAX_IPORT_LEN); @@ -1510,7 +1510,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( ret = -ENOMEM; goto out; } - if (strlen(isid) > PR_REG_ISID_LEN) { + if (strlen(isid) >= PR_REG_ISID_LEN) { printk(KERN_ERR "APTPL metadata initiator_isid" "= exceeds PR_REG_ISID_LEN: %d\n", PR_REG_ISID_LEN); @@ -1571,7 +1571,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( ret = -ENOMEM; goto out; } - if (strlen(t_port) > PR_APTPL_MAX_TPORT_LEN) { + if (strlen(t_port) >= PR_APTPL_MAX_TPORT_LEN) { printk(KERN_ERR "APTPL metadata target_node=" " exceeds PR_APTPL_MAX_TPORT_LEN: %d\n", PR_APTPL_MAX_TPORT_LEN); @@ -3052,7 +3052,7 @@ static struct config_group *target_core_call_addhbatotarget( int ret; memset(buf, 0, TARGET_CORE_NAME_MAX_LEN); - if (strlen(name) > TARGET_CORE_NAME_MAX_LEN) { + if (strlen(name) >= TARGET_CORE_NAME_MAX_LEN) { printk(KERN_ERR "Passed *name strlen(): %d exceeds" " TARGET_CORE_NAME_MAX_LEN: %d\n", (int)strlen(name), TARGET_CORE_NAME_MAX_LEN); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 8407f9ca2b3..ba698ea62bb 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -192,7 +192,7 @@ int transport_get_lun_for_tmr( &SE_NODE_ACL(se_sess)->device_list[unpacked_lun]; if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) { se_lun = se_cmd->se_lun = se_tmr->tmr_lun = deve->se_lun; - dev = se_tmr->tmr_dev = se_lun->lun_se_dev; + dev = se_lun->lun_se_dev; se_cmd->pr_res_key = deve->pr_res_key; se_cmd->orig_fe_lun = unpacked_lun; se_cmd->se_orig_obj_ptr = SE_LUN(se_cmd)->lun_se_dev; @@ -216,6 +216,7 @@ int transport_get_lun_for_tmr( se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; return -1; } + se_tmr->tmr_dev = dev; spin_lock(&dev->se_tmr_lock); list_add_tail(&se_tmr->tmr_list, &dev->dev_tmr_list); @@ -1430,7 +1431,7 @@ struct se_lun_acl *core_dev_init_initiator_node_lun_acl( struct se_lun_acl *lacl; struct se_node_acl *nacl; - if (strlen(initiatorname) > TRANSPORT_IQN_LEN) { + if (strlen(initiatorname) >= TRANSPORT_IQN_LEN) { printk(KERN_ERR "%s InitiatorName exceeds maximum size.\n", TPG_TFO(tpg)->get_fabric_name()); *ret = -EOVERFLOW; diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index a79f518ca6e..b662db3a320 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -1916,7 +1916,7 @@ static int __core_scsi3_update_aptpl_buf( pr_reg->pr_res_mapped_lun); } - if ((len + strlen(tmp) > pr_aptpl_buf_len)) { + if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { printk(KERN_ERR "Unable to update renaming" " APTPL metadata\n"); spin_unlock(&T10_RES(su_dev)->registration_lock); @@ -1934,7 +1934,7 @@ static int __core_scsi3_update_aptpl_buf( TPG_TFO(tpg)->tpg_get_tag(tpg), lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count); - if ((len + strlen(tmp) > pr_aptpl_buf_len)) { + if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { printk(KERN_ERR "Unable to update renaming" " APTPL metadata\n"); spin_unlock(&T10_RES(su_dev)->registration_lock); @@ -1986,7 +1986,7 @@ static int __core_scsi3_write_aptpl_to_file( memset(iov, 0, sizeof(struct iovec)); memset(path, 0, 512); - if (strlen(&wwn->unit_serial[0]) > 512) { + if (strlen(&wwn->unit_serial[0]) >= 512) { printk(KERN_ERR "WWN value for struct se_device does not fit" " into path buffer\n"); return -1; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 59b8b9c5ad7..179063d81cd 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -75,10 +75,16 @@ void core_tmr_release_req( { struct se_device *dev = tmr->tmr_dev; + if (!dev) { + kmem_cache_free(se_tmr_req_cache, tmr); + return; + } + spin_lock(&dev->se_tmr_lock); list_del(&tmr->tmr_list); - kmem_cache_free(se_tmr_req_cache, tmr); spin_unlock(&dev->se_tmr_lock); + + kmem_cache_free(se_tmr_req_cache, tmr); } static void core_tmr_handle_tas_abort( diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 4dafeb8b563..4b9b7169bdd 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -536,13 +536,13 @@ EXPORT_SYMBOL(transport_register_session); void transport_deregister_session_configfs(struct se_session *se_sess) { struct se_node_acl *se_nacl; - + unsigned long flags; /* * Used by struct se_node_acl's under ConfigFS to locate active struct se_session */ se_nacl = se_sess->se_node_acl; if ((se_nacl)) { - spin_lock_irq(&se_nacl->nacl_sess_lock); + spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags); list_del(&se_sess->sess_acl_list); /* * If the session list is empty, then clear the pointer. @@ -556,7 +556,7 @@ void transport_deregister_session_configfs(struct se_session *se_sess) se_nacl->acl_sess_list.prev, struct se_session, sess_acl_list); } - spin_unlock_irq(&se_nacl->nacl_sess_lock); + spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags); } } EXPORT_SYMBOL(transport_deregister_session_configfs); diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h index defff32b788..7b82f1b7fef 100644 --- a/drivers/target/tcm_fc/tcm_fc.h +++ b/drivers/target/tcm_fc/tcm_fc.h @@ -144,7 +144,7 @@ enum ft_cmd_state { */ struct ft_cmd { enum ft_cmd_state state; - u16 lun; /* LUN from request */ + u32 lun; /* LUN from request */ struct ft_sess *sess; /* session held for cmd */ struct fc_seq *seq; /* sequence in exchange mgr */ struct se_cmd se_cmd; /* Local TCM I/O descriptor */ diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index c056a1132ae..b2a106729d4 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -94,29 +94,6 @@ void ft_dump_cmd(struct ft_cmd *cmd, const char *caller) 16, 4, cmd->cdb, MAX_COMMAND_SIZE, 0); } -/* - * Get LUN from CDB. - */ -static int ft_get_lun_for_cmd(struct ft_cmd *cmd, u8 *lunp) -{ - u64 lun; - - lun = lunp[1]; - switch (lunp[0] >> 6) { - case 0: - break; - case 1: - lun |= (lunp[0] & 0x3f) << 8; - break; - default: - return -1; - } - if (lun >= TRANSPORT_MAX_LUNS_PER_TPG) - return -1; - cmd->lun = lun; - return transport_get_lun_for_cmd(&cmd->se_cmd, NULL, lun); -} - static void ft_queue_cmd(struct ft_sess *sess, struct ft_cmd *cmd) { struct se_queue_obj *qobj; @@ -418,6 +395,7 @@ static void ft_send_tm(struct ft_cmd *cmd) { struct se_tmr_req *tmr; struct fcp_cmnd *fcp; + struct ft_sess *sess; u8 tm_func; fcp = fc_frame_payload_get(cmd->req_frame, sizeof(*fcp)); @@ -425,13 +403,6 @@ static void ft_send_tm(struct ft_cmd *cmd) switch (fcp->fc_tm_flags) { case FCP_TMF_LUN_RESET: tm_func = TMR_LUN_RESET; - if (ft_get_lun_for_cmd(cmd, fcp->fc_lun) < 0) { - ft_dump_cmd(cmd, __func__); - transport_send_check_condition_and_sense(&cmd->se_cmd, - cmd->se_cmd.scsi_sense_reason, 0); - ft_sess_put(cmd->sess); - return; - } break; case FCP_TMF_TGT_RESET: tm_func = TMR_TARGET_WARM_RESET; @@ -463,6 +434,36 @@ static void ft_send_tm(struct ft_cmd *cmd) return; } cmd->se_cmd.se_tmr_req = tmr; + + switch (fcp->fc_tm_flags) { + case FCP_TMF_LUN_RESET: + cmd->lun = scsilun_to_int((struct scsi_lun *)fcp->fc_lun); + if (transport_get_lun_for_tmr(&cmd->se_cmd, cmd->lun) < 0) { + /* + * Make sure to clean up newly allocated TMR request + * since "unable to handle TMR request because failed + * to get to LUN" + */ + FT_TM_DBG("Failed to get LUN for TMR func %d, " + "se_cmd %p, unpacked_lun %d\n", + tm_func, &cmd->se_cmd, cmd->lun); + ft_dump_cmd(cmd, __func__); + sess = cmd->sess; + transport_send_check_condition_and_sense(&cmd->se_cmd, + cmd->se_cmd.scsi_sense_reason, 0); + transport_generic_free_cmd(&cmd->se_cmd, 0, 1, 0); + ft_sess_put(sess); + return; + } + break; + case FCP_TMF_TGT_RESET: + case FCP_TMF_CLR_TASK_SET: + case FCP_TMF_ABT_TASK_SET: + case FCP_TMF_CLR_ACA: + break; + default: + return; + } transport_generic_handle_tmr(&cmd->se_cmd); } @@ -635,7 +636,8 @@ static void ft_send_cmd(struct ft_cmd *cmd) fc_seq_exch(cmd->seq)->lp->tt.seq_set_resp(cmd->seq, ft_recv_seq, cmd); - ret = ft_get_lun_for_cmd(cmd, fcp->fc_lun); + cmd->lun = scsilun_to_int((struct scsi_lun *)fcp->fc_lun); + ret = transport_get_lun_for_cmd(&cmd->se_cmd, NULL, cmd->lun); if (ret < 0) { ft_dump_cmd(cmd, __func__); transport_send_check_condition_and_sense(&cmd->se_cmd, diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index 4c3c0efbe13..8c4a24077d9 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -203,7 +203,7 @@ int ft_queue_data_in(struct se_cmd *se_cmd) /* XXX For now, initiator will retry */ if (printk_ratelimit()) printk(KERN_ERR "%s: Failed to send frame %p, " - "xid <0x%x>, remaining <0x%x>, " + "xid <0x%x>, remaining %zu, " "lso_max <0x%x>\n", __func__, fp, ep->xid, remaining, lport->lso_max); diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index a3bd57f2ea3..7491e21cc6a 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -229,7 +229,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id, return NULL; sess->se_sess = transport_init_session(); - if (!sess->se_sess) { + if (IS_ERR(sess->se_sess)) { kfree(sess); return NULL; } @@ -332,7 +332,7 @@ void ft_sess_close(struct se_session *se_sess) lport = sess->tport->lport; port_id = sess->port_id; if (port_id == -1) { - mutex_lock(&ft_lport_lock); + mutex_unlock(&ft_lport_lock); return; } FT_SESS_DBG("port_id %x\n", port_id); diff --git a/drivers/tty/serial/mrst_max3110.c b/drivers/tty/serial/mrst_max3110.c index 1bd28450ca4..a764bf99743 100644 --- a/drivers/tty/serial/mrst_max3110.c +++ b/drivers/tty/serial/mrst_max3110.c @@ -421,7 +421,6 @@ static int max3110_main_thread(void *_max) int ret = 0; struct circ_buf *xmit = &max->con_xmit; - init_waitqueue_head(wq); pr_info(PR_FMT "start main thread\n"); do { @@ -823,7 +822,7 @@ static int __devinit serial_m3110_probe(struct spi_device *spi) res = RC_TAG; ret = max3110_write_then_read(max, (u8 *)&res, (u8 *)&res, 2, 0); if (ret < 0 || res == 0 || res == 0xffff) { - printk(KERN_ERR "MAX3111 deemed not present (conf reg %04x)", + dev_dbg(&spi->dev, "MAX3111 deemed not present (conf reg %04x)", res); ret = -ENODEV; goto err_get_page; @@ -838,6 +837,8 @@ static int __devinit serial_m3110_probe(struct spi_device *spi) max->con_xmit.head = 0; max->con_xmit.tail = 0; + init_waitqueue_head(&max->wq); + max->main_thread = kthread_run(max3110_main_thread, max, "max3110_main"); if (IS_ERR(max->main_thread)) { diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index e35a17687c0..aa3cc465a60 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -375,7 +375,7 @@ static int usb_unbind_interface(struct device *dev) * Just re-enable it without affecting the endpoint toggles. */ usb_enable_interface(udev, intf, false); - } else if (!error && !intf->dev.power.in_suspend) { + } else if (!error && !intf->dev.power.is_prepared) { r = usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); if (r < 0) @@ -960,7 +960,7 @@ void usb_rebind_intf(struct usb_interface *intf) } /* Try to rebind the interface */ - if (!intf->dev.power.in_suspend) { + if (!intf->dev.power.is_prepared) { intf->needs_binding = 0; rc = device_attach(&intf->dev); if (rc < 0) @@ -1107,7 +1107,7 @@ static int usb_resume_interface(struct usb_device *udev, if (intf->condition == USB_INTERFACE_UNBOUND) { /* Carry out a deferred switch to altsetting 0 */ - if (intf->needs_altsetting0 && !intf->dev.power.in_suspend) { + if (intf->needs_altsetting0 && !intf->dev.power.is_prepared) { usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); intf->needs_altsetting0 = 0; diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 553da68bd51..30df85d8fca 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -395,9 +395,9 @@ static void unmask_evtchn(int port) static void xen_irq_init(unsigned irq) { struct irq_info *info; +#ifdef CONFIG_SMP struct irq_desc *desc = irq_to_desc(irq); -#ifdef CONFIG_SMP /* By default all event channels notify CPU#0. */ cpumask_copy(desc->irq_data.affinity, cpumask_of(0)); #endif diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 9ad2369d9e3..bfcb18feb1d 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -231,9 +231,6 @@ static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, static int bad_inode_permission(struct inode *inode, int mask, unsigned int flags) { - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - return -EIO; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 1a2421f908f..610e8e0b04b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -762,7 +762,19 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, if (!disk) return ERR_PTR(-ENXIO); - whole = bdget_disk(disk, 0); + /* + * Normally, @bdev should equal what's returned from bdget_disk() + * if partno is 0; however, some drivers (floppy) use multiple + * bdev's for the same physical device and @bdev may be one of the + * aliases. Keep @bdev if partno is 0. This means claimer + * tracking is broken for those devices but it has always been that + * way. + */ + if (partno) + whole = bdget_disk(disk, 0); + else + whole = bdgrab(bdev); + module_put(disk->fops->owner); put_disk(disk); if (!whole) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 378b5b4443f..f30ac05dbda 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -19,7 +19,6 @@ #ifndef __BTRFS_CTREE__ #define __BTRFS_CTREE__ -#include <linux/version.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/fs.h> @@ -967,6 +966,12 @@ struct btrfs_fs_info { struct srcu_struct subvol_srcu; spinlock_t trans_lock; + /* + * the reloc mutex goes with the trans lock, it is taken + * during commit to protect us from the relocation code + */ + struct mutex reloc_mutex; + struct list_head trans_list; struct list_head hashers; struct list_head dead_roots; @@ -1172,6 +1177,14 @@ struct btrfs_root { u32 type; u64 highest_objectid; + + /* btrfs_record_root_in_trans is a multi-step process, + * and it can race with the balancing code. But the + * race is very small, and only the first time the root + * is added to each transaction. So in_trans_setup + * is used to tell us when more checks are required + */ + unsigned long in_trans_setup; int ref_cows; int track_dirty; int in_radix; @@ -1181,7 +1194,6 @@ struct btrfs_root { struct btrfs_key defrag_max; int defrag_running; char *name; - int in_sysfs; /* the dirty list is only used by non-reference counted roots */ struct list_head dirty_list; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 6462c29d2d3..98c68e658a9 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -82,19 +82,16 @@ static inline struct btrfs_delayed_root *btrfs_get_delayed_root( return root->fs_info->delayed_root; } -static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( - struct inode *inode) +static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode) { - struct btrfs_delayed_node *node; struct btrfs_inode *btrfs_inode = BTRFS_I(inode); struct btrfs_root *root = btrfs_inode->root; u64 ino = btrfs_ino(inode); - int ret; + struct btrfs_delayed_node *node; -again: node = ACCESS_ONCE(btrfs_inode->delayed_node); if (node) { - atomic_inc(&node->refs); /* can be accessed */ + atomic_inc(&node->refs); return node; } @@ -102,8 +99,10 @@ again: node = radix_tree_lookup(&root->delayed_nodes_tree, ino); if (node) { if (btrfs_inode->delayed_node) { + atomic_inc(&node->refs); /* can be accessed */ + BUG_ON(btrfs_inode->delayed_node != node); spin_unlock(&root->inode_lock); - goto again; + return node; } btrfs_inode->delayed_node = node; atomic_inc(&node->refs); /* can be accessed */ @@ -113,6 +112,23 @@ again: } spin_unlock(&root->inode_lock); + return NULL; +} + +static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( + struct inode *inode) +{ + struct btrfs_delayed_node *node; + struct btrfs_inode *btrfs_inode = BTRFS_I(inode); + struct btrfs_root *root = btrfs_inode->root; + u64 ino = btrfs_ino(inode); + int ret; + +again: + node = btrfs_get_delayed_node(inode); + if (node) + return node; + node = kmem_cache_alloc(delayed_node_cache, GFP_NOFS); if (!node) return ERR_PTR(-ENOMEM); @@ -297,7 +313,6 @@ struct btrfs_delayed_item *btrfs_alloc_delayed_item(u32 data_len) item->data_len = data_len; item->ins_or_del = 0; item->bytes_reserved = 0; - item->block_rsv = NULL; item->delayed_node = NULL; atomic_set(&item->refs, 1); } @@ -549,19 +564,6 @@ struct btrfs_delayed_item *__btrfs_next_delayed_item( return next; } -static inline struct btrfs_delayed_node *btrfs_get_delayed_node( - struct inode *inode) -{ - struct btrfs_inode *btrfs_inode = BTRFS_I(inode); - struct btrfs_delayed_node *delayed_node; - - delayed_node = btrfs_inode->delayed_node; - if (delayed_node) - atomic_inc(&delayed_node->refs); - - return delayed_node; -} - static inline struct btrfs_root *btrfs_get_fs_root(struct btrfs_root *root, u64 root_id) { @@ -593,10 +595,8 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans, num_bytes = btrfs_calc_trans_metadata_size(root, 1); ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); - if (!ret) { + if (!ret) item->bytes_reserved = num_bytes; - item->block_rsv = dst_rsv; - } return ret; } @@ -604,10 +604,13 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans, static void btrfs_delayed_item_release_metadata(struct btrfs_root *root, struct btrfs_delayed_item *item) { + struct btrfs_block_rsv *rsv; + if (!item->bytes_reserved) return; - btrfs_block_rsv_release(root, item->block_rsv, + rsv = &root->fs_info->global_block_rsv; + btrfs_block_rsv_release(root, rsv, item->bytes_reserved); } @@ -1014,6 +1017,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, struct btrfs_delayed_root *delayed_root; struct btrfs_delayed_node *curr_node, *prev_node; struct btrfs_path *path; + struct btrfs_block_rsv *block_rsv; int ret = 0; path = btrfs_alloc_path(); @@ -1021,6 +1025,9 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->leave_spinning = 1; + block_rsv = trans->block_rsv; + trans->block_rsv = &root->fs_info->global_block_rsv; + delayed_root = btrfs_get_delayed_root(root); curr_node = btrfs_first_delayed_node(delayed_root); @@ -1045,6 +1052,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, } btrfs_free_path(path); + trans->block_rsv = block_rsv; return ret; } @@ -1052,6 +1060,7 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, struct btrfs_delayed_node *node) { struct btrfs_path *path; + struct btrfs_block_rsv *block_rsv; int ret; path = btrfs_alloc_path(); @@ -1059,6 +1068,9 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, return -ENOMEM; path->leave_spinning = 1; + block_rsv = trans->block_rsv; + trans->block_rsv = &node->root->fs_info->global_block_rsv; + ret = btrfs_insert_delayed_items(trans, path, node->root, node); if (!ret) ret = btrfs_delete_delayed_items(trans, path, node->root, node); @@ -1066,6 +1078,7 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, ret = btrfs_update_delayed_inode(trans, node->root, path, node); btrfs_free_path(path); + trans->block_rsv = block_rsv; return ret; } @@ -1116,6 +1129,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) struct btrfs_path *path; struct btrfs_delayed_node *delayed_node = NULL; struct btrfs_root *root; + struct btrfs_block_rsv *block_rsv; unsigned long nr = 0; int need_requeue = 0; int ret; @@ -1134,6 +1148,9 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) if (IS_ERR(trans)) goto free_path; + block_rsv = trans->block_rsv; + trans->block_rsv = &root->fs_info->global_block_rsv; + ret = btrfs_insert_delayed_items(trans, path, root, delayed_node); if (!ret) ret = btrfs_delete_delayed_items(trans, path, root, @@ -1176,6 +1193,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) nr = trans->blocks_used; + trans->block_rsv = block_rsv; btrfs_end_transaction_dmeta(trans, root); __btrfs_btree_balance_dirty(root, nr); free_path: @@ -1222,6 +1240,13 @@ again: return 0; } +void btrfs_assert_delayed_root_empty(struct btrfs_root *root) +{ + struct btrfs_delayed_root *delayed_root; + delayed_root = btrfs_get_delayed_root(root); + WARN_ON(btrfs_first_delayed_node(delayed_root)); +} + void btrfs_balance_delayed_items(struct btrfs_root *root) { struct btrfs_delayed_root *delayed_root; @@ -1382,8 +1407,7 @@ end: int btrfs_inode_delayed_dir_index_count(struct inode *inode) { - struct btrfs_delayed_node *delayed_node = BTRFS_I(inode)->delayed_node; - int ret = 0; + struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode); if (!delayed_node) return -ENOENT; @@ -1393,11 +1417,14 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode) * a new directory index is added into the delayed node and index_cnt * is updated now. So we needn't lock the delayed node. */ - if (!delayed_node->index_cnt) + if (!delayed_node->index_cnt) { + btrfs_release_delayed_node(delayed_node); return -EINVAL; + } BTRFS_I(inode)->index_cnt = delayed_node->index_cnt; - return ret; + btrfs_release_delayed_node(delayed_node); + return 0; } void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, @@ -1591,6 +1618,57 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, inode->i_ctime.tv_nsec); } +int btrfs_fill_inode(struct inode *inode, u32 *rdev) +{ + struct btrfs_delayed_node *delayed_node; + struct btrfs_inode_item *inode_item; + struct btrfs_timespec *tspec; + + delayed_node = btrfs_get_delayed_node(inode); + if (!delayed_node) + return -ENOENT; + + mutex_lock(&delayed_node->mutex); + if (!delayed_node->inode_dirty) { + mutex_unlock(&delayed_node->mutex); + btrfs_release_delayed_node(delayed_node); + return -ENOENT; + } + + inode_item = &delayed_node->inode_item; + + inode->i_uid = btrfs_stack_inode_uid(inode_item); + inode->i_gid = btrfs_stack_inode_gid(inode_item); + btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); + inode->i_mode = btrfs_stack_inode_mode(inode_item); + inode->i_nlink = btrfs_stack_inode_nlink(inode_item); + inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); + BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item); + BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item); + inode->i_rdev = 0; + *rdev = btrfs_stack_inode_rdev(inode_item); + BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item); + + tspec = btrfs_inode_atime(inode_item); + inode->i_atime.tv_sec = btrfs_stack_timespec_sec(tspec); + inode->i_atime.tv_nsec = btrfs_stack_timespec_nsec(tspec); + + tspec = btrfs_inode_mtime(inode_item); + inode->i_mtime.tv_sec = btrfs_stack_timespec_sec(tspec); + inode->i_mtime.tv_nsec = btrfs_stack_timespec_nsec(tspec); + + tspec = btrfs_inode_ctime(inode_item); + inode->i_ctime.tv_sec = btrfs_stack_timespec_sec(tspec); + inode->i_ctime.tv_nsec = btrfs_stack_timespec_nsec(tspec); + + inode->i_generation = BTRFS_I(inode)->generation; + BTRFS_I(inode)->index_cnt = (u64)-1; + + mutex_unlock(&delayed_node->mutex); + btrfs_release_delayed_node(delayed_node); + return 0; +} + int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode) { diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index eb7d240aa64..8d27af4bd8b 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -75,7 +75,6 @@ struct btrfs_delayed_item { struct list_head tree_list; /* used for batch insert/delete items */ struct list_head readdir_list; /* used for readdir items */ u64 bytes_reserved; - struct btrfs_block_rsv *block_rsv; struct btrfs_delayed_node *delayed_node; atomic_t refs; int ins_or_del; @@ -120,6 +119,7 @@ void btrfs_kill_delayed_inode_items(struct inode *inode); int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); +int btrfs_fill_inode(struct inode *inode, u32 *rdev); /* Used for drop dead root */ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root); @@ -138,4 +138,8 @@ int btrfs_readdir_delayed_dir_index(struct file *filp, void *dirent, /* for init */ int __init btrfs_delayed_inode_init(void); void btrfs_delayed_inode_exit(void); + +/* for debugging */ +void btrfs_assert_delayed_root_empty(struct btrfs_root *root); + #endif diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 9f68c689865..1ac8db5dc0a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1044,7 +1044,6 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, root->last_trans = 0; root->highest_objectid = 0; root->name = NULL; - root->in_sysfs = 0; root->inode_tree = RB_ROOT; INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); root->block_rsv = NULL; @@ -1300,19 +1299,21 @@ again: return root; root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS); - if (!root->free_ino_ctl) - goto fail; root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned), GFP_NOFS); - if (!root->free_ino_pinned) + if (!root->free_ino_pinned || !root->free_ino_ctl) { + ret = -ENOMEM; goto fail; + } btrfs_init_free_ino_ctl(root); mutex_init(&root->fs_commit_mutex); spin_lock_init(&root->cache_lock); init_waitqueue_head(&root->cache_wait); - set_anon_super(&root->anon_super, NULL); + ret = set_anon_super(&root->anon_super, NULL); + if (ret) + goto fail; if (btrfs_root_refs(&root->root_item) == 0) { ret = -ENOENT; @@ -1618,6 +1619,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); + mutex_init(&fs_info->reloc_mutex); init_completion(&fs_info->kobj_unregister); fs_info->tree_root = tree_root; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b42efc2ded5..71cd456fdb6 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3314,10 +3314,6 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, if (reserved == 0) return 0; - /* nothing to shrink - nothing to reclaim */ - if (root->fs_info->delalloc_bytes == 0) - return 0; - max_reclaim = min(reserved, to_reclaim); while (loops < 1024) { @@ -4846,7 +4842,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, u64 num_bytes, u64 empty_size, u64 search_start, u64 search_end, u64 hint_byte, struct btrfs_key *ins, - int data) + u64 data) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -4873,7 +4869,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, space_info = __find_space_info(root->fs_info, data); if (!space_info) { - printk(KERN_ERR "No space info for %d\n", data); + printk(KERN_ERR "No space info for %llu\n", data); return -ENOSPC; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 9f985a42987..bf0d61567f3 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1893,9 +1893,12 @@ void __btrfs_remove_free_space_cache_locked(struct btrfs_free_space_ctl *ctl) while ((node = rb_last(&ctl->free_space_offset)) != NULL) { info = rb_entry(node, struct btrfs_free_space, offset_index); - unlink_free_space(ctl, info); - kfree(info->bitmap); - kmem_cache_free(btrfs_free_space_cachep, info); + if (!info->bitmap) { + unlink_free_space(ctl, info); + kmem_cache_free(btrfs_free_space_cachep, info); + } else { + free_bitmap(ctl, info); + } if (need_resched()) { spin_unlock(&ctl->tree_lock); cond_resched(); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 751ddf8fc58..d340f63d8f0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2509,6 +2509,11 @@ static void btrfs_read_locked_inode(struct inode *inode) int maybe_acls; u32 rdev; int ret; + bool filled = false; + + ret = btrfs_fill_inode(inode, &rdev); + if (!ret) + filled = true; path = btrfs_alloc_path(); BUG_ON(!path); @@ -2520,6 +2525,10 @@ static void btrfs_read_locked_inode(struct inode *inode) goto make_bad; leaf = path->nodes[0]; + + if (filled) + goto cache_acl; + inode_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item); if (!leaf->map_token) @@ -2556,7 +2565,7 @@ static void btrfs_read_locked_inode(struct inode *inode) BTRFS_I(inode)->index_cnt = (u64)-1; BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item); - +cache_acl: /* * try to precache a NULL acl entry for files that don't have * any xattrs or acls @@ -2572,7 +2581,6 @@ static void btrfs_read_locked_inode(struct inode *inode) } btrfs_free_path(path); - inode_item = NULL; switch (inode->i_mode & S_IFMT) { case S_IFREG: @@ -3076,6 +3084,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, root, dir); BUG_ON(ret); + btrfs_free_path(path); return 0; } @@ -4519,6 +4528,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, inode_tree_add(inode); trace_btrfs_inode_new(inode); + btrfs_set_inode_last_trans(trans, inode); return inode; fail: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b793d112d1f..a3c4751e07d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -482,8 +482,10 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, ret = btrfs_snap_reserve_metadata(trans, pending_snapshot); BUG_ON(ret); + spin_lock(&root->fs_info->trans_lock); list_add(&pending_snapshot->list, &trans->transaction->pending_snapshots); + spin_unlock(&root->fs_info->trans_lock); if (async_transid) { *async_transid = trans->transid; ret = btrfs_commit_transaction_async(trans, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b1ef27cc673..5e0a3dc79a4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1368,7 +1368,7 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, int ret; if (!root->reloc_root) - return 0; + goto out; reloc_root = root->reloc_root; root_item = &reloc_root->root_item; @@ -1390,6 +1390,8 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, ret = btrfs_update_root(trans, root->fs_info->tree_root, &reloc_root->root_key, root_item); BUG_ON(ret); + +out: return 0; } @@ -2142,10 +2144,11 @@ int prepare_to_merge(struct reloc_control *rc, int err) u64 num_bytes = 0; int ret; - spin_lock(&root->fs_info->trans_lock); + mutex_lock(&root->fs_info->reloc_mutex); rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2; rc->merging_rsv_size += rc->nodes_relocated * 2; - spin_unlock(&root->fs_info->trans_lock); + mutex_unlock(&root->fs_info->reloc_mutex); + again: if (!err) { num_bytes = rc->merging_rsv_size; @@ -2214,9 +2217,16 @@ int merge_reloc_roots(struct reloc_control *rc) int ret; again: root = rc->extent_root; - spin_lock(&root->fs_info->trans_lock); + + /* + * this serializes us with btrfs_record_root_in_transaction, + * we have to make sure nobody is in the middle of + * adding their roots to the list while we are + * doing this splice + */ + mutex_lock(&root->fs_info->reloc_mutex); list_splice_init(&rc->reloc_roots, &reloc_roots); - spin_unlock(&root->fs_info->trans_lock); + mutex_unlock(&root->fs_info->reloc_mutex); while (!list_empty(&reloc_roots)) { found = 1; @@ -3590,17 +3600,19 @@ next: static void set_reloc_control(struct reloc_control *rc) { struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; - spin_lock(&fs_info->trans_lock); + + mutex_lock(&fs_info->reloc_mutex); fs_info->reloc_ctl = rc; - spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->reloc_mutex); } static void unset_reloc_control(struct reloc_control *rc) { struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; - spin_lock(&fs_info->trans_lock); + + mutex_lock(&fs_info->reloc_mutex); fs_info->reloc_ctl = NULL; - spin_unlock(&fs_info->trans_lock); + mutex_unlock(&fs_info->reloc_mutex); } static int check_extent_flags(u64 flags) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index c3c223ae669..daac9ae6d73 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -28,152 +28,6 @@ #include "disk-io.h" #include "transaction.h" -static ssize_t root_blocks_used_show(struct btrfs_root *root, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_root_used(&root->root_item)); -} - -static ssize_t root_block_limit_show(struct btrfs_root *root, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_root_limit(&root->root_item)); -} - -static ssize_t super_blocks_used_show(struct btrfs_fs_info *fs, char *buf) -{ - - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_super_bytes_used(&fs->super_copy)); -} - -static ssize_t super_total_blocks_show(struct btrfs_fs_info *fs, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_super_total_bytes(&fs->super_copy)); -} - -static ssize_t super_blocksize_show(struct btrfs_fs_info *fs, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)btrfs_super_sectorsize(&fs->super_copy)); -} - -/* this is for root attrs (subvols/snapshots) */ -struct btrfs_root_attr { - struct attribute attr; - ssize_t (*show)(struct btrfs_root *, char *); - ssize_t (*store)(struct btrfs_root *, const char *, size_t); -}; - -#define ROOT_ATTR(name, mode, show, store) \ -static struct btrfs_root_attr btrfs_root_attr_##name = __ATTR(name, mode, \ - show, store) - -ROOT_ATTR(blocks_used, 0444, root_blocks_used_show, NULL); -ROOT_ATTR(block_limit, 0644, root_block_limit_show, NULL); - -static struct attribute *btrfs_root_attrs[] = { - &btrfs_root_attr_blocks_used.attr, - &btrfs_root_attr_block_limit.attr, - NULL, -}; - -/* this is for super attrs (actual full fs) */ -struct btrfs_super_attr { - struct attribute attr; - ssize_t (*show)(struct btrfs_fs_info *, char *); - ssize_t (*store)(struct btrfs_fs_info *, const char *, size_t); -}; - -#define SUPER_ATTR(name, mode, show, store) \ -static struct btrfs_super_attr btrfs_super_attr_##name = __ATTR(name, mode, \ - show, store) - -SUPER_ATTR(blocks_used, 0444, super_blocks_used_show, NULL); -SUPER_ATTR(total_blocks, 0444, super_total_blocks_show, NULL); -SUPER_ATTR(blocksize, 0444, super_blocksize_show, NULL); - -static struct attribute *btrfs_super_attrs[] = { - &btrfs_super_attr_blocks_used.attr, - &btrfs_super_attr_total_blocks.attr, - &btrfs_super_attr_blocksize.attr, - NULL, -}; - -static ssize_t btrfs_super_attr_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info, - super_kobj); - struct btrfs_super_attr *a = container_of(attr, - struct btrfs_super_attr, - attr); - - return a->show ? a->show(fs, buf) : 0; -} - -static ssize_t btrfs_super_attr_store(struct kobject *kobj, - struct attribute *attr, - const char *buf, size_t len) -{ - struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info, - super_kobj); - struct btrfs_super_attr *a = container_of(attr, - struct btrfs_super_attr, - attr); - - return a->store ? a->store(fs, buf, len) : 0; -} - -static ssize_t btrfs_root_attr_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct btrfs_root *root = container_of(kobj, struct btrfs_root, - root_kobj); - struct btrfs_root_attr *a = container_of(attr, - struct btrfs_root_attr, - attr); - - return a->show ? a->show(root, buf) : 0; -} - -static ssize_t btrfs_root_attr_store(struct kobject *kobj, - struct attribute *attr, - const char *buf, size_t len) -{ - struct btrfs_root *root = container_of(kobj, struct btrfs_root, - root_kobj); - struct btrfs_root_attr *a = container_of(attr, - struct btrfs_root_attr, - attr); - return a->store ? a->store(root, buf, len) : 0; -} - -static void btrfs_super_release(struct kobject *kobj) -{ - struct btrfs_fs_info *fs = container_of(kobj, struct btrfs_fs_info, - super_kobj); - complete(&fs->kobj_unregister); -} - -static void btrfs_root_release(struct kobject *kobj) -{ - struct btrfs_root *root = container_of(kobj, struct btrfs_root, - root_kobj); - complete(&root->kobj_unregister); -} - -static const struct sysfs_ops btrfs_super_attr_ops = { - .show = btrfs_super_attr_show, - .store = btrfs_super_attr_store, -}; - -static const struct sysfs_ops btrfs_root_attr_ops = { - .show = btrfs_root_attr_show, - .store = btrfs_root_attr_store, -}; - /* /sys/fs/btrfs/ entry */ static struct kset *btrfs_kset; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 2b3590b9fe9..51dcec86757 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -126,28 +126,85 @@ static noinline int join_transaction(struct btrfs_root *root, int nofail) * to make sure the old root from before we joined the transaction is deleted * when the transaction commits */ -int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, +static int record_root_in_trans(struct btrfs_trans_handle *trans, struct btrfs_root *root) { if (root->ref_cows && root->last_trans < trans->transid) { WARN_ON(root == root->fs_info->extent_root); WARN_ON(root->commit_root != root->node); + /* + * see below for in_trans_setup usage rules + * we have the reloc mutex held now, so there + * is only one writer in this function + */ + root->in_trans_setup = 1; + + /* make sure readers find in_trans_setup before + * they find our root->last_trans update + */ + smp_wmb(); + spin_lock(&root->fs_info->fs_roots_radix_lock); if (root->last_trans == trans->transid) { spin_unlock(&root->fs_info->fs_roots_radix_lock); return 0; } - root->last_trans = trans->transid; radix_tree_tag_set(&root->fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); spin_unlock(&root->fs_info->fs_roots_radix_lock); + root->last_trans = trans->transid; + + /* this is pretty tricky. We don't want to + * take the relocation lock in btrfs_record_root_in_trans + * unless we're really doing the first setup for this root in + * this transaction. + * + * Normally we'd use root->last_trans as a flag to decide + * if we want to take the expensive mutex. + * + * But, we have to set root->last_trans before we + * init the relocation root, otherwise, we trip over warnings + * in ctree.c. The solution used here is to flag ourselves + * with root->in_trans_setup. When this is 1, we're still + * fixing up the reloc trees and everyone must wait. + * + * When this is zero, they can trust root->last_trans and fly + * through btrfs_record_root_in_trans without having to take the + * lock. smp_wmb() makes sure that all the writes above are + * done before we pop in the zero below + */ btrfs_init_reloc_root(trans, root); + smp_wmb(); + root->in_trans_setup = 0; } return 0; } + +int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + if (!root->ref_cows) + return 0; + + /* + * see record_root_in_trans for comments about in_trans_setup usage + * and barriers + */ + smp_rmb(); + if (root->last_trans == trans->transid && + !root->in_trans_setup) + return 0; + + mutex_lock(&root->fs_info->reloc_mutex); + record_root_in_trans(trans, root); + mutex_unlock(&root->fs_info->reloc_mutex); + + return 0; +} + /* wait for commit against the current transaction to become unblocked * when this is done, it is safe to start a new transaction, but the current * transaction might not be fully on disk. @@ -882,7 +939,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, parent = dget_parent(dentry); parent_inode = parent->d_inode; parent_root = BTRFS_I(parent_inode)->root; - btrfs_record_root_in_trans(trans, parent_root); + record_root_in_trans(trans, parent_root); /* * insert the directory item @@ -900,7 +957,16 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, parent_root, parent_inode); BUG_ON(ret); - btrfs_record_root_in_trans(trans, root); + /* + * pull in the delayed directory update + * and the delayed inode item + * otherwise we corrupt the FS during + * snapshot + */ + ret = btrfs_run_delayed_items(trans, root); + BUG_ON(ret); + + record_root_in_trans(trans, root); btrfs_set_root_last_snapshot(&root->root_item, trans->transid); memcpy(new_root_item, &root->root_item, sizeof(*new_root_item)); btrfs_check_and_init_root_item(new_root_item); @@ -961,14 +1027,6 @@ static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans, int ret; list_for_each_entry(pending, head, list) { - /* - * We must deal with the delayed items before creating - * snapshots, or we will create a snapthot with inconsistent - * information. - */ - ret = btrfs_run_delayed_items(trans, fs_info->fs_root); - BUG_ON(ret); - ret = create_pending_snapshot(trans, fs_info, pending); BUG_ON(ret); } @@ -1241,21 +1299,42 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, schedule_timeout(1); finish_wait(&cur_trans->writer_wait, &wait); - spin_lock(&root->fs_info->trans_lock); - root->fs_info->trans_no_join = 1; - spin_unlock(&root->fs_info->trans_lock); } while (atomic_read(&cur_trans->num_writers) > 1 || (should_grow && cur_trans->num_joined != joined)); - ret = create_pending_snapshots(trans, root->fs_info); - BUG_ON(ret); + /* + * Ok now we need to make sure to block out any other joins while we + * commit the transaction. We could have started a join before setting + * no_join so make sure to wait for num_writers to == 1 again. + */ + spin_lock(&root->fs_info->trans_lock); + root->fs_info->trans_no_join = 1; + spin_unlock(&root->fs_info->trans_lock); + wait_event(cur_trans->writer_wait, + atomic_read(&cur_trans->num_writers) == 1); + + /* + * the reloc mutex makes sure that we stop + * the balancing code from coming in and moving + * extents around in the middle of the commit + */ + mutex_lock(&root->fs_info->reloc_mutex); ret = btrfs_run_delayed_items(trans, root); BUG_ON(ret); + ret = create_pending_snapshots(trans, root->fs_info); + BUG_ON(ret); + ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1); BUG_ON(ret); + /* + * make sure none of the code above managed to slip in a + * delayed item + */ + btrfs_assert_delayed_root_empty(root); + WARN_ON(cur_trans != trans->transaction); btrfs_scrub_pause(root); @@ -1312,6 +1391,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, root->fs_info->running_transaction = NULL; root->fs_info->trans_no_join = 0; spin_unlock(&root->fs_info->trans_lock); + mutex_unlock(&root->fs_info->reloc_mutex); wake_up(&root->fs_info->transaction_wait); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 592396c6dc4..4ce8a9f41d1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3177,7 +3177,7 @@ again: tmp_key.offset = (u64)-1; wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key); - BUG_ON(!wc.replay_dest); + BUG_ON(IS_ERR_OR_NULL(wc.replay_dest)); wc.replay_dest->log_root = log; btrfs_record_root_in_trans(trans, wc.replay_dest); diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 53ed1ad2c11..f66cc162515 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -156,6 +156,6 @@ config CIFS_ACL config CIFS_NFSD_EXPORT bool "Allow nfsd to export CIFS file system (EXPERIMENTAL)" - depends on CIFS && EXPERIMENTAL + depends on CIFS && EXPERIMENTAL && BROKEN help Allows NFS server to export a CIFS mounted share (nfsd over cifs) diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index ffb1459dc6e..7260e11e21f 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -42,6 +42,7 @@ #define CIFS_MOUNT_MULTIUSER 0x20000 /* multiuser mount */ #define CIFS_MOUNT_STRICT_IO 0x40000 /* strict cache mode */ #define CIFS_MOUNT_RWPIDFORWARD 0x80000 /* use pid forwarding for rw */ +#define CIFS_MOUNT_POSIXACL 0x100000 /* mirror of MS_POSIXACL in mnt_cifs_flags */ struct cifs_sb_info { struct rb_root tlink_tree; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e9def996e38..35f9154615f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -104,8 +104,7 @@ cifs_sb_deactive(struct super_block *sb) } static int -cifs_read_super(struct super_block *sb, struct smb_vol *volume_info, - const char *devname, int silent) +cifs_read_super(struct super_block *sb) { struct inode *inode; struct cifs_sb_info *cifs_sb; @@ -113,22 +112,16 @@ cifs_read_super(struct super_block *sb, struct smb_vol *volume_info, cifs_sb = CIFS_SB(sb); - spin_lock_init(&cifs_sb->tlink_tree_lock); - cifs_sb->tlink_tree = RB_ROOT; + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL) + sb->s_flags |= MS_POSIXACL; - rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); - if (rc) - return rc; - - cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages; + if (cifs_sb_master_tcon(cifs_sb)->ses->capabilities & CAP_LARGE_FILES) + sb->s_maxbytes = MAX_LFS_FILESIZE; + else + sb->s_maxbytes = MAX_NON_LFS; - rc = cifs_mount(sb, cifs_sb, volume_info, devname); - - if (rc) { - if (!silent) - cERROR(1, "cifs_mount failed w/return code = %d", rc); - goto out_mount_failed; - } + /* BB FIXME fix time_gran to be larger for LANMAN sessions */ + sb->s_time_gran = 100; sb->s_magic = CIFS_MAGIC_NUMBER; sb->s_op = &cifs_super_ops; @@ -170,37 +163,14 @@ out_no_root: if (inode) iput(inode); - cifs_umount(sb, cifs_sb); - -out_mount_failed: - bdi_destroy(&cifs_sb->bdi); return rc; } -static void -cifs_put_super(struct super_block *sb) +static void cifs_kill_sb(struct super_block *sb) { - int rc = 0; - struct cifs_sb_info *cifs_sb; - - cFYI(1, "In cifs_put_super"); - cifs_sb = CIFS_SB(sb); - if (cifs_sb == NULL) { - cFYI(1, "Empty cifs superblock info passed to unmount"); - return; - } - - rc = cifs_umount(sb, cifs_sb); - if (rc) - cERROR(1, "cifs_umount failed with return code %d", rc); - if (cifs_sb->mountdata) { - kfree(cifs_sb->mountdata); - cifs_sb->mountdata = NULL; - } - - unload_nls(cifs_sb->local_nls); - bdi_destroy(&cifs_sb->bdi); - kfree(cifs_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + kill_anon_super(sb); + cifs_umount(cifs_sb); } static int @@ -257,9 +227,6 @@ static int cifs_permission(struct inode *inode, int mask, unsigned int flags) { struct cifs_sb_info *cifs_sb; - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - cifs_sb = CIFS_SB(inode->i_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) { @@ -551,7 +518,6 @@ static int cifs_drop_inode(struct inode *inode) } static const struct super_operations cifs_super_ops = { - .put_super = cifs_put_super, .statfs = cifs_statfs, .alloc_inode = cifs_alloc_inode, .destroy_inode = cifs_destroy_inode, @@ -588,7 +554,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) full_path = cifs_build_path_to_root(vol, cifs_sb, cifs_sb_master_tcon(cifs_sb)); if (full_path == NULL) - return NULL; + return ERR_PTR(-ENOMEM); cFYI(1, "Get root dentry for %s", full_path); @@ -617,7 +583,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) dchild = d_alloc(dparent, &name); if (dchild == NULL) { dput(dparent); - dparent = NULL; + dparent = ERR_PTR(-ENOMEM); goto out; } } @@ -635,7 +601,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) if (rc) { dput(dchild); dput(dparent); - dparent = NULL; + dparent = ERR_PTR(rc); goto out; } alias = d_materialise_unique(dchild, inode); @@ -643,7 +609,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) dput(dchild); if (IS_ERR(alias)) { dput(dparent); - dparent = NULL; + dparent = ERR_PTR(-EINVAL); /* XXX */ goto out; } dchild = alias; @@ -663,6 +629,13 @@ out: return dparent; } +static int cifs_set_super(struct super_block *sb, void *data) +{ + struct cifs_mnt_data *mnt_data = data; + sb->s_fs_info = mnt_data->cifs_sb; + return set_anon_super(sb, NULL); +} + static struct dentry * cifs_do_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) @@ -683,75 +656,73 @@ cifs_do_mount(struct file_system_type *fs_type, cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL); if (cifs_sb == NULL) { root = ERR_PTR(-ENOMEM); - goto out; + goto out_nls; + } + + cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL); + if (cifs_sb->mountdata == NULL) { + root = ERR_PTR(-ENOMEM); + goto out_cifs_sb; } cifs_setup_cifs_sb(volume_info, cifs_sb); + rc = cifs_mount(cifs_sb, volume_info); + if (rc) { + if (!(flags & MS_SILENT)) + cERROR(1, "cifs_mount failed w/return code = %d", rc); + root = ERR_PTR(rc); + goto out_mountdata; + } + mnt_data.vol = volume_info; mnt_data.cifs_sb = cifs_sb; mnt_data.flags = flags; - sb = sget(fs_type, cifs_match_super, set_anon_super, &mnt_data); + sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data); if (IS_ERR(sb)) { root = ERR_CAST(sb); - goto out_cifs_sb; + cifs_umount(cifs_sb); + goto out; } - if (sb->s_fs_info) { + if (sb->s_root) { cFYI(1, "Use existing superblock"); - goto out_shared; - } + cifs_umount(cifs_sb); + } else { + sb->s_flags = flags; + /* BB should we make this contingent on mount parm? */ + sb->s_flags |= MS_NODIRATIME | MS_NOATIME; + + rc = cifs_read_super(sb); + if (rc) { + root = ERR_PTR(rc); + goto out_super; + } - /* - * Copy mount params for use in submounts. Better to do - * the copy here and deal with the error before cleanup gets - * complicated post-mount. - */ - cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL); - if (cifs_sb->mountdata == NULL) { - root = ERR_PTR(-ENOMEM); - goto out_super; + sb->s_flags |= MS_ACTIVE; } - sb->s_flags = flags; - /* BB should we make this contingent on mount parm? */ - sb->s_flags |= MS_NODIRATIME | MS_NOATIME; - sb->s_fs_info = cifs_sb; - - rc = cifs_read_super(sb, volume_info, dev_name, - flags & MS_SILENT ? 1 : 0); - if (rc) { - root = ERR_PTR(rc); - goto out_super; - } - - sb->s_flags |= MS_ACTIVE; - root = cifs_get_root(volume_info, sb); - if (root == NULL) + if (IS_ERR(root)) goto out_super; cFYI(1, "dentry root is: %p", root); goto out; -out_shared: - root = cifs_get_root(volume_info, sb); - if (root) - cFYI(1, "dentry root is: %p", root); - goto out; - out_super: - kfree(cifs_sb->mountdata); deactivate_locked_super(sb); - -out_cifs_sb: - unload_nls(cifs_sb->local_nls); - kfree(cifs_sb); - out: cifs_cleanup_volume_info(&volume_info); return root; + +out_mountdata: + kfree(cifs_sb->mountdata); +out_cifs_sb: + kfree(cifs_sb); +out_nls: + unload_nls(volume_info->local_nls); + goto out; } static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, @@ -840,7 +811,7 @@ struct file_system_type cifs_fs_type = { .owner = THIS_MODULE, .name = "cifs", .mount = cifs_do_mount, - .kill_sb = kill_anon_super, + .kill_sb = cifs_kill_sb, /* .fs_flags */ }; const struct inode_operations cifs_dir_inode_ops = { diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 953f84413c7..257f312ede4 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -157,9 +157,8 @@ extern int cifs_match_super(struct super_block *, void *); extern void cifs_cleanup_volume_info(struct smb_vol **pvolume_info); extern int cifs_setup_volume_info(struct smb_vol **pvolume_info, char *mount_data, const char *devname); -extern int cifs_mount(struct super_block *, struct cifs_sb_info *, - struct smb_vol *, const char *); -extern int cifs_umount(struct super_block *, struct cifs_sb_info *); +extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *); +extern void cifs_umount(struct cifs_sb_info *); extern void cifs_dfs_release_automount_timer(void); void cifs_proc_init(void); void cifs_proc_clean(void); @@ -218,7 +217,8 @@ extern int get_dfs_path(int xid, struct cifs_ses *pSesInfo, struct dfs_info3_param **preferrals, int remap); extern void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon, - struct super_block *sb, struct smb_vol *vol); + struct cifs_sb_info *cifs_sb, + struct smb_vol *vol); extern int CIFSSMBQFSInfo(const int xid, struct cifs_tcon *tcon, struct kstatfs *FSData); extern int SMBOldQFSInfo(const int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 12cf72dd0c4..7f540df5252 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2546,7 +2546,7 @@ ip_connect(struct TCP_Server_Info *server) } void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon, - struct super_block *sb, struct smb_vol *vol_info) + struct cifs_sb_info *cifs_sb, struct smb_vol *vol_info) { /* if we are reconnecting then should we check to see if * any requested capabilities changed locally e.g. via @@ -2600,22 +2600,23 @@ void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon, cap &= ~CIFS_UNIX_POSIX_ACL_CAP; else if (CIFS_UNIX_POSIX_ACL_CAP & cap) { cFYI(1, "negotiated posix acl support"); - if (sb) - sb->s_flags |= MS_POSIXACL; + if (cifs_sb) + cifs_sb->mnt_cifs_flags |= + CIFS_MOUNT_POSIXACL; } if (vol_info && vol_info->posix_paths == 0) cap &= ~CIFS_UNIX_POSIX_PATHNAMES_CAP; else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) { cFYI(1, "negotiate posix pathnames"); - if (sb) - CIFS_SB(sb)->mnt_cifs_flags |= + if (cifs_sb) + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; } - if (sb && (CIFS_SB(sb)->rsize > 127 * 1024)) { + if (cifs_sb && (cifs_sb->rsize > 127 * 1024)) { if ((cap & CIFS_UNIX_LARGE_READ_CAP) == 0) { - CIFS_SB(sb)->rsize = 127 * 1024; + cifs_sb->rsize = 127 * 1024; cFYI(DBG2, "larger reads not supported by srv"); } } @@ -2662,6 +2663,9 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, { INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks); + spin_lock_init(&cifs_sb->tlink_tree_lock); + cifs_sb->tlink_tree = RB_ROOT; + if (pvolume_info->rsize > CIFSMaxBufSize) { cERROR(1, "rsize %d too large, using MaxBufSize", pvolume_info->rsize); @@ -2750,21 +2754,21 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, /* * When the server supports very large writes via POSIX extensions, we can - * allow up to 2^24 - PAGE_CACHE_SIZE. + * allow up to 2^24-1, minus the size of a WRITE_AND_X header, not including + * the RFC1001 length. * * Note that this might make for "interesting" allocation problems during - * writeback however (as we have to allocate an array of pointers for the - * pages). A 16M write means ~32kb page array with PAGE_CACHE_SIZE == 4096. + * writeback however as we have to allocate an array of pointers for the + * pages. A 16M write means ~32kb page array with PAGE_CACHE_SIZE == 4096. */ -#define CIFS_MAX_WSIZE ((1<<24) - PAGE_CACHE_SIZE) +#define CIFS_MAX_WSIZE ((1<<24) - 1 - sizeof(WRITE_REQ) + 4) /* - * When the server doesn't allow large posix writes, default to a wsize of - * 128k - PAGE_CACHE_SIZE -- one page less than the largest frame size - * described in RFC1001. This allows space for the header without going over - * that by default. + * When the server doesn't allow large posix writes, only allow a wsize of + * 128k minus the size of the WRITE_AND_X header. That allows for a write up + * to the maximum size described by RFC1002. */ -#define CIFS_MAX_RFC1001_WSIZE (128 * 1024 - PAGE_CACHE_SIZE) +#define CIFS_MAX_RFC1002_WSIZE (128 * 1024 - sizeof(WRITE_REQ) + 4) /* * The default wsize is 1M. find_get_pages seems to return a maximum of 256 @@ -2783,11 +2787,18 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) /* can server support 24-bit write sizes? (via UNIX extensions) */ if (!tcon->unix_ext || !(unix_cap & CIFS_UNIX_LARGE_WRITE_CAP)) - wsize = min_t(unsigned int, wsize, CIFS_MAX_RFC1001_WSIZE); + wsize = min_t(unsigned int, wsize, CIFS_MAX_RFC1002_WSIZE); - /* no CAP_LARGE_WRITE_X? Limit it to 16 bits */ - if (!(server->capabilities & CAP_LARGE_WRITE_X)) - wsize = min_t(unsigned int, wsize, USHRT_MAX); + /* + * no CAP_LARGE_WRITE_X or is signing enabled without CAP_UNIX set? + * Limit it to max buffer offered by the server, minus the size of the + * WRITEX header, not including the 4 byte RFC1001 length. + */ + if (!(server->capabilities & CAP_LARGE_WRITE_X) || + (!(server->capabilities & CAP_UNIX) && + (server->sec_mode & (SECMODE_SIGN_ENABLED|SECMODE_SIGN_REQUIRED)))) + wsize = min_t(unsigned int, wsize, + server->maxBuf - sizeof(WRITE_REQ) + 4); /* hard limit of CIFS_MAX_WSIZE */ wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE); @@ -2937,7 +2948,11 @@ int cifs_setup_volume_info(struct smb_vol **pvolume_info, char *mount_data, if (volume_info->nullauth) { cFYI(1, "null user"); - volume_info->username = ""; + volume_info->username = kzalloc(1, GFP_KERNEL); + if (volume_info->username == NULL) { + rc = -ENOMEM; + goto out; + } } else if (volume_info->username) { /* BB fixme parse for domain name here */ cFYI(1, "Username: %s", volume_info->username); @@ -2971,8 +2986,7 @@ out: } int -cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, - struct smb_vol *volume_info, const char *devname) +cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) { int rc = 0; int xid; @@ -2983,6 +2997,13 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, struct tcon_link *tlink; #ifdef CONFIG_CIFS_DFS_UPCALL int referral_walks_count = 0; + + rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); + if (rc) + return rc; + + cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages; + try_mount_again: /* cleanup activities if we're chasing a referral */ if (referral_walks_count) { @@ -3007,6 +3028,7 @@ try_mount_again: srvTcp = cifs_get_tcp_session(volume_info); if (IS_ERR(srvTcp)) { rc = PTR_ERR(srvTcp); + bdi_destroy(&cifs_sb->bdi); goto out; } @@ -3018,14 +3040,6 @@ try_mount_again: goto mount_fail_check; } - if (pSesInfo->capabilities & CAP_LARGE_FILES) - sb->s_maxbytes = MAX_LFS_FILESIZE; - else - sb->s_maxbytes = MAX_NON_LFS; - - /* BB FIXME fix time_gran to be larger for LANMAN sessions */ - sb->s_time_gran = 100; - /* search for existing tcon to this server share */ tcon = cifs_get_tcon(pSesInfo, volume_info); if (IS_ERR(tcon)) { @@ -3038,7 +3052,7 @@ try_mount_again: if (tcon->ses->capabilities & CAP_UNIX) { /* reset of caps checks mount to see if unix extensions disabled for just this mount */ - reset_cifs_unix_caps(xid, tcon, sb, volume_info); + reset_cifs_unix_caps(xid, tcon, cifs_sb, volume_info); if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && (le64_to_cpu(tcon->fsUnixInfo.Capability) & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { @@ -3161,6 +3175,7 @@ mount_fail_check: cifs_put_smb_ses(pSesInfo); else cifs_put_tcp_session(srvTcp); + bdi_destroy(&cifs_sb->bdi); goto out; } @@ -3335,8 +3350,8 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses, return rc; } -int -cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) +void +cifs_umount(struct cifs_sb_info *cifs_sb) { struct rb_root *root = &cifs_sb->tlink_tree; struct rb_node *node; @@ -3357,7 +3372,10 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) } spin_unlock(&cifs_sb->tlink_tree_lock); - return 0; + bdi_destroy(&cifs_sb->bdi); + kfree(cifs_sb->mountdata); + unload_nls(cifs_sb->local_nls); + kfree(cifs_sb); } int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses) diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index 1525d5e662b..1c5b770c314 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -90,12 +90,10 @@ smbhash(unsigned char *out, const unsigned char *in, unsigned char *key) sg_init_one(&sgout, out, 8); rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, 8); - if (rc) { + if (rc) cERROR(1, "could not encrypt crypt key rc: %d\n", rc); - crypto_free_blkcipher(tfm_des); - goto smbhash_err; - } + crypto_free_blkcipher(tfm_des); smbhash_err: return rc; } diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index 6cbb3afb36d..cb140ef293e 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -43,8 +43,6 @@ const struct file_operations coda_ioctl_operations = { /* the coda pioctl inode ops */ static int coda_ioctl_permission(struct inode *inode, int mask, unsigned int flags) { - if (flags & IPERM_FLAG_RCU) - return -ECHILD; return (mask & MAY_EXEC) ? -EACCES : 0; } diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 2e29abb30f7..095c36f3b61 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -125,7 +125,7 @@ struct ext4_ext_path { * positive retcode - signal for ext4_ext_walk_space(), see below * callback must return valid extent (passed or newly created) */ -typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, +typedef int (*ext_prepare_callback)(struct inode *, ext4_lblk_t, struct ext4_ext_cache *, struct ext4_extent *, void *); @@ -133,8 +133,11 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_BREAK 1 #define EXT_REPEAT 2 -/* Maximum logical block in a file; ext4_extent's ee_block is __le32 */ -#define EXT_MAX_BLOCK 0xffffffff +/* + * Maximum number of logical blocks in a file; ext4_extent's ee_block is + * __le32. + */ +#define EXT_MAX_BLOCKS 0xffffffff /* * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5199bac7fc6..f815cc81e7a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1408,7 +1408,7 @@ got_index: /* * ext4_ext_next_allocated_block: - * returns allocated block in subsequent extent or EXT_MAX_BLOCK. + * returns allocated block in subsequent extent or EXT_MAX_BLOCKS. * NOTE: it considers block number from index entry as * allocated block. Thus, index entries have to be consistent * with leaves. @@ -1422,7 +1422,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) depth = path->p_depth; if (depth == 0 && path->p_ext == NULL) - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; while (depth >= 0) { if (depth == path->p_depth) { @@ -1439,12 +1439,12 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) depth--; } - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; } /* * ext4_ext_next_leaf_block: - * returns first allocated block from next leaf or EXT_MAX_BLOCK + * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, struct ext4_ext_path *path) @@ -1456,7 +1456,7 @@ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, /* zero-tree has no leaf blocks at all */ if (depth == 0) - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; /* go to index block */ depth--; @@ -1469,7 +1469,7 @@ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, depth--; } - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; } /* @@ -1677,13 +1677,13 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode, */ if (b2 < b1) { b2 = ext4_ext_next_allocated_block(path); - if (b2 == EXT_MAX_BLOCK) + if (b2 == EXT_MAX_BLOCKS) goto out; } /* check for wrap through zero on extent logical start block*/ if (b1 + len1 < b1) { - len1 = EXT_MAX_BLOCK - b1; + len1 = EXT_MAX_BLOCKS - b1; newext->ee_len = cpu_to_le16(len1); ret = 1; } @@ -1767,7 +1767,7 @@ repeat: fex = EXT_LAST_EXTENT(eh); next = ext4_ext_next_leaf_block(inode, path); if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block) - && next != EXT_MAX_BLOCK) { + && next != EXT_MAX_BLOCKS) { ext_debug("next leaf block - %d\n", next); BUG_ON(npath != NULL); npath = ext4_ext_find_extent(inode, next, NULL); @@ -1887,7 +1887,7 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, BUG_ON(func == NULL); BUG_ON(inode == NULL); - while (block < last && block != EXT_MAX_BLOCK) { + while (block < last && block != EXT_MAX_BLOCKS) { num = last - block; /* find extent for this block */ down_read(&EXT4_I(inode)->i_data_sem); @@ -1958,7 +1958,7 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, err = -EIO; break; } - err = func(inode, path, &cbex, ex, cbdata); + err = func(inode, next, &cbex, ex, cbdata); ext4_ext_drop_refs(path); if (err < 0) @@ -2020,7 +2020,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, if (ex == NULL) { /* there is no extent yet, so gap is [0;-] */ lblock = 0; - len = EXT_MAX_BLOCK; + len = EXT_MAX_BLOCKS; ext_debug("cache gap(whole file):"); } else if (block < le32_to_cpu(ex->ee_block)) { lblock = block; @@ -2350,7 +2350,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * never happen because at least one of the end points * needs to be on the edge of the extent. */ - if (end == EXT_MAX_BLOCK) { + if (end == EXT_MAX_BLOCKS - 1) { ext_debug(" bad truncate %u:%u\n", start, end); block = 0; @@ -2398,7 +2398,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * If this is a truncate, this condition * should never happen */ - if (end == EXT_MAX_BLOCK) { + if (end == EXT_MAX_BLOCKS - 1) { ext_debug(" bad truncate %u:%u\n", start, end); err = -EIO; @@ -2478,7 +2478,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * we need to remove it from the leaf */ if (num == 0) { - if (end != EXT_MAX_BLOCK) { + if (end != EXT_MAX_BLOCKS - 1) { /* * For hole punching, we need to scoot all the * extents up when an extent is removed so that @@ -3699,7 +3699,7 @@ void ext4_ext_truncate(struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); - err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCK); + err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); /* In a multi-transaction truncate, we only make the final * transaction synchronous. @@ -3914,14 +3914,13 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset, /* * Callback function called for each extent to gather FIEMAP information. */ -static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, +static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next, struct ext4_ext_cache *newex, struct ext4_extent *ex, void *data) { __u64 logical; __u64 physical; __u64 length; - loff_t size; __u32 flags = 0; int ret = 0; struct fiemap_extent_info *fieinfo = data; @@ -4103,8 +4102,7 @@ found_delayed_extent: if (ex && ext4_ext_is_uninitialized(ex)) flags |= FIEMAP_EXTENT_UNWRITTEN; - size = i_size_read(inode); - if (logical + length >= size) + if (next == EXT_MAX_BLOCKS) flags |= FIEMAP_EXTENT_LAST; ret = fiemap_fill_next_extent(fieinfo, logical, physical, @@ -4347,8 +4345,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, start_blk = start >> inode->i_sb->s_blocksize_bits; last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; - if (last_blk >= EXT_MAX_BLOCK) - last_blk = EXT_MAX_BLOCK-1; + if (last_blk >= EXT_MAX_BLOCKS) + last_blk = EXT_MAX_BLOCKS-1; len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a5763e3505b..e3126c05100 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2634,7 +2634,7 @@ static int ext4_writepage(struct page *page, struct buffer_head *page_bufs = NULL; struct inode *inode = page->mapping->host; - trace_ext4_writepage(inode, page); + trace_ext4_writepage(page); size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 859f2ae8864..6ed859d5685 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3578,8 +3578,8 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); - trace_ext4_mb_release_inode_pa(sb, pa->pa_inode, pa, - grp_blk_start + bit, next - bit); + trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit, + next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } @@ -3608,7 +3608,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ext4_group_t group; ext4_grpblk_t bit; - trace_ext4_mb_release_group_pa(sb, pa); + trace_ext4_mb_release_group_pa(pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); @@ -4448,7 +4448,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, * @inode: inode * @block: start physical block to free * @count: number of blocks to count - * @metadata: Are these metadata blocks + * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 2b8304bf3c5..f57455a1b1b 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -1002,12 +1002,12 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - if ((orig_start > EXT_MAX_BLOCK) || - (donor_start > EXT_MAX_BLOCK) || - (*len > EXT_MAX_BLOCK) || - (orig_start + *len > EXT_MAX_BLOCK)) { + if ((orig_start >= EXT_MAX_BLOCKS) || + (donor_start >= EXT_MAX_BLOCKS) || + (*len > EXT_MAX_BLOCKS) || + (orig_start + *len >= EXT_MAX_BLOCKS)) { ext4_debug("ext4 move extent: Can't handle over [%u] blocks " - "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK, + "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cc5c157aa11..9ea71aa864b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2243,6 +2243,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, * so that won't be a limiting factor. * + * However there is other limiting factor. We do store extents in the form + * of starting block and length, hence the resulting length of the extent + * covering maximum file size must fit into on-disk format containers as + * well. Given that length is always by 1 unit bigger than max unit (because + * we count 0 as well) we have to lower the s_maxbytes by one fs block. + * * Note, this does *not* consider any metadata overhead for vfs i_blocks. */ static loff_t ext4_max_size(int blkbits, int has_huge_files) @@ -2264,10 +2270,13 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) upper_limit <<= blkbits; } - /* 32-bit extent-start container, ee_block */ - res = 1LL << 32; + /* + * 32-bit extent-start container, ee_block. We lower the maxbytes + * by one fs block, so ee_len can cover the extent of maximum file + * size + */ + res = (1LL << 32) - 1; res <<= blkbits; - res -= 1; /* Sanity check against vm- & vfs- imposed limits */ if (res > upper_limit) diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 6a79fd0a1a3..2c62c5aae82 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -97,10 +97,14 @@ static int __try_to_free_cp_buf(struct journal_head *jh) if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh) && !buffer_write_io_error(bh)) { + /* + * Get our reference so that bh cannot be freed before + * we unlock it + */ + get_bh(bh); JBUFFER_TRACE(jh, "remove from checkpoint list"); ret = __jbd2_journal_remove_checkpoint(jh) + 1; jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); BUFFER_TRACE(bh, "release"); __brelse(bh); } else { @@ -223,8 +227,8 @@ restart: spin_lock(&journal->j_list_lock); goto restart; } + get_bh(bh); if (buffer_locked(bh)) { - atomic_inc(&bh->b_count); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); wait_on_buffer(bh); @@ -243,7 +247,6 @@ restart: */ released = __jbd2_journal_remove_checkpoint(jh); jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); __brelse(bh); } @@ -284,7 +287,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, int ret = 0; if (buffer_locked(bh)) { - atomic_inc(&bh->b_count); + get_bh(bh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); wait_on_buffer(bh); @@ -316,12 +319,12 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, ret = 1; if (unlikely(buffer_write_io_error(bh))) ret = -EIO; + get_bh(bh); J_ASSERT_JH(jh, !buffer_jbddirty(bh)); BUFFER_TRACE(bh, "remove from checkpoint"); __jbd2_journal_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); __brelse(bh); } else { /* @@ -554,7 +557,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* * journal_clean_one_cp_list * - * Find all the written-back checkpoint buffers in the given list and release them. + * Find all the written-back checkpoint buffers in the given list and + * release them. * * Called with the journal locked. * Called with j_list_lock held. @@ -663,8 +667,8 @@ out: * checkpoint lists. * * The function returns 1 if it frees the transaction, 0 otherwise. + * The function can free jh and bh. * - * This function is called with the journal locked. * This function is called with j_list_lock held. * This function is called with jbd_lock_bh_state(jh2bh(jh)) */ @@ -684,13 +688,14 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) } journal = transaction->t_journal; + JBUFFER_TRACE(jh, "removing from transaction"); __buffer_unlink(jh); jh->b_cp_transaction = NULL; + jbd2_journal_put_journal_head(jh); if (transaction->t_checkpoint_list != NULL || transaction->t_checkpoint_io_list != NULL) goto out; - JBUFFER_TRACE(jh, "transaction has no more buffers"); /* * There is one special case to worry about: if we have just pulled the @@ -701,10 +706,8 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) * The locking here around t_state is a bit sleazy. * See the comment at the end of jbd2_journal_commit_transaction(). */ - if (transaction->t_state != T_FINISHED) { - JBUFFER_TRACE(jh, "belongs to running/committing transaction"); + if (transaction->t_state != T_FINISHED) goto out; - } /* OK, that was the last buffer for the transaction: we can now safely remove this transaction from the log */ @@ -723,7 +726,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) wake_up(&journal->j_wait_logspace); ret = 1; out: - JBUFFER_TRACE(jh, "exit"); return ret; } @@ -742,6 +744,8 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh, J_ASSERT_JH(jh, buffer_dirty(jh2bh(jh)) || buffer_jbddirty(jh2bh(jh))); J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + /* Get reference for checkpointing transaction */ + jbd2_journal_grab_journal_head(jh2bh(jh)); jh->b_cp_transaction = transaction; if (!transaction->t_checkpoint_list) { diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7f21cf3aaf9..eef6979821a 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -848,10 +848,16 @@ restart_loop: while (commit_transaction->t_forget) { transaction_t *cp_transaction; struct buffer_head *bh; + int try_to_free = 0; jh = commit_transaction->t_forget; spin_unlock(&journal->j_list_lock); bh = jh2bh(jh); + /* + * Get a reference so that bh cannot be freed before we are + * done with it. + */ + get_bh(bh); jbd_lock_bh_state(bh); J_ASSERT_JH(jh, jh->b_transaction == commit_transaction); @@ -914,28 +920,27 @@ restart_loop: __jbd2_journal_insert_checkpoint(jh, commit_transaction); if (is_journal_aborted(journal)) clear_buffer_jbddirty(bh); - JBUFFER_TRACE(jh, "refile for checkpoint writeback"); - __jbd2_journal_refile_buffer(jh); - jbd_unlock_bh_state(bh); } else { J_ASSERT_BH(bh, !buffer_dirty(bh)); - /* The buffer on BJ_Forget list and not jbddirty means + /* + * The buffer on BJ_Forget list and not jbddirty means * it has been freed by this transaction and hence it * could not have been reallocated until this * transaction has committed. *BUT* it could be * reallocated once we have written all the data to * disk and before we process the buffer on BJ_Forget - * list. */ - JBUFFER_TRACE(jh, "refile or unfile freed buffer"); - __jbd2_journal_refile_buffer(jh); - if (!jh->b_transaction) { - jbd_unlock_bh_state(bh); - /* needs a brelse */ - jbd2_journal_remove_journal_head(bh); - release_buffer_page(bh); - } else - jbd_unlock_bh_state(bh); + * list. + */ + if (!jh->b_next_transaction) + try_to_free = 1; } + JBUFFER_TRACE(jh, "refile or unfile buffer"); + __jbd2_journal_refile_buffer(jh); + jbd_unlock_bh_state(bh); + if (try_to_free) + release_buffer_page(bh); /* Drops bh reference */ + else + __brelse(bh); cond_resched_lock(&journal->j_list_lock); } spin_unlock(&journal->j_list_lock); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 9a782699030..0dfa5b598e6 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2078,10 +2078,9 @@ static void journal_free_journal_head(struct journal_head *jh) * When a buffer has its BH_JBD bit set it is immune from being released by * core kernel code, mainly via ->b_count. * - * A journal_head may be detached from its buffer_head when the journal_head's - * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL. - * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the - * journal_head can be dropped if needed. + * A journal_head is detached from its buffer_head when the journal_head's + * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint + * transaction (b_cp_transaction) hold their references to b_jcount. * * Various places in the kernel want to attach a journal_head to a buffer_head * _before_ attaching the journal_head to a transaction. To protect the @@ -2094,17 +2093,16 @@ static void journal_free_journal_head(struct journal_head *jh) * (Attach a journal_head if needed. Increments b_jcount) * struct journal_head *jh = jbd2_journal_add_journal_head(bh); * ... + * (Get another reference for transaction) + * jbd2_journal_grab_journal_head(bh); * jh->b_transaction = xxx; + * (Put original reference) * jbd2_journal_put_journal_head(jh); - * - * Now, the journal_head's b_jcount is zero, but it is safe from being released - * because it has a non-zero b_transaction. */ /* * Give a buffer_head a journal_head. * - * Doesn't need the journal lock. * May sleep. */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) @@ -2168,61 +2166,29 @@ static void __journal_remove_journal_head(struct buffer_head *bh) struct journal_head *jh = bh2jh(bh); J_ASSERT_JH(jh, jh->b_jcount >= 0); - - get_bh(bh); - if (jh->b_jcount == 0) { - if (jh->b_transaction == NULL && - jh->b_next_transaction == NULL && - jh->b_cp_transaction == NULL) { - J_ASSERT_JH(jh, jh->b_jlist == BJ_None); - J_ASSERT_BH(bh, buffer_jbd(bh)); - J_ASSERT_BH(bh, jh2bh(jh) == bh); - BUFFER_TRACE(bh, "remove journal_head"); - if (jh->b_frozen_data) { - printk(KERN_WARNING "%s: freeing " - "b_frozen_data\n", - __func__); - jbd2_free(jh->b_frozen_data, bh->b_size); - } - if (jh->b_committed_data) { - printk(KERN_WARNING "%s: freeing " - "b_committed_data\n", - __func__); - jbd2_free(jh->b_committed_data, bh->b_size); - } - bh->b_private = NULL; - jh->b_bh = NULL; /* debug, really */ - clear_buffer_jbd(bh); - __brelse(bh); - journal_free_journal_head(jh); - } else { - BUFFER_TRACE(bh, "journal_head was locked"); - } + J_ASSERT_JH(jh, jh->b_transaction == NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + J_ASSERT_JH(jh, jh->b_jlist == BJ_None); + J_ASSERT_BH(bh, buffer_jbd(bh)); + J_ASSERT_BH(bh, jh2bh(jh) == bh); + BUFFER_TRACE(bh, "remove journal_head"); + if (jh->b_frozen_data) { + printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); + jbd2_free(jh->b_frozen_data, bh->b_size); } + if (jh->b_committed_data) { + printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__); + jbd2_free(jh->b_committed_data, bh->b_size); + } + bh->b_private = NULL; + jh->b_bh = NULL; /* debug, really */ + clear_buffer_jbd(bh); + journal_free_journal_head(jh); } /* - * jbd2_journal_remove_journal_head(): if the buffer isn't attached to a transaction - * and has a zero b_jcount then remove and release its journal_head. If we did - * see that the buffer is not used by any transaction we also "logically" - * decrement ->b_count. - * - * We in fact take an additional increment on ->b_count as a convenience, - * because the caller usually wants to do additional things with the bh - * after calling here. - * The caller of jbd2_journal_remove_journal_head() *must* run __brelse(bh) at some - * time. Once the caller has run __brelse(), the buffer is eligible for - * reaping by try_to_free_buffers(). - */ -void jbd2_journal_remove_journal_head(struct buffer_head *bh) -{ - jbd_lock_bh_journal_head(bh); - __journal_remove_journal_head(bh); - jbd_unlock_bh_journal_head(bh); -} - -/* - * Drop a reference on the passed journal_head. If it fell to zero then try to + * Drop a reference on the passed journal_head. If it fell to zero then * release the journal_head from the buffer_head. */ void jbd2_journal_put_journal_head(struct journal_head *jh) @@ -2232,11 +2198,12 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) jbd_lock_bh_journal_head(bh); J_ASSERT_JH(jh, jh->b_jcount > 0); --jh->b_jcount; - if (!jh->b_jcount && !jh->b_transaction) { + if (!jh->b_jcount) { __journal_remove_journal_head(bh); + jbd_unlock_bh_journal_head(bh); __brelse(bh); - } - jbd_unlock_bh_journal_head(bh); + } else + jbd_unlock_bh_journal_head(bh); } /* diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 3eec82d32fd..2d7109414cd 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -30,6 +30,7 @@ #include <linux/module.h> static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); +static void __jbd2_journal_unfile_buffer(struct journal_head *jh); /* * jbd2_get_transaction: obtain a new transaction_t object. @@ -764,7 +765,6 @@ repeat: if (!jh->b_transaction) { JBUFFER_TRACE(jh, "no transaction"); J_ASSERT_JH(jh, !jh->b_next_transaction); - jh->b_transaction = transaction; JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); @@ -814,7 +814,6 @@ out: * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes - * @credits: variable that will receive credits for the buffer * * Returns an error code or 0 on success. * @@ -896,8 +895,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) * committed and so it's safe to clear the dirty bit. */ clear_buffer_dirty(jh2bh(jh)); - jh->b_transaction = transaction; - /* first access by this transaction */ jh->b_modified = 0; @@ -932,7 +929,6 @@ out: * non-rewindable consequences * @handle: transaction * @bh: buffer to undo - * @credits: store the number of taken credits here (if not NULL) * * Sometimes there is a need to distinguish between metadata which has * been committed to disk and that which has not. The ext3fs code uses @@ -1232,8 +1228,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); - jbd2_journal_remove_journal_head(bh); - __brelse(bh); if (!buffer_jbd(bh)) { spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); @@ -1556,19 +1550,32 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) mark_buffer_dirty(bh); /* Expose it to the VM */ } -void __jbd2_journal_unfile_buffer(struct journal_head *jh) +/* + * Remove buffer from all transactions. + * + * Called with bh_state lock and j_list_lock + * + * jh and bh may be already freed when this function returns. + */ +static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; + jbd2_journal_put_journal_head(jh); } void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) { - jbd_lock_bh_state(jh2bh(jh)); + struct buffer_head *bh = jh2bh(jh); + + /* Get reference so that buffer cannot be freed before we unlock it */ + get_bh(bh); + jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); __jbd2_journal_unfile_buffer(jh); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(jh2bh(jh)); + jbd_unlock_bh_state(bh); + __brelse(bh); } /* @@ -1595,8 +1602,6 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) if (jh->b_jlist == BJ_None) { JBUFFER_TRACE(jh, "remove from checkpoint list"); __jbd2_journal_remove_checkpoint(jh); - jbd2_journal_remove_journal_head(bh); - __brelse(bh); } } spin_unlock(&journal->j_list_lock); @@ -1659,7 +1664,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, /* * We take our own ref against the journal_head here to avoid * having to add tons of locking around each instance of - * jbd2_journal_remove_journal_head() and * jbd2_journal_put_journal_head(). */ jh = jbd2_journal_grab_journal_head(bh); @@ -1697,10 +1701,9 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) int may_free = 1; struct buffer_head *bh = jh2bh(jh); - __jbd2_journal_unfile_buffer(jh); - if (jh->b_cp_transaction) { JBUFFER_TRACE(jh, "on running+cp transaction"); + __jbd2_journal_temp_unlink_buffer(jh); /* * We don't want to write the buffer anymore, clear the * bit so that we don't confuse checks in @@ -1711,8 +1714,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) may_free = 0; } else { JBUFFER_TRACE(jh, "on running transaction"); - jbd2_journal_remove_journal_head(bh); - __brelse(bh); + __jbd2_journal_unfile_buffer(jh); } return may_free; } @@ -1990,6 +1992,8 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, if (jh->b_transaction) __jbd2_journal_temp_unlink_buffer(jh); + else + jbd2_journal_grab_journal_head(bh); jh->b_transaction = transaction; switch (jlist) { @@ -2041,9 +2045,10 @@ void jbd2_journal_file_buffer(struct journal_head *jh, * already started to be used by a subsequent transaction, refile the * buffer on that transaction's metadata list. * - * Called under journal->j_list_lock - * + * Called under j_list_lock * Called under jbd_lock_bh_state(jh2bh(jh)) + * + * jh and bh may be already free when this function returns */ void __jbd2_journal_refile_buffer(struct journal_head *jh) { @@ -2067,6 +2072,11 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); + /* + * We set b_transaction here because b_next_transaction will inherit + * our jh reference and thus __jbd2_journal_file_buffer() must not + * take a new one. + */ jh->b_transaction = jh->b_next_transaction; jh->b_next_transaction = NULL; if (buffer_freed(bh)) @@ -2083,30 +2093,21 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) } /* - * For the unlocked version of this call, also make sure that any - * hanging journal_head is cleaned up if necessary. - * - * __jbd2_journal_refile_buffer is usually called as part of a single locked - * operation on a buffer_head, in which the caller is probably going to - * be hooking the journal_head onto other lists. In that case it is up - * to the caller to remove the journal_head if necessary. For the - * unlocked jbd2_journal_refile_buffer call, the caller isn't going to be - * doing anything else to the buffer so we need to do the cleanup - * ourselves to avoid a jh leak. - * - * *** The journal_head may be freed by this call! *** + * __jbd2_journal_refile_buffer() with necessary locking added. We take our + * bh reference so that we can safely unlock bh. + * + * The jh and bh may be freed by this call. */ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); + /* Get reference so that buffer cannot be freed before we unlock it */ + get_bh(bh); jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); - __jbd2_journal_refile_buffer(jh); jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); - spin_unlock(&journal->j_list_lock); __brelse(bh); } diff --git a/fs/jfs/file.c b/fs/jfs/file.c index c5ce6c1d1ff..2f3f531f360 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -66,9 +66,9 @@ static int jfs_open(struct inode *inode, struct file *file) struct jfs_inode_info *ji = JFS_IP(inode); spin_lock_irq(&ji->ag_lock); if (ji->active_ag == -1) { - ji->active_ag = ji->agno; - atomic_inc( - &JFS_SBI(inode->i_sb)->bmap->db_active[ji->agno]); + struct jfs_sb_info *jfs_sb = JFS_SBI(inode->i_sb); + ji->active_ag = BLKTOAG(addressPXD(&ji->ixpxd), jfs_sb); + atomic_inc( &jfs_sb->bmap->db_active[ji->active_ag]); } spin_unlock_irq(&ji->ag_lock); } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index ed53a474016..b78b2f978f0 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -397,7 +397,7 @@ int diRead(struct inode *ip) release_metapage(mp); /* set the ag for the inode */ - JFS_IP(ip)->agno = BLKTOAG(agstart, sbi); + JFS_IP(ip)->agstart = agstart; JFS_IP(ip)->active_ag = -1; return (rc); @@ -901,7 +901,7 @@ int diFree(struct inode *ip) /* get the allocation group for this ino. */ - agno = JFS_IP(ip)->agno; + agno = BLKTOAG(JFS_IP(ip)->agstart, JFS_SBI(ip->i_sb)); /* Lock the AG specific inode map information */ @@ -1315,12 +1315,11 @@ int diFree(struct inode *ip) static inline void diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) { - struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); struct jfs_inode_info *jfs_ip = JFS_IP(ip); ip->i_ino = (iagno << L2INOSPERIAG) + ino; jfs_ip->ixpxd = iagp->inoext[extno]; - jfs_ip->agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + jfs_ip->agstart = le64_to_cpu(iagp->agstart); jfs_ip->active_ag = -1; } @@ -1379,7 +1378,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) */ /* get the ag number of this iag */ - agno = JFS_IP(pip)->agno; + agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb)); if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) { /* @@ -2921,10 +2920,9 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) continue; } - /* agstart that computes to the same ag is treated as same; */ agstart = le64_to_cpu(iagp->agstart); - /* iagp->agstart = agstart & ~(mp->db_agsize - 1); */ n = agstart >> mp->db_agl2size; + iagp->agstart = cpu_to_le64((s64)n << mp->db_agl2size); /* compute backed inodes */ numinos = (EXTSPERIAG - le32_to_cpu(iagp->nfreeexts)) diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 1439f119ec8..584a4a1a6e8 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -50,8 +50,9 @@ struct jfs_inode_info { short btindex; /* btpage entry index*/ struct inode *ipimap; /* inode map */ unsigned long cflag; /* commit flags */ + u64 agstart; /* agstart of the containing IAG */ u16 bxflag; /* xflag of pseudo buffer? */ - unchar agno; /* ag number */ + unchar pad; signed char active_ag; /* ag currently allocating from */ lid_t blid; /* lid of pseudo buffer? */ lid_t atlhead; /* anonymous tlock list head */ diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 8ea5efb5a34..8d0c1c7c082 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -80,7 +80,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) int log_formatted = 0; struct inode *iplist[1]; struct jfs_superblock *j_sb, *j_sb2; - uint old_agsize; + s64 old_agsize; int agsizechanged = 0; struct buffer_head *bh, *bh2; diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index adb45ec9038..e374050a911 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -708,7 +708,13 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data) if (task->tk_status < 0) { dprintk("lockd: unlock failed (err = %d)\n", -task->tk_status); - goto retry_rebind; + switch (task->tk_status) { + case -EACCES: + case -EIO: + goto die; + default: + goto retry_rebind; + } } if (status == NLM_LCK_DENIED_GRACE_PERIOD) { rpc_delay(task, NLMCLNT_GRACE_WAIT); diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 9ed89d1663f..1afae26cf23 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -555,13 +555,6 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry, return __logfs_create(dir, dentry, inode, target, destlen); } -static int logfs_permission(struct inode *inode, int mask, unsigned int flags) -{ - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - return generic_permission(inode, mask, flags, NULL); -} - static int logfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { @@ -820,7 +813,6 @@ const struct inode_operations logfs_dir_iops = { .mknod = logfs_mknod, .rename = logfs_rename, .rmdir = logfs_rmdir, - .permission = logfs_permission, .symlink = logfs_symlink, .unlink = logfs_unlink, }; diff --git a/fs/namei.c b/fs/namei.c index 9e425e7e6c8..0223c41fb11 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -238,7 +238,8 @@ int generic_permission(struct inode *inode, int mask, unsigned int flags, /* * Read/write DACs are always overridable. - * Executable DACs are overridable if at least one exec bit is set. + * Executable DACs are overridable for all directories and + * for non-directories that have least one exec bit set. */ if (!(mask & MAY_EXEC) || execute_ok(inode)) if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE)) @@ -1011,9 +1012,6 @@ failed: * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. - * - * Care must be taken as namespace_sem may be held (indicated by mounting_here - * being true). */ int follow_down(struct path *path) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 144f2a3c718..6f4850deb27 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -256,7 +256,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) nfs_attr_check_mountpoint(sb, fattr); - if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0 && (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) + if (((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) && + !nfs_attr_use_mounted_on_fileid(fattr)) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; @@ -1294,7 +1295,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (new_isize != cur_isize) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ - if (nfsi->npages == 0 || new_isize > cur_isize) { + if ((nfsi->npages == 0 && !test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) || + new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b9056cbe68d..2a55347a2da 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -45,6 +45,17 @@ static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } +static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) +{ + if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || + (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && + ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) + return 0; + + fattr->fileid = fattr->mounted_on_fileid; + return 1; +} + struct nfs_clone_mount { const struct super_block *sb; const struct dentry *dentry; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 426908809c9..0bafcc91c27 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -30,6 +30,7 @@ */ #include <linux/nfs_fs.h> +#include <linux/nfs_page.h> #include "internal.h" #include "nfs4filelayout.h" @@ -552,13 +553,18 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, __func__, nfl_util, fl->num_fh, fl->first_stripe_index, fl->pattern_offset); - if (!fl->num_fh) + /* Note that a zero value for num_fh is legal for STRIPE_SPARSE. + * Futher checking is done in filelayout_check_layout */ + if (fl->num_fh < 0 || fl->num_fh > + max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT)) goto out_err; - fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), - gfp_flags); - if (!fl->fh_array) - goto out_err; + if (fl->num_fh > 0) { + fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), + gfp_flags); + if (!fl->fh_array) + goto out_err; + } for (i = 0; i < fl->num_fh; i++) { /* Do we want to use a mempool here? */ @@ -661,8 +667,9 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, u64 p_stripe, r_stripe; u32 stripe_unit; - if (!pnfs_generic_pg_test(pgio, prev, req)) - return 0; + if (!pnfs_generic_pg_test(pgio, prev, req) || + !nfs_generic_pg_test(pgio, prev, req)) + return false; if (!pgio->pg_lseg) return 1; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d2c4b59c896..5879b23e0c9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2265,12 +2265,14 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, return nfs4_map_errors(status); } +static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); /* * Get locations and (maybe) other attributes of a referral. * Note that we'll actually follow the referral later when * we detect fsid mismatch in inode revalidation */ -static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct nfs_fattr *fattr, struct nfs_fh *fhandle) +static int nfs4_get_referral(struct inode *dir, const struct qstr *name, + struct nfs_fattr *fattr, struct nfs_fh *fhandle) { int status = -ENOMEM; struct page *page = NULL; @@ -2288,15 +2290,16 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct goto out; /* Make sure server returned a different fsid for the referral */ 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); + dprintk("%s: server did not return a different fsid for" + " a referral at %s\n", __func__, name->name); status = -EIO; goto out; } + /* Fixup attributes for the nfs_lookup() call to nfs_fhget() */ + nfs_fixup_referral_attributes(&locations->fattr); + /* replace the lookup nfs_fattr with the locations nfs_fattr */ memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr)); - fattr->valid |= NFS_ATTR_FATTR_V4_REFERRAL; - if (!fattr->mode) - fattr->mode = S_IFDIR; memset(fhandle, 0, sizeof(struct nfs_fh)); out: if (page) @@ -4667,11 +4670,15 @@ static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list, return len; } +/* + * nfs_fhget will use either the mounted_on_fileid or the fileid + */ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr) { - if (!((fattr->valid & NFS_ATTR_FATTR_FILEID) && - (fattr->valid & NFS_ATTR_FATTR_FSID) && - (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL))) + if (!(((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) || + (fattr->valid & NFS_ATTR_FATTR_FILEID)) && + (fattr->valid & NFS_ATTR_FATTR_FSID) && + (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL))) return; fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | @@ -4686,7 +4693,6 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, struct nfs_server *server = NFS_SERVER(dir); u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, - [1] = FATTR4_WORD1_MOUNTED_ON_FILEID, }; struct nfs4_fs_locations_arg args = { .dir_fh = NFS_FH(dir), @@ -4705,11 +4711,18 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, int status; dprintk("%s: start\n", __func__); + + /* Ask for the fileid of the absent filesystem if mounted_on_fileid + * is not supported */ + if (NFS_SERVER(dir)->attr_bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) + bitmask[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID; + else + bitmask[0] |= FATTR4_WORD0_FILEID; + nfs_fattr_init(&fs_locations->fattr); fs_locations->server = server; fs_locations->nlocations = 0; status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); - nfs_fixup_referral_attributes(&fs_locations->fattr); dprintk("%s: returned status = %d\n", __func__, status); return status; } @@ -5098,7 +5111,6 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) if (mxresp_sz == 0) mxresp_sz = NFS_MAX_FILE_IO_SIZE; /* Fore channel attributes */ - args->fc_attrs.headerpadsz = 0; args->fc_attrs.max_rqst_sz = mxrqst_sz; args->fc_attrs.max_resp_sz = mxresp_sz; args->fc_attrs.max_ops = NFS4_MAX_OPS; @@ -5111,7 +5123,6 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) args->fc_attrs.max_ops, args->fc_attrs.max_reqs); /* Back channel attributes */ - args->bc_attrs.headerpadsz = 0; args->bc_attrs.max_rqst_sz = PAGE_SIZE; args->bc_attrs.max_resp_sz = PAGE_SIZE; args->bc_attrs.max_resp_sz_cached = 0; @@ -5131,8 +5142,6 @@ static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args struct nfs4_channel_attrs *sent = &args->fc_attrs; struct nfs4_channel_attrs *rcvd = &session->fc_attrs; - if (rcvd->headerpadsz > sent->headerpadsz) - return -EINVAL; if (rcvd->max_resp_sz > sent->max_resp_sz) return -EINVAL; /* @@ -5697,6 +5706,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) { struct nfs4_layoutreturn *lrp = calldata; struct nfs_server *server; + struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout; dprintk("--> %s\n", __func__); @@ -5708,16 +5718,15 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) nfs_restart_rpc(task, lrp->clp); return; } + spin_lock(&lo->plh_inode->i_lock); if (task->tk_status == 0) { - struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout; - if (lrp->res.lrs_present) { - spin_lock(&lo->plh_inode->i_lock); pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - spin_unlock(&lo->plh_inode->i_lock); } else BUG_ON(!list_empty(&lo->plh_segs)); } + lo->plh_block_lgets--; + spin_unlock(&lo->plh_inode->i_lock); dprintk("<-- %s\n", __func__); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d869a5e5464..6870bc61cee 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -255,7 +255,7 @@ static int nfs4_stat_to_errno(int); #define decode_fs_locations_maxsz \ (0) #define encode_secinfo_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) -#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 4 + (NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN))) +#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4)) #if defined(CONFIG_NFS_V4_1) #define NFS4_MAX_MACHINE_NAME_LEN (64) @@ -1725,7 +1725,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(args->flags); /*flags */ /* Fore Channel */ - *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(0); /* header padding size */ *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */ *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz); /* max resp size */ *p++ = cpu_to_be32(max_resp_sz_cached); /* Max resp sz cached */ @@ -1734,7 +1734,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ /* Back Channel */ - *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(0); /* header padding size */ *p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz); /* max req size */ *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz); /* max resp size */ *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ @@ -3098,7 +3098,7 @@ out_overflow: return -EIO; } -static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap) +static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap, int32_t *res) { __be32 *p; @@ -3109,7 +3109,7 @@ static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap) if (unlikely(!p)) goto out_overflow; bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR; - return -be32_to_cpup(p); + *res = -be32_to_cpup(p); } return 0; out_overflow: @@ -4070,6 +4070,7 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, int status; umode_t fmode = 0; uint32_t type; + int32_t err; status = decode_attr_type(xdr, bitmap, &type); if (status < 0) @@ -4095,13 +4096,12 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; - status = decode_attr_error(xdr, bitmap); - if (status == -NFS4ERR_WRONGSEC) { - nfs_fixup_secinfo_attributes(fattr, fh); - status = 0; - } + err = 0; + status = decode_attr_error(xdr, bitmap, &err); if (status < 0) goto xdr_error; + if (err == -NFS4ERR_WRONGSEC) + nfs_fixup_secinfo_attributes(fattr, fh); status = decode_attr_filehandle(xdr, bitmap, fh); if (status < 0) @@ -4997,12 +4997,14 @@ static int decode_chan_attrs(struct xdr_stream *xdr, struct nfs4_channel_attrs *attrs) { __be32 *p; - u32 nr_attrs; + u32 nr_attrs, val; p = xdr_inline_decode(xdr, 28); if (unlikely(!p)) goto out_overflow; - attrs->headerpadsz = be32_to_cpup(p++); + val = be32_to_cpup(p++); /* headerpadsz */ + if (val) + return -EINVAL; /* no support for header padding yet */ attrs->max_rqst_sz = be32_to_cpup(p++); attrs->max_resp_sz = be32_to_cpup(p++); attrs->max_resp_sz_cached = be32_to_cpup(p++); diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 9cf208df1f2..8ff2ea3f10e 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -108,7 +108,6 @@ _dev_list_add(const struct nfs_server *nfss, de = n; } - atomic_inc(&de->id_node.ref); return de; } @@ -1001,6 +1000,9 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, if (!pnfs_generic_pg_test(pgio, prev, req)) return false; + if (pgio->pg_lseg == NULL) + return true; + return pgio->pg_count + req->wb_bytes <= OBJIO_LSEG(pgio->pg_lseg)->max_io_size; } diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index dc3956c0de8..1d06f8e2ade 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -291,7 +291,7 @@ objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync) struct nfs_read_data *rdata; state->status = status; - dprintk("%s: Begin status=%ld eof=%d\n", __func__, status, eof); + dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof); rdata = state->rpcdata; rdata->task.tk_status = status; if (status >= 0) { diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 7913961aff2..00985571628 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -204,7 +204,7 @@ nfs_wait_on_request(struct nfs_page *req) TASK_UNINTERRUPTIBLE); } -static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) +bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) { /* * FIXME: ideally we should be able to coalesce all requests @@ -218,6 +218,7 @@ static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_p return desc->pg_count + req->wb_bytes <= desc->pg_bsize; } +EXPORT_SYMBOL_GPL(nfs_generic_pg_test); /** * nfs_pageio_init - initialise a page io descriptor diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8c1309d852a..29c0ca7fc34 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -634,14 +634,16 @@ _pnfs_return_layout(struct inode *ino) spin_lock(&ino->i_lock); lo = nfsi->layout; - if (!lo || !mark_matching_lsegs_invalid(lo, &tmp_list, NULL)) { + if (!lo) { spin_unlock(&ino->i_lock); - dprintk("%s: no layout segments to return\n", __func__); - goto out; + dprintk("%s: no layout to return\n", __func__); + return status; } stateid = nfsi->layout->plh_stateid; /* Reference matched in nfs4_layoutreturn_release */ get_layout_hdr(lo); + mark_matching_lsegs_invalid(lo, &tmp_list, NULL); + lo->plh_block_lgets++; spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); @@ -650,6 +652,9 @@ _pnfs_return_layout(struct inode *ino) lrp = kzalloc(sizeof(*lrp), GFP_KERNEL); if (unlikely(lrp == NULL)) { status = -ENOMEM; + set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags); + set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags); + put_layout_hdr(lo); goto out; } @@ -887,7 +892,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, ret = get_lseg(lseg); break; } - if (cmp_layout(range, &lseg->pls_range) > 0) + if (lseg->pls_range.offset > range->offset) break; } @@ -1059,23 +1064,36 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, gfp_flags = GFP_NOFS; } - if (pgio->pg_count == prev->wb_bytes) { + if (pgio->pg_lseg == NULL) { + if (pgio->pg_count != prev->wb_bytes) + return true; /* This is first coelesce call for a series of nfs_pages */ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, prev->wb_context, - req_offset(req), + req_offset(prev), pgio->pg_count, access_type, gfp_flags); - return true; + if (pgio->pg_lseg == NULL) + return true; } - if (pgio->pg_lseg && - req_offset(req) > end_offset(pgio->pg_lseg->pls_range.offset, - pgio->pg_lseg->pls_range.length)) - return false; - - return true; + /* + * Test if a nfs_page is fully contained in the pnfs_layout_range. + * Note that this test makes several assumptions: + * - that the previous nfs_page in the struct nfs_pageio_descriptor + * is known to lie within the range. + * - that the nfs_page being tested is known to be contiguous with the + * previous nfs_page. + * - Layout ranges are page aligned, so we only have to test the + * start offset of the request. + * + * Please also note that 'end_offset' is actually the offset of the + * first byte that lies outside the pnfs_layout_range. FIXME? + * + */ + return req_offset(req) < end_offset(pgio->pg_lseg->pls_range.offset, + pgio->pg_lseg->pls_range.length); } EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 48d0a8e4d06..96bf4e6f45b 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -186,6 +186,7 @@ int pnfs_ld_read_done(struct nfs_read_data *); /* pnfs_dev.c */ struct nfs4_deviceid_node { struct hlist_node node; + struct hlist_node tmpnode; const struct pnfs_layoutdriver_type *ld; const struct nfs_client *nfs_client; struct nfs4_deviceid deviceid; diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index c65e133ce9c..f0f8e1e22f6 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -174,6 +174,7 @@ nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, const struct nfs4_deviceid *id) { INIT_HLIST_NODE(&d->node); + INIT_HLIST_NODE(&d->tmpnode); d->ld = ld; d->nfs_client = nfs_client; d->deviceid = *id; @@ -208,6 +209,7 @@ nfs4_insert_deviceid_node(struct nfs4_deviceid_node *new) hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]); spin_unlock(&nfs4_deviceid_lock); + atomic_inc(&new->ref); return new; } @@ -238,24 +240,29 @@ static void _deviceid_purge_client(const struct nfs_client *clp, long hash) { struct nfs4_deviceid_node *d; - struct hlist_node *n, *next; + struct hlist_node *n; HLIST_HEAD(tmp); + spin_lock(&nfs4_deviceid_lock); rcu_read_lock(); hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node) if (d->nfs_client == clp && atomic_read(&d->ref)) { hlist_del_init_rcu(&d->node); - hlist_add_head(&d->node, &tmp); + hlist_add_head(&d->tmpnode, &tmp); } rcu_read_unlock(); + spin_unlock(&nfs4_deviceid_lock); if (hlist_empty(&tmp)) return; synchronize_rcu(); - hlist_for_each_entry_safe(d, n, next, &tmp, node) + while (!hlist_empty(&tmp)) { + d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode); + hlist_del(&d->tmpnode); if (atomic_dec_and_test(&d->ref)) d->ld->free_deviceid_node(d); + } } void @@ -263,8 +270,8 @@ nfs4_deviceid_purge_client(const struct nfs_client *clp) { long h; - spin_lock(&nfs4_deviceid_lock); + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_MDS)) + return; for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++) _deviceid_purge_client(clp, h); - spin_unlock(&nfs4_deviceid_lock); } diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 18b3e8975fe..fbb2a5ef581 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -82,6 +82,7 @@ config NFSD_V4 select NFSD_V3 select FS_POSIX_ACL select SUNRPC_GSS + select CRYPTO help This option enables support in your system's NFS server for version 4 of the NFS protocol (RFC 3530). diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 1f5eae40f34..2b1449dd2f4 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -13,6 +13,7 @@ #include <linux/lockd/lockd.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/gss_api.h> +#include <linux/sunrpc/gss_krb5_enctypes.h> #include "idmap.h" #include "nfsd.h" @@ -189,18 +190,10 @@ static struct file_operations export_features_operations = { .release = single_release, }; -#ifdef CONFIG_SUNRPC_GSS +#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) static int supported_enctypes_show(struct seq_file *m, void *v) { - struct gss_api_mech *k5mech; - - k5mech = gss_mech_get_by_name("krb5"); - if (k5mech == NULL) - goto out; - if (k5mech->gm_upcall_enctypes != NULL) - seq_printf(m, k5mech->gm_upcall_enctypes); - gss_mech_put(k5mech); -out: + seq_printf(m, KRB5_SUPPORTED_ENCTYPES); return 0; } @@ -215,7 +208,7 @@ static struct file_operations supported_enctypes_ops = { .llseek = seq_lseek, .release = single_release, }; -#endif /* CONFIG_SUNRPC_GSS */ +#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ extern int nfsd_pool_stats_open(struct inode *inode, struct file *file); extern int nfsd_pool_stats_release(struct inode *inode, struct file *file); @@ -1427,9 +1420,9 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, -#ifdef CONFIG_SUNRPC_GSS +#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", &supported_enctypes_ops, S_IRUGO}, -#endif /* CONFIG_SUNRPC_GSS */ +#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR}, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index d5718273bb3..fd0acca5370 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -696,7 +696,15 @@ nfsd_access(struct svc_rqst *rqstp, struct svc_fh *fhp, u32 *access, u32 *suppor } #endif /* CONFIG_NFSD_V3 */ +static int nfsd_open_break_lease(struct inode *inode, int access) +{ + unsigned int mode; + if (access & NFSD_MAY_NOT_BREAK_LEASE) + return 0; + mode = (access & NFSD_MAY_WRITE) ? O_WRONLY : O_RDONLY; + return break_lease(inode, mode | O_NONBLOCK); +} /* * Open an existing file or directory. @@ -744,12 +752,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, if (!inode->i_fop) goto out; - /* - * Check to see if there are any leases on this file. - * This may block while leases are broken. - */ - if (!(access & NFSD_MAY_NOT_BREAK_LEASE)) - host_err = break_lease(inode, O_NONBLOCK | ((access & NFSD_MAY_WRITE) ? O_WRONLY : 0)); + host_err = nfsd_open_break_lease(inode, access); if (host_err) /* NOMEM or WOULDBLOCK */ goto out_nfserr; @@ -1660,8 +1663,10 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (!dold->d_inode) goto out_drop_write; host_err = nfsd_break_lease(dold->d_inode); - if (host_err) + if (host_err) { + err = nfserrno(host_err); goto out_drop_write; + } host_err = vfs_link(dold, dirp, dnew); if (!host_err) { err = nfserrno(commit_metadata(ffhp)); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index b954878ad6c..b9b45fc2903 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -801,12 +801,7 @@ out_err: int nilfs_permission(struct inode *inode, int mask, unsigned int flags) { - struct nilfs_root *root; - - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - - root = NILFS_I(inode)->i_root; + struct nilfs_root *root = NILFS_I(inode)->i_root; if ((mask & MAY_WRITE) && root && root->cno != NILFS_CPTREE_CURRENT_CNO) return -EROFS; /* snapshot is not writable */ diff --git a/fs/omfs/file.c b/fs/omfs/file.c index d738a7e493d..2c6d95257a4 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -4,7 +4,6 @@ * Released under GPL v2. */ -#include <linux/version.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/buffer_head.h> diff --git a/fs/proc/base.c b/fs/proc/base.c index 14def991d9d..8a84210ca08 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2169,11 +2169,7 @@ static const struct file_operations proc_fd_operations = { */ static int proc_fd_permission(struct inode *inode, int mask, unsigned int flags) { - int rv; - - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - rv = generic_permission(inode, mask, flags, NULL); + int rv = generic_permission(inode, mask, flags, NULL); if (rv == 0) return 0; if (task_pid(current) == proc_pid(inode)) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index f50133c11c2..d167de365a8 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -304,9 +304,6 @@ static int proc_sys_permission(struct inode *inode, int mask,unsigned int flags) struct ctl_table *table; int error; - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - /* Executable files are not allowed under /proc/sys/ */ if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) return -EACCES; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index e8a62f41b45..d7808969096 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -954,8 +954,6 @@ static int xattr_mount_check(struct super_block *s) int reiserfs_permission(struct inode *inode, int mask, unsigned int flags) { - if (flags & IPERM_FLAG_RCU) - return -ECHILD; /* * We don't do permission checks on the internal objects. * Permissions are determined by the "owning" object. diff --git a/fs/timerfd.c b/fs/timerfd.c index f67acbdda5e..dffeb3795af 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -61,7 +61,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) /* * Called when the clock was set to cancel the timers in the cancel - * list. + * list. This will wake up processes waiting on these timers. The + * wake-up requires ctx->ticks to be non zero, therefore we increment + * it before calling wake_up_locked(). */ void timerfd_clock_was_set(void) { @@ -76,6 +78,7 @@ void timerfd_clock_was_set(void) spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->moffs.tv64 != moffs.tv64) { ctx->moffs.tv64 = KTIME_MAX; + ctx->ticks++; wake_up_locked(&ctx->wqh); } spin_unlock_irqrestore(&ctx->wqh.lock, flags); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 8c892c2d530..529be058202 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2146,6 +2146,7 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, if (IS_ERR(sb)) { err = PTR_ERR(sb); kfree(c); + goto out_close; } if (sb->s_root) { diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index c8637537881..01d2072fb6d 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -490,6 +490,13 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags) args.whichfork = XFS_ATTR_FORK; /* + * we have no control over the attribute names that userspace passes us + * to remove, so we have to allow the name lookup prior to attribute + * removal to fail. + */ + args.op_flags = XFS_DA_OP_OKNOENT; + + /* * Attach the dquots to the inode. */ error = xfs_qm_dqattach(dp, 0); diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index cb9b6d1469f..3631783b2b5 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -253,16 +253,21 @@ xfs_iget_cache_hit( rcu_read_lock(); spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~XFS_INEW; - ip->i_flags |= XFS_IRECLAIMABLE; - __xfs_inode_set_reclaim_tag(pag, ip); + ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); + ASSERT(ip->i_flags & XFS_IRECLAIMABLE); trace_xfs_iget_reclaim_fail(ip); goto out_error; } spin_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM); + + /* + * Clear the per-lifetime state in the inode as we are now + * effectively a new inode and need to return to the initial + * state before reuse occurs. + */ + ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS; ip->i_flags |= XFS_INEW; __xfs_inode_clear_reclaim_tag(mp, pag, ip); inode->i_state = I_NEW; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 3ae6d58e547..964cfea7768 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -384,6 +384,16 @@ static inline void xfs_ifunlock(xfs_inode_t *ip) #define XFS_IDIRTY_RELEASE 0x0040 /* dirty release already seen */ /* + * Per-lifetime flags need to be reset when re-using a reclaimable inode during + * inode lookup. Thi prevents unintended behaviour on the new inode from + * ocurring. + */ +#define XFS_IRECLAIM_RESET_FLAGS \ + (XFS_IRECLAIMABLE | XFS_IRECLAIM | \ + XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \ + XFS_IFILESTREAM); + +/* * Flags for inode locking. * Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield) * 1<<16 - 1<<32-1 -- lockdep annotation (integers) diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index b7a5fe7c52c..619720705bc 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -960,8 +960,11 @@ xfs_release( * be exposed to that problem. */ truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED); - if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) - xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE); + if (truncated) { + xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE); + if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) + xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE); + } } if (ip->i_d.di_nlink == 0) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 2a7cea53ca0..6395692b2e7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -167,7 +167,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ - REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_RAHEAD (1 << __REQ_RAHEAD) diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index b22fb0d3db0..8c7c2de7631 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -169,7 +169,8 @@ extern void blk_trace_shutdown(struct request_queue *); extern int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts); -extern void __trace_note_message(struct blk_trace *, const char *fmt, ...); +extern __attribute__((format(printf, 2, 3))) +void __trace_note_message(struct blk_trace *, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d4646b48dc4..18a1baf31f2 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -188,6 +188,7 @@ struct clocksource { #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; + cycle_t cs_last; cycle_t wd_last; #endif } ____cacheline_aligned; diff --git a/include/linux/device.h b/include/linux/device.h index c66111affca..553fd37b173 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -654,13 +654,13 @@ static inline int device_is_registered(struct device *dev) static inline void device_enable_async_suspend(struct device *dev) { - if (!dev->power.in_suspend) + if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { - if (!dev->power.in_suspend) + if (!dev->power.is_prepared) dev->power.async_suspend = false; } diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 0b0d9c39ed6..7aad1f44086 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -2,8 +2,16 @@ #include <linux/fs.h> #ifdef CONFIG_CGROUP_DEVICE -extern int devcgroup_inode_permission(struct inode *inode, int mask); +extern int __devcgroup_inode_permission(struct inode *inode, int mask); extern int devcgroup_inode_mknod(int mode, dev_t dev); +static inline int devcgroup_inode_permission(struct inode *inode, int mask) +{ + if (likely(!inode->i_rdev)) + return 0; + if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) + return 0; + return __devcgroup_inode_permission(inode, mask); +} #else static inline int devcgroup_inode_permission(struct inode *inode, int mask) { return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c777878f1e..6e73e2e9ae3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -744,7 +744,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned int i_flags; - unsigned int i_state; + unsigned long i_state; #ifdef CONFIG_SECURITY void *i_security; #endif diff --git a/include/linux/input/sh_keysc.h b/include/linux/input/sh_keysc.h index 649dc7f1292..5d253cd9369 100644 --- a/include/linux/input/sh_keysc.h +++ b/include/linux/input/sh_keysc.h @@ -1,7 +1,7 @@ #ifndef __SH_KEYSC_H__ #define __SH_KEYSC_H__ -#define SH_KEYSC_MAXKEYS 49 +#define SH_KEYSC_MAXKEYS 64 struct sh_keysc_info { enum { SH_KEYSC_MODE_1, SH_KEYSC_MODE_2, SH_KEYSC_MODE_3, diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 6c12989839d..f6efed0039e 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -414,6 +414,7 @@ enum TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, + RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS }; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4ecb7b16b27..d087c2e7b2a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1024,7 +1024,6 @@ struct journal_s /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __jbd2_journal_unfile_buffer(struct journal_head *); extern void __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); @@ -1165,7 +1164,6 @@ extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_in */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); -void jbd2_journal_remove_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c928dac6cad..9f7c3ebcbba 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -647,6 +647,13 @@ typedef struct pglist_data { #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) +#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) + +#define node_end_pfn(nid) ({\ + pg_data_t *__pgdat = NODE_DATA(nid);\ + __pgdat->node_start_pfn + __pgdat->node_spanned_pages;\ +}) + #include <linux/memory_hotplug.h> extern struct mutex zonelists_mutex; diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 3a34e80ae92..25311b3bedf 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -92,6 +92,9 @@ extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, struct nfs_page *); extern void nfs_pageio_complete(struct nfs_pageio_descriptor *desc); extern void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t); +extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, + struct nfs_page *prev, + struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern int nfs_set_page_tag_locked(struct nfs_page *req); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5e8444a11ad..00848d86ffb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -158,7 +158,6 @@ struct nfs_seqid; /* nfs41 sessions channel attributes */ struct nfs4_channel_attrs { - u32 headerpadsz; u32 max_rqst_sz; u32 max_resp_sz; u32 max_resp_sz_cached; diff --git a/include/linux/pm.h b/include/linux/pm.h index 3160648ccdd..411e4f4be52 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -425,7 +425,8 @@ struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; unsigned int async_suspend:1; - unsigned int in_suspend:1; /* Owned by the PM core */ + bool is_prepared:1; /* Owned by the PM core */ + bool is_suspended:1; /* Ditto */ spinlock_t lock; #ifdef CONFIG_PM_SLEEP struct list_head entry; diff --git a/include/linux/smp.h b/include/linux/smp.h index 7ad824d510a..8cc38d3bab0 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -85,12 +85,15 @@ int smp_call_function_any(const struct cpumask *mask, * Generic and arch helpers */ #ifdef CONFIG_USE_GENERIC_SMP_HELPERS +void __init call_function_init(void); void generic_smp_call_function_single_interrupt(void); void generic_smp_call_function_interrupt(void); void ipi_call_lock(void); void ipi_call_unlock(void); void ipi_call_lock_irq(void); void ipi_call_unlock_irq(void); +#else +static inline void call_function_init(void) { } #endif /* @@ -134,7 +137,7 @@ static inline void smp_send_reschedule(int cpu) { } #define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) -static inline void init_call_single_data(void) { } +static inline void call_function_init(void) { } static inline int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, diff --git a/include/linux/sunrpc/gss_krb5_enctypes.h b/include/linux/sunrpc/gss_krb5_enctypes.h new file mode 100644 index 00000000000..ec6234eee89 --- /dev/null +++ b/include/linux/sunrpc/gss_krb5_enctypes.h @@ -0,0 +1,4 @@ +/* + * Dumb way to share this static piece of information with nfsd + */ +#define KRB5_SUPPORTED_ENCTYPES "18,17,16,23,3,1,2" diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index f73c482ec9c..fe2d8e6b923 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -84,7 +84,8 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2; + tk_cred_retry : 2, + tk_rebind_retry : 2; }; #define tk_xprt tk_client->cl_xprt diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index c7c42e7acc3..5d4f8e586e3 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -307,6 +307,12 @@ static inline int nf_ct_is_untracked(const struct nf_conn *ct) return test_bit(IPS_UNTRACKED_BIT, &ct->status); } +/* Packet is received from loopback */ +static inline bool nf_is_loopback_packet(const struct sk_buff *skb) +{ + return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK; +} + extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); extern unsigned int nf_conntrack_htable_size; extern unsigned int nf_conntrack_max; diff --git a/include/sound/soc.h b/include/sound/soc.h index f1de3e0c75b..3a4bd3a3c68 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -248,8 +248,7 @@ typedef int (*hw_write_t)(void *,const char* ,int); extern struct snd_ac97_bus_ops soc_ac97_ops; enum snd_soc_control_type { - SND_SOC_CUSTOM = 1, - SND_SOC_I2C, + SND_SOC_I2C = 1, SND_SOC_SPI, }; diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index e09592d2f91..5ce2b2f5f52 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -26,7 +26,7 @@ TRACE_EVENT(ext4_free_inode, __field( umode_t, mode ) __field( uid_t, uid ) __field( gid_t, gid ) - __field( blkcnt_t, blocks ) + __field( __u64, blocks ) ), TP_fast_assign( @@ -40,9 +40,8 @@ TRACE_EVENT(ext4_free_inode, TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->mode, __entry->uid, __entry->gid, - (unsigned long long) __entry->blocks) + (unsigned long) __entry->ino, __entry->mode, + __entry->uid, __entry->gid, __entry->blocks) ); TRACE_EVENT(ext4_request_inode, @@ -178,7 +177,7 @@ TRACE_EVENT(ext4_begin_ordered_truncate, TP_printk("dev %d,%d ino %lu new_size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (long long) __entry->new_size) + __entry->new_size) ); DECLARE_EVENT_CLASS(ext4__write_begin, @@ -204,7 +203,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu pos %llu len %u flags %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->flags) @@ -248,7 +247,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, __entry->copied = copied; ), - TP_printk("dev %d,%d ino %lu pos %llu len %u copied %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u copied %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->copied) @@ -286,29 +285,6 @@ DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_ARGS(inode, pos, len, copied) ); -TRACE_EVENT(ext4_writepage, - TP_PROTO(struct inode *inode, struct page *page), - - TP_ARGS(inode, page), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( pgoff_t, index ) - - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->index = page->index; - ), - - TP_printk("dev %d,%d ino %lu page_index %lu", - MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, __entry->index) -); - TRACE_EVENT(ext4_da_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), @@ -341,7 +317,7 @@ TRACE_EVENT(ext4_da_writepages, ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " - "range_start %llu range_end %llu sync_mode %d" + "range_start %lld range_end %lld sync_mode %d" "for_kupdate %d range_cyclic %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, @@ -449,7 +425,14 @@ DECLARE_EVENT_CLASS(ext4__page_op, TP_printk("dev %d,%d ino %lu page_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->index) + (unsigned long) __entry->index) +); + +DEFINE_EVENT(ext4__page_op, ext4_writepage, + + TP_PROTO(struct page *page), + + TP_ARGS(page) ); DEFINE_EVENT(ext4__page_op, ext4_readpage, @@ -489,7 +472,7 @@ TRACE_EVENT(ext4_invalidatepage, TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->index, __entry->offset) + (unsigned long) __entry->index, __entry->offset) ); TRACE_EVENT(ext4_discard_blocks, @@ -562,12 +545,10 @@ DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, ); TRACE_EVENT(ext4_mb_release_inode_pa, - TP_PROTO(struct super_block *sb, - struct inode *inode, - struct ext4_prealloc_space *pa, + TP_PROTO(struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), - TP_ARGS(sb, inode, pa, block, count), + TP_ARGS(pa, block, count), TP_STRUCT__entry( __field( dev_t, dev ) @@ -578,8 +559,8 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ), TP_fast_assign( - __entry->dev = sb->s_dev; - __entry->ino = inode->i_ino; + __entry->dev = pa->pa_inode->i_sb->s_dev; + __entry->ino = pa->pa_inode->i_ino; __entry->block = block; __entry->count = count; ), @@ -591,10 +572,9 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ); TRACE_EVENT(ext4_mb_release_group_pa, - TP_PROTO(struct super_block *sb, - struct ext4_prealloc_space *pa), + TP_PROTO(struct ext4_prealloc_space *pa), - TP_ARGS(sb, pa), + TP_ARGS(pa), TP_STRUCT__entry( __field( dev_t, dev ) @@ -604,7 +584,7 @@ TRACE_EVENT(ext4_mb_release_group_pa, ), TP_fast_assign( - __entry->dev = sb->s_dev; + __entry->dev = pa->pa_inode->i_sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), @@ -666,10 +646,10 @@ TRACE_EVENT(ext4_request_blocks, __field( ino_t, ino ) __field( unsigned int, flags ) __field( unsigned int, len ) - __field( __u64, logical ) + __field( __u32, logical ) + __field( __u32, lleft ) + __field( __u32, lright ) __field( __u64, goal ) - __field( __u64, lleft ) - __field( __u64, lright ) __field( __u64, pleft ) __field( __u64, pright ) ), @@ -687,17 +667,13 @@ TRACE_EVENT(ext4_request_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu " - "lleft %llu lright %llu pleft %llu pright %llu ", + TP_printk("dev %d,%d ino %lu flags %u len %u lblk %u goal %llu " + "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->flags, __entry->len, - (unsigned long long) __entry->logical, - (unsigned long long) __entry->goal, - (unsigned long long) __entry->lleft, - (unsigned long long) __entry->lright, - (unsigned long long) __entry->pleft, - (unsigned long long) __entry->pright) + (unsigned long) __entry->ino, __entry->flags, + __entry->len, __entry->logical, __entry->goal, + __entry->lleft, __entry->lright, __entry->pleft, + __entry->pright) ); TRACE_EVENT(ext4_allocate_blocks, @@ -711,10 +687,10 @@ TRACE_EVENT(ext4_allocate_blocks, __field( __u64, block ) __field( unsigned int, flags ) __field( unsigned int, len ) - __field( __u64, logical ) + __field( __u32, logical ) + __field( __u32, lleft ) + __field( __u32, lright ) __field( __u64, goal ) - __field( __u64, lleft ) - __field( __u64, lright ) __field( __u64, pleft ) __field( __u64, pright ) ), @@ -733,17 +709,13 @@ TRACE_EVENT(ext4_allocate_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu " - "goal %llu lleft %llu lright %llu pleft %llu pright %llu", + TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %u " + "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->flags, __entry->len, __entry->block, - (unsigned long long) __entry->logical, - (unsigned long long) __entry->goal, - (unsigned long long) __entry->lleft, - (unsigned long long) __entry->lright, - (unsigned long long) __entry->pleft, - (unsigned long long) __entry->pright) + (unsigned long) __entry->ino, __entry->flags, + __entry->len, __entry->block, __entry->logical, + __entry->goal, __entry->lleft, __entry->lright, + __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_free_blocks, @@ -755,10 +727,10 @@ TRACE_EVENT(ext4_free_blocks, TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) - __field( umode_t, mode ) + __field( umode_t, mode ) __field( __u64, block ) __field( unsigned long, count ) - __field( int, flags ) + __field( int, flags ) ), TP_fast_assign( @@ -798,7 +770,7 @@ TRACE_EVENT(ext4_sync_file_enter, __entry->parent = dentry->d_parent->d_inode->i_ino; ), - TP_printk("dev %d,%d ino %ld parent %ld datasync %d ", + TP_printk("dev %d,%d ino %lu parent %lu datasync %d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) @@ -821,7 +793,7 @@ TRACE_EVENT(ext4_sync_file_exit, __entry->dev = inode->i_sb->s_dev; ), - TP_printk("dev %d,%d ino %ld ret %d", + TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) @@ -1005,7 +977,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, __entry->result_len = len; ), - TP_printk("dev %d,%d inode %lu extent %u/%d/%u ", + TP_printk("dev %d,%d inode %lu extent %u/%d/%d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, @@ -1093,7 +1065,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, "allocated_meta_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->mode, (unsigned long long) __entry->i_blocks, + __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) ); @@ -1127,7 +1099,7 @@ TRACE_EVENT(ext4_da_reserve_space, "reserved_data_blocks %d reserved_meta_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->mode, (unsigned long long) __entry->i_blocks, + __entry->mode, __entry->i_blocks, __entry->md_needed, __entry->reserved_data_blocks, __entry->reserved_meta_blocks) ); @@ -1164,7 +1136,7 @@ TRACE_EVENT(ext4_da_release_space, "allocated_meta_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->mode, (unsigned long long) __entry->i_blocks, + __entry->mode, __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks, __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) ); @@ -1239,14 +1211,15 @@ TRACE_EVENT(ext4_direct_IO_enter, __entry->rw = rw; ), - TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lu rw %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, __entry->len, __entry->rw) + __entry->pos, __entry->len, __entry->rw) ); TRACE_EVENT(ext4_direct_IO_exit, - TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw, int ret), + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, + int rw, int ret), TP_ARGS(inode, offset, len, rw, ret), @@ -1268,10 +1241,10 @@ TRACE_EVENT(ext4_direct_IO_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d ret %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lu rw %d ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, __entry->len, + __entry->pos, __entry->len, __entry->rw, __entry->ret) ); @@ -1296,15 +1269,15 @@ TRACE_EVENT(ext4_fallocate_enter, __entry->mode = mode; ), - TP_printk("dev %d,%d ino %ld pos %llu len %llu mode %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, - (unsigned long long) __entry->len, __entry->mode) + (unsigned long) __entry->ino, __entry->pos, + __entry->len, __entry->mode) ); TRACE_EVENT(ext4_fallocate_exit, - TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), + TP_PROTO(struct inode *inode, loff_t offset, + unsigned int max_blocks, int ret), TP_ARGS(inode, offset, max_blocks, ret), @@ -1312,7 +1285,7 @@ TRACE_EVENT(ext4_fallocate_exit, __field( ino_t, ino ) __field( dev_t, dev ) __field( loff_t, pos ) - __field( unsigned, blocks ) + __field( unsigned int, blocks ) __field( int, ret ) ), @@ -1324,10 +1297,10 @@ TRACE_EVENT(ext4_fallocate_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d ino %ld pos %llu blocks %d ret %d", + TP_printk("dev %d,%d ino %lu pos %lld blocks %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, __entry->blocks, + __entry->pos, __entry->blocks, __entry->ret) ); @@ -1350,7 +1323,7 @@ TRACE_EVENT(ext4_unlink_enter, __entry->dev = dentry->d_inode->i_sb->s_dev; ), - TP_printk("dev %d,%d ino %ld size %lld parent %ld", + TP_printk("dev %d,%d ino %lu size %lld parent %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->size, (unsigned long) __entry->parent) @@ -1373,7 +1346,7 @@ TRACE_EVENT(ext4_unlink_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d ino %ld ret %d", + TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) @@ -1387,7 +1360,7 @@ DECLARE_EVENT_CLASS(ext4__truncate, TP_STRUCT__entry( __field( ino_t, ino ) __field( dev_t, dev ) - __field( blkcnt_t, blocks ) + __field( __u64, blocks ) ), TP_fast_assign( @@ -1396,9 +1369,9 @@ DECLARE_EVENT_CLASS(ext4__truncate, __entry->blocks = inode->i_blocks; ), - TP_printk("dev %d,%d ino %lu blocks %lu", + TP_printk("dev %d,%d ino %lu blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, (unsigned long) __entry->blocks) + (unsigned long) __entry->ino, __entry->blocks) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, @@ -1417,7 +1390,7 @@ DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - unsigned len, unsigned flags), + unsigned int len, unsigned int flags), TP_ARGS(inode, lblk, len, flags), @@ -1425,8 +1398,8 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter, __field( ino_t, ino ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) - __field( unsigned, len ) - __field( unsigned, flags ) + __field( unsigned int, len ) + __field( unsigned int, flags ) ), TP_fast_assign( @@ -1440,7 +1413,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned) __entry->lblk, __entry->len, __entry->flags) + __entry->lblk, __entry->len, __entry->flags) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, @@ -1459,7 +1432,7 @@ DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - ext4_fsblk_t pblk, unsigned len, int ret), + ext4_fsblk_t pblk, unsigned int len, int ret), TP_ARGS(inode, lblk, pblk, len, ret), @@ -1468,7 +1441,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit, __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) - __field( unsigned, len ) + __field( unsigned int, len ) __field( int, ret ) ), @@ -1484,7 +1457,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, + __entry->lblk, __entry->pblk, __entry->len, __entry->ret) ); @@ -1524,7 +1497,7 @@ TRACE_EVENT(ext4_ext_load_extent, TP_printk("dev %d,%d ino %lu lblk %u pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned) __entry->lblk, (unsigned long long) __entry->pblk) + __entry->lblk, __entry->pblk) ); TRACE_EVENT(ext4_load_inode, diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h index ae045ca7d35..1c09820df58 100644 --- a/include/trace/events/irq.h +++ b/include/trace/events/irq.h @@ -20,7 +20,8 @@ struct softirq_action; softirq_name(BLOCK_IOPOLL), \ softirq_name(TASKLET), \ softirq_name(SCHED), \ - softirq_name(HRTIMER)) + softirq_name(HRTIMER), \ + softirq_name(RCU)) /** * irq_handler_entry - called immediately before the irq action handler diff --git a/init/calibrate.c b/init/calibrate.c index 2568d22a304..aae2f40fea4 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -245,30 +245,32 @@ recalibrate: void __cpuinit calibrate_delay(void) { + unsigned long lpj; static bool printed; if (preset_lpj) { - loops_per_jiffy = preset_lpj; + lpj = preset_lpj; if (!printed) pr_info("Calibrating delay loop (skipped) " "preset value.. "); } else if ((!printed) && lpj_fine) { - loops_per_jiffy = lpj_fine; + lpj = lpj_fine; pr_info("Calibrating delay loop (skipped), " "value calculated using timer frequency.. "); - } else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) { + } else if ((lpj = calibrate_delay_direct()) != 0) { if (!printed) pr_info("Calibrating delay using timer " "specific routine.. "); } else { if (!printed) pr_info("Calibrating delay loop... "); - loops_per_jiffy = calibrate_delay_converge(); + lpj = calibrate_delay_converge(); } if (!printed) pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n", - loops_per_jiffy/(500000/HZ), - (loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy); + lpj/(500000/HZ), + (lpj/(5000/HZ)) % 100, lpj); + loops_per_jiffy = lpj; printed = true; } diff --git a/init/main.c b/init/main.c index cafba67c13b..d7211faed2a 100644 --- a/init/main.c +++ b/init/main.c @@ -542,6 +542,7 @@ asmlinkage void __init start_kernel(void) timekeeping_init(); time_init(); profile_init(); + call_function_init(); if (!irqs_disabled()) printk(KERN_CRIT "start_kernel(): bug: interrupts were " "enabled early\n"); diff --git a/kernel/power/user.c b/kernel/power/user.c index 7d02d33be69..42ddbc6f0de 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -113,8 +113,10 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) pm_notifier_call_chain(PM_POST_RESTORE); } - if (error) + if (error) { + free_basic_memory_bitmaps(); atomic_inc(&snapshot_device_available); + } data->frozen = 0; data->ready = 0; data->platform_support = 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 89419ff92e9..7e59ffb3d0b 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -87,6 +87,8 @@ static struct rcu_state *rcu_state; int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +#ifdef CONFIG_RCU_BOOST + /* * Control variables for per-CPU and per-rcu_node kthreads. These * handle all flavors of RCU. @@ -98,8 +100,11 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); static char rcu_kthreads_spawnable; +#endif /* #ifdef CONFIG_RCU_BOOST */ + static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); -static void invoke_rcu_cpu_kthread(void); +static void invoke_rcu_core(void); +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); #define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */ @@ -1088,14 +1093,8 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) int need_report = 0; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp; - struct task_struct *t; - /* Stop the CPU's kthread. */ - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t != NULL) { - per_cpu(rcu_cpu_kthread_task, cpu) = NULL; - kthread_stop(t); - } + rcu_stop_cpu_kthread(cpu); /* Exclude any attempts to start a new grace period. */ raw_spin_lock_irqsave(&rsp->onofflock, flags); @@ -1231,7 +1230,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Re-raise the RCU softirq if there are callbacks remaining. */ if (cpu_has_callbacks_ready_to_invoke(rdp)) - invoke_rcu_cpu_kthread(); + invoke_rcu_core(); } /* @@ -1277,7 +1276,7 @@ void rcu_check_callbacks(int cpu, int user) } rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) - invoke_rcu_cpu_kthread(); + invoke_rcu_core(); } #ifdef CONFIG_SMP @@ -1442,13 +1441,14 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) } /* If there are callbacks ready, invoke them. */ - rcu_do_batch(rsp, rdp); + if (cpu_has_callbacks_ready_to_invoke(rdp)) + invoke_rcu_callbacks(rsp, rdp); } /* * Do softirq processing for the current CPU. */ -static void rcu_process_callbacks(void) +static void rcu_process_callbacks(struct softirq_action *unused) { __rcu_process_callbacks(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); @@ -1465,342 +1465,20 @@ static void rcu_process_callbacks(void) * the current CPU with interrupts disabled, the rcu_cpu_kthread_task * cannot disappear out from under us. */ -static void invoke_rcu_cpu_kthread(void) -{ - unsigned long flags; - - local_irq_save(flags); - __this_cpu_write(rcu_cpu_has_work, 1); - if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) { - local_irq_restore(flags); - return; - } - wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); - local_irq_restore(flags); -} - -/* - * Wake up the specified per-rcu_node-structure kthread. - * Because the per-rcu_node kthreads are immortal, we don't need - * to do anything to keep them alive. - */ -static void invoke_rcu_node_kthread(struct rcu_node *rnp) -{ - struct task_struct *t; - - t = rnp->node_kthread_task; - if (t != NULL) - wake_up_process(t); -} - -/* - * Set the specified CPU's kthread to run RT or not, as specified by - * the to_rt argument. The CPU-hotplug locks are held, so the task - * is not going away. - */ -static void rcu_cpu_kthread_setrt(int cpu, int to_rt) -{ - int policy; - struct sched_param sp; - struct task_struct *t; - - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t == NULL) - return; - if (to_rt) { - policy = SCHED_FIFO; - sp.sched_priority = RCU_KTHREAD_PRIO; - } else { - policy = SCHED_NORMAL; - sp.sched_priority = 0; - } - sched_setscheduler_nocheck(t, policy, &sp); -} - -/* - * Timer handler to initiate the waking up of per-CPU kthreads that - * have yielded the CPU due to excess numbers of RCU callbacks. - * We wake up the per-rcu_node kthread, which in turn will wake up - * the booster kthread. - */ -static void rcu_cpu_kthread_timer(unsigned long arg) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); - struct rcu_node *rnp = rdp->mynode; - - atomic_or(rdp->grpmask, &rnp->wakemask); - invoke_rcu_node_kthread(rnp); -} - -/* - * Drop to non-real-time priority and yield, but only after posting a - * timer that will cause us to regain our real-time priority if we - * remain preempted. Either way, we restore our real-time priority - * before returning. - */ -static void rcu_yield(void (*f)(unsigned long), unsigned long arg) -{ - struct sched_param sp; - struct timer_list yield_timer; - - setup_timer_on_stack(&yield_timer, f, arg); - mod_timer(&yield_timer, jiffies + 2); - sp.sched_priority = 0; - sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); - set_user_nice(current, 19); - schedule(); - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); - del_timer(&yield_timer); -} - -/* - * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. - * This can happen while the corresponding CPU is either coming online - * or going offline. We cannot wait until the CPU is fully online - * before starting the kthread, because the various notifier functions - * can wait for RCU grace periods. So we park rcu_cpu_kthread() until - * the corresponding CPU is online. - * - * Return 1 if the kthread needs to stop, 0 otherwise. - * - * Caller must disable bh. This function can momentarily enable it. - */ -static int rcu_cpu_kthread_should_stop(int cpu) -{ - while (cpu_is_offline(cpu) || - !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || - smp_processor_id() != cpu) { - if (kthread_should_stop()) - return 1; - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; - per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); - local_bh_enable(); - schedule_timeout_uninterruptible(1); - if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - local_bh_disable(); - } - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - return 0; -} - -/* - * Per-CPU kernel thread that invokes RCU callbacks. This replaces the - * earlier RCU softirq. - */ -static int rcu_cpu_kthread(void *arg) -{ - int cpu = (int)(long)arg; - unsigned long flags; - int spincnt = 0; - unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); - char work; - char *workp = &per_cpu(rcu_cpu_has_work, cpu); - - for (;;) { - *statusp = RCU_KTHREAD_WAITING; - rcu_wait(*workp != 0 || kthread_should_stop()); - local_bh_disable(); - if (rcu_cpu_kthread_should_stop(cpu)) { - local_bh_enable(); - break; - } - *statusp = RCU_KTHREAD_RUNNING; - per_cpu(rcu_cpu_kthread_loops, cpu)++; - local_irq_save(flags); - work = *workp; - *workp = 0; - local_irq_restore(flags); - if (work) - rcu_process_callbacks(); - local_bh_enable(); - if (*workp != 0) - spincnt++; - else - spincnt = 0; - if (spincnt > 10) { - *statusp = RCU_KTHREAD_YIELDING; - rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); - spincnt = 0; - } - } - *statusp = RCU_KTHREAD_STOPPED; - return 0; -} - -/* - * Spawn a per-CPU kthread, setting up affinity and priority. - * Because the CPU hotplug lock is held, no other CPU will be attempting - * to manipulate rcu_cpu_kthread_task. There might be another CPU - * attempting to access it during boot, but the locking in kthread_bind() - * will enforce sufficient ordering. - */ -static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { - struct sched_param sp; - struct task_struct *t; - - if (!rcu_kthreads_spawnable || - per_cpu(rcu_cpu_kthread_task, cpu) != NULL) - return 0; - t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); - if (IS_ERR(t)) - return PTR_ERR(t); - kthread_bind(t, cpu); - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); - per_cpu(rcu_cpu_kthread_task, cpu) = t; - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - return 0; -} - -/* - * Per-rcu_node kthread, which is in charge of waking up the per-CPU - * kthreads when needed. We ignore requests to wake up kthreads - * for offline CPUs, which is OK because force_quiescent_state() - * takes care of this case. - */ -static int rcu_node_kthread(void *arg) -{ - int cpu; - unsigned long flags; - unsigned long mask; - struct rcu_node *rnp = (struct rcu_node *)arg; - struct sched_param sp; - struct task_struct *t; - - for (;;) { - rnp->node_kthread_status = RCU_KTHREAD_WAITING; - rcu_wait(atomic_read(&rnp->wakemask) != 0); - rnp->node_kthread_status = RCU_KTHREAD_RUNNING; - raw_spin_lock_irqsave(&rnp->lock, flags); - mask = atomic_xchg(&rnp->wakemask, 0); - rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { - if ((mask & 0x1) == 0) - continue; - preempt_disable(); - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (!cpu_online(cpu) || t == NULL) { - preempt_enable(); - continue; - } - per_cpu(rcu_cpu_has_work, cpu) = 1; - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - preempt_enable(); - } - } - /* NOTREACHED */ - rnp->node_kthread_status = RCU_KTHREAD_STOPPED; - return 0; -} - -/* - * Set the per-rcu_node kthread's affinity to cover all CPUs that are - * served by the rcu_node in question. The CPU hotplug lock is still - * held, so the value of rnp->qsmaskinit will be stable. - * - * We don't include outgoingcpu in the affinity set, use -1 if there is - * no outgoing CPU. If there are no CPUs left in the affinity set, - * this function allows the kthread to execute on any CPU. - */ -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) -{ - cpumask_var_t cm; - int cpu; - unsigned long mask = rnp->qsmaskinit; - - if (rnp->node_kthread_task == NULL) - return; - if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + if (likely(!rsp->boost)) { + rcu_do_batch(rsp, rdp); return; - cpumask_clear(cm); - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) - if ((mask & 0x1) && cpu != outgoingcpu) - cpumask_set_cpu(cpu, cm); - if (cpumask_weight(cm) == 0) { - cpumask_setall(cm); - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) - cpumask_clear_cpu(cpu, cm); - WARN_ON_ONCE(cpumask_weight(cm) == 0); } - set_cpus_allowed_ptr(rnp->node_kthread_task, cm); - rcu_boost_kthread_setaffinity(rnp, cm); - free_cpumask_var(cm); + invoke_rcu_callbacks_kthread(); } -/* - * Spawn a per-rcu_node kthread, setting priority and affinity. - * Called during boot before online/offline can happen, or, if - * during runtime, with the main CPU-hotplug locks held. So only - * one of these can be executing at a time. - */ -static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, - struct rcu_node *rnp) +static void invoke_rcu_core(void) { - unsigned long flags; - int rnp_index = rnp - &rsp->node[0]; - struct sched_param sp; - struct task_struct *t; - - if (!rcu_kthreads_spawnable || - rnp->qsmaskinit == 0) - return 0; - if (rnp->node_kthread_task == NULL) { - t = kthread_create(rcu_node_kthread, (void *)rnp, - "rcun%d", rnp_index); - if (IS_ERR(t)) - return PTR_ERR(t); - raw_spin_lock_irqsave(&rnp->lock, flags); - rnp->node_kthread_task = t; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - sp.sched_priority = 99; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - } - return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); + raise_softirq(RCU_SOFTIRQ); } -static void rcu_wake_one_boost_kthread(struct rcu_node *rnp); - -/* - * Spawn all kthreads -- called as soon as the scheduler is running. - */ -static int __init rcu_spawn_kthreads(void) -{ - int cpu; - struct rcu_node *rnp; - struct task_struct *t; - - rcu_kthreads_spawnable = 1; - for_each_possible_cpu(cpu) { - per_cpu(rcu_cpu_has_work, cpu) = 0; - if (cpu_online(cpu)) { - (void)rcu_spawn_one_cpu_kthread(cpu); - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t) - wake_up_process(t); - } - } - rnp = rcu_get_root(rcu_state); - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - if (rnp->node_kthread_task) - wake_up_process(rnp->node_kthread_task); - if (NUM_RCU_NODES > 1) { - rcu_for_each_leaf_node(rcu_state, rnp) { - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - t = rnp->node_kthread_task; - if (t) - wake_up_process(t); - rcu_wake_one_boost_kthread(rnp); - } - } - return 0; -} -early_initcall(rcu_spawn_kthreads); - static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp) @@ -2207,44 +1885,6 @@ static void __cpuinit rcu_prepare_cpu(int cpu) rcu_preempt_init_percpu_data(cpu); } -static void __cpuinit rcu_prepare_kthreads(int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); - struct rcu_node *rnp = rdp->mynode; - - /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ - if (rcu_kthreads_spawnable) { - (void)rcu_spawn_one_cpu_kthread(cpu); - if (rnp->node_kthread_task == NULL) - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - } -} - -/* - * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state, - * but the RCU threads are woken on demand, and if demand is low this - * could be a while triggering the hung task watchdog. - * - * In order to avoid this, poke all tasks once the CPU is fully - * up and running. - */ -static void __cpuinit rcu_online_kthreads(int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); - struct rcu_node *rnp = rdp->mynode; - struct task_struct *t; - - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t) - wake_up_process(t); - - t = rnp->node_kthread_task; - if (t) - wake_up_process(t); - - rcu_wake_one_boost_kthread(rnp); -} - /* * Handle CPU online/offline notification events. */ @@ -2262,7 +1902,6 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, rcu_prepare_kthreads(cpu); break; case CPU_ONLINE: - rcu_online_kthreads(cpu); case CPU_DOWN_FAILED: rcu_node_kthread_setaffinity(rnp, -1); rcu_cpu_kthread_setrt(cpu, 1); @@ -2410,6 +2049,7 @@ void __init rcu_init(void) rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* * We don't need protection against CPU-hotplug here because diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 7b9a08b4aae..01b2ccda26f 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -369,6 +369,7 @@ struct rcu_state { /* period because */ /* force_quiescent_state() */ /* was running. */ + u8 boost; /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ @@ -426,6 +427,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); +static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static void rcu_print_task_stall(struct rcu_node *rnp); @@ -450,11 +452,19 @@ static void rcu_preempt_send_cbs_to_online(void); static void __init __rcu_init_preempt(void); static void rcu_needs_cpu_flush(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +static void invoke_rcu_callbacks_kthread(void); +#ifdef CONFIG_RCU_BOOST +static void rcu_preempt_do_callbacks(void); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, cpumask_var_t cm); -static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct rcu_node *rnp, int rnp_index); +static void invoke_rcu_node_kthread(struct rcu_node *rnp); +static void rcu_yield(void (*f)(unsigned long), unsigned long arg); +#endif /* #ifdef CONFIG_RCU_BOOST */ +static void rcu_cpu_kthread_setrt(int cpu, int to_rt); +static void __cpuinit rcu_prepare_kthreads(int cpu); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index c8bff3099a8..14dc7dd0090 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -602,6 +602,15 @@ static void rcu_preempt_process_callbacks(void) &__get_cpu_var(rcu_preempt_data)); } +#ifdef CONFIG_RCU_BOOST + +static void rcu_preempt_do_callbacks(void) +{ + rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data)); +} + +#endif /* #ifdef CONFIG_RCU_BOOST */ + /* * Queue a preemptible-RCU callback for invocation after a grace period. */ @@ -1249,6 +1258,23 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) } /* + * Wake up the per-CPU kthread to invoke RCU callbacks. + */ +static void invoke_rcu_callbacks_kthread(void) +{ + unsigned long flags; + + local_irq_save(flags); + __this_cpu_write(rcu_cpu_has_work, 1); + if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) { + local_irq_restore(flags); + return; + } + wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); + local_irq_restore(flags); +} + +/* * Set the affinity of the boost kthread. The CPU-hotplug locks are * held, so no one should be messing with the existence of the boost * kthread. @@ -1288,6 +1314,7 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, if (&rcu_preempt_state != rsp) return 0; + rsp->boost = 1; if (rnp->boost_kthread_task != NULL) return 0; t = kthread_create(rcu_boost_kthread, (void *)rnp, @@ -1299,13 +1326,372 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, raw_spin_unlock_irqrestore(&rnp->lock, flags); sp.sched_priority = RCU_KTHREAD_PRIO; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ return 0; } -static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp) +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Stop the RCU's per-CPU kthread when its CPU goes offline,. + */ +static void rcu_stop_cpu_kthread(int cpu) { - if (rnp->boost_kthread_task) - wake_up_process(rnp->boost_kthread_task); + struct task_struct *t; + + /* Stop the CPU's kthread. */ + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t != NULL) { + per_cpu(rcu_cpu_kthread_task, cpu) = NULL; + kthread_stop(t); + } +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_kthread_do_work(void) +{ + rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); + rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); + rcu_preempt_do_callbacks(); +} + +/* + * Wake up the specified per-rcu_node-structure kthread. + * Because the per-rcu_node kthreads are immortal, we don't need + * to do anything to keep them alive. + */ +static void invoke_rcu_node_kthread(struct rcu_node *rnp) +{ + struct task_struct *t; + + t = rnp->node_kthread_task; + if (t != NULL) + wake_up_process(t); +} + +/* + * Set the specified CPU's kthread to run RT or not, as specified by + * the to_rt argument. The CPU-hotplug locks are held, so the task + * is not going away. + */ +static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +{ + int policy; + struct sched_param sp; + struct task_struct *t; + + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t == NULL) + return; + if (to_rt) { + policy = SCHED_FIFO; + sp.sched_priority = RCU_KTHREAD_PRIO; + } else { + policy = SCHED_NORMAL; + sp.sched_priority = 0; + } + sched_setscheduler_nocheck(t, policy, &sp); +} + +/* + * Timer handler to initiate the waking up of per-CPU kthreads that + * have yielded the CPU due to excess numbers of RCU callbacks. + * We wake up the per-rcu_node kthread, which in turn will wake up + * the booster kthread. + */ +static void rcu_cpu_kthread_timer(unsigned long arg) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); + struct rcu_node *rnp = rdp->mynode; + + atomic_or(rdp->grpmask, &rnp->wakemask); + invoke_rcu_node_kthread(rnp); +} + +/* + * Drop to non-real-time priority and yield, but only after posting a + * timer that will cause us to regain our real-time priority if we + * remain preempted. Either way, we restore our real-time priority + * before returning. + */ +static void rcu_yield(void (*f)(unsigned long), unsigned long arg) +{ + struct sched_param sp; + struct timer_list yield_timer; + + setup_timer_on_stack(&yield_timer, f, arg); + mod_timer(&yield_timer, jiffies + 2); + sp.sched_priority = 0; + sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); + set_user_nice(current, 19); + schedule(); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); + del_timer(&yield_timer); +} + +/* + * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. + * This can happen while the corresponding CPU is either coming online + * or going offline. We cannot wait until the CPU is fully online + * before starting the kthread, because the various notifier functions + * can wait for RCU grace periods. So we park rcu_cpu_kthread() until + * the corresponding CPU is online. + * + * Return 1 if the kthread needs to stop, 0 otherwise. + * + * Caller must disable bh. This function can momentarily enable it. + */ +static int rcu_cpu_kthread_should_stop(int cpu) +{ + while (cpu_is_offline(cpu) || + !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || + smp_processor_id() != cpu) { + if (kthread_should_stop()) + return 1; + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; + per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); + local_bh_enable(); + schedule_timeout_uninterruptible(1); + if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) + set_cpus_allowed_ptr(current, cpumask_of(cpu)); + local_bh_disable(); + } + per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; + return 0; +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * earlier RCU softirq. + */ +static int rcu_cpu_kthread(void *arg) +{ + int cpu = (int)(long)arg; + unsigned long flags; + int spincnt = 0; + unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); + char work; + char *workp = &per_cpu(rcu_cpu_has_work, cpu); + + for (;;) { + *statusp = RCU_KTHREAD_WAITING; + rcu_wait(*workp != 0 || kthread_should_stop()); + local_bh_disable(); + if (rcu_cpu_kthread_should_stop(cpu)) { + local_bh_enable(); + break; + } + *statusp = RCU_KTHREAD_RUNNING; + per_cpu(rcu_cpu_kthread_loops, cpu)++; + local_irq_save(flags); + work = *workp; + *workp = 0; + local_irq_restore(flags); + if (work) + rcu_kthread_do_work(); + local_bh_enable(); + if (*workp != 0) + spincnt++; + else + spincnt = 0; + if (spincnt > 10) { + *statusp = RCU_KTHREAD_YIELDING; + rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); + spincnt = 0; + } + } + *statusp = RCU_KTHREAD_STOPPED; + return 0; +} + +/* + * Spawn a per-CPU kthread, setting up affinity and priority. + * Because the CPU hotplug lock is held, no other CPU will be attempting + * to manipulate rcu_cpu_kthread_task. There might be another CPU + * attempting to access it during boot, but the locking in kthread_bind() + * will enforce sufficient ordering. + * + * Please note that we cannot simply refuse to wake up the per-CPU + * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state, + * which can result in softlockup complaints if the task ends up being + * idle for more than a couple of minutes. + * + * However, please note also that we cannot bind the per-CPU kthread to its + * CPU until that CPU is fully online. We also cannot wait until the + * CPU is fully online before we create its per-CPU kthread, as this would + * deadlock the system when CPU notifiers tried waiting for grace + * periods. So we bind the per-CPU kthread to its CPU only if the CPU + * is online. If its CPU is not yet fully online, then the code in + * rcu_cpu_kthread() will wait until it is fully online, and then do + * the binding. + */ +static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) +{ + struct sched_param sp; + struct task_struct *t; + + if (!rcu_kthreads_spawnable || + per_cpu(rcu_cpu_kthread_task, cpu) != NULL) + return 0; + t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); + if (IS_ERR(t)) + return PTR_ERR(t); + if (cpu_online(cpu)) + kthread_bind(t, cpu); + per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; + WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + per_cpu(rcu_cpu_kthread_task, cpu) = t; + wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */ + return 0; +} + +/* + * Per-rcu_node kthread, which is in charge of waking up the per-CPU + * kthreads when needed. We ignore requests to wake up kthreads + * for offline CPUs, which is OK because force_quiescent_state() + * takes care of this case. + */ +static int rcu_node_kthread(void *arg) +{ + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp = (struct rcu_node *)arg; + struct sched_param sp; + struct task_struct *t; + + for (;;) { + rnp->node_kthread_status = RCU_KTHREAD_WAITING; + rcu_wait(atomic_read(&rnp->wakemask) != 0); + rnp->node_kthread_status = RCU_KTHREAD_RUNNING; + raw_spin_lock_irqsave(&rnp->lock, flags); + mask = atomic_xchg(&rnp->wakemask, 0); + rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { + if ((mask & 0x1) == 0) + continue; + preempt_disable(); + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (!cpu_online(cpu) || t == NULL) { + preempt_enable(); + continue; + } + per_cpu(rcu_cpu_has_work, cpu) = 1; + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + preempt_enable(); + } + } + /* NOTREACHED */ + rnp->node_kthread_status = RCU_KTHREAD_STOPPED; + return 0; +} + +/* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still + * held, so the value of rnp->qsmaskinit will be stable. + * + * We don't include outgoingcpu in the affinity set, use -1 if there is + * no outgoing CPU. If there are no CPUs left in the affinity set, + * this function allows the kthread to execute on any CPU. + */ +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ + cpumask_var_t cm; + int cpu; + unsigned long mask = rnp->qsmaskinit; + + if (rnp->node_kthread_task == NULL) + return; + if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + return; + cpumask_clear(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) + if ((mask & 0x1) && cpu != outgoingcpu) + cpumask_set_cpu(cpu, cm); + if (cpumask_weight(cm) == 0) { + cpumask_setall(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) + cpumask_clear_cpu(cpu, cm); + WARN_ON_ONCE(cpumask_weight(cm) == 0); + } + set_cpus_allowed_ptr(rnp->node_kthread_task, cm); + rcu_boost_kthread_setaffinity(rnp, cm); + free_cpumask_var(cm); +} + +/* + * Spawn a per-rcu_node kthread, setting priority and affinity. + * Called during boot before online/offline can happen, or, if + * during runtime, with the main CPU-hotplug locks held. So only + * one of these can be executing at a time. + */ +static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + unsigned long flags; + int rnp_index = rnp - &rsp->node[0]; + struct sched_param sp; + struct task_struct *t; + + if (!rcu_kthreads_spawnable || + rnp->qsmaskinit == 0) + return 0; + if (rnp->node_kthread_task == NULL) { + t = kthread_create(rcu_node_kthread, (void *)rnp, + "rcun%d", rnp_index); + if (IS_ERR(t)) + return PTR_ERR(t); + raw_spin_lock_irqsave(&rnp->lock, flags); + rnp->node_kthread_task = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + sp.sched_priority = 99; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + } + return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); +} + +/* + * Spawn all kthreads -- called as soon as the scheduler is running. + */ +static int __init rcu_spawn_kthreads(void) +{ + int cpu; + struct rcu_node *rnp; + + rcu_kthreads_spawnable = 1; + for_each_possible_cpu(cpu) { + per_cpu(rcu_cpu_has_work, cpu) = 0; + if (cpu_online(cpu)) + (void)rcu_spawn_one_cpu_kthread(cpu); + } + rnp = rcu_get_root(rcu_state); + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + if (NUM_RCU_NODES > 1) { + rcu_for_each_leaf_node(rcu_state, rnp) + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + } + return 0; +} +early_initcall(rcu_spawn_kthreads); + +static void __cpuinit rcu_prepare_kthreads(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); + struct rcu_node *rnp = rdp->mynode; + + /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ + if (rcu_kthreads_spawnable) { + (void)rcu_spawn_one_cpu_kthread(cpu); + if (rnp->node_kthread_task == NULL) + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + } } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1315,23 +1701,32 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) raw_spin_unlock_irqrestore(&rnp->lock, flags); } -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, - cpumask_var_t cm) +static void invoke_rcu_callbacks_kthread(void) { + WARN_ON_ONCE(1); } static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } -static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp, - int rnp_index) +#ifdef CONFIG_HOTPLUG_CPU + +static void rcu_stop_cpu_kthread(int cpu) +{ +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ +} + +static void rcu_cpu_kthread_setrt(int cpu, int to_rt) { - return 0; } -static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp) +static void __cpuinit rcu_prepare_kthreads(int cpu) { } @@ -1509,7 +1904,7 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); * * Because it is not legal to invoke rcu_process_callbacks() with irqs * disabled, we do one pass of force_quiescent_state(), then do a - * invoke_rcu_cpu_kthread() to cause rcu_process_callbacks() to be invoked + * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked * later. The per-cpu rcu_dyntick_drain variable controls the sequencing. */ int rcu_needs_cpu(int cpu) @@ -1560,7 +1955,7 @@ int rcu_needs_cpu(int cpu) /* If RCU callbacks are still pending, RCU still needs this CPU. */ if (c) - invoke_rcu_cpu_kthread(); + invoke_rcu_core(); return c; } diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 9678cc3650f..4e144876dc6 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -46,6 +46,8 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu); DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); @@ -58,6 +60,8 @@ static char convert_kthread_status(unsigned int kthread_status) return "SRWOY"[kthread_status]; } +#endif /* #ifdef CONFIG_RCU_BOOST */ + static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) @@ -76,7 +80,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, " ql=%ld qs=%c%c%c%c kt=%d/%c/%d ktl=%x b=%ld", + seq_printf(m, " ql=%ld qs=%c%c%c%c", rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], @@ -84,13 +88,16 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->nxttail[RCU_NEXT_READY_TAIL]], ".W"[rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_WAIT_TAIL]], - ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, " kt=%d/%c/%d ktl=%x", per_cpu(rcu_cpu_has_work, rdp->cpu), convert_kthread_status(per_cpu(rcu_cpu_kthread_status, rdp->cpu)), per_cpu(rcu_cpu_kthread_cpu, rdp->cpu), - per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff, - rdp->blimit); + per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, " b=%ld", rdp->blimit); seq_printf(m, " ci=%lu co=%lu ca=%lu\n", rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } @@ -147,18 +154,21 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, ",%ld,\"%c%c%c%c\",%d,\"%c\",%ld", rdp->qlen, + seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], ".R"[rdp->nxttail[RCU_WAIT_TAIL] != rdp->nxttail[RCU_NEXT_READY_TAIL]], ".W"[rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_WAIT_TAIL]], - ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, ",%d,\"%c\"", per_cpu(rcu_cpu_has_work, rdp->cpu), convert_kthread_status(per_cpu(rcu_cpu_kthread_status, - rdp->cpu)), - rdp->blimit); + rdp->cpu))); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, ",%ld", rdp->blimit); seq_printf(m, ",%lu,%lu,%lu\n", rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } @@ -169,7 +179,11 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) #ifdef CONFIG_NO_HZ seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ - seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n"); + seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\""); +#ifdef CONFIG_RCU_BOOST + seq_puts(m, "\"kt\",\"ktl\""); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); #ifdef CONFIG_TREE_PREEMPT_RCU seq_puts(m, "\"rcu_preempt:\"\n"); PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); diff --git a/kernel/smp.c b/kernel/smp.c index 73a19519355..fb67dfa8394 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -74,7 +74,7 @@ static struct notifier_block __cpuinitdata hotplug_cfd_notifier = { .notifier_call = hotplug_cfd, }; -static int __cpuinit init_call_single_data(void) +void __init call_function_init(void) { void *cpu = (void *)(long)smp_processor_id(); int i; @@ -88,10 +88,7 @@ static int __cpuinit init_call_single_data(void) hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); register_cpu_notifier(&hotplug_cfd_notifier); - - return 0; } -early_initcall(init_call_single_data); /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources diff --git a/kernel/softirq.c b/kernel/softirq.c index 13960170cad..40cf63ddd4b 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd); char *softirq_to_name[NR_SOFTIRQS] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", - "TASKLET", "SCHED", "HRTIMER" + "TASKLET", "SCHED", "HRTIMER", "RCU" }; /* diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 2d966244ea6..59f369f98a0 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -42,15 +42,75 @@ static struct alarm_base { clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; +/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */ +static ktime_t freezer_delta; +static DEFINE_SPINLOCK(freezer_delta_lock); + #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; -#endif +static DEFINE_SPINLOCK(rtcdev_lock); -/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */ -static ktime_t freezer_delta; -static DEFINE_SPINLOCK(freezer_delta_lock); +/** + * has_wakealarm - check rtc device has wakealarm ability + * @dev: current device + * @name_ptr: name to be returned + * + * This helper function checks to see if the rtc device can wake + * from suspend. + */ +static int has_wakealarm(struct device *dev, void *name_ptr) +{ + struct rtc_device *candidate = to_rtc_device(dev); + + if (!candidate->ops->set_alarm) + return 0; + if (!device_may_wakeup(candidate->dev.parent)) + return 0; + + *(const char **)name_ptr = dev_name(dev); + return 1; +} + +/** + * alarmtimer_get_rtcdev - Return selected rtcdevice + * + * This function returns the rtc device to use for wakealarms. + * If one has not already been chosen, it checks to see if a + * functional rtc device is available. + */ +static struct rtc_device *alarmtimer_get_rtcdev(void) +{ + struct device *dev; + char *str; + unsigned long flags; + struct rtc_device *ret; + + spin_lock_irqsave(&rtcdev_lock, flags); + if (!rtcdev) { + /* Find an rtc device and init the rtc_timer */ + dev = class_find_device(rtc_class, NULL, &str, has_wakealarm); + /* If we have a device then str is valid. See has_wakealarm() */ + if (dev) { + rtcdev = rtc_class_open(str); + /* + * Drop the reference we got in class_find_device, + * rtc_open takes its own. + */ + put_device(dev); + rtc_timer_init(&rtctimer, NULL, NULL); + } + } + ret = rtcdev; + spin_unlock_irqrestore(&rtcdev_lock, flags); + + return ret; +} +#else +#define alarmtimer_get_rtcdev() (0) +#define rtcdev (0) +#endif /** @@ -166,6 +226,7 @@ static int alarmtimer_suspend(struct device *dev) struct rtc_time tm; ktime_t min, now; unsigned long flags; + struct rtc_device *rtc; int i; spin_lock_irqsave(&freezer_delta_lock, flags); @@ -173,8 +234,9 @@ static int alarmtimer_suspend(struct device *dev) freezer_delta = ktime_set(0, 0); spin_unlock_irqrestore(&freezer_delta_lock, flags); + rtc = rtcdev; /* If we have no rtcdev, just return */ - if (!rtcdev) + if (!rtc) return 0; /* Find the soonest timer to expire*/ @@ -199,12 +261,12 @@ static int alarmtimer_suspend(struct device *dev) WARN_ON(min.tv64 < NSEC_PER_SEC); /* Setup an rtc timer to fire that far in the future */ - rtc_timer_cancel(rtcdev, &rtctimer); - rtc_read_time(rtcdev, &tm); + rtc_timer_cancel(rtc, &rtctimer); + rtc_read_time(rtc, &tm); now = rtc_tm_to_ktime(tm); now = ktime_add(now, min); - rtc_timer_start(rtcdev, &rtctimer, now, ktime_set(0, 0)); + rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0)); return 0; } @@ -322,6 +384,9 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp) { clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + return hrtimer_get_res(baseid, tp); } @@ -336,6 +401,9 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + *tp = ktime_to_timespec(base->gettime()); return 0; } @@ -351,6 +419,9 @@ static int alarm_timer_create(struct k_itimer *new_timer) enum alarmtimer_type type; struct alarm_base *base; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; @@ -385,6 +456,9 @@ static void alarm_timer_get(struct k_itimer *timr, */ static int alarm_timer_del(struct k_itimer *timr) { + if (!rtcdev) + return -ENOTSUPP; + alarm_cancel(&timr->it.alarmtimer); return 0; } @@ -402,6 +476,9 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { + if (!rtcdev) + return -ENOTSUPP; + /* Save old values */ old_setting->it_interval = ktime_to_timespec(timr->it.alarmtimer.period); @@ -541,6 +618,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, int ret = 0; struct restart_block *restart; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; @@ -638,65 +718,3 @@ static int __init alarmtimer_init(void) } device_initcall(alarmtimer_init); -#ifdef CONFIG_RTC_CLASS -/** - * has_wakealarm - check rtc device has wakealarm ability - * @dev: current device - * @name_ptr: name to be returned - * - * This helper function checks to see if the rtc device can wake - * from suspend. - */ -static int __init has_wakealarm(struct device *dev, void *name_ptr) -{ - struct rtc_device *candidate = to_rtc_device(dev); - - if (!candidate->ops->set_alarm) - return 0; - if (!device_may_wakeup(candidate->dev.parent)) - return 0; - - *(const char **)name_ptr = dev_name(dev); - return 1; -} - -/** - * alarmtimer_init_late - Late initializing of alarmtimer code - * - * This function locates a rtc device to use for wakealarms. - * Run as late_initcall to make sure rtc devices have been - * registered. - */ -static int __init alarmtimer_init_late(void) -{ - struct device *dev; - char *str; - - /* Find an rtc device and init the rtc_timer */ - dev = class_find_device(rtc_class, NULL, &str, has_wakealarm); - /* If we have a device then str is valid. See has_wakealarm() */ - if (dev) { - rtcdev = rtc_class_open(str); - /* - * Drop the reference we got in class_find_device, - * rtc_open takes its own. - */ - put_device(dev); - } - if (!rtcdev) { - printk(KERN_WARNING "No RTC device found, ALARM timers will" - " not wake from suspend"); - } - rtc_timer_init(&rtctimer, NULL, NULL); - - return 0; -} -#else -static int __init alarmtimer_init_late(void) -{ - printk(KERN_WARNING "Kernel not built with RTC support, ALARM timers" - " will not wake from suspend"); - return 0; -} -#endif -late_initcall(alarmtimer_init_late); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1c95fd67732..e0980f0d9a0 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -185,7 +185,6 @@ static struct clocksource *watchdog; static struct timer_list watchdog_timer; static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); -static cycle_t watchdog_last; static int watchdog_running; static int clocksource_watchdog_kthread(void *data); @@ -254,11 +253,6 @@ static void clocksource_watchdog(unsigned long data) if (!watchdog_running) goto out; - wdnow = watchdog->read(watchdog); - wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask, - watchdog->mult, watchdog->shift); - watchdog_last = wdnow; - list_for_each_entry(cs, &watchdog_list, wd_list) { /* Clocksource already marked unstable? */ @@ -268,19 +262,28 @@ static void clocksource_watchdog(unsigned long data) continue; } + local_irq_disable(); csnow = cs->read(cs); + wdnow = watchdog->read(watchdog); + local_irq_enable(); /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { cs->flags |= CLOCK_SOURCE_WATCHDOG; - cs->wd_last = csnow; + cs->wd_last = wdnow; + cs->cs_last = csnow; continue; } - /* Check the deviation from the watchdog clocksource. */ - cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) & + wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, + watchdog->mult, watchdog->shift); + + cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & cs->mask, cs->mult, cs->shift); - cs->wd_last = csnow; + cs->cs_last = csnow; + cs->wd_last = wdnow; + + /* Check the deviation from the watchdog clocksource. */ if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { clocksource_unstable(cs, cs_nsec - wd_nsec); continue; @@ -318,7 +321,6 @@ static inline void clocksource_start_watchdog(void) return; init_timer(&watchdog_timer); watchdog_timer.function = clocksource_watchdog; - watchdog_last = watchdog->read(watchdog); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); watchdog_running = 1; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index dff763b7baf..1f06468a10d 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -240,13 +240,10 @@ static const char **find_next(void *v, loff_t *pos) const char **fmt = v; int start_index; - if (!fmt) - fmt = __start___trace_bprintk_fmt + *pos; - start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt; if (*pos < start_index) - return fmt; + return __start___trace_bprintk_fmt + *pos; return find_next_mod_format(start_index, v, fmt, pos); } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 02159c75513..c46887b5a11 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -498,7 +498,9 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ + mutex_lock(&zonelists_mutex); build_all_zonelists(NULL); + mutex_unlock(&zonelists_mutex); return pgdat; } @@ -521,7 +523,7 @@ int mem_online_node(int nid) lock_memory_hotplug(); pgdat = hotadd_new_pgdat(nid, 0); - if (pgdat) { + if (!pgdat) { ret = -ENOMEM; goto out; } diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index c7a581a9689..917ecb93ea2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -205,7 +205,7 @@ int register_vlan_dev(struct net_device *dev) grp->nr_vlans++; if (ngrp) { - if (ops->ndo_vlan_rx_register) + if (ops->ndo_vlan_rx_register && (real_dev->features & NETIF_F_HW_VLAN_RX)) ops->ndo_vlan_rx_register(real_dev, ngrp); rcu_assign_pointer(real_dev->vlgrp, ngrp); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f13ddbf858b..77930aa522e 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -477,14 +477,16 @@ static void hci_setup_event_mask(struct hci_dev *hdev) * command otherwise */ u8 events[8] = { 0xff, 0xff, 0xfb, 0xff, 0x00, 0x00, 0x00, 0x00 }; - /* Events for 1.2 and newer controllers */ - if (hdev->lmp_ver > 1) { - events[4] |= 0x01; /* Flow Specification Complete */ - events[4] |= 0x02; /* Inquiry Result with RSSI */ - events[4] |= 0x04; /* Read Remote Extended Features Complete */ - events[5] |= 0x08; /* Synchronous Connection Complete */ - events[5] |= 0x10; /* Synchronous Connection Changed */ - } + /* CSR 1.1 dongles does not accept any bitfield so don't try to set + * any event mask for pre 1.2 devices */ + if (hdev->lmp_ver <= 1) + return; + + events[4] |= 0x01; /* Flow Specification Complete */ + events[4] |= 0x02; /* Inquiry Result with RSSI */ + events[4] |= 0x04; /* Read Remote Extended Features Complete */ + events[5] |= 0x08; /* Synchronous Connection Complete */ + events[5] |= 0x10; /* Synchronous Connection Changed */ if (hdev->features[3] & LMP_RSSI_INQ) events[4] |= 0x04; /* Inquiry Result with RSSI */ diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 18dc9888d8c..8248303f44e 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -413,6 +413,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us break; } + memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 386cfaffd4b..1b10727ce52 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -788,6 +788,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u l2cap_sk = rfcomm_pi(sk)->dlc->session->sock->sk; + memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = conn->hcon->handle; memcpy(cinfo.dev_class, conn->hcon->dev_class, 3); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 42fdffd1d76..cb4fb7837e5 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -369,6 +369,15 @@ static void __sco_sock_close(struct sock *sk) case BT_CONNECTED: case BT_CONFIG: + if (sco_pi(sk)->conn) { + sk->sk_state = BT_DISCONN; + sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); + hci_conn_put(sco_pi(sk)->conn->hcon); + sco_pi(sk)->conn->hcon = NULL; + } else + sco_chan_del(sk, ECONNRESET); + break; + case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); @@ -819,7 +828,9 @@ static void sco_chan_del(struct sock *sk, int err) conn->sk = NULL; sco_pi(sk)->conn = NULL; sco_conn_unlock(conn); - hci_conn_put(conn->hcon); + + if (conn->hcon) + hci_conn_put(conn->hcon); } sk->sk_state = BT_CLOSED; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index a6b2f86378c..c188c803c09 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -243,6 +243,7 @@ int br_netpoll_enable(struct net_bridge_port *p) goto out; np->dev = p->dev; + strlcpy(np->dev_name, p->dev->name, IFNAMSIZ); err = __netpoll_setup(np); if (err) { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 2f14eafdeea..29b9812c8da 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1424,7 +1424,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip4_multicast_add_group(br, port, ih->group); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: @@ -1543,7 +1543,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, goto out; } mld = (struct mld_msg *)skb_transport_header(skb2); - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(br, port, &mld->mld_mca); break; } diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index 3a66b8c10e0..c23979e79df 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -255,7 +255,7 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) { - if ((ctrl == _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND || + if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && layer->id != 0) { diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index ed0eab39f53..02548b292b5 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -44,7 +44,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, pr_debug("%s\n", __func__); if (!buf) - goto out; + return -EMSGSIZE; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, IEEE802154_LIST_PHY); @@ -65,6 +65,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, pages * sizeof(uint32_t), buf); mutex_unlock(&phy->pib_lock); + kfree(buf); return genlmsg_end(msg, hdr); nla_put_failure: diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9c1926027a2..eae1f676f87 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -676,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk2); + sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE))); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 6ffe94ca5bc..3267d389843 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -437,7 +437,7 @@ static int valid_cc(const void *bc, int len, int cc) return 0; if (cc == len) return 1; - if (op->yes < 4) + if (op->yes < 4 || op->yes & 3) return 0; len -= op->yes; bc += op->yes; @@ -447,11 +447,11 @@ static int valid_cc(const void *bc, int len, int cc) static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) { - const unsigned char *bc = bytecode; + const void *bc = bytecode; int len = bytecode_len; while (len > 0) { - struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc; + const struct inet_diag_bc_op *op = bc; //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len); switch (op->code) { @@ -462,22 +462,20 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) case INET_DIAG_BC_S_LE: case INET_DIAG_BC_D_GE: case INET_DIAG_BC_D_LE: - if (op->yes < 4 || op->yes > len + 4) - return -EINVAL; case INET_DIAG_BC_JMP: - if (op->no < 4 || op->no > len + 4) + if (op->no < 4 || op->no > len + 4 || op->no & 3) return -EINVAL; if (op->no < len && !valid_cc(bytecode, bytecode_len, len - op->no)) return -EINVAL; break; case INET_DIAG_BC_NOP: - if (op->yes < 4 || op->yes > len + 4) - return -EINVAL; break; default: return -EINVAL; } + if (op->yes < 4 || op->yes > len + 4 || op->yes & 3) + return -EINVAL; bc += op->yes; len -= op->yes; } diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index f7f9bd7ba12..5c9b9d96391 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -203,7 +203,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) else pmsg->outdev_name[0] = '\0'; - if (entry->indev && entry->skb->dev) { + if (entry->indev && entry->skb->dev && + entry->skb->mac_header != entry->skb->network_header) { pmsg->hw_type = entry->skb->dev->type; pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 76474384350..24e556e83a3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -566,7 +566,7 @@ check_entry(const struct ipt_entry *e, const char *name) const struct xt_entry_target *t; if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, par->match->name); + duprintf("ip check failed %p %s.\n", e, name); return -EINVAL; } diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index af6e9c77834..2b57e52c746 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -25,7 +25,8 @@ MODULE_LICENSE("GPL"); static inline bool match_ip(const struct sk_buff *skb, const struct ipt_ecn_info *einfo) { - return (ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect; + return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^ + !!(einfo->invert & IPT_ECN_OP_MATCH_IP); } static inline bool match_tcp(const struct sk_buff *skb, @@ -76,8 +77,6 @@ static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) { - if (ip_hdr(skb)->protocol != IPPROTO_TCP) - return false; if (!match_tcp(skb, info, &par->hotdrop)) return false; } @@ -97,7 +96,7 @@ static int ecn_mt_check(const struct xt_mtchk_param *par) return -EINVAL; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && - ip->proto != IPPROTO_TCP) { + (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) { pr_info("cannot match TCP bits in rule for non-tcp packets\n"); return -EINVAL; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index db10075dd88..de9da21113a 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -121,7 +121,9 @@ static unsigned int ipv4_confirm(unsigned int hooknum, return ret; } - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) { + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { typeof(nf_nat_seq_adjust_hook) seq_adjust; seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9aaa67165f4..39b403f854c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -41,7 +41,6 @@ #include <linux/proc_fs.h> #include <net/sock.h> #include <net/ping.h> -#include <net/icmp.h> #include <net/udp.h> #include <net/route.h> #include <net/inet_common.h> diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 045f0ec6a4a..aa13ef10511 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1902,9 +1902,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); rth = rt_intern_hash(hash, rth, skb, dev->ifindex); - err = 0; - if (IS_ERR(rth)) - err = PTR_ERR(rth); + return IS_ERR(rth) ? PTR_ERR(rth) : 0; e_nobufs: return -ENOBUFS; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7d6671e33b..708dc203b03 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1589,6 +1589,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 065fe405fb5..24939486328 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -204,7 +204,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) else pmsg->outdev_name[0] = '\0'; - if (entry->indev && entry->skb->dev) { + if (entry->indev && entry->skb->dev && + entry->skb->mac_header != entry->skb->network_header) { pmsg->hw_type = entry->skb->dev->type; pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d1fd28711ba..87551ca568c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1644,6 +1644,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * the new socket.. */ if(nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index bf28ac2fc99..782db275ac5 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -776,8 +776,16 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->control) ip_vs_control_del(cp); - if (cp->flags & IP_VS_CONN_F_NFCT) + if (cp->flags & IP_VS_CONN_F_NFCT) { ip_vs_conn_drop_conntrack(cp); + /* Do not access conntracks during subsys cleanup + * because nf_conntrack_find_get can not be used after + * conntrack cleanup for the net. + */ + smp_rmb(); + if (ipvs->enable) + ip_vs_conn_drop_conntrack(cp); + } ip_vs_pe_put(cp->pe); kfree(cp->pe_data); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 55af2242bcc..24c28d238dc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1945,6 +1945,7 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net) { EnterFunction(2); net_ipvs(net)->enable = 0; /* Disable packet reception */ + smp_wmb(); __ip_vs_sync_cleanup(net); LeaveFunction(2); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e0ee010935e..2e7ccbb43dd 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -456,7 +456,8 @@ __build_packet_message(struct nfulnl_instance *inst, if (skb->mark) NLA_PUT_BE32(inst->skb, NFULA_MARK, htonl(skb->mark)); - if (indev && skb->dev) { + if (indev && skb->dev && + skb->mac_header != skb->network_header) { struct nfulnl_msg_packet_hw phw; int len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index b83123f12b4..fdd2fafe0a1 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -335,7 +335,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (entskb->mark) NLA_PUT_BE32(skb, NFQA_MARK, htonl(entskb->mark)); - if (indev && entskb->dev) { + if (indev && entskb->dev && + entskb->mac_header != entskb->network_header) { struct nfqnl_msg_packet_hw phw; int len = dev_parse_header(entskb, phw.hw_addr); if (len) { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 339ba64cce1..5daf6cc4fae 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -577,13 +577,13 @@ retry: } inode = &gss_msg->inode->vfs_inode; for (;;) { - prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_KILLABLE); spin_lock(&inode->i_lock); if (gss_msg->ctx != NULL || gss_msg->msg.errno < 0) { break; } spin_unlock(&inode->i_lock); - if (signalled()) { + if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto out_intr; } diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0a9a2ec2e46..c3b75333b82 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -43,6 +43,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/xdr.h> #include <linux/crypto.h> +#include <linux/sunrpc/gss_krb5_enctypes.h> #ifdef RPC_DEBUG # define RPCDBG_FACILITY RPCDBG_AUTH @@ -750,7 +751,7 @@ static struct gss_api_mech gss_kerberos_mech = { .gm_ops = &gss_kerberos_ops, .gm_pf_num = ARRAY_SIZE(gss_kerberos_pfs), .gm_pfs = gss_kerberos_pfs, - .gm_upcall_enctypes = "18,17,16,23,3,1,2", + .gm_upcall_enctypes = KRB5_SUPPORTED_ENCTYPES, }; static int __init init_kerberos_module(void) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b84d7395535..8c9141583d6 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1061,7 +1061,7 @@ call_allocate(struct rpc_task *task) dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid); - if (RPC_IS_ASYNC(task) || !signalled()) { + if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) { task->tk_action = call_allocate; rpc_delay(task, HZ>>4); return; @@ -1175,6 +1175,9 @@ call_bind_status(struct rpc_task *task) status = -EOPNOTSUPP; break; } + if (task->tk_rebind_retry == 0) + break; + task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; case -ETIMEDOUT: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6b43ee7221d..a27406b1654 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -792,6 +792,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; + task->tk_rebind_retry = 2; task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; diff --git a/security/device_cgroup.c b/security/device_cgroup.c index cd1f779fa51..1be68269e1c 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -474,17 +474,11 @@ struct cgroup_subsys devices_subsys = { .subsys_id = devices_subsys_id, }; -int devcgroup_inode_permission(struct inode *inode, int mask) +int __devcgroup_inode_permission(struct inode *inode, int mask) { struct dev_cgroup *dev_cgroup; struct dev_whitelist_item *wh; - dev_t device = inode->i_rdev; - if (!device) - return 0; - if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)) - return 0; - rcu_read_lock(); dev_cgroup = task_devcgroup(current); diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 8e319a416ee..82465328c39 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -469,7 +469,7 @@ static struct key *construct_key_and_link(struct key_type *type, } else if (ret == -EINPROGRESS) { ret = 0; } else { - key = ERR_PTR(ret); + goto couldnt_alloc_key; } key_put(dest_keyring); @@ -479,6 +479,7 @@ static struct key *construct_key_and_link(struct key_type *type, construction_failed: key_negate_and_link(key, key_negative_timeout, NULL, NULL); key_put(key); +couldnt_alloc_key: key_put(dest_keyring); kleave(" = %d", ret); return ERR_PTR(ret); diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c index 2ca6f4f85b4..e3569bdd3b6 100644 --- a/sound/pci/asihpi/asihpi.c +++ b/sound/pci/asihpi/asihpi.c @@ -27,7 +27,6 @@ #include "hpioctl.h" #include <linux/pci.h> -#include <linux/version.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/slab.h> diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 61a774b3d3c..d21191dcfe8 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4883,7 +4883,6 @@ static const struct snd_pci_quirk alc880_cfg_tbl[] = { SND_PCI_QUIRK(0x1025, 0xe309, "ULI", ALC880_3ST_DIG), SND_PCI_QUIRK(0x1025, 0xe310, "ULI", ALC880_3ST), SND_PCI_QUIRK(0x1039, 0x1234, NULL, ALC880_6ST_DIG), - SND_PCI_QUIRK(0x103c, 0x2a09, "HP", ALC880_5ST), SND_PCI_QUIRK(0x1043, 0x10b3, "ASUS W1V", ALC880_ASUS_W1V), SND_PCI_QUIRK(0x1043, 0x10c2, "ASUS W6A", ALC880_ASUS_DIG), SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS Wxx", ALC880_ASUS_DIG), @@ -12600,6 +12599,7 @@ static const struct hda_verb alc262_toshiba_rx1_unsol_verbs[] = { */ enum { PINFIX_FSC_H270, + PINFIX_HP_Z200, }; static const struct alc_fixup alc262_fixups[] = { @@ -12612,9 +12612,17 @@ static const struct alc_fixup alc262_fixups[] = { { } } }, + [PINFIX_HP_Z200] = { + .type = ALC_FIXUP_PINS, + .v.pins = (const struct alc_pincfg[]) { + { 0x16, 0x99130120 }, /* internal speaker */ + { } + } + }, }; static const struct snd_pci_quirk alc262_fixup_tbl[] = { + SND_PCI_QUIRK(0x103c, 0x170b, "HP Z200", PINFIX_HP_Z200), SND_PCI_QUIRK(0x1734, 0x1147, "FSC Celsius H270", PINFIX_FSC_H270), {} }; @@ -12731,6 +12739,8 @@ static const struct snd_pci_quirk alc262_cfg_tbl[] = { ALC262_HP_BPC), SND_PCI_QUIRK_MASK(0x103c, 0xff00, 0x1500, "HP z series", ALC262_HP_BPC), + SND_PCI_QUIRK(0x103c, 0x170b, "HP Z200", + ALC262_AUTO), SND_PCI_QUIRK_MASK(0x103c, 0xff00, 0x1700, "HP xw series", ALC262_HP_BPC), SND_PCI_QUIRK(0x103c, 0x2800, "HP D7000", ALC262_HP_BPC_D7000_WL), @@ -13872,7 +13882,6 @@ static const struct snd_pci_quirk alc268_cfg_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1205, "ASUS W7J", ALC268_3ST), SND_PCI_QUIRK(0x1170, 0x0040, "ZEPTO", ALC268_ZEPTO), SND_PCI_QUIRK(0x14c0, 0x0025, "COMPAL IFL90/JFL-92", ALC268_TOSHIBA), - SND_PCI_QUIRK(0x152d, 0x0763, "Diverse (CPR2000)", ALC268_ACER), SND_PCI_QUIRK(0x152d, 0x0771, "Quanta IL1", ALC267_QUANTA_IL1), {} }; diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index c952582fb21..f43bb0eaed8 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -745,12 +745,23 @@ static int via_independent_hp_put(struct snd_kcontrol *kcontrol, struct via_spec *spec = codec->spec; hda_nid_t nid = kcontrol->private_value; unsigned int pinsel = ucontrol->value.enumerated.item[0]; + unsigned int parm0, parm1; /* Get Independent Mode index of headphone pin widget */ spec->hp_independent_mode = spec->hp_independent_mode_index == pinsel ? 1 : 0; - if (spec->codec_type == VT1718S) + if (spec->codec_type == VT1718S) { snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CONNECT_SEL, pinsel ? 2 : 0); + /* Set correct mute switch for MW3 */ + parm0 = spec->hp_independent_mode ? + AMP_IN_UNMUTE(0) : AMP_IN_MUTE(0); + parm1 = spec->hp_independent_mode ? + AMP_IN_MUTE(1) : AMP_IN_UNMUTE(1); + snd_hda_codec_write(codec, 0x1b, 0, + AC_VERB_SET_AMP_GAIN_MUTE, parm0); + snd_hda_codec_write(codec, 0x1b, 0, + AC_VERB_SET_AMP_GAIN_MUTE, parm1); + } else snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CONNECT_SEL, pinsel); @@ -4283,9 +4294,6 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = { {0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(2)}, {0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(3)}, {0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(5)}, - - /* Setup default input of Front HP to MW9 */ - {0x28, AC_VERB_SET_CONNECT_SEL, 0x1}, /* PW9 PW10 Output enable */ {0x2d, AC_VERB_SET_PIN_WIDGET_CONTROL, AC_PINCTL_OUT_EN}, {0x2e, AC_VERB_SET_PIN_WIDGET_CONTROL, AC_PINCTL_OUT_EN}, @@ -4294,10 +4302,10 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = { /* Enable Boost Volume backdoor */ {0x1, 0xf88, 0x8}, /* MW0/1/2/3/4: un-mute index 0 (AOWx), mute index 1 (MW9) */ - {0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, + {0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)}, {0x19, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, {0x1a, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, - {0x1b, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, + {0x1b, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)}, {0x1c, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, {0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(1)}, {0x19, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(1)}, @@ -4307,8 +4315,6 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = { /* set MUX1 = 2 (AOW4), MUX2 = 1 (AOW3) */ {0x34, AC_VERB_SET_CONNECT_SEL, 0x2}, {0x35, AC_VERB_SET_CONNECT_SEL, 0x1}, - /* Unmute MW4's index 0 */ - {0x1c, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, { } }; @@ -4456,6 +4462,19 @@ static int vt1718S_auto_create_multi_out_ctls(struct via_spec *spec, if (err < 0) return err; } else if (i == AUTO_SEQ_FRONT) { + /* add control to mixer index 0 */ + err = via_add_control(spec, VIA_CTL_WIDGET_VOL, + "Master Front Playback Volume", + HDA_COMPOSE_AMP_VAL(0x21, 3, 5, + HDA_INPUT)); + if (err < 0) + return err; + err = via_add_control(spec, VIA_CTL_WIDGET_MUTE, + "Master Front Playback Switch", + HDA_COMPOSE_AMP_VAL(0x21, 3, 5, + HDA_INPUT)); + if (err < 0) + return err; /* Front */ sprintf(name, "%s Playback Volume", chname[i]); err = via_add_control( diff --git a/sound/soc/codecs/wm8991.c b/sound/soc/codecs/wm8991.c index 3c2ee1bb73c..6af23d06870 100644 --- a/sound/soc/codecs/wm8991.c +++ b/sound/soc/codecs/wm8991.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/moduleparam.h> -#include <linux/version.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/delay.h> diff --git a/sound/soc/imx/Kconfig b/sound/soc/imx/Kconfig index d8f130d39dd..bb699bb55a5 100644 --- a/sound/soc/imx/Kconfig +++ b/sound/soc/imx/Kconfig @@ -11,9 +11,6 @@ menuconfig SND_IMX_SOC if SND_IMX_SOC -config SND_MXC_SOC_SSI - tristate - config SND_MXC_SOC_FIQ tristate @@ -24,7 +21,6 @@ config SND_MXC_SOC_WM1133_EV1 tristate "Audio on the the i.MX31ADS with WM1133-EV1 fitted" depends on MACH_MX31ADS_WM1133_EV1 && EXPERIMENTAL select SND_SOC_WM8350 - select SND_MXC_SOC_SSI select SND_MXC_SOC_FIQ help Enable support for audio on the i.MX31ADS with the WM1133-EV1 @@ -34,7 +30,6 @@ config SND_SOC_MX27VIS_AIC32X4 tristate "SoC audio support for Visstrim M10 boards" depends on MACH_IMX27_VISSTRIM_M10 select SND_SOC_TVL320AIC32X4 - select SND_MXC_SOC_SSI select SND_MXC_SOC_MX2 help Say Y if you want to add support for SoC audio on Visstrim SM10 @@ -44,7 +39,6 @@ config SND_SOC_PHYCORE_AC97 tristate "SoC Audio support for Phytec phyCORE (and phyCARD) boards" depends on MACH_PCM043 || MACH_PCA100 select SND_SOC_WM9712 - select SND_MXC_SOC_SSI select SND_MXC_SOC_FIQ help Say Y if you want to add support for SoC audio on Phytec phyCORE @@ -57,7 +51,6 @@ config SND_SOC_EUKREA_TLV320 || MACH_EUKREA_MBIMXSD35_BASEBOARD \ || MACH_EUKREA_MBIMXSD51_BASEBOARD select SND_SOC_TLV320AIC23 - select SND_MXC_SOC_SSI select SND_MXC_SOC_FIQ help Enable I2S based access to the TLV320AIC23B codec attached diff --git a/sound/soc/imx/imx-pcm-dma-mx2.c b/sound/soc/imx/imx-pcm-dma-mx2.c index aab7765f401..4173b3d87f9 100644 --- a/sound/soc/imx/imx-pcm-dma-mx2.c +++ b/sound/soc/imx/imx-pcm-dma-mx2.c @@ -337,3 +337,5 @@ static void __exit snd_imx_pcm_exit(void) platform_driver_unregister(&imx_pcm_driver); } module_exit(snd_imx_pcm_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:imx-pcm-audio"); diff --git a/sound/soc/imx/imx-ssi.c b/sound/soc/imx/imx-ssi.c index 5b13feca753..61fceb09cdb 100644 --- a/sound/soc/imx/imx-ssi.c +++ b/sound/soc/imx/imx-ssi.c @@ -774,4 +774,4 @@ module_exit(imx_ssi_exit); MODULE_AUTHOR("Sascha Hauer, <s.hauer@pengutronix.de>"); MODULE_DESCRIPTION("i.MX I2S/ac97 SoC Interface"); MODULE_LICENSE("GPL"); - +MODULE_ALIAS("platform:imx-ssi"); diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c index 2ce0b2d891d..fab20a54e86 100644 --- a/sound/soc/pxa/pxa2xx-pcm.c +++ b/sound/soc/pxa/pxa2xx-pcm.c @@ -95,14 +95,14 @@ static int pxa2xx_soc_pcm_new(struct snd_card *card, struct snd_soc_dai *dai, if (!card->dev->coherent_dma_mask) card->dev->coherent_dma_mask = DMA_BIT_MASK(32); - if (dai->driver->playback.channels_min) { + if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, SNDRV_PCM_STREAM_PLAYBACK); if (ret) goto out; } - if (dai->driver->capture.channels_min) { + if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) { ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, SNDRV_PCM_STREAM_CAPTURE); if (ret) diff --git a/sound/soc/soc-cache.c b/sound/soc/soc-cache.c index c005ceb70c9..039b9532b27 100644 --- a/sound/soc/soc-cache.c +++ b/sound/soc/soc-cache.c @@ -409,9 +409,6 @@ int snd_soc_codec_set_cache_io(struct snd_soc_codec *codec, codec->bulk_write_raw = snd_soc_hw_bulk_write_raw; switch (control) { - case SND_SOC_CUSTOM: - break; - case SND_SOC_I2C: #if defined(CONFIG_I2C) || (defined(CONFIG_I2C_MODULE) && defined(MODULE)) codec->hw_write = (hw_write_t)i2c_master_send; diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 032ba6398a5..940257b5774 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -633,7 +633,7 @@ prefix_SQ = $(subst ','\'',$(prefix)) SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) -LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive $(EXTLIBS) +LIBS = -Wl,--whole-archive $(PERFLIBS) -Wl,--no-whole-archive -Wl,--start-group $(EXTLIBS) -Wl,--end-group ALL_CFLAGS += $(BASIC_CFLAGS) ALL_CFLAGS += $(ARCH_CFLAGS) diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 1e88485c16a..0a7ed5b5e28 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -2187,6 +2187,7 @@ static const struct flag flags[] = { { "TASKLET_SOFTIRQ", 6 }, { "SCHED_SOFTIRQ", 7 }, { "HRTIMER_SOFTIRQ", 8 }, + { "RCU_SOFTIRQ", 9 }, { "HRTIMER_NORESTART", 0 }, { "HRTIMER_RESTART", 1 }, |