diff options
162 files changed, 1980 insertions, 1536 deletions
diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt index 64087c34327f..7671352216f1 100644 --- a/Documentation/filesystems/btrfs.txt +++ b/Documentation/filesystems/btrfs.txt @@ -63,8 +63,8 @@ IRC network. Userspace tools for creating and manipulating Btrfs file systems are available from the git repository at the following location: - http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git - git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git + http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs.git + git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs.git These include the following tools: @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Saber-toothed Squirrel # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 44789eff983f..e084b7e981e8 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1231,7 +1231,7 @@ config ARM_ERRATA_742231 capabilities of the processor. config PL310_ERRATA_588369 - bool "Clean & Invalidate maintenance operations do not invalidate clean lines" + bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines" depends on CACHE_L2X0 help The PL310 L2 cache controller implements three types of Clean & @@ -1256,7 +1256,7 @@ config ARM_ERRATA_720789 entries regardless of the ASID. config PL310_ERRATA_727915 - bool "Background Clean & Invalidate by Way operation can cause data corruption" + bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption" depends on CACHE_L2X0 help PL310 implements the Clean & Invalidate by Way L2 cache maintenance @@ -1289,8 +1289,8 @@ config ARM_ERRATA_751472 operation is received by a CPU before the ICIALLUIS has completed, potentially leading to corrupted entries in the cache or TLB. -config ARM_ERRATA_753970 - bool "ARM errata: cache sync operation may be faulty" +config PL310_ERRATA_753970 + bool "PL310 errata: cache sync operation may be faulty" depends on CACHE_PL310 help This option enables the workaround for the 753970 PL310 (r3p0) erratum. @@ -1352,6 +1352,18 @@ config ARM_ERRATA_764369 relevant cache maintenance functions and sets a specific bit in the diagnostic control register of the SCU. +config PL310_ERRATA_769419 + bool "PL310 errata: no automatic Store Buffer drain" + depends on CACHE_L2X0 + help + On revisions of the PL310 prior to r3p2, the Store Buffer does + not automatically drain. This can cause normal, non-cacheable + writes to be retained when the memory system is idle, leading + to suboptimal I/O performance for drivers using coherent DMA. + This option adds a write barrier to the cpu_idle loop so that, + on systems with an outer cache, the store buffer is drained + explicitly. + endmenu source "arch/arm/common/Kconfig" diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c index 0e6ae470c94f..410a546060a2 100644 --- a/arch/arm/common/gic.c +++ b/arch/arm/common/gic.c @@ -526,7 +526,8 @@ static void __init gic_pm_init(struct gic_chip_data *gic) sizeof(u32)); BUG_ON(!gic->saved_ppi_conf); - cpu_pm_register_notifier(&gic_notifier_block); + if (gic == &gic_data[0]) + cpu_pm_register_notifier(&gic_notifier_block); } #else static void __init gic_pm_init(struct gic_chip_data *gic) @@ -581,13 +582,16 @@ void __init gic_init(unsigned int gic_nr, int irq_start, * For primary GICs, skip over SGIs. * For secondary GICs, skip over PPIs, too. */ + domain->hwirq_base = 32; if (gic_nr == 0) { gic_cpu_base_addr = cpu_base; - domain->hwirq_base = 16; - if (irq_start > 0) - irq_start = (irq_start & ~31) + 16; - } else - domain->hwirq_base = 32; + + if ((irq_start & 31) > 0) { + domain->hwirq_base = 16; + if (irq_start != -1) + irq_start = (irq_start & ~31) + 16; + } + } /* * Find out how many interrupts are supported. diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c index 7129cfbdacd6..f407a6b35d3d 100644 --- a/arch/arm/common/pl330.c +++ b/arch/arm/common/pl330.c @@ -1211,8 +1211,8 @@ static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc) ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT); ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT); - ccr |= (rqc->dcctl << CC_SRCCCTRL_SHFT); - ccr |= (rqc->scctl << CC_DSTCCTRL_SHFT); + ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT); + ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT); ccr |= (rqc->swap << CC_SWAP_SHFT); @@ -1623,6 +1623,11 @@ static inline int _alloc_event(struct pl330_thread *thrd) return -1; } +static bool _chan_ns(const struct pl330_info *pi, int i) +{ + return pi->pcfg.irq_ns & (1 << i); +} + /* Upon success, returns IdentityToken for the * allocated channel, NULL otherwise. */ @@ -1647,7 +1652,8 @@ void *pl330_request_channel(const struct pl330_info *pi) for (i = 0; i < chans; i++) { thrd = &pl330->channels[i]; - if (thrd->free) { + if ((thrd->free) && (!_manager_ns(thrd) || + _chan_ns(pi, i))) { thrd->ev = _alloc_event(thrd); if (thrd->ev >= 0) { thrd->free = false; diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index 71d99b83cdb9..0bda22c094a6 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -55,16 +55,6 @@ reserve_pmu(enum arm_pmu_type type); extern void release_pmu(enum arm_pmu_type type); -/** - * init_pmu() - Initialise the PMU. - * - * Initialise the system ready for PMU enabling. This should typically set the - * IRQ affinity and nothing else. The users (oprofile/perf events etc) will do - * the actual hardware initialisation. - */ -extern int -init_pmu(enum arm_pmu_type type); - #else /* CONFIG_CPU_HAS_PMU */ #include <linux/err.h> diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index a7e457ed27c3..58b8b84adcd2 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -25,7 +25,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); -const struct cpumask *cpu_coregroup_mask(unsigned int cpu); +const struct cpumask *cpu_coregroup_mask(int cpu); #else diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 9ad50c4208ae..b145f16c91bc 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -497,7 +497,7 @@ ENDPROC(__und_usr) .popsection .pushsection __ex_table,"a" .long 1b, 4b -#if __LINUX_ARM_ARCH__ >= 7 +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 .long 2b, 4b .long 3b, 4b #endif diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c index 9fe8910308af..8a30c89da70e 100644 --- a/arch/arm/kernel/kprobes-arm.c +++ b/arch/arm/kernel/kprobes-arm.c @@ -519,10 +519,12 @@ static const union decode_item arm_cccc_0000_____1001_table[] = { static const union decode_item arm_cccc_0001_____1001_table[] = { /* Synchronization primitives */ +#if __LINUX_ARM_ARCH__ < 6 + /* Deprecated on ARMv6 and may be UNDEFINED on v7 */ /* SMP/SWPB cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */ DECODE_EMULATEX (0x0fb000f0, 0x01000090, emulate_rd12rn16rm0_rwflags_nopc, REGS(NOPC, NOPC, 0, 0, NOPC)), - +#endif /* LDREX/STREX{,D,B,H} cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */ /* And unallocated instructions... */ DECODE_END diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c index fc82de8bdcce..ba32b393b3f0 100644 --- a/arch/arm/kernel/kprobes-test-arm.c +++ b/arch/arm/kernel/kprobes-test-arm.c @@ -427,18 +427,25 @@ void kprobe_arm_test_cases(void) TEST_GROUP("Synchronization primitives") - /* - * Use hard coded constants for SWP instructions to avoid warnings - * about deprecated instructions. - */ - TEST_RP( ".word 0xe108e097 @ swp lr, r",7,VAL2,", [r",8,0,"]") - TEST_R( ".word 0x610d0091 @ swpvs r0, r",1,VAL1,", [sp]") - TEST_RP( ".word 0xe10cd09e @ swp sp, r",14,VAL2,", [r",12,13*4,"]") +#if __LINUX_ARM_ARCH__ < 6 + TEST_RP("swp lr, r",7,VAL2,", [r",8,0,"]") + TEST_R( "swpvs r0, r",1,VAL1,", [sp]") + TEST_RP("swp sp, r",14,VAL2,", [r",12,13*4,"]") +#else + TEST_UNSUPPORTED(".word 0xe108e097 @ swp lr, r7, [r8]") + TEST_UNSUPPORTED(".word 0x610d0091 @ swpvs r0, r1, [sp]") + TEST_UNSUPPORTED(".word 0xe10cd09e @ swp sp, r14 [r12]") +#endif TEST_UNSUPPORTED(".word 0xe102f091 @ swp pc, r1, [r2]") TEST_UNSUPPORTED(".word 0xe102009f @ swp r0, pc, [r2]") TEST_UNSUPPORTED(".word 0xe10f0091 @ swp r0, r1, [pc]") - TEST_RP( ".word 0xe148e097 @ swpb lr, r",7,VAL2,", [r",8,0,"]") - TEST_R( ".word 0x614d0091 @ swpvsb r0, r",1,VAL1,", [sp]") +#if __LINUX_ARM_ARCH__ < 6 + TEST_RP("swpb lr, r",7,VAL2,", [r",8,0,"]") + TEST_R( "swpvsb r0, r",1,VAL1,", [sp]") +#else + TEST_UNSUPPORTED(".word 0xe148e097 @ swpb lr, r7, [r8]") + TEST_UNSUPPORTED(".word 0x614d0091 @ swpvsb r0, r1, [sp]") +#endif TEST_UNSUPPORTED(".word 0xe142f091 @ swpb pc, r1, [r2]") TEST_UNSUPPORTED(".word 0xe1100090") /* Unallocated space */ @@ -550,7 +557,7 @@ void kprobe_arm_test_cases(void) TEST_RPR( "strccd r",8, VAL2,", [r",13,0, ", r",12,48,"]") TEST_RPR( "strd r",4, VAL1,", [r",2, 24,", r",3, 48,"]!") TEST_RPR( "strcsd r",12,VAL2,", [r",11,48,", -r",10,24,"]!") - TEST_RPR( "strd r",2, VAL1,", [r",3, 24,"], r",4,48,"") + TEST_RPR( "strd r",2, VAL1,", [r",5, 24,"], r",4,48,"") TEST_RPR( "strd r",10,VAL2,", [r",9, 48,"], -r",7,24,"") TEST_UNSUPPORTED(".word 0xe1afc0fa @ strd r12, [pc, r10]!") diff --git a/arch/arm/kernel/kprobes-test-thumb.c b/arch/arm/kernel/kprobes-test-thumb.c index 5e726c31c45a..5d8b85792222 100644 --- a/arch/arm/kernel/kprobes-test-thumb.c +++ b/arch/arm/kernel/kprobes-test-thumb.c @@ -222,8 +222,8 @@ void kprobe_thumb16_test_cases(void) DONT_TEST_IN_ITBLOCK( TEST_BF_R( "cbnz r",0,0, ", 2f") TEST_BF_R( "cbz r",2,-1,", 2f") - TEST_BF_RX( "cbnz r",4,1, ", 2f",0x20) - TEST_BF_RX( "cbz r",7,0, ", 2f",0x40) + TEST_BF_RX( "cbnz r",4,1, ", 2f", SPACE_0x20) + TEST_BF_RX( "cbz r",7,0, ", 2f", SPACE_0x40) ) TEST_R("sxth r0, r",7, HH1,"") TEST_R("sxth r7, r",0, HH2,"") @@ -246,7 +246,7 @@ DONT_TEST_IN_ITBLOCK( TESTCASE_START(code) \ TEST_ARG_PTR(13, offset) \ TEST_ARG_END("") \ - TEST_BRANCH_F(code,0) \ + TEST_BRANCH_F(code) \ TESTCASE_END TEST("push {r0}") @@ -319,8 +319,8 @@ CONDITION_INSTRUCTIONS(8, TEST_BF( "b 2f") TEST_BB( "b 2b") - TEST_BF_X("b 2f", 0x400) - TEST_BB_X("b 2b", 0x400) + TEST_BF_X("b 2f", SPACE_0x400) + TEST_BB_X("b 2b", SPACE_0x400) TEST_GROUP("Testing instructions in IT blocks") @@ -746,7 +746,7 @@ CONDITION_INSTRUCTIONS(22, TEST_BB("bne.w 2b") TEST_BF("bgt.w 2f") TEST_BB("blt.w 2b") - TEST_BF_X("bpl.w 2f",0x1000) + TEST_BF_X("bpl.w 2f", SPACE_0x1000) ) TEST_UNSUPPORTED("msr cpsr, r0") @@ -786,11 +786,11 @@ CONDITION_INSTRUCTIONS(22, TEST_BF( "b.w 2f") TEST_BB( "b.w 2b") - TEST_BF_X("b.w 2f", 0x1000) + TEST_BF_X("b.w 2f", SPACE_0x1000) TEST_BF( "bl.w 2f") TEST_BB( "bl.w 2b") - TEST_BB_X("bl.w 2b", 0x1000) + TEST_BB_X("bl.w 2b", SPACE_0x1000) TEST_X( "blx __dummy_arm_subroutine", ".arm \n\t" diff --git a/arch/arm/kernel/kprobes-test.h b/arch/arm/kernel/kprobes-test.h index 0dc5d77b9356..e28a869b1ae4 100644 --- a/arch/arm/kernel/kprobes-test.h +++ b/arch/arm/kernel/kprobes-test.h @@ -149,23 +149,31 @@ struct test_arg_end { "1: "instruction" \n\t" \ " nop \n\t" -#define TEST_BRANCH_F(instruction, xtra_dist) \ +#define TEST_BRANCH_F(instruction) \ TEST_INSTRUCTION(instruction) \ - ".if "#xtra_dist" \n\t" \ " b 99f \n\t" \ - ".space "#xtra_dist" \n\t" \ - ".endif \n\t" \ + "2: nop \n\t" + +#define TEST_BRANCH_B(instruction) \ + " b 50f \n\t" \ + " b 99f \n\t" \ + "2: nop \n\t" \ + " b 99f \n\t" \ + TEST_INSTRUCTION(instruction) + +#define TEST_BRANCH_FX(instruction, codex) \ + TEST_INSTRUCTION(instruction) \ + " b 99f \n\t" \ + codex" \n\t" \ " b 99f \n\t" \ "2: nop \n\t" -#define TEST_BRANCH_B(instruction, xtra_dist) \ +#define TEST_BRANCH_BX(instruction, codex) \ " b 50f \n\t" \ " b 99f \n\t" \ "2: nop \n\t" \ " b 99f \n\t" \ - ".if "#xtra_dist" \n\t" \ - ".space "#xtra_dist" \n\t" \ - ".endif \n\t" \ + codex" \n\t" \ TEST_INSTRUCTION(instruction) #define TESTCASE_END \ @@ -301,47 +309,60 @@ struct test_arg_end { TESTCASE_START(code1 #reg1 code2) \ TEST_ARG_PTR(reg1, val1) \ TEST_ARG_END("") \ - TEST_BRANCH_F(code1 #reg1 code2, 0) \ + TEST_BRANCH_F(code1 #reg1 code2) \ TESTCASE_END -#define TEST_BF_X(code, xtra_dist) \ +#define TEST_BF(code) \ TESTCASE_START(code) \ TEST_ARG_END("") \ - TEST_BRANCH_F(code, xtra_dist) \ + TEST_BRANCH_F(code) \ TESTCASE_END -#define TEST_BB_X(code, xtra_dist) \ +#define TEST_BB(code) \ TESTCASE_START(code) \ TEST_ARG_END("") \ - TEST_BRANCH_B(code, xtra_dist) \ + TEST_BRANCH_B(code) \ TESTCASE_END -#define TEST_BF_RX(code1, reg, val, code2, xtra_dist) \ - TESTCASE_START(code1 #reg code2) \ - TEST_ARG_REG(reg, val) \ - TEST_ARG_END("") \ - TEST_BRANCH_F(code1 #reg code2, xtra_dist) \ +#define TEST_BF_R(code1, reg, val, code2) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_BRANCH_F(code1 #reg code2) \ TESTCASE_END -#define TEST_BB_RX(code1, reg, val, code2, xtra_dist) \ - TESTCASE_START(code1 #reg code2) \ - TEST_ARG_REG(reg, val) \ - TEST_ARG_END("") \ - TEST_BRANCH_B(code1 #reg code2, xtra_dist) \ +#define TEST_BB_R(code1, reg, val, code2) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_BRANCH_B(code1 #reg code2) \ TESTCASE_END -#define TEST_BF(code) TEST_BF_X(code, 0) -#define TEST_BB(code) TEST_BB_X(code, 0) - -#define TEST_BF_R(code1, reg, val, code2) TEST_BF_RX(code1, reg, val, code2, 0) -#define TEST_BB_R(code1, reg, val, code2) TEST_BB_RX(code1, reg, val, code2, 0) - #define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3) \ TESTCASE_START(code1 #reg1 code2 #reg2 code3) \ TEST_ARG_REG(reg1, val1) \ TEST_ARG_REG(reg2, val2) \ TEST_ARG_END("") \ - TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3, 0) \ + TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3) \ + TESTCASE_END + +#define TEST_BF_X(code, codex) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + TEST_BRANCH_FX(code, codex) \ + TESTCASE_END + +#define TEST_BB_X(code, codex) \ + TESTCASE_START(code) \ + TEST_ARG_END("") \ + TEST_BRANCH_BX(code, codex) \ + TESTCASE_END + +#define TEST_BF_RX(code1, reg, val, code2, codex) \ + TESTCASE_START(code1 #reg code2) \ + TEST_ARG_REG(reg, val) \ + TEST_ARG_END("") \ + TEST_BRANCH_FX(code1 #reg code2, codex) \ TESTCASE_END #define TEST_X(code, codex) \ @@ -372,6 +393,25 @@ struct test_arg_end { TESTCASE_END +/* + * Macros for defining space directives spread over multiple lines. + * These are required so the compiler guesses better the length of inline asm + * code and will spill the literal pool early enough to avoid generating PC + * relative loads with out of range offsets. + */ +#define TWICE(x) x x +#define SPACE_0x8 TWICE(".space 4\n\t") +#define SPACE_0x10 TWICE(SPACE_0x8) +#define SPACE_0x20 TWICE(SPACE_0x10) +#define SPACE_0x40 TWICE(SPACE_0x20) +#define SPACE_0x80 TWICE(SPACE_0x40) +#define SPACE_0x100 TWICE(SPACE_0x80) +#define SPACE_0x200 TWICE(SPACE_0x100) +#define SPACE_0x400 TWICE(SPACE_0x200) +#define SPACE_0x800 TWICE(SPACE_0x400) +#define SPACE_0x1000 TWICE(SPACE_0x800) + + /* Various values used in test cases... */ #define N(val) (val ^ 0xffffffff) #define VAL1 0x12345678 diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 24e2347be6b1..c475379199b1 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -343,8 +343,14 @@ validate_group(struct perf_event *event) { struct perf_event *sibling, *leader = event->group_leader; struct pmu_hw_events fake_pmu; + DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS); - memset(&fake_pmu, 0, sizeof(fake_pmu)); + /* + * Initialise the fake PMU. We only need to populate the + * used_mask for the purposes of validation. + */ + memset(fake_used_mask, 0, sizeof(fake_used_mask)); + fake_pmu.used_mask = fake_used_mask; if (!validate_event(&fake_pmu, leader)) return -ENOSPC; @@ -396,6 +402,9 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu) int i, err, irq, irqs; struct platform_device *pmu_device = armpmu->plat_device; + if (!pmu_device) + return -ENODEV; + err = reserve_pmu(armpmu->type); if (err) { pr_warning("unable to reserve pmu\n"); diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c index 2c3407ee8576..2334bf8a650a 100644 --- a/arch/arm/kernel/pmu.c +++ b/arch/arm/kernel/pmu.c @@ -33,3 +33,4 @@ release_pmu(enum arm_pmu_type type) { clear_bit_unlock(type, pmu_lock); } +EXPORT_SYMBOL_GPL(release_pmu); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 75316f0dd02a..3d0c6fb74ae4 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -192,6 +192,9 @@ void cpu_idle(void) #endif local_irq_disable(); +#ifdef CONFIG_PL310_ERRATA_769419 + wmb(); +#endif if (hlt_counter) { local_irq_enable(); cpu_relax(); diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 1040c00405d0..8200deaa14f6 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -43,7 +43,7 @@ struct cputopo_arm cpu_topology[NR_CPUS]; -const struct cpumask *cpu_coregroup_mask(unsigned int cpu) +const struct cpumask *cpu_coregroup_mask(int cpu) { return &cpu_topology[cpu].core_sibling; } diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h index 10d868a5a481..d6408d1ee543 100644 --- a/arch/arm/lib/bitops.h +++ b/arch/arm/lib/bitops.h @@ -1,5 +1,9 @@ +#include <asm/unwind.h> + #if __LINUX_ARM_ARCH__ >= 6 - .macro bitop, instr + .macro bitop, name, instr +ENTRY( \name ) +UNWIND( .fnstart ) ands ip, r1, #3 strneb r1, [ip] @ assert word-aligned mov r2, #1 @@ -13,9 +17,13 @@ cmp r0, #0 bne 1b bx lr +UNWIND( .fnend ) +ENDPROC(\name ) .endm - .macro testop, instr, store + .macro testop, name, instr, store +ENTRY( \name ) +UNWIND( .fnstart ) ands ip, r1, #3 strneb r1, [ip] @ assert word-aligned mov r2, #1 @@ -34,9 +42,13 @@ cmp r0, #0 movne r0, #1 2: bx lr +UNWIND( .fnend ) +ENDPROC(\name ) .endm #else - .macro bitop, instr + .macro bitop, name, instr +ENTRY( \name ) +UNWIND( .fnstart ) ands ip, r1, #3 strneb r1, [ip] @ assert word-aligned and r2, r0, #31 @@ -49,6 +61,8 @@ str r2, [r1, r0, lsl #2] restore_irqs ip mov pc, lr +UNWIND( .fnend ) +ENDPROC(\name ) .endm /** @@ -59,7 +73,9 @@ * Note: we can trivially conditionalise the store instruction * to avoid dirtying the data cache. */ - .macro testop, instr, store + .macro testop, name, instr, store +ENTRY( \name ) +UNWIND( .fnstart ) ands ip, r1, #3 strneb r1, [ip] @ assert word-aligned and r3, r0, #31 @@ -73,5 +89,7 @@ moveq r0, #0 restore_irqs ip mov pc, lr +UNWIND( .fnend ) +ENDPROC(\name ) .endm #endif diff --git a/arch/arm/lib/changebit.S b/arch/arm/lib/changebit.S index 68ed5b62e839..f4027862172f 100644 --- a/arch/arm/lib/changebit.S +++ b/arch/arm/lib/changebit.S @@ -12,6 +12,4 @@ #include "bitops.h" .text -ENTRY(_change_bit) - bitop eor -ENDPROC(_change_bit) +bitop _change_bit, eor diff --git a/arch/arm/lib/clearbit.S b/arch/arm/lib/clearbit.S index 4c04c3b51eeb..f6b75fb64d30 100644 --- a/arch/arm/lib/clearbit.S +++ b/arch/arm/lib/clearbit.S @@ -12,6 +12,4 @@ #include "bitops.h" .text -ENTRY(_clear_bit) - bitop bic -ENDPROC(_clear_bit) +bitop _clear_bit, bic diff --git a/arch/arm/lib/setbit.S b/arch/arm/lib/setbit.S index bbee5c66a23e..618fedae4b37 100644 --- a/arch/arm/lib/setbit.S +++ b/arch/arm/lib/setbit.S @@ -12,6 +12,4 @@ #include "bitops.h" .text -ENTRY(_set_bit) - bitop orr -ENDPROC(_set_bit) +bitop _set_bit, orr diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S index 15a4d431f229..4becdc3a59cb 100644 --- a/arch/arm/lib/testchangebit.S +++ b/arch/arm/lib/testchangebit.S @@ -12,6 +12,4 @@ #include "bitops.h" .text -ENTRY(_test_and_change_bit) - testop eor, str -ENDPROC(_test_and_change_bit) +testop _test_and_change_bit, eor, str diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S index 521b66b5b95d..918841dcce7a 100644 --- a/arch/arm/lib/testclearbit.S +++ b/arch/arm/lib/testclearbit.S @@ -12,6 +12,4 @@ #include "bitops.h" .text -ENTRY(_test_and_clear_bit) - testop bicne, strne -ENDPROC(_test_and_clear_bit) +testop _test_and_clear_bit, bicne, strne diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S index 1c98cc2185bb..8d1b2fe9e487 100644 --- a/arch/arm/lib/testsetbit.S +++ b/arch/arm/lib/testsetbit.S @@ -12,6 +12,4 @@ #include "bitops.h" .text -ENTRY(_test_and_set_bit) - testop orreq, streq -ENDPROC(_test_and_set_bit) +testop _test_and_set_bit, orreq, streq diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 8ac9e9f84790..b1e192ba8c24 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -61,7 +61,7 @@ static inline void cache_sync(void) { void __iomem *base = l2x0_base; -#ifdef CONFIG_ARM_ERRATA_753970 +#ifdef CONFIG_PL310_ERRATA_753970 /* write to an unmmapped register */ writel_relaxed(0, base + L2X0_DUMMY_REG); #else diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index e4e7f6cba1ab..1aa664a1999f 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -168,7 +168,7 @@ static int __init consistent_init(void) pte_t *pte; int i = 0; unsigned long base = consistent_base; - unsigned long num_ptes = (CONSISTENT_END - base) >> PGDIR_SHIFT; + unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT; consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL); if (!consistent_pte) { @@ -332,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct page *page; void *addr; + /* + * Following is a work-around (a.k.a. hack) to prevent pages + * with __GFP_COMP being passed to split_page() which cannot + * handle them. The real problem is that this flag probably + * should be 0 on ARM as it is not supported on this + * platform; see CONFIG_HUGETLBFS. + */ + gfp &= ~(__GFP_COMP); + *handle = ~0; size = PAGE_ALIGN(size); diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 74be05f3e03a..44b628e4d6ea 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -9,8 +9,7 @@ #include <linux/io.h> #include <linux/personality.h> #include <linux/random.h> -#include <asm/cputype.h> -#include <asm/system.h> +#include <asm/cachetype.h> #define COLOUR_ALIGN(addr,pgoff) \ ((((addr)+SHMLBA-1)&~(SHMLBA-1)) + \ @@ -32,25 +31,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; -#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) - unsigned int cache_type; - int do_align = 0, aliasing = 0; + int do_align = 0; + int aliasing = cache_is_vipt_aliasing(); /* * We only need to do colour alignment if either the I or D - * caches alias. This is indicated by bits 9 and 21 of the - * cache type register. + * caches alias. */ - cache_type = read_cpuid_cachetype(); - if (cache_type != read_cpuid_id()) { - aliasing = (cache_type | cache_type >> 12) & (1 << 11); - if (aliasing) - do_align = filp || flags & MAP_SHARED; - } -#else -#define do_align 0 -#define aliasing 0 -#endif + if (aliasing) + do_align = filp || (flags & MAP_SHARED); /* * We enforce the MAP_FIXED case. diff --git a/drivers/firmware/sigma.c b/drivers/firmware/sigma.c index f10fc521951b..1eedb6f7fdab 100644 --- a/drivers/firmware/sigma.c +++ b/drivers/firmware/sigma.c @@ -14,13 +14,34 @@ #include <linux/module.h> #include <linux/sigma.h> -/* Return: 0==OK, <0==error, =1 ==no more actions */ +static size_t sigma_action_size(struct sigma_action *sa) +{ + size_t payload = 0; + + switch (sa->instr) { + case SIGMA_ACTION_WRITEXBYTES: + case SIGMA_ACTION_WRITESINGLE: + case SIGMA_ACTION_WRITESAFELOAD: + payload = sigma_action_len(sa); + break; + default: + break; + } + + payload = ALIGN(payload, 2); + + return payload + sizeof(struct sigma_action); +} + +/* + * Returns a negative error value in case of an error, 0 if processing of + * the firmware should be stopped after this action, 1 otherwise. + */ static int -process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw) +process_sigma_action(struct i2c_client *client, struct sigma_action *sa) { - struct sigma_action *sa = (void *)(ssfw->fw->data + ssfw->pos); size_t len = sigma_action_len(sa); - int ret = 0; + int ret; pr_debug("%s: instr:%i addr:%#x len:%zu\n", __func__, sa->instr, sa->addr, len); @@ -29,44 +50,50 @@ process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw) case SIGMA_ACTION_WRITEXBYTES: case SIGMA_ACTION_WRITESINGLE: case SIGMA_ACTION_WRITESAFELOAD: - if (ssfw->fw->size < ssfw->pos + len) - return -EINVAL; ret = i2c_master_send(client, (void *)&sa->addr, len); if (ret < 0) return -EINVAL; break; - case SIGMA_ACTION_DELAY: - ret = 0; udelay(len); len = 0; break; - case SIGMA_ACTION_END: - return 1; - + return 0; default: return -EINVAL; } - /* when arrive here ret=0 or sent data */ - ssfw->pos += sigma_action_size(sa, len); - return ssfw->pos == ssfw->fw->size; + return 1; } static int process_sigma_actions(struct i2c_client *client, struct sigma_firmware *ssfw) { - pr_debug("%s: processing %p\n", __func__, ssfw); + struct sigma_action *sa; + size_t size; + int ret; + + while (ssfw->pos + sizeof(*sa) <= ssfw->fw->size) { + sa = (struct sigma_action *)(ssfw->fw->data + ssfw->pos); + + size = sigma_action_size(sa); + ssfw->pos += size; + if (ssfw->pos > ssfw->fw->size || size == 0) + break; + + ret = process_sigma_action(client, sa); - while (1) { - int ret = process_sigma_action(client, ssfw); pr_debug("%s: action returned %i\n", __func__, ret); - if (ret == 1) - return 0; - else if (ret) + + if (ret <= 0) return ret; } + + if (ssfw->pos != ssfw->fw->size) + return -EINVAL; + + return 0; } int process_sigma_firmware(struct i2c_client *client, const char *name) @@ -89,16 +116,24 @@ int process_sigma_firmware(struct i2c_client *client, const char *name) /* then verify the header */ ret = -EINVAL; - if (fw->size < sizeof(*ssfw_head)) + + /* + * Reject too small or unreasonable large files. The upper limit has been + * chosen a bit arbitrarily, but it should be enough for all practical + * purposes and having the limit makes it easier to avoid integer + * overflows later in the loading process. + */ + if (fw->size < sizeof(*ssfw_head) || fw->size >= 0x4000000) goto done; ssfw_head = (void *)fw->data; if (memcmp(ssfw_head->magic, SIGMA_MAGIC, ARRAY_SIZE(ssfw_head->magic))) goto done; - crc = crc32(0, fw->data, fw->size); + crc = crc32(0, fw->data + sizeof(*ssfw_head), + fw->size - sizeof(*ssfw_head)); pr_debug("%s: crc=%x\n", __func__, crc); - if (crc != ssfw_head->crc) + if (crc != le32_to_cpu(ssfw_head->crc)) goto done; ssfw.pos = sizeof(*ssfw_head); diff --git a/drivers/i2c/busses/i2c-nuc900.c b/drivers/i2c/busses/i2c-nuc900.c index 835e47b39bc2..03b615778887 100644 --- a/drivers/i2c/busses/i2c-nuc900.c +++ b/drivers/i2c/busses/i2c-nuc900.c @@ -593,7 +593,7 @@ static int __devinit nuc900_i2c_probe(struct platform_device *pdev) i2c->adap.algo_data = i2c; i2c->adap.dev.parent = &pdev->dev; - mfp_set_groupg(&pdev->dev); + mfp_set_groupg(&pdev->dev, NULL); clk_get_rate(i2c->clk); diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c index 33ec9e467772..9021182c4b76 100644 --- a/drivers/isdn/divert/divert_procfs.c +++ b/drivers/isdn/divert/divert_procfs.c @@ -242,6 +242,12 @@ static int isdn_divert_ioctl_unlocked(struct file *file, uint cmd, ulong arg) case IIOCDOCFINT: if (!divert_if.drv_to_name(dioctl.cf_ctrl.drvid)) return (-EINVAL); /* invalid driver */ + if (strnlen(dioctl.cf_ctrl.msn, sizeof(dioctl.cf_ctrl.msn)) == + sizeof(dioctl.cf_ctrl.msn)) + return -EINVAL; + if (strnlen(dioctl.cf_ctrl.fwd_nr, sizeof(dioctl.cf_ctrl.fwd_nr)) == + sizeof(dioctl.cf_ctrl.fwd_nr)) + return -EINVAL; if ((i = cf_command(dioctl.cf_ctrl.drvid, (cmd == IIOCDOCFACT) ? 1 : (cmd == IIOCDOCFDIS) ? 0 : 2, dioctl.cf_ctrl.cfproc, diff --git a/drivers/isdn/i4l/isdn_net.c b/drivers/isdn/i4l/isdn_net.c index 1f73d7f7e024..2339d7396b9e 100644 --- a/drivers/isdn/i4l/isdn_net.c +++ b/drivers/isdn/i4l/isdn_net.c @@ -2756,6 +2756,9 @@ isdn_net_setcfg(isdn_net_ioctl_cfg * cfg) char *c, *e; + if (strnlen(cfg->drvid, sizeof(cfg->drvid)) == + sizeof(cfg->drvid)) + return -EINVAL; drvidx = -1; chidx = -1; strcpy(drvid, cfg->drvid); diff --git a/drivers/net/arcnet/Kconfig b/drivers/net/arcnet/Kconfig index a73d9dc80ff6..84fb6349a59a 100644 --- a/drivers/net/arcnet/Kconfig +++ b/drivers/net/arcnet/Kconfig @@ -4,7 +4,7 @@ menuconfig ARCNET depends on NETDEVICES && (ISA || PCI || PCMCIA) - bool "ARCnet support" + tristate "ARCnet support" ---help--- If you have a network card of this type, say Y and check out the (arguably) beautiful poetry in diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b0c577256487..7f8756825b8a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2553,30 +2553,6 @@ re_arm: } } -static __be32 bond_glean_dev_ip(struct net_device *dev) -{ - struct in_device *idev; - struct in_ifaddr *ifa; - __be32 addr = 0; - - if (!dev) - return 0; - - rcu_read_lock(); - idev = __in_dev_get_rcu(dev); - if (!idev) - goto out; - - ifa = idev->ifa_list; - if (!ifa) - goto out; - - addr = ifa->ifa_local; -out: - rcu_read_unlock(); - return addr; -} - static int bond_has_this_ip(struct bonding *bond, __be32 ip) { struct vlan_entry *vlan; @@ -3322,6 +3298,10 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, struct bonding *bond; struct vlan_entry *vlan; + /* we only care about primary address */ + if(ifa->ifa_flags & IFA_F_SECONDARY) + return NOTIFY_DONE; + list_for_each_entry(bond, &bn->dev_list, bond_list) { if (bond->dev == event_dev) { switch (event) { @@ -3329,7 +3309,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, bond->master_ip = ifa->ifa_local; return NOTIFY_OK; case NETDEV_DOWN: - bond->master_ip = bond_glean_dev_ip(bond->dev); + bond->master_ip = 0; return NOTIFY_OK; default: return NOTIFY_DONE; @@ -3345,8 +3325,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event, vlan->vlan_ip = ifa->ifa_local; return NOTIFY_OK; case NETDEV_DOWN: - vlan->vlan_ip = - bond_glean_dev_ip(vlan_dev); + vlan->vlan_ip = 0; return NOTIFY_OK; default: return NOTIFY_DONE; diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 905bce0b3a43..2c7f5036f570 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -20,7 +20,6 @@ */ #include <linux/kernel.h> -#include <linux/version.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/netdevice.h> diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 4cf835dbc122..3fb66d09ece5 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -608,7 +608,7 @@ static void b44_tx(struct b44 *bp) skb->len, DMA_TO_DEVICE); rp->skb = NULL; - dev_kfree_skb(skb); + dev_kfree_skb_irq(skb); } bp->tx_cons = cons; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index bce203fa4b9e..882f48f0a03c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -10327,6 +10327,43 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy, return 0; } + +static void bnx2x_5461x_set_link_led(struct bnx2x_phy *phy, + struct link_params *params, u8 mode) +{ + struct bnx2x *bp = params->bp; + u16 temp; + + bnx2x_cl22_write(bp, phy, + MDIO_REG_GPHY_SHADOW, + MDIO_REG_GPHY_SHADOW_LED_SEL1); + bnx2x_cl22_read(bp, phy, + MDIO_REG_GPHY_SHADOW, + &temp); + temp &= 0xff00; + + DP(NETIF_MSG_LINK, "54618x set link led (mode=%x)\n", mode); + switch (mode) { + case LED_MODE_FRONT_PANEL_OFF: + case LED_MODE_OFF: + temp |= 0x00ee; + break; + case LED_MODE_OPER: + temp |= 0x0001; + break; + case LED_MODE_ON: + temp |= 0x00ff; + break; + default: + break; + } + bnx2x_cl22_write(bp, phy, + MDIO_REG_GPHY_SHADOW, + MDIO_REG_GPHY_SHADOW_WR_ENA | temp); + return; +} + + static void bnx2x_54618se_link_reset(struct bnx2x_phy *phy, struct link_params *params) { @@ -11103,7 +11140,7 @@ static struct bnx2x_phy phy_54618se = { .config_loopback = (config_loopback_t)bnx2x_54618se_config_loopback, .format_fw_ver = (format_fw_ver_t)NULL, .hw_reset = (hw_reset_t)NULL, - .set_link_led = (set_link_led_t)NULL, + .set_link_led = (set_link_led_t)bnx2x_5461x_set_link_led, .phy_specific_func = (phy_specific_func_t)NULL }; /*****************************************************************/ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index fc7bd0f23c0b..e58073ef33b4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -6990,6 +6990,7 @@ Theotherbitsarereservedandshouldbezero*/ #define MDIO_REG_INTR_MASK 0x1b #define MDIO_REG_INTR_MASK_LINK_STATUS (0x1 << 1) #define MDIO_REG_GPHY_SHADOW 0x1c +#define MDIO_REG_GPHY_SHADOW_LED_SEL1 (0x0d << 10) #define MDIO_REG_GPHY_SHADOW_LED_SEL2 (0x0e << 10) #define MDIO_REG_GPHY_SHADOW_WR_ENA (0x1 << 15) #define MDIO_REG_GPHY_SHADOW_AUTO_DET_MED (0x1e << 10) diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 438f4580bf66..2a22f5256353 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -613,7 +613,7 @@ static int dm9000_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) if (!dm->wake_state) irq_set_irq_wake(dm->irq_wake, 1); - else if (dm->wake_state & !opts) + else if (dm->wake_state && !opts) irq_set_irq_wake(dm->irq_wake, 0); } diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index c520cfd3b298..5272f9d4dda9 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -24,6 +24,7 @@ config FEC bool "FEC ethernet controller (of ColdFire and some i.MX CPUs)" depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \ ARCH_MXC || ARCH_MXS) + default ARCH_MXC || ARCH_MXS if ARM select PHYLIB ---help--- Say Y here if you want to use the built-in 10/100 Fast ethernet diff --git a/drivers/net/ethernet/ibm/ehea/ehea.h b/drivers/net/ethernet/ibm/ehea/ehea.h index 410d6a1984ed..6650068c996c 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea.h +++ b/drivers/net/ethernet/ibm/ehea/ehea.h @@ -61,9 +61,9 @@ #ifdef EHEA_SMALL_QUEUES #define EHEA_MAX_CQE_COUNT 1023 #define EHEA_DEF_ENTRIES_SQ 1023 -#define EHEA_DEF_ENTRIES_RQ1 4095 +#define EHEA_DEF_ENTRIES_RQ1 1023 #define EHEA_DEF_ENTRIES_RQ2 1023 -#define EHEA_DEF_ENTRIES_RQ3 1023 +#define EHEA_DEF_ENTRIES_RQ3 511 #else #define EHEA_MAX_CQE_COUNT 4080 #define EHEA_DEF_ENTRIES_SQ 4080 diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 37b70f7052b6..bfeccbfde236 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -371,7 +371,8 @@ static void ehea_update_stats(struct work_struct *work) out_herr: free_page((unsigned long)cb2); resched: - schedule_delayed_work(&port->stats_work, msecs_to_jiffies(1000)); + schedule_delayed_work(&port->stats_work, + round_jiffies_relative(msecs_to_jiffies(1000))); } static void ehea_refill_rq1(struct ehea_port_res *pr, int index, int nr_of_wqes) @@ -2434,7 +2435,8 @@ static int ehea_open(struct net_device *dev) } mutex_unlock(&port->port_lock); - schedule_delayed_work(&port->stats_work, msecs_to_jiffies(1000)); + schedule_delayed_work(&port->stats_work, + round_jiffies_relative(msecs_to_jiffies(1000))); return ret; } diff --git a/drivers/net/ethernet/ibm/iseries_veth.c b/drivers/net/ethernet/ibm/iseries_veth.c index 4326681df382..acc31af6594a 100644 --- a/drivers/net/ethernet/ibm/iseries_veth.c +++ b/drivers/net/ethernet/ibm/iseries_veth.c @@ -1421,7 +1421,7 @@ static void veth_receive(struct veth_lpar_connection *cnx, /* FIXME: do we need this? */ memset(local_list, 0, sizeof(local_list)); - memset(remote_list, 0, sizeof(VETH_MAX_FRAMES_PER_MSG)); + memset(remote_list, 0, sizeof(remote_list)); /* a 0 address marks the end of the valid entries */ if (senddata->addr[startchunk] == 0) diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 7becff1f387d..76b84573566b 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -1745,6 +1745,112 @@ jme_phy_off(struct jme_adapter *jme) } static int +jme_phy_specreg_read(struct jme_adapter *jme, u32 specreg) +{ + u32 phy_addr; + + phy_addr = JM_PHY_SPEC_REG_READ | specreg; + jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_ADDR_REG, + phy_addr); + return jme_mdio_read(jme->dev, jme->mii_if.phy_id, + JM_PHY_SPEC_DATA_REG); +} + +static void +jme_phy_specreg_write(struct jme_adapter *jme, u32 ext_reg, u32 phy_data) +{ + u32 phy_addr; + + phy_addr = JM_PHY_SPEC_REG_WRITE | ext_reg; + jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_DATA_REG, + phy_data); + jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_ADDR_REG, + phy_addr); +} + +static int +jme_phy_calibration(struct jme_adapter *jme) +{ + u32 ctrl1000, phy_data; + + jme_phy_off(jme); + jme_phy_on(jme); + /* Enabel PHY test mode 1 */ + ctrl1000 = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_CTRL1000); + ctrl1000 &= ~PHY_GAD_TEST_MODE_MSK; + ctrl1000 |= PHY_GAD_TEST_MODE_1; + jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_CTRL1000, ctrl1000); + + phy_data = jme_phy_specreg_read(jme, JM_PHY_EXT_COMM_2_REG); + phy_data &= ~JM_PHY_EXT_COMM_2_CALI_MODE_0; + phy_data |= JM_PHY_EXT_COMM_2_CALI_LATCH | + JM_PHY_EXT_COMM_2_CALI_ENABLE; + jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_2_REG, phy_data); + msleep(20); + phy_data = jme_phy_specreg_read(jme, JM_PHY_EXT_COMM_2_REG); + phy_data &= ~(JM_PHY_EXT_COMM_2_CALI_ENABLE | + JM_PHY_EXT_COMM_2_CALI_MODE_0 | + JM_PHY_EXT_COMM_2_CALI_LATCH); + jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_2_REG, phy_data); + + /* Disable PHY test mode */ + ctrl1000 = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_CTRL1000); + ctrl1000 &= ~PHY_GAD_TEST_MODE_MSK; + jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_CTRL1000, ctrl1000); + return 0; +} + +static int +jme_phy_setEA(struct jme_adapter *jme) +{ + u32 phy_comm0 = 0, phy_comm1 = 0; + u8 nic_ctrl; + + pci_read_config_byte(jme->pdev, PCI_PRIV_SHARE_NICCTRL, &nic_ctrl); + if ((nic_ctrl & 0x3) == JME_FLAG_PHYEA_ENABLE) + return 0; + + switch (jme->pdev->device) { + case PCI_DEVICE_ID_JMICRON_JMC250: + if (((jme->chip_main_rev == 5) && + ((jme->chip_sub_rev == 0) || (jme->chip_sub_rev == 1) || + (jme->chip_sub_rev == 3))) || + (jme->chip_main_rev >= 6)) { + phy_comm0 = 0x008A; + phy_comm1 = 0x4109; + } + if ((jme->chip_main_rev == 3) && + ((jme->chip_sub_rev == 1) || (jme->chip_sub_rev == 2))) + phy_comm0 = 0xE088; + break; + case PCI_DEVICE_ID_JMICRON_JMC260: + if (((jme->chip_main_rev == 5) && + ((jme->chip_sub_rev == 0) || (jme->chip_sub_rev == 1) || + (jme->chip_sub_rev == 3))) || + (jme->chip_main_rev >= 6)) { + phy_comm0 = 0x008A; + phy_comm1 = 0x4109; + } + if ((jme->chip_main_rev == 3) && + ((jme->chip_sub_rev == 1) || (jme->chip_sub_rev == 2))) + phy_comm0 = 0xE088; + if ((jme->chip_main_rev == 2) && (jme->chip_sub_rev == 0)) + phy_comm0 = 0x608A; + if ((jme->chip_main_rev == 2) && (jme->chip_sub_rev == 2)) + phy_comm0 = 0x408A; + break; + default: + return -ENODEV; + } + if (phy_comm0) + jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_0_REG, phy_comm0); + if (phy_comm1) + jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_1_REG, phy_comm1); + + return 0; +} + +static int jme_open(struct net_device *netdev) { struct jme_adapter *jme = netdev_priv(netdev); @@ -1769,7 +1875,8 @@ jme_open(struct net_device *netdev) jme_set_settings(netdev, &jme->old_ecmd); else jme_reset_phy_processor(jme); - + jme_phy_calibration(jme); + jme_phy_setEA(jme); jme_reset_link(jme); return 0; @@ -3184,7 +3291,8 @@ jme_resume(struct device *dev) jme_set_settings(netdev, &jme->old_ecmd); else jme_reset_phy_processor(jme); - + jme_phy_calibration(jme); + jme_phy_setEA(jme); jme_start_irq(jme); netif_device_attach(netdev); @@ -3239,4 +3347,3 @@ MODULE_DESCRIPTION("JMicron JMC2x0 PCI Express Ethernet driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, jme_pci_tbl); - diff --git a/drivers/net/ethernet/jme.h b/drivers/net/ethernet/jme.h index 02ea27c1dcb5..4304072bd3c5 100644 --- a/drivers/net/ethernet/jme.h +++ b/drivers/net/ethernet/jme.h @@ -760,6 +760,25 @@ enum jme_rxmcs_bits { RXMCS_CHECKSUM, }; +/* Extern PHY common register 2 */ + +#define PHY_GAD_TEST_MODE_1 0x00002000 +#define PHY_GAD_TEST_MODE_MSK 0x0000E000 +#define JM_PHY_SPEC_REG_READ 0x00004000 +#define JM_PHY_SPEC_REG_WRITE 0x00008000 +#define PHY_CALIBRATION_DELAY 20 +#define JM_PHY_SPEC_ADDR_REG 0x1E +#define JM_PHY_SPEC_DATA_REG 0x1F + +#define JM_PHY_EXT_COMM_0_REG 0x30 +#define JM_PHY_EXT_COMM_1_REG 0x31 +#define JM_PHY_EXT_COMM_2_REG 0x32 +#define JM_PHY_EXT_COMM_2_CALI_ENABLE 0x01 +#define JM_PHY_EXT_COMM_2_CALI_MODE_0 0x02 +#define JM_PHY_EXT_COMM_2_CALI_LATCH 0x10 +#define PCI_PRIV_SHARE_NICCTRL 0xF5 +#define JME_FLAG_PHYEA_ENABLE 0x2 + /* * Wakeup Frame setup interface registers */ diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 8731f79c9efc..b8478aab050e 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -58,10 +58,8 @@ #define TX_DESC_PER_IOCB 8 -/* The maximum number of frags we handle is based - * on PAGE_SIZE... - */ -#if (PAGE_SHIFT == 12) || (PAGE_SHIFT == 13) /* 4k & 8k pages */ + +#if ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2) > 0 #define TX_DESC_PER_OAL ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2) #else /* all other page sizes */ #define TX_DESC_PER_OAL 0 @@ -1353,7 +1351,7 @@ struct tx_ring_desc { struct ob_mac_iocb_req *queue_entry; u32 index; struct oal oal; - struct map_list map[MAX_SKB_FRAGS + 1]; + struct map_list map[MAX_SKB_FRAGS + 2]; int map_cnt; struct tx_ring_desc *next; }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8ea770a89f25..72cd190b9c1a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -781,10 +781,15 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv) unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET | MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET; - /* Do not manage MMC IRQ (FIXME) */ + /* Mask MMC irq, counters are managed in SW and registers + * are cleared on each READ eventually. */ dwmac_mmc_intr_all_mask(priv->ioaddr); - dwmac_mmc_ctrl(priv->ioaddr, mode); - memset(&priv->mmc, 0, sizeof(struct stmmac_counters)); + + if (priv->dma_cap.rmon) { + dwmac_mmc_ctrl(priv->ioaddr, mode); + memset(&priv->mmc, 0, sizeof(struct stmmac_counters)); + } else + pr_info(" No MAC Management Counters available"); } static u32 stmmac_get_synopsys_id(struct stmmac_priv *priv) @@ -1012,8 +1017,7 @@ static int stmmac_open(struct net_device *dev) memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats)); priv->xstats.threshold = tc; - if (priv->dma_cap.rmon) - stmmac_mmc_setup(priv); + stmmac_mmc_setup(priv); /* Start the ball rolling... */ DBG(probe, DEBUG, "%s: DMA RX/TX processes started...\n", dev->name); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index bb88e12101c7..a70244306c94 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -3,7 +3,7 @@ # menuconfig PHYLIB - bool "PHY Device support and infrastructure" + tristate "PHY Device support and infrastructure" depends on !S390 depends on NETDEVICES help diff --git a/drivers/net/wireless/p54/p54spi.c b/drivers/net/wireless/p54/p54spi.c index f18df82eeb92..78d0d6988553 100644 --- a/drivers/net/wireless/p54/p54spi.c +++ b/drivers/net/wireless/p54/p54spi.c @@ -588,8 +588,6 @@ static void p54spi_op_stop(struct ieee80211_hw *dev) WARN_ON(priv->fw_state != FW_STATE_READY); - cancel_work_sync(&priv->work); - p54spi_power_off(priv); spin_lock_irqsave(&priv->tx_lock, flags); INIT_LIST_HEAD(&priv->tx_pending); @@ -597,6 +595,8 @@ static void p54spi_op_stop(struct ieee80211_hw *dev) priv->fw_state = FW_STATE_OFF; mutex_unlock(&priv->mutex); + + cancel_work_sync(&priv->work); } static int __devinit p54spi_probe(struct spi_device *spi) @@ -656,6 +656,7 @@ static int __devinit p54spi_probe(struct spi_device *spi) init_completion(&priv->fw_comp); INIT_LIST_HEAD(&priv->tx_pending); mutex_init(&priv->mutex); + spin_lock_init(&priv->tx_lock); SET_IEEE80211_DEV(hw, &spi->dev); priv->common.open = p54spi_op_start; priv->common.stop = p54spi_op_stop; diff --git a/drivers/net/wireless/prism54/isl_ioctl.c b/drivers/net/wireless/prism54/isl_ioctl.c index d97a2caf582b..bc2ba80c47bb 100644 --- a/drivers/net/wireless/prism54/isl_ioctl.c +++ b/drivers/net/wireless/prism54/isl_ioctl.c @@ -778,7 +778,7 @@ prism54_get_essid(struct net_device *ndev, struct iw_request_info *info, dwrq->flags = 0; dwrq->length = 0; } - essid->octets[essid->length] = '\0'; + essid->octets[dwrq->length] = '\0'; memcpy(extra, essid->octets, dwrq->length); kfree(essid); diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 3f183a15186e..1ba079dffb11 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -3771,7 +3771,7 @@ static void rt2800_efuse_read(struct rt2x00_dev *rt2x00dev, unsigned int i) /* Apparently the data is read from end to start */ rt2800_register_read_lock(rt2x00dev, EFUSE_DATA3, ®); /* The returned value is in CPU order, but eeprom is le */ - rt2x00dev->eeprom[i] = cpu_to_le32(reg); + *(u32 *)&rt2x00dev->eeprom[i] = cpu_to_le32(reg); rt2800_register_read_lock(rt2x00dev, EFUSE_DATA2, ®); *(u32 *)&rt2x00dev->eeprom[i + 2] = cpu_to_le32(reg); rt2800_register_read_lock(rt2x00dev, EFUSE_DATA1, ®); diff --git a/drivers/net/wireless/rtlwifi/ps.c b/drivers/net/wireless/rtlwifi/ps.c index db5262844543..55c8e50f45fd 100644 --- a/drivers/net/wireless/rtlwifi/ps.c +++ b/drivers/net/wireless/rtlwifi/ps.c @@ -395,7 +395,7 @@ void rtl_lps_enter(struct ieee80211_hw *hw) if (mac->link_state != MAC80211_LINKED) return; - spin_lock(&rtlpriv->locks.lps_lock); + spin_lock_irq(&rtlpriv->locks.lps_lock); /* Idle for a while if we connect to AP a while ago. */ if (mac->cnt_after_linked >= 2) { @@ -407,7 +407,7 @@ void rtl_lps_enter(struct ieee80211_hw *hw) } } - spin_unlock(&rtlpriv->locks.lps_lock); + spin_unlock_irq(&rtlpriv->locks.lps_lock); } /*Leave the leisure power save mode.*/ @@ -416,8 +416,9 @@ void rtl_lps_leave(struct ieee80211_hw *hw) struct rtl_priv *rtlpriv = rtl_priv(hw); struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); + unsigned long flags; - spin_lock(&rtlpriv->locks.lps_lock); + spin_lock_irqsave(&rtlpriv->locks.lps_lock, flags); if (ppsc->fwctrl_lps) { if (ppsc->dot11_psmode != EACTIVE) { @@ -438,7 +439,7 @@ void rtl_lps_leave(struct ieee80211_hw *hw) rtl_lps_set_psmode(hw, EACTIVE); } } - spin_unlock(&rtlpriv->locks.lps_lock); + spin_unlock_irqrestore(&rtlpriv->locks.lps_lock, flags); } /* For sw LPS*/ @@ -539,9 +540,9 @@ void rtl_swlps_rf_awake(struct ieee80211_hw *hw) RT_CLEAR_PS_LEVEL(ppsc, RT_PS_LEVEL_ASPM); } - spin_lock(&rtlpriv->locks.lps_lock); + spin_lock_irq(&rtlpriv->locks.lps_lock); rtl_ps_set_rf_state(hw, ERFON, RF_CHANGE_BY_PS); - spin_unlock(&rtlpriv->locks.lps_lock); + spin_unlock_irq(&rtlpriv->locks.lps_lock); } void rtl_swlps_rfon_wq_callback(void *data) @@ -574,9 +575,9 @@ void rtl_swlps_rf_sleep(struct ieee80211_hw *hw) if (rtlpriv->link_info.busytraffic) return; - spin_lock(&rtlpriv->locks.lps_lock); + spin_lock_irq(&rtlpriv->locks.lps_lock); rtl_ps_set_rf_state(hw, ERFSLEEP, RF_CHANGE_BY_PS); - spin_unlock(&rtlpriv->locks.lps_lock); + spin_unlock_irq(&rtlpriv->locks.lps_lock); if (ppsc->reg_rfps_level & RT_RF_OFF_LEVL_ASPM && !RT_IN_PS_LEVEL(ppsc, RT_PS_LEVEL_ASPM)) { diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 0cb594c86090..1ae270eed51a 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1021,7 +1021,7 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk, pending_idx = *((u16 *)skb->data); xen_netbk_idx_release(netbk, pending_idx); for (j = start; j < i; j++) { - pending_idx = frag_get_pending_idx(&shinfo->frags[i]); + pending_idx = frag_get_pending_idx(&shinfo->frags[j]); xen_netbk_idx_release(netbk, pending_idx); } diff --git a/drivers/spi/spi-nuc900.c b/drivers/spi/spi-nuc900.c index e763254741c2..21c70b2b8311 100644 --- a/drivers/spi/spi-nuc900.c +++ b/drivers/spi/spi-nuc900.c @@ -426,7 +426,7 @@ static int __devinit nuc900_spi_probe(struct platform_device *pdev) goto err_clk; } - mfp_set_groupg(&pdev->dev); + mfp_set_groupg(&pdev->dev, NULL); nuc900_init_spi(hw); err = spi_bitbang_start(&hw->bitbang); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 04a5dfcee5a1..50634abef9b4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2369,6 +2369,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root, int btrfs_block_rsv_refill(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, u64 min_reserved); +int btrfs_block_rsv_refill_noflush(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 min_reserved); int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv, struct btrfs_block_rsv *dst_rsv, u64 num_bytes); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 930ae8949737..f0d5718d2587 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3888,9 +3888,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root, return ret; } -int btrfs_block_rsv_refill(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, - u64 min_reserved) +static inline int __btrfs_block_rsv_refill(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 min_reserved, int flush) { u64 num_bytes = 0; int ret = -ENOSPC; @@ -3909,7 +3909,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root, if (!ret) return 0; - ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1); + ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush); if (!ret) { block_rsv_add_bytes(block_rsv, num_bytes, 0); return 0; @@ -3918,6 +3918,20 @@ int btrfs_block_rsv_refill(struct btrfs_root *root, return ret; } +int btrfs_block_rsv_refill(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 min_reserved) +{ + return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 1); +} + +int btrfs_block_rsv_refill_noflush(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 min_reserved) +{ + return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 0); +} + int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv, struct btrfs_block_rsv *dst_rsv, u64 num_bytes) @@ -5265,7 +5279,7 @@ alloc: spin_lock(&block_group->free_space_ctl->tree_lock); if (cached && block_group->free_space_ctl->free_space < - num_bytes + empty_size) { + num_bytes + empty_cluster + empty_size) { spin_unlock(&block_group->free_space_ctl->tree_lock); goto loop; } @@ -5286,12 +5300,10 @@ alloc: * people trying to start a new cluster */ spin_lock(&last_ptr->refill_lock); - if (last_ptr->block_group && - (last_ptr->block_group->ro || - !block_group_bits(last_ptr->block_group, data))) { - offset = 0; + if (!last_ptr->block_group || + last_ptr->block_group->ro || + !block_group_bits(last_ptr->block_group, data)) goto refill_cluster; - } offset = btrfs_alloc_from_cluster(block_group, last_ptr, num_bytes, search_start); @@ -5342,7 +5354,7 @@ refill_cluster: /* allocate a cluster in this block group */ ret = btrfs_find_space_cluster(trans, root, block_group, last_ptr, - offset, num_bytes, + search_start, num_bytes, empty_cluster + empty_size); if (ret == 0) { /* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 9472d3de5e52..be1bf627a14b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2287,14 +2287,20 @@ static void end_bio_extent_readpage(struct bio *bio, int err) if (!uptodate) { int failed_mirror; failed_mirror = (int)(unsigned long)bio->bi_bdev; - if (tree->ops && tree->ops->readpage_io_failed_hook) - ret = tree->ops->readpage_io_failed_hook( - bio, page, start, end, - failed_mirror, state); - else - ret = bio_readpage_error(bio, page, start, end, - failed_mirror, NULL); + /* + * The generic bio_readpage_error handles errors the + * following way: If possible, new read requests are + * created and submitted and will end up in + * end_bio_extent_readpage as well (if we're lucky, not + * in the !uptodate case). In that case it returns 0 and + * we just go on with the next page in our bio. If it + * can't handle the error it will return -EIO and we + * remain responsible for that page. + */ + ret = bio_readpage_error(bio, page, start, end, + failed_mirror, NULL); if (ret == 0) { +error_handled: uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); if (err) @@ -2302,6 +2308,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err) uncache_state(&cached); continue; } + if (tree->ops && tree->ops->readpage_io_failed_hook) { + ret = tree->ops->readpage_io_failed_hook( + bio, page, start, end, + failed_mirror, state); + if (ret == 0) + goto error_handled; + } } if (uptodate) { diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 6e5b7e463698..ec23d43d0c35 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1470,6 +1470,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl, { info->offset = offset_to_bitmap(ctl, offset); info->bytes = 0; + INIT_LIST_HEAD(&info->list); link_free_space(ctl, info); ctl->total_bitmaps++; @@ -2319,6 +2320,7 @@ again: if (!found) { start = i; + cluster->max_size = 0; found = true; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 526dd51a1966..2c984f7d4c2a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3490,7 +3490,7 @@ void btrfs_evict_inode(struct inode *inode) * doing the truncate. */ while (1) { - ret = btrfs_block_rsv_refill(root, rsv, min_size); + ret = btrfs_block_rsv_refill_noflush(root, rsv, min_size); /* * Try and steal from the global reserve since we will diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a90e749ed6d2..72d461656f60 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1278,7 +1278,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans, root); - } else { + } else if (new_size < old_size) { ret = btrfs_shrink_device(device, new_size); } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index fab420db5121..c27bcb67f330 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -256,6 +256,11 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx) btrfs_release_path(swarn->path); ipath = init_ipath(4096, local_root, swarn->path); + if (IS_ERR(ipath)) { + ret = PTR_ERR(ipath); + ipath = NULL; + goto err; + } ret = paths_from_inode(inum, ipath); if (ret < 0) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 17ee7fc5e64e..e28ad4baf483 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1057,7 +1057,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) int i = 0, nr_devices; int ret; - nr_devices = fs_info->fs_devices->rw_devices; + nr_devices = fs_info->fs_devices->open_devices; BUG_ON(!nr_devices); devices_info = kmalloc(sizeof(*devices_info) * nr_devices, @@ -1079,8 +1079,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) else min_stripe_size = BTRFS_STRIPE_LEN; - list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { - if (!device->in_fs_metadata) + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (!device->in_fs_metadata || !device->bdev) continue; avail_space = device->total_bytes - device->bytes_used; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index ed553c60de82..3165aebb43c8 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5699,7 +5699,7 @@ int ocfs2_remove_btree_range(struct inode *inode, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); - goto out; + goto out_commit; } dquot_free_space_nodirty(inode, diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index c1efe939c774..78b68af3b0e3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -290,7 +290,15 @@ static int ocfs2_readpage(struct file *file, struct page *page) } if (down_read_trylock(&oi->ip_alloc_sem) == 0) { + /* + * Unlock the page and cycle ip_alloc_sem so that we don't + * busyloop waiting for ip_alloc_sem to unlock + */ ret = AOP_TRUNCATED_PAGE; + unlock_page(page); + unlock = 0; + down_read(&oi->ip_alloc_sem); + up_read(&oi->ip_alloc_sem); goto out_inode_unlock; } @@ -563,6 +571,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; int level; + wait_queue_head_t *wq = ocfs2_ioend_wq(inode); /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); @@ -570,6 +579,15 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, if (ocfs2_iocb_is_sem_locked(iocb)) ocfs2_iocb_clear_sem_locked(iocb); + if (ocfs2_iocb_is_unaligned_aio(iocb)) { + ocfs2_iocb_clear_unaligned_aio(iocb); + + if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) && + waitqueue_active(wq)) { + wake_up_all(wq); + } + } + ocfs2_iocb_clear_rw_locked(iocb); level = ocfs2_iocb_rw_locked_level(iocb); @@ -863,6 +881,12 @@ struct ocfs2_write_ctxt { struct page *w_target_page; /* + * w_target_locked is used for page_mkwrite path indicating no unlocking + * against w_target_page in ocfs2_write_end_nolock. + */ + unsigned int w_target_locked:1; + + /* * ocfs2_write_end() uses this to know what the real range to * write in the target should be. */ @@ -895,6 +919,24 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) { + int i; + + /* + * w_target_locked is only set to true in the page_mkwrite() case. + * The intent is to allow us to lock the target page from write_begin() + * to write_end(). The caller must hold a ref on w_target_page. + */ + if (wc->w_target_locked) { + BUG_ON(!wc->w_target_page); + for (i = 0; i < wc->w_num_pages; i++) { + if (wc->w_target_page == wc->w_pages[i]) { + wc->w_pages[i] = NULL; + break; + } + } + mark_page_accessed(wc->w_target_page); + page_cache_release(wc->w_target_page); + } ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); brelse(wc->w_di_bh); @@ -1132,20 +1174,17 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, */ lock_page(mmap_page); + /* Exit and let the caller retry */ if (mmap_page->mapping != mapping) { + WARN_ON(mmap_page->mapping); unlock_page(mmap_page); - /* - * Sanity check - the locking in - * ocfs2_pagemkwrite() should ensure - * that this code doesn't trigger. - */ - ret = -EINVAL; - mlog_errno(ret); + ret = -EAGAIN; goto out; } page_cache_get(mmap_page); wc->w_pages[i] = mmap_page; + wc->w_target_locked = true; } else { wc->w_pages[i] = find_or_create_page(mapping, index, GFP_NOFS); @@ -1160,6 +1199,8 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, wc->w_target_page = wc->w_pages[i]; } out: + if (ret) + wc->w_target_locked = false; return ret; } @@ -1817,11 +1858,23 @@ try_again: */ ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len, cluster_of_pages, mmap_page); - if (ret) { + if (ret && ret != -EAGAIN) { mlog_errno(ret); goto out_quota; } + /* + * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock + * the target page. In this case, we exit with no error and no target + * page. This will trigger the caller, page_mkwrite(), to re-try + * the operation. + */ + if (ret == -EAGAIN) { + BUG_ON(wc->w_target_page); + ret = 0; + goto out_quota; + } + ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos, len); if (ret) { diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 75cf3ad987a6..ffb2da370a99 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -78,6 +78,7 @@ enum ocfs2_iocb_lock_bits { OCFS2_IOCB_RW_LOCK = 0, OCFS2_IOCB_RW_LOCK_LEVEL, OCFS2_IOCB_SEM, + OCFS2_IOCB_UNALIGNED_IO, OCFS2_IOCB_NUM_LOCKS }; @@ -91,4 +92,17 @@ enum ocfs2_iocb_lock_bits { clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private) #define ocfs2_iocb_is_sem_locked(iocb) \ test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private) + +#define ocfs2_iocb_set_unaligned_aio(iocb) \ + set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private) +#define ocfs2_iocb_clear_unaligned_aio(iocb) \ + clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private) +#define ocfs2_iocb_is_unaligned_aio(iocb) \ + test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private) + +#define OCFS2_IOEND_WQ_HASH_SZ 37 +#define ocfs2_ioend_wq(v) (&ocfs2__ioend_wq[((unsigned long)(v)) %\ + OCFS2_IOEND_WQ_HASH_SZ]) +extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ]; + #endif /* OCFS2_FILE_H */ diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 9a3e6bbff27b..a4e855e3690e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -216,6 +216,7 @@ struct o2hb_region { struct list_head hr_all_item; unsigned hr_unclean_stop:1, + hr_aborted_start:1, hr_item_pinned:1, hr_item_dropped:1; @@ -254,6 +255,10 @@ struct o2hb_region { * a more complete api that doesn't lead to this sort of fragility. */ atomic_t hr_steady_iterations; + /* terminate o2hb thread if it does not reach steady state + * (hr_steady_iterations == 0) within hr_unsteady_iterations */ + atomic_t hr_unsteady_iterations; + char hr_dev_name[BDEVNAME_SIZE]; unsigned int hr_timeout_ms; @@ -324,6 +329,10 @@ static void o2hb_write_timeout(struct work_struct *work) static void o2hb_arm_write_timeout(struct o2hb_region *reg) { + /* Arm writeout only after thread reaches steady state */ + if (atomic_read(®->hr_steady_iterations) != 0) + return; + mlog(ML_HEARTBEAT, "Queue write timeout for %u ms\n", O2HB_MAX_WRITE_TIMEOUT_MS); @@ -537,9 +546,14 @@ static int o2hb_verify_crc(struct o2hb_region *reg, return read == computed; } -/* We want to make sure that nobody is heartbeating on top of us -- - * this will help detect an invalid configuration. */ -static void o2hb_check_last_timestamp(struct o2hb_region *reg) +/* + * Compare the slot data with what we wrote in the last iteration. + * If the match fails, print an appropriate error message. This is to + * detect errors like... another node hearting on the same slot, + * flaky device that is losing writes, etc. + * Returns 1 if check succeeds, 0 otherwise. + */ +static int o2hb_check_own_slot(struct o2hb_region *reg) { struct o2hb_disk_slot *slot; struct o2hb_disk_heartbeat_block *hb_block; @@ -548,13 +562,13 @@ static void o2hb_check_last_timestamp(struct o2hb_region *reg) slot = ®->hr_slots[o2nm_this_node()]; /* Don't check on our 1st timestamp */ if (!slot->ds_last_time) - return; + return 0; hb_block = slot->ds_raw_block; if (le64_to_cpu(hb_block->hb_seq) == slot->ds_last_time && le64_to_cpu(hb_block->hb_generation) == slot->ds_last_generation && hb_block->hb_node == slot->ds_node_num) - return; + return 1; #define ERRSTR1 "Another node is heartbeating on device" #define ERRSTR2 "Heartbeat generation mismatch on device" @@ -574,6 +588,8 @@ static void o2hb_check_last_timestamp(struct o2hb_region *reg) (unsigned long long)slot->ds_last_time, hb_block->hb_node, (unsigned long long)le64_to_cpu(hb_block->hb_generation), (unsigned long long)le64_to_cpu(hb_block->hb_seq)); + + return 0; } static inline void o2hb_prepare_block(struct o2hb_region *reg, @@ -719,17 +735,24 @@ static void o2hb_shutdown_slot(struct o2hb_disk_slot *slot) o2nm_node_put(node); } -static void o2hb_set_quorum_device(struct o2hb_region *reg, - struct o2hb_disk_slot *slot) +static void o2hb_set_quorum_device(struct o2hb_region *reg) { - assert_spin_locked(&o2hb_live_lock); - if (!o2hb_global_heartbeat_active()) return; - if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap)) + /* Prevent race with o2hb_heartbeat_group_drop_item() */ + if (kthread_should_stop()) + return; + + /* Tag region as quorum only after thread reaches steady state */ + if (atomic_read(®->hr_steady_iterations) != 0) return; + spin_lock(&o2hb_live_lock); + + if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap)) + goto unlock; + /* * A region can be added to the quorum only when it sees all * live nodes heartbeat on it. In other words, the region has been @@ -737,13 +760,10 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg, */ if (memcmp(reg->hr_live_node_bitmap, o2hb_live_node_bitmap, sizeof(o2hb_live_node_bitmap))) - return; - - if (slot->ds_changed_samples < O2HB_LIVE_THRESHOLD) - return; + goto unlock; - printk(KERN_NOTICE "o2hb: Region %s is now a quorum device\n", - config_item_name(®->hr_item)); + printk(KERN_NOTICE "o2hb: Region %s (%s) is now a quorum device\n", + config_item_name(®->hr_item), reg->hr_dev_name); set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap); @@ -754,6 +774,8 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg, if (o2hb_pop_count(&o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS) > O2HB_PIN_CUT_OFF) o2hb_region_unpin(NULL); +unlock: + spin_unlock(&o2hb_live_lock); } static int o2hb_check_slot(struct o2hb_region *reg, @@ -925,8 +947,6 @@ fire_callbacks: slot->ds_equal_samples = 0; } out: - o2hb_set_quorum_device(reg, slot); - spin_unlock(&o2hb_live_lock); o2hb_run_event_list(&event); @@ -957,7 +977,8 @@ static int o2hb_highest_node(unsigned long *nodes, static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) { - int i, ret, highest_node, change = 0; + int i, ret, highest_node; + int membership_change = 0, own_slot_ok = 0; unsigned long configured_nodes[BITS_TO_LONGS(O2NM_MAX_NODES)]; unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; struct o2hb_bio_wait_ctxt write_wc; @@ -966,7 +987,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) sizeof(configured_nodes)); if (ret) { mlog_errno(ret); - return ret; + goto bail; } /* @@ -982,8 +1003,9 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) highest_node = o2hb_highest_node(configured_nodes, O2NM_MAX_NODES); if (highest_node >= O2NM_MAX_NODES) { - mlog(ML_NOTICE, "ocfs2_heartbeat: no configured nodes found!\n"); - return -EINVAL; + mlog(ML_NOTICE, "o2hb: No configured nodes found!\n"); + ret = -EINVAL; + goto bail; } /* No sense in reading the slots of nodes that don't exist @@ -993,29 +1015,27 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) ret = o2hb_read_slots(reg, highest_node + 1); if (ret < 0) { mlog_errno(ret); - return ret; + goto bail; } /* With an up to date view of the slots, we can check that no * other node has been improperly configured to heartbeat in * our slot. */ - o2hb_check_last_timestamp(reg); + own_slot_ok = o2hb_check_own_slot(reg); /* fill in the proper info for our next heartbeat */ o2hb_prepare_block(reg, reg->hr_generation); - /* And fire off the write. Note that we don't wait on this I/O - * until later. */ ret = o2hb_issue_node_write(reg, &write_wc); if (ret < 0) { mlog_errno(ret); - return ret; + goto bail; } i = -1; while((i = find_next_bit(configured_nodes, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) { - change |= o2hb_check_slot(reg, ®->hr_slots[i]); + membership_change |= o2hb_check_slot(reg, ®->hr_slots[i]); } /* @@ -1030,18 +1050,39 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) * disk */ mlog(ML_ERROR, "Write error %d on device \"%s\"\n", write_wc.wc_error, reg->hr_dev_name); - return write_wc.wc_error; + ret = write_wc.wc_error; + goto bail; } - o2hb_arm_write_timeout(reg); + /* Skip disarming the timeout if own slot has stale/bad data */ + if (own_slot_ok) { + o2hb_set_quorum_device(reg); + o2hb_arm_write_timeout(reg); + } +bail: /* let the person who launched us know when things are steady */ - if (!change && (atomic_read(®->hr_steady_iterations) != 0)) { - if (atomic_dec_and_test(®->hr_steady_iterations)) + if (atomic_read(®->hr_steady_iterations) != 0) { + if (!ret && own_slot_ok && !membership_change) { + if (atomic_dec_and_test(®->hr_steady_iterations)) + wake_up(&o2hb_steady_queue); + } + } + + if (atomic_read(®->hr_steady_iterations) != 0) { + if (atomic_dec_and_test(®->hr_unsteady_iterations)) { + printk(KERN_NOTICE "o2hb: Unable to stabilize " + "heartbeart on region %s (%s)\n", + config_item_name(®->hr_item), + reg->hr_dev_name); + atomic_set(®->hr_steady_iterations, 0); + reg->hr_aborted_start = 1; wake_up(&o2hb_steady_queue); + ret = -EIO; + } } - return 0; + return ret; } /* Subtract b from a, storing the result in a. a *must* have a larger @@ -1095,7 +1136,8 @@ static int o2hb_thread(void *data) /* Pin node */ o2nm_depend_this_node(); - while (!kthread_should_stop() && !reg->hr_unclean_stop) { + while (!kthread_should_stop() && + !reg->hr_unclean_stop && !reg->hr_aborted_start) { /* We track the time spent inside * o2hb_do_disk_heartbeat so that we avoid more than * hr_timeout_ms between disk writes. On busy systems @@ -1103,10 +1145,7 @@ static int o2hb_thread(void *data) * likely to time itself out. */ do_gettimeofday(&before_hb); - i = 0; - do { - ret = o2hb_do_disk_heartbeat(reg); - } while (ret && ++i < 2); + ret = o2hb_do_disk_heartbeat(reg); do_gettimeofday(&after_hb); elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb); @@ -1117,7 +1156,8 @@ static int o2hb_thread(void *data) after_hb.tv_sec, (unsigned long) after_hb.tv_usec, elapsed_msec); - if (elapsed_msec < reg->hr_timeout_ms) { + if (!kthread_should_stop() && + elapsed_msec < reg->hr_timeout_ms) { /* the kthread api has blocked signals for us so no * need to record the return value. */ msleep_interruptible(reg->hr_timeout_ms - elapsed_msec); @@ -1134,20 +1174,20 @@ static int o2hb_thread(void *data) * to timeout on this region when we could just as easily * write a clear generation - thus indicating to them that * this node has left this region. - * - * XXX: Should we skip this on unclean_stop? */ - o2hb_prepare_block(reg, 0); - ret = o2hb_issue_node_write(reg, &write_wc); - if (ret == 0) { - o2hb_wait_on_io(reg, &write_wc); - } else { - mlog_errno(ret); + */ + if (!reg->hr_unclean_stop && !reg->hr_aborted_start) { + o2hb_prepare_block(reg, 0); + ret = o2hb_issue_node_write(reg, &write_wc); + if (ret == 0) + o2hb_wait_on_io(reg, &write_wc); + else + mlog_errno(ret); } /* Unpin node */ o2nm_undepend_this_node(); - mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread exiting\n"); + mlog(ML_HEARTBEAT|ML_KTHREAD, "o2hb thread exiting\n"); return 0; } @@ -1158,6 +1198,7 @@ static int o2hb_debug_open(struct inode *inode, struct file *file) struct o2hb_debug_buf *db = inode->i_private; struct o2hb_region *reg; unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)]; + unsigned long lts; char *buf = NULL; int i = -1; int out = 0; @@ -1194,9 +1235,11 @@ static int o2hb_debug_open(struct inode *inode, struct file *file) case O2HB_DB_TYPE_REGION_ELAPSED_TIME: reg = (struct o2hb_region *)db->db_data; - out += snprintf(buf + out, PAGE_SIZE - out, "%u\n", - jiffies_to_msecs(jiffies - - reg->hr_last_timeout_start)); + lts = reg->hr_last_timeout_start; + /* If 0, it has never been set before */ + if (lts) + lts = jiffies_to_msecs(jiffies - lts); + out += snprintf(buf + out, PAGE_SIZE - out, "%lu\n", lts); goto done; case O2HB_DB_TYPE_REGION_PINNED: @@ -1426,6 +1469,8 @@ static void o2hb_region_release(struct config_item *item) struct page *page; struct o2hb_region *reg = to_o2hb_region(item); + mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name); + if (reg->hr_tmp_block) kfree(reg->hr_tmp_block); @@ -1792,7 +1837,10 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, live_threshold <<= 1; spin_unlock(&o2hb_live_lock); } - atomic_set(®->hr_steady_iterations, live_threshold + 1); + ++live_threshold; + atomic_set(®->hr_steady_iterations, live_threshold); + /* unsteady_iterations is double the steady_iterations */ + atomic_set(®->hr_unsteady_iterations, (live_threshold << 1)); hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s", reg->hr_item.ci_name); @@ -1809,14 +1857,12 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, ret = wait_event_interruptible(o2hb_steady_queue, atomic_read(®->hr_steady_iterations) == 0); if (ret) { - /* We got interrupted (hello ptrace!). Clean up */ - spin_lock(&o2hb_live_lock); - hb_task = reg->hr_task; - reg->hr_task = NULL; - spin_unlock(&o2hb_live_lock); + atomic_set(®->hr_steady_iterations, 0); + reg->hr_aborted_start = 1; + } - if (hb_task) - kthread_stop(hb_task); + if (reg->hr_aborted_start) { + ret = -EIO; goto out; } @@ -1833,8 +1879,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, ret = -EIO; if (hb_task && o2hb_global_heartbeat_active()) - printk(KERN_NOTICE "o2hb: Heartbeat started on region %s\n", - config_item_name(®->hr_item)); + printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n", + config_item_name(®->hr_item), reg->hr_dev_name); out: if (filp) @@ -2092,13 +2138,6 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, /* stop the thread when the user removes the region dir */ spin_lock(&o2hb_live_lock); - if (o2hb_global_heartbeat_active()) { - clear_bit(reg->hr_region_num, o2hb_region_bitmap); - clear_bit(reg->hr_region_num, o2hb_live_region_bitmap); - if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap)) - quorum_region = 1; - clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap); - } hb_task = reg->hr_task; reg->hr_task = NULL; reg->hr_item_dropped = 1; @@ -2107,19 +2146,30 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, if (hb_task) kthread_stop(hb_task); + if (o2hb_global_heartbeat_active()) { + spin_lock(&o2hb_live_lock); + clear_bit(reg->hr_region_num, o2hb_region_bitmap); + clear_bit(reg->hr_region_num, o2hb_live_region_bitmap); + if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap)) + quorum_region = 1; + clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap); + spin_unlock(&o2hb_live_lock); + printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%s)\n", + ((atomic_read(®->hr_steady_iterations) == 0) ? + "stopped" : "start aborted"), config_item_name(item), + reg->hr_dev_name); + } + /* * If we're racing a dev_write(), we need to wake them. They will * check reg->hr_task */ if (atomic_read(®->hr_steady_iterations) != 0) { + reg->hr_aborted_start = 1; atomic_set(®->hr_steady_iterations, 0); wake_up(&o2hb_steady_queue); } - if (o2hb_global_heartbeat_active()) - printk(KERN_NOTICE "o2hb: Heartbeat stopped on region %s\n", - config_item_name(®->hr_item)); - config_item_put(item); if (!o2hb_global_heartbeat_active() || !quorum_region) diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index 3a5835904b3d..dc45deb19e68 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -47,6 +47,7 @@ #define SC_DEBUG_NAME "sock_containers" #define NST_DEBUG_NAME "send_tracking" #define STATS_DEBUG_NAME "stats" +#define NODES_DEBUG_NAME "connected_nodes" #define SHOW_SOCK_CONTAINERS 0 #define SHOW_SOCK_STATS 1 @@ -55,6 +56,7 @@ static struct dentry *o2net_dentry; static struct dentry *sc_dentry; static struct dentry *nst_dentry; static struct dentry *stats_dentry; +static struct dentry *nodes_dentry; static DEFINE_SPINLOCK(o2net_debug_lock); @@ -491,53 +493,87 @@ static const struct file_operations sc_seq_fops = { .release = sc_fop_release, }; -int o2net_debugfs_init(void) +static int o2net_fill_bitmap(char *buf, int len) { - o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL); - if (!o2net_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } + unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)]; + int i = -1, out = 0; - nst_dentry = debugfs_create_file(NST_DEBUG_NAME, S_IFREG|S_IRUSR, - o2net_dentry, NULL, - &nst_seq_fops); - if (!nst_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } + o2net_fill_node_map(map, sizeof(map)); - sc_dentry = debugfs_create_file(SC_DEBUG_NAME, S_IFREG|S_IRUSR, - o2net_dentry, NULL, - &sc_seq_fops); - if (!sc_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } + while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) + out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i); + out += snprintf(buf + out, PAGE_SIZE - out, "\n"); - stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, S_IFREG|S_IRUSR, - o2net_dentry, NULL, - &stats_seq_fops); - if (!stats_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } + return out; +} + +static int nodes_fop_open(struct inode *inode, struct file *file) +{ + char *buf; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + i_size_write(inode, o2net_fill_bitmap(buf, PAGE_SIZE)); + + file->private_data = buf; return 0; -bail: - debugfs_remove(stats_dentry); - debugfs_remove(sc_dentry); - debugfs_remove(nst_dentry); - debugfs_remove(o2net_dentry); - return -ENOMEM; } +static int o2net_debug_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static ssize_t o2net_debug_read(struct file *file, char __user *buf, + size_t nbytes, loff_t *ppos) +{ + return simple_read_from_buffer(buf, nbytes, ppos, file->private_data, + i_size_read(file->f_mapping->host)); +} + +static const struct file_operations nodes_fops = { + .open = nodes_fop_open, + .release = o2net_debug_release, + .read = o2net_debug_read, + .llseek = generic_file_llseek, +}; + void o2net_debugfs_exit(void) { + debugfs_remove(nodes_dentry); debugfs_remove(stats_dentry); debugfs_remove(sc_dentry); debugfs_remove(nst_dentry); debugfs_remove(o2net_dentry); } +int o2net_debugfs_init(void) +{ + mode_t mode = S_IFREG|S_IRUSR; + + o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL); + if (o2net_dentry) + nst_dentry = debugfs_create_file(NST_DEBUG_NAME, mode, + o2net_dentry, NULL, &nst_seq_fops); + if (nst_dentry) + sc_dentry = debugfs_create_file(SC_DEBUG_NAME, mode, + o2net_dentry, NULL, &sc_seq_fops); + if (sc_dentry) + stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, mode, + o2net_dentry, NULL, &stats_seq_fops); + if (stats_dentry) + nodes_dentry = debugfs_create_file(NODES_DEBUG_NAME, mode, + o2net_dentry, NULL, &nodes_fops); + if (nodes_dentry) + return 0; + + o2net_debugfs_exit(); + mlog_errno(-ENOMEM); + return -ENOMEM; +} + #endif /* CONFIG_DEBUG_FS */ diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index ad7d0c155de4..044e7b58d31c 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -546,7 +546,7 @@ static void o2net_set_nn_state(struct o2net_node *nn, } if (was_valid && !valid) { - printk(KERN_NOTICE "o2net: no longer connected to " + printk(KERN_NOTICE "o2net: No longer connected to " SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc)); o2net_complete_nodes_nsw(nn); } @@ -556,7 +556,7 @@ static void o2net_set_nn_state(struct o2net_node *nn, cancel_delayed_work(&nn->nn_connect_expired); printk(KERN_NOTICE "o2net: %s " SC_NODEF_FMT "\n", o2nm_this_node() > sc->sc_node->nd_num ? - "connected to" : "accepted connection from", + "Connected to" : "Accepted connection from", SC_NODEF_ARGS(sc)); } @@ -644,7 +644,7 @@ static void o2net_state_change(struct sock *sk) o2net_sc_queue_work(sc, &sc->sc_connect_work); break; default: - printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT + printk(KERN_INFO "o2net: Connection to " SC_NODEF_FMT " shutdown, state %d\n", SC_NODEF_ARGS(sc), sk->sk_state); o2net_sc_queue_work(sc, &sc->sc_shutdown_work); @@ -1035,6 +1035,25 @@ static int o2net_tx_can_proceed(struct o2net_node *nn, return ret; } +/* Get a map of all nodes to which this node is currently connected to */ +void o2net_fill_node_map(unsigned long *map, unsigned bytes) +{ + struct o2net_sock_container *sc; + int node, ret; + + BUG_ON(bytes < (BITS_TO_LONGS(O2NM_MAX_NODES) * sizeof(unsigned long))); + + memset(map, 0, bytes); + for (node = 0; node < O2NM_MAX_NODES; ++node) { + o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret); + if (!ret) { + set_bit(node, map); + sc_put(sc); + } + } +} +EXPORT_SYMBOL_GPL(o2net_fill_node_map); + int o2net_send_message_vec(u32 msg_type, u32 key, struct kvec *caller_vec, size_t caller_veclen, u8 target_node, int *status) { @@ -1285,11 +1304,11 @@ static int o2net_check_handshake(struct o2net_sock_container *sc) struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); if (hand->protocol_version != cpu_to_be64(O2NET_PROTOCOL_VERSION)) { - mlog(ML_NOTICE, SC_NODEF_FMT " advertised net protocol " - "version %llu but %llu is required, disconnecting\n", - SC_NODEF_ARGS(sc), - (unsigned long long)be64_to_cpu(hand->protocol_version), - O2NET_PROTOCOL_VERSION); + printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " Advertised net " + "protocol version %llu but %llu is required. " + "Disconnecting.\n", SC_NODEF_ARGS(sc), + (unsigned long long)be64_to_cpu(hand->protocol_version), + O2NET_PROTOCOL_VERSION); /* don't bother reconnecting if its the wrong version. */ o2net_ensure_shutdown(nn, sc, -ENOTCONN); @@ -1303,33 +1322,33 @@ static int o2net_check_handshake(struct o2net_sock_container *sc) */ if (be32_to_cpu(hand->o2net_idle_timeout_ms) != o2net_idle_timeout()) { - mlog(ML_NOTICE, SC_NODEF_FMT " uses a network idle timeout of " - "%u ms, but we use %u ms locally. disconnecting\n", - SC_NODEF_ARGS(sc), - be32_to_cpu(hand->o2net_idle_timeout_ms), - o2net_idle_timeout()); + printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a network " + "idle timeout of %u ms, but we use %u ms locally. " + "Disconnecting.\n", SC_NODEF_ARGS(sc), + be32_to_cpu(hand->o2net_idle_timeout_ms), + o2net_idle_timeout()); o2net_ensure_shutdown(nn, sc, -ENOTCONN); return -1; } if (be32_to_cpu(hand->o2net_keepalive_delay_ms) != o2net_keepalive_delay()) { - mlog(ML_NOTICE, SC_NODEF_FMT " uses a keepalive delay of " - "%u ms, but we use %u ms locally. disconnecting\n", - SC_NODEF_ARGS(sc), - be32_to_cpu(hand->o2net_keepalive_delay_ms), - o2net_keepalive_delay()); + printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a keepalive " + "delay of %u ms, but we use %u ms locally. " + "Disconnecting.\n", SC_NODEF_ARGS(sc), + be32_to_cpu(hand->o2net_keepalive_delay_ms), + o2net_keepalive_delay()); o2net_ensure_shutdown(nn, sc, -ENOTCONN); return -1; } if (be32_to_cpu(hand->o2hb_heartbeat_timeout_ms) != O2HB_MAX_WRITE_TIMEOUT_MS) { - mlog(ML_NOTICE, SC_NODEF_FMT " uses a heartbeat timeout of " - "%u ms, but we use %u ms locally. disconnecting\n", - SC_NODEF_ARGS(sc), - be32_to_cpu(hand->o2hb_heartbeat_timeout_ms), - O2HB_MAX_WRITE_TIMEOUT_MS); + printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a heartbeat " + "timeout of %u ms, but we use %u ms locally. " + "Disconnecting.\n", SC_NODEF_ARGS(sc), + be32_to_cpu(hand->o2hb_heartbeat_timeout_ms), + O2HB_MAX_WRITE_TIMEOUT_MS); o2net_ensure_shutdown(nn, sc, -ENOTCONN); return -1; } @@ -1540,28 +1559,16 @@ static void o2net_idle_timer(unsigned long data) { struct o2net_sock_container *sc = (struct o2net_sock_container *)data; struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); - #ifdef CONFIG_DEBUG_FS - ktime_t now = ktime_get(); + unsigned long msecs = ktime_to_ms(ktime_get()) - + ktime_to_ms(sc->sc_tv_timer); +#else + unsigned long msecs = o2net_idle_timeout(); #endif - printk(KERN_NOTICE "o2net: connection to " SC_NODEF_FMT " has been idle for %u.%u " - "seconds, shutting it down.\n", SC_NODEF_ARGS(sc), - o2net_idle_timeout() / 1000, - o2net_idle_timeout() % 1000); - -#ifdef CONFIG_DEBUG_FS - mlog(ML_NOTICE, "Here are some times that might help debug the " - "situation: (Timer: %lld, Now %lld, DataReady %lld, Advance %lld-%lld, " - "Key 0x%08x, Func %u, FuncTime %lld-%lld)\n", - (long long)ktime_to_us(sc->sc_tv_timer), (long long)ktime_to_us(now), - (long long)ktime_to_us(sc->sc_tv_data_ready), - (long long)ktime_to_us(sc->sc_tv_advance_start), - (long long)ktime_to_us(sc->sc_tv_advance_stop), - sc->sc_msg_key, sc->sc_msg_type, - (long long)ktime_to_us(sc->sc_tv_func_start), - (long long)ktime_to_us(sc->sc_tv_func_stop)); -#endif + printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been " + "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc), + msecs / 1000, msecs % 1000); /* * Initialize the nn_timeout so that the next connection attempt @@ -1694,8 +1701,8 @@ static void o2net_start_connect(struct work_struct *work) out: if (ret) { - mlog(ML_NOTICE, "connect attempt to " SC_NODEF_FMT " failed " - "with errno %d\n", SC_NODEF_ARGS(sc), ret); + printk(KERN_NOTICE "o2net: Connect attempt to " SC_NODEF_FMT + " failed with errno %d\n", SC_NODEF_ARGS(sc), ret); /* 0 err so that another will be queued and attempted * from set_nn_state */ if (sc) @@ -1718,8 +1725,8 @@ static void o2net_connect_expired(struct work_struct *work) spin_lock(&nn->nn_lock); if (!nn->nn_sc_valid) { - mlog(ML_ERROR, "no connection established with node %u after " - "%u.%u seconds, giving up and returning errors.\n", + printk(KERN_NOTICE "o2net: No connection established with " + "node %u after %u.%u seconds, giving up.\n", o2net_num_from_nn(nn), o2net_idle_timeout() / 1000, o2net_idle_timeout() % 1000); @@ -1862,21 +1869,21 @@ static int o2net_accept_one(struct socket *sock) node = o2nm_get_node_by_ip(sin.sin_addr.s_addr); if (node == NULL) { - mlog(ML_NOTICE, "attempt to connect from unknown node at %pI4:%d\n", - &sin.sin_addr.s_addr, ntohs(sin.sin_port)); + printk(KERN_NOTICE "o2net: Attempt to connect from unknown " + "node at %pI4:%d\n", &sin.sin_addr.s_addr, + ntohs(sin.sin_port)); ret = -EINVAL; goto out; } if (o2nm_this_node() >= node->nd_num) { local_node = o2nm_get_node_by_num(o2nm_this_node()); - mlog(ML_NOTICE, "unexpected connect attempt seen at node '%s' (" - "%u, %pI4:%d) from node '%s' (%u, %pI4:%d)\n", - local_node->nd_name, local_node->nd_num, - &(local_node->nd_ipv4_address), - ntohs(local_node->nd_ipv4_port), - node->nd_name, node->nd_num, &sin.sin_addr.s_addr, - ntohs(sin.sin_port)); + printk(KERN_NOTICE "o2net: Unexpected connect attempt seen " + "at node '%s' (%u, %pI4:%d) from node '%s' (%u, " + "%pI4:%d)\n", local_node->nd_name, local_node->nd_num, + &(local_node->nd_ipv4_address), + ntohs(local_node->nd_ipv4_port), node->nd_name, + node->nd_num, &sin.sin_addr.s_addr, ntohs(sin.sin_port)); ret = -EINVAL; goto out; } @@ -1901,10 +1908,10 @@ static int o2net_accept_one(struct socket *sock) ret = 0; spin_unlock(&nn->nn_lock); if (ret) { - mlog(ML_NOTICE, "attempt to connect from node '%s' at " - "%pI4:%d but it already has an open connection\n", - node->nd_name, &sin.sin_addr.s_addr, - ntohs(sin.sin_port)); + printk(KERN_NOTICE "o2net: Attempt to connect from node '%s' " + "at %pI4:%d but it already has an open connection\n", + node->nd_name, &sin.sin_addr.s_addr, + ntohs(sin.sin_port)); goto out; } @@ -1984,7 +1991,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port) ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) { - mlog(ML_ERROR, "unable to create socket, ret=%d\n", ret); + printk(KERN_ERR "o2net: Error %d while creating socket\n", ret); goto out; } @@ -2001,16 +2008,15 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port) sock->sk->sk_reuse = 1; ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin)); if (ret < 0) { - mlog(ML_ERROR, "unable to bind socket at %pI4:%u, " - "ret=%d\n", &addr, ntohs(port), ret); + printk(KERN_ERR "o2net: Error %d while binding socket at " + "%pI4:%u\n", ret, &addr, ntohs(port)); goto out; } ret = sock->ops->listen(sock, 64); - if (ret < 0) { - mlog(ML_ERROR, "unable to listen on %pI4:%u, ret=%d\n", - &addr, ntohs(port), ret); - } + if (ret < 0) + printk(KERN_ERR "o2net: Error %d while listening on %pI4:%u\n", + ret, &addr, ntohs(port)); out: if (ret) { diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h index fd6179eb26d4..5bada2a69b50 100644 --- a/fs/ocfs2/cluster/tcp.h +++ b/fs/ocfs2/cluster/tcp.h @@ -106,6 +106,8 @@ int o2net_register_handler(u32 msg_type, u32 key, u32 max_len, struct list_head *unreg_list); void o2net_unregister_handler_list(struct list_head *list); +void o2net_fill_node_map(unsigned long *map, unsigned bytes); + struct o2nm_node; int o2net_register_hb_callbacks(void); void o2net_unregister_hb_callbacks(void); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index e2878b5895fb..8fe4e2892ab9 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1184,8 +1184,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, if (pde) le16_add_cpu(&pde->rec_len, le16_to_cpu(de->rec_len)); - else - de->inode = 0; + de->inode = 0; dir->i_version++; ocfs2_journal_dirty(handle, bh); goto bail; diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index d602abb51b61..a5952ceecba5 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -859,8 +859,8 @@ void dlm_complete_recovery_thread(struct dlm_ctxt *dlm); void dlm_wait_for_recovery(struct dlm_ctxt *dlm); void dlm_kick_recovery_thread(struct dlm_ctxt *dlm); int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node); -int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout); -int dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout); +void dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout); +void dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout); void dlm_put(struct dlm_ctxt *dlm); struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm); @@ -877,9 +877,8 @@ static inline void dlm_lockres_get(struct dlm_lock_resource *res) kref_get(&res->refs); } void dlm_lockres_put(struct dlm_lock_resource *res); -void __dlm_unhash_lockres(struct dlm_lock_resource *res); -void __dlm_insert_lockres(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res); +void __dlm_unhash_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); +void __dlm_insert_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm, const char *name, unsigned int len, @@ -902,46 +901,15 @@ struct dlm_lock_resource *dlm_new_lockres(struct dlm_ctxt *dlm, const char *name, unsigned int namelen); -#define dlm_lockres_set_refmap_bit(bit,res) \ - __dlm_lockres_set_refmap_bit(bit,res,__FILE__,__LINE__) -#define dlm_lockres_clear_refmap_bit(bit,res) \ - __dlm_lockres_clear_refmap_bit(bit,res,__FILE__,__LINE__) +void dlm_lockres_set_refmap_bit(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, int bit); +void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, int bit); -static inline void __dlm_lockres_set_refmap_bit(int bit, - struct dlm_lock_resource *res, - const char *file, - int line) -{ - //printk("%s:%d:%.*s: setting bit %d\n", file, line, - // res->lockname.len, res->lockname.name, bit); - set_bit(bit, res->refmap); -} - -static inline void __dlm_lockres_clear_refmap_bit(int bit, - struct dlm_lock_resource *res, - const char *file, - int line) -{ - //printk("%s:%d:%.*s: clearing bit %d\n", file, line, - // res->lockname.len, res->lockname.name, bit); - clear_bit(bit, res->refmap); -} - -void __dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, - const char *file, - int line); -void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, - int new_lockres, - const char *file, - int line); -#define dlm_lockres_drop_inflight_ref(d,r) \ - __dlm_lockres_drop_inflight_ref(d,r,__FILE__,__LINE__) -#define dlm_lockres_grab_inflight_ref(d,r) \ - __dlm_lockres_grab_inflight_ref(d,r,0,__FILE__,__LINE__) -#define dlm_lockres_grab_inflight_ref_new(d,r) \ - __dlm_lockres_grab_inflight_ref(d,r,1,__FILE__,__LINE__) +void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res); +void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res); void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock); void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock); diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 6ed6b95dcf93..92f2ead0fab6 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -157,16 +157,18 @@ static int dlm_protocol_compare(struct dlm_protocol_version *existing, static void dlm_unregister_domain_handlers(struct dlm_ctxt *dlm); -void __dlm_unhash_lockres(struct dlm_lock_resource *lockres) +void __dlm_unhash_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { - if (!hlist_unhashed(&lockres->hash_node)) { - hlist_del_init(&lockres->hash_node); - dlm_lockres_put(lockres); - } + if (hlist_unhashed(&res->hash_node)) + return; + + mlog(0, "%s: Unhash res %.*s\n", dlm->name, res->lockname.len, + res->lockname.name); + hlist_del_init(&res->hash_node); + dlm_lockres_put(res); } -void __dlm_insert_lockres(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res) +void __dlm_insert_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { struct hlist_head *bucket; struct qstr *q; @@ -180,6 +182,9 @@ void __dlm_insert_lockres(struct dlm_ctxt *dlm, dlm_lockres_get(res); hlist_add_head(&res->hash_node, bucket); + + mlog(0, "%s: Hash res %.*s\n", dlm->name, res->lockname.len, + res->lockname.name); } struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm, @@ -539,17 +544,17 @@ again: static void __dlm_print_nodes(struct dlm_ctxt *dlm) { - int node = -1; + int node = -1, num = 0; assert_spin_locked(&dlm->spinlock); - printk(KERN_NOTICE "o2dlm: Nodes in domain %s: ", dlm->name); - + printk("( "); while ((node = find_next_bit(dlm->domain_map, O2NM_MAX_NODES, node + 1)) < O2NM_MAX_NODES) { printk("%d ", node); + ++num; } - printk("\n"); + printk(") %u nodes\n", num); } static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data, @@ -566,11 +571,10 @@ static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data, node = exit_msg->node_idx; - printk(KERN_NOTICE "o2dlm: Node %u leaves domain %s\n", node, dlm->name); - spin_lock(&dlm->spinlock); clear_bit(node, dlm->domain_map); clear_bit(node, dlm->exit_domain_map); + printk(KERN_NOTICE "o2dlm: Node %u leaves domain %s ", node, dlm->name); __dlm_print_nodes(dlm); /* notify anything attached to the heartbeat events */ @@ -755,6 +759,7 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm) dlm_mark_domain_leaving(dlm); dlm_leave_domain(dlm); + printk(KERN_NOTICE "o2dlm: Leaving domain %s\n", dlm->name); dlm_force_free_mles(dlm); dlm_complete_dlm_shutdown(dlm); } @@ -970,7 +975,7 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data, clear_bit(assert->node_idx, dlm->exit_domain_map); __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN); - printk(KERN_NOTICE "o2dlm: Node %u joins domain %s\n", + printk(KERN_NOTICE "o2dlm: Node %u joins domain %s ", assert->node_idx, dlm->name); __dlm_print_nodes(dlm); @@ -1701,8 +1706,10 @@ static int dlm_try_to_join_domain(struct dlm_ctxt *dlm) bail: spin_lock(&dlm->spinlock); __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN); - if (!status) + if (!status) { + printk(KERN_NOTICE "o2dlm: Joining domain %s ", dlm->name); __dlm_print_nodes(dlm); + } spin_unlock(&dlm->spinlock); if (ctxt) { @@ -2131,13 +2138,6 @@ struct dlm_ctxt * dlm_register_domain(const char *domain, goto leave; } - if (!o2hb_check_local_node_heartbeating()) { - mlog(ML_ERROR, "the local node has not been configured, or is " - "not heartbeating\n"); - ret = -EPROTO; - goto leave; - } - mlog(0, "register called for domain \"%s\"\n", domain); retry: diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 8d39e0fd66f7..975810b98492 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -183,10 +183,6 @@ static enum dlm_status dlmlock_master(struct dlm_ctxt *dlm, kick_thread = 1; } } - /* reduce the inflight count, this may result in the lockres - * being purged below during calc_usage */ - if (lock->ml.node == dlm->node_num) - dlm_lockres_drop_inflight_ref(dlm, res); spin_unlock(&res->spinlock); wake_up(&res->wq); @@ -231,10 +227,16 @@ static enum dlm_status dlmlock_remote(struct dlm_ctxt *dlm, lock->ml.type, res->lockname.len, res->lockname.name, flags); + /* + * Wait if resource is getting recovered, remastered, etc. + * If the resource was remastered and new owner is self, then exit. + */ spin_lock(&res->spinlock); - - /* will exit this call with spinlock held */ __dlm_wait_on_lockres(res); + if (res->owner == dlm->node_num) { + spin_unlock(&res->spinlock); + return DLM_RECOVERING; + } res->state |= DLM_LOCK_RES_IN_PROGRESS; /* add lock to local (secondary) queue */ @@ -319,27 +321,23 @@ static enum dlm_status dlm_send_remote_lock_request(struct dlm_ctxt *dlm, tmpret = o2net_send_message(DLM_CREATE_LOCK_MSG, dlm->key, &create, sizeof(create), res->owner, &status); if (tmpret >= 0) { - // successfully sent and received - ret = status; // this is already a dlm_status + ret = status; if (ret == DLM_REJECTED) { - mlog(ML_ERROR, "%s:%.*s: BUG. this is a stale lockres " - "no longer owned by %u. that node is coming back " - "up currently.\n", dlm->name, create.namelen, + mlog(ML_ERROR, "%s: res %.*s, Stale lockres no longer " + "owned by node %u. That node is coming back up " + "currently.\n", dlm->name, create.namelen, create.name, res->owner); dlm_print_one_lock_resource(res); BUG(); } } else { - mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to " - "node %u\n", tmpret, DLM_CREATE_LOCK_MSG, dlm->key, - res->owner); - if (dlm_is_host_down(tmpret)) { + mlog(ML_ERROR, "%s: res %.*s, Error %d send CREATE LOCK to " + "node %u\n", dlm->name, create.namelen, create.name, + tmpret, res->owner); + if (dlm_is_host_down(tmpret)) ret = DLM_RECOVERING; - mlog(0, "node %u died so returning DLM_RECOVERING " - "from lock message!\n", res->owner); - } else { + else ret = dlm_err_to_dlm_status(tmpret); - } } return ret; @@ -440,7 +438,7 @@ struct dlm_lock * dlm_new_lock(int type, u8 node, u64 cookie, /* zero memory only if kernel-allocated */ lksb = kzalloc(sizeof(*lksb), GFP_NOFS); if (!lksb) { - kfree(lock); + kmem_cache_free(dlm_lock_cache, lock); return NULL; } kernel_allocated = 1; @@ -718,18 +716,10 @@ retry_lock: if (status == DLM_RECOVERING || status == DLM_MIGRATING || status == DLM_FORWARD) { - mlog(0, "retrying lock with migration/" - "recovery/in progress\n"); msleep(100); - /* no waiting for dlm_reco_thread */ if (recovery) { if (status != DLM_RECOVERING) goto retry_lock; - - mlog(0, "%s: got RECOVERING " - "for $RECOVERY lock, master " - "was %u\n", dlm->name, - res->owner); /* wait to see the node go down, then * drop down and allow the lockres to * get cleaned up. need to remaster. */ @@ -741,6 +731,14 @@ retry_lock: } } + /* Inflight taken in dlm_get_lock_resource() is dropped here */ + spin_lock(&res->spinlock); + dlm_lockres_drop_inflight_ref(dlm, res); + spin_unlock(&res->spinlock); + + dlm_lockres_calc_usage(dlm, res); + dlm_kick_thread(dlm, res); + if (status != DLM_NORMAL) { lock->lksb->flags &= ~DLM_LKSB_GET_LVB; if (status != DLM_NOTQUEUED) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 11eefb8c12e9..005261c333b0 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -631,39 +631,54 @@ error: return NULL; } -void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, - int new_lockres, - const char *file, - int line) +void dlm_lockres_set_refmap_bit(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, int bit) { - if (!new_lockres) - assert_spin_locked(&res->spinlock); + assert_spin_locked(&res->spinlock); + + mlog(0, "res %.*s, set node %u, %ps()\n", res->lockname.len, + res->lockname.name, bit, __builtin_return_address(0)); + + set_bit(bit, res->refmap); +} + +void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, int bit) +{ + assert_spin_locked(&res->spinlock); + + mlog(0, "res %.*s, clr node %u, %ps()\n", res->lockname.len, + res->lockname.name, bit, __builtin_return_address(0)); + + clear_bit(bit, res->refmap); +} + + +void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); - if (!test_bit(dlm->node_num, res->refmap)) { - BUG_ON(res->inflight_locks != 0); - dlm_lockres_set_refmap_bit(dlm->node_num, res); - } res->inflight_locks++; - mlog(0, "%s:%.*s: inflight++: now %u\n", - dlm->name, res->lockname.len, res->lockname.name, - res->inflight_locks); + + mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name, + res->lockname.len, res->lockname.name, res->inflight_locks, + __builtin_return_address(0)); } -void __dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, - struct dlm_lock_resource *res, - const char *file, - int line) +void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) { assert_spin_locked(&res->spinlock); BUG_ON(res->inflight_locks == 0); + res->inflight_locks--; - mlog(0, "%s:%.*s: inflight--: now %u\n", - dlm->name, res->lockname.len, res->lockname.name, - res->inflight_locks); - if (res->inflight_locks == 0) - dlm_lockres_clear_refmap_bit(dlm->node_num, res); + + mlog(0, "%s: res %.*s, inflight--: now %u, %ps()\n", dlm->name, + res->lockname.len, res->lockname.name, res->inflight_locks, + __builtin_return_address(0)); + wake_up(&res->wq); } @@ -697,7 +712,6 @@ struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm, unsigned int hash; int tries = 0; int bit, wait_on_recovery = 0; - int drop_inflight_if_nonlocal = 0; BUG_ON(!lockid); @@ -709,36 +723,33 @@ lookup: spin_lock(&dlm->spinlock); tmpres = __dlm_lookup_lockres_full(dlm, lockid, namelen, hash); if (tmpres) { - int dropping_ref = 0; - spin_unlock(&dlm->spinlock); - spin_lock(&tmpres->spinlock); - /* We wait for the other thread that is mastering the resource */ + /* Wait on the thread that is mastering the resource */ if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { __dlm_wait_on_lockres(tmpres); BUG_ON(tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN); + spin_unlock(&tmpres->spinlock); + dlm_lockres_put(tmpres); + tmpres = NULL; + goto lookup; } - if (tmpres->owner == dlm->node_num) { - BUG_ON(tmpres->state & DLM_LOCK_RES_DROPPING_REF); - dlm_lockres_grab_inflight_ref(dlm, tmpres); - } else if (tmpres->state & DLM_LOCK_RES_DROPPING_REF) - dropping_ref = 1; - spin_unlock(&tmpres->spinlock); - - /* wait until done messaging the master, drop our ref to allow - * the lockres to be purged, start over. */ - if (dropping_ref) { - spin_lock(&tmpres->spinlock); - __dlm_wait_on_lockres_flags(tmpres, DLM_LOCK_RES_DROPPING_REF); + /* Wait on the resource purge to complete before continuing */ + if (tmpres->state & DLM_LOCK_RES_DROPPING_REF) { + BUG_ON(tmpres->owner == dlm->node_num); + __dlm_wait_on_lockres_flags(tmpres, + DLM_LOCK_RES_DROPPING_REF); spin_unlock(&tmpres->spinlock); dlm_lockres_put(tmpres); tmpres = NULL; goto lookup; } - mlog(0, "found in hash!\n"); + /* Grab inflight ref to pin the resource */ + dlm_lockres_grab_inflight_ref(dlm, tmpres); + + spin_unlock(&tmpres->spinlock); if (res) dlm_lockres_put(res); res = tmpres; @@ -829,8 +840,8 @@ lookup: * but they might own this lockres. wait on them. */ bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0); if (bit < O2NM_MAX_NODES) { - mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to " - "recover before lock mastery can begin\n", + mlog(0, "%s: res %.*s, At least one node (%d) " + "to recover before lock mastery can begin\n", dlm->name, namelen, (char *)lockid, bit); wait_on_recovery = 1; } @@ -843,12 +854,11 @@ lookup: /* finally add the lockres to its hash bucket */ __dlm_insert_lockres(dlm, res); - /* since this lockres is new it doesn't not require the spinlock */ - dlm_lockres_grab_inflight_ref_new(dlm, res); - /* if this node does not become the master make sure to drop - * this inflight reference below */ - drop_inflight_if_nonlocal = 1; + /* Grab inflight ref to pin the resource */ + spin_lock(&res->spinlock); + dlm_lockres_grab_inflight_ref(dlm, res); + spin_unlock(&res->spinlock); /* get an extra ref on the mle in case this is a BLOCK * if so, the creator of the BLOCK may try to put the last @@ -864,8 +874,8 @@ redo_request: * dlm spinlock would be detectable be a change on the mle, * so we only need to clear out the recovery map once. */ if (dlm_is_recovery_lock(lockid, namelen)) { - mlog(ML_NOTICE, "%s: recovery map is not empty, but " - "must master $RECOVERY lock now\n", dlm->name); + mlog(0, "%s: Recovery map is not empty, but must " + "master $RECOVERY lock now\n", dlm->name); if (!dlm_pre_master_reco_lockres(dlm, res)) wait_on_recovery = 0; else { @@ -883,8 +893,8 @@ redo_request: spin_lock(&dlm->spinlock); bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0); if (bit < O2NM_MAX_NODES) { - mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to " - "recover before lock mastery can begin\n", + mlog(0, "%s: res %.*s, At least one node (%d) " + "to recover before lock mastery can begin\n", dlm->name, namelen, (char *)lockid, bit); wait_on_recovery = 1; } else @@ -913,8 +923,8 @@ redo_request: * yet, keep going until it does. this is how the * master will know that asserts are needed back to * the lower nodes. */ - mlog(0, "%s:%.*s: requests only up to %u but master " - "is %u, keep going\n", dlm->name, namelen, + mlog(0, "%s: res %.*s, Requests only up to %u but " + "master is %u, keep going\n", dlm->name, namelen, lockid, nodenum, mle->master); } } @@ -924,13 +934,12 @@ wait: ret = dlm_wait_for_lock_mastery(dlm, res, mle, &blocked); if (ret < 0) { wait_on_recovery = 1; - mlog(0, "%s:%.*s: node map changed, redo the " - "master request now, blocked=%d\n", - dlm->name, res->lockname.len, + mlog(0, "%s: res %.*s, Node map changed, redo the master " + "request now, blocked=%d\n", dlm->name, res->lockname.len, res->lockname.name, blocked); if (++tries > 20) { - mlog(ML_ERROR, "%s:%.*s: spinning on " - "dlm_wait_for_lock_mastery, blocked=%d\n", + mlog(ML_ERROR, "%s: res %.*s, Spinning on " + "dlm_wait_for_lock_mastery, blocked = %d\n", dlm->name, res->lockname.len, res->lockname.name, blocked); dlm_print_one_lock_resource(res); @@ -940,7 +949,8 @@ wait: goto redo_request; } - mlog(0, "lockres mastered by %u\n", res->owner); + mlog(0, "%s: res %.*s, Mastered by %u\n", dlm->name, res->lockname.len, + res->lockname.name, res->owner); /* make sure we never continue without this */ BUG_ON(res->owner == O2NM_MAX_NODES); @@ -952,8 +962,6 @@ wait: wake_waiters: spin_lock(&res->spinlock); - if (res->owner != dlm->node_num && drop_inflight_if_nonlocal) - dlm_lockres_drop_inflight_ref(dlm, res); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; spin_unlock(&res->spinlock); wake_up(&res->wq); @@ -1426,9 +1434,7 @@ way_up_top: } if (res->owner == dlm->node_num) { - mlog(0, "%s:%.*s: setting bit %u in refmap\n", - dlm->name, namelen, name, request->node_idx); - dlm_lockres_set_refmap_bit(request->node_idx, res); + dlm_lockres_set_refmap_bit(dlm, res, request->node_idx); spin_unlock(&res->spinlock); response = DLM_MASTER_RESP_YES; if (mle) @@ -1493,10 +1499,8 @@ way_up_top: * go back and clean the mles on any * other nodes */ dispatch_assert = 1; - dlm_lockres_set_refmap_bit(request->node_idx, res); - mlog(0, "%s:%.*s: setting bit %u in refmap\n", - dlm->name, namelen, name, - request->node_idx); + dlm_lockres_set_refmap_bit(dlm, res, + request->node_idx); } else response = DLM_MASTER_RESP_NO; } else { @@ -1702,7 +1706,7 @@ again: "lockres, set the bit in the refmap\n", namelen, lockname, to); spin_lock(&res->spinlock); - dlm_lockres_set_refmap_bit(to, res); + dlm_lockres_set_refmap_bit(dlm, res, to); spin_unlock(&res->spinlock); } } @@ -2187,8 +2191,6 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) namelen = res->lockname.len; BUG_ON(namelen > O2NM_MAX_NAME_LEN); - mlog(0, "%s:%.*s: sending deref to %d\n", - dlm->name, namelen, lockname, res->owner); memset(&deref, 0, sizeof(deref)); deref.node_idx = dlm->node_num; deref.namelen = namelen; @@ -2197,14 +2199,12 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) ret = o2net_send_message(DLM_DEREF_LOCKRES_MSG, dlm->key, &deref, sizeof(deref), res->owner, &r); if (ret < 0) - mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to " - "node %u\n", ret, DLM_DEREF_LOCKRES_MSG, dlm->key, - res->owner); + mlog(ML_ERROR, "%s: res %.*s, error %d send DEREF to node %u\n", + dlm->name, namelen, lockname, ret, res->owner); else if (r < 0) { /* BAD. other node says I did not have a ref. */ - mlog(ML_ERROR,"while dropping ref on %s:%.*s " - "(master=%u) got %d.\n", dlm->name, namelen, - lockname, res->owner, r); + mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n", + dlm->name, namelen, lockname, res->owner, r); dlm_print_one_lock_resource(res); BUG(); } @@ -2260,7 +2260,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data, else { BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF); if (test_bit(node, res->refmap)) { - dlm_lockres_clear_refmap_bit(node, res); + dlm_lockres_clear_refmap_bit(dlm, res, node); cleared = 1; } } @@ -2320,7 +2320,7 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data) BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF); if (test_bit(node, res->refmap)) { __dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG); - dlm_lockres_clear_refmap_bit(node, res); + dlm_lockres_clear_refmap_bit(dlm, res, node); cleared = 1; } spin_unlock(&res->spinlock); @@ -2802,7 +2802,8 @@ static void dlm_remove_nonlocal_locks(struct dlm_ctxt *dlm, BUG_ON(!list_empty(&lock->bast_list)); BUG_ON(lock->ast_pending); BUG_ON(lock->bast_pending); - dlm_lockres_clear_refmap_bit(lock->ml.node, res); + dlm_lockres_clear_refmap_bit(dlm, res, + lock->ml.node); list_del_init(&lock->list); dlm_lock_put(lock); /* In a normal unlock, we would have added a @@ -2823,7 +2824,7 @@ static void dlm_remove_nonlocal_locks(struct dlm_ctxt *dlm, mlog(0, "%s:%.*s: node %u had a ref to this " "migrating lockres, clearing\n", dlm->name, res->lockname.len, res->lockname.name, bit); - dlm_lockres_clear_refmap_bit(bit, res); + dlm_lockres_clear_refmap_bit(dlm, res, bit); } bit++; } @@ -2916,9 +2917,9 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm, &migrate, sizeof(migrate), nodenum, &status); if (ret < 0) { - mlog(ML_ERROR, "Error %d when sending message %u (key " - "0x%x) to node %u\n", ret, DLM_MIGRATE_REQUEST_MSG, - dlm->key, nodenum); + mlog(ML_ERROR, "%s: res %.*s, Error %d send " + "MIGRATE_REQUEST to node %u\n", dlm->name, + migrate.namelen, migrate.name, ret, nodenum); if (!dlm_is_host_down(ret)) { mlog(ML_ERROR, "unhandled error=%d!\n", ret); BUG(); @@ -2937,7 +2938,7 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm, dlm->name, res->lockname.len, res->lockname.name, nodenum); spin_lock(&res->spinlock); - dlm_lockres_set_refmap_bit(nodenum, res); + dlm_lockres_set_refmap_bit(dlm, res, nodenum); spin_unlock(&res->spinlock); } } @@ -3271,7 +3272,7 @@ int dlm_finish_migration(struct dlm_ctxt *dlm, struct dlm_lock_resource *res, * mastery reference here since old_master will briefly have * a reference after the migration completes */ spin_lock(&res->spinlock); - dlm_lockres_set_refmap_bit(old_master, res); + dlm_lockres_set_refmap_bit(dlm, res, old_master); spin_unlock(&res->spinlock); mlog(0, "now time to do a migrate request to other nodes\n"); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 7efab6d28a21..01ebfd0bdad7 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -362,40 +362,38 @@ static int dlm_is_node_recovered(struct dlm_ctxt *dlm, u8 node) } -int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout) +void dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout) { - if (timeout) { - mlog(ML_NOTICE, "%s: waiting %dms for notification of " - "death of node %u\n", dlm->name, timeout, node); + if (dlm_is_node_dead(dlm, node)) + return; + + printk(KERN_NOTICE "o2dlm: Waiting on the death of node %u in " + "domain %s\n", node, dlm->name); + + if (timeout) wait_event_timeout(dlm->dlm_reco_thread_wq, - dlm_is_node_dead(dlm, node), - msecs_to_jiffies(timeout)); - } else { - mlog(ML_NOTICE, "%s: waiting indefinitely for notification " - "of death of node %u\n", dlm->name, node); + dlm_is_node_dead(dlm, node), + msecs_to_jiffies(timeout)); + else wait_event(dlm->dlm_reco_thread_wq, dlm_is_node_dead(dlm, node)); - } - /* for now, return 0 */ - return 0; } -int dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout) +void dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout) { - if (timeout) { - mlog(0, "%s: waiting %dms for notification of " - "recovery of node %u\n", dlm->name, timeout, node); + if (dlm_is_node_recovered(dlm, node)) + return; + + printk(KERN_NOTICE "o2dlm: Waiting on the recovery of node %u in " + "domain %s\n", node, dlm->name); + + if (timeout) wait_event_timeout(dlm->dlm_reco_thread_wq, - dlm_is_node_recovered(dlm, node), - msecs_to_jiffies(timeout)); - } else { - mlog(0, "%s: waiting indefinitely for notification " - "of recovery of node %u\n", dlm->name, node); + dlm_is_node_recovered(dlm, node), + msecs_to_jiffies(timeout)); + else wait_event(dlm->dlm_reco_thread_wq, dlm_is_node_recovered(dlm, node)); - } - /* for now, return 0 */ - return 0; } /* callers of the top-level api calls (dlmlock/dlmunlock) should @@ -430,6 +428,8 @@ static void dlm_begin_recovery(struct dlm_ctxt *dlm) { spin_lock(&dlm->spinlock); BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE); + printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n", + dlm->name, dlm->reco.dead_node); dlm->reco.state |= DLM_RECO_STATE_ACTIVE; spin_unlock(&dlm->spinlock); } @@ -440,9 +440,18 @@ static void dlm_end_recovery(struct dlm_ctxt *dlm) BUG_ON(!(dlm->reco.state & DLM_RECO_STATE_ACTIVE)); dlm->reco.state &= ~DLM_RECO_STATE_ACTIVE; spin_unlock(&dlm->spinlock); + printk(KERN_NOTICE "o2dlm: End recovery on domain %s\n", dlm->name); wake_up(&dlm->reco.event); } +static void dlm_print_recovery_master(struct dlm_ctxt *dlm) +{ + printk(KERN_NOTICE "o2dlm: Node %u (%s) is the Recovery Master for the " + "dead node %u in domain %s\n", dlm->reco.new_master, + (dlm->node_num == dlm->reco.new_master ? "me" : "he"), + dlm->reco.dead_node, dlm->name); +} + static int dlm_do_recovery(struct dlm_ctxt *dlm) { int status = 0; @@ -505,9 +514,8 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) } mlog(0, "another node will master this recovery session.\n"); } - mlog(0, "dlm=%s (%d), new_master=%u, this node=%u, dead_node=%u\n", - dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.new_master, - dlm->node_num, dlm->reco.dead_node); + + dlm_print_recovery_master(dlm); /* it is safe to start everything back up here * because all of the dead node's lock resources @@ -518,15 +526,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) return 0; master_here: - mlog(ML_NOTICE, "(%d) Node %u is the Recovery Master for the Dead Node " - "%u for Domain %s\n", task_pid_nr(dlm->dlm_reco_thread_task), - dlm->node_num, dlm->reco.dead_node, dlm->name); + dlm_print_recovery_master(dlm); status = dlm_remaster_locks(dlm, dlm->reco.dead_node); if (status < 0) { /* we should never hit this anymore */ - mlog(ML_ERROR, "error %d remastering locks for node %u, " - "retrying.\n", status, dlm->reco.dead_node); + mlog(ML_ERROR, "%s: Error %d remastering locks for node %u, " + "retrying.\n", dlm->name, status, dlm->reco.dead_node); /* yield a bit to allow any final network messages * to get handled on remaining nodes */ msleep(100); @@ -567,7 +573,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) BUG_ON(ndata->state != DLM_RECO_NODE_DATA_INIT); ndata->state = DLM_RECO_NODE_DATA_REQUESTING; - mlog(0, "requesting lock info from node %u\n", + mlog(0, "%s: Requesting lock info from node %u\n", dlm->name, ndata->node_num); if (ndata->node_num == dlm->node_num) { @@ -640,7 +646,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) spin_unlock(&dlm_reco_state_lock); } - mlog(0, "done requesting all lock info\n"); + mlog(0, "%s: Done requesting all lock info\n", dlm->name); /* nodes should be sending reco data now * just need to wait */ @@ -802,10 +808,9 @@ static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from, /* negative status is handled by caller */ if (ret < 0) - mlog(ML_ERROR, "Error %d when sending message %u (key " - "0x%x) to node %u\n", ret, DLM_LOCK_REQUEST_MSG, - dlm->key, request_from); - + mlog(ML_ERROR, "%s: Error %d send LOCK_REQUEST to node %u " + "to recover dead node %u\n", dlm->name, ret, + request_from, dead_node); // return from here, then // sleep until all received or error return ret; @@ -956,9 +961,9 @@ static int dlm_send_all_done_msg(struct dlm_ctxt *dlm, u8 dead_node, u8 send_to) ret = o2net_send_message(DLM_RECO_DATA_DONE_MSG, dlm->key, &done_msg, sizeof(done_msg), send_to, &tmpret); if (ret < 0) { - mlog(ML_ERROR, "Error %d when sending message %u (key " - "0x%x) to node %u\n", ret, DLM_RECO_DATA_DONE_MSG, - dlm->key, send_to); + mlog(ML_ERROR, "%s: Error %d send RECO_DATA_DONE to node %u " + "to recover dead node %u\n", dlm->name, ret, send_to, + dead_node); if (!dlm_is_host_down(ret)) { BUG(); } @@ -1127,9 +1132,11 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, if (ret < 0) { /* XXX: negative status is not handled. * this will end up killing this node. */ - mlog(ML_ERROR, "Error %d when sending message %u (key " - "0x%x) to node %u\n", ret, DLM_MIG_LOCKRES_MSG, - dlm->key, send_to); + mlog(ML_ERROR, "%s: res %.*s, Error %d send MIG_LOCKRES to " + "node %u (%s)\n", dlm->name, mres->lockname_len, + mres->lockname, ret, send_to, + (orig_flags & DLM_MRES_MIGRATION ? + "migration" : "recovery")); } else { /* might get an -ENOMEM back here */ ret = status; @@ -1767,7 +1774,7 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, dlm->name, mres->lockname_len, mres->lockname, from); spin_lock(&res->spinlock); - dlm_lockres_set_refmap_bit(from, res); + dlm_lockres_set_refmap_bit(dlm, res, from); spin_unlock(&res->spinlock); added++; break; @@ -1965,7 +1972,7 @@ skip_lvb: mlog(0, "%s:%.*s: added lock for node %u, " "setting refmap bit\n", dlm->name, res->lockname.len, res->lockname.name, ml->node); - dlm_lockres_set_refmap_bit(ml->node, res); + dlm_lockres_set_refmap_bit(dlm, res, ml->node); added++; } spin_unlock(&res->spinlock); @@ -2084,6 +2091,9 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm, list_for_each_entry_safe(res, next, &dlm->reco.resources, recovering) { if (res->owner == dead_node) { + mlog(0, "%s: res %.*s, Changing owner from %u to %u\n", + dlm->name, res->lockname.len, res->lockname.name, + res->owner, new_master); list_del_init(&res->recovering); spin_lock(&res->spinlock); /* new_master has our reference from @@ -2105,40 +2115,30 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm, for (i = 0; i < DLM_HASH_BUCKETS; i++) { bucket = dlm_lockres_hash(dlm, i); hlist_for_each_entry(res, hash_iter, bucket, hash_node) { - if (res->state & DLM_LOCK_RES_RECOVERING) { - if (res->owner == dead_node) { - mlog(0, "(this=%u) res %.*s owner=%u " - "was not on recovering list, but " - "clearing state anyway\n", - dlm->node_num, res->lockname.len, - res->lockname.name, new_master); - } else if (res->owner == dlm->node_num) { - mlog(0, "(this=%u) res %.*s owner=%u " - "was not on recovering list, " - "owner is THIS node, clearing\n", - dlm->node_num, res->lockname.len, - res->lockname.name, new_master); - } else - continue; + if (!(res->state & DLM_LOCK_RES_RECOVERING)) + continue; - if (!list_empty(&res->recovering)) { - mlog(0, "%s:%.*s: lockres was " - "marked RECOVERING, owner=%u\n", - dlm->name, res->lockname.len, - res->lockname.name, res->owner); - list_del_init(&res->recovering); - dlm_lockres_put(res); - } - spin_lock(&res->spinlock); - /* new_master has our reference from - * the lock state sent during recovery */ - dlm_change_lockres_owner(dlm, res, new_master); - res->state &= ~DLM_LOCK_RES_RECOVERING; - if (__dlm_lockres_has_locks(res)) - __dlm_dirty_lockres(dlm, res); - spin_unlock(&res->spinlock); - wake_up(&res->wq); + if (res->owner != dead_node && + res->owner != dlm->node_num) + continue; + + if (!list_empty(&res->recovering)) { + list_del_init(&res->recovering); + dlm_lockres_put(res); } + + /* new_master has our reference from + * the lock state sent during recovery */ + mlog(0, "%s: res %.*s, Changing owner from %u to %u\n", + dlm->name, res->lockname.len, res->lockname.name, + res->owner, new_master); + spin_lock(&res->spinlock); + dlm_change_lockres_owner(dlm, res, new_master); + res->state &= ~DLM_LOCK_RES_RECOVERING; + if (__dlm_lockres_has_locks(res)) + __dlm_dirty_lockres(dlm, res); + spin_unlock(&res->spinlock); + wake_up(&res->wq); } } } @@ -2252,12 +2252,12 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm, res->lockname.len, res->lockname.name, freed, dead_node); __dlm_print_one_lock_resource(res); } - dlm_lockres_clear_refmap_bit(dead_node, res); + dlm_lockres_clear_refmap_bit(dlm, res, dead_node); } else if (test_bit(dead_node, res->refmap)) { mlog(0, "%s:%.*s: dead node %u had a ref, but had " "no locks and had not purged before dying\n", dlm->name, res->lockname.len, res->lockname.name, dead_node); - dlm_lockres_clear_refmap_bit(dead_node, res); + dlm_lockres_clear_refmap_bit(dlm, res, dead_node); } /* do not kick thread yet */ @@ -2324,9 +2324,9 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) dlm_revalidate_lvb(dlm, res, dead_node); if (res->owner == dead_node) { if (res->state & DLM_LOCK_RES_DROPPING_REF) { - mlog(ML_NOTICE, "Ignore %.*s for " + mlog(ML_NOTICE, "%s: res %.*s, Skip " "recovery as it is being freed\n", - res->lockname.len, + dlm->name, res->lockname.len, res->lockname.name); } else dlm_move_lockres_to_recovery_list(dlm, diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 1d6d1d22c471..e73c833fc2a1 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -94,24 +94,26 @@ int __dlm_lockres_unused(struct dlm_lock_resource *res) { int bit; + assert_spin_locked(&res->spinlock); + if (__dlm_lockres_has_locks(res)) return 0; + /* Locks are in the process of being created */ + if (res->inflight_locks) + return 0; + if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY) return 0; if (res->state & DLM_LOCK_RES_RECOVERING) return 0; + /* Another node has this resource with this node as the master */ bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0); if (bit < O2NM_MAX_NODES) return 0; - /* - * since the bit for dlm->node_num is not set, inflight_locks better - * be zero - */ - BUG_ON(res->inflight_locks != 0); return 1; } @@ -185,8 +187,6 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm, /* clear our bit from the master's refmap, ignore errors */ ret = dlm_drop_lockres_ref(dlm, res); if (ret < 0) { - mlog(ML_ERROR, "%s: deref %.*s failed %d\n", dlm->name, - res->lockname.len, res->lockname.name, ret); if (!dlm_is_host_down(ret)) BUG(); } @@ -209,7 +209,7 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm, BUG(); } - __dlm_unhash_lockres(res); + __dlm_unhash_lockres(dlm, res); /* lockres is not in the hash now. drop the flag and wake up * any processes waiting in dlm_get_lock_resource. */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index e1ed5e502ff2..81a4cd22f80b 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1692,7 +1692,7 @@ int ocfs2_open_lock(struct inode *inode) mlog(0, "inode %llu take PRMODE open lock\n", (unsigned long long)OCFS2_I(inode)->ip_blkno); - if (ocfs2_mount_local(osb)) + if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb)) goto out; lockres = &OCFS2_I(inode)->ip_open_lockres; @@ -1718,6 +1718,12 @@ int ocfs2_try_open_lock(struct inode *inode, int write) (unsigned long long)OCFS2_I(inode)->ip_blkno, write ? "EXMODE" : "PRMODE"); + if (ocfs2_is_hard_readonly(osb)) { + if (write) + status = -EROFS; + goto out; + } + if (ocfs2_mount_local(osb)) goto out; @@ -2298,7 +2304,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, if (ocfs2_is_hard_readonly(osb)) { if (ex) status = -EROFS; - goto bail; + goto getbh; } if (ocfs2_mount_local(osb)) @@ -2356,7 +2362,7 @@ local: mlog_errno(status); goto bail; } - +getbh: if (ret_bh) { status = ocfs2_assign_bh(inode, ret_bh, local_bh); if (status < 0) { @@ -2628,8 +2634,11 @@ int ocfs2_dentry_lock(struct dentry *dentry, int ex) BUG_ON(!dl); - if (ocfs2_is_hard_readonly(osb)) - return -EROFS; + if (ocfs2_is_hard_readonly(osb)) { + if (ex) + return -EROFS; + return 0; + } if (ocfs2_mount_local(osb)) return 0; @@ -2647,7 +2656,7 @@ void ocfs2_dentry_unlock(struct dentry *dentry, int ex) struct ocfs2_dentry_lock *dl = dentry->d_fsdata; struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (!ocfs2_mount_local(osb)) + if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) ocfs2_cluster_unlock(osb, &dl->dl_lockres, level); } diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 23457b491e8c..2f5b92ef0e53 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -832,6 +832,102 @@ out: return ret; } +int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin) +{ + struct inode *inode = file->f_mapping->host; + int ret; + unsigned int is_last = 0, is_data = 0; + u16 cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits; + u32 cpos, cend, clen, hole_size; + u64 extoff, extlen; + struct buffer_head *di_bh = NULL; + struct ocfs2_extent_rec rec; + + BUG_ON(origin != SEEK_DATA && origin != SEEK_HOLE); + + ret = ocfs2_inode_lock(inode, &di_bh, 0); + if (ret) { + mlog_errno(ret); + goto out; + } + + down_read(&OCFS2_I(inode)->ip_alloc_sem); + + if (*offset >= inode->i_size) { + ret = -ENXIO; + goto out_unlock; + } + + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + if (origin == SEEK_HOLE) + *offset = inode->i_size; + goto out_unlock; + } + + clen = 0; + cpos = *offset >> cs_bits; + cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size); + + while (cpos < cend && !is_last) { + ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size, + &rec, &is_last); + if (ret) { + mlog_errno(ret); + goto out_unlock; + } + + extoff = cpos; + extoff <<= cs_bits; + + if (rec.e_blkno == 0ULL) { + clen = hole_size; + is_data = 0; + } else { + clen = le16_to_cpu(rec.e_leaf_clusters) - + (cpos - le32_to_cpu(rec.e_cpos)); + is_data = (rec.e_flags & OCFS2_EXT_UNWRITTEN) ? 0 : 1; + } + + if ((!is_data && origin == SEEK_HOLE) || + (is_data && origin == SEEK_DATA)) { + if (extoff > *offset) + *offset = extoff; + goto out_unlock; + } + + if (!is_last) + cpos += clen; + } + + if (origin == SEEK_HOLE) { + extoff = cpos; + extoff <<= cs_bits; + extlen = clen; + extlen <<= cs_bits; + + if ((extoff + extlen) > inode->i_size) + extlen = inode->i_size - extoff; + extoff += extlen; + if (extoff > *offset) + *offset = extoff; + goto out_unlock; + } + + ret = -ENXIO; + +out_unlock: + + brelse(di_bh); + + up_read(&OCFS2_I(inode)->ip_alloc_sem); + + ocfs2_inode_unlock(inode, 0); +out: + if (ret && ret != -ENXIO) + ret = -ENXIO; + return ret; +} + int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr, struct buffer_head *bhs[], int flags, int (*validate)(struct super_block *sb, diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h index e79d41c2c909..67ea57d2fd59 100644 --- a/fs/ocfs2/extent_map.h +++ b/fs/ocfs2/extent_map.h @@ -53,6 +53,8 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno, int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 map_start, u64 map_len); +int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin); + int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster, u32 *p_cluster, u32 *num_clusters, struct ocfs2_extent_list *el, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index de4ea1af041b..6e396683c3d4 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1950,6 +1950,9 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, if (ret < 0) mlog_errno(ret); + if (file->f_flags & O_SYNC) + handle->h_sync = 1; + ocfs2_commit_trans(osb, handle); out_inode_unlock: @@ -2052,6 +2055,23 @@ out: return ret; } +static void ocfs2_aiodio_wait(struct inode *inode) +{ + wait_queue_head_t *wq = ocfs2_ioend_wq(inode); + + wait_event(*wq, (atomic_read(&OCFS2_I(inode)->ip_unaligned_aio) == 0)); +} + +static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) +{ + int blockmask = inode->i_sb->s_blocksize - 1; + loff_t final_size = pos + count; + + if ((pos & blockmask) || (final_size & blockmask)) + return 1; + return 0; +} + static int ocfs2_prepare_inode_for_refcount(struct inode *inode, struct file *file, loff_t pos, size_t count, @@ -2230,6 +2250,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); + int unaligned_dio = 0; trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -2297,6 +2318,10 @@ relock: goto out; } + if (direct_io && !is_sync_kiocb(iocb)) + unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_left, + *ppos); + /* * We can't complete the direct I/O as requested, fall back to * buffered I/O. @@ -2311,6 +2336,18 @@ relock: goto relock; } + if (unaligned_dio) { + /* + * Wait on previous unaligned aio to complete before + * proceeding. + */ + ocfs2_aiodio_wait(inode); + + /* Mark the iocb as needing a decrement in ocfs2_dio_end_io */ + atomic_inc(&OCFS2_I(inode)->ip_unaligned_aio); + ocfs2_iocb_set_unaligned_aio(iocb); + } + /* * To later detect whether a journal commit for sync writes is * necessary, we sample i_size, and cluster count here. @@ -2382,8 +2419,12 @@ out_dio: if ((ret == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) { rw_level = -1; have_alloc_sem = 0; + unaligned_dio = 0; } + if (unaligned_dio) + atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio); + out: if (rw_level != -1) ocfs2_rw_unlock(inode, rw_level); @@ -2591,6 +2632,57 @@ bail: return ret; } +/* Refer generic_file_llseek_unlocked() */ +static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin) +{ + struct inode *inode = file->f_mapping->host; + int ret = 0; + + mutex_lock(&inode->i_mutex); + + switch (origin) { + case SEEK_SET: + break; + case SEEK_END: + offset += inode->i_size; + break; + case SEEK_CUR: + if (offset == 0) { + offset = file->f_pos; + goto out; + } + offset += file->f_pos; + break; + case SEEK_DATA: + case SEEK_HOLE: + ret = ocfs2_seek_data_hole_offset(file, &offset, origin); + if (ret) + goto out; + break; + default: + ret = -EINVAL; + goto out; + } + + if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) + ret = -EINVAL; + if (!ret && offset > inode->i_sb->s_maxbytes) + ret = -EINVAL; + if (ret) + goto out; + + if (offset != file->f_pos) { + file->f_pos = offset; + file->f_version = 0; + } + +out: + mutex_unlock(&inode->i_mutex); + if (ret) + return ret; + return offset; +} + const struct inode_operations ocfs2_file_iops = { .setattr = ocfs2_setattr, .getattr = ocfs2_getattr, @@ -2615,7 +2707,7 @@ const struct inode_operations ocfs2_special_file_iops = { * ocfs2_fops_no_plocks and ocfs2_dops_no_plocks! */ const struct file_operations ocfs2_fops = { - .llseek = generic_file_llseek, + .llseek = ocfs2_file_llseek, .read = do_sync_read, .write = do_sync_write, .mmap = ocfs2_mmap, @@ -2663,7 +2755,7 @@ const struct file_operations ocfs2_dops = { * the cluster. */ const struct file_operations ocfs2_fops_no_plocks = { - .llseek = generic_file_llseek, + .llseek = ocfs2_file_llseek, .read = do_sync_read, .write = do_sync_write, .mmap = ocfs2_mmap, diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index a22d2c098890..17454a904d7b 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -951,7 +951,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode, trace_ocfs2_cleanup_delete_inode( (unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data); if (sync_data) - write_inode_now(inode, 1); + filemap_write_and_wait(inode->i_mapping); truncate_inode_pages(&inode->i_data, 0); } diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 1c508b149b3a..88924a3133fa 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -43,6 +43,9 @@ struct ocfs2_inode_info /* protects extended attribute changes on this inode */ struct rw_semaphore ip_xattr_sem; + /* Number of outstanding AIO's which are not page aligned */ + atomic_t ip_unaligned_aio; + /* These fields are protected by ip_lock */ spinlock_t ip_lock; u32 ip_open_count; diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index bc91072b7219..726ff265b296 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -122,7 +122,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) & (OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) { if (!capable(CAP_LINUX_IMMUTABLE)) - goto bail_unlock; + goto bail_commit; } ocfs2_inode->ip_attr = flags; @@ -132,6 +132,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, if (status < 0) mlog_errno(status); +bail_commit: ocfs2_commit_trans(osb, handle); bail_unlock: ocfs2_inode_unlock(inode, 1); @@ -381,7 +382,7 @@ int ocfs2_info_handle_freeinode(struct inode *inode, if (!oifi) { status = -ENOMEM; mlog_errno(status); - goto bail; + goto out_err; } if (o2info_from_user(*oifi, req)) @@ -431,7 +432,7 @@ bail: o2info_set_request_error(&oifi->ifi_req, req); kfree(oifi); - +out_err: return status; } @@ -666,7 +667,7 @@ int ocfs2_info_handle_freefrag(struct inode *inode, if (!oiff) { status = -ENOMEM; mlog_errno(status); - goto bail; + goto out_err; } if (o2info_from_user(*oiff, req)) @@ -716,7 +717,7 @@ bail: o2info_set_request_error(&oiff->iff_req, req); kfree(oiff); - +out_err: return status; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 295d56454e8b..0a42ae96dca7 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1544,9 +1544,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb, /* we need to run complete recovery for offline orphan slots */ ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); - mlog(ML_NOTICE, "Recovering node %d from slot %d on device (%u,%u)\n", - node_num, slot_num, - MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); + printk(KERN_NOTICE "ocfs2: Begin replay journal (node %d, slot %d) on "\ + "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev), + MINOR(osb->sb->s_dev)); OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters); @@ -1601,6 +1601,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb, jbd2_journal_destroy(journal); + printk(KERN_NOTICE "ocfs2: End replay journal (node %d, slot %d) on "\ + "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev), + MINOR(osb->sb->s_dev)); done: /* drop the lock on this nodes journal */ if (got_lock) @@ -1808,6 +1811,20 @@ static inline unsigned long ocfs2_orphan_scan_timeout(void) * every slot, queuing a recovery of the slot on the ocfs2_wq thread. This * is done to catch any orphans that are left over in orphan directories. * + * It scans all slots, even ones that are in use. It does so to handle the + * case described below: + * + * Node 1 has an inode it was using. The dentry went away due to memory + * pressure. Node 1 closes the inode, but it's on the free list. The node + * has the open lock. + * Node 2 unlinks the inode. It grabs the dentry lock to notify others, + * but node 1 has no dentry and doesn't get the message. It trylocks the + * open lock, sees that another node has a PR, and does nothing. + * Later node 2 runs its orphan dir. It igets the inode, trylocks the + * open lock, sees the PR still, and does nothing. + * Basically, we have to trigger an orphan iput on node 1. The only way + * for this to happen is if node 1 runs node 2's orphan dir. + * * ocfs2_queue_orphan_scan gets called every ORPHAN_SCAN_SCHEDULE_TIMEOUT * seconds. It gets an EX lock on os_lockres and checks sequence number * stored in LVB. If the sequence number has changed, it means some other diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 68cf2f6d3c6a..a3385b63ff5e 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -441,10 +441,11 @@ static inline int ocfs2_mknod_credits(struct super_block *sb, int is_dir, #define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2) /* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota - * update on dir + index leaf + dx root update for free list */ + * update on dir + index leaf + dx root update for free list + + * previous dirblock update in the free list */ static inline int ocfs2_link_credits(struct super_block *sb) { - return 2*OCFS2_INODE_UPDATE_CREDITS + 3 + + return 2*OCFS2_INODE_UPDATE_CREDITS + 4 + ocfs2_quota_trans_credits(sb); } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 3e9393ca39eb..9cd41083e991 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -61,7 +61,7 @@ static int ocfs2_fault(struct vm_area_struct *area, struct vm_fault *vmf) static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, struct page *page) { - int ret; + int ret = VM_FAULT_NOPAGE; struct inode *inode = file->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; loff_t pos = page_offset(page); @@ -71,32 +71,25 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, void *fsdata; loff_t size = i_size_read(inode); - /* - * Another node might have truncated while we were waiting on - * cluster locks. - * We don't check size == 0 before the shift. This is borrowed - * from do_generic_file_read. - */ last_index = (size - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(!size || page->index > last_index)) { - ret = -EINVAL; - goto out; - } /* - * The i_size check above doesn't catch the case where nodes - * truncated and then re-extended the file. We'll re-check the - * page mapping after taking the page lock inside of - * ocfs2_write_begin_nolock(). + * There are cases that lead to the page no longer bebongs to the + * mapping. + * 1) pagecache truncates locally due to memory pressure. + * 2) pagecache truncates when another is taking EX lock against + * inode lock. see ocfs2_data_convert_worker. + * + * The i_size check doesn't catch the case where nodes truncated and + * then re-extended the file. We'll re-check the page mapping after + * taking the page lock inside of ocfs2_write_begin_nolock(). + * + * Let VM retry with these cases. */ - if (!PageUptodate(page) || page->mapping != inode->i_mapping) { - /* - * the page has been umapped in ocfs2_data_downconvert_worker. - * So return 0 here and let VFS retry. - */ - ret = 0; + if ((page->mapping != inode->i_mapping) || + (!PageUptodate(page)) || + (page_offset(page) >= size)) goto out; - } /* * Call ocfs2_write_begin() and ocfs2_write_end() to take @@ -116,17 +109,21 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, if (ret) { if (ret != -ENOSPC) mlog_errno(ret); + if (ret == -ENOMEM) + ret = VM_FAULT_OOM; + else + ret = VM_FAULT_SIGBUS; goto out; } - ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page, - fsdata); - if (ret < 0) { - mlog_errno(ret); + if (!locked_page) { + ret = VM_FAULT_NOPAGE; goto out; } + ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page, + fsdata); BUG_ON(ret != len); - ret = 0; + ret = VM_FAULT_LOCKED; out: return ret; } @@ -168,8 +165,6 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) out: ocfs2_unblock_signals(&oldset); - if (ret) - ret = VM_FAULT_SIGBUS; return ret; } diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index d53cb706f14c..184c76b8c293 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -745,7 +745,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, */ ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop, new_phys_cpos); - if (!new_phys_cpos) { + if (!*new_phys_cpos) { ret = -ENOSPC; goto out_commit; } diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 409285854f64..d355e6e36b36 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -836,18 +836,65 @@ static inline unsigned int ocfs2_clusters_to_megabytes(struct super_block *sb, static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap) { - __test_and_set_bit_le(bit, bitmap); + __set_bit_le(bit, bitmap); } #define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr)) static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap) { - __test_and_clear_bit_le(bit, bitmap); + __clear_bit_le(bit, bitmap); } #define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr)) #define ocfs2_test_bit test_bit_le #define ocfs2_find_next_zero_bit find_next_zero_bit_le #define ocfs2_find_next_bit find_next_bit_le + +static inline void *correct_addr_and_bit_unaligned(int *bit, void *addr) +{ +#if BITS_PER_LONG == 64 + *bit += ((unsigned long) addr & 7UL) << 3; + addr = (void *) ((unsigned long) addr & ~7UL); +#elif BITS_PER_LONG == 32 + *bit += ((unsigned long) addr & 3UL) << 3; + addr = (void *) ((unsigned long) addr & ~3UL); +#else +#error "how many bits you are?!" +#endif + return addr; +} + +static inline void ocfs2_set_bit_unaligned(int bit, void *bitmap) +{ + bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); + ocfs2_set_bit(bit, bitmap); +} + +static inline void ocfs2_clear_bit_unaligned(int bit, void *bitmap) +{ + bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); + ocfs2_clear_bit(bit, bitmap); +} + +static inline int ocfs2_test_bit_unaligned(int bit, void *bitmap) +{ + bitmap = correct_addr_and_bit_unaligned(&bit, bitmap); + return ocfs2_test_bit(bit, bitmap); +} + +static inline int ocfs2_find_next_zero_bit_unaligned(void *bitmap, int max, + int start) +{ + int fix = 0, ret, tmpmax; + bitmap = correct_addr_and_bit_unaligned(&fix, bitmap); + tmpmax = max + fix; + start += fix; + + ret = ocfs2_find_next_zero_bit(bitmap, tmpmax, start) - fix; + if (ret > max) + return max; + return ret; +} + #endif /* OCFS2_H */ diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index dc8007fc9247..f100bf70a906 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -404,7 +404,9 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery( int status = 0; struct ocfs2_quota_recovery *rec; - mlog(ML_NOTICE, "Beginning quota recovery in slot %u\n", slot_num); + printk(KERN_NOTICE "ocfs2: Beginning quota recovery on device (%s) for " + "slot %u\n", osb->dev_str, slot_num); + rec = ocfs2_alloc_quota_recovery(); if (!rec) return ERR_PTR(-ENOMEM); @@ -549,8 +551,8 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode, goto out_commit; } lock_buffer(qbh); - WARN_ON(!ocfs2_test_bit(bit, dchunk->dqc_bitmap)); - ocfs2_clear_bit(bit, dchunk->dqc_bitmap); + WARN_ON(!ocfs2_test_bit_unaligned(bit, dchunk->dqc_bitmap)); + ocfs2_clear_bit_unaligned(bit, dchunk->dqc_bitmap); le32_add_cpu(&dchunk->dqc_free, 1); unlock_buffer(qbh); ocfs2_journal_dirty(handle, qbh); @@ -596,7 +598,9 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, struct inode *lqinode; unsigned int flags; - mlog(ML_NOTICE, "Finishing quota recovery in slot %u\n", slot_num); + printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for " + "slot %u\n", osb->dev_str, slot_num); + mutex_lock(&sb_dqopt(sb)->dqonoff_mutex); for (type = 0; type < MAXQUOTAS; type++) { if (list_empty(&(rec->r_list[type]))) @@ -612,8 +616,9 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, /* Someone else is holding the lock? Then he must be * doing the recovery. Just skip the file... */ if (status == -EAGAIN) { - mlog(ML_NOTICE, "skipping quota recovery for slot %d " - "because quota file is locked.\n", slot_num); + printk(KERN_NOTICE "ocfs2: Skipping quota recovery on " + "device (%s) for slot %d because quota file is " + "locked.\n", osb->dev_str, slot_num); status = 0; goto out_put; } else if (status < 0) { @@ -944,7 +949,7 @@ static struct ocfs2_quota_chunk *ocfs2_find_free_entry(struct super_block *sb, * ol_quota_entries_per_block(sb); } - found = ocfs2_find_next_zero_bit(dchunk->dqc_bitmap, len, 0); + found = ocfs2_find_next_zero_bit_unaligned(dchunk->dqc_bitmap, len, 0); /* We failed? */ if (found == len) { mlog(ML_ERROR, "Did not find empty entry in chunk %d with %u" @@ -1208,7 +1213,7 @@ static void olq_alloc_dquot(struct buffer_head *bh, void *private) struct ocfs2_local_disk_chunk *dchunk; dchunk = (struct ocfs2_local_disk_chunk *)bh->b_data; - ocfs2_set_bit(*offset, dchunk->dqc_bitmap); + ocfs2_set_bit_unaligned(*offset, dchunk->dqc_bitmap); le32_add_cpu(&dchunk->dqc_free, -1); } @@ -1289,7 +1294,7 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot) (od->dq_chunk->qc_headerbh->b_data); /* Mark structure as freed */ lock_buffer(od->dq_chunk->qc_headerbh); - ocfs2_clear_bit(offset, dchunk->dqc_bitmap); + ocfs2_clear_bit_unaligned(offset, dchunk->dqc_bitmap); le32_add_cpu(&dchunk->dqc_free, 1); unlock_buffer(od->dq_chunk->qc_headerbh); ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh); diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index 26fc0014d509..1424c151cccc 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -493,8 +493,8 @@ int ocfs2_find_slot(struct ocfs2_super *osb) goto bail; } } else - mlog(ML_NOTICE, "slot %d is already allocated to this node!\n", - slot); + printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already " + "allocated to this node!\n", slot, osb->dev_str); ocfs2_set_slot(si, slot, osb->node_num); osb->slot_num = slot; diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index 19965b00c43c..94368017edb3 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -28,6 +28,7 @@ #include "cluster/masklog.h" #include "cluster/nodemanager.h" #include "cluster/heartbeat.h" +#include "cluster/tcp.h" #include "stackglue.h" @@ -256,6 +257,61 @@ static void o2cb_dump_lksb(struct ocfs2_dlm_lksb *lksb) } /* + * Check if this node is heartbeating and is connected to all other + * heartbeating nodes. + */ +static int o2cb_cluster_check(void) +{ + u8 node_num; + int i; + unsigned long hbmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; + unsigned long netmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; + + node_num = o2nm_this_node(); + if (node_num == O2NM_MAX_NODES) { + printk(KERN_ERR "o2cb: This node has not been configured.\n"); + return -EINVAL; + } + + /* + * o2dlm expects o2net sockets to be created. If not, then + * dlm_join_domain() fails with a stack of errors which are both cryptic + * and incomplete. The idea here is to detect upfront whether we have + * managed to connect to all nodes or not. If not, then list the nodes + * to allow the user to check the configuration (incorrect IP, firewall, + * etc.) Yes, this is racy. But its not the end of the world. + */ +#define O2CB_MAP_STABILIZE_COUNT 60 + for (i = 0; i < O2CB_MAP_STABILIZE_COUNT; ++i) { + o2hb_fill_node_map(hbmap, sizeof(hbmap)); + if (!test_bit(node_num, hbmap)) { + printk(KERN_ERR "o2cb: %s heartbeat has not been " + "started.\n", (o2hb_global_heartbeat_active() ? + "Global" : "Local")); + return -EINVAL; + } + o2net_fill_node_map(netmap, sizeof(netmap)); + /* Force set the current node to allow easy compare */ + set_bit(node_num, netmap); + if (!memcmp(hbmap, netmap, sizeof(hbmap))) + return 0; + if (i < O2CB_MAP_STABILIZE_COUNT) + msleep(1000); + } + + printk(KERN_ERR "o2cb: This node could not connect to nodes:"); + i = -1; + while ((i = find_next_bit(hbmap, O2NM_MAX_NODES, + i + 1)) < O2NM_MAX_NODES) { + if (!test_bit(i, netmap)) + printk(" %u", i); + } + printk(".\n"); + + return -ENOTCONN; +} + +/* * Called from the dlm when it's about to evict a node. This is how the * classic stack signals node death. */ @@ -263,8 +319,8 @@ static void o2dlm_eviction_cb(int node_num, void *data) { struct ocfs2_cluster_connection *conn = data; - mlog(ML_NOTICE, "o2dlm has evicted node %d from group %.*s\n", - node_num, conn->cc_namelen, conn->cc_name); + printk(KERN_NOTICE "o2cb: o2dlm has evicted node %d from domain %.*s\n", + node_num, conn->cc_namelen, conn->cc_name); conn->cc_recovery_handler(node_num, conn->cc_recovery_data); } @@ -280,12 +336,11 @@ static int o2cb_cluster_connect(struct ocfs2_cluster_connection *conn) BUG_ON(conn == NULL); BUG_ON(conn->cc_proto == NULL); - /* for now we only have one cluster/node, make sure we see it - * in the heartbeat universe */ - if (!o2hb_check_local_node_heartbeating()) { - if (o2hb_global_heartbeat_active()) - mlog(ML_ERROR, "Global heartbeat not started\n"); - rc = -EINVAL; + /* Ensure cluster stack is up and all nodes are connected */ + rc = o2cb_cluster_check(); + if (rc) { + printk(KERN_ERR "o2cb: Cluster check failed. Fix errors " + "before retrying.\n"); goto out; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 56f61027236b..4994f8b0e604 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -54,6 +54,7 @@ #include "ocfs1_fs_compat.h" #include "alloc.h" +#include "aops.h" #include "blockcheck.h" #include "dlmglue.h" #include "export.h" @@ -1107,9 +1108,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) ocfs2_set_ro_flag(osb, 1); - printk(KERN_NOTICE "Readonly device detected. No cluster " - "services will be utilized for this mount. Recovery " - "will be skipped.\n"); + printk(KERN_NOTICE "ocfs2: Readonly device (%s) detected. " + "Cluster services will not be used for this mount. " + "Recovery will be skipped.\n", osb->dev_str); } if (!ocfs2_is_hard_readonly(osb)) { @@ -1616,12 +1617,17 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt) return 0; } +wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ]; + static int __init ocfs2_init(void) { - int status; + int status, i; ocfs2_print_version(); + for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++) + init_waitqueue_head(&ocfs2__ioend_wq[i]); + status = init_ocfs2_uptodate_cache(); if (status < 0) { mlog_errno(status); @@ -1760,7 +1766,7 @@ static void ocfs2_inode_init_once(void *data) ocfs2_extent_map_init(&oi->vfs_inode); INIT_LIST_HEAD(&oi->ip_io_markers); oi->ip_dir_start_lookup = 0; - + atomic_set(&oi->ip_unaligned_aio, 0); init_rwsem(&oi->ip_alloc_sem); init_rwsem(&oi->ip_xattr_sem); mutex_init(&oi->ip_io_mutex); @@ -1974,7 +1980,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) * If we failed before we got a uuid_str yet, we can't stop * heartbeat. Otherwise, do it. */ - if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str) + if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str && + !ocfs2_is_hard_readonly(osb)) hangup_needed = 1; if (osb->cconn) @@ -2353,7 +2360,7 @@ static int ocfs2_initialize_super(struct super_block *sb, mlog_errno(status); goto bail; } - cleancache_init_shared_fs((char *)&uuid_net_key, sb); + cleancache_init_shared_fs((char *)&di->id2.i_super.s_uuid, sb); bail: return status; @@ -2462,8 +2469,8 @@ static int ocfs2_check_volume(struct ocfs2_super *osb) goto finally; } } else { - mlog(ML_NOTICE, "File system was not unmounted cleanly, " - "recovering volume.\n"); + printk(KERN_NOTICE "ocfs2: File system on device (%s) was not " + "unmounted cleanly, recovering it.\n", osb->dev_str); } local = ocfs2_mount_local(osb); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 194fb22ef79d..aa9e8777b09a 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -2376,16 +2376,18 @@ static int ocfs2_remove_value_outside(struct inode*inode, } ret = ocfs2_xattr_value_truncate(inode, vb, 0, &ctxt); - if (ret < 0) { - mlog_errno(ret); - break; - } ocfs2_commit_trans(osb, ctxt.handle); if (ctxt.meta_ac) { ocfs2_free_alloc_context(ctxt.meta_ac); ctxt.meta_ac = NULL; } + + if (ret < 0) { + mlog_errno(ret); + break; + } + } if (ctxt.meta_ac) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cbeb5867cff7..a82ad4dd306a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2536,6 +2536,8 @@ extern void net_disable_timestamp(void); extern void *dev_seq_start(struct seq_file *seq, loff_t *pos); extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos); extern void dev_seq_stop(struct seq_file *seq, void *v); +extern int dev_seq_open_ops(struct inode *inode, struct file *file, + const struct seq_operations *ops); #endif extern int netdev_class_create_file(struct class_attribute *class_attr); diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index c5336705921f..7281d5acf2f9 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -30,7 +30,7 @@ */ struct tc_stats { - __u64 bytes; /* NUmber of enqueues bytes */ + __u64 bytes; /* Number of enqueued bytes */ __u32 packets; /* Number of enqueued packets */ __u32 drops; /* Packets dropped because of lack of resources */ __u32 overlimits; /* Number of throttle events when this @@ -297,7 +297,7 @@ struct tc_htb_glob { __u32 debug; /* debug flags */ /* stats */ - __u32 direct_pkts; /* count of non shapped packets */ + __u32 direct_pkts; /* count of non shaped packets */ }; enum { TCA_HTB_UNSPEC, @@ -503,7 +503,7 @@ enum { }; #define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1) -/* State transition probablities for 4 state model */ +/* State transition probabilities for 4 state model */ struct tc_netem_gimodel { __u32 p13; __u32 p31; diff --git a/include/linux/sigma.h b/include/linux/sigma.h index e2accb3164d8..d0de882c0d96 100644 --- a/include/linux/sigma.h +++ b/include/linux/sigma.h @@ -24,7 +24,7 @@ struct sigma_firmware { struct sigma_firmware_header { unsigned char magic[7]; u8 version; - u32 crc; + __le32 crc; }; enum { @@ -40,19 +40,14 @@ enum { struct sigma_action { u8 instr; u8 len_hi; - u16 len; - u16 addr; + __le16 len; + __be16 addr; unsigned char payload[]; }; static inline u32 sigma_action_len(struct sigma_action *sa) { - return (sa->len_hi << 16) | sa->len; -} - -static inline size_t sigma_action_size(struct sigma_action *sa, u32 payload_len) -{ - return sizeof(*sa) + payload_len + (payload_len % 2); + return (sa->len_hi << 16) | le16_to_cpu(sa->len); } extern int process_sigma_firmware(struct i2c_client *client, const char *name); diff --git a/include/net/dst.h b/include/net/dst.h index 4fb6c4381791..6faec1a60216 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -205,12 +205,7 @@ dst_feature(const struct dst_entry *dst, u32 feature) static inline u32 dst_mtu(const struct dst_entry *dst) { - u32 mtu = dst_metric_raw(dst, RTAX_MTU); - - if (!mtu) - mtu = dst->ops->default_mtu(dst); - - return mtu; + return dst->ops->mtu(dst); } /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 9adb99845a56..e1c2ee0eef47 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -17,7 +17,7 @@ struct dst_ops { int (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); - unsigned int (*default_mtu)(const struct dst_entry *); + unsigned int (*mtu)(const struct dst_entry *); u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index b897d6e6d0a5..f941964a9931 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -31,6 +31,7 @@ /** struct ip_options - IP Options * * @faddr - Saved first hop address + * @nexthop - Saved nexthop address in LSRR and SSRR * @is_data - Options in __data, rather than skb * @is_strictroute - Strict source route * @srr_is_hit - Packet destination addr was our one @@ -41,6 +42,7 @@ */ struct ip_options { __be32 faddr; + __be32 nexthop; unsigned char optlen; unsigned char srr; unsigned char rr; diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 78c83e62218f..e9ff3fc5e688 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -35,6 +35,7 @@ struct inet_peer { u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ + int redirect_genid; unsigned long rate_last; unsigned long pmtu_expires; u32 pmtu_orig; diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 4283508b3e18..a88fb6939387 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -67,18 +67,18 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; -extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); -extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); +extern int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *nb); +extern void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb); extern void nf_ct_deliver_cached_events(struct nf_conn *ct); static inline void nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; - if (nf_conntrack_event_cb == NULL) + if (net->ct.nf_conntrack_event_cb == NULL) return; e = nf_ct_ecache_find(ct); @@ -95,11 +95,12 @@ nf_conntrack_eventmask_report(unsigned int eventmask, int report) { int ret = 0; + struct net *net = nf_ct_net(ct); struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_conntrack_event_cb); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (notify == NULL) goto out_unlock; @@ -164,9 +165,8 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; -extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); -extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); +extern int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *nb); +extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb); static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, @@ -174,11 +174,12 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event, u32 pid, int report) { + struct net *net = nf_ct_exp_net(exp); struct nf_exp_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_expect_event_cb); + notify = rcu_dereference(net->ct.nf_expect_event_cb); if (notify == NULL) goto out_unlock; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 0249399e51a7..7a911eca0f18 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -18,6 +18,8 @@ struct netns_ct { struct hlist_nulls_head unconfirmed; struct hlist_nulls_head dying; struct ip_conntrack_stat __percpu *stat; + struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; + struct nf_exp_event_notifier __rcu *nf_expect_event_cb; int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; diff --git a/include/net/red.h b/include/net/red.h index 3319f16b3beb..b72a3b833936 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -116,7 +116,7 @@ struct red_parms { u32 qR; /* Cached random number */ unsigned long qavg; /* Average queue length: A scaled */ - psched_time_t qidlestart; /* Start of current idle period */ + ktime_t qidlestart; /* Start of current idle period */ }; static inline u32 red_rmask(u8 Plog) @@ -148,17 +148,17 @@ static inline void red_set_parms(struct red_parms *p, static inline int red_is_idling(struct red_parms *p) { - return p->qidlestart != PSCHED_PASTPERFECT; + return p->qidlestart.tv64 != 0; } static inline void red_start_of_idle_period(struct red_parms *p) { - p->qidlestart = psched_get_time(); + p->qidlestart = ktime_get(); } static inline void red_end_of_idle_period(struct red_parms *p) { - p->qidlestart = PSCHED_PASTPERFECT; + p->qidlestart.tv64 = 0; } static inline void red_restart(struct red_parms *p) @@ -170,13 +170,10 @@ static inline void red_restart(struct red_parms *p) static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p) { - psched_time_t now; - long us_idle; + s64 delta = ktime_us_delta(ktime_get(), p->qidlestart); + long us_idle = min_t(s64, delta, p->Scell_max); int shift; - now = psched_get_time(); - us_idle = psched_tdiff_bounded(now, p->qidlestart, p->Scell_max); - /* * The problem: ideally, average length queue recalcultion should * be done over constant clock intervals. This is too expensive, so diff --git a/include/net/route.h b/include/net/route.h index db7b3432f07c..91855d185b53 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -71,12 +71,12 @@ struct rtable { struct fib_info *fi; /* for client ref to shared metrics */ }; -static inline bool rt_is_input_route(struct rtable *rt) +static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_route_iif != 0; } -static inline bool rt_is_output_route(struct rtable *rt) +static inline bool rt_is_output_route(const struct rtable *rt) { return rt->rt_route_iif == 0; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e5f9ece3c9a0..a1daf8227ed1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -18,6 +18,7 @@ #include <net/sock.h> #include "br_private.h" +#include "br_private_stp.h" static inline size_t br_nlmsg_size(void) { @@ -188,6 +189,11 @@ static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) p->state = new_state; br_log_state(p); + + spin_lock_bh(&p->br->lock); + br_port_state_selection(p->br); + spin_unlock_bh(&p->br->lock); + br_ifinfo_notify(RTM_NEWLINK, p); return 0; diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index ad0a3f7cf6cc..dd147d78a588 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -399,25 +399,24 @@ void br_port_state_selection(struct net_bridge *br) struct net_bridge_port *p; unsigned int liveports = 0; - /* Don't change port states if userspace is handling STP */ - if (br->stp_enabled == BR_USER_STP) - return; - list_for_each_entry(p, &br->port_list, list) { if (p->state == BR_STATE_DISABLED) continue; - if (p->port_no == br->root_port) { - p->config_pending = 0; - p->topology_change_ack = 0; - br_make_forwarding(p); - } else if (br_is_designated_port(p)) { - del_timer(&p->message_age_timer); - br_make_forwarding(p); - } else { - p->config_pending = 0; - p->topology_change_ack = 0; - br_make_blocking(p); + /* Don't change port states if userspace is handling STP */ + if (br->stp_enabled != BR_USER_STP) { + if (p->port_no == br->root_port) { + p->config_pending = 0; + p->topology_change_ack = 0; + br_make_forwarding(p); + } else if (br_is_designated_port(p)) { + del_timer(&p->message_age_timer); + br_make_forwarding(p); + } else { + p->config_pending = 0; + p->topology_change_ack = 0; + br_make_blocking(p); + } } if (p->state == BR_STATE_FORWARDING) diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index f39921171d0d..d3ca87bf23b7 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -136,20 +136,21 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt) { - int tmp; u16 chks; u16 len; + __le16 data; + struct cffrml *this = container_obj(layr); if (this->dofcs) { chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff); - tmp = cpu_to_le16(chks); - cfpkt_add_trail(pkt, &tmp, 2); + data = cpu_to_le16(chks); + cfpkt_add_trail(pkt, &data, 2); } else { cfpkt_pad_trail(pkt, 2); } len = cfpkt_getlen(pkt); - tmp = cpu_to_le16(len); - cfpkt_add_head(pkt, &tmp, 2); + data = cpu_to_le16(len); + cfpkt_add_head(pkt, &data, 2); cfpkt_info(pkt)->hdr_len += 2; if (cfpkt_erroneous(pkt)) { pr_err("Packet is erroneous!\n"); diff --git a/net/core/dev.c b/net/core/dev.c index 6ba50a1e404c..5a13edfc9f73 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1396,7 +1396,7 @@ rollback: for_each_net(net) { for_each_netdev(net, dev) { if (dev == last) - break; + goto outroll; if (dev->flags & IFF_UP) { nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); @@ -1407,6 +1407,7 @@ rollback: } } +outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -4282,6 +4283,12 @@ static int dev_seq_open(struct inode *inode, struct file *file) sizeof(struct dev_iter_state)); } +int dev_seq_open_ops(struct inode *inode, struct file *file, + const struct seq_operations *ops) +{ + return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state)); +} + static const struct file_operations dev_seq_fops = { .owner = THIS_MODULE, .open = dev_seq_open, diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 277faef9148d..febba516db62 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -696,8 +696,7 @@ static const struct seq_operations dev_mc_seq_ops = { static int dev_mc_seq_open(struct inode *inode, struct file *file) { - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); + return dev_seq_open_ops(inode, file, &dev_mc_seq_ops); } static const struct file_operations dev_mc_seq_fops = { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 039d51e6c284..5ac07d31fbc9 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2397,7 +2397,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 18a3cebb753d..3c30ee4a5710 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2230,7 +2230,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than - * the length of the skb, from tgt to skb. Returns number bytes shifted. + * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 90a919afbed7..3f4e5414c8e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -111,6 +111,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { + err = PTR_ERR(rt); rt = NULL; goto failure; } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index a77d16158eb6..94f4ec036669 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -112,7 +112,7 @@ static unsigned long dn_rt_deadline; static int dn_dst_gc(struct dst_ops *ops); static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst); +static unsigned int dn_dst_mtu(const struct dst_entry *dst); static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); @@ -135,7 +135,7 @@ static struct dst_ops dn_dst_ops = { .gc = dn_dst_gc, .check = dn_dst_check, .default_advmss = dn_dst_default_advmss, - .default_mtu = dn_dst_default_mtu, + .mtu = dn_dst_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = dn_dst_destroy, .negative_advice = dn_dst_negative_advice, @@ -825,9 +825,11 @@ static unsigned int dn_dst_default_advmss(const struct dst_entry *dst) return dn_mss_from_pmtu(dst->dev, dst_mtu(dst)); } -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst) +static unsigned int dn_dst_mtu(const struct dst_entry *dst) { - return dst->dev->mtu; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c index 67f691bd4acf..d9c150cc59a9 100644 --- a/net/decnet/dn_timer.c +++ b/net/decnet/dn_timer.c @@ -36,16 +36,13 @@ static void dn_slow_timer(unsigned long arg); void dn_start_slow_timer(struct sock *sk) { - sk->sk_timer.expires = jiffies + SLOW_INTERVAL; - sk->sk_timer.function = dn_slow_timer; - sk->sk_timer.data = (unsigned long)sk; - - add_timer(&sk->sk_timer); + setup_timer(&sk->sk_timer, dn_slow_timer, (unsigned long)sk); + sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); } void dn_stop_slow_timer(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } static void dn_slow_timer(unsigned long arg) @@ -53,12 +50,10 @@ static void dn_slow_timer(unsigned long arg) struct sock *sk = (struct sock *)arg; struct dn_scp *scp = DN_SK(sk); - sock_hold(sk); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - sk->sk_timer.expires = jiffies + HZ / 10; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10); goto out; } @@ -100,9 +95,7 @@ static void dn_slow_timer(unsigned long arg) scp->keepalive_fxn(sk); } - sk->sk_timer.expires = jiffies + SLOW_INTERVAL; - - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); out: bh_unlock_sock(sk); sock_put(sk); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c6b5092f29a1..65f01dc47565 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if ((new_value == 0) && (old_value != 0)) + rt_cache_flush(net, 0); } return ret; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c7472eff2d51..b2ca095cb9da 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1716,7 +1716,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (err) { int j; - pmc->sfcount[sfmode]--; + if (!delta) + pmc->sfcount[sfmode]--; for (j=0; j<i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 68e8ac514383..ccee270a9b65 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,9 +108,6 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops->name); } - if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -125,16 +122,23 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, + * hence this needs to be included regardless of socket family. + */ + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); + if (ext & (1 << (INET_DIAG_TCLASS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); + ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, &np->rcv_saddr); ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, &np->daddr); - if (ext & (1 << (INET_DIAG_TCLASS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); } #endif diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c86270..29a07b6c7168 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 05d20cca9d66..1e60f7679075 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,7 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; - iph->daddr = nexthop; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 9899619ab9b8..4f47e064e262 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -64,7 +64,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && - pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), + 0, GFP_ATOMIC)) return -1; return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1dfc18a03fd4..f19f2182894c 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0c74da8a0473..ca5e237df029 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -131,6 +131,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; +static int redirect_genid; /* * Interface to generic destination cache. @@ -138,7 +139,7 @@ static int rt_chain_length_max __read_mostly = 20; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_default_mtu(const struct dst_entry *dst); +static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -193,7 +194,7 @@ static struct dst_ops ipv4_dst_ops = { .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, - .default_mtu = ipv4_default_mtu, + .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, @@ -416,9 +417,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) else { struct rtable *r = v; struct neighbour *n; - int len; + int len, HHUptod; + rcu_read_lock(); n = dst_get_neighbour(&r->dst); + HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; + rcu_read_unlock(); + seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->dst.dev ? r->dst.dev->name : "*", @@ -432,7 +437,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, -1, - (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0, + HHUptod, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -837,6 +842,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); + redirect_genid++; } /* @@ -1391,8 +1397,10 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, peer = rt->peer; if (peer) { - if (peer->redirect_learned.a4 != new_gw) { + if (peer->redirect_learned.a4 != new_gw || + peer->redirect_genid != redirect_genid) { peer->redirect_learned.a4 = new_gw; + peer->redirect_genid = redirect_genid; atomic_inc(&__rt_peer_genid); } check_peer_redir(&rt->dst, peer); @@ -1685,12 +1693,8 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } -static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +static struct rtable *ipv4_validate_peer(struct rtable *rt) { - struct rtable *rt = (struct rtable *) dst; - - if (rt_is_expired(rt)) - return NULL; if (rt->rt_peer_genid != rt_peer_genid()) { struct inet_peer *peer; @@ -1699,17 +1703,29 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) peer = rt->peer; if (peer) { - check_peer_pmtu(dst, peer); + check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { - if (check_peer_redir(dst, peer)) + if (check_peer_redir(&rt->dst, peer)) return NULL; } } rt->rt_peer_genid = rt_peer_genid(); } + return rt; +} + +static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +{ + struct rtable *rt = (struct rtable *) dst; + + if (rt_is_expired(rt)) + return NULL; + dst = (struct dst_entry *) ipv4_validate_peer(rt); return dst; } @@ -1814,12 +1830,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return advmss; } -static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_mtu(const struct dst_entry *dst) { - unsigned int mtu = dst->dev->mtu; + const struct rtable *rt = (const struct rtable *) dst; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu && rt_is_output_route(rt)) + return mtu; + + mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - const struct rtable *rt = (const struct rtable *) dst; if (rt->rt_gateway != rt->rt_dst && mtu > 576) mtu = 576; @@ -1852,6 +1873,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, dst_init_metrics(&rt->dst, peer->metrics, false); check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; @@ -2357,6 +2380,9 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + rth = ipv4_validate_peer(rth); + if (!rth) + continue; if (noref) { dst_use_noref(&rth->dst, jiffies); skb_dst_set_noref(skb, &rth->dst); @@ -2732,6 +2758,9 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) (IPTOS_RT_MASK | RTO_ONLINK)) && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + rth = ipv4_validate_peer(rth); + if (!rth) + continue; dst_use(&rth->dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); @@ -2755,9 +2784,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } -static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -2775,7 +2806,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, - .default_mtu = ipv4_blackhole_default_mtu, + .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ab0966df1e2a..5a65eeac1d29 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1164,7 +1164,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -1186,9 +1186,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; /* @@ -1197,14 +1198,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, len); + msg->msg_iov, copied); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), @@ -1233,7 +1234,7 @@ try_again: if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fee46d5a2f12..1567fb120392 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -85,7 +85,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, * request_sock (formerly open request) hash tables. */ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, - const u32 rnd, const u16 synq_hsize) + const u32 rnd, const u32 synq_hsize) { u32 c; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c99e3ee9781f..26cb08c84b74 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -503,7 +503,7 @@ done: goto e_inval; if (val > 255 || val < -1) goto e_inval; - np->mcast_hops = val; + np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val); retv = 0; break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 44e5b7f2a6c1..0cb78d7ddaf5 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1571,7 +1571,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, } if (!rt->rt6i_peer) rt6_bind_peer(rt, 1); - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 448464844a25..f792b34cbe9c 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -186,7 +186,6 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8473016bba4a..3399dd326287 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -77,7 +77,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_default_mtu(const struct dst_entry *dst); +static unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -144,7 +144,7 @@ static struct dst_ops ip6_dst_ops_template = { .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, - .default_mtu = ip6_default_mtu, + .mtu = ip6_mtu, .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, @@ -155,9 +155,11 @@ static struct dst_ops ip6_dst_ops_template = { .neigh_lookup = ip6_neigh_lookup, }; -static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -175,7 +177,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, - .default_mtu = ip6_blackhole_default_mtu, + .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .cow_metrics = ip6_rt_blackhole_cow_metrics, @@ -1041,10 +1043,15 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_mtu(const struct dst_entry *dst) { - unsigned int mtu = IPV6_MIN_MTU; struct inet6_dev *idev; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu) + return mtu; + + mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 36131d122a6f..2dea4bb7b54a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1255,6 +1255,13 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, tcp_hdr(skb)); + treq->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = inet6_iif(skb); + if (!isn) { struct inet_peer *peer = NULL; @@ -1264,12 +1271,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) atomic_inc(&skb->users); treq->pktopts = skb; } - treq->iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); if (want_cookie) { isn = cookie_v6_init_sequence(sk, skb, &req->mss); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 846f4757eb8d..8c2541915183 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -340,7 +340,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -363,9 +363,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; is_udp4 = (skb->protocol == htons(ETH_P_IP)); @@ -376,14 +377,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov,len); + msg->msg_iov, copied ); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); if (err == -EINVAL) @@ -432,7 +433,7 @@ try_again: datagram_recv_ctl(sk, msg, skb); } - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index cf0f308abf5e..89ff8c67943e 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1072,7 +1072,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Get routing info from the tunnel socket */ skb_dst_drop(skb); - skb_dst_set(skb, dst_clone(__sk_dst_get(sk))); + skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); inet = inet_sk(sk); fl = &inet->cork.fl; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index b3f65520e7a7..b064e4df12c6 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -161,6 +161,12 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return -ENOENT; } + /* if we're already stopping ignore any new requests to stop */ + if (test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { + spin_unlock_bh(&sta->lock); + return -EALREADY; + } + if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { /* not even started yet! */ ieee80211_assign_tid_tx(sta, tid, NULL); @@ -169,6 +175,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, return 0; } + set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + spin_unlock_bh(&sta->lock); #ifdef CONFIG_MAC80211_HT_DEBUG @@ -176,8 +184,6 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, sta->sta.addr, tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); - del_timer_sync(&tid_tx->addba_resp_timer); /* @@ -187,6 +193,20 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, */ clear_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state); + /* + * There might be a few packets being processed right now (on + * another CPU) that have already gotten past the aggregation + * check when it was still OPERATIONAL and consequently have + * IEEE80211_TX_CTL_AMPDU set. In that case, this code might + * call into the driver at the same time or even before the + * TX paths calls into it, which could confuse the driver. + * + * Wait for all currently running TX paths to finish before + * telling the driver. New packets will not go through since + * the aggregation session is no longer OPERATIONAL. + */ + synchronize_net(); + tid_tx->stop_initiator = initiator; tid_tx->tx_stop = tx; @@ -757,11 +777,27 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, goto out; } - del_timer(&tid_tx->addba_resp_timer); + del_timer_sync(&tid_tx->addba_resp_timer); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "switched off addBA timer for tid %d\n", tid); #endif + + /* + * addba_resp_timer may have fired before we got here, and + * caused WANT_STOP to be set. If the stop then was already + * processed further, STOPPING might be set. + */ + if (test_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state) || + test_bit(HT_AGG_STATE_STOPPING, &tid_tx->state)) { +#ifdef CONFIG_MAC80211_HT_DEBUG + printk(KERN_DEBUG + "got addBA resp for tid %d but we already gave up\n", + tid); +#endif + goto out; + } + /* * IEEE 802.11-2007 7.3.1.14: * In an ADDBA Response frame, when the Status Code field diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index c5f341798c16..3110cbdc501b 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -274,9 +274,9 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, PRINT_HT_CAP((htc->cap & BIT(10)), "HT Delayed Block Ack"); - PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " - "3839 bytes"); PRINT_HT_CAP(!(htc->cap & BIT(11)), "Max AMSDU length: " + "3839 bytes"); + PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " "7935 bytes"); /* diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 80de436eae20..16518f386117 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -260,7 +260,7 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; unsigned char *pos; - __le16 txflags; + u16 txflags; rthdr = (struct ieee80211_radiotap_header *) skb_push(skb, rtap_len); @@ -290,13 +290,13 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band txflags = 0; if (!(info->flags & IEEE80211_TX_STAT_ACK) && !is_multicast_ether_addr(hdr->addr1)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); + txflags |= IEEE80211_RADIOTAP_F_TX_FAIL; if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); + txflags |= IEEE80211_RADIOTAP_F_TX_CTS; else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); + txflags |= IEEE80211_RADIOTAP_F_TX_RTS; put_unaligned_le16(txflags, pos); pos += 2; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8260b13d93c9..d5597b759ba3 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -201,7 +201,6 @@ config NF_CONNTRACK_BROADCAST config NF_CONNTRACK_NETBIOS_NS tristate "NetBIOS name service protocol support" - depends on NETFILTER_ADVANCED select NF_CONNTRACK_BROADCAST help NetBIOS name service requests are sent as broadcast messages from an @@ -542,7 +541,6 @@ config NETFILTER_XT_TARGET_NOTRACK tristate '"NOTRACK" target support' depends on IP_NF_RAW || IP6_NF_RAW depends on NF_CONNTRACK - depends on NETFILTER_ADVANCED help The NOTRACK target allows a select rule to specify which packets *not* to enter the conntrack/NAT diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 6ee10f5d59bd..37d667e3f6f8 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -158,7 +158,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem data = { }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index fb90e344e907..e69e2718fbe1 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -162,7 +162,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem data = { }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index deb3e3dfa5fc..64199b4e93c9 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -184,7 +184,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; - u32 ip, ip_to, p = 0, port, port_to; + u32 ip, ip_to = 0, p = 0, port, port_to; u32 ip2_from = 0, ip2_to, ip2_last, ip2; u32 timeout = h->timeout; bool with_ports = false; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 6b368be937c6..b62c4148b921 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -27,22 +27,17 @@ static DEFINE_MUTEX(nf_ct_ecache_mutex); -struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly; -EXPORT_SYMBOL_GPL(nf_conntrack_event_cb); - -struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly; -EXPORT_SYMBOL_GPL(nf_expect_event_cb); - /* deliver cached events and clear cache entry - must be called with locally * disabled softirqs */ void nf_ct_deliver_cached_events(struct nf_conn *ct) { + struct net *net = nf_ct_net(ct); unsigned long events; struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); - notify = rcu_dereference(nf_conntrack_event_cb); + notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (notify == NULL) goto out_unlock; @@ -83,19 +78,20 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); -int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new) +int nf_conntrack_register_notifier(struct net *net, + struct nf_ct_event_notifier *new) { int ret = 0; struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_conntrack_event_cb, + notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); if (notify != NULL) { ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(nf_conntrack_event_cb, new); + RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -105,32 +101,34 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); -void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new) +void nf_conntrack_unregister_notifier(struct net *net, + struct nf_ct_event_notifier *new) { struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_conntrack_event_cb, + notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - RCU_INIT_POINTER(nf_conntrack_event_cb, NULL); + RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); -int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new) +int nf_ct_expect_register_notifier(struct net *net, + struct nf_exp_event_notifier *new) { int ret = 0; struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_expect_event_cb, + notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); if (notify != NULL) { ret = -EBUSY; goto out_unlock; } - RCU_INIT_POINTER(nf_expect_event_cb, new); + RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); return ret; @@ -140,15 +138,16 @@ out_unlock: } EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier); -void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new) +void nf_ct_expect_unregister_notifier(struct net *net, + struct nf_exp_event_notifier *new) { struct nf_exp_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); - notify = rcu_dereference_protected(nf_expect_event_cb, + notify = rcu_dereference_protected(net->ct.nf_expect_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); BUG_ON(notify != new); - RCU_INIT_POINTER(nf_expect_event_cb, NULL); + RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index e58aa9b1fe8a..ef21b221f036 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -4,7 +4,7 @@ * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> - * (C) 2005-2008 by Pablo Neira Ayuso <pablo@netfilter.org> + * (C) 2005-2011 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) @@ -2163,6 +2163,54 @@ MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); +static int __net_init ctnetlink_net_init(struct net *net) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + int ret; + + ret = nf_conntrack_register_notifier(net, &ctnl_notifier); + if (ret < 0) { + pr_err("ctnetlink_init: cannot register notifier.\n"); + goto err_out; + } + + ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp); + if (ret < 0) { + pr_err("ctnetlink_init: cannot expect register notifier.\n"); + goto err_unreg_notifier; + } +#endif + return 0; + +#ifdef CONFIG_NF_CONNTRACK_EVENTS +err_unreg_notifier: + nf_conntrack_unregister_notifier(net, &ctnl_notifier); +err_out: + return ret; +#endif +} + +static void ctnetlink_net_exit(struct net *net) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp); + nf_conntrack_unregister_notifier(net, &ctnl_notifier); +#endif +} + +static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) +{ + struct net *net; + + list_for_each_entry(net, net_exit_list, exit_list) + ctnetlink_net_exit(net); +} + +static struct pernet_operations ctnetlink_net_ops = { + .init = ctnetlink_net_init, + .exit_batch = ctnetlink_net_exit_batch, +}; + static int __init ctnetlink_init(void) { int ret; @@ -2180,28 +2228,15 @@ static int __init ctnetlink_init(void) goto err_unreg_subsys; } -#ifdef CONFIG_NF_CONNTRACK_EVENTS - ret = nf_conntrack_register_notifier(&ctnl_notifier); - if (ret < 0) { - pr_err("ctnetlink_init: cannot register notifier.\n"); + if (register_pernet_subsys(&ctnetlink_net_ops)) { + pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } - ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp); - if (ret < 0) { - pr_err("ctnetlink_init: cannot expect register notifier.\n"); - goto err_unreg_notifier; - } -#endif - return 0; -#ifdef CONFIG_NF_CONNTRACK_EVENTS -err_unreg_notifier: - nf_conntrack_unregister_notifier(&ctnl_notifier); err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); -#endif err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: @@ -2213,11 +2248,7 @@ static void __exit ctnetlink_exit(void) pr_info("ctnetlink: unregistering from nfnetlink.\n"); nf_ct_remove_userspace_expectations(); -#ifdef CONFIG_NF_CONNTRACK_EVENTS - nf_ct_expect_unregister_notifier(&ctnl_notifier_exp); - nf_conntrack_unregister_notifier(&ctnl_notifier); -#endif - + unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); } diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 9c24de10a657..824f184f7a9b 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -111,8 +111,6 @@ int netlbl_cfg_unlbl_map_add(const char *domain, struct netlbl_domaddr_map *addrmap = NULL; struct netlbl_domaddr4_map *map4 = NULL; struct netlbl_domaddr6_map *map6 = NULL; - const struct in_addr *addr4, *mask4; - const struct in6_addr *addr6, *mask6; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (entry == NULL) @@ -133,9 +131,9 @@ int netlbl_cfg_unlbl_map_add(const char *domain, INIT_LIST_HEAD(&addrmap->list6); switch (family) { - case AF_INET: - addr4 = addr; - mask4 = mask; + case AF_INET: { + const struct in_addr *addr4 = addr; + const struct in_addr *mask4 = mask; map4 = kzalloc(sizeof(*map4), GFP_ATOMIC); if (map4 == NULL) goto cfg_unlbl_map_add_failure; @@ -148,9 +146,11 @@ int netlbl_cfg_unlbl_map_add(const char *domain, if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; - case AF_INET6: - addr6 = addr; - mask6 = mask; + } +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: { + const struct in6_addr *addr6 = addr; + const struct in6_addr *mask6 = mask; map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); if (map6 == NULL) goto cfg_unlbl_map_add_failure; @@ -162,11 +162,13 @@ int netlbl_cfg_unlbl_map_add(const char *domain, map6->list.addr.s6_addr32[3] &= mask6->s6_addr32[3]; ipv6_addr_copy(&map6->list.mask, mask6); map6->list.valid = 1; - ret_val = netlbl_af4list_add(&map4->list, - &addrmap->list4); + ret_val = netlbl_af6list_add(&map6->list, + &addrmap->list6); if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; + } +#endif /* IPv6 */ default: goto cfg_unlbl_map_add_failure; break; @@ -225,9 +227,11 @@ int netlbl_cfg_unlbl_static_add(struct net *net, case AF_INET: addr_len = sizeof(struct in_addr); break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case AF_INET6: addr_len = sizeof(struct in6_addr); break; +#endif /* IPv6 */ default: return -EPFNOSUPPORT; } @@ -266,9 +270,11 @@ int netlbl_cfg_unlbl_static_del(struct net *net, case AF_INET: addr_len = sizeof(struct in_addr); break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case AF_INET6: addr_len = sizeof(struct in6_addr); break; +#endif /* IPv6 */ default: return -EPFNOSUPPORT; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 6649463da1b6..d617161f8dd3 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -209,8 +209,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) ctl->Plog, ctl->Scell_log, nla_data(tb[TCA_RED_STAB])); - if (skb_queue_empty(&sch->q)) - red_end_of_idle_period(&q->parms); + if (!q->qdisc->q.qlen) + red_start_of_idle_period(&q->parms); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index a3b7120fcc74..4f4c52c0eeb3 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -225,11 +225,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) static int -__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev) +__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, + struct net_device *dev, struct netdev_queue *txq, + struct neighbour *mn) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); - struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc); - struct neighbour *mn = dst_get_neighbour(skb_dst(skb)); + struct teql_sched_data *q = qdisc_priv(txq->qdisc); struct neighbour *n = q->ncache; if (mn->tbl == NULL) @@ -262,17 +262,26 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * } static inline int teql_resolve(struct sk_buff *skb, - struct sk_buff *skb_res, struct net_device *dev) + struct sk_buff *skb_res, + struct net_device *dev, + struct netdev_queue *txq) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct dst_entry *dst = skb_dst(skb); + struct neighbour *mn; + int res; + if (txq->qdisc == &noop_qdisc) return -ENODEV; - if (dev->header_ops == NULL || - skb_dst(skb) == NULL || - dst_get_neighbour(skb_dst(skb)) == NULL) + if (!dev->header_ops || !dst) return 0; - return __teql_resolve(skb, skb_res, dev); + + rcu_read_lock(); + mn = dst_get_neighbour(dst); + res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0; + rcu_read_unlock(); + + return res; } static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) @@ -307,7 +316,7 @@ restart: continue; } - switch (teql_resolve(skb, skb_res, slave)) { + switch (teql_resolve(skb, skb_res, slave, slave_txq)) { case 0: if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 865e68fef21c..bf812048cf6f 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -82,7 +82,7 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp) struct sctp_auth_bytes *key; /* Verify that we are not going to overflow INT_MAX */ - if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes)) + if (key_len > (INT_MAX - sizeof(struct sctp_auth_bytes))) return NULL; /* Allocate the shared key */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 466fbcc5cf77..b595a3d8679f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1957,6 +1957,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if ((UNIXCB(skb).pid != siocb->scm->pid) || (UNIXCB(skb).cred != siocb->scm->cred)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } else { @@ -1974,6 +1975,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, chunk = min_t(unsigned int, skb->len, size); if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); if (copied == 0) copied = -EFAULT; break; @@ -1991,6 +1993,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put the skb back if we didn't use it up.. */ if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } @@ -2006,6 +2009,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } while (size); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b3a476fe8272..ffafda5022c2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -89,8 +89,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_IFINDEX] = { .type = NLA_U32 }, [NL80211_ATTR_IFNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ-1 }, - [NL80211_ATTR_MAC] = { .type = NLA_BINARY, .len = ETH_ALEN }, - [NL80211_ATTR_PREV_BSSID] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [NL80211_ATTR_MAC] = { .len = ETH_ALEN }, + [NL80211_ATTR_PREV_BSSID] = { .len = ETH_ALEN }, [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index e71f5a66574e..77e926738014 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2037,6 +2037,10 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) } request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + if (!request_wiphy) { + reg_set_request_processed(); + return -ENODEV; + } if (!last_request->intersect) { int r; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 552df27dcf53..2118d6446630 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2382,9 +2382,11 @@ static unsigned int xfrm_default_advmss(const struct dst_entry *dst) return dst_metric_advmss(dst->path); } -static unsigned int xfrm_default_mtu(const struct dst_entry *dst) +static unsigned int xfrm_mtu(const struct dst_entry *dst) { - return dst_mtu(dst->path); + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst_mtu(dst->path); } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr) @@ -2411,8 +2413,8 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; - if (likely(dst_ops->default_mtu == NULL)) - dst_ops->default_mtu = xfrm_default_mtu; + if (likely(dst_ops->mtu == NULL)) + dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 096507d2ca9a..7d98240def0b 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2508,7 +2508,6 @@ static struct snd_pci_quirk position_fix_list[] __devinitdata = { SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB), SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB), SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB), - SND_PCI_QUIRK(0x1106, 0x3288, "ASUS M2V-MX SE", POS_FIX_LPIB), SND_PCI_QUIRK(0x1297, 0x3166, "Shuttle", POS_FIX_LPIB), SND_PCI_QUIRK(0x1458, 0xa022, "ga-ma770-ud3", POS_FIX_LPIB), SND_PCI_QUIRK(0x1462, 0x1002, "MSI Wind U115", POS_FIX_LPIB), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index f3658658548e..d8d2f9dccd9b 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -4441,7 +4441,9 @@ static int stac92xx_init(struct hda_codec *codec) int pinctl, def_conf; /* power on when no jack detection is available */ - if (!spec->hp_detect) { + /* or when the VREF is used for controlling LED */ + if (!spec->hp_detect || + (spec->gpio_led > 8 && spec->gpio_led == nid)) { stac_toggle_power_map(codec, nid, 1); continue; } @@ -5055,20 +5057,6 @@ static int stac92xx_pre_resume(struct hda_codec *codec) return 0; } -static int stac92xx_post_suspend(struct hda_codec *codec) -{ - struct sigmatel_spec *spec = codec->spec; - if (spec->gpio_led > 8) { - /* with vref-out pin used for mute led control - * codec AFG is prevented from D3 state, but on - * system suspend it can (and should) be used - */ - snd_hda_codec_read(codec, codec->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D3); - } - return 0; -} - static void stac92xx_set_power_state(struct hda_codec *codec, hda_nid_t fg, unsigned int power_state) { @@ -5668,8 +5656,6 @@ again: } else { codec->patch_ops.set_power_state = stac92xx_set_power_state; - codec->patch_ops.post_suspend = - stac92xx_post_suspend; } codec->patch_ops.pre_resume = stac92xx_pre_resume; codec->patch_ops.check_power_status = @@ -5983,8 +5969,6 @@ again: } else { codec->patch_ops.set_power_state = stac92xx_set_power_state; - codec->patch_ops.post_suspend = - stac92xx_post_suspend; } codec->patch_ops.pre_resume = stac92xx_pre_resume; codec->patch_ops.check_power_status = diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig index bee3c94f58b0..d1fcc816ce97 100644 --- a/sound/soc/atmel/Kconfig +++ b/sound/soc/atmel/Kconfig @@ -1,6 +1,6 @@ config SND_ATMEL_SOC tristate "SoC Audio for the Atmel System-on-Chip" - depends on ARCH_AT91 || AVR32 + depends on ARCH_AT91 help Say Y or M if you want to add support for codecs attached to the ATMEL SSC interface. You will also need @@ -24,25 +24,6 @@ config SND_AT91_SOC_SAM9G20_WM8731 Say Y if you want to add support for SoC audio on WM8731-based AT91sam9g20 evaluation board. -config SND_AT32_SOC_PLAYPAQ - tristate "SoC Audio support for PlayPaq with WM8510" - depends on SND_ATMEL_SOC && BOARD_PLAYPAQ && AT91_PROGRAMMABLE_CLOCKS - select SND_ATMEL_SOC_SSC - select SND_SOC_WM8510 - help - Say Y or M here if you want to add support for SoC audio - on the LRS PlayPaq. - -config SND_AT32_SOC_PLAYPAQ_SLAVE - bool "Run CODEC on PlayPaq in slave mode" - depends on SND_AT32_SOC_PLAYPAQ - default n - help - Say Y if you want to run with the AT32 SSC generating the BCLK - and FRAME signals on the PlayPaq. Unless you want to play - with the AT32 as the SSC master, you probably want to say N here, - as this will give you better sound quality. - config SND_AT91_SOC_AFEB9260 tristate "SoC Audio support for AFEB9260 board" depends on ARCH_AT91 && MACH_AFEB9260 && SND_ATMEL_SOC diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile index e7ea56bd5f82..a5c0bf19da78 100644 --- a/sound/soc/atmel/Makefile +++ b/sound/soc/atmel/Makefile @@ -8,9 +8,5 @@ obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o # AT91 Machine Support snd-soc-sam9g20-wm8731-objs := sam9g20_wm8731.o -# AT32 Machine Support -snd-soc-playpaq-objs := playpaq_wm8510.o - obj-$(CONFIG_SND_AT91_SOC_SAM9G20_WM8731) += snd-soc-sam9g20-wm8731.o -obj-$(CONFIG_SND_AT32_SOC_PLAYPAQ) += snd-soc-playpaq.o obj-$(CONFIG_SND_AT91_SOC_AFEB9260) += snd-soc-afeb9260.o diff --git a/sound/soc/atmel/playpaq_wm8510.c b/sound/soc/atmel/playpaq_wm8510.c deleted file mode 100644 index 73ae99ad4578..000000000000 --- a/sound/soc/atmel/playpaq_wm8510.c +++ /dev/null @@ -1,473 +0,0 @@ -/* sound/soc/at32/playpaq_wm8510.c - * ASoC machine driver for PlayPaq using WM8510 codec - * - * Copyright (C) 2008 Long Range Systems - * Geoffrey Wossum <gwossum@acm.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This code is largely inspired by sound/soc/at91/eti_b1_wm8731.c - * - * NOTE: If you don't have the AT32 enhanced portmux configured (which - * isn't currently in the mainline or Atmel patched kernel), you will - * need to set the MCLK pin (PA30) to peripheral A in your board initialization - * code. Something like: - * at32_select_periph(GPIO_PIN_PA(30), GPIO_PERIPH_A, 0); - * - */ - -/* #define DEBUG */ - -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/clk.h> -#include <linux/timer.h> -#include <linux/interrupt.h> -#include <linux/platform_device.h> - -#include <sound/core.h> -#include <sound/pcm.h> -#include <sound/pcm_params.h> -#include <sound/soc.h> - -#include <mach/at32ap700x.h> -#include <mach/portmux.h> - -#include "../codecs/wm8510.h" -#include "atmel-pcm.h" -#include "atmel_ssc_dai.h" - - -/*-------------------------------------------------------------------------*\ - * constants -\*-------------------------------------------------------------------------*/ -#define MCLK_PIN GPIO_PIN_PA(30) -#define MCLK_PERIPH GPIO_PERIPH_A - - -/*-------------------------------------------------------------------------*\ - * data types -\*-------------------------------------------------------------------------*/ -/* SSC clocking data */ -struct ssc_clock_data { - /* CMR div */ - unsigned int cmr_div; - - /* Frame period (as needed by xCMR.PERIOD) */ - unsigned int period; - - /* The SSC clock rate these settings where calculated for */ - unsigned long ssc_rate; -}; - - -/*-------------------------------------------------------------------------*\ - * module data -\*-------------------------------------------------------------------------*/ -static struct clk *_gclk0; -static struct clk *_pll0; - -#define CODEC_CLK (_gclk0) - - -/*-------------------------------------------------------------------------*\ - * Sound SOC operations -\*-------------------------------------------------------------------------*/ -#if defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE -static struct ssc_clock_data playpaq_wm8510_calc_ssc_clock( - struct snd_pcm_hw_params *params, - struct snd_soc_dai *cpu_dai) -{ - struct at32_ssc_info *ssc_p = snd_soc_dai_get_drvdata(cpu_dai); - struct ssc_device *ssc = ssc_p->ssc; - struct ssc_clock_data cd; - unsigned int rate, width_bits, channels; - unsigned int bitrate, ssc_div; - unsigned actual_rate; - - - /* - * Figure out required bitrate - */ - rate = params_rate(params); - channels = params_channels(params); - width_bits = snd_pcm_format_physical_width(params_format(params)); - bitrate = rate * width_bits * channels; - - - /* - * Figure out required SSC divider and period for required bitrate - */ - cd.ssc_rate = clk_get_rate(ssc->clk); - ssc_div = cd.ssc_rate / bitrate; - cd.cmr_div = ssc_div / 2; - if (ssc_div & 1) { - /* round cmr_div up */ - cd.cmr_div++; - } - cd.period = width_bits - 1; - - - /* - * Find actual rate, compare to requested rate - */ - actual_rate = (cd.ssc_rate / (cd.cmr_div * 2)) / (2 * (cd.period + 1)); - pr_debug("playpaq_wm8510: Request rate = %u, actual rate = %u\n", - rate, actual_rate); - - - return cd; -} -#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */ - - - -static int playpaq_wm8510_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params) -{ - struct snd_soc_pcm_runtime *rtd = substream->private_data; - struct snd_soc_dai *codec_dai = rtd->codec_dai; - struct snd_soc_dai *cpu_dai = rtd->cpu_dai; - struct at32_ssc_info *ssc_p = snd_soc_dai_get_drvdata(cpu_dai); - struct ssc_device *ssc = ssc_p->ssc; - unsigned int pll_out = 0, bclk = 0, mclk_div = 0; - int ret; - - - /* Due to difficulties with getting the correct clocks from the AT32's - * PLL0, we're going to let the CODEC be in charge of all the clocks - */ -#if !defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE - const unsigned int fmt = (SND_SOC_DAIFMT_I2S | - SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBM_CFM); -#else - struct ssc_clock_data cd; - const unsigned int fmt = (SND_SOC_DAIFMT_I2S | - SND_SOC_DAIFMT_NB_NF | - SND_SOC_DAIFMT_CBS_CFS); -#endif - - if (ssc == NULL) { - pr_warning("playpaq_wm8510_hw_params: ssc is NULL!\n"); - return -EINVAL; - } - - - /* - * Figure out PLL and BCLK dividers for WM8510 - */ - switch (params_rate(params)) { - case 48000: - pll_out = 24576000; - mclk_div = WM8510_MCLKDIV_2; - bclk = WM8510_BCLKDIV_8; - break; - - case 44100: - pll_out = 22579200; - mclk_div = WM8510_MCLKDIV_2; - bclk = WM8510_BCLKDIV_8; - break; - - case 22050: - pll_out = 22579200; - mclk_div = WM8510_MCLKDIV_4; - bclk = WM8510_BCLKDIV_8; - break; - - case 16000: - pll_out = 24576000; - mclk_div = WM8510_MCLKDIV_6; - bclk = WM8510_BCLKDIV_8; - break; - - case 11025: - pll_out = 22579200; - mclk_div = WM8510_MCLKDIV_8; - bclk = WM8510_BCLKDIV_8; - break; - - case 8000: - pll_out = 24576000; - mclk_div = WM8510_MCLKDIV_12; - bclk = WM8510_BCLKDIV_8; - break; - - default: - pr_warning("playpaq_wm8510: Unsupported sample rate %d\n", - params_rate(params)); - return -EINVAL; - } - - - /* - * set CPU and CODEC DAI configuration - */ - ret = snd_soc_dai_set_fmt(codec_dai, fmt); - if (ret < 0) { - pr_warning("playpaq_wm8510: " - "Failed to set CODEC DAI format (%d)\n", - ret); - return ret; - } - ret = snd_soc_dai_set_fmt(cpu_dai, fmt); - if (ret < 0) { - pr_warning("playpaq_wm8510: " - "Failed to set CPU DAI format (%d)\n", - ret); - return ret; - } - - - /* - * Set CPU clock configuration - */ -#if defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE - cd = playpaq_wm8510_calc_ssc_clock(params, cpu_dai); - pr_debug("playpaq_wm8510: cmr_div = %d, period = %d\n", - cd.cmr_div, cd.period); - ret = snd_soc_dai_set_clkdiv(cpu_dai, AT32_SSC_CMR_DIV, cd.cmr_div); - if (ret < 0) { - pr_warning("playpaq_wm8510: Failed to set CPU CMR_DIV (%d)\n", - ret); - return ret; - } - ret = snd_soc_dai_set_clkdiv(cpu_dai, AT32_SSC_TCMR_PERIOD, - cd.period); - if (ret < 0) { - pr_warning("playpaq_wm8510: " - "Failed to set CPU transmit period (%d)\n", - ret); - return ret; - } -#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */ - - - /* - * Set CODEC clock configuration - */ - pr_debug("playpaq_wm8510: " - "pll_in = %ld, pll_out = %u, bclk = %x, mclk = %x\n", - clk_get_rate(CODEC_CLK), pll_out, bclk, mclk_div); - - -#if !defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE - ret = snd_soc_dai_set_clkdiv(codec_dai, WM8510_BCLKDIV, bclk); - if (ret < 0) { - pr_warning - ("playpaq_wm8510: Failed to set CODEC DAI BCLKDIV (%d)\n", - ret); - return ret; - } -#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */ - - - ret = snd_soc_dai_set_pll(codec_dai, 0, 0, - clk_get_rate(CODEC_CLK), pll_out); - if (ret < 0) { - pr_warning("playpaq_wm8510: Failed to set CODEC DAI PLL (%d)\n", - ret); - return ret; - } - - - ret = snd_soc_dai_set_clkdiv(codec_dai, WM8510_MCLKDIV, mclk_div); - if (ret < 0) { - pr_warning("playpaq_wm8510: Failed to set CODEC MCLKDIV (%d)\n", - ret); - return ret; - } - - - return 0; -} - - - -static struct snd_soc_ops playpaq_wm8510_ops = { - .hw_params = playpaq_wm8510_hw_params, -}; - - - -static const struct snd_soc_dapm_widget playpaq_dapm_widgets[] = { - SND_SOC_DAPM_MIC("Int Mic", NULL), - SND_SOC_DAPM_SPK("Ext Spk", NULL), -}; - - - -static const struct snd_soc_dapm_route intercon[] = { - /* speaker connected to SPKOUT */ - {"Ext Spk", NULL, "SPKOUTP"}, - {"Ext Spk", NULL, "SPKOUTN"}, - - {"Mic Bias", NULL, "Int Mic"}, - {"MICN", NULL, "Mic Bias"}, - {"MICP", NULL, "Mic Bias"}, -}; - - - -static int playpaq_wm8510_init(struct snd_soc_pcm_runtime *rtd) -{ - struct snd_soc_codec *codec = rtd->codec; - struct snd_soc_dapm_context *dapm = &codec->dapm; - int i; - - /* - * Add DAPM widgets - */ - for (i = 0; i < ARRAY_SIZE(playpaq_dapm_widgets); i++) - snd_soc_dapm_new_control(dapm, &playpaq_dapm_widgets[i]); - - - - /* - * Setup audio path interconnects - */ - snd_soc_dapm_add_routes(dapm, intercon, ARRAY_SIZE(intercon)); - - - - /* always connected pins */ - snd_soc_dapm_enable_pin(dapm, "Int Mic"); - snd_soc_dapm_enable_pin(dapm, "Ext Spk"); - - - - /* Make CSB show PLL rate */ - snd_soc_dai_set_clkdiv(rtd->codec_dai, WM8510_OPCLKDIV, - WM8510_OPCLKDIV_1 | 4); - - return 0; -} - - - -static struct snd_soc_dai_link playpaq_wm8510_dai = { - .name = "WM8510", - .stream_name = "WM8510 PCM", - .cpu_dai_name= "atmel-ssc-dai.0", - .platform_name = "atmel-pcm-audio", - .codec_name = "wm8510-codec.0-0x1a", - .codec_dai_name = "wm8510-hifi", - .init = playpaq_wm8510_init, - .ops = &playpaq_wm8510_ops, -}; - - - -static struct snd_soc_card snd_soc_playpaq = { - .name = "LRS_PlayPaq_WM8510", - .dai_link = &playpaq_wm8510_dai, - .num_links = 1, -}; - -static struct platform_device *playpaq_snd_device; - - -static int __init playpaq_asoc_init(void) -{ - int ret = 0; - - /* - * Configure MCLK for WM8510 - */ - _gclk0 = clk_get(NULL, "gclk0"); - if (IS_ERR(_gclk0)) { - _gclk0 = NULL; - ret = PTR_ERR(_gclk0); - goto err_gclk0; - } - _pll0 = clk_get(NULL, "pll0"); - if (IS_ERR(_pll0)) { - _pll0 = NULL; - ret = PTR_ERR(_pll0); - goto err_pll0; - } - ret = clk_set_parent(_gclk0, _pll0); - if (ret) { - pr_warning("snd-soc-playpaq: " - "Failed to set PLL0 as parent for DAC clock\n"); - goto err_set_clk; - } - clk_set_rate(CODEC_CLK, 12000000); - clk_enable(CODEC_CLK); - -#if defined CONFIG_AT32_ENHANCED_PORTMUX - at32_select_periph(MCLK_PIN, MCLK_PERIPH, 0); -#endif - - - /* - * Create and register platform device - */ - playpaq_snd_device = platform_device_alloc("soc-audio", 0); - if (playpaq_snd_device == NULL) { - ret = -ENOMEM; - goto err_device_alloc; - } - - platform_set_drvdata(playpaq_snd_device, &snd_soc_playpaq); - - ret = platform_device_add(playpaq_snd_device); - if (ret) { - pr_warning("playpaq_wm8510: platform_device_add failed (%d)\n", - ret); - goto err_device_add; - } - - return 0; - - -err_device_add: - if (playpaq_snd_device != NULL) { - platform_device_put(playpaq_snd_device); - playpaq_snd_device = NULL; - } -err_device_alloc: -err_set_clk: - if (_pll0 != NULL) { - clk_put(_pll0); - _pll0 = NULL; - } -err_pll0: - if (_gclk0 != NULL) { - clk_put(_gclk0); - _gclk0 = NULL; - } - return ret; -} - - -static void __exit playpaq_asoc_exit(void) -{ - if (_gclk0 != NULL) { - clk_put(_gclk0); - _gclk0 = NULL; - } - if (_pll0 != NULL) { - clk_put(_pll0); - _pll0 = NULL; - } - -#if defined CONFIG_AT32_ENHANCED_PORTMUX - at32_free_pin(MCLK_PIN); -#endif - - platform_device_unregister(playpaq_snd_device); - playpaq_snd_device = NULL; -} - -module_init(playpaq_asoc_init); -module_exit(playpaq_asoc_exit); - -MODULE_AUTHOR("Geoffrey Wossum <gwossum@acm.org>"); -MODULE_DESCRIPTION("ASoC machine driver for LRS PlayPaq"); -MODULE_LICENSE("GPL"); diff --git a/sound/soc/codecs/ad1836.h b/sound/soc/codecs/ad1836.h index 444747f0db26..dd7be0dbbc58 100644 --- a/sound/soc/codecs/ad1836.h +++ b/sound/soc/codecs/ad1836.h @@ -34,7 +34,7 @@ #define AD1836_ADC_CTRL2 13 #define AD1836_ADC_WORD_LEN_MASK 0x30 -#define AD1836_ADC_WORD_OFFSET 5 +#define AD1836_ADC_WORD_OFFSET 4 #define AD1836_ADC_SERFMT_MASK (7 << 6) #define AD1836_ADC_SERFMT_PCK256 (0x4 << 6) #define AD1836_ADC_SERFMT_PCK128 (0x5 << 6) diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c index f1f237ecec2a..73f46eb459f1 100644 --- a/sound/soc/codecs/cs4270.c +++ b/sound/soc/codecs/cs4270.c @@ -601,7 +601,6 @@ static int cs4270_soc_suspend(struct snd_soc_codec *codec, pm_message_t mesg) static int cs4270_soc_resume(struct snd_soc_codec *codec) { struct cs4270_private *cs4270 = snd_soc_codec_get_drvdata(codec); - struct i2c_client *i2c_client = to_i2c_client(codec->dev); int reg; regulator_bulk_enable(ARRAY_SIZE(cs4270->supplies), @@ -612,14 +611,7 @@ static int cs4270_soc_resume(struct snd_soc_codec *codec) ndelay(500); /* first restore the entire register cache ... */ - for (reg = CS4270_FIRSTREG; reg <= CS4270_LASTREG; reg++) { - u8 val = snd_soc_read(codec, reg); - - if (i2c_smbus_write_byte_data(i2c_client, reg, val)) { - dev_err(codec->dev, "i2c write failed\n"); - return -EIO; - } - } + snd_soc_cache_sync(codec); /* ... then disable the power-down bits */ reg = snd_soc_read(codec, CS4270_PWRCTL); diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index 8c3c8205d19e..1ee66361f61b 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -555,7 +555,7 @@ static int cs42l51_probe(struct snd_soc_codec *codec) static struct snd_soc_codec_driver soc_codec_device_cs42l51 = { .probe = cs42l51_probe, - .reg_cache_size = CS42L51_NUMREGS, + .reg_cache_size = CS42L51_NUMREGS + 1, .reg_word_size = sizeof(u8), }; diff --git a/sound/soc/codecs/max9877.c b/sound/soc/codecs/max9877.c index 9e7e964a5fa3..dcf6f2a1600a 100644 --- a/sound/soc/codecs/max9877.c +++ b/sound/soc/codecs/max9877.c @@ -106,13 +106,13 @@ static int max9877_set_2reg(struct snd_kcontrol *kcontrol, unsigned int mask = mc->max; unsigned int val = (ucontrol->value.integer.value[0] & mask); unsigned int val2 = (ucontrol->value.integer.value[1] & mask); - unsigned int change = 1; + unsigned int change = 0; - if (((max9877_regs[reg] >> shift) & mask) == val) - change = 0; + if (((max9877_regs[reg] >> shift) & mask) != val) + change = 1; - if (((max9877_regs[reg2] >> shift) & mask) == val2) - change = 0; + if (((max9877_regs[reg2] >> shift) & mask) != val2) + change = 1; if (change) { max9877_regs[reg] &= ~(mask << shift); diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 9c982e47eb99..6c2988549003 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -2357,6 +2357,11 @@ static int wm8994_hw_params(struct snd_pcm_substream *substream, bclk |= best << WM8994_AIF1_BCLK_DIV_SHIFT; lrclk = bclk_rate / params_rate(params); + if (!lrclk) { + dev_err(dai->dev, "Unable to generate LRCLK from %dHz BCLK\n", + bclk_rate); + return -EINVAL; + } dev_dbg(dai->dev, "Using LRCLK rate %d for actual LRCLK %dHz\n", lrclk, bclk_rate / lrclk); @@ -3178,6 +3183,8 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec) switch (wm8994->revision) { case 0: case 1: + case 2: + case 3: wm8994->hubs.dcs_codes_l = -9; wm8994->hubs.dcs_codes_r = -5; break; diff --git a/sound/soc/fsl/mpc8610_hpcd.c b/sound/soc/fsl/mpc8610_hpcd.c index 31af405bda84..ae49f1c78c6d 100644 --- a/sound/soc/fsl/mpc8610_hpcd.c +++ b/sound/soc/fsl/mpc8610_hpcd.c @@ -392,7 +392,8 @@ static int mpc8610_hpcd_probe(struct platform_device *pdev) } if (strcasecmp(sprop, "i2s-slave") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_I2S; + machine_data->dai_format = + SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM; machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT; machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN; @@ -409,31 +410,38 @@ static int mpc8610_hpcd_probe(struct platform_device *pdev) } machine_data->clk_frequency = be32_to_cpup(iprop); } else if (strcasecmp(sprop, "i2s-master") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_I2S; + machine_data->dai_format = + SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS; machine_data->codec_clk_direction = SND_SOC_CLOCK_IN; machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT; } else if (strcasecmp(sprop, "lj-slave") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_LEFT_J; + machine_data->dai_format = + SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM; machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT; machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN; } else if (strcasecmp(sprop, "lj-master") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_LEFT_J; + machine_data->dai_format = + SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS; machine_data->codec_clk_direction = SND_SOC_CLOCK_IN; machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT; } else if (strcasecmp(sprop, "rj-slave") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_RIGHT_J; + machine_data->dai_format = + SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM; machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT; machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN; } else if (strcasecmp(sprop, "rj-master") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_RIGHT_J; + machine_data->dai_format = + SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS; machine_data->codec_clk_direction = SND_SOC_CLOCK_IN; machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT; } else if (strcasecmp(sprop, "ac97-slave") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_AC97; + machine_data->dai_format = + SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM; machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT; machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN; } else if (strcasecmp(sprop, "ac97-master") == 0) { - machine_data->dai_format = SND_SOC_DAIFMT_AC97; + machine_data->dai_format = + SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS; machine_data->codec_clk_direction = SND_SOC_CLOCK_IN; machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT; } else { diff --git a/sound/soc/nuc900/nuc900-ac97.c b/sound/soc/nuc900/nuc900-ac97.c index 9c0edad90d8b..a4e3237956e2 100644 --- a/sound/soc/nuc900/nuc900-ac97.c +++ b/sound/soc/nuc900/nuc900-ac97.c @@ -365,7 +365,8 @@ static int __devinit nuc900_ac97_drvprobe(struct platform_device *pdev) if (ret) goto out3; - mfp_set_groupg(nuc900_audio->dev); /* enbale ac97 multifunction pin*/ + /* enbale ac97 multifunction pin */ + mfp_set_groupg(nuc900_audio->dev, "nuc900-audio"); return 0; diff --git a/sound/soc/samsung/smdk_wm8994.c b/sound/soc/samsung/smdk_wm8994.c index f75e43997d5b..ad9ac42522e2 100644 --- a/sound/soc/samsung/smdk_wm8994.c +++ b/sound/soc/samsung/smdk_wm8994.c @@ -9,6 +9,7 @@ #include "../codecs/wm8994.h" #include <sound/pcm_params.h> +#include <linux/module.h> /* * Default CFG switch settings to use this driver: diff --git a/sound/soc/samsung/speyside.c b/sound/soc/samsung/speyside.c index 85bf541a771d..4b8e35410eb1 100644 --- a/sound/soc/samsung/speyside.c +++ b/sound/soc/samsung/speyside.c @@ -191,7 +191,7 @@ static int speyside_late_probe(struct snd_soc_card *card) snd_soc_dapm_ignore_suspend(&card->dapm, "Headset Mic"); snd_soc_dapm_ignore_suspend(&card->dapm, "Main AMIC"); snd_soc_dapm_ignore_suspend(&card->dapm, "Main DMIC"); - snd_soc_dapm_ignore_suspend(&card->dapm, "Speaker"); + snd_soc_dapm_ignore_suspend(&card->dapm, "Main Speaker"); snd_soc_dapm_ignore_suspend(&card->dapm, "WM1250 Output"); snd_soc_dapm_ignore_suspend(&card->dapm, "WM1250 Input"); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index a5d3685a5d38..a25fa63ce9a2 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -709,6 +709,12 @@ int snd_soc_resume(struct device *dev) struct snd_soc_card *card = dev_get_drvdata(dev); int i, ac97_control = 0; + /* If the initialization of this soc device failed, there is no codec + * associated with it. Just bail out in this case. + */ + if (list_empty(&card->codec_dev_list)) + return 0; + /* AC97 devices might have other drivers hanging off them so * need to resume immediately. Other drivers don't have that * problem and may take a substantial amount of time to resume diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index b61945f3af9e..32d2a21f2e3b 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -1633,6 +1633,37 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, { + /* Roland GAIA SH-01 */ + USB_DEVICE(0x0582, 0x0111), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .vendor_name = "Roland", + .product_name = "GAIA", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 1, + .type = QUIRK_AUDIO_STANDARD_INTERFACE + }, + { + .ifnum = 2, + .type = QUIRK_MIDI_FIXED_ENDPOINT, + .data = &(const struct snd_usb_midi_endpoint_info) { + .out_cables = 0x0003, + .in_cables = 0x0003 + } + }, + { + .ifnum = -1 + } + } + } +}, +{ USB_DEVICE(0x0582, 0x0113), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { /* .vendor_name = "BOSS", */ |