diff options
46 files changed, 382 insertions, 153 deletions
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt index 0924aac..29bdf62 100644 --- a/Documentation/vm/transhuge.txt +++ b/Documentation/vm/transhuge.txt @@ -123,10 +123,11 @@ be automatically shutdown if it's set to "never". khugepaged runs usually at low frequency so while one may not want to invoke defrag algorithms synchronously during the page faults, it should be worth invoking defrag at least in khugepaged. However it's -also possible to disable defrag in khugepaged: +also possible to disable defrag in khugepaged by writing 0 or enable +defrag in khugepaged by writing 1: -echo yes >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag -echo no >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag +echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag +echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag You can also control how many pages khugepaged should scan at each pass: diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3269576..3146ed3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1283,6 +1283,20 @@ config ARM_ERRATA_364296 processor into full low interrupt latency mode. ARM11MPCore is not affected. +config ARM_ERRATA_764369 + bool "ARM errata: Data cache line maintenance operation by MVA may not succeed" + depends on CPU_V7 && SMP + help + This option enables the workaround for erratum 764369 + affecting Cortex-A9 MPCore with two or more processors (all + current revisions). Under certain timing circumstances, a data + cache line maintenance operation by MVA targeting an Inner + Shareable memory region may fail to proceed up to either the + Point of Coherency or to the Point of Unification of the + system. This workaround adds a DSB instruction before the + relevant cache maintenance functions and sets a specific bit + in the diagnostic control register of the SCU. + endmenu source "arch/arm/common/Kconfig" diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index 8c73900..253cc86 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -25,17 +25,17 @@ #ifdef CONFIG_SMP -#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ +#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ smp_mb(); \ __asm__ __volatile__( \ - "1: ldrex %1, [%2]\n" \ + "1: ldrex %1, [%3]\n" \ " " insn "\n" \ - "2: strex %1, %0, [%2]\n" \ - " teq %1, #0\n" \ + "2: strex %2, %0, [%3]\n" \ + " teq %2, #0\n" \ " bne 1b\n" \ " mov %0, #0\n" \ - __futex_atomic_ex_table("%4") \ - : "=&r" (ret), "=&r" (oldval) \ + __futex_atomic_ex_table("%5") \ + : "=&r" (ret), "=&r" (oldval), "=&r" (tmp) \ : "r" (uaddr), "r" (oparg), "Ir" (-EFAULT) \ : "cc", "memory") @@ -73,14 +73,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, #include <linux/preempt.h> #include <asm/domain.h> -#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ +#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg) \ __asm__ __volatile__( \ - "1: " T(ldr) " %1, [%2]\n" \ + "1: " T(ldr) " %1, [%3]\n" \ " " insn "\n" \ - "2: " T(str) " %0, [%2]\n" \ + "2: " T(str) " %0, [%3]\n" \ " mov %0, #0\n" \ - __futex_atomic_ex_table("%4") \ - : "=&r" (ret), "=&r" (oldval) \ + __futex_atomic_ex_table("%5") \ + : "=&r" (ret), "=&r" (oldval), "=&r" (tmp) \ : "r" (uaddr), "r" (oparg), "Ir" (-EFAULT) \ : "cc", "memory") @@ -117,7 +117,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) int cmp = (encoded_op >> 24) & 15; int oparg = (encoded_op << 8) >> 20; int cmparg = (encoded_op << 20) >> 20; - int oldval = 0, ret; + int oldval = 0, ret, tmp; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) oparg = 1 << oparg; @@ -129,19 +129,19 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %0, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("mov %0, %4", ret, oldval, tmp, uaddr, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %0, %1, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("add %0, %1, %4", ret, oldval, tmp, uaddr, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %0, %1, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("orr %0, %1, %4", ret, oldval, tmp, uaddr, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %0, %1, %3", ret, oldval, uaddr, ~oparg); + __futex_atomic_op("and %0, %1, %4", ret, oldval, tmp, uaddr, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %0, %1, %3", ret, oldval, uaddr, oparg); + __futex_atomic_op("eor %0, %1, %4", ret, oldval, tmp, uaddr, oparg); break; default: ret = -ENOSYS; diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 2c04ed5..c60a294 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -478,8 +478,8 @@ /* * Unimplemented (or alternatively implemented) syscalls */ -#define __IGNORE_fadvise64_64 1 -#define __IGNORE_migrate_pages 1 +#define __IGNORE_fadvise64_64 +#define __IGNORE_migrate_pages #endif /* __KERNEL__ */ #endif /* __ASM_ARM_UNISTD_H */ diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 79ed5e7..7fcddb7 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -13,6 +13,7 @@ #include <asm/smp_scu.h> #include <asm/cacheflush.h> +#include <asm/cputype.h> #define SCU_CTRL 0x00 #define SCU_CONFIG 0x04 @@ -37,6 +38,15 @@ void __init scu_enable(void __iomem *scu_base) { u32 scu_ctrl; +#ifdef CONFIG_ARM_ERRATA_764369 + /* Cortex-A9 only */ + if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) { + scu_ctrl = __raw_readl(scu_base + 0x30); + if (!(scu_ctrl & 1)) + __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); + } +#endif + scu_ctrl = __raw_readl(scu_base + SCU_CTRL); /* already enabled? */ if (scu_ctrl & 1) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index bf977f8..4e66f62 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -23,8 +23,10 @@ #if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK) #define ARM_EXIT_KEEP(x) x +#define ARM_EXIT_DISCARD(x) #else #define ARM_EXIT_KEEP(x) +#define ARM_EXIT_DISCARD(x) x #endif OUTPUT_ARCH(arm) @@ -39,6 +41,11 @@ jiffies = jiffies_64 + 4; SECTIONS { /* + * XXX: The linker does not define how output sections are + * assigned to input sections when there are multiple statements + * matching the same input section name. There is no documented + * order of matching. + * * unwind exit sections must be discarded before the rest of the * unwind sections get included. */ @@ -47,6 +54,9 @@ SECTIONS *(.ARM.extab.exit.text) ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text)) ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text)) + ARM_EXIT_DISCARD(EXIT_TEXT) + ARM_EXIT_DISCARD(EXIT_DATA) + EXIT_CALL #ifndef CONFIG_HOTPLUG *(.ARM.exidx.devexit.text) *(.ARM.extab.devexit.text) @@ -58,6 +68,8 @@ SECTIONS #ifndef CONFIG_SMP_ON_UP *(.alt.smp.init) #endif + *(.discard) + *(.discard.*) } #ifdef CONFIG_XIP_KERNEL @@ -279,9 +291,6 @@ SECTIONS STABS_DEBUG .comment 0 : { *(.comment) } - - /* Default discards */ - DISCARDS } /* diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 3b24bfa..07c4bc8 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -174,6 +174,10 @@ ENTRY(v7_coherent_user_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r12, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: USER( mcr p15, 0, r12, c7, c11, 1 ) @ clean D line to the point of unification add r12, r12, r2 @@ -223,6 +227,10 @@ ENTRY(v7_flush_kern_dcache_area) add r1, r0, r1 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line / unified line add r0, r0, r2 @@ -247,6 +255,10 @@ v7_dma_inv_range: sub r3, r2, #1 tst r0, r3 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif mcrne p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line tst r1, r3 @@ -270,6 +282,10 @@ v7_dma_clean_range: dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c10, 1 @ clean D / U line add r0, r0, r2 @@ -288,6 +304,10 @@ ENTRY(v7_dma_flush_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 +#ifdef CONFIG_ARM_ERRATA_764369 + ALT_SMP(W(dsb)) + ALT_UP(W(nop)) +#endif 1: mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line add r0, r0, r2 diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 0a0a1e7..c3ff82f 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -324,6 +324,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, if (addr) *handle = pfn_to_dma(dev, page_to_pfn(page)); + else + __dma_free_buffer(page, size); return addr; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 519eb5f..c0cb794 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -658,12 +658,14 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste) * struct gmap_struct - guest address space * @mm: pointer to the parent mm_struct * @table: pointer to the page directory + * @asce: address space control element for gmap page table * @crst_list: list of all crst tables used in the guest address space */ struct gmap { struct list_head list; struct mm_struct *mm; unsigned long *table; + unsigned long asce; struct list_head crst_list; }; diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 532fd43..2b45591 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <asm/vdso.h> #include <asm/sigp.h> +#include <asm/pgtable.h> /* * Make sure that the compiler is new enough. We want a compiler that @@ -126,6 +127,7 @@ int main(void) DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack)); DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack)); DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack)); + DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce)); DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags)); @@ -151,6 +153,7 @@ int main(void) DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data)); DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap)); DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp)); + DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce)); #endif /* CONFIG_32BIT */ return 0; } diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 5f729d6..713da07 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -1076,6 +1076,11 @@ sie_loop: lg %r14,__LC_THREAD_INFO # pointer thread_info struct tm __TI_flags+7(%r14),_TIF_EXIT_SIE jnz sie_exit + lg %r14,__LC_GMAP # get gmap pointer + ltgr %r14,%r14 + jz sie_gmap + lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce +sie_gmap: lg %r14,__SF_EMPTY(%r15) # get control block pointer SPP __SF_EMPTY(%r15) # set guest id sie 0(%r14) @@ -1083,6 +1088,7 @@ sie_done: SPP __LC_CMF_HPP # set host id lg %r14,__LC_THREAD_INFO # pointer thread_info struct sie_exit: + lctlg %c1,%c1,__LC_USER_ASCE # load primary asce ni __TI_flags+6(%r14),255-(_TIF_SIE>>8) lg %r14,__SF_EMPTY+8(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f17296e..dc2b580 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -123,6 +123,7 @@ int kvm_dev_ioctl_check_extension(long ext) switch (ext) { case KVM_CAP_S390_PSW: + case KVM_CAP_S390_GMAP: r = 1; break; default: @@ -263,10 +264,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK; restore_fp_regs(&vcpu->arch.guest_fpregs); restore_access_regs(vcpu->arch.guest_acrs); + gmap_enable(vcpu->arch.gmap); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + gmap_disable(vcpu->arch.gmap); save_fp_regs(&vcpu->arch.guest_fpregs); save_access_regs(vcpu->arch.guest_acrs); restore_fp_regs(&vcpu->arch.host_fpregs); @@ -461,7 +464,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu) local_irq_disable(); kvm_guest_enter(); local_irq_enable(); - gmap_enable(vcpu->arch.gmap); VCPU_EVENT(vcpu, 6, "entering sie flags %x", atomic_read(&vcpu->arch.sie_block->cpuflags)); if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) { @@ -470,7 +472,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu) } VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); - gmap_disable(vcpu->arch.gmap); local_irq_disable(); kvm_guest_exit(); local_irq_enable(); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 4d1f2bc..f69ff3c 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -160,6 +160,8 @@ struct gmap *gmap_alloc(struct mm_struct *mm) table = (unsigned long *) page_to_phys(page); crst_table_init(table, _REGION1_ENTRY_EMPTY); gmap->table = table; + gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | __pa(table); list_add(&gmap->list, &mm->context.gmap_list); return gmap; @@ -240,10 +242,6 @@ EXPORT_SYMBOL_GPL(gmap_free); */ void gmap_enable(struct gmap *gmap) { - /* Load primary space page table origin. */ - S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | __pa(gmap->table); - asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) ); S390_lowcore.gmap = (unsigned long) gmap; } EXPORT_SYMBOL_GPL(gmap_enable); @@ -254,10 +252,6 @@ EXPORT_SYMBOL_GPL(gmap_enable); */ void gmap_disable(struct gmap *gmap) { - /* Load primary space page table origin. */ - S390_lowcore.user_asce = - gmap->mm->context.asce_bits | __pa(gmap->mm->pgd); - asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) ); S390_lowcore.gmap = 0UL; } EXPORT_SYMBOL_GPL(gmap_disable); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 6f08bc9..8b4cc5f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3603,7 +3603,7 @@ done_prefixes: break; case Src2CL: ctxt->src2.bytes = 1; - ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0x8; + ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff; break; case Src2ImmByte: rc = decode_imm(ctxt, &ctxt->src2, 1, true); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 1c5b693..8e8da79 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -400,7 +400,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte) /* xchg acts as a barrier before the setting of the high bits */ orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low); - orig.spte_high = ssptep->spte_high = sspte.spte_high; + orig.spte_high = ssptep->spte_high; + ssptep->spte_high = sspte.spte_high; count_spte_clear(sptep, spte); return orig.spte; diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index f6595ab..fa567f1 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -43,6 +43,7 @@ config TCG_NSC config TCG_ATMEL tristate "Atmel TPM Interface" + depends on PPC64 || HAS_IOPORT ---help--- If you have a TPM security chip from Atmel say Yes and it will be accessible from within Linux. To compile this driver diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c index caf8012..9ca5c02 100644 --- a/drivers/char/tpm/tpm.c +++ b/drivers/char/tpm/tpm.c @@ -383,6 +383,9 @@ static ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf, u32 count, ordinal; unsigned long stop; + if (bufsiz > TPM_BUFSIZE) + bufsiz = TPM_BUFSIZE; + count = be32_to_cpu(*((__be32 *) (buf + 2))); ordinal = be32_to_cpu(*((__be32 *) (buf + 6))); if (count == 0) @@ -1102,6 +1105,7 @@ ssize_t tpm_read(struct file *file, char __user *buf, { struct tpm_chip *chip = file->private_data; ssize_t ret_size; + int rc; del_singleshot_timer_sync(&chip->user_read_timer); flush_work_sync(&chip->work); @@ -1112,8 +1116,11 @@ ssize_t tpm_read(struct file *file, char __user *buf, ret_size = size; mutex_lock(&chip->buffer_mutex); - if (copy_to_user(buf, chip->data_buffer, ret_size)) + rc = copy_to_user(buf, chip->data_buffer, ret_size); + memset(chip->data_buffer, 0, ret_size); + if (rc) ret_size = -EFAULT; + mutex_unlock(&chip->buffer_mutex); } diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c index 82facc9..4d24648 100644 --- a/drivers/char/tpm/tpm_nsc.c +++ b/drivers/char/tpm/tpm_nsc.c @@ -396,8 +396,6 @@ static void __exit cleanup_nsc(void) if (pdev) { tpm_nsc_remove(&pdev->dev); platform_device_unregister(pdev); - kfree(pdev); - pdev = NULL; } platform_driver_unregister(&nsc_drv); diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 5b1837b..7fcdbbb 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -773,8 +773,8 @@ int r100_copy_blit(struct radeon_device *rdev, radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16)); radeon_ring_write(rdev, 0); radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16)); - radeon_ring_write(rdev, cur_pages); - radeon_ring_write(rdev, cur_pages); + radeon_ring_write(rdev, num_gpu_pages); + radeon_ring_write(rdev, num_gpu_pages); radeon_ring_write(rdev, cur_pages | (stride_pixels << 16)); } radeon_ring_write(rdev, PACKET0(RADEON_DSTCACHE_CTLSTAT, 0)); diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index 319d85d..13690f3 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -1507,7 +1507,14 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode) switch (mode) { case DRM_MODE_DPMS_ON: args.ucAction = ATOM_ENABLE; - atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + /* workaround for DVOOutputControl on some RS690 systems */ + if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_DDI) { + u32 reg = RREG32(RADEON_BIOS_3_SCRATCH); + WREG32(RADEON_BIOS_3_SCRATCH, reg & ~ATOM_S3_DFP2I_ACTIVE); + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + WREG32(RADEON_BIOS_3_SCRATCH, reg); + } else + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) { args.ucAction = ATOM_LCD_BLON; atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8d9dae8..3878b73 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -837,6 +837,7 @@ config SCSI_ISCI # (temporary): known alpha quality driver depends on EXPERIMENTAL select SCSI_SAS_LIBSAS + select SCSI_SAS_HOST_SMP ---help--- This driver supports the 6Gb/s SAS capabilities of the storage control unit found in the Intel(R) C600 series chipset. diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 646fc52..8a7591f 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1507,8 +1507,8 @@ qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24) if (k != blocks_done) { qla_printk(KERN_WARNING, sp->fcport->vha->hw, - "unexpected tag values tag:lba=%x:%lx)\n", - e_ref_tag, lba_s); + "unexpected tag values tag:lba=%x:%llx)\n", + e_ref_tag, (unsigned long long)lba_s); return 1; } diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c index d240755..24cacff 100644 --- a/drivers/spi/spi-fsl-spi.c +++ b/drivers/spi/spi-fsl-spi.c @@ -825,6 +825,9 @@ static void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi) { struct device *dev = mspi->dev; + if (!(mspi->flags & SPI_CPM_MODE)) + return; + dma_unmap_single(dev, mspi->dma_dummy_rx, SPI_MRBLR, DMA_FROM_DEVICE); dma_unmap_single(dev, mspi->dma_dummy_tx, PAGE_SIZE, DMA_TO_DEVICE); cpm_muram_free(cpm_muram_offset(mspi->tx_bd)); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 8ac6542..fa594d6 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -786,9 +786,11 @@ static int __devinit spi_imx_probe(struct platform_device *pdev) int cs_gpio = of_get_named_gpio(np, "cs-gpios", i); if (cs_gpio < 0) cs_gpio = mxc_platform_info->chipselect[i]; + + spi_imx->chipselect[i] = cs_gpio; if (cs_gpio < 0) continue; - spi_imx->chipselect[i] = cs_gpio; + ret = gpio_request(spi_imx->chipselect[i], DRIVER_NAME); if (ret) { while (i > 0) { diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c index e0c2807..181fa81 100644 --- a/drivers/zorro/zorro.c +++ b/drivers/zorro/zorro.c @@ -148,10 +148,10 @@ static int __init amiga_zorro_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, bus); - /* Register all devices */ pr_info("Zorro: Probing AutoConfig expansion devices: %u device%s\n", zorro_num_autocon, zorro_num_autocon == 1 ? "" : "s"); + /* First identify all devices ... */ for (i = 0; i < zorro_num_autocon; i++) { z = &zorro_autocon[i]; z->id = (z->rom.er_Manufacturer<<16) | (z->rom.er_Product<<8); @@ -172,6 +172,11 @@ static int __init amiga_zorro_probe(struct platform_device *pdev) dev_set_name(&z->dev, "%02x", i); z->dev.parent = &bus->dev; z->dev.bus = &zorro_bus_type; + } + + /* ... then register them */ + for (i = 0; i < zorro_num_autocon; i++) { + z = &zorro_autocon[i]; error = device_register(&z->dev); if (error) { dev_err(&bus->dev, "Error registering device %s\n", diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 2c366b5..aace6b8 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -553,6 +553,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_SPAPR_TCE 63 #define KVM_CAP_PPC_SMT 64 #define KVM_CAP_PPC_RMA 65 +#define KVM_CAP_S390_GMAP 71 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 9de3ecf..a70d2a5 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -744,20 +744,17 @@ int ptrace_request(struct task_struct *child, long request, break; si = child->last_siginfo; - if (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP)) - break; - - child->jobctl |= JOBCTL_LISTENING; - - /* - * If NOTIFY is set, it means event happened between start - * of this trap and now. Trigger re-trap immediately. - */ - if (child->jobctl & JOBCTL_TRAP_NOTIFY) - signal_wake_up(child, true); - + if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { + child->jobctl |= JOBCTL_LISTENING; + /* + * If NOTIFY is set, it means event happened between + * start of this trap and now. Trigger re-trap. + */ + if (child->jobctl & JOBCTL_TRAP_NOTIFY) + signal_wake_up(child, true); + ret = 0; + } unlock_task_sighand(child, &flags); - ret = 0; break; case PTRACE_DETACH: /* detach a process that was attached. */ diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c index f9123f0..32b02d9 100644 --- a/sound/pci/fm801.c +++ b/sound/pci/fm801.c @@ -68,6 +68,7 @@ MODULE_PARM_DESC(enable, "Enable FM801 soundcard."); module_param_array(tea575x_tuner, int, NULL, 0444); MODULE_PARM_DESC(tea575x_tuner, "TEA575x tuner access method (0 = auto, 1 = SF256-PCS, 2=SF256-PCP, 3=SF64-PCR, 8=disable, +16=tuner-only)."); +#define TUNER_DISABLED (1<<3) #define TUNER_ONLY (1<<4) #define TUNER_TYPE_MASK (~TUNER_ONLY & 0xFFFF) @@ -1150,7 +1151,8 @@ static int snd_fm801_free(struct fm801 *chip) __end_hw: #ifdef CONFIG_SND_FM801_TEA575X_BOOL - snd_tea575x_exit(&chip->tea); + if (!(chip->tea575x_tuner & TUNER_DISABLED)) + snd_tea575x_exit(&chip->tea); #endif if (chip->irq >= 0) free_irq(chip->irq, chip); @@ -1236,7 +1238,6 @@ static int __devinit snd_fm801_create(struct snd_card *card, (tea575x_tuner & TUNER_TYPE_MASK) < 4) { if (snd_tea575x_init(&chip->tea)) { snd_printk(KERN_ERR "TEA575x radio not found\n"); - snd_fm801_free(chip); return -ENODEV; } } else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0) { @@ -1251,11 +1252,15 @@ static int __devinit snd_fm801_create(struct snd_card *card, } if (tea575x_tuner == 4) { snd_printk(KERN_ERR "TEA575x radio not found\n"); - snd_fm801_free(chip); - return -ENODEV; + chip->tea575x_tuner = TUNER_DISABLED; } } - strlcpy(chip->tea.card, snd_fm801_tea575x_gpios[(tea575x_tuner & TUNER_TYPE_MASK) - 1].name, sizeof(chip->tea.card)); + if (!(chip->tea575x_tuner & TUNER_DISABLED)) { + strlcpy(chip->tea.card, + snd_fm801_tea575x_gpios[(tea575x_tuner & + TUNER_TYPE_MASK) - 1].name, + sizeof(chip->tea.card)); + } #endif *rchip = chip; diff --git a/sound/soc/blackfin/bf5xx-ad73311.c b/sound/soc/blackfin/bf5xx-ad73311.c index 732a247..b94eb7e 100644 --- a/sound/soc/blackfin/bf5xx-ad73311.c +++ b/sound/soc/blackfin/bf5xx-ad73311.c @@ -128,7 +128,7 @@ static int snd_ad73311_configure(void) return 0; } -static int bf5xx_probe(struct platform_device *pdev) +static int bf5xx_probe(struct snd_soc_card *card) { int err; if (gpio_request(GPIO_SE, "AD73311_SE")) { diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 1725550..d2c315f 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -3479,31 +3479,6 @@ int wm8962_mic_detect(struct snd_soc_codec *codec, struct snd_soc_jack *jack) } EXPORT_SYMBOL_GPL(wm8962_mic_detect); -#ifdef CONFIG_PM -static int wm8962_resume(struct snd_soc_codec *codec) -{ - u16 *reg_cache = codec->reg_cache; - int i; - - /* Restore the registers */ - for (i = 1; i < codec->driver->reg_cache_size; i++) { - switch (i) { - case WM8962_SOFTWARE_RESET: - continue; - default: - break; - } - - if (reg_cache[i] != wm8962_reg[i]) - snd_soc_write(codec, i, reg_cache[i]); - } - - return 0; -} -#else -#define wm8962_resume NULL -#endif - #if defined(CONFIG_INPUT) || defined(CONFIG_INPUT_MODULE) static int beep_rates[] = { 500, 1000, 2000, 4000, @@ -4015,7 +3990,6 @@ static int wm8962_remove(struct snd_soc_codec *codec) static struct snd_soc_codec_driver soc_codec_dev_wm8962 = { .probe = wm8962_probe, .remove = wm8962_remove, - .resume = wm8962_resume, .set_bias_level = wm8962_set_bias_level, .reg_cache_size = WM8962_MAX_REGISTER + 1, .reg_word_size = sizeof(u16), diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index d2ef014..ef69f5a 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -30,6 +30,7 @@ #include <linux/bitops.h> #include <linux/debugfs.h> #include <linux/platform_device.h> +#include <linux/ctype.h> #include <linux/slab.h> #include <sound/ac97_codec.h> #include <sound/core.h> @@ -1434,9 +1435,20 @@ static void snd_soc_instantiate_card(struct snd_soc_card *card) "%s", card->name); snprintf(card->snd_card->longname, sizeof(card->snd_card->longname), "%s", card->long_name ? card->long_name : card->name); - if (card->driver_name) - strlcpy(card->snd_card->driver, card->driver_name, - sizeof(card->snd_card->driver)); + snprintf(card->snd_card->driver, sizeof(card->snd_card->driver), + "%s", card->driver_name ? card->driver_name : card->name); + for (i = 0; i < ARRAY_SIZE(card->snd_card->driver); i++) { + switch (card->snd_card->driver[i]) { + case '_': + case '-': + case '\0': + break; + default: + if (!isalnum(card->snd_card->driver[i])) + card->snd_card->driver[i] = '_'; + break; + } + } if (card->late_probe) { ret = card->late_probe(card); diff --git a/sound/usb/card.c b/sound/usb/card.c index 781d9e6..ed120ca 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -532,6 +532,7 @@ snd_usb_audio_probe(struct usb_device *dev, __error: if (chip && !chip->num_interfaces) snd_card_free(chip->card); + chip->probing = 0; mutex_unlock(®ister_mutex); __err_val: return NULL; diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 3b8f7b8..e9d5c27 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -30,6 +30,8 @@ endif # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds. # # Define NO_DWARF if you do not want debug-info analysis feature at all. +# +# Define WERROR=0 to disable treating any warnings as errors. $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE @$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT) @@ -63,6 +65,11 @@ ifeq ($(ARCH),x86_64) endif endif +# Treat warnings as errors unless directed not to +ifneq ($(WERROR),0) + CFLAGS_WERROR := -Werror +endif + # # Include saner warnings here, which can catch bugs: # @@ -95,7 +102,7 @@ ifndef PERF_DEBUG CFLAGS_OPTIMIZE = -O6 endif -CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) +CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) EXTLIBS = -lpthread -lrt -lelf -lm ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 ALL_LDFLAGS = $(LDFLAGS) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 6b0519f..f4c3fbe 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -161,6 +161,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist) struct perf_event_attr *attr = &evsel->attr; int track = !evsel->idx; /* only the first counter needs these */ + attr->disabled = 1; attr->inherit = !no_inherit; attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING | @@ -671,6 +672,8 @@ static int __cmd_record(int argc, const char **argv) } } + perf_evlist__enable(evsel_list); + /* * Let the child rip */ diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 55f4c76..efe696f 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -561,7 +561,7 @@ static int test__basic_mmap(void) } err = perf_event__parse_sample(event, attr.sample_type, sample_size, - false, &sample); + false, &sample, false); if (err) { pr_err("Can't parse sample, err = %d\n", err); goto out_munmap; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index a43433f..d28013b 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -191,7 +191,8 @@ static void __zero_source_counters(struct sym_entry *syme) symbol__annotate_zero_histograms(sym); } -static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip) +static void record_precise_ip(struct sym_entry *syme, struct map *map, + int counter, u64 ip) { struct annotation *notes; struct symbol *sym; @@ -205,8 +206,8 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip) if (pthread_mutex_trylock(¬es->lock)) return; - ip = syme->map->map_ip(syme->map, ip); - symbol__inc_addr_samples(sym, syme->map, counter, ip); + ip = map->map_ip(map, ip); + symbol__inc_addr_samples(sym, map, counter, ip); pthread_mutex_unlock(¬es->lock); } @@ -810,7 +811,7 @@ static void perf_event__process_sample(const union perf_event *event, evsel = perf_evlist__id2evsel(top.evlist, sample->id); assert(evsel != NULL); syme->count[evsel->idx]++; - record_precise_ip(syme, evsel->idx, ip); + record_precise_ip(syme, al.map, evsel->idx, ip); pthread_mutex_lock(&top.active_symbols_lock); if (list_empty(&syme->node) || !syme->node.next) { static bool first = true; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 3c1b8a6..437f8ca 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -169,12 +169,17 @@ static int perf_event__synthesize_mmap_events(union perf_event *event, continue; pbf += n + 3; if (*pbf == 'x') { /* vm_exec */ + char anonstr[] = "//anon\n"; char *execname = strchr(bf, '/'); /* Catch VDSO */ if (execname == NULL) execname = strstr(bf, "[vdso]"); + /* Catch anonymous mmaps */ + if ((execname == NULL) && !strstr(bf, "[")) + execname = anonstr; + if (execname == NULL) continue; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 1d7f664..357a85b 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -186,6 +186,6 @@ const char *perf_event__name(unsigned int id); int perf_event__parse_sample(const union perf_event *event, u64 type, int sample_size, bool sample_id_all, - struct perf_sample *sample); + struct perf_sample *sample, bool swapped); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index c12bd47..72e9f48 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -113,6 +113,19 @@ void perf_evlist__disable(struct perf_evlist *evlist) } } +void perf_evlist__enable(struct perf_evlist *evlist) +{ + int cpu, thread; + struct perf_evsel *pos; + + for (cpu = 0; cpu < evlist->cpus->nr; cpu++) { + list_for_each_entry(pos, &evlist->entries, node) { + for (thread = 0; thread < evlist->threads->nr; thread++) + ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE); + } + } +} + int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index ce85ae9..f349150 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -54,6 +54,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); void perf_evlist__disable(struct perf_evlist *evlist); +void perf_evlist__enable(struct perf_evlist *evlist); static inline void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a03a36b..c5748c5 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -7,6 +7,8 @@ * Released under the GPL v2. (and only v2, not any later version) */ +#include <byteswap.h> +#include "asm/bug.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -342,10 +344,20 @@ static bool sample_overlap(const union perf_event *event, int perf_event__parse_sample(const union perf_event *event, u64 type, int sample_size, bool sample_id_all, - struct perf_sample *data) + struct perf_sample *data, bool swapped) { const u64 *array; + /* + * used for cross-endian analysis. See git commit 65014ab3 + * for why this goofiness is needed. + */ + union { + u64 val64; + u32 val32[2]; + } u; + + data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; @@ -366,9 +378,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_TID) { - u32 *p = (u32 *)array; - data->pid = p[0]; - data->tid = p[1]; + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } + + data->pid = u.val32[0]; + data->tid = u.val32[1]; array++; } @@ -395,8 +414,15 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_CPU) { - u32 *p = (u32 *)array; - data->cpu = *p; + + u.val64 = *array; + if (swapped) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + } + + data->cpu = u.val32[0]; array++; } @@ -423,18 +449,24 @@ int perf_event__parse_sample(const union perf_event *event, u64 type, } if (type & PERF_SAMPLE_RAW) { - u32 *p = (u32 *)array; + u.val64 = *array; + if (WARN_ONCE(swapped, + "Endianness of raw data not corrected!\n")) { + /* undo swap of u64, then swap on individual u32s */ + u.val64 = bswap_64(u.val64); + u.val32[0] = bswap_32(u.val32[0]); + u.val32[1] = bswap_32(u.val32[1]); + } if (sample_overlap(event, array, sizeof(u32))) return -EFAULT; - data->raw_size = *p; - p++; + data->raw_size = u.val32[0]; - if (sample_overlap(event, p, data->raw_size)) + if (sample_overlap(event, &u.val32[1], data->raw_size)) return -EFAULT; - data->raw_data = p; + data->raw_data = &u.val32[1]; } return 0; diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 555fc38..5d73262 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -659,7 +659,7 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) ret = -ENOENT; } - if (ret == 0) + if (ret >= 0) ret = convert_variable(&vr_die, pf); if (ret < 0) diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index cbc8f21..7624324 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -803,7 +803,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, first = list_entry(evlist->entries.next, struct perf_evsel, node); err = perf_event__parse_sample(event, first->attr.sample_type, perf_evsel__sample_size(first), - sample_id_all, &pevent->sample); + sample_id_all, &pevent->sample, false); if (err) return PyErr_Format(PyExc_OSError, "perf: can't parse sample, err=%d", err); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 170601e..974d0cb 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -162,7 +162,8 @@ static inline int perf_session__parse_sample(struct perf_session *session, { return perf_event__parse_sample(event, session->sample_type, session->sample_size, - session->sample_id_all, sample); + session->sample_id_all, sample, + session->header.needs_swap); } struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 401e220..1ee8f1e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -151,11 +151,17 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right) { u64 ip_l, ip_r; + if (!left->ms.sym && !right->ms.sym) + return right->level - left->level; + + if (!left->ms.sym || !right->ms.sym) + return cmp_null(left->ms.sym, right->ms.sym); + if (left->ms.sym == right->ms.sym) return 0; - ip_l = left->ms.sym ? left->ms.sym->start : left->ip; - ip_r = right->ms.sym ? right->ms.sym->start : right->ip; + ip_l = left->ms.sym->start; + ip_r = right->ms.sym->start; return (int64_t)(ip_r - ip_l); } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 469c026..40eeaf0 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -74,16 +74,104 @@ static void dso__set_sorted_by_name(struct dso *dso, enum map_type type) bool symbol_type__is_a(char symbol_type, enum map_type map_type) { + symbol_type = toupper(symbol_type); + switch (map_type) { case MAP__FUNCTION: return symbol_type == 'T' || symbol_type == 'W'; case MAP__VARIABLE: - return symbol_type == 'D' || symbol_type == 'd'; + return symbol_type == 'D'; default: return false; } } +static int prefix_underscores_count(const char *str) +{ + const char *tail = str; + + while (*tail == '_') + tail++; + + return tail - str; +} + +#define SYMBOL_A 0 +#define SYMBOL_B 1 + +static int choose_best_symbol(struct symbol *syma, struct symbol *symb) +{ + s64 a; + s64 b; + + /* Prefer a symbol with non zero length */ + a = syma->end - syma->start; + b = symb->end - symb->start; + if ((b == 0) && (a > 0)) + return SYMBOL_A; + else if ((a == 0) && (b > 0)) + return SYMBOL_B; + + /* Prefer a non weak symbol over a weak one */ + a = syma->binding == STB_WEAK; + b = symb->binding == STB_WEAK; + if (b && !a) + return SYMBOL_A; + if (a && !b) + return SYMBOL_B; + + /* Prefer a global symbol over a non global one */ + a = syma->binding == STB_GLOBAL; + b = symb->binding == STB_GLOBAL; + if (a && !b) + return SYMBOL_A; + if (b && !a) + return SYMBOL_B; + + /* Prefer a symbol with less underscores */ + a = prefix_underscores_count(syma->name); + b = prefix_underscores_count(symb->name); + if (b > a) + return SYMBOL_A; + else if (a > b) + return SYMBOL_B; + + /* If all else fails, choose the symbol with the longest name */ + if (strlen(syma->name) >= strlen(symb->name)) + return SYMBOL_A; + else + return SYMBOL_B; +} + +static void symbols__fixup_duplicate(struct rb_root *symbols) +{ + struct rb_node *nd; + struct symbol *curr, *next; + + nd = rb_first(symbols); + + while (nd) { + curr = rb_entry(nd, struct symbol, rb_node); +again: + nd = rb_next(&curr->rb_node); + next = rb_entry(nd, struct symbol, rb_node); + + if (!nd) + break; + + if (curr->start != next->start) + continue; + + if (choose_best_symbol(curr, next) == SYMBOL_A) { + rb_erase(&next->rb_node, symbols); + goto again; + } else { + nd = rb_next(&curr->rb_node); + rb_erase(&curr->rb_node, symbols); + } + } +} + static void symbols__fixup_end(struct rb_root *symbols) { struct rb_node *nd, *prevnd = rb_first(symbols); @@ -438,18 +526,11 @@ int kallsyms__parse(const char *filename, void *arg, char *line = NULL; size_t n; int err = -1; - u64 prev_start = 0; - char prev_symbol_type = 0; - char *prev_symbol_name; FILE *file = fopen(filename, "r"); if (file == NULL) goto out_failure; - prev_symbol_name = malloc(KSYM_NAME_LEN); - if (prev_symbol_name == NULL) - goto out_close; - err = 0; while (!feof(file)) { @@ -470,7 +551,7 @@ int kallsyms__parse(const char *filename, void *arg, if (len + 2 >= line_len) continue; - symbol_type = toupper(line[len]); + symbol_type = line[len]; len += 2; symbol_name = line + len; len = line_len - len; @@ -480,24 +561,18 @@ int kallsyms__parse(const char *filename, void *arg, break; } - if (prev_symbol_type) { - u64 end = start; - if (end != prev_start) - --end; - err = process_symbol(arg, prev_symbol_name, - prev_symbol_type, prev_start, end); - if (err) - break; - } - - memcpy(prev_symbol_name, symbol_name, len + 1); - prev_symbol_type = symbol_type; - prev_start = start; + /* + * module symbols are not sorted so we add all + * symbols with zero length and rely on + * symbols__fixup_end() to fix it up. + */ + err = process_symbol(arg, symbol_name, + symbol_type, start, start); + if (err) + break; } - free(prev_symbol_name); free(line); -out_close: fclose(file); return err; @@ -703,6 +778,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, if (dso__load_all_kallsyms(dso, filename, map) < 0) return -1; + symbols__fixup_duplicate(&dso->symbols[map->type]); + symbols__fixup_end(&dso->symbols[map->type]); + if (dso->kernel == DSO_TYPE_GUEST_KERNEL) dso->symtab_type = SYMTAB__GUEST_KALLSYMS; else @@ -1092,8 +1170,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name, if (dso->has_build_id) { u8 build_id[BUILD_ID_SIZE]; - if (elf_read_build_id(elf, build_id, - BUILD_ID_SIZE) != BUILD_ID_SIZE) + if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0) goto out_elf_end; if (!dso__build_id_equal(dso, build_id)) @@ -1111,6 +1188,8 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name, } opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx); + if (opdshdr.sh_type != SHT_PROGBITS) + opdsec = NULL; if (opdsec) opddata = elf_rawdata(opdsec, NULL); @@ -1276,6 +1355,7 @@ new_symbol: * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { + symbols__fixup_duplicate(&dso->symbols[map->type]); symbols__fixup_end(&dso->symbols[map->type]); if (kmap) { /* @@ -1362,8 +1442,8 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) ptr = data->d_buf; while (ptr < (data->d_buf + data->d_size)) { GElf_Nhdr *nhdr = ptr; - int namesz = NOTE_ALIGN(nhdr->n_namesz), - descsz = NOTE_ALIGN(nhdr->n_descsz); + size_t namesz = NOTE_ALIGN(nhdr->n_namesz), + descsz = NOTE_ALIGN(nhdr->n_descsz); const char *name; ptr += sizeof(*nhdr); @@ -1372,8 +1452,10 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) if (nhdr->n_type == NT_GNU_BUILD_ID && nhdr->n_namesz == sizeof("GNU")) { if (memcmp(name, "GNU", sizeof("GNU")) == 0) { - memcpy(bf, ptr, BUILD_ID_SIZE); - err = BUILD_ID_SIZE; + size_t sz = min(size, descsz); + memcpy(bf, ptr, sz); + memset(bf + sz, 0, size - sz); + err = descsz; break; } } @@ -1425,7 +1507,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) while (1) { char bf[BUFSIZ]; GElf_Nhdr nhdr; - int namesz, descsz; + size_t namesz, descsz; if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr)) break; @@ -1434,15 +1516,16 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size) descsz = NOTE_ALIGN(nhdr.n_descsz); if (nhdr.n_type == NT_GNU_BUILD_ID && nhdr.n_namesz == sizeof("GNU")) { - if (read(fd, bf, namesz) != namesz) + if (read(fd, bf, namesz) != (ssize_t)namesz) break; if (memcmp(bf, "GNU", sizeof("GNU")) == 0) { - if (read(fd, build_id, - BUILD_ID_SIZE) == BUILD_ID_SIZE) { + size_t sz = min(descsz, size); + if (read(fd, build_id, sz) == (ssize_t)sz) { + memset(build_id + sz, 0, size - sz); err = 0; break; } - } else if (read(fd, bf, descsz) != descsz) + } else if (read(fd, bf, descsz) != (ssize_t)descsz) break; } else { int n = namesz + descsz; |
