diff options
96 files changed, 3878 insertions, 1507 deletions
@@ -1468,6 +1468,13 @@ kernelrelease: kernelversion: @echo $(KERNELVERSION) +# Clear a bunch of variables before executing the submake +tools/: FORCE + $(Q)$(MAKE) LDFLAGS= MAKEFLAGS= -C $(src)/tools/ + +tools/%: FORCE + $(Q)$(MAKE) LDFLAGS= MAKEFLAGS= -C $(src)/tools/ $* + # Single targets # --------------------------------------------------------------------------- # Single targets are compatible with: diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index 0dae252f7a33..d821b17047e0 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -824,7 +824,6 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, idx = la_ptr; - perf_sample_data_init(&data, 0); for (j = 0; j < cpuc->n_events; j++) { if (cpuc->current_idx[j] == idx) break; @@ -848,7 +847,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, hwc = &event->hw; alpha_perf_event_update(event, hwc, idx, alpha_pmu->pmc_max_period[idx]+1); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (alpha_perf_event_set_period(event, hwc, idx)) { if (perf_event_overflow(event, &data, regs)) { diff --git a/arch/arm/configs/bcmring_defconfig b/arch/arm/configs/bcmring_defconfig index 795374d48f81..9e6a8fe13164 100644 --- a/arch/arm/configs/bcmring_defconfig +++ b/arch/arm/configs/bcmring_defconfig @@ -11,7 +11,7 @@ CONFIG_KALLSYMS_EXTRA_PASS=y # CONFIG_TIMERFD is not set # CONFIG_EVENTFD is not set # CONFIG_AIO is not set -CONFIG_PERF_COUNTERS=y +CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index b78af0cc6ef3..ab627a740fa3 100644 --- a/arch/arm/kernel/perf_event_v6.c +++ b/arch/arm/kernel/perf_event_v6.c @@ -489,8 +489,6 @@ armv6pmu_handle_irq(int irq_num, */ armv6_pmcr_write(pmcr); - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; @@ -509,7 +507,7 @@ armv6pmu_handle_irq(int irq_num, hwc = &event->hw; armpmu_event_update(event, hwc, idx); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (!armpmu_event_set_period(event, hwc, idx)) continue; diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 00755d82e2f2..d3c536068162 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -1077,8 +1077,6 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; @@ -1097,7 +1095,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) hwc = &event->hw; armpmu_event_update(event, hwc, idx); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (!armpmu_event_set_period(event, hwc, idx)) continue; diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c index 71a21e6712f5..e34e7254e652 100644 --- a/arch/arm/kernel/perf_event_xscale.c +++ b/arch/arm/kernel/perf_event_xscale.c @@ -248,8 +248,6 @@ xscale1pmu_handle_irq(int irq_num, void *dev) regs = get_irq_regs(); - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; @@ -263,7 +261,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev) hwc = &event->hw; armpmu_event_update(event, hwc, idx); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (!armpmu_event_set_period(event, hwc, idx)) continue; @@ -588,8 +586,6 @@ xscale2pmu_handle_irq(int irq_num, void *dev) regs = get_irq_regs(); - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; @@ -603,7 +599,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev) hwc = &event->hw; armpmu_event_update(event, hwc, idx); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (!armpmu_event_set_period(event, hwc, idx)) continue; diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 811084f4e422..ab73fa2fb9b5 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -1325,7 +1325,7 @@ static int mipsxx_pmu_handle_shared_irq(void) regs = get_irq_regs(); - perf_sample_data_init(&data, 0); + perf_sample_data_init(&data, 0, 0); switch (counters) { #define HANDLE_COUNTER(n) \ diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig index f104ccde6b53..b1f9597fe312 100644 --- a/arch/powerpc/configs/chroma_defconfig +++ b/arch/powerpc/configs/chroma_defconfig @@ -32,7 +32,7 @@ CONFIG_RD_LZMA=y CONFIG_INITRAMFS_COMPRESSION_GZIP=y CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y -CONFIG_PERF_COUNTERS=y +CONFIG_PERF_EVENTS=y CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_KPROBES=y diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig index e74d3a483705..9ef2cc13e1b4 100644 --- a/arch/powerpc/configs/gamecube_defconfig +++ b/arch/powerpc/configs/gamecube_defconfig @@ -8,7 +8,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_EXPERT=y # CONFIG_ELF_CORE is not set -CONFIG_PERF_COUNTERS=y +CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index 175295fbf4f3..1e2b7d062aa4 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -9,7 +9,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_EXPERT=y # CONFIG_ELF_CORE is not set -CONFIG_PERF_COUNTERS=y +CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 02aee03e713c..8f84bcba18da 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1299,8 +1299,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (record) { struct perf_sample_data data; - perf_sample_data_init(&data, ~0ULL); - data.period = event->hw.last_period; + perf_sample_data_init(&data, ~0ULL, event->hw.last_period); if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c index 0a6d2a9d569c..106c53354675 100644 --- a/arch/powerpc/perf/core-fsl-emb.c +++ b/arch/powerpc/perf/core-fsl-emb.c @@ -613,8 +613,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (record) { struct perf_sample_data data; - perf_sample_data_init(&data, 0); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, event->hw.last_period); if (perf_event_overflow(event, &data, regs)) fsl_emb_pmu_stop(event, 0); diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig index 7b9c696ac5e0..9bdcf72ec06a 100644 --- a/arch/sh/configs/sh7785lcr_32bit_defconfig +++ b/arch/sh/configs/sh7785lcr_32bit_defconfig @@ -5,7 +5,7 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 -CONFIG_PERF_COUNTERS=y +CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y CONFIG_PROFILING=y diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 3c1e85807403..9d8521b8c854 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -5,7 +5,7 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_BLK_DEV_INITRD=y -CONFIG_PERF_COUNTERS=y +CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y CONFIG_PROFILING=y diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 28559ce5eeb5..5713957dcb8a 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1296,8 +1296,6 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, regs = args->regs; - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); /* If the PMU has the TOE IRQ enable bits, we need to do a @@ -1321,7 +1319,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, if (val & (1ULL << 31)) continue; - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (!sparc_perf_event_set_period(event, hwc, idx)) continue; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d14cc6b79ad..1324139612e1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -40,7 +40,6 @@ config X86 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_FUNCTION_TRACE_MCOUNT_TEST - select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE select HAVE_SYSCALL_TRACEPOINTS select HAVE_KVM select HAVE_ARCH_KGDB diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 268c783ab1c0..18d9005d9e4f 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -34,6 +34,7 @@ #ifndef __ASSEMBLY__ extern void mcount(void); +extern int modifying_ftrace_code; static inline unsigned long ftrace_call_adjust(unsigned long addr) { @@ -50,6 +51,8 @@ struct dyn_arch_ftrace { /* No extra data needed for x86 */ }; +int ftrace_int3_handler(struct pt_regs *regs); + #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ccb805966f68..957ec87385af 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -134,6 +134,8 @@ #define MSR_AMD64_IBSFETCHCTL 0xc0011030 #define MSR_AMD64_IBSFETCHLINAD 0xc0011031 #define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032 +#define MSR_AMD64_IBSFETCH_REG_COUNT 3 +#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1) #define MSR_AMD64_IBSOPCTL 0xc0011033 #define MSR_AMD64_IBSOPRIP 0xc0011034 #define MSR_AMD64_IBSOPDATA 0xc0011035 @@ -141,8 +143,11 @@ #define MSR_AMD64_IBSOPDATA3 0xc0011037 #define MSR_AMD64_IBSDCLINAD 0xc0011038 #define MSR_AMD64_IBSDCPHYSAD 0xc0011039 +#define MSR_AMD64_IBSOP_REG_COUNT 7 +#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1) #define MSR_AMD64_IBSCTL 0xc001103a #define MSR_AMD64_IBSBRTARGET 0xc001103b +#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ /* Fam 15h MSRs */ #define MSR_F15H_PERF_CTL 0xc0010200 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 2291895b1836..588f52ea810e 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -158,6 +158,7 @@ struct x86_pmu_capability { #define IBS_CAPS_OPCNT (1U<<4) #define IBS_CAPS_BRNTRGT (1U<<5) #define IBS_CAPS_OPCNTEXT (1U<<6) +#define IBS_CAPS_RIPINVALIDCHK (1U<<7) #define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ | IBS_CAPS_FETCHSAM \ @@ -170,21 +171,28 @@ struct x86_pmu_capability { #define IBSCTL_LVT_OFFSET_VALID (1ULL<<8) #define IBSCTL_LVT_OFFSET_MASK 0x0F -/* IbsFetchCtl bits/masks */ +/* ibs fetch bits/masks */ #define IBS_FETCH_RAND_EN (1ULL<<57) #define IBS_FETCH_VAL (1ULL<<49) #define IBS_FETCH_ENABLE (1ULL<<48) #define IBS_FETCH_CNT 0xFFFF0000ULL #define IBS_FETCH_MAX_CNT 0x0000FFFFULL -/* IbsOpCtl bits */ +/* ibs op bits/masks */ +/* lower 4 bits of the current count are ignored: */ +#define IBS_OP_CUR_CNT (0xFFFF0ULL<<32) #define IBS_OP_CNT_CTL (1ULL<<19) #define IBS_OP_VAL (1ULL<<18) #define IBS_OP_ENABLE (1ULL<<17) #define IBS_OP_MAX_CNT 0x0000FFFFULL #define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ +#define IBS_RIP_INVALID (1ULL<<38) +#ifdef CONFIG_X86_LOCAL_APIC extern u32 get_ibs_caps(void); +#else +static inline u32 get_ibs_caps(void) { return 0; } +#endif #ifdef CONFIG_PERF_EVENTS extern void perf_events_lapic_init(void); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index bb8e03407e18..e049d6da0183 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -484,9 +484,6 @@ static int __x86_pmu_event_init(struct perf_event *event) /* mark unused */ event->hw.extra_reg.idx = EXTRA_REG_NONE; - - /* mark not used */ - event->hw.extra_reg.idx = EXTRA_REG_NONE; event->hw.branch_reg.idx = EXTRA_REG_NONE; return x86_pmu.hw_config(event); @@ -1186,8 +1183,6 @@ int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); /* @@ -1222,7 +1217,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) * event overflow */ handled++; - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, event->hw.last_period); if (!x86_perf_event_set_period(event)) continue; diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 95e7fe1c5f0b..65652265fffd 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -134,8 +134,13 @@ static u64 amd_pmu_event_map(int hw_event) static int amd_pmu_hw_config(struct perf_event *event) { - int ret = x86_pmu_hw_config(event); + int ret; + /* pass precise event sampling to ibs: */ + if (event->attr.precise_ip && get_ibs_caps()) + return -ENOENT; + + ret = x86_pmu_hw_config(event); if (ret) return ret; @@ -205,10 +210,8 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc, * when we come here */ for (i = 0; i < x86_pmu.num_counters; i++) { - if (nb->owners[i] == event) { - cmpxchg(nb->owners+i, event, NULL); + if (cmpxchg(nb->owners + i, event, NULL) == event) break; - } } } diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 3b8a2d30d14e..da9bcdcd9856 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -9,6 +9,7 @@ #include <linux/perf_event.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/ptrace.h> #include <asm/apic.h> @@ -16,36 +17,591 @@ static u32 ibs_caps; #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) -static struct pmu perf_ibs; +#include <linux/kprobes.h> +#include <linux/hardirq.h> + +#include <asm/nmi.h> + +#define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT) +#define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT + +enum ibs_states { + IBS_ENABLED = 0, + IBS_STARTED = 1, + IBS_STOPPING = 2, + + IBS_MAX_STATES, +}; + +struct cpu_perf_ibs { + struct perf_event *event; + unsigned long state[BITS_TO_LONGS(IBS_MAX_STATES)]; +}; + +struct perf_ibs { + struct pmu pmu; + unsigned int msr; + u64 config_mask; + u64 cnt_mask; + u64 enable_mask; + u64 valid_mask; + u64 max_period; + unsigned long offset_mask[1]; + int offset_max; + struct cpu_perf_ibs __percpu *pcpu; + u64 (*get_count)(u64 config); +}; + +struct perf_ibs_data { + u32 size; + union { + u32 data[0]; /* data buffer starts here */ + u32 caps; + }; + u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX]; +}; + +static int +perf_event_set_period(struct hw_perf_event *hwc, u64 min, u64 max, u64 *hw_period) +{ + s64 left = local64_read(&hwc->period_left); + s64 period = hwc->sample_period; + int overflow = 0; + + /* + * If we are way outside a reasonable range then just skip forward: + */ + if (unlikely(left <= -period)) { + left = period; + local64_set(&hwc->period_left, left); + hwc->last_period = period; + overflow = 1; + } + + if (unlikely(left < (s64)min)) { + left += period; + local64_set(&hwc->period_left, left); + hwc->last_period = period; + overflow = 1; + } + + /* + * If the hw period that triggers the sw overflow is too short + * we might hit the irq handler. This biases the results. + * Thus we shorten the next-to-last period and set the last + * period to the max period. + */ + if (left > max) { + left -= max; + if (left > max) + left = max; + else if (left < min) + left = min; + } + + *hw_period = (u64)left; + + return overflow; +} + +static int +perf_event_try_update(struct perf_event *event, u64 new_raw_count, int width) +{ + struct hw_perf_event *hwc = &event->hw; + int shift = 64 - width; + u64 prev_raw_count; + u64 delta; + + /* + * Careful: an NMI might modify the previous event value. + * + * Our tactic to handle this is to first atomically read and + * exchange a new raw count - then add that new-prev delta + * count to the generic event atomically: + */ + prev_raw_count = local64_read(&hwc->prev_count); + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) + return 0; + + /* + * Now we have the new raw value and have updated the prev + * timestamp already. We can now calculate the elapsed delta + * (event-)time and add that to the generic event. + * + * Careful, not all hw sign-extends above the physical width + * of the count. + */ + delta = (new_raw_count << shift) - (prev_raw_count << shift); + delta >>= shift; + + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); + + return 1; +} + +static struct perf_ibs perf_ibs_fetch; +static struct perf_ibs perf_ibs_op; + +static struct perf_ibs *get_ibs_pmu(int type) +{ + if (perf_ibs_fetch.pmu.type == type) + return &perf_ibs_fetch; + if (perf_ibs_op.pmu.type == type) + return &perf_ibs_op; + return NULL; +} + +/* + * Use IBS for precise event sampling: + * + * perf record -a -e cpu-cycles:p ... # use ibs op counting cycle count + * perf record -a -e r076:p ... # same as -e cpu-cycles:p + * perf record -a -e r0C1:p ... # use ibs op counting micro-ops + * + * IbsOpCntCtl (bit 19) of IBS Execution Control Register (IbsOpCtl, + * MSRC001_1033) is used to select either cycle or micro-ops counting + * mode. + * + * The rip of IBS samples has skid 0. Thus, IBS supports precise + * levels 1 and 2 and the PERF_EFLAGS_EXACT is set. In rare cases the + * rip is invalid when IBS was not able to record the rip correctly. + * We clear PERF_EFLAGS_EXACT and take the rip from pt_regs then. + * + */ +static int perf_ibs_precise_event(struct perf_event *event, u64 *config) +{ + switch (event->attr.precise_ip) { + case 0: + return -ENOENT; + case 1: + case 2: + break; + default: + return -EOPNOTSUPP; + } + + switch (event->attr.type) { + case PERF_TYPE_HARDWARE: + switch (event->attr.config) { + case PERF_COUNT_HW_CPU_CYCLES: + *config = 0; + return 0; + } + break; + case PERF_TYPE_RAW: + switch (event->attr.config) { + case 0x0076: + *config = 0; + return 0; + case 0x00C1: + *config = IBS_OP_CNT_CTL; + return 0; + } + break; + default: + return -ENOENT; + } + + return -EOPNOTSUPP; +} static int perf_ibs_init(struct perf_event *event) { - if (perf_ibs.type != event->attr.type) + struct hw_perf_event *hwc = &event->hw; + struct perf_ibs *perf_ibs; + u64 max_cnt, config; + int ret; + + perf_ibs = get_ibs_pmu(event->attr.type); + if (perf_ibs) { + config = event->attr.config; + } else { + perf_ibs = &perf_ibs_op; + ret = perf_ibs_precise_event(event, &config); + if (ret) + return ret; + } + + if (event->pmu != &perf_ibs->pmu) return -ENOENT; + + if (config & ~perf_ibs->config_mask) + return -EINVAL; + + if (hwc->sample_period) { + if (config & perf_ibs->cnt_mask) + /* raw max_cnt may not be set */ + return -EINVAL; + if (!event->attr.sample_freq && hwc->sample_period & 0x0f) + /* + * lower 4 bits can not be set in ibs max cnt, + * but allowing it in case we adjust the + * sample period to set a frequency. + */ + return -EINVAL; + hwc->sample_period &= ~0x0FULL; + if (!hwc->sample_period) + hwc->sample_period = 0x10; + } else { + max_cnt = config & perf_ibs->cnt_mask; + config &= ~perf_ibs->cnt_mask; + event->attr.sample_period = max_cnt << 4; + hwc->sample_period = event->attr.sample_period; + } + + if (!hwc->sample_period) + return -EINVAL; + + /* + * If we modify hwc->sample_period, we also need to update + * hwc->last_period and hwc->period_left. + */ + hwc->last_period = hwc->sample_period; + local64_set(&hwc->period_left, hwc->sample_period); + + hwc->config_base = perf_ibs->msr; + hwc->config = config; + return 0; } +static int perf_ibs_set_period(struct perf_ibs *perf_ibs, + struct hw_perf_event *hwc, u64 *period) +{ + int overflow; + + /* ignore lower 4 bits in min count: */ + overflow = perf_event_set_period(hwc, 1<<4, perf_ibs->max_period, period); + local64_set(&hwc->prev_count, 0); + + return overflow; +} + +static u64 get_ibs_fetch_count(u64 config) +{ + return (config & IBS_FETCH_CNT) >> 12; +} + +static u64 get_ibs_op_count(u64 config) +{ + u64 count = 0; + + if (config & IBS_OP_VAL) + count += (config & IBS_OP_MAX_CNT) << 4; /* cnt rolled over */ + + if (ibs_caps & IBS_CAPS_RDWROPCNT) + count += (config & IBS_OP_CUR_CNT) >> 32; + + return count; +} + +static void +perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event, + u64 *config) +{ + u64 count = perf_ibs->get_count(*config); + + /* + * Set width to 64 since we do not overflow on max width but + * instead on max count. In perf_ibs_set_period() we clear + * prev count manually on overflow. + */ + while (!perf_event_try_update(event, count, 64)) { + rdmsrl(event->hw.config_base, *config); + count = perf_ibs->get_count(*config); + } +} + +static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs, + struct hw_perf_event *hwc, u64 config) +{ + wrmsrl(hwc->config_base, hwc->config | config | perf_ibs->enable_mask); +} + +/* + * Erratum #420 Instruction-Based Sampling Engine May Generate + * Interrupt that Cannot Be Cleared: + * + * Must clear counter mask first, then clear the enable bit. See + * Revision Guide for AMD Family 10h Processors, Publication #41322. + */ +static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, + struct hw_perf_event *hwc, u64 config) +{ + config &= ~perf_ibs->cnt_mask; + wrmsrl(hwc->config_base, config); + config &= ~perf_ibs->enable_mask; + wrmsrl(hwc->config_base, config); +} + +/* + * We cannot restore the ibs pmu state, so we always needs to update + * the event while stopping it and then reset the state when starting + * again. Thus, ignoring PERF_EF_RELOAD and PERF_EF_UPDATE flags in + * perf_ibs_start()/perf_ibs_stop() and instead always do it. + */ +static void perf_ibs_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu); + struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); + u64 period; + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + hwc->state = 0; + + perf_ibs_set_period(perf_ibs, hwc, &period); + set_bit(IBS_STARTED, pcpu->state); + perf_ibs_enable_event(perf_ibs, hwc, period >> 4); + + perf_event_update_userpage(event); +} + +static void perf_ibs_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu); + struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); + u64 config; + int stopping; + + stopping = test_and_clear_bit(IBS_STARTED, pcpu->state); + + if (!stopping && (hwc->state & PERF_HES_UPTODATE)) + return; + + rdmsrl(hwc->config_base, config); + + if (stopping) { + set_bit(IBS_STOPPING, pcpu->state); + perf_ibs_disable_event(perf_ibs, hwc, config); + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + } + + if (hwc->state & PERF_HES_UPTODATE) + return; + + /* + * Clear valid bit to not count rollovers on update, rollovers + * are only updated in the irq handler. + */ + config &= ~perf_ibs->valid_mask; + + perf_ibs_event_update(perf_ibs, event, &config); + hwc->state |= PERF_HES_UPTODATE; +} + static int perf_ibs_add(struct perf_event *event, int flags) { + struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu); + struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); + + if (test_and_set_bit(IBS_ENABLED, pcpu->state)) + return -ENOSPC; + + event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + pcpu->event = event; + + if (flags & PERF_EF_START) + perf_ibs_start(event, PERF_EF_RELOAD); + return 0; } static void perf_ibs_del(struct perf_event *event, int flags) { + struct perf_ibs *perf_ibs = container_of(event->pmu, struct perf_ibs, pmu); + struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); + + if (!test_and_clear_bit(IBS_ENABLED, pcpu->state)) + return; + + perf_ibs_stop(event, PERF_EF_UPDATE); + + pcpu->event = NULL; + + perf_event_update_userpage(event); } -static struct pmu perf_ibs = { - .event_init= perf_ibs_init, - .add= perf_ibs_add, - .del= perf_ibs_del, +static void perf_ibs_read(struct perf_event *event) { } + +static struct perf_ibs perf_ibs_fetch = { + .pmu = { + .task_ctx_nr = perf_invalid_context, + + .event_init = perf_ibs_init, + .add = perf_ibs_add, + .del = perf_ibs_del, + .start = perf_ibs_start, + .stop = perf_ibs_stop, + .read = perf_ibs_read, + }, + .msr = MSR_AMD64_IBSFETCHCTL, + .config_mask = IBS_FETCH_CONFIG_MASK, + .cnt_mask = IBS_FETCH_MAX_CNT, + .enable_mask = IBS_FETCH_ENABLE, + .valid_mask = IBS_FETCH_VAL, + .max_period = IBS_FETCH_MAX_CNT << 4, + .offset_mask = { MSR_AMD64_IBSFETCH_REG_MASK }, + .offset_max = MSR_AMD64_IBSFETCH_REG_COUNT, + + .get_count = get_ibs_fetch_count, }; +static struct perf_ibs perf_ibs_op = { + .pmu = { + .task_ctx_nr = perf_invalid_context, + + .event_init = perf_ibs_init, + .add = perf_ibs_add, + .del = perf_ibs_del, + .start = perf_ibs_start, + .stop = perf_ibs_stop, + .read = perf_ibs_read, + }, + .msr = MSR_AMD64_IBSOPCTL, + .config_mask = IBS_OP_CONFIG_MASK, + .cnt_mask = IBS_OP_MAX_CNT, + .enable_mask = IBS_OP_ENABLE, + .valid_mask = IBS_OP_VAL, + .max_period = IBS_OP_MAX_CNT << 4, + .offset_mask = { MSR_AMD64_IBSOP_REG_MASK }, + .offset_max = MSR_AMD64_IBSOP_REG_COUNT, + + .get_count = get_ibs_op_count, +}; + +static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) +{ + struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); + struct perf_event *event = pcpu->event; + struct hw_perf_event *hwc = &event->hw; + struct perf_sample_data data; + struct perf_raw_record raw; + struct pt_regs regs; + struct perf_ibs_data ibs_data; + int offset, size, check_rip, offset_max, throttle = 0; + unsigned int msr; + u64 *buf, *config, period; + + if (!test_bit(IBS_STARTED, pcpu->state)) { + /* + * Catch spurious interrupts after stopping IBS: After + * disabling IBS there could be still incomming NMIs + * with samples that even have the valid bit cleared. + * Mark all this NMIs as handled. + */ + return test_and_clear_bit(IBS_STOPPING, pcpu->state) ? 1 : 0; + } + + msr = hwc->config_base; + buf = ibs_data.regs; + rdmsrl(msr, *buf); + if (!(*buf++ & perf_ibs->valid_mask)) + return 0; + + config = &ibs_data.regs[0]; + perf_ibs_event_update(perf_ibs, event, config); + perf_sample_data_init(&data, 0, hwc->last_period); + if (!perf_ibs_set_period(perf_ibs, hwc, &period)) + goto out; /* no sw counter overflow */ + + ibs_data.caps = ibs_caps; + size = 1; + offset = 1; + check_rip = (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_RIPINVALIDCHK)); + if (event->attr.sample_type & PERF_SAMPLE_RAW) + offset_max = perf_ibs->offset_max; + else if (check_rip) + offset_max = 2; + else + offset_max = 1; + do { + rdmsrl(msr + offset, *buf++); + size++; + offset = find_next_bit(perf_ibs->offset_mask, + perf_ibs->offset_max, + offset + 1); + } while (offset < offset_max); + ibs_data.size = sizeof(u64) * size; + + regs = *iregs; + if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) { + regs.flags &= ~PERF_EFLAGS_EXACT; + } else { + instruction_pointer_set(®s, ibs_data.regs[1]); + regs.flags |= PERF_EFLAGS_EXACT; + } + + if (event->attr.sample_type & PERF_SAMPLE_RAW) { + raw.size = sizeof(u32) + ibs_data.size; + raw.data = ibs_data.data; + data.raw = &raw; + } + + throttle = perf_event_overflow(event, &data, ®s); +out: + if (throttle) + perf_ibs_disable_event(perf_ibs, hwc, *config); + else + perf_ibs_enable_event(perf_ibs, hwc, period >> 4); + + perf_event_update_userpage(event); + + return 1; +} + +static int __kprobes +perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs) +{ + int handled = 0; + + handled += perf_ibs_handle_irq(&perf_ibs_fetch, regs); + handled += perf_ibs_handle_irq(&perf_ibs_op, regs); + + if (handled) + inc_irq_stat(apic_perf_irqs); + + return handled; +} + +static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) +{ + struct cpu_perf_ibs __percpu *pcpu; + int ret; + + pcpu = alloc_percpu(struct cpu_perf_ibs); + if (!pcpu) + return -ENOMEM; + + perf_ibs->pcpu = pcpu; + + ret = perf_pmu_register(&perf_ibs->pmu, name, -1); + if (ret) { + perf_ibs->pcpu = NULL; + free_percpu(pcpu); + } + + return ret; +} + static __init int perf_event_ibs_init(void) { if (!ibs_caps) return -ENODEV; /* ibs not supported by the cpu */ - perf_pmu_register(&perf_ibs, "ibs", -1); + perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch"); + if (ibs_caps & IBS_CAPS_OPCNT) + perf_ibs_op.config_mask |= IBS_OP_CNT_CTL; + perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); + register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps); return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 26b3e2fef104..166546ec6aef 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1027,8 +1027,6 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) u64 status; int handled; - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); /* @@ -1082,7 +1080,7 @@ again: if (!intel_pmu_save_and_restart(event)) continue; - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) data.br_stack = &cpuc->lbr_stack; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 7f64df19e7dd..5a3edc27f6e5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -316,8 +316,7 @@ int intel_pmu_drain_bts_buffer(void) ds->bts_index = ds->bts_buffer_base; - perf_sample_data_init(&data, 0); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, event->hw.last_period); regs.ip = 0; /* @@ -564,8 +563,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, if (!intel_pmu_save_and_restart(event)) return; - perf_sample_data_init(&data, 0); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, event->hw.last_period); /* * We use the interrupt regs as a base because the PEBS record diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index a2dfacfd7103..47124a73dd73 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -1005,8 +1005,6 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - perf_sample_data_init(&data, 0); - cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -1034,10 +1032,12 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) handled += overflow; /* event overflow for sure */ - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, hwc->last_period); if (!x86_perf_event_set_period(event)) continue; + + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c9a281f272fd..4243e8bbdcb1 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -24,40 +24,21 @@ #include <trace/syscall.h> #include <asm/cacheflush.h> +#include <asm/kprobes.h> #include <asm/ftrace.h> #include <asm/nops.h> -#include <asm/nmi.h> - #ifdef CONFIG_DYNAMIC_FTRACE -/* - * modifying_code is set to notify NMIs that they need to use - * memory barriers when entering or exiting. But we don't want - * to burden NMIs with unnecessary memory barriers when code - * modification is not being done (which is most of the time). - * - * A mutex is already held when ftrace_arch_code_modify_prepare - * and post_process are called. No locks need to be taken here. - * - * Stop machine will make sure currently running NMIs are done - * and new NMIs will see the updated variable before we need - * to worry about NMIs doing memory barriers. - */ -static int modifying_code __read_mostly; -static DEFINE_PER_CPU(int, save_modifying_code); - int ftrace_arch_code_modify_prepare(void) { set_kernel_text_rw(); set_all_modules_text_rw(); - modifying_code = 1; return 0; } int ftrace_arch_code_modify_post_process(void) { - modifying_code = 0; set_all_modules_text_ro(); set_kernel_text_ro(); return 0; @@ -90,134 +71,6 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) return calc.code; } -/* - * Modifying code must take extra care. On an SMP machine, if - * the code being modified is also being executed on another CPU - * that CPU will have undefined results and possibly take a GPF. - * We use kstop_machine to stop other CPUS from exectuing code. - * But this does not stop NMIs from happening. We still need - * to protect against that. We separate out the modification of - * the code to take care of this. - * - * Two buffers are added: An IP buffer and a "code" buffer. - * - * 1) Put the instruction pointer into the IP buffer - * and the new code into the "code" buffer. - * 2) Wait for any running NMIs to finish and set a flag that says - * we are modifying code, it is done in an atomic operation. - * 3) Write the code - * 4) clear the flag. - * 5) Wait for any running NMIs to finish. - * - * If an NMI is executed, the first thing it does is to call - * "ftrace_nmi_enter". This will check if the flag is set to write - * and if it is, it will write what is in the IP and "code" buffers. - * - * The trick is, it does not matter if everyone is writing the same - * content to the code location. Also, if a CPU is executing code - * it is OK to write to that code location if the contents being written - * are the same as what exists. - */ - -#define MOD_CODE_WRITE_FLAG (1 << 31) /* set when NMI should do the write */ -static atomic_t nmi_running = ATOMIC_INIT(0); -static int mod_code_status; /* holds return value of text write */ -static void *mod_code_ip; /* holds the IP to write to */ -static const void *mod_code_newcode; /* holds the text to write to the IP */ - -static unsigned nmi_wait_count; -static atomic_t nmi_update_count = ATOMIC_INIT(0); - -int ftrace_arch_read_dyn_info(char *buf, int size) -{ - int r; - - r = snprintf(buf, size, "%u %u", - nmi_wait_count, - atomic_read(&nmi_update_count)); - return r; -} - -static void clear_mod_flag(void) -{ - int old = atomic_read(&nmi_running); - - for (;;) { - int new = old & ~MOD_CODE_WRITE_FLAG; - - if (old == new) - break; - - old = atomic_cmpxchg(&nmi_running, old, new); - } -} - -static void ftrace_mod_code(void) -{ - /* - * Yes, more than one CPU process can be writing to mod_code_status. - * (and the code itself) - * But if one were to fail, then they all should, and if one were - * to succeed, then they all should. - */ - mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, - MCOUNT_INSN_SIZE); - - /* if we fail, then kill any new writers */ - if (mod_code_status) - clear_mod_flag(); -} - -void ftrace_nmi_enter(void) -{ - __this_cpu_write(save_modifying_code, modifying_code); - - if (!__this_cpu_read(save_modifying_code)) - return; - - if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { - smp_rmb(); - ftrace_mod_code(); - atomic_inc(&nmi_update_count); - } - /* Must have previous changes seen before executions */ - smp_mb(); -} - -void ftrace_nmi_exit(void) -{ - if (!__this_cpu_read(save_modifying_code)) - return; - - /* Finish all executions before clearing nmi_running */ - smp_mb(); - atomic_dec(&nmi_running); -} - -static void wait_for_nmi_and_set_mod_flag(void) -{ - if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)) - return; - - do { - cpu_relax(); - } while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)); - - nmi_wait_count++; -} - -static void wait_for_nmi(void) -{ - if (!atomic_read(&nmi_running)) - return; - - do { - cpu_relax(); - } while (atomic_read(&nmi_running)); - - nmi_wait_count++; -} - static inline int within(unsigned long addr, unsigned long start, unsigned long end) { @@ -238,26 +91,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) if (within(ip, (unsigned long)_text, (unsigned long)_etext)) ip = (unsigned long)__va(__pa(ip)); - mod_code_ip = (void *)ip; - mod_code_newcode = new_code; - - /* The buffers need to be visible before we let NMIs write them */ - smp_mb(); - - wait_for_nmi_and_set_mod_flag(); - - /* Make sure all running NMIs have finished before we write the code */ - smp_mb(); - - ftrace_mod_code(); - - /* Make sure the write happens before clearing the bit */ - smp_mb(); - - clear_mod_flag(); - wait_for_nmi(); - - return mod_code_status; + return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); } static const unsigned char *ftrace_nop_replace(void) @@ -334,6 +168,347 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } +int modifying_ftrace_code __read_mostly; + +/* + * A breakpoint was added to the code address we are about to + * modify, and this is the handle that will just skip over it. + * We are either changing a nop into a trace call, or a trace + * call to a nop. While the change is taking place, we treat + * it just like it was a nop. + */ +int ftrace_int3_handler(struct pt_regs *regs) +{ + if (WARN_ON_ONCE(!regs)) + return 0; + + if (!ftrace_location(regs->ip - 1)) + return 0; + + regs->ip += MCOUNT_INSN_SIZE - 1; + + return 1; +} + +static int ftrace_write(unsigned long ip, const char *val, int size) +{ + /* + * On x86_64, kernel text mappings are mapped read-only with + * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead + * of the kernel text mapping to modify the kernel text. + * + * For 32bit kernels, these mappings are same and we can use + * kernel identity mapping to modify code. + */ + if (within(ip, (unsigned long)_text, (unsigned long)_etext)) + ip = (unsigned long)__va(__pa(ip)); + + return probe_kernel_write((void *)ip, val, size); +} + +static int add_break(unsigned long ip, const char *old) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + unsigned char brk = BREAKPOINT_INSTRUCTION; + + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + + if (ftrace_write(ip, &brk, 1)) + return -EPERM; + + return 0; +} + +static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned const char *old; + unsigned long ip = rec->ip; + + old = ftrace_call_replace(ip, addr); + + return add_break(rec->ip, old); +} + + +static int add_brk_on_nop(struct dyn_ftrace *rec) +{ + unsigned const char *old; + + old = ftrace_nop_replace(); + + return add_break(rec->ip, old); +} + +static int add_breakpoints(struct dyn_ftrace *rec, int enable) +{ + unsigned long ftrace_addr; + int ret; + + ret = ftrace_test_record(rec, enable); + + ftrace_addr = (unsigned long)FTRACE_ADDR; + + switch (ret) { + case FTRACE_UPDATE_IGNORE: + return 0; + + case FTRACE_UPDATE_MAKE_CALL: + /* converting nop to call */ + return add_brk_on_nop(rec); + + case FTRACE_UPDATE_MAKE_NOP: + /* converting a call to a nop */ + return add_brk_on_call(rec, ftrace_addr); + } + return 0; +} + +/* + * On error, we need to remove breakpoints. This needs to + * be done caefully. If the address does not currently have a + * breakpoint, we know we are done. Otherwise, we look at the + * remaining 4 bytes of the instruction. If it matches a nop + * we replace the breakpoint with the nop. Otherwise we replace + * it with the call instruction. + */ +static int remove_breakpoint(struct dyn_ftrace *rec) +{ + unsigned char ins[MCOUNT_INSN_SIZE]; + unsigned char brk = BREAKPOINT_INSTRUCTION; + const unsigned char *nop; + unsigned long ftrace_addr; + unsigned long ip = rec->ip; + + /* If we fail the read, just give up */ + if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* If this does not have a breakpoint, we are done */ + if (ins[0] != brk) + return -1; + + nop = ftrace_nop_replace(); + + /* + * If the last 4 bytes of the instruction do not match + * a nop, then we assume that this is a call to ftrace_addr. + */ + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) { + /* + * For extra paranoidism, we check if the breakpoint is on + * a call that would actually jump to the ftrace_addr. + * If not, don't touch the breakpoint, we make just create + * a disaster. + */ + ftrace_addr = (unsigned long)FTRACE_ADDR; + nop = ftrace_call_replace(ip, ftrace_addr); + + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) + return -EINVAL; + } + + return probe_kernel_write((void *)ip, &nop[0], 1); +} + +static int add_update_code(unsigned long ip, unsigned const char *new) +{ + /* skip breakpoint */ + ip++; + new++; + if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1)) + return -EPERM; + return 0; +} + +static int add_update_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + unsigned const char *new; + + new = ftrace_call_replace(ip, addr); + return add_update_code(ip, new); +} + +static int add_update_nop(struct dyn_ftrace *rec) +{ + unsigned long ip = rec->ip; + unsigned const char *new; + + new = ftrace_nop_replace(); + return add_update_code(ip, new); +} + +static int add_update(struct dyn_ftrace *rec, int enable) +{ + unsigned long ftrace_addr; + int ret; + + ret = ftrace_test_record(rec, enable); + + ftrace_addr = (unsigned long)FTRACE_ADDR; + + switch (ret) { + case FTRACE_UPDATE_IGNORE: + return 0; + + case FTRACE_UPDATE_MAKE_CALL: + /* converting nop to call */ + return add_update_call(rec, ftrace_addr); + + case FTRACE_UPDATE_MAKE_NOP: + /* converting a call to a nop */ + return add_update_nop(rec); + } + + return 0; +} + +static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long ip = rec->ip; + unsigned const char *new; + + new = ftrace_call_replace(ip, addr); + + if (ftrace_write(ip, new, 1)) + return -EPERM; + + return 0; +} + +static int finish_update_nop(struct dyn_ftrace *rec) +{ + unsigned long ip = rec->ip; + unsigned const char *new; + + new = ftrace_nop_replace(); + + if (ftrace_write(ip, new, 1)) + return -EPERM; + return 0; +} + +static int finish_update(struct dyn_ftrace *rec, int enable) +{ + unsigned long ftrace_addr; + int ret; + + ret = ftrace_update_record(rec, enable); + + ftrace_addr = (unsigned long)FTRACE_ADDR; + + switch (ret) { + case FTRACE_UPDATE_IGNORE: + return 0; + + case FTRACE_UPDATE_MAKE_CALL: + /* converting nop to call */ + return finish_update_call(rec, ftrace_addr); + + case FTRACE_UPDATE_MAKE_NOP: + /* converting a call to a nop */ + return finish_update_nop(rec); + } + + return 0; +} + +static void do_sync_core(void *data) +{ + sync_core(); +} + +static void run_sync(void) +{ + int enable_irqs = irqs_disabled(); + + /* We may be called with interrupts disbled (on bootup). */ + if (enable_irqs) + local_irq_enable(); + on_each_cpu(do_sync_core, NULL, 1); + if (enable_irqs) + local_irq_disable(); +} + +static void ftrace_replace_code(int enable) +{ + struct ftrace_rec_iter *iter; + struct dyn_ftrace *rec; + const char *report = "adding breakpoints"; + int count = 0; + int ret; + + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + + ret = add_breakpoints(rec, enable); + if (ret) + goto remove_breakpoints; + count++; + } + + run_sync(); + + report = "updating code"; + + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + + ret = add_update(rec, enable); + if (ret) + goto remove_breakpoints; + } + + run_sync(); + + report = "removing breakpoints"; + + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + + ret = finish_update(rec, enable); + if (ret) + goto remove_breakpoints; + } + + run_sync(); + + return; + + remove_breakpoints: + ftrace_bug(ret, rec ? rec->ip : 0); + printk(KERN_WARNING "Failed on %s (%d):\n", report, count); + for_ftrace_rec_iter(iter) { + rec = ftrace_rec_iter_record(iter); + remove_breakpoint(rec); + } +} + +void arch_ftrace_update_code(int command) +{ + modifying_ftrace_code++; + + if (command & FTRACE_UPDATE_CALLS) + ftrace_replace_code(1); + else if (command & FTRACE_DISABLE_CALLS) + ftrace_replace_code(0); + + if (command & FTRACE_UPDATE_TRACE_FUNC) + ftrace_update_ftrace_func(ftrace_trace_function); + + if (command & FTRACE_START_FUNC_RET) + ftrace_enable_ftrace_graph_caller(); + else if (command & FTRACE_STOP_FUNC_RET) + ftrace_disable_ftrace_graph_caller(); + + modifying_ftrace_code--; +} + int __init ftrace_dyn_arch_init(void *data) { /* The return code is retured via data */ diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 47acaf319165..eb1539eac393 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -84,7 +84,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) -static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -209,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) EXPORT_SYMBOL_GPL(unregister_nmi_handler); -static notrace __kprobes void +static __kprobes void pci_serr_error(unsigned char reason, struct pt_regs *regs) { pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", @@ -236,7 +236,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) outb(reason, NMI_REASON_PORT); } -static notrace __kprobes void +static __kprobes void io_check_error(unsigned char reason, struct pt_regs *regs) { unsigned long i; @@ -263,7 +263,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs) outb(reason, NMI_REASON_PORT); } -static notrace __kprobes void +static __kprobes void unknown_nmi_error(unsigned char reason, struct pt_regs *regs) { int handled; @@ -305,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) static DEFINE_PER_CPU(bool, swallow_nmi); static DEFINE_PER_CPU(unsigned long, last_nmi_rip); -static notrace __kprobes void default_do_nmi(struct pt_regs *regs) +static __kprobes void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; int handled; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ff9281f16029..92d5756d85fc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -50,6 +50,7 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <linux/atomic.h> +#include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> #include <asm/i387.h> @@ -303,8 +304,13 @@ gp_in_kernel: } /* May run on IST stack. */ -dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code) +dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code) { +#ifdef CONFIG_DYNAMIC_FTRACE + /* ftrace must be first, everything else may cause a recursive crash */ + if (unlikely(modifying_ftrace_code) && ftrace_int3_handler(regs)) + return; +#endif #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 72a6cabb4d5b..d32cc5e4b0cc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -286,6 +286,12 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void); struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter); struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter); +#define for_ftrace_rec_iter(iter) \ + for (iter = ftrace_rec_iter_start(); \ + iter; \ + iter = ftrace_rec_iter_next(iter)) + + int ftrace_update_record(struct dyn_ftrace *rec, int enable); int ftrace_test_record(struct dyn_ftrace *rec, int enable); void ftrace_run_stop_machine(int command); @@ -485,8 +491,12 @@ static inline void __ftrace_enabled_restore(int enabled) extern void trace_preempt_on(unsigned long a0, unsigned long a1); extern void trace_preempt_off(unsigned long a0, unsigned long a1); #else - static inline void trace_preempt_on(unsigned long a0, unsigned long a1) { } - static inline void trace_preempt_off(unsigned long a0, unsigned long a1) { } +/* + * Use defines instead of static inlines because some arches will make code out + * of the CALLER_ADDR, when we really want these to be a real nop. + */ +# define trace_preempt_on(a0, a1) do { } while (0) +# define trace_preempt_off(a0, a1) do { } while (0) #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 645231c373c8..c0d34420a913 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -480,15 +480,16 @@ do { \ #define trace_printk(fmt, args...) \ do { \ + static const char *trace_printk_fmt \ + __attribute__((section("__trace_printk_fmt"))) = \ + __builtin_constant_p(fmt) ? fmt : NULL; \ + \ __trace_printk_check_format(fmt, ##args); \ - if (__builtin_constant_p(fmt)) { \ - static const char *trace_printk_fmt \ - __attribute__((section("__trace_printk_fmt"))) = \ - __builtin_constant_p(fmt) ? fmt : NULL; \ \ + if (__builtin_constant_p(fmt)) \ __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \ - } else \ - __trace_printk(_THIS_IP_, fmt, ##args); \ + else \ + __trace_printk(_THIS_IP_, fmt, ##args); \ } while (0) extern __printf(2, 3) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ddbb6a901f65..8adf70e9e3cc 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1084,10 +1084,8 @@ extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); -extern void __perf_event_task_sched_in(struct task_struct *prev, - struct task_struct *task); -extern void __perf_event_task_sched_out(struct task_struct *prev, - struct task_struct *next); +extern void __perf_event_task_sched(struct task_struct *prev, + struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); @@ -1132,11 +1130,14 @@ struct perf_sample_data { struct perf_branch_stack *br_stack; }; -static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr) +static inline void perf_sample_data_init(struct perf_sample_data *data, + u64 addr, u64 period) { + /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; + data->period = period; } extern void perf_output_sample(struct perf_output_handle *handle, @@ -1204,20 +1205,13 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) extern struct static_key_deferred perf_sched_events; -static inline void perf_event_task_sched_in(struct task_struct *prev, +static inline void perf_event_task_sched(struct task_struct *prev, struct task_struct *task) { - if (static_key_false(&perf_sched_events.key)) - __perf_event_task_sched_in(prev, task); -} - -static inline void perf_event_task_sched_out(struct task_struct *prev, - struct task_struct *next) -{ perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); if (static_key_false(&perf_sched_events.key)) - __perf_event_task_sched_out(prev, next); + __perf_event_task_sched(prev, task); } extern void perf_event_mmap(struct vm_area_struct *vma); @@ -1292,11 +1286,8 @@ extern void perf_event_disable(struct perf_event *event); extern void perf_event_task_tick(void); #else static inline void -perf_event_task_sched_in(struct task_struct *prev, - struct task_struct *task) { } -static inline void -perf_event_task_sched_out(struct task_struct *prev, - struct task_struct *next) { } +perf_event_task_sched(struct task_struct *prev, + struct task_struct *task) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 7be2e88f23fd..6c8835f74f79 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -96,9 +96,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k __ring_buffer_alloc((size), (flags), &__key); \ }) +#define RING_BUFFER_ALL_CPUS -1 + void ring_buffer_free(struct ring_buffer *buffer); -int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size); +int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, int cpu); void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val); @@ -129,7 +131,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts); void ring_buffer_iter_reset(struct ring_buffer_iter *iter); int ring_buffer_iter_empty(struct ring_buffer_iter *iter); -unsigned long ring_buffer_size(struct ring_buffer *buffer); +unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu); void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_reset(struct ring_buffer *buffer); diff --git a/init/Kconfig b/init/Kconfig index 6cfd71d06463..7e3713519b0e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1156,7 +1156,7 @@ menu "Kernel Performance Events And Counters" config PERF_EVENTS bool "Kernel performance events and counters" - default y if (PROFILING || PERF_COUNTERS) + default y if PROFILING depends on HAVE_PERF_EVENTS select ANON_INODES select IRQ_WORK @@ -1183,18 +1183,6 @@ config PERF_EVENTS Say Y if unsure. -config PERF_COUNTERS - bool "Kernel performance counters (old config option)" - depends on HAVE_PERF_EVENTS - help - This config has been obsoleted by the PERF_EVENTS - config option - please see that one for details. - - It has no effect on the kernel whether you enable - it or not, it is a compatibility placeholder. - - Say N if unsure. - config DEBUG_PERF_USE_VMALLOC default n bool "Debug: use vmalloc to back perf mmap() buffers" diff --git a/kernel/events/core.c b/kernel/events/core.c index fd126f82b57c..91a445925855 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2039,8 +2039,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, * accessing the event control register. If a NMI hits, then it will * not restart the event. */ -void __perf_event_task_sched_out(struct task_struct *task, - struct task_struct *next) +static void __perf_event_task_sched_out(struct task_struct *task, + struct task_struct *next) { int ctxn; @@ -2279,8 +2279,8 @@ static void perf_branch_stack_sched_in(struct task_struct *prev, * accessing the event control register. If a NMI hits, then it will * keep the event running. */ -void __perf_event_task_sched_in(struct task_struct *prev, - struct task_struct *task) +static void __perf_event_task_sched_in(struct task_struct *prev, + struct task_struct *task) { struct perf_event_context *ctx; int ctxn; @@ -2305,6 +2305,12 @@ void __perf_event_task_sched_in(struct task_struct *prev, perf_branch_stack_sched_in(prev, task); } +void __perf_event_task_sched(struct task_struct *prev, struct task_struct *next) +{ + __perf_event_task_sched_out(prev, next); + __perf_event_task_sched_in(prev, next); +} + static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count) { u64 frequency = event->attr.sample_freq; @@ -4957,7 +4963,7 @@ void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) if (rctx < 0) return; - perf_sample_data_init(&data, addr); + perf_sample_data_init(&data, addr, 0); do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs); @@ -5215,7 +5221,7 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, .data = record, }; - perf_sample_data_init(&data, addr); + perf_sample_data_init(&data, addr, 0); data.raw = &raw; hlist_for_each_entry_rcu(event, node, head, hlist_entry) { @@ -5318,7 +5324,7 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; - perf_sample_data_init(&sample, bp->attr.bp_addr); + perf_sample_data_init(&sample, bp->attr.bp_addr, 0); if (!bp->hw.state && !perf_exclude_event(bp, regs)) perf_swevent_event(bp, 1, &sample, regs); @@ -5344,13 +5350,12 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) event->pmu->read(event); - perf_sample_data_init(&data, 0); - data.period = event->hw.last_period; + perf_sample_data_init(&data, 0, event->hw.last_period); regs = get_irq_regs(); if (regs && !perf_exclude_event(event, regs)) { if (!(event->attr.exclude_idle && is_idle_task(current))) - if (perf_event_overflow(event, &data, regs)) + if (__perf_event_overflow(event, 1, &data, regs)) ret = HRTIMER_NORESTART; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0533a688ce22..13c38837f2cd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1913,7 +1913,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { sched_info_switch(prev, next); - perf_event_task_sched_out(prev, next); + perf_event_task_sched(prev, next); fire_sched_out_preempt_notifiers(prev, next); prepare_lock_switch(rq, next); prepare_arch_switch(next); @@ -1956,13 +1956,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) */ prev_state = prev->state; finish_arch_switch(prev); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_disable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ - perf_event_task_sched_in(prev, current); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_enable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); finish_arch_post_lock_switch(); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0fa92f677c92..cf81f27ce6c6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2469,57 +2469,35 @@ static int ftrace_avail_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; - int ret; if (unlikely(ftrace_disabled)) return -ENODEV; - iter = kzalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) - return -ENOMEM; - - iter->pg = ftrace_pages_start; - iter->ops = &global_ops; - - ret = seq_open(file, &show_ftrace_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - - m->private = iter; - } else { - kfree(iter); + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (iter) { + iter->pg = ftrace_pages_start; + iter->ops = &global_ops; } - return ret; + return iter ? 0 : -ENOMEM; } static int ftrace_enabled_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; - int ret; if (unlikely(ftrace_disabled)) return -ENODEV; - iter = kzalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) - return -ENOMEM; - - iter->pg = ftrace_pages_start; - iter->flags = FTRACE_ITER_ENABLED; - iter->ops = &global_ops; - - ret = seq_open(file, &show_ftrace_seq_ops); - if (!ret) { - struct seq_file *m = file->private_data; - - m->private = iter; - } else { - kfree(iter); + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (iter) { + iter->pg = ftrace_pages_start; + iter->flags = FTRACE_ITER_ENABLED; + iter->ops = &global_ops; } - return ret; + return iter ? 0 : -ENOMEM; } static void ftrace_filter_reset(struct ftrace_hash *hash) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index cf8d11e91efd..2d5eb3320827 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -449,6 +449,7 @@ struct ring_buffer_per_cpu { raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; + unsigned int nr_pages; struct list_head *pages; struct buffer_page *head_page; /* read from head */ struct buffer_page *tail_page; /* write to tail */ @@ -466,10 +467,12 @@ struct ring_buffer_per_cpu { unsigned long read_bytes; u64 write_stamp; u64 read_stamp; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ + int nr_pages_to_update; + struct list_head new_pages; /* new pages to add */ }; struct ring_buffer { - unsigned pages; unsigned flags; int cpus; atomic_t record_disabled; @@ -963,14 +966,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) return 0; } -static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, - unsigned nr_pages) +static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu) { + int i; struct buffer_page *bpage, *tmp; - LIST_HEAD(pages); - unsigned i; - - WARN_ON(!nr_pages); for (i = 0; i < nr_pages; i++) { struct page *page; @@ -981,15 +980,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, */ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL | __GFP_NORETRY, - cpu_to_node(cpu_buffer->cpu)); + cpu_to_node(cpu)); if (!bpage) goto free_pages; - rb_check_bpage(cpu_buffer, bpage); + list_add(&bpage->list, pages); - list_add(&bpage->list, &pages); - - page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); if (!page) goto free_pages; @@ -997,6 +994,27 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, rb_init_page(bpage->page); } + return 0; + +free_pages: + list_for_each_entry_safe(bpage, tmp, pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } + + return -ENOMEM; +} + +static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, + unsigned nr_pages) +{ + LIST_HEAD(pages); + + WARN_ON(!nr_pages); + + if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu)) + return -ENOMEM; + /* * The ring buffer page list is a circular list that does not * start and end with a list head. All page list items point to @@ -1005,20 +1023,15 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, cpu_buffer->pages = pages.next; list_del(&pages); + cpu_buffer->nr_pages = nr_pages; + rb_check_pages(cpu_buffer); return 0; - - free_pages: - list_for_each_entry_safe(bpage, tmp, &pages, list) { - list_del_init(&bpage->list); - free_buffer_page(bpage); - } - return -ENOMEM; } static struct ring_buffer_per_cpu * -rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) +rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; @@ -1052,7 +1065,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) INIT_LIST_HEAD(&cpu_buffer->reader_page->list); - ret = rb_allocate_pages(cpu_buffer, buffer->pages); + ret = rb_allocate_pages(cpu_buffer, nr_pages); if (ret < 0) goto fail_free_reader; @@ -1113,7 +1126,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, { struct ring_buffer *buffer; int bsize; - int cpu; + int cpu, nr_pages; /* keep it in its own cache line */ buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()), @@ -1124,14 +1137,14 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) goto fail_free_buffer; - buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); + nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); buffer->flags = flags; buffer->clock = trace_clock_local; buffer->reader_lock_key = key; /* need at least two pages */ - if (buffer->pages < 2) - buffer->pages = 2; + if (nr_pages < 2) + nr_pages = 2; /* * In case of non-hotplug cpu, if the ring-buffer is allocated @@ -1154,7 +1167,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, for_each_buffer_cpu(buffer, cpu) { buffer->buffers[cpu] = - rb_allocate_cpu_buffer(buffer, cpu); + rb_allocate_cpu_buffer(buffer, nr_pages, cpu); if (!buffer->buffers[cpu]) goto fail_free_buffers; } @@ -1276,6 +1289,18 @@ out: raw_spin_unlock_irq(&cpu_buffer->reader_lock); } +static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer) +{ + if (cpu_buffer->nr_pages_to_update > 0) + rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages, + cpu_buffer->nr_pages_to_update); + else + rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update); + cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update; + /* reset this value */ + cpu_buffer->nr_pages_to_update = 0; +} + /** * ring_buffer_resize - resize the ring buffer * @buffer: the buffer to resize. @@ -1285,14 +1310,12 @@ out: * * Returns -1 on failure. */ -int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) +int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, + int cpu_id) { struct ring_buffer_per_cpu *cpu_buffer; - unsigned nr_pages, rm_pages, new_pages; - struct buffer_page *bpage, *tmp; - unsigned long buffer_size; - LIST_HEAD(pages); - int i, cpu; + unsigned nr_pages; + int cpu; /* * Always succeed at resizing a non-existent buffer: @@ -1302,15 +1325,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) size = DIV_ROUND_UP(size, BUF_PAGE_SIZE); size *= BUF_PAGE_SIZE; - buffer_size = buffer->pages * BUF_PAGE_SIZE; /* we need a minimum of two pages */ if (size < BUF_PAGE_SIZE * 2) size = BUF_PAGE_SIZE * 2; - if (size == buffer_size) - return size; - atomic_inc(&buffer->record_disabled); /* Make sure all writers are done with this buffer. */ @@ -1321,68 +1340,56 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); - if (size < buffer_size) { - - /* easy case, just free pages */ - if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) - goto out_fail; - - rm_pages = buffer->pages - nr_pages; - + if (cpu_id == RING_BUFFER_ALL_CPUS) { + /* calculate the pages to update */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - rb_remove_pages(cpu_buffer, rm_pages); - } - goto out; - } - /* - * This is a bit more difficult. We only want to add pages - * when we can allocate enough for all CPUs. We do this - * by allocating all the pages and storing them on a local - * link list. If we succeed in our allocation, then we - * add these pages to the cpu_buffers. Otherwise we just free - * them all and return -ENOMEM; - */ - if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) - goto out_fail; + cpu_buffer->nr_pages_to_update = nr_pages - + cpu_buffer->nr_pages; - new_pages = nr_pages - buffer->pages; + /* + * nothing more to do for removing pages or no update + */ + if (cpu_buffer->nr_pages_to_update <= 0) + continue; - for_each_buffer_cpu(buffer, cpu) { - for (i = 0; i < new_pages; i++) { - struct page *page; /* - * __GFP_NORETRY flag makes sure that the allocation - * fails gracefully without invoking oom-killer and - * the system is not destabilized. + * to add pages, make sure all new pages can be + * allocated without receiving ENOMEM */ - bpage = kzalloc_node(ALIGN(sizeof(*bpage), - cache_line_size()), - GFP_KERNEL | __GFP_NORETRY, - cpu_to_node(cpu)); - if (!bpage) - goto free_pages; - list_add(&bpage->list, &pages); - page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) - goto free_pages; - bpage->page = page_address(page); - rb_init_page(bpage->page); + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages, cpu)) + /* not enough memory for new pages */ + goto no_mem; } - } - for_each_buffer_cpu(buffer, cpu) { - cpu_buffer = buffer->buffers[cpu]; - rb_insert_pages(cpu_buffer, &pages, new_pages); - } + /* wait for all the updates to complete */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (cpu_buffer->nr_pages_to_update) { + update_pages_handler(cpu_buffer); + } + } + } else { + cpu_buffer = buffer->buffers[cpu_id]; + if (nr_pages == cpu_buffer->nr_pages) + goto out; - if (RB_WARN_ON(buffer, !list_empty(&pages))) - goto out_fail; + cpu_buffer->nr_pages_to_update = nr_pages - + cpu_buffer->nr_pages; + + INIT_LIST_HEAD(&cpu_buffer->new_pages); + if (cpu_buffer->nr_pages_to_update > 0 && + __rb_allocate_pages(cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages, cpu_id)) + goto no_mem; + + update_pages_handler(cpu_buffer); + } out: - buffer->pages = nr_pages; put_online_cpus(); mutex_unlock(&buffer->mutex); @@ -1390,25 +1397,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) return size; - free_pages: - list_for_each_entry_safe(bpage, tmp, &pages, list) { - list_del_init(&bpage->list); - free_buffer_page(bpage); + no_mem: + for_each_buffer_cpu(buffer, cpu) { + struct buffer_page *bpage, *tmp; + cpu_buffer = buffer->buffers[cpu]; + /* reset this number regardless */ + cpu_buffer->nr_pages_to_update = 0; + if (list_empty(&cpu_buffer->new_pages)) + continue; + list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages, + list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); + } } put_online_cpus(); mutex_unlock(&buffer->mutex); atomic_dec(&buffer->record_disabled); return -ENOMEM; - - /* - * Something went totally wrong, and we are too paranoid - * to even clean up the mess. - */ - out_fail: - put_online_cpus(); - mutex_unlock(&buffer->mutex); - atomic_dec(&buffer->record_disabled); - return -1; } EXPORT_SYMBOL_GPL(ring_buffer_resize); @@ -1510,7 +1516,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) * assign the commit to the tail. */ again: - max_count = cpu_buffer->buffer->pages * 100; + max_count = cpu_buffer->nr_pages * 100; while (cpu_buffer->commit_page != cpu_buffer->tail_page) { if (RB_WARN_ON(cpu_buffer, !(--max_count))) @@ -3588,9 +3594,18 @@ EXPORT_SYMBOL_GPL(ring_buffer_read); * ring_buffer_size - return the size of the ring buffer (in bytes) * @buffer: The ring buffer. */ -unsigned long ring_buffer_size(struct ring_buffer *buffer) +unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu) { - return BUF_PAGE_SIZE * buffer->pages; + /* + * Earlier, this method returned + * BUF_PAGE_SIZE * buffer->nr_pages + * Since the nr_pages field is now removed, we have converted this to + * return the per cpu buffer value. + */ + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return 0; + + return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages; } EXPORT_SYMBOL_GPL(ring_buffer_size); @@ -3765,8 +3780,11 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, !cpumask_test_cpu(cpu, buffer_b->cpumask)) goto out; + cpu_buffer_a = buffer_a->buffers[cpu]; + cpu_buffer_b = buffer_b->buffers[cpu]; + /* At least make sure the two buffers are somewhat the same */ - if (buffer_a->pages != buffer_b->pages) + if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; ret = -EAGAIN; @@ -3780,9 +3798,6 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, if (atomic_read(&buffer_b->record_disabled)) goto out; - cpu_buffer_a = buffer_a->buffers[cpu]; - cpu_buffer_b = buffer_b->buffers[cpu]; - if (atomic_read(&cpu_buffer_a->record_disabled)) goto out; @@ -4071,6 +4086,8 @@ static int rb_cpu_notify(struct notifier_block *self, struct ring_buffer *buffer = container_of(self, struct ring_buffer, cpu_notify); long cpu = (long)hcpu; + int cpu_i, nr_pages_same; + unsigned int nr_pages; switch (action) { case CPU_UP_PREPARE: @@ -4078,8 +4095,23 @@ static int rb_cpu_notify(struct notifier_block *self, if (cpumask_test_cpu(cpu, buffer->cpumask)) return NOTIFY_OK; + nr_pages = 0; + nr_pages_same = 1; + /* check if all cpu sizes are same */ + for_each_buffer_cpu(buffer, cpu_i) { + /* fill in the size from first enabled cpu */ + if (nr_pages == 0) + nr_pages = buffer->buffers[cpu_i]->nr_pages; + if (nr_pages != buffer->buffers[cpu_i]->nr_pages) { + nr_pages_same = 0; + break; + } + } + /* allocate minimum pages, user can later expand it */ + if (!nr_pages_same) + nr_pages = 2; buffer->buffers[cpu] = - rb_allocate_cpu_buffer(buffer, cpu); + rb_allocate_cpu_buffer(buffer, nr_pages, cpu); if (!buffer->buffers[cpu]) { WARN(1, "failed to allocate ring buffer on CPU %ld\n", cpu); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2a22255c1010..509e8615f504 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -87,18 +87,6 @@ static int tracing_disabled = 1; DEFINE_PER_CPU(int, ftrace_cpu_disabled); -static inline void ftrace_disable_cpu(void) -{ - preempt_disable(); - __this_cpu_inc(ftrace_cpu_disabled); -} - -static inline void ftrace_enable_cpu(void) -{ - __this_cpu_dec(ftrace_cpu_disabled); - preempt_enable(); -} - cpumask_var_t __read_mostly tracing_buffer_mask; /* @@ -629,7 +617,6 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; - void *ret; if (s->len <= s->readpos) return -EBUSY; @@ -637,9 +624,7 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) len = s->len - s->readpos; if (cnt > len) cnt = len; - ret = memcpy(buf, s->buffer + s->readpos, cnt); - if (!ret) - return -EFAULT; + memcpy(buf, s->buffer + s->readpos, cnt); s->readpos += cnt; return cnt; @@ -751,8 +736,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&ftrace_max_lock); - ftrace_disable_cpu(); - ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu); if (ret == -EBUSY) { @@ -766,8 +749,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) "Failed to swap buffers due to commit in progress\n"); } - ftrace_enable_cpu(); - WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); __update_max_tr(tr, tsk, cpu); @@ -841,7 +822,8 @@ __acquires(kernel_lock) /* If we expanded the buffers, make sure the max is expanded too */ if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, trace_buf_size); + ring_buffer_resize(max_tr.buffer, trace_buf_size, + RING_BUFFER_ALL_CPUS); /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); @@ -857,7 +839,8 @@ __acquires(kernel_lock) /* Shrink the max buffer again */ if (ring_buffer_expanded && type->use_max_tr) - ring_buffer_resize(max_tr.buffer, 1); + ring_buffer_resize(max_tr.buffer, 1, + RING_BUFFER_ALL_CPUS); printk(KERN_CONT "PASSED\n"); } @@ -917,13 +900,6 @@ out: mutex_unlock(&trace_types_lock); } -static void __tracing_reset(struct ring_buffer *buffer, int cpu) -{ - ftrace_disable_cpu(); - ring_buffer_reset_cpu(buffer, cpu); - ftrace_enable_cpu(); -} - void tracing_reset(struct trace_array *tr, int cpu) { struct ring_buffer *buffer = tr->buffer; @@ -932,7 +908,7 @@ void tracing_reset(struct trace_array *tr, int cpu) /* Make sure all commits have finished */ synchronize_sched(); - __tracing_reset(buffer, cpu); + ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } @@ -950,7 +926,7 @@ void tracing_reset_online_cpus(struct trace_array *tr) tr->time_start = ftrace_now(tr->cpu); for_each_online_cpu(cpu) - __tracing_reset(buffer, cpu); + ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } @@ -1498,25 +1474,119 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags) #endif /* CONFIG_STACKTRACE */ +/* created for use with alloc_percpu */ +struct trace_buffer_struct { + char buffer[TRACE_BUF_SIZE]; +}; + +static struct trace_buffer_struct *trace_percpu_buffer; +static struct trace_buffer_struct *trace_percpu_sirq_buffer; +static struct trace_buffer_struct *trace_percpu_irq_buffer; +static struct trace_buffer_struct *trace_percpu_nmi_buffer; + +/* + * The buffer used is dependent on the context. There is a per cpu + * buffer for normal context, softirq contex, hard irq context and + * for NMI context. Thise allows for lockless recording. + * + * Note, if the buffers failed to be allocated, then this returns NULL + */ +static char *get_trace_buf(void) +{ + struct trace_buffer_struct *percpu_buffer; + struct trace_buffer_struct *buffer; + + /* + * If we have allocated per cpu buffers, then we do not + * need to do any locking. + */ + if (in_nmi()) + percpu_buffer = trace_percpu_nmi_buffer; + else if (in_irq()) + percpu_buffer = trace_percpu_irq_buffer; + else if (in_softirq()) + percpu_buffer = trace_percpu_sirq_buffer; + else + percpu_buffer = trace_percpu_buffer; + + if (!percpu_buffer) + return NULL; + + buffer = per_cpu_ptr(percpu_buffer, smp_processor_id()); + + return buffer->buffer; +} + +static int alloc_percpu_trace_buffer(void) +{ + struct trace_buffer_struct *buffers; + struct trace_buffer_struct *sirq_buffers; + struct trace_buffer_struct *irq_buffers; + struct trace_buffer_struct *nmi_buffers; + + buffers = alloc_percpu(struct trace_buffer_struct); + if (!buffers) + goto err_warn; + + sirq_buffers = alloc_percpu(struct trace_buffer_struct); + if (!sirq_buffers) + goto err_sirq; + + irq_buffers = alloc_percpu(struct trace_buffer_struct); + if (!irq_buffers) + goto err_irq; + + nmi_buffers = alloc_percpu(struct trace_buffer_struct); + if (!nmi_buffers) + goto err_nmi; + + trace_percpu_buffer = buffers; + trace_percpu_sirq_buffer = sirq_buffers; + trace_percpu_irq_buffer = irq_buffers; + trace_percpu_nmi_buffer = nmi_buffers; + + return 0; + + err_nmi: + free_percpu(irq_buffers); + err_irq: + free_percpu(sirq_buffers); + err_sirq: + free_percpu(buffers); + err_warn: + WARN(1, "Could not allocate percpu trace_printk buffer"); + return -ENOMEM; +} + +void trace_printk_init_buffers(void) +{ + static int buffers_allocated; + + if (buffers_allocated) + return; + + if (alloc_percpu_trace_buffer()) + return; + + pr_info("ftrace: Allocated trace_printk buffers\n"); + + buffers_allocated = 1; +} + /** * trace_vbprintk - write binary msg to tracing buffer * */ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { - static arch_spinlock_t trace_buf_lock = - (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; - static u32 trace_buf[TRACE_BUF_SIZE]; - struct ftrace_event_call *call = &event_bprint; struct ring_buffer_event *event; struct ring_buffer *buffer; struct trace_array *tr = &global_trace; - struct trace_array_cpu *data; struct bprint_entry *entry; unsigned long flags; - int disable; - int cpu, len = 0, size, pc; + char *tbuffer; + int len = 0, size, pc; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; @@ -1526,43 +1596,36 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) pc = preempt_count(); preempt_disable_notrace(); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disable = atomic_inc_return(&data->disabled); - if (unlikely(disable != 1)) + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; goto out; + } - /* Lockdep uses trace_printk for lock tracing */ - local_irq_save(flags); - arch_spin_lock(&trace_buf_lock); - len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args); + len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); - if (len > TRACE_BUF_SIZE || len < 0) - goto out_unlock; + if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) + goto out; + local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, flags, pc); if (!event) - goto out_unlock; + goto out; entry = ring_buffer_event_data(event); entry->ip = ip; entry->fmt = fmt; - memcpy(entry->buf, trace_buf, sizeof(u32) * len); + memcpy(entry->buf, tbuffer, sizeof(u32) * len); if (!filter_check_discard(call, entry, buffer, event)) { ring_buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } -out_unlock: - arch_spin_unlock(&trace_buf_lock); - local_irq_restore(flags); - out: - atomic_dec_return(&data->disabled); preempt_enable_notrace(); unpause_graph_tracing(); @@ -1588,58 +1651,53 @@ int trace_array_printk(struct trace_array *tr, int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { - static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED; - static char trace_buf[TRACE_BUF_SIZE]; - struct ftrace_event_call *call = &event_print; struct ring_buffer_event *event; struct ring_buffer *buffer; - struct trace_array_cpu *data; - int cpu, len = 0, size, pc; + int len = 0, size, pc; struct print_entry *entry; - unsigned long irq_flags; - int disable; + unsigned long flags; + char *tbuffer; if (tracing_disabled || tracing_selftest_running) return 0; + /* Don't pollute graph traces with trace_vprintk internals */ + pause_graph_tracing(); + pc = preempt_count(); preempt_disable_notrace(); - cpu = raw_smp_processor_id(); - data = tr->data[cpu]; - disable = atomic_inc_return(&data->disabled); - if (unlikely(disable != 1)) + + tbuffer = get_trace_buf(); + if (!tbuffer) { + len = 0; goto out; + } - pause_graph_tracing(); - raw_local_irq_save(irq_flags); - arch_spin_lock(&trace_buf_lock); - len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); + len = vsnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); + if (len > TRACE_BUF_SIZE) + goto out; + local_save_flags(flags); size = sizeof(*entry) + len + 1; buffer = tr->buffer; event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, - irq_flags, pc); + flags, pc); if (!event) - goto out_unlock; + goto out; entry = ring_buffer_event_data(event); entry->ip = ip; - memcpy(&entry->buf, trace_buf, len); + memcpy(&entry->buf, tbuffer, len); entry->buf[len] = '\0'; if (!filter_check_discard(call, entry, buffer, event)) { ring_buffer_unlock_commit(buffer, event); - ftrace_trace_stack(buffer, irq_flags, 6, pc); + ftrace_trace_stack(buffer, flags, 6, pc); } - - out_unlock: - arch_spin_unlock(&trace_buf_lock); - raw_local_irq_restore(irq_flags); - unpause_graph_tracing(); out: - atomic_dec_return(&data->disabled); preempt_enable_notrace(); + unpause_graph_tracing(); return len; } @@ -1652,14 +1710,9 @@ EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { - /* Don't allow ftrace to trace into the ring buffers */ - ftrace_disable_cpu(); - iter->idx++; if (iter->buffer_iter[iter->cpu]) ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); - - ftrace_enable_cpu(); } static struct trace_entry * @@ -1669,17 +1722,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu]; - /* Don't allow ftrace to trace into the ring buffers */ - ftrace_disable_cpu(); - if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); else event = ring_buffer_peek(iter->tr->buffer, cpu, ts, lost_events); - ftrace_enable_cpu(); - if (event) { iter->ent_size = ring_buffer_event_length(event); return ring_buffer_event_data(event); @@ -1769,11 +1817,8 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter) static void trace_consume(struct trace_iterator *iter) { - /* Don't allow ftrace to trace into the ring buffers */ - ftrace_disable_cpu(); ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts, &iter->lost_events); - ftrace_enable_cpu(); } static void *s_next(struct seq_file *m, void *v, loff_t *pos) @@ -1862,16 +1907,12 @@ static void *s_start(struct seq_file *m, loff_t *pos) iter->cpu = 0; iter->idx = -1; - ftrace_disable_cpu(); - if (cpu_file == TRACE_PIPE_ALL_CPU) { for_each_tracing_cpu(cpu) tracing_iter_reset(iter, cpu); } else tracing_iter_reset(iter, cpu_file); - ftrace_enable_cpu(); - iter->leftover = 0; for (p = iter; p && l < *pos; p = s_next(m, p, &l)) ; @@ -2332,15 +2373,13 @@ static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file) { long cpu_file = (long) inode->i_private; - void *fail_ret = ERR_PTR(-ENOMEM); struct trace_iterator *iter; - struct seq_file *m; - int cpu, ret; + int cpu; if (tracing_disabled) return ERR_PTR(-ENODEV); - iter = kzalloc(sizeof(*iter), GFP_KERNEL); + iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter)); if (!iter) return ERR_PTR(-ENOMEM); @@ -2397,32 +2436,15 @@ __tracing_open(struct inode *inode, struct file *file) tracing_iter_reset(iter, cpu); } - ret = seq_open(file, &tracer_seq_ops); - if (ret < 0) { - fail_ret = ERR_PTR(ret); - goto fail_buffer; - } - - m = file->private_data; - m->private = iter; - mutex_unlock(&trace_types_lock); return iter; - fail_buffer: - for_each_tracing_cpu(cpu) { - if (iter->buffer_iter[cpu]) - ring_buffer_read_finish(iter->buffer_iter[cpu]); - } - free_cpumask_var(iter->started); - tracing_start(); fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); - kfree(iter); - - return fail_ret; + seq_release_private(inode, file); + return ERR_PTR(-ENOMEM); } int tracing_open_generic(struct inode *inode, struct file *filp) @@ -2458,11 +2480,10 @@ static int tracing_release(struct inode *inode, struct file *file) tracing_start(); mutex_unlock(&trace_types_lock); - seq_release(inode, file); mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); kfree(iter->trace); - kfree(iter); + seq_release_private(inode, file); return 0; } @@ -2974,7 +2995,14 @@ int tracer_init(struct tracer *t, struct trace_array *tr) return t->init(tr); } -static int __tracing_resize_ring_buffer(unsigned long size) +static void set_buffer_entries(struct trace_array *tr, unsigned long val) +{ + int cpu; + for_each_tracing_cpu(cpu) + tr->data[cpu]->entries = val; +} + +static int __tracing_resize_ring_buffer(unsigned long size, int cpu) { int ret; @@ -2985,19 +3013,32 @@ static int __tracing_resize_ring_buffer(unsigned long size) */ ring_buffer_expanded = 1; - ret = ring_buffer_resize(global_trace.buffer, size); + ret = ring_buffer_resize(global_trace.buffer, size, cpu); if (ret < 0) return ret; if (!current_trace->use_max_tr) goto out; - ret = ring_buffer_resize(max_tr.buffer, size); + ret = ring_buffer_resize(max_tr.buffer, size, cpu); if (ret < 0) { - int r; + int r = 0; + + if (cpu == RING_BUFFER_ALL_CPUS) { + int i; + for_each_tracing_cpu(i) { + r = ring_buffer_resize(global_trace.buffer, + global_trace.data[i]->entries, + i); + if (r < 0) + break; + } + } else { + r = ring_buffer_resize(global_trace.buffer, + global_trace.data[cpu]->entries, + cpu); + } - r = ring_buffer_resize(global_trace.buffer, - global_trace.entries); if (r < 0) { /* * AARGH! We are left with different @@ -3019,14 +3060,21 @@ static int __tracing_resize_ring_buffer(unsigned long size) return ret; } - max_tr.entries = size; + if (cpu == RING_BUFFER_ALL_CPUS) + set_buffer_entries(&max_tr, size); + else + max_tr.data[cpu]->entries = size; + out: - global_trace.entries = size; + if (cpu == RING_BUFFER_ALL_CPUS) + set_buffer_entries(&global_trace, size); + else + global_trace.data[cpu]->entries = size; return ret; } -static ssize_t tracing_resize_ring_buffer(unsigned long size) +static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id) { int cpu, ret = size; @@ -3042,12 +3090,19 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size) atomic_inc(&max_tr.data[cpu]->disabled); } - if (size != global_trace.entries) - ret = __tracing_resize_ring_buffer(size); + if (cpu_id != RING_BUFFER_ALL_CPUS) { + /* make sure, this cpu is enabled in the mask */ + if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) { + ret = -EINVAL; + goto out; + } + } + ret = __tracing_resize_ring_buffer(size, cpu_id); if (ret < 0) ret = -ENOMEM; +out: for_each_tracing_cpu(cpu) { if (global_trace.data[cpu]) atomic_dec(&global_trace.data[cpu]->disabled); @@ -3078,7 +3133,8 @@ int tracing_update_buffers(void) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) - ret = __tracing_resize_ring_buffer(trace_buf_size); + ret = __tracing_resize_ring_buffer(trace_buf_size, + RING_BUFFER_ALL_CPUS); mutex_unlock(&trace_types_lock); return ret; @@ -3102,7 +3158,8 @@ static int tracing_set_tracer(const char *buf) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) { - ret = __tracing_resize_ring_buffer(trace_buf_size); + ret = __tracing_resize_ring_buffer(trace_buf_size, + RING_BUFFER_ALL_CPUS); if (ret < 0) goto out; ret = 0; @@ -3128,8 +3185,8 @@ static int tracing_set_tracer(const char *buf) * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ - ring_buffer_resize(max_tr.buffer, 1); - max_tr.entries = 1; + ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS); + set_buffer_entries(&max_tr, 1); } destroy_trace_option_files(topts); @@ -3137,10 +3194,17 @@ static int tracing_set_tracer(const char *buf) topts = create_trace_option_files(current_trace); if (current_trace->use_max_tr) { - ret = ring_buffer_resize(max_tr.buffer, global_trace.entries); - if (ret < 0) - goto out; - max_tr.entries = global_trace.entries; + int cpu; + /* we need to make per cpu buffer sizes equivalent */ + for_each_tracing_cpu(cpu) { + ret = ring_buffer_resize(max_tr.buffer, + global_trace.data[cpu]->entries, + cpu); + if (ret < 0) + goto out; + max_tr.data[cpu]->entries = + global_trace.data[cpu]->entries; + } } if (t->init) { @@ -3642,30 +3706,82 @@ out_err: goto out; } +struct ftrace_entries_info { + struct trace_array *tr; + int cpu; +}; + +static int tracing_entries_open(struct inode *inode, struct file *filp) +{ + struct ftrace_entries_info *info; + + if (tracing_disabled) + return -ENODEV; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->tr = &global_trace; + info->cpu = (unsigned long)inode->i_private; + + filp->private_data = info; + + return 0; +} + static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct trace_array *tr = filp->private_data; - char buf[96]; - int r; + struct ftrace_entries_info *info = filp->private_data; + struct trace_array *tr = info->tr; + char buf[64]; + int r = 0; + ssize_t ret; mutex_lock(&trace_types_lock); - if (!ring_buffer_expanded) - r = sprintf(buf, "%lu (expanded: %lu)\n", - tr->entries >> 10, - trace_buf_size >> 10); - else - r = sprintf(buf, "%lu\n", tr->entries >> 10); + + if (info->cpu == RING_BUFFER_ALL_CPUS) { + int cpu, buf_size_same; + unsigned long size; + + size = 0; + buf_size_same = 1; + /* check if all cpu sizes are same */ + for_each_tracing_cpu(cpu) { + /* fill in the size from first enabled cpu */ + if (size == 0) + size = tr->data[cpu]->entries; + if (size != tr->data[cpu]->entries) { + buf_size_same = 0; + break; + } + } + + if (buf_size_same) { + if (!ring_buffer_expanded) + r = sprintf(buf, "%lu (expanded: %lu)\n", + size >> 10, + trace_buf_size >> 10); + else + r = sprintf(buf, "%lu\n", size >> 10); + } else + r = sprintf(buf, "X\n"); + } else + r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10); + mutex_unlock(&trace_types_lock); - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + return ret; } static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { + struct ftrace_entries_info *info = filp->private_data; unsigned long val; int ret; @@ -3680,7 +3796,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, /* value is in KB */ val <<= 10; - ret = tracing_resize_ring_buffer(val); + ret = tracing_resize_ring_buffer(val, info->cpu); if (ret < 0) return ret; @@ -3689,6 +3805,16 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, return cnt; } +static int +tracing_entries_release(struct inode *inode, struct file *filp) +{ + struct ftrace_entries_info *info = filp->private_data; + + kfree(info); + + return 0; +} + static ssize_t tracing_total_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -3700,7 +3826,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += tr->entries >> 10; + size += tr->data[cpu]->entries >> 10; if (!ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } @@ -3734,7 +3860,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) if (trace_flags & TRACE_ITER_STOP_ON_FREE) tracing_off(); /* resize the ring buffer to 0 */ - tracing_resize_ring_buffer(0); + tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS); return 0; } @@ -3933,9 +4059,10 @@ static const struct file_operations tracing_pipe_fops = { }; static const struct file_operations tracing_entries_fops = { - .open = tracing_open_generic, + .open = tracing_entries_open, .read = tracing_entries_read, .write = tracing_entries_write, + .release = tracing_entries_release, .llseek = generic_file_llseek, }; @@ -4387,6 +4514,9 @@ static void tracing_init_debugfs_percpu(long cpu) trace_create_file("stats", 0444, d_cpu, (void *) cpu, &tracing_stats_fops); + + trace_create_file("buffer_size_kb", 0444, d_cpu, + (void *) cpu, &tracing_entries_fops); } #ifdef CONFIG_FTRACE_SELFTEST @@ -4718,7 +4848,7 @@ static __init int tracer_init_debugfs(void) (void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops); trace_create_file("buffer_size_kb", 0644, d_tracer, - &global_trace, &tracing_entries_fops); + (void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops); trace_create_file("buffer_total_size_kb", 0444, d_tracer, &global_trace, &tracing_total_entries_fops); @@ -4957,6 +5087,10 @@ __init static int tracer_alloc_buffers(void) if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL)) goto out_free_buffer_mask; + /* Only allocate trace_printk buffers if a trace_printk exists */ + if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + trace_printk_init_buffers(); + /* To save memory, keep the ring buffer size to its minimum */ if (ring_buffer_expanded) ring_buf_size = trace_buf_size; @@ -4975,7 +5109,6 @@ __init static int tracer_alloc_buffers(void) WARN_ON(1); goto out_free_cpumask; } - global_trace.entries = ring_buffer_size(global_trace.buffer); if (global_trace.buffer_disabled) tracing_off(); @@ -4988,7 +5121,6 @@ __init static int tracer_alloc_buffers(void) ring_buffer_free(global_trace.buffer); goto out_free_cpumask; } - max_tr.entries = 1; #endif /* Allocate the first page for all buffers */ @@ -4997,6 +5129,11 @@ __init static int tracer_alloc_buffers(void) max_tr.data[i] = &per_cpu(max_tr_data, i); } + set_buffer_entries(&global_trace, ring_buf_size); +#ifdef CONFIG_TRACER_MAX_TRACE + set_buffer_entries(&max_tr, 1); +#endif + trace_init_cmdlines(); register_tracer(&nop_trace); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f95d65da6db8..6c6f7933eede 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -131,6 +131,7 @@ struct trace_array_cpu { atomic_t disabled; void *buffer_page; /* ring buffer spare */ + unsigned long entries; unsigned long saved_latency; unsigned long critical_start; unsigned long critical_end; @@ -152,7 +153,6 @@ struct trace_array_cpu { */ struct trace_array { struct ring_buffer *buffer; - unsigned long entries; int cpu; int buffer_disabled; cycle_t time_start; @@ -826,6 +826,8 @@ extern struct list_head ftrace_events; extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; +void trace_printk_init_buffers(void); + #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ extern struct ftrace_event_call \ diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 6fd4ffd042f9..a9077c1b4ad3 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -51,6 +51,10 @@ void hold_module_trace_bprintk_format(const char **start, const char **end) const char **iter; char *fmt; + /* allocate the trace_printk per cpu buffers */ + if (start != end) + trace_printk_init_buffers(); + mutex_lock(&btrace_mutex); for (iter = start; iter < end; iter++) { struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter); diff --git a/tools/Makefile b/tools/Makefile new file mode 100644 index 000000000000..3ae43947a171 --- /dev/null +++ b/tools/Makefile @@ -0,0 +1,77 @@ +include scripts/Makefile.include + +help: + @echo 'Possible targets:' + @echo '' + @echo ' cpupower - a tool for all things x86 CPU power' + @echo ' firewire - the userspace part of nosy, an IEEE-1394 traffic sniffer' + @echo ' lguest - a minimal 32-bit x86 hypervisor' + @echo ' perf - Linux performance measurement and analysis tool' + @echo ' selftests - various kernel selftests' + @echo ' turbostat - Intel CPU idle stats and freq reporting tool' + @echo ' usb - USB testing tools' + @echo ' virtio - vhost test module' + @echo ' vm - misc vm tools' + @echo ' x86_energy_perf_policy - Intel energy policy tool' + @echo '' + @echo 'You can do:' + @echo ' $$ make -C tools/<tool>_install' + @echo '' + @echo ' from the kernel command line to build and install one of' + @echo ' the tools above' + @echo '' + @echo ' $$ make tools/install' + @echo '' + @echo ' installs all tools.' + @echo '' + @echo 'Cleaning targets:' + @echo '' + @echo ' all of the above with the "_clean" string appended cleans' + @echo ' the respective build directory.' + @echo ' clean: a summary clean target to clean _all_ folders' + +cpupower: FORCE + $(QUIET_SUBDIR0)power/$@/ $(QUIET_SUBDIR1) + +firewire lguest perf usb virtio vm: FORCE + $(QUIET_SUBDIR0)$@/ $(QUIET_SUBDIR1) + +selftests: FORCE + $(QUIET_SUBDIR0)testing/$@/ $(QUIET_SUBDIR1) + +turbostat x86_energy_perf_policy: FORCE + $(QUIET_SUBDIR0)power/x86/$@/ $(QUIET_SUBDIR1) + +cpupower_install: + $(QUIET_SUBDIR0)power/$(@:_install=)/ $(QUIET_SUBDIR1) install + +firewire_install lguest_install perf_install usb_install virtio_install vm_install: + $(QUIET_SUBDIR0)$(@:_install=)/ $(QUIET_SUBDIR1) install + +selftests_install: + $(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) install + +turbostat_install x86_energy_perf_policy_install: + $(QUIET_SUBDIR0)power/x86/$(@:_install=)/ $(QUIET_SUBDIR1) install + +install: cpupower_install firewire_install lguest_install perf_install \ + selftests_install turbostat_install usb_install virtio_install \ + vm_install x86_energy_perf_policy_install + +cpupower_clean: + $(QUIET_SUBDIR0)power/cpupower/ $(QUIET_SUBDIR1) clean + +firewire_clean lguest_clean perf_clean usb_clean virtio_clean vm_clean: + $(QUIET_SUBDIR0)$(@:_clean=)/ $(QUIET_SUBDIR1) clean + +selftests_clean: + $(QUIET_SUBDIR0)testing/$(@:_clean=)/ $(QUIET_SUBDIR1) clean + +turbostat_clean x86_energy_perf_policy_clean: + $(QUIET_SUBDIR0)power/x86/$(@:_clean=)/ $(QUIET_SUBDIR1) clean + +clean: cpupower_clean firewire_clean lguest_clean perf_clean selftests_clean \ + turbostat_clean usb_clean virtio_clean vm_clean \ + x86_energy_perf_policy_clean + +.PHONY: FORCE diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example index d1448668f4d4..42c6fd2ae85d 100644 --- a/tools/perf/Documentation/perfconfig.example +++ b/tools/perf/Documentation/perfconfig.example @@ -6,6 +6,7 @@ normal = black, lightgray selected = lightgray, magenta code = blue, lightgray + addr = magenta, lightgray [tui] diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 92271d32bc30..398094c3d3c9 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -1,18 +1,10 @@ -ifeq ("$(origin O)", "command line") - OUTPUT := $(O)/ -endif +include ../scripts/Makefile.include # The default target of this Makefile is... all: include config/utilities.mak -ifneq ($(OUTPUT),) -# check that the output directory actually exists -OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) -$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) -endif - # Define V to have a more verbose compile. # # Define O to save output files in a separate directory. @@ -84,31 +76,6 @@ ifneq ($(WERROR),0) CFLAGS_WERROR := -Werror endif -# -# Include saner warnings here, which can catch bugs: -# - -EXTRA_WARNINGS := -Wformat -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wformat-security -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wformat-y2k -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wshadow -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Winit-self -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wpacked -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wredundant-decls -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-aliasing=3 -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-default -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wswitch-enum -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wno-system-headers -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wundef -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wwrite-strings -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wbad-function-cast -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-declarations -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wmissing-prototypes -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wnested-externs -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wold-style-definition -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wstrict-prototypes -EXTRA_WARNINGS := $(EXTRA_WARNINGS) -Wdeclaration-after-statement - ifeq ("$(origin DEBUG)", "command line") PERF_DEBUG = $(DEBUG) endif @@ -333,6 +300,7 @@ LIB_H += util/cpumap.h LIB_H += util/top.h LIB_H += $(ARCH_INCLUDE) LIB_H += util/cgroup.h +LIB_H += util/target.h LIB_OBJS += $(OUTPUT)util/abspath.o LIB_OBJS += $(OUTPUT)util/alias.o @@ -394,6 +362,7 @@ LIB_OBJS += $(OUTPUT)util/util.o LIB_OBJS += $(OUTPUT)util/xyarray.o LIB_OBJS += $(OUTPUT)util/cpumap.o LIB_OBJS += $(OUTPUT)util/cgroup.o +LIB_OBJS += $(OUTPUT)util/target.o BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o @@ -506,22 +475,23 @@ else # Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h BASIC_CFLAGS += -I/usr/include/slang EXTLIBS += -lnewt -lslang - LIB_OBJS += $(OUTPUT)util/ui/setup.o - LIB_OBJS += $(OUTPUT)util/ui/browser.o - LIB_OBJS += $(OUTPUT)util/ui/browsers/annotate.o - LIB_OBJS += $(OUTPUT)util/ui/browsers/hists.o - LIB_OBJS += $(OUTPUT)util/ui/browsers/map.o - LIB_OBJS += $(OUTPUT)util/ui/helpline.o - LIB_OBJS += $(OUTPUT)util/ui/progress.o - LIB_OBJS += $(OUTPUT)util/ui/util.o - LIB_H += util/ui/browser.h - LIB_H += util/ui/browsers/map.h - LIB_H += util/ui/helpline.h - LIB_H += util/ui/keysyms.h - LIB_H += util/ui/libslang.h - LIB_H += util/ui/progress.h - LIB_H += util/ui/util.h - LIB_H += util/ui/ui.h + LIB_OBJS += $(OUTPUT)ui/setup.o + LIB_OBJS += $(OUTPUT)ui/browser.o + LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o + LIB_OBJS += $(OUTPUT)ui/browsers/hists.o + LIB_OBJS += $(OUTPUT)ui/browsers/map.o + LIB_OBJS += $(OUTPUT)ui/helpline.o + LIB_OBJS += $(OUTPUT)ui/progress.o + LIB_OBJS += $(OUTPUT)ui/util.o + LIB_OBJS += $(OUTPUT)ui/tui/setup.o + LIB_H += ui/browser.h + LIB_H += ui/browsers/map.h + LIB_H += ui/helpline.h + LIB_H += ui/keysyms.h + LIB_H += ui/libslang.h + LIB_H += ui/progress.h + LIB_H += ui/util.h + LIB_H += ui/ui.h endif endif @@ -535,7 +505,12 @@ else else BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0) EXTLIBS += $(shell pkg-config --libs gtk+-2.0) - LIB_OBJS += $(OUTPUT)util/gtk/browser.o + LIB_OBJS += $(OUTPUT)ui/gtk/browser.o + LIB_OBJS += $(OUTPUT)ui/gtk/setup.o + # Make sure that it'd be included only once. + ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),) + LIB_OBJS += $(OUTPUT)ui/setup.o + endif endif endif @@ -678,18 +653,6 @@ else endif endif -ifneq ($(findstring $(MAKEFLAGS),s),s) -ifndef V - QUIET_CC = @echo ' ' CC $@; - QUIET_AR = @echo ' ' AR $@; - QUIET_LINK = @echo ' ' LINK $@; - QUIET_MKDIR = @echo ' ' MKDIR $@; - QUIET_GEN = @echo ' ' GEN $@; - QUIET_FLEX = @echo ' ' FLEX $@; - QUIET_BISON = @echo ' ' BISON $@; -endif -endif - ifdef ASCIIDOC8 export ASCIIDOC8 endif @@ -800,16 +763,16 @@ $(OUTPUT)util/exec_cmd.o: util/exec_cmd.c $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/config.o: util/config.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $< -$(OUTPUT)util/ui/browser.o: util/ui/browser.c $(OUTPUT)PERF-CFLAGS +$(OUTPUT)ui/browser.o: ui/browser.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< -$(OUTPUT)util/ui/browsers/annotate.o: util/ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS +$(OUTPUT)ui/browsers/annotate.o: ui/browsers/annotate.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< -$(OUTPUT)util/ui/browsers/hists.o: util/ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS +$(OUTPUT)ui/browsers/hists.o: ui/browsers/hists.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< -$(OUTPUT)util/ui/browsers/map.o: util/ui/browsers/map.c $(OUTPUT)PERF-CFLAGS +$(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DENABLE_SLFUTURE_CONST $< $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index be4e1eee782e..8a3dfac161e2 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -44,7 +44,6 @@ struct perf_record { struct perf_evlist *evlist; struct perf_session *session; const char *progname; - const char *uid_str; int output; unsigned int page_size; int realtime_prio; @@ -218,7 +217,7 @@ try_again: if (err == EPERM || err == EACCES) { ui__error_paranoid(); exit(EXIT_FAILURE); - } else if (err == ENODEV && opts->cpu_list) { + } else if (err == ENODEV && opts->target.cpu_list) { die("No such device - did you specify" " an out-of-range profile CPU?\n"); } else if (err == EINVAL) { @@ -243,9 +242,13 @@ try_again: /* * If it's cycles then fall back to hrtimer * based cpu-clock-tick sw counter, which - * is always available even if no PMU support: + * is always available even if no PMU support. + * + * PPC returns ENXIO until 2.6.37 (behavior changed + * with commit b0a873e). */ - if (attr->type == PERF_TYPE_HARDWARE + if ((err == ENOENT || err == ENXIO) + && attr->type == PERF_TYPE_HARDWARE && attr->config == PERF_COUNT_HW_CPU_CYCLES) { if (verbose) @@ -253,6 +256,10 @@ try_again: "trying to fall back to cpu-clock-ticks\n"); attr->type = PERF_TYPE_SOFTWARE; attr->config = PERF_COUNT_SW_CPU_CLOCK; + if (pos->name) { + free(pos->name); + pos->name = NULL; + } goto try_again; } @@ -578,7 +585,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) perf_session__process_machines(session, tool, perf_event__synthesize_guest_os); - if (!opts->system_wide) + if (!opts->target.system_wide) perf_event__synthesize_thread_map(tool, evsel_list->threads, process_synthesized_event, machine); @@ -747,6 +754,9 @@ static struct perf_record record = { .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, .freq = 1000, + .target = { + .uses_mmap = true, + }, }, .write_mode = WRITE_FORCE, .file_new = true, @@ -765,9 +775,9 @@ const struct option record_options[] = { parse_events_option), OPT_CALLBACK(0, "filter", &record.evlist, "filter", "event filter", parse_filter), - OPT_STRING('p', "pid", &record.opts.target_pid, "pid", + OPT_STRING('p', "pid", &record.opts.target.pid, "pid", "record events on existing process id"), - OPT_STRING('t', "tid", &record.opts.target_tid, "tid", + OPT_STRING('t', "tid", &record.opts.target.tid, "tid", "record events on existing thread id"), OPT_INTEGER('r', "realtime", &record.realtime_prio, "collect data with this RT SCHED_FIFO priority"), @@ -775,11 +785,11 @@ const struct option record_options[] = { "collect data without buffering"), OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples, "collect raw sample records from all opened counters"), - OPT_BOOLEAN('a', "all-cpus", &record.opts.system_wide, + OPT_BOOLEAN('a', "all-cpus", &record.opts.target.system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('A', "append", &record.append_file, "append to the output file to do incremental profiling"), - OPT_STRING('C', "cpu", &record.opts.cpu_list, "cpu", + OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu", "list of cpus to monitor"), OPT_BOOLEAN('f', "force", &record.force, "overwrite existing data file (deprecated)"), @@ -813,7 +823,8 @@ const struct option record_options[] = { OPT_CALLBACK('G', "cgroup", &record.evlist, "name", "monitor event in cgroup name only", parse_cgroups), - OPT_STRING('u', "uid", &record.uid_str, "user", "user to profile"), + OPT_STRING('u', "uid", &record.opts.target.uid_str, "user", + "user to profile"), OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack, "branch any", "sample any taken branches", @@ -831,6 +842,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) struct perf_evsel *pos; struct perf_evlist *evsel_list; struct perf_record *rec = &record; + char errbuf[BUFSIZ]; perf_header__set_cmdline(argc, argv); @@ -842,8 +854,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); - if (!argc && !rec->opts.target_pid && !rec->opts.target_tid && - !rec->opts.system_wide && !rec->opts.cpu_list && !rec->uid_str) + if (!argc && perf_target__none(&rec->opts.target)) usage_with_options(record_usage, record_options); if (rec->force && rec->append_file) { @@ -856,7 +867,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) rec->write_mode = WRITE_FORCE; } - if (nr_cgroups && !rec->opts.system_wide) { + if (nr_cgroups && !rec->opts.target.system_wide) { fprintf(stderr, "cgroup monitoring only available in" " system-wide mode\n"); usage_with_options(record_usage, record_options); @@ -883,17 +894,25 @@ int cmd_record(int argc, const char **argv, const char *prefix __used) goto out_symbol_exit; } - rec->opts.uid = parse_target_uid(rec->uid_str, rec->opts.target_tid, - rec->opts.target_pid); - if (rec->uid_str != NULL && rec->opts.uid == UINT_MAX - 1) - goto out_free_fd; + err = perf_target__validate(&rec->opts.target); + if (err) { + perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ); + ui__warning("%s", errbuf); + } + + err = perf_target__parse_uid(&rec->opts.target); + if (err) { + int saved_errno = errno; - if (rec->opts.target_pid) - rec->opts.target_tid = rec->opts.target_pid; + perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ); + ui__warning("%s", errbuf); + + err = -saved_errno; + goto out_free_fd; + } - if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid, - rec->opts.target_tid, rec->opts.uid, - rec->opts.cpu_list) < 0) + err = -ENOMEM; + if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); list_for_each_entry(pos, &evsel_list->entries, node) { diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index cdae9b2db1cc..d58e41445d0d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -296,12 +296,15 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, { size_t ret; char unit; - unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE]; + unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE]; + u64 nr_events = self->stats.total_period; - nr_events = convert_unit(nr_events, &unit); - ret = fprintf(fp, "# Events: %lu%c", nr_events, unit); + nr_samples = convert_unit(nr_samples, &unit); + ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit); if (evname != NULL) - ret += fprintf(fp, " %s", evname); + ret += fprintf(fp, " of event '%s'", evname); + + ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); return ret + fprintf(fp, "\n#\n"); } @@ -680,14 +683,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __used) } - if (strcmp(report.input_name, "-") != 0) { - if (report.use_gtk) - perf_gtk_setup_browser(argc, argv, true); - else - setup_browser(true); - } else { + if (strcmp(report.input_name, "-") != 0) + setup_browser(true); + else use_browser = 0; - } /* * Only in the newt browser we are doing integrated annotation, diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 1e5e9b270f5e..62ae30d34fa6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -173,24 +173,23 @@ static struct perf_event_attr very_very_detailed_attrs[] = { -struct perf_evlist *evsel_list; +static struct perf_evlist *evsel_list; -static bool system_wide = false; -static int run_idx = 0; +static struct perf_target target = { + .uid = UINT_MAX, +}; +static int run_idx = 0; static int run_count = 1; static bool no_inherit = false; static bool scale = true; static bool no_aggr = false; -static const char *target_pid; -static const char *target_tid; static pid_t child_pid = -1; static bool null_run = false; static int detailed_run = 0; static bool sync_run = false; static bool big_num = true; static int big_num_opt = -1; -static const char *cpu_list; static const char *csv_sep = NULL; static bool csv_output = false; static bool group = false; @@ -265,18 +264,18 @@ static double stddev_stats(struct stats *stats) return sqrt(variance_mean); } -struct stats runtime_nsecs_stats[MAX_NR_CPUS]; -struct stats runtime_cycles_stats[MAX_NR_CPUS]; -struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS]; -struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS]; -struct stats runtime_branches_stats[MAX_NR_CPUS]; -struct stats runtime_cacherefs_stats[MAX_NR_CPUS]; -struct stats runtime_l1_dcache_stats[MAX_NR_CPUS]; -struct stats runtime_l1_icache_stats[MAX_NR_CPUS]; -struct stats runtime_ll_cache_stats[MAX_NR_CPUS]; -struct stats runtime_itlb_cache_stats[MAX_NR_CPUS]; -struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS]; -struct stats walltime_nsecs_stats; +static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; +static struct stats runtime_cycles_stats[MAX_NR_CPUS]; +static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS]; +static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS]; +static struct stats runtime_branches_stats[MAX_NR_CPUS]; +static struct stats runtime_cacherefs_stats[MAX_NR_CPUS]; +static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS]; +static struct stats runtime_l1_icache_stats[MAX_NR_CPUS]; +static struct stats runtime_ll_cache_stats[MAX_NR_CPUS]; +static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS]; +static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS]; +static struct stats walltime_nsecs_stats; static int create_perf_stat_counter(struct perf_evsel *evsel, struct perf_evsel *first) @@ -299,15 +298,15 @@ retry: if (exclude_guest_missing) evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; - if (system_wide) { + if (perf_target__has_cpu(&target)) { ret = perf_evsel__open_per_cpu(evsel, evsel_list->cpus, - group, group_fd); + group, group_fd); if (ret) goto check_ret; return 0; } - if (!target_pid && !target_tid && (!group || evsel == first)) { + if (!perf_target__has_task(&target) && (!group || evsel == first)) { attr->disabled = 1; attr->enable_on_exec = 1; } @@ -471,7 +470,7 @@ static int run_perf_stat(int argc __used, const char **argv) exit(-1); } - if (!target_tid && !target_pid && !system_wide) + if (perf_target__none(&target)) evsel_list->threads->map[0] = child_pid; /* @@ -506,7 +505,7 @@ static int run_perf_stat(int argc __used, const char **argv) error("You may not have permission to collect %sstats.\n" "\t Consider tweaking" " /proc/sys/kernel/perf_event_paranoid or running as root.", - system_wide ? "system-wide " : ""); + target.system_wide ? "system-wide " : ""); } else { error("open_counter returned with %d (%s). " "/bin/dmesg may provide additional information.\n", @@ -998,14 +997,14 @@ static void print_stat(int argc, const char **argv) if (!csv_output) { fprintf(output, "\n"); fprintf(output, " Performance counter stats for "); - if (!target_pid && !target_tid) { + if (!perf_target__has_task(&target)) { fprintf(output, "\'%s", argv[0]); for (i = 1; i < argc; i++) fprintf(output, " %s", argv[i]); - } else if (target_pid) - fprintf(output, "process id \'%s", target_pid); + } else if (target.pid) + fprintf(output, "process id \'%s", target.pid); else - fprintf(output, "thread id \'%s", target_tid); + fprintf(output, "thread id \'%s", target.tid); fprintf(output, "\'"); if (run_count > 1) @@ -1079,11 +1078,11 @@ static const struct option options[] = { "event filter", parse_filter), OPT_BOOLEAN('i', "no-inherit", &no_inherit, "child tasks do not inherit counters"), - OPT_STRING('p', "pid", &target_pid, "pid", + OPT_STRING('p', "pid", &target.pid, "pid", "stat events on existing process id"), - OPT_STRING('t', "tid", &target_tid, "tid", + OPT_STRING('t', "tid", &target.tid, "tid", "stat events on existing thread id"), - OPT_BOOLEAN('a', "all-cpus", &system_wide, + OPT_BOOLEAN('a', "all-cpus", &target.system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('g', "group", &group, "put the counters into a counter group"), @@ -1102,7 +1101,7 @@ static const struct option options[] = { OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, "print large numbers with thousands\' separators", stat__set_big_num), - OPT_STRING('C', "cpu", &cpu_list, "cpu", + OPT_STRING('C', "cpu", &target.cpu_list, "cpu", "list of cpus to monitor in system-wide"), OPT_BOOLEAN('A', "no-aggr", &no_aggr, "disable CPU count aggregation"), @@ -1220,13 +1219,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) } else if (big_num_opt == 0) /* User passed --no-big-num */ big_num = false; - if (!argc && !target_pid && !target_tid) + if (!argc && !perf_target__has_task(&target)) usage_with_options(stat_usage, options); if (run_count <= 0) usage_with_options(stat_usage, options); /* no_aggr, cgroup are for system-wide only */ - if ((no_aggr || nr_cgroups) && !system_wide) { + if ((no_aggr || nr_cgroups) && !perf_target__has_cpu(&target)) { fprintf(stderr, "both cgroup and no-aggregation " "modes only available in system-wide mode\n"); @@ -1236,23 +1235,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used) if (add_default_attributes()) goto out; - if (target_pid) - target_tid = target_pid; + perf_target__validate(&target); - evsel_list->threads = thread_map__new_str(target_pid, - target_tid, UINT_MAX); - if (evsel_list->threads == NULL) { - pr_err("Problems finding threads of monitor\n"); - usage_with_options(stat_usage, options); - } - - if (system_wide) - evsel_list->cpus = cpu_map__new(cpu_list); - else - evsel_list->cpus = cpu_map__dummy_new(); + if (perf_evlist__create_maps(evsel_list, &target) < 0) { + if (perf_target__has_task(&target)) + pr_err("Problems finding threads of monitor\n"); + if (perf_target__has_cpu(&target)) + perror("failed to parse CPUs map"); - if (evsel_list->cpus == NULL) { - perror("failed to parse CPUs map"); usage_with_options(stat_usage, options); return -1; } diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c index 223ffdcc0fd8..6c47376e29d8 100644 --- a/tools/perf/builtin-test.c +++ b/tools/perf/builtin-test.c @@ -1195,6 +1195,10 @@ realloc: static int test__PERF_RECORD(void) { struct perf_record_opts opts = { + .target = { + .uid = UINT_MAX, + .uses_mmap = true, + }, .no_delay = true, .freq = 10, .mmap_pages = 256, @@ -1237,8 +1241,7 @@ static int test__PERF_RECORD(void) * perf_evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - err = perf_evlist__create_maps(evlist, opts.target_pid, - opts.target_tid, UINT_MAX, opts.cpu_list); + err = perf_evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; @@ -1579,8 +1582,6 @@ static int __test__rdpmc(void) sa.sa_sigaction = segfault_handler; sigaction(SIGSEGV, &sa, NULL); - fprintf(stderr, "\n\n"); - fd = sys_perf_event_open(&attr, 0, -1, -1, 0); if (fd < 0) { die("Error: sys_perf_event_open() syscall returned " @@ -1605,7 +1606,7 @@ static int __test__rdpmc(void) loops *= 10; delta = now - stamp; - fprintf(stderr, "%14d: %14Lu\n", n, (long long)delta); + pr_debug("%14d: %14Lu\n", n, (long long)delta); delta_sum += delta; } @@ -1613,7 +1614,7 @@ static int __test__rdpmc(void) munmap(addr, page_size); close(fd); - fprintf(stderr, " "); + pr_debug(" "); if (!delta_sum) return -1; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 8ef59f8262bb..3e981a710c4d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -588,7 +588,7 @@ static void *display_thread_tui(void *arg) * via --uid. */ list_for_each_entry(pos, &top->evlist->entries, node) - pos->hists.uid_filter_str = top->uid_str; + pos->hists.uid_filter_str = top->target.uid_str; perf_evlist__tui_browse_hists(top->evlist, help, perf_top__sort_new_samples, @@ -948,6 +948,10 @@ try_again: attr->type = PERF_TYPE_SOFTWARE; attr->config = PERF_COUNT_SW_CPU_CLOCK; + if (counter->name) { + free(counter->name); + counter->name = strdup(event_name(counter)); + } goto try_again; } @@ -1016,7 +1020,7 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; - if (top->target_tid || top->uid != UINT_MAX) + if (perf_target__has_task(&top->target)) perf_event__synthesize_thread_map(&top->tool, top->evlist->threads, perf_event__process, &top->session->host_machine); @@ -1150,14 +1154,17 @@ static const char * const top_usage[] = { int cmd_top(int argc, const char **argv, const char *prefix __used) { struct perf_evsel *pos; - int status = -ENOMEM; + int status; + char errbuf[BUFSIZ]; struct perf_top top = { .count_filter = 5, .delay_secs = 2, - .uid = UINT_MAX, .freq = 1000, /* 1 KHz */ .mmap_pages = 128, .sym_pcnt_filter = 5, + .target = { + .uses_mmap = true, + }, }; char callchain_default_opt[] = "fractal,0.5,callee"; const struct option options[] = { @@ -1166,13 +1173,13 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) parse_events_option), OPT_INTEGER('c', "count", &top.default_interval, "event period to sample"), - OPT_STRING('p', "pid", &top.target_pid, "pid", + OPT_STRING('p', "pid", &top.target.pid, "pid", "profile events on existing process id"), - OPT_STRING('t', "tid", &top.target_tid, "tid", + OPT_STRING('t', "tid", &top.target.tid, "tid", "profile events on existing thread id"), - OPT_BOOLEAN('a', "all-cpus", &top.system_wide, + OPT_BOOLEAN('a', "all-cpus", &top.target.system_wide, "system-wide collection from all CPUs"), - OPT_STRING('C', "cpu", &top.cpu_list, "cpu", + OPT_STRING('C', "cpu", &top.target.cpu_list, "cpu", "list of cpus to monitor"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, "file", "vmlinux pathname"), @@ -1227,7 +1234,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), - OPT_STRING('u', "uid", &top.uid_str, "user", "user to profile"), + OPT_STRING('u', "uid", &top.target.uid_str, "user", "user to profile"), OPT_END() }; @@ -1253,22 +1260,27 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) setup_browser(false); - top.uid = parse_target_uid(top.uid_str, top.target_tid, top.target_pid); - if (top.uid_str != NULL && top.uid == UINT_MAX - 1) - goto out_delete_evlist; + status = perf_target__validate(&top.target); + if (status) { + perf_target__strerror(&top.target, status, errbuf, BUFSIZ); + ui__warning("%s", errbuf); + } - /* CPU and PID are mutually exclusive */ - if (top.target_tid && top.cpu_list) { - printf("WARNING: PID switch overriding CPU\n"); - sleep(1); - top.cpu_list = NULL; + status = perf_target__parse_uid(&top.target); + if (status) { + int saved_errno = errno; + + perf_target__strerror(&top.target, status, errbuf, BUFSIZ); + ui__warning("%s", errbuf); + + status = -saved_errno; + goto out_delete_evlist; } - if (top.target_pid) - top.target_tid = top.target_pid; + if (perf_target__none(&top.target)) + top.target.system_wide = true; - if (perf_evlist__create_maps(top.evlist, top.target_pid, - top.target_tid, top.uid, top.cpu_list) < 0) + if (perf_evlist__create_maps(top.evlist, &top.target) < 0) usage_with_options(top_usage, options); if (!top.evlist->nr_entries && diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 89e3355ab173..14f1034f14f9 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -207,10 +207,10 @@ extern const char perf_version_string[]; void pthread__unblock_sigwinch(void); +#include "util/target.h" + struct perf_record_opts { - const char *target_pid; - const char *target_tid; - uid_t uid; + struct perf_target target; bool call_graph; bool group; bool inherit_stat; @@ -223,7 +223,6 @@ struct perf_record_opts { bool sample_time; bool sample_id_all_missing; bool exclude_guest_missing; - bool system_wide; bool period; unsigned int freq; unsigned int mmap_pages; @@ -231,7 +230,6 @@ struct perf_record_opts { int branch_stack; u64 default_interval; u64 user_interval; - const char *cpu_list; }; #endif diff --git a/tools/perf/util/ui/browser.c b/tools/perf/ui/browser.c index 556829124b02..cde4d0f0ddb9 100644 --- a/tools/perf/util/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -27,9 +27,12 @@ static int ui_browser__percent_color(struct ui_browser *browser, return HE_COLORSET_NORMAL; } -void ui_browser__set_color(struct ui_browser *self __used, int color) +int ui_browser__set_color(struct ui_browser *browser, int color) { + int ret = browser->current_color; + browser->current_color = color; SLsmg_set_color(color); + return ret; } void ui_browser__set_percent_color(struct ui_browser *self, @@ -503,6 +506,12 @@ static struct ui_browser__colorset { .bg = "default", }, { + .colorset = HE_COLORSET_ADDR, + .name = "addr", + .fg = "magenta", + .bg = "default", + }, + { .name = NULL, } }; @@ -584,6 +593,111 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser) return row; } +void __ui_browser__vline(struct ui_browser *browser, unsigned int column, + u16 start, u16 end) +{ + SLsmg_set_char_set(1); + ui_browser__gotorc(browser, start, column); + SLsmg_draw_vline(end - start + 1); + SLsmg_set_char_set(0); +} + +void ui_browser__write_graph(struct ui_browser *browser __used, int graph) +{ + SLsmg_set_char_set(1); + SLsmg_write_char(graph); + SLsmg_set_char_set(0); +} + +static void __ui_browser__line_arrow_up(struct ui_browser *browser, + unsigned int column, + u64 start, u64 end) +{ + unsigned int row, end_row; + + SLsmg_set_char_set(1); + + if (start < browser->top_idx + browser->height) { + row = start - browser->top_idx; + ui_browser__gotorc(browser, row, column); + SLsmg_write_char(SLSMG_LLCORN_CHAR); + ui_browser__gotorc(browser, row, column + 1); + SLsmg_draw_hline(2); + + if (row-- == 0) + goto out; + } else + row = browser->height - 1; + + if (end > browser->top_idx) + end_row = end - browser->top_idx; + else + end_row = 0; + + ui_browser__gotorc(browser, end_row, column); + SLsmg_draw_vline(row - end_row + 1); + + ui_browser__gotorc(browser, end_row, column); + if (end >= browser->top_idx) { + SLsmg_write_char(SLSMG_ULCORN_CHAR); + ui_browser__gotorc(browser, end_row, column + 1); + SLsmg_write_char(SLSMG_HLINE_CHAR); + ui_browser__gotorc(browser, end_row, column + 2); + SLsmg_write_char(SLSMG_RARROW_CHAR); + } +out: + SLsmg_set_char_set(0); +} + +static void __ui_browser__line_arrow_down(struct ui_browser *browser, + unsigned int column, + u64 start, u64 end) +{ + unsigned int row, end_row; + + SLsmg_set_char_set(1); + + if (start >= browser->top_idx) { + row = start - browser->top_idx; + ui_browser__gotorc(browser, row, column); + SLsmg_write_char(SLSMG_ULCORN_CHAR); + ui_browser__gotorc(browser, row, column + 1); + SLsmg_draw_hline(2); + + if (row++ == 0) + goto out; + } else + row = 0; + + if (end >= browser->top_idx + browser->height) + end_row = browser->height - 1; + else + end_row = end - browser->top_idx;; + + ui_browser__gotorc(browser, row, column); + SLsmg_draw_vline(end_row - row + 1); + + ui_browser__gotorc(browser, end_row, column); + if (end < browser->top_idx + browser->height) { + SLsmg_write_char(SLSMG_LLCORN_CHAR); + ui_browser__gotorc(browser, end_row, column + 1); + SLsmg_write_char(SLSMG_HLINE_CHAR); + ui_browser__gotorc(browser, end_row, column + 2); + SLsmg_write_char(SLSMG_RARROW_CHAR); + } +out: + SLsmg_set_char_set(0); +} + +void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, + u64 start, u64 end) +{ + if (start > end) + __ui_browser__line_arrow_up(browser, column, start, end); + else + __ui_browser__line_arrow_down(browser, column, start, end); +} + void ui_browser__init(void) { int i = 0; diff --git a/tools/perf/util/ui/browser.h b/tools/perf/ui/browser.h index 6ee82f60feaf..dd96d8229902 100644 --- a/tools/perf/util/ui/browser.h +++ b/tools/perf/ui/browser.h @@ -10,11 +10,13 @@ #define HE_COLORSET_NORMAL 52 #define HE_COLORSET_SELECTED 53 #define HE_COLORSET_CODE 54 +#define HE_COLORSET_ADDR 55 struct ui_browser { u64 index, top_idx; void *top, *entries; u16 y, x, width, height; + int current_color; void *priv; const char *title; char *helpline; @@ -27,7 +29,7 @@ struct ui_browser { bool use_navkeypressed; }; -void ui_browser__set_color(struct ui_browser *self, int color); +int ui_browser__set_color(struct ui_browser *browser, int color); void ui_browser__set_percent_color(struct ui_browser *self, double percent, bool current); bool ui_browser__is_current_entry(struct ui_browser *self, unsigned row); @@ -35,6 +37,9 @@ void ui_browser__refresh_dimensions(struct ui_browser *self); void ui_browser__reset_index(struct ui_browser *self); void ui_browser__gotorc(struct ui_browser *self, int y, int x); +void ui_browser__write_graph(struct ui_browser *browser, int graph); +void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column, + u64 start, u64 end); void __ui_browser__show_title(struct ui_browser *browser, const char *title); void ui_browser__show_title(struct ui_browser *browser, const char *title); int ui_browser__show(struct ui_browser *self, const char *title, @@ -44,6 +49,8 @@ int ui_browser__refresh(struct ui_browser *self); int ui_browser__run(struct ui_browser *browser, int delay_secs); void ui_browser__update_nr_entries(struct ui_browser *browser, u32 nr_entries); void ui_browser__handle_resize(struct ui_browser *browser); +void __ui_browser__vline(struct ui_browser *browser, unsigned int column, + u16 start, u16 end); int ui_browser__warning(struct ui_browser *browser, int timeout, const char *format, ...); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c new file mode 100644 index 000000000000..6e0ef79be169 --- /dev/null +++ b/tools/perf/ui/browsers/annotate.c @@ -0,0 +1,867 @@ +#include "../../util/util.h" +#include "../browser.h" +#include "../helpline.h" +#include "../libslang.h" +#include "../ui.h" +#include "../util.h" +#include "../../util/annotate.h" +#include "../../util/hist.h" +#include "../../util/sort.h" +#include "../../util/symbol.h" +#include <pthread.h> +#include <newt.h> + +struct browser_disasm_line { + struct rb_node rb_node; + double percent; + u32 idx; + int idx_asm; + int jump_sources; +}; + +struct annotate_browser { + struct ui_browser b; + struct rb_root entries; + struct rb_node *curr_hot; + struct disasm_line *selection; + struct disasm_line **offsets; + u64 start; + int nr_asm_entries; + int nr_entries; + int max_jump_sources; + int nr_jumps; + bool hide_src_code; + bool use_offset; + bool jump_arrows; + bool show_nr_jumps; + bool searching_backwards; + u8 addr_width; + u8 jumps_width; + u8 target_width; + u8 min_addr_width; + u8 max_addr_width; + char search_bf[128]; +}; + +static inline struct browser_disasm_line *disasm_line__browser(struct disasm_line *dl) +{ + return (struct browser_disasm_line *)(dl + 1); +} + +static bool disasm_line__filter(struct ui_browser *browser, void *entry) +{ + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + + if (ab->hide_src_code) { + struct disasm_line *dl = list_entry(entry, struct disasm_line, node); + return dl->offset == -1; + } + + return false; +} + +static int annotate_browser__jumps_percent_color(struct annotate_browser *browser, + int nr, bool current) +{ + if (current && (!browser->b.use_navkeypressed || browser->b.navkeypressed)) + return HE_COLORSET_SELECTED; + if (nr == browser->max_jump_sources) + return HE_COLORSET_TOP; + if (nr > 1) + return HE_COLORSET_MEDIUM; + return HE_COLORSET_NORMAL; +} + +static int annotate_browser__set_jumps_percent_color(struct annotate_browser *browser, + int nr, bool current) +{ + int color = annotate_browser__jumps_percent_color(browser, nr, current); + return ui_browser__set_color(&browser->b, color); +} + +static void annotate_browser__write(struct ui_browser *self, void *entry, int row) +{ + struct annotate_browser *ab = container_of(self, struct annotate_browser, b); + struct disasm_line *dl = list_entry(entry, struct disasm_line, node); + struct browser_disasm_line *bdl = disasm_line__browser(dl); + bool current_entry = ui_browser__is_current_entry(self, row); + bool change_color = (!ab->hide_src_code && + (!current_entry || (self->use_navkeypressed && + !self->navkeypressed))); + int width = self->width, printed; + char bf[256]; + + if (dl->offset != -1 && bdl->percent != 0.0) { + ui_browser__set_percent_color(self, bdl->percent, current_entry); + slsmg_printf("%6.2f ", bdl->percent); + } else { + ui_browser__set_percent_color(self, 0, current_entry); + slsmg_write_nstring(" ", 7); + } + + SLsmg_write_char(' '); + + /* The scroll bar isn't being used */ + if (!self->navkeypressed) + width += 1; + + if (!*dl->line) + slsmg_write_nstring(" ", width - 7); + else if (dl->offset == -1) { + printed = scnprintf(bf, sizeof(bf), "%*s ", + ab->addr_width, " "); + slsmg_write_nstring(bf, printed); + slsmg_write_nstring(dl->line, width - printed - 6); + } else { + u64 addr = dl->offset; + int color = -1; + + if (!ab->use_offset) + addr += ab->start; + + if (!ab->use_offset) { + printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr); + } else { + if (bdl->jump_sources) { + if (ab->show_nr_jumps) { + int prev; + printed = scnprintf(bf, sizeof(bf), "%*d ", + ab->jumps_width, + bdl->jump_sources); + prev = annotate_browser__set_jumps_percent_color(ab, bdl->jump_sources, + current_entry); + slsmg_write_nstring(bf, printed); + ui_browser__set_color(self, prev); + } + + printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ", + ab->target_width, addr); + } else { + printed = scnprintf(bf, sizeof(bf), "%*s ", + ab->addr_width, " "); + } + } + + if (change_color) + color = ui_browser__set_color(self, HE_COLORSET_ADDR); + slsmg_write_nstring(bf, printed); + if (change_color) + ui_browser__set_color(self, color); + if (dl->ins && dl->ins->ops->scnprintf) { + if (ins__is_jump(dl->ins)) { + bool fwd = dl->ops.target.offset > (u64)dl->offset; + + ui_browser__write_graph(self, fwd ? SLSMG_DARROW_CHAR : + SLSMG_UARROW_CHAR); + SLsmg_write_char(' '); + } else if (ins__is_call(dl->ins)) { + ui_browser__write_graph(self, SLSMG_RARROW_CHAR); + SLsmg_write_char(' '); + } else { + slsmg_write_nstring(" ", 2); + } + } else { + if (strcmp(dl->name, "retq")) { + slsmg_write_nstring(" ", 2); + } else { + ui_browser__write_graph(self, SLSMG_LARROW_CHAR); + SLsmg_write_char(' '); + } + } + + disasm_line__scnprintf(dl, bf, sizeof(bf), !ab->use_offset); + slsmg_write_nstring(bf, width - 10 - printed); + } + + if (current_entry) + ab->selection = dl; +} + +static void annotate_browser__draw_current_jump(struct ui_browser *browser) +{ + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + struct disasm_line *cursor = ab->selection, *target; + struct browser_disasm_line *btarget, *bcursor; + unsigned int from, to; + + if (!cursor->ins || !ins__is_jump(cursor->ins) || + !disasm_line__has_offset(cursor)) + return; + + target = ab->offsets[cursor->ops.target.offset]; + if (!target) + return; + + bcursor = disasm_line__browser(cursor); + btarget = disasm_line__browser(target); + + if (ab->hide_src_code) { + from = bcursor->idx_asm; + to = btarget->idx_asm; + } else { + from = (u64)bcursor->idx; + to = (u64)btarget->idx; + } + + ui_browser__set_color(browser, HE_COLORSET_CODE); + __ui_browser__line_arrow(browser, 9 + ab->addr_width, from, to); +} + +static unsigned int annotate_browser__refresh(struct ui_browser *browser) +{ + struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); + int ret = ui_browser__list_head_refresh(browser); + + if (ab->jump_arrows) + annotate_browser__draw_current_jump(browser); + + ui_browser__set_color(browser, HE_COLORSET_NORMAL); + __ui_browser__vline(browser, 7, 0, browser->height - 1); + return ret; +} + +static double disasm_line__calc_percent(struct disasm_line *dl, struct symbol *sym, int evidx) +{ + double percent = 0.0; + + if (dl->offset != -1) { + int len = sym->end - sym->start; + unsigned int hits = 0; + struct annotation *notes = symbol__annotation(sym); + struct source_line *src_line = notes->src->lines; + struct sym_hist *h = annotation__histogram(notes, evidx); + s64 offset = dl->offset; + struct disasm_line *next; + + next = disasm__get_next_ip_line(¬es->src->source, dl); + while (offset < (s64)len && + (next == NULL || offset < next->offset)) { + if (src_line) { + percent += src_line[offset].percent; + } else + hits += h->addr[offset]; + + ++offset; + } + /* + * If the percentage wasn't already calculated in + * symbol__get_source_line, do it now: + */ + if (src_line == NULL && h->sum) + percent = 100.0 * hits / h->sum; + } + + return percent; +} + +static void disasm_rb_tree__insert(struct rb_root *root, struct browser_disasm_line *bdl) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct browser_disasm_line *l; + + while (*p != NULL) { + parent = *p; + l = rb_entry(parent, struct browser_disasm_line, rb_node); + if (bdl->percent < l->percent) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + rb_link_node(&bdl->rb_node, parent, p); + rb_insert_color(&bdl->rb_node, root); +} + +static void annotate_browser__set_top(struct annotate_browser *self, + struct disasm_line *pos, u32 idx) +{ + unsigned back; + + ui_browser__refresh_dimensions(&self->b); + back = self->b.height / 2; + self->b.top_idx = self->b.index = idx; + + while (self->b.top_idx != 0 && back != 0) { + pos = list_entry(pos->node.prev, struct disasm_line, node); + + if (disasm_line__filter(&self->b, &pos->node)) + continue; + + --self->b.top_idx; + --back; + } + + self->b.top = pos; + self->b.navkeypressed = true; +} + +static void annotate_browser__set_rb_top(struct annotate_browser *browser, + struct rb_node *nd) +{ + struct browser_disasm_line *bpos; + struct disasm_line *pos; + + bpos = rb_entry(nd, struct browser_disasm_line, rb_node); + pos = ((struct disasm_line *)bpos) - 1; + annotate_browser__set_top(browser, pos, bpos->idx); + browser->curr_hot = nd; +} + +static void annotate_browser__calc_percent(struct annotate_browser *browser, + int evidx) +{ + struct map_symbol *ms = browser->b.priv; + struct symbol *sym = ms->sym; + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *pos; + + browser->entries = RB_ROOT; + + pthread_mutex_lock(¬es->lock); + + list_for_each_entry(pos, ¬es->src->source, node) { + struct browser_disasm_line *bpos = disasm_line__browser(pos); + bpos->percent = disasm_line__calc_percent(pos, sym, evidx); + if (bpos->percent < 0.01) { + RB_CLEAR_NODE(&bpos->rb_node); + continue; + } + disasm_rb_tree__insert(&browser->entries, bpos); + } + pthread_mutex_unlock(¬es->lock); + + browser->curr_hot = rb_last(&browser->entries); +} + +static bool annotate_browser__toggle_source(struct annotate_browser *browser) +{ + struct disasm_line *dl; + struct browser_disasm_line *bdl; + off_t offset = browser->b.index - browser->b.top_idx; + + browser->b.seek(&browser->b, offset, SEEK_CUR); + dl = list_entry(browser->b.top, struct disasm_line, node); + bdl = disasm_line__browser(dl); + + if (browser->hide_src_code) { + if (bdl->idx_asm < offset) + offset = bdl->idx; + + browser->b.nr_entries = browser->nr_entries; + browser->hide_src_code = false; + browser->b.seek(&browser->b, -offset, SEEK_CUR); + browser->b.top_idx = bdl->idx - offset; + browser->b.index = bdl->idx; + } else { + if (bdl->idx_asm < 0) { + ui_helpline__puts("Only available for assembly lines."); + browser->b.seek(&browser->b, -offset, SEEK_CUR); + return false; + } + + if (bdl->idx_asm < offset) + offset = bdl->idx_asm; + + browser->b.nr_entries = browser->nr_asm_entries; + browser->hide_src_code = true; + browser->b.seek(&browser->b, -offset, SEEK_CUR); + browser->b.top_idx = bdl->idx_asm - offset; + browser->b.index = bdl->idx_asm; + } + + return true; +} + +static bool annotate_browser__callq(struct annotate_browser *browser, + int evidx, void (*timer)(void *arg), + void *arg, int delay_secs) +{ + struct map_symbol *ms = browser->b.priv; + struct disasm_line *dl = browser->selection; + struct symbol *sym = ms->sym; + struct annotation *notes; + struct symbol *target; + u64 ip; + + if (!ins__is_call(dl->ins)) + return false; + + ip = ms->map->map_ip(ms->map, dl->ops.target.addr); + target = map__find_symbol(ms->map, ip, NULL); + if (target == NULL) { + ui_helpline__puts("The called function was not found."); + return true; + } + + notes = symbol__annotation(target); + pthread_mutex_lock(¬es->lock); + + if (notes->src == NULL && symbol__alloc_hist(target) < 0) { + pthread_mutex_unlock(¬es->lock); + ui__warning("Not enough memory for annotating '%s' symbol!\n", + target->name); + return true; + } + + pthread_mutex_unlock(¬es->lock); + symbol__tui_annotate(target, ms->map, evidx, timer, arg, delay_secs); + ui_browser__show_title(&browser->b, sym->name); + return true; +} + +static +struct disasm_line *annotate_browser__find_offset(struct annotate_browser *browser, + s64 offset, s64 *idx) +{ + struct map_symbol *ms = browser->b.priv; + struct symbol *sym = ms->sym; + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *pos; + + *idx = 0; + list_for_each_entry(pos, ¬es->src->source, node) { + if (pos->offset == offset) + return pos; + if (!disasm_line__filter(&browser->b, &pos->node)) + ++*idx; + } + + return NULL; +} + +static bool annotate_browser__jump(struct annotate_browser *browser) +{ + struct disasm_line *dl = browser->selection; + s64 idx; + + if (!ins__is_jump(dl->ins)) + return false; + + dl = annotate_browser__find_offset(browser, dl->ops.target.offset, &idx); + if (dl == NULL) { + ui_helpline__puts("Invallid jump offset"); + return true; + } + + annotate_browser__set_top(browser, dl, idx); + + return true; +} + +static +struct disasm_line *annotate_browser__find_string(struct annotate_browser *browser, + char *s, s64 *idx) +{ + struct map_symbol *ms = browser->b.priv; + struct symbol *sym = ms->sym; + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *pos = browser->selection; + + *idx = browser->b.index; + list_for_each_entry_continue(pos, ¬es->src->source, node) { + if (disasm_line__filter(&browser->b, &pos->node)) + continue; + + ++*idx; + + if (pos->line && strstr(pos->line, s) != NULL) + return pos; + } + + return NULL; +} + +static bool __annotate_browser__search(struct annotate_browser *browser) +{ + struct disasm_line *dl; + s64 idx; + + dl = annotate_browser__find_string(browser, browser->search_bf, &idx); + if (dl == NULL) { + ui_helpline__puts("String not found!"); + return false; + } + + annotate_browser__set_top(browser, dl, idx); + browser->searching_backwards = false; + return true; +} + +static +struct disasm_line *annotate_browser__find_string_reverse(struct annotate_browser *browser, + char *s, s64 *idx) +{ + struct map_symbol *ms = browser->b.priv; + struct symbol *sym = ms->sym; + struct annotation *notes = symbol__annotation(sym); + struct disasm_line *pos = browser->selection; + + *idx = browser->b.index; + list_for_each_entry_continue_reverse(pos, ¬es->src->source, node) { + if (disasm_line__filter(&browser->b, &pos->node)) + continue; + + --*idx; + + if (pos->line && strstr(pos->line, s) != NULL) + return pos; + } + + return NULL; +} + +static bool __annotate_browser__search_reverse(struct annotate_browser *browser) +{ + struct disasm_line *dl; + s64 idx; + + dl = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx); + if (dl == NULL) { + ui_helpline__puts("String not found!"); + return false; + } + + annotate_browser__set_top(browser, dl, idx); + browser->searching_backwards = true; + return true; +} + +static bool annotate_browser__search_window(struct annotate_browser *browser, + int delay_secs) +{ + if (ui_browser__input_window("Search", "String: ", browser->search_bf, + "ENTER: OK, ESC: Cancel", + delay_secs * 2) != K_ENTER || + !*browser->search_bf) + return false; + + return true; +} + +static bool annotate_browser__search(struct annotate_browser *browser, int delay_secs) +{ + if (annotate_browser__search_window(browser, delay_secs)) + return __annotate_browser__search(browser); + + return false; +} + +static bool annotate_browser__continue_search(struct annotate_browser *browser, + int delay_secs) +{ + if (!*browser->search_bf) + return annotate_browser__search(browser, delay_secs); + + return __annotate_browser__search(browser); +} + +static bool annotate_browser__search_reverse(struct annotate_browser *browser, + int delay_secs) +{ + if (annotate_browser__search_window(browser, delay_secs)) + return __annotate_browser__search_reverse(browser); + + return false; +} + +static +bool annotate_browser__continue_search_reverse(struct annotate_browser *browser, + int delay_secs) +{ + if (!*browser->search_bf) + return annotate_browser__search_reverse(browser, delay_secs); + + return __annotate_browser__search_reverse(browser); +} + +static int annotate_browser__run(struct annotate_browser *self, int evidx, + void(*timer)(void *arg), + void *arg, int delay_secs) +{ + struct rb_node *nd = NULL; + struct map_symbol *ms = self->b.priv; + struct symbol *sym = ms->sym; + const char *help = "Press 'h' for help on key bindings"; + int key; + + if (ui_browser__show(&self->b, sym->name, help) < 0) + return -1; + + annotate_browser__calc_percent(self, evidx); + + if (self->curr_hot) { + annotate_browser__set_rb_top(self, self->curr_hot); + self->b.navkeypressed = false; + } + + nd = self->curr_hot; + + while (1) { + key = ui_browser__run(&self->b, delay_secs); + + if (delay_secs != 0) { + annotate_browser__calc_percent(self, evidx); + /* + * Current line focus got out of the list of most active + * lines, NULL it so that if TAB|UNTAB is pressed, we + * move to curr_hot (current hottest line). + */ + if (nd != NULL && RB_EMPTY_NODE(nd)) + nd = NULL; + } + + switch (key) { + case K_TIMER: + if (timer != NULL) + timer(arg); + + if (delay_secs != 0) + symbol__annotate_decay_histogram(sym, evidx); + continue; + case K_TAB: + if (nd != NULL) { + nd = rb_prev(nd); + if (nd == NULL) + nd = rb_last(&self->entries); + } else + nd = self->curr_hot; + break; + case K_UNTAB: + if (nd != NULL) + nd = rb_next(nd); + if (nd == NULL) + nd = rb_first(&self->entries); + else + nd = self->curr_hot; + break; + case K_F1: + case 'h': + ui_browser__help_window(&self->b, + "UP/DOWN/PGUP\n" + "PGDN/SPACE Navigate\n" + "q/ESC/CTRL+C Exit\n\n" + "-> Go to target\n" + "<- Exit\n" + "h Cycle thru hottest instructions\n" + "j Toggle showing jump to target arrows\n" + "J Toggle showing number of jump sources on targets\n" + "n Search next string\n" + "o Toggle disassembler output/simplified view\n" + "s Toggle source code view\n" + "/ Search string\n" + "? Search previous string\n"); + continue; + case 'H': + nd = self->curr_hot; + break; + case 's': + if (annotate_browser__toggle_source(self)) + ui_helpline__puts(help); + continue; + case 'o': + self->use_offset = !self->use_offset; + if (self->use_offset) + self->target_width = self->min_addr_width; + else + self->target_width = self->max_addr_width; +update_addr_width: + self->addr_width = self->target_width; + if (self->show_nr_jumps) + self->addr_width += self->jumps_width + 1; + continue; + case 'j': + self->jump_arrows = !self->jump_arrows; + continue; + case 'J': + self->show_nr_jumps = !self->show_nr_jumps; + goto update_addr_width; + case '/': + if (annotate_browser__search(self, delay_secs)) { +show_help: + ui_helpline__puts(help); + } + continue; + case 'n': + if (self->searching_backwards ? + annotate_browser__continue_search_reverse(self, delay_secs) : + annotate_browser__continue_search(self, delay_secs)) + goto show_help; + continue; + case '?': + if (annotate_browser__search_reverse(self, delay_secs)) + goto show_help; + continue; + case K_ENTER: + case K_RIGHT: + if (self->selection == NULL) + ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org"); + else if (self->selection->offset == -1) + ui_helpline__puts("Actions are only available for assembly lines."); + else if (!self->selection->ins) { + if (strcmp(self->selection->name, "retq")) + goto show_sup_ins; + goto out; + } else if (!(annotate_browser__jump(self) || + annotate_browser__callq(self, evidx, timer, arg, delay_secs))) { +show_sup_ins: + ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions."); + } + continue; + case K_LEFT: + case K_ESC: + case 'q': + case CTRL('c'): + goto out; + default: + continue; + } + + if (nd != NULL) + annotate_browser__set_rb_top(self, nd); + } +out: + ui_browser__hide(&self->b); + return key; +} + +int hist_entry__tui_annotate(struct hist_entry *he, int evidx, + void(*timer)(void *arg), void *arg, int delay_secs) +{ + return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, + timer, arg, delay_secs); +} + +static void annotate_browser__mark_jump_targets(struct annotate_browser *browser, + size_t size) +{ + u64 offset; + + for (offset = 0; offset < size; ++offset) { + struct disasm_line *dl = browser->offsets[offset], *dlt; + struct browser_disasm_line *bdlt; + + if (!dl || !dl->ins || !ins__is_jump(dl->ins) || + !disasm_line__has_offset(dl)) + continue; + + if (dl->ops.target.offset >= size) { + ui__error("jump to after symbol!\n" + "size: %zx, jump target: %" PRIx64, + size, dl->ops.target.offset); + continue; + } + + dlt = browser->offsets[dl->ops.target.offset]; + /* + * FIXME: Oops, no jump target? Buggy disassembler? Or do we + * have to adjust to the previous offset? + */ + if (dlt == NULL) + continue; + + bdlt = disasm_line__browser(dlt); + if (++bdlt->jump_sources > browser->max_jump_sources) + browser->max_jump_sources = bdlt->jump_sources; + + ++browser->nr_jumps; + } + +} + +static inline int width_jumps(int n) +{ + if (n >= 100) + return 5; + if (n / 10) + return 2; + return 1; +} + +int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, + void(*timer)(void *arg), void *arg, + int delay_secs) +{ + struct disasm_line *pos, *n; + struct annotation *notes; + const size_t size = symbol__size(sym); + struct map_symbol ms = { + .map = map, + .sym = sym, + }; + struct annotate_browser browser = { + .b = { + .refresh = annotate_browser__refresh, + .seek = ui_browser__list_head_seek, + .write = annotate_browser__write, + .filter = disasm_line__filter, + .priv = &ms, + .use_navkeypressed = true, + }, + .use_offset = true, + .jump_arrows = true, + }; + int ret = -1; + + if (sym == NULL) + return -1; + + if (map->dso->annotate_warned) + return -1; + + browser.offsets = zalloc(size * sizeof(struct disasm_line *)); + if (browser.offsets == NULL) { + ui__error("Not enough memory!"); + return -1; + } + + if (symbol__annotate(sym, map, sizeof(struct browser_disasm_line)) < 0) { + ui__error("%s", ui_helpline__last_msg); + goto out_free_offsets; + } + + ui_helpline__push("Press <- or ESC to exit"); + + notes = symbol__annotation(sym); + browser.start = map__rip_2objdump(map, sym->start); + + list_for_each_entry(pos, ¬es->src->source, node) { + struct browser_disasm_line *bpos; + size_t line_len = strlen(pos->line); + + if (browser.b.width < line_len) + browser.b.width = line_len; + bpos = disasm_line__browser(pos); + bpos->idx = browser.nr_entries++; + if (pos->offset != -1) { + bpos->idx_asm = browser.nr_asm_entries++; + /* + * FIXME: short term bandaid to cope with assembly + * routines that comes with labels in the same column + * as the address in objdump, sigh. + * + * E.g. copy_user_generic_unrolled + */ + if (pos->offset < (s64)size) + browser.offsets[pos->offset] = pos; + } else + bpos->idx_asm = -1; + } + + annotate_browser__mark_jump_targets(&browser, size); + + browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size); + browser.max_addr_width = hex_width(sym->end); + browser.jumps_width = width_jumps(browser.max_jump_sources); + browser.b.nr_entries = browser.nr_entries; + browser.b.entries = ¬es->src->source, + browser.b.width += 18; /* Percentage */ + ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs); + list_for_each_entry_safe(pos, n, ¬es->src->source, node) { + list_del(&pos->node); + disasm_line__free(pos); + } + +out_free_offsets: + free(browser.offsets); + return ret; +} diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 2f83e5dc9967..a372a4b02635 100644 --- a/tools/perf/util/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -5,12 +5,12 @@ #include <newt.h> #include <linux/rbtree.h> -#include "../../evsel.h" -#include "../../evlist.h" -#include "../../hist.h" -#include "../../pstack.h" -#include "../../sort.h" -#include "../../util.h" +#include "../../util/evsel.h" +#include "../../util/evlist.h" +#include "../../util/hist.h" +#include "../../util/pstack.h" +#include "../../util/sort.h" +#include "../../util/util.h" #include "../browser.h" #include "../helpline.h" @@ -840,10 +840,14 @@ static int hists__browser_title(struct hists *self, char *bf, size_t size, int printed; const struct dso *dso = self->dso_filter; const struct thread *thread = self->thread_filter; - unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE]; + unsigned long nr_samples = self->stats.nr_events[PERF_RECORD_SAMPLE]; + u64 nr_events = self->stats.total_period; + + nr_samples = convert_unit(nr_samples, &unit); + printed = scnprintf(bf, size, + "Samples: %lu%c of event '%s', Event count (approx.): %lu", + nr_samples, unit, ev_name, nr_events); - nr_events = convert_unit(nr_events, &unit); - printed = scnprintf(bf, size, "Events: %lu%c %s", nr_events, unit, ev_name); if (self->uid_filter_str) printed += snprintf(bf + printed, size - printed, @@ -937,7 +941,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, goto zoom_dso; case 't': goto zoom_thread; - case 's': + case '/': if (ui_browser__input_window("Symbol to show", "Please enter the name of symbol you want to see", buf, "ENTER: OK, ESC: Cancel", @@ -965,7 +969,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, "E Expand all callchains\n" "d Zoom into current DSO\n" "t Zoom into current Thread\n" - "s Filter symbol by name"); + "/ Filter symbol by name"); continue; case K_ENTER: case K_RIGHT: diff --git a/tools/perf/util/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index eca6575abfd0..98851d55a53e 100644 --- a/tools/perf/util/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -5,9 +5,9 @@ #include <sys/ttydefaults.h> #include <string.h> #include <linux/bitops.h> -#include "../../util.h" -#include "../../debug.h" -#include "../../symbol.h" +#include "../../util/util.h" +#include "../../util/debug.h" +#include "../../util/symbol.h" #include "../browser.h" #include "../helpline.h" #include "map.h" diff --git a/tools/perf/util/ui/browsers/map.h b/tools/perf/ui/browsers/map.h index df8581a43e17..df8581a43e17 100644 --- a/tools/perf/util/ui/browsers/map.h +++ b/tools/perf/ui/browsers/map.h diff --git a/tools/perf/util/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 258352a2356c..0656c381a89c 100644 --- a/tools/perf/util/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -9,24 +9,13 @@ #define MAX_COLUMNS 32 -void perf_gtk_setup_browser(int argc, const char *argv[], - bool fallback_to_pager __used) -{ - gtk_init(&argc, (char ***)&argv); -} - -void perf_gtk_exit_browser(bool wait_for_ok __used) -{ - gtk_main_quit(); -} - -static void perf_gtk_signal(int sig) +static void perf_gtk__signal(int sig) { psignal(sig, "perf"); gtk_main_quit(); } -static void perf_gtk_resize_window(GtkWidget *window) +static void perf_gtk__resize_window(GtkWidget *window) { GdkRectangle rect; GdkScreen *screen; @@ -46,7 +35,7 @@ static void perf_gtk_resize_window(GtkWidget *window) gtk_window_resize(GTK_WINDOW(window), width, height); } -static void perf_gtk_show_hists(GtkWidget *window, struct hists *hists) +static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists) { GType col_types[MAX_COLUMNS]; GtkCellRenderer *renderer; @@ -142,11 +131,11 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, GtkWidget *notebook; GtkWidget *window; - signal(SIGSEGV, perf_gtk_signal); - signal(SIGFPE, perf_gtk_signal); - signal(SIGINT, perf_gtk_signal); - signal(SIGQUIT, perf_gtk_signal); - signal(SIGTERM, perf_gtk_signal); + signal(SIGSEGV, perf_gtk__signal); + signal(SIGFPE, perf_gtk__signal); + signal(SIGINT, perf_gtk__signal); + signal(SIGQUIT, perf_gtk__signal); + signal(SIGTERM, perf_gtk__signal); window = gtk_window_new(GTK_WINDOW_TOPLEVEL); @@ -168,7 +157,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, GTK_POLICY_AUTOMATIC, GTK_POLICY_AUTOMATIC); - perf_gtk_show_hists(scrolled_window, hists); + perf_gtk__show_hists(scrolled_window, hists); tab_label = gtk_label_new(evname); @@ -179,7 +168,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist, gtk_widget_show_all(window); - perf_gtk_resize_window(window); + perf_gtk__resize_window(window); gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER); diff --git a/tools/perf/util/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index 75177ee04032..75177ee04032 100644 --- a/tools/perf/util/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h diff --git a/tools/perf/ui/gtk/setup.c b/tools/perf/ui/gtk/setup.c new file mode 100644 index 000000000000..829529957766 --- /dev/null +++ b/tools/perf/ui/gtk/setup.c @@ -0,0 +1,12 @@ +#include "gtk.h" +#include "../../util/cache.h" + +int perf_gtk__init(void) +{ + return gtk_init_check(NULL, NULL) ? 0 : -1; +} + +void perf_gtk__exit(bool wait_for_ok __used) +{ + gtk_main_quit(); +} diff --git a/tools/perf/util/ui/helpline.c b/tools/perf/ui/helpline.c index 2f950c2641c8..2f950c2641c8 100644 --- a/tools/perf/util/ui/helpline.c +++ b/tools/perf/ui/helpline.c diff --git a/tools/perf/util/ui/helpline.h b/tools/perf/ui/helpline.h index 7bab6b34e35e..7bab6b34e35e 100644 --- a/tools/perf/util/ui/helpline.h +++ b/tools/perf/ui/helpline.h diff --git a/tools/perf/util/ui/keysyms.h b/tools/perf/ui/keysyms.h index 809eca5707fa..809eca5707fa 100644 --- a/tools/perf/util/ui/keysyms.h +++ b/tools/perf/ui/keysyms.h diff --git a/tools/perf/util/ui/libslang.h b/tools/perf/ui/libslang.h index 4d54b6450f5b..4d54b6450f5b 100644 --- a/tools/perf/util/ui/libslang.h +++ b/tools/perf/ui/libslang.h diff --git a/tools/perf/util/ui/progress.c b/tools/perf/ui/progress.c index 13aa64e50e11..13aa64e50e11 100644 --- a/tools/perf/util/ui/progress.c +++ b/tools/perf/ui/progress.c diff --git a/tools/perf/util/ui/progress.h b/tools/perf/ui/progress.h index d9c205b59aa1..d9c205b59aa1 100644 --- a/tools/perf/util/ui/progress.h +++ b/tools/perf/ui/progress.h diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c new file mode 100644 index 000000000000..9f5f888f73e3 --- /dev/null +++ b/tools/perf/ui/setup.c @@ -0,0 +1,45 @@ +#include "../cache.h" +#include "../debug.h" + + +void setup_browser(bool fallback_to_pager) +{ + if (!isatty(1) || dump_trace) + use_browser = 0; + + /* default to TUI */ + if (use_browser < 0) + use_browser = 1; + + switch (use_browser) { + case 2: + if (perf_gtk__init() == 0) + break; + /* fall through */ + case 1: + use_browser = 1; + if (ui__init() == 0) + break; + /* fall through */ + default: + if (fallback_to_pager) + setup_pager(); + break; + } +} + +void exit_browser(bool wait_for_ok) +{ + switch (use_browser) { + case 2: + perf_gtk__exit(wait_for_ok); + break; + + case 1: + ui__exit(wait_for_ok); + break; + + default: + break; + } +} diff --git a/tools/perf/util/ui/setup.c b/tools/perf/ui/tui/setup.c index 85a69faa09aa..d33e943ac434 100644 --- a/tools/perf/util/ui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -2,14 +2,14 @@ #include <signal.h> #include <stdbool.h> -#include "../cache.h" -#include "../debug.h" -#include "browser.h" -#include "helpline.h" -#include "ui.h" -#include "util.h" -#include "libslang.h" -#include "keysyms.h" +#include "../../util/cache.h" +#include "../../util/debug.h" +#include "../browser.h" +#include "../helpline.h" +#include "../ui.h" +#include "../util.h" +#include "../libslang.h" +#include "../keysyms.h" pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; @@ -93,45 +93,26 @@ static void newt_suspend(void *d __used) newtResume(); } -static int ui__init(void) -{ - int err = SLkp_init(); - - if (err < 0) - goto out; - - SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB); -out: - return err; -} - -static void ui__exit(void) -{ - SLtt_set_cursor_visibility(1); - SLsmg_refresh(); - SLsmg_reset_smg(); - SLang_reset_tty(); -} - static void ui__signal(int sig) { - ui__exit(); + ui__exit(false); psignal(sig, "perf"); exit(0); } -void setup_browser(bool fallback_to_pager) +int ui__init(void) { - if (!isatty(1) || !use_browser || dump_trace) { - use_browser = 0; - if (fallback_to_pager) - setup_pager(); - return; - } + int err; - use_browser = 1; newtInit(); - ui__init(); + err = SLkp_init(); + if (err < 0) { + pr_err("TUI initialization failed.\n"); + goto out; + } + + SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB); + newtSetSuspendCallback(newt_suspend, NULL); ui_helpline__init(); ui_browser__init(); @@ -141,15 +122,19 @@ void setup_browser(bool fallback_to_pager) signal(SIGINT, ui__signal); signal(SIGQUIT, ui__signal); signal(SIGTERM, ui__signal); +out: + return err; } -void exit_browser(bool wait_for_ok) +void ui__exit(bool wait_for_ok) { - if (use_browser > 0) { - if (wait_for_ok) - ui__question_window("Fatal Error", - ui_helpline__last_msg, - "Press any key...", 0); - ui__exit(); - } + if (wait_for_ok) + ui__question_window("Fatal Error", + ui_helpline__last_msg, + "Press any key...", 0); + + SLtt_set_cursor_visibility(1); + SLsmg_refresh(); + SLsmg_reset_smg(); + SLang_reset_tty(); } diff --git a/tools/perf/util/ui/ui.h b/tools/perf/ui/ui.h index 7b67045479f6..7b67045479f6 100644 --- a/tools/perf/util/ui/ui.h +++ b/tools/perf/ui/ui.h diff --git a/tools/perf/util/ui/util.c b/tools/perf/ui/util.c index ad4374a16bb0..ad4374a16bb0 100644 --- a/tools/perf/util/ui/util.c +++ b/tools/perf/ui/util.c diff --git a/tools/perf/util/ui/util.h b/tools/perf/ui/util.h index 2d1738bd71c8..2d1738bd71c8 100644 --- a/tools/perf/util/ui/util.h +++ b/tools/perf/ui/util.h diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 08c6d138a655..8069dfb5ba77 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -18,6 +18,403 @@ const char *disassembler_style; +static struct ins *ins__find(const char *name); +static int disasm_line__parse(char *line, char **namep, char **rawp); + +static void ins__delete(struct ins_operands *ops) +{ + free(ops->source.raw); + free(ops->source.name); + free(ops->target.raw); + free(ops->target.name); +} + +static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw); +} + +int ins__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + if (ins->ops->scnprintf) + return ins->ops->scnprintf(ins, bf, size, ops); + + return ins__raw_scnprintf(ins, bf, size, ops); +} + +static int call__parse(struct ins_operands *ops) +{ + char *endptr, *tok, *name; + + ops->target.addr = strtoull(ops->raw, &endptr, 16); + + name = strchr(endptr, '<'); + if (name == NULL) + goto indirect_call; + + name++; + + tok = strchr(name, '>'); + if (tok == NULL) + return -1; + + *tok = '\0'; + ops->target.name = strdup(name); + *tok = '>'; + + return ops->target.name == NULL ? -1 : 0; + +indirect_call: + tok = strchr(endptr, '('); + if (tok != NULL) { + ops->target.addr = 0; + return 0; + } + + tok = strchr(endptr, '*'); + if (tok == NULL) + return -1; + + ops->target.addr = strtoull(tok + 1, NULL, 16); + return 0; +} + +static int call__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + if (ops->target.name) + return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name); + + if (ops->target.addr == 0) + return ins__raw_scnprintf(ins, bf, size, ops); + + return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr); +} + +static struct ins_ops call_ops = { + .parse = call__parse, + .scnprintf = call__scnprintf, +}; + +bool ins__is_call(const struct ins *ins) +{ + return ins->ops == &call_ops; +} + +static int jump__parse(struct ins_operands *ops) +{ + const char *s = strchr(ops->raw, '+'); + + ops->target.addr = strtoll(ops->raw, NULL, 16); + + if (s++ != NULL) + ops->target.offset = strtoll(s, NULL, 16); + else + ops->target.offset = UINT64_MAX; + + return 0; +} + +static int jump__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset); +} + +static struct ins_ops jump_ops = { + .parse = jump__parse, + .scnprintf = jump__scnprintf, +}; + +bool ins__is_jump(const struct ins *ins) +{ + return ins->ops == &jump_ops; +} + +static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep) +{ + char *endptr, *name, *t; + + if (strstr(raw, "(%rip)") == NULL) + return 0; + + *addrp = strtoull(comment, &endptr, 16); + name = strchr(endptr, '<'); + if (name == NULL) + return -1; + + name++; + + t = strchr(name, '>'); + if (t == NULL) + return 0; + + *t = '\0'; + *namep = strdup(name); + *t = '>'; + + return 0; +} + +static int lock__parse(struct ins_operands *ops) +{ + char *name; + + ops->locked.ops = zalloc(sizeof(*ops->locked.ops)); + if (ops->locked.ops == NULL) + return 0; + + if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0) + goto out_free_ops; + + ops->locked.ins = ins__find(name); + if (ops->locked.ins == NULL) + goto out_free_ops; + + if (!ops->locked.ins->ops) + return 0; + + if (ops->locked.ins->ops->parse) + ops->locked.ins->ops->parse(ops->locked.ops); + + return 0; + +out_free_ops: + free(ops->locked.ops); + ops->locked.ops = NULL; + return 0; +} + +static int lock__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + int printed; + + if (ops->locked.ins == NULL) + return ins__raw_scnprintf(ins, bf, size, ops); + + printed = scnprintf(bf, size, "%-6.6s ", ins->name); + return printed + ins__scnprintf(ops->locked.ins, bf + printed, + size - printed, ops->locked.ops); +} + +static void lock__delete(struct ins_operands *ops) +{ + free(ops->locked.ops); + free(ops->target.raw); + free(ops->target.name); +} + +static struct ins_ops lock_ops = { + .free = lock__delete, + .parse = lock__parse, + .scnprintf = lock__scnprintf, +}; + +static int mov__parse(struct ins_operands *ops) +{ + char *s = strchr(ops->raw, ','), *target, *comment, prev; + + if (s == NULL) + return -1; + + *s = '\0'; + ops->source.raw = strdup(ops->raw); + *s = ','; + + if (ops->source.raw == NULL) + return -1; + + target = ++s; + + while (s[0] != '\0' && !isspace(s[0])) + ++s; + prev = *s; + *s = '\0'; + + ops->target.raw = strdup(target); + *s = prev; + + if (ops->target.raw == NULL) + goto out_free_source; + + comment = strchr(s, '#'); + if (comment == NULL) + return 0; + + while (comment[0] != '\0' && isspace(comment[0])) + ++comment; + + comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name); + comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); + + return 0; + +out_free_source: + free(ops->source.raw); + ops->source.raw = NULL; + return -1; +} + +static int mov__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %s,%s", ins->name, + ops->source.name ?: ops->source.raw, + ops->target.name ?: ops->target.raw); +} + +static struct ins_ops mov_ops = { + .parse = mov__parse, + .scnprintf = mov__scnprintf, +}; + +static int dec__parse(struct ins_operands *ops) +{ + char *target, *comment, *s, prev; + + target = s = ops->raw; + + while (s[0] != '\0' && !isspace(s[0])) + ++s; + prev = *s; + *s = '\0'; + + ops->target.raw = strdup(target); + *s = prev; + + if (ops->target.raw == NULL) + return -1; + + comment = strchr(s, '#'); + if (comment == NULL) + return 0; + + while (comment[0] != '\0' && isspace(comment[0])) + ++comment; + + comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); + + return 0; +} + +static int dec__scnprintf(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops) +{ + return scnprintf(bf, size, "%-6.6s %s", ins->name, + ops->target.name ?: ops->target.raw); +} + +static struct ins_ops dec_ops = { + .parse = dec__parse, + .scnprintf = dec__scnprintf, +}; + +static int nop__scnprintf(struct ins *ins __used, char *bf, size_t size, + struct ins_operands *ops __used) +{ + return scnprintf(bf, size, "%-6.6s", "nop"); +} + +static struct ins_ops nop_ops = { + .scnprintf = nop__scnprintf, +}; + +/* + * Must be sorted by name! + */ +static struct ins instructions[] = { + { .name = "add", .ops = &mov_ops, }, + { .name = "addl", .ops = &mov_ops, }, + { .name = "addq", .ops = &mov_ops, }, + { .name = "addw", .ops = &mov_ops, }, + { .name = "and", .ops = &mov_ops, }, + { .name = "bts", .ops = &mov_ops, }, + { .name = "call", .ops = &call_ops, }, + { .name = "callq", .ops = &call_ops, }, + { .name = "cmp", .ops = &mov_ops, }, + { .name = "cmpb", .ops = &mov_ops, }, + { .name = "cmpl", .ops = &mov_ops, }, + { .name = "cmpq", .ops = &mov_ops, }, + { .name = "cmpw", .ops = &mov_ops, }, + { .name = "cmpxch", .ops = &mov_ops, }, + { .name = "dec", .ops = &dec_ops, }, + { .name = "decl", .ops = &dec_ops, }, + { .name = "imul", .ops = &mov_ops, }, + { .name = "inc", .ops = &dec_ops, }, + { .name = "incl", .ops = &dec_ops, }, + { .name = "ja", .ops = &jump_ops, }, + { .name = "jae", .ops = &jump_ops, }, + { .name = "jb", .ops = &jump_ops, }, + { .name = "jbe", .ops = &jump_ops, }, + { .name = "jc", .ops = &jump_ops, }, + { .name = "jcxz", .ops = &jump_ops, }, + { .name = "je", .ops = &jump_ops, }, + { .name = "jecxz", .ops = &jump_ops, }, + { .name = "jg", .ops = &jump_ops, }, + { .name = "jge", .ops = &jump_ops, }, + { .name = "jl", .ops = &jump_ops, }, + { .name = "jle", .ops = &jump_ops, }, + { .name = "jmp", .ops = &jump_ops, }, + { .name = "jmpq", .ops = &jump_ops, }, + { .name = "jna", .ops = &jump_ops, }, + { .name = "jnae", .ops = &jump_ops, }, + { .name = "jnb", .ops = &jump_ops, }, + { .name = "jnbe", .ops = &jump_ops, }, + { .name = "jnc", .ops = &jump_ops, }, + { .name = "jne", .ops = &jump_ops, }, + { .name = "jng", .ops = &jump_ops, }, + { .name = "jnge", .ops = &jump_ops, }, + { .name = "jnl", .ops = &jump_ops, }, + { .name = "jnle", .ops = &jump_ops, }, + { .name = "jno", .ops = &jump_ops, }, + { .name = "jnp", .ops = &jump_ops, }, + { .name = "jns", .ops = &jump_ops, }, + { .name = "jnz", .ops = &jump_ops, }, + { .name = "jo", .ops = &jump_ops, }, + { .name = "jp", .ops = &jump_ops, }, + { .name = "jpe", .ops = &jump_ops, }, + { .name = "jpo", .ops = &jump_ops, }, + { .name = "jrcxz", .ops = &jump_ops, }, + { .name = "js", .ops = &jump_ops, }, + { .name = "jz", .ops = &jump_ops, }, + { .name = "lea", .ops = &mov_ops, }, + { .name = "lock", .ops = &lock_ops, }, + { .name = "mov", .ops = &mov_ops, }, + { .name = "movb", .ops = &mov_ops, }, + { .name = "movdqa",.ops = &mov_ops, }, + { .name = "movl", .ops = &mov_ops, }, + { .name = "movq", .ops = &mov_ops, }, + { .name = "movslq", .ops = &mov_ops, }, + { .name = "movzbl", .ops = &mov_ops, }, + { .name = "movzwl", .ops = &mov_ops, }, + { .name = "nop", .ops = &nop_ops, }, + { .name = "nopl", .ops = &nop_ops, }, + { .name = "nopw", .ops = &nop_ops, }, + { .name = "or", .ops = &mov_ops, }, + { .name = "orl", .ops = &mov_ops, }, + { .name = "test", .ops = &mov_ops, }, + { .name = "testb", .ops = &mov_ops, }, + { .name = "testl", .ops = &mov_ops, }, + { .name = "xadd", .ops = &mov_ops, }, +}; + +static int ins__cmp(const void *name, const void *insp) +{ + const struct ins *ins = insp; + + return strcmp(name, ins->name); +} + +static struct ins *ins__find(const char *name) +{ + const int nmemb = ARRAY_SIZE(instructions); + + return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__cmp); +} + int symbol__annotate_init(struct map *map __used, struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); @@ -28,7 +425,7 @@ int symbol__annotate_init(struct map *map __used, struct symbol *sym) int symbol__alloc_hist(struct symbol *sym) { struct annotation *notes = symbol__annotation(sym); - const size_t size = sym->end - sym->start + 1; + const size_t size = symbol__size(sym); size_t sizeof_sym_hist = (sizeof(struct sym_hist) + size * sizeof(u64)); notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist); @@ -78,31 +475,110 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map, return 0; } -static struct objdump_line *objdump_line__new(s64 offset, char *line, size_t privsize) +static void disasm_line__init_ins(struct disasm_line *dl) +{ + dl->ins = ins__find(dl->name); + + if (dl->ins == NULL) + return; + + if (!dl->ins->ops) + return; + + if (dl->ins->ops->parse) + dl->ins->ops->parse(&dl->ops); +} + +static int disasm_line__parse(char *line, char **namep, char **rawp) +{ + char *name = line, tmp; + + while (isspace(name[0])) + ++name; + + if (name[0] == '\0') + return -1; + + *rawp = name + 1; + + while ((*rawp)[0] != '\0' && !isspace((*rawp)[0])) + ++*rawp; + + tmp = (*rawp)[0]; + (*rawp)[0] = '\0'; + *namep = strdup(name); + + if (*namep == NULL) + goto out_free_name; + + (*rawp)[0] = tmp; + + if ((*rawp)[0] != '\0') { + (*rawp)++; + while (isspace((*rawp)[0])) + ++(*rawp); + } + + return 0; + +out_free_name: + free(*namep); + *namep = NULL; + return -1; +} + +static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize) { - struct objdump_line *self = malloc(sizeof(*self) + privsize); + struct disasm_line *dl = zalloc(sizeof(*dl) + privsize); - if (self != NULL) { - self->offset = offset; - self->line = line; + if (dl != NULL) { + dl->offset = offset; + dl->line = strdup(line); + if (dl->line == NULL) + goto out_delete; + + if (offset != -1) { + if (disasm_line__parse(dl->line, &dl->name, &dl->ops.raw) < 0) + goto out_free_line; + + disasm_line__init_ins(dl); + } } - return self; + return dl; + +out_free_line: + free(dl->line); +out_delete: + free(dl); + return NULL; +} + +void disasm_line__free(struct disasm_line *dl) +{ + free(dl->line); + free(dl->name); + if (dl->ins && dl->ins->ops->free) + dl->ins->ops->free(&dl->ops); + else + ins__delete(&dl->ops); + free(dl); } -void objdump_line__free(struct objdump_line *self) +int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw) { - free(self->line); - free(self); + if (raw || !dl->ins) + return scnprintf(bf, size, "%-6.6s %s", dl->name, dl->ops.raw); + + return ins__scnprintf(dl->ins, bf, size, &dl->ops); } -static void objdump__add_line(struct list_head *head, struct objdump_line *line) +static void disasm__add(struct list_head *head, struct disasm_line *line) { list_add_tail(&line->node, head); } -struct objdump_line *objdump__get_next_ip_line(struct list_head *head, - struct objdump_line *pos) +struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos) { list_for_each_entry_continue(pos, head, node) if (pos->offset >= 0) @@ -111,15 +587,14 @@ struct objdump_line *objdump__get_next_ip_line(struct list_head *head, return NULL; } -static int objdump_line__print(struct objdump_line *oline, struct symbol *sym, - int evidx, u64 len, int min_pcnt, - int printed, int max_lines, - struct objdump_line *queue) +static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start, + int evidx, u64 len, int min_pcnt, int printed, + int max_lines, struct disasm_line *queue) { static const char *prev_line; static const char *prev_color; - if (oline->offset != -1) { + if (dl->offset != -1) { const char *path = NULL; unsigned int hits = 0; double percent = 0.0; @@ -127,10 +602,11 @@ static int objdump_line__print(struct objdump_line *oline, struct symbol *sym, struct annotation *notes = symbol__annotation(sym); struct source_line *src_line = notes->src->lines; struct sym_hist *h = annotation__histogram(notes, evidx); - s64 offset = oline->offset; - struct objdump_line *next; + s64 offset = dl->offset; + const u64 addr = start + offset; + struct disasm_line *next; - next = objdump__get_next_ip_line(¬es->src->source, oline); + next = disasm__get_next_ip_line(¬es->src->source, dl); while (offset < (s64)len && (next == NULL || offset < next->offset)) { @@ -155,9 +631,9 @@ static int objdump_line__print(struct objdump_line *oline, struct symbol *sym, if (queue != NULL) { list_for_each_entry_from(queue, ¬es->src->source, node) { - if (queue == oline) + if (queue == dl) break; - objdump_line__print(queue, sym, evidx, len, + disasm_line__print(queue, sym, start, evidx, len, 0, 0, 1, NULL); } } @@ -180,17 +656,18 @@ static int objdump_line__print(struct objdump_line *oline, struct symbol *sym, color_fprintf(stdout, color, " %7.2f", percent); printf(" : "); - color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", oline->line); + color_fprintf(stdout, PERF_COLOR_MAGENTA, " %" PRIx64 ":", addr); + color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line); } else if (max_lines && printed >= max_lines) return 1; else { if (queue) return -1; - if (!*oline->line) + if (!*dl->line) printf(" :\n"); else - printf(" : %s\n", oline->line); + printf(" : %s\n", dl->line); } return 0; @@ -200,8 +677,8 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, FILE *file, size_t privsize) { struct annotation *notes = symbol__annotation(sym); - struct objdump_line *objdump_line; - char *line = NULL, *tmp, *tmp2, *c; + struct disasm_line *dl; + char *line = NULL, *parsed_line, *tmp, *tmp2, *c; size_t line_len; s64 line_ip, offset = -1; @@ -219,6 +696,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, *c = 0; line_ip = -1; + parsed_line = line; /* * Strip leading spaces: @@ -246,14 +724,17 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, offset = line_ip - start; if (offset < 0 || (u64)line_ip > end) offset = -1; + else + parsed_line = tmp2 + 1; } - objdump_line = objdump_line__new(offset, line, privsize); - if (objdump_line == NULL) { - free(line); + dl = disasm_line__new(offset, parsed_line, privsize); + free(line); + + if (dl == NULL) return -1; - } - objdump__add_line(¬es->src->source, objdump_line); + + disasm__add(¬es->src->source, dl); return 0; } @@ -476,7 +957,7 @@ static void symbol__annotate_hits(struct symbol *sym, int evidx) { struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evidx); - u64 len = sym->end - sym->start, offset; + u64 len = symbol__size(sym), offset; for (offset = 0; offset < len; ++offset) if (h->addr[offset] != 0) @@ -492,7 +973,8 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, struct dso *dso = map->dso; const char *filename = dso->long_name, *d_filename; struct annotation *notes = symbol__annotation(sym); - struct objdump_line *pos, *queue = NULL; + struct disasm_line *pos, *queue = NULL; + u64 start = map__rip_2objdump(map, sym->start); int printed = 2, queue_len = 0; int more = 0; u64 len; @@ -502,7 +984,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, else d_filename = basename(filename); - len = sym->end - sym->start; + len = symbol__size(sym); printf(" Percent | Source code & Disassembly of %s\n", d_filename); printf("------------------------------------------------\n"); @@ -516,8 +998,9 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, queue_len = 0; } - switch (objdump_line__print(pos, sym, evidx, len, min_pcnt, - printed, max_lines, queue)) { + switch (disasm_line__print(pos, sym, start, evidx, len, + min_pcnt, printed, max_lines, + queue)) { case 0: ++printed; if (context) { @@ -561,7 +1044,7 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) { struct annotation *notes = symbol__annotation(sym); struct sym_hist *h = annotation__histogram(notes, evidx); - int len = sym->end - sym->start, offset; + int len = symbol__size(sym), offset; h->sum = 0; for (offset = 0; offset < len; ++offset) { @@ -570,14 +1053,42 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx) } } -void objdump_line_list__purge(struct list_head *head) +void disasm__purge(struct list_head *head) { - struct objdump_line *pos, *n; + struct disasm_line *pos, *n; list_for_each_entry_safe(pos, n, head, node) { list_del(&pos->node); - objdump_line__free(pos); + disasm_line__free(pos); + } +} + +static size_t disasm_line__fprintf(struct disasm_line *dl, FILE *fp) +{ + size_t printed; + + if (dl->offset == -1) + return fprintf(fp, "%s\n", dl->line); + + printed = fprintf(fp, "%#" PRIx64 " %s", dl->offset, dl->name); + + if (dl->ops.raw[0] != '\0') { + printed += fprintf(fp, "%.*s %s\n", 6 - (int)printed, " ", + dl->ops.raw); } + + return printed + fprintf(fp, "\n"); +} + +size_t disasm__fprintf(struct list_head *head, FILE *fp) +{ + struct disasm_line *pos; + size_t printed = 0; + + list_for_each_entry(pos, head, node) + printed += disasm_line__fprintf(pos, fp); + + return printed; } int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, @@ -592,7 +1103,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, if (symbol__annotate(sym, map, 0) < 0) return -1; - len = sym->end - sym->start; + len = symbol__size(sym); if (print_lines) { symbol__get_source_line(sym, map, evidx, &source_line, @@ -605,7 +1116,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, if (print_lines) symbol__free_source_line(sym, len); - objdump_line_list__purge(&symbol__annotation(sym)->src->source); + disasm__purge(&symbol__annotation(sym)->src->source); return 0; } diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index efa5dc82bfae..78a5692dd718 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -2,20 +2,69 @@ #define __PERF_ANNOTATE_H #include <stdbool.h> +#include <stdint.h> #include "types.h" #include "symbol.h" #include <linux/list.h> #include <linux/rbtree.h> -struct objdump_line { - struct list_head node; - s64 offset; - char *line; +struct ins; + +struct ins_operands { + char *raw; + struct { + char *raw; + char *name; + u64 addr; + u64 offset; + } target; + union { + struct { + char *raw; + char *name; + u64 addr; + } source; + struct { + struct ins *ins; + struct ins_operands *ops; + } locked; + }; }; -void objdump_line__free(struct objdump_line *self); -struct objdump_line *objdump__get_next_ip_line(struct list_head *head, - struct objdump_line *pos); +struct ins_ops { + void (*free)(struct ins_operands *ops); + int (*parse)(struct ins_operands *ops); + int (*scnprintf)(struct ins *ins, char *bf, size_t size, + struct ins_operands *ops); +}; + +struct ins { + const char *name; + struct ins_ops *ops; +}; + +bool ins__is_jump(const struct ins *ins); +bool ins__is_call(const struct ins *ins); +int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops); + +struct disasm_line { + struct list_head node; + s64 offset; + char *line; + char *name; + struct ins *ins; + struct ins_operands ops; +}; + +static inline bool disasm_line__has_offset(const struct disasm_line *dl) +{ + return dl->ops.target.offset != UINT64_MAX; +} + +void disasm_line__free(struct disasm_line *dl); +struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disasm_line *pos); +int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw); +size_t disasm__fprintf(struct list_head *head, FILE *fp); struct sym_hist { u64 sum; @@ -32,7 +81,7 @@ struct source_line { * * @histogram: Array of addr hit histograms per event being monitored * @lines: If 'print_lines' is specified, per source code line percentages - * @source: source parsed from objdump -dS + * @source: source parsed from a disassembler like objdump -dS * * lines is allocated, percentages calculated and all sorted by percentage * when the annotation is about to be presented, so the percentages are for @@ -82,7 +131,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, int evidx, int context); void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); -void objdump_line_list__purge(struct list_head *head); +void disasm__purge(struct list_head *head); int symbol__tty_annotate(struct symbol *sym, struct map *map, int evidx, bool print_lines, bool full_paths, int min_pcnt, diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 8dd224df3e54..cff18c617d13 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -33,7 +33,7 @@ extern int pager_use_color; extern int use_browser; -#ifdef NO_NEWT_SUPPORT +#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT) static inline void setup_browser(bool fallback_to_pager) { if (fallback_to_pager) @@ -43,19 +43,29 @@ static inline void exit_browser(bool wait_for_ok __used) {} #else void setup_browser(bool fallback_to_pager); void exit_browser(bool wait_for_ok); + +#ifdef NO_NEWT_SUPPORT +static inline int ui__init(void) +{ + return -1; +} +static inline void ui__exit(bool wait_for_ok __used) {} +#else +int ui__init(void); +void ui__exit(bool wait_for_ok); #endif #ifdef NO_GTK2_SUPPORT -static inline void perf_gtk_setup_browser(int argc __used, const char *argv[] __used, bool fallback_to_pager) +static inline int perf_gtk__init(void) { - if (fallback_to_pager) - setup_pager(); + return -1; } -static inline void perf_gtk_exit_browser(bool wait_for_ok __used) {} +static inline void perf_gtk__exit(bool wait_for_ok __used) {} #else -void perf_gtk_setup_browser(int argc, const char *argv[], bool fallback_to_pager); -void perf_gtk_exit_browser(bool wait_for_ok); +int perf_gtk__init(void); +void perf_gtk__exit(bool wait_for_ok); #endif +#endif /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */ char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 26817daa2961..efb1fce259a4 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -11,6 +11,7 @@ #include "event.h" #include "debug.h" #include "util.h" +#include "target.h" int verbose; bool dump_trace = false, quiet = false; diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index f2ce88d04f54..6bebe7f0a20c 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -26,7 +26,7 @@ static inline void ui_progress__update(u64 curr __used, u64 total __used, #else extern char ui_helpline__last_msg[]; int ui_helpline__show_help(const char *format, va_list ap); -#include "ui/progress.h" +#include "../ui/progress.h" int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2))); #endif diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 1986d8051bd1..4ac5f5ae4ce9 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -11,6 +11,7 @@ #include <poll.h> #include "cpumap.h" #include "thread_map.h" +#include "target.h" #include "evlist.h" #include "evsel.h" #include <unistd.h> @@ -599,18 +600,21 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, return perf_evlist__mmap_per_cpu(evlist, prot, mask); } -int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid, - const char *target_tid, uid_t uid, const char *cpu_list) +int perf_evlist__create_maps(struct perf_evlist *evlist, + struct perf_target *target) { - evlist->threads = thread_map__new_str(target_pid, target_tid, uid); + evlist->threads = thread_map__new_str(target->pid, target->tid, + target->uid); if (evlist->threads == NULL) return -1; - if (uid != UINT_MAX || (cpu_list == NULL && target_tid)) + if (perf_target__has_task(target)) + evlist->cpus = cpu_map__dummy_new(); + else if (!perf_target__has_cpu(target) && !target->uses_mmap) evlist->cpus = cpu_map__dummy_new(); else - evlist->cpus = cpu_map__new(cpu_list); + evlist->cpus = cpu_map__new(target->cpu_list); if (evlist->cpus == NULL) goto out_delete_threads; @@ -827,7 +831,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, exit(-1); } - if (!opts->system_wide && !opts->target_tid && !opts->target_pid) + if (perf_target__none(&opts->target)) evlist->threads->map[0] = evlist->workload.pid; close(child_ready_pipe[1]); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 21f1c9e57f13..58abb63ac13a 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -106,8 +106,8 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = threads; } -int perf_evlist__create_maps(struct perf_evlist *evlist, const char *target_pid, - const char *tid, uid_t uid, const char *cpu_list); +int perf_evlist__create_maps(struct perf_evlist *evlist, + struct perf_target *target); void perf_evlist__delete_maps(struct perf_evlist *evlist); int perf_evlist__set_filters(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8c13dbcb84b9..d7a2b4b9801d 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -14,6 +14,7 @@ #include "util.h" #include "cpumap.h" #include "thread_map.h" +#include "target.h" #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) #define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0)) @@ -106,15 +107,15 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, if (opts->call_graph) attr->sample_type |= PERF_SAMPLE_CALLCHAIN; - if (opts->system_wide) + if (opts->target.system_wide) attr->sample_type |= PERF_SAMPLE_CPU; if (opts->period) attr->sample_type |= PERF_SAMPLE_PERIOD; if (!opts->sample_id_all_missing && - (opts->sample_time || opts->system_wide || - !opts->no_inherit || opts->cpu_list)) + (opts->sample_time || !opts->no_inherit || + perf_target__has_cpu(&opts->target))) attr->sample_type |= PERF_SAMPLE_TIME; if (opts->raw_samples) { @@ -135,7 +136,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts, attr->mmap = track; attr->comm = track; - if (!opts->target_pid && !opts->target_tid && !opts->system_wide && + if (perf_target__none(&opts->target) && (!opts->group || evsel == first)) { attr->disabled = 1; attr->enable_on_exec = 1; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index c0b70c697a36..538598012139 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -31,21 +31,16 @@ static const char **header_argv; int perf_header__push_event(u64 id, const char *name) { + struct perf_trace_event_type *nevents; + if (strlen(name) > MAX_EVENT_NAME) pr_warning("Event %s will be truncated\n", name); - if (!events) { - events = malloc(sizeof(struct perf_trace_event_type)); - if (events == NULL) - return -ENOMEM; - } else { - struct perf_trace_event_type *nevents; + nevents = realloc(events, (event_count + 1) * sizeof(*events)); + if (nevents == NULL) + return -ENOMEM; + events = nevents; - nevents = realloc(events, (event_count + 1) * sizeof(*events)); - if (nevents == NULL) - return -ENOMEM; - events = nevents; - } memset(&events[event_count], 0, sizeof(struct perf_trace_event_type)); events[event_count].event_id = id; strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 9f6d630d5316..1293b5ebea4d 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -599,7 +599,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, if (chain->ms.sym) ret += fprintf(fp, "%s\n", chain->ms.sym->name); else - ret += fprintf(fp, "%p\n", (void *)(long)chain->ip); + ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip); return ret; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 2cae9df40e04..cfc64e293f90 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -138,7 +138,7 @@ static inline int hist_entry__tui_annotate(struct hist_entry *self __used, #define K_LEFT -1 #define K_RIGHT -2 #else -#include "ui/keysyms.h" +#include "../ui/keysyms.h" int hist_entry__tui_annotate(struct hist_entry *he, int evidx, void(*timer)(void *arg), void *arg, int delay_secs); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5b3a0ef4e232..c7fc18a33d54 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -593,17 +593,27 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, static int config_term(struct perf_event_attr *attr, struct parse_events__term *term) { - switch (term->type) { +#define CHECK_TYPE_VAL(type) \ +do { \ + if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val) \ + return -EINVAL; \ +} while (0) + + switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_CONFIG: + CHECK_TYPE_VAL(NUM); attr->config = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_CONFIG1: + CHECK_TYPE_VAL(NUM); attr->config1 = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_CONFIG2: + CHECK_TYPE_VAL(NUM); attr->config2 = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: + CHECK_TYPE_VAL(NUM); attr->sample_period = term->val.num; break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: @@ -615,7 +625,9 @@ static int config_term(struct perf_event_attr *attr, default: return -EINVAL; } + return 0; +#undef CHECK_TYPE_VAL } static int config_attr(struct perf_event_attr *attr, @@ -1015,11 +1027,12 @@ void print_events(const char *event_glob) int parse_events__is_hardcoded_term(struct parse_events__term *term) { - return term->type <= PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX; + return term->type_term != PARSE_EVENTS__TERM_TYPE_USER; } -int parse_events__new_term(struct parse_events__term **_term, int type, - char *config, char *str, long num) +static int new_term(struct parse_events__term **_term, int type_val, + int type_term, char *config, + char *str, long num) { struct parse_events__term *term; @@ -1028,15 +1041,11 @@ int parse_events__new_term(struct parse_events__term **_term, int type, return -ENOMEM; INIT_LIST_HEAD(&term->list); - term->type = type; + term->type_val = type_val; + term->type_term = type_term; term->config = config; - switch (type) { - case PARSE_EVENTS__TERM_TYPE_CONFIG: - case PARSE_EVENTS__TERM_TYPE_CONFIG1: - case PARSE_EVENTS__TERM_TYPE_CONFIG2: - case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: - case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: + switch (type_val) { case PARSE_EVENTS__TERM_TYPE_NUM: term->val.num = num; break; @@ -1051,6 +1060,20 @@ int parse_events__new_term(struct parse_events__term **_term, int type, return 0; } +int parse_events__term_num(struct parse_events__term **term, + int type_term, char *config, long num) +{ + return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, + config, NULL, num); +} + +int parse_events__term_str(struct parse_events__term **term, + int type_term, char *config, char *str) +{ + return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term, + config, str, 0); +} + void parse_events__free_terms(struct list_head *terms) { struct parse_events__term *term, *h; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index ca069f893381..3fddd610d350 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -4,7 +4,9 @@ * Parse symbolic events/counts passed in as options: */ +#include <stdbool.h> #include "../../../include/linux/perf_event.h" +#include "types.h" struct list_head; struct perf_evsel; @@ -34,16 +36,17 @@ extern int parse_filter(const struct option *opt, const char *str, int unset); #define EVENTS_HELP_MAX (128*1024) enum { + PARSE_EVENTS__TERM_TYPE_NUM, + PARSE_EVENTS__TERM_TYPE_STR, +}; + +enum { + PARSE_EVENTS__TERM_TYPE_USER, PARSE_EVENTS__TERM_TYPE_CONFIG, PARSE_EVENTS__TERM_TYPE_CONFIG1, PARSE_EVENTS__TERM_TYPE_CONFIG2, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, - PARSE_EVENTS__TERM_TYPE_NUM, - PARSE_EVENTS__TERM_TYPE_STR, - - PARSE_EVENTS__TERM_TYPE_HARDCODED_MAX = - PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, }; struct parse_events__term { @@ -52,14 +55,16 @@ struct parse_events__term { char *str; long num; } val; - int type; - + int type_val; + int type_term; struct list_head list; }; int parse_events__is_hardcoded_term(struct parse_events__term *term); -int parse_events__new_term(struct parse_events__term **term, int type, - char *config, char *str, long num); +int parse_events__term_num(struct parse_events__term **_term, + int type_term, char *config, long num); +int parse_events__term_str(struct parse_events__term **_term, + int type_term, char *config, char *str); void parse_events__free_terms(struct list_head *terms); int parse_events_modifier(struct list_head *list __used, char *str __used); int parse_events_add_tracepoint(struct list_head *list, int *idx, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index d9637da7333c..936913ea0ab6 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -176,8 +176,8 @@ PE_NAME '=' PE_NAME { struct parse_events__term *term; - ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_STR, - $1, $3, 0)); + ABORT_ON(parse_events__term_str(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3)); $$ = term; } | @@ -185,8 +185,8 @@ PE_NAME '=' PE_VALUE { struct parse_events__term *term; - ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM, - $1, NULL, $3)); + ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, $3)); $$ = term; } | @@ -194,8 +194,8 @@ PE_NAME { struct parse_events__term *term; - ABORT_ON(parse_events__new_term(&term, PARSE_EVENTS__TERM_TYPE_NUM, - $1, NULL, 1)); + ABORT_ON(parse_events__term_num(&term, PARSE_EVENTS__TERM_TYPE_USER, + $1, 1)); $$ = term; } | @@ -203,7 +203,7 @@ PE_TERM '=' PE_VALUE { struct parse_events__term *term; - ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, $3)); + ABORT_ON(parse_events__term_num(&term, $1, NULL, $3)); $$ = term; } | @@ -211,7 +211,7 @@ PE_TERM { struct parse_events__term *term; - ABORT_ON(parse_events__new_term(&term, $1, NULL, NULL, 1)); + ABORT_ON(parse_events__term_num(&term, $1, NULL, 1)); $$ = term; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index cb08a118e811..8ee219b7285b 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -225,7 +225,7 @@ static int pmu_config_term(struct list_head *formats, if (parse_events__is_hardcoded_term(term)) return 0; - if (term->type != PARSE_EVENTS__TERM_TYPE_NUM) + if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) return -EINVAL; format = pmu_find_format(formats, term->config); @@ -246,6 +246,11 @@ static int pmu_config_term(struct list_head *formats, return -EINVAL; } + /* + * XXX If we ever decide to go with string values for + * non-hardcoded terms, here's the place to translate + * them into value. + */ *vp |= pmu_format_value(format->bits, term->val.num); return 0; } @@ -324,49 +329,58 @@ static struct test_format { /* Simulated users input. */ static struct parse_events__term test_terms[] = { { - .config = (char *) "krava01", - .val.num = 15, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava01", + .val.num = 15, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava02", - .val.num = 170, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava02", + .val.num = 170, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava03", - .val.num = 1, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava03", + .val.num = 1, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava11", - .val.num = 27, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava11", + .val.num = 27, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava12", - .val.num = 1, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava12", + .val.num = 1, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava13", - .val.num = 2, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava13", + .val.num = 2, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava21", - .val.num = 119, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava21", + .val.num = 119, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava22", - .val.num = 11, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava22", + .val.num = 11, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, { - .config = (char *) "krava23", - .val.num = 2, - .type = PARSE_EVENTS__TERM_TYPE_NUM, + .config = (char *) "krava23", + .val.num = 2, + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, }, }; #define TERMS_CNT (sizeof(test_terms) / sizeof(struct parse_events__term)) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 1efd3bee6336..4dcc8f3190cf 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1108,16 +1108,10 @@ more: } if ((skip = perf_session__process_event(self, &event, tool, head)) < 0) { - dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n", - head, event.header.size, event.header.type); - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; + pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", + head, event.header.size, event.header.type); + err = -EINVAL; + goto out_err; } head += size; @@ -1226,17 +1220,11 @@ more: if (size == 0 || perf_session__process_event(session, event, tool, file_pos) < 0) { - dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n", - file_offset + head, event->header.size, - event->header.type); - /* - * assume we lost track of the stream, check alignment, and - * increment a single u64 in the hope to catch on again 'soon'. - */ - if (unlikely(head & 7)) - head &= ~7ULL; - - size = 8; + pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n", + file_offset + head, event->header.size, + event->header.type); + err = -EINVAL; + goto out_err; } head += size; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index ac49ef208a5f..1f003884f1ab 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -65,6 +65,11 @@ struct symbol { void symbol__delete(struct symbol *sym); +static inline size_t symbol__size(const struct symbol *sym) +{ + return sym->end - sym->start + 1; +} + struct strlist; struct symbol_conf { diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c new file mode 100644 index 000000000000..1064d5b148ad --- /dev/null +++ b/tools/perf/util/target.c @@ -0,0 +1,142 @@ +/* + * Helper functions for handling target threads/cpus + * + * Copyright (C) 2012, LG Electronics, Namhyung Kim <namhyung.kim@lge.com> + * + * Released under the GPL v2. + */ + +#include "target.h" +#include "debug.h" + +#include <pwd.h> +#include <string.h> + + +enum perf_target_errno perf_target__validate(struct perf_target *target) +{ + enum perf_target_errno ret = PERF_ERRNO_TARGET__SUCCESS; + + if (target->pid) + target->tid = target->pid; + + /* CPU and PID are mutually exclusive */ + if (target->tid && target->cpu_list) { + target->cpu_list = NULL; + if (ret == PERF_ERRNO_TARGET__SUCCESS) + ret = PERF_ERRNO_TARGET__PID_OVERRIDE_CPU; + } + + /* UID and PID are mutually exclusive */ + if (target->tid && target->uid_str) { + target->uid_str = NULL; + if (ret == PERF_ERRNO_TARGET__SUCCESS) + ret = PERF_ERRNO_TARGET__PID_OVERRIDE_UID; + } + + /* UID and CPU are mutually exclusive */ + if (target->uid_str && target->cpu_list) { + target->cpu_list = NULL; + if (ret == PERF_ERRNO_TARGET__SUCCESS) + ret = PERF_ERRNO_TARGET__UID_OVERRIDE_CPU; + } + + /* PID and SYSTEM are mutually exclusive */ + if (target->tid && target->system_wide) { + target->system_wide = false; + if (ret == PERF_ERRNO_TARGET__SUCCESS) + ret = PERF_ERRNO_TARGET__PID_OVERRIDE_SYSTEM; + } + + /* UID and SYSTEM are mutually exclusive */ + if (target->uid_str && target->system_wide) { + target->system_wide = false; + if (ret == PERF_ERRNO_TARGET__SUCCESS) + ret = PERF_ERRNO_TARGET__UID_OVERRIDE_SYSTEM; + } + + return ret; +} + +enum perf_target_errno perf_target__parse_uid(struct perf_target *target) +{ + struct passwd pwd, *result; + char buf[1024]; + const char *str = target->uid_str; + + target->uid = UINT_MAX; + if (str == NULL) + return PERF_ERRNO_TARGET__SUCCESS; + + /* Try user name first */ + getpwnam_r(str, &pwd, buf, sizeof(buf), &result); + + if (result == NULL) { + /* + * The user name not found. Maybe it's a UID number. + */ + char *endptr; + int uid = strtol(str, &endptr, 10); + + if (*endptr != '\0') + return PERF_ERRNO_TARGET__INVALID_UID; + + getpwuid_r(uid, &pwd, buf, sizeof(buf), &result); + + if (result == NULL) + return PERF_ERRNO_TARGET__USER_NOT_FOUND; + } + + target->uid = result->pw_uid; + return PERF_ERRNO_TARGET__SUCCESS; +} + +/* + * This must have a same ordering as the enum perf_target_errno. + */ +static const char *perf_target__error_str[] = { + "PID/TID switch overriding CPU", + "PID/TID switch overriding UID", + "UID switch overriding CPU", + "PID/TID switch overriding SYSTEM", + "UID switch overriding SYSTEM", + "Invalid User: %s", + "Problems obtaining information for user %s", +}; + +int perf_target__strerror(struct perf_target *target, int errnum, + char *buf, size_t buflen) +{ + int idx; + const char *msg; + + if (errnum >= 0) { + strerror_r(errnum, buf, buflen); + return 0; + } + + if (errnum < __PERF_ERRNO_TARGET__START || + errnum >= __PERF_ERRNO_TARGET__END) + return -1; + + idx = errnum - __PERF_ERRNO_TARGET__START; + msg = perf_target__error_str[idx]; + + switch (errnum) { + case PERF_ERRNO_TARGET__PID_OVERRIDE_CPU + ... PERF_ERRNO_TARGET__UID_OVERRIDE_SYSTEM: + snprintf(buf, buflen, "%s", msg); + break; + + case PERF_ERRNO_TARGET__INVALID_UID: + case PERF_ERRNO_TARGET__USER_NOT_FOUND: + snprintf(buf, buflen, msg, target->uid_str); + break; + + default: + /* cannot reach here */ + break; + } + + return 0; +} diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h new file mode 100644 index 000000000000..a4be8575fda5 --- /dev/null +++ b/tools/perf/util/target.h @@ -0,0 +1,65 @@ +#ifndef _PERF_TARGET_H +#define _PERF_TARGET_H + +#include <stdbool.h> +#include <sys/types.h> + +struct perf_target { + const char *pid; + const char *tid; + const char *cpu_list; + const char *uid_str; + uid_t uid; + bool system_wide; + bool uses_mmap; +}; + +enum perf_target_errno { + PERF_ERRNO_TARGET__SUCCESS = 0, + + /* + * Choose an arbitrary negative big number not to clash with standard + * errno since SUS requires the errno has distinct positive values. + * See 'Issue 6' in the link below. + * + * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html + */ + __PERF_ERRNO_TARGET__START = -10000, + + + /* for perf_target__validate() */ + PERF_ERRNO_TARGET__PID_OVERRIDE_CPU = __PERF_ERRNO_TARGET__START, + PERF_ERRNO_TARGET__PID_OVERRIDE_UID, + PERF_ERRNO_TARGET__UID_OVERRIDE_CPU, + PERF_ERRNO_TARGET__PID_OVERRIDE_SYSTEM, + PERF_ERRNO_TARGET__UID_OVERRIDE_SYSTEM, + + /* for perf_target__parse_uid() */ + PERF_ERRNO_TARGET__INVALID_UID, + PERF_ERRNO_TARGET__USER_NOT_FOUND, + + __PERF_ERRNO_TARGET__END, +}; + +enum perf_target_errno perf_target__validate(struct perf_target *target); +enum perf_target_errno perf_target__parse_uid(struct perf_target *target); + +int perf_target__strerror(struct perf_target *target, int errnum, char *buf, + size_t buflen); + +static inline bool perf_target__has_task(struct perf_target *target) +{ + return target->tid || target->pid || target->uid_str; +} + +static inline bool perf_target__has_cpu(struct perf_target *target) +{ + return target->system_wide || target->cpu_list; +} + +static inline bool perf_target__none(struct perf_target *target) +{ + return !perf_target__has_task(target) && !perf_target__has_cpu(target); +} + +#endif /* _PERF_TARGET_H */ diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 7da80f14418b..f718df8a3c59 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -6,7 +6,7 @@ struct thread_map { int nr; - int map[]; + pid_t map[]; }; struct thread_map *thread_map__new_by_pid(pid_t pid); diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index 09fe579ccafb..abe0e8e95068 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -69,23 +69,24 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size) ret += SNPRINTF(bf + ret, size - ret, "], "); - if (top->target_pid) + if (top->target.pid) ret += SNPRINTF(bf + ret, size - ret, " (target_pid: %s", - top->target_pid); - else if (top->target_tid) + top->target.pid); + else if (top->target.tid) ret += SNPRINTF(bf + ret, size - ret, " (target_tid: %s", - top->target_tid); - else if (top->uid_str != NULL) + top->target.tid); + else if (top->target.uid_str != NULL) ret += SNPRINTF(bf + ret, size - ret, " (uid: %s", - top->uid_str); + top->target.uid_str); else ret += SNPRINTF(bf + ret, size - ret, " (all"); - if (top->cpu_list) + if (top->target.cpu_list) ret += SNPRINTF(bf + ret, size - ret, ", CPU%s: %s)", - top->evlist->cpus->nr > 1 ? "s" : "", top->cpu_list); + top->evlist->cpus->nr > 1 ? "s" : "", + top->target.cpu_list); else { - if (top->target_tid) + if (top->target.tid) ret += SNPRINTF(bf + ret, size - ret, ")"); else ret += SNPRINTF(bf + ret, size - ret, ", %d CPU%s)", diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index ce61cb2d1acf..33347ca89ee4 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -13,6 +13,7 @@ struct perf_session; struct perf_top { struct perf_tool tool; struct perf_evlist *evlist; + struct perf_target target; /* * Symbols will be added here in perf_event__process_sample and will * get out after decayed. @@ -23,10 +24,7 @@ struct perf_top { u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; int freq; - const char *target_pid, *target_tid; - uid_t uid; bool hide_kernel_symbols, hide_user_symbols, zero; - bool system_wide; bool use_tui, use_stdio; bool sort_has_symbols; bool dont_use_callchains; @@ -37,7 +35,6 @@ struct perf_top { bool sample_id_all_missing; bool exclude_guest_missing; bool dump_symtab; - const char *cpu_list; struct hist_entry *sym_filter_entry; struct perf_evsel *sym_evsel; struct perf_session *session; @@ -47,7 +44,6 @@ struct perf_top { int realtime_prio; int sym_pcnt_filter; const char *sym_filter; - const char *uid_str; }; size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size); diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c deleted file mode 100644 index 57a4c6ef3fd2..000000000000 --- a/tools/perf/util/ui/browsers/annotate.c +++ /dev/null @@ -1,433 +0,0 @@ -#include "../../util.h" -#include "../browser.h" -#include "../helpline.h" -#include "../libslang.h" -#include "../ui.h" -#include "../util.h" -#include "../../annotate.h" -#include "../../hist.h" -#include "../../sort.h" -#include "../../symbol.h" -#include <pthread.h> -#include <newt.h> - -struct annotate_browser { - struct ui_browser b; - struct rb_root entries; - struct rb_node *curr_hot; - struct objdump_line *selection; - int nr_asm_entries; - int nr_entries; - bool hide_src_code; -}; - -struct objdump_line_rb_node { - struct rb_node rb_node; - double percent; - u32 idx; - int idx_asm; -}; - -static inline -struct objdump_line_rb_node *objdump_line__rb(struct objdump_line *self) -{ - return (struct objdump_line_rb_node *)(self + 1); -} - -static bool objdump_line__filter(struct ui_browser *browser, void *entry) -{ - struct annotate_browser *ab = container_of(browser, struct annotate_browser, b); - - if (ab->hide_src_code) { - struct objdump_line *ol = list_entry(entry, struct objdump_line, node); - return ol->offset == -1; - } - - return false; -} - -static void annotate_browser__write(struct ui_browser *self, void *entry, int row) -{ - struct annotate_browser *ab = container_of(self, struct annotate_browser, b); - struct objdump_line *ol = list_entry(entry, struct objdump_line, node); - bool current_entry = ui_browser__is_current_entry(self, row); - int width = self->width; - - if (ol->offset != -1) { - struct objdump_line_rb_node *olrb = objdump_line__rb(ol); - ui_browser__set_percent_color(self, olrb->percent, current_entry); - slsmg_printf(" %7.2f ", olrb->percent); - } else { - ui_browser__set_percent_color(self, 0, current_entry); - slsmg_write_nstring(" ", 9); - } - - SLsmg_write_char(':'); - slsmg_write_nstring(" ", 8); - - /* The scroll bar isn't being used */ - if (!self->navkeypressed) - width += 1; - - if (!ab->hide_src_code && ol->offset != -1) - if (!current_entry || (self->use_navkeypressed && - !self->navkeypressed)) - ui_browser__set_color(self, HE_COLORSET_CODE); - - if (!*ol->line) - slsmg_write_nstring(" ", width - 18); - else - slsmg_write_nstring(ol->line, width - 18); - - if (current_entry) - ab->selection = ol; -} - -static double objdump_line__calc_percent(struct objdump_line *self, - struct symbol *sym, int evidx) -{ - double percent = 0.0; - - if (self->offset != -1) { - int len = sym->end - sym->start; - unsigned int hits = 0; - struct annotation *notes = symbol__annotation(sym); - struct source_line *src_line = notes->src->lines; - struct sym_hist *h = annotation__histogram(notes, evidx); - s64 offset = self->offset; - struct objdump_line *next; - - next = objdump__get_next_ip_line(¬es->src->source, self); - while (offset < (s64)len && - (next == NULL || offset < next->offset)) { - if (src_line) { - percent += src_line[offset].percent; - } else - hits += h->addr[offset]; - - ++offset; - } - /* - * If the percentage wasn't already calculated in - * symbol__get_source_line, do it now: - */ - if (src_line == NULL && h->sum) - percent = 100.0 * hits / h->sum; - } - - return percent; -} - -static void objdump__insert_line(struct rb_root *self, - struct objdump_line_rb_node *line) -{ - struct rb_node **p = &self->rb_node; - struct rb_node *parent = NULL; - struct objdump_line_rb_node *l; - - while (*p != NULL) { - parent = *p; - l = rb_entry(parent, struct objdump_line_rb_node, rb_node); - if (line->percent < l->percent) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&line->rb_node, parent, p); - rb_insert_color(&line->rb_node, self); -} - -static void annotate_browser__set_top(struct annotate_browser *self, - struct rb_node *nd) -{ - struct objdump_line_rb_node *rbpos; - struct objdump_line *pos; - unsigned back; - - ui_browser__refresh_dimensions(&self->b); - back = self->b.height / 2; - rbpos = rb_entry(nd, struct objdump_line_rb_node, rb_node); - pos = ((struct objdump_line *)rbpos) - 1; - self->b.top_idx = self->b.index = rbpos->idx; - - while (self->b.top_idx != 0 && back != 0) { - pos = list_entry(pos->node.prev, struct objdump_line, node); - - --self->b.top_idx; - --back; - } - - self->b.top = pos; - self->curr_hot = nd; -} - -static void annotate_browser__calc_percent(struct annotate_browser *browser, - int evidx) -{ - struct map_symbol *ms = browser->b.priv; - struct symbol *sym = ms->sym; - struct annotation *notes = symbol__annotation(sym); - struct objdump_line *pos; - - browser->entries = RB_ROOT; - - pthread_mutex_lock(¬es->lock); - - list_for_each_entry(pos, ¬es->src->source, node) { - struct objdump_line_rb_node *rbpos = objdump_line__rb(pos); - rbpos->percent = objdump_line__calc_percent(pos, sym, evidx); - if (rbpos->percent < 0.01) { - RB_CLEAR_NODE(&rbpos->rb_node); - continue; - } - objdump__insert_line(&browser->entries, rbpos); - } - pthread_mutex_unlock(¬es->lock); - - browser->curr_hot = rb_last(&browser->entries); -} - -static bool annotate_browser__toggle_source(struct annotate_browser *browser) -{ - struct objdump_line *ol; - struct objdump_line_rb_node *olrb; - off_t offset = browser->b.index - browser->b.top_idx; - - browser->b.seek(&browser->b, offset, SEEK_CUR); - ol = list_entry(browser->b.top, struct objdump_line, node); - olrb = objdump_line__rb(ol); - - if (browser->hide_src_code) { - if (olrb->idx_asm < offset) - offset = olrb->idx; - - browser->b.nr_entries = browser->nr_entries; - browser->hide_src_code = false; - browser->b.seek(&browser->b, -offset, SEEK_CUR); - browser->b.top_idx = olrb->idx - offset; - browser->b.index = olrb->idx; - } else { - if (olrb->idx_asm < 0) { - ui_helpline__puts("Only available for assembly lines."); - browser->b.seek(&browser->b, -offset, SEEK_CUR); - return false; - } - - if (olrb->idx_asm < offset) - offset = olrb->idx_asm; - - browser->b.nr_entries = browser->nr_asm_entries; - browser->hide_src_code = true; - browser->b.seek(&browser->b, -offset, SEEK_CUR); - browser->b.top_idx = olrb->idx_asm - offset; - browser->b.index = olrb->idx_asm; - } - - return true; -} - -static int annotate_browser__run(struct annotate_browser *self, int evidx, - void(*timer)(void *arg), - void *arg, int delay_secs) -{ - struct rb_node *nd = NULL; - struct map_symbol *ms = self->b.priv; - struct symbol *sym = ms->sym; - const char *help = "<-/ESC: Exit, TAB/shift+TAB: Cycle hot lines, " - "H: Go to hottest line, ->/ENTER: Line action, " - "S: Toggle source code view"; - int key; - - if (ui_browser__show(&self->b, sym->name, help) < 0) - return -1; - - annotate_browser__calc_percent(self, evidx); - - if (self->curr_hot) - annotate_browser__set_top(self, self->curr_hot); - - nd = self->curr_hot; - - while (1) { - key = ui_browser__run(&self->b, delay_secs); - - if (delay_secs != 0) { - annotate_browser__calc_percent(self, evidx); - /* - * Current line focus got out of the list of most active - * lines, NULL it so that if TAB|UNTAB is pressed, we - * move to curr_hot (current hottest line). - */ - if (nd != NULL && RB_EMPTY_NODE(nd)) - nd = NULL; - } - - switch (key) { - case K_TIMER: - if (timer != NULL) - timer(arg); - - if (delay_secs != 0) - symbol__annotate_decay_histogram(sym, evidx); - continue; - case K_TAB: - if (nd != NULL) { - nd = rb_prev(nd); - if (nd == NULL) - nd = rb_last(&self->entries); - } else - nd = self->curr_hot; - break; - case K_UNTAB: - if (nd != NULL) - nd = rb_next(nd); - if (nd == NULL) - nd = rb_first(&self->entries); - else - nd = self->curr_hot; - break; - case 'H': - case 'h': - nd = self->curr_hot; - break; - case 'S': - case 's': - if (annotate_browser__toggle_source(self)) - ui_helpline__puts(help); - continue; - case K_ENTER: - case K_RIGHT: - if (self->selection == NULL) { - ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org"); - continue; - } - - if (self->selection->offset == -1) { - ui_helpline__puts("Actions are only available for assembly lines."); - continue; - } else { - char *s = strstr(self->selection->line, "callq "); - struct annotation *notes; - struct symbol *target; - u64 ip; - - if (s == NULL) { - ui_helpline__puts("Actions are only available for the 'callq' instruction."); - continue; - } - - s = strchr(s, ' '); - if (s++ == NULL) { - ui_helpline__puts("Invallid callq instruction."); - continue; - } - - ip = strtoull(s, NULL, 16); - ip = ms->map->map_ip(ms->map, ip); - target = map__find_symbol(ms->map, ip, NULL); - if (target == NULL) { - ui_helpline__puts("The called function was not found."); - continue; - } - - notes = symbol__annotation(target); - pthread_mutex_lock(¬es->lock); - - if (notes->src == NULL && symbol__alloc_hist(target) < 0) { - pthread_mutex_unlock(¬es->lock); - ui__warning("Not enough memory for annotating '%s' symbol!\n", - target->name); - continue; - } - - pthread_mutex_unlock(¬es->lock); - symbol__tui_annotate(target, ms->map, evidx, - timer, arg, delay_secs); - ui_browser__show_title(&self->b, sym->name); - } - continue; - case K_LEFT: - case K_ESC: - case 'q': - case CTRL('c'): - goto out; - default: - continue; - } - - if (nd != NULL) - annotate_browser__set_top(self, nd); - } -out: - ui_browser__hide(&self->b); - return key; -} - -int hist_entry__tui_annotate(struct hist_entry *he, int evidx, - void(*timer)(void *arg), void *arg, int delay_secs) -{ - return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, - timer, arg, delay_secs); -} - -int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx, - void(*timer)(void *arg), void *arg, - int delay_secs) -{ - struct objdump_line *pos, *n; - struct annotation *notes; - struct map_symbol ms = { - .map = map, - .sym = sym, - }; - struct annotate_browser browser = { - .b = { - .refresh = ui_browser__list_head_refresh, - .seek = ui_browser__list_head_seek, - .write = annotate_browser__write, - .filter = objdump_line__filter, - .priv = &ms, - .use_navkeypressed = true, - }, - }; - int ret; - - if (sym == NULL) - return -1; - - if (map->dso->annotate_warned) - return -1; - - if (symbol__annotate(sym, map, sizeof(struct objdump_line_rb_node)) < 0) { - ui__error("%s", ui_helpline__last_msg); - return -1; - } - - ui_helpline__push("Press <- or ESC to exit"); - - notes = symbol__annotation(sym); - - list_for_each_entry(pos, ¬es->src->source, node) { - struct objdump_line_rb_node *rbpos; - size_t line_len = strlen(pos->line); - - if (browser.b.width < line_len) - browser.b.width = line_len; - rbpos = objdump_line__rb(pos); - rbpos->idx = browser.nr_entries++; - if (pos->offset != -1) - rbpos->idx_asm = browser.nr_asm_entries++; - else - rbpos->idx_asm = -1; - } - - browser.b.nr_entries = browser.nr_entries; - browser.b.entries = ¬es->src->source, - browser.b.width += 18; /* Percentage */ - ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs); - list_for_each_entry_safe(pos, n, ¬es->src->source, node) { - list_del(&pos->node); - objdump_line__free(pos); - } - return ret; -} diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 52bb07c6442a..4007aca8e0ca 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -82,41 +82,3 @@ void warning(const char *warn, ...) warn_routine(warn, params); va_end(params); } - -uid_t parse_target_uid(const char *str, const char *tid, const char *pid) -{ - struct passwd pwd, *result; - char buf[1024]; - - if (str == NULL) - return UINT_MAX; - - /* UID and PID are mutually exclusive */ - if (tid || pid) { - ui__warning("PID/TID switch overriding UID\n"); - sleep(1); - return UINT_MAX; - } - - getpwnam_r(str, &pwd, buf, sizeof(buf), &result); - - if (result == NULL) { - char *endptr; - int uid = strtol(str, &endptr, 10); - - if (*endptr != '\0') { - ui__error("Invalid user %s\n", str); - return UINT_MAX - 1; - } - - getpwuid_r(uid, &pwd, buf, sizeof(buf), &result); - - if (result == NULL) { - ui__error("Problems obtaining information for user %s\n", - str); - return UINT_MAX - 1; - } - } - - return result->pw_uid; -} diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 8109a907841e..d03599fbe78b 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -148,3 +148,13 @@ int readn(int fd, void *buf, size_t n) return buf - buf_start; } + +size_t hex_width(u64 v) +{ + size_t n = 1; + + while ((v >>= 4)) + ++n; + + return n; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 0f99f394d8e0..2daaedb83d84 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -74,7 +74,6 @@ #include <netinet/tcp.h> #include <arpa/inet.h> #include <netdb.h> -#include <pwd.h> #include <inttypes.h> #include "../../../include/linux/magic.h" #include "types.h" @@ -249,8 +248,6 @@ struct perf_event_attr; void event_attr_init(struct perf_event_attr *attr); -uid_t parse_target_uid(const char *str, const char *tid, const char *pid); - #define _STR(x) #x #define STR(x) _STR(x) @@ -265,4 +262,6 @@ bool is_power_of_2(unsigned long n) return (n != 0 && ((n & (n - 1)) == 0)); } +size_t hex_width(u64 v); + #endif diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include new file mode 100644 index 000000000000..87b55a729a5f --- /dev/null +++ b/tools/scripts/Makefile.include @@ -0,0 +1,57 @@ +ifeq ("$(origin O)", "command line") + OUTPUT := $(O)/ +endif + +ifneq ($(OUTPUT),) +# check that the output directory actually exists +OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd) +$(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist)) +endif + +# +# Include saner warnings here, which can catch bugs: +# +EXTRA_WARNINGS := -Wbad-function-cast +EXTRA_WARNINGS += -Wdeclaration-after-statement +EXTRA_WARNINGS += -Wformat-security +EXTRA_WARNINGS += -Wformat-y2k +EXTRA_WARNINGS += -Winit-self +EXTRA_WARNINGS += -Wmissing-declarations +EXTRA_WARNINGS += -Wmissing-prototypes +EXTRA_WARNINGS += -Wnested-externs +EXTRA_WARNINGS += -Wno-system-headers +EXTRA_WARNINGS += -Wold-style-definition +EXTRA_WARNINGS += -Wpacked +EXTRA_WARNINGS += -Wredundant-decls +EXTRA_WARNINGS += -Wshadow +EXTRA_WARNINGS += -Wstrict-aliasing=3 +EXTRA_WARNINGS += -Wstrict-prototypes +EXTRA_WARNINGS += -Wswitch-default +EXTRA_WARNINGS += -Wswitch-enum +EXTRA_WARNINGS += -Wundef +EXTRA_WARNINGS += -Wwrite-strings +EXTRA_WARNINGS += -Wformat + +ifneq ($(findstring $(MAKEFLAGS), w),w) +PRINT_DIR = --no-print-directory +else +NO_SUBDIR = : +endif + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),s),s) +ifndef V + QUIET_CC = @echo ' ' CC $@; + QUIET_AR = @echo ' ' AR $@; + QUIET_LINK = @echo ' ' LINK $@; + QUIET_MKDIR = @echo ' ' MKDIR $@; + QUIET_GEN = @echo ' ' GEN $@; + QUIET_SUBDIR0 = +@subdir= + QUIET_SUBDIR1 = ;$(NO_SUBDIR) echo ' ' SUBDIR $$subdir; \ + $(MAKE) $(PRINT_DIR) -C $$subdir + QUIET_FLEX = @echo ' ' FLEX $@; + QUIET_BISON = @echo ' ' BISON $@; +endif +endif |