diff options
131 files changed, 4450 insertions, 1530 deletions
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 6284779d64ee..b8df45883cf7 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -631,7 +631,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) info->address &= ~alignment_mask; info->ctrl.len <<= offset; - if (!bp->overflow_handler) { + if (is_default_overflow_handler(bp)) { /* * Mismatch breakpoints are required for single-stepping * breakpoints. @@ -754,7 +754,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, * mismatch breakpoint so we can single-step over the * watchpoint trigger. */ - if (!wp->overflow_handler) + if (is_default_overflow_handler(wp)) enable_single_step(wp, instruction_pointer(regs)); unlock: diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index b45c95d34b83..4ef5373f9a76 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -616,7 +616,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr, perf_bp_event(bp, regs); /* Do we need to handle the stepping? */ - if (!bp->overflow_handler) + if (is_default_overflow_handler(bp)) step = 1; unlock: rcu_read_unlock(); @@ -712,7 +712,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, perf_bp_event(wp, regs); /* Do we need to handle the stepping? */ - if (!wp->overflow_handler) + if (is_default_overflow_handler(wp)) step = 1; unlock: diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2dc18605831f..a494fa34713a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -164,10 +164,6 @@ config INSTRUCTION_DECODER def_bool y depends on KPROBES || PERF_EVENTS || UPROBES -config PERF_EVENTS_INTEL_UNCORE - def_bool y - depends on PERF_EVENTS && CPU_SUP_INTEL && PCI - config OUTPUT_FORMAT string default "elf32-i386" if X86_32 @@ -1046,6 +1042,8 @@ config X86_THERMAL_VECTOR def_bool y depends on X86_MCE_INTEL +source "arch/x86/events/Kconfig" + config X86_LEGACY_VM86 bool "Legacy VM86 support" default n @@ -1210,15 +1208,6 @@ config MICROCODE_OLD_INTERFACE def_bool y depends on MICROCODE -config PERF_EVENTS_AMD_POWER - depends on PERF_EVENTS && CPU_SUP_AMD - tristate "AMD Processor Power Reporting Mechanism" - ---help--- - Provide power reporting mechanism support for AMD processors. - Currently, it leverages X86_FEATURE_ACC_POWER - (CPUID Fn8000_0007_EDX[12]) interface to calculate the - average power consumption on Family 15h processors. - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" ---help--- diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig new file mode 100644 index 000000000000..98397db5ceae --- /dev/null +++ b/arch/x86/events/Kconfig @@ -0,0 +1,36 @@ +menu "Performance monitoring" + +config PERF_EVENTS_INTEL_UNCORE + tristate "Intel uncore performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel uncore performance events. These are + available on NehalemEX and more modern processors. + +config PERF_EVENTS_INTEL_RAPL + tristate "Intel rapl performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel rapl performance events for power + monitoring on modern processors. + +config PERF_EVENTS_INTEL_CSTATE + tristate "Intel cstate performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel cstate performance events for power + monitoring on modern processors. + +config PERF_EVENTS_AMD_POWER + depends on PERF_EVENTS && CPU_SUP_AMD + tristate "AMD Processor Power Reporting Mechanism" + ---help--- + Provide power reporting mechanism support for AMD processors. + Currently, it leverages X86_FEATURE_ACC_POWER + (CPUID Fn8000_0007_EDX[12]) interface to calculate the + average power consumption on Family 15h processors. + +endmenu diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index f59618a39990..1d392c39fe56 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -6,9 +6,6 @@ obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o ifdef CONFIG_AMD_IOMMU obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o endif -obj-$(CONFIG_CPU_SUP_INTEL) += intel/core.o intel/bts.o intel/cqm.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/cstate.o intel/ds.o intel/knc.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/lbr.o intel/p4.o intel/p6.o intel/pt.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/rapl.o msr.o -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore.o intel/uncore_nhmex.o -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore_snb.o intel/uncore_snbep.o + +obj-$(CONFIG_CPU_SUP_INTEL) += msr.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 3db9569e658c..98ac57381bf9 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -263,6 +263,7 @@ static const struct attribute_group *amd_uncore_attr_groups[] = { }; static struct pmu amd_nb_pmu = { + .task_ctx_nr = perf_invalid_context, .attr_groups = amd_uncore_attr_groups, .name = "amd_nb", .event_init = amd_uncore_event_init, @@ -274,6 +275,7 @@ static struct pmu amd_nb_pmu = { }; static struct pmu amd_l2_pmu = { + .task_ctx_nr = perf_invalid_context, .attr_groups = amd_uncore_attr_groups, .name = "amd_l2", .event_init = amd_uncore_event_init, diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile new file mode 100644 index 000000000000..3660b2cf245a --- /dev/null +++ b/arch/x86/events/intel/Makefile @@ -0,0 +1,9 @@ +obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o +obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o +intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o +intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o +obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o +intel-cstate-objs := cstate.o diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index b99dc9258c0f..0a6e393a2e62 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -171,18 +171,6 @@ static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head) memset(page_address(phys->page) + index, 0, phys->size - index); } -static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts) -{ - if (buf->snapshot) - return false; - - if (local_read(&buf->data_size) >= bts->handle.size || - bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE) - return true; - - return false; -} - static void bts_update(struct bts_ctx *bts) { int cpu = raw_smp_processor_id(); @@ -213,18 +201,15 @@ static void bts_update(struct bts_ctx *bts) } } +static int +bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle); + static void __bts_event_start(struct perf_event *event) { struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct bts_buffer *buf = perf_get_aux(&bts->handle); u64 config = 0; - if (!buf || bts_buffer_is_full(buf, bts)) - return; - - event->hw.itrace_started = 1; - event->hw.state = 0; - if (!buf->snapshot) config |= ARCH_PERFMON_EVENTSEL_INT; if (!event->attr.exclude_kernel) @@ -241,16 +226,41 @@ static void __bts_event_start(struct perf_event *event) wmb(); intel_pmu_enable_bts(config); + } static void bts_event_start(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf; + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + goto fail_stop; + + if (bts_buffer_reset(buf, &bts->handle)) + goto fail_end_stop; + + bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; + bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; + bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; + + event->hw.itrace_started = 1; + event->hw.state = 0; __bts_event_start(event); /* PMI handler: this counter is running and likely generating PMIs */ ACCESS_ONCE(bts->started) = 1; + + return; + +fail_end_stop: + perf_aux_output_end(&bts->handle, 0, false); + +fail_stop: + event->hw.state = PERF_HES_STOPPED; } static void __bts_event_stop(struct perf_event *event) @@ -269,15 +279,32 @@ static void __bts_event_stop(struct perf_event *event) static void bts_event_stop(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); /* PMI handler: don't restart this counter */ ACCESS_ONCE(bts->started) = 0; __bts_event_stop(event); - if (flags & PERF_EF_UPDATE) + if (flags & PERF_EF_UPDATE) { bts_update(bts); + + if (buf) { + if (buf->snapshot) + bts->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + } + + cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; + cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; + } } void intel_bts_enable_local(void) @@ -417,34 +444,14 @@ int intel_bts_interrupt(void) static void bts_event_del(struct perf_event *event, int mode) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); - struct bts_buffer *buf = perf_get_aux(&bts->handle); - bts_event_stop(event, PERF_EF_UPDATE); - - if (buf) { - if (buf->snapshot) - bts->handle.head = - local_xchg(&buf->data_size, - buf->nr_pages << PAGE_SHIFT); - perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), - !!local_xchg(&buf->lost, 0)); - } - - cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; - cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; - cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; - cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; } static int bts_event_add(struct perf_event *event, int mode) { - struct bts_buffer *buf; struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int ret = -EBUSY; event->hw.state = PERF_HES_STOPPED; @@ -454,26 +461,10 @@ static int bts_event_add(struct perf_event *event, int mode) if (bts->handle.event) return -EBUSY; - buf = perf_aux_output_begin(&bts->handle, event); - if (!buf) - return -EINVAL; - - ret = bts_buffer_reset(buf, &bts->handle); - if (ret) { - perf_aux_output_end(&bts->handle, 0, false); - return ret; - } - - bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; - bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; - bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; - if (mode & PERF_EF_START) { bts_event_start(event, 0); - if (hwc->state & PERF_HES_STOPPED) { - bts_event_del(event, 0); - return -EBUSY; - } + if (hwc->state & PERF_HES_STOPPED) + return -EINVAL; } return 0; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 7946c4231169..9ba4e4136a15 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -91,6 +91,8 @@ #include <asm/cpu_device_id.h> #include "../perf_event.h" +MODULE_LICENSE("GPL"); + #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ struct kobj_attribute *attr, \ @@ -106,22 +108,27 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf); +/* Model -> events mapping */ +struct cstate_model { + unsigned long core_events; + unsigned long pkg_events; + unsigned long quirks; +}; + +/* Quirk flags */ +#define SLM_PKG_C6_USE_C7_MSR (1UL << 0) + struct perf_cstate_msr { u64 msr; struct perf_pmu_events_attr *attr; - bool (*test)(int idx); }; /* cstate_core PMU */ - static struct pmu cstate_core_pmu; static bool has_cstate_core; -enum perf_cstate_core_id { - /* - * cstate_core events - */ +enum perf_cstate_core_events { PERF_CSTATE_CORE_C1_RES = 0, PERF_CSTATE_CORE_C3_RES, PERF_CSTATE_CORE_C6_RES, @@ -130,69 +137,16 @@ enum perf_cstate_core_id { PERF_CSTATE_CORE_EVENT_MAX, }; -bool test_core(int idx) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || - boot_cpu_data.x86 != 6) - return false; - - switch (boot_cpu_data.x86_model) { - case 30: /* 45nm Nehalem */ - case 26: /* 45nm Nehalem-EP */ - case 46: /* 45nm Nehalem-EX */ - - case 37: /* 32nm Westmere */ - case 44: /* 32nm Westmere-EP */ - case 47: /* 32nm Westmere-EX */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - case 42: /* 32nm SandyBridge */ - case 45: /* 32nm SandyBridge-E/EN/EP */ - - case 58: /* 22nm IvyBridge */ - case 62: /* 22nm IvyBridge-EP/EX */ - - case 60: /* 22nm Haswell Core */ - case 63: /* 22nm Haswell Server */ - case 69: /* 22nm Haswell ULT */ - case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ - - case 61: /* 14nm Broadwell Core-M */ - case 86: /* 14nm Broadwell Xeon D */ - case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ - case 79: /* 14nm Broadwell Server */ - - case 78: /* 14nm Skylake Mobile */ - case 94: /* 14nm Skylake Desktop */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES || - idx == PERF_CSTATE_CORE_C7_RES) - return true; - break; - case 55: /* 22nm Atom "Silvermont" */ - case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ - case 76: /* 14nm Atom "Airmont" */ - if (idx == PERF_CSTATE_CORE_C1_RES || - idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - } - - return false; -} - PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00"); PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01"); PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02"); PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03"); static struct perf_cstate_msr core_msr[] = { - [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1, test_core, }, - [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3, test_core, }, - [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6, test_core, }, - [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7, test_core, }, + [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 }, + [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 }, + [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 }, + [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 }, }; static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = { @@ -234,18 +188,11 @@ static const struct attribute_group *core_attr_groups[] = { NULL, }; -/* cstate_core PMU end */ - - /* cstate_pkg PMU */ - static struct pmu cstate_pkg_pmu; static bool has_cstate_pkg; -enum perf_cstate_pkg_id { - /* - * cstate_pkg events - */ +enum perf_cstate_pkg_events { PERF_CSTATE_PKG_C2_RES = 0, PERF_CSTATE_PKG_C3_RES, PERF_CSTATE_PKG_C6_RES, @@ -257,69 +204,6 @@ enum perf_cstate_pkg_id { PERF_CSTATE_PKG_EVENT_MAX, }; -bool test_pkg(int idx) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || - boot_cpu_data.x86 != 6) - return false; - - switch (boot_cpu_data.x86_model) { - case 30: /* 45nm Nehalem */ - case 26: /* 45nm Nehalem-EP */ - case 46: /* 45nm Nehalem-EX */ - - case 37: /* 32nm Westmere */ - case 44: /* 32nm Westmere-EP */ - case 47: /* 32nm Westmere-EX */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES || - idx == PERF_CSTATE_CORE_C7_RES) - return true; - break; - case 42: /* 32nm SandyBridge */ - case 45: /* 32nm SandyBridge-E/EN/EP */ - - case 58: /* 22nm IvyBridge */ - case 62: /* 22nm IvyBridge-EP/EX */ - - case 60: /* 22nm Haswell Core */ - case 63: /* 22nm Haswell Server */ - case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ - - case 61: /* 14nm Broadwell Core-M */ - case 86: /* 14nm Broadwell Xeon D */ - case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ - case 79: /* 14nm Broadwell Server */ - - case 78: /* 14nm Skylake Mobile */ - case 94: /* 14nm Skylake Desktop */ - if (idx == PERF_CSTATE_PKG_C2_RES || - idx == PERF_CSTATE_PKG_C3_RES || - idx == PERF_CSTATE_PKG_C6_RES || - idx == PERF_CSTATE_PKG_C7_RES) - return true; - break; - case 55: /* 22nm Atom "Silvermont" */ - case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ - case 76: /* 14nm Atom "Airmont" */ - if (idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - case 69: /* 22nm Haswell ULT */ - if (idx == PERF_CSTATE_PKG_C2_RES || - idx == PERF_CSTATE_PKG_C3_RES || - idx == PERF_CSTATE_PKG_C6_RES || - idx == PERF_CSTATE_PKG_C7_RES || - idx == PERF_CSTATE_PKG_C8_RES || - idx == PERF_CSTATE_PKG_C9_RES || - idx == PERF_CSTATE_PKG_C10_RES) - return true; - break; - } - - return false; -} - PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00"); PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01"); PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02"); @@ -329,13 +213,13 @@ PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05"); PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06"); static struct perf_cstate_msr pkg_msr[] = { - [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2, test_pkg, }, - [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3, test_pkg, }, - [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6, test_pkg, }, - [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7, test_pkg, }, - [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8, test_pkg, }, - [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9, test_pkg, }, - [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10, test_pkg, }, + [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 }, + [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 }, + [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 }, + [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 }, + [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 }, + [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 }, + [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 }, }; static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = { @@ -366,8 +250,6 @@ static const struct attribute_group *pkg_attr_groups[] = { NULL, }; -/* cstate_pkg PMU end*/ - static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) @@ -385,7 +267,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, static int cstate_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config; - int ret = 0; + int cpu; if (event->attr.type != event->pmu->type) return -ENOENT; @@ -400,26 +282,36 @@ static int cstate_pmu_event_init(struct perf_event *event) event->attr.sample_period) /* no sampling */ return -EINVAL; + if (event->cpu < 0) + return -EINVAL; + if (event->pmu == &cstate_core_pmu) { if (cfg >= PERF_CSTATE_CORE_EVENT_MAX) return -EINVAL; if (!core_msr[cfg].attr) return -EINVAL; event->hw.event_base = core_msr[cfg].msr; + cpu = cpumask_any_and(&cstate_core_cpu_mask, + topology_sibling_cpumask(event->cpu)); } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; if (!pkg_msr[cfg].attr) return -EINVAL; event->hw.event_base = pkg_msr[cfg].msr; - } else + cpu = cpumask_any_and(&cstate_pkg_cpu_mask, + topology_core_cpumask(event->cpu)); + } else { return -ENOENT; + } + + if (cpu >= nr_cpu_ids) + return -ENODEV; - /* must be done before validate_group */ + event->cpu = cpu; event->hw.config = cfg; event->hw.idx = -1; - - return ret; + return 0; } static inline u64 cstate_pmu_read_counter(struct perf_event *event) @@ -469,172 +361,91 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode) return 0; } +/* + * Check if exiting cpu is the designated reader. If so migrate the + * events when there is a valid target available + */ static void cstate_cpu_exit(int cpu) { - int i, id, target; + unsigned int target; - /* cpu exit for cstate core */ - if (has_cstate_core) { - id = topology_core_id(cpu); - target = -1; - - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (id == topology_core_id(i)) { - target = i; - break; - } - } - if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0) + if (has_cstate_core && + cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) { + + target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &cstate_core_cpu_mask); - WARN_ON(cpumask_empty(&cstate_core_cpu_mask)); - if (target >= 0) perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); + } } - /* cpu exit for cstate pkg */ - if (has_cstate_pkg) { - id = topology_physical_package_id(cpu); - target = -1; - - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (id == topology_physical_package_id(i)) { - target = i; - break; - } - } - if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0) + if (has_cstate_pkg && + cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) { + + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &cstate_pkg_cpu_mask); - WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask)); - if (target >= 0) perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); + } } } static void cstate_cpu_init(int cpu) { - int i, id; + unsigned int target; - /* cpu init for cstate core */ - if (has_cstate_core) { - id = topology_core_id(cpu); - for_each_cpu(i, &cstate_core_cpu_mask) { - if (id == topology_core_id(i)) - break; - } - if (i >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_core_cpu_mask); - } + /* + * If this is the first online thread of that core, set it in + * the core cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_core_cpu_mask, + topology_sibling_cpumask(cpu)); - /* cpu init for cstate pkg */ - if (has_cstate_pkg) { - id = topology_physical_package_id(cpu); - for_each_cpu(i, &cstate_pkg_cpu_mask) { - if (id == topology_physical_package_id(i)) - break; - } - if (i >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); - } + if (has_cstate_core && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_core_cpu_mask); + + /* + * If this is the first online thread of that package, set it + * in the package cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_pkg_cpu_mask, + topology_core_cpumask(cpu)); + if (has_cstate_pkg && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); } static int cstate_cpu_notifier(struct notifier_block *self, - unsigned long action, void *hcpu) + unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - break; case CPU_STARTING: cstate_cpu_init(cpu); break; - case CPU_UP_CANCELED: - case CPU_DYING: - break; - case CPU_ONLINE: - case CPU_DEAD: - break; case CPU_DOWN_PREPARE: cstate_cpu_exit(cpu); break; default: break; } - return NOTIFY_OK; } -/* - * Probe the cstate events and insert the available one into sysfs attrs - * Return false if there is no available events. - */ -static bool cstate_probe_msr(struct perf_cstate_msr *msr, - struct attribute **events_attrs, - int max_event_nr) -{ - int i, j = 0; - u64 val; - - /* Probe the cstate events. */ - for (i = 0; i < max_event_nr; i++) { - if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) - msr[i].attr = NULL; - } - - /* List remaining events in the sysfs attrs. */ - for (i = 0; i < max_event_nr; i++) { - if (msr[i].attr) - events_attrs[j++] = &msr[i].attr->attr.attr; - } - events_attrs[j] = NULL; - - return (j > 0) ? true : false; -} - -static int __init cstate_init(void) -{ - /* SLM has different MSR for PKG C6 */ - switch (boot_cpu_data.x86_model) { - case 55: - case 76: - case 77: - pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; - } - - if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX)) - has_cstate_core = true; - - if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX)) - has_cstate_pkg = true; - - return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; -} - -static void __init cstate_cpumask_init(void) -{ - int cpu; - - cpu_notifier_register_begin(); - - for_each_online_cpu(cpu) - cstate_cpu_init(cpu); - - __perf_cpu_notifier(cstate_cpu_notifier); - - cpu_notifier_register_done(); -} +static struct notifier_block cstate_cpu_nb = { + .notifier_call = cstate_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; static struct pmu cstate_core_pmu = { .attr_groups = core_attr_groups, .name = "cstate_core", .task_ctx_nr = perf_invalid_context, .event_init = cstate_pmu_event_init, - .add = cstate_pmu_event_add, /* must have */ - .del = cstate_pmu_event_del, /* must have */ + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, .start = cstate_pmu_event_start, .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, @@ -646,49 +457,203 @@ static struct pmu cstate_pkg_pmu = { .name = "cstate_pkg", .task_ctx_nr = perf_invalid_context, .event_init = cstate_pmu_event_init, - .add = cstate_pmu_event_add, /* must have */ - .del = cstate_pmu_event_del, /* must have */ + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, .start = cstate_pmu_event_start, .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, }; -static void __init cstate_pmus_register(void) +static const struct cstate_model nhm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES), +}; + +static const struct cstate_model snb_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES), +}; + +static const struct cstate_model hswult_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES) | + BIT(PERF_CSTATE_PKG_C8_RES) | + BIT(PERF_CSTATE_PKG_C9_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + +static const struct cstate_model slm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C6_RES), + .quirks = SLM_PKG_C6_USE_C7_MSR, +}; + +#define X86_CSTATES_MODEL(model, states) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } + +static const struct x86_cpu_id intel_cstates_match[] __initconst = { + X86_CSTATES_MODEL(30, nhm_cstates), /* 45nm Nehalem */ + X86_CSTATES_MODEL(26, nhm_cstates), /* 45nm Nehalem-EP */ + X86_CSTATES_MODEL(46, nhm_cstates), /* 45nm Nehalem-EX */ + + X86_CSTATES_MODEL(37, nhm_cstates), /* 32nm Westmere */ + X86_CSTATES_MODEL(44, nhm_cstates), /* 32nm Westmere-EP */ + X86_CSTATES_MODEL(47, nhm_cstates), /* 32nm Westmere-EX */ + + X86_CSTATES_MODEL(42, snb_cstates), /* 32nm SandyBridge */ + X86_CSTATES_MODEL(45, snb_cstates), /* 32nm SandyBridge-E/EN/EP */ + + X86_CSTATES_MODEL(58, snb_cstates), /* 22nm IvyBridge */ + X86_CSTATES_MODEL(62, snb_cstates), /* 22nm IvyBridge-EP/EX */ + + X86_CSTATES_MODEL(60, snb_cstates), /* 22nm Haswell Core */ + X86_CSTATES_MODEL(63, snb_cstates), /* 22nm Haswell Server */ + X86_CSTATES_MODEL(70, snb_cstates), /* 22nm Haswell + GT3e */ + + X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT */ + + X86_CSTATES_MODEL(55, slm_cstates), /* 22nm Atom Silvermont */ + X86_CSTATES_MODEL(77, slm_cstates), /* 22nm Atom Avoton/Rangely */ + X86_CSTATES_MODEL(76, slm_cstates), /* 22nm Atom Airmont */ + + X86_CSTATES_MODEL(61, snb_cstates), /* 14nm Broadwell Core-M */ + X86_CSTATES_MODEL(86, snb_cstates), /* 14nm Broadwell Xeon D */ + X86_CSTATES_MODEL(71, snb_cstates), /* 14nm Broadwell + GT3e */ + X86_CSTATES_MODEL(79, snb_cstates), /* 14nm Broadwell Server */ + + X86_CSTATES_MODEL(78, snb_cstates), /* 14nm Skylake Mobile */ + X86_CSTATES_MODEL(94, snb_cstates), /* 14nm Skylake Desktop */ + { }, +}; +MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); + +/* + * Probe the cstate events and insert the available one into sysfs attrs + * Return false if there are no available events. + */ +static bool __init cstate_probe_msr(const unsigned long evmsk, int max, + struct perf_cstate_msr *msr, + struct attribute **attrs) { - int err; + bool found = false; + unsigned int bit; + u64 val; + + for (bit = 0; bit < max; bit++) { + if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) { + *attrs++ = &msr[bit].attr->attr.attr; + found = true; + } else { + msr[bit].attr = NULL; + } + } + *attrs = NULL; + + return found; +} + +static int __init cstate_probe(const struct cstate_model *cm) +{ + /* SLM has different MSR for PKG C6 */ + if (cm->quirks & SLM_PKG_C6_USE_C7_MSR) + pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + + has_cstate_core = cstate_probe_msr(cm->core_events, + PERF_CSTATE_CORE_EVENT_MAX, + core_msr, core_events_attrs); + + has_cstate_pkg = cstate_probe_msr(cm->pkg_events, + PERF_CSTATE_PKG_EVENT_MAX, + pkg_msr, pkg_events_attrs); + + return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; +} + +static inline void cstate_cleanup(void) +{ + if (has_cstate_core) + perf_pmu_unregister(&cstate_core_pmu); + + if (has_cstate_pkg) + perf_pmu_unregister(&cstate_pkg_pmu); +} + +static int __init cstate_init(void) +{ + int cpu, err; + + cpu_notifier_register_begin(); + for_each_online_cpu(cpu) + cstate_cpu_init(cpu); if (has_cstate_core) { err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); - if (WARN_ON(err)) - pr_info("Failed to register PMU %s error %d\n", - cstate_core_pmu.name, err); + if (err) { + has_cstate_core = false; + pr_info("Failed to register cstate core pmu\n"); + goto out; + } } if (has_cstate_pkg) { err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1); - if (WARN_ON(err)) - pr_info("Failed to register PMU %s error %d\n", - cstate_pkg_pmu.name, err); + if (err) { + has_cstate_pkg = false; + pr_info("Failed to register cstate pkg pmu\n"); + cstate_cleanup(); + goto out; + } } + __register_cpu_notifier(&cstate_cpu_nb); +out: + cpu_notifier_register_done(); + return err; } static int __init cstate_pmu_init(void) { + const struct x86_cpu_id *id; int err; - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + + id = x86_match_cpu(intel_cstates_match); + if (!id) return -ENODEV; - err = cstate_init(); + err = cstate_probe((const struct cstate_model *) id->driver_data); if (err) return err; - cstate_cpumask_init(); - - cstate_pmus_register(); - - return 0; + return cstate_init(); } +module_init(cstate_pmu_init); -device_initcall(cstate_pmu_init); +static void __exit cstate_pmu_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&cstate_cpu_nb); + cstate_cleanup(); + cpu_notifier_register_done(); +} +module_exit(cstate_pmu_exit); diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 6af7cf71d6b2..1aefd430e752 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -906,26 +906,6 @@ static void pt_buffer_free_aux(void *data) } /** - * pt_buffer_is_full() - check if the buffer is full - * @buf: PT buffer. - * @pt: Per-cpu pt handle. - * - * If the user hasn't read data from the output region that aux_head - * points to, the buffer is considered full: the user needs to read at - * least this region and update aux_tail to point past it. - */ -static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt) -{ - if (buf->snapshot) - return false; - - if (local_read(&buf->data_size) >= pt->handle.size) - return true; - - return false; -} - -/** * intel_pt_interrupt() - PT PMI handler */ void intel_pt_interrupt(void) @@ -989,20 +969,33 @@ void intel_pt_interrupt(void) static void pt_event_start(struct perf_event *event, int mode) { + struct hw_perf_event *hwc = &event->hw; struct pt *pt = this_cpu_ptr(&pt_ctx); - struct pt_buffer *buf = perf_get_aux(&pt->handle); + struct pt_buffer *buf; - if (!buf || pt_buffer_is_full(buf, pt)) { - event->hw.state = PERF_HES_STOPPED; - return; + buf = perf_aux_output_begin(&pt->handle, event); + if (!buf) + goto fail_stop; + + pt_buffer_reset_offsets(buf, pt->handle.head); + if (!buf->snapshot) { + if (pt_buffer_reset_markers(buf, &pt->handle)) + goto fail_end_stop; } ACCESS_ONCE(pt->handle_nmi) = 1; - event->hw.state = 0; + hwc->state = 0; pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); pt_config(event); + + return; + +fail_end_stop: + perf_aux_output_end(&pt->handle, 0, true); +fail_stop: + hwc->state = PERF_HES_STOPPED; } static void pt_event_stop(struct perf_event *event, int mode) @@ -1035,19 +1028,7 @@ static void pt_event_stop(struct perf_event *event, int mode) pt_handle_status(pt); pt_update_head(pt); - } -} -static void pt_event_del(struct perf_event *event, int mode) -{ - struct pt *pt = this_cpu_ptr(&pt_ctx); - struct pt_buffer *buf; - - pt_event_stop(event, PERF_EF_UPDATE); - - buf = perf_get_aux(&pt->handle); - - if (buf) { if (buf->snapshot) pt->handle.head = local_xchg(&buf->data_size, @@ -1057,9 +1038,13 @@ static void pt_event_del(struct perf_event *event, int mode) } } +static void pt_event_del(struct perf_event *event, int mode) +{ + pt_event_stop(event, PERF_EF_UPDATE); +} + static int pt_event_add(struct perf_event *event, int mode) { - struct pt_buffer *buf; struct pt *pt = this_cpu_ptr(&pt_ctx); struct hw_perf_event *hwc = &event->hw; int ret = -EBUSY; @@ -1067,34 +1052,18 @@ static int pt_event_add(struct perf_event *event, int mode) if (pt->handle.event) goto fail; - buf = perf_aux_output_begin(&pt->handle, event); - ret = -EINVAL; - if (!buf) - goto fail_stop; - - pt_buffer_reset_offsets(buf, pt->handle.head); - if (!buf->snapshot) { - ret = pt_buffer_reset_markers(buf, &pt->handle); - if (ret) - goto fail_end_stop; - } - if (mode & PERF_EF_START) { pt_event_start(event, 0); - ret = -EBUSY; + ret = -EINVAL; if (hwc->state == PERF_HES_STOPPED) - goto fail_end_stop; + goto fail; } else { hwc->state = PERF_HES_STOPPED; } - return 0; - -fail_end_stop: - perf_aux_output_end(&pt->handle, 0, true); -fail_stop: - hwc->state = PERF_HES_STOPPED; + ret = 0; fail: + return ret; } @@ -1137,7 +1106,7 @@ static __init int pt_init(void) BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); - if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + if (!boot_cpu_has(X86_FEATURE_INTEL_PT)) return -ENODEV; get_online_cpus(); diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 1705c9d75e44..c9b7489ae8ee 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -53,6 +53,8 @@ #include <asm/cpu_device_id.h> #include "../perf_event.h" +MODULE_LICENSE("GPL"); + /* * RAPL energy status counters */ @@ -592,6 +594,11 @@ static int rapl_cpu_notifier(struct notifier_block *self, return NOTIFY_OK; } +static struct notifier_block rapl_cpu_nb = { + .notifier_call = rapl_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; + static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -660,7 +667,7 @@ static int __init rapl_prepare_cpus(void) return 0; } -static void __init cleanup_rapl_pmus(void) +static void cleanup_rapl_pmus(void) { int i; @@ -691,52 +698,78 @@ static int __init init_rapl_pmus(void) return 0; } +#define X86_RAPL_MODEL_MATCH(model, init) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } + +struct intel_rapl_init_fun { + bool apply_quirk; + int cntr_mask; + struct attribute **attrs; +}; + +static const struct intel_rapl_init_fun snb_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_CLN, + .attrs = rapl_events_cln_attr, +}; + +static const struct intel_rapl_init_fun hsx_rapl_init __initconst = { + .apply_quirk = true, + .cntr_mask = RAPL_IDX_SRV, + .attrs = rapl_events_srv_attr, +}; + +static const struct intel_rapl_init_fun hsw_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_HSW, + .attrs = rapl_events_hsw_attr, +}; + +static const struct intel_rapl_init_fun snbep_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_SRV, + .attrs = rapl_events_srv_attr, +}; + +static const struct intel_rapl_init_fun knl_rapl_init __initconst = { + .apply_quirk = true, + .cntr_mask = RAPL_IDX_KNL, + .attrs = rapl_events_knl_attr, +}; + static const struct x86_cpu_id rapl_cpu_match[] __initconst = { - [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, - [1] = {}, + X86_RAPL_MODEL_MATCH(42, snb_rapl_init), /* Sandy Bridge */ + X86_RAPL_MODEL_MATCH(58, snb_rapl_init), /* Ivy Bridge */ + X86_RAPL_MODEL_MATCH(63, hsx_rapl_init), /* Haswell-Server */ + X86_RAPL_MODEL_MATCH(79, hsx_rapl_init), /* Broadwell-Server */ + X86_RAPL_MODEL_MATCH(60, hsw_rapl_init), /* Haswell */ + X86_RAPL_MODEL_MATCH(69, hsw_rapl_init), /* Haswell-Celeron */ + X86_RAPL_MODEL_MATCH(70, hsw_rapl_init), /* Haswell GT3e */ + X86_RAPL_MODEL_MATCH(61, hsw_rapl_init), /* Broadwell */ + X86_RAPL_MODEL_MATCH(71, hsw_rapl_init), /* Broadwell-H */ + X86_RAPL_MODEL_MATCH(45, snbep_rapl_init), /* Sandy Bridge-EP */ + X86_RAPL_MODEL_MATCH(62, snbep_rapl_init), /* IvyTown */ + X86_RAPL_MODEL_MATCH(87, knl_rapl_init), /* Knights Landing */ + {}, }; +MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match); + static int __init rapl_pmu_init(void) { - bool apply_quirk = false; + const struct x86_cpu_id *id; + struct intel_rapl_init_fun *rapl_init; + bool apply_quirk; int ret; - if (!x86_match_cpu(rapl_cpu_match)) + id = x86_match_cpu(rapl_cpu_match); + if (!id) return -ENODEV; - switch (boot_cpu_data.x86_model) { - case 42: /* Sandy Bridge */ - case 58: /* Ivy Bridge */ - rapl_cntr_mask = RAPL_IDX_CLN; - rapl_pmu_events_group.attrs = rapl_events_cln_attr; - break; - case 63: /* Haswell-Server */ - case 79: /* Broadwell-Server */ - apply_quirk = true; - rapl_cntr_mask = RAPL_IDX_SRV; - rapl_pmu_events_group.attrs = rapl_events_srv_attr; - break; - case 60: /* Haswell */ - case 69: /* Haswell-Celeron */ - case 70: /* Haswell GT3e */ - case 61: /* Broadwell */ - case 71: /* Broadwell-H */ - rapl_cntr_mask = RAPL_IDX_HSW; - rapl_pmu_events_group.attrs = rapl_events_hsw_attr; - break; - case 45: /* Sandy Bridge-EP */ - case 62: /* IvyTown */ - rapl_cntr_mask = RAPL_IDX_SRV; - rapl_pmu_events_group.attrs = rapl_events_srv_attr; - break; - case 87: /* Knights Landing */ - apply_quirk = true; - rapl_cntr_mask = RAPL_IDX_KNL; - rapl_pmu_events_group.attrs = rapl_events_knl_attr; - break; - default: - return -ENODEV; - } + rapl_init = (struct intel_rapl_init_fun *)id->driver_data; + apply_quirk = rapl_init->apply_quirk; + rapl_cntr_mask = rapl_init->cntr_mask; + rapl_pmu_events_group.attrs = rapl_init->attrs; ret = rapl_check_hw_unit(apply_quirk); if (ret) @@ -756,7 +789,7 @@ static int __init rapl_pmu_init(void) if (ret) goto out; - __perf_cpu_notifier(rapl_cpu_notifier); + __register_cpu_notifier(&rapl_cpu_nb); cpu_notifier_register_done(); rapl_advertise(); return 0; @@ -767,4 +800,14 @@ out: cpu_notifier_register_done(); return ret; } -device_initcall(rapl_pmu_init); +module_init(rapl_pmu_init); + +static void __exit intel_rapl_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&rapl_cpu_nb); + perf_pmu_unregister(&rapl_pmus->pmu); + cleanup_rapl_pmus(); + cpu_notifier_register_done(); +} +module_exit(intel_rapl_exit); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7012d18bb293..17734a6ef474 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1,3 +1,4 @@ +#include <asm/cpu_device_id.h> #include "uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; @@ -21,6 +22,8 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +MODULE_LICENSE("GPL"); + static int uncore_pcibus_to_physid(struct pci_bus *bus) { struct pci2phy_map *map; @@ -754,7 +757,7 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) +static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) { struct intel_uncore_pmu *pmu = type->pmus; struct intel_uncore_box *box; @@ -770,7 +773,7 @@ static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) } } -static void __init uncore_exit_boxes(void *dummy) +static void uncore_exit_boxes(void *dummy) { struct intel_uncore_type **types; @@ -787,7 +790,7 @@ static void uncore_free_boxes(struct intel_uncore_pmu *pmu) kfree(pmu->boxes); } -static void __init uncore_type_exit(struct intel_uncore_type *type) +static void uncore_type_exit(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmu = type->pmus; int i; @@ -804,7 +807,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) type->events_group = NULL; } -static void __init uncore_types_exit(struct intel_uncore_type **types) +static void uncore_types_exit(struct intel_uncore_type **types) { for (; *types; types++) uncore_type_exit(*types); @@ -989,46 +992,6 @@ static int __init uncore_pci_init(void) size_t size; int ret; - switch (boot_cpu_data.x86_model) { - case 45: /* Sandy Bridge-EP */ - ret = snbep_uncore_pci_init(); - break; - case 62: /* Ivy Bridge-EP */ - ret = ivbep_uncore_pci_init(); - break; - case 63: /* Haswell-EP */ - ret = hswep_uncore_pci_init(); - break; - case 79: /* BDX-EP */ - case 86: /* BDX-DE */ - ret = bdx_uncore_pci_init(); - break; - case 42: /* Sandy Bridge */ - ret = snb_uncore_pci_init(); - break; - case 58: /* Ivy Bridge */ - ret = ivb_uncore_pci_init(); - break; - case 60: /* Haswell */ - case 69: /* Haswell Celeron */ - ret = hsw_uncore_pci_init(); - break; - case 61: /* Broadwell */ - ret = bdw_uncore_pci_init(); - break; - case 87: /* Knights Landing */ - ret = knl_uncore_pci_init(); - break; - case 94: /* SkyLake */ - ret = skl_uncore_pci_init(); - break; - default: - return -ENODEV; - } - - if (ret) - return ret; - size = max_packages * sizeof(struct pci_extra_dev); uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL); if (!uncore_extra_pci_dev) { @@ -1060,7 +1023,7 @@ err: return ret; } -static void __init uncore_pci_exit(void) +static void uncore_pci_exit(void) { if (pcidrv_registered) { pcidrv_registered = false; @@ -1287,46 +1250,6 @@ static int __init uncore_cpu_init(void) { int ret; - switch (boot_cpu_data.x86_model) { - case 26: /* Nehalem */ - case 30: - case 37: /* Westmere */ - case 44: - nhm_uncore_cpu_init(); - break; - case 42: /* Sandy Bridge */ - case 58: /* Ivy Bridge */ - case 60: /* Haswell */ - case 69: /* Haswell */ - case 70: /* Haswell */ - case 61: /* Broadwell */ - case 71: /* Broadwell */ - snb_uncore_cpu_init(); - break; - case 45: /* Sandy Bridge-EP */ - snbep_uncore_cpu_init(); - break; - case 46: /* Nehalem-EX */ - case 47: /* Westmere-EX aka. Xeon E7 */ - nhmex_uncore_cpu_init(); - break; - case 62: /* Ivy Bridge-EP */ - ivbep_uncore_cpu_init(); - break; - case 63: /* Haswell-EP */ - hswep_uncore_cpu_init(); - break; - case 79: /* BDX-EP */ - case 86: /* BDX-DE */ - bdx_uncore_cpu_init(); - break; - case 87: /* Knights Landing */ - knl_uncore_cpu_init(); - break; - default: - return -ENODEV; - } - ret = uncore_types_init(uncore_msr_uncores, true); if (ret) goto err; @@ -1376,11 +1299,105 @@ static int __init uncore_cpumask_init(bool msr) return 0; } +#define X86_UNCORE_MODEL_MATCH(model, init) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } + +struct intel_uncore_init_fun { + void (*cpu_init)(void); + int (*pci_init)(void); +}; + +static const struct intel_uncore_init_fun nhm_uncore_init __initconst = { + .cpu_init = nhm_uncore_cpu_init, +}; + +static const struct intel_uncore_init_fun snb_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = snb_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun ivb_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = ivb_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun hsw_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = hsw_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun bdw_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = bdw_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun snbep_uncore_init __initconst = { + .cpu_init = snbep_uncore_cpu_init, + .pci_init = snbep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun nhmex_uncore_init __initconst = { + .cpu_init = nhmex_uncore_cpu_init, +}; + +static const struct intel_uncore_init_fun ivbep_uncore_init __initconst = { + .cpu_init = ivbep_uncore_cpu_init, + .pci_init = ivbep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun hswep_uncore_init __initconst = { + .cpu_init = hswep_uncore_cpu_init, + .pci_init = hswep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun bdx_uncore_init __initconst = { + .cpu_init = bdx_uncore_cpu_init, + .pci_init = bdx_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun knl_uncore_init __initconst = { + .cpu_init = knl_uncore_cpu_init, + .pci_init = knl_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun skl_uncore_init __initconst = { + .pci_init = skl_uncore_pci_init, +}; + +static const struct x86_cpu_id intel_uncore_match[] __initconst = { + X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init), /* Nehalem */ + X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init), + X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init), /* Westmere */ + X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init), + X86_UNCORE_MODEL_MATCH(42, snb_uncore_init), /* Sandy Bridge */ + X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init), /* Ivy Bridge */ + X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init), /* Haswell */ + X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init), /* Haswell Celeron */ + X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init), /* Haswell */ + X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init), /* Broadwell */ + X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init), /* Broadwell */ + X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init), /* Sandy Bridge-EP */ + X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init), /* Nehalem-EX */ + X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init), /* Westmere-EX aka. Xeon E7 */ + X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init), /* Ivy Bridge-EP */ + X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init), /* Haswell-EP */ + X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init), /* BDX-EP */ + X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init), /* BDX-DE */ + X86_UNCORE_MODEL_MATCH(87, knl_uncore_init), /* Knights Landing */ + X86_UNCORE_MODEL_MATCH(94, skl_uncore_init), /* SkyLake */ + {}, +}; + +MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); + static int __init intel_uncore_init(void) { - int pret, cret, ret; + const struct x86_cpu_id *id; + struct intel_uncore_init_fun *uncore_init; + int pret = 0, cret = 0, ret; - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + id = x86_match_cpu(intel_uncore_match); + if (!id) return -ENODEV; if (cpu_has_hypervisor) @@ -1388,8 +1405,17 @@ static int __init intel_uncore_init(void) max_packages = topology_max_packages(); - pret = uncore_pci_init(); - cret = uncore_cpu_init(); + uncore_init = (struct intel_uncore_init_fun *)id->driver_data; + if (uncore_init->pci_init) { + pret = uncore_init->pci_init(); + if (!pret) + pret = uncore_pci_init(); + } + + if (uncore_init->cpu_init) { + uncore_init->cpu_init(); + cret = uncore_cpu_init(); + } if (cret && pret) return -ENODEV; @@ -1409,4 +1435,14 @@ err: cpu_notifier_register_done(); return ret; } -device_initcall(intel_uncore_init); +module_init(intel_uncore_init); + +static void __exit intel_uncore_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&uncore_cpu_nb); + uncore_types_exit(uncore_msr_uncores); + uncore_pci_exit(); + cpu_notifier_register_done(); +} +module_exit(intel_uncore_exit); diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ec863b9a9f78..7111400a1f9a 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -6,6 +6,8 @@ enum perf_msr_id { PERF_MSR_MPERF = 2, PERF_MSR_PPERF = 3, PERF_MSR_SMI = 4, + PERF_MSR_PTSC = 5, + PERF_MSR_IRPERF = 6, PERF_MSR_EVENT_MAX, }; @@ -15,6 +17,16 @@ static bool test_aperfmperf(int idx) return boot_cpu_has(X86_FEATURE_APERFMPERF); } +static bool test_ptsc(int idx) +{ + return boot_cpu_has(X86_FEATURE_PTSC); +} + +static bool test_irperf(int idx) +{ + return boot_cpu_has(X86_FEATURE_IRPERF); +} + static bool test_intel(int idx) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || @@ -69,18 +81,22 @@ struct perf_msr { bool (*test)(int idx); }; -PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); -PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); -PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); -PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); -PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); +PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); +PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); +PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); +PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); +PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); +PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05"); +PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06"); static struct perf_msr msr[] = { - [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, - [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, - [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, - [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, - [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, + [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, + [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, + [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, + [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, + [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, + [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, }, + [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, }, }; static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8f9afefd2dc5..8cd6a320f658 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -177,6 +177,7 @@ #define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ #define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ @@ -250,6 +251,7 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5b3c9a55f51c..f882cbf9e3da 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -315,6 +315,9 @@ #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +/* Fam 17h MSRs */ +#define MSR_F17H_IRPERF 0xc00000e9 + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 @@ -328,6 +331,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_PTSC 0xc0010280 #define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index bf4db6eaec8f..bd074151bfd6 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -578,7 +578,7 @@ static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs) riprel_post_xol(auprobe, regs); } -static struct uprobe_xol_ops default_xol_ops = { +static const struct uprobe_xol_ops default_xol_ops = { .pre_xol = default_pre_xol_op, .post_xol = default_post_xol_op, .abort = default_abort_op, @@ -695,7 +695,7 @@ static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn) 0, insn->immediate.nbytes); } -static struct uprobe_xol_ops branch_xol_ops = { +static const struct uprobe_xol_ops branch_xol_ops = { .emulate = branch_emulate_op, .post_xol = branch_post_xol_op, }; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f291275ffd71..b8b195fbe787 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -838,6 +838,12 @@ extern void perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); +static inline bool +is_default_overflow_handler(struct perf_event *event) +{ + return (event->overflow_handler == perf_event_output); +} + extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1afe9623c1a7..a3c19034d5f8 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -401,6 +401,7 @@ struct perf_event_attr { #define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) #define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) #define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) enum perf_event_ioc_flags { PERF_IOC_FLAG_GROUP = 1U << 0, diff --git a/kernel/events/core.c b/kernel/events/core.c index 2c78b6f47339..21ba024c9ed1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1926,8 +1926,13 @@ event_sched_in(struct perf_event *event, if (event->state <= PERF_EVENT_STATE_OFF) return 0; - event->state = PERF_EVENT_STATE_ACTIVE; - event->oncpu = smp_processor_id(); + WRITE_ONCE(event->oncpu, smp_processor_id()); + /* + * Order event::oncpu write to happen before the ACTIVE state + * is visible. + */ + smp_wmb(); + WRITE_ONCE(event->state, PERF_EVENT_STATE_ACTIVE); /* * Unthrottle events, since we scheduled we might have missed several @@ -2359,6 +2364,29 @@ void perf_event_enable(struct perf_event *event) } EXPORT_SYMBOL_GPL(perf_event_enable); +static int __perf_event_stop(void *info) +{ + struct perf_event *event = info; + + /* for AUX events, our job is done if the event is already inactive */ + if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE) + return 0; + + /* matches smp_wmb() in event_sched_in() */ + smp_rmb(); + + /* + * There is a window with interrupts enabled before we get here, + * so we need to check again lest we try to stop another CPU's event. + */ + if (READ_ONCE(event->oncpu) != smp_processor_id()) + return -EAGAIN; + + event->pmu->stop(event, PERF_EF_UPDATE); + + return 0; +} + static int _perf_event_refresh(struct perf_event *event, int refresh) { /* @@ -4352,6 +4380,19 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon case PERF_EVENT_IOC_SET_BPF: return perf_event_set_bpf_prog(event, arg); + case PERF_EVENT_IOC_PAUSE_OUTPUT: { + struct ring_buffer *rb; + + rcu_read_lock(); + rb = rcu_dereference(event->rb); + if (!rb || !rb->nr_pages) { + rcu_read_unlock(); + return -EINVAL; + } + rb_toggle_paused(rb, !!arg); + rcu_read_unlock(); + return 0; + } default: return -ENOTTY; } @@ -4668,6 +4709,8 @@ static void perf_mmap_open(struct vm_area_struct *vma) event->pmu->event_mapped(event); } +static void perf_pmu_output_stop(struct perf_event *event); + /* * A buffer can be mmap()ed multiple times; either directly through the same * event, or through other events by use of perf_event_set_output(). @@ -4695,10 +4738,22 @@ static void perf_mmap_close(struct vm_area_struct *vma) */ if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff && atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) { + /* + * Stop all AUX events that are writing to this buffer, + * so that we can free its AUX pages and corresponding PMU + * data. Note that after rb::aux_mmap_count dropped to zero, + * they won't start any more (see perf_aux_output_begin()). + */ + perf_pmu_output_stop(event); + + /* now it's safe to free the pages */ atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm); vma->vm_mm->pinned_vm -= rb->aux_mmap_locked; + /* this has to be the last one */ rb_free_aux(rb); + WARN_ON_ONCE(atomic_read(&rb->aux_refcount)); + mutex_unlock(&event->mmap_mutex); } @@ -5769,6 +5824,80 @@ next: rcu_read_unlock(); } +struct remote_output { + struct ring_buffer *rb; + int err; +}; + +static void __perf_event_output_stop(struct perf_event *event, void *data) +{ + struct perf_event *parent = event->parent; + struct remote_output *ro = data; + struct ring_buffer *rb = ro->rb; + + if (!has_aux(event)) + return; + + if (!parent) + parent = event; + + /* + * In case of inheritance, it will be the parent that links to the + * ring-buffer, but it will be the child that's actually using it: + */ + if (rcu_dereference(parent->rb) == rb) + ro->err = __perf_event_stop(event); +} + +static int __perf_pmu_output_stop(void *info) +{ + struct perf_event *event = info; + struct pmu *pmu = event->pmu; + struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct remote_output ro = { + .rb = event->rb, + }; + + rcu_read_lock(); + perf_event_aux_ctx(&cpuctx->ctx, __perf_event_output_stop, &ro); + if (cpuctx->task_ctx) + perf_event_aux_ctx(cpuctx->task_ctx, __perf_event_output_stop, + &ro); + rcu_read_unlock(); + + return ro.err; +} + +static void perf_pmu_output_stop(struct perf_event *event) +{ + struct perf_event *iter; + int err, cpu; + +restart: + rcu_read_lock(); + list_for_each_entry_rcu(iter, &event->rb->event_list, rb_entry) { + /* + * For per-CPU events, we need to make sure that neither they + * nor their children are running; for cpu==-1 events it's + * sufficient to stop the event itself if it's active, since + * it can't have children. + */ + cpu = iter->cpu; + if (cpu == -1) + cpu = READ_ONCE(iter->oncpu); + + if (cpu == -1) + continue; + + err = cpu_function_call(cpu, __perf_pmu_output_stop, event); + if (err == -EAGAIN) { + rcu_read_unlock(); + goto restart; + } + } + rcu_read_unlock(); +} + /* * task tracking -- fork/exit * @@ -6500,10 +6629,7 @@ static int __perf_event_overflow(struct perf_event *event, irq_work_queue(&event->pending); } - if (event->overflow_handler) - event->overflow_handler(event, data, regs); - else - perf_event_output(event, data, regs); + event->overflow_handler(event, data, regs); if (*perf_event_fasync(event) && event->pending_kill) { event->pending_wakeup = 1; @@ -7694,6 +7820,15 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) } skip_type: + if (pmu->task_ctx_nr == perf_hw_context) { + static int hw_context_taken = 0; + + if (WARN_ON_ONCE(hw_context_taken)) + pmu->task_ctx_nr = perf_invalid_context; + + hw_context_taken = 1; + } + pmu->pmu_cpu_context = find_pmu_context(pmu->task_ctx_nr); if (pmu->pmu_cpu_context) goto got_cpu_context; @@ -8015,8 +8150,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, context = parent_event->overflow_handler_context; } - event->overflow_handler = overflow_handler; - event->overflow_handler_context = context; + if (overflow_handler) { + event->overflow_handler = overflow_handler; + event->overflow_handler_context = context; + } else { + event->overflow_handler = perf_event_output; + event->overflow_handler_context = NULL; + } perf_event__state_init(event); diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 4199b6d193f5..05f9f6d626df 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -11,13 +11,13 @@ struct ring_buffer { atomic_t refcount; struct rcu_head rcu_head; - struct irq_work irq_work; #ifdef CONFIG_PERF_USE_VMALLOC struct work_struct work; int page_order; /* allocation order */ #endif int nr_pages; /* nr of data pages */ int overwrite; /* can overwrite itself */ + int paused; /* can write into ring buffer */ atomic_t poll; /* POLL_ for wakeups */ @@ -65,6 +65,14 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head) rb_free(rb); } +static inline void rb_toggle_paused(struct ring_buffer *rb, bool pause) +{ + if (!pause && rb->nr_pages) + rb->paused = 0; + else + rb->paused = 1; +} + extern struct ring_buffer * rb_alloc(int nr_pages, long watermark, int cpu, int flags); extern void perf_event_wakeup(struct perf_event *event); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index c61f0cbd308b..60be55a64040 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -102,8 +102,21 @@ out: preempt_enable(); } -int perf_output_begin(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size) +static bool __always_inline +ring_buffer_has_space(unsigned long head, unsigned long tail, + unsigned long data_size, unsigned int size, + bool backward) +{ + if (!backward) + return CIRC_SPACE(head, tail, data_size) >= size; + else + return CIRC_SPACE(tail, head, data_size) >= size; +} + +static int __always_inline +__perf_output_begin(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size, + bool backward) { struct ring_buffer *rb; unsigned long tail, offset, head; @@ -125,8 +138,11 @@ int perf_output_begin(struct perf_output_handle *handle, if (unlikely(!rb)) goto out; - if (unlikely(!rb->nr_pages)) + if (unlikely(rb->paused)) { + if (rb->nr_pages) + local_inc(&rb->lost); goto out; + } handle->rb = rb; handle->event = event; @@ -143,9 +159,12 @@ int perf_output_begin(struct perf_output_handle *handle, do { tail = READ_ONCE(rb->user_page->data_tail); offset = head = local_read(&rb->head); - if (!rb->overwrite && - unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size)) - goto fail; + if (!rb->overwrite) { + if (unlikely(!ring_buffer_has_space(head, tail, + perf_data_size(rb), + size, backward))) + goto fail; + } /* * The above forms a control dependency barrier separating the @@ -159,9 +178,17 @@ int perf_output_begin(struct perf_output_handle *handle, * See perf_output_put_handle(). */ - head += size; + if (!backward) + head += size; + else + head -= size; } while (local_cmpxchg(&rb->head, offset, head) != offset); + if (backward) { + offset = head; + head = (u64)(-head); + } + /* * We rely on the implied barrier() by local_cmpxchg() to ensure * none of the data stores below can be lifted up by the compiler. @@ -203,6 +230,12 @@ out: return -ENOSPC; } +int perf_output_begin(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + return __perf_output_begin(handle, event, size, false); +} + unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { @@ -221,8 +254,6 @@ void perf_output_end(struct perf_output_handle *handle) rcu_read_unlock(); } -static void rb_irq_work(struct irq_work *work); - static void ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) { @@ -243,16 +274,13 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) INIT_LIST_HEAD(&rb->event_list); spin_lock_init(&rb->event_lock); - init_irq_work(&rb->irq_work, rb_irq_work); -} -static void ring_buffer_put_async(struct ring_buffer *rb) -{ - if (!atomic_dec_and_test(&rb->refcount)) - return; - - rb->rcu_head.next = (void *)rb; - irq_work_queue(&rb->irq_work); + /* + * perf_output_begin() only checks rb->paused, therefore + * rb->paused must be true if we have no pages for output. + */ + if (!rb->nr_pages) + rb->paused = 1; } /* @@ -264,6 +292,10 @@ static void ring_buffer_put_async(struct ring_buffer *rb) * The ordering is similar to that of perf_output_{begin,end}, with * the exception of (B), which should be taken care of by the pmu * driver, since ordering rules will differ depending on hardware. + * + * Call this from pmu::start(); see the comment in perf_aux_output_end() + * about its use in pmu callbacks. Both can also be called from the PMI + * handler if needed. */ void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) @@ -288,6 +320,13 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, goto err; /* + * If rb::aux_mmap_count is zero (and rb_has_aux() above went through), + * the aux buffer is in perf_mmap_close(), about to get freed. + */ + if (!atomic_read(&rb->aux_mmap_count)) + goto err_put; + + /* * Nesting is not supported for AUX area, make sure nested * writers are caught early */ @@ -328,10 +367,11 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, return handle->rb->aux_priv; err_put: + /* can't be last */ rb_free_aux(rb); err: - ring_buffer_put_async(rb); + ring_buffer_put(rb); handle->event = NULL; return NULL; @@ -342,6 +382,10 @@ err: * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the * pmu driver's responsibility to observe ordering rules of the hardware, * so that all the data is externally visible before this is called. + * + * Note: this has to be called from pmu::stop() callback, as the assumption + * of the AUX buffer management code is that after pmu::stop(), the AUX + * transaction must be stopped and therefore drop the AUX reference count. */ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, bool truncated) @@ -381,8 +425,9 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size, handle->event = NULL; local_set(&rb->aux_nest, 0); + /* can't be last */ rb_free_aux(rb); - ring_buffer_put_async(rb); + ring_buffer_put(rb); } /* @@ -463,6 +508,14 @@ static void __rb_free_aux(struct ring_buffer *rb) { int pg; + /* + * Should never happen, the last reference should be dropped from + * perf_mmap_close() path, which first stops aux transactions (which + * in turn are the atomic holders of aux_refcount) and then does the + * last rb_free_aux(). + */ + WARN_ON_ONCE(in_atomic()); + if (rb->aux_priv) { rb->free_aux(rb->aux_priv); rb->free_aux = NULL; @@ -574,18 +627,7 @@ out: void rb_free_aux(struct ring_buffer *rb) { if (atomic_dec_and_test(&rb->aux_refcount)) - irq_work_queue(&rb->irq_work); -} - -static void rb_irq_work(struct irq_work *work) -{ - struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work); - - if (!atomic_read(&rb->aux_refcount)) __rb_free_aux(rb); - - if (rb->rcu_head.next == (void *)rb) - call_rcu(&rb->rcu_head, rb_free_rcu); } #ifndef CONFIG_PERF_USE_VMALLOC diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 00df25fd86ef..e11108f1d197 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -47,6 +47,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event, if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) return -EPERM; + if (!is_sampling_event(p_event)) + return 0; + /* * We don't allow user space callchains for function trace * event, due to issues with page faults while tracing page diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 6b7707270aa3..9f878619077a 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -30,6 +30,7 @@ endef FEATURE_TESTS_BASIC := \ backtrace \ dwarf \ + dwarf_getlocations \ fortify-source \ sync-compare-and-swap \ glibc \ @@ -78,6 +79,7 @@ endif FEATURE_DISPLAY ?= \ dwarf \ + dwarf_getlocations \ glibc \ gtk2 \ libaudit \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index c5f4c417428d..4ae94dbfdab9 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -3,6 +3,7 @@ FILES= \ test-backtrace.bin \ test-bionic.bin \ test-dwarf.bin \ + test-dwarf_getlocations.bin \ test-fortify-source.bin \ test-sync-compare-and-swap.bin \ test-glibc.bin \ @@ -82,6 +83,9 @@ endif $(OUTPUT)test-dwarf.bin: $(BUILD) $(DWARFLIBS) +$(OUTPUT)test-dwarf_getlocations.bin: + $(BUILD) $(DWARFLIBS) + $(OUTPUT)test-libelf-mmap.bin: $(BUILD) -lelf diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index e499a36c1e4a..a282e8cb84f3 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -41,6 +41,10 @@ # include "test-dwarf.c" #undef main +#define main main_test_dwarf_getlocations +# include "test-dwarf_getlocations.c" +#undef main + #define main main_test_libelf_getphdrnum # include "test-libelf-getphdrnum.c" #undef main @@ -143,6 +147,7 @@ int main(int argc, char *argv[]) main_test_libelf_mmap(); main_test_glibc(); main_test_dwarf(); + main_test_dwarf_getlocations(); main_test_libelf_getphdrnum(); main_test_libunwind(); main_test_libaudit(); diff --git a/tools/build/feature/test-dwarf_getlocations.c b/tools/build/feature/test-dwarf_getlocations.c new file mode 100644 index 000000000000..70162699dd43 --- /dev/null +++ b/tools/build/feature/test-dwarf_getlocations.c @@ -0,0 +1,12 @@ +#include <stdlib.h> +#include <elfutils/libdw.h> + +int main(void) +{ + Dwarf_Addr base, start, end; + Dwarf_Attribute attr; + Dwarf_Op *op; + size_t nops; + ptrdiff_t offset = 0; + return (int)dwarf_getlocations(&attr, offset, &base, &start, &end, &op, &nops); +} diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt index be764f9ec769..c6c8318e38a2 100644 --- a/tools/perf/Documentation/intel-pt.txt +++ b/tools/perf/Documentation/intel-pt.txt @@ -672,6 +672,7 @@ The letters are: d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) + s skip initial number of events "Instructions" events look like they were recorded by "perf record -e instructions". @@ -730,6 +731,12 @@ from one sample to the next. To disable trace decoding entirely, use the option --no-itrace. +It is also possible to skip events generated (instructions, branches, transactions) +at the beginning. This is useful to ignore initialization code. + + --itrace=i0nss1000000 + +skips the first million instructions. dump option ----------- diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index 65453f4c7006..e2a4c5e0dbe5 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -7,6 +7,7 @@ d create a debug log g synthesize a call chain (use with i or x) l synthesize last branch entries (use with i or x) + s skip initial number of events The default is all events i.e. the same as --itrace=ibxe @@ -24,3 +25,10 @@ Also the number of last branch entries (default 64, max. 1024) for instructions or transactions events can be specified. + + It is also possible to skip events generated (instructions, branches, transactions) + at the beginning. This is useful to ignore initialization code. + + --itrace=i0nss1000000 + + skips the first million instructions. diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index e9cd39a92dc2..778f54d4d0bd 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -33,7 +33,7 @@ OPTIONS -f:: --force:: - Don't complain, do it. + Don't do ownership validation. -v:: --verbose:: diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index d1deb573877f..3e9490b9c533 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -75,7 +75,7 @@ OPTIONS -f:: --force:: - Don't complain, do it. + Don't do ownership validation. --symfs=<directory>:: Look for files with symbols relative to this directory. diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index ec723d0a5bb3..a126e97a8114 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -93,6 +93,67 @@ raw encoding of 0x1A8 can be used: You should refer to the processor specific documentation for getting these details. Some of them are referenced in the SEE ALSO section below. +ARBITRARY PMUS +-------------- + +perf also supports an extended syntax for specifying raw parameters +to PMUs. Using this typically requires looking up the specific event +in the CPU vendor specific documentation. + +The available PMUs and their raw parameters can be listed with + + ls /sys/devices/*/format + +For example the raw event "LSD.UOPS" core pmu event above could +be specified as + + perf stat -e cpu/event=0xa8,umask=0x1,name=LSD.UOPS_CYCLES,cmask=1/ ... + +PER SOCKET PMUS +--------------- + +Some PMUs are not associated with a core, but with a whole CPU socket. +Events on these PMUs generally cannot be sampled, but only counted globally +with perf stat -a. They can be bound to one logical CPU, but will measure +all the CPUs in the same socket. + +This example measures memory bandwidth every second +on the first memory controller on socket 0 of a Intel Xeon system + + perf stat -C 0 -a uncore_imc_0/cas_count_read/,uncore_imc_0/cas_count_write/ -I 1000 ... + +Each memory controller has its own PMU. Measuring the complete system +bandwidth would require specifying all imc PMUs (see perf list output), +and adding the values together. + +This example measures the combined core power every second + + perf stat -I 1000 -e power/energy-cores/ -a + +ACCESS RESTRICTIONS +------------------- + +For non root users generally only context switched PMU events are available. +This is normally only the events in the cpu PMU, the predefined events +like cycles and instructions and some software events. + +Other PMUs and global measurements are normally root only. +Some event qualifiers, such as "any", are also root only. + +This can be overriden by setting the kernel.perf_event_paranoid +sysctl to -1, which allows non root to use these events. + +For accessing trace point events perf needs to have read access to +/sys/kernel/debug/tracing, even when perf_event_paranoid is in a relaxed +setting. + +TRACING +------- + +Some PMUs control advanced hardware tracing capabilities, such as Intel PT, +that allows low overhead execution tracing. These are described in a separate +intel-pt.txt document. + PARAMETERIZED EVENTS -------------------- @@ -106,6 +167,50 @@ also be supplied. For example: perf stat -C 0 -e 'hv_gpci/dtbp_ptitc,phys_processor_idx=0x2/' ... +EVENT GROUPS +------------ + +Perf supports time based multiplexing of events, when the number of events +active exceeds the number of hardware performance counters. Multiplexing +can cause measurement errors when the workload changes its execution +profile. + +When metrics are computed using formulas from event counts, it is useful to +ensure some events are always measured together as a group to minimize multiplexing +errors. Event groups can be specified using { }. + + perf stat -e '{instructions,cycles}' ... + +The number of available performance counters depend on the CPU. A group +cannot contain more events than available counters. +For example Intel Core CPUs typically have four generic performance counters +for the core, plus three fixed counters for instructions, cycles and +ref-cycles. Some special events have restrictions on which counter they +can schedule, and may not support multiple instances in a single group. +When too many events are specified in the group none of them will not +be measured. + +Globally pinned events can limit the number of counters available for +other groups. On x86 systems, the NMI watchdog pins a counter by default. +The nmi watchdog can be disabled as root with + + echo 0 > /proc/sys/kernel/nmi_watchdog + +Events from multiple different PMUs cannot be mixed in a group, with +some exceptions for software events. + +LEADER SAMPLING +--------------- + +perf also supports group leader sampling using the :S specifier. + + perf record -e '{cycles,instructions}:S' ... + perf report --group + +Normally all events in a event group sample, but with :S only +the first event (the leader) samples, and it only reads the values of the +other events in the group. + OPTIONS ------- @@ -143,5 +248,5 @@ SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-top[1], linkperf:perf-record[1], -http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], +http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide], http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming] diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 43310d8661fe..1d6092c460dd 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -48,6 +48,14 @@ OPTIONS option can be passed in record mode. It will be interpreted the same way as perf record. +-K:: +--all-kernel:: + Configure all used events to run in kernel space. + +-U:: +--all-user:: + Configure all used events to run in user space. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-report[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 12113992ac9d..496d42cdf02b 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -285,7 +285,7 @@ OPTIONS -f:: --force:: - Don't complain, do it. + Don't do ownership validation. --symfs=<directory>:: Look for files with symbols relative to this directory. diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 8ff4df956951..1cc08cc47ac5 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -50,6 +50,22 @@ OPTIONS --dump-raw-trace=:: Display verbose dump of the sched data. +OPTIONS for 'perf sched map' +---------------------------- + +--compact:: + Show only CPUs with activity. Helps visualizing on high core + count systems. + +--cpus:: + Show just entries with activities for the given CPUs. + +--color-cpus:: + Highlight the given cpus. + +--color-pids:: + Highlight the given pids. + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 382ddfb45d1d..4fc44c75263f 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -259,9 +259,23 @@ include::itrace.txt[] --full-source-path:: Show the full path for source files for srcline output. +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. This is a trade-off + between information loss and faster processing especially for + workloads that can have a very long callchain stack. + Note that when using the --itrace option the synthesized callchain size + will override this value if the synthesized callchain size is bigger. + + Default: 127 + --ns:: Use 9 decimal places when displaying time (i.e. show the nanoseconds) +-f:: +--force:: + Don't do ownership validation. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 13293de8869f..c075c002eaa4 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -117,9 +117,41 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --syscalls:: Trace system calls. This options is enabled by default. +--call-graph [mode,type,min[,limit],order[,key][,branch]]:: + Setup and enable call-graph (stack chain/backtrace) recording. + See `--call-graph` section in perf-record and perf-report + man pages for details. The ones that are most useful in 'perf trace' + are 'dwarf' and 'lbr', where available, try: 'perf trace --call-graph dwarf'. + + Using this will, for the root user, bump the value of --mmap-pages to 4 + times the maximum for non-root users, based on the kernel.perf_event_mlock_kb + sysctl. This is done only if the user doesn't specify a --mmap-pages value. + +--kernel-syscall-graph:: + Show the kernel callchains on the syscall exit path. + --event:: Trace other events, see 'perf list' for a complete list. +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. Note that at this point + this is just about the presentation part, i.e. the kernel is still + not limiting, the overhead of callchains needs to be set via the + knobs in --call-graph dwarf. + + Implies '--call-graph dwarf' when --call-graph not present on the + command line, on systems where DWARF unwinding was built in. + + Default: 127 + +--min-stack:: + Set the stack depth limit when parsing the callchain, anything + below the specified depth will be ignored. Disabled by default. + + Implies '--call-graph dwarf' when --call-graph not present on the + command line, on systems where DWARF unwinding was built in. + --proc-map-timeout:: When processing pre-existing threads /proc/XXX/mmap, it may take a long time, because the file may be huge. A time out is needed in such cases. diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 000ea210389d..bde8cbae7dd9 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -183,6 +183,11 @@ endif include config/Makefile endif +ifeq ($(config),0) +include $(srctree)/tools/scripts/Makefile.arch +-include arch/$(ARCH)/Makefile +endif + # The FEATURE_DUMP_EXPORT holds location of the actual # FEATURE_DUMP file to be used to bypass feature detection # (for bpf or any other subproject) @@ -297,8 +302,6 @@ endif # because maintaining the nesting to match is a pain. If # we had "elif" things would have been much nicer... --include arch/$(ARCH)/Makefile - ifneq ($(OUTPUT),) CFLAGS += -I$(OUTPUT) endif @@ -390,7 +393,7 @@ endif __build-dir = $(subst $(OUTPUT),,$(dir $@)) build-dir = $(if $(__build-dir),$(__build-dir),.) -prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep +prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h fixdep archheaders $(OUTPUT)%.o: %.c prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ @@ -430,7 +433,7 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) LIBPERF_IN := $(OUTPUT)libperf-in.o -$(LIBPERF_IN): fixdep FORCE +$(LIBPERF_IN): prepare fixdep FORCE $(Q)$(MAKE) $(build)=libperf $(LIB_FILE): $(LIBPERF_IN) @@ -625,7 +628,7 @@ config-clean: $(call QUIET_CLEAN, config) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null -clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected @@ -662,5 +665,5 @@ FORCE: .PHONY: all install clean config-clean strip install-gtk .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell .PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE prepare -.PHONY: libtraceevent_plugins +.PHONY: libtraceevent_plugins archheaders diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile index 269af2143735..a33729173b13 100644 --- a/tools/perf/arch/x86/Makefile +++ b/tools/perf/arch/x86/Makefile @@ -4,3 +4,26 @@ endif HAVE_KVM_STAT_SUPPORT := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 PERF_HAVE_JITDUMP := 1 + +### +# Syscall table generation +# + +out := $(OUTPUT)arch/x86/include/generated/asm +header := $(out)/syscalls_64.c +sys := $(srctree)/tools/perf/arch/x86/entry/syscalls +systbl := $(sys)/syscalltbl.sh + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sys)/syscall_64.tbl $(systbl) + @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + (diff -B arch/x86/entry/syscalls/syscall_64.tbl ../../arch/x86/entry/syscalls/syscall_64.tbl >/dev/null) \ + || echo "Warning: x86_64's syscall_64.tbl differs from kernel" >&2 )) || true + $(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@ + +clean:: + rm -f $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl new file mode 100644 index 000000000000..2e5b565adacc --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -0,0 +1,374 @@ +# +# 64-bit system call numbers and entry vectors +# +# The format is: +# <number> <abi> <name> <entry point> +# +# The abi is "common", "64" or "x32" for this file. +# +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 common rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn sys_rt_sigreturn/ptregs +16 64 ioctl sys_ioctl +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt +56 common clone sys_clone/ptregs +57 common fork sys_fork/ptregs +58 common vfork sys_vfork/ptregs +59 64 execve sys_execve/ptregs +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times +101 64 ptrace sys_ptrace +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 common rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack sys_sigaltstack +132 common utime sys_utime +133 common mknod sys_mknod +134 64 uselib +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl sys_iopl/ptregs +173 common ioperm sys_ioperm +174 64 create_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module +177 64 get_kernel_syms +178 64 query_module +179 common quotactl sys_quotactl +180 64 nfsservctl +181 common getpmsg +182 common putpmsg +183 common afs_syscall +184 common tuxcall +185 common security +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity +205 64 set_thread_area +206 64 io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 64 io_submit sys_io_submit +210 common io_cancel sys_io_cancel +211 64 get_thread_area +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create +214 64 epoll_ctl_old +215 64 epoll_wait_old +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes +236 64 vserver +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 common mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 common perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 common setns sys_setns +309 common getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev +312 common kcmp sys_kcmp +313 common finit_module sys_finit_module +314 common sched_setattr sys_sched_setattr +315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 +317 common seccomp sys_seccomp +318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create +320 common kexec_file_load sys_kexec_file_load +321 common bpf sys_bpf +322 64 execveat sys_execveat/ptregs +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range + +# +# x32-specific system call numbers start at 512 to avoid cache impact +# for native 64-bit operation. +# +512 x32 rt_sigaction compat_sys_rt_sigaction +513 x32 rt_sigreturn sys32_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve compat_sys_execve/ptregs +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending compat_sys_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait +524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo +525 x32 sigaltstack compat_sys_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit +545 x32 execveat compat_sys_execveat/ptregs diff --git a/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh new file mode 100755 index 000000000000..49a18b9ad9cf --- /dev/null +++ b/tools/perf/arch/x86/entry/syscalls/syscalltbl.sh @@ -0,0 +1,39 @@ +#!/bin/sh + +in="$1" +arch="$2" + +syscall_macro() { + nr="$1" + name="$2" + + echo " [$nr] = \"$name\"," +} + +emit() { + nr="$1" + entry="$2" + + syscall_macro "$nr" "$entry" +} + +echo "static const char *syscalltbl_${arch}[] = {" + +sorted_table=$(mktemp /tmp/syscalltbl.XXXXXX) +grep '^[0-9]' "$in" | sort -n > $sorted_table + +max_nr=0 +while read nr abi name entry compat; do + if [ $nr -ge 512 ] ; then # discard compat sycalls + break + fi + + emit "$nr" "$name" + max_nr=$nr +done < $sorted_table + +rm -f $sorted_table + +echo "};" + +echo "#define SYSCALLTBL_${arch}_MAX_ID ${max_nr}" diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 9d29ee283ac5..d4aa567a29c4 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -71,7 +71,7 @@ int test__perf_time_to_tsc(int subtest __maybe_unused) CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); evsel = perf_evlist__first(evlist); diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c index 9223c164e545..1f86ee8fb831 100644 --- a/tools/perf/arch/x86/util/dwarf-regs.c +++ b/tools/perf/arch/x86/util/dwarf-regs.c @@ -63,6 +63,8 @@ struct pt_regs_offset { # define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)} #endif +/* TODO: switching by dwarf address size */ +#ifndef __x86_64__ static const struct pt_regs_offset x86_32_regoffset_table[] = { REG_OFFSET_NAME_32("%ax", eax), REG_OFFSET_NAME_32("%cx", ecx), @@ -75,6 +77,8 @@ static const struct pt_regs_offset x86_32_regoffset_table[] = { REG_OFFSET_END, }; +#define regoffset_table x86_32_regoffset_table +#else static const struct pt_regs_offset x86_64_regoffset_table[] = { REG_OFFSET_NAME_64("%ax", rax), REG_OFFSET_NAME_64("%dx", rdx), @@ -95,11 +99,7 @@ static const struct pt_regs_offset x86_64_regoffset_table[] = { REG_OFFSET_END, }; -/* TODO: switching by dwarf address size */ -#ifdef __x86_64__ #define regoffset_table x86_64_regoffset_table -#else -#define regoffset_table x86_32_regoffset_table #endif /* Minus 1 for the ending REG_OFFSET_END */ diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index d66f9ad4df2e..7dc30637cf66 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -438,6 +438,11 @@ struct auxtrace_record *intel_bts_recording_init(int *err) if (!intel_bts_pmu) return NULL; + if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) { + *err = -errno; + return NULL; + } + btsr = zalloc(sizeof(struct intel_bts_recording)); if (!btsr) { *err = -ENOMEM; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index a3395179c9ee..a07b9605e93b 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -1027,6 +1027,11 @@ struct auxtrace_record *intel_pt_recording_init(int *err) if (!intel_pt_pmu) return NULL; + if (setenv("JITDUMP_USE_ARCH_TIMESTAMP", "1", 1)) { + *err = -errno; + return NULL; + } + ptr = zalloc(sizeof(struct intel_pt_recording)); if (!ptr) { *err = -ENOMEM; diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index fd2868490d00..357f1b13b5ae 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -7,7 +7,6 @@ #include <linux/types.h> #include "../../util/debug.h" #include "../../util/tsc.h" -#include "tsc.h" int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) @@ -46,3 +45,34 @@ u64 rdtsc(void) return low | ((u64)high) << 32; } + +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, + struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event event = { + .time_conv = { + .header = { + .type = PERF_RECORD_TIME_CONV, + .size = sizeof(struct time_conv_event), + }, + }, + }; + struct perf_tsc_conversion tc; + int err; + + err = perf_read_tsc_conversion(pc, &tc); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + pr_debug2("Synthesizing TSC conversion information\n"); + + event.time_conv.time_mult = tc.time_mult; + event.time_conv.time_shift = tc.time_shift; + event.time_conv.time_zero = tc.time_zero; + + return process(tool, &event, NULL, machine); +} diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h deleted file mode 100644 index 2edc4d31065c..000000000000 --- a/tools/perf/arch/x86/util/tsc.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ -#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ - -#include <linux/types.h> - -struct perf_tsc_conversion { - u16 time_shift; - u32 time_mult; - u64 time_zero; -}; - -struct perf_event_mmap_page; - -int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, - struct perf_tsc_conversion *tc); - -#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */ diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index c42448ed5dfe..fe1b77fa21f9 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -12,6 +12,7 @@ #include <subcmd/parse-options.h> #include "util/util.h" #include "util/debug.h" +#include "util/config.h" static bool use_system_config, use_user_config; @@ -32,13 +33,28 @@ static struct option config_options[] = { OPT_END() }; -static int show_config(const char *key, const char *value, - void *cb __maybe_unused) +static int show_config(struct perf_config_set *set) { - if (value) - printf("%s=%s\n", key, value); - else - printf("%s\n", key); + struct perf_config_section *section; + struct perf_config_item *item; + struct list_head *sections; + + if (set == NULL) + return -1; + + sections = &set->sections; + if (list_empty(sections)) + return -1; + + list_for_each_entry(section, sections, node) { + list_for_each_entry(item, §ion->items, node) { + char *value = item->value; + + if (value) + printf("%s.%s=%s\n", section->name, + item->name, value); + } + } return 0; } @@ -46,6 +62,7 @@ static int show_config(const char *key, const char *value, int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) { int ret = 0; + struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); argc = parse_options(argc, argv, config_options, config_usage, @@ -63,13 +80,19 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) else if (use_user_config) config_exclusive_filename = user_config; + set = perf_config_set__new(); + if (!set) { + ret = -1; + goto out_err; + } + switch (actions) { case ACTION_LIST: if (argc) { pr_err("Error: takes no arguments\n"); parse_options_usage(config_usage, config_options, "l", 1); } else { - ret = perf_config(show_config, NULL); + ret = show_config(set); if (ret < 0) { const char * config_filename = config_exclusive_filename; if (!config_exclusive_filename) @@ -83,5 +106,7 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) usage_with_options(config_usage, config_options); } + perf_config_set__delete(set); +out_err: return ret; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index d1a2d104f2bc..e5afa8fe1bf1 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -748,6 +748,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) .auxtrace_info = perf_event__repipe_op2_synth, .auxtrace = perf_event__repipe_auxtrace, .auxtrace_error = perf_event__repipe_op2_synth, + .time_conv = perf_event__repipe_op2_synth, .finished_round = perf_event__repipe_oe_synth, .build_id = perf_event__repipe_op2_synth, .id_index = perf_event__repipe_op2_synth, diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index c9cb3be47cff..58adfee230de 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -375,7 +375,7 @@ static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample) } al.thread = machine__findnew_thread(machine, sample->pid, sample->tid); - sample__resolve_callchain(sample, NULL, evsel, &al, 16); + sample__resolve_callchain(sample, &callchain_cursor, NULL, evsel, &al, 16); callchain_cursor_commit(&callchain_cursor); while (true) { diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index bff666458b28..6487c06d2708 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -982,7 +982,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) struct perf_evlist *evlist = kvm->evlist; char sbuf[STRERR_BUFSIZE]; - perf_evlist__config(evlist, &kvm->opts); + perf_evlist__config(evlist, &kvm->opts, NULL); /* * Note: exclude_{guest,host} do not apply here. diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 85db3be4b3cb..1dc140c5481d 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -62,19 +62,22 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) int rec_argc, i = 0, j; const char **rec_argv; int ret; + bool all_user = false, all_kernel = false; struct option options[] = { OPT_CALLBACK('e', "event", &mem, "event", "event selector. use 'perf mem record -e list' to list available events", parse_record_events), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), + OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"), + OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"), OPT_END() }; argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_STOP_AT_NON_OPTION); - rec_argc = argc + 7; /* max number of arguments */ + rec_argc = argc + 9; /* max number of arguments */ rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; @@ -103,6 +106,12 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = perf_mem_events__name(j); }; + if (all_user) + rec_argv[i++] = "--all-user"; + + if (all_kernel) + rec_argv[i++] = "--all-kernel"; + for (j = 0; j < argc; j++, i++) rec_argv[i] = argv[j]; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 515510ecc76a..5b4758a08a49 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -29,6 +29,7 @@ #include "util/data.h" #include "util/perf_regs.h" #include "util/auxtrace.h" +#include "util/tsc.h" #include "util/parse-branch-options.h" #include "util/parse-regs-options.h" #include "util/llvm-utils.h" @@ -55,6 +56,7 @@ struct record { bool no_buildid_cache; bool no_buildid_cache_set; bool buildid_all; + bool timestamp_filename; unsigned long long samples; }; @@ -124,7 +126,43 @@ out: static volatile int done; static volatile int signr = -1; static volatile int child_finished; -static volatile int auxtrace_snapshot_enabled; + +static volatile enum { + AUXTRACE_SNAPSHOT_OFF = -1, + AUXTRACE_SNAPSHOT_DISABLED = 0, + AUXTRACE_SNAPSHOT_ENABLED = 1, +} auxtrace_snapshot_state = AUXTRACE_SNAPSHOT_OFF; + +static inline void +auxtrace_snapshot_on(void) +{ + auxtrace_snapshot_state = AUXTRACE_SNAPSHOT_DISABLED; +} + +static inline void +auxtrace_snapshot_enable(void) +{ + if (auxtrace_snapshot_state == AUXTRACE_SNAPSHOT_OFF) + return; + auxtrace_snapshot_state = AUXTRACE_SNAPSHOT_ENABLED; +} + +static inline void +auxtrace_snapshot_disable(void) +{ + if (auxtrace_snapshot_state == AUXTRACE_SNAPSHOT_OFF) + return; + auxtrace_snapshot_state = AUXTRACE_SNAPSHOT_DISABLED; +} + +static inline bool +auxtrace_snapshot_is_enabled(void) +{ + if (auxtrace_snapshot_state == AUXTRACE_SNAPSHOT_OFF) + return false; + return auxtrace_snapshot_state == AUXTRACE_SNAPSHOT_ENABLED; +} + static volatile int auxtrace_snapshot_err; static volatile int auxtrace_record__snapshot_started; @@ -248,7 +286,7 @@ static void record__read_auxtrace_snapshot(struct record *rec) } else { auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr); if (!auxtrace_snapshot_err) - auxtrace_snapshot_enabled = 1; + auxtrace_snapshot_enable(); } } @@ -283,7 +321,7 @@ static int record__open(struct record *rec) struct record_opts *opts = &rec->opts; int rc = 0; - perf_evlist__config(evlist, opts); + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each(evlist, pos) { try_again: @@ -494,6 +532,37 @@ record__finish_output(struct record *rec) return; } +static int +record__switch_output(struct record *rec, bool at_exit) +{ + struct perf_data_file *file = &rec->file; + int fd, err; + + /* Same Size: "2015122520103046"*/ + char timestamp[] = "InvalidTimestamp"; + + rec->samples = 0; + record__finish_output(rec); + err = fetch_current_timestamp(timestamp, sizeof(timestamp)); + if (err) { + pr_err("Failed to get current timestamp\n"); + return -EINVAL; + } + + fd = perf_data_file__switch(file, timestamp, + rec->session->header.data_offset, + at_exit); + if (fd >= 0 && !at_exit) { + rec->bytes_written = 0; + rec->session->header.data_size = 0; + } + + if (!quiet) + fprintf(stderr, "[ perf record: Dump %s.%s ]\n", + file->path, timestamp); + return fd; +} + static volatile int workload_exec_errno; /* @@ -512,6 +581,15 @@ static void workload_exec_failed_signal(int signo __maybe_unused, static void snapshot_sig_handler(int sig); +int __weak +perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, + struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + static int record__synthesize(struct record *rec) { struct perf_session *session = rec->session; @@ -549,6 +627,11 @@ static int record__synthesize(struct record *rec) } } + err = perf_event__synth_time_conv(rec->evlist->mmap[0].base, tool, + process_synthesized_event, machine); + if (err) + goto out; + if (rec->opts.full_auxtrace) { err = perf_event__synthesize_auxtrace_info(rec->itr, tool, session, process_synthesized_event); @@ -600,10 +683,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); signal(SIGTERM, sig_handler); - if (rec->opts.auxtrace_snapshot_mode) + + if (rec->opts.auxtrace_snapshot_mode) { signal(SIGUSR2, snapshot_sig_handler); - else + auxtrace_snapshot_on(); + } else { signal(SIGUSR2, SIG_IGN); + } session = perf_session__new(file, false, tool); if (session == NULL) { @@ -729,12 +815,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) perf_evlist__enable(rec->evlist); } - auxtrace_snapshot_enabled = 1; + auxtrace_snapshot_enable(); for (;;) { unsigned long long hits = rec->samples; if (record__mmap_read_all(rec) < 0) { - auxtrace_snapshot_enabled = 0; + auxtrace_snapshot_disable(); err = -1; goto out_child; } @@ -772,12 +858,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * disable events in this case. */ if (done && !disabled && !target__none(&opts->target)) { - auxtrace_snapshot_enabled = 0; + auxtrace_snapshot_disable(); perf_evlist__disable(rec->evlist); disabled = true; } } - auxtrace_snapshot_enabled = 0; + auxtrace_snapshot_disable(); if (forks && workload_exec_errno) { char msg[STRERR_BUFSIZE]; @@ -811,11 +897,22 @@ out_child: /* this will be recalculated during process_buildids() */ rec->samples = 0; - if (!err) - record__finish_output(rec); + if (!err) { + if (!rec->timestamp_filename) { + record__finish_output(rec); + } else { + fd = record__switch_output(rec, true); + if (fd < 0) { + status = fd; + goto out_delete_session; + } + } + } if (!err && !quiet) { char samples[128]; + const char *postfix = rec->timestamp_filename ? + ".<timestamp>" : ""; if (rec->samples && !rec->opts.full_auxtrace) scnprintf(samples, sizeof(samples), @@ -823,9 +920,9 @@ out_child: else samples[0] = '\0'; - fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s ]\n", + fprintf(stderr, "[ perf record: Captured and wrote %.3f MB %s%s%s ]\n", perf_data_file__size(file) / 1024.0 / 1024.0, - file->path, samples); + file->path, postfix, samples); } out_delete_session: @@ -833,45 +930,50 @@ out_delete_session: return status; } -static void callchain_debug(void) +static void callchain_debug(struct callchain_param *callchain) { static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" }; - pr_debug("callchain: type %s\n", str[callchain_param.record_mode]); + pr_debug("callchain: type %s\n", str[callchain->record_mode]); - if (callchain_param.record_mode == CALLCHAIN_DWARF) + if (callchain->record_mode == CALLCHAIN_DWARF) pr_debug("callchain: stack dump size %d\n", - callchain_param.dump_size); + callchain->dump_size); } -int record_parse_callchain_opt(const struct option *opt, - const char *arg, - int unset) +int record_opts__parse_callchain(struct record_opts *record, + struct callchain_param *callchain, + const char *arg, bool unset) { int ret; - struct record_opts *record = (struct record_opts *)opt->value; - record->callgraph_set = true; - callchain_param.enabled = !unset; + callchain->enabled = !unset; /* --no-call-graph */ if (unset) { - callchain_param.record_mode = CALLCHAIN_NONE; + callchain->record_mode = CALLCHAIN_NONE; pr_debug("callchain: disabled\n"); return 0; } - ret = parse_callchain_record_opt(arg, &callchain_param); + ret = parse_callchain_record_opt(arg, callchain); if (!ret) { /* Enable data address sampling for DWARF unwind. */ - if (callchain_param.record_mode == CALLCHAIN_DWARF) + if (callchain->record_mode == CALLCHAIN_DWARF) record->sample_address = true; - callchain_debug(); + callchain_debug(callchain); } return ret; } +int record_parse_callchain_opt(const struct option *opt, + const char *arg, + int unset) +{ + return record_opts__parse_callchain(opt->value, &callchain_param, arg, unset); +} + int record_callchain_opt(const struct option *opt, const char *arg __maybe_unused, int unset __maybe_unused) @@ -884,7 +986,7 @@ int record_callchain_opt(const struct option *opt, if (callchain_param.record_mode == CALLCHAIN_NONE) callchain_param.record_mode = CALLCHAIN_FP; - callchain_debug(); + callchain_debug(&callchain_param); return 0; } @@ -1195,6 +1297,8 @@ struct option __record_options[] = { "file", "vmlinux pathname"), OPT_BOOLEAN(0, "buildid-all", &record.buildid_all, "Record build-id of all DSOs regardless of hits"), + OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, + "append timestamp to output filename"), OPT_END() }; @@ -1261,6 +1365,14 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (err) return err; + err = bpf__setup_stdout(rec->evlist); + if (err) { + bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf)); + pr_err("ERROR: Setup BPF stdout failed: %s\n", + errbuf); + return err; + } + err = -ENOMEM; symbol__init(NULL); @@ -1335,9 +1447,9 @@ out_symbol_exit: static void snapshot_sig_handler(int sig __maybe_unused) { - if (!auxtrace_snapshot_enabled) + if (!auxtrace_snapshot_is_enabled()) return; - auxtrace_snapshot_enabled = 0; + auxtrace_snapshot_disable(); auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr); auxtrace_record__snapshot_started = 1; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 871b55ae22a4..afa057666c2a 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -11,6 +11,8 @@ #include "util/session.h" #include "util/tool.h" #include "util/cloexec.h" +#include "util/thread_map.h" +#include "util/color.h" #include <subcmd/parse-options.h> #include "util/trace-event.h" @@ -122,6 +124,21 @@ struct trace_sched_handler { struct machine *machine); }; +#define COLOR_PIDS PERF_COLOR_BLUE +#define COLOR_CPUS PERF_COLOR_BG_RED + +struct perf_sched_map { + DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS); + int *comp_cpus; + bool comp; + struct thread_map *color_pids; + const char *color_pids_str; + struct cpu_map *color_cpus; + const char *color_cpus_str; + struct cpu_map *cpus; + const char *cpus_str; +}; + struct perf_sched { struct perf_tool tool; const char *sort_order; @@ -173,6 +190,7 @@ struct perf_sched { struct list_head sort_list, cmp_pid; bool force; bool skip_merge; + struct perf_sched_map map; }; static u64 get_nsecs(void) @@ -1339,6 +1357,38 @@ static int process_sched_wakeup_event(struct perf_tool *tool, return 0; } +union map_priv { + void *ptr; + bool color; +}; + +static bool thread__has_color(struct thread *thread) +{ + union map_priv priv = { + .ptr = thread__priv(thread), + }; + + return priv.color; +} + +static struct thread* +map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid) +{ + struct thread *thread = machine__findnew_thread(machine, pid, tid); + union map_priv priv = { + .color = false, + }; + + if (!sched->map.color_pids || !thread || thread__priv(thread)) + return thread; + + if (thread_map__has(sched->map.color_pids, tid)) + priv.color = true; + + thread__set_priv(thread, priv.ptr); + return thread; +} + static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, struct perf_sample *sample, struct machine *machine) { @@ -1347,13 +1397,25 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, int new_shortname; u64 timestamp0, timestamp = sample->time; s64 delta; - int cpu, this_cpu = sample->cpu; + int i, this_cpu = sample->cpu; + int cpus_nr; + bool new_cpu = false; + const char *color = PERF_COLOR_NORMAL; BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0); if (this_cpu > sched->max_cpu) sched->max_cpu = this_cpu; + if (sched->map.comp) { + cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS); + if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) { + sched->map.comp_cpus[cpus_nr++] = this_cpu; + new_cpu = true; + } + } else + cpus_nr = sched->max_cpu; + timestamp0 = sched->cpu_last_switched[this_cpu]; sched->cpu_last_switched[this_cpu] = timestamp; if (timestamp0) @@ -1366,7 +1428,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, return -1; } - sched_in = machine__findnew_thread(machine, -1, next_pid); + sched_in = map__findnew_thread(sched, machine, -1, next_pid); if (sched_in == NULL) return -1; @@ -1400,26 +1462,52 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, new_shortname = 1; } - for (cpu = 0; cpu <= sched->max_cpu; cpu++) { + for (i = 0; i < cpus_nr; i++) { + int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i; + struct thread *curr_thread = sched->curr_thread[cpu]; + const char *pid_color = color; + const char *cpu_color = color; + + if (curr_thread && thread__has_color(curr_thread)) + pid_color = COLOR_PIDS; + + if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu)) + continue; + + if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu)) + cpu_color = COLOR_CPUS; + if (cpu != this_cpu) - printf(" "); + color_fprintf(stdout, cpu_color, " "); else - printf("*"); + color_fprintf(stdout, cpu_color, "*"); if (sched->curr_thread[cpu]) - printf("%2s ", sched->curr_thread[cpu]->shortname); + color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname); else - printf(" "); + color_fprintf(stdout, color, " "); } - printf(" %12.6f secs ", (double)timestamp/1e9); + if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu)) + goto out; + + color_fprintf(stdout, color, " %12.6f secs ", (double)timestamp/1e9); if (new_shortname) { - printf("%s => %s:%d\n", + const char *pid_color = color; + + if (thread__has_color(sched_in)) + pid_color = COLOR_PIDS; + + color_fprintf(stdout, pid_color, "%s => %s:%d", sched_in->shortname, thread__comm_str(sched_in), sched_in->tid); - } else { - printf("\n"); } + if (sched->map.comp && new_cpu) + color_fprintf(stdout, color, " (CPU %d)", this_cpu); + +out: + color_fprintf(stdout, color, "\n"); + thread__put(sched_in); return 0; @@ -1675,9 +1763,75 @@ static int perf_sched__lat(struct perf_sched *sched) return 0; } +static int setup_map_cpus(struct perf_sched *sched) +{ + struct cpu_map *map; + + sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + + if (sched->map.comp) { + sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int)); + if (!sched->map.comp_cpus) + return -1; + } + + if (!sched->map.cpus_str) + return 0; + + map = cpu_map__new(sched->map.cpus_str); + if (!map) { + pr_err("failed to get cpus map from %s\n", sched->map.cpus_str); + return -1; + } + + sched->map.cpus = map; + return 0; +} + +static int setup_color_pids(struct perf_sched *sched) +{ + struct thread_map *map; + + if (!sched->map.color_pids_str) + return 0; + + map = thread_map__new_by_tid_str(sched->map.color_pids_str); + if (!map) { + pr_err("failed to get thread map from %s\n", sched->map.color_pids_str); + return -1; + } + + sched->map.color_pids = map; + return 0; +} + +static int setup_color_cpus(struct perf_sched *sched) +{ + struct cpu_map *map; + + if (!sched->map.color_cpus_str) + return 0; + + map = cpu_map__new(sched->map.color_cpus_str); + if (!map) { + pr_err("failed to get thread map from %s\n", sched->map.color_cpus_str); + return -1; + } + + sched->map.color_cpus = map; + return 0; +} + static int perf_sched__map(struct perf_sched *sched) { - sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF); + if (setup_map_cpus(sched)) + return -1; + + if (setup_color_pids(sched)) + return -1; + + if (setup_color_cpus(sched)) + return -1; setup_pager(); if (perf_sched__read_events(sched)) @@ -1831,6 +1985,17 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) "dump raw trace in ASCII"), OPT_END() }; + const struct option map_options[] = { + OPT_BOOLEAN(0, "compact", &sched.map.comp, + "map output in compact mode"), + OPT_STRING(0, "color-pids", &sched.map.color_pids_str, "pids", + "highlight given pids in map"), + OPT_STRING(0, "color-cpus", &sched.map.color_cpus_str, "cpus", + "highlight given CPUs in map"), + OPT_STRING(0, "cpus", &sched.map.cpus_str, "cpus", + "display given CPUs in map"), + OPT_END() + }; const char * const latency_usage[] = { "perf sched latency [<options>]", NULL @@ -1839,6 +2004,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) "perf sched replay [<options>]", NULL }; + const char * const map_usage[] = { + "perf sched map [<options>]", + NULL + }; const char *const sched_subcommands[] = { "record", "latency", "map", "replay", "script", NULL }; const char *sched_usage[] = { @@ -1887,6 +2056,11 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) setup_sorting(&sched, latency_options, latency_usage); return perf_sched__lat(&sched); } else if (!strcmp(argv[0], "map")) { + if (argc) { + argc = parse_options(argc, argv, map_options, map_usage, 0); + if (argc) + usage_with_options(map_usage, map_options); + } sched.tp_handler = &map_ops; setup_sorting(&sched, latency_options, latency_usage); return perf_sched__map(&sched); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 3770c3dffe5e..0e93282b405e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -22,6 +22,7 @@ #include "util/thread_map.h" #include "util/stat.h" #include <linux/bitmap.h> +#include <linux/stringify.h> #include "asm/bug.h" #include "util/mem-events.h" @@ -317,19 +318,19 @@ static void set_print_ip_opts(struct perf_event_attr *attr) output[type].print_ip_opts = 0; if (PRINT_FIELD(IP)) - output[type].print_ip_opts |= PRINT_IP_OPT_IP; + output[type].print_ip_opts |= EVSEL__PRINT_IP; if (PRINT_FIELD(SYM)) - output[type].print_ip_opts |= PRINT_IP_OPT_SYM; + output[type].print_ip_opts |= EVSEL__PRINT_SYM; if (PRINT_FIELD(DSO)) - output[type].print_ip_opts |= PRINT_IP_OPT_DSO; + output[type].print_ip_opts |= EVSEL__PRINT_DSO; if (PRINT_FIELD(SYMOFFSET)) - output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET; + output[type].print_ip_opts |= EVSEL__PRINT_SYMOFFSET; if (PRINT_FIELD(SRCLINE)) - output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE; + output[type].print_ip_opts |= EVSEL__PRINT_SRCLINE; } /* @@ -569,18 +570,23 @@ static void print_sample_bts(struct perf_sample *sample, /* print branch_from information */ if (PRINT_FIELD(IP)) { unsigned int print_opts = output[attr->type].print_ip_opts; + struct callchain_cursor *cursor = NULL, cursor_callchain; - if (symbol_conf.use_callchain && sample->callchain) { - printf("\n"); - } else { - printf(" "); - if (print_opts & PRINT_IP_OPT_SRCLINE) { + if (symbol_conf.use_callchain && sample->callchain && + thread__resolve_callchain(al->thread, &cursor_callchain, evsel, + sample, NULL, NULL, scripting_max_stack) == 0) + cursor = &cursor_callchain; + + if (cursor == NULL) { + putchar(' '); + if (print_opts & EVSEL__PRINT_SRCLINE) { print_srcline_last = true; - print_opts &= ~PRINT_IP_OPT_SRCLINE; + print_opts &= ~EVSEL__PRINT_SRCLINE; } - } - perf_evsel__print_ip(evsel, sample, al, print_opts, - scripting_max_stack); + } else + putchar('\n'); + + sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout); } /* print branch_to information */ @@ -783,14 +789,15 @@ static void process_event(struct perf_script *script, printf("%16" PRIu64, sample->weight); if (PRINT_FIELD(IP)) { - if (!symbol_conf.use_callchain) - printf(" "); - else - printf("\n"); + struct callchain_cursor *cursor = NULL, cursor_callchain; + + if (symbol_conf.use_callchain && + thread__resolve_callchain(al->thread, &cursor_callchain, evsel, + sample, NULL, NULL, scripting_max_stack) == 0) + cursor = &cursor_callchain; - perf_evsel__print_ip(evsel, sample, al, - output[attr->type].print_ip_opts, - scripting_max_stack); + putchar(cursor ? '\n' : ' '); + sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout); } if (PRINT_FIELD(IREGS)) @@ -1415,21 +1422,19 @@ static int is_directory(const char *base_path, const struct dirent *dent) return S_ISDIR(st.st_mode); } -#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\ - while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) && \ - lang_next) \ - if ((lang_dirent.d_type == DT_DIR || \ - (lang_dirent.d_type == DT_UNKNOWN && \ - is_directory(scripts_path, &lang_dirent))) && \ - (strcmp(lang_dirent.d_name, ".")) && \ - (strcmp(lang_dirent.d_name, ".."))) +#define for_each_lang(scripts_path, scripts_dir, lang_dirent) \ + while ((lang_dirent = readdir(scripts_dir)) != NULL) \ + if ((lang_dirent->d_type == DT_DIR || \ + (lang_dirent->d_type == DT_UNKNOWN && \ + is_directory(scripts_path, lang_dirent))) && \ + (strcmp(lang_dirent->d_name, ".")) && \ + (strcmp(lang_dirent->d_name, ".."))) -#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\ - while (!readdir_r(lang_dir, &script_dirent, &script_next) && \ - script_next) \ - if (script_dirent.d_type != DT_DIR && \ - (script_dirent.d_type != DT_UNKNOWN || \ - !is_directory(lang_path, &script_dirent))) +#define for_each_script(lang_path, lang_dir, script_dirent) \ + while ((script_dirent = readdir(lang_dir)) != NULL) \ + if (script_dirent->d_type != DT_DIR && \ + (script_dirent->d_type != DT_UNKNOWN || \ + !is_directory(lang_path, script_dirent))) #define RECORD_SUFFIX "-record" @@ -1575,7 +1580,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, const char *s __maybe_unused, int unset __maybe_unused) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; char script_path[MAXPATHLEN]; @@ -1590,19 +1595,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused, if (!scripts_dir) return -1; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - script_root = get_script_root(&script_dirent, REPORT_SUFFIX); + for_each_script(lang_path, lang_dir, script_dirent) { + script_root = get_script_root(script_dirent, REPORT_SUFFIX); if (script_root) { desc = script_desc__findnew(script_root); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); read_script_info(desc, script_path); free(script_root); } @@ -1690,7 +1695,7 @@ static int check_ev_match(char *dir_name, char *scriptname, */ int find_scripts(char **scripts_array, char **scripts_path_array) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; struct perf_session *session; @@ -1713,9 +1718,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array) return -1; } - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); #ifdef NO_LIBPERL if (strstr(lang_path, "perl")) continue; @@ -1729,16 +1734,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array) if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { + for_each_script(lang_path, lang_dir, script_dirent) { /* Skip those real time scripts: xxxtop.p[yl] */ - if (strstr(script_dirent.d_name, "top.")) + if (strstr(script_dirent->d_name, "top.")) continue; sprintf(scripts_path_array[i], "%s/%s", lang_path, - script_dirent.d_name); - temp = strchr(script_dirent.d_name, '.'); + script_dirent->d_name); + temp = strchr(script_dirent->d_name, '.'); snprintf(scripts_array[i], - (temp - script_dirent.d_name) + 1, - "%s", script_dirent.d_name); + (temp - script_dirent->d_name) + 1, + "%s", script_dirent->d_name); if (check_ev_match(lang_path, scripts_array[i], session)) @@ -1756,7 +1761,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array) static char *get_script_path(const char *script_root, const char *suffix) { - struct dirent *script_next, *lang_next, script_dirent, lang_dirent; + struct dirent *script_dirent, *lang_dirent; char scripts_path[MAXPATHLEN]; char script_path[MAXPATHLEN]; DIR *scripts_dir, *lang_dir; @@ -1769,21 +1774,21 @@ static char *get_script_path(const char *script_root, const char *suffix) if (!scripts_dir) return NULL; - for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) { + for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, - lang_dirent.d_name); + lang_dirent->d_name); lang_dir = opendir(lang_path); if (!lang_dir) continue; - for_each_script(lang_path, lang_dir, script_dirent, script_next) { - __script_root = get_script_root(&script_dirent, suffix); + for_each_script(lang_path, lang_dir, script_dirent) { + __script_root = get_script_root(script_dirent, suffix); if (__script_root && !strcmp(script_root, __script_root)) { free(__script_root); closedir(lang_dir); closedir(scripts_dir); snprintf(script_path, MAXPATHLEN, "%s/%s", - lang_path, script_dirent.d_name); + lang_path, script_dirent->d_name); return strdup(script_path); } free(__script_root); @@ -1961,6 +1966,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, + .event_update = perf_event__process_event_update, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, .id_index = perf_event__process_id_index, @@ -2022,6 +2028,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "only consider symbols in these pids"), OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]", "only consider symbols in these tids"), + OPT_UINTEGER(0, "max-stack", &scripting_max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 833214979c4f..8846df0ec0c3 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -886,7 +886,7 @@ static int perf_top__start_counters(struct perf_top *top) struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; - perf_evlist__config(evlist, opts); + perf_evlist__config(evlist, opts, &callchain_param); evlist__for_each(evlist, counter) { try_again: diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 93ac724fb635..026ec0c749b0 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -34,59 +34,24 @@ #include "trace-event.h" #include "util/parse-events.h" #include "util/bpf-loader.h" +#include "callchain.h" +#include "syscalltbl.h" -#include <libaudit.h> +#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */ #include <stdlib.h> -#include <sys/mman.h> #include <linux/futex.h> #include <linux/err.h> - -/* For older distros: */ -#ifndef MAP_STACK -# define MAP_STACK 0x20000 -#endif - -#ifndef MADV_HWPOISON -# define MADV_HWPOISON 100 - -#endif - -#ifndef MADV_MERGEABLE -# define MADV_MERGEABLE 12 -#endif - -#ifndef MADV_UNMERGEABLE -# define MADV_UNMERGEABLE 13 -#endif - -#ifndef EFD_SEMAPHORE -# define EFD_SEMAPHORE 1 -#endif - -#ifndef EFD_NONBLOCK -# define EFD_NONBLOCK 00004000 -#endif - -#ifndef EFD_CLOEXEC -# define EFD_CLOEXEC 02000000 -#endif +#include <linux/seccomp.h> +#include <linux/filter.h> +#include <linux/audit.h> +#include <sys/ptrace.h> +#include <linux/random.h> +#include <linux/stringify.h> #ifndef O_CLOEXEC # define O_CLOEXEC 02000000 #endif -#ifndef SOCK_DCCP -# define SOCK_DCCP 6 -#endif - -#ifndef SOCK_CLOEXEC -# define SOCK_CLOEXEC 02000000 -#endif - -#ifndef SOCK_NONBLOCK -# define SOCK_NONBLOCK 00004000 -#endif - #ifndef MSG_CMSG_CLOEXEC # define MSG_CMSG_CLOEXEC 0x40000000 #endif @@ -107,6 +72,59 @@ # define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ #endif +struct trace { + struct perf_tool tool; + struct syscalltbl *sctbl; + struct { + int max; + struct syscall *table; + struct { + struct perf_evsel *sys_enter, + *sys_exit; + } events; + } syscalls; + struct record_opts opts; + struct perf_evlist *evlist; + struct machine *host; + struct thread *current; + u64 base_time; + FILE *output; + unsigned long nr_events; + struct strlist *ev_qualifier; + struct { + size_t nr; + int *entries; + } ev_qualifier_ids; + struct intlist *tid_list; + struct intlist *pid_list; + struct { + size_t nr; + pid_t *entries; + } filter_pids; + double duration_filter; + double runtime_ms; + struct { + u64 vfs_getname, + proc_getname; + } stats; + unsigned int max_stack; + unsigned int min_stack; + bool not_ev_qualifier; + bool live; + bool full_time; + bool sched; + bool multiple_threads; + bool summary; + bool summary_only; + bool show_comm; + bool show_tool_stats; + bool trace_syscalls; + bool kernel_syscallchains; + bool force; + bool vfs_getname; + int trace_pgfaults; + int open_id; +}; struct tp_field { int offset; @@ -371,147 +389,6 @@ static size_t syscall_arg__scnprintf_int(char *bf, size_t size, #define SCA_INT syscall_arg__scnprintf_int -static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, prot = arg->val; - - if (prot == PROT_NONE) - return scnprintf(bf, size, "NONE"); -#define P_MMAP_PROT(n) \ - if (prot & PROT_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - prot &= ~PROT_##n; \ - } - - P_MMAP_PROT(EXEC); - P_MMAP_PROT(READ); - P_MMAP_PROT(WRITE); -#ifdef PROT_SEM - P_MMAP_PROT(SEM); -#endif - P_MMAP_PROT(GROWSDOWN); - P_MMAP_PROT(GROWSUP); -#undef P_MMAP_PROT - - if (prot) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot); - - return printed; -} - -#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot - -static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - -#define P_MMAP_FLAG(n) \ - if (flags & MAP_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~MAP_##n; \ - } - - P_MMAP_FLAG(SHARED); - P_MMAP_FLAG(PRIVATE); -#ifdef MAP_32BIT - P_MMAP_FLAG(32BIT); -#endif - P_MMAP_FLAG(ANONYMOUS); - P_MMAP_FLAG(DENYWRITE); - P_MMAP_FLAG(EXECUTABLE); - P_MMAP_FLAG(FILE); - P_MMAP_FLAG(FIXED); - P_MMAP_FLAG(GROWSDOWN); -#ifdef MAP_HUGETLB - P_MMAP_FLAG(HUGETLB); -#endif - P_MMAP_FLAG(LOCKED); - P_MMAP_FLAG(NONBLOCK); - P_MMAP_FLAG(NORESERVE); - P_MMAP_FLAG(POPULATE); - P_MMAP_FLAG(STACK); -#ifdef MAP_UNINITIALIZED - P_MMAP_FLAG(UNINITIALIZED); -#endif -#undef P_MMAP_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags - -static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - -#define P_MREMAP_FLAG(n) \ - if (flags & MREMAP_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~MREMAP_##n; \ - } - - P_MREMAP_FLAG(MAYMOVE); -#ifdef MREMAP_FIXED - P_MREMAP_FLAG(FIXED); -#endif -#undef P_MREMAP_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags - -static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, - struct syscall_arg *arg) -{ - int behavior = arg->val; - - switch (behavior) { -#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n) - P_MADV_BHV(NORMAL); - P_MADV_BHV(RANDOM); - P_MADV_BHV(SEQUENTIAL); - P_MADV_BHV(WILLNEED); - P_MADV_BHV(DONTNEED); - P_MADV_BHV(REMOVE); - P_MADV_BHV(DONTFORK); - P_MADV_BHV(DOFORK); - P_MADV_BHV(HWPOISON); -#ifdef MADV_SOFT_OFFLINE - P_MADV_BHV(SOFT_OFFLINE); -#endif - P_MADV_BHV(MERGEABLE); - P_MADV_BHV(UNMERGEABLE); -#ifdef MADV_HUGEPAGE - P_MADV_BHV(HUGEPAGE); -#endif -#ifdef MADV_NOHUGEPAGE - P_MADV_BHV(NOHUGEPAGE); -#endif -#ifdef MADV_DONTDUMP - P_MADV_BHV(DONTDUMP); -#endif -#ifdef MADV_DODUMP - P_MADV_BHV(DODUMP); -#endif -#undef P_MADV_PHV - default: break; - } - - return scnprintf(bf, size, "%#x", behavior); -} - -#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior - static size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg) { @@ -652,53 +529,6 @@ static const char *socket_families[] = { }; static DEFINE_STRARRAY(socket_families); -#ifndef SOCK_TYPE_MASK -#define SOCK_TYPE_MASK 0xf -#endif - -static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size, - struct syscall_arg *arg) -{ - size_t printed; - int type = arg->val, - flags = type & ~SOCK_TYPE_MASK; - - type &= SOCK_TYPE_MASK; - /* - * Can't use a strarray, MIPS may override for ABI reasons. - */ - switch (type) { -#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break; - P_SK_TYPE(STREAM); - P_SK_TYPE(DGRAM); - P_SK_TYPE(RAW); - P_SK_TYPE(RDM); - P_SK_TYPE(SEQPACKET); - P_SK_TYPE(DCCP); - P_SK_TYPE(PACKET); -#undef P_SK_TYPE - default: - printed = scnprintf(bf, size, "%#x", type); - } - -#define P_SK_FLAG(n) \ - if (flags & SOCK_##n) { \ - printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ - flags &= ~SOCK_##n; \ - } - - P_SK_FLAG(CLOEXEC); - P_SK_FLAG(NONBLOCK); -#undef P_SK_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "|%#x", flags); - - return printed; -} - -#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type - #ifndef MSG_PROBE #define MSG_PROBE 0x10 #endif @@ -872,32 +702,6 @@ static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size, #define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags -static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size, - struct syscall_arg *arg) -{ - int printed = 0, flags = arg->val; - - if (flags == 0) - return scnprintf(bf, size, "NONE"); -#define P_FLAG(n) \ - if (flags & EFD_##n) { \ - printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ - flags &= ~EFD_##n; \ - } - - P_FLAG(SEMAPHORE); - P_FLAG(CLOEXEC); - P_FLAG(NONBLOCK); -#undef P_FLAG - - if (flags) - printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); - - return printed; -} - -#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags - static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size, struct syscall_arg *arg) { @@ -1001,16 +805,106 @@ static const char *tioctls[] = { static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); #endif /* defined(__i386__) || defined(__x86_64__) */ +#ifndef SECCOMP_SET_MODE_STRICT +#define SECCOMP_SET_MODE_STRICT 0 +#endif +#ifndef SECCOMP_SET_MODE_FILTER +#define SECCOMP_SET_MODE_FILTER 1 +#endif + +static size_t syscall_arg__scnprintf_seccomp_op(char *bf, size_t size, struct syscall_arg *arg) +{ + int op = arg->val; + size_t printed = 0; + + switch (op) { +#define P_SECCOMP_SET_MODE_OP(n) case SECCOMP_SET_MODE_##n: printed = scnprintf(bf, size, #n); break + P_SECCOMP_SET_MODE_OP(STRICT); + P_SECCOMP_SET_MODE_OP(FILTER); +#undef P_SECCOMP_SET_MODE_OP + default: printed = scnprintf(bf, size, "%#x", op); break; + } + + return printed; +} + +#define SCA_SECCOMP_OP syscall_arg__scnprintf_seccomp_op + +#ifndef SECCOMP_FILTER_FLAG_TSYNC +#define SECCOMP_FILTER_FLAG_TSYNC 1 +#endif + +static size_t syscall_arg__scnprintf_seccomp_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & SECCOMP_FILTER_FLAG_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~SECCOMP_FILTER_FLAG_##n; \ + } + + P_FLAG(TSYNC); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_SECCOMP_FLAGS syscall_arg__scnprintf_seccomp_flags + +#ifndef GRND_NONBLOCK +#define GRND_NONBLOCK 0x0001 +#endif +#ifndef GRND_RANDOM +#define GRND_RANDOM 0x0002 +#endif + +static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & GRND_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~GRND_##n; \ + } + + P_FLAG(RANDOM); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags + #define STRARRAY(arg, name, array) \ .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ .arg_parm = { [arg] = &strarray__##array, } +#include "trace/beauty/eventfd.c" +#include "trace/beauty/pid.c" +#include "trace/beauty/mmap.c" +#include "trace/beauty/mode_t.c" +#include "trace/beauty/sched_policy.c" +#include "trace/beauty/socket_type.c" +#include "trace/beauty/waitid_options.c" + static struct syscall_fmt { const char *name; const char *alias; size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg); void *arg_parm[6]; bool errmsg; + bool errpid; bool timeout; bool hexret; } syscall_fmts[] = { @@ -1028,6 +922,7 @@ static struct syscall_fmt { { .name = "chroot", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, { .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), }, + { .name = "clone", .errpid = true, }, { .name = "close", .errmsg = true, .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, { .name = "connect", .errmsg = true, }, @@ -1093,6 +988,11 @@ static struct syscall_fmt { { .name = "getdents64", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "getpid", .errpid = true, }, + { .name = "getpgid", .errpid = true, }, + { .name = "getppid", .errpid = true, }, + { .name = "getrandom", .errmsg = true, + .arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, }, { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "getxattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, @@ -1234,6 +1134,11 @@ static struct syscall_fmt { .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, { .name = "rt_tgsigqueueinfo", .errmsg = true, .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, }, + { .name = "sched_setscheduler", .errmsg = true, + .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, }, + { .name = "seccomp", .errmsg = true, + .arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */ + [1] = SCA_SECCOMP_FLAGS, /* flags */ }, }, { .name = "select", .errmsg = true, .timeout = true, }, { .name = "sendmmsg", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ @@ -1244,7 +1149,9 @@ static struct syscall_fmt { { .name = "sendto", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ [3] = SCA_MSG_FLAGS, /* flags */ }, }, + { .name = "set_tid_address", .errpid = true, }, { .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), }, + { .name = "setpgid", .errmsg = true, }, { .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "setxattr", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* pathname */ }, }, @@ -1287,6 +1194,10 @@ static struct syscall_fmt { .arg_scnprintf = { [0] = SCA_FILENAME, /* filename */ }, }, { .name = "vmsplice", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, + { .name = "wait4", .errpid = true, + .arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, }, + { .name = "waitid", .errpid = true, + .arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, }, { .name = "write", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, { .name = "writev", .errmsg = true, @@ -1398,59 +1309,6 @@ fail: static const size_t trace__entry_str_size = 2048; -struct trace { - struct perf_tool tool; - struct { - int machine; - int open_id; - } audit; - struct { - int max; - struct syscall *table; - struct { - struct perf_evsel *sys_enter, - *sys_exit; - } events; - } syscalls; - struct record_opts opts; - struct perf_evlist *evlist; - struct machine *host; - struct thread *current; - u64 base_time; - FILE *output; - unsigned long nr_events; - struct strlist *ev_qualifier; - struct { - size_t nr; - int *entries; - } ev_qualifier_ids; - struct intlist *tid_list; - struct intlist *pid_list; - struct { - size_t nr; - pid_t *entries; - } filter_pids; - double duration_filter; - double runtime_ms; - struct { - u64 vfs_getname, - proc_getname; - } stats; - bool not_ev_qualifier; - bool live; - bool full_time; - bool sched; - bool multiple_threads; - bool summary; - bool summary_only; - bool show_comm; - bool show_tool_stats; - bool trace_syscalls; - bool force; - bool vfs_getname; - int trace_pgfaults; -}; - static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname) { struct thread_trace *ttrace = thread__priv(thread); @@ -1618,6 +1476,7 @@ static int trace__process_event(struct trace *trace, struct machine *machine, color_fprintf(trace->output, PERF_COLOR_RED, "LOST %" PRIu64 " events!\n", event->lost.lost); ret = machine__process_lost_event(machine, event, sample); + break; default: ret = machine__process_event(machine, event, sample); break; @@ -1675,6 +1534,10 @@ static int syscall__set_arg_fmts(struct syscall *sc) sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx]; else if (field->flags & FIELD_IS_POINTER) sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex; + else if (strcmp(field->type, "pid_t") == 0) + sc->arg_scnprintf[idx] = SCA_PID; + else if (strcmp(field->type, "umode_t") == 0) + sc->arg_scnprintf[idx] = SCA_MODE_T; ++idx; } @@ -1685,7 +1548,7 @@ static int trace__read_syscall_info(struct trace *trace, int id) { char tp_name[128]; struct syscall *sc; - const char *name = audit_syscall_to_name(id, trace->audit.machine); + const char *name = syscalltbl__name(trace->sctbl, id); if (name == NULL) return -1; @@ -1760,7 +1623,7 @@ static int trace__validate_ev_qualifier(struct trace *trace) strlist__for_each(pos, trace->ev_qualifier) { const char *sc = pos->s; - int id = audit_name_to_syscall(sc, trace->audit.machine); + int id = syscalltbl__id(trace->sctbl, sc); if (id < 0) { if (err == 0) { @@ -1987,7 +1850,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, goto out_put; } - if (!trace->summary_only) + if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) trace__printf_interrupted_entry(trace, sample); ttrace->entry_time = sample->time; @@ -1998,7 +1861,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, args, trace, thread); if (sc->is_exit) { - if (!trace->duration_filter && !trace->summary_only) { + if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output); fprintf(trace->output, "%-70s\n", ttrace->entry_str); } @@ -2018,6 +1881,29 @@ out_put: return err; } +static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel, + struct perf_sample *sample, + struct callchain_cursor *cursor) +{ + struct addr_location al; + + if (machine__resolve(trace->host, &al, sample) < 0 || + thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->max_stack)) + return -1; + + return 0; +} + +static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample) +{ + /* TODO: user-configurable print_opts */ + const unsigned int print_opts = EVSEL__PRINT_SYM | + EVSEL__PRINT_DSO | + EVSEL__PRINT_UNKNOWN_AS_ADDR; + + return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output); +} + static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, union perf_event *event __maybe_unused, struct perf_sample *sample) @@ -2025,7 +1911,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, long ret; u64 duration = 0; struct thread *thread; - int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1; + int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0; struct syscall *sc = trace__syscall_info(trace, evsel, id); struct thread_trace *ttrace; @@ -2042,7 +1928,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, ret = perf_evsel__sc_tp_uint(evsel, ret, sample); - if (id == trace->audit.open_id && ret >= 0 && ttrace->filename.pending_open) { + if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) { trace__set_fd_pathname(thread, ret, ttrace->filename.name); ttrace->filename.pending_open = false; ++trace->stats.vfs_getname; @@ -2057,6 +1943,15 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, } else if (trace->duration_filter) goto out; + if (sample->callchain) { + callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor); + if (callchain_ret == 0) { + if (callchain_cursor.nr < trace->min_stack) + goto out; + callchain_ret = 1; + } + } + if (trace->summary_only) goto out; @@ -2073,7 +1968,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (sc->fmt == NULL) { signed_print: fprintf(trace->output, ") = %ld", ret); - } else if (ret < 0 && sc->fmt->errmsg) { + } else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) { char bf[STRERR_BUFSIZE]; const char *emsg = strerror_r(-ret, bf, sizeof(bf)), *e = audit_errno_to_name(-ret); @@ -2083,10 +1978,24 @@ signed_print: fprintf(trace->output, ") = 0 Timeout"); else if (sc->fmt->hexret) fprintf(trace->output, ") = %#lx", ret); - else + else if (sc->fmt->errpid) { + struct thread *child = machine__find_thread(trace->host, ret, ret); + + if (child != NULL) { + fprintf(trace->output, ") = %ld", ret); + if (child->comm_set) + fprintf(trace->output, " (%s)", thread__comm_str(child)); + thread__put(child); + } + } else goto signed_print; fputc('\n', trace->output); + + if (callchain_ret > 0) + trace__fprintf_callchain(trace, sample); + else if (callchain_ret < 0) + pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel)); out: ttrace->entry_pending = false; err = 0; @@ -2234,6 +2143,12 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel, } fprintf(trace->output, ")\n"); + + if (sample->callchain) { + if (trace__resolve_callchain(trace, evsel, sample, &callchain_cursor) == 0) + trace__fprintf_callchain(trace, sample); + } + return 0; } @@ -2326,6 +2241,23 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample) return false; } +static void trace__set_base_time(struct trace *trace, + struct perf_evsel *evsel, + struct perf_sample *sample) +{ + /* + * BPF events were not setting PERF_SAMPLE_TIME, so be more robust + * and don't use sample->time unconditionally, we may end up having + * some other event in the future without PERF_SAMPLE_TIME for good + * reason, i.e. we may not be interested in its timestamps, just in + * it taking place, picking some piece of information when it + * appears in our event stream (vfs_getname comes to mind). + */ + if (trace->base_time == 0 && !trace->full_time && + (evsel->attr.sample_type & PERF_SAMPLE_TIME)) + trace->base_time = sample->time; +} + static int trace__process_sample(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -2340,8 +2272,7 @@ static int trace__process_sample(struct perf_tool *tool, if (skip_sample(trace, sample)) return 0; - if (!trace->full_time && trace->base_time == 0) - trace->base_time = sample->time; + trace__set_base_time(trace, evsel, sample); if (handler) { ++trace->nr_events; @@ -2479,9 +2410,6 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st const u32 type = event->header.type; struct perf_evsel *evsel; - if (!trace->full_time && trace->base_time == 0) - trace->base_time = sample->time; - if (type != PERF_RECORD_SAMPLE) { trace__process_event(trace, trace->host, event, sample); return; @@ -2493,6 +2421,8 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st return; } + trace__set_base_time(trace, evsel, sample); + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && sample->raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", @@ -2527,6 +2457,15 @@ static int trace__add_syscall_newtp(struct trace *trace) perf_evlist__add(evlist, sys_enter); perf_evlist__add(evlist, sys_exit); + if (trace->opts.callgraph_set && !trace->kernel_syscallchains) { + /* + * We're interested only in the user space callchain + * leading to the syscall, allow overriding that for + * debugging reasons using --kernel_syscall_callchains + */ + sys_exit->attr.exclude_callchain_kernel = 1; + } + trace->syscalls.events.sys_enter = sys_enter; trace->syscalls.events.sys_exit = sys_exit; @@ -2605,7 +2544,27 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_delete_evlist; } - perf_evlist__config(evlist, &trace->opts); + perf_evlist__config(evlist, &trace->opts, NULL); + + if (trace->opts.callgraph_set && trace->syscalls.events.sys_exit) { + perf_evsel__config_callchain(trace->syscalls.events.sys_exit, + &trace->opts, &callchain_param); + /* + * Now we have evsels with different sample_ids, use + * PERF_SAMPLE_IDENTIFIER to map from sample to evsel + * from a fixed position in each ring buffer record. + * + * As of this the changeset introducing this comment, this + * isn't strictly needed, as the fields that can come before + * PERF_SAMPLE_ID are all used, but we'll probably disable + * some of those for things like copying the payload of + * pointer syscall arguments, and for vfs_getname we don't + * need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this + * here as a warning we need to use PERF_SAMPLE_IDENTIFIER. + */ + perf_evlist__set_sample_bit(evlist, IDENTIFIER); + perf_evlist__reset_sample_bit(evlist, ID); + } signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); @@ -3070,10 +3029,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; struct trace trace = { - .audit = { - .machine = audit_detect_machine(), - .open_id = audit_name_to_syscall("open", trace.audit.machine), - }, .syscalls = { . max = -1, }, @@ -3091,6 +3046,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .output = stderr, .show_comm = true, .trace_syscalls = true, + .kernel_syscallchains = false, + .max_stack = UINT_MAX, }; const char *output_name = NULL; const char *ev_qualifier_str = NULL; @@ -3136,10 +3093,24 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) "Trace pagefaults", parse_pagefaults, "maj"), OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"), OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"), + OPT_CALLBACK(0, "call-graph", &trace.opts, + "record_mode[,record_size]", record_callchain_help, + &record_parse_callchain_opt), + OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains, + "Show the kernel callchains on the syscall exit path"), + OPT_UINTEGER(0, "min-stack", &trace.min_stack, + "Set the minimum stack depth when parsing the callchain, " + "anything below the specified depth will be ignored."), + OPT_UINTEGER(0, "max-stack", &trace.max_stack, + "Set the maximum stack depth when parsing the callchain, " + "anything beyond the specified depth will be ignored. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), OPT_END() }; + bool max_stack_user_set = true; + bool mmap_pages_user_set = true; const char * const trace_subcommands[] = { "record", NULL }; int err; char bf[BUFSIZ]; @@ -3148,8 +3119,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) signal(SIGFPE, sighandler_dump_stack); trace.evlist = perf_evlist__new(); + trace.sctbl = syscalltbl__new(); - if (trace.evlist == NULL) { + if (trace.evlist == NULL || trace.sctbl == NULL) { pr_err("Not enough memory to run!\n"); err = -ENOMEM; goto out; @@ -3158,11 +3130,40 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands, trace_usage, PARSE_OPT_STOP_AT_NON_OPTION); + err = bpf__setup_stdout(trace.evlist); + if (err) { + bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf)); + pr_err("ERROR: Setup BPF stdout failed: %s\n", bf); + goto out; + } + + err = -1; + if (trace.trace_pgfaults) { trace.opts.sample_address = true; trace.opts.sample_time = true; } + if (trace.opts.mmap_pages == UINT_MAX) + mmap_pages_user_set = false; + + if (trace.max_stack == UINT_MAX) { + trace.max_stack = PERF_MAX_STACK_DEPTH; + max_stack_user_set = false; + } + +#ifdef HAVE_DWARF_UNWIND_SUPPORT + if ((trace.min_stack || max_stack_user_set) && !trace.opts.callgraph_set) + record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false); +#endif + + if (trace.opts.callgraph_set) { + if (!mmap_pages_user_set && geteuid() == 0) + trace.opts.mmap_pages = perf_event_mlock_kb_in_pages() * 4; + + symbol_conf.use_callchain = true; + } + if (trace.evlist->nr_entries > 0) evlist__set_evsel_handler(trace.evlist, trace__event_handler); @@ -3179,6 +3180,11 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } + if (!trace.trace_syscalls && ev_qualifier_str) { + pr_err("The -e option can't be used with --no-syscalls.\n"); + goto out; + } + if (output_name != NULL) { err = trace__open_output(&trace, output_name); if (err < 0) { @@ -3187,6 +3193,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) } } + trace.open_id = syscalltbl__id(trace.sctbl, "open"); + if (ev_qualifier_str != NULL) { const char *s = ev_qualifier_str; struct strlist_config slist_config = { diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index f7d7f5a1cad5..1e46277286c2 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -27,7 +27,7 @@ NO_PERF_REGS := 1 ifeq ($(ARCH),x86) $(call detected,CONFIG_X86) ifeq (${IS_64_BIT}, 1) - CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT + CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 $(call detected,CONFIG_X86_64) @@ -268,6 +268,12 @@ else ifneq ($(feature-dwarf), 1) msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); NO_DWARF := 1 + else + ifneq ($(feature-dwarf_getlocations), 1) + msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); + else + CFLAGS += -DHAVE_DWARF_GETLOCATIONS + endif # dwarf_getlocations endif # Dwarf support endif # libelf support endif # NO_LIBELF @@ -289,9 +295,6 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT endif - # include ARCH specific config - -include $(src-perf)/arch/$(ARCH)/Makefile - ifndef NO_DWARF ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined) msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled); diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index 6461e02ab940..3573f315f955 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -92,6 +92,22 @@ error: return ret; } +static int use_arch_timestamp; + +static inline uint64_t +get_arch_timestamp(void) +{ +#if defined(__i386__) || defined(__x86_64__) + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((uint64_t)high) << 32; +#else + return 0; +#endif +} + #define NSEC_PER_SEC 1000000000 static int perf_clk_id = CLOCK_MONOTONIC; @@ -107,6 +123,9 @@ perf_get_timestamp(void) struct timespec ts; int ret; + if (use_arch_timestamp) + return get_arch_timestamp(); + ret = clock_gettime(perf_clk_id, &ts); if (ret) return 0; @@ -203,6 +222,17 @@ perf_close_marker_file(void) munmap(marker_addr, pgsz); } +static void +init_arch_timestamp(void) +{ + char *str = getenv("JITDUMP_USE_ARCH_TIMESTAMP"); + + if (!str || !*str || !strcmp(str, "0")) + return; + + use_arch_timestamp = 1; +} + void *jvmti_open(void) { int pad_cnt; @@ -211,11 +241,17 @@ void *jvmti_open(void) int fd; FILE *fp; + init_arch_timestamp(); + /* * check if clockid is supported */ - if (!perf_get_timestamp()) - warnx("jvmti: kernel does not support %d clock id", perf_clk_id); + if (!perf_get_timestamp()) { + if (use_arch_timestamp) + warnx("jvmti: arch timestamp not supported"); + else + warnx("jvmti: kernel does not support %d clock id", perf_clk_id); + } memset(&header, 0, sizeof(header)); @@ -263,6 +299,9 @@ void *jvmti_open(void) header.timestamp = perf_get_timestamp(); + if (use_arch_timestamp) + header.flags |= JITDUMP_FLAGS_ARCH_TIMESTAMP; + if (!fwrite(&header, sizeof(header), 1, fp)) { warn("jvmti: cannot write dumpfile header"); goto error; diff --git a/tools/perf/perf.c b/tools/perf/perf.c index aaee0a782747..7b2df2b46525 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -549,6 +549,7 @@ int main(int argc, const char **argv) srandom(time(NULL)); perf_config(perf_default_config, NULL); + set_buildid_dir(NULL); /* get debugfs/tracefs mount point from /proc/mounts */ tracing_path_mount(); @@ -572,7 +573,6 @@ int main(int argc, const char **argv) } if (!prefixcmp(cmd, "trace")) { #ifdef HAVE_LIBAUDIT_SUPPORT - set_buildid_dir(NULL); setup_path(); argv[0] = "trace"; return cmd_trace(argc, argv, NULL); @@ -587,7 +587,6 @@ int main(int argc, const char **argv) argc--; handle_options(&argv, &argc, NULL); commit_pager_choice(); - set_buildid_dir(NULL); if (argc > 0) { if (!prefixcmp(argv[0], "--")) diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 1ba628ed049a..449fe97a555f 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -37,6 +37,7 @@ perf-y += topology.o perf-y += cpumap.o perf-y += stat.o perf-y += event_update.o +perf-y += event-times.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 199501c71e27..f31eed31c1a9 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -138,7 +138,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), perf_evlist__splice_list_tail(evlist, &parse_evlist.list); evlist->nr_groups = parse_evlist.nr_groups; - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); err = perf_evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index f2b1dcac45d3..93c467015e71 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -204,6 +204,10 @@ static struct test generic_tests[] = { .func = test__event_update, }, { + .desc = "Test events times", + .func = test__event_times, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index abd3f0ec0c0b..68a69a195545 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -532,7 +532,7 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); evsel = perf_evlist__first(evlist); diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c new file mode 100644 index 000000000000..95fb744f6628 --- /dev/null +++ b/tools/perf/tests/event-times.c @@ -0,0 +1,236 @@ +#include <linux/compiler.h> +#include <string.h> +#include "tests.h" +#include "evlist.h" +#include "evsel.h" +#include "util.h" +#include "debug.h" +#include "thread_map.h" +#include "target.h" + +static int attach__enable_on_exec(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct target target = { + .uid = UINT_MAX, + }; + const char *argv[] = { "true", NULL, }; + char sbuf[STRERR_BUFSIZE]; + int err; + + pr_debug("attaching to spawned child, enable on exec\n"); + + err = perf_evlist__create_maps(evlist, &target); + if (err < 0) { + pr_debug("Not enough memory to create thread/cpu maps\n"); + return err; + } + + err = perf_evlist__prepare_workload(evlist, &target, argv, false, NULL); + if (err < 0) { + pr_debug("Couldn't run the workload!\n"); + return err; + } + + evsel->attr.enable_on_exec = 1; + + err = perf_evlist__open(evlist); + if (err < 0) { + pr_debug("perf_evlist__open: %s\n", + strerror_r(errno, sbuf, sizeof(sbuf))); + return err; + } + + return perf_evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; +} + +static int detach__enable_on_exec(struct perf_evlist *evlist) +{ + waitpid(evlist->workload.pid, NULL, 0); + return 0; +} + +static int attach__current_disabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct thread_map *threads; + int err; + + pr_debug("attaching to current thread as disabled\n"); + + threads = thread_map__new(-1, getpid(), UINT_MAX); + if (threads == NULL) { + pr_debug("thread_map__new\n"); + return -1; + } + + evsel->attr.disabled = 1; + + err = perf_evsel__open_per_thread(evsel, threads); + if (err) { + pr_debug("Failed to open event cpu-clock:u\n"); + return err; + } + + thread_map__put(threads); + return perf_evsel__enable(evsel) == 0 ? TEST_OK : TEST_FAIL; +} + +static int attach__current_enabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct thread_map *threads; + int err; + + pr_debug("attaching to current thread as enabled\n"); + + threads = thread_map__new(-1, getpid(), UINT_MAX); + if (threads == NULL) { + pr_debug("failed to call thread_map__new\n"); + return -1; + } + + err = perf_evsel__open_per_thread(evsel, threads); + + thread_map__put(threads); + return err == 0 ? TEST_OK : TEST_FAIL; +} + +static int detach__disable(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + + return perf_evsel__enable(evsel); +} + +static int attach__cpu_disabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct cpu_map *cpus; + int err; + + pr_debug("attaching to CPU 0 as enabled\n"); + + cpus = cpu_map__new("0"); + if (cpus == NULL) { + pr_debug("failed to call cpu_map__new\n"); + return -1; + } + + evsel->attr.disabled = 1; + + err = perf_evsel__open_per_cpu(evsel, cpus); + if (err) { + if (err == -EACCES) + return TEST_SKIP; + + pr_debug("Failed to open event cpu-clock:u\n"); + return err; + } + + cpu_map__put(cpus); + return perf_evsel__enable(evsel); +} + +static int attach__cpu_enabled(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel = perf_evlist__last(evlist); + struct cpu_map *cpus; + int err; + + pr_debug("attaching to CPU 0 as enabled\n"); + + cpus = cpu_map__new("0"); + if (cpus == NULL) { + pr_debug("failed to call cpu_map__new\n"); + return -1; + } + + err = perf_evsel__open_per_cpu(evsel, cpus); + if (err == -EACCES) + return TEST_SKIP; + + cpu_map__put(cpus); + return err ? TEST_FAIL : TEST_OK; +} + +static int test_times(int (attach)(struct perf_evlist *), + int (detach)(struct perf_evlist *)) +{ + struct perf_counts_values count; + struct perf_evlist *evlist = NULL; + struct perf_evsel *evsel; + int err = -1, i; + + evlist = perf_evlist__new(); + if (!evlist) { + pr_debug("failed to create event list\n"); + goto out_err; + } + + err = parse_events(evlist, "cpu-clock:u", NULL); + if (err) { + pr_debug("failed to parse event cpu-clock:u\n"); + goto out_err; + } + + evsel = perf_evlist__last(evlist); + evsel->attr.read_format |= + PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING; + + err = attach(evlist); + if (err == TEST_SKIP) { + pr_debug(" SKIP : not enough rights\n"); + return err; + } + + TEST_ASSERT_VAL("failed to attach", !err); + + for (i = 0; i < 100000000; i++) { } + + TEST_ASSERT_VAL("failed to detach", !detach(evlist)); + + perf_evsel__read(evsel, 0, 0, &count); + + err = !(count.ena == count.run); + + pr_debug(" %s: ena %" PRIu64", run %" PRIu64"\n", + !err ? "OK " : "FAILED", + count.ena, count.run); + +out_err: + if (evlist) + perf_evlist__delete(evlist); + return !err ? TEST_OK : TEST_FAIL; +} + +/* + * This test creates software event 'cpu-clock' + * attaches it in several ways (explained below) + * and checks that enabled and running times + * match. + */ +int test__event_times(int subtest __maybe_unused) +{ + int err, ret = 0; + +#define _T(attach, detach) \ + err = test_times(attach, detach); \ + if (err && (ret == TEST_OK || ret == TEST_SKIP)) \ + ret = err; + + /* attach on newly spawned process after exec */ + _T(attach__enable_on_exec, detach__enable_on_exec) + /* attach on current process as enabled */ + _T(attach__current_enabled, detach__disable) + /* attach on current process as disabled */ + _T(attach__current_disabled, detach__disable) + /* attach on cpu as disabled */ + _T(attach__cpu_disabled, detach__disable) + /* attach on cpu as enabled */ + _T(attach__cpu_enabled, detach__disable) + +#undef _T + return ret; +} diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index ddb78fae064a..614e45a3c603 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -80,7 +80,7 @@ int test__keep_tracking(int subtest __maybe_unused) CHECK__(parse_events(evlist, "dummy:u", NULL)); CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); evsel = perf_evlist__first(evlist); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index eb99a105f31c..4344fe482c1d 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -44,7 +44,7 @@ int test__syscall_openat_tp_fields(int subtest __maybe_unused) goto out_delete_evlist; } - perf_evsel__config(evsel, &opts); + perf_evsel__config(evsel, &opts, NULL); thread_map__set_pid(evlist->threads, 0, getpid()); diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 1cc78cefe399..b836ee6a8d9b 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -99,7 +99,7 @@ int test__PERF_RECORD(int subtest __maybe_unused) perf_evsel__set_sample_bit(evsel, CPU); perf_evsel__set_sample_bit(evsel, TID); perf_evsel__set_sample_bit(evsel, TIME); - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); if (err < 0) { diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index ebd80168d51e..39a689bf7574 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -417,7 +417,7 @@ int test__switch_tracking(int subtest __maybe_unused) perf_evsel__set_sample_bit(tracking_evsel, TIME); /* Config events */ - perf_evlist__config(evlist, &opts); + perf_evlist__config(evlist, &opts, NULL); /* Check moved event is still at the front */ if (cycles_evsel != perf_evlist__first(evlist)) { diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 82b2b5e6ba7c..0fc946989cf0 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -85,6 +85,7 @@ int test__synthesize_stat_config(int subtest); int test__synthesize_stat(int subtest); int test__synthesize_stat_round(int subtest); int test__event_update(int subtest); +int test__event_times(int subtest); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c new file mode 100644 index 000000000000..d64f4a9128a1 --- /dev/null +++ b/tools/perf/trace/beauty/eventfd.c @@ -0,0 +1,38 @@ +#include <sys/eventfd.h> + +#ifndef EFD_SEMAPHORE +#define EFD_SEMAPHORE 1 +#endif + +#ifndef EFD_NONBLOCK +#define EFD_NONBLOCK 00004000 +#endif + +#ifndef EFD_CLOEXEC +#define EFD_CLOEXEC 02000000 +#endif + +static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "NONE"); +#define P_FLAG(n) \ + if (flags & EFD_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~EFD_##n; \ + } + + P_FLAG(SEMAPHORE); + P_FLAG(CLOEXEC); + P_FLAG(NONBLOCK); +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c new file mode 100644 index 000000000000..3444a4d5382d --- /dev/null +++ b/tools/perf/trace/beauty/mmap.c @@ -0,0 +1,158 @@ +#include <sys/mman.h> + +static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, prot = arg->val; + + if (prot == PROT_NONE) + return scnprintf(bf, size, "NONE"); +#define P_MMAP_PROT(n) \ + if (prot & PROT_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + prot &= ~PROT_##n; \ + } + + P_MMAP_PROT(EXEC); + P_MMAP_PROT(READ); + P_MMAP_PROT(WRITE); +#ifdef PROT_SEM + P_MMAP_PROT(SEM); +#endif + P_MMAP_PROT(GROWSDOWN); + P_MMAP_PROT(GROWSUP); +#undef P_MMAP_PROT + + if (prot) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot); + + return printed; +} + +#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot + +#ifndef MAP_STACK +# define MAP_STACK 0x20000 +#endif + +static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_MMAP_FLAG(n) \ + if (flags & MAP_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MAP_##n; \ + } + + P_MMAP_FLAG(SHARED); + P_MMAP_FLAG(PRIVATE); +#ifdef MAP_32BIT + P_MMAP_FLAG(32BIT); +#endif + P_MMAP_FLAG(ANONYMOUS); + P_MMAP_FLAG(DENYWRITE); + P_MMAP_FLAG(EXECUTABLE); + P_MMAP_FLAG(FILE); + P_MMAP_FLAG(FIXED); + P_MMAP_FLAG(GROWSDOWN); +#ifdef MAP_HUGETLB + P_MMAP_FLAG(HUGETLB); +#endif + P_MMAP_FLAG(LOCKED); + P_MMAP_FLAG(NONBLOCK); + P_MMAP_FLAG(NORESERVE); + P_MMAP_FLAG(POPULATE); + P_MMAP_FLAG(STACK); +#ifdef MAP_UNINITIALIZED + P_MMAP_FLAG(UNINITIALIZED); +#endif +#undef P_MMAP_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags + +static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_MREMAP_FLAG(n) \ + if (flags & MREMAP_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~MREMAP_##n; \ + } + + P_MREMAP_FLAG(MAYMOVE); +#ifdef MREMAP_FIXED + P_MREMAP_FLAG(FIXED); +#endif +#undef P_MREMAP_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags + +#ifndef MADV_HWPOISON +#define MADV_HWPOISON 100 +#endif + +#ifndef MADV_MERGEABLE +#define MADV_MERGEABLE 12 +#endif + +#ifndef MADV_UNMERGEABLE +#define MADV_UNMERGEABLE 13 +#endif + +static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size, + struct syscall_arg *arg) +{ + int behavior = arg->val; + + switch (behavior) { +#define P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n) + P_MADV_BHV(NORMAL); + P_MADV_BHV(RANDOM); + P_MADV_BHV(SEQUENTIAL); + P_MADV_BHV(WILLNEED); + P_MADV_BHV(DONTNEED); + P_MADV_BHV(REMOVE); + P_MADV_BHV(DONTFORK); + P_MADV_BHV(DOFORK); + P_MADV_BHV(HWPOISON); +#ifdef MADV_SOFT_OFFLINE + P_MADV_BHV(SOFT_OFFLINE); +#endif + P_MADV_BHV(MERGEABLE); + P_MADV_BHV(UNMERGEABLE); +#ifdef MADV_HUGEPAGE + P_MADV_BHV(HUGEPAGE); +#endif +#ifdef MADV_NOHUGEPAGE + P_MADV_BHV(NOHUGEPAGE); +#endif +#ifdef MADV_DONTDUMP + P_MADV_BHV(DONTDUMP); +#endif +#ifdef MADV_DODUMP + P_MADV_BHV(DODUMP); +#endif +#undef P_MADV_PHV + default: break; + } + + return scnprintf(bf, size, "%#x", behavior); +} + +#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c new file mode 100644 index 000000000000..930d8fef2400 --- /dev/null +++ b/tools/perf/trace/beauty/mode_t.c @@ -0,0 +1,68 @@ +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +/* From include/linux/stat.h */ +#ifndef S_IRWXUGO +#define S_IRWXUGO (S_IRWXU|S_IRWXG|S_IRWXO) +#endif +#ifndef S_IALLUGO +#define S_IALLUGO (S_ISUID|S_ISGID|S_ISVTX|S_IRWXUGO) +#endif +#ifndef S_IRUGO +#define S_IRUGO (S_IRUSR|S_IRGRP|S_IROTH) +#endif +#ifndef S_IWUGO +#define S_IWUGO (S_IWUSR|S_IWGRP|S_IWOTH) +#endif +#ifndef S_IXUGO +#define S_IXUGO (S_IXUSR|S_IXGRP|S_IXOTH) +#endif + +static size_t syscall_arg__scnprintf_mode_t(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, mode = arg->val; + +#define P_MODE(n) \ + if ((mode & S_##n) == S_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + mode &= ~S_##n; \ + } + + P_MODE(IALLUGO); + P_MODE(IRWXUGO); + P_MODE(IRUGO); + P_MODE(IWUGO); + P_MODE(IXUGO); + P_MODE(IFMT); + P_MODE(IFSOCK); + P_MODE(IFLNK); + P_MODE(IFREG); + P_MODE(IFBLK); + P_MODE(IFDIR); + P_MODE(IFCHR); + P_MODE(IFIFO); + P_MODE(ISUID); + P_MODE(ISGID); + P_MODE(ISVTX); + P_MODE(IRWXU); + P_MODE(IRUSR); + P_MODE(IWUSR); + P_MODE(IXUSR); + P_MODE(IRWXG); + P_MODE(IRGRP); + P_MODE(IWGRP); + P_MODE(IXGRP); + P_MODE(IRWXO); + P_MODE(IROTH); + P_MODE(IWOTH); + P_MODE(IXOTH); +#undef P_MODE + + if (mode) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", mode); + + return printed; +} + +#define SCA_MODE_T syscall_arg__scnprintf_mode_t diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c new file mode 100644 index 000000000000..111ae08d38f1 --- /dev/null +++ b/tools/perf/trace/beauty/pid.c @@ -0,0 +1,18 @@ +static size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg) +{ + int pid = arg->val; + struct trace *trace = arg->trace; + size_t printed = scnprintf(bf, size, "%d", pid); + struct thread *thread = machine__find_thread(trace->host, pid, pid); + + if (thread != NULL) { + if (thread->comm_set) + printed += scnprintf(bf + printed, size - printed, + " (%s)", thread__comm_str(thread)); + thread__put(thread); + } + + return printed; +} + +#define SCA_PID syscall_arg__scnprintf_pid diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c new file mode 100644 index 000000000000..c205bc608b3c --- /dev/null +++ b/tools/perf/trace/beauty/sched_policy.c @@ -0,0 +1,44 @@ +#include <sched.h> + +/* + * Not defined anywhere else, probably, just to make sure we + * catch future flags + */ +#define SCHED_POLICY_MASK 0xff + +#ifndef SCHED_DEADLINE +#define SCHED_DEADLINE 6 +#endif + +static size_t syscall_arg__scnprintf_sched_policy(char *bf, size_t size, + struct syscall_arg *arg) +{ + const char *policies[] = { + "NORMAL", "FIFO", "RR", "BATCH", "ISO", "IDLE", "DEADLINE", + }; + size_t printed; + int policy = arg->val, + flags = policy & ~SCHED_POLICY_MASK; + + policy &= SCHED_POLICY_MASK; + if (policy <= SCHED_DEADLINE) + printed = scnprintf(bf, size, "%s", policies[policy]); + else + printed = scnprintf(bf, size, "%#x", policy); + +#define P_POLICY_FLAG(n) \ + if (flags & SCHED_##n) { \ + printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ + flags &= ~SCHED_##n; \ + } + + P_POLICY_FLAG(RESET_ON_FORK); +#undef P_POLICY_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "|%#x", flags); + + return printed; +} + +#define SCA_SCHED_POLICY syscall_arg__scnprintf_sched_policy diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c new file mode 100644 index 000000000000..0a5ce818131c --- /dev/null +++ b/tools/perf/trace/beauty/socket_type.c @@ -0,0 +1,60 @@ +#include <sys/types.h> +#include <sys/socket.h> + +#ifndef SOCK_DCCP +# define SOCK_DCCP 6 +#endif + +#ifndef SOCK_CLOEXEC +# define SOCK_CLOEXEC 02000000 +#endif + +#ifndef SOCK_NONBLOCK +# define SOCK_NONBLOCK 00004000 +#endif + +#ifndef SOCK_TYPE_MASK +#define SOCK_TYPE_MASK 0xf +#endif + +static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size, struct syscall_arg *arg) +{ + size_t printed; + int type = arg->val, + flags = type & ~SOCK_TYPE_MASK; + + type &= SOCK_TYPE_MASK; + /* + * Can't use a strarray, MIPS may override for ABI reasons. + */ + switch (type) { +#define P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break; + P_SK_TYPE(STREAM); + P_SK_TYPE(DGRAM); + P_SK_TYPE(RAW); + P_SK_TYPE(RDM); + P_SK_TYPE(SEQPACKET); + P_SK_TYPE(DCCP); + P_SK_TYPE(PACKET); +#undef P_SK_TYPE + default: + printed = scnprintf(bf, size, "%#x", type); + } + +#define P_SK_FLAG(n) \ + if (flags & SOCK_##n) { \ + printed += scnprintf(bf + printed, size - printed, "|%s", #n); \ + flags &= ~SOCK_##n; \ + } + + P_SK_FLAG(CLOEXEC); + P_SK_FLAG(NONBLOCK); +#undef P_SK_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "|%#x", flags); + + return printed; +} + +#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c new file mode 100644 index 000000000000..7942724adec8 --- /dev/null +++ b/tools/perf/trace/beauty/waitid_options.c @@ -0,0 +1,26 @@ +#include <sys/types.h> +#include <sys/wait.h> + +static size_t syscall_arg__scnprintf_waitid_options(char *bf, size_t size, + struct syscall_arg *arg) +{ + int printed = 0, options = arg->val; + +#define P_OPTION(n) \ + if (options & W##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + options &= ~W##n; \ + } + + P_OPTION(NOHANG); + P_OPTION(UNTRACED); + P_OPTION(CONTINUED); +#undef P_OPTION + + if (options) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", options); + + return printed; +} + +#define SCA_WAITID_OPTIONS syscall_arg__scnprintf_waitid_options diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 2a83414159a6..e70df2e54d66 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1607,9 +1607,8 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); dummy_hpp.buf[ret] = '\0'; - rtrim(dummy_hpp.buf); - start = ltrim(dummy_hpp.buf); + start = trim(dummy_hpp.buf); ret = strlen(start); if (start != dummy_hpp.buf) diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 7aff5acf3265..560eb47d56f9 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -569,9 +569,8 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp, first_col = false; fmt->header(fmt, hpp, hists_to_evsel(hists)); - rtrim(hpp->buf); - header_width += fprintf(fp, "%s", ltrim(hpp->buf)); + header_width += fprintf(fp, "%s", trim(hpp->buf)); } } diff --git a/tools/perf/util/Build b/tools/perf/util/Build index da48fd843438..85a9ab62e23f 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -8,6 +8,7 @@ libperf-y += env.o libperf-y += event.o libperf-y += evlist.o libperf-y += evsel.o +libperf-y += evsel_fprintf.o libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o @@ -29,6 +30,7 @@ libperf-y += usage.o libperf-y += wrapper.o libperf-y += dso.o libperf-y += symbol.o +libperf-y += symbol_fprintf.o libperf-y += color.o libperf-y += header.o libperf-y += callchain.o @@ -38,6 +40,7 @@ libperf-y += machine.o libperf-y += map.o libperf-y += pstack.o libperf-y += session.o +libperf-$(CONFIG_AUDIT) += syscalltbl.o libperf-y += ordered-events.o libperf-y += comm.o libperf-y += thread.o @@ -69,8 +72,7 @@ libperf-y += stat-shadow.o libperf-y += record.o libperf-y += srcline.o libperf-y += data.o -libperf-$(CONFIG_X86) += tsc.o -libperf-$(CONFIG_AUXTRACE) += tsc.o +libperf-y += tsc.o libperf-y += cloexec.o libperf-y += thread-stack.o libperf-$(CONFIG_AUXTRACE) += auxtrace.o @@ -148,6 +150,10 @@ CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_parse-events.o += -Wno-redundant-decls +$(OUTPUT)util/syscalltbl.o: util/syscalltbl.c arch/x86/entry/syscalls/syscall_64.tbl $(OUTPUT)arch/x86/include/generated/asm/syscalls_64.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index ec164fe70718..c9169011e55e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -940,6 +940,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts) synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD; synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ; synth_opts->last_branch_sz = PERF_ITRACE_DEFAULT_LAST_BRANCH_SZ; + synth_opts->initial_skip = 0; } /* @@ -1064,6 +1065,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, synth_opts->last_branch_sz = val; } break; + case 's': + synth_opts->initial_skip = strtoul(p, &endptr, 10); + if (p == endptr) + goto out_err; + p = endptr; + break; case ' ': case ',': break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 57ff31ecb8e4..767989e0e312 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -68,6 +68,7 @@ enum itrace_period_type { * @last_branch_sz: branch context size * @period: 'instructions' events period * @period_type: 'instructions' events period type + * @initial_skip: skip N events at the beginning. */ struct itrace_synth_opts { bool set; @@ -86,6 +87,7 @@ struct itrace_synth_opts { unsigned int last_branch_sz; unsigned long long period; enum itrace_period_type period_type; + unsigned long initial_skip; }; /** diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 0967ce601931..493307d1414c 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -842,6 +842,58 @@ bpf_map_op__new(struct parse_events_term *term) return op; } +static struct bpf_map_op * +bpf_map_op__clone(struct bpf_map_op *op) +{ + struct bpf_map_op *newop; + + newop = memdup(op, sizeof(*op)); + if (!newop) { + pr_debug("Failed to alloc bpf_map_op\n"); + return NULL; + } + + INIT_LIST_HEAD(&newop->list); + if (op->key_type == BPF_MAP_KEY_RANGES) { + size_t memsz = op->k.array.nr_ranges * + sizeof(op->k.array.ranges[0]); + + newop->k.array.ranges = memdup(op->k.array.ranges, memsz); + if (!newop->k.array.ranges) { + pr_debug("Failed to alloc indices for map\n"); + free(newop); + return NULL; + } + } + + return newop; +} + +static struct bpf_map_priv * +bpf_map_priv__clone(struct bpf_map_priv *priv) +{ + struct bpf_map_priv *newpriv; + struct bpf_map_op *pos, *newop; + + newpriv = zalloc(sizeof(*newpriv)); + if (!newpriv) { + pr_debug("No enough memory to alloc map private\n"); + return NULL; + } + INIT_LIST_HEAD(&newpriv->ops_list); + + list_for_each_entry(pos, &priv->ops_list, list) { + newop = bpf_map_op__clone(pos); + if (!newop) { + bpf_map_priv__purge(newpriv); + return NULL; + } + list_add_tail(&newop->list, &newpriv->ops_list); + } + + return newpriv; +} + static int bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op) { @@ -1417,6 +1469,89 @@ int bpf__apply_obj_config(void) return 0; } +#define bpf__for_each_map(pos, obj, objtmp) \ + bpf_object__for_each_safe(obj, objtmp) \ + bpf_map__for_each(pos, obj) + +#define bpf__for_each_stdout_map(pos, obj, objtmp) \ + bpf__for_each_map(pos, obj, objtmp) \ + if (bpf_map__get_name(pos) && \ + (strcmp("__bpf_stdout__", \ + bpf_map__get_name(pos)) == 0)) + +int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) +{ + struct bpf_map_priv *tmpl_priv = NULL; + struct bpf_object *obj, *tmp; + struct perf_evsel *evsel = NULL; + struct bpf_map *map; + int err; + bool need_init = false; + + bpf__for_each_stdout_map(map, obj, tmp) { + struct bpf_map_priv *priv; + + err = bpf_map__get_private(map, (void **)&priv); + if (err) + return -BPF_LOADER_ERRNO__INTERNAL; + + /* + * No need to check map type: type should have been + * verified by kernel. + */ + if (!need_init && !priv) + need_init = !priv; + if (!tmpl_priv && priv) + tmpl_priv = priv; + } + + if (!need_init) + return 0; + + if (!tmpl_priv) { + err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/", + NULL); + if (err) { + pr_debug("ERROR: failed to create bpf-output event\n"); + return -err; + } + + evsel = perf_evlist__last(evlist); + } + + bpf__for_each_stdout_map(map, obj, tmp) { + struct bpf_map_priv *priv; + + err = bpf_map__get_private(map, (void **)&priv); + if (err) + return -BPF_LOADER_ERRNO__INTERNAL; + if (priv) + continue; + + if (tmpl_priv) { + priv = bpf_map_priv__clone(tmpl_priv); + if (!priv) + return -ENOMEM; + + err = bpf_map__set_private(map, priv, bpf_map_priv__clear); + if (err) { + bpf_map_priv__clear(map, priv); + return err; + } + } else if (evsel) { + struct bpf_map_op *op; + + op = bpf_map__add_newop(map, NULL); + if (IS_ERR(op)) + return PTR_ERR(op); + op->op_type = BPF_MAP_OP_SET_EVSEL; + op->v.evsel = evsel; + } + } + + return 0; +} + #define ERRNO_OFFSET(e) ((e) - __BPF_LOADER_ERRNO__START) #define ERRCODE_OFFSET(c) ERRNO_OFFSET(BPF_LOADER_ERRNO__##c) #define NR_ERRNO (__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START) @@ -1590,3 +1725,11 @@ int bpf__strerror_apply_obj_config(int err, char *buf, size_t size) bpf__strerror_end(buf, size); return 0; } + +int bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, + int err, char *buf, size_t size) +{ + bpf__strerror_head(err, buf, size); + bpf__strerror_end(buf, size); + return 0; +} diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index be4311944e3d..941e17275aa7 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -79,6 +79,11 @@ int bpf__strerror_config_obj(struct bpf_object *obj, size_t size); int bpf__apply_obj_config(void); int bpf__strerror_apply_obj_config(int err, char *buf, size_t size); + +int bpf__setup_stdout(struct perf_evlist *evlist); +int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, + char *buf, size_t size); + #else static inline struct bpf_object * bpf__prepare_load(const char *filename __maybe_unused, @@ -125,6 +130,12 @@ bpf__apply_obj_config(void) } static inline int +bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused) +{ + return 0; +} + +static inline int __bpf_strerror(char *buf, size_t size) { if (!size) @@ -177,5 +188,13 @@ bpf__strerror_apply_obj_config(int err __maybe_unused, { return __bpf_strerror(buf, size); } + +static inline int +bpf__strerror_setup_stdout(struct perf_evlist *evlist __maybe_unused, + int err __maybe_unused, char *buf, + size_t size) +{ + return __bpf_strerror(buf, size); +} #endif #endif diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 24b4bd0d7754..2b4ceaf058bb 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -788,7 +788,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor, return 0; } -int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, +int sample__resolve_callchain(struct perf_sample *sample, + struct callchain_cursor *cursor, struct symbol **parent, struct perf_evsel *evsel, struct addr_location *al, int max_stack) { @@ -797,7 +798,7 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain || sort__has_parent) { - return thread__resolve_callchain(al->thread, evsel, sample, + return thread__resolve_callchain(al->thread, cursor, evsel, sample, parent, al, max_stack); } return 0; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index d2a9e694810c..65e2a4f7cb4e 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -212,7 +212,14 @@ struct hist_entry; int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); int record_callchain_opt(const struct option *opt, const char *arg, int unset); -int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent, +struct record_opts; + +int record_opts__parse_callchain(struct record_opts *record, + struct callchain_param *callchain, + const char *arg, bool unset); + +int sample__resolve_callchain(struct perf_sample *sample, + struct callchain_cursor *cursor, struct symbol **parent, struct perf_evsel *evsel, struct addr_location *al, int max_stack); int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample); diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 4e727635476e..dad7d8272168 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -13,6 +13,7 @@ #include <subcmd/exec-cmd.h> #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ +#include "config.h" #define MAXNAME (256) @@ -377,6 +378,21 @@ const char *perf_config_dirname(const char *name, const char *value) return value; } +static int perf_buildid_config(const char *var, const char *value) +{ + /* same dir for all commands */ + if (!strcmp(var, "buildid.dir")) { + const char *dir = perf_config_dirname(var, value); + + if (!dir) + return -1; + strncpy(buildid_dir, dir, MAXPATHLEN-1); + buildid_dir[MAXPATHLEN-1] = '\0'; + } + + return 0; +} + static int perf_default_core_config(const char *var __maybe_unused, const char *value __maybe_unused) { @@ -412,6 +428,9 @@ int perf_default_config(const char *var, const char *value, if (!prefixcmp(var, "llvm.")) return perf_llvm_config(var, value); + if (!prefixcmp(var, "buildid.")) + return perf_buildid_config(var, value); + /* Add other config variables here. */ return 0; } @@ -506,41 +525,185 @@ out: return ret; } -/* - * Call this to report error for your variable that should not - * get a boolean value (i.e. "[my] var" means "true"). - */ -int config_error_nonbool(const char *var) +static struct perf_config_section *find_section(struct list_head *sections, + const char *section_name) { - return error("Missing value for '%s'", var); + struct perf_config_section *section; + + list_for_each_entry(section, sections, node) + if (!strcmp(section->name, section_name)) + return section; + + return NULL; +} + +static struct perf_config_item *find_config_item(const char *name, + struct perf_config_section *section) +{ + struct perf_config_item *item; + + list_for_each_entry(item, §ion->items, node) + if (!strcmp(item->name, name)) + return item; + + return NULL; } -struct buildid_dir_config { - char *dir; -}; +static struct perf_config_section *add_section(struct list_head *sections, + const char *section_name) +{ + struct perf_config_section *section = zalloc(sizeof(*section)); + + if (!section) + return NULL; + + INIT_LIST_HEAD(§ion->items); + section->name = strdup(section_name); + if (!section->name) { + pr_debug("%s: strdup failed\n", __func__); + free(section); + return NULL; + } + + list_add_tail(§ion->node, sections); + return section; +} -static int buildid_dir_command_config(const char *var, const char *value, - void *data) +static struct perf_config_item *add_config_item(struct perf_config_section *section, + const char *name) { - struct buildid_dir_config *c = data; - const char *v; + struct perf_config_item *item = zalloc(sizeof(*item)); - /* same dir for all commands */ - if (!strcmp(var, "buildid.dir")) { - v = perf_config_dirname(var, value); - if (!v) - return -1; - strncpy(c->dir, v, MAXPATHLEN-1); - c->dir[MAXPATHLEN-1] = '\0'; + if (!item) + return NULL; + + item->name = strdup(name); + if (!item->name) { + pr_debug("%s: strdup failed\n", __func__); + free(item); + return NULL; } + + list_add_tail(&item->node, §ion->items); + return item; +} + +static int set_value(struct perf_config_item *item, const char *value) +{ + char *val = strdup(value); + + if (!val) + return -1; + + zfree(&item->value); + item->value = val; return 0; } -static void check_buildid_dir_config(void) +static int collect_config(const char *var, const char *value, + void *perf_config_set) { - struct buildid_dir_config c; - c.dir = buildid_dir; - perf_config(buildid_dir_command_config, &c); + int ret = -1; + char *ptr, *key; + char *section_name, *name; + struct perf_config_section *section = NULL; + struct perf_config_item *item = NULL; + struct perf_config_set *set = perf_config_set; + struct list_head *sections = &set->sections; + + key = ptr = strdup(var); + if (!key) { + pr_debug("%s: strdup failed\n", __func__); + return -1; + } + + section_name = strsep(&ptr, "."); + name = ptr; + if (name == NULL || value == NULL) + goto out_free; + + section = find_section(sections, section_name); + if (!section) { + section = add_section(sections, section_name); + if (!section) + goto out_free; + } + + item = find_config_item(name, section); + if (!item) { + item = add_config_item(section, name); + if (!item) + goto out_free; + } + + ret = set_value(item, value); + return ret; + +out_free: + free(key); + perf_config_set__delete(set); + return -1; +} + +struct perf_config_set *perf_config_set__new(void) +{ + struct perf_config_set *set = zalloc(sizeof(*set)); + + if (set) { + INIT_LIST_HEAD(&set->sections); + perf_config(collect_config, set); + } + + return set; +} + +static void perf_config_item__delete(struct perf_config_item *item) +{ + zfree(&item->name); + zfree(&item->value); + free(item); +} + +static void perf_config_section__purge(struct perf_config_section *section) +{ + struct perf_config_item *item, *tmp; + + list_for_each_entry_safe(item, tmp, §ion->items, node) { + list_del_init(&item->node); + perf_config_item__delete(item); + } +} + +static void perf_config_section__delete(struct perf_config_section *section) +{ + perf_config_section__purge(section); + zfree(§ion->name); + free(section); +} + +static void perf_config_set__purge(struct perf_config_set *set) +{ + struct perf_config_section *section, *tmp; + + list_for_each_entry_safe(section, tmp, &set->sections, node) { + list_del_init(§ion->node); + perf_config_section__delete(section); + } +} + +void perf_config_set__delete(struct perf_config_set *set) +{ + perf_config_set__purge(set); + free(set); +} + +/* + * Call this to report error for your variable that should not + * get a boolean value (i.e. "[my] var" means "true"). + */ +int config_error_nonbool(const char *var) +{ + return error("Missing value for '%s'", var); } void set_buildid_dir(const char *dir) @@ -548,16 +711,13 @@ void set_buildid_dir(const char *dir) if (dir) scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir); - /* try config file */ - if (buildid_dir[0] == '\0') - check_buildid_dir_config(); - /* default to $HOME/.debug */ if (buildid_dir[0] == '\0') { - char *v = getenv("HOME"); - if (v) { + char *home = getenv("HOME"); + + if (home) { snprintf(buildid_dir, MAXPATHLEN-1, "%s/%s", - v, DEBUG_CACHE_DIR); + home, DEBUG_CACHE_DIR); } else { strncpy(buildid_dir, DEBUG_CACHE_DIR, MAXPATHLEN-1); } diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h new file mode 100644 index 000000000000..22ec626ac718 --- /dev/null +++ b/tools/perf/util/config.h @@ -0,0 +1,26 @@ +#ifndef __PERF_CONFIG_H +#define __PERF_CONFIG_H + +#include <stdbool.h> +#include <linux/list.h> + +struct perf_config_item { + char *name; + char *value; + struct list_head node; +}; + +struct perf_config_section { + char *name; + struct list_head items; + struct list_head node; +}; + +struct perf_config_set { + struct list_head sections; +}; + +struct perf_config_set *perf_config_set__new(void); +void perf_config_set__delete(struct perf_config_set *set); + +#endif /* __PERF_CONFIG_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 9bcf2bed3a6d..02d801670f30 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -587,3 +587,15 @@ int cpu__setup_cpunode_map(void) closedir(dir1); return 0; } + +bool cpu_map__has(struct cpu_map *cpus, int cpu) +{ + int i; + + for (i = 0; i < cpus->nr; ++i) { + if (cpus->map[i] == cpu) + return true; + } + + return false; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 81a2562aaa2b..1a0a35073ce1 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -66,4 +66,6 @@ int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, int (*f)(struct cpu_map *map, int cpu, void *data), void *data); + +bool cpu_map__has(struct cpu_map *cpus, int cpu); #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 1921942fc2e0..be83516155ee 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -136,3 +136,44 @@ ssize_t perf_data_file__write(struct perf_data_file *file, { return writen(file->fd, buf, size); } + +int perf_data_file__switch(struct perf_data_file *file, + const char *postfix, + size_t pos, bool at_exit) +{ + char *new_filepath; + int ret; + + if (check_pipe(file)) + return -EINVAL; + if (perf_data_file__is_read(file)) + return -EINVAL; + + if (asprintf(&new_filepath, "%s.%s", file->path, postfix) < 0) + return -ENOMEM; + + /* + * Only fire a warning, don't return error, continue fill + * original file. + */ + if (rename(file->path, new_filepath)) + pr_warning("Failed to rename %s to %s\n", file->path, new_filepath); + + if (!at_exit) { + close(file->fd); + ret = perf_data_file__open(file); + if (ret < 0) + goto out; + + if (lseek(file->fd, pos, SEEK_SET) == (off_t)-1) { + ret = -errno; + pr_debug("Failed to lseek to %zu: %s", + pos, strerror(errno)); + goto out; + } + } + ret = file->fd; +out: + free(new_filepath); + return ret; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 2b15d0c95c7f..ae510ce16cb1 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -46,5 +46,14 @@ int perf_data_file__open(struct perf_data_file *file); void perf_data_file__close(struct perf_data_file *file); ssize_t perf_data_file__write(struct perf_data_file *file, void *buf, size_t size); - +/* + * If at_exit is set, only rename current perf.data to + * perf.data.<postfix>, continue write on original file. + * Set at_exit when flushing the last output. + * + * Return value is fd of new output. + */ +int perf_data_file__switch(struct perf_data_file *file, + const char *postfix, + size_t pos, bool at_exit); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 577e600c8eb1..aea189b41cc8 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -959,6 +959,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf) return 0; } +#ifdef HAVE_DWARF_GETLOCATIONS /** * die_get_var_innermost_scope - Get innermost scope range of given variable DIE * @sp_die: a subprogram DIE @@ -1080,3 +1081,11 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf) return ret; } +#else +int die_get_var_range(Dwarf_Die *sp_die __maybe_unused, + Dwarf_Die *vr_die __maybe_unused, + struct strbuf *buf __maybe_unused) +{ + return -ENOTSUP; +} +#endif diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index dad55d04ffdd..f6fcc6832949 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -45,6 +45,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_STAT] = "STAT", [PERF_RECORD_STAT_ROUND] = "STAT_ROUND", [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", + [PERF_RECORD_TIME_CONV] = "TIME_CONV", }; const char *perf_event__name(unsigned int id) @@ -433,7 +434,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, { char filename[PATH_MAX]; DIR *tasks; - struct dirent dirent, *next; + struct dirent *dirent; pid_t tgid, ppid; int rc = 0; @@ -462,11 +463,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, return 0; } - while (!readdir_r(tasks, &dirent, &next) && next) { + while ((dirent = readdir(tasks)) != NULL) { char *end; pid_t _pid; - _pid = strtol(dirent.d_name, &end, 10); + _pid = strtol(dirent->d_name, &end, 10); if (*end) continue; @@ -575,7 +576,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, { DIR *proc; char proc_path[PATH_MAX]; - struct dirent dirent, *next; + struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; int err = -1; @@ -600,9 +601,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (proc == NULL) goto out_free_fork; - while (!readdir_r(proc, &dirent, &next) && next) { + while ((dirent = readdir(proc)) != NULL) { char *end; - pid_t pid = strtol(dirent.d_name, &end, 10); + pid_t pid = strtol(dirent->d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 6bb1c928350d..8d363d5e65a2 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -233,6 +233,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_STAT = 76, PERF_RECORD_STAT_ROUND = 77, PERF_RECORD_EVENT_UPDATE = 78, + PERF_RECORD_TIME_CONV = 79, PERF_RECORD_HEADER_MAX }; @@ -469,6 +470,13 @@ struct stat_round_event { u64 time; }; +struct time_conv_event { + struct perf_event_header header; + u64 time_shift; + u64 time_mult; + u64 time_zero; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -497,6 +505,7 @@ union perf_event { struct stat_config_event stat_config; struct stat_event stat; struct stat_round_event stat_round; + struct time_conv_event time_conv; }; void perf_event__print_totals(void); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 86a03836a83f..6fb5725821de 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -986,26 +986,34 @@ out_unmap: return -1; } -static size_t perf_evlist__mmap_size(unsigned long pages) +unsigned long perf_event_mlock_kb_in_pages(void) { - if (pages == UINT_MAX) { - int max; + unsigned long pages; + int max; - if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) { - /* - * Pick a once upon a time good value, i.e. things look - * strange since we can't read a sysctl value, but lets not - * die yet... - */ - max = 512; - } else { - max -= (page_size / 1024); - } + if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) { + /* + * Pick a once upon a time good value, i.e. things look + * strange since we can't read a sysctl value, but lets not + * die yet... + */ + max = 512; + } else { + max -= (page_size / 1024); + } - pages = (max * 1024) / page_size; - if (!is_power_of_2(pages)) - pages = rounddown_pow_of_two(pages); - } else if (!is_power_of_2(pages)) + pages = (max * 1024) / page_size; + if (!is_power_of_2(pages)) + pages = rounddown_pow_of_two(pages); + + return pages; +} + +static size_t perf_evlist__mmap_size(unsigned long pages) +{ + if (pages == UINT_MAX) + pages = perf_event_mlock_kb_in_pages(); + else if (!is_power_of_2(pages)) return 0; return (pages + 1) * page_size; @@ -1192,6 +1200,24 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus, perf_evlist__propagate_maps(evlist); } +void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + __perf_evsel__set_sample_bit(evsel, bit); +} + +void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) + __perf_evsel__reset_sample_bit(evsel, bit); +} + int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel) { struct perf_evsel *evsel; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a0d15221db6e..208897a646ca 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -87,6 +87,17 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist); int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); +void __perf_evlist__set_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit); +void __perf_evlist__reset_sample_bit(struct perf_evlist *evlist, + enum perf_event_sample_format bit); + +#define perf_evlist__set_sample_bit(evlist, bit) \ + __perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit) + +#define perf_evlist__reset_sample_bit(evlist, bit) \ + __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit) + int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter); int perf_evlist__set_filter_pid(struct perf_evlist *evlist, pid_t pid); int perf_evlist__set_filter_pids(struct perf_evlist *evlist, size_t npids, pid_t *pids); @@ -123,11 +134,14 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); +struct callchain_param; + void perf_evlist__set_id_pos(struct perf_evlist *evlist); bool perf_can_sample_identifier(void); bool perf_can_record_switch_events(void); bool perf_can_record_cpu_wide(void); -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts); +void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, + struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, @@ -144,6 +158,8 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset); +unsigned long perf_event_mlock_kb_in_pages(void); + int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages, bool overwrite, unsigned int auxtrace_pages, bool auxtrace_overwrite); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 738ce226002b..545bb3f0b2b0 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -226,7 +226,8 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { - evsel->attr.sample_type |= PERF_SAMPLE_RAW; + evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | + PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), evsel->attr.sample_period = 1; } @@ -561,10 +562,9 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size) return ret; } -static void -perf_evsel__config_callgraph(struct perf_evsel *evsel, - struct record_opts *opts, - struct callchain_param *param) +void perf_evsel__config_callchain(struct perf_evsel *evsel, + struct record_opts *opts, + struct callchain_param *param) { bool function = perf_evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->attr; @@ -704,7 +704,7 @@ static void apply_config_terms(struct perf_evsel *evsel, /* set perf-event callgraph */ if (param.enabled) - perf_evsel__config_callgraph(evsel, opts, ¶m); + perf_evsel__config_callchain(evsel, opts, ¶m); } } @@ -736,7 +736,8 @@ static void apply_config_terms(struct perf_evsel *evsel, * enable/disable events specifically, as there's no * initial traced exec call. */ -void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) +void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, + struct callchain_param *callchain) { struct perf_evsel *leader = evsel->leader; struct perf_event_attr *attr = &evsel->attr; @@ -811,8 +812,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts) if (perf_evsel__is_function_event(evsel)) evsel->attr.exclude_callchain_user = 1; - if (callchain_param.enabled && !evsel->no_aux_samples) - perf_evsel__config_callgraph(evsel, opts, &callchain_param); + if (callchain && callchain->enabled && !evsel->no_aux_samples) + perf_evsel__config_callchain(evsel, opts, callchain); if (opts->sample_intr_regs) { attr->sample_regs_intr = opts->sample_intr_regs; @@ -2253,95 +2254,6 @@ u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample, return 0; } -static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) -{ - va_list args; - int ret = 0; - - if (!*first) { - ret += fprintf(fp, ","); - } else { - ret += fprintf(fp, ":"); - *first = false; - } - - va_start(args, fmt); - ret += vfprintf(fp, fmt, args); - va_end(args); - return ret; -} - -static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv) -{ - return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); -} - -int perf_evsel__fprintf(struct perf_evsel *evsel, - struct perf_attr_details *details, FILE *fp) -{ - bool first = true; - int printed = 0; - - if (details->event_group) { - struct perf_evsel *pos; - - if (!perf_evsel__is_group_leader(evsel)) - return 0; - - if (evsel->nr_members > 1) - printed += fprintf(fp, "%s{", evsel->group_name ?: ""); - - printed += fprintf(fp, "%s", perf_evsel__name(evsel)); - for_each_group_member(pos, evsel) - printed += fprintf(fp, ",%s", perf_evsel__name(pos)); - - if (evsel->nr_members > 1) - printed += fprintf(fp, "}"); - goto out; - } - - printed += fprintf(fp, "%s", perf_evsel__name(evsel)); - - if (details->verbose) { - printed += perf_event_attr__fprintf(fp, &evsel->attr, - __print_attr__fprintf, &first); - } else if (details->freq) { - const char *term = "sample_freq"; - - if (!evsel->attr.freq) - term = "sample_period"; - - printed += comma_fprintf(fp, &first, " %s=%" PRIu64, - term, (u64)evsel->attr.sample_freq); - } - - if (details->trace_fields) { - struct format_field *field; - - if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { - printed += comma_fprintf(fp, &first, " (not a tracepoint)"); - goto out; - } - - field = evsel->tp_format->format.fields; - if (field == NULL) { - printed += comma_fprintf(fp, &first, " (no trace field)"); - goto out; - } - - printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name); - - field = field->next; - while (field) { - printed += comma_fprintf(fp, &first, "%s", field->name); - field = field->next; - } - } -out: - fputc('\n', fp); - return ++printed; -} - bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize) { diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 501ea6e565f1..b993218744d4 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -178,8 +178,14 @@ void perf_evsel__init(struct perf_evsel *evsel, void perf_evsel__exit(struct perf_evsel *evsel); void perf_evsel__delete(struct perf_evsel *evsel); +struct callchain_param; + void perf_evsel__config(struct perf_evsel *evsel, - struct record_opts *opts); + struct record_opts *opts, + struct callchain_param *callchain); +void perf_evsel__config_callchain(struct perf_evsel *evsel, + struct record_opts *opts, + struct callchain_param *callchain); int __perf_evsel__sample_size(u64 sample_type); void perf_evsel__calc_id_pos(struct perf_evsel *evsel); @@ -381,6 +387,24 @@ struct perf_attr_details { int perf_evsel__fprintf(struct perf_evsel *evsel, struct perf_attr_details *details, FILE *fp); +#define EVSEL__PRINT_IP (1<<0) +#define EVSEL__PRINT_SYM (1<<1) +#define EVSEL__PRINT_DSO (1<<2) +#define EVSEL__PRINT_SYMOFFSET (1<<3) +#define EVSEL__PRINT_ONELINE (1<<4) +#define EVSEL__PRINT_SRCLINE (1<<5) +#define EVSEL__PRINT_UNKNOWN_AS_ADDR (1<<6) + +struct callchain_cursor; + +int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, + unsigned int print_opts, + struct callchain_cursor *cursor, FILE *fp); + +int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, + int left_alignment, unsigned int print_opts, + struct callchain_cursor *cursor, FILE *fp); + bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *msg, size_t msgsize); int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c new file mode 100644 index 000000000000..3674e77ad640 --- /dev/null +++ b/tools/perf/util/evsel_fprintf.c @@ -0,0 +1,212 @@ +#include <stdio.h> +#include <stdbool.h> +#include <traceevent/event-parse.h> +#include "evsel.h" +#include "callchain.h" +#include "map.h" +#include "symbol.h" + +static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) +{ + va_list args; + int ret = 0; + + if (!*first) { + ret += fprintf(fp, ","); + } else { + ret += fprintf(fp, ":"); + *first = false; + } + + va_start(args, fmt); + ret += vfprintf(fp, fmt, args); + va_end(args); + return ret; +} + +static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv) +{ + return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val); +} + +int perf_evsel__fprintf(struct perf_evsel *evsel, + struct perf_attr_details *details, FILE *fp) +{ + bool first = true; + int printed = 0; + + if (details->event_group) { + struct perf_evsel *pos; + + if (!perf_evsel__is_group_leader(evsel)) + return 0; + + if (evsel->nr_members > 1) + printed += fprintf(fp, "%s{", evsel->group_name ?: ""); + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + for_each_group_member(pos, evsel) + printed += fprintf(fp, ",%s", perf_evsel__name(pos)); + + if (evsel->nr_members > 1) + printed += fprintf(fp, "}"); + goto out; + } + + printed += fprintf(fp, "%s", perf_evsel__name(evsel)); + + if (details->verbose) { + printed += perf_event_attr__fprintf(fp, &evsel->attr, + __print_attr__fprintf, &first); + } else if (details->freq) { + const char *term = "sample_freq"; + + if (!evsel->attr.freq) + term = "sample_period"; + + printed += comma_fprintf(fp, &first, " %s=%" PRIu64, + term, (u64)evsel->attr.sample_freq); + } + + if (details->trace_fields) { + struct format_field *field; + + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + printed += comma_fprintf(fp, &first, " (not a tracepoint)"); + goto out; + } + + field = evsel->tp_format->format.fields; + if (field == NULL) { + printed += comma_fprintf(fp, &first, " (no trace field)"); + goto out; + } + + printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name); + + field = field->next; + while (field) { + printed += comma_fprintf(fp, &first, "%s", field->name); + field = field->next; + } + } +out: + fputc('\n', fp); + return ++printed; +} + +int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, + unsigned int print_opts, struct callchain_cursor *cursor, + FILE *fp) +{ + int printed = 0; + struct callchain_cursor_node *node; + int print_ip = print_opts & EVSEL__PRINT_IP; + int print_sym = print_opts & EVSEL__PRINT_SYM; + int print_dso = print_opts & EVSEL__PRINT_DSO; + int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET; + int print_oneline = print_opts & EVSEL__PRINT_ONELINE; + int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; + int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; + char s = print_oneline ? ' ' : '\t'; + + if (sample->callchain) { + struct addr_location node_al; + + callchain_cursor_commit(cursor); + + while (1) { + u64 addr = 0; + + node = callchain_cursor_current(cursor); + if (!node) + break; + + if (node->sym && node->sym->ignore) + goto next; + + printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); + + if (print_ip) + printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); + + if (node->map) + addr = node->map->map_ip(node->map, node->ip); + + if (print_sym) { + printed += fprintf(fp, " "); + node_al.addr = addr; + node_al.map = node->map; + + if (print_symoffset) { + printed += __symbol__fprintf_symname_offs(node->sym, &node_al, + print_unknown_as_addr, fp); + } else { + printed += __symbol__fprintf_symname(node->sym, &node_al, + print_unknown_as_addr, fp); + } + } + + if (print_dso) { + printed += fprintf(fp, " ("); + printed += map__fprintf_dsoname(node->map, fp); + printed += fprintf(fp, ")"); + } + + if (print_srcline) + printed += map__fprintf_srcline(node->map, addr, "\n ", fp); + + if (!print_oneline) + printed += fprintf(fp, "\n"); +next: + callchain_cursor_advance(cursor); + } + } + + return printed; +} + +int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al, + int left_alignment, unsigned int print_opts, + struct callchain_cursor *cursor, FILE *fp) +{ + int printed = 0; + int print_ip = print_opts & EVSEL__PRINT_IP; + int print_sym = print_opts & EVSEL__PRINT_SYM; + int print_dso = print_opts & EVSEL__PRINT_DSO; + int print_symoffset = print_opts & EVSEL__PRINT_SYMOFFSET; + int print_srcline = print_opts & EVSEL__PRINT_SRCLINE; + int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR; + + if (cursor != NULL) { + printed += sample__fprintf_callchain(sample, left_alignment, + print_opts, cursor, fp); + } else if (!(al->sym && al->sym->ignore)) { + printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " "); + + if (print_ip) + printed += fprintf(fp, "%16" PRIx64, sample->ip); + + if (print_sym) { + printed += fprintf(fp, " "); + if (print_symoffset) { + printed += __symbol__fprintf_symname_offs(al->sym, al, + print_unknown_as_addr, fp); + } else { + printed += __symbol__fprintf_symname(al->sym, al, + print_unknown_as_addr, fp); + } + } + + if (print_dso) { + printed += fprintf(fp, " ("); + printed += map__fprintf_dsoname(al->map, fp); + printed += fprintf(fp, ")"); + } + + if (print_srcline) + printed += map__fprintf_srcline(al->map, al->addr, "\n ", fp); + } + + return printed; +} diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 31c4641fe5ff..991a351a8a41 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -953,7 +953,7 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, { int err, err2; - err = sample__resolve_callchain(iter->sample, &iter->parent, + err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent, iter->evsel, al, max_stack_depth); if (err) return err; @@ -1295,8 +1295,9 @@ static int hists__hierarchy_insert_entry(struct hists *hists, return ret; } -int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root, - struct hist_entry *he) +static int hists__collapse_insert_entry(struct hists *hists, + struct rb_root *root, + struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index bec0cd660fbd..588596561cb3 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -199,8 +199,6 @@ int hists__init(void); int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list); struct rb_root *hists__get_rotate_entries_in(struct hists *hists); -int hists__collapse_insert_entry(struct hists *hists, - struct rb_root *root, struct hist_entry *he); struct perf_hpp { char *buf; diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index abf1366e2a24..9df996085563 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -66,6 +66,7 @@ struct intel_bts { u64 branches_id; size_t branches_event_size; bool synth_needs_swap; + unsigned long num_events; }; struct intel_bts_queue { @@ -275,6 +276,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq, union perf_event event; struct perf_sample sample = { .ip = 0, }; + if (bts->synth_opts.initial_skip && + bts->num_events++ <= bts->synth_opts.initial_skip) + return 0; + event.sample.header.type = PERF_RECORD_SAMPLE; event.sample.header.misc = PERF_RECORD_MISC_USER; event.sample.header.size = sizeof(struct perf_event_header); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 617578440989..137196990012 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -100,6 +100,8 @@ struct intel_pt { u64 cyc_bit; u64 noretcomp_bit; unsigned max_non_turbo_ratio; + + unsigned long num_events; }; enum switch_state { @@ -972,6 +974,10 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq) if (pt->branches_filter && !(pt->branches_filter & ptq->flags)) return 0; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1029,6 +1035,10 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq) union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1087,6 +1097,10 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq) union perf_event *event = ptq->event_buf; struct perf_sample sample = { .ip = 0, }; + if (pt->synth_opts.initial_skip && + pt->num_events++ < pt->synth_opts.initial_skip) + return 0; + event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = PERF_RECORD_MISC_USER; event->sample.header.size = sizeof(struct perf_event_header); @@ -1199,14 +1213,18 @@ static int intel_pt_sample(struct intel_pt_queue *ptq) ptq->have_sample = false; if (pt->sample_instructions && - (state->type & INTEL_PT_INSTRUCTION)) { + (state->type & INTEL_PT_INSTRUCTION) && + (!pt->synth_opts.initial_skip || + pt->num_events++ >= pt->synth_opts.initial_skip)) { err = intel_pt_synth_instruction_sample(ptq); if (err) return err; } if (pt->sample_transactions && - (state->type & INTEL_PT_TRANSACTION)) { + (state->type & INTEL_PT_TRANSACTION) && + (!pt->synth_opts.initial_skip || + pt->num_events++ >= pt->synth_opts.initial_skip)) { err = intel_pt_synth_transaction_sample(ptq); if (err) return err; diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index ad0c0bb1fbc7..52fcef3074fe 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -17,6 +17,7 @@ #include "strlist.h" #include <elf.h> +#include "tsc.h" #include "session.h" #include "jit.h" #include "jitdump.h" @@ -33,6 +34,7 @@ struct jit_buf_desc { size_t bufsize; FILE *in; bool needs_bswap; /* handles cross-endianess */ + bool use_arch_timestamp; void *debug_data; size_t nr_debug_entries; uint32_t code_load_count; @@ -158,13 +160,16 @@ jit_open(struct jit_buf_desc *jd, const char *name) header.flags = bswap_64(header.flags); } + jd->use_arch_timestamp = header.flags & JITDUMP_FLAGS_ARCH_TIMESTAMP; + if (verbose > 2) - pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n", + pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\nuse_arch_timestamp=%d\n", header.version, header.total_size, (unsigned long long)header.timestamp, header.pid, - header.elf_mach); + header.elf_mach, + jd->use_arch_timestamp); if (header.flags & JITDUMP_FLAGS_RESERVED) { pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n", @@ -172,10 +177,15 @@ jit_open(struct jit_buf_desc *jd, const char *name) goto error; } + if (jd->use_arch_timestamp && !jd->session->time_conv.time_mult) { + pr_err("jitdump file uses arch timestamps but there is no timestamp conversion\n"); + goto error; + } + /* * validate event is using the correct clockid */ - if (jit_validate_events(jd->session)) { + if (!jd->use_arch_timestamp && jit_validate_events(jd->session)) { pr_err("error, jitted code must be sampled with perf record -k 1\n"); goto error; } @@ -329,6 +339,23 @@ jit_inject_event(struct jit_buf_desc *jd, union perf_event *event) return 0; } +static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp) +{ + struct perf_tsc_conversion tc; + + if (!jd->use_arch_timestamp) + return timestamp; + + tc.time_shift = jd->session->time_conv.time_shift; + tc.time_mult = jd->session->time_conv.time_mult; + tc.time_zero = jd->session->time_conv.time_zero; + + if (!tc.time_mult) + return 0; + + return tsc_to_perf_time(timestamp, &tc); +} + static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) { struct perf_sample sample; @@ -410,7 +437,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) id->tid = tid; } if (jd->sample_type & PERF_SAMPLE_TIME) - id->time = jr->load.p.timestamp; + id->time = convert_timestamp(jd, jr->load.p.timestamp); /* * create pseudo sample to induce dso hit increment @@ -499,7 +526,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr) id->tid = tid; } if (jd->sample_type & PERF_SAMPLE_TIME) - id->time = jr->load.p.timestamp; + id->time = convert_timestamp(jd, jr->load.p.timestamp); /* * create pseudo sample to induce dso hit increment diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h index b66c1f503d9e..bcacd20d0c1c 100644 --- a/tools/perf/util/jitdump.h +++ b/tools/perf/util/jitdump.h @@ -23,9 +23,12 @@ #define JITHEADER_VERSION 1 enum jitdump_flags_bits { + JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT, JITDUMP_FLAGS_MAX_BIT, }; +#define JITDUMP_FLAGS_ARCH_TIMESTAMP (1ULL << JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT) + #define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \ (~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 80b9b6a87990..0c4dabc69932 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1599,6 +1599,7 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, } static int add_callchain_ip(struct thread *thread, + struct callchain_cursor *cursor, struct symbol **parent, struct addr_location *root_al, u8 *cpumode, @@ -1630,7 +1631,7 @@ static int add_callchain_ip(struct thread *thread, * It seems the callchain is corrupted. * Discard all. */ - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); return 1; } return 0; @@ -1648,13 +1649,13 @@ static int add_callchain_ip(struct thread *thread, /* Treat this symbol as the root, forgetting its callees. */ *root_al = al; - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); } } if (symbol_conf.hide_unresolved && al.sym == NULL) return 0; - return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); + return callchain_cursor_append(cursor, al.addr, al.map, al.sym); } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, @@ -1724,6 +1725,7 @@ static int remove_loops(struct branch_entry *l, int nr) * negative error code on other errors. */ static int resolve_lbr_callchain_sample(struct thread *thread, + struct callchain_cursor *cursor, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, @@ -1778,7 +1780,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, ip = lbr_stack->entries[0].to; } - err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; } @@ -1789,6 +1791,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread, } static int thread__resolve_callchain_sample(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, @@ -1803,10 +1806,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, int skip_idx = -1; int first_call = 0; - callchain_cursor_reset(&callchain_cursor); + callchain_cursor_reset(cursor); if (has_branch_callstack(evsel)) { - err = resolve_lbr_callchain_sample(thread, sample, parent, + err = resolve_lbr_callchain_sample(thread, cursor, sample, parent, root_al, max_stack); if (err) return (err < 0) ? err : 0; @@ -1863,10 +1866,10 @@ static int thread__resolve_callchain_sample(struct thread *thread, nr = remove_loops(be, nr); for (i = 0; i < nr; i++) { - err = add_callchain_ip(thread, parent, root_al, + err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].to); if (!err) - err = add_callchain_ip(thread, parent, root_al, + err = add_callchain_ip(thread, cursor, parent, root_al, NULL, be[i].from); if (err == -EINVAL) break; @@ -1896,7 +1899,7 @@ check_calls: #endif ip = chain->ips[j]; - err = add_callchain_ip(thread, parent, root_al, &cpumode, ip); + err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip); if (err) return (err < 0) ? err : 0; @@ -1916,13 +1919,14 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) } int thread__resolve_callchain(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, struct addr_location *root_al, int max_stack) { - int ret = thread__resolve_callchain_sample(thread, evsel, + int ret = thread__resolve_callchain_sample(thread, cursor, evsel, sample, parent, root_al, max_stack); if (ret) @@ -1938,7 +1942,7 @@ int thread__resolve_callchain(struct thread *thread, (!sample->user_stack.size)) return 0; - return unwind__get_entries(unwind_entry, &callchain_cursor, + return unwind__get_entries(unwind_entry, cursor, thread, sample, max_stack); } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 8499db281158..382873bdc563 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -141,7 +141,11 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample, struct addr_location *al); struct mem_info *sample__resolve_mem(struct perf_sample *sample, struct addr_location *al); + +struct callchain_cursor; + int thread__resolve_callchain(struct thread *thread, + struct callchain_cursor *cursor, struct perf_evsel *evsel, struct perf_sample *sample, struct symbol **parent, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 171b6d10a04b..02c31865648b 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -431,6 +431,13 @@ u64 map__rip_2objdump(struct map *map, u64 rip) if (map->dso->rel) return rip - map->pgoff; + /* + * kernel modules also have DSO_TYPE_USER in dso->kernel, + * but all kernel modules are ET_REL, so won't get here. + */ + if (map->dso->kernel == DSO_TYPE_USER) + return rip + map->dso->text_offset; + return map->unmap_ip(map, rip) - map->reloc; } @@ -454,6 +461,13 @@ u64 map__objdump_2mem(struct map *map, u64 ip) if (map->dso->rel) return map->unmap_ip(map, ip + map->pgoff); + /* + * kernel modules also have DSO_TYPE_USER in dso->kernel, + * but all kernel modules are ET_REL, so won't get here. + */ + if (map->dso->kernel == DSO_TYPE_USER) + return map->unmap_ip(map, ip - map->dso->text_offset); + return ip + map->reloc; } diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index b1b9e2385f4b..fe84df1875aa 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -308,3 +308,12 @@ void ordered_events__free(struct ordered_events *oe) free(event); } } + +void ordered_events__reinit(struct ordered_events *oe) +{ + ordered_events__deliver_t old_deliver = oe->deliver; + + ordered_events__free(oe); + memset(oe, '\0', sizeof(*oe)); + ordered_events__init(oe, old_deliver); +} diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h index f403991e3bfd..e11468a9a6e4 100644 --- a/tools/perf/util/ordered-events.h +++ b/tools/perf/util/ordered-events.h @@ -49,6 +49,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve int ordered_events__flush(struct ordered_events *oe, enum oe_flush how); void ordered_events__init(struct ordered_events *oe, ordered_events__deliver_t deliver); void ordered_events__free(struct ordered_events *oe); +void ordered_events__reinit(struct ordered_events *oe); static inline void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 4c19d5e79d8c..bcbc983d4b12 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -138,11 +138,11 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { #define PERF_EVENT_TYPE(config) __PERF_EVENT_FIELD(config, TYPE) #define PERF_EVENT_ID(config) __PERF_EVENT_FIELD(config, EVENT) -#define for_each_subsystem(sys_dir, sys_dirent, sys_next) \ - while (!readdir_r(sys_dir, &sys_dirent, &sys_next) && sys_next) \ - if (sys_dirent.d_type == DT_DIR && \ - (strcmp(sys_dirent.d_name, ".")) && \ - (strcmp(sys_dirent.d_name, ".."))) +#define for_each_subsystem(sys_dir, sys_dirent) \ + while ((sys_dirent = readdir(sys_dir)) != NULL) \ + if (sys_dirent->d_type == DT_DIR && \ + (strcmp(sys_dirent->d_name, ".")) && \ + (strcmp(sys_dirent->d_name, ".."))) static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) { @@ -159,12 +159,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) return 0; } -#define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) \ - while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next) \ - if (evt_dirent.d_type == DT_DIR && \ - (strcmp(evt_dirent.d_name, ".")) && \ - (strcmp(evt_dirent.d_name, "..")) && \ - (!tp_event_has_id(&sys_dirent, &evt_dirent))) +#define for_each_event(sys_dirent, evt_dir, evt_dirent) \ + while ((evt_dirent = readdir(evt_dir)) != NULL) \ + if (evt_dirent->d_type == DT_DIR && \ + (strcmp(evt_dirent->d_name, ".")) && \ + (strcmp(evt_dirent->d_name, "..")) && \ + (!tp_event_has_id(sys_dirent, evt_dirent))) #define MAX_EVENT_LENGTH 512 @@ -173,7 +173,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) { struct tracepoint_path *path = NULL; DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char id_buf[24]; int fd; u64 id; @@ -184,18 +184,18 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) if (!sys_dir) return NULL; - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, - evt_dirent.d_name); + evt_dirent->d_name); fd = open(evt_path, O_RDONLY); if (fd < 0) continue; @@ -220,9 +220,9 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) free(path); return NULL; } - strncpy(path->system, sys_dirent.d_name, + strncpy(path->system, sys_dirent->d_name, MAX_EVENT_LENGTH); - strncpy(path->name, evt_dirent.d_name, + strncpy(path->name, evt_dirent->d_name, MAX_EVENT_LENGTH); return path; } @@ -1812,7 +1812,7 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob, bool name_only) { DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; char **evt_list = NULL; @@ -1830,20 +1830,20 @@ restart: goto out_close_sys_dir; } - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { if (subsys_glob != NULL && - !strglobmatch(sys_dirent.d_name, subsys_glob)) + !strglobmatch(sys_dirent->d_name, subsys_glob)) continue; snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { if (event_glob != NULL && - !strglobmatch(evt_dirent.d_name, event_glob)) + !strglobmatch(evt_dirent->d_name, event_glob)) continue; if (!evt_num_known) { @@ -1852,7 +1852,7 @@ restart: } snprintf(evt_path, MAXPATHLEN, "%s:%s", - sys_dirent.d_name, evt_dirent.d_name); + sys_dirent->d_name, evt_dirent->d_name); evt_list[evt_i] = strdup(evt_path); if (evt_list[evt_i] == NULL) @@ -1905,7 +1905,7 @@ out_close_sys_dir: int is_valid_tracepoint(const char *event_string) { DIR *sys_dir, *evt_dir; - struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent; + struct dirent *sys_dirent, *evt_dirent; char evt_path[MAXPATHLEN]; char dir_path[MAXPATHLEN]; @@ -1913,17 +1913,17 @@ int is_valid_tracepoint(const char *event_string) if (!sys_dir) return 0; - for_each_subsystem(sys_dir, sys_dirent, sys_next) { + for_each_subsystem(sys_dir, sys_dirent) { snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path, - sys_dirent.d_name); + sys_dirent->d_name); evt_dir = opendir(dir_path); if (!evt_dir) continue; - for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) { + for_each_event(sys_dirent, evt_dir, evt_dirent) { snprintf(evt_path, MAXPATHLEN, "%s:%s", - sys_dirent.d_name, evt_dirent.d_name); + sys_dirent->d_name, evt_dirent->d_name); if (!strcmp(evt_path, event_string)) { closedir(evt_dir); closedir(sys_dir); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index adef23b1352e..bf34468a99cb 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -602,14 +602,13 @@ static void pmu_format_value(unsigned long *format, __u64 value, __u64 *v, static __u64 pmu_format_max_value(const unsigned long *format) { - int w; + __u64 w = 0; + int fbit; - w = bitmap_weight(format, PERF_PMU_FORMAT_BITS); - if (!w) - return 0; - if (w < 64) - return (1ULL << w) - 1; - return -1; + for_each_set_bit(fbit, format, PERF_PMU_FORMAT_BITS) + w |= (1ULL << fbit); + + return w; } /* diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 8162ba0e2e57..36c6862119e3 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -23,3 +23,4 @@ util/strlist.c util/trace-event.c ../lib/rbtree.c util/string.c +util/symbol_fprintf.c diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 0467367dc315..481792c7484b 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -129,7 +129,8 @@ bool perf_can_record_cpu_wide(void) return true; } -void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) +void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, + struct callchain_param *callchain) { struct perf_evsel *evsel; bool use_sample_identifier = false; @@ -148,7 +149,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts) use_comm_exec = perf_can_comm_exec(); evlist__for_each(evlist, evsel) { - perf_evsel__config(evsel, opts); + perf_evsel__config(evsel, opts, callchain); if (evsel->tracking && use_comm_exec) evsel->attr.comm_exec = 1; } diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index b3aabc0d4eb0..ae1cebc307c5 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -31,6 +31,8 @@ #include <perl.h> #include "../../perf.h" +#include "../callchain.h" +#include "../machine.h" #include "../thread.h" #include "../event.h" #include "../trace-event.h" @@ -248,10 +250,90 @@ static void define_event_symbols(struct event_format *event, define_event_symbols(event, ev_name, args->next); } +static SV *perl_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + AV *list; + + list = newAV(); + if (!list) + goto exit; + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { + pr_err("Failed to resolve callchain. Skipping\n"); + goto exit; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + HV *elem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + elem = newHV(); + if (!elem) + goto exit; + + if (!hv_stores(elem, "ip", newSVuv(node->ip))) { + hv_undef(elem); + goto exit; + } + + if (node->sym) { + HV *sym = newHV(); + if (!sym) { + hv_undef(elem); + goto exit; + } + if (!hv_stores(sym, "start", newSVuv(node->sym->start)) || + !hv_stores(sym, "end", newSVuv(node->sym->end)) || + !hv_stores(sym, "binding", newSVuv(node->sym->binding)) || + !hv_stores(sym, "name", newSVpvn(node->sym->name, + node->sym->namelen)) || + !hv_stores(elem, "sym", newRV_noinc((SV*)sym))) { + hv_undef(sym); + hv_undef(elem); + goto exit; + } + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { + hv_undef(elem); + goto exit; + } + } + + callchain_cursor_advance(&callchain_cursor); + av_push(list, newRV_noinc((SV*)elem)); + } + +exit: + return newRV_noinc((SV*)list); +} + static void perl_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, - struct thread *thread) + struct addr_location *al) { + struct thread *thread = al->thread; struct event_format *event = evsel->tp_format; struct format_field *field; static char handler[256]; @@ -295,6 +377,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, XPUSHs(sv_2mortal(newSVuv(ns))); XPUSHs(sv_2mortal(newSViv(pid))); XPUSHs(sv_2mortal(newSVpv(comm, 0))); + XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al))); /* common fields other than pid can be accessed via xsub fns */ @@ -329,6 +412,7 @@ static void perl_process_tracepoint(struct perf_sample *sample, XPUSHs(sv_2mortal(newSVuv(nsecs))); XPUSHs(sv_2mortal(newSViv(pid))); XPUSHs(sv_2mortal(newSVpv(comm, 0))); + XPUSHs(sv_2mortal(perl_process_callchain(sample, evsel, al))); call_pv("main::trace_unhandled", G_SCALAR); } SPAGAIN; @@ -366,7 +450,7 @@ static void perl_process_event(union perf_event *event, struct perf_evsel *evsel, struct addr_location *al) { - perl_process_tracepoint(sample, evsel, al->thread); + perl_process_tracepoint(sample, evsel, al); perl_process_event_generic(event, sample, evsel); } @@ -490,7 +574,27 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "use Perf::Trace::Util;\n\n"); fprintf(ofp, "sub trace_begin\n{\n\t# optional\n}\n\n"); - fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n\n"); + fprintf(ofp, "sub trace_end\n{\n\t# optional\n}\n"); + + + fprintf(ofp, "\n\ +sub print_backtrace\n\ +{\n\ + my $callchain = shift;\n\ + for my $node (@$callchain)\n\ + {\n\ + if(exists $node->{sym})\n\ + {\n\ + printf( \"\\t[\\%%x] \\%%s\\n\", $node->{ip}, $node->{sym}{name});\n\ + }\n\ + else\n\ + {\n\ + printf( \"\\t[\\%%x]\\n\", $node{ip});\n\ + }\n\ + }\n\ +}\n\n\ +"); + while ((event = trace_find_next_event(pevent, event))) { fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name); @@ -502,7 +606,8 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "$common_secs, "); fprintf(ofp, "$common_nsecs,\n"); fprintf(ofp, "\t $common_pid, "); - fprintf(ofp, "$common_comm,\n\t "); + fprintf(ofp, "$common_comm, "); + fprintf(ofp, "$common_callchain,\n\t "); not_first = 0; count = 0; @@ -519,7 +624,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "\tprint_header($event_name, $common_cpu, " "$common_secs, $common_nsecs,\n\t " - "$common_pid, $common_comm);\n\n"); + "$common_pid, $common_comm, $common_callchain);\n\n"); fprintf(ofp, "\tprintf(\""); @@ -581,17 +686,22 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "$%s", f->name); } - fprintf(ofp, ");\n"); + fprintf(ofp, ");\n\n"); + + fprintf(ofp, "\tprint_backtrace($common_callchain);\n"); + fprintf(ofp, "}\n\n"); } fprintf(ofp, "sub trace_unhandled\n{\n\tmy ($event_name, $context, " "$common_cpu, $common_secs, $common_nsecs,\n\t " - "$common_pid, $common_comm) = @_;\n\n"); + "$common_pid, $common_comm, $common_callchain) = @_;\n\n"); fprintf(ofp, "\tprint_header($event_name, $common_cpu, " "$common_secs, $common_nsecs,\n\t $common_pid, " - "$common_comm);\n}\n\n"); + "$common_comm, $common_callchain);\n"); + fprintf(ofp, "\tprint_backtrace($common_callchain);\n"); + fprintf(ofp, "}\n\n"); fprintf(ofp, "sub print_header\n{\n" "\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n" diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index fbd05242b4e5..525eb49e7ba6 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -323,7 +323,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (!symbol_conf.use_callchain || !sample->callchain) goto exit; - if (thread__resolve_callchain(al->thread, evsel, + if (thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, scripting_max_stack) != 0) { pr_err("Failed to resolve callchain. Skipping\n"); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 4abd85c6346d..ca1827c4af4a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -409,6 +409,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->stat = process_stat_stub; if (tool->stat_round == NULL) tool->stat_round = process_stat_round_stub; + if (tool->time_conv == NULL) + tool->time_conv = process_event_op2_stub; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -794,6 +796,7 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_STAT] = perf_event__stat_swap, [PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap, [PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap, + [PERF_RECORD_TIME_CONV] = perf_event__all64_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; @@ -1341,6 +1344,9 @@ static s64 perf_session__process_user_event(struct perf_session *session, return tool->stat(tool, event, session); case PERF_RECORD_STAT_ROUND: return tool->stat_round(tool, event, session); + case PERF_RECORD_TIME_CONV: + session->time_conv = event->time_conv; + return tool->time_conv(tool, event, session); default: return -EINVAL; } @@ -1830,7 +1836,11 @@ out: out_err: ui_progress__finish(); perf_session__warn_about_errors(session); - ordered_events__free(&session->ordered_events); + /* + * We may switching perf.data output, make ordered_events + * reusable. + */ + ordered_events__reinit(&session->ordered_events); auxtrace__free_events(session); session->one_mmap = false; return err; @@ -1947,105 +1957,6 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, return NULL; } -void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, - struct addr_location *al, - unsigned int print_opts, unsigned int stack_depth) -{ - struct callchain_cursor_node *node; - int print_ip = print_opts & PRINT_IP_OPT_IP; - int print_sym = print_opts & PRINT_IP_OPT_SYM; - int print_dso = print_opts & PRINT_IP_OPT_DSO; - int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET; - int print_oneline = print_opts & PRINT_IP_OPT_ONELINE; - int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE; - char s = print_oneline ? ' ' : '\t'; - - if (symbol_conf.use_callchain && sample->callchain) { - struct addr_location node_al; - - if (thread__resolve_callchain(al->thread, evsel, - sample, NULL, NULL, - stack_depth) != 0) { - if (verbose) - error("Failed to resolve callchain. Skipping\n"); - return; - } - callchain_cursor_commit(&callchain_cursor); - - if (print_symoffset) - node_al = *al; - - while (stack_depth) { - u64 addr = 0; - - node = callchain_cursor_current(&callchain_cursor); - if (!node) - break; - - if (node->sym && node->sym->ignore) - goto next; - - if (print_ip) - printf("%c%16" PRIx64, s, node->ip); - - if (node->map) - addr = node->map->map_ip(node->map, node->ip); - - if (print_sym) { - printf(" "); - if (print_symoffset) { - node_al.addr = addr; - node_al.map = node->map; - symbol__fprintf_symname_offs(node->sym, &node_al, stdout); - } else - symbol__fprintf_symname(node->sym, stdout); - } - - if (print_dso) { - printf(" ("); - map__fprintf_dsoname(node->map, stdout); - printf(")"); - } - - if (print_srcline) - map__fprintf_srcline(node->map, addr, "\n ", - stdout); - - if (!print_oneline) - printf("\n"); - - stack_depth--; -next: - callchain_cursor_advance(&callchain_cursor); - } - - } else { - if (al->sym && al->sym->ignore) - return; - - if (print_ip) - printf("%16" PRIx64, sample->ip); - - if (print_sym) { - printf(" "); - if (print_symoffset) - symbol__fprintf_symname_offs(al->sym, al, - stdout); - else - symbol__fprintf_symname(al->sym, stdout); - } - - if (print_dso) { - printf(" ("); - map__fprintf_dsoname(al->map, stdout); - printf(")"); - } - - if (print_srcline) - map__fprintf_srcline(al->map, al->addr, "\n ", stdout); - } -} - int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap) { diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 5f792e35d4c1..4bd758553450 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -26,6 +26,7 @@ struct perf_session { struct itrace_synth_opts *itrace_synth_opts; struct list_head auxtrace_index; struct trace_event tevent; + struct time_conv_event time_conv; bool repipe; bool one_mmap; void *one_mmap_addr; @@ -35,13 +36,6 @@ struct perf_session { struct perf_tool *tool; }; -#define PRINT_IP_OPT_IP (1<<0) -#define PRINT_IP_OPT_SYM (1<<1) -#define PRINT_IP_OPT_DSO (1<<2) -#define PRINT_IP_OPT_SYMOFFSET (1<<3) -#define PRINT_IP_OPT_ONELINE (1<<4) -#define PRINT_IP_OPT_SRCLINE (1<<5) - struct perf_tool; struct perf_session *perf_session__new(struct perf_data_file *file, @@ -103,10 +97,6 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp); struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session, unsigned int type); -void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample, - struct addr_location *al, - unsigned int print_opts, unsigned int stack_depth); - int perf_session__cpu_bitmap(struct perf_session *session, const char *cpu_list, unsigned long *cpu_bitmap); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index bc229a74c6a9..3f9d6798bd18 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -709,17 +709,10 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, if (ss->opdshdr.sh_type != SHT_PROGBITS) ss->opdsec = NULL; - if (dso->kernel == DSO_TYPE_USER) { - GElf_Shdr shdr; - ss->adjust_symbols = (ehdr.e_type == ET_EXEC || - ehdr.e_type == ET_REL || - dso__is_vdso(dso) || - elf_section_by_name(elf, &ehdr, &shdr, - ".gnu.prelink_undo", - NULL) != NULL); - } else { + if (dso->kernel == DSO_TYPE_USER) + ss->adjust_symbols = true; + else ss->adjust_symbols = elf__needs_adjust_symbols(ehdr); - } ss->name = strdup(name); if (!ss->name) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e7588dc91518..a36823c3b7c0 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -255,40 +255,6 @@ void symbol__delete(struct symbol *sym) free(((void *)sym) - symbol_conf.priv_size); } -size_t symbol__fprintf(struct symbol *sym, FILE *fp) -{ - return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n", - sym->start, sym->end, - sym->binding == STB_GLOBAL ? 'g' : - sym->binding == STB_LOCAL ? 'l' : 'w', - sym->name); -} - -size_t symbol__fprintf_symname_offs(const struct symbol *sym, - const struct addr_location *al, FILE *fp) -{ - unsigned long offset; - size_t length; - - if (sym && sym->name) { - length = fprintf(fp, "%s", sym->name); - if (al) { - if (al->addr < sym->end) - offset = al->addr - sym->start; - else - offset = al->addr - al->map->start - sym->start; - length += fprintf(fp, "+0x%lx", offset); - } - return length; - } else - return fprintf(fp, "[unknown]"); -} - -size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) -{ - return symbol__fprintf_symname_offs(sym, NULL, fp); -} - void symbols__delete(struct rb_root *symbols) { struct symbol *pos; @@ -364,11 +330,6 @@ static struct symbol *symbols__next(struct symbol *sym) return NULL; } -struct symbol_name_rb_node { - struct rb_node rb_node; - struct symbol sym; -}; - static void symbols__insert_by_name(struct rb_root *symbols, struct symbol *sym) { struct rb_node **p = &symbols->rb_node; @@ -497,21 +458,6 @@ void dso__sort_by_name(struct dso *dso, enum map_type type) &dso->symbols[type]); } -size_t dso__fprintf_symbols_by_name(struct dso *dso, - enum map_type type, FILE *fp) -{ - size_t ret = 0; - struct rb_node *nd; - struct symbol_name_rb_node *pos; - - for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { - pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); - fprintf(fp, "%s\n", pos->sym.name); - } - - return ret; -} - int modules__parse(const char *filename, void *arg, int (*process_module)(void *arg, const char *name, u64 start)) diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index c8b7544d9267..1da7b101bc7f 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -140,6 +140,11 @@ struct symbol_conf { extern struct symbol_conf symbol_conf; +struct symbol_name_rb_node { + struct rb_node rb_node; + struct symbol sym; +}; + static inline int __symbol__join_symfs(char *bf, size_t size, const char *path) { return path__join(bf, size, symbol_conf.symfs, path); @@ -262,8 +267,14 @@ int symbol__init(struct perf_env *env); void symbol__exit(void); void symbol__elf_init(void); struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name); +size_t __symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp); size_t symbol__fprintf_symname_offs(const struct symbol *sym, const struct addr_location *al, FILE *fp); +size_t __symbol__fprintf_symname(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp); size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp); size_t symbol__fprintf(struct symbol *sym, FILE *fp); bool symbol_type__is_a(char symbol_type, enum map_type map_type); diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c new file mode 100644 index 000000000000..a680bdaa65dc --- /dev/null +++ b/tools/perf/util/symbol_fprintf.c @@ -0,0 +1,71 @@ +#include <elf.h> +#include <inttypes.h> +#include <stdio.h> + +#include "symbol.h" + +size_t symbol__fprintf(struct symbol *sym, FILE *fp) +{ + return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %c %s\n", + sym->start, sym->end, + sym->binding == STB_GLOBAL ? 'g' : + sym->binding == STB_LOCAL ? 'l' : 'w', + sym->name); +} + +size_t __symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp) +{ + unsigned long offset; + size_t length; + + if (sym && sym->name) { + length = fprintf(fp, "%s", sym->name); + if (al) { + if (al->addr < sym->end) + offset = al->addr - sym->start; + else + offset = al->addr - al->map->start - sym->start; + length += fprintf(fp, "+0x%lx", offset); + } + return length; + } else if (al && unknown_as_addr) + return fprintf(fp, "[%#" PRIx64 "]", al->addr); + else + return fprintf(fp, "[unknown]"); +} + +size_t symbol__fprintf_symname_offs(const struct symbol *sym, + const struct addr_location *al, + FILE *fp) +{ + return __symbol__fprintf_symname_offs(sym, al, false, fp); +} + +size_t __symbol__fprintf_symname(const struct symbol *sym, + const struct addr_location *al, + bool unknown_as_addr, FILE *fp) +{ + return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, fp); +} + +size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp) +{ + return __symbol__fprintf_symname_offs(sym, NULL, false, fp); +} + +size_t dso__fprintf_symbols_by_name(struct dso *dso, + enum map_type type, FILE *fp) +{ + size_t ret = 0; + struct rb_node *nd; + struct symbol_name_rb_node *pos; + + for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) { + pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); + fprintf(fp, "%s\n", pos->sym.name); + } + + return ret; +} diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c new file mode 100644 index 000000000000..bbb4c1957578 --- /dev/null +++ b/tools/perf/util/syscalltbl.c @@ -0,0 +1,134 @@ +/* + * System call table mapper + * + * (C) 2016 Arnaldo Carvalho de Melo <[email protected]> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include "syscalltbl.h" +#include <stdlib.h> + +#ifdef HAVE_SYSCALL_TABLE +#include <linux/compiler.h> +#include <string.h> +#include "util.h" + +#if defined(__x86_64__) +#include <asm/syscalls_64.c> +const int syscalltbl_native_max_id = SYSCALLTBL_x86_64_MAX_ID; +static const char **syscalltbl_native = syscalltbl_x86_64; +#endif + +struct syscall { + int id; + const char *name; +}; + +static int syscallcmpname(const void *vkey, const void *ventry) +{ + const char *key = vkey; + const struct syscall *entry = ventry; + + return strcmp(key, entry->name); +} + +static int syscallcmp(const void *va, const void *vb) +{ + const struct syscall *a = va, *b = vb; + + return strcmp(a->name, b->name); +} + +static int syscalltbl__init_native(struct syscalltbl *tbl) +{ + int nr_entries = 0, i, j; + struct syscall *entries; + + for (i = 0; i <= syscalltbl_native_max_id; ++i) + if (syscalltbl_native[i]) + ++nr_entries; + + entries = tbl->syscalls.entries = malloc(sizeof(struct syscall) * nr_entries); + if (tbl->syscalls.entries == NULL) + return -1; + + for (i = 0, j = 0; i <= syscalltbl_native_max_id; ++i) { + if (syscalltbl_native[i]) { + entries[j].name = syscalltbl_native[i]; + entries[j].id = i; + ++j; + } + } + + qsort(tbl->syscalls.entries, nr_entries, sizeof(struct syscall), syscallcmp); + tbl->syscalls.nr_entries = nr_entries; + return 0; +} + +struct syscalltbl *syscalltbl__new(void) +{ + struct syscalltbl *tbl = malloc(sizeof(*tbl)); + if (tbl) { + if (syscalltbl__init_native(tbl)) { + free(tbl); + return NULL; + } + } + return tbl; +} + +void syscalltbl__delete(struct syscalltbl *tbl) +{ + zfree(&tbl->syscalls.entries); + free(tbl); +} + +const char *syscalltbl__name(const struct syscalltbl *tbl __maybe_unused, int id) +{ + return id <= syscalltbl_native_max_id ? syscalltbl_native[id]: NULL; +} + +int syscalltbl__id(struct syscalltbl *tbl, const char *name) +{ + struct syscall *sc = bsearch(name, tbl->syscalls.entries, + tbl->syscalls.nr_entries, sizeof(*sc), + syscallcmpname); + + return sc ? sc->id : -1; +} + +#else /* HAVE_SYSCALL_TABLE */ + +#include <libaudit.h> + +struct syscalltbl *syscalltbl__new(void) +{ + struct syscalltbl *tbl = malloc(sizeof(*tbl)); + if (tbl) + tbl->audit_machine = audit_detect_machine(); + return tbl; +} + +void syscalltbl__delete(struct syscalltbl *tbl) +{ + free(tbl); +} + +const char *syscalltbl__name(const struct syscalltbl *tbl, int id) +{ + return audit_syscall_to_name(id, tbl->audit_machine); +} + +int syscalltbl__id(struct syscalltbl *tbl, const char *name) +{ + return audit_name_to_syscall(name, tbl->audit_machine); +} +#endif /* HAVE_SYSCALL_TABLE */ diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h new file mode 100644 index 000000000000..e2951510484f --- /dev/null +++ b/tools/perf/util/syscalltbl.h @@ -0,0 +1,20 @@ +#ifndef __PERF_SYSCALLTBL_H +#define __PERF_SYSCALLTBL_H + +struct syscalltbl { + union { + int audit_machine; + struct { + int nr_entries; + void *entries; + } syscalls; + }; +}; + +struct syscalltbl *syscalltbl__new(void); +void syscalltbl__delete(struct syscalltbl *tbl); + +const char *syscalltbl__name(const struct syscalltbl *tbl, int id); +int syscalltbl__id(struct syscalltbl *tbl, const char *name); + +#endif /* __PERF_SYSCALLTBL_H */ diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index a0ac0317affb..e214207bb13a 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -9,6 +9,9 @@ #include "symbol.h" #include <strlist.h> #include <intlist.h> +#ifdef HAVE_LIBUNWIND_SUPPORT +#include <libunwind.h> +#endif struct thread_stack; @@ -32,6 +35,9 @@ struct thread { void *priv; struct thread_stack *ts; +#ifdef HAVE_LIBUNWIND_SUPPORT + unw_addr_space_t addr_space; +#endif }; struct machine; diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 08afc6909953..5654fe15e036 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -94,7 +94,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) DIR *proc; int max_threads = 32, items, i; char path[256]; - struct dirent dirent, *next, **namelist = NULL; + struct dirent *dirent, **namelist = NULL; struct thread_map *threads = thread_map__alloc(max_threads); if (threads == NULL) @@ -107,16 +107,16 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) threads->nr = 0; atomic_set(&threads->refcnt, 1); - while (!readdir_r(proc, &dirent, &next) && next) { + while ((dirent = readdir(proc)) != NULL) { char *end; bool grow = false; struct stat st; - pid_t pid = strtol(dirent.d_name, &end, 10); + pid_t pid = strtol(dirent->d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; - snprintf(path, sizeof(path), "/proc/%s", dirent.d_name); + snprintf(path, sizeof(path), "/proc/%s", dirent->d_name); if (stat(path, &st) != 0) continue; @@ -260,7 +260,7 @@ struct thread_map *thread_map__new_dummy(void) return threads; } -static struct thread_map *thread_map__new_by_tid_str(const char *tid_str) +struct thread_map *thread_map__new_by_tid_str(const char *tid_str) { struct thread_map *threads = NULL, *nt; int ntasks = 0; @@ -436,3 +436,15 @@ struct thread_map *thread_map__new_event(struct thread_map_event *event) return threads; } + +bool thread_map__has(struct thread_map *threads, pid_t pid) +{ + int i; + + for (i = 0; i < threads->nr; ++i) { + if (threads->map[i].pid == pid) + return true; + } + + return false; +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index 85e4c7c4fbde..bd3b971588da 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -31,6 +31,8 @@ void thread_map__put(struct thread_map *map); struct thread_map *thread_map__new_str(const char *pid, const char *tid, uid_t uid); +struct thread_map *thread_map__new_by_tid_str(const char *tid_str); + size_t thread_map__fprintf(struct thread_map *threads, FILE *fp); static inline int thread_map__nr(struct thread_map *threads) @@ -55,4 +57,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread) } void thread_map__read_comms(struct thread_map *threads); +bool thread_map__has(struct thread_map *threads, pid_t pid); #endif /* __PERF_THREAD_MAP_H */ diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 55de4cffcd4e..ac2590a3de2d 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -57,6 +57,7 @@ struct perf_tool { id_index, auxtrace_info, auxtrace_error, + time_conv, thread_map, cpu_map, stat_config, diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h index a8b78f1b3243..d5b11e2b85e0 100644 --- a/tools/perf/util/tsc.h +++ b/tools/perf/util/tsc.h @@ -3,10 +3,29 @@ #include <linux/types.h> -#include "../arch/x86/util/tsc.h" +#include "event.h" + +struct perf_tsc_conversion { + u16 time_shift; + u32 time_mult; + u64 time_zero; +}; +struct perf_event_mmap_page; + +int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, + struct perf_tsc_conversion *tc); u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc); u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc); u64 rdtsc(void); +struct perf_event_mmap_page; +struct perf_tool; +struct machine; + +int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, + struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine); + #endif diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index ee7e372297e5..63687d3a344e 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -32,6 +32,7 @@ #include "symbol.h" #include "util.h" #include "debug.h" +#include "asm/bug.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -580,43 +581,33 @@ static unw_accessors_t accessors = { int unwind__prepare_access(struct thread *thread) { - unw_addr_space_t addr_space; - if (callchain_param.record_mode != CALLCHAIN_DWARF) return 0; - addr_space = unw_create_addr_space(&accessors, 0); - if (!addr_space) { + thread->addr_space = unw_create_addr_space(&accessors, 0); + if (!thread->addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; } - unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL); - thread__set_priv(thread, addr_space); - + unw_set_caching_policy(thread->addr_space, UNW_CACHE_GLOBAL); return 0; } void unwind__flush_access(struct thread *thread) { - unw_addr_space_t addr_space; - if (callchain_param.record_mode != CALLCHAIN_DWARF) return; - addr_space = thread__priv(thread); - unw_flush_cache(addr_space, 0, 0); + unw_flush_cache(thread->addr_space, 0, 0); } void unwind__finish_access(struct thread *thread) { - unw_addr_space_t addr_space; - if (callchain_param.record_mode != CALLCHAIN_DWARF) return; - addr_space = thread__priv(thread); - unw_destroy_addr_space(addr_space); + unw_destroy_addr_space(thread->addr_space); } static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, @@ -639,7 +630,9 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, * unwind itself. */ if (max_stack - 1 > 0) { - addr_space = thread__priv(ui->thread); + WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); + addr_space = ui->thread->addr_space; + if (addr_space == NULL) return -1; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 8298d607c738..3bf3de86d429 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -254,6 +254,11 @@ int hex2u64(const char *ptr, u64 *val); char *ltrim(char *s); char *rtrim(char *s); +static inline char *trim(char *s) +{ + return ltrim(rtrim(s)); +} + void dump_stack(void); void sighandler_dump_stack(int sig); |