- panic_on_warn
- perf_cpu_time_max_percent
- perf_event_paranoid
+- perf_event_max_stack
- pid_max
- powersave-nap [ PPC only ]
- printk
==============================================================
+perf_event_max_stack:
+
+Controls maximum number of stack frames to copy for (attr.sample_type &
+PERF_SAMPLE_CALLCHAIN) configured events, for instance, when using
+'perf record -g' or 'perf trace --call-graph fp'.
+
+This can only be done when no events are in use that have callchains
+enabled, otherwise writing to this file will return -EBUSY.
+
+The default value is 127.
+
+==============================================================
+
pid_max:
PID allocation wrap value. When the kernel's next PID value
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.
* 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:
tail = (struct frame_tail __user *)regs->ARM_fp - 1;
- while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+ while ((entry->nr < sysctl_perf_event_max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = user_backtrace(tail, entry);
}
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();
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:
tail = (struct frame_tail __user *)regs->regs[29];
- while (entry->nr < PERF_MAX_STACK_DEPTH &&
+ while (entry->nr < sysctl_perf_event_max_stack &&
tail && !((unsigned long)tail & 0xf))
tail = user_backtrace(tail, entry);
} else {
tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
- while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+ while ((entry->nr < sysctl_perf_event_max_stack) &&
tail && !((unsigned long)tail & 0x3))
tail = compat_user_backtrace(tail, entry);
#endif
--frame;
- while ((entry->nr < PERF_MAX_STACK_DEPTH) && frame)
+ while ((entry->nr < sysctl_perf_event_max_stack) && frame)
frame = user_backtrace(frame, entry);
}
addr = *sp++;
if (__kernel_text_address(addr)) {
perf_callchain_store(entry, addr);
- if (entry->nr >= PERF_MAX_STACK_DEPTH)
+ if (entry->nr >= sysctl_perf_event_max_stack)
break;
}
}
}
do {
perf_callchain_store(entry, pc);
- if (entry->nr >= PERF_MAX_STACK_DEPTH)
+ if (entry->nr >= sysctl_perf_event_max_stack)
break;
pc = unwind_stack(current, &sp, pc, &ra);
} while (pc);
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
- while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ while (entry->nr < sysctl_perf_event_max_stack) {
fp = (unsigned long __user *) sp;
if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
return;
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
- while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ while (entry->nr < sysctl_perf_event_max_stack) {
fp = (unsigned int __user *) (unsigned long) sp;
if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
return;
}
}
#endif
- } while (entry->nr < PERF_MAX_STACK_DEPTH);
+ } while (entry->nr < sysctl_perf_event_max_stack);
}
static inline int
pc = sf.callers_pc;
ufp = (unsigned long)sf.fp + STACK_BIAS;
perf_callchain_store(entry, pc);
- } while (entry->nr < PERF_MAX_STACK_DEPTH);
+ } while (entry->nr < sysctl_perf_event_max_stack);
}
static void perf_callchain_user_32(struct perf_callchain_entry *entry,
ufp = (unsigned long)sf.fp;
}
perf_callchain_store(entry, pc);
- } while (entry->nr < PERF_MAX_STACK_DEPTH);
+ } while (entry->nr < sysctl_perf_event_max_stack);
}
void
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
def_bool y
depends on X86_MCE_INTEL
+source "arch/x86/events/Kconfig"
+
config X86_LEGACY_VM86
bool "Legacy VM86 support"
default n
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---
--- /dev/null
+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
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-$(CONFIG_CPU_SUP_INTEL) += intel/
};
static struct pmu amd_nb_pmu = {
+ .task_ctx_nr = perf_invalid_context,
.attr_groups = amd_uncore_attr_groups,
.name = "amd_nb",
.event_init = amd_uncore_event_init,
};
static struct pmu amd_l2_pmu = {
+ .task_ctx_nr = perf_invalid_context,
.attr_groups = amd_uncore_attr_groups,
.name = "amd_l2",
.event_init = amd_uncore_event_init,
{
int i;
+ if (x86_pmu.lbr_pt_coexist)
+ return 0;
+
if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) {
mutex_lock(&pmc_reserve_mutex);
for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) {
void x86_del_exclusive(unsigned int what)
{
+ if (x86_pmu.lbr_pt_coexist)
+ return;
+
atomic_dec(&x86_pmu.lbr_exclusive[what]);
atomic_dec(&active_events);
}
fp = compat_ptr(ss_base + regs->bp);
pagefault_disable();
- while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ while (entry->nr < sysctl_perf_event_max_stack) {
unsigned long bytes;
frame.next_frame = 0;
frame.return_address = 0;
return;
pagefault_disable();
- while (entry->nr < PERF_MAX_STACK_DEPTH) {
+ while (entry->nr < sysctl_perf_event_max_stack) {
unsigned long bytes;
frame.next_frame = NULL;
frame.return_address = 0;
--- /dev/null
+obj-$(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
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();
}
}
+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)
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)
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)
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;
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;
},
};
+static struct extra_reg intel_glm_extra_regs[] __read_mostly = {
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x360005ffbfull, RSP_1),
+ EVENT_EXTRA_END
+};
+
+#define GLM_DEMAND_DATA_RD BIT_ULL(0)
+#define GLM_DEMAND_RFO BIT_ULL(1)
+#define GLM_ANY_RESPONSE BIT_ULL(16)
+#define GLM_SNP_NONE_OR_MISS BIT_ULL(33)
+#define GLM_DEMAND_READ GLM_DEMAND_DATA_RD
+#define GLM_DEMAND_WRITE GLM_DEMAND_RFO
+#define GLM_DEMAND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO)
+#define GLM_LLC_ACCESS GLM_ANY_RESPONSE
+#define GLM_SNP_ANY (GLM_SNP_NONE_OR_MISS|SNB_NO_FWD|SNB_HITM)
+#define GLM_LLC_MISS (GLM_SNP_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 glm_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
+ [C(RESULT_MISS)] = 0x0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
+ [C(RESULT_MISS)] = 0x0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x0,
+ [C(RESULT_MISS)] = 0x0,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x0380, /* ICACHE.ACCESSES */
+ [C(RESULT_MISS)] = 0x0280, /* ICACHE.MISSES */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x0,
+ [C(RESULT_MISS)] = 0x0,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */
+ [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */
+ [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */
+ [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */
+ [C(RESULT_MISS)] = 0x0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */
+ [C(RESULT_MISS)] = 0x0,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = 0x0,
+ [C(RESULT_MISS)] = 0x0,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */
+ [C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [C(RESULT_MISS)] = 0x00c5, /* BR_MISP_RETIRED.ALL_BRANCHES */
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+};
+
+static __initconst const u64 glm_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = GLM_DEMAND_READ|
+ GLM_LLC_ACCESS,
+ [C(RESULT_MISS)] = GLM_DEMAND_READ|
+ GLM_LLC_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = GLM_DEMAND_WRITE|
+ GLM_LLC_ACCESS,
+ [C(RESULT_MISS)] = GLM_DEMAND_WRITE|
+ GLM_LLC_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = GLM_DEMAND_PREFETCH|
+ GLM_LLC_ACCESS,
+ [C(RESULT_MISS)] = GLM_DEMAND_PREFETCH|
+ GLM_LLC_MISS,
+ },
+ },
+};
+
#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
#define KNL_MCDRAM_LOCAL BIT_ULL(21)
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
sizeof(hw_cache_extra_regs));
- intel_pmu_lbr_init_atom();
+ intel_pmu_lbr_init_slm();
x86_pmu.event_constraints = intel_slm_event_constraints;
x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
pr_cont("Silvermont events, ");
break;
+ case 92: /* 14nm Atom "Goldmont" */
+ case 95: /* 14nm Atom "Goldmont Denverton" */
+ memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.pebs_constraints = intel_glm_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_glm_extra_regs;
+ /*
+ * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+ * for precise cycles.
+ * :pp is identical to :ppp
+ */
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ pr_cont("Goldmont events, ");
+ break;
+
case 37: /* 32nm Westmere */
case 44: /* 32nm Westmere-EP */
case 47: /* 32nm Westmere-EX */
#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, \
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,
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] = {
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,
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");
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] = {
NULL,
};
-/* cstate_pkg PMU end*/
-
static ssize_t cstate_get_attr_cpumask(struct device *dev,
struct device_attribute *attr,
char *buf)
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;
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)
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,
.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);
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_glm_pebs_event_constraints[] = {
+ /* Allow all events as PEBS with no flags */
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
LBR_FORMAT_EIP_FLAGS = 0x03,
LBR_FORMAT_EIP_FLAGS2 = 0x04,
LBR_FORMAT_INFO = 0x05,
- LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO,
+ LBR_FORMAT_TIME = 0x06,
+ LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME,
};
static enum {
abort = !!(info & LBR_INFO_ABORT);
cycles = (info & LBR_INFO_CYCLES);
}
+
+ if (lbr_format == LBR_FORMAT_TIME) {
+ mis = !!(from & LBR_FROM_FLAG_MISPRED);
+ pred = !mis;
+ skip = 1;
+ cycles = ((to >> 48) & LBR_INFO_CYCLES);
+
+ to = (u64)((((s64)to) << 16) >> 16);
+ }
+
if (lbr_flags & LBR_EIP_FLAGS) {
mis = !!(from & LBR_FROM_FLAG_MISPRED);
pred = !mis;
pr_cont("8-deep LBR, ");
}
+/* slm */
+void __init intel_pmu_lbr_init_slm(void)
+{
+ x86_pmu.lbr_nr = 8;
+ x86_pmu.lbr_tos = MSR_LBR_TOS;
+ x86_pmu.lbr_from = MSR_LBR_CORE_FROM;
+ x86_pmu.lbr_to = MSR_LBR_CORE_TO;
+
+ x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+ x86_pmu.lbr_sel_map = nhm_lbr_sel_map;
+
+ /*
+ * SW branch filter usage:
+ * - compensate for lack of HW filter
+ */
+ pr_cont("8-deep LBR, ");
+}
+
/* Knights Landing */
void intel_pmu_lbr_init_knl(void)
{
PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff),
PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)),
PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)),
+ PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)),
PT_CAP(mtc, 0, CR_EBX, BIT(3)),
PT_CAP(topa_output, 0, CR_ECX, BIT(0)),
PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)),
PT_CAP(single_range_output, 0, CR_ECX, BIT(2)),
PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)),
+ PT_CAP(num_address_ranges, 1, CR_EAX, 0x3),
PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000),
PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff),
PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000),
.attrs = pt_formats_attr,
};
+static ssize_t
+pt_timing_attr_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr =
+ container_of(attr, struct perf_pmu_events_attr, attr);
+
+ switch (pmu_attr->id) {
+ case 0:
+ return sprintf(page, "%lu\n", pt_pmu.max_nonturbo_ratio);
+ case 1:
+ return sprintf(page, "%u:%u\n",
+ pt_pmu.tsc_art_num,
+ pt_pmu.tsc_art_den);
+ default:
+ break;
+ }
+
+ return -EINVAL;
+}
+
+PMU_EVENT_ATTR(max_nonturbo_ratio, timing_attr_max_nonturbo_ratio, 0,
+ pt_timing_attr_show);
+PMU_EVENT_ATTR(tsc_art_ratio, timing_attr_tsc_art_ratio, 1,
+ pt_timing_attr_show);
+
+static struct attribute *pt_timing_attr[] = {
+ &timing_attr_max_nonturbo_ratio.attr.attr,
+ &timing_attr_tsc_art_ratio.attr.attr,
+ NULL,
+};
+
+static struct attribute_group pt_timing_group = {
+ .attrs = pt_timing_attr,
+};
+
static const struct attribute_group *pt_attr_groups[] = {
&pt_cap_group,
&pt_format_group,
+ &pt_timing_group,
NULL,
};
int ret;
long i;
+ rdmsrl(MSR_PLATFORM_INFO, reg);
+ pt_pmu.max_nonturbo_ratio = (reg & 0xff00) >> 8;
+
+ /*
+ * if available, read in TSC to core crystal clock ratio,
+ * otherwise, zero for numerator stands for "not enumerated"
+ * as per SDM
+ */
+ if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) {
+ u32 eax, ebx, ecx, edx;
+
+ cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx);
+
+ pt_pmu.tsc_art_num = ebx;
+ pt_pmu.tsc_art_den = eax;
+ }
+
if (boot_cpu_has(X86_FEATURE_VMX)) {
/*
* Intel SDM, 36.5 "Tracing post-VMXON" says that
* These all are cpu affine and operate on a local PT
*/
+/* Address ranges and their corresponding msr configuration registers */
+static const struct pt_address_range {
+ unsigned long msr_a;
+ unsigned long msr_b;
+ unsigned int reg_off;
+} pt_address_ranges[] = {
+ {
+ .msr_a = MSR_IA32_RTIT_ADDR0_A,
+ .msr_b = MSR_IA32_RTIT_ADDR0_B,
+ .reg_off = RTIT_CTL_ADDR0_OFFSET,
+ },
+ {
+ .msr_a = MSR_IA32_RTIT_ADDR1_A,
+ .msr_b = MSR_IA32_RTIT_ADDR1_B,
+ .reg_off = RTIT_CTL_ADDR1_OFFSET,
+ },
+ {
+ .msr_a = MSR_IA32_RTIT_ADDR2_A,
+ .msr_b = MSR_IA32_RTIT_ADDR2_B,
+ .reg_off = RTIT_CTL_ADDR2_OFFSET,
+ },
+ {
+ .msr_a = MSR_IA32_RTIT_ADDR3_A,
+ .msr_b = MSR_IA32_RTIT_ADDR3_B,
+ .reg_off = RTIT_CTL_ADDR3_OFFSET,
+ }
+};
+
+static u64 pt_config_filters(struct perf_event *event)
+{
+ struct pt_filters *filters = event->hw.addr_filters;
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+ unsigned int range = 0;
+ u64 rtit_ctl = 0;
+
+ if (!filters)
+ return 0;
+
+ perf_event_addr_filters_sync(event);
+
+ for (range = 0; range < filters->nr_filters; range++) {
+ struct pt_filter *filter = &filters->filter[range];
+
+ /*
+ * Note, if the range has zero start/end addresses due
+ * to its dynamic object not being loaded yet, we just
+ * go ahead and program zeroed range, which will simply
+ * produce no data. Note^2: if executable code at 0x0
+ * is a concern, we can set up an "invalid" configuration
+ * such as msr_b < msr_a.
+ */
+
+ /* avoid redundant msr writes */
+ if (pt->filters.filter[range].msr_a != filter->msr_a) {
+ wrmsrl(pt_address_ranges[range].msr_a, filter->msr_a);
+ pt->filters.filter[range].msr_a = filter->msr_a;
+ }
+
+ if (pt->filters.filter[range].msr_b != filter->msr_b) {
+ wrmsrl(pt_address_ranges[range].msr_b, filter->msr_b);
+ pt->filters.filter[range].msr_b = filter->msr_b;
+ }
+
+ rtit_ctl |= filter->config << pt_address_ranges[range].reg_off;
+ }
+
+ return rtit_ctl;
+}
+
static void pt_config(struct perf_event *event)
{
u64 reg;
wrmsrl(MSR_IA32_RTIT_STATUS, 0);
}
- reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
+ reg = pt_config_filters(event);
+ reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
if (!event->attr.exclude_kernel)
reg |= RTIT_CTL_OS;
kfree(buf);
}
-/**
- * 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)
+static int pt_addr_filters_init(struct perf_event *event)
{
- if (buf->snapshot)
- return false;
+ struct pt_filters *filters;
+ int node = event->cpu == -1 ? -1 : cpu_to_node(event->cpu);
+
+ if (!pt_cap_get(PT_CAP_num_address_ranges))
+ return 0;
+
+ filters = kzalloc_node(sizeof(struct pt_filters), GFP_KERNEL, node);
+ if (!filters)
+ return -ENOMEM;
+
+ if (event->parent)
+ memcpy(filters, event->parent->hw.addr_filters,
+ sizeof(*filters));
+
+ event->hw.addr_filters = filters;
+
+ return 0;
+}
+
+static void pt_addr_filters_fini(struct perf_event *event)
+{
+ kfree(event->hw.addr_filters);
+ event->hw.addr_filters = NULL;
+}
+
+static int pt_event_addr_filters_validate(struct list_head *filters)
+{
+ struct perf_addr_filter *filter;
+ int range = 0;
+
+ list_for_each_entry(filter, filters, entry) {
+ /* PT doesn't support single address triggers */
+ if (!filter->range)
+ return -EOPNOTSUPP;
+
+ if (!filter->inode && !kernel_ip(filter->offset))
+ return -EINVAL;
+
+ if (++range > pt_cap_get(PT_CAP_num_address_ranges))
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static void pt_event_addr_filters_sync(struct perf_event *event)
+{
+ struct perf_addr_filters_head *head = perf_event_addr_filters(event);
+ unsigned long msr_a, msr_b, *offs = event->addr_filters_offs;
+ struct pt_filters *filters = event->hw.addr_filters;
+ struct perf_addr_filter *filter;
+ int range = 0;
+
+ if (!filters)
+ return;
- if (local_read(&buf->data_size) >= pt->handle.size)
- return true;
+ list_for_each_entry(filter, &head->list, entry) {
+ if (filter->inode && !offs[range]) {
+ msr_a = msr_b = 0;
+ } else {
+ /* apply the offset */
+ msr_a = filter->offset + offs[range];
+ msr_b = filter->size + msr_a;
+ }
+
+ filters->filter[range].msr_a = msr_a;
+ filters->filter[range].msr_b = msr_b;
+ filters->filter[range].config = filter->filter ? 1 : 2;
+ range++;
+ }
- return false;
+ filters->nr_filters = range;
}
/**
* after PT has been disabled by pt_event_stop(). Make sure we don't
* do anything (particularly, re-enable) for this event here.
*/
- if (!ACCESS_ONCE(pt->handle_nmi))
+ if (!READ_ONCE(pt->handle_nmi))
return;
/*
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 (READ_ONCE(pt->vmx_on))
return;
- 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;
+ WRITE_ONCE(pt->handle_nmi, 1);
+ 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)
* Protect against the PMI racing with disabling wrmsr,
* see comment in intel_pt_interrupt().
*/
- ACCESS_ONCE(pt->handle_nmi) = 0;
+ WRITE_ONCE(pt->handle_nmi, 0);
pt_config_stop(event);
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,
}
}
+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;
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;
}
static void pt_event_destroy(struct perf_event *event)
{
+ pt_addr_filters_fini(event);
x86_del_exclusive(x86_lbr_exclusive_pt);
}
if (x86_add_exclusive(x86_lbr_exclusive_pt))
return -EBUSY;
+ if (pt_addr_filters_init(event)) {
+ x86_del_exclusive(x86_lbr_exclusive_pt);
+ return -ENOMEM;
+ }
+
event->destroy = pt_event_destroy;
return 0;
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();
PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
- pt_pmu.pmu.attr_groups = pt_attr_groups;
- pt_pmu.pmu.task_ctx_nr = perf_sw_context;
- pt_pmu.pmu.event_init = pt_event_init;
- pt_pmu.pmu.add = pt_event_add;
- pt_pmu.pmu.del = pt_event_del;
- pt_pmu.pmu.start = pt_event_start;
- pt_pmu.pmu.stop = pt_event_stop;
- pt_pmu.pmu.read = pt_event_read;
- pt_pmu.pmu.setup_aux = pt_buffer_setup_aux;
- pt_pmu.pmu.free_aux = pt_buffer_free_aux;
+ pt_pmu.pmu.attr_groups = pt_attr_groups;
+ pt_pmu.pmu.task_ctx_nr = perf_sw_context;
+ pt_pmu.pmu.event_init = pt_event_init;
+ pt_pmu.pmu.add = pt_event_add;
+ pt_pmu.pmu.del = pt_event_del;
+ pt_pmu.pmu.start = pt_event_start;
+ pt_pmu.pmu.stop = pt_event_stop;
+ pt_pmu.pmu.read = pt_event_read;
+ pt_pmu.pmu.setup_aux = pt_buffer_setup_aux;
+ pt_pmu.pmu.free_aux = pt_buffer_free_aux;
+ pt_pmu.pmu.addr_filters_sync = pt_event_addr_filters_sync;
+ pt_pmu.pmu.addr_filters_validate = pt_event_addr_filters_validate;
+ pt_pmu.pmu.nr_addr_filters =
+ pt_cap_get(PT_CAP_num_address_ranges);
+
ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1);
return ret;
#ifndef __INTEL_PT_H__
#define __INTEL_PT_H__
+/*
+ * PT MSR bit definitions
+ */
+#define RTIT_CTL_TRACEEN BIT(0)
+#define RTIT_CTL_CYCLEACC BIT(1)
+#define RTIT_CTL_OS BIT(2)
+#define RTIT_CTL_USR BIT(3)
+#define RTIT_CTL_CR3EN BIT(7)
+#define RTIT_CTL_TOPA BIT(8)
+#define RTIT_CTL_MTC_EN BIT(9)
+#define RTIT_CTL_TSC_EN BIT(10)
+#define RTIT_CTL_DISRETC BIT(11)
+#define RTIT_CTL_BRANCH_EN BIT(13)
+#define RTIT_CTL_MTC_RANGE_OFFSET 14
+#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
+#define RTIT_CTL_CYC_THRESH_OFFSET 19
+#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
+#define RTIT_CTL_PSB_FREQ_OFFSET 24
+#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
+#define RTIT_CTL_ADDR0_OFFSET 32
+#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET)
+#define RTIT_CTL_ADDR1_OFFSET 36
+#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET)
+#define RTIT_CTL_ADDR2_OFFSET 40
+#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET)
+#define RTIT_CTL_ADDR3_OFFSET 44
+#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET)
+#define RTIT_STATUS_FILTEREN BIT(0)
+#define RTIT_STATUS_CONTEXTEN BIT(1)
+#define RTIT_STATUS_TRIGGEREN BIT(2)
+#define RTIT_STATUS_BUFFOVF BIT(3)
+#define RTIT_STATUS_ERROR BIT(4)
+#define RTIT_STATUS_STOPPED BIT(5)
+
/*
* Single-entry ToPA: when this close to region boundary, switch
* buffers to avoid losing data.
#define PT_CPUID_LEAVES 2
#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */
+/* TSC to Core Crystal Clock Ratio */
+#define CPUID_TSC_LEAF 0x15
+
enum pt_capabilities {
PT_CAP_max_subleaf = 0,
PT_CAP_cr3_filtering,
PT_CAP_psb_cyc,
+ PT_CAP_ip_filtering,
PT_CAP_mtc,
PT_CAP_topa_output,
PT_CAP_topa_multiple_entries,
PT_CAP_single_range_output,
PT_CAP_payloads_lip,
+ PT_CAP_num_address_ranges,
PT_CAP_mtc_periods,
PT_CAP_cycle_thresholds,
PT_CAP_psb_periods,
struct pmu pmu;
u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
bool vmx;
+ unsigned long max_nonturbo_ratio;
+ unsigned int tsc_art_num;
+ unsigned int tsc_art_den;
};
/**
struct topa_entry *topa_index[0];
};
+#define PT_FILTERS_NUM 4
+
+/**
+ * struct pt_filter - IP range filter configuration
+ * @msr_a: range start, goes to RTIT_ADDRn_A
+ * @msr_b: range end, goes to RTIT_ADDRn_B
+ * @config: 4-bit field in RTIT_CTL
+ */
+struct pt_filter {
+ unsigned long msr_a;
+ unsigned long msr_b;
+ unsigned long config;
+};
+
+/**
+ * struct pt_filters - IP range filtering context
+ * @filter: filters defined for this context
+ * @nr_filters: number of defined filters in the @filter array
+ */
+struct pt_filters {
+ struct pt_filter filter[PT_FILTERS_NUM];
+ unsigned int nr_filters;
+};
+
/**
* struct pt - per-cpu pt context
* @handle: perf output handle
+ * @filters: last configured filters
* @handle_nmi: do handle PT PMI on this cpu, there's an active event
* @vmx_on: 1 if VMX is ON on this cpu
*/
struct pt {
struct perf_output_handle handle;
+ struct pt_filters filters;
int handle_nmi;
int vmx_on;
};
* event: rapl_energy_dram
* perf code: 0x3
*
- * dram counter: consumption of the builtin-gpu domain (client only)
+ * gpu counter: consumption of the builtin-gpu domain (client only)
* event: rapl_energy_gpu
* perf code: 0x4
*
+ * psys counter: consumption of the builtin-psys domain (client only)
+ * event: rapl_energy_psys
+ * perf code: 0x5
+ *
* We manage those counters as free running (read-only). They may be
* use simultaneously by other tools, such as turbostat.
*
#include <asm/cpu_device_id.h>
#include "../perf_event.h"
+MODULE_LICENSE("GPL");
+
/*
* RAPL energy status counters
*/
#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
+#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */
+#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */
-#define NR_RAPL_DOMAINS 0x4
+#define NR_RAPL_DOMAINS 0x5
static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
"pp0-core",
"package",
"dram",
"pp1-gpu",
+ "psys",
};
/* Clients have PP0, PKG */
1<<RAPL_IDX_RAM_NRG_STAT|\
1<<RAPL_IDX_PP1_NRG_STAT)
+/* SKL clients have PP0, PKG, RAM, PP1, PSYS */
+#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
+ 1<<RAPL_IDX_PKG_NRG_STAT|\
+ 1<<RAPL_IDX_RAM_NRG_STAT|\
+ 1<<RAPL_IDX_PP1_NRG_STAT|\
+ 1<<RAPL_IDX_PSYS_NRG_STAT)
+
/* Knights Landing has PKG, RAM */
#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT)
bit = RAPL_IDX_PP1_NRG_STAT;
msr = MSR_PP1_ENERGY_STATUS;
break;
+ case INTEL_RAPL_PSYS:
+ bit = RAPL_IDX_PSYS_NRG_STAT;
+ msr = MSR_PLATFORM_ENERGY_STATUS;
+ break;
default:
return -EINVAL;
}
RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04");
+RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05");
RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules");
/*
* we compute in 0.23 nJ increments regardless of MSR
RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10");
static struct attribute *rapl_events_srv_attr[] = {
EVENT_PTR(rapl_cores),
NULL,
};
+static struct attribute *rapl_events_skl_attr[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_ram),
+ EVENT_PTR(rapl_psys),
+
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_ram_unit),
+ EVENT_PTR(rapl_psys_unit),
+
+ EVENT_PTR(rapl_cores_scale),
+ EVENT_PTR(rapl_pkg_scale),
+ EVENT_PTR(rapl_gpu_scale),
+ EVENT_PTR(rapl_ram_scale),
+ EVENT_PTR(rapl_psys_scale),
+ NULL,
+};
+
static struct attribute *rapl_events_knl_attr[] = {
EVENT_PTR(rapl_pkg),
EVENT_PTR(rapl_ram),
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;
return 0;
}
-static void __init cleanup_rapl_pmus(void)
+static void cleanup_rapl_pmus(void)
{
int i;
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 intel_rapl_init_fun skl_rapl_init __initconst = {
+ .apply_quirk = false,
+ .cntr_mask = RAPL_IDX_SKL_CLN,
+ .attrs = rapl_events_skl_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(45, snbep_rapl_init), /* Sandy Bridge-EP */
+
+ X86_RAPL_MODEL_MATCH(58, snb_rapl_init), /* Ivy Bridge */
+ X86_RAPL_MODEL_MATCH(62, snbep_rapl_init), /* IvyTown */
+
+ X86_RAPL_MODEL_MATCH(60, hsw_rapl_init), /* Haswell */
+ X86_RAPL_MODEL_MATCH(63, hsx_rapl_init), /* Haswell-Server */
+ 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(79, hsx_rapl_init), /* Broadwell-Server */
+ X86_RAPL_MODEL_MATCH(86, hsx_rapl_init), /* Broadwell Xeon D */
+
+ X86_RAPL_MODEL_MATCH(87, knl_rapl_init), /* Knights Landing */
+
+ X86_RAPL_MODEL_MATCH(78, skl_rapl_init), /* Skylake */
+ X86_RAPL_MODEL_MATCH(94, skl_rapl_init), /* Skylake H/S */
+ {},
};
+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)
if (ret)
goto out;
- __perf_cpu_notifier(rapl_cpu_notifier);
+ __register_cpu_notifier(&rapl_cpu_nb);
cpu_notifier_register_done();
rapl_advertise();
return 0;
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);
+#include <asm/cpu_device_id.h>
#include "uncore.h"
static struct intel_uncore_type *empty_uncore[] = { NULL, };
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;
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;
}
}
-static void __init uncore_exit_boxes(void *dummy)
+static void uncore_exit_boxes(void *dummy)
{
struct intel_uncore_type **types;
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;
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);
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) {
return ret;
}
-static void __init uncore_pci_exit(void)
+static void uncore_pci_exit(void)
{
if (pcidrv_registered) {
pcidrv_registered = false;
{
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;
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)
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;
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);
PERF_MSR_MPERF = 2,
PERF_MSR_PPERF = 3,
PERF_MSR_SMI = 4,
+ PERF_MSR_PTSC = 5,
+ PERF_MSR_IRPERF = 6,
PERF_MSR_EVENT_MAX,
};
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 ||
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] = {
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
bool lbr_double_abort; /* duplicated lbr aborts */
+ bool lbr_pt_coexist; /* LBR may coexist with PT */
/*
* Intel PT/LBR/BTS are exclusive
extern struct event_constraint intel_slm_pebs_event_constraints[];
+extern struct event_constraint intel_glm_pebs_event_constraints[];
+
extern struct event_constraint intel_nehalem_pebs_event_constraints[];
extern struct event_constraint intel_westmere_pebs_event_constraints[];
void intel_pmu_lbr_init_atom(void);
+void intel_pmu_lbr_init_slm(void);
+
void intel_pmu_lbr_init_snb(void);
void intel_pmu_lbr_init_hsw(void);
#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) */
/* 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 */
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
#define MSR_IA32_RTIT_CTL 0x00000570
-#define RTIT_CTL_TRACEEN BIT(0)
-#define RTIT_CTL_CYCLEACC BIT(1)
-#define RTIT_CTL_OS BIT(2)
-#define RTIT_CTL_USR BIT(3)
-#define RTIT_CTL_CR3EN BIT(7)
-#define RTIT_CTL_TOPA BIT(8)
-#define RTIT_CTL_MTC_EN BIT(9)
-#define RTIT_CTL_TSC_EN BIT(10)
-#define RTIT_CTL_DISRETC BIT(11)
-#define RTIT_CTL_BRANCH_EN BIT(13)
-#define RTIT_CTL_MTC_RANGE_OFFSET 14
-#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
-#define RTIT_CTL_CYC_THRESH_OFFSET 19
-#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET)
-#define RTIT_CTL_PSB_FREQ_OFFSET 24
-#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET)
#define MSR_IA32_RTIT_STATUS 0x00000571
-#define RTIT_STATUS_CONTEXTEN BIT(1)
-#define RTIT_STATUS_TRIGGEREN BIT(2)
-#define RTIT_STATUS_ERROR BIT(4)
-#define RTIT_STATUS_STOPPED BIT(5)
+#define MSR_IA32_RTIT_STATUS 0x00000571
+#define MSR_IA32_RTIT_ADDR0_A 0x00000580
+#define MSR_IA32_RTIT_ADDR0_B 0x00000581
+#define MSR_IA32_RTIT_ADDR1_A 0x00000582
+#define MSR_IA32_RTIT_ADDR1_B 0x00000583
+#define MSR_IA32_RTIT_ADDR2_A 0x00000584
+#define MSR_IA32_RTIT_ADDR2_B 0x00000585
+#define MSR_IA32_RTIT_ADDR3_A 0x00000586
+#define MSR_IA32_RTIT_ADDR3_B 0x00000587
#define MSR_IA32_RTIT_CR3_MATCH 0x00000572
#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560
#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561
#define MSR_CONFIG_TDP_CONTROL 0x0000064B
#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C
+#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D
+
#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658
#define MSR_PKG_ANY_CORE_C0_RES 0x00000659
#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A
#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
#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 */
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,
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,
};
void perf_callchain_kernel(struct perf_callchain_entry *entry,
struct pt_regs *regs)
{
- xtensa_backtrace_kernel(regs, PERF_MAX_STACK_DEPTH,
+ xtensa_backtrace_kernel(regs, sysctl_perf_event_max_stack,
callchain_trace, NULL, entry);
}
void perf_callchain_user(struct perf_callchain_entry *entry,
struct pt_regs *regs)
{
- xtensa_backtrace_user(regs, PERF_MAX_STACK_DEPTH,
+ xtensa_backtrace_user(regs, sysctl_perf_event_max_stack,
callchain_trace, entry);
}
if (!platform_get_irq(cpu_pmu->plat_device, 0))
cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+ /*
+ * This is a CPU PMU potentially in a heterogeneous configuration (e.g.
+ * big.LITTLE). This is not an uncore PMU, and we have taken ctx
+ * sharing into account (e.g. with our pmu::filter_match callback and
+ * pmu::event_init group validation).
+ */
+ cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS;
+
return 0;
out_unregister:
#include <asm/processor.h>
#include <asm/cpu_device_id.h>
+/* Local defines */
+#define MSR_PLATFORM_POWER_LIMIT 0x0000065C
+
/* bitmasks for RAPL MSRs, used by primitive access functions */
#define ENERGY_STATUS_MASK 0xffffffff
RAPL_DOMAIN_PP0, /* core power plane */
RAPL_DOMAIN_PP1, /* graphics uncore */
RAPL_DOMAIN_DRAM,/* DRAM control_type */
+ RAPL_DOMAIN_PLATFORM, /* PSys control_type */
RAPL_DOMAIN_MAX,
};
"core",
"uncore",
"dram",
+ "psys",
};
static struct powercap_control_type *control_type; /* PowerCap Controller */
+static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */
/* caller to ensure CPU hotplug lock is held */
static struct rapl_package *find_package_by_id(int id)
.set_enable = set_domain_enable,
.get_enable = get_domain_enable,
},
+ /* RAPL_DOMAIN_PLATFORM */
+ {
+ .get_energy_uj = get_energy_counter,
+ .get_max_energy_range_uj = get_max_energy_counter,
+ .release = release_zone,
+ .set_enable = set_domain_enable,
+ .get_enable = get_domain_enable,
+ },
};
static int set_power_limit(struct powercap_zone *power_zone, int id,
powercap_unregister_zone(control_type,
&rd_package->power_zone);
}
+
+ if (platform_rapl_domain) {
+ powercap_unregister_zone(control_type,
+ &platform_rapl_domain->power_zone);
+ kfree(platform_rapl_domain);
+ }
+
powercap_unregister_control_type(control_type);
return 0;
return ret;
}
+static int rapl_register_psys(void)
+{
+ struct rapl_domain *rd;
+ struct powercap_zone *power_zone;
+ u64 val;
+
+ if (rdmsrl_safe_on_cpu(0, MSR_PLATFORM_ENERGY_STATUS, &val) || !val)
+ return -ENODEV;
+
+ if (rdmsrl_safe_on_cpu(0, MSR_PLATFORM_POWER_LIMIT, &val) || !val)
+ return -ENODEV;
+
+ rd = kzalloc(sizeof(*rd), GFP_KERNEL);
+ if (!rd)
+ return -ENOMEM;
+
+ rd->name = rapl_domain_names[RAPL_DOMAIN_PLATFORM];
+ rd->id = RAPL_DOMAIN_PLATFORM;
+ rd->msrs[0] = MSR_PLATFORM_POWER_LIMIT;
+ rd->msrs[1] = MSR_PLATFORM_ENERGY_STATUS;
+ rd->rpl[0].prim_id = PL1_ENABLE;
+ rd->rpl[0].name = pl1_name;
+ rd->rpl[1].prim_id = PL2_ENABLE;
+ rd->rpl[1].name = pl2_name;
+ rd->rp = find_package_by_id(0);
+
+ power_zone = powercap_register_zone(&rd->power_zone, control_type,
+ "psys", NULL,
+ &zone_ops[RAPL_DOMAIN_PLATFORM],
+ 2, &constraint_ops);
+
+ if (IS_ERR(power_zone)) {
+ kfree(rd);
+ return PTR_ERR(power_zone);
+ }
+
+ platform_rapl_domain = rd;
+
+ return 0;
+}
+
static int rapl_register_powercap(void)
{
struct rapl_domain *rd;
list_for_each_entry(rp, &rapl_packages, plist)
if (rapl_package_register_powercap(rp))
goto err_cleanup_package;
+
+ /* Don't bail out if PSys is not supported */
+ rapl_register_psys();
+
return ret;
err_cleanup_package:
case RAPL_DOMAIN_DRAM:
msr = MSR_DRAM_ENERGY_STATUS;
break;
+ case RAPL_DOMAIN_PLATFORM:
+ /* PSYS(PLATFORM) is not a CPU domain, so avoid printng error */
+ return -EINVAL;
default:
pr_err("invalid domain id %d\n", domain);
return -EINVAL;
struct perf_callchain_entry {
__u64 nr;
- __u64 ip[PERF_MAX_STACK_DEPTH];
+ __u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
};
struct perf_raw_record {
*/
struct task_struct *target;
+ /*
+ * PMU would store hardware filter configuration
+ * here.
+ */
+ void *addr_filters;
+
+ /* Last sync'ed generation of filters */
+ unsigned long addr_filters_gen;
+
/*
* hw_perf_event::state flags; used to track the PERF_EF_* state.
*/
#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08
#define PERF_PMU_CAP_EXCLUSIVE 0x10
#define PERF_PMU_CAP_ITRACE 0x20
+#define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40
/**
* struct pmu - generic performance monitoring unit
int task_ctx_nr;
int hrtimer_interval_ms;
+ /* number of address filters this PMU can do */
+ unsigned int nr_addr_filters;
+
/*
* Fully disable/enable this PMU, can be used to protect from the PMI
* as well as for lazy/batch writing of the MSRs.
*/
void (*free_aux) (void *aux); /* optional */
+ /*
+ * Validate address range filters: make sure the HW supports the
+ * requested configuration and number of filters; return 0 if the
+ * supplied filters are valid, -errno otherwise.
+ *
+ * Runs in the context of the ioctl()ing process and is not serialized
+ * with the rest of the PMU callbacks.
+ */
+ int (*addr_filters_validate) (struct list_head *filters);
+ /* optional */
+
+ /*
+ * Synchronize address range filter configuration:
+ * translate hw-agnostic filters into hardware configuration in
+ * event::hw::addr_filters.
+ *
+ * Runs as a part of filter sync sequence that is done in ->start()
+ * callback by calling perf_event_addr_filters_sync().
+ *
+ * May (and should) traverse event::addr_filters::list, for which its
+ * caller provides necessary serialization.
+ */
+ void (*addr_filters_sync) (struct perf_event *event);
+ /* optional */
+
/*
* Filter events for PMU-specific reasons.
*/
int (*filter_match) (struct perf_event *event); /* optional */
};
+/**
+ * struct perf_addr_filter - address range filter definition
+ * @entry: event's filter list linkage
+ * @inode: object file's inode for file-based filters
+ * @offset: filter range offset
+ * @size: filter range size
+ * @range: 1: range, 0: address
+ * @filter: 1: filter/start, 0: stop
+ *
+ * This is a hardware-agnostic filter configuration as specified by the user.
+ */
+struct perf_addr_filter {
+ struct list_head entry;
+ struct inode *inode;
+ unsigned long offset;
+ unsigned long size;
+ unsigned int range : 1,
+ filter : 1;
+};
+
+/**
+ * struct perf_addr_filters_head - container for address range filters
+ * @list: list of filters for this event
+ * @lock: spinlock that serializes accesses to the @list and event's
+ * (and its children's) filter generations.
+ *
+ * A child event will use parent's @list (and therefore @lock), so they are
+ * bundled together; see perf_event_addr_filters().
+ */
+struct perf_addr_filters_head {
+ struct list_head list;
+ raw_spinlock_t lock;
+};
+
/**
* enum perf_event_active_state - the states of a event
*/
atomic_t event_limit;
+ /* address range filters */
+ struct perf_addr_filters_head addr_filters;
+ /* vma address array for file-based filders */
+ unsigned long *addr_filters_offs;
+ unsigned long addr_filters_gen;
+
void (*destroy)(struct perf_event *);
struct rcu_head rcu_head;
struct perf_sample_data *data,
struct pt_regs *regs);
+extern void perf_event_output_forward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
+extern void perf_event_output_backward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
extern void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs);
+ struct perf_sample_data *data,
+ struct pt_regs *regs);
+
+static inline bool
+is_default_overflow_handler(struct perf_event *event)
+{
+ if (likely(event->overflow_handler == perf_event_output_forward))
+ return true;
+ if (unlikely(event->overflow_handler == perf_event_output_backward))
+ return true;
+ return false;
+}
extern void
perf_event_header__init_id(struct perf_event_header *header,
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
+extern int sysctl_perf_event_max_stack;
+
static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
{
- if (entry->nr < PERF_MAX_STACK_DEPTH) {
+ if (entry->nr < sysctl_perf_event_max_stack) {
entry->ip[entry->nr++] = ip;
return 0;
} else {
void __user *buffer, size_t *lenp,
loff_t *ppos);
+int perf_event_max_stack_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos);
static inline bool perf_paranoid_tracepoint_raw(void)
{
return event->pmu->setup_aux;
}
+static inline bool is_write_backward(struct perf_event *event)
+{
+ return !!event->attr.write_backward;
+}
+
+static inline bool has_addr_filter(struct perf_event *event)
+{
+ return event->pmu->nr_addr_filters;
+}
+
+/*
+ * An inherited event uses parent's filters
+ */
+static inline struct perf_addr_filters_head *
+perf_event_addr_filters(struct perf_event *event)
+{
+ struct perf_addr_filters_head *ifh = &event->addr_filters;
+
+ if (event->parent)
+ ifh = &event->parent->addr_filters;
+
+ return ifh;
+}
+
+extern void perf_event_addr_filters_sync(struct perf_event *event);
+
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
+extern int perf_output_begin_forward(struct perf_output_handle *handle,
+ struct perf_event *event,
+ unsigned int size);
+extern int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_event *event,
+ unsigned int size);
+
extern void perf_output_end(struct perf_output_handle *handle);
extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
comm_exec : 1, /* flag comm events that are due to an exec */
use_clockid : 1, /* use @clockid for time fields */
context_switch : 1, /* context switch data */
- __reserved_1 : 37;
+ write_backward : 1, /* Write ring buffer from end to beginning */
+ __reserved_1 : 36;
union {
__u32 wakeup_events; /* wakeup every n events */
#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,
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
value_size < 8 || value_size % 8 ||
- value_size / 8 > PERF_MAX_STACK_DEPTH)
+ value_size / 8 > sysctl_perf_event_max_stack)
return ERR_PTR(-EINVAL);
/* hash table size must be power of 2 */
struct perf_callchain_entry *trace;
struct stack_map_bucket *bucket, *new_bucket, *old_bucket;
u32 max_depth = map->value_size / 8;
- /* stack_map_alloc() checks that max_depth <= PERF_MAX_STACK_DEPTH */
- u32 init_nr = PERF_MAX_STACK_DEPTH - max_depth;
+ /* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
+ u32 init_nr = sysctl_perf_event_max_stack - max_depth;
u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
u32 hash, id, trace_nr, trace_len;
bool user = flags & BPF_F_USER_STACK;
return -EFAULT;
/* get_perf_callchain() guarantees that trace->nr >= init_nr
- * and trace-nr <= PERF_MAX_STACK_DEPTH, so trace_nr <= max_depth
+ * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
*/
trace_nr = trace->nr - init_nr;
struct perf_callchain_entry *cpu_entries[0];
};
+int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH;
+
+static inline size_t perf_callchain_entry__sizeof(void)
+{
+ return (sizeof(struct perf_callchain_entry) +
+ sizeof(__u64) * sysctl_perf_event_max_stack);
+}
+
static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
static atomic_t nr_callchain_events;
static DEFINE_MUTEX(callchain_mutex);
if (!entries)
return -ENOMEM;
- size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+ size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS;
for_each_possible_cpu(cpu) {
entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
cpu = smp_processor_id();
- return &entries->cpu_entries[cpu][*rctx];
+ return (((void *)entries->cpu_entries[cpu]) +
+ (*rctx * perf_callchain_entry__sizeof()));
}
static void
return entry;
}
+
+int perf_event_max_stack_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int new_value = sysctl_perf_event_max_stack, ret;
+ struct ctl_table new_table = *table;
+
+ new_table.data = &new_value;
+ ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
+ mutex_lock(&callchain_mutex);
+ if (atomic_read(&nr_callchain_events))
+ ret = -EBUSY;
+ else
+ sysctl_perf_event_max_stack = new_value;
+
+ mutex_unlock(&callchain_mutex);
+
+ return ret;
+}
#include <linux/compat.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/namei.h>
+#include <linux/parser.h>
#include "internal.h"
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
}
EXPORT_SYMBOL_GPL(perf_event_enable);
+struct stop_event_data {
+ struct perf_event *event;
+ unsigned int restart;
+};
+
+static int __perf_event_stop(void *info)
+{
+ struct stop_event_data *sd = info;
+ struct perf_event *event = sd->event;
+
+ /* if it's already INACTIVE, do nothing */
+ 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);
+
+ /*
+ * May race with the actual stop (through perf_pmu_output_stop()),
+ * but it is only used for events with AUX ring buffer, and such
+ * events will refuse to restart because of rb::aux_mmap_count==0,
+ * see comments in perf_aux_output_begin().
+ *
+ * Since this is happening on a event-local CPU, no trace is lost
+ * while restarting.
+ */
+ if (sd->restart)
+ event->pmu->start(event, PERF_EF_START);
+
+ return 0;
+}
+
+static int perf_event_restart(struct perf_event *event)
+{
+ struct stop_event_data sd = {
+ .event = event,
+ .restart = 1,
+ };
+ int ret = 0;
+
+ do {
+ if (READ_ONCE(event->state) != PERF_EVENT_STATE_ACTIVE)
+ return 0;
+
+ /* matches smp_wmb() in event_sched_in() */
+ smp_rmb();
+
+ /*
+ * We only want to restart ACTIVE events, so if the event goes
+ * inactive here (event->oncpu==-1), there's nothing more to do;
+ * fall through with ret==-ENXIO.
+ */
+ ret = cpu_function_call(READ_ONCE(event->oncpu),
+ __perf_event_stop, &sd);
+ } while (ret == -EAGAIN);
+
+ return ret;
+}
+
+/*
+ * In order to contain the amount of racy and tricky in the address filter
+ * configuration management, it is a two part process:
+ *
+ * (p1) when userspace mappings change as a result of (1) or (2) or (3) below,
+ * we update the addresses of corresponding vmas in
+ * event::addr_filters_offs array and bump the event::addr_filters_gen;
+ * (p2) when an event is scheduled in (pmu::add), it calls
+ * perf_event_addr_filters_sync() which calls pmu::addr_filters_sync()
+ * if the generation has changed since the previous call.
+ *
+ * If (p1) happens while the event is active, we restart it to force (p2).
+ *
+ * (1) perf_addr_filters_apply(): adjusting filters' offsets based on
+ * pre-existing mappings, called once when new filters arrive via SET_FILTER
+ * ioctl;
+ * (2) perf_addr_filters_adjust(): adjusting filters' offsets based on newly
+ * registered mapping, called for every new mmap(), with mm::mmap_sem down
+ * for reading;
+ * (3) perf_event_addr_filters_exec(): clearing filters' offsets in the process
+ * of exec.
+ */
+void perf_event_addr_filters_sync(struct perf_event *event)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+
+ if (!has_addr_filter(event))
+ return;
+
+ raw_spin_lock(&ifh->lock);
+ if (event->addr_filters_gen != event->hw.addr_filters_gen) {
+ event->pmu->addr_filters_sync(event);
+ event->hw.addr_filters_gen = event->addr_filters_gen;
+ }
+ raw_spin_unlock(&ifh->lock);
+}
+EXPORT_SYMBOL_GPL(perf_event_addr_filters_sync);
+
static int _perf_event_refresh(struct perf_event *event, int refresh)
{
/*
put_ctx(clone_ctx);
}
-void perf_event_exec(void)
-{
- int ctxn;
-
- rcu_read_lock();
- for_each_task_context_nr(ctxn)
- perf_event_enable_on_exec(ctxn);
- rcu_read_unlock();
-}
-
struct perf_read_data {
struct perf_event *event;
bool group;
return true;
}
+static void perf_addr_filters_splice(struct perf_event *event,
+ struct list_head *head);
+
static void _free_event(struct perf_event *event)
{
irq_work_sync(&event->pending);
}
perf_event_free_bpf_prog(event);
+ perf_addr_filters_splice(event, NULL);
+ kfree(event->addr_filters_offs);
if (event->destroy)
event->destroy(event);
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;
}
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().
*/
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);
}
}
}
-void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+static void __always_inline
+__perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs,
+ int (*output_begin)(struct perf_output_handle *,
+ struct perf_event *,
+ unsigned int))
{
struct perf_output_handle handle;
struct perf_event_header header;
perf_prepare_sample(&header, data, event, regs);
- if (perf_output_begin(&handle, event, header.size))
+ if (output_begin(&handle, event, header.size))
goto exit;
perf_output_sample(&handle, &header, data, event);
rcu_read_unlock();
}
+void
+perf_event_output_forward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ __perf_event_output(event, data, regs, perf_output_begin_forward);
+}
+
+void
+perf_event_output_backward(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ __perf_event_output(event, data, regs, perf_output_begin_backward);
+}
+
+void
+perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ __perf_event_output(event, data, regs, perf_output_begin);
+}
+
/*
* read event_id
*/
static void
perf_event_aux_ctx(struct perf_event_context *ctx,
perf_event_aux_output_cb output,
- void *data)
+ void *data, bool all)
{
struct perf_event *event;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
- if (event->state < PERF_EVENT_STATE_INACTIVE)
- continue;
- if (!event_filter_match(event))
- continue;
+ if (!all) {
+ if (event->state < PERF_EVENT_STATE_INACTIVE)
+ continue;
+ if (!event_filter_match(event))
+ continue;
+ }
+
output(event, data);
}
}
{
rcu_read_lock();
preempt_disable();
- perf_event_aux_ctx(task_ctx, output, data);
+ perf_event_aux_ctx(task_ctx, output, data, false);
preempt_enable();
rcu_read_unlock();
}
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
if (cpuctx->unique_pmu != pmu)
goto next;
- perf_event_aux_ctx(&cpuctx->ctx, output, data);
+ perf_event_aux_ctx(&cpuctx->ctx, output, data, false);
ctxn = pmu->task_ctx_nr;
if (ctxn < 0)
goto next;
ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
if (ctx)
- perf_event_aux_ctx(ctx, output, data);
+ perf_event_aux_ctx(ctx, output, data, false);
next:
put_cpu_ptr(pmu->pmu_cpu_context);
}
rcu_read_unlock();
}
+/*
+ * Clear all file-based filters at exec, they'll have to be
+ * re-instated when/if these objects are mmapped again.
+ */
+static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+ struct perf_addr_filter *filter;
+ unsigned int restart = 0, count = 0;
+ unsigned long flags;
+
+ if (!has_addr_filter(event))
+ return;
+
+ raw_spin_lock_irqsave(&ifh->lock, flags);
+ list_for_each_entry(filter, &ifh->list, entry) {
+ if (filter->inode) {
+ event->addr_filters_offs[count] = 0;
+ restart++;
+ }
+
+ count++;
+ }
+
+ if (restart)
+ event->addr_filters_gen++;
+ raw_spin_unlock_irqrestore(&ifh->lock, flags);
+
+ if (restart)
+ perf_event_restart(event);
+}
+
+void perf_event_exec(void)
+{
+ struct perf_event_context *ctx;
+ int ctxn;
+
+ rcu_read_lock();
+ for_each_task_context_nr(ctxn) {
+ ctx = current->perf_event_ctxp[ctxn];
+ if (!ctx)
+ continue;
+
+ perf_event_enable_on_exec(ctxn);
+
+ perf_event_aux_ctx(ctx, perf_event_addr_filters_exec, NULL,
+ true);
+ }
+ 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;
+ struct stop_event_data sd = {
+ .event = event,
+ };
+
+ 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(&sd);
+}
+
+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, false);
+ if (cpuctx->task_ctx)
+ perf_event_aux_ctx(cpuctx->task_ctx, __perf_event_output_stop,
+ &ro, false);
+ 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
*
kfree(buf);
}
+/*
+ * Whether this @filter depends on a dynamic object which is not loaded
+ * yet or its load addresses are not known.
+ */
+static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
+{
+ return filter->filter && filter->inode;
+}
+
+/*
+ * Check whether inode and address range match filter criteria.
+ */
+static bool perf_addr_filter_match(struct perf_addr_filter *filter,
+ struct file *file, unsigned long offset,
+ unsigned long size)
+{
+ if (filter->inode != file->f_inode)
+ return false;
+
+ if (filter->offset > offset + size)
+ return false;
+
+ if (filter->offset + filter->size < offset)
+ return false;
+
+ return true;
+}
+
+static void __perf_addr_filters_adjust(struct perf_event *event, void *data)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+ struct vm_area_struct *vma = data;
+ unsigned long off = vma->vm_pgoff << PAGE_SHIFT, flags;
+ struct file *file = vma->vm_file;
+ struct perf_addr_filter *filter;
+ unsigned int restart = 0, count = 0;
+
+ if (!has_addr_filter(event))
+ return;
+
+ if (!file)
+ return;
+
+ raw_spin_lock_irqsave(&ifh->lock, flags);
+ list_for_each_entry(filter, &ifh->list, entry) {
+ if (perf_addr_filter_match(filter, file, off,
+ vma->vm_end - vma->vm_start)) {
+ event->addr_filters_offs[count] = vma->vm_start;
+ restart++;
+ }
+
+ count++;
+ }
+
+ if (restart)
+ event->addr_filters_gen++;
+ raw_spin_unlock_irqrestore(&ifh->lock, flags);
+
+ if (restart)
+ perf_event_restart(event);
+}
+
+/*
+ * Adjust all task's events' filters to the new vma
+ */
+static void perf_addr_filters_adjust(struct vm_area_struct *vma)
+{
+ struct perf_event_context *ctx;
+ int ctxn;
+
+ rcu_read_lock();
+ for_each_task_context_nr(ctxn) {
+ ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
+ if (!ctx)
+ continue;
+
+ perf_event_aux_ctx(ctx, __perf_addr_filters_adjust, vma, true);
+ }
+ rcu_read_unlock();
+}
+
void perf_event_mmap(struct vm_area_struct *vma)
{
struct perf_mmap_event mmap_event;
/* .flags (attr_mmap2 only) */
};
+ perf_addr_filters_adjust(vma);
perf_event_mmap_event(&mmap_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;
perf_pmu_register(&perf_tracepoint, "tracepoint", PERF_TYPE_TRACEPOINT);
}
-static int perf_event_set_filter(struct perf_event *event, void __user *arg)
-{
- char *filter_str;
- int ret;
-
- if (event->attr.type != PERF_TYPE_TRACEPOINT)
- return -EINVAL;
-
- filter_str = strndup_user(arg, PAGE_SIZE);
- if (IS_ERR(filter_str))
- return PTR_ERR(filter_str);
-
- ret = ftrace_profile_set_filter(event, event->attr.config, filter_str);
-
- kfree(filter_str);
- return ret;
-}
-
static void perf_event_free_filter(struct perf_event *event)
{
ftrace_profile_free_filter(event);
{
}
-static int perf_event_set_filter(struct perf_event *event, void __user *arg)
-{
- return -ENOENT;
-}
-
static void perf_event_free_filter(struct perf_event *event)
{
}
}
#endif
+/*
+ * Allocate a new address filter
+ */
+static struct perf_addr_filter *
+perf_addr_filter_new(struct perf_event *event, struct list_head *filters)
+{
+ int node = cpu_to_node(event->cpu == -1 ? 0 : event->cpu);
+ struct perf_addr_filter *filter;
+
+ filter = kzalloc_node(sizeof(*filter), GFP_KERNEL, node);
+ if (!filter)
+ return NULL;
+
+ INIT_LIST_HEAD(&filter->entry);
+ list_add_tail(&filter->entry, filters);
+
+ return filter;
+}
+
+static void free_filters_list(struct list_head *filters)
+{
+ struct perf_addr_filter *filter, *iter;
+
+ list_for_each_entry_safe(filter, iter, filters, entry) {
+ if (filter->inode)
+ iput(filter->inode);
+ list_del(&filter->entry);
+ kfree(filter);
+ }
+}
+
+/*
+ * Free existing address filters and optionally install new ones
+ */
+static void perf_addr_filters_splice(struct perf_event *event,
+ struct list_head *head)
+{
+ unsigned long flags;
+ LIST_HEAD(list);
+
+ if (!has_addr_filter(event))
+ return;
+
+ /* don't bother with children, they don't have their own filters */
+ if (event->parent)
+ return;
+
+ raw_spin_lock_irqsave(&event->addr_filters.lock, flags);
+
+ list_splice_init(&event->addr_filters.list, &list);
+ if (head)
+ list_splice(head, &event->addr_filters.list);
+
+ raw_spin_unlock_irqrestore(&event->addr_filters.lock, flags);
+
+ free_filters_list(&list);
+}
+
+/*
+ * Scan through mm's vmas and see if one of them matches the
+ * @filter; if so, adjust filter's address range.
+ * Called with mm::mmap_sem down for reading.
+ */
+static unsigned long perf_addr_filter_apply(struct perf_addr_filter *filter,
+ struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ struct file *file = vma->vm_file;
+ unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long vma_size = vma->vm_end - vma->vm_start;
+
+ if (!file)
+ continue;
+
+ if (!perf_addr_filter_match(filter, file, off, vma_size))
+ continue;
+
+ return vma->vm_start;
+ }
+
+ return 0;
+}
+
+/*
+ * Update event's address range filters based on the
+ * task's existing mappings, if any.
+ */
+static void perf_event_addr_filters_apply(struct perf_event *event)
+{
+ struct perf_addr_filters_head *ifh = perf_event_addr_filters(event);
+ struct task_struct *task = READ_ONCE(event->ctx->task);
+ struct perf_addr_filter *filter;
+ struct mm_struct *mm = NULL;
+ unsigned int count = 0;
+ unsigned long flags;
+
+ /*
+ * We may observe TASK_TOMBSTONE, which means that the event tear-down
+ * will stop on the parent's child_mutex that our caller is also holding
+ */
+ if (task == TASK_TOMBSTONE)
+ return;
+
+ mm = get_task_mm(event->ctx->task);
+ if (!mm)
+ goto restart;
+
+ down_read(&mm->mmap_sem);
+
+ raw_spin_lock_irqsave(&ifh->lock, flags);
+ list_for_each_entry(filter, &ifh->list, entry) {
+ event->addr_filters_offs[count] = 0;
+
+ if (perf_addr_filter_needs_mmap(filter))
+ event->addr_filters_offs[count] =
+ perf_addr_filter_apply(filter, mm);
+
+ count++;
+ }
+
+ event->addr_filters_gen++;
+ raw_spin_unlock_irqrestore(&ifh->lock, flags);
+
+ up_read(&mm->mmap_sem);
+
+ mmput(mm);
+
+restart:
+ perf_event_restart(event);
+}
+
+/*
+ * Address range filtering: limiting the data to certain
+ * instruction address ranges. Filters are ioctl()ed to us from
+ * userspace as ascii strings.
+ *
+ * Filter string format:
+ *
+ * ACTION RANGE_SPEC
+ * where ACTION is one of the
+ * * "filter": limit the trace to this region
+ * * "start": start tracing from this address
+ * * "stop": stop tracing at this address/region;
+ * RANGE_SPEC is
+ * * for kernel addresses: <start address>[/<size>]
+ * * for object files: <start address>[/<size>]@</path/to/object/file>
+ *
+ * if <size> is not specified, the range is treated as a single address.
+ */
+enum {
+ IF_ACT_FILTER,
+ IF_ACT_START,
+ IF_ACT_STOP,
+ IF_SRC_FILE,
+ IF_SRC_KERNEL,
+ IF_SRC_FILEADDR,
+ IF_SRC_KERNELADDR,
+};
+
+enum {
+ IF_STATE_ACTION = 0,
+ IF_STATE_SOURCE,
+ IF_STATE_END,
+};
+
+static const match_table_t if_tokens = {
+ { IF_ACT_FILTER, "filter" },
+ { IF_ACT_START, "start" },
+ { IF_ACT_STOP, "stop" },
+ { IF_SRC_FILE, "%u/%u@%s" },
+ { IF_SRC_KERNEL, "%u/%u" },
+ { IF_SRC_FILEADDR, "%u@%s" },
+ { IF_SRC_KERNELADDR, "%u" },
+};
+
+/*
+ * Address filter string parser
+ */
+static int
+perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
+ struct list_head *filters)
+{
+ struct perf_addr_filter *filter = NULL;
+ char *start, *orig, *filename = NULL;
+ struct path path;
+ substring_t args[MAX_OPT_ARGS];
+ int state = IF_STATE_ACTION, token;
+ unsigned int kernel = 0;
+ int ret = -EINVAL;
+
+ orig = fstr = kstrdup(fstr, GFP_KERNEL);
+ if (!fstr)
+ return -ENOMEM;
+
+ while ((start = strsep(&fstr, " ,\n")) != NULL) {
+ ret = -EINVAL;
+
+ if (!*start)
+ continue;
+
+ /* filter definition begins */
+ if (state == IF_STATE_ACTION) {
+ filter = perf_addr_filter_new(event, filters);
+ if (!filter)
+ goto fail;
+ }
+
+ token = match_token(start, if_tokens, args);
+ switch (token) {
+ case IF_ACT_FILTER:
+ case IF_ACT_START:
+ filter->filter = 1;
+
+ case IF_ACT_STOP:
+ if (state != IF_STATE_ACTION)
+ goto fail;
+
+ state = IF_STATE_SOURCE;
+ break;
+
+ case IF_SRC_KERNELADDR:
+ case IF_SRC_KERNEL:
+ kernel = 1;
+
+ case IF_SRC_FILEADDR:
+ case IF_SRC_FILE:
+ if (state != IF_STATE_SOURCE)
+ goto fail;
+
+ if (token == IF_SRC_FILE || token == IF_SRC_KERNEL)
+ filter->range = 1;
+
+ *args[0].to = 0;
+ ret = kstrtoul(args[0].from, 0, &filter->offset);
+ if (ret)
+ goto fail;
+
+ if (filter->range) {
+ *args[1].to = 0;
+ ret = kstrtoul(args[1].from, 0, &filter->size);
+ if (ret)
+ goto fail;
+ }
+
+ if (token == IF_SRC_FILE) {
+ filename = match_strdup(&args[2]);
+ if (!filename) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+
+ state = IF_STATE_END;
+ break;
+
+ default:
+ goto fail;
+ }
+
+ /*
+ * Filter definition is fully parsed, validate and install it.
+ * Make sure that it doesn't contradict itself or the event's
+ * attribute.
+ */
+ if (state == IF_STATE_END) {
+ if (kernel && event->attr.exclude_kernel)
+ goto fail;
+
+ if (!kernel) {
+ if (!filename)
+ goto fail;
+
+ /* look up the path and grab its inode */
+ ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+ if (ret)
+ goto fail_free_name;
+
+ filter->inode = igrab(d_inode(path.dentry));
+ path_put(&path);
+ kfree(filename);
+ filename = NULL;
+
+ ret = -EINVAL;
+ if (!filter->inode ||
+ !S_ISREG(filter->inode->i_mode))
+ /* free_filters_list() will iput() */
+ goto fail;
+ }
+
+ /* ready to consume more filters */
+ state = IF_STATE_ACTION;
+ filter = NULL;
+ }
+ }
+
+ if (state != IF_STATE_ACTION)
+ goto fail;
+
+ kfree(orig);
+
+ return 0;
+
+fail_free_name:
+ kfree(filename);
+fail:
+ free_filters_list(filters);
+ kfree(orig);
+
+ return ret;
+}
+
+static int
+perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
+{
+ LIST_HEAD(filters);
+ int ret;
+
+ /*
+ * Since this is called in perf_ioctl() path, we're already holding
+ * ctx::mutex.
+ */
+ lockdep_assert_held(&event->ctx->mutex);
+
+ if (WARN_ON_ONCE(event->parent))
+ return -EINVAL;
+
+ /*
+ * For now, we only support filtering in per-task events; doing so
+ * for CPU-wide events requires additional context switching trickery,
+ * since same object code will be mapped at different virtual
+ * addresses in different processes.
+ */
+ if (!event->ctx->task)
+ return -EOPNOTSUPP;
+
+ ret = perf_event_parse_addr_filter(event, filter_str, &filters);
+ if (ret)
+ return ret;
+
+ ret = event->pmu->addr_filters_validate(&filters);
+ if (ret) {
+ free_filters_list(&filters);
+ return ret;
+ }
+
+ /* remove existing filters, if any */
+ perf_addr_filters_splice(event, &filters);
+
+ /* install new filters */
+ perf_event_for_each_child(event, perf_event_addr_filters_apply);
+
+ return ret;
+}
+
+static int perf_event_set_filter(struct perf_event *event, void __user *arg)
+{
+ char *filter_str;
+ int ret = -EINVAL;
+
+ if ((event->attr.type != PERF_TYPE_TRACEPOINT ||
+ !IS_ENABLED(CONFIG_EVENT_TRACING)) &&
+ !has_addr_filter(event))
+ return -EINVAL;
+
+ filter_str = strndup_user(arg, PAGE_SIZE);
+ if (IS_ERR(filter_str))
+ return PTR_ERR(filter_str);
+
+ if (IS_ENABLED(CONFIG_EVENT_TRACING) &&
+ event->attr.type == PERF_TYPE_TRACEPOINT)
+ ret = ftrace_profile_set_filter(event, event->attr.config,
+ filter_str);
+ else if (has_addr_filter(event))
+ ret = perf_event_set_addr_filter(event, filter_str);
+
+ kfree(filter_str);
+ return ret;
+}
+
/*
* hrtimer based swevent callback
*/
out:
mutex_unlock(&pmus_lock);
}
+
+/*
+ * Let userspace know that this PMU supports address range filtering:
+ */
+static ssize_t nr_addr_filters_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ struct pmu *pmu = dev_get_drvdata(dev);
+
+ return snprintf(page, PAGE_SIZE - 1, "%d\n", pmu->nr_addr_filters);
+}
+DEVICE_ATTR_RO(nr_addr_filters);
+
static struct idr pmu_idr;
static ssize_t
if (ret)
goto free_dev;
+ /* For PMUs with address filters, throw in an extra attribute: */
+ if (pmu->nr_addr_filters)
+ ret = device_create_file(pmu->dev, &dev_attr_nr_addr_filters);
+
+ if (ret)
+ goto del_dev;
+
out:
return ret;
+del_dev:
+ device_del(pmu->dev);
+
free_dev:
put_device(pmu->dev);
goto out;
}
skip_type:
+ if (pmu->task_ctx_nr == perf_hw_context) {
+ static int hw_context_taken = 0;
+
+ /*
+ * Other than systems with heterogeneous CPUs, it never makes
+ * sense for two PMUs to share perf_hw_context. PMUs which are
+ * uncore must use perf_invalid_context.
+ */
+ if (WARN_ON_ONCE(hw_context_taken &&
+ !(pmu->capabilities & PERF_PMU_CAP_HETEROGENEOUS_CPUS)))
+ 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;
free_percpu(pmu->pmu_disable_count);
if (pmu->type >= PERF_TYPE_MAX)
idr_remove(&pmu_idr, pmu->type);
+ if (pmu->nr_addr_filters)
+ device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
device_del(pmu->dev);
put_device(pmu->dev);
free_pmu_context(pmu);
INIT_LIST_HEAD(&event->sibling_list);
INIT_LIST_HEAD(&event->rb_entry);
INIT_LIST_HEAD(&event->active_entry);
+ INIT_LIST_HEAD(&event->addr_filters.list);
INIT_HLIST_NODE(&event->hlist_entry);
init_irq_work(&event->pending, perf_pending_event);
mutex_init(&event->mmap_mutex);
+ raw_spin_lock_init(&event->addr_filters.lock);
atomic_long_set(&event->refcount, 1);
event->cpu = 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 if (is_write_backward(event)){
+ event->overflow_handler = perf_event_output_backward;
+ event->overflow_handler_context = NULL;
+ } else {
+ event->overflow_handler = perf_event_output_forward;
+ event->overflow_handler_context = NULL;
+ }
perf_event__state_init(event);
if (err)
goto err_pmu;
+ if (has_addr_filter(event)) {
+ event->addr_filters_offs = kcalloc(pmu->nr_addr_filters,
+ sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!event->addr_filters_offs)
+ goto err_per_task;
+
+ /* force hw sync on the address filters */
+ event->addr_filters_gen = 1;
+ }
+
if (!event->parent) {
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
err = get_callchain_buffers();
if (err)
- goto err_per_task;
+ goto err_addr_filters;
}
}
return event;
+err_addr_filters:
+ kfree(event->addr_filters_offs);
+
err_per_task:
exclusive_event_destroy(event);
if (output_event->clock != event->clock)
goto out;
+ /*
+ * Either writing ring buffer from beginning or from end.
+ * Mixing is not allowed.
+ */
+ if (is_write_backward(output_event) != is_write_backward(event))
+ goto out;
+
/*
* If both events generate aux data, they must be on the same PMU
*/
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 */
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);
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;
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;
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
* 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.
return -ENOSPC;
}
+int perf_output_begin_forward(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size)
+{
+ return __perf_output_begin(handle, event, size, false);
+}
+
+int perf_output_begin_backward(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size)
+{
+ return __perf_output_begin(handle, event, size, true);
+}
+
+int perf_output_begin(struct perf_output_handle *handle,
+ struct perf_event *event, unsigned int size)
+{
+
+ return __perf_output_begin(handle, event, size,
+ unlikely(is_write_backward(event)));
+}
+
unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len)
{
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)
{
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;
}
/*
* 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)
if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
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
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;
* 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)
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);
}
/*
{
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;
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
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
#endif
+#ifdef CONFIG_PERF_EVENTS
+static int six_hundred_forty_kb = 640 * 1024;
+#endif
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
.extra1 = &zero,
.extra2 = &one_hundred,
},
+ {
+ .procname = "perf_event_max_stack",
+ .data = NULL, /* filled in by handler */
+ .maxlen = sizeof(sysctl_perf_event_max_stack),
+ .mode = 0644,
+ .proc_handler = perf_event_max_stack_handler,
+ .extra1 = &zero,
+ .extra2 = &six_hundred_forty_kb,
+ },
#endif
#ifdef CONFIG_KMEMCHECK
{
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
$(call descend,lib/subcmd,clean)
perf_clean:
- $(call descend,$(@:_clean=),clean)
+ $(Q)mkdir -p $(PERF_O) .
+ $(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir= clean
selftests_clean:
$(call descend,testing/$(@:_clean=),clean)
FEATURE_TESTS_BASIC := \
backtrace \
dwarf \
+ dwarf_getlocations \
fortify-source \
sync-compare-and-swap \
glibc \
FEATURE_DISPLAY ?= \
dwarf \
+ dwarf_getlocations \
glibc \
gtk2 \
libaudit \
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 \
$(OUTPUT)test-dwarf.bin:
$(BUILD) $(DWARFLIBS)
+$(OUTPUT)test-dwarf_getlocations.bin:
+ $(BUILD) $(DWARFLIBS)
+
$(OUTPUT)test-libelf-mmap.bin:
$(BUILD) -lelf
# 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
main_test_libelf_mmap();
main_test_glibc();
main_test_dwarf();
+ main_test_dwarf_getlocations();
main_test_libelf_getphdrnum();
main_test_libunwind();
main_test_libaudit();
attr.log_level = 0;
attr.kern_version = 0;
- attr = attr;
/*
* Test existence of __NR_bpf and BPF_PROG_LOAD.
* This call should fail if we run the testcase.
*/
- return syscall(__NR_bpf, BPF_PROG_LOAD, attr, sizeof(attr));
+ return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
}
--- /dev/null
+#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);
+}
return err;
}
+int procfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+ char path[PATH_MAX];
+ const char *procfs = procfs__mountpoint();
+
+ if (!procfs)
+ return -1;
+
+ snprintf(path, sizeof(path), "%s/%s", procfs, entry);
+
+ return filename__read_str(path, buf, sizep);
+}
+
int sysfs__read_ull(const char *entry, unsigned long long *value)
{
char path[PATH_MAX];
int filename__read_ull(const char *filename, unsigned long long *value);
int filename__read_str(const char *filename, char **buf, size_t *sizep);
+int procfs__read_str(const char *entry, char **buf, size_t *sizep);
+
int sysctl__read_int(const char *sysctl, int *value);
int sysfs__read_int(const char *entry, int *value);
int sysfs__read_ull(const char *entry, unsigned long long *value);
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".
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
-----------
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
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.
-f::
--force::
- Don't complain, do it.
+ Don't do ownership validation.
-v::
--verbose::
-f::
--force::
- Don't complain, do it.
+ Don't do ownership validation.
--symfs=<directory>::
Look for files with symbols relative to this directory.
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
--------------------
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
-------
--------
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]
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]
--all-user::
Configure all used events to run in user space.
+--timestamp-filename
+Append timestamp to output file name.
+
+--switch-output::
+Generate multiple perf.data files, timestamp prefixed, switching to a new one
+when receiving a SIGUSR2.
+
+A possible use case is to, given an external event, slice the perf.data file
+that gets then processed, possibly via a perf script, to decide if that
+particular perf.data snapshot should be kept or not.
+
+Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+
SEE ALSO
--------
linkperf:perf-stat[1], linkperf:perf-list[1]
Note that when using the --itrace option the synthesized callchain size
will override this value if the synthesized callchain size is bigger.
- Default: 127
+ Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
-G::
--inverted::
-f::
--force::
- Don't complain, do it.
+ Don't do ownership validation.
--symfs=<directory>::
Look for files with symbols relative to this directory.
--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]
--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: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+
--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],
between information loss and faster processing especially for
workloads that can have a very long callchain stack.
- Default: 127
+ Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
--ignore-callees=<regex>::
Ignore callees of the function(s) matching the given regex.
--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: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
+
+--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.
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)
# 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
__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) $@
LIBPERF_IN := $(OUTPUT)libperf-in.o
-$(LIBPERF_IN): fixdep FORCE
+$(LIBPERF_IN): prepare fixdep FORCE
$(Q)$(MAKE) $(build)=libperf
$(LIB_FILE): $(LIBPERF_IN)
$(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
.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
endif
HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
PERF_HAVE_JITDUMP := 1
*/
#include <stddef.h>
+#include <errno.h>
+#include <string.h>
#include <dwarf-regs.h>
-
+#include <linux/ptrace.h>
+#include <linux/kernel.h>
+#include "util.h"
struct pt_regs_dwarfnum {
const char *name;
unsigned int dwarfnum;
+ unsigned int ptregs_offset;
};
-#define STR(s) #s
-#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
-#define GPR_DWARFNUM_NAME(num) \
- {.name = STR(%gpr##num), .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+#define REG_DWARFNUM_NAME(r, num) \
+ {.name = STR(%)STR(r), .dwarfnum = num, \
+ .ptregs_offset = offsetof(struct pt_regs, r)}
+#define GPR_DWARFNUM_NAME(num) \
+ {.name = STR(%gpr##num), .dwarfnum = num, \
+ .ptregs_offset = offsetof(struct pt_regs, gpr[num])}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0}
/*
* Reference:
GPR_DWARFNUM_NAME(29),
GPR_DWARFNUM_NAME(30),
GPR_DWARFNUM_NAME(31),
- REG_DWARFNUM_NAME("%msr", 66),
- REG_DWARFNUM_NAME("%ctr", 109),
- REG_DWARFNUM_NAME("%link", 108),
- REG_DWARFNUM_NAME("%xer", 101),
- REG_DWARFNUM_NAME("%dar", 119),
- REG_DWARFNUM_NAME("%dsisr", 118),
+ REG_DWARFNUM_NAME(msr, 66),
+ REG_DWARFNUM_NAME(ctr, 109),
+ REG_DWARFNUM_NAME(link, 108),
+ REG_DWARFNUM_NAME(xer, 101),
+ REG_DWARFNUM_NAME(dar, 119),
+ REG_DWARFNUM_NAME(dsisr, 118),
REG_DWARFNUM_END,
};
return roff->name;
return NULL;
}
+
+int regs_query_register_offset(const char *name)
+{
+ const struct pt_regs_dwarfnum *roff;
+ for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+ if (!strcmp(roff->name, name))
+ return roff->ptregs_offset;
+ return -EINVAL;
+}
ehdr.e_type == ET_DYN;
}
-#if defined(_CALL_ELF) && _CALL_ELF == 2
-void arch__elf_sym_adjust(GElf_Sym *sym)
-{
- sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
-}
-#endif
#endif
#if !defined(_CALL_ELF) || _CALL_ELF != 2
return true;
}
+#ifdef HAVE_LIBELF_SUPPORT
+void arch__sym_update(struct symbol *s, GElf_Sym *sym)
+{
+ s->arch_sym = sym->st_other;
+}
+#endif
+
#define PPC64LE_LEP_OFFSET 8
void arch__fix_tev_from_maps(struct perf_probe_event *pev,
- struct probe_trace_event *tev, struct map *map)
+ struct probe_trace_event *tev, struct map *map,
+ struct symbol *sym)
{
+ int lep_offset;
+
/*
- * ppc64 ABIv2 local entry point is currently always 2 instructions
- * (8 bytes) after the global entry point.
+ * When probing at a function entry point, we normally always want the
+ * LEP since that catches calls to the function through both the GEP and
+ * the LEP. Hence, we would like to probe at an offset of 8 bytes if
+ * the user only specified the function entry.
+ *
+ * However, if the user specifies an offset, we fall back to using the
+ * GEP since all userspace applications (objdump/readelf) show function
+ * disassembly with offsets from the GEP.
+ *
+ * In addition, we shouldn't specify an offset for kretprobes.
*/
- if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
- tev->point.address += PPC64LE_LEP_OFFSET;
+ if (pev->point.offset || pev->point.retprobe || !map || !sym)
+ return;
+
+ lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
+
+ if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
tev->point.offset += PPC64LE_LEP_OFFSET;
+ else if (lep_offset) {
+ if (pev->uprobes)
+ tev->point.address += lep_offset;
+ else
+ tev->point.offset += lep_offset;
}
}
#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::
+ $(call QUIET_CLEAN, x86) $(RM) $(header)
+
+archheaders: $(header)
--- /dev/null
+#
+# 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
+327 64 preadv2 sys_preadv2
+328 64 pwritev2 sys_pwritev2
+
+#
+# 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
--- /dev/null
+#!/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}"
CHECK__(parse_events(evlist, "cycles:u", NULL));
- perf_evlist__config(evlist, &opts);
+ perf_evlist__config(evlist, &opts, NULL);
evsel = perf_evlist__first(evlist);
# 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),
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),
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 */
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;
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;
#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)
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);
+}
+++ /dev/null
-#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__ */
do {
int ret;
again:
- ret = futex_lock_pi(w->futex, NULL, 0, futex_flag);
+ ret = futex_lock_pi(w->futex, NULL, futex_flag);
if (ret) { /* handle lock acquisition */
if (!silent)
/**
* futex_lock_pi() - block on uaddr as a PI mutex
- * @detect: whether (1) or not (0) to perform deadlock detection
*/
static inline int
-futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int detect,
- int opflags)
+futex_lock_pi(u_int32_t *uaddr, struct timespec *timeout, int opflags)
{
- return futex(uaddr, FUTEX_LOCK_PI, detect, timeout, NULL, 0, opflags);
+ return futex(uaddr, FUTEX_LOCK_PI, 0, timeout, NULL, 0, opflags);
}
/**
* Written by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
*/
+#include "debug.h"
#include "../perf.h"
#include "../util/util.h"
#include <subcmd/parse-options.h>
.config = PERF_COUNT_HW_CPU_CYCLES
};
-static void init_cycles(void)
+static int init_cycles(void)
{
cycles_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, perf_event_open_cloexec_flag());
- if (cycles_fd < 0 && errno == ENOSYS)
- die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
- else
- BUG_ON(cycles_fd < 0);
+ if (cycles_fd < 0 && errno == ENOSYS) {
+ pr_debug("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+ return -1;
+ }
+
+ return cycles_fd;
}
static u64 get_cycles(void)
argc = parse_options(argc, argv, options, info->usage, 0);
- if (use_cycles)
- init_cycles();
+ if (use_cycles) {
+ i = init_cycles();
+ if (i < 0) {
+ fprintf(stderr, "Failed to open cycles counter\n");
+ return i;
+ }
+ }
size = (size_t)perf_atoll((char *)size_str);
size_total = (double)size * nr_loops;
#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;
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;
}
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,
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)
usage_with_options(config_usage, config_options);
}
+ perf_config_set__delete(set);
+out_err:
return ret;
}
struct rb_root *root;
struct rb_node *next;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
struct rb_root *root;
struct rb_node *next;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
.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,
}
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) {
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.
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;
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];
#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"
#include "util/bpf-loader.h"
+#include "util/trigger.h"
#include "asm/bug.h"
#include <unistd.h>
bool no_buildid_cache;
bool no_buildid_cache_set;
bool buildid_all;
+ bool timestamp_filename;
+ bool switch_output;
unsigned long long samples;
};
static volatile int done;
static volatile int signr = -1;
static volatile int child_finished;
-static volatile int auxtrace_snapshot_enabled;
-static volatile int auxtrace_snapshot_err;
+
static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
static void sig_handler(int sig)
{
{
pr_debug("Recording AUX area tracing snapshot\n");
if (record__auxtrace_read_snapshot_all(rec) < 0) {
- auxtrace_snapshot_err = -1;
+ trigger_error(&auxtrace_snapshot_trigger);
} else {
- auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
- if (!auxtrace_snapshot_err)
- auxtrace_snapshot_enabled = 1;
+ if (auxtrace_record__snapshot_finish(rec->itr))
+ trigger_error(&auxtrace_snapshot_trigger);
+ else
+ trigger_ready(&auxtrace_snapshot_trigger);
}
}
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:
return;
}
+static int record__synthesize_workload(struct record *rec)
+{
+ struct {
+ struct thread_map map;
+ struct thread_map_data map_data;
+ } thread_map;
+
+ thread_map.map.nr = 1;
+ thread_map.map.map[0].pid = rec->evlist->workload.pid;
+ thread_map.map.map[0].comm = NULL;
+ return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map,
+ process_synthesized_event,
+ &rec->session->machines.host,
+ rec->opts.sample_address,
+ rec->opts.proc_map_timeout);
+}
+
+static int record__synthesize(struct record *rec);
+
+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);
+
+ /* Output tracking events */
+ if (!at_exit) {
+ record__synthesize(rec);
+
+ /*
+ * In 'perf record --switch-output' without -a,
+ * record__synthesize() in record__switch_output() won't
+ * generate tracking events because there's no thread_map
+ * in evlist. Which causes newly created perf.data doesn't
+ * contain map and comm information.
+ * Create a fake thread_map and directly call
+ * perf_event__synthesize_thread_map() for those events.
+ */
+ if (target__none(&rec->opts.target))
+ record__synthesize_workload(rec);
+ }
+ return fd;
+}
+
static volatile int workload_exec_errno;
/*
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;
}
}
+ 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);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
- if (rec->opts.auxtrace_snapshot_mode)
+
+ if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
signal(SIGUSR2, snapshot_sig_handler);
- else
+ if (rec->opts.auxtrace_snapshot_mode)
+ trigger_on(&auxtrace_snapshot_trigger);
+ if (rec->switch_output)
+ trigger_on(&switch_output_trigger);
+ } else {
signal(SIGUSR2, SIG_IGN);
+ }
session = perf_session__new(file, false, tool);
if (session == NULL) {
perf_evlist__enable(rec->evlist);
}
- auxtrace_snapshot_enabled = 1;
+ trigger_ready(&auxtrace_snapshot_trigger);
+ trigger_ready(&switch_output_trigger);
for (;;) {
unsigned long long hits = rec->samples;
if (record__mmap_read_all(rec) < 0) {
- auxtrace_snapshot_enabled = 0;
+ trigger_error(&auxtrace_snapshot_trigger);
+ trigger_error(&switch_output_trigger);
err = -1;
goto out_child;
}
if (auxtrace_record__snapshot_started) {
auxtrace_record__snapshot_started = 0;
- if (!auxtrace_snapshot_err)
+ if (!trigger_is_error(&auxtrace_snapshot_trigger))
record__read_auxtrace_snapshot(rec);
- if (auxtrace_snapshot_err) {
+ if (trigger_is_error(&auxtrace_snapshot_trigger)) {
pr_err("AUX area tracing snapshot failed\n");
err = -1;
goto out_child;
}
}
+ if (trigger_is_hit(&switch_output_trigger)) {
+ trigger_ready(&switch_output_trigger);
+
+ if (!quiet)
+ fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n",
+ waking);
+ waking = 0;
+ fd = record__switch_output(rec, false);
+ if (fd < 0) {
+ pr_err("Failed to switch to new file\n");
+ trigger_error(&switch_output_trigger);
+ err = fd;
+ goto out_child;
+ }
+ }
+
if (hits == rec->samples) {
if (done || draining)
break;
* disable events in this case.
*/
if (done && !disabled && !target__none(&opts->target)) {
- auxtrace_snapshot_enabled = 0;
+ trigger_off(&auxtrace_snapshot_trigger);
perf_evlist__disable(rec->evlist);
disabled = true;
}
}
- auxtrace_snapshot_enabled = 0;
+ trigger_off(&auxtrace_snapshot_trigger);
+ trigger_off(&switch_output_trigger);
if (forks && workload_exec_errno) {
char msg[STRERR_BUFSIZE];
/* 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),
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:
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)
{
- struct record_opts *record = (struct record_opts *)opt->value;
+ struct callchain_param *callchain = opt->value;
- record->callgraph_set = true;
- callchain_param.enabled = true;
+ callchain->enabled = true;
- if (callchain_param.record_mode == CALLCHAIN_NONE)
- callchain_param.record_mode = CALLCHAIN_FP;
+ if (callchain->record_mode == CALLCHAIN_NONE)
+ callchain->record_mode = CALLCHAIN_FP;
- callchain_debug();
+ callchain_debug(callchain);
return 0;
}
record__parse_mmap_pages),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
- OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
+ OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
NULL, "enables call-graph recording" ,
&record_callchain_opt),
OPT_CALLBACK(0, "call-graph", &record.opts,
"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_BOOLEAN(0, "switch-output", &record.switch_output,
+ "Switch output when receive SIGUSR2"),
OPT_END()
};
return -EINVAL;
}
+ if (rec->switch_output)
+ rec->timestamp_filename = true;
+
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
if (err)
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);
"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
"even with a suitable vmlinux or kallsyms file.\n\n");
- if (rec->no_buildid_cache || rec->no_buildid)
+ if (rec->no_buildid_cache || rec->no_buildid) {
disable_buildid_cache();
+ } else if (rec->switch_output) {
+ /*
+ * In 'perf record --switch-output', disable buildid
+ * generation by default to reduce data file switching
+ * overhead. Still generate buildid if they are required
+ * explicitly using
+ *
+ * perf record --signal-trigger --no-no-buildid \
+ * --no-no-buildid-cache
+ *
+ * Following code equals to:
+ *
+ * if ((rec->no_buildid || !rec->no_buildid_set) &&
+ * (rec->no_buildid_cache || !rec->no_buildid_cache_set))
+ * disable_buildid_cache();
+ */
+ bool disable = true;
+
+ if (rec->no_buildid_set && !rec->no_buildid)
+ disable = false;
+ if (rec->no_buildid_cache_set && !rec->no_buildid_cache)
+ disable = false;
+ if (disable) {
+ rec->no_buildid = true;
+ rec->no_buildid_cache = true;
+ disable_buildid_cache();
+ }
+ }
if (rec->evlist->nr_entries == 0 &&
perf_evlist__add_default(rec->evlist) < 0) {
static void snapshot_sig_handler(int sig __maybe_unused)
{
- if (!auxtrace_snapshot_enabled)
- return;
- auxtrace_snapshot_enabled = 0;
- auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
- auxtrace_record__snapshot_started = 1;
+ if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
+ trigger_hit(&auxtrace_snapshot_trigger);
+ auxtrace_record__snapshot_started = 1;
+ if (auxtrace_record__snapshot_start(record.itr))
+ trigger_error(&auxtrace_snapshot_trigger);
+ }
+
+ if (trigger_is_ready(&switch_output_trigger))
+ trigger_hit(&switch_output_trigger);
}
struct perf_tool tool;
struct perf_session *session;
bool use_tui, use_gtk, use_stdio;
- bool dont_use_callchains;
bool show_full_info;
bool show_threads;
bool inverted_callchain;
sample_type |= PERF_SAMPLE_BRANCH_STACK;
if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
- if (sort__has_parent) {
+ if (perf_hpp_list.parent) {
ui__error("Selected --sort parent, but no "
"callchain data. Did you call "
"'perf record' without -g?\n");
"you call 'perf record' without -g?\n");
return -1;
}
- } else if (!rep->dont_use_callchains &&
+ } else if (!callchain_param.enabled &&
callchain_param.mode != CHAIN_NONE &&
!symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
static int
report_parse_callchain_opt(const struct option *opt, const char *arg, int unset)
{
- struct report *rep = (struct report *)opt->value;
+ struct callchain_param *callchain = opt->value;
+ callchain->enabled = !unset;
/*
* --no-call-graph
*/
if (unset) {
- rep->dont_use_callchains = true;
+ symbol_conf.use_callchain = false;
+ callchain->mode = CHAIN_NONE;
return 0;
}
.ordered_events = true,
.ordering_requires_timestamps = true,
},
- .max_stack = PERF_MAX_STACK_DEPTH,
+ .max_stack = sysctl_perf_event_max_stack,
.pretty_printing_style = "normal",
.socket_filter = -1,
};
"regex filter to identify parent, see: '--sort parent'"),
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
"Only display entries with parent-match"),
- OPT_CALLBACK_DEFAULT('g', "call-graph", &report,
+ OPT_CALLBACK_DEFAULT('g', "call-graph", &callchain_param,
"print_type,threshold[,print_limit],order,sort_key[,branch],value",
report_callchain_help, &report_parse_callchain_opt,
callchain_default_opt),
OPT_INTEGER(0, "max-stack", &report.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)),
+ "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
"alias for inverted call graph"),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
goto error;
}
- sort__need_collapse = true;
+ perf_hpp_list.need_collapse = true;
}
/* Force tty output for header output and per-thread stat. */
#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"
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;
struct list_head sort_list, cmp_pid;
bool force;
bool skip_merge;
+ struct perf_sched_map map;
};
static u64 get_nsecs(void)
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)
{
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)
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;
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;
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))
"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
"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[] = {
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);
#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"
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;
}
/*
/* print branch_from information */
if (PRINT_FIELD(IP)) {
unsigned int print_opts = output[attr->type].print_ip_opts;
+ struct callchain_cursor *cursor = NULL;
- 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, &callchain_cursor, evsel,
+ sample, NULL, NULL, scripting_max_stack) == 0)
+ cursor = &callchain_cursor;
+
+ 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 */
printf("%16" PRIu64, sample->weight);
if (PRINT_FIELD(IP)) {
- if (!symbol_conf.use_callchain)
- printf(" ");
- else
- printf("\n");
+ struct callchain_cursor *cursor = NULL;
+
+ if (symbol_conf.use_callchain && sample->callchain &&
+ thread__resolve_callchain(al->thread, &callchain_cursor, evsel,
+ sample, NULL, NULL, scripting_max_stack) == 0)
+ cursor = &callchain_cursor;
- 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))
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"
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];
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);
}
*/
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;
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;
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))
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;
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);
.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,
"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: kernel.perf_event_max_stack or " __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,
NULL
};
+ scripting_max_stack = sysctl_perf_event_max_stack;
+
setup_scripting();
argc = parse_options_subcommand(argc, argv, options, script_subcommands, script_usage,
return -1;
}
}
+
+ if (verbose > 1) {
+ fprintf(stat_config.output,
+ "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+ perf_evsel__name(counter),
+ cpu,
+ count->val, count->ena, count->run);
+ }
}
}
struct hist_entry *he = iter->he;
struct perf_evsel *evsel = iter->evsel;
- if (sort__has_sym && single)
+ if (perf_hpp_list.sym && single)
perf_top__record_precise_ip(top, he, evsel->idx, al->addr);
hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
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:
return -1;
}
-static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
+static int callchain_param__setup_sample_type(struct callchain_param *callchain)
{
- if (!sort__has_sym) {
- if (symbol_conf.use_callchain) {
+ if (!perf_hpp_list.sym) {
+ if (callchain->enabled) {
ui__error("Selected -g but \"sym\" not present in --sort/-s.");
return -EINVAL;
}
- } else if (callchain_param.mode != CHAIN_NONE) {
- if (callchain_register_param(&callchain_param) < 0) {
+ } else if (callchain->mode != CHAIN_NONE) {
+ if (callchain_register_param(callchain) < 0) {
ui__error("Can't register callchain params.\n");
return -EINVAL;
}
goto out_delete;
}
- ret = perf_top__setup_sample_type(top);
+ ret = callchain_param__setup_sample_type(&callchain_param);
if (ret)
goto out_delete;
machine__synthesize_threads(&top->session->machines.host, &opts->target,
top->evlist->threads, false, opts->proc_map_timeout);
- if (sort__has_socket) {
+ if (perf_hpp_list.socket) {
ret = perf_env__read_cpu_topology_map(&perf_env);
if (ret < 0)
goto out_err_cpu_topo;
static int
parse_callchain_opt(const struct option *opt, const char *arg, int unset)
{
- struct record_opts *record = (struct record_opts *)opt->value;
+ struct callchain_param *callchain = opt->value;
- record->callgraph_set = true;
- callchain_param.enabled = !unset;
- callchain_param.record_mode = CALLCHAIN_FP;
+ callchain->enabled = !unset;
+ callchain->record_mode = CALLCHAIN_FP;
/*
* --no-call-graph
*/
if (unset) {
symbol_conf.use_callchain = false;
- callchain_param.record_mode = CALLCHAIN_NONE;
+ callchain->record_mode = CALLCHAIN_NONE;
return 0;
}
},
.proc_map_timeout = 500,
},
- .max_stack = PERF_MAX_STACK_DEPTH,
+ .max_stack = sysctl_perf_event_max_stack,
.sym_pcnt_filter = 5,
};
struct record_opts *opts = &top.record_opts;
"output field(s): overhead, period, sample plus all of sort keys"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
- OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
+ OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
NULL, "enables call-graph recording and display",
&callchain_opt),
- OPT_CALLBACK(0, "call-graph", &top.record_opts,
+ OPT_CALLBACK(0, "call-graph", &callchain_param,
"record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]",
top_callchain_help, &parse_callchain_opt),
OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
"Accumulate callchains of children and show total overhead as well"),
OPT_INTEGER(0, "max-stack", &top.max_stack,
"Set the maximum stack depth when parsing the callchain. "
- "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
+ "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
"ignore callees of these functions in call graphs",
report_parse_ignore_callees_opt),
sort__mode = SORT_MODE__TOP;
/* display thread wants entries to be collapsed in a different tree */
- sort__need_collapse = 1;
+ perf_hpp_list.need_collapse = 1;
if (top.use_stdio)
use_browser = 0;
top.sym_evsel = perf_evlist__first(top.evlist);
- if (!symbol_conf.use_callchain) {
+ if (!callchain_param.enabled) {
symbol_conf.cumulate_callchain = false;
perf_hpp__cancel_cumulate();
}
#include "trace-event.h"
#include "util/parse-events.h"
#include "util/bpf-loader.h"
+#include "callchain.h"
+#include "syscalltbl.h"
+#include "rb_resort.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
-
-#ifndef PERF_FLAG_FD_NO_GROUP
-# define PERF_FLAG_FD_NO_GROUP (1UL << 0)
-#endif
-
-#ifndef PERF_FLAG_FD_OUTPUT
-# define PERF_FLAG_FD_OUTPUT (1UL << 1)
-#endif
-
-#ifndef PERF_FLAG_PID_CGROUP
-# define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
-#endif
-
-#ifndef PERF_FLAG_FD_CLOEXEC
-# 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;
#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)
{
#define SCA_FLOCK syscall_arg__scnprintf_flock
-static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
-{
- enum syscall_futex_args {
- SCF_UADDR = (1 << 0),
- SCF_OP = (1 << 1),
- SCF_VAL = (1 << 2),
- SCF_TIMEOUT = (1 << 3),
- SCF_UADDR2 = (1 << 4),
- SCF_VAL3 = (1 << 5),
- };
- int op = arg->val;
- int cmd = op & FUTEX_CMD_MASK;
- size_t printed = 0;
-
- switch (cmd) {
-#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
- P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
- P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break;
- P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break;
- P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break;
- P_FUTEX_OP(WAKE_OP); break;
- P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
- P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
- P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break;
- P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break;
- P_FUTEX_OP(WAIT_REQUEUE_PI); break;
- default: printed = scnprintf(bf, size, "%#x", cmd); break;
- }
-
- if (op & FUTEX_PRIVATE_FLAG)
- printed += scnprintf(bf + printed, size - printed, "|PRIV");
-
- if (op & FUTEX_CLOCK_REALTIME)
- printed += scnprintf(bf + printed, size - printed, "|CLKRT");
-
- return printed;
-}
-
-#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op
-
static const char *bpf_cmd[] = {
"MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
"MAP_GET_NEXT_KEY", "PROG_LOAD",
};
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
-#ifndef MSG_WAITFORONE
-#define MSG_WAITFORONE 0x10000
-#endif
-#ifndef MSG_SENDPAGE_NOTLAST
-#define MSG_SENDPAGE_NOTLAST 0x20000
-#endif
-#ifndef MSG_FASTOPEN
-#define MSG_FASTOPEN 0x20000000
-#endif
-
-static size_t syscall_arg__scnprintf_msg_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_MSG_FLAG(n) \
- if (flags & MSG_##n) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~MSG_##n; \
- }
-
- P_MSG_FLAG(OOB);
- P_MSG_FLAG(PEEK);
- P_MSG_FLAG(DONTROUTE);
- P_MSG_FLAG(TRYHARD);
- P_MSG_FLAG(CTRUNC);
- P_MSG_FLAG(PROBE);
- P_MSG_FLAG(TRUNC);
- P_MSG_FLAG(DONTWAIT);
- P_MSG_FLAG(EOR);
- P_MSG_FLAG(WAITALL);
- P_MSG_FLAG(FIN);
- P_MSG_FLAG(SYN);
- P_MSG_FLAG(CONFIRM);
- P_MSG_FLAG(RST);
- P_MSG_FLAG(ERRQUEUE);
- P_MSG_FLAG(NOSIGNAL);
- P_MSG_FLAG(MORE);
- P_MSG_FLAG(WAITFORONE);
- P_MSG_FLAG(SENDPAGE_NOTLAST);
- P_MSG_FLAG(FASTOPEN);
- P_MSG_FLAG(CMSG_CLOEXEC);
-#undef P_MSG_FLAG
-
- if (flags)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
- return printed;
-}
-
-#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags
-
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
struct syscall_arg *arg)
{
#define SCA_FILENAME syscall_arg__scnprintf_filename
-static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
- struct syscall_arg *arg)
+static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
{
int printed = 0, flags = arg->val;
- if (!(flags & O_CREAT))
- arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
-
- if (flags == 0)
- return scnprintf(bf, size, "RDONLY");
#define P_FLAG(n) \
if (flags & O_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
flags &= ~O_##n; \
}
- P_FLAG(APPEND);
- P_FLAG(ASYNC);
P_FLAG(CLOEXEC);
- P_FLAG(CREAT);
- P_FLAG(DIRECT);
- P_FLAG(DIRECTORY);
- P_FLAG(EXCL);
- P_FLAG(LARGEFILE);
- P_FLAG(NOATIME);
- P_FLAG(NOCTTY);
-#ifdef O_NONBLOCK
P_FLAG(NONBLOCK);
-#elif O_NDELAY
- P_FLAG(NDELAY);
-#endif
-#ifdef O_PATH
- P_FLAG(PATH);
-#endif
- P_FLAG(RDWR);
-#ifdef O_DSYNC
- if ((flags & O_SYNC) == O_SYNC)
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
- else {
- P_FLAG(DSYNC);
- }
-#else
- P_FLAG(SYNC);
-#endif
- P_FLAG(TRUNC);
- P_FLAG(WRONLY);
#undef P_FLAG
if (flags)
return printed;
}
-#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
+#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
-static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
- struct syscall_arg *arg)
-{
- int printed = 0, flags = arg->val;
+#if defined(__i386__) || defined(__x86_64__)
+/*
+ * FIXME: Make this available to all arches.
+ */
+#define TCGETS 0x5401
- if (flags == 0)
- return 0;
+static const char *tioctls[] = {
+ "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
+ "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
+ "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
+ "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
+ "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
+ "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
+ "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
+ "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
+ "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
+ "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
+ "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
+ [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
+ "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
+ "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
+ "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
+};
-#define P_FLAG(n) \
- if (flags & PERF_FLAG_##n) { \
- printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~PERF_FLAG_##n; \
- }
+static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
+#endif /* defined(__i386__) || defined(__x86_64__) */
- P_FLAG(FD_NO_GROUP);
- P_FLAG(FD_OUTPUT);
- P_FLAG(PID_CGROUP);
- P_FLAG(FD_CLOEXEC);
-#undef P_FLAG
+#ifndef SECCOMP_SET_MODE_STRICT
+#define SECCOMP_SET_MODE_STRICT 0
+#endif
+#ifndef SECCOMP_SET_MODE_FILTER
+#define SECCOMP_SET_MODE_FILTER 1
+#endif
- if (flags)
- printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+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_PERF_FLAGS syscall_arg__scnprintf_perf_flags
+#define SCA_SECCOMP_OP syscall_arg__scnprintf_seccomp_op
-static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
+#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;
- if (flags == 0)
- return scnprintf(bf, size, "NONE");
#define P_FLAG(n) \
- if (flags & EFD_##n) { \
+ if (flags & SECCOMP_FILTER_FLAG_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~EFD_##n; \
+ flags &= ~SECCOMP_FILTER_FLAG_##n; \
}
- P_FLAG(SEMAPHORE);
- P_FLAG(CLOEXEC);
- P_FLAG(NONBLOCK);
+ P_FLAG(TSYNC);
#undef P_FLAG
if (flags)
return printed;
}
-#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags
+#define SCA_SECCOMP_FLAGS syscall_arg__scnprintf_seccomp_flags
-static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
- struct syscall_arg *arg)
+#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 & O_##n) { \
+ if (flags & GRND_##n) { \
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
- flags &= ~O_##n; \
+ flags &= ~GRND_##n; \
}
- P_FLAG(CLOEXEC);
+ P_FLAG(RANDOM);
P_FLAG(NONBLOCK);
#undef P_FLAG
return printed;
}
-#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
-
-static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
-{
- int sig = arg->val;
-
- switch (sig) {
-#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
- P_SIGNUM(HUP);
- P_SIGNUM(INT);
- P_SIGNUM(QUIT);
- P_SIGNUM(ILL);
- P_SIGNUM(TRAP);
- P_SIGNUM(ABRT);
- P_SIGNUM(BUS);
- P_SIGNUM(FPE);
- P_SIGNUM(KILL);
- P_SIGNUM(USR1);
- P_SIGNUM(SEGV);
- P_SIGNUM(USR2);
- P_SIGNUM(PIPE);
- P_SIGNUM(ALRM);
- P_SIGNUM(TERM);
- P_SIGNUM(CHLD);
- P_SIGNUM(CONT);
- P_SIGNUM(STOP);
- P_SIGNUM(TSTP);
- P_SIGNUM(TTIN);
- P_SIGNUM(TTOU);
- P_SIGNUM(URG);
- P_SIGNUM(XCPU);
- P_SIGNUM(XFSZ);
- P_SIGNUM(VTALRM);
- P_SIGNUM(PROF);
- P_SIGNUM(WINCH);
- P_SIGNUM(IO);
- P_SIGNUM(PWR);
- P_SIGNUM(SYS);
-#ifdef SIGEMT
- P_SIGNUM(EMT);
-#endif
-#ifdef SIGSTKFLT
- P_SIGNUM(STKFLT);
-#endif
-#ifdef SIGSWI
- P_SIGNUM(SWI);
-#endif
- default: break;
- }
-
- return scnprintf(bf, size, "%#x", sig);
-}
-
-#define SCA_SIGNUM syscall_arg__scnprintf_signum
-
-#if defined(__i386__) || defined(__x86_64__)
-/*
- * FIXME: Make this available to all arches.
- */
-#define TCGETS 0x5401
-
-static const char *tioctls[] = {
- "TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
- "TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
- "TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
- "TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
- "TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
- "TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
- "TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
- "TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
- "TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
- "TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
- "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
- [0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
- "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
- "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
- "TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
-};
-
-static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
-#endif /* defined(__i386__) || defined(__x86_64__) */
+#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/futex_op.c"
+#include "trace/beauty/mmap.c"
+#include "trace/beauty/mode_t.c"
+#include "trace/beauty/msg_flags.c"
+#include "trace/beauty/open_flags.c"
+#include "trace/beauty/perf_event_open.c"
+#include "trace/beauty/pid.c"
+#include "trace/beauty/sched_policy.c"
+#include "trace/beauty/signum.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[] = {
{ .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, },
{ .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 */ }, },
[1] = SCA_FILENAME, /* filename */
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
{ .name = "perf_event_open", .errmsg = true,
- .arg_scnprintf = { [1] = SCA_INT, /* pid */
- [2] = SCA_INT, /* cpu */
+ .arg_scnprintf = { [2] = SCA_INT, /* cpu */
[3] = SCA_FD, /* group_fd */
[4] = SCA_PERF_FLAGS, /* flags */ }, },
{ .name = "pipe2", .errmsg = true,
.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 */
{ .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 */ }, },
.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,
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);
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;
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;
}
{
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;
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) {
"%ld", val);
}
}
- } else {
+ } else if (IS_ERR(sc->tp_format)) {
+ /*
+ * If we managed to read the tracepoint /format file, then we
+ * may end up not having any args, like with gettid(), so only
+ * print the raw args when we didn't manage to read it.
+ */
int i = 0;
while (i < 6) {
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;
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);
}
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)
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;
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;
} 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;
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);
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;
union perf_event *event __maybe_unused,
struct perf_sample *sample)
{
+ int callchain_ret = 0;
+
+ 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;
+ }
+ }
+
trace__printf_interrupted_entry(trace, sample);
trace__fprintf_tstamp(trace, sample->time, trace->output);
}
fprintf(trace->output, ")\n");
+
+ 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:
return 0;
}
char map_type = 'd';
struct thread_trace *ttrace;
int err = -1;
+ int callchain_ret = 0;
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+
+ 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_put;
+ callchain_ret = 1;
+ }
+ }
+
ttrace = thread__trace(thread, trace->output);
if (ttrace == NULL)
goto out_put;
print_location(trace->output, sample, &al, true, false);
fprintf(trace->output, " (%c%c)\n", map_type, al.level);
+
+ 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:
err = 0;
out_put:
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,
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;
return true;
}
-static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
- u64 config)
+static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
{
struct perf_evsel *evsel;
struct perf_event_attr attr = {
event_attr_init(&attr);
evsel = perf_evsel__new(&attr);
- if (!evsel)
- return -ENOMEM;
-
- evsel->handler = trace__pgfault;
- perf_evlist__add(evlist, evsel);
+ if (evsel)
+ evsel->handler = trace__pgfault;
- return 0;
+ return evsel;
}
static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
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;
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",
perf_evlist__add(evlist, sys_enter);
perf_evlist__add(evlist, sys_exit);
+ if (callchain_param.enabled && !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;
static int trace__run(struct trace *trace, int argc, const char **argv)
{
struct perf_evlist *evlist = trace->evlist;
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL;
int err = -1, i;
unsigned long before;
const bool forks = argc > 0;
if (trace->trace_syscalls)
trace->vfs_getname = perf_evlist__add_vfs_getname(evlist);
- if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
- perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ)) {
- goto out_error_mem;
+ if ((trace->trace_pgfaults & TRACE_PFMAJ)) {
+ pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
+ if (pgfault_maj == NULL)
+ goto out_error_mem;
+ perf_evlist__add(evlist, pgfault_maj);
}
- if ((trace->trace_pgfaults & TRACE_PFMIN) &&
- perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
- goto out_error_mem;
+ if ((trace->trace_pgfaults & TRACE_PFMIN)) {
+ pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
+ if (pgfault_min == NULL)
+ goto out_error_mem;
+ perf_evlist__add(evlist, pgfault_min);
+ }
if (trace->sched &&
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
goto out_delete_evlist;
}
- perf_evlist__config(evlist, &trace->opts);
+ perf_evlist__config(evlist, &trace->opts, NULL);
+
+ if (callchain_param.enabled) {
+ bool use_identifier = false;
+
+ if (trace->syscalls.events.sys_exit) {
+ perf_evsel__config_callchain(trace->syscalls.events.sys_exit,
+ &trace->opts, &callchain_param);
+ use_identifier = true;
+ }
+
+ if (pgfault_maj) {
+ perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
+ use_identifier = true;
+ }
+
+ if (pgfault_min) {
+ perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
+ use_identifier = true;
+ }
+
+ if (use_identifier) {
+ /*
+ * 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);
return printed;
}
+DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs,
+ struct stats *stats;
+ double msecs;
+ int syscall;
+)
+{
+ struct int_node *source = rb_entry(nd, struct int_node, rb_node);
+ struct stats *stats = source->priv;
+
+ entry->syscall = source->i;
+ entry->stats = stats;
+ entry->msecs = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0;
+}
+
static size_t thread__dump_stats(struct thread_trace *ttrace,
struct trace *trace, FILE *fp)
{
- struct stats *stats;
size_t printed = 0;
struct syscall *sc;
- struct int_node *inode = intlist__first(ttrace->syscall_stats);
+ struct rb_node *nd;
+ DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
- if (inode == NULL)
+ if (syscall_stats == NULL)
return 0;
printed += fprintf(fp, "\n");
printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n");
printed += fprintf(fp, " --------------- -------- --------- --------- --------- --------- ------\n");
- /* each int_node is a syscall */
- while (inode) {
- stats = inode->priv;
+ resort_rb__for_each(nd, syscall_stats) {
+ struct stats *stats = syscall_stats_entry->stats;
if (stats) {
double min = (double)(stats->min) / NSEC_PER_MSEC;
double max = (double)(stats->max) / NSEC_PER_MSEC;
pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
avg /= NSEC_PER_MSEC;
- sc = &trace->syscalls.table[inode->i];
+ sc = &trace->syscalls.table[syscall_stats_entry->syscall];
printed += fprintf(fp, " %-15s", sc->name);
printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
- n, avg * n, min, avg);
+ n, syscall_stats_entry->msecs, min, avg);
printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
}
-
- inode = intlist__next(inode);
}
+ resort_rb__delete(syscall_stats);
printed += fprintf(fp, "\n\n");
return printed;
}
-/* struct used to pass data to per-thread function */
-struct summary_data {
- FILE *fp;
- struct trace *trace;
- size_t printed;
-};
-
-static int trace__fprintf_one_thread(struct thread *thread, void *priv)
+static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
{
- struct summary_data *data = priv;
- FILE *fp = data->fp;
- size_t printed = data->printed;
- struct trace *trace = data->trace;
+ size_t printed = 0;
struct thread_trace *ttrace = thread__priv(thread);
double ratio;
printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
if (ttrace->pfmin)
printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
- printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+ if (trace->sched)
+ printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+ else if (fputc('\n', fp) != EOF)
+ ++printed;
+
printed += thread__dump_stats(ttrace, trace, fp);
- data->printed += printed;
+ return printed;
+}
- return 0;
+static unsigned long thread__nr_events(struct thread_trace *ttrace)
+{
+ return ttrace ? ttrace->nr_events : 0;
+}
+
+DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_events(b->thread->priv)),
+ struct thread *thread;
+)
+{
+ entry->thread = rb_entry(nd, struct thread, rb_node);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
- struct summary_data data = {
- .fp = fp,
- .trace = trace
- };
- data.printed = trace__fprintf_threads_header(fp);
+ DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
+ size_t printed = trace__fprintf_threads_header(fp);
+ struct rb_node *nd;
+
+ if (threads == NULL) {
+ fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+ return 0;
+ }
- machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);
+ resort_rb__for_each(nd, threads)
+ printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
- return data.printed;
+ resort_rb__delete(threads);
+
+ return printed;
}
static int trace__set_duration(const struct option *opt, const char *str,
NULL
};
struct trace trace = {
- .audit = {
- .machine = audit_detect_machine(),
- .open_id = audit_name_to_syscall("open", trace.audit.machine),
- },
.syscalls = {
. max = -1,
},
.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;
"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: kernel.perf_event_max_stack or " __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 __maybe_unused max_stack_user_set = true;
+ bool mmap_pages_user_set = true;
const char * const trace_subcommands[] = { "record", NULL };
int err;
char bf[BUFSIZ];
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;
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 = sysctl_perf_event_max_stack;
+ max_stack_user_set = false;
+ }
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+ if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled)
+ record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
+#endif
+
+ if (callchain_param.enabled) {
+ 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);
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) {
}
}
+ trace.open_id = syscalltbl__id(trace.sctbl, "open");
+
if (ev_qualifier_str != NULL) {
const char *s = ev_qualifier_str;
struct strlist_config slist_config = {
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
$(call detected,CONFIG_X86_64)
ifneq ($(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
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);
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;
struct timespec ts;
int ret;
+ if (use_arch_timestamp)
+ return get_arch_timestamp();
+
ret = clock_gettime(perf_clk_id, &ts);
if (ret)
return 0;
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;
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));
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;
#include <subcmd/parse-options.h>
#include "util/bpf-loader.h"
#include "util/debug.h"
+#include <api/fs/fs.h>
#include <api/fs/tracing_path.h>
#include <pthread.h>
#include <stdlib.h>
{
const char *cmd;
char sbuf[STRERR_BUFSIZE];
+ int value;
/* libsubcmd init */
exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
page_size = sysconf(_SC_PAGE_SIZE);
cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
+ if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
+ sysctl_perf_event_max_stack = value;
+
cmd = extract_argv0_path(argv[0]);
if (!cmd)
cmd = "perf-help";
srandom(time(NULL));
perf_config(perf_default_config, NULL);
+ set_buildid_dir(NULL);
/* get debugfs/tracefs mount point from /proc/mounts */
tracing_path_mount();
}
if (!prefixcmp(cmd, "trace")) {
#ifdef HAVE_LIBAUDIT_SUPPORT
- set_buildid_dir(NULL);
setup_path();
argv[0] = "trace";
return cmd_trace(argc, argv, NULL);
argc--;
handle_options(&argv, &argc, NULL);
commit_pager_choice();
- set_buildid_dir(NULL);
if (argc > 0) {
if (!prefixcmp(argv[0], "--"))
bool sample_weight;
bool sample_time;
bool sample_time_set;
- bool callgraph_set;
bool period;
bool running_time;
bool full_auxtrace;
#
# ubuntu:
#
-# $ sudo apt-get install postgresql
+# $ sudo apt-get install postgresql python-pyside.qtsql libqt4-sql-psql
# $ sudo su - postgres
-# $ createuser <your user id here>
-# Shall the new role be a superuser? (y/n) y
+# $ createuser -s <your user id here>
#
# An example of using this script with Intel PT:
#
perf_db_export_mode = True
perf_db_export_calls = False
+perf_db_export_callchains = False
+
def usage():
- print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
+ print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]"
print >> sys.stderr, "where: columns 'all' or 'branches'"
- print >> sys.stderr, " calls 'calls' => create calls table"
+ print >> sys.stderr, " calls 'calls' => create calls and call_paths table"
+ print >> sys.stderr, " callchains 'callchains' => create call_paths table"
raise Exception("Too few arguments")
if (len(sys.argv) < 2):
branches = (columns == "branches")
-if (len(sys.argv) >= 4):
- if (sys.argv[3] == "calls"):
+for i in range(3,len(sys.argv)):
+ if (sys.argv[i] == "calls"):
perf_db_export_calls = True
+ elif (sys.argv[i] == "callchains"):
+ perf_db_export_callchains = True
else:
usage()
'transaction bigint,'
'data_src bigint,'
'branch_type integer,'
- 'in_tx boolean)')
+ 'in_tx boolean,'
+ 'call_path_id bigint)')
-if perf_db_export_calls:
+if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'CREATE TABLE call_paths ('
'id bigint NOT NULL,'
'parent_id bigint,'
'symbol_id bigint,'
'ip bigint)')
+if perf_db_export_calls:
do_query(query, 'CREATE TABLE calls ('
'id bigint NOT NULL,'
'thread_id bigint,'
'(SELECT tid FROM threads WHERE id = thread_id) AS tid'
' FROM comm_threads')
-if perf_db_export_calls:
+if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'CREATE VIEW call_paths_view AS '
'SELECT '
'c.id,'
'(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,'
'(SELECT dso FROM symbols_view WHERE id = p.symbol_id) AS parent_dso_short_name'
' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id')
+if perf_db_export_calls:
do_query(query, 'CREATE VIEW calls_view AS '
'SELECT '
'calls.id,'
symbol_file = open_output_file("symbol_table.bin")
branch_type_file = open_output_file("branch_type_table.bin")
sample_file = open_output_file("sample_table.bin")
-if perf_db_export_calls:
+if perf_db_export_calls or perf_db_export_callchains:
call_path_file = open_output_file("call_path_table.bin")
+if perf_db_export_calls:
call_file = open_output_file("call_table.bin")
def trace_begin():
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
- sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
- if perf_db_export_calls:
+ sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ if perf_db_export_calls or perf_db_export_callchains:
call_path_table(0, 0, 0, 0)
unhandled_count = 0
copy_output_file(symbol_file, "symbols")
copy_output_file(branch_type_file, "branch_types")
copy_output_file(sample_file, "samples")
- if perf_db_export_calls:
+ if perf_db_export_calls or perf_db_export_callchains:
copy_output_file(call_path_file, "call_paths")
+ if perf_db_export_calls:
copy_output_file(call_file, "calls")
print datetime.datetime.today(), "Removing intermediate files..."
remove_output_file(symbol_file)
remove_output_file(branch_type_file)
remove_output_file(sample_file)
- if perf_db_export_calls:
+ if perf_db_export_calls or perf_db_export_callchains:
remove_output_file(call_path_file)
+ if perf_db_export_calls:
remove_output_file(call_file)
os.rmdir(output_dir_name)
print datetime.datetime.today(), "Adding primary keys"
do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)')
- if perf_db_export_calls:
+ if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)')
+ if perf_db_export_calls:
do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)')
print datetime.datetime.today(), "Adding foreign keys"
'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id),'
'ADD CONSTRAINT todsofk FOREIGN KEY (to_dso_id) REFERENCES dsos (id),'
'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols (id)')
- if perf_db_export_calls:
+ if perf_db_export_calls or perf_db_export_callchains:
do_query(query, 'ALTER TABLE call_paths '
'ADD CONSTRAINT parentfk FOREIGN KEY (parent_id) REFERENCES call_paths (id),'
'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id)')
+ if perf_db_export_calls:
do_query(query, 'ALTER TABLE calls '
'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),'
'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),'
value = struct.pack(fmt, 2, 4, branch_type, n, name)
branch_type_file.write(value)
-def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, *x):
if branches:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiq", 18, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id)
else:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiq", 22, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id)
sample_file.write(value)
def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
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)
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) {
.desc = "Test attr update synthesize",
.func = test__event_update,
},
+ {
+ .desc = "Test events times",
+ .func = test__event_times,
+ },
{
.func = NULL,
},
goto out_put;
}
- perf_evlist__config(evlist, &opts);
+ perf_evlist__config(evlist, &opts, NULL);
evsel = perf_evlist__first(evlist);
{
int i;
- dsos = malloc(sizeof(dsos) * cnt);
+ dsos = malloc(sizeof(*dsos) * cnt);
TEST_ASSERT_VAL("failed to alloc dsos array", dsos);
for (i = 0; i < cnt; i++) {
--- /dev/null
+#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;
+}
TEST_ASSERT_VAL("wrong id", ev->id == 123);
TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__SCALE);
- TEST_ASSERT_VAL("wrong scale", ev_data->scale = 0.123);
+ TEST_ASSERT_VAL("wrong scale", ev_data->scale == 0.123);
return 0;
}
struct rb_root *root;
struct rb_node *node;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
if (machine__resolve(machine, &al, &sample) < 0)
goto out;
- if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+ if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack,
NULL) < 0) {
addr_location__put(&al);
goto out;
struct rb_root *root_out;
struct rb_node *node;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root_in = &hists->entries_collapsed;
else
root_in = hists->entries_in;
al.socket = fake_samples[i].socket;
if (hist_entry_iter__add(&iter, &al,
- PERF_MAX_STACK_DEPTH, NULL) < 0) {
+ sysctl_perf_event_max_stack, NULL) < 0) {
addr_location__put(&al);
goto out;
}
/*
* Only entries from fake_common_samples should have a pair.
*/
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
* and some entries will have no pair. However every entry
* in other hists should have (dummy) pair.
*/
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
if (machine__resolve(machine, &al, &sample) < 0)
goto out;
- if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+ if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack,
NULL) < 0) {
addr_location__put(&al);
goto out;
struct rb_root *root_out;
struct rb_node *node;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root_in = &hists->entries_collapsed;
else
root_in = hists->entries_in;
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);
goto out_delete_evlist;
}
- perf_evsel__config(evsel, &opts);
+ perf_evsel__config(evsel, &opts, NULL);
thread_map__set_pid(evlist->threads, 0, getpid());
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) {
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)) {
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
* Step 3:
*
* Load and split /proc/kallsyms into multiple maps, one per module.
+ * Do not use kcore, as this test was designed before kcore support
+ * and has parts that only make sense if using the non-kcore code.
+ * XXX: extend it to stress the kcorre code as well, hint: the list
+ * of modules extracted from /proc/kcore, in its current form, can't
+ * be compacted against the list of modules found in the "vmlinux"
+ * code and with the one got from /proc/modules from the "kallsyms" code.
*/
- if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, NULL) <= 0) {
+ if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true, NULL) <= 0) {
pr_debug("dso__load_kallsyms ");
goto out;
}
pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
mem_start, sym->name, pair->name);
+ } else {
+ pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+ mem_start, sym->name, first_pair->name);
}
}
} else
--- /dev/null
+#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
--- /dev/null
+#include <linux/futex.h>
+
+static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
+{
+ enum syscall_futex_args {
+ SCF_UADDR = (1 << 0),
+ SCF_OP = (1 << 1),
+ SCF_VAL = (1 << 2),
+ SCF_TIMEOUT = (1 << 3),
+ SCF_UADDR2 = (1 << 4),
+ SCF_VAL3 = (1 << 5),
+ };
+ int op = arg->val;
+ int cmd = op & FUTEX_CMD_MASK;
+ size_t printed = 0;
+
+ switch (cmd) {
+#define P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
+ P_FUTEX_OP(WAIT); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
+ P_FUTEX_OP(WAKE); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(FD); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(REQUEUE); arg->mask |= SCF_VAL3|SCF_TIMEOUT; break;
+ P_FUTEX_OP(CMP_REQUEUE); arg->mask |= SCF_TIMEOUT; break;
+ P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT; break;
+ P_FUTEX_OP(WAKE_OP); break;
+ P_FUTEX_OP(LOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(UNLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
+ P_FUTEX_OP(TRYLOCK_PI); arg->mask |= SCF_VAL3|SCF_UADDR2; break;
+ P_FUTEX_OP(WAIT_BITSET); arg->mask |= SCF_UADDR2; break;
+ P_FUTEX_OP(WAKE_BITSET); arg->mask |= SCF_UADDR2; break;
+ P_FUTEX_OP(WAIT_REQUEUE_PI); break;
+ default: printed = scnprintf(bf, size, "%#x", cmd); break;
+ }
+
+ if (op & FUTEX_PRIVATE_FLAG)
+ printed += scnprintf(bf + printed, size - printed, "|PRIV");
+
+ if (op & FUTEX_CLOCK_REALTIME)
+ printed += scnprintf(bf + printed, size - printed, "|CLKRT");
+
+ return printed;
+}
+
+#define SCA_FUTEX_OP syscall_arg__scnprintf_futex_op
--- /dev/null
+#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
--- /dev/null
+#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
--- /dev/null
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#ifndef MSG_PROBE
+#define MSG_PROBE 0x10
+#endif
+#ifndef MSG_WAITFORONE
+#define MSG_WAITFORONE 0x10000
+#endif
+#ifndef MSG_SENDPAGE_NOTLAST
+#define MSG_SENDPAGE_NOTLAST 0x20000
+#endif
+#ifndef MSG_FASTOPEN
+#define MSG_FASTOPEN 0x20000000
+#endif
+#ifndef MSG_CMSG_CLOEXEC
+# define MSG_CMSG_CLOEXEC 0x40000000
+#endif
+
+static size_t syscall_arg__scnprintf_msg_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_MSG_FLAG(n) \
+ if (flags & MSG_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~MSG_##n; \
+ }
+
+ P_MSG_FLAG(OOB);
+ P_MSG_FLAG(PEEK);
+ P_MSG_FLAG(DONTROUTE);
+ P_MSG_FLAG(TRYHARD);
+ P_MSG_FLAG(CTRUNC);
+ P_MSG_FLAG(PROBE);
+ P_MSG_FLAG(TRUNC);
+ P_MSG_FLAG(DONTWAIT);
+ P_MSG_FLAG(EOR);
+ P_MSG_FLAG(WAITALL);
+ P_MSG_FLAG(FIN);
+ P_MSG_FLAG(SYN);
+ P_MSG_FLAG(CONFIRM);
+ P_MSG_FLAG(RST);
+ P_MSG_FLAG(ERRQUEUE);
+ P_MSG_FLAG(NOSIGNAL);
+ P_MSG_FLAG(MORE);
+ P_MSG_FLAG(WAITFORONE);
+ P_MSG_FLAG(SENDPAGE_NOTLAST);
+ P_MSG_FLAG(FASTOPEN);
+ P_MSG_FLAG(CMSG_CLOEXEC);
+#undef P_MSG_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags
--- /dev/null
+
+static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+ if (!(flags & O_CREAT))
+ arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
+
+ if (flags == 0)
+ return scnprintf(bf, size, "RDONLY");
+#define P_FLAG(n) \
+ if (flags & O_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~O_##n; \
+ }
+
+ P_FLAG(APPEND);
+ P_FLAG(ASYNC);
+ P_FLAG(CLOEXEC);
+ P_FLAG(CREAT);
+ P_FLAG(DIRECT);
+ P_FLAG(DIRECTORY);
+ P_FLAG(EXCL);
+ P_FLAG(LARGEFILE);
+ P_FLAG(NOATIME);
+ P_FLAG(NOCTTY);
+#ifdef O_NONBLOCK
+ P_FLAG(NONBLOCK);
+#elif O_NDELAY
+ P_FLAG(NDELAY);
+#endif
+#ifdef O_PATH
+ P_FLAG(PATH);
+#endif
+ P_FLAG(RDWR);
+#ifdef O_DSYNC
+ if ((flags & O_SYNC) == O_SYNC)
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
+ else {
+ P_FLAG(DSYNC);
+ }
+#else
+ P_FLAG(SYNC);
+#endif
+ P_FLAG(TRUNC);
+ P_FLAG(WRONLY);
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
--- /dev/null
+#ifndef PERF_FLAG_FD_NO_GROUP
+# define PERF_FLAG_FD_NO_GROUP (1UL << 0)
+#endif
+
+#ifndef PERF_FLAG_FD_OUTPUT
+# define PERF_FLAG_FD_OUTPUT (1UL << 1)
+#endif
+
+#ifndef PERF_FLAG_PID_CGROUP
+# define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#endif
+
+#ifndef PERF_FLAG_FD_CLOEXEC
+# define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */
+#endif
+
+static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
+ struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+ if (flags == 0)
+ return 0;
+
+#define P_FLAG(n) \
+ if (flags & PERF_FLAG_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~PERF_FLAG_##n; \
+ }
+
+ P_FLAG(FD_NO_GROUP);
+ P_FLAG(FD_OUTPUT);
+ P_FLAG(PID_CGROUP);
+ P_FLAG(FD_CLOEXEC);
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
--- /dev/null
+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__findnew_thread(trace->host, pid, pid);
+
+ if (thread != NULL) {
+ if (!thread->comm_set)
+ thread__set_comm_from_proc(thread);
+
+ 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
--- /dev/null
+#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
--- /dev/null
+
+static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
+{
+ int sig = arg->val;
+
+ switch (sig) {
+#define P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
+ P_SIGNUM(HUP);
+ P_SIGNUM(INT);
+ P_SIGNUM(QUIT);
+ P_SIGNUM(ILL);
+ P_SIGNUM(TRAP);
+ P_SIGNUM(ABRT);
+ P_SIGNUM(BUS);
+ P_SIGNUM(FPE);
+ P_SIGNUM(KILL);
+ P_SIGNUM(USR1);
+ P_SIGNUM(SEGV);
+ P_SIGNUM(USR2);
+ P_SIGNUM(PIPE);
+ P_SIGNUM(ALRM);
+ P_SIGNUM(TERM);
+ P_SIGNUM(CHLD);
+ P_SIGNUM(CONT);
+ P_SIGNUM(STOP);
+ P_SIGNUM(TSTP);
+ P_SIGNUM(TTIN);
+ P_SIGNUM(TTOU);
+ P_SIGNUM(URG);
+ P_SIGNUM(XCPU);
+ P_SIGNUM(XFSZ);
+ P_SIGNUM(VTALRM);
+ P_SIGNUM(PROF);
+ P_SIGNUM(WINCH);
+ P_SIGNUM(IO);
+ P_SIGNUM(PWR);
+ P_SIGNUM(SYS);
+#ifdef SIGEMT
+ P_SIGNUM(EMT);
+#endif
+#ifdef SIGSTKFLT
+ P_SIGNUM(STKFLT);
+#endif
+#ifdef SIGSWI
+ P_SIGNUM(SWI);
+#endif
+ default: break;
+ }
+
+ return scnprintf(bf, size, "%#x", sig);
+}
+
+#define SCA_SIGNUM syscall_arg__scnprintf_signum
--- /dev/null
+#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
--- /dev/null
+#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
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)
bool first = true;
int ret;
- if (symbol_conf.use_callchain)
+ if (symbol_conf.use_callchain) {
folded_sign = hist_entry__folded(he);
-
- if (symbol_conf.use_callchain)
printed += fprintf(fp, "%c ", folded_sign);
+ }
hists__for_each_format(browser->hists, fmt) {
if (perf_hpp__should_skip(fmt, he->hists))
printed += snprintf(bf + printed, size - printed,
", UID: %s", hists->uid_filter_str);
if (thread) {
- if (sort__has_thread) {
+ if (hists__has(hists, thread)) {
printed += scnprintf(bf + printed, size - printed,
", Thread: %s(%d)",
(thread->comm_set ? thread__comm_str(thread) : ""),
{
struct thread *thread = act->thread;
- if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+ if ((!hists__has(browser->hists, thread) &&
+ !hists__has(browser->hists, comm)) || thread == NULL)
return 0;
if (browser->hists->thread_filter) {
thread__zput(browser->hists->thread_filter);
ui_helpline__pop();
} else {
- if (sort__has_thread) {
+ if (hists__has(browser->hists, thread)) {
ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
thread->comm_set ? thread__comm_str(thread) : "",
thread->tid);
{
int ret;
- if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+ if ((!hists__has(browser->hists, thread) &&
+ !hists__has(browser->hists, comm)) || thread == NULL)
return 0;
- if (sort__has_thread) {
+ if (hists__has(browser->hists, thread)) {
ret = asprintf(optstr, "Zoom %s %s(%d) thread",
browser->hists->thread_filter ? "out of" : "into",
thread->comm_set ? thread__comm_str(thread) : "",
{
struct map *map = act->ms.map;
- if (!sort__has_dso || map == NULL)
+ if (!hists__has(browser->hists, dso) || map == NULL)
return 0;
if (browser->hists->dso_filter) {
add_dso_opt(struct hist_browser *browser, struct popup_action *act,
char **optstr, struct map *map)
{
- if (!sort__has_dso || map == NULL)
+ if (!hists__has(browser->hists, dso) || map == NULL)
return 0;
if (asprintf(optstr, "Zoom %s %s DSO",
}
static int
-add_map_opt(struct hist_browser *browser __maybe_unused,
+add_map_opt(struct hist_browser *browser,
struct popup_action *act, char **optstr, struct map *map)
{
- if (!sort__has_dso || map == NULL)
+ if (!hists__has(browser->hists, dso) || map == NULL)
return 0;
if (asprintf(optstr, "Browse map details") < 0)
static int
do_zoom_socket(struct hist_browser *browser, struct popup_action *act)
{
- if (!sort__has_socket || act->socket < 0)
+ if (!hists__has(browser->hists, socket) || act->socket < 0)
return 0;
if (browser->hists->socket_filter > -1) {
add_socket_opt(struct hist_browser *browser, struct popup_action *act,
char **optstr, int socket_id)
{
- if (!sort__has_socket || socket_id < 0)
+ if (!hists__has(browser->hists, socket) || socket_id < 0)
return 0;
if (asprintf(optstr, "Zoom %s Processor Socket %d",
*/
goto out_free_stack;
case 'a':
- if (!sort__has_sym) {
+ if (!hists__has(hists, sym)) {
ui_browser__warning(&browser->b, delay_secs * 2,
"Annotation is only available for symbolic views, "
"include \"sym*\" in --sort to use it.");
continue;
}
- if (!sort__has_sym || browser->selection == NULL)
+ if (!hists__has(hists, sym) || browser->selection == NULL)
goto skip_annotation;
if (sort__mode == SORT_MODE__BRANCH) {
goto skip_scripting;
if (browser->he_selection) {
- if (sort__has_thread && thread) {
+ if (hists__has(hists, thread) && thread) {
nr_options += add_script_opt(browser,
&actions[nr_options],
&options[nr_options],
*
* See hist_browser__show_entry.
*/
- if (sort__has_sym && browser->selection->sym) {
+ if (hists__has(hists, sym) && browser->selection->sym) {
nr_options += add_script_opt(browser,
&actions[nr_options],
&options[nr_options],
gtk_tree_store_set(store, &iter, col_idx++, s, -1);
}
- if (symbol_conf.use_callchain && sort__has_sym) {
+ if (symbol_conf.use_callchain && hists__has(hists, sym)) {
if (callchain_param.mode == CHAIN_GRAPH_REL)
total = symbol_conf.cumulate_callchain ?
h->stat_acc->period : h->stat.period;
ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
}
- if (verbose && sort__has_sym) /* Addr + origin */
+ if (verbose && hists__has(hists, sym)) /* Addr + origin */
ret += 3 + BITS_PER_LONG / 4;
return ret;
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));
}
}
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
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
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
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 += call-path.o
libperf-y += thread-stack.o
libperf-$(CONFIG_AUXTRACE) += auxtrace.o
libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
bool ui__has_annotation(void)
{
- return use_browser == 1 && sort__has_sym;
+ return use_browser == 1 && perf_hpp_list.sym;
}
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;
}
/*
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;
* @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;
unsigned int last_branch_sz;
unsigned long long period;
enum itrace_period_type period_type;
+ unsigned long initial_skip;
};
/**
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)
{
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)
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;
+}
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,
return 0;
}
+static inline int
+bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
+{
+ return 0;
+}
+
static inline int
__bpf_strerror(char *buf, size_t size)
{
{
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
if (dso__is_vdso(pos)) {
name = pos->short_name;
- name_len = pos->short_name_len + 1;
+ name_len = pos->short_name_len;
} else if (dso__is_kcore(pos)) {
machine__mmap_name(machine, nm, sizeof(nm));
name = nm;
- name_len = strlen(nm) + 1;
+ name_len = strlen(nm);
} else {
name = pos->long_name;
- name_len = pos->long_name_len + 1;
+ name_len = pos->long_name_len;
}
in_kernel = pos->kernel ||
--- /dev/null
+/*
+ * call-path.h: Manipulate a tree data structure containing function call paths
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * 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 <linux/rbtree.h>
+#include <linux/list.h>
+
+#include "util.h"
+#include "call-path.h"
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+ struct symbol *sym, u64 ip, bool in_kernel)
+{
+ cp->parent = parent;
+ cp->sym = sym;
+ cp->ip = sym ? 0 : ip;
+ cp->db_id = 0;
+ cp->in_kernel = in_kernel;
+ RB_CLEAR_NODE(&cp->rb_node);
+ cp->children = RB_ROOT;
+}
+
+struct call_path_root *call_path_root__new(void)
+{
+ struct call_path_root *cpr;
+
+ cpr = zalloc(sizeof(struct call_path_root));
+ if (!cpr)
+ return NULL;
+ call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+ INIT_LIST_HEAD(&cpr->blocks);
+ return cpr;
+}
+
+void call_path_root__free(struct call_path_root *cpr)
+{
+ struct call_path_block *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+ list_del(&pos->node);
+ free(pos);
+ }
+ free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip,
+ bool in_kernel)
+{
+ struct call_path_block *cpb;
+ struct call_path *cp;
+ size_t n;
+
+ if (cpr->next < cpr->sz) {
+ cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+ node);
+ } else {
+ cpb = zalloc(sizeof(struct call_path_block));
+ if (!cpb)
+ return NULL;
+ list_add_tail(&cpb->node, &cpr->blocks);
+ cpr->sz += CALL_PATH_BLOCK_SIZE;
+ }
+
+ n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+ cp = &cpb->cp[n];
+
+ call_path__init(cp, parent, sym, ip, in_kernel);
+
+ return cp;
+}
+
+struct call_path *call_path__findnew(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip, u64 ks)
+{
+ struct rb_node **p;
+ struct rb_node *node_parent = NULL;
+ struct call_path *cp;
+ bool in_kernel = ip >= ks;
+
+ if (sym)
+ ip = 0;
+
+ if (!parent)
+ return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+ p = &parent->children.rb_node;
+ while (*p != NULL) {
+ node_parent = *p;
+ cp = rb_entry(node_parent, struct call_path, rb_node);
+
+ if (cp->sym == sym && cp->ip == ip)
+ return cp;
+
+ if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+ if (!cp)
+ return NULL;
+
+ rb_link_node(&cp->rb_node, node_parent, p);
+ rb_insert_color(&cp->rb_node, &parent->children);
+
+ return cp;
+}
--- /dev/null
+/*
+ * call-path.h: Manipulate a tree data structure containing function call paths
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * 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.
+ *
+ */
+
+#ifndef __PERF_CALL_PATH_H
+#define __PERF_CALL_PATH_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+ struct call_path *parent;
+ struct symbol *sym;
+ u64 ip;
+ u64 db_id;
+ bool in_kernel;
+ struct rb_node rb_node;
+ struct rb_root children;
+};
+
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+
+struct call_path_block {
+ struct call_path cp[CALL_PATH_BLOCK_SIZE];
+ struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+ struct call_path call_path;
+ struct list_head blocks;
+ size_t next;
+ size_t sz;
+};
+
+struct call_path_root *call_path_root__new(void);
+void call_path_root__free(struct call_path_root *cpr);
+
+struct call_path *call_path__findnew(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip, u64 ks);
+
+#endif
bool record_opt_set = false;
bool try_stack_size = false;
+ callchain_param.enabled = true;
symbol_conf.use_callchain = true;
if (!arg)
while ((tok = strtok((char *)arg, ",")) != NULL) {
if (!strncmp(tok, "none", strlen(tok))) {
callchain_param.mode = CHAIN_NONE;
+ callchain_param.enabled = false;
symbol_conf.use_callchain = false;
return 0;
}
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)
{
return 0;
if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
- sort__has_parent) {
- return thread__resolve_callchain(al->thread, evsel, sample,
+ perf_hpp_list.parent) {
+ return thread__resolve_callchain(al->thread, cursor, evsel, sample,
parent, al, max_stack);
}
return 0;
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);
#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)
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)
{
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;
}
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)
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);
}
--- /dev/null
+#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 */
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;
+}
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 */
{
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;
+}
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 */
#include "event.h"
#include "util.h"
#include "thread-stack.h"
+#include "callchain.h"
+#include "call-path.h"
#include "db-export.h"
struct deferred_export {
return 0;
}
+static struct call_path *call_path_from_sample(struct db_export *dbe,
+ struct machine *machine,
+ struct thread *thread,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel)
+{
+ u64 kernel_start = machine__kernel_start(machine);
+ struct call_path *current = &dbe->cpr->call_path;
+ enum chain_order saved_order = callchain_param.order;
+ int err;
+
+ if (!symbol_conf.use_callchain || !sample->callchain)
+ return NULL;
+
+ /*
+ * Since the call path tree must be built starting with the root, we
+ * must use ORDER_CALL for call chain resolution, in order to process
+ * the callchain starting with the root node and ending with the leaf.
+ */
+ callchain_param.order = ORDER_CALLER;
+ err = thread__resolve_callchain(thread, &callchain_cursor, evsel,
+ sample, NULL, NULL,
+ sysctl_perf_event_max_stack);
+ if (err) {
+ callchain_param.order = saved_order;
+ return NULL;
+ }
+ callchain_cursor_commit(&callchain_cursor);
+
+ while (1) {
+ struct callchain_cursor_node *node;
+ struct addr_location al;
+ u64 dso_db_id = 0, sym_db_id = 0, offset = 0;
+
+ memset(&al, 0, sizeof(al));
+
+ node = callchain_cursor_current(&callchain_cursor);
+ if (!node)
+ break;
+ /*
+ * Handle export of symbol and dso for this node by
+ * constructing an addr_location struct and then passing it to
+ * db_ids_from_al() to perform the export.
+ */
+ al.sym = node->sym;
+ al.map = node->map;
+ al.machine = machine;
+ if (al.map)
+ al.addr = al.map->map_ip(al.map, node->ip);
+ else
+ al.addr = node->ip;
+
+ db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset);
+
+ /* add node to the call path tree if it doesn't exist */
+ current = call_path__findnew(dbe->cpr, current,
+ al.sym, node->ip,
+ kernel_start);
+
+ callchain_cursor_advance(&callchain_cursor);
+ }
+
+ /* Reset the callchain order to its prior value. */
+ callchain_param.order = saved_order;
+
+ if (current == &dbe->cpr->call_path) {
+ /* Bail because the callchain was empty. */
+ return NULL;
+ }
+
+ return current;
+}
+
int db_export__branch_type(struct db_export *dbe, u32 branch_type,
const char *name)
{
if (err)
goto out_put;
+ if (dbe->cpr) {
+ struct call_path *cp = call_path_from_sample(dbe, al->machine,
+ thread, sample,
+ evsel);
+ if (cp) {
+ db_export__call_path(dbe, cp);
+ es.call_path_id = cp->db_id;
+ }
+ }
+
if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
sample_addr_correlates_sym(&evsel->attr)) {
struct addr_location addr_al;
struct perf_sample;
struct addr_location;
struct call_return_processor;
+struct call_path_root;
struct call_path;
struct call_return;
u64 addr_dso_db_id;
u64 addr_sym_db_id;
u64 addr_offset; /* addr offset from symbol start */
+ u64 call_path_id;
};
struct db_export {
int (*export_call_return)(struct db_export *dbe,
struct call_return *cr);
struct call_return_processor *crp;
+ struct call_path_root *cpr;
u64 evsel_last_db_id;
u64 machine_last_db_id;
u64 thread_last_db_id;
return 0;
}
+#ifdef HAVE_DWARF_GETLOCATIONS
/**
* die_get_var_innermost_scope - Get innermost scope range of given variable DIE
* @sp_die: a subprogram DIE
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
[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)
{
char filename[PATH_MAX];
DIR *tasks;
- struct dirent dirent, *next;
+ struct dirent *dirent;
pid_t tgid, ppid;
int rc = 0;
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;
{
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;
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;
PERF_RECORD_STAT = 76,
PERF_RECORD_STAT_ROUND = 77,
PERF_RECORD_EVENT_UPDATE = 78,
+ PERF_RECORD_TIME_CONV = 79,
PERF_RECORD_HEADER_MAX
};
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;
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);
return NULL;
}
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+/* When check_messup is true, 'end' must points to a good entry */
+static union perf_event *
+perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
+ u64 end, u64 *prev)
{
- struct perf_mmap *md = &evlist->mmap[idx];
- u64 head;
- u64 old = md->prev;
unsigned char *data = md->base + page_size;
union perf_event *event = NULL;
+ int diff = end - start;
- /*
- * Check if event was unmapped due to a POLLHUP/POLLERR.
- */
- if (!atomic_read(&md->refcnt))
- return NULL;
-
- head = perf_mmap__read_head(md);
- if (evlist->overwrite) {
+ if (check_messup) {
/*
* If we're further behind than half the buffer, there's a chance
* the writer will bite our tail and mess up the samples under us.
*
- * If we somehow ended up ahead of the head, we got messed up.
+ * If we somehow ended up ahead of the 'end', we got messed up.
*
- * In either case, truncate and restart at head.
+ * In either case, truncate and restart at 'end'.
*/
- int diff = head - old;
if (diff > md->mask / 2 || diff < 0) {
fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
/*
- * head points to a known good entry, start there.
+ * 'end' points to a known good entry, start there.
*/
- old = head;
+ start = end;
+ diff = 0;
}
}
- if (old != head) {
+ if (diff >= (int)sizeof(event->header)) {
size_t size;
- event = (union perf_event *)&data[old & md->mask];
+ event = (union perf_event *)&data[start & md->mask];
size = event->header.size;
+ if (size < sizeof(event->header) || diff < (int)size) {
+ event = NULL;
+ goto broken_event;
+ }
+
/*
* Event straddles the mmap boundary -- header should always
* be inside due to u64 alignment of output.
*/
- if ((old & md->mask) + size != ((old + size) & md->mask)) {
- unsigned int offset = old;
+ if ((start & md->mask) + size != ((start + size) & md->mask)) {
+ unsigned int offset = start;
unsigned int len = min(sizeof(*event), size), cpy;
void *dst = md->event_copy;
event = (union perf_event *) md->event_copy;
}
- old += size;
+ start += size;
}
- md->prev = old;
+broken_event:
+ if (prev)
+ *prev = start;
return event;
}
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+{
+ struct perf_mmap *md = &evlist->mmap[idx];
+ u64 head;
+ u64 old = md->prev;
+
+ /*
+ * Check if event was unmapped due to a POLLHUP/POLLERR.
+ */
+ if (!atomic_read(&md->refcnt))
+ return NULL;
+
+ head = perf_mmap__read_head(md);
+
+ return perf_mmap__read(md, evlist->overwrite, old, head, &md->prev);
+}
+
static bool perf_mmap__empty(struct perf_mmap *md)
{
return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
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);
+
+ return pages;
+}
- pages = (max * 1024) / page_size;
- if (!is_power_of_2(pages))
- pages = rounddown_pow_of_two(pages);
- } else if (!is_power_of_2(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;
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;
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);
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,
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);
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;
}
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;
/* set perf-event callgraph */
if (param.enabled)
- perf_evsel__config_callgraph(evsel, opts, ¶m);
+ perf_evsel__config_callchain(evsel, opts, ¶m);
}
}
* 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;
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;
__p_bits(buf, size, value, bits);
}
+static void __p_branch_sample_type(char *buf, size_t size, u64 value)
+{
+#define bit_name(n) { PERF_SAMPLE_BRANCH_##n, #n }
+ struct bit_names bits[] = {
+ bit_name(USER), bit_name(KERNEL), bit_name(HV), bit_name(ANY),
+ bit_name(ANY_CALL), bit_name(ANY_RETURN), bit_name(IND_CALL),
+ bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
+ bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
+ bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+ { .name = NULL, }
+ };
+#undef bit_name
+ __p_bits(buf, size, value, bits);
+}
+
static void __p_read_format(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_FORMAT_##n, #n }
#define p_unsigned(val) snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
#define p_signed(val) snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
#define p_sample_type(val) __p_sample_type(buf, BUF_SIZE, val)
+#define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
#define p_read_format(val) __p_read_format(buf, BUF_SIZE, val)
#define PRINT_ATTRn(_n, _f, _p) \
PRINT_ATTRf(bp_type, p_unsigned);
PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
- PRINT_ATTRf(branch_sample_type, p_unsigned);
+ PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
PRINT_ATTRf(sample_regs_user, p_hex);
PRINT_ATTRf(sample_stack_user, p_unsigned);
PRINT_ATTRf(clockid, p_signed);
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)
{
"Probably the maximum number of open file descriptors has been reached.\n"
"Hint: Try again after reducing the number of events.\n"
"Hint: Try increasing the limit with 'ulimit -n <limit>'");
+ case ENOMEM:
+ if ((evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0 &&
+ access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0)
+ return scnprintf(msg, size,
+ "Not enough memory to setup event with callchain.\n"
+ "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
+ "Hint: Current value: %d", sysctl_perf_event_max_stack);
+ break;
case ENODEV:
if (target->cpu_list)
return scnprintf(msg, size, "%s",
- "No such device - did you specify an out-of-range profile CPU?\n");
+ "No such device - did you specify an out-of-range profile CPU?");
break;
case EOPNOTSUPP:
if (evsel->attr.precise_ip)
return scnprintf(msg, size,
"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
"/bin/dmesg may provide additional information.\n"
- "No CONFIG_PERF_EVENTS=y kernel support configured?\n",
+ "No CONFIG_PERF_EVENTS=y kernel support configured?",
err, strerror_r(err, sbuf, sizeof(sbuf)),
perf_evsel__name(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);
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,
(_evsel) && (_evsel)->leader == (_leader); \
(_evsel) = list_entry((_evsel)->node.next, struct perf_evsel, node))
-static inline bool has_branch_callstack(struct perf_evsel *evsel)
+static inline bool perf_evsel__has_branch_callstack(const struct perf_evsel *evsel)
{
return evsel->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
}
--- /dev/null
+#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;
+}
root_in = &he->parent_he->hroot_in;
root_out = &he->parent_he->hroot_out;
} else {
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root_in = &hists->entries_collapsed;
else
root_in = hists->entries_in;
{
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;
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;
struct hist_entry *n;
int ret;
- if (!sort__need_collapse)
+ if (!hists__has(hists, need_collapse))
return 0;
hists->nr_entries = 0;
return;
}
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
struct hist_entry *he;
int64_t cmp;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
root = &hists->entries_collapsed;
else
root = hists->entries_in;
if (he) {
memset(&he->stat, 0, sizeof(he->stat));
he->hists = hists;
+ if (symbol_conf.cumulate_callchain)
+ memset(he->stat_acc, 0, sizeof(he->stat));
rb_link_node(&he->rb_node_in, parent, p);
rb_insert_color(&he->rb_node_in, root);
hists__inc_stats(hists, he);
{
struct rb_node *n;
- if (sort__need_collapse)
+ if (hists__has(hists, need_collapse))
n = hists->entries_collapsed.rb_node;
else
n = hists->entries_in->rb_node;
struct rb_node *nd;
struct hist_entry *pos, *pair;
- if (sort__need_collapse)
+ if (hists__has(leader, need_collapse))
root = &leader->entries_collapsed;
else
root = leader->entries_in;
struct rb_node *nd;
struct hist_entry *pos, *pair;
- if (sort__need_collapse)
+ if (hists__has(other, need_collapse))
root = &other->entries_collapsed;
else
root = other->entries_in;
int nr_hpp_node;
};
+#define hists__has(__h, __f) (__h)->hpp_list->__f
+
struct hist_entry_iter;
struct hist_iter_ops {
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;
struct perf_hpp_list {
struct list_head fields;
struct list_head sorts;
+
+ int need_collapse;
+ int parent;
+ int sym;
+ int dso;
+ int socket;
+ int thread;
+ int comm;
};
extern struct perf_hpp_list perf_hpp_list;
u64 branches_id;
size_t branches_event_size;
bool synth_needs_swap;
+ unsigned long num_events;
};
struct intel_bts_queue {
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);
int intel_pt__strerror(int code, char *buf, size_t buflen)
{
- if (code < 1 || code > INTEL_PT_ERR_MAX)
+ if (code < 1 || code >= INTEL_PT_ERR_MAX)
code = INTEL_PT_ERR_UNK;
strlcpy(buf, intel_pt_err_msgs[code], buflen);
return 0;
u64 cyc_bit;
u64 noretcomp_bit;
unsigned max_non_turbo_ratio;
+
+ unsigned long num_events;
};
enum switch_state {
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);
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);
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);
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;
#include "strlist.h"
#include <elf.h>
+#include "tsc.h"
#include "session.h"
#include "jit.h"
#include "jitdump.h"
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;
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",
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;
}
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;
return -1;
}
if (stat(filename, &st))
- memset(&st, 0, sizeof(stat));
+ memset(&st, 0, sizeof(st));
event->mmap2.header.type = PERF_RECORD_MMAP2;
event->mmap2.header.misc = PERF_RECORD_MISC_USER;
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
size++; /* for \0 */
if (stat(filename, &st))
- memset(&st, 0, sizeof(stat));
+ memset(&st, 0, sizeof(st));
size = PERF_ALIGN(size, sizeof(u64));
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
#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)
machine->threads = RB_ROOT;
pthread_rwlock_init(&machine->threads_lock, NULL);
+ machine->nr_threads = 0;
INIT_LIST_HEAD(&machine->dead_threads);
machine->last_match = NULL;
*/
thread__get(th);
machine->last_match = th;
+ ++machine->nr_threads;
}
return th;
size_t machine__fprintf(struct machine *machine, FILE *fp)
{
- size_t ret = 0;
+ size_t ret;
struct rb_node *nd;
pthread_rwlock_rdlock(&machine->threads_lock);
+ ret = fprintf(fp, "Threads: %u\n", machine->nr_threads);
+
for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
struct thread *pos = rb_entry(nd, struct thread, rb_node);
return machine__create_kernel_maps(machine);
}
-int machine__load_kallsyms(struct machine *machine, const char *filename,
- enum map_type type, symbol_filter_t filter)
+int __machine__load_kallsyms(struct machine *machine, const char *filename,
+ enum map_type type, bool no_kcore, symbol_filter_t filter)
{
struct map *map = machine__kernel_map(machine);
- int ret = dso__load_kallsyms(map->dso, filename, map, filter);
+ int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore, filter);
if (ret > 0) {
dso__set_loaded(map->dso, type);
return ret;
}
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+ enum map_type type, symbol_filter_t filter)
+{
+ return __machine__load_kallsyms(machine, filename, type, false, filter);
+}
+
int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
symbol_filter_t filter)
{
pthread_rwlock_wrlock(&machine->threads_lock);
rb_erase_init(&th->rb_node, &machine->threads);
RB_CLEAR_NODE(&th->rb_node);
+ --machine->nr_threads;
/*
* Move it first to the dead_threads list, then drop the reference,
* if this is the last reference, then the thread__delete destructor
}
static int add_callchain_ip(struct thread *thread,
+ struct callchain_cursor *cursor,
struct symbol **parent,
struct addr_location *root_al,
u8 *cpumode,
* It seems the callchain is corrupted.
* Discard all.
*/
- callchain_cursor_reset(&callchain_cursor);
+ callchain_cursor_reset(cursor);
return 1;
}
return 0;
}
if (al.sym != NULL) {
- if (sort__has_parent && !*parent &&
+ if (perf_hpp_list.parent && !*parent &&
symbol__match_regex(al.sym, &parent_regex))
*parent = al.sym;
else if (have_ignore_callees && root_al &&
/* 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,
* 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,
*/
int mix_chain_nr = i + 1 + lbr_nr + 1;
- if (mix_chain_nr > PERF_MAX_STACK_DEPTH + PERF_MAX_BRANCH_DEPTH) {
+ if (mix_chain_nr > (int)sysctl_perf_event_max_stack + PERF_MAX_BRANCH_DEPTH) {
pr_warning("corrupted callchain. skipping...\n");
return 0;
}
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;
}
}
static int thread__resolve_callchain_sample(struct thread *thread,
+ struct callchain_cursor *cursor,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct symbol **parent,
int skip_idx = -1;
int first_call = 0;
- callchain_cursor_reset(&callchain_cursor);
-
- if (has_branch_callstack(evsel)) {
- err = resolve_lbr_callchain_sample(thread, sample, parent,
+ if (perf_evsel__has_branch_callstack(evsel)) {
+ err = resolve_lbr_callchain_sample(thread, cursor, sample, parent,
root_al, max_stack);
if (err)
return (err < 0) ? err : 0;
* Based on DWARF debug information, some architectures skip
* a callchain entry saved by the kernel.
*/
- if (chain->nr < PERF_MAX_STACK_DEPTH)
+ if (chain->nr < sysctl_perf_event_max_stack)
skip_idx = arch_skip_callchain_idx(thread, chain);
/*
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;
}
check_calls:
- if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) {
+ if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
pr_warning("corrupted callchain. skipping...\n");
return 0;
}
#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;
entry->map, entry->sym);
}
-int thread__resolve_callchain(struct thread *thread,
- struct perf_evsel *evsel,
- struct perf_sample *sample,
- struct symbol **parent,
- struct addr_location *root_al,
- int max_stack)
+static int thread__resolve_callchain_unwind(struct thread *thread,
+ struct callchain_cursor *cursor,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ int max_stack)
{
- int ret = thread__resolve_callchain_sample(thread, evsel,
- sample, parent,
- root_al, max_stack);
- if (ret)
- return ret;
-
/* Can we do dwarf post unwind? */
if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
(evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
(!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);
+}
+
+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 = 0;
+
+ callchain_cursor_reset(&callchain_cursor);
+ if (callchain_param.order == ORDER_CALLEE) {
+ ret = thread__resolve_callchain_sample(thread, cursor,
+ evsel, sample,
+ parent, root_al,
+ max_stack);
+ if (ret)
+ return ret;
+ ret = thread__resolve_callchain_unwind(thread, cursor,
+ evsel, sample,
+ max_stack);
+ } else {
+ ret = thread__resolve_callchain_unwind(thread, cursor,
+ evsel, sample,
+ max_stack);
+ if (ret)
+ return ret;
+ ret = thread__resolve_callchain_sample(thread, cursor,
+ evsel, sample,
+ parent, root_al,
+ max_stack);
+ }
+
+ return ret;
}
int machine__for_each_thread(struct machine *machine,
char *root_dir;
struct rb_root threads;
pthread_rwlock_t threads_lock;
+ unsigned int nr_threads;
struct list_head dead_threads;
struct thread *last_match;
struct vdso_info *vdso_info;
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,
struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename);
+int __machine__load_kallsyms(struct machine *machine, const char *filename,
+ enum map_type type, bool no_kcore, symbol_filter_t filter);
int machine__load_kallsyms(struct machine *machine, const char *filename,
enum map_type type, symbol_filter_t filter);
int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
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;
}
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;
}
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);
+}
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)
#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)
{
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
{
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;
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;
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;
}
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;
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) {
}
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)
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];
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);
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;
}
/*
return true;
}
+/*
+ * NOTE:
+ * '.gnu.linkonce.this_module' section of kernel module elf directly
+ * maps to 'struct module' from linux/module.h. This section contains
+ * actual module name which will be used by kernel after loading it.
+ * But, we cannot use 'struct module' here since linux/module.h is not
+ * exposed to user-space. Offset of 'name' has remained same from long
+ * time, so hardcoding it here.
+ */
+#ifdef __LP64__
+#define MOD_NAME_OFFSET 24
+#else
+#define MOD_NAME_OFFSET 12
+#endif
+
+/*
+ * @module can be module name of module file path. In case of path,
+ * inspect elf and find out what is actual module name.
+ * Caller has to free mod_name after using it.
+ */
+static char *find_module_name(const char *module)
+{
+ int fd;
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ Elf_Data *data;
+ Elf_Scn *sec;
+ char *mod_name = NULL;
+
+ fd = open(module, O_RDONLY);
+ if (fd < 0)
+ return NULL;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL)
+ goto elf_err;
+
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ goto ret_err;
+
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".gnu.linkonce.this_module", NULL);
+ if (!sec)
+ goto ret_err;
+
+ data = elf_getdata(sec, NULL);
+ if (!data || !data->d_buf)
+ goto ret_err;
+
+ mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+
+ret_err:
+ elf_end(elf);
+elf_err:
+ close(fd);
+ return mod_name;
+}
+
#ifdef HAVE_DWARF_SUPPORT
static int kernel_get_module_dso(const char *module, struct dso **pdso)
return -errno;
elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
- if (elf == NULL)
- return -EINVAL;
+ if (elf == NULL) {
+ ret = -EINVAL;
+ goto out_close;
+ }
if (gelf_getehdr(elf, &ehdr) == NULL)
goto out;
ret = 0;
out:
elf_end(elf);
+out_close:
+ close(fd);
+
return ret;
}
int ntevs, const char *module)
{
int i, ret = 0;
- char *tmp;
+ char *mod_name = NULL;
if (!module)
return 0;
- tmp = strrchr(module, '/');
- if (tmp) {
- /* This is a module path -- get the module name */
- module = strdup(tmp + 1);
- if (!module)
- return -ENOMEM;
- tmp = strchr(module, '.');
- if (tmp)
- *tmp = '\0';
- tmp = (char *)module; /* For free() */
- }
+ mod_name = find_module_name(module);
for (i = 0; i < ntevs; i++) {
- tevs[i].point.module = strdup(module);
+ tevs[i].point.module =
+ strdup(mod_name ? mod_name : module);
if (!tevs[i].point.module) {
ret = -ENOMEM;
break;
}
}
- free(tmp);
+ free(mod_name);
return ret;
}
}
/* Compose only probe arg */
-int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
+char *synthesize_perf_probe_arg(struct perf_probe_arg *pa)
{
struct perf_probe_arg_field *field = pa->field;
- int ret;
- char *tmp = buf;
+ struct strbuf buf;
+ char *ret;
+ strbuf_init(&buf, 64);
if (pa->name && pa->var)
- ret = e_snprintf(tmp, len, "%s=%s", pa->name, pa->var);
+ strbuf_addf(&buf, "%s=%s", pa->name, pa->var);
else
- ret = e_snprintf(tmp, len, "%s", pa->name ? pa->name : pa->var);
- if (ret <= 0)
- goto error;
- tmp += ret;
- len -= ret;
+ strbuf_addstr(&buf, pa->name ?: pa->var);
while (field) {
if (field->name[0] == '[')
- ret = e_snprintf(tmp, len, "%s", field->name);
+ strbuf_addstr(&buf, field->name);
else
- ret = e_snprintf(tmp, len, "%s%s",
- field->ref ? "->" : ".", field->name);
- if (ret <= 0)
- goto error;
- tmp += ret;
- len -= ret;
+ strbuf_addf(&buf, "%s%s", field->ref ? "->" : ".",
+ field->name);
field = field->next;
}
- if (pa->type) {
- ret = e_snprintf(tmp, len, ":%s", pa->type);
- if (ret <= 0)
- goto error;
- tmp += ret;
- len -= ret;
- }
+ if (pa->type)
+ strbuf_addf(&buf, ":%s", pa->type);
+
+ ret = strbuf_detach(&buf, NULL);
- return tmp - buf;
-error:
- pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
return ret;
}
/* Compose only probe point (not argument) */
static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
{
- char *buf, *tmp;
- char offs[32] = "", line[32] = "", file[32] = "";
- int ret, len;
-
- buf = zalloc(MAX_CMDLEN);
- if (buf == NULL) {
- ret = -ENOMEM;
- goto error;
- }
- if (pp->offset) {
- ret = e_snprintf(offs, 32, "+%lu", pp->offset);
- if (ret <= 0)
- goto error;
- }
- if (pp->line) {
- ret = e_snprintf(line, 32, ":%d", pp->line);
- if (ret <= 0)
- goto error;
+ struct strbuf buf;
+ char *tmp;
+ int len;
+
+ strbuf_init(&buf, 64);
+ if (pp->function) {
+ strbuf_addstr(&buf, pp->function);
+ if (pp->offset)
+ strbuf_addf(&buf, "+%lu", pp->offset);
+ else if (pp->line)
+ strbuf_addf(&buf, ":%d", pp->line);
+ else if (pp->retprobe)
+ strbuf_addstr(&buf, "%return");
}
if (pp->file) {
tmp = pp->file;
tmp = strchr(pp->file + len - 30, '/');
tmp = tmp ? tmp + 1 : pp->file + len - 30;
}
- ret = e_snprintf(file, 32, "@%s", tmp);
- if (ret <= 0)
- goto error;
+ strbuf_addf(&buf, "@%s", tmp);
+ if (!pp->function && pp->line)
+ strbuf_addf(&buf, ":%d", pp->line);
}
- if (pp->function)
- ret = e_snprintf(buf, MAX_CMDLEN, "%s%s%s%s%s", pp->function,
- offs, pp->retprobe ? "%return" : "", line,
- file);
- else
- ret = e_snprintf(buf, MAX_CMDLEN, "%s%s", file, line);
- if (ret <= 0)
- goto error;
-
- return buf;
-error:
- pr_debug("Failed to synthesize perf probe point: %d\n", ret);
- free(buf);
- return NULL;
+ return strbuf_detach(&buf, NULL);
}
#if 0
#endif
static int __synthesize_probe_trace_arg_ref(struct probe_trace_arg_ref *ref,
- char **buf, size_t *buflen,
- int depth)
+ struct strbuf *buf, int depth)
{
- int ret;
if (ref->next) {
depth = __synthesize_probe_trace_arg_ref(ref->next, buf,
- buflen, depth + 1);
+ depth + 1);
if (depth < 0)
goto out;
}
-
- ret = e_snprintf(*buf, *buflen, "%+ld(", ref->offset);
- if (ret < 0)
- depth = ret;
- else {
- *buf += ret;
- *buflen -= ret;
- }
+ strbuf_addf(buf, "%+ld(", ref->offset);
out:
return depth;
-
}
static int synthesize_probe_trace_arg(struct probe_trace_arg *arg,
- char *buf, size_t buflen)
+ struct strbuf *buf)
{
struct probe_trace_arg_ref *ref = arg->ref;
- int ret, depth = 0;
- char *tmp = buf;
+ int depth = 0;
/* Argument name or separator */
if (arg->name)
- ret = e_snprintf(buf, buflen, " %s=", arg->name);
+ strbuf_addf(buf, " %s=", arg->name);
else
- ret = e_snprintf(buf, buflen, " ");
- if (ret < 0)
- return ret;
- buf += ret;
- buflen -= ret;
+ strbuf_addch(buf, ' ');
/* Special case: @XXX */
if (arg->value[0] == '@' && arg->ref)
/* Dereferencing arguments */
if (ref) {
- depth = __synthesize_probe_trace_arg_ref(ref, &buf,
- &buflen, 1);
+ depth = __synthesize_probe_trace_arg_ref(ref, buf, 1);
if (depth < 0)
return depth;
}
/* Print argument value */
if (arg->value[0] == '@' && arg->ref)
- ret = e_snprintf(buf, buflen, "%s%+ld", arg->value,
- arg->ref->offset);
+ strbuf_addf(buf, "%s%+ld", arg->value, arg->ref->offset);
else
- ret = e_snprintf(buf, buflen, "%s", arg->value);
- if (ret < 0)
- return ret;
- buf += ret;
- buflen -= ret;
+ strbuf_addstr(buf, arg->value);
/* Closing */
- while (depth--) {
- ret = e_snprintf(buf, buflen, ")");
- if (ret < 0)
- return ret;
- buf += ret;
- buflen -= ret;
- }
+ while (depth--)
+ strbuf_addch(buf, ')');
/* Print argument type */
- if (arg->type) {
- ret = e_snprintf(buf, buflen, ":%s", arg->type);
- if (ret <= 0)
- return ret;
- buf += ret;
- }
+ if (arg->type)
+ strbuf_addf(buf, ":%s", arg->type);
- return buf - tmp;
+ return 0;
}
char *synthesize_probe_trace_command(struct probe_trace_event *tev)
{
struct probe_trace_point *tp = &tev->point;
- char *buf;
- int i, len, ret;
-
- buf = zalloc(MAX_CMDLEN);
- if (buf == NULL)
- return NULL;
-
- len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
- tev->group, tev->event);
- if (len <= 0)
- goto error;
+ struct strbuf buf;
+ char *ret = NULL;
+ int i;
/* Uprobes must have tp->module */
if (tev->uprobes && !tp->module)
- goto error;
+ return NULL;
+
+ strbuf_init(&buf, 32);
+ strbuf_addf(&buf, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+ tev->group, tev->event);
/*
* If tp->address == 0, then this point must be a
* absolute address uprobe.
/* Use the tp->address for uprobes */
if (tev->uprobes)
- ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
- tp->module, tp->address);
+ strbuf_addf(&buf, "%s:0x%lx", tp->module, tp->address);
else if (!strncmp(tp->symbol, "0x", 2))
/* Absolute address. See try_to_find_absolute_address() */
- ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s0x%lx",
- tp->module ?: "", tp->module ? ":" : "",
- tp->address);
+ strbuf_addf(&buf, "%s%s0x%lx", tp->module ?: "",
+ tp->module ? ":" : "", tp->address);
else
- ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
- tp->module ?: "", tp->module ? ":" : "",
- tp->symbol, tp->offset);
+ strbuf_addf(&buf, "%s%s%s+%lu", tp->module ?: "",
+ tp->module ? ":" : "", tp->symbol, tp->offset);
- if (ret <= 0)
- goto error;
- len += ret;
-
- for (i = 0; i < tev->nargs; i++) {
- ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
- MAX_CMDLEN - len);
- if (ret <= 0)
+ for (i = 0; i < tev->nargs; i++)
+ if (synthesize_probe_trace_arg(&tev->args[i], &buf) < 0)
goto error;
- len += ret;
- }
- return buf;
+ ret = strbuf_detach(&buf, NULL);
error:
- free(buf);
- return NULL;
+ strbuf_release(&buf);
+ return ret;
}
static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
static int convert_to_perf_probe_event(struct probe_trace_event *tev,
struct perf_probe_event *pev, bool is_kprobe)
{
- char buf[64] = "";
+ struct strbuf buf = STRBUF_INIT;
int i, ret;
/* Convert event/group name */
if (tev->args[i].name)
pev->args[i].name = strdup(tev->args[i].name);
else {
- ret = synthesize_probe_trace_arg(&tev->args[i],
- buf, 64);
- pev->args[i].name = strdup(buf);
+ strbuf_init(&buf, 32);
+ ret = synthesize_probe_trace_arg(&tev->args[i], &buf);
+ pev->args[i].name = strbuf_detach(&buf, NULL);
}
if (pev->args[i].name == NULL && ret >= 0)
ret = -ENOMEM;
const char *module,
struct strbuf *result)
{
- int i, ret;
- char buf[128];
- char *place;
+ int i;
+ char *buf;
- /* Synthesize only event probe point */
- place = synthesize_perf_probe_point(&pev->point);
- if (!place)
- return -EINVAL;
+ if (asprintf(&buf, "%s:%s", group, event) < 0)
+ return -errno;
+ strbuf_addf(result, " %-20s (on ", buf);
+ free(buf);
- ret = e_snprintf(buf, 128, "%s:%s", group, event);
- if (ret < 0)
- goto out;
+ /* Synthesize only event probe point */
+ buf = synthesize_perf_probe_point(&pev->point);
+ if (!buf)
+ return -ENOMEM;
+ strbuf_addstr(result, buf);
+ free(buf);
- strbuf_addf(result, " %-20s (on %s", buf, place);
if (module)
strbuf_addf(result, " in %s", module);
if (pev->nargs > 0) {
strbuf_add(result, " with", 5);
for (i = 0; i < pev->nargs; i++) {
- ret = synthesize_perf_probe_arg(&pev->args[i],
- buf, 128);
- if (ret < 0)
- goto out;
+ buf = synthesize_perf_probe_arg(&pev->args[i]);
+ if (!buf)
+ return -ENOMEM;
strbuf_addf(result, " %s", buf);
+ free(buf);
}
}
strbuf_addch(result, ')');
-out:
- free(place);
- return ret;
+
+ return 0;
}
/* Show an event */
void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
struct probe_trace_event *tev __maybe_unused,
- struct map *map __maybe_unused) { }
+ struct map *map __maybe_unused,
+ struct symbol *sym __maybe_unused) { }
/*
* Find probe function addresses from map.
struct probe_trace_point *tp;
int num_matched_functions;
int ret, i, j, skipped = 0;
+ char *mod_name;
map = get_target_map(pev->target, pev->uprobes);
if (!map) {
tp->realname = strdup_or_goto(sym->name, nomem_out);
tp->retprobe = pp->retprobe;
- if (pev->target)
- tev->point.module = strdup_or_goto(pev->target,
- nomem_out);
+ if (pev->target) {
+ if (pev->uprobes) {
+ tev->point.module = strdup_or_goto(pev->target,
+ nomem_out);
+ } else {
+ mod_name = find_module_name(pev->target);
+ tev->point.module =
+ strdup(mod_name ? mod_name : pev->target);
+ free(mod_name);
+ if (!tev->point.module)
+ goto nomem_out;
+ }
+ }
tev->uprobes = pev->uprobes;
tev->nargs = pev->nargs;
if (tev->nargs) {
strdup_or_goto(pev->args[i].type,
nomem_out);
}
- arch__fix_tev_from_maps(pev, tev, map);
+ arch__fix_tev_from_maps(pev, tev, map, sym);
}
if (ret == skipped) {
ret = -ENOENT;
{
int ret;
- if (pev->uprobes && !pev->group) {
- /* Replace group name if not given */
- ret = convert_exec_to_group(pev->target, &pev->group);
+ if (!pev->group) {
+ /* Set group name if not given */
+ if (!pev->uprobes) {
+ pev->group = strdup(PERFPROBE_GROUP);
+ ret = pev->group ? 0 : -ENOMEM;
+ } else
+ ret = convert_exec_to_group(pev->target, &pev->group);
if (ret != 0) {
pr_warning("Failed to make a group name.\n");
return ret;
/* Events to command string */
char *synthesize_perf_probe_command(struct perf_probe_event *pev);
char *synthesize_probe_trace_command(struct probe_trace_event *tev);
-int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len);
+char *synthesize_perf_probe_arg(struct perf_probe_arg *pa);
/* Check the perf_probe_event needs debuginfo */
bool perf_probe_event_need_dwarf(struct perf_probe_event *pev);
int show_available_funcs(const char *module, struct strfilter *filter, bool user);
bool arch__prefers_symtab(void);
void arch__fix_tev_from_maps(struct perf_probe_event *pev,
- struct probe_trace_event *tev, struct map *map);
+ struct probe_trace_event *tev, struct map *map,
+ struct symbol *sym);
/* If there is no space to write, returns -E2BIG. */
int e_snprintf(char *str, size_t size, const char *format, ...)
pr_debug("Writing event: %s\n", buf);
if (!probe_event_dry_run) {
- ret = write(fd, buf, strlen(buf));
- if (ret <= 0) {
+ if (write(fd, buf, strlen(buf)) < (int)strlen(buf)) {
ret = -errno;
pr_warning("Failed to write event: %s\n",
strerror_r(errno, sbuf, sizeof(sbuf)));
static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
{
Dwarf_Die vr_die;
- char buf[32], *ptr;
+ char *buf, *ptr;
int ret = 0;
/* Copy raw parameters */
if (pf->pvar->name)
pf->tvar->name = strdup(pf->pvar->name);
else {
- ret = synthesize_perf_probe_arg(pf->pvar, buf, 32);
- if (ret < 0)
- return ret;
+ buf = synthesize_perf_probe_arg(pf->pvar);
+ if (!buf)
+ return -ENOMEM;
ptr = strchr(buf, ':'); /* Change type separator to _ */
if (ptr)
*ptr = '_';
- pf->tvar->name = strdup(buf);
+ pf->tvar->name = buf;
}
if (pf->tvar->name == NULL)
return -ENOMEM;
if (ret2 == 0) {
strlist__add(vl->vars,
strbuf_detach(&buf, NULL));
- }
- strbuf_release(&buf);
+ } else
+ strbuf_release(&buf);
}
}
util/trace-event.c
../lib/rbtree.c
util/string.c
+util/symbol_fprintf.c
--- /dev/null
+#ifndef _PERF_RESORT_RB_H_
+#define _PERF_RESORT_RB_H_
+/*
+ * Template for creating a class to resort an existing rb_tree according to
+ * a new sort criteria, that must be present in the entries of the source
+ * rb_tree.
+ *
+ * (c) 2016 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Quick example, resorting threads by its shortname:
+ *
+ * First define the prefix (threads) to be used for the functions and data
+ * structures created, and provide an expression for the sorting, then the
+ * fields to be present in each of the entries in the new, sorted, rb_tree.
+ *
+ * The body of the init function should collect the fields, maybe
+ * pre-calculating them from multiple entries in the original 'entry' from
+ * the rb_tree used as a source for the entries to be sorted:
+
+DEFINE_RB_RESORT_RB(threads, strcmp(a->thread->shortname,
+ b->thread->shortname) < 0,
+ struct thread *thread;
+)
+{
+ entry->thread = rb_entry(nd, struct thread, rb_node);
+}
+
+ * After this it is just a matter of instantiating it and iterating it,
+ * for a few data structures with existing rb_trees, such as 'struct machine',
+ * helpers are available to get the rb_root and the nr_entries:
+
+ DECLARE_RESORT_RB_MACHINE_THREADS(threads, machine_ptr);
+
+ * This will instantiate the new rb_tree and a cursor for it, that can be used as:
+
+ struct rb_node *nd;
+
+ resort_rb__for_each(nd, threads) {
+ struct thread *t = threads_entry;
+ printf("%s: %d\n", t->shortname, t->tid);
+ }
+
+ * Then delete it:
+
+ resort_rb__delete(threads);
+
+ * The name of the data structures and functions will have a _sorted suffix
+ * right before the method names, i.e. will look like:
+ *
+ * struct threads_sorted_entry {}
+ * threads_sorted__insert()
+ */
+
+#define DEFINE_RESORT_RB(__name, __comp, ...) \
+struct __name##_sorted_entry { \
+ struct rb_node rb_node; \
+ __VA_ARGS__ \
+}; \
+static void __name##_sorted__init_entry(struct rb_node *nd, \
+ struct __name##_sorted_entry *entry); \
+ \
+static int __name##_sorted__cmp(struct rb_node *nda, struct rb_node *ndb) \
+{ \
+ struct __name##_sorted_entry *a, *b; \
+ a = rb_entry(nda, struct __name##_sorted_entry, rb_node); \
+ b = rb_entry(ndb, struct __name##_sorted_entry, rb_node); \
+ return __comp; \
+} \
+ \
+struct __name##_sorted { \
+ struct rb_root entries; \
+ struct __name##_sorted_entry nd[0]; \
+}; \
+ \
+static void __name##_sorted__insert(struct __name##_sorted *sorted, \
+ struct rb_node *sorted_nd) \
+{ \
+ struct rb_node **p = &sorted->entries.rb_node, *parent = NULL; \
+ while (*p != NULL) { \
+ parent = *p; \
+ if (__name##_sorted__cmp(sorted_nd, parent)) \
+ p = &(*p)->rb_left; \
+ else \
+ p = &(*p)->rb_right; \
+ } \
+ rb_link_node(sorted_nd, parent, p); \
+ rb_insert_color(sorted_nd, &sorted->entries); \
+} \
+ \
+static void __name##_sorted__sort(struct __name##_sorted *sorted, \
+ struct rb_root *entries) \
+{ \
+ struct rb_node *nd; \
+ unsigned int i = 0; \
+ for (nd = rb_first(entries); nd; nd = rb_next(nd)) { \
+ struct __name##_sorted_entry *snd = &sorted->nd[i++]; \
+ __name##_sorted__init_entry(nd, snd); \
+ __name##_sorted__insert(sorted, &snd->rb_node); \
+ } \
+} \
+ \
+static struct __name##_sorted *__name##_sorted__new(struct rb_root *entries, \
+ int nr_entries) \
+{ \
+ struct __name##_sorted *sorted; \
+ sorted = malloc(sizeof(*sorted) + sizeof(sorted->nd[0]) * nr_entries); \
+ if (sorted) { \
+ sorted->entries = RB_ROOT; \
+ __name##_sorted__sort(sorted, entries); \
+ } \
+ return sorted; \
+} \
+ \
+static void __name##_sorted__delete(struct __name##_sorted *sorted) \
+{ \
+ free(sorted); \
+} \
+ \
+static void __name##_sorted__init_entry(struct rb_node *nd, \
+ struct __name##_sorted_entry *entry)
+
+#define DECLARE_RESORT_RB(__name) \
+struct __name##_sorted_entry *__name##_entry; \
+struct __name##_sorted *__name = __name##_sorted__new
+
+#define resort_rb__for_each(__nd, __name) \
+ for (__nd = rb_first(&__name->entries); \
+ __name##_entry = rb_entry(__nd, struct __name##_sorted_entry, \
+ rb_node), __nd; \
+ __nd = rb_next(__nd))
+
+#define resort_rb__delete(__name) \
+ __name##_sorted__delete(__name), __name = NULL
+
+/*
+ * Helpers for other classes that contains both an rbtree and the
+ * number of entries in it:
+ */
+
+/* For 'struct intlist' */
+#define DECLARE_RESORT_RB_INTLIST(__name, __ilist) \
+ DECLARE_RESORT_RB(__name)(&__ilist->rblist.entries, \
+ __ilist->rblist.nr_entries)
+
+/* For 'struct machine->threads' */
+#define DECLARE_RESORT_RB_MACHINE_THREADS(__name, __machine) \
+ DECLARE_RESORT_RB(__name)(&__machine->threads, __machine->nr_threads)
+
+#endif /* _PERF_RESORT_RB_H_ */
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;
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;
}
#include <perl.h>
#include "../../perf.h"
+#include "../callchain.h"
+#include "../machine.h"
#include "../thread.h"
#include "../event.h"
#include "../trace-event.h"
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,
+ sysctl_perf_event_max_stack) != 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];
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 */
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;
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);
}
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\", $node{ip});\n\
+ }\n\
+ }\n\
+}\n\n\
+");
+
while ((event = trace_find_next_event(pevent, event))) {
fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
fprintf(ofp, "$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;
fprintf(ofp, "\tprint_header($event_name, $common_cpu, "
"$common_secs, $common_nsecs,\n\t "
- "$common_pid, $common_comm);\n\n");
+ "$common_pid, $common_comm, $common_callchain);\n\n");
fprintf(ofp, "\tprintf(\"");
fprintf(ofp, "$%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"
#include "../thread-stack.h"
#include "../trace-event.h"
#include "../machine.h"
+#include "../call-path.h"
#include "thread_map.h"
#include "cpumap.h"
#include "stat.h"
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");
struct tables *tables = container_of(dbe, struct tables, dbe);
PyObject *t;
- t = tuple_new(21);
+ t = tuple_new(22);
tuple_set_u64(t, 0, es->db_id);
tuple_set_u64(t, 1, es->evsel->db_id);
tuple_set_u64(t, 18, es->sample->data_src);
tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
+ tuple_set_u64(t, 21, es->call_path_id);
call_object(tables->sample_handler, t, "sample_table");
{
const char *perf_db_export_mode = "perf_db_export_mode";
const char *perf_db_export_calls = "perf_db_export_calls";
- PyObject *db_export_mode, *db_export_calls;
+ const char *perf_db_export_callchains = "perf_db_export_callchains";
+ PyObject *db_export_mode, *db_export_calls, *db_export_callchains;
bool export_calls = false;
+ bool export_callchains = false;
int ret;
memset(tables, 0, sizeof(struct tables));
if (!ret)
return;
+ /* handle export calls */
tables->dbe.crp = NULL;
db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
if (db_export_calls) {
Py_FatalError("failed to create calls processor");
}
+ /* handle export callchains */
+ tables->dbe.cpr = NULL;
+ db_export_callchains = PyDict_GetItemString(main_dict,
+ perf_db_export_callchains);
+ if (db_export_callchains) {
+ ret = PyObject_IsTrue(db_export_callchains);
+ if (ret == -1)
+ handler_call_die(perf_db_export_callchains);
+ export_callchains = !!ret;
+ }
+
+ if (export_callchains) {
+ /*
+ * Attempt to use the call path root from the call return
+ * processor, if the call return processor is in use. Otherwise,
+ * we allocate a new call path root. This prevents exporting
+ * duplicate call path ids when both are in use simultaniously.
+ */
+ if (tables->dbe.crp)
+ tables->dbe.cpr = tables->dbe.crp->cpr;
+ else
+ tables->dbe.cpr = call_path_root__new();
+
+ if (!tables->dbe.cpr)
+ Py_FatalError("failed to create calls processor");
+ }
+
tables->db_export_mode = true;
/*
* Reserve per symbol space for symbol->db_id via symbol__priv()
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)
[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,
};
unsigned int i;
struct ip_callchain *callchain = sample->callchain;
- if (has_branch_callstack(evsel))
+ if (perf_evsel__has_branch_callstack(evsel))
callchain__lbr_callstack_printf(sample);
printf("... FP chain: nr:%" PRIu64 "\n", callchain->nr);
if (sample_type & PERF_SAMPLE_CALLCHAIN)
callchain__printf(evsel, sample);
- if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !has_branch_callstack(evsel))
+ if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel))
branch_stack__printf(sample);
if (sample_type & PERF_SAMPLE_REGS_USER)
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;
}
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;
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)
{
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;
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,
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);
const char *field_order;
regex_t ignore_callees_regex;
int have_ignore_callees = 0;
-int sort__need_collapse = 0;
-int sort__has_parent = 0;
-int sort__has_sym = 0;
-int sort__has_dso = 0;
-int sort__has_socket = 0;
-int sort__has_thread = 0;
-int sort__has_comm = 0;
enum sort_mode sort__mode = SORT_MODE__NORMAL;
/*
* comparing symbol address alone is not enough since it's a
* relative address within a dso.
*/
- if (!sort__has_dso) {
+ if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) {
ret = sort__dso_cmp(left, right);
if (ret != 0)
return ret;
return -1;
if (sd->entry->se_collapse)
- sort__need_collapse = 1;
+ list->need_collapse = 1;
sd->taken = 1;
pr_err("Invalid regex: %s\n%s", parent_pattern, err);
return -EINVAL;
}
- sort__has_parent = 1;
+ list->parent = 1;
} else if (sd->entry == &sort_sym) {
- sort__has_sym = 1;
+ list->sym = 1;
/*
* perf diff displays the performance difference amongst
* two or more perf.data files. Those files could come
sd->entry->se_collapse = sort__sym_sort;
} else if (sd->entry == &sort_dso) {
- sort__has_dso = 1;
+ list->dso = 1;
} else if (sd->entry == &sort_socket) {
- sort__has_socket = 1;
+ list->socket = 1;
} else if (sd->entry == &sort_thread) {
- sort__has_thread = 1;
+ list->thread = 1;
} else if (sd->entry == &sort_comm) {
- sort__has_comm = 1;
+ list->comm = 1;
}
return __sort_dimension__add(sd, list, level);
return -EINVAL;
if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
- sort__has_sym = 1;
+ list->sym = 1;
__sort_dimension__add(sd, list, level);
return 0;
return -EINVAL;
if (sd->entry == &sort_mem_daddr_sym)
- sort__has_sym = 1;
+ list->sym = 1;
__sort_dimension__add(sd, list, level);
return 0;
void reset_output_field(void)
{
- sort__need_collapse = 0;
- sort__has_parent = 0;
- sort__has_sym = 0;
- sort__has_dso = 0;
+ perf_hpp_list.need_collapse = 0;
+ perf_hpp_list.parent = 0;
+ perf_hpp_list.sym = 0;
+ perf_hpp_list.dso = 0;
field_order = NULL;
sort_order = NULL;
extern const char default_sort_order[];
extern regex_t ignore_callees_regex;
extern int have_ignore_callees;
-extern int sort__need_collapse;
-extern int sort__has_dso;
-extern int sort__has_parent;
-extern int sort__has_sym;
-extern int sort__has_socket;
-extern int sort__has_thread;
-extern int sort__has_comm;
extern enum sort_mode sort__mode;
extern struct sort_entry sort_comm;
extern struct sort_entry sort_dso;
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) {
return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
}
-void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+void __weak arch__sym_update(struct symbol *s __maybe_unused,
+ GElf_Sym *sym __maybe_unused) { }
int dso__load_sym(struct dso *dso, struct map *map,
struct symsrc *syms_ss, struct symsrc *runtime_ss,
(sym.st_value & 1))
--sym.st_value;
- arch__elf_sym_adjust(&sym);
-
if (dso->kernel || kmodule) {
char dso_name[PATH_MAX];
if (!f)
goto out_elf_end;
+ arch__sym_update(f, &sym);
+
if (filter && filter(curr_map, f))
symbol__delete(f);
else {
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;
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;
&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))
return 0;
}
-int dso__load_kallsyms(struct dso *dso, const char *filename,
- struct map *map, symbol_filter_t filter)
+int __dso__load_kallsyms(struct dso *dso, const char *filename,
+ struct map *map, bool no_kcore, symbol_filter_t filter)
{
u64 delta = 0;
else
dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
- if (!dso__load_kcore(dso, map, filename))
+ if (!no_kcore && !dso__load_kcore(dso, map, filename))
return dso__split_kallsyms_for_kcore(dso, map, filter);
else
return dso__split_kallsyms(dso, map, delta, filter);
}
+int dso__load_kallsyms(struct dso *dso, const char *filename,
+ struct map *map, symbol_filter_t filter)
+{
+ return __dso__load_kallsyms(dso, filename, map, false, filter);
+}
+
static int dso__load_perf_map(struct dso *dso, struct map *map,
symbol_filter_t filter)
{
u16 namelen;
u8 binding;
bool ignore;
+ u8 arch_sym;
char name[0];
};
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);
symbol_filter_t filter);
int dso__load_vmlinux_path(struct dso *dso, struct map *map,
symbol_filter_t filter);
+int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
+ bool no_kcore, symbol_filter_t filter);
int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
symbol_filter_t filter);
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);
#ifdef HAVE_LIBELF_SUPPORT
bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
-void arch__elf_sym_adjust(GElf_Sym *sym);
+void arch__sym_update(struct symbol *s, GElf_Sym *sym);
#endif
#define SYMBOL_A 0
--- /dev/null
+#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;
+}
--- /dev/null
+/*
+ * System call table mapper
+ *
+ * (C) 2016 Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * 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 */
--- /dev/null
+#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 */
#include "debug.h"
#include "symbol.h"
#include "comm.h"
+#include "call-path.h"
#include "thread-stack.h"
-#define CALL_PATH_BLOCK_SHIFT 8
-#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
-#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
-
-struct call_path_block {
- struct call_path cp[CALL_PATH_BLOCK_SIZE];
- struct list_head node;
-};
-
-/**
- * struct call_path_root - root of all call paths.
- * @call_path: root call path
- * @blocks: list of blocks to store call paths
- * @next: next free space
- * @sz: number of spaces
- */
-struct call_path_root {
- struct call_path call_path;
- struct list_head blocks;
- size_t next;
- size_t sz;
-};
-
-/**
- * struct call_return_processor - provides a call-back to consume call-return
- * information.
- * @cpr: call path root
- * @process: call-back that accepts call/return information
- * @data: anonymous data for call-back
- */
-struct call_return_processor {
- struct call_path_root *cpr;
- int (*process)(struct call_return *cr, void *data);
- void *data;
-};
-
#define STACK_GROWTH 2048
/**
chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
}
-static void call_path__init(struct call_path *cp, struct call_path *parent,
- struct symbol *sym, u64 ip, bool in_kernel)
-{
- cp->parent = parent;
- cp->sym = sym;
- cp->ip = sym ? 0 : ip;
- cp->db_id = 0;
- cp->in_kernel = in_kernel;
- RB_CLEAR_NODE(&cp->rb_node);
- cp->children = RB_ROOT;
-}
-
-static struct call_path_root *call_path_root__new(void)
-{
- struct call_path_root *cpr;
-
- cpr = zalloc(sizeof(struct call_path_root));
- if (!cpr)
- return NULL;
- call_path__init(&cpr->call_path, NULL, NULL, 0, false);
- INIT_LIST_HEAD(&cpr->blocks);
- return cpr;
-}
-
-static void call_path_root__free(struct call_path_root *cpr)
-{
- struct call_path_block *pos, *n;
-
- list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
- list_del(&pos->node);
- free(pos);
- }
- free(cpr);
-}
-
-static struct call_path *call_path__new(struct call_path_root *cpr,
- struct call_path *parent,
- struct symbol *sym, u64 ip,
- bool in_kernel)
-{
- struct call_path_block *cpb;
- struct call_path *cp;
- size_t n;
-
- if (cpr->next < cpr->sz) {
- cpb = list_last_entry(&cpr->blocks, struct call_path_block,
- node);
- } else {
- cpb = zalloc(sizeof(struct call_path_block));
- if (!cpb)
- return NULL;
- list_add_tail(&cpb->node, &cpr->blocks);
- cpr->sz += CALL_PATH_BLOCK_SIZE;
- }
-
- n = cpr->next++ & CALL_PATH_BLOCK_MASK;
- cp = &cpb->cp[n];
-
- call_path__init(cp, parent, sym, ip, in_kernel);
-
- return cp;
-}
-
-static struct call_path *call_path__findnew(struct call_path_root *cpr,
- struct call_path *parent,
- struct symbol *sym, u64 ip, u64 ks)
-{
- struct rb_node **p;
- struct rb_node *node_parent = NULL;
- struct call_path *cp;
- bool in_kernel = ip >= ks;
-
- if (sym)
- ip = 0;
-
- if (!parent)
- return call_path__new(cpr, parent, sym, ip, in_kernel);
-
- p = &parent->children.rb_node;
- while (*p != NULL) {
- node_parent = *p;
- cp = rb_entry(node_parent, struct call_path, rb_node);
-
- if (cp->sym == sym && cp->ip == ip)
- return cp;
-
- if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
- p = &(*p)->rb_left;
- else
- p = &(*p)->rb_right;
- }
-
- cp = call_path__new(cpr, parent, sym, ip, in_kernel);
- if (!cp)
- return NULL;
-
- rb_link_node(&cp->rb_node, node_parent, p);
- rb_insert_color(&cp->rb_node, &parent->children);
-
- return cp;
-}
-
struct call_return_processor *
call_return_processor__new(int (*process)(struct call_return *cr, void *data),
void *data)
#include <sys/types.h>
#include <linux/types.h>
-#include <linux/rbtree.h>
struct thread;
struct comm;
struct ip_callchain;
struct symbol;
struct dso;
-struct call_return_processor;
struct comm;
struct perf_sample;
struct addr_location;
+struct call_path;
/*
* Call/Return flags.
};
/**
- * struct call_path - node in list of calls leading to a function call.
- * @parent: call path to the parent function call
- * @sym: symbol of function called
- * @ip: only if sym is null, the ip of the function
- * @db_id: id used for db-export
- * @in_kernel: whether function is a in the kernel
- * @rb_node: node in parent's tree of called functions
- * @children: tree of call paths of functions called
- *
- * In combination with the call_return structure, the call_path structure
- * defines a context-sensitve call-graph.
+ * struct call_return_processor - provides a call-back to consume call-return
+ * information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
*/
-struct call_path {
- struct call_path *parent;
- struct symbol *sym;
- u64 ip;
- u64 db_id;
- bool in_kernel;
- struct rb_node rb_node;
- struct rb_root children;
+struct call_return_processor {
+ struct call_path_root *cpr;
+ int (*process)(struct call_return *cr, void *data);
+ void *data;
};
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
#include "comm.h"
#include "unwind.h"
+#include <api/fs/fs.h>
+
int thread__init_map_groups(struct thread *thread, struct machine *machine)
{
struct thread *leader;
return 0;
}
+int thread__set_comm_from_proc(struct thread *thread)
+{
+ char path[64];
+ char *comm = NULL;
+ size_t sz;
+ int err = -1;
+
+ if (!(snprintf(path, sizeof(path), "%d/task/%d/comm",
+ thread->pid_, thread->tid) >= (int)sizeof(path)) &&
+ procfs__read_str(path, &comm, &sz) == 0) {
+ comm[sz - 1] = '\0';
+ err = thread__set_comm(thread, comm, 0);
+ }
+
+ return err;
+}
+
const char *thread__comm_str(const struct thread *thread)
{
const struct comm *comm = thread__comm(thread);
struct addr_location *al)
{
size_t i;
- const u8 const cpumodes[] = {
+ const u8 cpumodes[] = {
PERF_RECORD_MISC_USER,
PERF_RECORD_MISC_KERNEL,
PERF_RECORD_MISC_GUEST_USER,
#include "symbol.h"
#include <strlist.h>
#include <intlist.h>
+#ifdef HAVE_LIBUNWIND_SUPPORT
+#include <libunwind.h>
+#endif
struct thread_stack;
void *priv;
struct thread_stack *ts;
+#ifdef HAVE_LIBUNWIND_SUPPORT
+ unw_addr_space_t addr_space;
+#endif
};
struct machine;
return __thread__set_comm(thread, comm, timestamp, false);
}
+int thread__set_comm_from_proc(struct thread *thread);
+
int thread__comm_len(struct thread *thread);
struct comm *thread__comm(const struct thread *thread);
struct comm *thread__exec_comm(const struct thread *thread);
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)
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;
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;
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;
+}
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)
}
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 */
id_index,
auxtrace_info,
auxtrace_error,
+ time_conv,
thread_map,
cpu_map,
stat_config,
--- /dev/null
+#ifndef __TRIGGER_H_
+#define __TRIGGER_H_ 1
+
+#include "util/debug.h"
+#include "asm/bug.h"
+
+/*
+ * Use trigger to model operations which need to be executed when
+ * an event (a signal, for example) is observed.
+ *
+ * States and transits:
+ *
+ *
+ * OFF--(on)--> READY --(hit)--> HIT
+ * ^ |
+ * | (ready)
+ * | |
+ * \_____________/
+ *
+ * is_hit and is_ready are two key functions to query the state of
+ * a trigger. is_hit means the event already happen; is_ready means the
+ * trigger is waiting for the event.
+ */
+
+struct trigger {
+ volatile enum {
+ TRIGGER_ERROR = -2,
+ TRIGGER_OFF = -1,
+ TRIGGER_READY = 0,
+ TRIGGER_HIT = 1,
+ } state;
+ const char *name;
+};
+
+#define TRIGGER_WARN_ONCE(t, exp) \
+ WARN_ONCE(t->state != exp, "trigger '%s' state transist error: %d in %s()\n", \
+ t->name, t->state, __func__)
+
+static inline bool trigger_is_available(struct trigger *t)
+{
+ return t->state >= 0;
+}
+
+static inline bool trigger_is_error(struct trigger *t)
+{
+ return t->state <= TRIGGER_ERROR;
+}
+
+static inline void trigger_on(struct trigger *t)
+{
+ TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
+ t->state = TRIGGER_READY;
+}
+
+static inline void trigger_ready(struct trigger *t)
+{
+ if (!trigger_is_available(t))
+ return;
+ t->state = TRIGGER_READY;
+}
+
+static inline void trigger_hit(struct trigger *t)
+{
+ if (!trigger_is_available(t))
+ return;
+ TRIGGER_WARN_ONCE(t, TRIGGER_READY);
+ t->state = TRIGGER_HIT;
+}
+
+static inline void trigger_off(struct trigger *t)
+{
+ if (!trigger_is_available(t))
+ return;
+ t->state = TRIGGER_OFF;
+}
+
+static inline void trigger_error(struct trigger *t)
+{
+ t->state = TRIGGER_ERROR;
+}
+
+static inline bool trigger_is_ready(struct trigger *t)
+{
+ return t->state == TRIGGER_READY;
+}
+
+static inline bool trigger_is_hit(struct trigger *t)
+{
+ return t->state == TRIGGER_HIT;
+}
+
+#define DEFINE_TRIGGER(n) \
+struct trigger n = {.state = TRIGGER_OFF, .name = #n}
+#endif
#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
#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,
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,
* 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;
unsigned int page_size;
int cacheline_size;
+unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+
bool test_attr__enabled;
bool perf_host = true;
return rmdir(path);
}
+/* A filter which removes dot files */
+bool lsdir_no_dot_filter(const char *name __maybe_unused, struct dirent *d)
+{
+ return d->d_name[0] != '.';
+}
+
+/* lsdir reads a directory and store it in strlist */
+struct strlist *lsdir(const char *name,
+ bool (*filter)(const char *, struct dirent *))
+{
+ struct strlist *list = NULL;
+ DIR *dir;
+ struct dirent *d;
+
+ dir = opendir(name);
+ if (!dir)
+ return NULL;
+
+ list = strlist__new(NULL, NULL);
+ if (!list) {
+ errno = -ENOMEM;
+ goto out;
+ }
+
+ while ((d = readdir(dir)) != NULL) {
+ if (!filter || filter(name, d))
+ strlist__add(list, d->d_name);
+ }
+
+out:
+ closedir(dir);
+ return list;
+}
+
static int slow_copyfile(const char *from, const char *to)
{
int err = -1;
#include <termios.h>
#include <linux/bitops.h>
#include <termios.h>
+#include "strlist.h"
extern const char *graph_line;
extern const char *graph_dotted_line;
int mkdir_p(char *path, mode_t mode);
int rm_rf(char *path);
+struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
+bool lsdir_no_dot_filter(const char *name, struct dirent *d);
int copyfile(const char *from, const char *to);
int copyfile_mode(const char *from, const char *to, mode_t mode);
int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
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);
extern unsigned int page_size;
extern int cacheline_size;
+extern unsigned int sysctl_perf_event_max_stack;
struct parse_tag {
char tag;
projects / linux-2.6-block.git / commitdiff