Merge remote-tracking branch 'tip/perf/urgent' into perf/core
To pick fixes that are affecting tests of new 'perf diff' features in
perf/core.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/Makefile b/Makefile
index 96b27a8..b29c804 100644
--- a/Makefile
+++ b/Makefile
@@ -87,10 +87,12 @@
ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
quiet=silent_
+ tools_silent=s
endif
else # make-3.8x
ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
quiet=silent_
+ tools_silent=-s
endif
endif
@@ -1607,11 +1609,11 @@
# Clear a bunch of variables before executing the submake
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
- $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
+ $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
# Single targets
# ---------------------------------------------------------------------------
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 1d392c3..b8ccdb5 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,11 +1,4 @@
-obj-y += core.o
-
-obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o
-obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += amd/power.o
-obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o
-ifdef CONFIG_AMD_IOMMU
-obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o
-endif
-
-obj-$(CONFIG_CPU_SUP_INTEL) += msr.o
+obj-y += core.o
+obj-y += amd/
+obj-$(CONFIG_X86_LOCAL_APIC) += msr.o
obj-$(CONFIG_CPU_SUP_INTEL) += intel/
diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile
new file mode 100644
index 0000000..b1da46f
--- /dev/null
+++ b/arch/x86/events/amd/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_CPU_SUP_AMD) += core.o uncore.o
+obj-$(CONFIG_PERF_EVENTS_AMD_POWER) += power.o
+obj-$(CONFIG_X86_LOCAL_APIC) += ibs.o
+ifdef CONFIG_AMD_IOMMU
+obj-$(CONFIG_CPU_SUP_AMD) += iommu.o
+endif
+
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a0b1bdb..4d1f7f2d 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -22,13 +22,17 @@
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
-#define MAX_COUNTERS NUM_COUNTERS_NB
+#define NUM_COUNTERS_L3 6
+#define MAX_COUNTERS 6
#define RDPMC_BASE_NB 6
-#define RDPMC_BASE_L2 10
+#define RDPMC_BASE_LLC 10
#define COUNTER_SHIFT 16
+static int num_counters_llc;
+static int num_counters_nb;
+
static HLIST_HEAD(uncore_unused_list);
struct amd_uncore {
@@ -45,30 +49,30 @@ struct amd_uncore {
};
static struct amd_uncore * __percpu *amd_uncore_nb;
-static struct amd_uncore * __percpu *amd_uncore_l2;
+static struct amd_uncore * __percpu *amd_uncore_llc;
static struct pmu amd_nb_pmu;
-static struct pmu amd_l2_pmu;
+static struct pmu amd_llc_pmu;
static cpumask_t amd_nb_active_mask;
-static cpumask_t amd_l2_active_mask;
+static cpumask_t amd_llc_active_mask;
static bool is_nb_event(struct perf_event *event)
{
return event->pmu->type == amd_nb_pmu.type;
}
-static bool is_l2_event(struct perf_event *event)
+static bool is_llc_event(struct perf_event *event)
{
- return event->pmu->type == amd_l2_pmu.type;
+ return event->pmu->type == amd_llc_pmu.type;
}
static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
{
if (is_nb_event(event) && amd_uncore_nb)
return *per_cpu_ptr(amd_uncore_nb, event->cpu);
- else if (is_l2_event(event) && amd_uncore_l2)
- return *per_cpu_ptr(amd_uncore_l2, event->cpu);
+ else if (is_llc_event(event) && amd_uncore_llc)
+ return *per_cpu_ptr(amd_uncore_llc, event->cpu);
return NULL;
}
@@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event)
return -ENOENT;
/*
- * NB and L2 counters (MSRs) are shared across all cores that share the
- * same NB / L2 cache. Interrupts can be directed to a single target
- * core, however, event counts generated by processes running on other
- * cores cannot be masked out. So we do not support sampling and
- * per-thread events.
+ * NB and Last level cache counters (MSRs) are shared across all cores
+ * that share the same NB / Last level cache. Interrupts can be directed
+ * to a single target core, however, event counts generated by processes
+ * running on other cores cannot be masked out. So we do not support
+ * sampling and per-thread events.
*/
if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
return -EINVAL;
- /* NB and L2 counters do not have usr/os/guest/host bits */
+ /* NB and Last level cache counters do not have usr/os/guest/host bits */
if (event->attr.exclude_user || event->attr.exclude_kernel ||
event->attr.exclude_host || event->attr.exclude_guest)
return -EINVAL;
@@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
if (pmu->type == amd_nb_pmu.type)
active_mask = &amd_nb_active_mask;
- else if (pmu->type == amd_l2_pmu.type)
- active_mask = &amd_l2_active_mask;
+ else if (pmu->type == amd_llc_pmu.type)
+ active_mask = &amd_llc_active_mask;
else
return 0;
@@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = {
.attrs = amd_uncore_attrs,
};
-PMU_FORMAT_ATTR(event, "config:0-7,32-35");
-PMU_FORMAT_ATTR(umask, "config:8-15");
+/*
+ * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based
+ * on family
+ */
+#define AMD_FORMAT_ATTR(_dev, _name, _format) \
+static ssize_t \
+_dev##_show##_name(struct device *dev, \
+ struct device_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev);
-static struct attribute *amd_uncore_format_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- NULL,
+/* Used for each uncore counter type */
+#define AMD_ATTRIBUTE(_name) \
+static struct attribute *amd_uncore_format_attr_##_name[] = { \
+ &format_attr_event_##_name.attr, \
+ &format_attr_umask.attr, \
+ NULL, \
+}; \
+static struct attribute_group amd_uncore_format_group_##_name = { \
+ .name = "format", \
+ .attrs = amd_uncore_format_attr_##_name, \
+}; \
+static const struct attribute_group *amd_uncore_attr_groups_##_name[] = { \
+ &amd_uncore_attr_group, \
+ &amd_uncore_format_group_##_name, \
+ NULL, \
};
-static struct attribute_group amd_uncore_format_group = {
- .name = "format",
- .attrs = amd_uncore_format_attr,
-};
-
-static const struct attribute_group *amd_uncore_attr_groups[] = {
- &amd_uncore_attr_group,
- &amd_uncore_format_group,
- NULL,
-};
+AMD_FORMAT_ATTR(event, , "config:0-7,32-35");
+AMD_FORMAT_ATTR(umask, , "config:8-15");
+AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60");
+AMD_FORMAT_ATTR(event, _l3, "config:0-7");
+AMD_ATTRIBUTE(df);
+AMD_ATTRIBUTE(l3);
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,
.add = amd_uncore_add,
.del = amd_uncore_del,
@@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = {
.read = amd_uncore_read,
};
-static struct pmu amd_l2_pmu = {
+static struct pmu amd_llc_pmu = {
.task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_attr_groups,
- .name = "amd_l2",
.event_init = amd_uncore_event_init,
.add = amd_uncore_add,
.del = amd_uncore_del,
@@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
static int amd_uncore_cpu_up_prepare(unsigned int cpu)
{
- struct amd_uncore *uncore_nb = NULL, *uncore_l2;
+ struct amd_uncore *uncore_nb = NULL, *uncore_llc;
if (amd_uncore_nb) {
uncore_nb = amd_uncore_alloc(cpu);
if (!uncore_nb)
goto fail;
uncore_nb->cpu = cpu;
- uncore_nb->num_counters = NUM_COUNTERS_NB;
+ uncore_nb->num_counters = num_counters_nb;
uncore_nb->rdpmc_base = RDPMC_BASE_NB;
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
@@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
- if (amd_uncore_l2) {
- uncore_l2 = amd_uncore_alloc(cpu);
- if (!uncore_l2)
+ if (amd_uncore_llc) {
+ uncore_llc = amd_uncore_alloc(cpu);
+ if (!uncore_llc)
goto fail;
- uncore_l2->cpu = cpu;
- uncore_l2->num_counters = NUM_COUNTERS_L2;
- uncore_l2->rdpmc_base = RDPMC_BASE_L2;
- uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
- uncore_l2->active_mask = &amd_l2_active_mask;
- uncore_l2->pmu = &amd_l2_pmu;
- uncore_l2->id = -1;
- *per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
+ uncore_llc->cpu = cpu;
+ uncore_llc->num_counters = num_counters_llc;
+ uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
+ uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
+ uncore_llc->active_mask = &amd_llc_active_mask;
+ uncore_llc->pmu = &amd_llc_pmu;
+ uncore_llc->id = -1;
+ *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
}
return 0;
@@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
}
- if (amd_uncore_l2) {
+ if (amd_uncore_llc) {
unsigned int apicid = cpu_data(cpu).apicid;
unsigned int nshared;
- uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
+ uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
nshared = ((eax >> 14) & 0xfff) + 1;
uncore->id = apicid - (apicid % nshared);
- uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
- *per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+ uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
+ *per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
}
return 0;
@@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu)
if (amd_uncore_nb)
uncore_online(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_online(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_online(cpu, amd_uncore_llc);
return 0;
}
@@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu)
if (amd_uncore_nb)
uncore_down_prepare(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_down_prepare(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_down_prepare(cpu, amd_uncore_llc);
return 0;
}
@@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu)
if (amd_uncore_nb)
uncore_dead(cpu, amd_uncore_nb);
- if (amd_uncore_l2)
- uncore_dead(cpu, amd_uncore_l2);
+ if (amd_uncore_llc)
+ uncore_dead(cpu, amd_uncore_llc);
return 0;
}
@@ -492,6 +511,47 @@ static int __init amd_uncore_init(void)
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
goto fail_nodev;
+ switch(boot_cpu_data.x86) {
+ case 23:
+ /* Family 17h: */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L3;
+ /*
+ * For Family17h, the NorthBridge counters are
+ * re-purposed as Data Fabric counters. Also, support is
+ * added for L3 counters. The pmus are exported based on
+ * family as either L2 or L3 and NB or DF.
+ */
+ amd_nb_pmu.name = "amd_df";
+ amd_llc_pmu.name = "amd_l3";
+ format_attr_event_df.show = &event_show_df;
+ format_attr_event_l3.show = &event_show_l3;
+ break;
+ case 22:
+ /* Family 16h - may change: */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ break;
+ default:
+ /*
+ * All prior families have the same number of
+ * NorthBridge and Last Level Cache counters
+ */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ break;
+ }
+ amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
+ amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
+
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
goto fail_nodev;
@@ -510,16 +570,16 @@ static int __init amd_uncore_init(void)
}
if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
- amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
- if (!amd_uncore_l2) {
+ amd_uncore_llc = alloc_percpu(struct amd_uncore *);
+ if (!amd_uncore_llc) {
ret = -ENOMEM;
- goto fail_l2;
+ goto fail_llc;
}
- ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+ ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
if (ret)
- goto fail_l2;
+ goto fail_llc;
- pr_info("perf: AMD L2I counters detected\n");
+ pr_info("perf: AMD LLC counters detected\n");
ret = 0;
}
@@ -529,7 +589,7 @@ static int __init amd_uncore_init(void)
if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
"perf/x86/amd/uncore:prepare",
amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
- goto fail_l2;
+ goto fail_llc;
if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
"perf/x86/amd/uncore:starting",
@@ -546,11 +606,11 @@ static int __init amd_uncore_init(void)
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
fail_prep:
cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
-fail_l2:
+fail_llc:
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
perf_pmu_unregister(&amd_nb_pmu);
- if (amd_uncore_l2)
- free_percpu(amd_uncore_l2);
+ if (amd_uncore_llc)
+ free_percpu(amd_uncore_llc);
fail_nb:
if (amd_uncore_nb)
free_percpu(amd_uncore_nb);
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 1c1b9fe..5900471 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = {
};
PMU_FORMAT_ATTR(cyc, "config:1" );
+PMU_FORMAT_ATTR(pwr_evt, "config:4" );
+PMU_FORMAT_ATTR(fup_on_ptw, "config:5" );
PMU_FORMAT_ATTR(mtc, "config:9" );
PMU_FORMAT_ATTR(tsc, "config:10" );
PMU_FORMAT_ATTR(noretcomp, "config:11" );
+PMU_FORMAT_ATTR(ptw, "config:12" );
PMU_FORMAT_ATTR(mtc_period, "config:14-17" );
PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" );
PMU_FORMAT_ATTR(psb_period, "config:24-27" );
static struct attribute *pt_formats_attr[] = {
&format_attr_cyc.attr,
+ &format_attr_pwr_evt.attr,
+ &format_attr_fup_on_ptw.attr,
&format_attr_mtc.attr,
&format_attr_tsc.attr,
&format_attr_noretcomp.attr,
+ &format_attr_ptw.attr,
&format_attr_mtc_period.attr,
&format_attr_cyc_thresh.attr,
&format_attr_psb_period.attr,
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 8f68490..16ddfb8 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -278,9 +278,13 @@ struct kprobe_insn_cache {
int nr_garbage;
};
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c);
extern void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty);
+/* sleep-less address checking routine */
+extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c,
+ unsigned long addr);
#define DEFINE_INSN_CACHE_OPS(__name) \
extern struct kprobe_insn_cache kprobe_##__name##_slots; \
@@ -294,6 +298,18 @@ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\
{ \
__free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \
} \
+ \
+static inline bool is_kprobe_##__name##_slot(unsigned long addr) \
+{ \
+ return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \
+}
+#else /* __ARCH_WANT_KPROBES_INSN_SLOT */
+#define DEFINE_INSN_CACHE_OPS(__name) \
+static inline bool is_kprobe_##__name##_slot(unsigned long addr) \
+{ \
+ return 0; \
+}
+#endif
DEFINE_INSN_CACHE_OPS(insn);
@@ -330,7 +346,6 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table,
int write, void __user *buffer,
size_t *length, loff_t *ppos);
#endif
-
#endif /* CONFIG_OPTPROBES */
#ifdef CONFIG_KPROBES_ON_FTRACE
extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
@@ -481,6 +496,19 @@ static inline int enable_jprobe(struct jprobe *jp)
return enable_kprobe(&jp->kp);
}
+#ifndef CONFIG_KPROBES
+static inline bool is_kprobe_insn_slot(unsigned long addr)
+{
+ return false;
+}
+#endif
+#ifndef CONFIG_OPTPROBES
+static inline bool is_kprobe_optinsn_slot(unsigned long addr)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_KPROBES
/*
* Blacklist ganerating macro. Specify functions which is not probed
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 78ed810..5c58e93 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -785,9 +785,9 @@ struct perf_cpu_context {
ktime_t hrtimer_interval;
unsigned int hrtimer_active;
- struct pmu *unique_pmu;
#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
+ struct list_head cgrp_cpuctx_entry;
#endif
struct list_head sched_cb_entry;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e5aaa80..88676ff 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -355,6 +355,8 @@ enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
EVENT_TIME = 0x4,
+ /* see ctx_resched() for details */
+ EVENT_CPU = 0x8,
EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
};
@@ -678,6 +680,8 @@ perf_cgroup_set_timestamp(struct task_struct *task,
info->timestamp = ctx->timestamp;
}
+static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
+
#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */
@@ -690,61 +694,46 @@ perf_cgroup_set_timestamp(struct task_struct *task,
static void perf_cgroup_switch(struct task_struct *task, int mode)
{
struct perf_cpu_context *cpuctx;
- struct pmu *pmu;
+ struct list_head *list;
unsigned long flags;
/*
- * disable interrupts to avoid geting nr_cgroup
- * changes via __perf_event_disable(). Also
- * avoids preemption.
+ * Disable interrupts and preemption to avoid this CPU's
+ * cgrp_cpuctx_entry to change under us.
*/
local_irq_save(flags);
- /*
- * we reschedule only in the presence of cgroup
- * constrained events.
- */
+ list = this_cpu_ptr(&cgrp_cpuctx_list);
+ list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) {
+ WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- if (cpuctx->unique_pmu != pmu)
- continue; /* ensure we process each cpuctx once */
+ perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+ perf_pmu_disable(cpuctx->ctx.pmu);
- /*
- * perf_cgroup_events says at least one
- * context on this CPU has cgroup events.
- *
- * ctx->nr_cgroups reports the number of cgroup
- * events for a context.
- */
- if (cpuctx->ctx.nr_cgroups > 0) {
- perf_ctx_lock(cpuctx, cpuctx->task_ctx);
- perf_pmu_disable(cpuctx->ctx.pmu);
-
- if (mode & PERF_CGROUP_SWOUT) {
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
- /*
- * must not be done before ctxswout due
- * to event_filter_match() in event_sched_out()
- */
- cpuctx->cgrp = NULL;
- }
-
- if (mode & PERF_CGROUP_SWIN) {
- WARN_ON_ONCE(cpuctx->cgrp);
- /*
- * set cgrp before ctxsw in to allow
- * event_filter_match() to not have to pass
- * task around
- * we pass the cpuctx->ctx to perf_cgroup_from_task()
- * because cgorup events are only per-cpu
- */
- cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
- cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
- }
- perf_pmu_enable(cpuctx->ctx.pmu);
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+ if (mode & PERF_CGROUP_SWOUT) {
+ cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ /*
+ * must not be done before ctxswout due
+ * to event_filter_match() in event_sched_out()
+ */
+ cpuctx->cgrp = NULL;
}
+
+ if (mode & PERF_CGROUP_SWIN) {
+ WARN_ON_ONCE(cpuctx->cgrp);
+ /*
+ * set cgrp before ctxsw in to allow
+ * event_filter_match() to not have to pass
+ * task around
+ * we pass the cpuctx->ctx to perf_cgroup_from_task()
+ * because cgorup events are only per-cpu
+ */
+ cpuctx->cgrp = perf_cgroup_from_task(task,
+ &cpuctx->ctx);
+ cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
+ }
+ perf_pmu_enable(cpuctx->ctx.pmu);
+ perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
local_irq_restore(flags);
@@ -889,6 +878,7 @@ list_update_cgroup_event(struct perf_event *event,
struct perf_event_context *ctx, bool add)
{
struct perf_cpu_context *cpuctx;
+ struct list_head *cpuctx_entry;
if (!is_cgroup_event(event))
return;
@@ -902,15 +892,16 @@ list_update_cgroup_event(struct perf_event *event,
* this will always be called from the right CPU.
*/
cpuctx = __get_cpu_context(ctx);
-
- /*
- * cpuctx->cgrp is NULL until a cgroup event is sched in or
- * ctx->nr_cgroup == 0 .
- */
- if (add && perf_cgroup_from_task(current, ctx) == event->cgrp)
- cpuctx->cgrp = event->cgrp;
- else if (!add)
+ cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
+ /* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
+ if (add) {
+ list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
+ if (perf_cgroup_from_task(current, ctx) == event->cgrp)
+ cpuctx->cgrp = event->cgrp;
+ } else {
+ list_del(cpuctx_entry);
cpuctx->cgrp = NULL;
+ }
}
#else /* !CONFIG_CGROUP_PERF */
@@ -1453,6 +1444,20 @@ static void update_group_times(struct perf_event *leader)
update_event_times(event);
}
+static enum event_type_t get_event_type(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ enum event_type_t event_type;
+
+ lockdep_assert_held(&ctx->lock);
+
+ event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
+ if (!ctx->task)
+ event_type |= EVENT_CPU;
+
+ return event_type;
+}
+
static struct list_head *
ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
{
@@ -2226,7 +2231,8 @@ ctx_sched_in(struct perf_event_context *ctx,
struct task_struct *task);
static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx)
+ struct perf_event_context *ctx,
+ enum event_type_t event_type)
{
if (!cpuctx->task_ctx)
return;
@@ -2234,7 +2240,7 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
return;
- ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+ ctx_sched_out(ctx, cpuctx, event_type);
}
static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
@@ -2249,13 +2255,51 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
}
+/*
+ * We want to maintain the following priority of scheduling:
+ * - CPU pinned (EVENT_CPU | EVENT_PINNED)
+ * - task pinned (EVENT_PINNED)
+ * - CPU flexible (EVENT_CPU | EVENT_FLEXIBLE)
+ * - task flexible (EVENT_FLEXIBLE).
+ *
+ * In order to avoid unscheduling and scheduling back in everything every
+ * time an event is added, only do it for the groups of equal priority and
+ * below.
+ *
+ * This can be called after a batch operation on task events, in which case
+ * event_type is a bit mask of the types of events involved. For CPU events,
+ * event_type is only either EVENT_PINNED or EVENT_FLEXIBLE.
+ */
static void ctx_resched(struct perf_cpu_context *cpuctx,
- struct perf_event_context *task_ctx)
+ struct perf_event_context *task_ctx,
+ enum event_type_t event_type)
{
+ enum event_type_t ctx_event_type = event_type & EVENT_ALL;
+ bool cpu_event = !!(event_type & EVENT_CPU);
+
+ /*
+ * If pinned groups are involved, flexible groups also need to be
+ * scheduled out.
+ */
+ if (event_type & EVENT_PINNED)
+ event_type |= EVENT_FLEXIBLE;
+
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_ctx)
- task_ctx_sched_out(cpuctx, task_ctx);
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ task_ctx_sched_out(cpuctx, task_ctx, event_type);
+
+ /*
+ * Decide which cpu ctx groups to schedule out based on the types
+ * of events that caused rescheduling:
+ * - EVENT_CPU: schedule out corresponding groups;
+ * - EVENT_PINNED task events: schedule out EVENT_FLEXIBLE groups;
+ * - otherwise, do nothing more.
+ */
+ if (cpu_event)
+ cpu_ctx_sched_out(cpuctx, ctx_event_type);
+ else if (ctx_event_type & EVENT_PINNED)
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+
perf_event_sched_in(cpuctx, task_ctx, current);
perf_pmu_enable(cpuctx->ctx.pmu);
}
@@ -2302,7 +2346,7 @@ static int __perf_install_in_context(void *info)
if (reprogram) {
ctx_sched_out(ctx, cpuctx, EVENT_TIME);
add_event_to_ctx(event, ctx);
- ctx_resched(cpuctx, task_ctx);
+ ctx_resched(cpuctx, task_ctx, get_event_type(event));
} else {
add_event_to_ctx(event, ctx);
}
@@ -2469,7 +2513,7 @@ static void __perf_event_enable(struct perf_event *event,
if (ctx->task)
WARN_ON_ONCE(task_ctx != ctx);
- ctx_resched(cpuctx, task_ctx);
+ ctx_resched(cpuctx, task_ctx, get_event_type(event));
}
/*
@@ -2896,7 +2940,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
if (do_switch) {
raw_spin_lock(&ctx->lock);
- task_ctx_sched_out(cpuctx, ctx);
+ task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
raw_spin_unlock(&ctx->lock);
}
}
@@ -2943,7 +2987,7 @@ static void perf_pmu_sched_task(struct task_struct *prev,
return;
list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
- pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */
+ pmu = cpuctx->ctx.pmu; /* software PMUs will not have sched_task */
if (WARN_ON_ONCE(!pmu->sched_task))
continue;
@@ -3133,8 +3177,12 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
* We want to keep the following priority order:
* cpu pinned (that don't need to move), task pinned,
* cpu flexible, task flexible.
+ *
+ * However, if task's ctx is not carrying any pinned
+ * events, no need to flip the cpuctx's events around.
*/
- cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+ if (!list_empty(&ctx->pinned_groups))
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
perf_event_sched_in(cpuctx, ctx, task);
perf_pmu_enable(ctx->pmu);
perf_ctx_unlock(cpuctx, ctx);
@@ -3449,6 +3497,7 @@ static int event_enable_on_exec(struct perf_event *event,
static void perf_event_enable_on_exec(int ctxn)
{
struct perf_event_context *ctx, *clone_ctx = NULL;
+ enum event_type_t event_type = 0;
struct perf_cpu_context *cpuctx;
struct perf_event *event;
unsigned long flags;
@@ -3462,15 +3511,17 @@ static void perf_event_enable_on_exec(int ctxn)
cpuctx = __get_cpu_context(ctx);
perf_ctx_lock(cpuctx, ctx);
ctx_sched_out(ctx, cpuctx, EVENT_TIME);
- list_for_each_entry(event, &ctx->event_list, event_entry)
+ list_for_each_entry(event, &ctx->event_list, event_entry) {
enabled |= event_enable_on_exec(event, ctx);
+ event_type |= get_event_type(event);
+ }
/*
* Unclone and reschedule this context if we enabled any event.
*/
if (enabled) {
clone_ctx = unclone_ctx(ctx);
- ctx_resched(cpuctx, ctx);
+ ctx_resched(cpuctx, ctx, event_type);
}
perf_ctx_unlock(cpuctx, ctx);
@@ -8647,37 +8698,10 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
return NULL;
}
-static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct perf_cpu_context *cpuctx;
-
- cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
-
- if (cpuctx->unique_pmu == old_pmu)
- cpuctx->unique_pmu = pmu;
- }
-}
-
static void free_pmu_context(struct pmu *pmu)
{
- struct pmu *i;
-
mutex_lock(&pmus_lock);
- /*
- * Like a real lame refcount.
- */
- list_for_each_entry(i, &pmus, entry) {
- if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
- update_pmu_context(i, pmu);
- goto out;
- }
- }
-
free_percpu(pmu->pmu_cpu_context);
-out:
mutex_unlock(&pmus_lock);
}
@@ -8881,8 +8905,6 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
cpuctx->ctx.pmu = pmu;
__perf_mux_hrtimer_init(cpuctx, cpu);
-
- cpuctx->unique_pmu = pmu;
}
got_cpu_context:
@@ -9000,6 +9022,14 @@ static struct pmu *perf_init_event(struct perf_event *event)
idx = srcu_read_lock(&pmus_srcu);
+ /* Try parent's PMU first: */
+ if (event->parent && event->parent->pmu) {
+ pmu = event->parent->pmu;
+ ret = perf_try_init_event(pmu, event);
+ if (!ret)
+ goto unlock;
+ }
+
rcu_read_lock();
pmu = idr_find(&pmu_idr, event->attr.type);
rcu_read_unlock();
@@ -10260,7 +10290,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
* in.
*/
raw_spin_lock_irq(&child_ctx->lock);
- task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
+ task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx, EVENT_ALL);
/*
* Now that the context is inactive, destroy the task <-> ctx relation
@@ -10709,6 +10739,9 @@ static void __init perf_event_init_all_cpus(void)
INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
+#ifdef CONFIG_CGROUP_PERF
+ INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
+#endif
INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
}
}
diff --git a/kernel/extable.c b/kernel/extable.c
index e3beec4..e135947 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -20,6 +20,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/init.h>
+#include <linux/kprobes.h>
#include <asm/sections.h>
#include <linux/uaccess.h>
@@ -104,6 +105,8 @@ int __kernel_text_address(unsigned long addr)
return 1;
if (is_ftrace_trampoline(addr))
return 1;
+ if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+ return 1;
/*
* There might be init symbols in saved stacktraces.
* Give those symbols a chance to be printed in
@@ -123,7 +126,11 @@ int kernel_text_address(unsigned long addr)
return 1;
if (is_module_text_address(addr))
return 1;
- return is_ftrace_trampoline(addr);
+ if (is_ftrace_trampoline(addr))
+ return 1;
+ if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+ return 1;
+ return 0;
}
/*
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 4346010..ebb4dad 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -149,9 +149,11 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
struct kprobe_insn_page *kip;
kprobe_opcode_t *slot = NULL;
+ /* Since the slot array is not protected by rcu, we need a mutex */
mutex_lock(&c->mutex);
retry:
- list_for_each_entry(kip, &c->pages, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
if (kip->nused < slots_per_page(c)) {
int i;
for (i = 0; i < slots_per_page(c); i++) {
@@ -159,6 +161,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
kip->slot_used[i] = SLOT_USED;
kip->nused++;
slot = kip->insns + (i * c->insn_size);
+ rcu_read_unlock();
goto out;
}
}
@@ -167,6 +170,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
WARN_ON(1);
}
}
+ rcu_read_unlock();
/* If there are any garbage slots, collect it and try again. */
if (c->nr_garbage && collect_garbage_slots(c) == 0)
@@ -193,7 +197,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
kip->nused = 1;
kip->ngarbage = 0;
kip->cache = c;
- list_add(&kip->list, &c->pages);
+ list_add_rcu(&kip->list, &c->pages);
slot = kip->insns;
out:
mutex_unlock(&c->mutex);
@@ -213,7 +217,8 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
* next time somebody inserts a probe.
*/
if (!list_is_singular(&kip->list)) {
- list_del(&kip->list);
+ list_del_rcu(&kip->list);
+ synchronize_rcu();
kip->cache->free(kip->insns);
kfree(kip);
}
@@ -235,8 +240,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
continue;
kip->ngarbage = 0; /* we will collect all garbages */
for (i = 0; i < slots_per_page(c); i++) {
- if (kip->slot_used[i] == SLOT_DIRTY &&
- collect_one_slot(kip, i))
+ if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i))
break;
}
}
@@ -248,29 +252,60 @@ void __free_insn_slot(struct kprobe_insn_cache *c,
kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
+ long idx;
mutex_lock(&c->mutex);
- list_for_each_entry(kip, &c->pages, list) {
- long idx = ((long)slot - (long)kip->insns) /
- (c->insn_size * sizeof(kprobe_opcode_t));
- if (idx >= 0 && idx < slots_per_page(c)) {
- WARN_ON(kip->slot_used[idx] != SLOT_USED);
- if (dirty) {
- kip->slot_used[idx] = SLOT_DIRTY;
- kip->ngarbage++;
- if (++c->nr_garbage > slots_per_page(c))
- collect_garbage_slots(c);
- } else
- collect_one_slot(kip, idx);
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
+ idx = ((long)slot - (long)kip->insns) /
+ (c->insn_size * sizeof(kprobe_opcode_t));
+ if (idx >= 0 && idx < slots_per_page(c))
goto out;
+ }
+ /* Could not find this slot. */
+ WARN_ON(1);
+ kip = NULL;
+out:
+ rcu_read_unlock();
+ /* Mark and sweep: this may sleep */
+ if (kip) {
+ /* Check double free */
+ WARN_ON(kip->slot_used[idx] != SLOT_USED);
+ if (dirty) {
+ kip->slot_used[idx] = SLOT_DIRTY;
+ kip->ngarbage++;
+ if (++c->nr_garbage > slots_per_page(c))
+ collect_garbage_slots(c);
+ } else {
+ collect_one_slot(kip, idx);
}
}
- /* Could not free this slot. */
- WARN_ON(1);
-out:
mutex_unlock(&c->mutex);
}
+/*
+ * Check given address is on the page of kprobe instruction slots.
+ * This will be used for checking whether the address on a stack
+ * is on a text area or not.
+ */
+bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
+{
+ struct kprobe_insn_page *kip;
+ bool ret = false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(kip, &c->pages, list) {
+ if (addr >= (unsigned long)kip->insns &&
+ addr < (unsigned long)kip->insns + PAGE_SIZE) {
+ ret = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
#ifdef CONFIG_OPTPROBES
/* For optimized_kprobe buffer */
struct kprobe_insn_cache kprobe_optinsn_slots = {
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a2b3eb3..af05f8e 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -84,6 +84,15 @@ struct kvm_regs {
#define KVM_VGIC_V2_DIST_SIZE 0x1000
#define KVM_VGIC_V2_CPU_SIZE 0x2000
+/* Supported VGICv3 address types */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
+
+#define KVM_VGIC_V3_DIST_SIZE SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
+
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index c93cf35..3603b6f 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -573,6 +573,10 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
/* Transactional Memory checkpointed state:
* This is all GPRs, all VSX regs and a subset of SPRs
*/
@@ -596,6 +600,7 @@ struct kvm_get_htab_header {
#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
/* PPC64 eXternal Interrupt Controller Specification */
#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index cddd5d0..eafee31 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -105,6 +105,7 @@
#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */
@@ -188,10 +189,14 @@
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
@@ -220,11 +225,13 @@
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
@@ -278,8 +285,10 @@
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
@@ -310,4 +319,6 @@
#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 37fee27..1445865 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,8 @@
#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
#define EXIT_REASON_APIC_ACCESS 44
#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_GDTR_IDTR 46
+#define EXIT_REASON_LDTR_TR 47
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
@@ -113,6 +115,8 @@
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
{ EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
+ { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
+ { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
{ EXIT_REASON_INVEPT, "INVEPT" }, \
@@ -129,6 +133,7 @@
{ EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
+#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 99c0ccd..e279a71 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -19,6 +19,16 @@
Q=@
endif
+ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+ quiet=silent_
+endif
+else # make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+ quiet=silent_
+endif
+endif
+
build-dir := $(srctree)/tools/build
# Define $(fixdep) for dep-cmd function
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index f99f49e4..4b6bfc4 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -38,6 +38,10 @@
#define HUGETLBFS_MAGIC 0x958458f6
#endif
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
static const char * const sysfs__fs_known_mountpoints[] = {
"/sys",
0,
@@ -75,6 +79,11 @@ static const char * const hugetlbfs__known_mountpoints[] = {
0,
};
+static const char * const bpf_fs__known_mountpoints[] = {
+ "/sys/fs/bpf",
+ 0,
+};
+
struct fs {
const char *name;
const char * const *mounts;
@@ -89,6 +98,7 @@ enum {
FS__DEBUGFS = 2,
FS__TRACEFS = 3,
FS__HUGETLBFS = 4,
+ FS__BPF_FS = 5,
};
#ifndef TRACEFS_MAGIC
@@ -121,6 +131,11 @@ static struct fs fs__entries[] = {
.mounts = hugetlbfs__known_mountpoints,
.magic = HUGETLBFS_MAGIC,
},
+ [FS__BPF_FS] = {
+ .name = "bpf",
+ .mounts = bpf_fs__known_mountpoints,
+ .magic = BPF_FS_MAGIC,
+ },
};
static bool fs__read_mounts(struct fs *fs)
@@ -280,6 +295,7 @@ FS(procfs, FS__PROCFS);
FS(debugfs, FS__DEBUGFS);
FS(tracefs, FS__TRACEFS);
FS(hugetlbfs, FS__HUGETLBFS);
+FS(bpf_fs, FS__BPF_FS);
int filename__read_int(const char *filename, int *value)
{
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index a63269f..6b332dc 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -22,6 +22,7 @@ FS(procfs)
FS(debugfs)
FS(tracefs)
FS(hugetlbfs)
+FS(bpf_fs)
#undef FS
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 84e6b35..ac6eb86 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4,6 +4,7 @@
* Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
* Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
* Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
@@ -22,15 +23,21 @@
#include <stdlib.h>
#include <stdio.h>
#include <stdarg.h>
+#include <libgen.h>
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
+#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/bpf.h>
#include <linux/list.h>
+#include <linux/limits.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
#include <libelf.h>
#include <gelf.h>
@@ -41,6 +48,10 @@
#define EM_BPF 247
#endif
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC 0xcafe4a11
+#endif
+
#define __printf(a, b) __attribute__((format(printf, a, b)))
__printf(1, 2)
@@ -779,7 +790,7 @@ static int
bpf_program__collect_reloc(struct bpf_program *prog,
size_t nr_maps, GElf_Shdr *shdr,
Elf_Data *data, Elf_Data *symbols,
- int maps_shndx)
+ int maps_shndx, struct bpf_map *maps)
{
int i, nrels;
@@ -829,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
return -LIBBPF_ERRNO__RELOC;
}
- map_idx = sym.st_value / sizeof(struct bpf_map_def);
+ /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+ for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+ if (maps[map_idx].offset == sym.st_value) {
+ pr_debug("relocation: find map %zd (%s) for insn %u\n",
+ map_idx, maps[map_idx].name, insn_idx);
+ break;
+ }
+ }
+
if (map_idx >= nr_maps) {
pr_warning("bpf relocation: map_idx %d large than %d\n",
(int)map_idx, (int)nr_maps - 1);
@@ -953,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
err = bpf_program__collect_reloc(prog, nr_maps,
shdr, data,
obj->efile.symbols,
- obj->efile.maps_shndx);
+ obj->efile.maps_shndx,
+ obj->maps);
if (err)
return err;
}
@@ -1227,6 +1247,191 @@ int bpf_object__load(struct bpf_object *obj)
return err;
}
+static int check_path(const char *path)
+{
+ struct statfs st_fs;
+ char *dname, *dir;
+ int err = 0;
+
+ if (path == NULL)
+ return -EINVAL;
+
+ dname = strdup(path);
+ if (dname == NULL)
+ return -ENOMEM;
+
+ dir = dirname(dname);
+ if (statfs(dir, &st_fs)) {
+ pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+ err = -errno;
+ }
+ free(dname);
+
+ if (!err && st_fs.f_type != BPF_FS_MAGIC) {
+ pr_warning("specified path %s is not on BPF FS\n", path);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+ int instance)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (instance < 0 || instance >= prog->instances.nr) {
+ pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+ instance, prog->section_name, prog->instances.nr);
+ return -EINVAL;
+ }
+
+ if (bpf_obj_pin(prog->instances.fds[instance], path)) {
+ pr_warning("failed to pin program: %s\n", strerror(errno));
+ return -errno;
+ }
+ pr_debug("pinned program '%s'\n", path);
+
+ return 0;
+}
+
+static int make_dir(const char *path)
+{
+ int err = 0;
+
+ if (mkdir(path, 0700) && errno != EEXIST)
+ err = -errno;
+
+ if (err)
+ pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+ return err;
+}
+
+int bpf_program__pin(struct bpf_program *prog, const char *path)
+{
+ int i, err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (prog == NULL) {
+ pr_warning("invalid program pointer\n");
+ return -EINVAL;
+ }
+
+ if (prog->instances.nr <= 0) {
+ pr_warning("no instances of prog %s to pin\n",
+ prog->section_name);
+ return -EINVAL;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
+ for (i = 0; i < prog->instances.nr; i++) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_program__pin_instance(prog, buf, i);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int bpf_map__pin(struct bpf_map *map, const char *path)
+{
+ int err;
+
+ err = check_path(path);
+ if (err)
+ return err;
+
+ if (map == NULL) {
+ pr_warning("invalid map pointer\n");
+ return -EINVAL;
+ }
+
+ if (bpf_obj_pin(map->fd, path)) {
+ pr_warning("failed to pin map: %s\n", strerror(errno));
+ return -errno;
+ }
+
+ pr_debug("pinned map '%s'\n", path);
+ return 0;
+}
+
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+ struct bpf_program *prog;
+ struct bpf_map *map;
+ int err;
+
+ if (!obj)
+ return -ENOENT;
+
+ if (!obj->loaded) {
+ pr_warning("object not yet loaded; load it first\n");
+ return -ENOENT;
+ }
+
+ err = make_dir(path);
+ if (err)
+ return err;
+
+ bpf_map__for_each(map, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ bpf_map__name(map));
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_map__pin(map, buf);
+ if (err)
+ return err;
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ char buf[PATH_MAX];
+ int len;
+
+ len = snprintf(buf, PATH_MAX, "%s/%s", path,
+ prog->section_name);
+ if (len < 0)
+ return -EINVAL;
+ else if (len >= PATH_MAX)
+ return -ENAMETOOLONG;
+
+ err = bpf_program__pin(prog, buf);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
void bpf_object__close(struct bpf_object *obj)
{
size_t i;
@@ -1419,37 +1624,33 @@ static void bpf_program__set_type(struct bpf_program *prog,
prog->type = type;
}
-int bpf_program__set_tracepoint(struct bpf_program *prog)
-{
- if (!prog)
- return -EINVAL;
- bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
- return 0;
-}
-
-int bpf_program__set_kprobe(struct bpf_program *prog)
-{
- if (!prog)
- return -EINVAL;
- bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
- return 0;
-}
-
static bool bpf_program__is_type(struct bpf_program *prog,
enum bpf_prog_type type)
{
return prog ? (prog->type == type) : false;
}
-bool bpf_program__is_tracepoint(struct bpf_program *prog)
-{
- return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-}
+#define BPF_PROG_TYPE_FNS(NAME, TYPE) \
+int bpf_program__set_##NAME(struct bpf_program *prog) \
+{ \
+ if (!prog) \
+ return -EINVAL; \
+ bpf_program__set_type(prog, TYPE); \
+ return 0; \
+} \
+ \
+bool bpf_program__is_##NAME(struct bpf_program *prog) \
+{ \
+ return bpf_program__is_type(prog, TYPE); \
+} \
-bool bpf_program__is_kprobe(struct bpf_program *prog)
-{
- return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
-}
+BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
+BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
+BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
+BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
+BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
+BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
int bpf_map__fd(struct bpf_map *map)
{
@@ -1537,3 +1738,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
}
return ERR_PTR(-ENOENT);
}
+
+long libbpf_get_error(const void *ptr)
+{
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+ return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a5a8b86..b30394f 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -22,8 +22,8 @@
#define __BPF_LIBBPF_H
#include <stdio.h>
+#include <stdint.h>
#include <stdbool.h>
-#include <linux/err.h>
#include <sys/types.h> // for size_t
enum libbpf_errno {
@@ -65,6 +65,7 @@ struct bpf_object *bpf_object__open(const char *path);
struct bpf_object *bpf_object__open_buffer(void *obj_buf,
size_t obj_buf_sz,
const char *name);
+int bpf_object__pin(struct bpf_object *object, const char *path);
void bpf_object__close(struct bpf_object *object);
/* Load/unload object into/from kernel */
@@ -106,6 +107,9 @@ void *bpf_program__priv(struct bpf_program *prog);
const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
int bpf_program__fd(struct bpf_program *prog);
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+ int instance);
+int bpf_program__pin(struct bpf_program *prog, const char *path);
struct bpf_insn;
@@ -174,11 +178,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
/*
* Adjust type of bpf program. Default is kprobe.
*/
+int bpf_program__set_socket_filter(struct bpf_program *prog);
int bpf_program__set_tracepoint(struct bpf_program *prog);
int bpf_program__set_kprobe(struct bpf_program *prog);
+int bpf_program__set_sched_cls(struct bpf_program *prog);
+int bpf_program__set_sched_act(struct bpf_program *prog);
+int bpf_program__set_xdp(struct bpf_program *prog);
+int bpf_program__set_perf_event(struct bpf_program *prog);
+bool bpf_program__is_socket_filter(struct bpf_program *prog);
bool bpf_program__is_tracepoint(struct bpf_program *prog);
bool bpf_program__is_kprobe(struct bpf_program *prog);
+bool bpf_program__is_sched_cls(struct bpf_program *prog);
+bool bpf_program__is_sched_act(struct bpf_program *prog);
+bool bpf_program__is_xdp(struct bpf_program *prog);
+bool bpf_program__is_perf_event(struct bpf_program *prog);
/*
* We don't need __attribute__((packed)) now since it is
@@ -223,5 +237,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
int bpf_map__set_priv(struct bpf_map *map, void *priv,
bpf_map_clear_priv_t clear_priv);
void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__pin(struct bpf_map *map, const char *path);
+
+long libbpf_get_error(const void *ptr);
#endif
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 11c3be3..f054ca1 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,6 +1,7 @@
#ifndef __SUBCMD_PARSE_OPTIONS_H
#define __SUBCMD_PARSE_OPTIONS_H
+#include <linux/kernel.h>
#include <stdbool.h>
#include <stdint.h>
@@ -132,32 +133,32 @@ struct option {
#define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
#define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
#define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
-#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
- .value = check_vtype(v, const char **), (a), .help = (h), \
+ .value = check_vtype(v, const char **), .argh =(a), .help = (h), \
.flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
#define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
- .value = check_vtype(v, const char **), (a), .help = (h), \
+ .value = check_vtype(v, const char **), .argh = (a), .help = (h), \
.flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
.set = check_vtype(os, bool *)}
-#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
+#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
#define OPT_DATE(s, l, v, h) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
#define OPT_CALLBACK(s, l, v, a, h, f) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
- { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
#define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
- .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+ .value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
- .value = (v), (a), .help = (h), .callback = (f), \
+ .value = (v), .argh = (a), .help = (h), .callback = (f), \
.flags = PARSE_OPT_OPTARG, .data = (d) }
/* parse_options() will filter out the processed options and leave the
diff --git a/tools/perf/Build b/tools/perf/Build
index b12d5d1..9b79f8d 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -3,10 +3,12 @@
perf-y += builtin-config.o
perf-y += builtin-diff.o
perf-y += builtin-evlist.o
+perf-y += builtin-ftrace.o
perf-y += builtin-help.o
perf-y += builtin-sched.o
perf-y += builtin-buildid-list.o
perf-y += builtin-buildid-cache.o
+perf-y += builtin-kallsyms.o
perf-y += builtin-list.o
perf-y += builtin-record.o
perf-y += builtin-report.o
@@ -39,8 +41,7 @@
CFLAGS_builtin-timechart.o += $(paths)
CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \
-DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \
- -DPREFIX="BUILD_STR($(prefix_SQ))" \
- -include $(OUTPUT)PERF-VERSION-FILE
+ -DPREFIX="BUILD_STR($(prefix_SQ))"
CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 3f06730..2da07e5 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -248,7 +248,7 @@
Code address, Code symbol, Shared Object, Source line
dso - coalesced by shared object
-By default the coalescing is setup with 'pid,tid,iaddr'.
+By default the coalescing is setup with 'pid,iaddr'.
STDIO OUTPUT
------------
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
new file mode 100644
index 0000000..2d96de6
--- /dev/null
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -0,0 +1,36 @@
+perf-ftrace(1)
+=============
+
+NAME
+----
+perf-ftrace - simple wrapper for kernel's ftrace functionality
+
+
+SYNOPSIS
+--------
+[verse]
+'perf ftrace' <command>
+
+DESCRIPTION
+-----------
+The 'perf ftrace' command is a simple wrapper of kernel's ftrace
+functionality. It only supports single thread tracing currently and
+just reads trace_pipe in text and then write it to stdout.
+
+The following options apply to perf ftrace.
+
+OPTIONS
+-------
+
+-t::
+--tracer=::
+ Tracer to use: function_graph or function.
+
+-v::
+--verbose=::
+ Verbosity level.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
new file mode 100644
index 0000000..954ea9e
--- /dev/null
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -0,0 +1,24 @@
+perf-kallsyms(1)
+==============
+
+NAME
+----
+perf-kallsyms - Searches running kernel for symbols
+
+SYNOPSIS
+--------
+[verse]
+'perf kallsyms <options> symbol_name[,symbol_name...]'
+
+DESCRIPTION
+-----------
+This command searches the running kernel kallsyms file for the given symbol(s)
+and prints information about it, including the DSO, the kallsyms begin/end
+addresses and the addresses in the ELF kallsyms symbol table (for symbols in
+modules).
+
+OPTIONS
+-------
+-v::
+--verbose=::
+ Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5054d91..27256bc 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -421,9 +421,19 @@
--timestamp-filename
Append timestamp to output file name.
---switch-output::
+--switch-output[=mode]::
Generate multiple perf.data files, timestamp prefixed, switching to a new one
-when receiving a SIGUSR2.
+based on 'mode' value:
+ "signal" - when receiving a SIGUSR2 (default value) or
+ <size> - when reaching the size threshold, size is expected to
+ be a number with appended unit character - B/K/M/G
+ <time> - when reaching the time threshold, size is expected to
+ be a number with appended unit character - s/m/h/d
+
+ Note: the precision of the size threshold hugely depends
+ on your configuration - the number and size of your ring
+ buffers (-m). It is generally more precise for higher sizes
+ (like >5M), for lower values expect different sizes.
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
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 7617396..d33dedd 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -143,6 +143,8 @@
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
+--state::
+ Show task state when it switched out.
SEE ALSO
--------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5dc5c6a..4ed5f23 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -36,7 +36,7 @@
'perf script report <script> [args]' to run and display the results
of <script>. <script> is the name displayed in the output of 'perf
- trace --list' i.e. the actual script name minus any language
+ script --list' i.e. the actual script name minus any language
extension. The perf.data output from a previous run of 'perf script
record <script>' is used and should be present for this command to
succeed. [args] refers to the (mainly optional) args expected by
@@ -76,7 +76,7 @@
Any command you can specify in a shell.
-D::
---dump-raw-script=::
+--dump-raw-trace=::
Display verbose dump of the trace data.
-L::
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 781b019..afd7286 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,10 @@
-e::
--expr::
- List of syscalls to show, currently only syscall names.
+--event::
+ List of syscalls and other perf events (tracepoints, HW cache events,
+ etc) to show.
+ See 'perf list' for a complete list of events.
Prefixing with ! shows all syscalls but the ones specified. You may
need to escape it.
@@ -135,9 +138,6 @@
--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
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 76c84f0..03cf947 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -291,8 +291,10 @@
endif
endif
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
+ ifndef NO_DWARF
+ msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+ NO_DWARF := 1
+ endif
else
ifneq ($(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);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8bb16aa..4da19b6 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -661,6 +661,7 @@
endif
ifndef NO_JVMTI
$(call QUIET_INSTALL, $(LIBJVMTI)) \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
endif
$(call QUIET_INSTALL, libexec) \
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 2675936..36e375f 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -2,12 +2,12 @@
/* This is included in perf/util/dwarf-regs.c */
static const char * const aarch64_regstr_tbl[] = {
- "%r0", "%r1", "%r2", "%r3", "%r4",
- "%r5", "%r6", "%r7", "%r8", "%r9",
- "%r10", "%r11", "%r12", "%r13", "%r14",
- "%r15", "%r16", "%r17", "%r18", "%r19",
- "%r20", "%r21", "%r22", "%r23", "%r24",
- "%r25", "%r26", "%r27", "%r28", "%r29",
+ "%x0", "%x1", "%x2", "%x3", "%x4",
+ "%x5", "%x6", "%x7", "%x8", "%x9",
+ "%x10", "%x11", "%x12", "%x13", "%x14",
+ "%x15", "%x16", "%x17", "%x18", "%x19",
+ "%x20", "%x21", "%x22", "%x23", "%x24",
+ "%x25", "%x26", "%x27", "%x28", "%x29",
"%lr", "%sp",
};
#endif
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f8ca7a4..e2b2172 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -58,7 +58,7 @@ struct c2c_hist_entry {
struct hist_entry he;
};
-static char const *coalesce_default = "pid,tid,iaddr";
+static char const *coalesce_default = "pid,iaddr";
struct perf_c2c {
struct perf_tool tool;
@@ -2476,6 +2476,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
"mean_rmt,"
"mean_lcl,"
"mean_load,"
+ "tot_recs,"
"cpucnt,",
add_sym ? "symbol," : "",
add_dso ? "dso," : "",
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 0000000..c3e6436
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,265 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "builtin.h"
+#include "perf.h"
+
+#include <unistd.h>
+#include <signal.h>
+
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+#include "util/config.h"
+
+
+#define DEFAULT_TRACER "function_graph"
+
+struct perf_ftrace {
+ struct perf_evlist *evlist;
+ struct target target;
+ const char *tracer;
+};
+
+static bool done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+ done = true;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+ siginfo_t *info __maybe_unused,
+ void *ucontext __maybe_unused)
+{
+ /* workload_exec_errno = info->si_value.sival_int; */
+ done = true;
+}
+
+static int write_tracing_file(const char *name, const char *val)
+{
+ char *file;
+ int fd, ret = -1;
+ ssize_t size = strlen(val);
+
+ file = get_tracing_file(name);
+ if (!file) {
+ pr_debug("cannot get tracing file: %s\n", name);
+ return -1;
+ }
+
+ fd = open(file, O_WRONLY);
+ if (fd < 0) {
+ pr_debug("cannot open tracing file: %s\n", name);
+ goto out;
+ }
+
+ if (write(fd, val, size) == size)
+ ret = 0;
+ else
+ pr_debug("write '%s' to tracing/%s failed\n", val, name);
+
+ close(fd);
+out:
+ put_tracing_file(file);
+ return ret;
+}
+
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+ if (write_tracing_file("tracing_on", "0") < 0)
+ return -1;
+
+ if (write_tracing_file("current_tracer", "nop") < 0)
+ return -1;
+
+ if (write_tracing_file("set_ftrace_pid", " ") < 0)
+ return -1;
+
+ return 0;
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+ char *trace_file;
+ int trace_fd;
+ char *trace_pid;
+ char buf[4096];
+ struct pollfd pollfd = {
+ .events = POLLIN,
+ };
+
+ if (geteuid() != 0) {
+ pr_err("ftrace only works for root!\n");
+ return -1;
+ }
+
+ if (argc < 1)
+ return -1;
+
+ signal(SIGINT, sig_handler);
+ signal(SIGUSR1, sig_handler);
+ signal(SIGCHLD, sig_handler);
+
+ reset_tracing_files(ftrace);
+
+ /* reset ftrace buffer */
+ if (write_tracing_file("trace", "0") < 0)
+ goto out;
+
+ if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+ argv, false, ftrace__workload_exec_failed_signal) < 0)
+ goto out;
+
+ if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+ pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+ goto out;
+ }
+
+ if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+ pr_err("failed to allocate pid string\n");
+ goto out;
+ }
+
+ if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+ pr_err("failed to set pid: %s\n", trace_pid);
+ goto out_free_pid;
+ }
+
+ trace_file = get_tracing_file("trace_pipe");
+ if (!trace_file) {
+ pr_err("failed to open trace_pipe\n");
+ goto out_free_pid;
+ }
+
+ trace_fd = open(trace_file, O_RDONLY);
+
+ put_tracing_file(trace_file);
+
+ if (trace_fd < 0) {
+ pr_err("failed to open trace_pipe\n");
+ goto out_free_pid;
+ }
+
+ fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+ pollfd.fd = trace_fd;
+
+ if (write_tracing_file("tracing_on", "1") < 0) {
+ pr_err("can't enable tracing\n");
+ goto out_close_fd;
+ }
+
+ perf_evlist__start_workload(ftrace->evlist);
+
+ while (!done) {
+ if (poll(&pollfd, 1, -1) < 0)
+ break;
+
+ if (pollfd.revents & POLLIN) {
+ int n = read(trace_fd, buf, sizeof(buf));
+ if (n < 0)
+ break;
+ if (fwrite(buf, n, 1, stdout) != 1)
+ break;
+ }
+ }
+
+ write_tracing_file("tracing_on", "0");
+
+ /* read remaining buffer contents */
+ while (true) {
+ int n = read(trace_fd, buf, sizeof(buf));
+ if (n <= 0)
+ break;
+ if (fwrite(buf, n, 1, stdout) != 1)
+ break;
+ }
+
+out_close_fd:
+ close(trace_fd);
+out_free_pid:
+ free(trace_pid);
+out:
+ reset_tracing_files(ftrace);
+
+ return done ? 0 : -1;
+}
+
+static int perf_ftrace_config(const char *var, const char *value, void *cb)
+{
+ struct perf_ftrace *ftrace = cb;
+
+ if (prefixcmp(var, "ftrace."))
+ return 0;
+
+ if (strcmp(var, "ftrace.tracer"))
+ return -1;
+
+ if (!strcmp(value, "function_graph") ||
+ !strcmp(value, "function")) {
+ ftrace->tracer = value;
+ return 0;
+ }
+
+ pr_err("Please select \"function_graph\" (default) or \"function\"\n");
+ return -1;
+}
+
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ int ret;
+ struct perf_ftrace ftrace = {
+ .tracer = DEFAULT_TRACER,
+ .target = { .uid = UINT_MAX, },
+ };
+ const char * const ftrace_usage[] = {
+ "perf ftrace [<options>] <command>",
+ "perf ftrace [<options>] -- <command> [<options>]",
+ NULL
+ };
+ const struct option ftrace_options[] = {
+ OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+ "tracer to use: function_graph(default) or function"),
+ OPT_INCR('v', "verbose", &verbose,
+ "be more verbose"),
+ OPT_END()
+ };
+
+ ret = perf_config(perf_ftrace_config, &ftrace);
+ if (ret < 0)
+ return -1;
+
+ argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (!argc)
+ usage_with_options(ftrace_usage, ftrace_options);
+
+ ftrace.evlist = perf_evlist__new();
+ if (ftrace.evlist == NULL)
+ return -ENOMEM;
+
+ ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+ if (ret < 0)
+ goto out_delete_evlist;
+
+ ret = __cmd_ftrace(&ftrace, argc, argv);
+
+out_delete_evlist:
+ perf_evlist__delete(ftrace.evlist);
+
+ return ret;
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3bdb2c7..aed0d84 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
const char * const builtin_help_subcommands[] = {
"buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
"record", "report", "bench", "stat", "timechart", "top", "annotate",
- "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
+ "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
#ifdef HAVE_LIBELF_SUPPORT
"probe",
#endif
@@ -447,11 +447,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
const char *alias;
- int rc = 0;
+ int rc;
load_command_list("perf-", &main_cmds, &other_cmds);
- perf_config(perf_help_config, &help_format);
+ rc = perf_config(perf_help_config, &help_format);
+ if (rc)
+ return rc;
argc = parse_options_subcommand(argc, argv, builtin_help_options,
builtin_help_subcommands, builtin_help_usage, 0);
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
new file mode 100644
index 0000000..224bfc4
--- /dev/null
+++ b/tools/perf/builtin-kallsyms.c
@@ -0,0 +1,67 @@
+/*
+ * builtin-kallsyms.c
+ *
+ * Builtin command: Look for a symbol in the running kernel and its modules
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+#include <linux/compiler.h>
+#include <subcmd/parse-options.h>
+#include "debug.h"
+#include "machine.h"
+#include "symbol.h"
+
+static int __cmd_kallsyms(int argc, const char **argv)
+{
+ int i;
+ struct machine *machine = machine__new_kallsyms();
+
+ if (machine == NULL) {
+ pr_err("Couldn't read /proc/kallsyms\n");
+ return -1;
+ }
+
+ for (i = 0; i < argc; ++i) {
+ struct map *map;
+ struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+
+ if (symbol == NULL) {
+ printf("%s: not found\n", argv[i]);
+ continue;
+ }
+
+ printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
+ symbol->name, map->dso->short_name, map->dso->long_name,
+ map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
+ symbol->start, symbol->end);
+ }
+
+ machine__delete(machine);
+ return 0;
+}
+
+int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+ const struct option options[] = {
+ OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+ OPT_END()
+ };
+ const char * const kallsyms_usage[] = {
+ "perf kallsyms [<options>] symbol_name",
+ NULL
+ };
+
+ argc = parse_options(argc, argv, options, kallsyms_usage, 0);
+ if (argc < 1)
+ usage_with_options(kallsyms_usage, options);
+
+ symbol_conf.sort_by_name = true;
+ symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+ if (symbol__init(NULL) < 0)
+ return -1;
+
+ return __cmd_kallsyms(argc, argv);
+}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 915869e..29f4751 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1920,10 +1920,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
NULL
};
struct perf_session *session;
- int ret = -1;
const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n";
+ int ret = perf_config(kmem_config, NULL);
- perf_config(kmem_config, NULL);
+ if (ret)
+ return ret;
+
argc = parse_options_subcommand(argc, argv, kmem_options,
kmem_subcommands, kmem_usage, 0);
@@ -1948,6 +1950,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
if (session == NULL)
return -1;
+ ret = -1;
+
if (kmem_slab) {
if (!perf_evlist__find_tracepoint_by_name(session->evlist,
"kmem:kmalloc")) {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4ec10e9..ffac8ca 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -46,6 +46,15 @@
#include <asm/bug.h>
#include <linux/time64.h>
+struct switch_output {
+ bool enabled;
+ bool signal;
+ unsigned long size;
+ unsigned long time;
+ const char *str;
+ bool set;
+};
+
struct record {
struct perf_tool tool;
struct record_opts opts;
@@ -62,10 +71,33 @@ struct record {
bool no_buildid_cache_set;
bool buildid_all;
bool timestamp_filename;
- bool switch_output;
+ struct switch_output switch_output;
unsigned long long samples;
};
+static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
+
+static bool switch_output_signal(struct record *rec)
+{
+ return rec->switch_output.signal &&
+ trigger_is_ready(&switch_output_trigger);
+}
+
+static bool switch_output_size(struct record *rec)
+{
+ return rec->switch_output.size &&
+ trigger_is_ready(&switch_output_trigger) &&
+ (rec->bytes_written >= rec->switch_output.size);
+}
+
+static bool switch_output_time(struct record *rec)
+{
+ return rec->switch_output.time &&
+ trigger_is_ready(&switch_output_trigger);
+}
+
static int record__write(struct record *rec, void *bf, size_t size)
{
if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@@ -74,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size)
}
rec->bytes_written += size;
+
+ if (switch_output_size(rec))
+ trigger_hit(&switch_output_trigger);
+
return 0;
}
@@ -193,10 +229,6 @@ static volatile int done;
static volatile int signr = -1;
static volatile int child_finished;
-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)
{
if (sig == SIGCHLD)
@@ -712,6 +744,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
}
static void snapshot_sig_handler(int sig);
+static void alarm_sig_handler(int sig);
int __weak
perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@@ -842,11 +875,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
signal(SIGTERM, sig_handler);
signal(SIGSEGV, sigsegv_handler);
- if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
+ if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
signal(SIGUSR2, snapshot_sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
trigger_on(&auxtrace_snapshot_trigger);
- if (rec->switch_output)
+ if (rec->switch_output.enabled)
trigger_on(&switch_output_trigger);
} else {
signal(SIGUSR2, SIG_IGN);
@@ -1043,6 +1076,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
err = fd;
goto out_child;
}
+
+ /* re-arm the alarm */
+ if (rec->switch_output.time)
+ alarm(rec->switch_output.time);
}
if (hits == rec->samples) {
@@ -1352,6 +1389,78 @@ static int record__parse_mmap_pages(const struct option *opt,
return ret;
}
+static void switch_output_size_warn(struct record *rec)
+{
+ u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+ struct switch_output *s = &rec->switch_output;
+
+ wakeup_size /= 2;
+
+ if (s->size < wakeup_size) {
+ char buf[100];
+
+ unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
+ pr_warning("WARNING: switch-output data size lower than "
+ "wakeup kernel buffer size (%s) "
+ "expect bigger perf.data sizes\n", buf);
+ }
+}
+
+static int switch_output_setup(struct record *rec)
+{
+ struct switch_output *s = &rec->switch_output;
+ static struct parse_tag tags_size[] = {
+ { .tag = 'B', .mult = 1 },
+ { .tag = 'K', .mult = 1 << 10 },
+ { .tag = 'M', .mult = 1 << 20 },
+ { .tag = 'G', .mult = 1 << 30 },
+ { .tag = 0 },
+ };
+ static struct parse_tag tags_time[] = {
+ { .tag = 's', .mult = 1 },
+ { .tag = 'm', .mult = 60 },
+ { .tag = 'h', .mult = 60*60 },
+ { .tag = 'd', .mult = 60*60*24 },
+ { .tag = 0 },
+ };
+ unsigned long val;
+
+ if (!s->set)
+ return 0;
+
+ if (!strcmp(s->str, "signal")) {
+ s->signal = true;
+ pr_debug("switch-output with SIGUSR2 signal\n");
+ goto enabled;
+ }
+
+ val = parse_tag_value(s->str, tags_size);
+ if (val != (unsigned long) -1) {
+ s->size = val;
+ pr_debug("switch-output with %s size threshold\n", s->str);
+ goto enabled;
+ }
+
+ val = parse_tag_value(s->str, tags_time);
+ if (val != (unsigned long) -1) {
+ s->time = val;
+ pr_debug("switch-output with %s time threshold (%lu seconds)\n",
+ s->str, s->time);
+ goto enabled;
+ }
+
+ return -1;
+
+enabled:
+ rec->timestamp_filename = true;
+ s->enabled = true;
+
+ if (s->size && !rec->opts.no_buffering)
+ switch_output_size_warn(rec);
+
+ return 0;
+}
+
static const char * const __record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
@@ -1519,8 +1628,10 @@ static struct option __record_options[] = {
"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_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
+ &record.switch_output.set, "signal,size,time",
+ "Switch output when receive SIGUSR2 or cross size,time threshold",
+ "signal"),
OPT_BOOLEAN(0, "dry-run", &dry_run,
"Parse options then exit"),
OPT_END()
@@ -1559,7 +1670,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (rec->evlist == NULL)
return -ENOMEM;
- perf_config(perf_record_config, rec);
+ err = perf_config(perf_record_config, rec);
+ if (err)
+ return err;
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
@@ -1578,8 +1691,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
return -EINVAL;
}
- if (rec->switch_output)
- rec->timestamp_filename = true;
+ if (switch_output_setup(rec)) {
+ parse_options_usage(record_usage, record_options, "switch-output", 0);
+ return -EINVAL;
+ }
+
+ if (rec->switch_output.time) {
+ signal(SIGALRM, alarm_sig_handler);
+ alarm(rec->switch_output.time);
+ }
if (!rec->itr) {
rec->itr = auxtrace_record__init(rec->evlist, &err);
@@ -1629,7 +1749,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
if (rec->no_buildid_cache || rec->no_buildid) {
disable_buildid_cache();
- } else if (rec->switch_output) {
+ } else if (rec->switch_output.enabled) {
/*
* In 'perf record --switch-output', disable buildid
* generation by default to reduce data file switching
@@ -1721,6 +1841,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
static void snapshot_sig_handler(int sig __maybe_unused)
{
+ struct record *rec = &record;
+
if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
trigger_hit(&auxtrace_snapshot_trigger);
auxtrace_record__snapshot_started = 1;
@@ -1728,6 +1850,14 @@ static void snapshot_sig_handler(int sig __maybe_unused)
trigger_error(&auxtrace_snapshot_trigger);
}
- if (trigger_is_ready(&switch_output_trigger))
+ if (switch_output_signal(rec))
+ trigger_hit(&switch_output_trigger);
+}
+
+static void alarm_sig_handler(int sig __maybe_unused)
+{
+ struct record *rec = &record;
+
+ if (switch_output_time(rec))
trigger_hit(&switch_output_trigger);
}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 06cc759..dbd7fa0 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -847,7 +847,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
if (ret < 0)
return ret;
- perf_config(report__config, &report);
+ ret = perf_config(report__config, &report);
+ if (ret)
+ return ret;
argc = parse_options(argc, argv, options, report_usage, 0);
if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5b134b0..daceb32 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -77,6 +77,22 @@ struct sched_atom {
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
+/* task state bitmask, copied from include/linux/sched.h */
+#define TASK_RUNNING 0
+#define TASK_INTERRUPTIBLE 1
+#define TASK_UNINTERRUPTIBLE 2
+#define __TASK_STOPPED 4
+#define __TASK_TRACED 8
+/* in tsk->exit_state */
+#define EXIT_DEAD 16
+#define EXIT_ZOMBIE 32
+#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
+/* in tsk->state again */
+#define TASK_DEAD 64
+#define TASK_WAKEKILL 128
+#define TASK_WAKING 256
+#define TASK_PARKED 512
+
enum thread_state {
THREAD_SLEEPING = 0,
THREAD_WAIT_CPU,
@@ -206,6 +222,7 @@ struct perf_sched {
bool show_cpu_visual;
bool show_wakeups;
bool show_migrations;
+ bool show_state;
u64 skipped_samples;
const char *time_str;
struct perf_time_interval ptime;
@@ -216,13 +233,20 @@ struct perf_sched {
struct thread_runtime {
u64 last_time; /* time of previous sched in/out event */
u64 dt_run; /* run time */
- u64 dt_wait; /* time between CPU access (off cpu) */
+ u64 dt_sleep; /* time between CPU access by sleep (off cpu) */
+ u64 dt_iowait; /* time between CPU access by iowait (off cpu) */
+ u64 dt_preempt; /* time between CPU access by preempt (off cpu) */
u64 dt_delay; /* time between wakeup and sched-in */
u64 ready_to_run; /* time of wakeup */
struct stats run_stats;
u64 total_run_time;
+ u64 total_sleep_time;
+ u64 total_iowait_time;
+ u64 total_preempt_time;
+ u64 total_delay_time;
+ int last_state;
u64 migrations;
};
@@ -1821,6 +1845,9 @@ static void timehist_header(struct perf_sched *sched)
printf(" %-*s %9s %9s %9s", comm_width,
"task name", "wait time", "sch delay", "run time");
+ if (sched->show_state)
+ printf(" %s", "state");
+
printf("\n");
/*
@@ -1831,9 +1858,14 @@ static void timehist_header(struct perf_sched *sched)
if (sched->show_cpu_visual)
printf(" %*s ", ncpus, "");
- printf(" %-*s %9s %9s %9s\n", comm_width,
+ printf(" %-*s %9s %9s %9s", comm_width,
"[tid/pid]", "(msec)", "(msec)", "(msec)");
+ if (sched->show_state)
+ printf(" %5s", "");
+
+ printf("\n");
+
/*
* separator
*/
@@ -1846,18 +1878,34 @@ static void timehist_header(struct perf_sched *sched)
graph_dotted_line, graph_dotted_line, graph_dotted_line,
graph_dotted_line);
+ if (sched->show_state)
+ printf(" %.5s", graph_dotted_line);
+
printf("\n");
}
+static char task_state_char(struct thread *thread, int state)
+{
+ static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+ unsigned bit = state ? ffs(state) : 0;
+
+ /* 'I' for idle */
+ if (thread->tid == 0)
+ return 'I';
+
+ return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
static void timehist_print_sample(struct perf_sched *sched,
struct perf_sample *sample,
struct addr_location *al,
struct thread *thread,
- u64 t)
+ u64 t, int state)
{
struct thread_runtime *tr = thread__priv(thread);
u32 max_cpus = sched->max_cpu + 1;
char tstr[64];
+ u64 wait_time;
timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
printf("%15s [%04d] ", tstr, sample->cpu);
@@ -1880,10 +1928,15 @@ static void timehist_print_sample(struct perf_sched *sched,
printf(" %-*s ", comm_width, timehist_get_commstr(thread));
- print_sched_time(tr->dt_wait, 6);
+ wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
+ print_sched_time(wait_time, 6);
+
print_sched_time(tr->dt_delay, 6);
print_sched_time(tr->dt_run, 6);
+ if (sched->show_state)
+ printf(" %5c ", task_state_char(thread, state));
+
if (sched->show_wakeups)
printf(" %-*s", comm_width, "");
@@ -1930,8 +1983,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
u64 t, u64 tprev)
{
r->dt_delay = 0;
- r->dt_wait = 0;
+ r->dt_sleep = 0;
+ r->dt_iowait = 0;
+ r->dt_preempt = 0;
r->dt_run = 0;
+
if (tprev) {
r->dt_run = t - tprev;
if (r->ready_to_run) {
@@ -1943,12 +1999,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
if (r->last_time > tprev)
pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
- else if (r->last_time)
- r->dt_wait = tprev - r->last_time;
+ else if (r->last_time) {
+ u64 dt_wait = tprev - r->last_time;
+
+ if (r->last_state == TASK_RUNNING)
+ r->dt_preempt = dt_wait;
+ else if (r->last_state == TASK_UNINTERRUPTIBLE)
+ r->dt_iowait = dt_wait;
+ else
+ r->dt_sleep = dt_wait;
+ }
}
update_stats(&r->run_stats, r->dt_run);
- r->total_run_time += r->dt_run;
+
+ r->total_run_time += r->dt_run;
+ r->total_delay_time += r->dt_delay;
+ r->total_sleep_time += r->dt_sleep;
+ r->total_iowait_time += r->dt_iowait;
+ r->total_preempt_time += r->dt_preempt;
}
static bool is_idle_sample(struct perf_sample *sample,
@@ -2373,6 +2442,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
struct thread_runtime *tr = NULL;
u64 tprev, t = sample->time;
int rc = 0;
+ int state = perf_evsel__intval(evsel, sample, "prev_state");
+
if (machine__resolve(machine, &al, sample) < 0) {
pr_err("problem processing %d event. skipping it\n",
@@ -2447,8 +2518,10 @@ static int timehist_sched_change_event(struct perf_tool *tool,
* time. we only care total run time and run stat.
*/
last_tr->dt_run = 0;
- last_tr->dt_wait = 0;
last_tr->dt_delay = 0;
+ last_tr->dt_sleep = 0;
+ last_tr->dt_iowait = 0;
+ last_tr->dt_preempt = 0;
if (itr->cursor.nr)
callchain_append(&itr->callchain, &itr->cursor, t - tprev);
@@ -2458,7 +2531,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
}
if (!sched->summary_only)
- timehist_print_sample(sched, sample, &al, thread, t);
+ timehist_print_sample(sched, sample, &al, thread, t, state);
out:
if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -2470,6 +2543,9 @@ static int timehist_sched_change_event(struct perf_tool *tool,
/* time of this sched_switch event becomes last time task seen */
tr->last_time = sample->time;
+ /* last state is used to determine where to account wait time */
+ tr->last_state = state;
+
/* sched out event for task so reset ready to run time */
tr->ready_to_run = 0;
}
@@ -2526,7 +2602,26 @@ static void print_thread_runtime(struct thread *t,
printf("\n");
}
+static void print_thread_waittime(struct thread *t,
+ struct thread_runtime *r)
+{
+ printf("%*s %5d %9" PRIu64 " ",
+ comm_width, timehist_get_commstr(t), t->ppid,
+ (u64) r->run_stats.n);
+
+ print_sched_time(r->total_run_time, 8);
+ print_sched_time(r->total_sleep_time, 6);
+ printf(" ");
+ print_sched_time(r->total_iowait_time, 6);
+ printf(" ");
+ print_sched_time(r->total_preempt_time, 6);
+ printf(" ");
+ print_sched_time(r->total_delay_time, 6);
+ printf("\n");
+}
+
struct total_run_stats {
+ struct perf_sched *sched;
u64 sched_count;
u64 task_count;
u64 total_run_time;
@@ -2545,7 +2640,11 @@ static int __show_thread_runtime(struct thread *t, void *priv)
stats->task_count++;
stats->sched_count += r->run_stats.n;
stats->total_run_time += r->total_run_time;
- print_thread_runtime(t, r);
+
+ if (stats->sched->show_state)
+ print_thread_waittime(t, r);
+ else
+ print_thread_runtime(t, r);
}
return 0;
@@ -2633,18 +2732,24 @@ static void timehist_print_summary(struct perf_sched *sched,
u64 hist_time = sched->hist_time.end - sched->hist_time.start;
memset(&totals, 0, sizeof(totals));
+ totals.sched = sched;
if (sched->idle_hist) {
printf("\nIdle-time summary\n");
printf("%*s parent sched-out ", comm_width, "comm");
printf(" idle-time min-idle avg-idle max-idle stddev migrations\n");
+ } else if (sched->show_state) {
+ printf("\nWait-time summary\n");
+ printf("%*s parent sched-in ", comm_width, "comm");
+ printf(" run-time sleep iowait preempt delay\n");
} else {
printf("\nRuntime summary\n");
printf("%*s parent sched-in ", comm_width, "comm");
printf(" run-time min-run avg-run max-run stddev migrations\n");
}
printf("%*s (count) ", comm_width, "");
- printf(" (msec) (msec) (msec) (msec) %%\n");
+ printf(" (msec) (msec) (msec) (msec) %s\n",
+ sched->show_state ? "(msec)" : "%");
printf("%.117s\n", graph_dotted_line);
machine__for_each_thread(m, show_thread_runtime, &totals);
@@ -3240,6 +3345,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
OPT_STRING(0, "time", &sched.time_str, "str",
"Time span for analysis (start,stop)"),
+ OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
OPT_PARENT(sched_options)
};
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f3ff69..c0783b4 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2180,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
"Show the mmap events"),
OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
"Show context switch events (if recorded)"),
- OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
OPT_BOOLEAN(0, "ns", &nanosecs,
"Use 9 decimal places when displaying time"),
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2212,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
PARSE_OPT_STOP_AT_NON_OPTION);
file.path = input_name;
+ file.force = symbol_conf.force;
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 3df4178..20aef98 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1216,7 +1216,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
if (top.evlist == NULL)
return -ENOMEM;
- perf_config(perf_top_config, &top);
+ status = perf_config(perf_top_config, &top);
+ if (status)
+ return status;
argc = parse_options(argc, argv, options, top_usage, 0);
if (argc)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 206bf72..40ef9b2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -40,6 +40,7 @@
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
#include <stdlib.h>
+#include <string.h>
#include <linux/err.h>
#include <linux/filter.h>
#include <linux/audit.h>
@@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
evsel->handler = handler;
}
+/*
+ * XXX: Hackish, just splitting the combined -e+--event (syscalls
+ * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
+ * existing facilities unchanged (trace->ev_qualifier + parse_options()).
+ *
+ * It'd be better to introduce a parse_options() variant that would return a
+ * list with the terms it didn't match to an event...
+ */
+static int trace__parse_events_option(const struct option *opt, const char *str,
+ int unset __maybe_unused)
+{
+ struct trace *trace = (struct trace *)opt->value;
+ const char *s = str;
+ char *sep = NULL, *lists[2] = { NULL, NULL, };
+ int len = strlen(str), err = -1, list;
+ char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
+ char group_name[PATH_MAX];
+
+ if (strace_groups_dir == NULL)
+ return -1;
+
+ if (*s == '!') {
+ ++s;
+ trace->not_ev_qualifier = true;
+ }
+
+ while (1) {
+ if ((sep = strchr(s, ',')) != NULL)
+ *sep = '\0';
+
+ list = 0;
+ if (syscalltbl__id(trace->sctbl, s) >= 0) {
+ list = 1;
+ } else {
+ path__join(group_name, sizeof(group_name), strace_groups_dir, s);
+ if (access(group_name, R_OK) == 0)
+ list = 1;
+ }
+
+ if (lists[list]) {
+ sprintf(lists[list] + strlen(lists[list]), ",%s", s);
+ } else {
+ lists[list] = malloc(len);
+ if (lists[list] == NULL)
+ goto out;
+ strcpy(lists[list], s);
+ }
+
+ if (!sep)
+ break;
+
+ *sep = ',';
+ s = sep + 1;
+ }
+
+ if (lists[1] != NULL) {
+ struct strlist_config slist_config = {
+ .dirname = strace_groups_dir,
+ };
+
+ trace->ev_qualifier = strlist__new(lists[1], &slist_config);
+ if (trace->ev_qualifier == NULL) {
+ fputs("Not enough memory to parse event qualifier", trace->output);
+ goto out;
+ }
+
+ if (trace__validate_ev_qualifier(trace))
+ goto out;
+ }
+
+ err = 0;
+
+ if (lists[0]) {
+ struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+ "event selector. use 'perf list' to list available events",
+ parse_events_option);
+ err = parse_events_option(&o, lists[0], 0);
+ }
+out:
+ if (sep)
+ *sep = ',';
+
+ return err;
+}
+
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char *trace_usage[] = {
@@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
.max_stack = UINT_MAX,
};
const char *output_name = NULL;
- const char *ev_qualifier_str = NULL;
const struct option trace_options[] = {
- OPT_CALLBACK(0, "event", &trace.evlist, "event",
- "event selector. use 'perf list' to list available events",
- parse_events_option),
+ OPT_CALLBACK('e', "event", &trace, "event",
+ "event/syscall selector. use 'perf list' to list available events",
+ trace__parse_events_option),
OPT_BOOLEAN(0, "comm", &trace.show_comm,
"show the thread COMM next to its id"),
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
- OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
+ OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
+ trace__parse_events_option),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
return -1;
}
- if (!trace.trace_syscalls && ev_qualifier_str) {
+ if (!trace.trace_syscalls && trace.ev_qualifier) {
pr_err("The -e option can't be used with --no-syscalls.\n");
goto out;
}
@@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
trace.open_id = syscalltbl__id(trace.sctbl, "open");
- if (ev_qualifier_str != NULL) {
- const char *s = ev_qualifier_str;
- struct strlist_config slist_config = {
- .dirname = system_path(STRACE_GROUPS_DIR),
- };
-
- trace.not_ev_qualifier = *s == '!';
- if (trace.not_ev_qualifier)
- ++s;
- trace.ev_qualifier = strlist__new(s, &slist_config);
- if (trace.ev_qualifier == NULL) {
- fputs("Not enough memory to parse event qualifier",
- trace.output);
- err = -ENOMEM;
- goto out_close;
- }
-
- err = trace__validate_ev_qualifier(&trace);
- if (err)
- goto out_close;
- }
-
err = target__validate(&trace.opts.target);
if (err) {
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 0bcf68e..036e1e3 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -23,6 +23,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix);
int cmd_evlist(int argc, const char **argv, const char *prefix);
int cmd_help(int argc, const char **argv, const char *prefix);
int cmd_sched(int argc, const char **argv, const char *prefix);
+int cmd_kallsyms(int argc, const char **argv, const char *prefix);
int cmd_list(int argc, const char **argv, const char *prefix);
int cmd_record(int argc, const char **argv, const char *prefix);
int cmd_report(int argc, const char **argv, const char *prefix);
@@ -40,6 +41,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix);
int cmd_inject(int argc, const char **argv, const char *prefix);
int cmd_mem(int argc, const char **argv, const char *prefix);
int cmd_data(int argc, const char **argv, const char *prefix);
+int cmd_ftrace(int argc, const char **argv, const char *prefix);
int find_scripts(char **scripts_array, char **scripts_path_array);
#endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ab5cbaa..ac3efd3 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -11,7 +11,9 @@
perf-diff mainporcelain common
perf-config mainporcelain common
perf-evlist mainporcelain common
+perf-ftrace mainporcelain common
perf-inject mainporcelain common
+perf-kallsyms mainporcelain common
perf-kmem mainporcelain common
perf-kvm mainporcelain common
perf-list mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index aa23b33..6d5479e 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -29,7 +29,6 @@ const char perf_usage_string[] =
const char perf_more_info_string[] =
"See 'perf help COMMAND' for more information on a specific command.";
-int use_browser = -1;
static int use_pager = -1;
const char *input_name;
@@ -47,6 +46,7 @@ static struct cmd_struct commands[] = {
{ "diff", cmd_diff, 0 },
{ "evlist", cmd_evlist, 0 },
{ "help", cmd_help, 0 },
+ { "kallsyms", cmd_kallsyms, 0 },
{ "list", cmd_list, 0 },
{ "record", cmd_record, 0 },
{ "report", cmd_report, 0 },
@@ -71,6 +71,7 @@ static struct cmd_struct commands[] = {
{ "inject", cmd_inject, 0 },
{ "mem", cmd_mem, 0 },
{ "data", cmd_data, 0 },
+ { "ftrace", cmd_ftrace, 0 },
};
struct pager_config {
@@ -89,11 +90,12 @@ static int pager_command_config(const char *var, const char *value, void *data)
/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
int check_pager_config(const char *cmd)
{
+ int err;
struct pager_config c;
c.cmd = cmd;
c.val = -1;
- perf_config(pager_command_config, &c);
- return c.val;
+ err = perf_config(pager_command_config, &c);
+ return err ?: c.val;
}
static int browser_command_config(const char *var, const char *value, void *data)
@@ -112,11 +114,12 @@ static int browser_command_config(const char *var, const char *value, void *data
*/
static int check_browser_config(const char *cmd)
{
+ int err;
struct pager_config c;
c.cmd = cmd;
c.val = -1;
- perf_config(browser_command_config, &c);
- return c.val;
+ err = perf_config(browser_command_config, &c);
+ return err ?: c.val;
}
static void commit_pager_choice(void)
@@ -329,8 +332,6 @@ static int handle_alias(int *argcp, const char ***argv)
return ret;
}
-const char perf_version_string[] = PERF_VERSION;
-
#define RUN_SETUP (1<<0)
#define USE_PAGER (1<<1)
@@ -510,6 +511,7 @@ static void cache_line_size(int *cacheline_sizep)
int main(int argc, const char **argv)
{
+ int err;
const char *cmd;
char sbuf[STRERR_BUFSIZE];
int value;
@@ -535,7 +537,9 @@ int main(int argc, const char **argv)
srandom(time(NULL));
perf_config__init();
- perf_config(perf_default_config, NULL);
+ err = perf_config(perf_default_config, NULL);
+ if (err)
+ return err;
set_buildid_dir(NULL);
/* get debugfs/tracefs mount point from /proc/mounts */
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6676c2d..1cb3d9b 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -44,6 +44,7 @@
perf-y += bitmap.o
perf-y += perf-hooks.o
perf-y += clang.o
+perf-y += unit_number__scnprintf.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 92343f4..1a04fe7 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -5,11 +5,13 @@
#include <util/evlist.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <api/fs/fs.h>
#include <bpf/bpf.h>
#include "tests.h"
#include "llvm.h"
#include "debug.h"
#define NR_ITERS 111
+#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
#ifdef HAVE_LIBBPF_SUPPORT
@@ -54,6 +56,7 @@ static struct {
const char *msg_load_fail;
int (*target_func)(void);
int expect_result;
+ bool pin;
} bpf_testcase_table[] = {
{
LLVM_TESTCASE_BASE,
@@ -63,6 +66,17 @@ static struct {
"load bpf object failed",
&epoll_wait_loop,
(NR_ITERS + 1) / 2,
+ false,
+ },
+ {
+ LLVM_TESTCASE_BASE,
+ "BPF pinning",
+ "[bpf_pinning]",
+ "fix kbuild first",
+ "check your vmlinux setting?",
+ &epoll_wait_loop,
+ (NR_ITERS + 1) / 2,
+ true,
},
#ifdef HAVE_BPF_PROLOGUE
{
@@ -73,6 +87,7 @@ static struct {
"check your vmlinux setting?",
&llseek_loop,
(NR_ITERS + 1) / 4,
+ false,
},
#endif
{
@@ -83,6 +98,7 @@ static struct {
"libbpf error when dealing with relocation",
NULL,
0,
+ false,
},
};
@@ -226,10 +242,34 @@ static int __test__bpf(int idx)
goto out;
}
- if (obj)
+ if (obj) {
ret = do_test(obj,
bpf_testcase_table[idx].target_func,
bpf_testcase_table[idx].expect_result);
+ if (ret != TEST_OK)
+ goto out;
+ if (bpf_testcase_table[idx].pin) {
+ int err;
+
+ if (!bpf_fs__mount()) {
+ pr_debug("BPF filesystem not mounted\n");
+ ret = TEST_FAIL;
+ goto out;
+ }
+ err = mkdir(PERF_TEST_BPF_PATH, 0777);
+ if (err && errno != EEXIST) {
+ pr_debug("Failed to make perf_test dir: %s\n",
+ strerror(errno));
+ ret = TEST_FAIL;
+ goto out;
+ }
+ if (bpf_object__pin(obj, PERF_TEST_BPF_PATH))
+ ret = TEST_FAIL;
+ if (rm_rf(PERF_TEST_BPF_PATH))
+ ret = TEST_FAIL;
+ }
+ }
+
out:
bpf__clear();
return ret;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a77dcc0..37e326b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -247,6 +247,10 @@ static struct test generic_tests[] = {
}
},
{
+ .desc = "unit_number__scnprintf",
+ .func = test__unit_number__scnprint,
+ },
+ {
.func = NULL,
},
};
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 02a33eb..d357dab 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
struct bpf_object *obj;
obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
- if (IS_ERR(obj))
+ if (libbpf_get_error(obj))
return TEST_FAIL;
bpf_object__close(obj);
return TEST_OK;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a512f0c..1fa9b9d 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -96,6 +96,7 @@ int test__perf_hooks(int subtest);
int test__clang(int subtest);
const char *test__clang_subtest_get_desc(int subtest);
int test__clang_subtest_get_nr(void);
+int test__unit_number__scnprint(int subtest);
#if defined(__arm__) || defined(__aarch64__)
#ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
new file mode 100644
index 0000000..623c2aa
--- /dev/null
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -0,0 +1,37 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "tests.h"
+#include "util.h"
+#include "debug.h"
+
+int test__unit_number__scnprint(int subtest __maybe_unused)
+{
+ struct {
+ u64 n;
+ const char *str;
+ } test[] = {
+ { 1, "1B" },
+ { 10*1024, "10K" },
+ { 20*1024*1024, "20M" },
+ { 30*1024*1024*1024ULL, "30G" },
+ { 0, "0B" },
+ { 0, NULL },
+ };
+ unsigned i = 0;
+
+ while (test[i].str) {
+ char buf[100];
+
+ unit_number__scnprintf(buf, sizeof(buf), test[i].n);
+
+ pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n",
+ test[i].n, test[i].str, buf);
+
+ if (strcmp(test[i].str, buf))
+ return TEST_FAIL;
+
+ i++;
+ }
+
+ return TEST_OK;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 641b402..fc4fb66 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -501,8 +501,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
return n;
}
-static void hist_entry__set_folding(struct hist_entry *he,
- struct hist_browser *hb, bool unfold)
+static void __hist_entry__set_folding(struct hist_entry *he,
+ struct hist_browser *hb, bool unfold)
{
hist_entry__init_have_children(he);
he->unfolded = unfold ? he->has_children : false;
@@ -520,12 +520,34 @@ static void hist_entry__set_folding(struct hist_entry *he,
he->nr_rows = 0;
}
+static void hist_entry__set_folding(struct hist_entry *he,
+ struct hist_browser *browser, bool unfold)
+{
+ double percent;
+
+ percent = hist_entry__get_percent_limit(he);
+ if (he->filtered || percent < browser->min_pcnt)
+ return;
+
+ __hist_entry__set_folding(he, browser, unfold);
+
+ if (!he->depth || unfold)
+ browser->nr_hierarchy_entries++;
+ if (he->leaf)
+ browser->nr_callchain_rows += he->nr_rows;
+ else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+ browser->nr_hierarchy_entries++;
+ he->has_no_entry = true;
+ he->nr_rows = 1;
+ } else
+ he->has_no_entry = false;
+}
+
static void
__hist_browser__set_folding(struct hist_browser *browser, bool unfold)
{
struct rb_node *nd;
struct hist_entry *he;
- double percent;
nd = rb_first(&browser->hists->entries);
while (nd) {
@@ -535,21 +557,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
hist_entry__set_folding(he, browser, unfold);
-
- percent = hist_entry__get_percent_limit(he);
- if (he->filtered || percent < browser->min_pcnt)
- continue;
-
- if (!he->depth || unfold)
- browser->nr_hierarchy_entries++;
- if (he->leaf)
- browser->nr_callchain_rows += he->nr_rows;
- else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
- browser->nr_hierarchy_entries++;
- he->has_no_entry = true;
- he->nr_rows = 1;
- } else
- he->has_no_entry = false;
}
}
@@ -564,6 +571,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
ui_browser__reset_index(&browser->b);
}
+static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold)
+{
+ if (!browser->he_selection)
+ return;
+
+ hist_entry__set_folding(browser->he_selection, browser, unfold);
+ browser->b.nr_entries = hist_browser__nr_entries(browser);
+}
+
static void ui_browser__warn_lost_events(struct ui_browser *browser)
{
ui_browser__warning(browser, 4,
@@ -637,10 +653,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
/* Collapse the whole world. */
hist_browser__set_folding(browser, false);
break;
+ case 'c':
+ /* Collapse the selected entry. */
+ hist_browser__set_folding_selected(browser, false);
+ break;
case 'E':
/* Expand the whole world. */
hist_browser__set_folding(browser, true);
break;
+ case 'e':
+ /* Expand the selected entry. */
+ hist_browser__set_folding_selected(browser, true);
+ break;
case 'H':
browser->show_headers = !browser->show_headers;
hist_browser__update_rows(browser);
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 1f6b099..50d13e58 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -7,6 +7,7 @@
pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
void *perf_gtk_handle;
+int use_browser = -1;
#ifdef HAVE_GTK2_SUPPORT
static int setup_gtk_browser(void)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3840e3a..5da376b 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -162,6 +162,7 @@
CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
CFLAGS_parse-events.o += -Wno-redundant-decls
+CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE
$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
$(call rule_mkdir)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8b610dd..aba9534 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -48,6 +48,8 @@ static int parse_callchain_mode(const char *value)
callchain_param.mode = CHAIN_FOLDED;
return 0;
}
+
+ pr_err("Invalid callchain mode: %s\n", value);
return -1;
}
@@ -63,6 +65,8 @@ static int parse_callchain_order(const char *value)
callchain_param.order_set = true;
return 0;
}
+
+ pr_err("Invalid callchain order: %s\n", value);
return -1;
}
@@ -80,6 +84,8 @@ static int parse_callchain_sort_key(const char *value)
callchain_param.branch_callstack = 1;
return 0;
}
+
+ pr_err("Invalid callchain sort key: %s\n", value);
return -1;
}
@@ -97,6 +103,8 @@ static int parse_callchain_value(const char *value)
callchain_param.value = CCVAL_COUNT;
return 0;
}
+
+ pr_err("Invalid callchain config key: %s\n", value);
return -1;
}
@@ -210,13 +218,17 @@ int perf_callchain_config(const char *var, const char *value)
return parse_callchain_sort_key(value);
if (!strcmp(var, "threshold")) {
callchain_param.min_percent = strtod(value, &endptr);
- if (value == endptr)
+ if (value == endptr) {
+ pr_err("Invalid callchain threshold: %s\n", value);
return -1;
+ }
}
if (!strcmp(var, "print-limit")) {
callchain_param.print_limit = strtod(value, &endptr);
- if (value == endptr)
+ if (value == endptr) {
+ pr_err("Invalid callchain print limit: %s\n", value);
return -1;
+ }
}
return 0;
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3d906db..0c7d5a4 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -386,8 +386,10 @@ static int perf_buildid_config(const char *var, const char *value)
if (!strcmp(var, "buildid.dir")) {
const char *dir = perf_config_dirname(var, value);
- if (!dir)
+ if (!dir) {
+ pr_err("Invalid buildid directory!\n");
return -1;
+ }
strncpy(buildid_dir, dir, MAXPATHLEN-1);
buildid_dir[MAXPATHLEN-1] = '\0';
}
@@ -405,10 +407,9 @@ static int perf_default_core_config(const char *var __maybe_unused,
static int perf_ui_config(const char *var, const char *value)
{
/* Add other config variables here. */
- if (!strcmp(var, "ui.show-headers")) {
+ if (!strcmp(var, "ui.show-headers"))
symbol_conf.show_hist_headers = perf_config_bool(var, value);
- return 0;
- }
+
return 0;
}
@@ -646,8 +647,13 @@ static int perf_config_set__init(struct perf_config_set *set)
goto out;
}
- if (stat(user_config, &st) < 0)
+ if (stat(user_config, &st) < 0) {
+ if (errno == ENOENT)
+ ret = 0;
goto out_free;
+ }
+
+ ret = 0;
if (st.st_uid && (st.st_uid != geteuid())) {
warning("File %s not owned by current user or root, "
@@ -655,11 +661,8 @@ static int perf_config_set__init(struct perf_config_set *set)
goto out_free;
}
- if (!st.st_size)
- goto out_free;
-
- ret = perf_config_from_file(collect_config, user_config, set);
-
+ if (st.st_size)
+ ret = perf_config_from_file(collect_config, user_config, set);
out_free:
free(user_config);
}
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 7123f4d..4e6cbc9 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1473,7 +1473,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
},
};
struct ctf_writer *cw = &c.writer;
- int err = -1;
+ int err;
if (opts->all) {
c.tool.comm = process_comm_event;
@@ -1481,12 +1481,15 @@ int bt_convert__perf2ctf(const char *input, const char *path,
c.tool.fork = process_fork_event;
}
- perf_config(convert__config, &c);
+ err = perf_config(convert__config, &c);
+ if (err)
+ return err;
/* CTF writer */
if (ctf_writer__init(cw, path))
return -1;
+ err = -1;
/* perf.data session */
session = perf_session__new(&file, 0, &c.tool);
if (!session)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d2c6cdd..28d41e7 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -9,6 +9,13 @@
#include "debug.h"
#include "vdso.h"
+static const char * const debuglink_paths[] = {
+ "%.0s%s",
+ "%s/%s",
+ "%s/.debug/%s",
+ "/usr/lib/debug%s/%s"
+};
+
char dso__symtab_origin(const struct dso *dso)
{
static const char origin[] = {
@@ -44,24 +51,43 @@ int dso__read_binary_type_filename(const struct dso *dso,
size_t len;
switch (type) {
- case DSO_BINARY_TYPE__DEBUGLINK: {
- char *debuglink;
+ case DSO_BINARY_TYPE__DEBUGLINK:
+ {
+ const char *last_slash;
+ char dso_dir[PATH_MAX];
+ char symfile[PATH_MAX];
+ unsigned int i;
len = __symbol__join_symfs(filename, size, dso->long_name);
- debuglink = filename + len;
- while (debuglink != filename && *debuglink != '/')
- debuglink--;
- if (*debuglink == '/')
- debuglink++;
+ last_slash = filename + len;
+ while (last_slash != filename && *last_slash != '/')
+ last_slash--;
- ret = -1;
- if (!is_regular_file(filename))
+ strncpy(dso_dir, filename, last_slash - filename);
+ dso_dir[last_slash-filename] = '\0';
+
+ if (!is_regular_file(filename)) {
+ ret = -1;
+ break;
+ }
+
+ ret = filename__read_debuglink(filename, symfile, PATH_MAX);
+ if (ret)
break;
- ret = filename__read_debuglink(filename, debuglink,
- size - (debuglink - filename));
+ /* Check predefined locations where debug file might reside */
+ ret = -1;
+ for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) {
+ snprintf(filename, size,
+ debuglink_paths[i], dso_dir, symfile);
+ if (is_regular_file(filename)) {
+ ret = 0;
+ break;
+ }
}
+
break;
+ }
case DSO_BINARY_TYPE__BUILD_ID_CACHE:
if (dso__build_id_filename(dso, filename, size) == NULL)
ret = -1;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d92e020..b601f28 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1184,7 +1184,7 @@ unsigned long perf_event_mlock_kb_in_pages(void)
return pages;
}
-static size_t perf_evlist__mmap_size(unsigned long pages)
+size_t perf_evlist__mmap_size(unsigned long pages)
{
if (pages == UINT_MAX)
pages = perf_event_mlock_kb_in_pages();
@@ -1224,12 +1224,16 @@ static long parse_pages_arg(const char *str, unsigned long min,
if (pages == 0 && min == 0) {
/* leave number of pages at 0 */
} else if (!is_power_of_2(pages)) {
+ char buf[100];
+
/* round pages up to next power of 2 */
pages = roundup_pow_of_two(pages);
if (!pages)
return -EINVAL;
- pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
- pages * page_size, pages);
+
+ unit_number__scnprintf(buf, sizeof(buf), pages * page_size);
+ pr_info("rounding mmap pages size to %s (%lu pages)\n",
+ buf, pages);
}
if (pages > max)
@@ -1797,7 +1801,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
*/
ret = write(evlist->workload.cork_fd, &bf, 1);
if (ret < 0)
- perror("enable to write to pipe");
+ perror("unable to write to pipe");
close(evlist->workload.cork_fd);
return ret;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4fd034f..389b9cc 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -218,6 +218,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
+size_t perf_evlist__mmap_size(unsigned long pages);
+
void perf_evlist__disable(struct perf_evlist *evlist);
void perf_evlist__enable(struct perf_evlist *evlist);
void perf_evlist__toggle_enable(struct perf_evlist *evlist);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d89c9c7..c567d9f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -41,6 +41,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
#define PERF_MAGIC __perf_magic2
+const char perf_version_string[] = PERF_VERSION;
+
struct perf_file_attr {
struct perf_event_attr attr;
struct perf_file_section ids;
@@ -2801,8 +2803,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
}
event = pevent_find_event(pevent, evsel->attr.config);
- if (event == NULL)
+ if (event == NULL) {
+ pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
return -1;
+ }
if (!evsel->name) {
snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 7d1b7d3..32c6a93 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2446,8 +2446,10 @@ int parse_filter_percentage(const struct option *opt __maybe_unused,
symbol_conf.filter_relative = true;
else if (!strcmp(arg, "absolute"))
symbol_conf.filter_relative = false;
- else
+ else {
+ pr_debug("Invalud percentage: %s\n", arg);
return -1;
+ }
return 0;
}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 85d5eeb..da20cd5 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2159,7 +2159,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
addr_filters__init(&pt->filts);
- perf_config(intel_pt_perf_config, pt);
+ err = perf_config(intel_pt_perf_config, pt);
+ if (err)
+ goto err_free;
err = auxtrace_queues__init(&pt->queues);
if (err)
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index b23ff44..8243564 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -48,8 +48,10 @@ int perf_llvm_config(const char *var, const char *value)
llvm_param.kbuild_opts = strdup(value);
else if (!strcmp(var, "dump-obj"))
llvm_param.dump_obj = !!perf_config_bool(var, value);
- else
+ else {
+ pr_debug("Invalid LLVM config option: %s\n", value);
return -1;
+ }
llvm_param.user_set_param = true;
return 0;
}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9b33bef..747a034 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -87,6 +87,25 @@ struct machine *machine__new_host(void)
return NULL;
}
+struct machine *machine__new_kallsyms(void)
+{
+ struct machine *machine = machine__new_host();
+ /*
+ * FIXME:
+ * 1) MAP__FUNCTION will go away when we stop loading separate maps for
+ * functions and data objects.
+ * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+ * ask for not using the kcore parsing code, once this one is fixed
+ * to create a map per module.
+ */
+ if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+ machine__delete(machine);
+ machine = NULL;
+ }
+
+ return machine;
+}
+
static void dsos__purge(struct dsos *dsos)
{
struct dso *pos, *n;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 354de6e..a283050 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -129,6 +129,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
void machines__set_comm_exec(struct machines *machines, bool comm_exec);
struct machine *machine__new_host(void);
+struct machine *machine__new_kallsyms(void);
int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
void machine__exit(struct machine *machine);
void machine__delete_threads(struct machine *machine);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index dc6ccaa..78b1610 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -94,6 +94,43 @@ static int pmu_format(const char *name, struct list_head *format)
return 0;
}
+static int convert_scale(const char *scale, char **end, double *sval)
+{
+ char *lc;
+ int ret = 0;
+
+ /*
+ * save current locale
+ */
+ lc = setlocale(LC_NUMERIC, NULL);
+
+ /*
+ * The lc string may be allocated in static storage,
+ * so get a dynamic copy to make it survive setlocale
+ * call below.
+ */
+ lc = strdup(lc);
+ if (!lc) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * force to C locale to ensure kernel
+ * scale string is converted correctly.
+ * kernel uses default C locale.
+ */
+ setlocale(LC_NUMERIC, "C");
+
+ *sval = strtod(scale, end);
+
+out:
+ /* restore locale */
+ setlocale(LC_NUMERIC, lc);
+ free(lc);
+ return ret;
+}
+
static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
{
struct stat st;
@@ -101,7 +138,6 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
char scale[128];
int fd, ret = -1;
char path[PATH_MAX];
- char *lc;
snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
@@ -121,37 +157,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
else
scale[sret] = '\0';
- /*
- * save current locale
- */
- lc = setlocale(LC_NUMERIC, NULL);
-
- /*
- * The lc string may be allocated in static storage,
- * so get a dynamic copy to make it survive setlocale
- * call below.
- */
- lc = strdup(lc);
- if (!lc) {
- ret = -ENOMEM;
- goto error;
- }
-
- /*
- * force to C locale to ensure kernel
- * scale string is converted correctly.
- * kernel uses default C locale.
- */
- setlocale(LC_NUMERIC, "C");
-
- alias->scale = strtod(scale, NULL);
-
- /* restore locale */
- setlocale(LC_NUMERIC, lc);
-
- free(lc);
-
- ret = 0;
+ ret = convert_scale(scale, NULL, &alias->scale);
error:
close(fd);
return ret;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6a6f44d..2c1bca2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -3023,20 +3023,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
tev->nargs = pev->nargs;
tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
- if (!tev->args) {
- err = -ENOMEM;
+ if (!tev->args)
goto errout;
- }
+
for (i = 0; i < tev->nargs; i++)
copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]);
return 1;
errout:
- if (*tevs) {
- clear_probe_trace_events(*tevs, 1);
- *tevs = NULL;
- }
+ clear_probe_trace_events(*tevs, 1);
+ *tevs = NULL;
return err;
}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e55a132..014ecd6 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -350,8 +350,10 @@ static void perl_process_tracepoint(struct perf_sample *sample,
if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
return;
- if (!event)
- die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+ if (!event) {
+ pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+ return;
+ }
pid = raw_field_value(event, "common_pid", data);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f268201..349c681 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1191,7 +1191,7 @@ static int
u64 sample_type = evsel->attr.sample_type;
u64 read_format = evsel->attr.read_format;
- /* Standard sample delievery. */
+ /* Standard sample delivery. */
if (!(sample_type & PERF_SAMPLE_READ))
return tool->sample(tool, event, sample, evsel, machine);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d995743..e7d60d0 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -42,7 +42,7 @@
#include "evsel.h"
#include "debug.h"
-#define VERSION "0.5"
+#define VERSION "0.6"
static int output_fd;
@@ -170,6 +170,12 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
return false;
}
+#define for_each_event(dir, dent, tps) \
+ while ((dent = readdir(dir))) \
+ if (dent->d_type == DT_DIR && \
+ (strcmp(dent->d_name, ".")) && \
+ (strcmp(dent->d_name, ".."))) \
+
static int copy_event_system(const char *sys, struct tracepoint_path *tps)
{
struct dirent *dent;
@@ -186,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
return -errno;
}
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- !name_in_tp_list(dent->d_name, tps))
+ for_each_event(dir, dent, tps) {
+ if (!name_in_tp_list(dent->d_name, tps))
continue;
+
if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
@@ -210,12 +214,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
}
rewinddir(dir);
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- !name_in_tp_list(dent->d_name, tps))
+ for_each_event(dir, dent, tps) {
+ if (!name_in_tp_list(dent->d_name, tps))
continue;
+
if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
@@ -290,13 +292,11 @@ static int record_event_files(struct tracepoint_path *tps)
goto out;
}
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- strcmp(dent->d_name, "ftrace") == 0 ||
+ for_each_event(dir, dent, tps) {
+ if (strcmp(dent->d_name, "ftrace") == 0 ||
!system_in_tp_list(dent->d_name, tps))
continue;
+
count++;
}
@@ -307,13 +307,11 @@ static int record_event_files(struct tracepoint_path *tps)
}
rewinddir(dir);
- while ((dent = readdir(dir))) {
- if (dent->d_type != DT_DIR ||
- strcmp(dent->d_name, ".") == 0 ||
- strcmp(dent->d_name, "..") == 0 ||
- strcmp(dent->d_name, "ftrace") == 0 ||
+ for_each_event(dir, dent, tps) {
+ if (strcmp(dent->d_name, "ftrace") == 0 ||
!system_in_tp_list(dent->d_name, tps))
continue;
+
if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
err = -ENOMEM;
goto out;
@@ -379,6 +377,34 @@ static int record_ftrace_printk(void)
return err;
}
+static int record_saved_cmdline(void)
+{
+ unsigned int size;
+ char *path;
+ struct stat st;
+ int ret, err = 0;
+
+ path = get_tracing_file("saved_cmdlines");
+ if (!path) {
+ pr_debug("can't get tracing/saved_cmdline");
+ return -ENOMEM;
+ }
+
+ ret = stat(path, &st);
+ if (ret < 0) {
+ /* not found */
+ size = 0;
+ if (write(output_fd, &size, 8) != 8)
+ err = -EIO;
+ goto out;
+ }
+ err = record_file(path, 8);
+
+out:
+ put_tracing_file(path);
+ return err;
+}
+
static void
put_tracepoints_path(struct tracepoint_path *tps)
{
@@ -539,6 +565,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
if (err)
goto out;
err = record_ftrace_printk();
+ if (err)
+ goto out;
+ err = record_saved_cmdline();
out:
/*
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 33b52ea..de0078e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -160,6 +160,23 @@ void parse_ftrace_printk(struct pevent *pevent,
}
}
+void parse_saved_cmdline(struct pevent *pevent,
+ char *file, unsigned int size __maybe_unused)
+{
+ char *comm;
+ char *line;
+ char *next = NULL;
+ int pid;
+
+ line = strtok_r(file, "\n", &next);
+ while (line) {
+ sscanf(line, "%d %ms", &pid, &comm);
+ pevent_register_comm(pevent, comm, pid);
+ free(comm);
+ line = strtok_r(NULL, "\n", &next);
+ }
+}
+
int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
{
return pevent_parse_event(pevent, buf, size, "ftrace");
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b67a0cc..2742015 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -260,39 +260,53 @@ static int read_header_files(struct pevent *pevent)
static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
{
+ int ret;
char *buf;
buf = malloc(size);
- if (buf == NULL)
- return -1;
-
- if (do_read(buf, size) < 0) {
- free(buf);
+ if (buf == NULL) {
+ pr_debug("memory allocation failure\n");
return -1;
}
- parse_ftrace_file(pevent, buf, size);
+ ret = do_read(buf, size);
+ if (ret < 0) {
+ pr_debug("error reading ftrace file.\n");
+ goto out;
+ }
+
+ ret = parse_ftrace_file(pevent, buf, size);
+ if (ret < 0)
+ pr_debug("error parsing ftrace file.\n");
+out:
free(buf);
- return 0;
+ return ret;
}
static int read_event_file(struct pevent *pevent, char *sys,
unsigned long long size)
{
+ int ret;
char *buf;
buf = malloc(size);
- if (buf == NULL)
- return -1;
-
- if (do_read(buf, size) < 0) {
- free(buf);
+ if (buf == NULL) {
+ pr_debug("memory allocation failure\n");
return -1;
}
- parse_event_file(pevent, buf, size, sys);
+ ret = do_read(buf, size);
+ if (ret < 0) {
+ free(buf);
+ goto out;
+ }
+
+ ret = parse_event_file(pevent, buf, size, sys);
+ if (ret < 0)
+ pr_debug("error parsing event file.\n");
+out:
free(buf);
- return 0;
+ return ret;
}
static int read_ftrace_files(struct pevent *pevent)
@@ -341,6 +355,36 @@ static int read_event_files(struct pevent *pevent)
return 0;
}
+static int read_saved_cmdline(struct pevent *pevent)
+{
+ unsigned long long size;
+ char *buf;
+ int ret;
+
+ /* it can have 0 size */
+ size = read8(pevent);
+ if (!size)
+ return 0;
+
+ buf = malloc(size + 1);
+ if (buf == NULL) {
+ pr_debug("memory allocation failure\n");
+ return -1;
+ }
+
+ ret = do_read(buf, size);
+ if (ret < 0) {
+ pr_debug("error reading saved cmdlines\n");
+ goto out;
+ }
+
+ parse_saved_cmdline(pevent, buf, size);
+ ret = 0;
+out:
+ free(buf);
+ return ret;
+}
+
ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
{
char buf[BUFSIZ];
@@ -379,10 +423,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
return -1;
if (show_version)
printf("version = %s\n", version);
- free(version);
- if (do_read(buf, 1) < 0)
+ if (do_read(buf, 1) < 0) {
+ free(version);
return -1;
+ }
file_bigendian = buf[0];
host_bigendian = bigendian();
@@ -423,6 +468,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
err = read_ftrace_printk(pevent);
if (err)
goto out;
+ if (atof(version) >= 0.6) {
+ err = read_saved_cmdline(pevent);
+ if (err)
+ goto out;
+ }
size = trace_data_size;
repipe = false;
@@ -438,5 +488,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
out:
if (pevent)
trace_event__cleanup(tevent);
+ free(version);
return size;
}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b0af9c8..1fbc044 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
+void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size);
ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6fec84d..bfb9b79 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -35,6 +35,7 @@
#include "util.h"
#include "debug.h"
#include "asm/bug.h"
+#include "dso.h"
extern int
UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -297,15 +298,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
int fd;
u64 ofs = dso->data.debug_frame_offset;
+ /* debug_frame can reside in:
+ * - dso
+ * - debug pointed by symsrc_filename
+ * - gnu_debuglink, which doesn't necessary
+ * has to be pointed by symsrc_filename
+ */
if (ofs == 0) {
fd = dso__data_get_fd(dso, machine);
- if (fd < 0)
- return -EINVAL;
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd, ".debug_frame");
+ dso__data_put_fd(dso);
+ }
- /* Check the .debug_frame section for unwinding info */
- ofs = elf_section_offset(fd, ".debug_frame");
+ if (ofs <= 0) {
+ fd = open(dso->symsrc_filename, O_RDONLY);
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd, ".debug_frame");
+ close(fd);
+ }
+ }
+
+ if (ofs <= 0) {
+ char *debuglink = malloc(PATH_MAX);
+ int ret = 0;
+
+ ret = dso__read_binary_type_filename(
+ dso, DSO_BINARY_TYPE__DEBUGLINK,
+ machine->root_dir, debuglink, PATH_MAX);
+ if (!ret) {
+ fd = open(debuglink, O_RDONLY);
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd,
+ ".debug_frame");
+ close(fd);
+ }
+ }
+ if (ofs > 0) {
+ if (dso->symsrc_filename != NULL) {
+ pr_warning(
+ "%s: overwrite symsrc(%s,%s)\n",
+ __func__,
+ dso->symsrc_filename,
+ debuglink);
+ free(dso->symsrc_filename);
+ }
+ dso->symsrc_filename = debuglink;
+ } else {
+ free(debuglink);
+ }
+ }
+
dso->data.debug_frame_offset = ofs;
- dso__data_put_fd(dso);
}
*offset = ofs;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9ddd988..d8b45ce 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -85,7 +85,7 @@ int mkdir_p(char *path, mode_t mode)
return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
}
-int rm_rf(char *path)
+int rm_rf(const char *path)
{
DIR *dir;
int ret = 0;
@@ -789,3 +789,16 @@ int is_printable_array(char *p, unsigned int len)
}
return 1;
}
+
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+ char unit[4] = "BKMG";
+ int i = 0;
+
+ while (((n / 1024) > 1) && (i < 3)) {
+ n /= 1024;
+ i++;
+ }
+
+ return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1d639e3..c74708d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -209,7 +209,7 @@ static inline int sane_case(int x, int high)
}
int mkdir_p(char *path, mode_t mode);
-int rm_rf(char *path);
+int rm_rf(const 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);
@@ -363,4 +363,5 @@ int is_printable_array(char *p, unsigned int len);
int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
#endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 8abbef1..19edc1a 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -46,6 +46,16 @@
NO_SUBDIR = :
endif
+ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+ silent=1
+endif
+else # make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+ silent=1
+endif
+endif
+
#
# Define a callable command for descending to a new directory
#
@@ -58,7 +68,7 @@
QUIET_SUBDIR0 = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
QUIET_SUBDIR1 =
-ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifneq ($(silent),1)
ifneq ($(V),1)
QUIET_CC = @echo ' CC '$@;
QUIET_CC_FPIC = @echo ' CC FPIC '$@;