summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-11-03 17:38:09 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2015-11-03 17:38:09 -0800
commitb02ac6b18cd4e2c76bf0a102c20c429b973f5f76 (patch)
tree87b3648f448627d61cb9ba32511584d6318b7bb6 /kernel
parent105ff3cbf225036b75a6a46c96d1ddce8e7bdc66 (diff)
parentbebd23a2ed31d47e7dd746d3b125068aa2c42d85 (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "Kernel side changes: - Improve accuracy of perf/sched clock on x86. (Adrian Hunter) - Intel DS and BTS updates. (Alexander Shishkin) - Intel cstate PMU support. (Kan Liang) - Add group read support to perf_event_read(). (Peter Zijlstra) - Branch call hardware sampling support, implemented on x86 and PowerPC. (Stephane Eranian) - Event groups transactional interface enhancements. (Sukadev Bhattiprolu) - Enable proper x86/intel/uncore PMU support on multi-segment PCI systems. (Taku Izumi) - ... misc fixes and cleanups. The perf tooling team was very busy again with 200+ commits, the full diff doesn't fit into lkml size limits. Here's an (incomplete) list of the tooling highlights: New features: - Change the default event used in all tools (record/top): use the most precise "cycles" hw counter available, i.e. when the user doesn't specify any event, it will try using cycles:ppp, cycles:pp, etc and fall back transparently until it finds a working counter. (Arnaldo Carvalho de Melo) - Integration of perf with eBPF that, given an eBPF .c source file (or .o file built for the 'bpf' target with clang), will get it automatically built, validated and loaded into the kernel via the sys_bpf syscall, which can then be used and seen using 'perf trace' and other tools. (Wang Nan) Various user interface improvements: - Automatic pager invocation on long help output. (Namhyung Kim) - Search for more options when passing args to -h, e.g.: (Arnaldo Carvalho de Melo) $ perf report -h interface Usage: perf report [<options>] --gtk Use the GTK2 interface --stdio Use the stdio interface --tui Use the TUI interface - Show ordered command line options when -h is used or when an unknown option is specified. (Arnaldo Carvalho de Melo) - If options are passed after -h, show just its descriptions, not all options. (Arnaldo Carvalho de Melo) - Implement column based horizontal scrolling in the hists browser (top, report), making it possible to use the TUI for things like 'perf mem report' where there are many more columns than can fit in a terminal. (Arnaldo Carvalho de Melo) - Enhance the error reporting of tracepoint event parsing, e.g.: $ oldperf record -e sched:sched_switc usleep 1 event syntax error: 'sched:sched_switc' \___ unknown tracepoint Run 'perf list' for a list of valid events Now we get the much nicer: $ perf record -e sched:sched_switc ls event syntax error: 'sched:sched_switc' \___ can't access trace events Error: No permissions to read /sys/kernel/debug/tracing/events/sched/sched_switc Hint: Try 'sudo mount -o remount,mode=755 /sys/kernel/debug' And after we have those mount point permissions fixed: $ perf record -e sched:sched_switc ls event syntax error: 'sched:sched_switc' \___ unknown tracepoint Error: File /sys/kernel/debug/tracing/events/sched/sched_switc not found. Hint: Perhaps this kernel misses some CONFIG_ setting to enable this feature?. I.e. basically now the event parsing routing uses the strerror_open() routines introduced by and used in 'perf trace' work. (Jiri Olsa) - Fail properly when pattern matching fails to find a tracepoint, i.e. '-e non:existent' was being correctly handled, with a proper error message about that not being a valid event, but '-e non:existent*' wasn't, fix it. (Jiri Olsa) - Do event name substring search as last resort in 'perf list'. (Arnaldo Carvalho de Melo) E.g.: # perf list clock List of pre-defined events (to be used in -e): cpu-clock [Software event] task-clock [Software event] uncore_cbox_0/clockticks/ [Kernel PMU event] uncore_cbox_1/clockticks/ [Kernel PMU event] kvm:kvm_pvclock_update [Tracepoint event] kvm:kvm_update_master_clock [Tracepoint event] power:clock_disable [Tracepoint event] power:clock_enable [Tracepoint event] power:clock_set_rate [Tracepoint event] syscalls:sys_enter_clock_adjtime [Tracepoint event] syscalls:sys_enter_clock_getres [Tracepoint event] syscalls:sys_enter_clock_gettime [Tracepoint event] syscalls:sys_enter_clock_nanosleep [Tracepoint event] syscalls:sys_enter_clock_settime [Tracepoint event] syscalls:sys_exit_clock_adjtime [Tracepoint event] syscalls:sys_exit_clock_getres [Tracepoint event] syscalls:sys_exit_clock_gettime [Tracepoint event] syscalls:sys_exit_clock_nanosleep [Tracepoint event] syscalls:sys_exit_clock_settime [Tracepoint event] Intel PT hardware tracing enhancements: - Accept a zero --itrace period, meaning "as often as possible". In the case of Intel PT that is the same as a period of 1 and a unit of 'instructions' (i.e. --itrace=i1i). (Adrian Hunter) - Harmonize itrace's synthesized callchains with the existing --max-stack tool option. (Adrian Hunter) - Allow time to be displayed in nanoseconds in 'perf script'. (Adrian Hunter) - Fix potential infinite loop when handling Intel PT timestamps. (Adrian Hunter) - Slighly improve Intel PT debug logging. (Adrian Hunter) - Warn when AUX data has been lost, just like when processing PERF_RECORD_LOST. (Adrian Hunter) - Further document export-to-postgresql.py script. (Adrian Hunter) - Add option to synthesize branch stack from auxtrace data. (Adrian Hunter) Misc notable changes: - Switch the default callchain output mode to 'graph,0.5,caller', to make it look like the default for other tools, reducing the learning curve for people used to 'caller' based viewing. (Arnaldo Carvalho de Melo) - various call chain usability enhancements. (Namhyung Kim) - Introduce the 'P' event modifier, meaning 'max precision level, please', i.e.: $ perf record -e cycles:P usleep 1 Is now similar to: $ perf record usleep 1 Useful, for instance, when specifying multiple events. (Jiri Olsa) - Add 'socket' sort entry, to sort by the processor socket in 'perf top' and 'perf report'. (Kan Liang) - Introduce --socket-filter to 'perf report', for filtering by processor socket. (Kan Liang) - Add new "Zoom into Processor Socket" operation in the perf hists browser, used in 'perf top' and 'perf report'. (Kan Liang) - Allow probing on kmodules without DWARF. (Masami Hiramatsu) - Fix 'perf probe -l' for probes added to kernel module functions. (Masami Hiramatsu) - Preparatory work for the 'perf stat record' feature that will allow generating perf.data files with counting data in addition to the sampling mode we have now (Jiri Olsa) - Update libtraceevent KVM plugin. (Paolo Bonzini) - ... plus lots of other enhancements that I failed to list properly, by: Adrian Hunter, Alexander Shishkin, Andi Kleen, Andrzej Hajda, Arnaldo Carvalho de Melo, Dima Kogan, Don Zickus, Geliang Tang, He Kuang, Huaitong Han, Ingo Molnar, Jan Stancek, Jiri Olsa, Kan Liang, Kirill Tkhai, Masami Hiramatsu, Matt Fleming, Namhyung Kim, Paolo Bonzini, Peter Zijlstra, Rabin Vincent, Scott Wood, Stephane Eranian, Sukadev Bhattiprolu, Taku Izumi, Vaishali Thakkar, Wang Nan, Yang Shi and Yunlong Song" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (260 commits) perf unwind: Pass symbol source to libunwind tools build: Fix libiberty feature detection perf tools: Compile scriptlets to BPF objects when passing '.c' to --event perf record: Add clang options for compiling BPF scripts perf bpf: Attach eBPF filter to perf event perf tools: Make sure fixdep is built before libbpf perf script: Enable printing of branch stack perf trace: Add cmd string table to decode sys_bpf first arg perf bpf: Collect perf_evsel in BPF object files perf tools: Load eBPF object into kernel perf tools: Create probe points for BPF programs perf tools: Enable passing bpf object file to --event perf ebpf: Add the libbpf glue perf tools: Make perf depend on libbpf perf symbols: Fix endless loop in dso__split_kallsyms_for_kcore perf tools: Enable pre-event inherit setting by config terms perf symbols: we can now read separate debug-info files based on a build ID perf symbols: Fix type error when reading a build-id perf tools: Search for more options when passing args to -h perf stat: Cache aggregated map entries in extra cpumap ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/events/core.c224
1 files changed, 165 insertions, 59 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b11756f9b6dc..ea02109aee77 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -196,7 +196,7 @@ static int perf_sample_period_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS;
static int perf_sample_allowed_ns __read_mostly =
DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100;
-void update_perf_cpu_limits(void)
+static void update_perf_cpu_limits(void)
{
u64 tmp = perf_sample_period_ns;
@@ -472,7 +472,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
* mode SWOUT : schedule out everything
* mode SWIN : schedule in based on cgroup for next
*/
-void perf_cgroup_switch(struct task_struct *task, int mode)
+static void perf_cgroup_switch(struct task_struct *task, int mode)
{
struct perf_cpu_context *cpuctx;
struct pmu *pmu;
@@ -1939,7 +1939,7 @@ group_sched_in(struct perf_event *group_event,
if (group_event->state == PERF_EVENT_STATE_OFF)
return 0;
- pmu->start_txn(pmu);
+ pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
if (event_sched_in(group_event, cpuctx, ctx)) {
pmu->cancel_txn(pmu);
@@ -3209,14 +3209,22 @@ void perf_event_exec(void)
rcu_read_unlock();
}
+struct perf_read_data {
+ struct perf_event *event;
+ bool group;
+ int ret;
+};
+
/*
* Cross CPU call to read the hardware event
*/
static void __perf_event_read(void *info)
{
- struct perf_event *event = info;
+ struct perf_read_data *data = info;
+ struct perf_event *sub, *event = data->event;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct pmu *pmu = event->pmu;
/*
* If this is a task context, we need to check whether it is
@@ -3233,9 +3241,35 @@ static void __perf_event_read(void *info)
update_context_time(ctx);
update_cgrp_time_from_event(event);
}
+
update_event_times(event);
- if (event->state == PERF_EVENT_STATE_ACTIVE)
- event->pmu->read(event);
+ if (event->state != PERF_EVENT_STATE_ACTIVE)
+ goto unlock;
+
+ if (!data->group) {
+ pmu->read(event);
+ data->ret = 0;
+ goto unlock;
+ }
+
+ pmu->start_txn(pmu, PERF_PMU_TXN_READ);
+
+ pmu->read(event);
+
+ list_for_each_entry(sub, &event->sibling_list, group_entry) {
+ update_event_times(sub);
+ if (sub->state == PERF_EVENT_STATE_ACTIVE) {
+ /*
+ * Use sibling's PMU rather than @event's since
+ * sibling could be on different (eg: software) PMU.
+ */
+ sub->pmu->read(sub);
+ }
+ }
+
+ data->ret = pmu->commit_txn(pmu);
+
+unlock:
raw_spin_unlock(&ctx->lock);
}
@@ -3300,15 +3334,23 @@ u64 perf_event_read_local(struct perf_event *event)
return val;
}
-static u64 perf_event_read(struct perf_event *event)
+static int perf_event_read(struct perf_event *event, bool group)
{
+ int ret = 0;
+
/*
* If event is enabled and currently active on a CPU, update the
* value in the event structure:
*/
if (event->state == PERF_EVENT_STATE_ACTIVE) {
+ struct perf_read_data data = {
+ .event = event,
+ .group = group,
+ .ret = 0,
+ };
smp_call_function_single(event->oncpu,
- __perf_event_read, event, 1);
+ __perf_event_read, &data, 1);
+ ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
unsigned long flags;
@@ -3323,11 +3365,14 @@ static u64 perf_event_read(struct perf_event *event)
update_context_time(ctx);
update_cgrp_time_from_event(event);
}
- update_event_times(event);
+ if (group)
+ update_group_times(event);
+ else
+ update_event_times(event);
raw_spin_unlock_irqrestore(&ctx->lock, flags);
}
- return perf_event_count(event);
+ return ret;
}
/*
@@ -3769,7 +3814,7 @@ static void put_event(struct perf_event *event)
* see the comment there.
*
* 2) there is a lock-inversion with mmap_sem through
- * perf_event_read_group(), which takes faults while
+ * perf_read_group(), which takes faults while
* holding ctx->mutex, however this is called after
* the last filedesc died, so there is no possibility
* to trigger the AB-BA case.
@@ -3843,14 +3888,18 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
*running = 0;
mutex_lock(&event->child_mutex);
- total += perf_event_read(event);
+
+ (void)perf_event_read(event, false);
+ total += perf_event_count(event);
+
*enabled += event->total_time_enabled +
atomic64_read(&event->child_total_time_enabled);
*running += event->total_time_running +
atomic64_read(&event->child_total_time_running);
list_for_each_entry(child, &event->child_list, child_list) {
- total += perf_event_read(child);
+ (void)perf_event_read(child, false);
+ total += perf_event_count(child);
*enabled += child->total_time_enabled;
*running += child->total_time_running;
}
@@ -3860,55 +3909,95 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
}
EXPORT_SYMBOL_GPL(perf_event_read_value);
-static int perf_event_read_group(struct perf_event *event,
- u64 read_format, char __user *buf)
+static int __perf_read_group_add(struct perf_event *leader,
+ u64 read_format, u64 *values)
{
- struct perf_event *leader = event->group_leader, *sub;
- struct perf_event_context *ctx = leader->ctx;
- int n = 0, size = 0, ret;
- u64 count, enabled, running;
- u64 values[5];
+ struct perf_event *sub;
+ int n = 1; /* skip @nr */
+ int ret;
- lockdep_assert_held(&ctx->mutex);
+ ret = perf_event_read(leader, true);
+ if (ret)
+ return ret;
- count = perf_event_read_value(leader, &enabled, &running);
+ /*
+ * Since we co-schedule groups, {enabled,running} times of siblings
+ * will be identical to those of the leader, so we only publish one
+ * set.
+ */
+ if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+ values[n++] += leader->total_time_enabled +
+ atomic64_read(&leader->child_total_time_enabled);
+ }
- values[n++] = 1 + leader->nr_siblings;
- if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
- values[n++] = enabled;
- if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
- values[n++] = running;
- values[n++] = count;
+ if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+ values[n++] += leader->total_time_running +
+ atomic64_read(&leader->child_total_time_running);
+ }
+
+ /*
+ * Write {count,id} tuples for every sibling.
+ */
+ values[n++] += perf_event_count(leader);
if (read_format & PERF_FORMAT_ID)
values[n++] = primary_event_id(leader);
- size = n * sizeof(u64);
+ list_for_each_entry(sub, &leader->sibling_list, group_entry) {
+ values[n++] += perf_event_count(sub);
+ if (read_format & PERF_FORMAT_ID)
+ values[n++] = primary_event_id(sub);
+ }
- if (copy_to_user(buf, values, size))
- return -EFAULT;
+ return 0;
+}
+
+static int perf_read_group(struct perf_event *event,
+ u64 read_format, char __user *buf)
+{
+ struct perf_event *leader = event->group_leader, *child;
+ struct perf_event_context *ctx = leader->ctx;
+ int ret;
+ u64 *values;
- ret = size;
+ lockdep_assert_held(&ctx->mutex);
- list_for_each_entry(sub, &leader->sibling_list, group_entry) {
- n = 0;
+ values = kzalloc(event->read_size, GFP_KERNEL);
+ if (!values)
+ return -ENOMEM;
- values[n++] = perf_event_read_value(sub, &enabled, &running);
- if (read_format & PERF_FORMAT_ID)
- values[n++] = primary_event_id(sub);
+ values[0] = 1 + leader->nr_siblings;
- size = n * sizeof(u64);
+ /*
+ * By locking the child_mutex of the leader we effectively
+ * lock the child list of all siblings.. XXX explain how.
+ */
+ mutex_lock(&leader->child_mutex);
- if (copy_to_user(buf + ret, values, size)) {
- return -EFAULT;
- }
+ ret = __perf_read_group_add(leader, read_format, values);
+ if (ret)
+ goto unlock;
- ret += size;
+ list_for_each_entry(child, &leader->child_list, child_list) {
+ ret = __perf_read_group_add(child, read_format, values);
+ if (ret)
+ goto unlock;
}
+ mutex_unlock(&leader->child_mutex);
+
+ ret = event->read_size;
+ if (copy_to_user(buf, values, event->read_size))
+ ret = -EFAULT;
+ goto out;
+
+unlock:
+ mutex_unlock(&leader->child_mutex);
+out:
+ kfree(values);
return ret;
}
-static int perf_event_read_one(struct perf_event *event,
+static int perf_read_one(struct perf_event *event,
u64 read_format, char __user *buf)
{
u64 enabled, running;
@@ -3946,7 +4035,7 @@ static bool is_event_hup(struct perf_event *event)
* Read the performance event - simple non blocking version for now
*/
static ssize_t
-perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
+__perf_read(struct perf_event *event, char __user *buf, size_t count)
{
u64 read_format = event->attr.read_format;
int ret;
@@ -3964,9 +4053,9 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
WARN_ON_ONCE(event->ctx->parent_ctx);
if (read_format & PERF_FORMAT_GROUP)
- ret = perf_event_read_group(event, read_format, buf);
+ ret = perf_read_group(event, read_format, buf);
else
- ret = perf_event_read_one(event, read_format, buf);
+ ret = perf_read_one(event, read_format, buf);
return ret;
}
@@ -3979,7 +4068,7 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
int ret;
ctx = perf_event_ctx_lock(event);
- ret = perf_read_hw(event, buf, count);
+ ret = __perf_read(event, buf, count);
perf_event_ctx_unlock(event, ctx);
return ret;
@@ -4010,7 +4099,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
static void _perf_event_reset(struct perf_event *event)
{
- (void)perf_event_read(event);
+ (void)perf_event_read(event, false);
local64_set(&event->count, 0);
perf_event_update_userpage(event);
}
@@ -7292,24 +7381,49 @@ static void perf_pmu_nop_void(struct pmu *pmu)
{
}
+static void perf_pmu_nop_txn(struct pmu *pmu, unsigned int flags)
+{
+}
+
static int perf_pmu_nop_int(struct pmu *pmu)
{
return 0;
}
-static void perf_pmu_start_txn(struct pmu *pmu)
+static DEFINE_PER_CPU(unsigned int, nop_txn_flags);
+
+static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
{
+ __this_cpu_write(nop_txn_flags, flags);
+
+ if (flags & ~PERF_PMU_TXN_ADD)
+ return;
+
perf_pmu_disable(pmu);
}
static int perf_pmu_commit_txn(struct pmu *pmu)
{
+ unsigned int flags = __this_cpu_read(nop_txn_flags);
+
+ __this_cpu_write(nop_txn_flags, 0);
+
+ if (flags & ~PERF_PMU_TXN_ADD)
+ return 0;
+
perf_pmu_enable(pmu);
return 0;
}
static void perf_pmu_cancel_txn(struct pmu *pmu)
{
+ unsigned int flags = __this_cpu_read(nop_txn_flags);
+
+ __this_cpu_write(nop_txn_flags, 0);
+
+ if (flags & ~PERF_PMU_TXN_ADD)
+ return;
+
perf_pmu_enable(pmu);
}
@@ -7548,7 +7662,7 @@ got_cpu_context:
pmu->commit_txn = perf_pmu_commit_txn;
pmu->cancel_txn = perf_pmu_cancel_txn;
} else {
- pmu->start_txn = perf_pmu_nop_void;
+ pmu->start_txn = perf_pmu_nop_txn;
pmu->commit_txn = perf_pmu_nop_int;
pmu->cancel_txn = perf_pmu_nop_void;
}
@@ -7636,7 +7750,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
return ret;
}
-struct pmu *perf_init_event(struct perf_event *event)
+static struct pmu *perf_init_event(struct perf_event *event)
{
struct pmu *pmu = NULL;
int idx;
@@ -9345,14 +9459,6 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css,
struct cgroup_subsys_state *old_css,
struct task_struct *task)
{
- /*
- * cgroup_exit() is called in the copy_process() failure path.
- * Ignore this case since the task hasn't ran yet, this avoids
- * trying to poke a half freed task state from generic code.
- */
- if (!(task->flags & PF_EXITING))
- return;
-
task_function_call(task, __perf_cgroup_move, task);
}