summaryrefslogtreecommitdiff
path: root/kernel/events
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/events')
-rw-r--r--kernel/events/core.c267
-rw-r--r--kernel/events/internal.h19
-rw-r--r--kernel/events/ring_buffer.c39
3 files changed, 203 insertions, 122 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0ceb38677..e6feb5114 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -36,7 +36,7 @@
#include <linux/kernel_stat.h>
#include <linux/cgroup.h>
#include <linux/perf_event.h>
-#include <linux/ftrace_event.h>
+#include <linux/trace_events.h>
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
#include <linux/module.h>
@@ -51,9 +51,11 @@
static struct workqueue_struct *perf_wq;
+typedef int (*remote_function_f)(void *);
+
struct remote_function_call {
struct task_struct *p;
- int (*func)(void *info);
+ remote_function_f func;
void *info;
int ret;
};
@@ -86,7 +88,7 @@ static void remote_function(void *data)
* -EAGAIN - when the process moved away
*/
static int
-task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
+task_function_call(struct task_struct *p, remote_function_f func, void *info)
{
struct remote_function_call data = {
.p = p,
@@ -110,7 +112,7 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info)
*
* returns: @func return value or -ENXIO when the cpu is offline
*/
-static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
+static int cpu_function_call(int cpu, remote_function_f func, void *info)
{
struct remote_function_call data = {
.p = NULL,
@@ -747,62 +749,31 @@ perf_cgroup_mark_enabled(struct perf_event *event,
/*
* function must be called with interrupts disbled
*/
-static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr)
+static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
{
struct perf_cpu_context *cpuctx;
- enum hrtimer_restart ret = HRTIMER_NORESTART;
int rotations = 0;
WARN_ON(!irqs_disabled());
cpuctx = container_of(hr, struct perf_cpu_context, hrtimer);
-
rotations = perf_rotate_context(cpuctx);
- /*
- * arm timer if needed
- */
- if (rotations) {
+ raw_spin_lock(&cpuctx->hrtimer_lock);
+ if (rotations)
hrtimer_forward_now(hr, cpuctx->hrtimer_interval);
- ret = HRTIMER_RESTART;
- }
-
- return ret;
-}
-
-/* CPU is going down */
-void perf_cpu_hrtimer_cancel(int cpu)
-{
- struct perf_cpu_context *cpuctx;
- struct pmu *pmu;
- unsigned long flags;
-
- if (WARN_ON(cpu != smp_processor_id()))
- return;
-
- local_irq_save(flags);
-
- rcu_read_lock();
-
- list_for_each_entry_rcu(pmu, &pmus, entry) {
- cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
- if (pmu->task_ctx_nr == perf_sw_context)
- continue;
-
- hrtimer_cancel(&cpuctx->hrtimer);
- }
-
- rcu_read_unlock();
+ else
+ cpuctx->hrtimer_active = 0;
+ raw_spin_unlock(&cpuctx->hrtimer_lock);
- local_irq_restore(flags);
+ return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART;
}
-static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
+static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
{
- struct hrtimer *hr = &cpuctx->hrtimer;
+ struct hrtimer *timer = &cpuctx->hrtimer;
struct pmu *pmu = cpuctx->ctx.pmu;
- int timer;
+ u64 interval;
/* no multiplexing needed for SW PMU */
if (pmu->task_ctx_nr == perf_sw_context)
@@ -812,31 +783,36 @@ static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu)
* check default is sane, if not set then force to
* default interval (1/tick)
*/
- timer = pmu->hrtimer_interval_ms;
- if (timer < 1)
- timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
+ interval = pmu->hrtimer_interval_ms;
+ if (interval < 1)
+ interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER;
- cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
+ cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval);
- hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
- hr->function = perf_cpu_hrtimer_handler;
+ raw_spin_lock_init(&cpuctx->hrtimer_lock);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+ timer->function = perf_mux_hrtimer_handler;
}
-static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx)
+static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
{
- struct hrtimer *hr = &cpuctx->hrtimer;
+ struct hrtimer *timer = &cpuctx->hrtimer;
struct pmu *pmu = cpuctx->ctx.pmu;
+ unsigned long flags;
/* not for SW PMU */
if (pmu->task_ctx_nr == perf_sw_context)
- return;
+ return 0;
- if (hrtimer_active(hr))
- return;
+ raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags);
+ if (!cpuctx->hrtimer_active) {
+ cpuctx->hrtimer_active = 1;
+ hrtimer_forward_now(timer, cpuctx->hrtimer_interval);
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
+ }
+ raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags);
- if (!hrtimer_callback_running(hr))
- __hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval,
- 0, HRTIMER_MODE_REL_PINNED, 0);
+ return 0;
}
void perf_pmu_disable(struct pmu *pmu)
@@ -1526,11 +1502,17 @@ static int __init perf_workqueue_init(void)
core_initcall(perf_workqueue_init);
+static inline int pmu_filter_match(struct perf_event *event)
+{
+ struct pmu *pmu = event->pmu;
+ return pmu->filter_match ? pmu->filter_match(event) : 1;
+}
+
static inline int
event_filter_match(struct perf_event *event)
{
return (event->cpu == -1 || event->cpu == smp_processor_id())
- && perf_cgroup_match(event);
+ && perf_cgroup_match(event) && pmu_filter_match(event);
}
static void
@@ -1886,8 +1868,6 @@ event_sched_in(struct perf_event *event,
perf_pmu_disable(event->pmu);
- event->tstamp_running += tstamp - event->tstamp_stopped;
-
perf_set_shadow_time(event, ctx, tstamp);
perf_log_itrace_start(event);
@@ -1899,6 +1879,8 @@ event_sched_in(struct perf_event *event,
goto out;
}
+ event->tstamp_running += tstamp - event->tstamp_stopped;
+
if (!is_software_event(event))
cpuctx->active_oncpu++;
if (!ctx->nr_active++)
@@ -1935,7 +1917,7 @@ group_sched_in(struct perf_event *group_event,
if (event_sched_in(group_event, cpuctx, ctx)) {
pmu->cancel_txn(pmu);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
return -EAGAIN;
}
@@ -1982,7 +1964,7 @@ group_error:
pmu->cancel_txn(pmu);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
return -EAGAIN;
}
@@ -2255,7 +2237,7 @@ static int __perf_event_enable(void *info)
*/
if (leader != event) {
group_sched_out(leader, cpuctx, ctx);
- perf_cpu_hrtimer_restart(cpuctx);
+ perf_mux_hrtimer_restart(cpuctx);
}
if (leader->attr.pinned) {
update_group_times(leader);
@@ -3976,28 +3958,21 @@ static void perf_event_for_each(struct perf_event *event,
perf_event_for_each_child(sibling, func);
}
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
-{
- struct perf_event_context *ctx = event->ctx;
- int ret = 0, active;
+struct period_event {
+ struct perf_event *event;
u64 value;
+};
- if (!is_sampling_event(event))
- return -EINVAL;
-
- if (copy_from_user(&value, arg, sizeof(value)))
- return -EFAULT;
-
- if (!value)
- return -EINVAL;
+static int __perf_event_period(void *info)
+{
+ struct period_event *pe = info;
+ struct perf_event *event = pe->event;
+ struct perf_event_context *ctx = event->ctx;
+ u64 value = pe->value;
+ bool active;
- raw_spin_lock_irq(&ctx->lock);
+ raw_spin_lock(&ctx->lock);
if (event->attr.freq) {
- if (value > sysctl_perf_event_sample_rate) {
- ret = -EINVAL;
- goto unlock;
- }
-
event->attr.sample_freq = value;
} else {
event->attr.sample_period = value;
@@ -4016,11 +3991,53 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
event->pmu->start(event, PERF_EF_RELOAD);
perf_pmu_enable(ctx->pmu);
}
+ raw_spin_unlock(&ctx->lock);
-unlock:
+ return 0;
+}
+
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
+{
+ struct period_event pe = { .event = event, };
+ struct perf_event_context *ctx = event->ctx;
+ struct task_struct *task;
+ u64 value;
+
+ if (!is_sampling_event(event))
+ return -EINVAL;
+
+ if (copy_from_user(&value, arg, sizeof(value)))
+ return -EFAULT;
+
+ if (!value)
+ return -EINVAL;
+
+ if (event->attr.freq && value > sysctl_perf_event_sample_rate)
+ return -EINVAL;
+
+ task = ctx->task;
+ pe.value = value;
+
+ if (!task) {
+ cpu_function_call(event->cpu, __perf_event_period, &pe);
+ return 0;
+ }
+
+retry:
+ if (!task_function_call(task, __perf_event_period, &pe))
+ return 0;
+
+ raw_spin_lock_irq(&ctx->lock);
+ if (ctx->is_active) {
+ raw_spin_unlock_irq(&ctx->lock);
+ task = ctx->task;
+ goto retry;
+ }
+
+ __perf_event_period(&pe);
raw_spin_unlock_irq(&ctx->lock);
- return ret;
+ return 0;
}
static const struct file_operations perf_fops;
@@ -4376,14 +4393,6 @@ static void ring_buffer_wakeup(struct perf_event *event)
rcu_read_unlock();
}
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
- struct ring_buffer *rb;
-
- rb = container_of(rcu_head, struct ring_buffer, rcu_head);
- rb_free(rb);
-}
-
struct ring_buffer *ring_buffer_get(struct perf_event *event)
{
struct ring_buffer *rb;
@@ -4766,12 +4775,20 @@ static const struct file_operations perf_fops = {
* to user-space before waking everybody up.
*/
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+ /* only the parent has fasync state */
+ if (event->parent)
+ event = event->parent;
+ return &event->fasync;
+}
+
void perf_event_wakeup(struct perf_event *event)
{
ring_buffer_wakeup(event);
if (event->pending_kill) {
- kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+ kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
event->pending_kill = 0;
}
}
@@ -5381,9 +5398,9 @@ void perf_prepare_sample(struct perf_event_header *header,
}
}
-static void perf_event_output(struct perf_event *event,
- struct perf_sample_data *data,
- struct pt_regs *regs)
+void perf_event_output(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
struct perf_output_handle handle;
struct perf_event_header header;
@@ -5812,7 +5829,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
* need to add enough zero bytes after the string to handle
* the 64bit alignment we do later.
*/
- name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64));
+ name = file_path(file, buf, PATH_MAX - sizeof(u64));
if (IS_ERR(name)) {
name = "//toolong";
goto cpy_name;
@@ -5975,6 +5992,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
}
/*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+ struct perf_output_handle handle;
+ struct perf_sample_data sample;
+ int ret;
+
+ struct {
+ struct perf_event_header header;
+ u64 lost;
+ } lost_samples_event = {
+ .header = {
+ .type = PERF_RECORD_LOST_SAMPLES,
+ .misc = 0,
+ .size = sizeof(lost_samples_event),
+ },
+ .lost = lost,
+ };
+
+ perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+ ret = perf_output_begin(&handle, event,
+ lost_samples_event.header.size);
+ if (ret)
+ return;
+
+ perf_output_put(&handle, lost_samples_event);
+ perf_event__output_id_sample(event, &handle, &sample);
+ perf_output_end(&handle);
+}
+
+/*
* IRQ throttle logging
*/
@@ -6117,7 +6167,7 @@ static int __perf_event_overflow(struct perf_event *event,
else
perf_event_output(event, data, regs);
- if (event->fasync && event->pending_kill) {
+ if (*perf_event_fasync(event) && event->pending_kill) {
event->pending_wakeup = 1;
irq_work_queue(&event->pending);
}
@@ -6864,9 +6914,8 @@ static void perf_swevent_start_hrtimer(struct perf_event *event)
} else {
period = max_t(u64, 10000, hwc->sample_period);
}
- __hrtimer_start_range_ns(&hwc->hrtimer,
- ns_to_ktime(period), 0,
- HRTIMER_MODE_REL_PINNED, 0);
+ hrtimer_start(&hwc->hrtimer, ns_to_ktime(period),
+ HRTIMER_MODE_REL_PINNED);
}
static void perf_swevent_cancel_hrtimer(struct perf_event *event)
@@ -7167,6 +7216,8 @@ perf_event_mux_interval_ms_show(struct device *dev,
return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms);
}
+static DEFINE_MUTEX(mux_interval_mutex);
+
static ssize_t
perf_event_mux_interval_ms_store(struct device *dev,
struct device_attribute *attr,
@@ -7186,17 +7237,21 @@ perf_event_mux_interval_ms_store(struct device *dev,
if (timer == pmu->hrtimer_interval_ms)
return count;
+ mutex_lock(&mux_interval_mutex);
pmu->hrtimer_interval_ms = timer;
/* update all cpuctx for this PMU */
- for_each_possible_cpu(cpu) {
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
struct perf_cpu_context *cpuctx;
cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer);
- if (hrtimer_active(&cpuctx->hrtimer))
- hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval);
+ cpu_function_call(cpu,
+ (remote_function_f)perf_mux_hrtimer_restart, cpuctx);
}
+ put_online_cpus();
+ mutex_unlock(&mux_interval_mutex);
return count;
}
@@ -7301,7 +7356,7 @@ skip_type:
lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
cpuctx->ctx.pmu = pmu;
- __perf_cpu_hrtimer_init(cpuctx, cpu);
+ __perf_mux_hrtimer_init(cpuctx, cpu);
cpuctx->unique_pmu = pmu;
}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 9f6ce9ba4..2bbad9c12 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
struct ring_buffer {
atomic_t refcount;
struct rcu_head rcu_head;
+ struct irq_work irq_work;
#ifdef CONFIG_PERF_USE_VMALLOC
struct work_struct work;
int page_order; /* allocation order */
@@ -55,6 +56,15 @@ struct ring_buffer {
};
extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+ struct ring_buffer *rb;
+
+ rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+ rb_free(rb);
+}
+
extern struct ring_buffer *
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
extern void perf_event_wakeup(struct perf_event *event);
@@ -72,15 +82,6 @@ static inline bool rb_has_aux(struct ring_buffer *rb)
void perf_event_aux_event(struct perf_event *event, unsigned long head,
unsigned long size, u64 flags);
-extern void
-perf_event_header__init_id(struct perf_event_header *header,
- struct perf_sample_data *data,
- struct perf_event *event);
-extern void
-perf_event__output_id_sample(struct perf_event *event,
- struct perf_output_handle *handle,
- struct perf_sample_data *sample);
-
extern struct page *
perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 725c41608..c8aa3f75b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -141,7 +141,7 @@ int perf_output_begin(struct perf_output_handle *handle,
perf_output_get_handle(handle);
do {
- tail = ACCESS_ONCE(rb->user_page->data_tail);
+ tail = READ_ONCE_CTRL(rb->user_page->data_tail);
offset = head = local_read(&rb->head);
if (!rb->overwrite &&
unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
@@ -221,6 +221,8 @@ void perf_output_end(struct perf_output_handle *handle)
rcu_read_unlock();
}
+static void rb_irq_work(struct irq_work *work);
+
static void
ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
{
@@ -241,6 +243,16 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
INIT_LIST_HEAD(&rb->event_list);
spin_lock_init(&rb->event_lock);
+ init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+ if (!atomic_dec_and_test(&rb->refcount))
+ return;
+
+ rb->rcu_head.next = (void *)rb;
+ irq_work_queue(&rb->irq_work);
}
/*
@@ -319,7 +331,7 @@ err_put:
rb_free_aux(rb);
err:
- ring_buffer_put(rb);
+ ring_buffer_put_async(rb);
handle->event = NULL;
return NULL;
@@ -370,7 +382,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
local_set(&rb->aux_nest, 0);
rb_free_aux(rb);
- ring_buffer_put(rb);
+ ring_buffer_put_async(rb);
}
/*
@@ -547,17 +559,30 @@ static void __rb_free_aux(struct ring_buffer *rb)
rb->aux_priv = NULL;
}
- for (pg = 0; pg < rb->aux_nr_pages; pg++)
- rb_free_aux_page(rb, pg);
+ if (rb->aux_nr_pages) {
+ for (pg = 0; pg < rb->aux_nr_pages; pg++)
+ rb_free_aux_page(rb, pg);
- kfree(rb->aux_pages);
- rb->aux_nr_pages = 0;
+ kfree(rb->aux_pages);
+ rb->aux_nr_pages = 0;
+ }
}
void rb_free_aux(struct ring_buffer *rb)
{
if (atomic_dec_and_test(&rb->aux_refcount))
+ irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+ struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+ if (!atomic_read(&rb->aux_refcount))
__rb_free_aux(rb);
+
+ if (rb->rcu_head.next == (void *)rb)
+ call_rcu(&rb->rcu_head, rb_free_rcu);
}
#ifndef CONFIG_PERF_USE_VMALLOC