Commit bed5b25a authored by Alexander Shishkin's avatar Alexander Shishkin Committed by Ingo Molnar

perf: Add a pmu capability for "exclusive" events

Usually, pmus that do, for example, instruction tracing, would only ever
be able to have one event per task per cpu (or per perf_event_context). For
such pmus it makes sense to disallow creating conflicting events early on,
so as to provide consistent behavior for the user.

This patch adds a pmu capability that indicates such constraint on event
creation.
Signed-off-by: default avatarAlexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kaixu Xia <kaixu.xia@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: adrian.hunter@intel.com
Cc: kan.liang@intel.com
Cc: markus.t.metzger@intel.com
Cc: mathieu.poirier@linaro.org
Link: http://lkml.kernel.org/r/1422613866-113186-1-git-send-email-alexander.shishkin@linux.intel.comSigned-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent 6a279230
...@@ -176,6 +176,7 @@ struct perf_event; ...@@ -176,6 +176,7 @@ struct perf_event;
#define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_NO_NMI 0x02
#define PERF_PMU_CAP_AUX_NO_SG 0x04 #define PERF_PMU_CAP_AUX_NO_SG 0x04
#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08 #define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08
#define PERF_PMU_CAP_EXCLUSIVE 0x10
/** /**
* struct pmu - generic performance monitoring unit * struct pmu - generic performance monitoring unit
...@@ -196,6 +197,7 @@ struct pmu { ...@@ -196,6 +197,7 @@ struct pmu {
int * __percpu pmu_disable_count; int * __percpu pmu_disable_count;
struct perf_cpu_context * __percpu pmu_cpu_context; struct perf_cpu_context * __percpu pmu_cpu_context;
atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */
int task_ctx_nr; int task_ctx_nr;
int hrtimer_interval_ms; int hrtimer_interval_ms;
......
...@@ -3459,6 +3459,91 @@ static void unaccount_event(struct perf_event *event) ...@@ -3459,6 +3459,91 @@ static void unaccount_event(struct perf_event *event)
unaccount_event_cpu(event, event->cpu); unaccount_event_cpu(event, event->cpu);
} }
/*
* The following implement mutual exclusion of events on "exclusive" pmus
* (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled
* at a time, so we disallow creating events that might conflict, namely:
*
* 1) cpu-wide events in the presence of per-task events,
* 2) per-task events in the presence of cpu-wide events,
* 3) two matching events on the same context.
*
* The former two cases are handled in the allocation path (perf_event_alloc(),
* __free_event()), the latter -- before the first perf_install_in_context().
*/
static int exclusive_event_init(struct perf_event *event)
{
struct pmu *pmu = event->pmu;
if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
return 0;
/*
* Prevent co-existence of per-task and cpu-wide events on the
* same exclusive pmu.
*
* Negative pmu::exclusive_cnt means there are cpu-wide
* events on this "exclusive" pmu, positive means there are
* per-task events.
*
* Since this is called in perf_event_alloc() path, event::ctx
* doesn't exist yet; it is, however, safe to use PERF_ATTACH_TASK
* to mean "per-task event", because unlike other attach states it
* never gets cleared.
*/
if (event->attach_state & PERF_ATTACH_TASK) {
if (!atomic_inc_unless_negative(&pmu->exclusive_cnt))
return -EBUSY;
} else {
if (!atomic_dec_unless_positive(&pmu->exclusive_cnt))
return -EBUSY;
}
return 0;
}
static void exclusive_event_destroy(struct perf_event *event)
{
struct pmu *pmu = event->pmu;
if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
return;
/* see comment in exclusive_event_init() */
if (event->attach_state & PERF_ATTACH_TASK)
atomic_dec(&pmu->exclusive_cnt);
else
atomic_inc(&pmu->exclusive_cnt);
}
static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
{
if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
(e1->cpu == e2->cpu ||
e1->cpu == -1 ||
e2->cpu == -1))
return true;
return false;
}
/* Called under the same ctx::mutex as perf_install_in_context() */
static bool exclusive_event_installable(struct perf_event *event,
struct perf_event_context *ctx)
{
struct perf_event *iter_event;
struct pmu *pmu = event->pmu;
if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE))
return true;
list_for_each_entry(iter_event, &ctx->event_list, event_entry) {
if (exclusive_event_match(iter_event, event))
return false;
}
return true;
}
static void __free_event(struct perf_event *event) static void __free_event(struct perf_event *event)
{ {
if (!event->parent) { if (!event->parent) {
...@@ -3472,8 +3557,10 @@ static void __free_event(struct perf_event *event) ...@@ -3472,8 +3557,10 @@ static void __free_event(struct perf_event *event)
if (event->ctx) if (event->ctx)
put_ctx(event->ctx); put_ctx(event->ctx);
if (event->pmu) if (event->pmu) {
exclusive_event_destroy(event);
module_put(event->pmu->module); module_put(event->pmu->module);
}
call_rcu(&event->rcu_head, free_event_rcu); call_rcu(&event->rcu_head, free_event_rcu);
} }
...@@ -7150,6 +7237,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type) ...@@ -7150,6 +7237,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
pmu->event_idx = perf_event_idx_default; pmu->event_idx = perf_event_idx_default;
list_add_rcu(&pmu->entry, &pmus); list_add_rcu(&pmu->entry, &pmus);
atomic_set(&pmu->exclusive_cnt, 0);
ret = 0; ret = 0;
unlock: unlock:
mutex_unlock(&pmus_lock); mutex_unlock(&pmus_lock);
...@@ -7405,16 +7493,23 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, ...@@ -7405,16 +7493,23 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
goto err_ns; goto err_ns;
} }
err = exclusive_event_init(event);
if (err)
goto err_pmu;
if (!event->parent) { if (!event->parent) {
if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
err = get_callchain_buffers(); err = get_callchain_buffers();
if (err) if (err)
goto err_pmu; goto err_per_task;
} }
} }
return event; return event;
err_per_task:
exclusive_event_destroy(event);
err_pmu: err_pmu:
if (event->destroy) if (event->destroy)
event->destroy(event); event->destroy(event);
...@@ -7819,6 +7914,11 @@ SYSCALL_DEFINE5(perf_event_open, ...@@ -7819,6 +7914,11 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_alloc; goto err_alloc;
} }
if ((pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) && group_leader) {
err = -EBUSY;
goto err_context;
}
if (task) { if (task) {
put_task_struct(task); put_task_struct(task);
task = NULL; task = NULL;
...@@ -7941,6 +8041,13 @@ SYSCALL_DEFINE5(perf_event_open, ...@@ -7941,6 +8041,13 @@ SYSCALL_DEFINE5(perf_event_open,
get_ctx(ctx); get_ctx(ctx);
} }
if (!exclusive_event_installable(event, ctx)) {
err = -EBUSY;
mutex_unlock(&ctx->mutex);
fput(event_file);
goto err_context;
}
perf_install_in_context(ctx, event, event->cpu); perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx); perf_unpin_context(ctx);
...@@ -8032,6 +8139,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, ...@@ -8032,6 +8139,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
WARN_ON_ONCE(ctx->parent_ctx); WARN_ON_ONCE(ctx->parent_ctx);
mutex_lock(&ctx->mutex); mutex_lock(&ctx->mutex);
if (!exclusive_event_installable(event, ctx)) {
mutex_unlock(&ctx->mutex);
perf_unpin_context(ctx);
put_ctx(ctx);
err = -EBUSY;
goto err_free;
}
perf_install_in_context(ctx, event, cpu); perf_install_in_context(ctx, event, cpu);
perf_unpin_context(ctx); perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex); mutex_unlock(&ctx->mutex);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment