[tip: perf/core] perf/core: Add aux_pause, aux_resume, aux_start_paused
From: tip-bot2 for Adrian Hunter
Date: Mon Jul 29 2024 - 06:25:24 EST
The following commit has been merged into the perf/core branch of tip:
Commit-ID: 675ad74989c26fcaca9bbea7075b8a94a27b16f2
Gitweb: https://git.kernel.org/tip/675ad74989c26fcaca9bbea7075b8a94a27b16f2
Author: Adrian Hunter <adrian.hunter@xxxxxxxxx>
AuthorDate: Mon, 15 Jul 2024 19:07:01 +03:00
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Mon, 29 Jul 2024 12:16:24 +02:00
perf/core: Add aux_pause, aux_resume, aux_start_paused
Hardware traces, such as instruction traces, can produce a vast amount of
trace data, so being able to reduce tracing to more specific circumstances
can be useful.
The ability to pause or resume tracing when another event happens, can do
that.
Add ability for an event to "pause" or "resume" AUX area tracing.
Add aux_pause bit to perf_event_attr to indicate that, if the event
happens, the associated AUX area tracing should be paused. Ditto
aux_resume. Do not allow aux_pause and aux_resume to be set together.
Add aux_start_paused bit to perf_event_attr to indicate to an AUX area
event that it should start in a "paused" state.
Add aux_paused to struct hw_perf_event for AUX area events to keep track of
the "paused" state. aux_paused is initialized to aux_start_paused.
Add PERF_EF_PAUSE and PERF_EF_RESUME modes for ->stop() and ->start()
callbacks. Call as needed, during __perf_event_output(). Add
aux_in_pause_resume to struct perf_buffer to prevent races with the NMI
handler. Pause/resume in NMI context will miss out if it coincides with
another pause/resume.
To use aux_pause or aux_resume, an event must be in a group with the AUX
area event as the group leader.
Example (requires Intel PT and tools patches also):
$ perf record --kcore -e intel_pt/aux-action=start-paused/k,syscalls:sys_enter_newuname/aux-action=resume/,syscalls:sys_exit_newuname/aux-action=pause/ uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.043 MB perf.data ]
$ perf script --call-trace
uname 30805 [000] 24001.058782799: name: 0x7ffc9c1865b0
uname 30805 [000] 24001.058784424: psb offs: 0
uname 30805 [000] 24001.058784424: cbr: 39 freq: 3904 MHz (139%)
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __x64_sys_newuname
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) down_read
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) __cond_resched
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) in_lock_functions
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_sub
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) up_read
uname 30805 [000] 24001.058784629: ([kernel.kallsyms]) preempt_count_add
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) in_lock_functions
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) preempt_count_sub
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) _copy_to_user
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_to_user_mode
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) syscall_exit_work
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) perf_syscall_exit
uname 30805 [000] 24001.058784838: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_alloc
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_get_recursion_context
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_tp_event
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_trace_buf_update
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) tracing_gen_ctx_irq_test
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_swevent_event
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __perf_event_account_interrupt
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __this_cpu_preempt_check
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_output_forward
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) perf_event_aux_pause
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) ring_buffer_get
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_lock
uname 30805 [000] 24001.058785046: ([kernel.kallsyms]) __rcu_read_unlock
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) pt_event_stop
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) debug_smp_processor_id
uname 30805 [000] 24001.058785254: ([kernel.kallsyms]) native_write_msr
uname 30805 [000] 24001.058785463: ([kernel.kallsyms]) native_write_msr
uname 30805 [000] 24001.058785639: 0x0
Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Acked-by: James Clark <james.clark@xxxxxxx>
Link: https://lkml.kernel.org/r/20240715160712.127117-3-adrian.hunter@xxxxxxxxx
---
include/linux/perf_event.h | 28 +++++++++++++-
include/uapi/linux/perf_event.h | 11 ++++-
kernel/events/core.c | 71 ++++++++++++++++++++++++++++++--
kernel/events/internal.h | 1 +-
4 files changed, 107 insertions(+), 4 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 6bb0c21..8e508f7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -170,6 +170,12 @@ struct hw_perf_event {
};
struct { /* aux / Intel-PT */
u64 aux_config;
+ /*
+ * For AUX area events, aux_paused cannot be a state
+ * flag because it can be updated asynchronously to
+ * state.
+ */
+ unsigned int aux_paused;
};
struct { /* software */
struct hrtimer hrtimer;
@@ -294,6 +300,7 @@ struct perf_event_pmu_context;
#define PERF_PMU_CAP_NO_EXCLUDE 0x0040
#define PERF_PMU_CAP_AUX_OUTPUT 0x0080
#define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100
+#define PERF_PMU_CAP_AUX_PAUSE 0x0200
struct perf_output_handle;
@@ -366,6 +373,8 @@ struct pmu {
#define PERF_EF_START 0x01 /* start the counter when adding */
#define PERF_EF_RELOAD 0x02 /* reload the counter when starting */
#define PERF_EF_UPDATE 0x04 /* update the counter when stopping */
+#define PERF_EF_PAUSE 0x08 /* AUX area event, pause tracing */
+#define PERF_EF_RESUME 0x10 /* AUX area event, resume tracing */
/*
* Adds/Removes a counter to/from the PMU, can be done inside a
@@ -405,6 +414,18 @@ struct pmu {
*
* ->start() with PERF_EF_RELOAD will reprogram the counter
* value, must be preceded by a ->stop() with PERF_EF_UPDATE.
+ *
+ * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
+ * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
+ * PERF_EF_RESUME.
+ *
+ * ->start() with PERF_EF_RESUME will start as simply as possible but
+ * only if the counter is not otherwise stopped. Will not overlap
+ * another ->start() with PERF_EF_RESUME nor ->stop() with
+ * PERF_EF_PAUSE.
+ *
+ * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other
+ * ->stop()/->start() invocations, just not itself.
*/
void (*start) (struct perf_event *event, int flags);
void (*stop) (struct perf_event *event, int flags);
@@ -1660,6 +1681,13 @@ static inline bool has_aux(struct perf_event *event)
return event->pmu->setup_aux;
}
+static inline bool has_aux_action(struct perf_event *event)
+{
+ return event->attr.aux_sample_size ||
+ event->attr.aux_pause ||
+ event->attr.aux_resume;
+}
+
static inline bool is_write_backward(struct perf_event *event)
{
return !!event->attr.write_backward;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 4842c36..0524d54 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
__u16 sample_max_stack;
__u16 __reserved_2;
__u32 aux_sample_size;
- __u32 __reserved_3;
+
+ union {
+ __u32 aux_action;
+ struct {
+ __u32 aux_start_paused : 1, /* start AUX area tracing paused */
+ aux_pause : 1, /* on overflow, pause AUX area tracing */
+ aux_resume : 1, /* on overflow, resume AUX area tracing */
+ __reserved_3 : 29;
+ };
+ };
/*
* User provided data if sigtrap=1, passed back to user via
diff --git a/kernel/events/core.c b/kernel/events/core.c
index aa3450b..e4cb6e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2097,7 +2097,7 @@ static void perf_put_aux_event(struct perf_event *event)
static bool perf_need_aux_event(struct perf_event *event)
{
- return !!event->attr.aux_output || !!event->attr.aux_sample_size;
+ return event->attr.aux_output || has_aux_action(event);
}
static int perf_get_aux_event(struct perf_event *event,
@@ -2122,6 +2122,10 @@ static int perf_get_aux_event(struct perf_event *event,
!perf_aux_output_match(event, group_leader))
return 0;
+ if ((event->attr.aux_pause || event->attr.aux_resume) &&
+ !(group_leader->pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE))
+ return 0;
+
if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux)
return 0;
@@ -7904,6 +7908,49 @@ void perf_prepare_header(struct perf_event_header *header,
WARN_ON_ONCE(header->size & 7);
}
+static void __perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+ if (pause) {
+ if (!event->hw.aux_paused) {
+ event->hw.aux_paused = 1;
+ event->pmu->stop(event, PERF_EF_PAUSE);
+ }
+ } else {
+ if (event->hw.aux_paused) {
+ event->hw.aux_paused = 0;
+ event->pmu->start(event, PERF_EF_RESUME);
+ }
+ }
+}
+
+static void perf_event_aux_pause(struct perf_event *event, bool pause)
+{
+ struct perf_buffer *rb;
+
+ if (WARN_ON_ONCE(!event))
+ return;
+
+ rb = ring_buffer_get(event);
+ if (!rb)
+ return;
+
+ scoped_guard (irqsave) {
+ /*
+ * Guard against self-recursion here. Another event could trip
+ * this same from NMI context.
+ */
+ if (READ_ONCE(rb->aux_in_pause_resume))
+ break;
+
+ WRITE_ONCE(rb->aux_in_pause_resume, 1);
+ barrier();
+ __perf_event_aux_pause(event, pause);
+ barrier();
+ WRITE_ONCE(rb->aux_in_pause_resume, 0);
+ }
+ ring_buffer_put(rb);
+}
+
static __always_inline int
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
@@ -9706,6 +9753,11 @@ static int __perf_event_overflow(struct perf_event *event,
ret = __perf_event_account_interrupt(event, throttle);
+ if (event->attr.aux_pause)
+ perf_event_aux_pause(event->aux_event, true);
+ if (event->attr.aux_resume)
+ perf_event_aux_pause(event->aux_event, false);
+
if (event->prog && !bpf_overflow_handler(event, data, regs))
return ret;
@@ -12083,10 +12135,23 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
}
if (event->attr.aux_output &&
- !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+ (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) ||
+ event->attr.aux_pause || event->attr.aux_resume)) {
+ err = -EOPNOTSUPP;
+ goto err_pmu;
+ }
+
+ if (event->attr.aux_pause && event->attr.aux_resume) {
+ err = -EINVAL;
+ goto err_pmu;
+ }
+
+ if (event->attr.aux_start_paused &&
+ !(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) {
err = -EOPNOTSUPP;
goto err_pmu;
}
+ event->hw.aux_paused = event->attr.aux_start_paused;
if (cgroup_fd != -1) {
err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
@@ -12883,7 +12948,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
* Grouping is not supported for kernel events, neither is 'AUX',
* make sure the caller's intentions are adjusted.
*/
- if (attr->aux_output)
+ if (attr->aux_output || attr->aux_action)
return ERR_PTR(-EINVAL);
event = perf_event_alloc(attr, cpu, task, NULL, NULL,
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 4515144..001b1cb 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -51,6 +51,7 @@ struct perf_buffer {
void (*free_aux)(void *);
refcount_t aux_refcount;
int aux_in_sampling;
+ int aux_in_pause_resume;
void **aux_pages;
void *aux_priv;