5.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Namhyung Kim namhyung@kernel.org
[ Upstream commit 119a784c81270eb88e573174ed2209225d646656 ]
Sometimes we want to know an accurate number of samples even if it's lost. Currenlty PERF_RECORD_LOST is generated for a ring-buffer which might be shared with other events. So it's hard to know per-event lost count.
Add event->lost_samples field and PERF_FORMAT_LOST to retrieve it from userspace.
Original-patch-by: Jiri Olsa jolsa@redhat.com Signed-off-by: Namhyung Kim namhyung@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220616180623.1358843-1-namhyung@kernel.org Stable-dep-of: 382c27f4ed28 ("perf: Fix perf_event_validate_size()") Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/perf_event.h | 2 ++ include/uapi/linux/perf_event.h | 5 ++++- kernel/events/core.c | 21 ++++++++++++++++++--- kernel/events/ring_buffer.c | 5 ++++- 4 files changed, 28 insertions(+), 5 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 50557d903a059..3b038a2cc0071 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -744,6 +744,8 @@ struct perf_event { struct pid_namespace *ns; u64 id;
+ atomic64_t lost_samples; + u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b95d3c485d27e..6ca63ab6bee5d 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -279,6 +279,7 @@ enum { * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING * { u64 id; } && PERF_FORMAT_ID + * { u64 lost; } && PERF_FORMAT_LOST * } && !PERF_FORMAT_GROUP * * { u64 nr; @@ -286,6 +287,7 @@ enum { * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING * { u64 value; * { u64 id; } && PERF_FORMAT_ID + * { u64 lost; } && PERF_FORMAT_LOST * } cntr[nr]; * } && PERF_FORMAT_GROUP * }; @@ -295,8 +297,9 @@ enum perf_event_read_format { PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, PERF_FORMAT_ID = 1U << 2, PERF_FORMAT_GROUP = 1U << 3, + PERF_FORMAT_LOST = 1U << 4,
- PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ + PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ };
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 5072635f0b0c1..f7ac1b24f93e0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1927,6 +1927,9 @@ static void __perf_event_read_size(struct perf_event *event, int nr_siblings) if (event->attr.read_format & PERF_FORMAT_ID) entry += sizeof(u64);
+ if (event->attr.read_format & PERF_FORMAT_LOST) + entry += sizeof(u64); + if (event->attr.read_format & PERF_FORMAT_GROUP) { nr += nr_siblings; size += sizeof(u64); @@ -5283,11 +5286,15 @@ static int __perf_read_group_add(struct perf_event *leader, values[n++] += perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&leader->lost_samples);
for_each_sibling_event(sub, leader) { values[n++] += perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&sub->lost_samples); }
unlock: @@ -5341,7 +5348,7 @@ static int perf_read_one(struct perf_event *event, u64 read_format, char __user *buf) { u64 enabled, running; - u64 values[4]; + u64 values[5]; int n = 0;
values[n++] = __perf_event_read_value(event, &enabled, &running); @@ -5351,6 +5358,8 @@ static int perf_read_one(struct perf_event *event, values[n++] = running; if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&event->lost_samples);
if (copy_to_user(buf, values, n * sizeof(u64))) return -EFAULT; @@ -6830,7 +6839,7 @@ static void perf_output_read_one(struct perf_output_handle *handle, u64 enabled, u64 running) { u64 read_format = event->attr.read_format; - u64 values[4]; + u64 values[5]; int n = 0;
values[n++] = perf_event_count(event); @@ -6844,6 +6853,8 @@ static void perf_output_read_one(struct perf_output_handle *handle, } if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&event->lost_samples);
__output_copy(handle, values, n * sizeof(u64)); } @@ -6854,7 +6865,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, { struct perf_event *leader = event->group_leader, *sub; u64 read_format = event->attr.read_format; - u64 values[5]; + u64 values[6]; int n = 0;
values[n++] = 1 + leader->nr_siblings; @@ -6872,6 +6883,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, values[n++] = perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&leader->lost_samples);
__output_copy(handle, values, n * sizeof(u64));
@@ -6885,6 +6898,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, values[n++] = perf_event_count(sub); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); + if (read_format & PERF_FORMAT_LOST) + values[n++] = atomic64_read(&sub->lost_samples);
__output_copy(handle, values, n * sizeof(u64)); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 01351e7e25435..ca27946fdaaf2 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -172,8 +172,10 @@ __perf_output_begin(struct perf_output_handle *handle, goto out;
if (unlikely(rb->paused)) { - if (rb->nr_pages) + if (rb->nr_pages) { local_inc(&rb->lost); + atomic64_inc(&event->lost_samples); + } goto out; }
@@ -254,6 +256,7 @@ __perf_output_begin(struct perf_output_handle *handle,
fail: local_inc(&rb->lost); + atomic64_inc(&event->lost_samples); perf_output_put_handle(handle); out: rcu_read_unlock();