diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-01 22:24:30 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-01 22:24:30 +0300 |
commit | 63e6053add5a6cec4dbfa3dec12e0d4439daac4a (patch) | |
tree | 1bd4020af150d2bfec2b9a9ca9c63a8546c6a434 /kernel | |
parent | 22a39c3d8693001c301d070366435edb04d0778c (diff) | |
parent | 326ecc15c61c349cd49d1700ff9e3e31c6fd1cd5 (diff) | |
download | linux-63e6053add5a6cec4dbfa3dec12e0d4439daac4a.tar.xz |
Merge tag 'perf-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events updates from Ingo Molnar:
- Fix Intel Alder Lake PEBS memory access latency & data source
profiling info bugs.
- Use Intel large-PEBS hardware feature in more circumstances, to
reduce PMI overhead & reduce sampling data.
- Extend the lost-sample profiling output with the PERF_FORMAT_LOST ABI
variant, which tells tooling the exact number of samples lost.
- Add new IBS register bits definitions.
- AMD uncore events: Add PerfMonV2 DF (Data Fabric) enhancements.
* tag 'perf-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/ibs: Add new IBS register bits into header
perf/x86/intel: Fix PEBS data source encoding for ADL
perf/x86/intel: Fix PEBS memory access info encoding for ADL
perf/core: Add a new read format to get a number of lost samples
perf/x86/amd/uncore: Add PerfMonV2 RDPMC assignments
perf/x86/amd/uncore: Add PerfMonV2 DF event format
perf/x86/amd/uncore: Detect available DF counters
perf/x86/amd/uncore: Use attr_update for format attributes
perf/x86/amd/uncore: Use dynamic events array
x86/events/intel/ds: Enable large PEBS for PERF_SAMPLE_WEIGHT_TYPE
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/events/core.c | 21 | ||||
-rw-r--r-- | kernel/events/ring_buffer.c | 5 |
2 files changed, 22 insertions, 4 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index d2b354991bf5..c9d32d4d2e20 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1819,6 +1819,9 @@ 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); @@ -5260,11 +5263,15 @@ 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); } raw_spin_unlock_irqrestore(&ctx->lock, flags); @@ -5321,7 +5328,7 @@ 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); @@ -5331,6 +5338,8 @@ 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; @@ -6858,7 +6867,7 @@ 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); @@ -6872,6 +6881,8 @@ 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)); } @@ -6882,7 +6893,7 @@ 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; @@ -6900,6 +6911,8 @@ 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)); @@ -6913,6 +6926,8 @@ 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 fb35b926024c..726132039c38 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(); |