aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/perf_event.h
diff options
context:
space:
mode:
authorSong Liu <songliubraving@fb.com>2021-09-29 12:43:13 -0700
committerPeter Zijlstra <peterz@infradead.org>2021-10-01 13:57:54 +0200
commitf792565326825ed806626da50c6f9a928f1079c1 (patch)
tree09c2e29ea3fb5732a50748230db362bbd44fab5c /include/linux/perf_event.h
parentperf/x86/intel: Update event constraints for ICX (diff)
downloadlinux-dev-f792565326825ed806626da50c6f9a928f1079c1.tar.xz
linux-dev-f792565326825ed806626da50c6f9a928f1079c1.zip
perf/core: fix userpage->time_enabled of inactive events
Users of rdpmc rely on the mmapped user page to calculate accurate time_enabled. Currently, userpage->time_enabled is only updated when the event is added to the pmu. As a result, inactive event (due to counter multiplexing) does not have accurate userpage->time_enabled. This can be reproduced with something like: /* open 20 task perf_event "cycles", to create multiplexing */ fd = perf_event_open(); /* open task perf_event "cycles" */ userpage = mmap(fd); /* use mmap and rdmpc */ while (true) { time_enabled_mmap = xxx; /* use logic in perf_event_mmap_page */ time_enabled_read = read(fd).time_enabled; if (time_enabled_mmap > time_enabled_read) BUG(); } Fix this by updating userpage for inactive events in merge_sched_in. Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reported-and-tested-by: Lucian Grijincu <lucian@fb.com> Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20210929194313.2398474-1-songliubraving@fb.com
Diffstat (limited to 'include/linux/perf_event.h')
-rw-r--r--include/linux/perf_event.h4
1 files changed, 3 insertions, 1 deletions
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fe156a8170aa..9b60bb89d86a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -683,7 +683,9 @@ struct perf_event {
/*
* timestamp shadows the actual context timing but it can
* be safely used in NMI interrupt context. It reflects the
- * context time as it was when the event was last scheduled in.
+ * context time as it was when the event was last scheduled in,
+ * or when ctx_sched_in failed to schedule the event because we
+ * run out of PMC.
*
* ctx_time already accounts for ctx->timestamp. Therefore to
* compute ctx_time for a sample, simply add perf_clock().