From 92f22a3865abe87eea2609a6f8e5be5123f7ce4f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 2 Apr 2009 11:12:04 +0200 Subject: [PATCH] perf_counter: update mmap() counter read Paul noted that we don't need SMP barriers for the mmap() counter read because its always on the same cpu (otherwise you can't access the hw counter anyway). So remove the SMP barriers and replace them with regular compiler barriers. Further, update the comment to include a race free method of reading said hardware counter. The primary change is putting the pmc_read inside the seq-loop, otherwise we can still race and read rubbish. Noticed-by: Paul Mackerras Signed-off-by: Peter Zijlstra Cc: Corey Ashford Orig-LKML-Reference: <20090402091319.577951445@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_counter.h | 22 ++++++++++------------ kernel/perf_counter.c | 4 ++-- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index 90cce0c74a03..f2b914de3f0c 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -167,30 +167,28 @@ struct perf_counter_mmap_page { /* * Bits needed to read the hw counters in user-space. * - * The index and offset should be read atomically using the seqlock: - * - * __u32 seq, index; - * __s64 offset; + * u32 seq; + * s64 count; * * again: - * rmb(); * seq = pc->lock; - * * if (unlikely(seq & 1)) { * cpu_relax(); * goto again; * } * - * index = pc->index; - * offset = pc->offset; + * if (pc->index) { + * count = pmc_read(pc->index - 1); + * count += pc->offset; + * } else + * goto regular_read; * - * rmb(); + * barrier(); * if (pc->lock != seq) * goto again; * - * After this, index contains architecture specific counter index + 1, - * so that 0 means unavailable, offset contains the value to be added - * to the result of the raw timer read to obtain this counter's value. + * NOTE: for obvious reason this only works on self-monitoring + * processes. */ __u32 lock; /* seqlock for synchronization */ __u32 index; /* hardware counter identifier */ diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index f105a6e696c2..2a5d4f525567 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -1340,13 +1340,13 @@ void perf_counter_update_userpage(struct perf_counter *counter) */ preempt_disable(); ++userpg->lock; - smp_wmb(); + barrier(); userpg->index = counter->hw.idx; userpg->offset = atomic64_read(&counter->count); if (counter->state == PERF_COUNTER_STATE_ACTIVE) userpg->offset -= atomic64_read(&counter->hw.prev_count); - smp_wmb(); + barrier(); ++userpg->lock; preempt_enable(); unlock: -- GitLab