kevin/linux
1
Fork 0
Code

perf/x86/rapl: Stop doing cpu_relax() in the local64_cmpxchg() loop in rapl_event_update()

Browse Source 
According to the following commit:

   f5fe24ef17 ("lockref: stop doing cpu_relax in the cmpxchg loop")

   "On the x86-64 architecture even a failing cmpxchg grants exclusive
    access to the cacheline, making it preferable to retry the failed op
    immediately instead of stalling with the pause instruction."

Based on the above observation, remove cpu_relax() from the
local64_cmpxchg() loop of rapl_event_update().

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20230807145134.3176-1-ubizjak@gmail.com
This commit is contained in:
Uros Bizjak 2023-08-07 16:51:14 +02:00 committed by Ingo Molnar
parent de80193308
commit 1ce19bf90b
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
arch/x86/events/rapl.c
View File

@ -184,10 +184,8 @@ again:
rdmsrl(event->hw.event_base, new_raw_count); rdmsrl(event->hw.event_base, new_raw_count);
if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
new_raw_count) != prev_raw_count) { new_raw_count) != prev_raw_count)
cpu_relax();
goto again; goto again;
}
/* /*
* Now we have the new raw value and have updated the prev * Now we have the new raw value and have updated the prev