From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 7852) id 28D06385829F; Thu, 29 Sep 2022 00:48:04 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 28D06385829F DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1664412484; bh=g1w5RX1fwGXdgJsmFMsMt7HJAaSFEgG7ef+S5KQmBCY=; h=From:To:Subject:Date:From; b=vPfnZpYNwA6O6rxW4Xn6Bl3z6eInLfgeNWL95M7yLJnnn8xUYoSgi9jVYw6wfdWrk M+PZnH/ukk7CoB9TH4eqFP4g7E3oDvI3WA+wcLjz71uOqsBMAINDnAO8xYYP3TpOnb qE8p51S3xNdZlJ25OwLDcZeaQr34LKgtiqgvWreA= Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Sunil Pandey To: glibc-cvs@sourceware.org Subject: [glibc/release/2.33/master] Add LLL_MUTEX_READ_LOCK [BZ #28537] X-Act-Checkin: glibc X-Git-Author: H.J. Lu X-Git-Refname: refs/heads/release/2.33/master X-Git-Oldrev: 0ec276739a22c0305263941b5213e8c368269ec0 X-Git-Newrev: 8844d9b22dfa00675ef4f4e14ffe107a173bc068 Message-Id: <20220929004804.28D06385829F@sourceware.org> Date: Thu, 29 Sep 2022 00:48:04 +0000 (GMT) List-Id: https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=8844d9b22dfa00675ef4f4e14ffe107a173bc068 commit 8844d9b22dfa00675ef4f4e14ffe107a173bc068 Author: H.J. Lu Date: Tue Nov 2 18:33:07 2021 -0700 Add LLL_MUTEX_READ_LOCK [BZ #28537] CAS instruction is expensive. From the x86 CPU's point of view, getting a cache line for writing is more expensive than reading. See Appendix A.2 Spinlock in: https://www.intel.com/content/dam/www/public/us/en/documents/white-papers/xeon-lock-scaling-analysis-paper.pdf The full compare and swap will grab the cache line exclusive and cause excessive cache line bouncing. Add LLL_MUTEX_READ_LOCK to do an atomic load and skip CAS in spinlock loop if compare may fail to reduce cache line bouncing on contended locks. Reviewed-by: Szabolcs Nagy (cherry picked from commit d672a98a1af106bd68deb15576710cd61363f7a6) Diff: --- nptl/pthread_mutex_lock.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/nptl/pthread_mutex_lock.c b/nptl/pthread_mutex_lock.c index 0fd7467b97..ac8a472c08 100644 --- a/nptl/pthread_mutex_lock.c +++ b/nptl/pthread_mutex_lock.c @@ -56,6 +56,11 @@ #define FORCE_ELISION(m, s) #endif +#ifndef LLL_MUTEX_READ_LOCK +# define LLL_MUTEX_READ_LOCK(mutex) \ + atomic_load_relaxed (&(mutex)->__data.__lock) +#endif + static int __pthread_mutex_lock_full (pthread_mutex_t *mutex) __attribute_noinline__; @@ -133,6 +138,8 @@ __pthread_mutex_lock (pthread_mutex_t *mutex) break; } atomic_spin_nop (); + if (LLL_MUTEX_READ_LOCK (mutex) != 0) + continue; } while (LLL_MUTEX_TRYLOCK (mutex) != 0);