glibc/glibc-RHEL-15696-71.patch
DJ Delorie 02cfe04e36 Import Intel hyperscale improvements (RHEL-15696)
Resolves: RHEL-15696

Includes two additional (well, 1.5) upstream patches
to resolve roundeven redirects.
2023-12-15 17:33:06 -05:00

44 lines
1.3 KiB
Diff

From 6b8dbbd03ac88f169b65b5c7d7278576a11d2e44 Mon Sep 17 00:00:00 2001
From: Jangwoong Kim <6812skiii@gmail.com>
Date: Tue, 14 Dec 2021 21:30:51 +0900
Subject: [PATCH] nptl: Effectively skip CAS in spinlock loop
Content-type: text/plain; charset=UTF-8
The commit:
"Add LLL_MUTEX_READ_LOCK [BZ #28537]"
SHA1: d672a98a1af106bd68deb15576710cd61363f7a6
introduced LLL_MUTEX_READ_LOCK, to skip CAS in spinlock loop
if atomic load fails. But, "continue" inside of do-while loop
does not skip the evaluation of escape expression, thus CAS
is not skipped.
Replace do-while with while and skip LLL_MUTEX_TRYLOCK if
LLL_MUTEX_READ_LOCK fails.
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
---
nptl/pthread_mutex_lock.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/nptl/pthread_mutex_lock.c b/nptl/pthread_mutex_lock.c
index a633d95e..d96a9933 100644
--- a/nptl/pthread_mutex_lock.c
+++ b/nptl/pthread_mutex_lock.c
@@ -141,10 +141,9 @@ __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);
+ while (LLL_MUTEX_READ_LOCK (mutex) != 0
+ || LLL_MUTEX_TRYLOCK (mutex) != 0);
mutex->__data.__spins += (cnt - mutex->__data.__spins) / 8;
}
--
GitLab