From: "H.J. Lu" <hjl.tools@gmail.com>
To: libc-alpha@sourceware.org
Cc: Florian Weimer <fweimer@redhat.com>,
Oleh Derevenko <oleh.derevenko@gmail.com>,
Arjan van de Ven <arjan@linux.intel.com>,
Andreas Schwab <schwab@linux-m68k.org>
Subject: [PATCH v4 2/3] Reduce CAS in __pthread_mutex_lock_full [BZ #28537]
Date: Tue, 9 Nov 2021 16:16:13 -0800 [thread overview]
Message-ID: <20211110001614.2087610-3-hjl.tools@gmail.com> (raw)
In-Reply-To: <20211110001614.2087610-1-hjl.tools@gmail.com>
Change __pthread_mutex_lock_full to do an atomic load and skip CAS if
compare may fail to reduce cache line bouncing on contended locks.
---
nptl/pthread_mutex_lock.c | 38 +++++++++++++++++++++++++++++++-------
1 file changed, 31 insertions(+), 7 deletions(-)
diff --git a/nptl/pthread_mutex_lock.c b/nptl/pthread_mutex_lock.c
index 2bd41767e0..1126ecba95 100644
--- a/nptl/pthread_mutex_lock.c
+++ b/nptl/pthread_mutex_lock.c
@@ -204,6 +204,10 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
our TID | assume_other_futex_waiters. */
if (__glibc_likely (oldval == 0))
{
+ oldval = atomic_load_relaxed (&mutex->__data.__lock);
+ if (oldval != 0)
+ goto tid_failed;
+
oldval
= atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
id | assume_other_futex_waiters, 0);
@@ -213,6 +217,13 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
if ((oldval & FUTEX_OWNER_DIED) != 0)
{
+ int currval = atomic_load_relaxed (&mutex->__data.__lock);
+ if (currval != oldval)
+ {
+ oldval = currval;
+ continue;
+ }
+
/* The previous owner died. Try locking the mutex. */
int newval = id;
#ifdef NO_INCR
@@ -259,6 +270,7 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
return EOWNERDEAD;
}
+ tid_failed:
/* Check whether we already hold the mutex. */
if (__glibc_unlikely ((oldval & FUTEX_TID_MASK) == id))
{
@@ -411,11 +423,15 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
# ifdef NO_INCR
newval |= FUTEX_WAITERS;
# endif
+ oldval = atomic_load_relaxed (&mutex->__data.__lock);
+ if (oldval != 0)
+ goto locked_mutex;
oldval = atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
newval, 0);
if (oldval != 0)
{
+ locked_mutex:
/* The mutex is locked. The kernel will now take care of
everything. */
int private = (robust
@@ -554,6 +570,10 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
ceilval = ceiling << PTHREAD_MUTEX_PRIO_CEILING_SHIFT;
oldprio = ceiling;
+ oldval = atomic_load_relaxed (&mutex->__data.__lock);
+ if (oldval != ceilval)
+ goto ceilval_failed;
+
oldval
= atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
#ifdef NO_INCR
@@ -568,10 +588,13 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
do
{
- oldval
- = atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
- ceilval | 2,
- ceilval | 1);
+ oldval = atomic_load_relaxed (&mutex->__data.__lock);
+ ceilval_failed:
+ if (oldval == (ceilval | 1))
+ oldval
+ = atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
+ ceilval | 2,
+ ceilval | 1);
if ((oldval & PTHREAD_MUTEX_PRIO_CEILING_MASK) != ceilval)
break;
@@ -581,9 +604,10 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
ceilval | 2,
PTHREAD_MUTEX_PSHARED (mutex));
}
- while (atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
- ceilval | 2, ceilval)
- != ceilval);
+ while (atomic_load_relaxed (&mutex->__data.__lock) != ceilval
+ || (atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
+ ceilval | 2, ceilval)
+ != ceilval));
}
while ((oldval & PTHREAD_MUTEX_PRIO_CEILING_MASK) != ceilval);
--
2.33.1
next prev parent reply other threads:[~2021-11-10 0:16 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-10 0:16 [PATCH v4 0/3] Optimize CAS " H.J. Lu
2021-11-10 0:16 ` [PATCH v4 1/3] Reduce CAS in low level locks " H.J. Lu
2021-11-10 1:56 ` Noah Goldstein
2021-11-10 0:16 ` H.J. Lu [this message]
2021-11-10 0:16 ` [PATCH v4 3/3] Optimize CAS in __pthread_mutex_lock_full " H.J. Lu
2021-11-10 14:26 ` [PATCH v4 0/3] Optimize CAS " Paul E Murphy
2021-11-10 20:07 ` Paul A. Clarke
2021-11-10 21:33 ` H.J. Lu
2021-11-11 0:30 ` Paul A. Clarke
2021-11-10 23:34 ` H.J. Lu
2021-11-10 15:35 ` Paul A. Clarke
2021-11-10 15:42 ` H.J. Lu
2021-11-10 15:50 ` Paul A. Clarke
2021-11-10 15:52 ` H.J. Lu
2021-11-10 15:52 ` Florian Weimer
2021-11-10 16:03 ` H.J. Lu
2021-11-10 16:04 ` Paul A. Clarke
2021-11-10 16:14 ` Andreas Schwab
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20211110001614.2087610-3-hjl.tools@gmail.com \
--to=hjl.tools@gmail.com \
--cc=arjan@linux.intel.com \
--cc=fweimer@redhat.com \
--cc=libc-alpha@sourceware.org \
--cc=oleh.derevenko@gmail.com \
--cc=schwab@linux-m68k.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).