From: Nick Piggin <npiggin@suse.de>
To: Ingo Molnar <mingo@elte.hu>,
linux-arch@vger.kernel.org, linuxppc-dev@ozlabs.org,
paulus@samba.org, benh@kernel.crashing.org
Subject: [patch] powerpc: implement optimised mutex fastpaths
Date: Sun, 12 Oct 2008 07:47:32 +0200 [thread overview]
Message-ID: <20081012054732.GB12535@wotan.suse.de> (raw)
In-Reply-To: <20081012054634.GA12535@wotan.suse.de>
Implement a more optimal mutex fastpath for powerpc, making use of acquire
and release barrier semantics. This takes the mutex lock+unlock benchmark
from 203 to 173 cycles on a G5.
Signed-off-by: Nick Piggin <npiggin@suse.de>
---
Index: linux-2.6/arch/powerpc/include/asm/mutex.h
===================================================================
--- linux-2.6.orig/arch/powerpc/include/asm/mutex.h
+++ linux-2.6/arch/powerpc/include/asm/mutex.h
@@ -1,9 +1,136 @@
/*
- * Pull in the generic implementation for the mutex fastpath.
+ * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm
+ */
+#ifndef _ASM_POWERPC_MUTEX_H
+#define _ASM_POWERPC_MUTEX_H
+
+static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new)
+{
+ int t;
+
+ __asm__ __volatile__ (
+"1: lwarx %0,0,%1 # mutex trylock\n\
+ cmpw 0,%0,%2\n\
+ bne- 2f\n"
+ PPC405_ERR77(0,%1)
+" stwcx. %3,0,%1\n\
+ bne- 1b"
+ ISYNC_ON_SMP
+ "\n\
+2:"
+ : "=&r" (t)
+ : "r" (&v->counter), "r" (old), "r" (new)
+ : "cc", "memory");
+
+ return t;
+}
+
+static inline int __mutex_dec_return_lock(atomic_t *v)
+{
+ int t;
+
+ __asm__ __volatile__(
+"1: lwarx %0,0,%1 # mutex lock\n\
+ addic %0,%0,-1\n"
+ PPC405_ERR77(0,%1)
+" stwcx. %0,0,%1\n\
+ bne- 1b"
+ ISYNC_ON_SMP
+ : "=&r" (t)
+ : "r" (&v->counter)
+ : "cc", "memory");
+
+ return t;
+}
+
+static inline int __mutex_inc_return_unlock(atomic_t *v)
+{
+ int t;
+
+ __asm__ __volatile__(
+ LWSYNC_ON_SMP
+"1: lwarx %0,0,%1 # mutex unlock\n\
+ addic %0,%0,1\n"
+ PPC405_ERR77(0,%1)
+" stwcx. %0,0,%1 \n\
+ bne- 1b"
+ : "=&r" (t)
+ : "r" (&v->counter)
+ : "cc", "memory");
+
+ return t;
+}
+
+/**
+ * __mutex_fastpath_lock - try to take the lock by moving the count
+ * from 1 to a 0 value
+ * @count: pointer of type atomic_t
+ * @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function MUST leave the value lower than
+ * 1 even when the "1" assertion wasn't true.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+ if (unlikely(__mutex_dec_return_lock(count) < 0))
+ fail_fn(count);
+}
+
+/**
+ * __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ * from 1 to a 0 value
+ * @count: pointer of type atomic_t
+ * @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns.
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+ if (unlikely(__mutex_dec_return_lock(count) < 0))
+ return fail_fn(count);
+ return 0;
+}
+
+/**
+ * __mutex_fastpath_unlock - try to promote the count from 0 to 1
+ * @count: pointer of type atomic_t
+ * @fail_fn: function to call if the original value was not 0
+ *
+ * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value to
+ * 1, or to set it to a value lower than 1.
+ */
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+ if (unlikely(__mutex_inc_return_unlock(count) <= 0))
+ fail_fn(count);
+}
+
+#define __mutex_slowpath_needs_to_unlock() 1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ * @count: pointer of type atomic_t
+ * @fail_fn: fallback function
*
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
*/
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+ if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1))
+ return 1;
+}
-#include <asm-generic/mutex-dec.h>
+#endif
next prev parent reply other threads:[~2008-10-12 6:01 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-10-12 5:46 [patch] mutex: optimise generic mutex implementations Nick Piggin
2008-10-12 5:47 ` Nick Piggin [this message]
2008-10-13 1:18 ` [patch] powerpc: implement optimised mutex fastpaths Nick Piggin
2008-11-06 4:09 ` Paul Mackerras
2008-11-06 5:06 ` Nick Piggin
2008-10-13 16:15 ` Scott Wood
2008-10-13 16:20 ` Scott Wood
2008-10-14 7:06 ` Nick Piggin
2008-10-14 8:35 ` [patch] mutex: optimise generic mutex implementations Benjamin Herrenschmidt
2008-10-22 15:59 ` Ingo Molnar
2008-10-23 4:43 ` Benjamin Herrenschmidt
2008-10-23 7:02 ` Nick Piggin
2008-10-22 16:24 ` David Howells
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=20081012054732.GB12535@wotan.suse.de \
--to=npiggin@suse.de \
--cc=benh@kernel.crashing.org \
--cc=linux-arch@vger.kernel.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.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 NNTP newsgroup(s).