From: Anton Blanchard <anton@samba.org>
To: benh@kernel.crashing.org
Cc: npiggin@suse.de, linuxppc-dev@ozlabs.org
Subject: [PATCH 1/6] powerpc: Use lwarx hint in spinlocks
Date: Wed, 10 Feb 2010 21:57:28 +1100 [thread overview]
Message-ID: <20100210105728.GA3399@kryten> (raw)
Recent versions of the PowerPC architecture added a hint bit to the larx
instructions to differentiate between an atomic operation and a lock operation:
> 0 Other programs might attempt to modify the word in storage addressed by EA
> even if the subsequent Store Conditional succeeds.
>
> 1 Other programs will not attempt to modify the word in storage addressed by
> EA until the program that has acquired the lock performs a subsequent store
> releasing the lock.
To avoid a binutils dependency this patch create macros for the extended lwarx
format and uses it in the spinlock code. To test this change I used a simple
test case that acquires and releases a global pthread mutex:
pthread_mutex_lock(&mutex);
pthread_mutex_unlock(&mutex);
On a 32 core POWER6, running 32 test threads we spend almost all our time in
the futex spinlock code:
94.37% perf [kernel] [k] ._raw_spin_lock
|
|--99.95%-- ._raw_spin_lock
| |
| |--63.29%-- .futex_wake
| |
| |--36.64%-- .futex_wait_setup
Which is a good test for this patch. The results (in lock/unlock operations per
second) are:
before: 1538203 ops/sec
after: 2189219 ops/sec
An improvement of 42%
A 32 core POWER7 improves even more:
before: 1279529 ops/sec
after: 2282076 ops/sec
An improvement of 78%
Signed-off-by: Anton Blanchard <anton@samba.org>
---
v2: We do this only for 64bit until we can verify all 32bit CPUs.
Tested so far: 970 (thanks Ben), POWER5, POWER6, POWER7
Still to test: RS64, POWER3, POWER4
Index: powerpc.git/arch/powerpc/include/asm/ppc-opcode.h
===================================================================
--- powerpc.git.orig/arch/powerpc/include/asm/ppc-opcode.h 2010-02-10 15:28:58.453072362 +1100
+++ powerpc.git/arch/powerpc/include/asm/ppc-opcode.h 2010-02-10 15:33:08.963071793 +1100
@@ -24,6 +24,7 @@
#define PPC_INST_ISEL_MASK 0xfc00003e
#define PPC_INST_LSWI 0x7c0004aa
#define PPC_INST_LSWX 0x7c00042a
+#define PPC_INST_LWARX 0x7c000029
#define PPC_INST_LWSYNC 0x7c2004ac
#define PPC_INST_LXVD2X 0x7c000698
#define PPC_INST_MCRXR 0x7c000400
@@ -55,15 +56,28 @@
#define __PPC_RA(a) (((a) & 0x1f) << 16)
#define __PPC_RB(b) (((b) & 0x1f) << 11)
#define __PPC_RS(s) (((s) & 0x1f) << 21)
+#define __PPC_RT(s) __PPC_RS(s)
#define __PPC_XS(s) ((((s) & 0x1f) << 21) | (((s) & 0x20) >> 5))
#define __PPC_T_TLB(t) (((t) & 0x3) << 21)
#define __PPC_WC(w) (((w) & 0x3) << 21)
+/*
+ * Only use the larx hint bit on 64bit CPUs. Once we verify it doesn't have
+ * any side effects on all 32bit processors, we can do this all the time.
+ */
+#ifdef CONFIG_PPC64
+#define __PPC_EH(eh) (((eh) & 0x1) << 0)
+#else
+#define __PPC_EH(eh) 0
+#endif
/* Deal with instructions that older assemblers aren't aware of */
#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \
__PPC_RA(a) | __PPC_RB(b))
#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_INST_DCBZL | \
__PPC_RA(a) | __PPC_RB(b))
+#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \
+ __PPC_RT(t) | __PPC_RA(a) | \
+ __PPC_RB(b) | __PPC_EH(eh))
#define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \
__PPC_RB(b))
#define PPC_RFCI stringify_in_c(.long PPC_INST_RFCI)
Index: powerpc.git/arch/powerpc/include/asm/spinlock.h
===================================================================
--- powerpc.git.orig/arch/powerpc/include/asm/spinlock.h 2010-02-10 15:28:58.473072327 +1100
+++ powerpc.git/arch/powerpc/include/asm/spinlock.h 2010-02-10 15:29:29.454322618 +1100
@@ -27,6 +27,7 @@
#endif
#include <asm/asm-compat.h>
#include <asm/synch.h>
+#include <asm/ppc-opcode.h>
#define arch_spin_is_locked(x) ((x)->slock != 0)
@@ -60,7 +61,7 @@ static inline unsigned long __arch_spin_
token = LOCK_TOKEN;
__asm__ __volatile__(
-"1: lwarx %0,0,%2\n\
+"1: " PPC_LWARX(%0,0,%2,1) "\n\
cmpwi 0,%0,0\n\
bne- 2f\n\
stwcx. %1,0,%2\n\
@@ -186,7 +187,7 @@ static inline long __arch_read_trylock(a
long tmp;
__asm__ __volatile__(
-"1: lwarx %0,0,%1\n"
+"1: " PPC_LWARX(%0,0,%1,1) "\n"
__DO_SIGN_EXTEND
" addic. %0,%0,1\n\
ble- 2f\n"
@@ -211,7 +212,7 @@ static inline long __arch_write_trylock(
token = WRLOCK_TOKEN;
__asm__ __volatile__(
-"1: lwarx %0,0,%2\n\
+"1: " PPC_LWARX(%0,0,%2,1) "\n\
cmpwi 0,%0,0\n\
bne- 2f\n"
PPC405_ERR77(0,%1)
next reply other threads:[~2010-02-10 10:57 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-10 10:57 Anton Blanchard [this message]
2010-02-10 11:02 ` [PATCH 2/6] powerpc: Use lwarx/ldarx hint in bit locks Anton Blanchard
2010-02-10 11:03 ` [PATCH 3/6] powerpc: Convert open coded native hashtable bit lock Anton Blanchard
2010-02-10 11:04 ` [PATCH 4/6] powerpc: Rename LWSYNC_ON_SMP to PPC_RELEASE_BARRIER, ISYNC_ON_SMP to PPC_ACQUIRE_BARRIER Anton Blanchard
2010-02-10 11:07 ` [PATCH 5/6] powerpc: Fix lwsync patching code on 64bit Anton Blanchard
2010-02-10 11:10 ` [PATCH 6/6] powerpc: Use lwsync for acquire barrier if CPU supports it Anton Blanchard
2010-02-11 7:09 ` Nick Piggin
2010-02-17 9:43 ` Anton Blanchard
2010-02-17 10:41 ` Nick Piggin
2010-02-17 12:12 ` Benjamin Herrenschmidt
2010-02-16 4:22 ` Olof Johansson
2010-02-16 4:19 ` Benjamin Herrenschmidt
2010-02-16 6:07 ` Olof Johansson
2010-03-19 1:08 ` [PATCH 4/6] powerpc: Rename LWSYNC_ON_SMP to PPC_RELEASE_BARRIER, ISYNC_ON_SMP to PPC_ACQUIRE_BARRIER Nick Piggin
2010-03-19 1:36 ` Benjamin Herrenschmidt
2010-02-11 6:56 ` [PATCH 1/6] powerpc: Use lwarx hint in spinlocks Nick Piggin
2010-02-17 9:37 ` Anton Blanchard
2010-02-17 10:22 ` Nick Piggin
2010-02-16 4:16 ` Olof Johansson
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=20100210105728.GA3399@kryten \
--to=anton@samba.org \
--cc=benh@kernel.crashing.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=npiggin@suse.de \
/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).