From: Chuck Ebbert <76306.1226@compuserve.com>
To: linux-kernel <linux-kernel@vger.kernel.org>
Cc: Andrew Morton <akpm@osdl.org>, Linus Torvalds <torvalds@osdl.org>
Subject: [patch 2.6.13-rc3a] i386: inline restore_fpu
Date: Thu, 21 Jul 2005 23:06:22 -0400 [thread overview]
Message-ID: <200507212309_MC3-1-A534-95EF@compuserve.com> (raw)
This patch makes restore_fpu() an inline. When L1/L2 cache are saturated
it makes a measurable difference.
Results from profiling Volanomark follow. Sample rate was 2000 samples/sec
(HZ = 250, profile multiplier = 8) on a dual-processor Pentium II Xeon.
Before:
10680 restore_fpu 333.7500
8351 device_not_available 203.6829
3823 math_state_restore 59.7344
-----
22854
After:
12534 math_state_restore 130.5625
8354 device_not_available 203.7561
-----
20888
Patch is "obviously correct" and cuts 9% of the overhead. Please apply.
Next step should be to physically place math_state_restore() after
device_not_available(). Would such a patch be accepted? (Yes it
would be ugly and require linker script changes.)
Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com>
Index: 2.6.13-rc3a/arch/i386/kernel/i387.c
===================================================================
--- 2.6.13-rc3a.orig/arch/i386/kernel/i387.c
+++ 2.6.13-rc3a/arch/i386/kernel/i387.c
@@ -82,17 +82,6 @@
}
EXPORT_SYMBOL_GPL(kernel_fpu_begin);
-void restore_fpu( struct task_struct *tsk )
-{
- if ( cpu_has_fxsr ) {
- asm volatile( "fxrstor %0"
- : : "m" (tsk->thread.i387.fxsave) );
- } else {
- asm volatile( "frstor %0"
- : : "m" (tsk->thread.i387.fsave) );
- }
-}
-
/*
* FPU tag word conversions.
*/
Index: 2.6.13-rc3a/include/asm-i386/i387.h
===================================================================
--- 2.6.13-rc3a.orig/include/asm-i386/i387.h
+++ 2.6.13-rc3a/include/asm-i386/i387.h
@@ -22,11 +22,20 @@
/*
* FPU lazy state save handling...
*/
-extern void restore_fpu( struct task_struct *tsk );
-
extern void kernel_fpu_begin(void);
#define kernel_fpu_end() do { stts(); preempt_enable(); } while(0)
+static inline void restore_fpu( struct task_struct *tsk )
+{
+ if ( cpu_has_fxsr ) {
+ asm volatile( "fxrstor %0"
+ : : "m" (tsk->thread.i387.fxsave) );
+ } else {
+ asm volatile( "frstor %0"
+ : : "m" (tsk->thread.i387.fsave) );
+ }
+}
+
/*
* These must be called with preempt disabled
*/
__
Chuck
next reply other threads:[~2005-07-22 3:09 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-07-22 3:06 Chuck Ebbert [this message]
2005-07-22 3:27 ` Andrew Morton
2005-07-22 5:22 ` Linus Torvalds
2005-07-22 11:23 ` Arjan van de Ven
2005-07-22 8:14 ` Adrian Bunk
2005-07-22 18:13 ` Linus Torvalds
2005-07-25 19:26 ` Bill Davidsen
2005-07-22 23:19 ` Linus Torvalds
2005-07-22 9:58 Chuck Ebbert
2005-07-23 7:09 Chuck Ebbert
2005-07-23 17:38 ` Linus Torvalds
2005-07-23 17:46 ` Arjan van de Ven
2005-07-23 18:02 ` Linus Torvalds
2005-07-23 7:09 Chuck Ebbert
2005-07-23 17:33 ` Linus Torvalds
[not found] <200507212309_MC3-1-A534-95EF@compuserve.com.suse.lists.linux.kernel>
[not found] ` <20050722132756.578acca7.akpm@osdl.org.suse.lists.linux.kernel>
2005-07-23 15:35 ` Andi Kleen
2005-07-24 12:56 Kenneth Parrish
2005-07-25 2:34 Kenneth Parrish
2005-07-26 21:23 Chuck Ebbert
2005-07-26 21:23 Chuck Ebbert
2005-07-26 21:47 ` Linus Torvalds
2005-07-27 1:40 linux
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=200507212309_MC3-1-A534-95EF@compuserve.com \
--to=76306.1226@compuserve.com \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@osdl.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
all inboxes | Powered by JetHome®