lkml.org 
[lkml]   [2001]   [Apr]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subjectrep nop question
The Intel documentation recommends that spinlocks should use

loop:
rep;nop;
cmp $0,lock_var
jne loop

ftp://download.intel.com/design/perftool/cbts/appnotes/sse2/w_spinlock.pdf

but the linux spinlock implementation uses

loop:
cmp $0, lock_var
rep; nop;
jne loop.

Why?
According to the Intel documentation, rep nop is a predefined delay that
slows down the cpu to the speed of the memory bus. The linux
implementation will delay again _after_ the lock was released.

What about the attached patch? It also adds 'rep;nop' into the rw
spinlock implementation.

It boots with my Pentium III, but the cpu doesn't support 'rep nop'
(i.e. returns immediately)

--
Manfred// $Header$
// Kernel Version:
// VERSION = 2
// PATCHLEVEL = 4
// SUBLEVEL = 3
// EXTRAVERSION = -ac3
--- 2.4/arch/i386/kernel/semaphore.c Sun Nov 19 02:31:25 2000
+++ build-2.4/arch/i386/kernel/semaphore.c Sat Apr 7 21:26:35 2001
@@ -430,7 +430,8 @@
.globl __write_lock_failed
__write_lock_failed:
" LOCK "addl $" RW_LOCK_BIAS_STR ",(%eax)
-1: cmpl $" RW_LOCK_BIAS_STR ",(%eax)
+1: rep; nop
+ cmpl $" RW_LOCK_BIAS_STR ",(%eax)
jne 1b

" LOCK "subl $" RW_LOCK_BIAS_STR ",(%eax)
@@ -442,7 +443,8 @@
.globl __read_lock_failed
__read_lock_failed:
lock ; incl (%eax)
-1: cmpl $1,(%eax)
+1: rep; nop
+ cmpl $1,(%eax)
js 1b

lock ; decl (%eax)
--- 2.4/include/asm-i386/spinlock.h Sat Apr 7 22:02:23 2001
+++ build-2.4/include/asm-i386/spinlock.h Sat Apr 7 22:01:43 2001
@@ -58,10 +58,10 @@
"js 2f\n" \
".section .text.lock,\"ax\"\n" \
"2:\t" \
- "cmpb $0,%0\n\t" \
"rep;nop\n\t" \
- "jle 2b\n\t" \
- "jmp 1b\n" \
+ "cmpb $0,%0\n\t" \
+ "jg 1b\n\t" \
+ "jmp 2b\n" \
".previous"

/*
\
 
 \ /
  Last update: 2005-03-22 13:24    [W:0.025 / U:0.240 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site