Menu
▾
▴
[LV-kern-commit] CVS: kernel-2.4/arch/i386/lib strstr.c,NONE,1.1 Makefile,1.1.1.1,1.2 delay.c,1.1.1.1,1.2 mmx.c,1.1.1.2,1.2 usercopy.c,1.1.1.1,1.2 putuser.S,1.1.1.1,NONE
|
From: Andy P. <at...@us...> - 2002-04-10 18:37:43
|
Update of /cvsroot/linux-vax/kernel-2.4/arch/i386/lib
In directory usw-pr-cvs1:/tmp/cvs-serv10929/i386/lib
Modified Files:
Makefile delay.c mmx.c usercopy.c
Added Files:
strstr.c
Removed Files:
putuser.S
Log Message:
synch 2.4.15 commit 35
--- NEW FILE ---
#include <linux/string.h>
char * strstr(const char * cs,const char * ct)
{
int d0, d1;
register char * __res;
__asm__ __volatile__(
"movl %6,%%edi\n\t"
"repne\n\t"
"scasb\n\t"
"notl %%ecx\n\t"
"decl %%ecx\n\t" /* NOTE! This also sets Z if searchstring='' */
"movl %%ecx,%%edx\n"
"1:\tmovl %6,%%edi\n\t"
"movl %%esi,%%eax\n\t"
"movl %%edx,%%ecx\n\t"
"repe\n\t"
"cmpsb\n\t"
"je 2f\n\t" /* also works for empty string, see above */
"xchgl %%eax,%%esi\n\t"
"incl %%esi\n\t"
"cmpb $0,-1(%%eax)\n\t"
"jne 1b\n\t"
"xorl %%eax,%%eax\n\t"
"2:"
:"=a" (__res), "=&c" (d0), "=&S" (d1)
:"0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
:"dx", "di");
return __res;
}
Index: Makefile
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/lib/Makefile,v
retrieving revision 1.1.1.1
retrieving revision 1.2
diff -u -r1.1.1.1 -r1.2
--- Makefile 14 Jan 2001 19:20:53 -0000 1.1.1.1
+++ Makefile 10 Apr 2002 14:23:21 -0000 1.2
@@ -8,10 +8,11 @@
L_TARGET = lib.a
obj-y = checksum.o old-checksum.o delay.o \
- usercopy.o getuser.o putuser.o iodebug.o \
- memcpy.o
+ usercopy.o getuser.o \
+ memcpy.o strstr.o
obj-$(CONFIG_X86_USE_3DNOW) += mmx.o
obj-$(CONFIG_HAVE_DEC_LOCK) += dec_and_lock.o
+obj-$(CONFIG_DEBUG_IOVIRT) += iodebug.o
include $(TOPDIR)/Rules.make
Index: delay.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/lib/delay.c,v
retrieving revision 1.1.1.1
retrieving revision 1.2
diff -u -r1.1.1.1 -r1.2
--- delay.c 14 Jan 2001 19:20:53 -0000 1.1.1.1
+++ delay.c 10 Apr 2002 14:23:21 -0000 1.2
@@ -13,6 +13,7 @@
#include <linux/config.h>
#include <linux/sched.h>
#include <linux/delay.h>
+#include <asm/processor.h>
#include <asm/delay.h>
#ifdef CONFIG_SMP
@@ -34,9 +35,9 @@
rdtscl(bclock);
do
{
+ rep_nop();
rdtscl(now);
- }
- while((now-bclock) < loops);
+ } while ((now-bclock) < loops);
}
/*
@@ -58,7 +59,7 @@
void __delay(unsigned long loops)
{
- if(x86_udelay_tsc)
+ if (x86_udelay_tsc)
__rdtsc_delay(loops);
else
__loop_delay(loops);
Index: mmx.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/lib/mmx.c,v
retrieving revision 1.1.1.2
retrieving revision 1.2
diff -u -r1.1.1.2 -r1.2
--- mmx.c 25 Feb 2001 23:15:16 -0000 1.1.1.2
+++ mmx.c 10 Apr 2002 14:23:21 -0000 1.2
@@ -1,8 +1,11 @@
+#include <linux/config.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <asm/i387.h>
+#include <asm/hardirq.h>
+
/*
* MMX 3DNow! library helper functions
@@ -25,8 +28,14 @@
void *_mmx_memcpy(void *to, const void *from, size_t len)
{
- void *p=to;
- int i= len >> 6; /* len/64 */
+ void *p;
+ int i;
+
+ if (in_interrupt())
+ return __memcpy(to, from, len);
+
+ p = to;
+ i = len >> 6; /* len/64 */
kernel_fpu_begin();
@@ -88,6 +97,13 @@
return p;
}
+#ifdef CONFIG_MK7
+
+/*
+ * The K7 has streaming cache bypass load/store. The Cyrix III, K6 and
+ * other MMX using processors do not.
+ */
+
static void fast_clear_page(void *page)
{
int i;
@@ -147,7 +163,7 @@
".previous"
: : "r" (from) );
- for(i=0; i<4096/64; i++)
+ for(i=0; i<(4096-320)/64; i++)
{
__asm__ __volatile__ (
"1: prefetch 320(%0)\n"
@@ -179,6 +195,29 @@
from+=64;
to+=64;
}
+ for(i=(4096-320)/64; i<4096/64; i++)
+ {
+ __asm__ __volatile__ (
+ "2: movq (%0), %%mm0\n"
+ " movntq %%mm0, (%1)\n"
+ " movq 8(%0), %%mm1\n"
+ " movntq %%mm1, 8(%1)\n"
+ " movq 16(%0), %%mm2\n"
+ " movntq %%mm2, 16(%1)\n"
+ " movq 24(%0), %%mm3\n"
+ " movntq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm4\n"
+ " movntq %%mm4, 32(%1)\n"
+ " movq 40(%0), %%mm5\n"
+ " movntq %%mm5, 40(%1)\n"
+ " movq 48(%0), %%mm6\n"
+ " movntq %%mm6, 48(%1)\n"
+ " movq 56(%0), %%mm7\n"
+ " movntq %%mm7, 56(%1)\n"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
/* since movntq is weakly-ordered, a "sfence" is needed to become
* ordered again.
*/
@@ -187,6 +226,110 @@
);
kernel_fpu_end();
}
+
+#else
+
+/*
+ * Generic MMX implementation without K7 specific streaming
+ */
+
+static void fast_clear_page(void *page)
+{
+ int i;
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ " pxor %%mm0, %%mm0\n" : :
+ );
+
+ for(i=0;i<4096/128;i++)
+ {
+ __asm__ __volatile__ (
+ " movq %%mm0, (%0)\n"
+ " movq %%mm0, 8(%0)\n"
+ " movq %%mm0, 16(%0)\n"
+ " movq %%mm0, 24(%0)\n"
+ " movq %%mm0, 32(%0)\n"
+ " movq %%mm0, 40(%0)\n"
+ " movq %%mm0, 48(%0)\n"
+ " movq %%mm0, 56(%0)\n"
+ " movq %%mm0, 64(%0)\n"
+ " movq %%mm0, 72(%0)\n"
+ " movq %%mm0, 80(%0)\n"
+ " movq %%mm0, 88(%0)\n"
+ " movq %%mm0, 96(%0)\n"
+ " movq %%mm0, 104(%0)\n"
+ " movq %%mm0, 112(%0)\n"
+ " movq %%mm0, 120(%0)\n"
+ : : "r" (page) : "memory");
+ page+=128;
+ }
+
+ kernel_fpu_end();
+}
+
+static void fast_copy_page(void *to, void *from)
+{
+ int i;
+
+
+ kernel_fpu_begin();
+
+ __asm__ __volatile__ (
+ "1: prefetch (%0)\n"
+ " prefetch 64(%0)\n"
+ " prefetch 128(%0)\n"
+ " prefetch 192(%0)\n"
+ " prefetch 256(%0)\n"
+ "2: \n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x1AEB, 1b\n" /* jmp on 26 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from) );
+
+ for(i=0; i<4096/64; i++)
+ {
+ __asm__ __volatile__ (
+ "1: prefetch 320(%0)\n"
+ "2: movq (%0), %%mm0\n"
+ " movq 8(%0), %%mm1\n"
+ " movq 16(%0), %%mm2\n"
+ " movq 24(%0), %%mm3\n"
+ " movq %%mm0, (%1)\n"
+ " movq %%mm1, 8(%1)\n"
+ " movq %%mm2, 16(%1)\n"
+ " movq %%mm3, 24(%1)\n"
+ " movq 32(%0), %%mm0\n"
+ " movq 40(%0), %%mm1\n"
+ " movq 48(%0), %%mm2\n"
+ " movq 56(%0), %%mm3\n"
+ " movq %%mm0, 32(%1)\n"
+ " movq %%mm1, 40(%1)\n"
+ " movq %%mm2, 48(%1)\n"
+ " movq %%mm3, 56(%1)\n"
+ ".section .fixup, \"ax\"\n"
+ "3: movw $0x05EB, 1b\n" /* jmp on 5 bytes */
+ " jmp 2b\n"
+ ".previous\n"
+ ".section __ex_table,\"a\"\n"
+ " .align 4\n"
+ " .long 1b, 3b\n"
+ ".previous"
+ : : "r" (from), "r" (to) : "memory");
+ from+=64;
+ to+=64;
+ }
+ kernel_fpu_end();
+}
+
+
+#endif
/*
* Favour MMX for page clear and copy.
Index: usercopy.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/lib/usercopy.c,v
retrieving revision 1.1.1.1
retrieving revision 1.2
diff -u -r1.1.1.1 -r1.2
--- usercopy.c 14 Jan 2001 19:20:54 -0000 1.1.1.1
+++ usercopy.c 10 Apr 2002 14:23:21 -0000 1.2
@@ -34,6 +34,8 @@
else
mmx_copy_user_zeroing(to, from, n);
}
+ else
+ memset(to, 0, n);
return n;
}
@@ -42,6 +44,7 @@
unsigned long
__generic_copy_to_user(void *to, const void *from, unsigned long n)
{
+ prefetch(from);
if (access_ok(VERIFY_WRITE, to, n))
__copy_user(to,from,n);
return n;
@@ -50,8 +53,11 @@
unsigned long
__generic_copy_from_user(void *to, const void *from, unsigned long n)
{
+ prefetchw(to);
if (access_ok(VERIFY_READ, from, n))
__copy_user_zeroing(to,from,n);
+ else
+ memset(to, 0, n);
return n;
}
@@ -159,6 +165,8 @@
unsigned long res, tmp;
__asm__ __volatile__(
+ " testl %0, %0\n"
+ " jz 3f\n"
" andl %0,%%ecx\n"
"0: repne; scasb\n"
" setne %%al\n"
@@ -167,6 +175,8 @@
"1:\n"
".section .fixup,\"ax\"\n"
"2: xorl %%eax,%%eax\n"
+ " jmp 1b\n"
+ "3: movb $1,%%al\n"
" jmp 1b\n"
".previous\n"
".section __ex_table,\"a\"\n"
--- putuser.S DELETED ---
|
