kernel_optimize_test/arch/powerpc/kernel/vdso32/gettimeofday.S
Benjamin Herrenschmidt 5d66da3d71 [PATCH] powerpc: Make the vDSO functions set error code (#2)
The vDSO functions should have the same calling convention as a syscall.
Unfortunately, they currently don't set the cr0.so bit which is used to
indicate an error. This patch makes them clear this bit unconditionally
since all functions currently succeed. The syscall fallback done by some
of them will eventually override this if the syscall fails.

This also changes the symbol version of all vdso exports to make sure
glibc can differenciate between old and fixed calls for existing ones
like __kernel_gettimeofday.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
2005-11-16 14:05:11 +11:00

324 lines
7.2 KiB
ArmAsm

/*
* Userland implementation of gettimeofday() for 32 bits processes in a
* ppc64 kernel for use in the vDSO
*
* Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org,
* IBM Corp.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/config.h>
#include <asm/processor.h>
#include <asm/ppc_asm.h>
#include <asm/vdso.h>
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
.text
/*
* Exact prototype of gettimeofday
*
* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz);
*
*/
V_FUNCTION_BEGIN(__kernel_gettimeofday)
.cfi_startproc
mflr r12
.cfi_register lr,r12
mr r10,r3 /* r10 saves tv */
mr r11,r4 /* r11 saves tz */
bl __get_datapage@local /* get data page */
mr r9, r3 /* datapage ptr in r9 */
bl __do_get_xsec@local /* get xsec from tb & kernel */
bne- 2f /* out of line -> do syscall */
/* seconds are xsec >> 20 */
rlwinm r5,r4,12,20,31
rlwimi r5,r3,12,0,19
stw r5,TVAL32_TV_SEC(r10)
/* get remaining xsec and convert to usec. we scale
* up remaining xsec by 12 bits and get the top 32 bits
* of the multiplication
*/
rlwinm r5,r4,12,0,19
lis r6,1000000@h
ori r6,r6,1000000@l
mulhwu r5,r5,r6
stw r5,TVAL32_TV_USEC(r10)
cmpli cr0,r11,0 /* check if tz is NULL */
beq 1f
lwz r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
lwz r5,CFG_TZ_DSTTIME(r9)
stw r4,TZONE_TZ_MINWEST(r11)
stw r5,TZONE_TZ_DSTTIME(r11)
1: mtlr r12
crclr cr0*4+so
li r3,0
blr
2:
mtlr r12
mr r3,r10
mr r4,r11
li r0,__NR_gettimeofday
sc
blr
.cfi_endproc
V_FUNCTION_END(__kernel_gettimeofday)
/*
* Exact prototype of clock_gettime()
*
* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp);
*
*/
V_FUNCTION_BEGIN(__kernel_clock_gettime)
.cfi_startproc
/* Check for supported clock IDs */
cmpli cr0,r3,CLOCK_REALTIME
cmpli cr1,r3,CLOCK_MONOTONIC
cror cr0*4+eq,cr0*4+eq,cr1*4+eq
bne cr0,99f
mflr r12 /* r12 saves lr */
.cfi_register lr,r12
mr r10,r3 /* r10 saves id */
mr r11,r4 /* r11 saves tp */
bl __get_datapage@local /* get data page */
mr r9,r3 /* datapage ptr in r9 */
beq cr1,50f /* if monotonic -> jump there */
/*
* CLOCK_REALTIME
*/
bl __do_get_xsec@local /* get xsec from tb & kernel */
bne- 98f /* out of line -> do syscall */
/* seconds are xsec >> 20 */
rlwinm r5,r4,12,20,31
rlwimi r5,r3,12,0,19
stw r5,TSPC32_TV_SEC(r11)
/* get remaining xsec and convert to nsec. we scale
* up remaining xsec by 12 bits and get the top 32 bits
* of the multiplication, then we multiply by 1000
*/
rlwinm r5,r4,12,0,19
lis r6,1000000@h
ori r6,r6,1000000@l
mulhwu r5,r5,r6
mulli r5,r5,1000
stw r5,TSPC32_TV_NSEC(r11)
mtlr r12
crclr cr0*4+so
li r3,0
blr
/*
* CLOCK_MONOTONIC
*/
50: bl __do_get_xsec@local /* get xsec from tb & kernel */
bne- 98f /* out of line -> do syscall */
/* seconds are xsec >> 20 */
rlwinm r6,r4,12,20,31
rlwimi r6,r3,12,0,19
/* get remaining xsec and convert to nsec. we scale
* up remaining xsec by 12 bits and get the top 32 bits
* of the multiplication, then we multiply by 1000
*/
rlwinm r7,r4,12,0,19
lis r5,1000000@h
ori r5,r5,1000000@l
mulhwu r7,r7,r5
mulli r7,r7,1000
/* now we must fixup using wall to monotonic. We need to snapshot
* that value and do the counter trick again. Fortunately, we still
* have the counter value in r8 that was returned by __do_get_xsec.
* At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5
* can be used
*/
lwz r3,WTOM_CLOCK_SEC(r9)
lwz r4,WTOM_CLOCK_NSEC(r9)
/* We now have our result in r3,r4. We create a fake dependency
* on that result and re-check the counter
*/
or r5,r4,r3
xor r0,r5,r5
add r9,r9,r0
#ifdef CONFIG_PPC64
lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9)
#else
lwz r0,(CFG_TB_UPDATE_COUNT)(r9)
#endif
cmpl cr0,r8,r0 /* check if updated */
bne- 50b
/* Calculate and store result. Note that this mimmics the C code,
* which may cause funny results if nsec goes negative... is that
* possible at all ?
*/
add r3,r3,r6
add r4,r4,r7
lis r5,NSEC_PER_SEC@h
ori r5,r5,NSEC_PER_SEC@l
cmpl cr0,r4,r5
cmpli cr1,r4,0
blt 1f
subf r4,r5,r4
addi r3,r3,1
1: bge cr1,1f
addi r3,r3,-1
add r4,r4,r5
1: stw r3,TSPC32_TV_SEC(r11)
stw r4,TSPC32_TV_NSEC(r11)
mtlr r12
crclr cr0*4+so
li r3,0
blr
/*
* syscall fallback
*/
98:
mtlr r12
mr r3,r10
mr r4,r11
99:
li r0,__NR_clock_gettime
sc
blr
.cfi_endproc
V_FUNCTION_END(__kernel_clock_gettime)
/*
* Exact prototype of clock_getres()
*
* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res);
*
*/
V_FUNCTION_BEGIN(__kernel_clock_getres)
.cfi_startproc
/* Check for supported clock IDs */
cmpwi cr0,r3,CLOCK_REALTIME
cmpwi cr1,r3,CLOCK_MONOTONIC
cror cr0*4+eq,cr0*4+eq,cr1*4+eq
bne cr0,99f
li r3,0
cmpli cr0,r4,0
crclr cr0*4+so
beqlr
lis r5,CLOCK_REALTIME_RES@h
ori r5,r5,CLOCK_REALTIME_RES@l
stw r3,TSPC32_TV_SEC(r4)
stw r5,TSPC32_TV_NSEC(r4)
blr
/*
* syscall fallback
*/
99:
li r0,__NR_clock_getres
sc
blr
.cfi_endproc
V_FUNCTION_END(__kernel_clock_getres)
/*
* This is the core of gettimeofday() & friends, it returns the xsec
* value in r3 & r4 and expects the datapage ptr (non clobbered)
* in r9. clobbers r0,r4,r5,r6,r7,r8.
* When returning, r8 contains the counter value that can be reused
* by the monotonic clock implementation
*/
__do_get_xsec:
.cfi_startproc
/* Check for update count & load values. We use the low
* order 32 bits of the update count
*/
#ifdef CONFIG_PPC64
1: lwz r8,(CFG_TB_UPDATE_COUNT+4)(r9)
#else
1: lwz r8,(CFG_TB_UPDATE_COUNT)(r9)
#endif
andi. r0,r8,1 /* pending update ? loop */
bne- 1b
xor r0,r8,r8 /* create dependency */
add r9,r9,r0
/* Load orig stamp (offset to TB) */
lwz r5,CFG_TB_ORIG_STAMP(r9)
lwz r6,(CFG_TB_ORIG_STAMP+4)(r9)
/* Get a stable TB value */
2: mftbu r3
mftbl r4
mftbu r0
cmpl cr0,r3,r0
bne- 2b
/* Substract tb orig stamp. If the high part is non-zero, we jump to
* the slow path which call the syscall.
* If it's ok, then we have our 32 bits tb_ticks value in r7
*/
subfc r7,r6,r4
subfe. r0,r5,r3
bne- 3f
/* Load scale factor & do multiplication */
lwz r5,CFG_TB_TO_XS(r9) /* load values */
lwz r6,(CFG_TB_TO_XS+4)(r9)
mulhwu r4,r7,r5
mulhwu r6,r7,r6
mullw r0,r7,r5
addc r6,r6,r0
/* At this point, we have the scaled xsec value in r4 + XER:CA
* we load & add the stamp since epoch
*/
lwz r5,CFG_STAMP_XSEC(r9)
lwz r6,(CFG_STAMP_XSEC+4)(r9)
adde r4,r4,r6
addze r3,r5
/* We now have our result in r3,r4. We create a fake dependency
* on that result and re-check the counter
*/
or r6,r4,r3
xor r0,r6,r6
add r9,r9,r0
#ifdef CONFIG_PPC64
lwz r0,(CFG_TB_UPDATE_COUNT+4)(r9)
#else
lwz r0,(CFG_TB_UPDATE_COUNT)(r9)
#endif
cmpl cr0,r8,r0 /* check if updated */
bne- 1b
/* Warning ! The caller expects CR:EQ to be set to indicate a
* successful calculation (so it won't fallback to the syscall
* method). We have overriden that CR bit in the counter check,
* but fortunately, the loop exit condition _is_ CR:EQ set, so
* we can exit safely here. If you change this code, be careful
* of that side effect.
*/
3: blr
.cfi_endproc