mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
fcb41a2030
On 04/18/2013 07:38 PM, Anton Blanchard wrote: > Since you are only reading one long you shouldn't need to check the > update count and loop, you will always see a consistent value. The > system call version of time() just does an unprotected load for example. Fixed. > With the above change and with Michael's comments covered (decent > changelog entry and Signed-off-by): > > Acked-by: Anton Blanchard <anton@samba.org> Thanks for the review, below the updated patch: From: Adhemerval Zanella <azanella@linux.vnet.ibm.com> This patch implement the time syscall as vDSO. The performance speedups are: Baseline PPC32: 380 nsec Baseline PPC64: 350 nsec vdso PPC32: 20 nsec vsdo PPC64: 20 nsec Tested on 64 bit build with both 32 bit and 64 bit userland. Acked-by: Anton Blanchard <anton@samba.org> Signed-off-by: Adhemerval Zanella <azanella@linux.vnet.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
292 lines
6.8 KiB
ArmAsm
292 lines
6.8 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 <asm/processor.h>
|
|
#include <asm/ppc_asm.h>
|
|
#include <asm/vdso.h>
|
|
#include <asm/asm-offsets.h>
|
|
#include <asm/unistd.h>
|
|
|
|
/* Offset for the low 32-bit part of a field of long type */
|
|
#ifdef CONFIG_PPC64
|
|
#define LOPART 4
|
|
#define TSPEC_TV_SEC TSPC64_TV_SEC+LOPART
|
|
#else
|
|
#define LOPART 0
|
|
#define TSPEC_TV_SEC TSPC32_TV_SEC
|
|
#endif
|
|
|
|
.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 */
|
|
cmplwi r10,0 /* check if tv is NULL */
|
|
beq 3f
|
|
lis r7,1000000@ha /* load up USEC_PER_SEC */
|
|
addi r7,r7,1000000@l /* so we get microseconds in r4 */
|
|
bl __do_get_tspec@local /* get sec/usec from tb & kernel */
|
|
stw r3,TVAL32_TV_SEC(r10)
|
|
stw r4,TVAL32_TV_USEC(r10)
|
|
|
|
3: cmplwi 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
|
|
.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 r11,r4 /* r11 saves tp */
|
|
bl __get_datapage@local /* get data page */
|
|
mr r9,r3 /* datapage ptr in r9 */
|
|
lis r7,NSEC_PER_SEC@h /* want nanoseconds */
|
|
ori r7,r7,NSEC_PER_SEC@l
|
|
50: bl __do_get_tspec@local /* get sec/nsec from tb & kernel */
|
|
bne cr1,80f /* not monotonic -> all done */
|
|
|
|
/*
|
|
* CLOCK_MONOTONIC
|
|
*/
|
|
|
|
/* 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, r3,r4 contain our sec/nsec values, r5 and r6
|
|
* can be used, r7 contains NSEC_PER_SEC.
|
|
*/
|
|
|
|
lwz r5,WTOM_CLOCK_SEC(r9)
|
|
lwz r6,WTOM_CLOCK_NSEC(r9)
|
|
|
|
/* We now have our offset in r5,r6. We create a fake dependency
|
|
* on that value and re-check the counter
|
|
*/
|
|
or r0,r6,r5
|
|
xor r0,r0,r0
|
|
add r9,r9,r0
|
|
lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
|
|
cmpl cr0,r8,r0 /* check if updated */
|
|
bne- 50b
|
|
|
|
/* Calculate and store result. Note that this mimics the C code,
|
|
* which may cause funny results if nsec goes negative... is that
|
|
* possible at all ?
|
|
*/
|
|
add r3,r3,r5
|
|
add r4,r4,r6
|
|
cmpw cr0,r4,r7
|
|
cmpwi cr1,r4,0
|
|
blt 1f
|
|
subf r4,r7,r4
|
|
addi r3,r3,1
|
|
1: bge cr1,80f
|
|
addi r3,r3,-1
|
|
add r4,r4,r7
|
|
|
|
80: stw r3,TSPC32_TV_SEC(r11)
|
|
stw r4,TSPC32_TV_NSEC(r11)
|
|
|
|
mtlr r12
|
|
crclr cr0*4+so
|
|
li r3,0
|
|
blr
|
|
|
|
/*
|
|
* syscall fallback
|
|
*/
|
|
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)
|
|
|
|
|
|
/*
|
|
* Exact prototype of time()
|
|
*
|
|
* time_t time(time *t);
|
|
*
|
|
*/
|
|
V_FUNCTION_BEGIN(__kernel_time)
|
|
.cfi_startproc
|
|
mflr r12
|
|
.cfi_register lr,r12
|
|
|
|
mr r11,r3 /* r11 holds t */
|
|
bl __get_datapage@local
|
|
mr r9, r3 /* datapage ptr in r9 */
|
|
|
|
lwz r3,STAMP_XTIME+TSPEC_TV_SEC(r9)
|
|
|
|
cmplwi r11,0 /* check if t is NULL */
|
|
beq 2f
|
|
stw r3,0(r11) /* store result at *t */
|
|
2: mtlr r12
|
|
crclr cr0*4+so
|
|
blr
|
|
.cfi_endproc
|
|
V_FUNCTION_END(__kernel_time)
|
|
|
|
/*
|
|
* This is the core of clock_gettime() and gettimeofday(),
|
|
* it returns the current time in r3 (seconds) and r4.
|
|
* On entry, r7 gives the resolution of r4, either USEC_PER_SEC
|
|
* or NSEC_PER_SEC, giving r4 in microseconds or nanoseconds.
|
|
* It expects the datapage ptr in r9 and doesn't clobber it.
|
|
* It clobbers r0, r5 and r6.
|
|
* On return, r8 contains the counter value that can be reused.
|
|
* This clobbers cr0 but not any other cr field.
|
|
*/
|
|
__do_get_tspec:
|
|
.cfi_startproc
|
|
/* Check for update count & load values. We use the low
|
|
* order 32 bits of the update count
|
|
*/
|
|
1: lwz r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
|
|
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
|
|
cmplw cr0,r3,r0
|
|
bne- 2b
|
|
|
|
/* Subtract tb orig stamp and shift left 12 bits.
|
|
*/
|
|
subfc r4,r6,r4
|
|
subfe r0,r5,r3
|
|
slwi r0,r0,12
|
|
rlwimi. r0,r4,12,20,31
|
|
slwi r4,r4,12
|
|
|
|
/*
|
|
* Load scale factor & do multiplication.
|
|
* We only use the high 32 bits of the tb_to_xs value.
|
|
* Even with a 1GHz timebase clock, the high 32 bits of
|
|
* tb_to_xs will be at least 4 million, so the error from
|
|
* ignoring the low 32 bits will be no more than 0.25ppm.
|
|
* The error will just make the clock run very very slightly
|
|
* slow until the next time the kernel updates the VDSO data,
|
|
* at which point the clock will catch up to the kernel's value,
|
|
* so there is no long-term error accumulation.
|
|
*/
|
|
lwz r5,CFG_TB_TO_XS(r9) /* load values */
|
|
mulhwu r4,r4,r5
|
|
li r3,0
|
|
|
|
beq+ 4f /* skip high part computation if 0 */
|
|
mulhwu r3,r0,r5
|
|
mullw r5,r0,r5
|
|
addc r4,r4,r5
|
|
addze r3,r3
|
|
4:
|
|
/* At this point, we have seconds since the xtime stamp
|
|
* as a 32.32 fixed-point number in r3 and r4.
|
|
* Load & add the xtime stamp.
|
|
*/
|
|
lwz r5,STAMP_XTIME+TSPEC_TV_SEC(r9)
|
|
lwz r6,STAMP_SEC_FRAC(r9)
|
|
addc r4,r4,r6
|
|
adde r3,r3,r5
|
|
|
|
/* We create a fake dependency on the result in r3/r4
|
|
* and re-check the counter
|
|
*/
|
|
or r6,r4,r3
|
|
xor r0,r6,r6
|
|
add r9,r9,r0
|
|
lwz r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
|
|
cmplw cr0,r8,r0 /* check if updated */
|
|
bne- 1b
|
|
|
|
mulhwu r4,r4,r7 /* convert to micro or nanoseconds */
|
|
|
|
blr
|
|
.cfi_endproc
|