linux/arch/x86/vdso/vclock_gettime.c
Andy Lutomirski 0d7b8547fb x86-64: Remove kernel.vsyscall64 sysctl
It's unnecessary overhead in code that's supposed to be highly
optimized.  Removing it allows us to remove one of the two
syscall instructions in the vsyscall page.

The only sensible use for it is for UML users, and it doesn't
fully address inconsistent vsyscall results on UML.  The real
fix for UML is to stop using vsyscalls entirely.

Signed-off-by: Andy Lutomirski <luto@mit.edu>
Cc: Jesper Juhl <jj@chaosbits.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Jan Beulich <JBeulich@novell.com>
Cc: richard -rw- weinberger <richard.weinberger@gmail.com>
Cc: Mikael Pettersson <mikpe@it.uu.se>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Louis Rilling <Louis.Rilling@kerlabs.com>
Cc: Valdis.Kletnieks@vt.edu
Cc: pageexec@freemail.hu
Link: http://lkml.kernel.org/r/973ae803fe76f712da4b2740e66dccf452d3b1e4.1307292171.git.luto@mit.edu
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-06-05 21:30:33 +02:00

179 lines
4.5 KiB
C

/*
* Copyright 2006 Andi Kleen, SUSE Labs.
* Subject to the GNU Public License, v.2
*
* Fast user context implementation of clock_gettime, gettimeofday, and time.
*
* The code should have no internal unresolved relocations.
* Check with readelf after changing.
* Also alternative() doesn't work.
*/
/* Disable profiling for userspace code: */
#define DISABLE_BRANCH_PROFILING
#include <linux/kernel.h>
#include <linux/posix-timers.h>
#include <linux/time.h>
#include <linux/string.h>
#include <asm/vsyscall.h>
#include <asm/vgtod.h>
#include <asm/timex.h>
#include <asm/hpet.h>
#include <asm/unistd.h>
#include <asm/io.h>
#define gtod (&VVAR(vsyscall_gtod_data))
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
long ret;
asm("syscall" : "=a" (ret) :
"0" (__NR_clock_gettime),"D" (clock), "S" (ts) : "memory");
return ret;
}
notrace static inline long vgetns(void)
{
long v;
cycles_t (*vread)(void);
vread = gtod->clock.vread;
v = (vread() - gtod->clock.cycle_last) & gtod->clock.mask;
return (v * gtod->clock.mult) >> gtod->clock.shift;
}
notrace static noinline int do_realtime(struct timespec *ts)
{
unsigned long seq, ns;
do {
seq = read_seqbegin(&gtod->lock);
ts->tv_sec = gtod->wall_time_sec;
ts->tv_nsec = gtod->wall_time_nsec;
ns = vgetns();
} while (unlikely(read_seqretry(&gtod->lock, seq)));
timespec_add_ns(ts, ns);
return 0;
}
notrace static noinline int do_monotonic(struct timespec *ts)
{
unsigned long seq, ns, secs;
do {
seq = read_seqbegin(&gtod->lock);
secs = gtod->wall_time_sec;
ns = gtod->wall_time_nsec + vgetns();
secs += gtod->wall_to_monotonic.tv_sec;
ns += gtod->wall_to_monotonic.tv_nsec;
} while (unlikely(read_seqretry(&gtod->lock, seq)));
/* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec
* are all guaranteed to be nonnegative.
*/
while (ns >= NSEC_PER_SEC) {
ns -= NSEC_PER_SEC;
++secs;
}
ts->tv_sec = secs;
ts->tv_nsec = ns;
return 0;
}
notrace static noinline int do_realtime_coarse(struct timespec *ts)
{
unsigned long seq;
do {
seq = read_seqbegin(&gtod->lock);
ts->tv_sec = gtod->wall_time_coarse.tv_sec;
ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
} while (unlikely(read_seqretry(&gtod->lock, seq)));
return 0;
}
notrace static noinline int do_monotonic_coarse(struct timespec *ts)
{
unsigned long seq, ns, secs;
do {
seq = read_seqbegin(&gtod->lock);
secs = gtod->wall_time_coarse.tv_sec;
ns = gtod->wall_time_coarse.tv_nsec;
secs += gtod->wall_to_monotonic.tv_sec;
ns += gtod->wall_to_monotonic.tv_nsec;
} while (unlikely(read_seqretry(&gtod->lock, seq)));
/* wall_time_nsec and wall_to_monotonic.tv_nsec are
* guaranteed to be between 0 and NSEC_PER_SEC.
*/
if (ns >= NSEC_PER_SEC) {
ns -= NSEC_PER_SEC;
++secs;
}
ts->tv_sec = secs;
ts->tv_nsec = ns;
return 0;
}
notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
{
switch (clock) {
case CLOCK_REALTIME:
if (likely(gtod->clock.vread))
return do_realtime(ts);
break;
case CLOCK_MONOTONIC:
if (likely(gtod->clock.vread))
return do_monotonic(ts);
break;
case CLOCK_REALTIME_COARSE:
return do_realtime_coarse(ts);
case CLOCK_MONOTONIC_COARSE:
return do_monotonic_coarse(ts);
}
return vdso_fallback_gettime(clock, ts);
}
int clock_gettime(clockid_t, struct timespec *)
__attribute__((weak, alias("__vdso_clock_gettime")));
notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
{
long ret;
if (likely(gtod->clock.vread)) {
if (likely(tv != NULL)) {
BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
offsetof(struct timespec, tv_nsec) ||
sizeof(*tv) != sizeof(struct timespec));
do_realtime((struct timespec *)tv);
tv->tv_usec /= 1000;
}
if (unlikely(tz != NULL)) {
/* Avoid memcpy. Some old compilers fail to inline it */
tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
tz->tz_dsttime = gtod->sys_tz.tz_dsttime;
}
return 0;
}
asm("syscall" : "=a" (ret) :
"0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
return ret;
}
int gettimeofday(struct timeval *, struct timezone *)
__attribute__((weak, alias("__vdso_gettimeofday")));
/*
* This will break when the xtime seconds get inaccurate, but that is
* unlikely
*/
notrace time_t __vdso_time(time_t *t)
{
/* This is atomic on x86_64 so we don't need any locks. */
time_t result = ACCESS_ONCE(VVAR(vsyscall_gtod_data).wall_time_sec);
if (t)
*t = result;
return result;
}
int time(time_t *t)
__attribute__((weak, alias("__vdso_time")));