mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: tip-bot for John Stultz <johnstul@us.ibm.com>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com,
	johnstul@us.ibm.com, oleg@redhat.com, tglx@linutronix.de,
	jolsa@redhat.com
Subject: [tip:timers/clocksource] x86: Fix vtime/file timestamp inconsistencies
Date: Tue, 27 Jul 2010 10:45:50 GMT	[thread overview]
Message-ID: <tip-8c73626ab28527b7eb7f3061c027fbfe530c488c@git.kernel.org> (raw)
In-Reply-To: <1279068988-21864-2-git-send-email-johnstul@us.ibm.com>

Commit-ID:  8c73626ab28527b7eb7f3061c027fbfe530c488c
Gitweb:     http://git.kernel.org/tip/8c73626ab28527b7eb7f3061c027fbfe530c488c
Author:     John Stultz <johnstul@us.ibm.com>
AuthorDate: Tue, 13 Jul 2010 17:56:18 -0700
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Tue, 27 Jul 2010 12:40:53 +0200

x86: Fix vtime/file timestamp inconsistencies

Due to vtime calling vgettimeofday(), its possible that an application
could call  time();create("stuff",O_RDRW);  only to see the file's
creation timestamp to be before the value returned by time.

A similar way to reproduce the issue is to compare the vsyscall time()
with the syscall time(), and observe ordering issues.

The modified test case from Oleg Nesterov below can illustrate this:

int main(void)
{
	time_t sec1,sec2;
	do {
		sec1 = time(&sec2);
		sec2 = syscall(__NR_time, NULL);
	} while (sec1 <= sec2);

	printf("vtime: %d.000000\n", sec1);
	printf("time: %d.000000\n", sec2);
	return 0;
}

The proper fix is to make vtime use the same time value as
current_kernel_time() (which is exported via update_vsyscall) instead of
vgettime().

Thanks to Jiri Olsa for bringing up the issue and catching bugs in
earlier verisons of this fix.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
LKML-Reference: <1279068988-21864-2-git-send-email-johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/vsyscall_64.c |   11 ++++++++---
 1 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 1c0c6ab..dce0c3c 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -169,13 +169,18 @@ int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz)
  * unlikely */
 time_t __vsyscall(1) vtime(time_t *t)
 {
-	struct timeval tv;
+	unsigned seq;
 	time_t result;
 	if (unlikely(!__vsyscall_gtod_data.sysctl_enabled))
 		return time_syscall(t);
 
-	vgettimeofday(&tv, NULL);
-	result = tv.tv_sec;
+	do {
+		seq = read_seqbegin(&__vsyscall_gtod_data.lock);
+
+		result = __vsyscall_gtod_data.wall_time_sec;
+
+	} while (read_seqretry(&__vsyscall_gtod_data.lock, seq));
+
 	if (t)
 		*t = result;
 	return result;

      parent reply	other threads:[~2010-07-27 10:46 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-07-14  0:56 [PATCH 00/11] -tip Timekeeping changes for 2.6.36 John Stultz
2010-07-14  0:56 ` [PATCH 01/11] x86: Fix vtime/file timestamp inconsistencies John Stultz
2010-07-14  0:56   ` [PATCH 02/11] Implement timespec_add John Stultz
2010-07-14  0:56     ` [PATCH 03/11] time: Kill off CONFIG_GENERIC_TIME John Stultz
2010-07-14  0:56       ` [PATCH 04/11] powerpc: Simplify update_vsyscall John Stultz
2010-07-14  0:56         ` [PATCH 05/11] powerpc: Cleanup xtime usage John Stultz
2010-07-14  0:56           ` [PATCH 06/11] Fix update_vsyscall to provide wall_to_monotonic offset John Stultz
2010-07-14  0:56             ` [PATCH 07/11] Convert um to use read_persistent_clock John Stultz
2010-07-14  0:56               ` [PATCH 08/11] Cleanup hrtimer.c's direct access to wall_to_monotonic John Stultz
2010-07-14  0:56                 ` [PATCH 09/11] Make xtime and wall_to_monotonic static John Stultz
2010-07-14  0:56                   ` [PATCH 10/11] Convert common x86 clocksources to use clocksource_register_hz/khz John Stultz
2010-07-14  0:56                     ` [PATCH 11/11] Add __clocksource_updatefreq_hz/khz methods John Stultz
2010-07-27 10:49                       ` [tip:timers/clocksource] clocksource: " tip-bot for John Stultz
2010-07-27 10:48                     ` [tip:timers/clocksource] x86: Convert common clocksources to use clocksource_register_hz/khz tip-bot for John Stultz
2010-07-27 10:48                   ` [tip:timers/clocksource] timekeeping: Make xtime and wall_to_monotonic static tip-bot for John Stultz
2010-07-27 10:48                 ` [tip:timers/clocksource] hrtimer: Cleanup direct access to wall_to_monotonic tip-bot for John Stultz
2010-07-27 10:47               ` [tip:timers/clocksource] um: Convert to use read_persistent_clock tip-bot for John Stultz
2010-07-27 10:47             ` [tip:timers/clocksource] timkeeping: Fix update_vsyscall to provide wall_to_monotonic offset tip-bot for John Stultz
2010-07-27 10:47           ` [tip:timers/clocksource] powerpc: Cleanup xtime usage tip-bot for John Stultz
2010-07-27 10:46         ` [tip:timers/clocksource] powerpc: Simplify update_vsyscall tip-bot for John Stultz
2010-07-27 23:41         ` [PATCH 04/11] " Paul Mackerras
2010-07-28  1:33           ` john stultz
2010-07-27 10:46       ` [tip:timers/clocksource] time: Kill off CONFIG_GENERIC_TIME tip-bot for John Stultz
2010-07-27 10:46     ` [tip:timers/clocksource] time: Implement timespec_add tip-bot for John Stultz
2010-07-14  2:40   ` [PATCH 01/11] x86: Fix vtime/file timestamp inconsistencies KOSAKI Motohiro
2010-07-14 16:19     ` john stultz
2010-07-15  1:51       ` KOSAKI Motohiro
2010-07-15  2:46         ` john stultz
2010-07-15  4:41           ` KOSAKI Motohiro
2010-07-15 19:30             ` john stultz
2010-07-15  2:51         ` john stultz
2010-07-15  4:41           ` KOSAKI Motohiro
2010-07-27 10:45   ` tip-bot for John Stultz [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=tip-8c73626ab28527b7eb7f3061c027fbfe530c488c@git.kernel.org \
    --to=johnstul@us.ibm.com \
    --cc=hpa@zytor.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=oleg@redhat.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome