From 0696b711e4be45fa104c12329f617beb29c03f78 Mon Sep 17 00:00:00 2001
From: Lin Ming <ming.m.lin@intel.com>
Date: Tue, 17 Nov 2009 13:49:50 +0800
Subject: [PATCH 1/3] timekeeping: Fix clock_gettime vsyscall time warp
Since commit 0a544198 "timekeeping: Move NTP adjusted clock multiplier
to struct timekeeper" the clock multiplier of vsyscall is updated with
the unmodified clock multiplier of the clock source and not with the
NTP adjusted multiplier of the timekeeper.
This causes user space observerable time warps:
new CLOCK-warp maximum: 120 nsecs, 00000025c337c537 -> 00000025c337c4bf
Add a new argument "mult" to update_vsyscall() and hand in the
timekeeping internal NTP adjusted multiplier.
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Cc: "Zhang Yanmin" <yanmin_zhang@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Tony Luck <tony.luck@intel.com>
LKML-Reference: <1258436990.17765.83.camel@minggr.sh.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/ia64/kernel/time.c | 4 ++--
arch/powerpc/kernel/time.c | 5 +++--
arch/s390/kernel/time.c | 3 ++-
arch/x86/kernel/vsyscall_64.c | 5 +++--
include/linux/clocksource.h | 6 ++++--
kernel/time/timekeeping.c | 6 +++---
6 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 4990495d75318..a35c661e5e89a 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -473,7 +473,7 @@ void update_vsyscall_tz(void)
{
}
-void update_vsyscall(struct timespec *wall, struct clocksource *c)
+void update_vsyscall(struct timespec *wall, struct clocksource *c, u32 mult)
{
unsigned long flags;
@@ -481,7 +481,7 @@ void update_vsyscall(struct timespec *wall, struct clocksource *c)
/* copy fsyscall clock data */
fsyscall_gtod_data.clk_mask = c->mask;
- fsyscall_gtod_data.clk_mult = c->mult;
+ fsyscall_gtod_data.clk_mult = mult;
fsyscall_gtod_data.clk_shift = c->shift;
fsyscall_gtod_data.clk_fsys_mmio = c->fsys_mmio;
fsyscall_gtod_data.clk_cycle_last = c->cycle_last;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index a136a11c490d0..39713312fbc73 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -828,7 +828,8 @@ static cycle_t timebase_read(struct clocksource *cs)
return (cycle_t)get_tb();
}
-void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
+ u32 mult)
{
u64 t2x, stamp_xsec;
@@ -841,7 +842,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
/* XXX this assumes clock->shift == 22 */
/* 4611686018 ~= 2^(20+64-22) / 1e9 */
- t2x = (u64) clock->mult * 4611686018ULL;
+ t2x = (u64) mult * 4611686018ULL;
stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
do_div(stamp_xsec, 1000000000);
stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 34162a0b2caa6..68e1ecf5ebabf 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -214,7 +214,8 @@ struct clocksource * __init clocksource_default_clock(void)
return &clocksource_tod;
}
-void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
+ u32 mult)
{
if (clock != &clocksource_tod)
return;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 8cb4974ff5990..62f39d79b7754 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -73,7 +73,8 @@ void update_vsyscall_tz(void)
write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
}
-void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
+ u32 mult)
{
unsigned long flags;
@@ -82,7 +83,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
vsyscall_gtod_data.clock.vread = clock->vread;
vsyscall_gtod_data.clock.cycle_last = clock->cycle_last;
vsyscall_gtod_data.clock.mask = clock->mask;
- vsyscall_gtod_data.clock.mult = clock->mult;
+ vsyscall_gtod_data.clock.mult = mult;
vsyscall_gtod_data.clock.shift = clock->shift;
vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec;
vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 83d2fbd81b93a..95e4995d99879 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -280,10 +280,12 @@ extern struct clocksource * __init __weak clocksource_default_clock(void);
extern void clocksource_mark_unstable(struct clocksource *cs);
#ifdef CONFIG_GENERIC_TIME_VSYSCALL
-extern void update_vsyscall(struct timespec *ts, struct clocksource *c);
+extern void
+update_vsyscall(struct timespec *ts, struct clocksource *c, u32 mult);
extern void update_vsyscall_tz(void);
#else
-static inline void update_vsyscall(struct timespec *ts, struct clocksource *c)
+static inline void
+update_vsyscall(struct timespec *ts, struct clocksource *c, u32 mult)
{
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index c3a4e2907eaaf..2a6d3e3e2c3ec 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -177,7 +177,7 @@ void timekeeping_leap_insert(int leapsecond)
{
xtime.tv_sec += leapsecond;
wall_to_monotonic.tv_sec -= leapsecond;
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
}
#ifdef CONFIG_GENERIC_TIME
@@ -337,7 +337,7 @@ int do_settimeofday(struct timespec *tv)
timekeeper.ntp_error = 0;
ntp_clear();
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -811,7 +811,7 @@ void update_wall_time(void)
update_xtime_cache(nsecs);
/* check to see if there is a new clocksource to use */
- update_vsyscall(&xtime, timekeeper.clock);
+ update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
}
/**
From 8747d793fc5c4d3e4decd41d55f6dc24498dd5f5 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 17 Nov 2009 14:14:12 -0800
Subject: [PATCH 2/3] itimers: Fix racy writes to cpu_itimer fields
incr_error and error fields of struct cpu_itimer are used when calculating
next timer tick in check_cpu_itimers() and should not be modified without
tsk->sighand->siglock taken.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
LKML-Reference: <1253802903-979-1-git-send-email-sgruszka@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/itimer.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/kernel/itimer.c b/kernel/itimer.c
index b03451ede5285..d802883153da6 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -146,6 +146,7 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
{
cputime_t cval, nval, cinterval, ninterval;
s64 ns_ninterval, ns_nval;
+ u32 error, incr_error;
struct cpu_itimer *it = &tsk->signal->it[clock_id];
nval = timeval_to_cputime(&value->it_value);
@@ -153,8 +154,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
ninterval = timeval_to_cputime(&value->it_interval);
ns_ninterval = timeval_to_ns(&value->it_interval);
- it->incr_error = cputime_sub_ns(ninterval, ns_ninterval);
- it->error = cputime_sub_ns(nval, ns_nval);
+ error = cputime_sub_ns(nval, ns_nval);
+ incr_error = cputime_sub_ns(ninterval, ns_ninterval);
spin_lock_irq(&tsk->sighand->siglock);
@@ -168,6 +169,8 @@ static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
}
it->expires = nval;
it->incr = ninterval;
+ it->error = error;
+ it->incr_error = incr_error;
trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
From 8629ea2eaba8ca0de2e38ce1b4a825e16255976e Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@intel.com>
Date: Thu, 3 Sep 2009 16:32:53 +0800
Subject: [PATCH 3/3] hrtimer: Fix /proc/timer_list regression
commit 507e1231 (timer stats: Optimize by adding quick check to avoid
function calls) introduced a regression in /proc/timer_list.
/proc/timer_list shows now
#0: <c27d46b0>, tick_sched_timer, S:01, <(null)>, /-1
instead of
#0: <c27d46b0>, tick_sched_timer, S:01, hrtimer_start, swapper/0
Revert the hrtimer quick check for now. The optimization needs more
thought, but this is neither 2.6.32-rc7 nor stable material.
[ tglx: - Removed unrelated changes from the original patch
- Prevent unneccesary call to timer_stats_update_stats
- massaged the changelog ]
Signed-off-by: Feng Tang <feng.tang@intel.com>
LKML-Reference: <alpine.LFD.2.00.0911181933540.24119@localhost.localdomain>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: stable@kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
include/linux/hrtimer.h | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index ff037f0b1b4e0..9bace4b9f4fe9 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -446,7 +446,7 @@ extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
{
- if (likely(!timer->start_site))
+ if (likely(!timer_stats_active))
return;
timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
timer->function, timer->start_comm, 0);
@@ -457,8 +457,6 @@ extern void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer,
static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
{
- if (likely(!timer_stats_active))
- return;
__timer_stats_hrtimer_set_start_info(timer, __builtin_return_address(0));
}