[git pull] scheduler fixes

From: Ingo Molnar
Date: Tue Nov 18 2008 - 09:17:49 EST


Linus,

Please pull the latest sched-fixes-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus

Thanks,

Ingo

------------------>
Adrian Knoth (1):
sched: correct sched-rt-group.txt pathname in init/Kconfig

Ingo Molnar (1):
sched: fix kernel warning on /proc/sched_debug access

Li Zefan (1):
cpuset: fix regression when failed to generate sched domains

Oleg Nesterov (1):
sched, signals: fix the racy usage of ->signal in account_group_xxx/run_posix_cpu_timers


init/Kconfig | 2 +-
kernel/cpuset.c | 12 ++++++++----
kernel/posix-cpu-timers.c | 7 +++++--
kernel/sched.c | 13 +++++++------
kernel/sched_debug.c | 5 +++--
kernel/sched_stats.h | 15 +++++++++++----
6 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 86b00c5..2f850d8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -354,7 +354,7 @@ config RT_GROUP_SCHED
setting below. If enabled, it will also make it impossible to
schedule realtime tasks for non-root users until you allocate
realtime bandwidth for them.
- See Documentation/sched-rt-group.txt for more information.
+ See Documentation/scheduler/sched-rt-group.txt for more information.

choice
depends on GROUP_SCHED
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e00526..81fc679 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -587,7 +587,6 @@ static int generate_sched_domains(cpumask_t **domains,
int ndoms; /* number of sched domains in result */
int nslot; /* next empty doms[] cpumask_t slot */

- ndoms = 0;
doms = NULL;
dattr = NULL;
csa = NULL;
@@ -674,10 +673,8 @@ restart:
* Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
*/
doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
- if (!doms) {
- ndoms = 0;
+ if (!doms)
goto done;
- }

/*
* The rest of the code, including the scheduler, can deal with
@@ -732,6 +729,13 @@ restart:
done:
kfree(csa);

+ /*
+ * Fallback to the default domain if kmalloc() failed.
+ * See comments in partition_sched_domains().
+ */
+ if (doms == NULL)
+ ndoms = 1;
+
*domains = doms;
*attributes = dattr;
return ndoms;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 153dcb2..895337b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1308,9 +1308,10 @@ static inline int task_cputime_expired(const struct task_cputime *sample,
*/
static inline int fastpath_timer_check(struct task_struct *tsk)
{
- struct signal_struct *sig = tsk->signal;
+ struct signal_struct *sig;

- if (unlikely(!sig))
+ /* tsk == current, ensure it is safe to use ->signal/sighand */
+ if (unlikely(tsk->exit_state))
return 0;

if (!task_cputime_zero(&tsk->cputime_expires)) {
@@ -1323,6 +1324,8 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
return 1;
}
+
+ sig = tsk->signal;
if (!task_cputime_zero(&sig->cputime_expires)) {
struct task_cputime group_sample;

diff --git a/kernel/sched.c b/kernel/sched.c
index c94baf2..9b1e793 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7789,13 +7789,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
*
* The passed in 'doms_new' should be kmalloc'd. This routine takes
* ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL,
- * and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms', it also forces the domains to be rebuilt.
+ * failed the kmalloc call, then it can pass in doms_new == NULL &&
+ * ndoms_new == 1, and partition_sched_domains() will fallback to
+ * the single partition 'fallback_doms', it also forces the domains
+ * to be rebuilt.
*
- * If doms_new==NULL it will be replaced with cpu_online_map.
- * ndoms_new==0 is a special case for destroying existing domains.
- * It will not create the default domain.
+ * If doms_new == NULL it will be replaced with cpu_online_map.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
*
* Call with hotplug lock held
*/
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 48ecc51..26ed8e3 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -423,10 +423,11 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
#undef __P

{
+ unsigned int this_cpu = raw_smp_processor_id();
u64 t0, t1;

- t0 = sched_clock();
- t1 = sched_clock();
+ t0 = cpu_clock(this_cpu);
+ t1 = cpu_clock(this_cpu);
SEQ_printf(m, "%-35s:%21Ld\n",
"clock-delta", (long long)(t1-t0));
}
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index ee71bec..7dbf72a 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -298,9 +298,11 @@ static inline void account_group_user_time(struct task_struct *tsk,
{
struct signal_struct *sig;

- sig = tsk->signal;
- if (unlikely(!sig))
+ /* tsk == current, ensure it is safe to use ->signal */
+ if (unlikely(tsk->exit_state))
return;
+
+ sig = tsk->signal;
if (sig->cputime.totals) {
struct task_cputime *times;

@@ -325,9 +327,11 @@ static inline void account_group_system_time(struct task_struct *tsk,
{
struct signal_struct *sig;

- sig = tsk->signal;
- if (unlikely(!sig))
+ /* tsk == current, ensure it is safe to use ->signal */
+ if (unlikely(tsk->exit_state))
return;
+
+ sig = tsk->signal;
if (sig->cputime.totals) {
struct task_cputime *times;

@@ -353,8 +357,11 @@ static inline void account_group_exec_runtime(struct task_struct *tsk,
struct signal_struct *sig;

sig = tsk->signal;
+ /* see __exit_signal()->task_rq_unlock_wait() */
+ barrier();
if (unlikely(!sig))
return;
+
if (sig->cputime.totals) {
struct task_cputime *times;

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/