aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cpu.c4
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/futex_compat.c4
-rw-r--r--kernel/irq/manage.c11
-rw-r--r--kernel/kmod.c2
-rw-r--r--kernel/power/Kconfig41
-rw-r--r--kernel/ptrace.c1
-rw-r--r--kernel/sched.c16
-rw-r--r--kernel/sched_debug.c1
-rw-r--r--kernel/sched_fair.c45
-rw-r--r--kernel/signal.c19
-rw-r--r--kernel/sys.c3
-rw-r--r--kernel/time/ntp.c2
-rw-r--r--kernel/user_namespace.c1
14 files changed, 98 insertions, 54 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 181ae708602..38033db8d8e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -273,7 +273,7 @@ int __cpuinit cpu_up(unsigned int cpu)
return err;
}
-#ifdef CONFIG_SUSPEND_SMP
+#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_t frozen_cpus;
int disable_nonboot_cpus(void)
@@ -334,4 +334,4 @@ void enable_nonboot_cpus(void)
out:
mutex_unlock(&cpu_add_remove_lock);
}
-#endif
+#endif /* CONFIG_PM_SLEEP_SMP */
diff --git a/kernel/exit.c b/kernel/exit.c
index 9578c1ae19c..06b24b3aa37 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -975,6 +975,7 @@ fastcall NORET_TYPE void do_exit(long code)
if (unlikely(tsk->audit_context))
audit_free(tsk);
+ tsk->exit_code = code;
taskstats_exit(tsk, group_dead);
exit_mm(tsk);
@@ -996,7 +997,6 @@ fastcall NORET_TYPE void do_exit(long code)
if (tsk->binfmt)
module_put(tsk->binfmt->module);
- tsk->exit_code = code;
proc_exit_connector(tsk);
exit_task_namespaces(tsk);
exit_notify(tsk);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f7921360efa..7e52eb051f2 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -61,10 +61,10 @@ void compat_exit_robust_list(struct task_struct *curr)
if (fetch_robust_entry(&upending, &pending,
&head->list_op_pending, &pip))
return;
- if (upending)
+ if (pending)
handle_futex_death((void __user *)pending + futex_offset, curr, pip);
- while (compat_ptr(uentry) != &head->list) {
+ while (entry != (struct robust_list __user *) &head->list) {
/*
* A pending lock might already be on the list, so
* dont process it twice:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 853aefbd184..7230d914eaa 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -547,14 +547,11 @@ int request_irq(unsigned int irq, irq_handler_t handler,
* We do this before actually registering it, to make sure that
* a 'real' IRQ doesn't run in parallel with our fake
*/
- if (irqflags & IRQF_DISABLED) {
- unsigned long flags;
+ unsigned long flags;
- local_irq_save(flags);
- handler(irq, dev_id);
- local_irq_restore(flags);
- } else
- handler(irq, dev_id);
+ local_irq_save(flags);
+ handler(irq, dev_id);
+ local_irq_restore(flags);
}
#endif
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9809cc1f33d..c6a4f8aebeb 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -505,7 +505,7 @@ int call_usermodehelper_pipe(char *path, char **argv, char **envp,
if (ret < 0)
goto out;
- return call_usermodehelper_exec(sub_info, 1);
+ return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
out:
call_usermodehelper_freeinfo(sub_info);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 412859f8d94..c8580a1e687 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -72,15 +72,10 @@ config PM_TRACE
CAUTION: this option will cause your machine's real-time clock to be
set to an invalid time after a resume.
-config SUSPEND_SMP_POSSIBLE
- bool
- depends on (X86 && !X86_VOYAGER) || (PPC64 && (PPC_PSERIES || PPC_PMAC))
- depends on SMP
- default y
-
-config SUSPEND_SMP
+config PM_SLEEP_SMP
bool
- depends on SUSPEND_SMP_POSSIBLE && PM_SLEEP
+ depends on SUSPEND_SMP_POSSIBLE || HIBERNATION_SMP_POSSIBLE
+ depends on PM_SLEEP
select HOTPLUG_CPU
default y
@@ -89,20 +84,46 @@ config PM_SLEEP
depends on SUSPEND || HIBERNATION
default y
+config SUSPEND_UP_POSSIBLE
+ bool
+ depends on (X86 && !X86_VOYAGER) || PPC || ARM || BLACKFIN || MIPS \
+ || SUPERH || FRV
+ depends on !SMP
+ default y
+
+config SUSPEND_SMP_POSSIBLE
+ bool
+ depends on (X86 && !X86_VOYAGER) \
+ || (PPC && (PPC_PSERIES || PPC_PMAC)) || ARM
+ depends on SMP
+ default y
+
config SUSPEND
bool "Suspend to RAM and standby"
depends on PM
- depends on !SMP || SUSPEND_SMP_POSSIBLE
+ depends on SUSPEND_UP_POSSIBLE || SUSPEND_SMP_POSSIBLE
default y
---help---
Allow the system to enter sleep states in which main memory is
powered and thus its contents are preserved, such as the
suspend-to-RAM state (i.e. the ACPI S3 state).
+config HIBERNATION_UP_POSSIBLE
+ bool
+ depends on X86 || PPC64_SWSUSP || FRV || PPC32
+ depends on !SMP
+ default y
+
+config HIBERNATION_SMP_POSSIBLE
+ bool
+ depends on (X86 && !X86_VOYAGER) || PPC64_SWSUSP
+ depends on SMP
+ default y
+
config HIBERNATION
bool "Hibernation (aka 'suspend to disk')"
depends on PM && SWAP
- depends on ((X86 || PPC64_SWSUSP || FRV || PPC32) && !SMP) || SUSPEND_SMP_POSSIBLE
+ depends on HIBERNATION_UP_POSSIBLE || HIBERNATION_SMP_POSSIBLE
---help---
Enable the suspend to disk (STD) functionality, which is usually
called "hibernation" in user interfaces. STD checkpoints the
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 82a558b655d..3eca7a55f2e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -233,6 +233,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
/* Architecture-specific hardware disable .. */
ptrace_disable(child);
+ clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
write_lock_irq(&tasklist_lock);
/* protect against de_thread()->release_task() */
diff --git a/kernel/sched.c b/kernel/sched.c
index 9fe473a190d..deeb1f8e0c3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -668,7 +668,7 @@ static u64 div64_likely32(u64 divident, unsigned long divisor)
/*
* Shift right and round:
*/
-#define RSR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
@@ -684,10 +684,10 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
* Check whether we'd overflow the 64-bit multiplication:
*/
if (unlikely(tmp > WMULT_CONST))
- tmp = RSR(RSR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
+ tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
WMULT_SHIFT/2);
else
- tmp = RSR(tmp * lw->inv_weight, WMULT_SHIFT);
+ tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}
@@ -858,7 +858,6 @@ static void dec_nr_running(struct task_struct *p, struct rq *rq)
static void set_load_weight(struct task_struct *p)
{
- task_rq(p)->cfs.wait_runtime -= p->se.wait_runtime;
p->se.wait_runtime = 0;
if (task_has_rt_policy(p)) {
@@ -1587,6 +1586,7 @@ static void __sched_fork(struct task_struct *p)
p->se.wait_start_fair = 0;
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
+ p->se.prev_sum_exec_runtime = 0;
p->se.delta_exec = 0;
p->se.delta_fair_run = 0;
p->se.delta_fair_sleep = 0;
@@ -2511,7 +2511,7 @@ group_next:
* a think about bumping its value to force at least one task to be
* moved
*/
- if (*imbalance + SCHED_LOAD_SCALE_FUZZ < busiest_load_per_task) {
+ if (*imbalance < busiest_load_per_task) {
unsigned long tmp, pwr_now, pwr_move;
unsigned int imbn;
@@ -2563,10 +2563,8 @@ small_imbalance:
pwr_move /= SCHED_LOAD_SCALE;
/* Move if we gain throughput */
- if (pwr_move <= pwr_now)
- goto out_balanced;
-
- *imbalance = busiest_load_per_task;
+ if (pwr_move > pwr_now)
+ *imbalance = busiest_load_per_task;
}
return busiest;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index ab18f45f2ab..c3ee38bd342 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -283,4 +283,5 @@ void proc_sched_set_task(struct task_struct *p)
p->se.wait_runtime_overruns = p->se.wait_runtime_underruns = 0;
#endif
p->se.sum_exec_runtime = 0;
+ p->se.prev_sum_exec_runtime = 0;
}
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ee3771850aa..892616bf2c7 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -194,6 +194,8 @@ __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_add(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running++;
se->on_rq = 1;
+
+ schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
}
static inline void
@@ -205,6 +207,8 @@ __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_load_sub(&cfs_rq->load, se->load.weight);
cfs_rq->nr_running--;
se->on_rq = 0;
+
+ schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
}
static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
@@ -291,7 +295,7 @@ niced_granularity(struct sched_entity *curr, unsigned long granularity)
/*
* It will always fit into 'long':
*/
- return (long) (tmp >> WMULT_SHIFT);
+ return (long) (tmp >> (WMULT_SHIFT-NICE_0_SHIFT));
}
static inline void
@@ -354,7 +358,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
delta_fair = calc_delta_fair(delta_exec, lw);
delta_mine = calc_delta_mine(delta_exec, curr->load.weight, lw);
- if (cfs_rq->sleeper_bonus > sysctl_sched_latency) {
+ if (cfs_rq->sleeper_bonus > sysctl_sched_min_granularity) {
delta = min((u64)delta_mine, cfs_rq->sleeper_bonus);
delta = min(delta, (unsigned long)(
(long)sysctl_sched_runtime_limit - curr->wait_runtime));
@@ -489,6 +493,9 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
unsigned long delta_fair;
+ if (unlikely(!se->wait_start_fair))
+ return;
+
delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
(u64)(cfs_rq->fair_clock - se->wait_start_fair));
@@ -571,7 +578,6 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
prev_runtime = se->wait_runtime;
__add_wait_runtime(cfs_rq, se, delta_fair);
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
delta_fair = se->wait_runtime - prev_runtime;
/*
@@ -659,7 +665,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->block_start = rq_of(cfs_rq)->clock;
}
- cfs_rq->wait_runtime -= se->wait_runtime;
#endif
}
__dequeue_entity(cfs_rq, se);
@@ -673,11 +678,31 @@ __check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
struct sched_entity *curr, unsigned long granularity)
{
s64 __delta = curr->fair_key - se->fair_key;
+ unsigned long ideal_runtime, delta_exec;
+
+ /*
+ * ideal_runtime is compared against sum_exec_runtime, which is
+ * walltime, hence do not scale.
+ */
+ ideal_runtime = max(sysctl_sched_latency / cfs_rq->nr_running,
+ (unsigned long)sysctl_sched_min_granularity);
+
+ /*
+ * If we executed more than what the latency constraint suggests,
+ * reduce the rescheduling granularity. This way the total latency
+ * of how much a task is not scheduled converges to
+ * sysctl_sched_latency:
+ */
+ delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+ if (delta_exec > ideal_runtime)
+ granularity = 0;
/*
* Take scheduling granularity into account - do not
* preempt the current task unless the best task has
* a larger than sched_granularity fairness advantage:
+ *
+ * scale granularity as key space is in fair_clock.
*/
if (__delta > niced_granularity(curr, granularity))
resched_task(rq_of(cfs_rq)->curr);
@@ -696,6 +721,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
update_stats_wait_end(cfs_rq, se);
update_stats_curr_start(cfs_rq, se);
set_cfs_rq_curr(cfs_rq, se);
+ se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
@@ -1076,31 +1102,32 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr)
static void task_new_fair(struct rq *rq, struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
- struct sched_entity *se = &p->se;
+ struct sched_entity *se = &p->se, *curr = cfs_rq_curr(cfs_rq);
sched_info_queued(p);
+ update_curr(cfs_rq);
update_stats_enqueue(cfs_rq, se);
/*
* Child runs first: we let it run before the parent
* until it reschedules once. We set up the key so that
* it will preempt the parent:
*/
- p->se.fair_key = current->se.fair_key -
- niced_granularity(&rq->curr->se, sched_granularity(cfs_rq)) - 1;
+ se->fair_key = curr->fair_key -
+ niced_granularity(curr, sched_granularity(cfs_rq)) - 1;
/*
* The first wait is dominated by the child-runs-first logic,
* so do not credit it with that waiting time yet:
*/
if (sysctl_sched_features & SCHED_FEAT_SKIP_INITIAL)
- p->se.wait_start_fair = 0;
+ se->wait_start_fair = 0;
/*
* The statistical average of wait_runtime is about
* -granularity/2, so initialize the task with that:
*/
if (sysctl_sched_features & SCHED_FEAT_START_DEBIT)
- p->se.wait_runtime = -(sched_granularity(cfs_rq) / 2);
+ se->wait_runtime = -(sched_granularity(cfs_rq) / 2);
__enqueue_entity(cfs_rq, se);
}
diff --git a/kernel/signal.c b/kernel/signal.c
index ad63109e413..3169bed0b4d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1300,20 +1300,19 @@ struct sigqueue *sigqueue_alloc(void)
void sigqueue_free(struct sigqueue *q)
{
unsigned long flags;
+ spinlock_t *lock = &current->sighand->siglock;
+
BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
/*
* If the signal is still pending remove it from the
- * pending queue.
+ * pending queue. We must hold ->siglock while testing
+ * q->list to serialize with collect_signal().
*/
- if (unlikely(!list_empty(&q->list))) {
- spinlock_t *lock = &current->sighand->siglock;
- read_lock(&tasklist_lock);
- spin_lock_irqsave(lock, flags);
- if (!list_empty(&q->list))
- list_del_init(&q->list);
- spin_unlock_irqrestore(lock, flags);
- read_unlock(&tasklist_lock);
- }
+ spin_lock_irqsave(lock, flags);
+ if (!list_empty(&q->list))
+ list_del_init(&q->list);
+ spin_unlock_irqrestore(lock, flags);
+
q->flags &= ~SIGQUEUE_PREALLOC;
__sigqueue_free(q);
}
diff --git a/kernel/sys.c b/kernel/sys.c
index 449b81b98b3..1b33b05d346 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1442,7 +1442,6 @@ asmlinkage long sys_times(struct tms __user * tbuf)
* Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
* LBT 04.03.94
*/
-
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
@@ -1470,7 +1469,7 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
if (!thread_group_leader(p))
goto out;
- if (p->real_parent == group_leader) {
+ if (p->real_parent->tgid == group_leader->tgid) {
err = -EPERM;
if (task_session(p) != task_session(group_leader))
goto out;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index cd91237dbfe..de6a2d6b3eb 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -226,7 +226,7 @@ static void sync_cmos_clock(unsigned long dummy)
static void notify_cmos_timer(void)
{
- if (no_sync_cmos_clock)
+ if (!no_sync_cmos_clock)
mod_timer(&sync_cmos_timer, jiffies + 1);
}
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index d055d987850..85af9422ea6 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -81,6 +81,7 @@ void free_user_ns(struct kref *kref)
struct user_namespace *ns;
ns = container_of(kref, struct user_namespace, kref);
+ free_uid(ns->root_user);
kfree(ns);
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-04 05:05:32 +0000