Merge branch 'linux-2.6' into for-2.6.24

11 files changed, 123 insertions, 62 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 06b24b3aa37..993369ee94d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -24,7 +24,6 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/profile.h>
-#include <linux/signalfd.h>
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/kthread.h>
@@ -86,14 +85,6 @@ static void __exit_signal(struct task_struct *tsk)
 	sighand = rcu_dereference(tsk->sighand);
 	spin_lock(&sighand->siglock);
 
-	/*
-	 * Notify that this sighand has been detached. This must
-	 * be called with the tsk->sighand lock held. Also, this
-	 * access tsk->sighand internally, so it must be called
-	 * before tsk->sighand is reset.
-	 */
-	signalfd_detach_locked(tsk);
-
 	posix_cpu_timers_exit(tsk);
 	if (atomic_dec_and_test(&sig->count))
 		posix_cpu_timers_exit_group(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 7332e236d36..33f12f48684 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1438,7 +1438,7 @@ static void sighand_ctor(void *data, struct kmem_cache *cachep,
 	struct sighand_struct *sighand = data;
 
 	spin_lock_init(&sighand->siglock);
-	INIT_LIST_HEAD(&sighand->signalfd_list);
+	init_waitqueue_head(&sighand->signalfd_wqh);
 }
 
 void __init proc_caches_init(void)
diff --git a/kernel/futex.c b/kernel/futex.c
index e8935b195e8..fcc94e7b408 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1943,9 +1943,10 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
 void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
-	struct robust_list __user *entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	struct robust_list __user *entry, *next_entry, *pending;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
 	unsigned long futex_offset;
+	int rc;
 
 	/*
 	 * Fetch the list head (which was registered earlier, via
@@ -1965,12 +1966,14 @@ void exit_robust_list(struct task_struct *curr)
 	if (fetch_robust_entry(&pending, &head->list_op_pending, &pip))
 		return;
 
-	if (pending)
-		handle_futex_death((void __user *)pending + futex_offset,
-				   curr, pip);
-
+	next_entry = NULL;	/* avoid warning with gcc */
 	while (entry != &head->list) {
 		/*
+		 * Fetch the next entry in the list before calling
+		 * handle_futex_death:
+		 */
+		rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi);
+		/*
 		 * A pending lock might already be on the list, so
 		 * don't process it twice:
 		 */
@@ -1978,11 +1981,10 @@ void exit_robust_list(struct task_struct *curr)
 			if (handle_futex_death((void __user *)entry + futex_offset,
 						curr, pi))
 				return;
-		/*
-		 * Fetch the next entry in the list:
-		 */
-		if (fetch_robust_entry(&entry, &entry->next, &pi))
+		if (rc)
 			return;
+		entry = next_entry;
+		pi = next_pi;
 		/*
 		 * Avoid excessively long or circular lists:
 		 */
@@ -1991,6 +1993,10 @@ void exit_robust_list(struct task_struct *curr)
 
 		cond_resched();
 	}
+
+	if (pending)
+		handle_futex_death((void __user *)pending + futex_offset,
+				   curr, pip);
 }
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 7e52eb051f2..2c2e2954b71 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -38,10 +38,11 @@ fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
 void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
-	struct robust_list __user *entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	compat_uptr_t uentry, upending;
+	struct robust_list __user *entry, *next_entry, *pending;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
+	int rc;
 
 	/*
 	 * Fetch the list head (which was registered earlier, via
@@ -61,11 +62,16 @@ void compat_exit_robust_list(struct task_struct *curr)
 	if (fetch_robust_entry(&upending, &pending,
 			       &head->list_op_pending, &pip))
 		return;
-	if (pending)
-		handle_futex_death((void __user *)pending + futex_offset, curr, pip);
 
+	next_entry = NULL;	/* avoid warning with gcc */
 	while (entry != (struct robust_list __user *) &head->list) {
 		/*
+		 * Fetch the next entry in the list before calling
+		 * handle_futex_death:
+		 */
+		rc = fetch_robust_entry(&next_uentry, &next_entry,
+			(compat_uptr_t __user *)&entry->next, &next_pi);
+		/*
 		 * A pending lock might already be on the list, so
 		 * dont process it twice:
 		 */
@@ -74,12 +80,11 @@ void compat_exit_robust_list(struct task_struct *curr)
 						curr, pi))
 				return;
 
-		/*
-		 * Fetch the next entry in the list:
-		 */
-		if (fetch_robust_entry(&uentry, &entry,
-				       (compat_uptr_t __user *)&entry->next, &pi))
+		if (rc)
 			return;
+		uentry = next_uentry;
+		entry = next_entry;
+		pi = next_pi;
 		/*
 		 * Avoid excessively long or circular lists:
 		 */
@@ -88,6 +93,9 @@ void compat_exit_robust_list(struct task_struct *curr)
 
 		cond_resched();
 	}
+	if (pending)
+		handle_futex_death((void __user *)pending + futex_offset,
+				   curr, pip);
 }
 
 asmlinkage long
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index c8580a1e687..14b0e10dc95 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -110,7 +110,7 @@ config SUSPEND
 
 config HIBERNATION_UP_POSSIBLE
 	bool
-	depends on X86 || PPC64_SWSUSP || FRV || PPC32
+	depends on X86 || PPC64_SWSUSP || PPC32
 	depends on !SMP
 	default y
 
diff --git a/kernel/sched.c b/kernel/sched.c
index deeb1f8e0c3..6107a0cd632 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1682,6 +1682,11 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 
 	p->prio = effective_prio(p);
 
+	if (rt_prio(p->prio))
+		p->sched_class = &rt_sched_class;
+	else
+		p->sched_class = &fair_sched_class;
+
 	if (!p->sched_class->task_new || !sysctl_sched_child_runs_first ||
 			(clone_flags & CLONE_VM) || task_cpu(p) != this_cpu ||
 			!current->se.on_rq) {
@@ -4550,10 +4555,7 @@ asmlinkage long sys_sched_yield(void)
 	struct rq *rq = this_rq_lock();
 
 	schedstat_inc(rq, yld_cnt);
-	if (unlikely(rq->nr_running == 1))
-		schedstat_inc(rq, yld_act_empty);
-	else
-		current->sched_class->yield_task(rq, current);
+	current->sched_class->yield_task(rq, current);
 
 	/*
 	 * Since we are going to call schedule() anyway, there's
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 892616bf2c7..67c67a87146 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -43,6 +43,14 @@ unsigned int sysctl_sched_latency __read_mostly = 20000000ULL;
 unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
 
 /*
+ * sys_sched_yield() compat mode
+ *
+ * This option switches the agressive yield implementation of the
+ * old scheduler back on.
+ */
+unsigned int __read_mostly sysctl_sched_compat_yield;
+
+/*
  * SCHED_BATCH wake-up granularity.
  * (default: 25 msec, units: nanoseconds)
  *
@@ -631,6 +639,16 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 		se->block_start = 0;
 		se->sum_sleep_runtime += delta;
+
+		/*
+		 * Blocking time is in units of nanosecs, so shift by 20 to
+		 * get a milliseconds-range estimation of the amount of
+		 * time that the task spent sleeping:
+		 */
+		if (unlikely(prof_on == SLEEP_PROFILING)) {
+			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
+				     delta >> 20);
+		}
 	}
 #endif
 }
@@ -897,19 +915,62 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 }
 
 /*
- * sched_yield() support is very simple - we dequeue and enqueue
+ * sched_yield() support is very simple - we dequeue and enqueue.
+ *
+ * If compat_yield is turned on then we requeue to the end of the tree.
  */
 static void yield_task_fair(struct rq *rq, struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
+	struct sched_entity *rightmost, *se = &p->se;
+	struct rb_node *parent;
 
-	__update_rq_clock(rq);
 	/*
-	 * Dequeue and enqueue the task to update its
-	 * position within the tree:
+	 * Are we the only task in the tree?
+	 */
+	if (unlikely(cfs_rq->nr_running == 1))
+		return;
+
+	if (likely(!sysctl_sched_compat_yield)) {
+		__update_rq_clock(rq);
+		/*
+		 * Dequeue and enqueue the task to update its
+		 * position within the tree:
+		 */
+		dequeue_entity(cfs_rq, &p->se, 0);
+		enqueue_entity(cfs_rq, &p->se, 0);
+
+		return;
+	}
+	/*
+	 * Find the rightmost entry in the rbtree:
+	 */
+	do {
+		parent = *link;
+		link = &parent->rb_right;
+	} while (*link);
+
+	rightmost = rb_entry(parent, struct sched_entity, run_node);
+	/*
+	 * Already in the rightmost position?
 	 */
-	dequeue_entity(cfs_rq, &p->se, 0);
-	enqueue_entity(cfs_rq, &p->se, 0);
+	if (unlikely(rightmost == se))
+		return;
+
+	/*
+	 * Minimally necessary key value to be last in the tree:
+	 */
+	se->fair_key = rightmost->fair_key + 1;
+
+	if (cfs_rq->rb_leftmost == &se->run_node)
+		cfs_rq->rb_leftmost = rb_next(&se->run_node);
+	/*
+	 * Relink the task to the rightmost position:
+	 */
+	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
+	rb_link_node(&se->run_node, parent, link);
+	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
 /*
diff --git a/kernel/signal.c b/kernel/signal.c
index 3169bed0b4d..9fb91a32edd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -378,8 +378,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 	/* We only dequeue private signals from ourselves, we don't let
 	 * signalfd steal them
 	 */
-	if (likely(tsk == current))
-		signr = __dequeue_signal(&tsk->pending, mask, info);
+	signr = __dequeue_signal(&tsk->pending, mask, info);
 	if (!signr) {
 		signr = __dequeue_signal(&tsk->signal->shared_pending,
 					 mask, info);
@@ -407,8 +406,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 			}
 		}
 	}
-	if (likely(tsk == current))
-		recalc_sigpending();
+	recalc_sigpending();
 	if (signr && unlikely(sig_kernel_stop(signr))) {
 		/*
 		 * Set a marker that we have dequeued a stop signal.  Our
@@ -425,7 +423,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 		if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
 			tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
 	}
-	if (signr && likely(tsk == current) &&
+	if (signr &&
 	     ((info->si_code & __SI_MASK) == __SI_TIMER) &&
 	     info->si_sys_private){
 		/*
diff --git a/kernel/sys.c b/kernel/sys.c
index 1b33b05d346..8ae2e636eb1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -32,6 +32,7 @@
 #include <linux/getcpu.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/seccomp.h>
+#include <linux/cpu.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -878,6 +879,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
+	disable_nonboot_cpus();
 	sysdev_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	machine_power_off();
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6ace893c17c..53a456ebf6d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -303,6 +303,14 @@ static ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_compat_yield",
+		.data		= &sysctl_sched_compat_yield,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.ctl_name	= CTL_UNNUMBERED,
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index aab881c86a1..0962e057766 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -382,23 +382,8 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
-	int cpu = smp_processor_id();
-
-	/*
-	 * If the CPU is marked for broadcast, enforce oneshot
-	 * broadcast mode. The jinxed VAIO does not resume otherwise.
-	 * No idea why it ends up in a lower C State during resume
-	 * without notifying the clock events layer.
-	 */
-	if (cpu_isset(cpu, tick_broadcast_mask))
-		cpu_set(cpu, tick_broadcast_oneshot_mask);
-
 	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-
-	if(!cpus_empty(tick_broadcast_oneshot_mask))
-		tick_broadcast_set_event(ktime_get(), 1);
-
-	return cpu_isset(cpu, tick_broadcast_oneshot_mask);
+	return 0;
 }
 
 /*