Merge commit 'v2.6.30-rc5' into x86/mm

Merge reason: this branch was on a .30-rc2 base - sync it up with
              all the latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

18 files changed, 117 insertions, 74 deletions

diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 917ab952556..6e7351739a8 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -734,9 +734,6 @@ int audit_tag_tree(char *old, char *new)
 	dentry = dget(path.dentry);
 	path_put(&path);
 
-	if (dentry == tagged->mnt_root && dentry == mnt->mnt_root)
-		follow_up(&mnt, &dentry);
-
 	list_add_tail(&list, &tagged->mnt_list);
 
 	mutex_lock(&audit_filter_mutex);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a6fe71fd5d1..713098ee5a0 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1028,7 +1028,7 @@ static void audit_update_watch(struct audit_parent *parent,
 
 		if (audit_enabled) {
 			struct audit_buffer *ab;
-			ab = audit_log_start(NULL, GFP_KERNEL,
+			ab = audit_log_start(NULL, GFP_NOFS,
 				AUDIT_CONFIG_CHANGE);
 			audit_log_format(ab, "auid=%u ses=%u",
 				audit_get_loginuid(current),
@@ -1067,7 +1067,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 			e = container_of(r, struct audit_entry, rule);
 			if (audit_enabled) {
 				struct audit_buffer *ab;
-				ab = audit_log_start(NULL, GFP_KERNEL,
+				ab = audit_log_start(NULL, GFP_NOFS,
 					AUDIT_CONFIG_CHANGE);
 				audit_log_format(ab, "auid=%u ses=%u",
 					audit_get_loginuid(current),
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d82142be8dd..26e08754744 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -363,8 +363,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
 	irqreturn_t ret, retval = IRQ_NONE;
 	unsigned int status = 0;
 
-	WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!");
-
 	if (!(action->flags & IRQF_DISABLED))
 		local_irq_enable_in_hardirq();
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 7e2e7dd4cd2..2734eca5924 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -109,10 +109,9 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 	spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-		cpumask_copy(desc->affinity, cpumask);
+	if (desc->status & IRQ_MOVE_PCNTXT)
 		desc->chip->set_affinity(irq, cpumask);
-	} else {
+	else {
 		desc->status |= IRQ_MOVE_PENDING;
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index a5e74ddee0e..c0fa54b276d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -319,6 +319,22 @@ struct kprobe __kprobes *get_kprobe(void *addr)
 	return NULL;
 }
 
+/* Arm a kprobe with text_mutex */
+static void __kprobes arm_kprobe(struct kprobe *kp)
+{
+	mutex_lock(&text_mutex);
+	arch_arm_kprobe(kp);
+	mutex_unlock(&text_mutex);
+}
+
+/* Disarm a kprobe with text_mutex */
+static void __kprobes disarm_kprobe(struct kprobe *kp)
+{
+	mutex_lock(&text_mutex);
+	arch_disarm_kprobe(kp);
+	mutex_unlock(&text_mutex);
+}
+
 /*
  * Aggregate handlers for multiple kprobes support - these handlers
  * take care of invoking the individual kprobe handlers on p->list
@@ -538,7 +554,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 		ap->flags &= ~KPROBE_FLAG_DISABLED;
 		if (!kprobes_all_disarmed)
 			/* Arm the breakpoint again. */
-			arch_arm_kprobe(ap);
+			arm_kprobe(ap);
 	}
 	return 0;
 }
@@ -789,11 +805,8 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
 		 * enabled and not gone - otherwise, the breakpoint would
 		 * already have been removed. We save on flushing icache.
 		 */
-		if (!kprobes_all_disarmed && !kprobe_disabled(old_p)) {
-			mutex_lock(&text_mutex);
-			arch_disarm_kprobe(p);
-			mutex_unlock(&text_mutex);
-		}
+		if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
+			disarm_kprobe(p);
 		hlist_del_rcu(&old_p->hlist);
 	} else {
 		if (p->break_handler && !kprobe_gone(p))
@@ -810,7 +823,7 @@ noclean:
 		if (!kprobe_disabled(old_p)) {
 			try_to_disable_aggr_kprobe(old_p);
 			if (!kprobes_all_disarmed && kprobe_disabled(old_p))
-				arch_disarm_kprobe(old_p);
+				disarm_kprobe(old_p);
 		}
 	}
 	return 0;
@@ -1364,7 +1377,7 @@ int __kprobes disable_kprobe(struct kprobe *kp)
 		try_to_disable_aggr_kprobe(p);
 
 	if (!kprobes_all_disarmed && kprobe_disabled(p))
-		arch_disarm_kprobe(p);
+		disarm_kprobe(p);
 out:
 	mutex_unlock(&kprobe_mutex);
 	return ret;
@@ -1393,7 +1406,7 @@ int __kprobes enable_kprobe(struct kprobe *kp)
 	}
 
 	if (!kprobes_all_disarmed && kprobe_disabled(p))
-		arch_arm_kprobe(p);
+		arm_kprobe(p);
 
 	p->flags &= ~KPROBE_FLAG_DISABLED;
 	if (p != kp)
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index b0f01186696..accb40cdb12 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -2490,13 +2490,20 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		      struct lock_class_key *key, int subclass)
 {
-	if (unlikely(!debug_locks))
+	lock->class_cache = NULL;
+#ifdef CONFIG_LOCK_STAT
+	lock->cpu = raw_smp_processor_id();
+#endif
+
+	if (DEBUG_LOCKS_WARN_ON(!name)) {
+		lock->name = "NULL";
 		return;
+	}
+
+	lock->name = name;
 
 	if (DEBUG_LOCKS_WARN_ON(!key))
 		return;
-	if (DEBUG_LOCKS_WARN_ON(!name))
-		return;
 	/*
 	 * Sanity check, the lock-class key must be persistent:
 	 */
@@ -2505,12 +2512,11 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 		DEBUG_LOCKS_WARN_ON(1);
 		return;
 	}
-	lock->name = name;
 	lock->key = key;
-	lock->class_cache = NULL;
-#ifdef CONFIG_LOCK_STAT
-	lock->cpu = raw_smp_processor_id();
-#endif
+
+	if (unlikely(!debug_locks))
+		return;
+
 	if (subclass)
 		register_lock_class(lock, subclass, 1);
 }
diff --git a/kernel/panic.c b/kernel/panic.c
index 934fb377f4b..874ecf1307a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -221,7 +221,7 @@ void add_taint(unsigned flag)
 	 * post-warning case.
 	 */
 	if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off())
-		printk(KERN_WARNING "Disabling lockdep due to kernel taint\n");
+		printk(KERN_WARNING "Disabling lock debugging due to kernel taint\n");
 
 	set_bit(flag, &tainted_mask);
 }
@@ -340,7 +340,7 @@ void oops_exit(void)
 }
 
 #ifdef WANT_WARN_ON_SLOWPATH
-void warn_slowpath(const char *file, int line, const char *fmt, ...)
+void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
 {
 	va_list args;
 	char function[KSYM_SYMBOL_LEN];
@@ -356,7 +356,7 @@ void warn_slowpath(const char *file, int line, const char *fmt, ...)
 	if (board)
 		printk(KERN_WARNING "Hardware name: %s\n", board);
 
-	if (fmt) {
+	if (*fmt) {
 		va_start(args, fmt);
 		vprintk(fmt, args);
 		va_end(args);
@@ -367,7 +367,14 @@ void warn_slowpath(const char *file, int line, const char *fmt, ...)
 	print_oops_end_marker();
 	add_taint(TAINT_WARN);
 }
-EXPORT_SYMBOL(warn_slowpath);
+EXPORT_SYMBOL(warn_slowpath_fmt);
+
+void warn_slowpath_null(const char *file, int line)
+{
+	static const char *empty = "";
+	warn_slowpath_fmt(file, line, empty);
+}
+EXPORT_SYMBOL(warn_slowpath_null);
 #endif
 
 #ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c9dcf98b446..bece7c0b67b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1420,19 +1420,19 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * timer call will interfere.
 	 */
 	list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
-		int firing;
+		int cpu_firing;
+
 		spin_lock(&timer->it_lock);
 		list_del_init(&timer->it.cpu.entry);
-		firing = timer->it.cpu.firing;
+		cpu_firing = timer->it.cpu.firing;
 		timer->it.cpu.firing = 0;
 		/*
 		 * The firing flag is -1 if we collided with a reset
 		 * of the timer, which already reported this
 		 * almost-firing as an overrun.  So don't generate an event.
 		 */
-		if (likely(firing >= 0)) {
+		if (likely(cpu_firing >= 0))
 			cpu_timer_fire(timer);
-		}
 		spin_unlock(&timer->it_lock);
 	}
 }
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 0854770b63b..e71ca9cd81b 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -646,13 +646,6 @@ static int software_resume(void)
 		return 0;
 
 	/*
-	 * We can't depend on SCSI devices being available after loading one of
-	 * their modules if scsi_complete_async_scans() is not called and the
-	 * resume device usually is a SCSI one.
-	 */
-	scsi_complete_async_scans();
-
-	/*
 	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
 	 * is configured into the kernel. Since the regular hibernate
 	 * trigger path is via sysfs which takes a buffer mutex before
@@ -663,32 +656,42 @@ static int software_resume(void)
 	 * here to avoid lockdep complaining.
 	 */
 	mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+
+	if (swsusp_resume_device)
+		goto Check_image;
+
+	if (!strlen(resume_file)) {
+		error = -ENOENT;
+		goto Unlock;
+	}
+
+	pr_debug("PM: Checking image partition %s\n", resume_file);
+
+	/* Check if the device is there */
+	swsusp_resume_device = name_to_dev_t(resume_file);
 	if (!swsusp_resume_device) {
-		if (!strlen(resume_file)) {
-			mutex_unlock(&pm_mutex);
-			return -ENOENT;
-		}
 		/*
 		 * Some device discovery might still be in progress; we need
 		 * to wait for this to finish.
 		 */
 		wait_for_device_probe();
+		/*
+		 * We can't depend on SCSI devices being available after loading
+		 * one of their modules until scsi_complete_async_scans() is
+		 * called and the resume device usually is a SCSI one.
+		 */
+		scsi_complete_async_scans();
+
 		swsusp_resume_device = name_to_dev_t(resume_file);
-		pr_debug("PM: Resume from partition %s\n", resume_file);
-	} else {
-		pr_debug("PM: Resume from partition %d:%d\n",
-				MAJOR(swsusp_resume_device),
-				MINOR(swsusp_resume_device));
+		if (!swsusp_resume_device) {
+			error = -ENODEV;
+			goto Unlock;
+		}
 	}
 
-	if (noresume) {
-		/**
-		 * FIXME: If noresume is specified, we need to find the
-		 * partition and reset it back to normal swap space.
-		 */
-		mutex_unlock(&pm_mutex);
-		return 0;
-	}
+ Check_image:
+	pr_debug("PM: Resume from partition %d:%d\n",
+		MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device));
 
 	pr_debug("PM: Checking hibernation image.\n");
 	error = swsusp_check();
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index dfcd83ceee3..0692ab5a0d6 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -188,7 +188,7 @@ int ptrace_attach(struct task_struct *task)
 	/* Protect exec's credential calculations against our interference;
 	 * SUID, SGID and LSM creds get determined differently under ptrace.
 	 */
-	retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+	retval = mutex_lock_interruptible(&task->cred_exec_mutex);
 	if (retval  < 0)
 		goto out;
 
@@ -232,7 +232,7 @@ repeat:
 bad:
 	write_unlock_irqrestore(&tasklist_lock, flags);
 	task_unlock(task);
-	mutex_unlock(&current->cred_exec_mutex);
+	mutex_unlock(&task->cred_exec_mutex);
 out:
 	return retval;
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index b902e587a3a..26efa475bdc 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4732,7 +4732,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 
 	if (user_tick)
 		account_user_time(p, one_jiffy, one_jiffy_scaled);
-	else if (p != rq->idle)
+	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
 				    one_jiffy_scaled);
 	else
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index cf2bc01186e..b28d19135f4 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -609,14 +609,14 @@ void slow_work_unregister_user(void)
 	if (slow_work_user_count == 0) {
 		printk(KERN_NOTICE "Slow work thread pool: Shutting down\n");
 		slow_work_threads_should_exit = true;
+		del_timer_sync(&slow_work_cull_timer);
+		del_timer_sync(&slow_work_oom_timer);
 		wake_up_all(&slow_work_thread_wq);
 		wait_for_completion(&slow_work_last_thread_exited);
 		printk(KERN_NOTICE "Slow work thread pool:"
 		       " Shut down complete\n");
 	}
 
-	del_timer_sync(&slow_work_cull_timer);
-
 	mutex_unlock(&slow_work_user_lock);
 }
 EXPORT_SYMBOL(slow_work_unregister_user);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e3d2c7dd59b..ea78fa101ad 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -103,6 +103,9 @@ static unsigned long one_ul = 1;
 static int one_hundred = 100;
 static int one_thousand = 1000;
 
+/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
+static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
+
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
@@ -1006,7 +1009,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &dirty_bytes_handler,
 		.strategy	= &sysctl_intvec,
-		.extra1		= &one_ul,
+		.extra1		= &dirty_bytes_min,
 	},
 	{
 		.procname	= "dirty_writeback_centisecs",
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c46c931a7fe..ecfd7b5187e 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -181,12 +181,12 @@ static void clocksource_watchdog(unsigned long data)
 
 	resumed = test_and_clear_bit(0, &watchdog_resumed);
 
-	wdnow = watchdog->read();
+	wdnow = watchdog->read(watchdog);
 	wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask);
 	watchdog_last = wdnow;
 
 	list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) {
-		csnow = cs->read();
+		csnow = cs->read(cs);
 
 		if (unlikely(resumed)) {
 			cs->wd_last = csnow;
@@ -247,7 +247,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 
 		list_add(&cs->wd_list, &watchdog_list);
 		if (!started && watchdog) {
-			watchdog_last = watchdog->read();
+			watchdog_last = watchdog->read(watchdog);
 			watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
 			add_timer_on(&watchdog_timer,
 				     cpumask_first(cpu_online_mask));
@@ -268,7 +268,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 				cse->flags &= ~CLOCK_SOURCE_WATCHDOG;
 			/* Start if list is not empty */
 			if (!list_empty(&watchdog_list)) {
-				watchdog_last = watchdog->read();
+				watchdog_last = watchdog->read(watchdog);
 				watchdog_timer.expires =
 					jiffies + WATCHDOG_INTERVAL;
 				add_timer_on(&watchdog_timer,
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 06f197560f3..c3f6c30816e 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -50,7 +50,7 @@
  */
 #define JIFFIES_SHIFT	8
 
-static cycle_t jiffies_read(void)
+static cycle_t jiffies_read(struct clocksource *cs)
 {
 	return (cycle_t) jiffies;
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 21a5ca84951..83c4417b6a3 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -93,7 +93,17 @@ void tick_handle_periodic(struct clock_event_device *dev)
 	for (;;) {
 		if (!clockevents_program_event(dev, next, ktime_get()))
 			return;
-		tick_periodic(cpu);
+		/*
+		 * Have to be careful here. If we're in oneshot mode,
+		 * before we call tick_periodic() in a loop, we need
+		 * to be sure we're using a real hardware clocksource.
+		 * Otherwise we could get trapped in an infinite
+		 * loop, as the tick_periodic() increments jiffies,
+		 * when then will increment time, posibly causing
+		 * the loop to trigger again and again.
+		 */
+		if (timekeeping_valid_for_hres())
+			tick_periodic(cpu);
 		next = ktime_add(next, tick_period);
 	}
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 900f1b6598d..687dff49f6e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -182,7 +182,7 @@ EXPORT_SYMBOL(do_settimeofday);
  */
 static void change_clocksource(void)
 {
-	struct clocksource *new;
+	struct clocksource *new, *old;
 
 	new = clocksource_get_next();
 
@@ -191,11 +191,16 @@ static void change_clocksource(void)
 
 	clocksource_forward_now();
 
-	new->raw_time = clock->raw_time;
+	if (clocksource_enable(new))
+		return;
 
+	new->raw_time = clock->raw_time;
+	old = clock;
 	clock = new;
+	clocksource_disable(old);
+
 	clock->cycle_last = 0;
-	clock->cycle_last = clocksource_read(new);
+	clock->cycle_last = clocksource_read(clock);
 	clock->error = 0;
 	clock->xtime_nsec = 0;
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
@@ -292,6 +297,7 @@ void __init timekeeping_init(void)
 	ntp_init();
 
 	clock = clocksource_get_next();
+	clocksource_enable(clock);
 	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
 	clock->cycle_last = clocksource_read(clock);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1ce5dc6372b..a884c09006c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3448,6 +3448,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		if (!ref)
 			break;
 
+		ref->ref = 1;
 		ref->buffer = info->tr->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer);
 		if (!ref->page) {