Merge branch 'master' into for-2.6.31

Conflicts:
	drivers/block/hd.c
	drivers/block/mg_disk.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

17 files changed, 100 insertions, 81 deletions

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a6fe71f..713098e 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/cgroup.c b/kernel/cgroup.c
index 382109b..a7267bf 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1133,8 +1133,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
  free_cg_links:
 	free_cg_links(&tmp_cg_links);
  drop_new_super:
-	up_write(&sb->s_umount);
-	deactivate_super(sb);
+	deactivate_locked_super(sb);
 	return ret;
 }
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d82142b..26e0875 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 7e2e7dd..2734eca 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/kgdb.c b/kernel/kgdb.c
index e4dcfb2..9147a31 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -1583,8 +1583,8 @@ static void sysrq_handle_gdb(int key, struct tty_struct *tty)
 
 static struct sysrq_key_op sysrq_gdb_op = {
 	.handler	= sysrq_handle_gdb,
-	.help_msg	= "Gdb",
-	.action_msg	= "GDB",
+	.help_msg	= "debug(G)",
+	.action_msg	= "DEBUG",
 };
 #endif
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index a5e74dd..c0fa54b 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 b0f0118..accb40c 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/lockdep_internals.h b/kernel/lockdep_internals.h
index a2cc7e9..699a2ac 100644
--- a/kernel/lockdep_internals.h
+++ b/kernel/lockdep_internals.h
@@ -54,9 +54,9 @@ enum {
  * table (if it's not there yet), and we check it for lock order
  * conflicts and deadlocks.
  */
-#define MAX_LOCKDEP_ENTRIES	8192UL
+#define MAX_LOCKDEP_ENTRIES	16384UL
 
-#define MAX_LOCKDEP_CHAINS_BITS	14
+#define MAX_LOCKDEP_CHAINS_BITS	15
 #define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
 
 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)
diff --git a/kernel/panic.c b/kernel/panic.c
index 934fb37..984b3ec 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);
 }
@@ -340,34 +340,46 @@ void oops_exit(void)
 }
 
 #ifdef WANT_WARN_ON_SLOWPATH
-void warn_slowpath(const char *file, int line, const char *fmt, ...)
-{
+struct slowpath_args {
+	const char *fmt;
 	va_list args;
-	char function[KSYM_SYMBOL_LEN];
-	unsigned long caller = (unsigned long)__builtin_return_address(0);
-	const char *board;
+};
 
-	sprint_symbol(function, caller);
+static void warn_slowpath_common(const char *file, int line, void *caller, struct slowpath_args *args)
+{
+	const char *board;
 
 	printk(KERN_WARNING "------------[ cut here ]------------\n");
-	printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
-		line, function);
+	printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller);
 	board = dmi_get_system_info(DMI_PRODUCT_NAME);
 	if (board)
 		printk(KERN_WARNING "Hardware name: %s\n", board);
 
-	if (fmt) {
-		va_start(args, fmt);
-		vprintk(fmt, args);
-		va_end(args);
-	}
+	if (args)
+		vprintk(args->fmt, args->args);
 
 	print_modules();
 	dump_stack();
 	print_oops_end_marker();
 	add_taint(TAINT_WARN);
 }
-EXPORT_SYMBOL(warn_slowpath);
+
+void warn_slowpath_fmt(const char *file, int line, const char *fmt, ...)
+{
+	struct slowpath_args args;
+
+	args.fmt = fmt;
+	va_start(args.args, fmt);
+	warn_slowpath_common(file, line, __builtin_return_address(0), &args);
+	va_end(args.args);
+}
+EXPORT_SYMBOL(warn_slowpath_fmt);
+
+void warn_slowpath_null(const char *file, int line)
+{
+	warn_slowpath_common(file, line, __builtin_return_address(0), NULL);
+}
+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 c9dcf98..bece7c0 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 e71ca9c..b0dc9e7 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -241,9 +241,9 @@ static int create_image(int platform_mode)
 
 	local_irq_disable();
 
-	sysdev_suspend(PMSG_FREEZE);
+	error = sysdev_suspend(PMSG_FREEZE);
 	if (error) {
-		printk(KERN_ERR "PM: Some devices failed to power down, "
+		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
 		goto Enable_irqs;
 	}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index dfcd83c..0692ab5 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 b902e58..26efa47 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/sched_clock.c b/kernel/sched_clock.c
index 819f17a..e1d16c9 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -38,7 +38,8 @@
  */
 unsigned long long __attribute__((weak)) sched_clock(void)
 {
-	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+	return (unsigned long long)(jiffies - INITIAL_JIFFIES)
+					* (NSEC_PER_SEC / HZ);
 }
 
 static __read_mostly int sched_clock_running;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e3d2c7d..b2970d5 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -101,7 +101,9 @@ static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 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;
@@ -1006,7 +1008,7 @@ 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",
@@ -1031,28 +1033,6 @@ static struct ctl_table vm_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 	{
-		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "nr_pdflush_threads_min",
-		.data		= &nr_pdflush_threads_min,
-		.maxlen		= sizeof nr_pdflush_threads_min,
-		.mode		= 0644 /* read-write */,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= &one,
-		.extra2		= &nr_pdflush_threads_max,
-	},
-	{
-		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "nr_pdflush_threads_max",
-		.data		= &nr_pdflush_threads_max,
-		.maxlen		= sizeof nr_pdflush_threads_max,
-		.mode		= 0644 /* read-write */,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= &nr_pdflush_threads_min,
-		.extra2		= &one_thousand,
-	},
-	{
 		.ctl_name	= VM_SWAPPINESS,
 		.procname	= "swappiness",
 		.data		= &vm_swappiness,
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 21a5ca8..83c4417 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/trace/trace.c b/kernel/trace/trace.c
index 1ce5dc6..cda81ec 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2380,7 +2380,7 @@ static const char readme_msg[] =
 	"# echo print-parent > /debug/tracing/trace_options\n"
 	"# echo 1 > /debug/tracing/tracing_enabled\n"
 	"# cat /debug/tracing/trace > /tmp/trace.txt\n"
-	"echo 0 > /debug/tracing/tracing_enabled\n"
+	"# echo 0 > /debug/tracing/tracing_enabled\n"
 ;
 
 static ssize_t
@@ -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) {