Merge commit 'v2.6.39' into for-2.6.40/core

Since for-2.6.40/core was forked off the 2.6.39 devel tree, we've
had churn in the core area that makes it difficult to handle
patches for eg cfq or blk-throttle. Instead of requiring that they
be based in older versions with bugs that have been fixed later
in the rc cycle, merge in 2.6.39 final.

Also fixes up conflicts in the below files.

Conflicts:
	drivers/block/paride/pcd.c
	drivers/cdrom/viocd.c
	drivers/ide/ide-cd.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

18 files changed, 103 insertions, 40 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index bf0c734d0c12..32a80e08ff4b 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -399,3 +399,15 @@ bool task_ns_capable(struct task_struct *t, int cap)
 	return ns_capable(task_cred_xxx(t, user)->user_ns, cap);
 }
 EXPORT_SYMBOL(task_ns_capable);
+
+/**
+ * nsown_capable - Check superior capability to one's own user_ns
+ * @cap: The capability in question
+ *
+ * Return true if the current task has the given superior capability
+ * targeted at its own user namespace.
+ */
+bool nsown_capable(int cap)
+{
+	return ns_capable(current_user_ns(), cap);
+}
diff --git a/kernel/cred.c b/kernel/cred.c
index 5557b55048df..8093c16b84b1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -54,6 +54,7 @@ struct cred init_cred = {
 	.cap_effective		= CAP_INIT_EFF_SET,
 	.cap_bset		= CAP_INIT_BSET,
 	.user			= INIT_USER,
+	.user_ns		= &init_user_ns,
 	.group_info		= &init_groups,
 #ifdef CONFIG_KEYS
 	.tgcred			= &init_tgcred,
@@ -410,6 +411,11 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 			goto error_put;
 	}
 
+	/* cache user_ns in cred.  Doesn't need a refcount because it will
+	 * stay pinned by cred->user
+	 */
+	new->user_ns = new->user->user_ns;
+
 #ifdef CONFIG_KEYS
 	/* new threads get their own thread keyrings if their parent already
 	 * had one */
@@ -741,12 +747,6 @@ int set_create_files_as(struct cred *new, struct inode *inode)
 }
 EXPORT_SYMBOL(set_create_files_as);
 
-struct user_namespace *current_user_ns(void)
-{
-	return _current_user_ns();
-}
-EXPORT_SYMBOL(current_user_ns);
-
 #ifdef CONFIG_DEBUG_CREDENTIALS
 
 bool creds_are_invalid(const struct cred *cred)
diff --git a/kernel/exit.c b/kernel/exit.c
index f5d2f63bae0b..8dd874181542 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1016,7 +1016,7 @@ NORET_TYPE void do_exit(long code)
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
-	flush_ptrace_hw_breakpoint(tsk);
+	ptrace_put_breakpoints(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9017478c5d4c..87fdb3f8db14 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -81,7 +81,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 	}
 };
 
-static int hrtimer_clock_to_base_table[MAX_CLOCKS];
+static int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
+	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
+	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
+};
 
 static inline int hrtimer_clockid_to_base(clockid_t clock_id)
 {
@@ -1722,10 +1726,6 @@ static struct notifier_block __cpuinitdata hrtimers_nb = {
 
 void __init hrtimers_init(void)
 {
-	hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME;
-	hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC;
-	hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME;
-
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index dd201bd35103..834899f2500f 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -419,7 +419,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	} else {
 		seq_printf(p, " %8s", "None");
 	}
-#ifdef CONFIG_GENIRC_IRQ_SHOW_LEVEL
+#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
 	seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
 #endif
 	if (desc->name)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 55936f9cb251..87b77de03dd3 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -33,6 +33,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap.h>
 #include <linux/kmsg_dump.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -1532,6 +1533,11 @@ int kernel_kexec(void)
 		local_irq_disable();
 		/* Suspend system devices */
 		error = sysdev_suspend(PMSG_FREEZE);
+		if (!error) {
+			error = syscore_suspend();
+			if (error)
+				sysdev_resume();
+		}
 		if (error)
 			goto Enable_irqs;
 	} else
@@ -1546,6 +1552,7 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
+		syscore_resume();
 		sysdev_resume();
  Enable_irqs:
 		local_irq_enable();
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index aeabd26e3342..50aae660174d 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -273,8 +273,11 @@ static int create_image(int platform_mode)
 	local_irq_disable();
 
 	error = sysdev_suspend(PMSG_FREEZE);
-	if (!error)
+	if (!error) {
 		error = syscore_suspend();
+		if (error)
+			sysdev_resume();
+	}
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
 			"aborting hibernation\n");
@@ -407,8 +410,11 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_disable();
 
 	error = sysdev_suspend(PMSG_QUIESCE);
-	if (!error)
+	if (!error) {
 		error = syscore_suspend();
+		if (error)
+			sysdev_resume();
+	}
 	if (error)
 		goto Enable_irqs;
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 2814c32aed51..6275970b2189 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -164,8 +164,11 @@ static int suspend_enter(suspend_state_t state)
 	BUG_ON(!irqs_disabled());
 
 	error = sysdev_suspend(PMSG_SUSPEND);
-	if (!error)
+	if (!error) {
 		error = syscore_suspend();
+		if (error)
+			sysdev_resume();
+	}
 	if (!error) {
 		if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
 			error = suspend_ops->enter(state);
@@ -213,7 +216,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
-	pm_restrict_gfp_mask();
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -230,7 +232,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	pm_restore_gfp_mask();
 	resume_console();
  Close:
 	if (suspend_ops->end)
@@ -291,7 +292,9 @@ int enter_state(suspend_state_t state)
 		goto Finish;
 
 	pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
+	pm_restore_gfp_mask();
 
  Finish:
 	pr_debug("PM: Finishing wakeup.\n");
diff --git a/kernel/power/user.c b/kernel/power/user.c
index c36c3b9e8a84..7d02d33be699 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -135,8 +135,10 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 	free_basic_memory_bitmaps();
 	data = filp->private_data;
 	free_all_swap_pages(data->swap);
-	if (data->frozen)
+	if (data->frozen) {
+		pm_restore_gfp_mask();
 		thaw_processes();
+	}
 	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
 	atomic_inc(&snapshot_device_available);
@@ -379,6 +381,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		 * PM_HIBERNATION_PREPARE
 		 */
 		error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+		data->ready = 0;
 		break;
 
 	case SNAPSHOT_PLATFORM_SUPPORT:
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 0fc1eed28d27..dc7ab65f3b36 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
 
 
 /*
@@ -879,3 +880,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	return ret;
 }
 #endif	/* CONFIG_COMPAT */
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+int ptrace_get_breakpoints(struct task_struct *tsk)
+{
+	if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
+		return 0;
+
+	return -1;
+}
+
+void ptrace_put_breakpoints(struct task_struct *tsk)
+{
+	if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
+		flush_ptrace_hw_breakpoint(tsk);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 6519cf62d9cd..0e17c10f8a9d 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -685,8 +685,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 	/* Add clocksource to the clcoksource list */
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
-	clocksource_select();
 	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -706,8 +706,8 @@ int clocksource_register(struct clocksource *cs)
 
 	mutex_lock(&clocksource_mutex);
 	clocksource_enqueue(cs);
-	clocksource_select();
 	clocksource_enqueue_watchdog(cs);
+	clocksource_select();
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 25028dd4fa18..c340ca658f37 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -19,7 +19,6 @@
  */
 #include <linux/device.h>
 #include <linux/file.h>
-#include <linux/mutex.h>
 #include <linux/posix-clock.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
@@ -34,19 +33,19 @@ static struct posix_clock *get_posix_clock(struct file *fp)
 {
 	struct posix_clock *clk = fp->private_data;
 
-	mutex_lock(&clk->mutex);
+	down_read(&clk->rwsem);
 
 	if (!clk->zombie)
 		return clk;
 
-	mutex_unlock(&clk->mutex);
+	up_read(&clk->rwsem);
 
 	return NULL;
 }
 
 static void put_posix_clock(struct posix_clock *clk)
 {
-	mutex_unlock(&clk->mutex);
+	up_read(&clk->rwsem);
 }
 
 static ssize_t posix_clock_read(struct file *fp, char __user *buf,
@@ -156,7 +155,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 	struct posix_clock *clk =
 		container_of(inode->i_cdev, struct posix_clock, cdev);
 
-	mutex_lock(&clk->mutex);
+	down_read(&clk->rwsem);
 
 	if (clk->zombie) {
 		err = -ENODEV;
@@ -172,7 +171,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		fp->private_data = clk;
 	}
 out:
-	mutex_unlock(&clk->mutex);
+	up_read(&clk->rwsem);
 	return err;
 }
 
@@ -211,25 +210,20 @@ int posix_clock_register(struct posix_clock *clk, dev_t devid)
 	int err;
 
 	kref_init(&clk->kref);
-	mutex_init(&clk->mutex);
+	init_rwsem(&clk->rwsem);
 
 	cdev_init(&clk->cdev, &posix_clock_file_operations);
 	clk->cdev.owner = clk->ops.owner;
 	err = cdev_add(&clk->cdev, devid, 1);
-	if (err)
-		goto no_cdev;
 
 	return err;
-no_cdev:
-	mutex_destroy(&clk->mutex);
-	return err;
 }
 EXPORT_SYMBOL_GPL(posix_clock_register);
 
 static void delete_clock(struct kref *kref)
 {
 	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-	mutex_destroy(&clk->mutex);
+
 	if (clk->release)
 		clk->release(clk);
 }
@@ -238,9 +232,9 @@ void posix_clock_unregister(struct posix_clock *clk)
 {
 	cdev_del(&clk->cdev);
 
-	mutex_lock(&clk->mutex);
+	down_write(&clk->rwsem);
 	clk->zombie = true;
-	mutex_unlock(&clk->mutex);
+	up_write(&clk->rwsem);
 
 	kref_put(&clk->kref, delete_clock);
 }
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index da800ffa810c..723c7637e55a 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -522,10 +522,11 @@ static void tick_broadcast_init_next_event(struct cpumask *mask,
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
+	int cpu = smp_processor_id();
+
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
 		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
-		int cpu = smp_processor_id();
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
@@ -551,6 +552,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 			tick_broadcast_set_event(tick_next_period, 1);
 		} else
 			bc->next_event.tv64 = KTIME_MAX;
+	} else {
+		/*
+		 * The first cpu which switches to oneshot mode sets
+		 * the bit for all other cpus which are in the general
+		 * (periodic) broadcast mask. So the bit is set and
+		 * would prevent the first broadcast enter after this
+		 * to program the bc device.
+		 */
+		tick_broadcast_clear_oneshot(cpu);
 	}
 }
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61d7d59f4a1a..2ad39e556cb4 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,7 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if !ARM_UNWIND && !S390
+	select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d38c16a06a6f..1cb49be7c7fb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1110,6 +1110,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
+	entry->padding			= 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e88f74fe1d4c..2fe110341359 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,6 +116,7 @@ static int trace_define_common_fields(void)
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
+	__common_field(int, padding);
 
 	return ret;
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 140dce750450..14733d4d156b 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -430,9 +430,12 @@ static int watchdog_enable(int cpu)
 		p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu);
 		if (IS_ERR(p)) {
 			printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu);
-			if (!err)
+			if (!err) {
 				/* if hardlockup hasn't already set this */
 				err = PTR_ERR(p);
+				/* and disable the perf event */
+				watchdog_nmi_disable(cpu);
+			}
 			goto out;
 		}
 		kthread_bind(p, cpu);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8859a41806dd..e3378e8d3a5c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1291,8 +1291,14 @@ __acquires(&gcwq->lock)
 			return true;
 		spin_unlock_irq(&gcwq->lock);
 
-		/* CPU has come up in between, retry migration */
+		/*
+		 * We've raced with CPU hot[un]plug.  Give it a breather
+		 * and retry migration.  cond_resched() is required here;
+		 * otherwise, we might deadlock against cpu_stop trying to
+		 * bring down the CPU on non-preemptive kernel.
+		 */
 		cpu_relax();
+		cond_resched();
 	}
 }