Merge branch 'linus' into x86/apic

Conflicts:
	arch/x86/mach-default/setup.c

Semantic conflict resolution:
	arch/x86/kernel/setup.c

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

kernel/Makefile

@@ -51,6 +51,7 @@ obj-$(CONFIG_UID16) += uid16.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_PM) += power/
+obj-$(CONFIG_FREEZER) += power/
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o

kernel/cgroup.c

@@ -1122,8 +1122,8 @@ static void cgroup_kill_sb(struct super_block *sb) {
 
 	mutex_unlock(&cgroup_mutex);
 
-	kfree(root);
 	kill_litter_super(sb);
+	kfree(root);
 }
 
 static struct file_system_type cgroup_fs_type = {

kernel/futex.c

@@ -1165,6 +1165,7 @@ static int futex_wait(u32 __user *uaddr, int fshared,
 		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
 	struct task_struct *curr = current;
+	struct restart_block *restart;
 	DECLARE_WAITQUEUE(wait, curr);
 	struct futex_hash_bucket *hb;
 	struct futex_q q;
@@ -1216,11 +1217,13 @@ retry:
 
 		if (!ret)
 			goto retry;
-		return ret;
+		goto out;
 	}
 	ret = -EWOULDBLOCK;
-	if (uval != val)
-		goto out_unlock_put_key;
+	if (unlikely(uval != val)) {
+		queue_unlock(&q, hb);
+		goto out_put_key;
+	}
 
 	/* Only actually queue if *uaddr contained val.  */
 	queue_me(&q, hb);
@@ -1284,38 +1287,38 @@ retry:
 	 */
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
+	ret = 0;
 	if (!unqueue_me(&q))
-		return 0;
+		goto out_put_key;
+	ret = -ETIMEDOUT;
 	if (rem)
-		return -ETIMEDOUT;
+		goto out_put_key;
 
 	/*
 	 * We expect signal_pending(current), but another thread may
 	 * have handled it for us already.
 	 */
+	ret = -ERESTARTSYS;
 	if (!abs_time)
-		return -ERESTARTSYS;
-	else {
-		struct restart_block *restart;
-		restart = &current_thread_info()->restart_block;
-		restart->fn = futex_wait_restart;
-		restart->futex.uaddr = (u32 *)uaddr;
-		restart->futex.val = val;
-		restart->futex.time = abs_time->tv64;
-		restart->futex.bitset = bitset;
-		restart->futex.flags = 0;
+		goto out_put_key;
 
-		if (fshared)
-			restart->futex.flags |= FLAGS_SHARED;
-		if (clockrt)
-			restart->futex.flags |= FLAGS_CLOCKRT;
-		return -ERESTART_RESTARTBLOCK;
-	}
+	restart = &current_thread_info()->restart_block;
+	restart->fn = futex_wait_restart;
+	restart->futex.uaddr = (u32 *)uaddr;
+	restart->futex.val = val;
+	restart->futex.time = abs_time->tv64;
+	restart->futex.bitset = bitset;
+	restart->futex.flags = 0;
 
-out_unlock_put_key:
-	queue_unlock(&q, hb);
+	if (fshared)
+		restart->futex.flags |= FLAGS_SHARED;
+	if (clockrt)
+		restart->futex.flags |= FLAGS_CLOCKRT;
+
+	ret = -ERESTART_RESTARTBLOCK;
+
+out_put_key:
 	put_futex_key(fshared, &q.key);
-
 out:
 	return ret;
 }

kernel/kexec.c

@@ -1465,6 +1465,11 @@ int kernel_kexec(void)
 		error = device_power_down(PMSG_FREEZE);
 		if (error)
 			goto Enable_irqs;
+
+		/* Suspend system devices */
+		error = sysdev_suspend(PMSG_FREEZE);
+		if (error)
+			goto Power_up_devices;
 	} else
 #endif
 	{
@@ -1477,6 +1482,8 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
+		sysdev_resume();
+ Power_up_devices:
 		device_power_up(PMSG_RESTORE);
  Enable_irqs:
 		local_irq_enable();

kernel/posix-cpu-timers.c

@@ -680,6 +680,33 @@ static void cpu_timer_fire(struct k_itimer *timer)
 	}
 }
 
+/*
+ * Sample a process (thread group) timer for the given group_leader task.
+ * Must be called with tasklist_lock held for reading.
+ */
+static int cpu_timer_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  union cpu_time_count *cpu)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputimer(p, &cputime);
+	switch (CPUCLOCK_WHICH(which_clock)) {
+	default:
+		return -EINVAL;
+	case CPUCLOCK_PROF:
+		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
+		break;
+	case CPUCLOCK_VIRT:
+		cpu->cpu = cputime.utime;
+		break;
+	case CPUCLOCK_SCHED:
+		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
+		break;
+	}
+	return 0;
+}
+
 /*
  * Guts of sys_timer_settime for CPU timers.
  * This is called with the timer locked and interrupts disabled.
@@ -741,7 +768,7 @@ int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &val);
 	} else {
-		cpu_clock_sample_group(timer->it_clock, p, &val);
+		cpu_timer_sample_group(timer->it_clock, p, &val);
 	}
 
 	if (old) {
@@ -889,7 +916,7 @@ void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			read_unlock(&tasklist_lock);
 			goto dead;
 		} else {
-			cpu_clock_sample_group(timer->it_clock, p, &now);
+			cpu_timer_sample_group(timer->it_clock, p, &now);
 			clear_dead = (unlikely(p->exit_state) &&
 				      thread_group_empty(p));
 		}
@@ -1244,7 +1271,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			clear_dead_task(timer, now);
 			goto out_unlock;
 		}
-		cpu_clock_sample_group(timer->it_clock, p, &now);
+		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
 		/* Leave the tasklist_lock locked for the call below.  */
 	}
@@ -1408,33 +1435,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	}
 }
 
-/*
- * Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- */
-static int cpu_timer_sample_group(const clockid_t which_clock,
-				  struct task_struct *p,
-				  union cpu_time_count *cpu)
-{
-	struct task_cputime cputime;
-
-	thread_group_cputimer(p, &cputime);
-	switch (CPUCLOCK_WHICH(which_clock)) {
-	default:
-		return -EINVAL;
-	case CPUCLOCK_PROF:
-		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
-		break;
-	case CPUCLOCK_VIRT:
-		cpu->cpu = cputime.utime;
-		break;
-	case CPUCLOCK_SCHED:
-		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
-		break;
-	}
-	return 0;
-}
-
 /*
  * Set one of the process-wide special case CPU timers.
  * The tsk->sighand->siglock must be held by the caller.

kernel/power/Makefile

@@ -3,7 +3,7 @@ ifeq ($(CONFIG_PM_DEBUG),y)
 EXTRA_CFLAGS	+=	-DDEBUG
 endif
 
-obj-y				:= main.o
+obj-$(CONFIG_PM)		+= main.o
 obj-$(CONFIG_PM_SLEEP)		+= console.o
 obj-$(CONFIG_FREEZER)		+= process.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o disk.o snapshot.o swap.o user.o

kernel/power/console.c

@@ -78,6 +78,12 @@ void pm_restore_console(void)
 	}
 	set_console(orig_fgconsole);
 	release_console_sem();
+
+	if (vt_waitactive(orig_fgconsole)) {
+		pr_debug("Resume: Can't switch VCs.");
+		return;
+	}
+
 	kmsg_redirect = orig_kmsg;
 }
 #endif

kernel/power/disk.c

@@ -227,6 +227,12 @@ static int create_image(int platform_mode)
 			"aborting hibernation\n");
 		goto Enable_irqs;
 	}
+	sysdev_suspend(PMSG_FREEZE);
+	if (error) {
+		printk(KERN_ERR "PM: Some devices failed to power down, "
+			"aborting hibernation\n");
+		goto Power_up_devices;
+	}
 
 	if (hibernation_test(TEST_CORE))
 		goto Power_up;
@@ -242,9 +248,11 @@ static int create_image(int platform_mode)
 	if (!in_suspend)
 		platform_leave(platform_mode);
  Power_up:
+	sysdev_resume();
 	/* NOTE:  device_power_up() is just a resume() for devices
 	 * that suspended with irqs off ... no overall powerup.
 	 */
+ Power_up_devices:
 	device_power_up(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
  Enable_irqs:
@@ -335,6 +343,7 @@ static int resume_target_kernel(void)
 			"aborting resume\n");
 		goto Enable_irqs;
 	}
+	sysdev_suspend(PMSG_QUIESCE);
 	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
@@ -357,6 +366,7 @@ static int resume_target_kernel(void)
 	swsusp_free();
 	restore_processor_state();
 	touch_softlockup_watchdog();
+	sysdev_resume();
 	device_power_up(PMSG_RECOVER);
  Enable_irqs:
 	local_irq_enable();
@@ -440,6 +450,7 @@ int hibernation_platform_enter(void)
 	local_irq_disable();
 	error = device_power_down(PMSG_HIBERNATE);
 	if (!error) {
+		sysdev_suspend(PMSG_HIBERNATE);
 		hibernation_ops->enter();
 		/* We should never get here */
 		while (1);
@@ -594,6 +605,12 @@ static int software_resume(void)
 	int error;
 	unsigned int flags;
 
+	/*
+	 * If the user said "noresume".. bail out early.
+	 */
+	if (noresume)
+		return 0;
+
 	/*
 	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
 	 * is configured into the kernel. Since the regular hibernate
@@ -610,6 +627,11 @@ static int software_resume(void)
 			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();
 		swsusp_resume_device = name_to_dev_t(resume_file);
 		pr_debug("PM: Resume from partition %s\n", resume_file);
 	} else {

kernel/power/main.c

@@ -298,8 +298,12 @@ static int suspend_enter(suspend_state_t state)
 		goto Done;
 	}
 
-	if (!suspend_test(TEST_CORE))
-		error = suspend_ops->enter(state);
+	error = sysdev_suspend(PMSG_SUSPEND);
+	if (!error) {
+		if (!suspend_test(TEST_CORE))
+			error = suspend_ops->enter(state);
+		sysdev_resume();
+	}
 
 	device_power_up(PMSG_RESUME);
  Done:

kernel/power/swap.c

@@ -60,6 +60,7 @@ static struct block_device *resume_bdev;
 static int submit(int rw, pgoff_t page_off, struct page *page,
 			struct bio **bio_chain)
 {
+	const int bio_rw = rw | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
 	struct bio *bio;
 
 	bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
@@ -80,7 +81,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 	bio_get(bio);
 
 	if (bio_chain == NULL) {
-		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		submit_bio(bio_rw, bio);
 		wait_on_page_locked(page);
 		if (rw == READ)
 			bio_set_pages_dirty(bio);
@@ -90,7 +91,7 @@ static int submit(int rw, pgoff_t page_off, struct page *page,
 			get_page(page);	/* These pages are freed later */
 		bio->bi_private = *bio_chain;
 		*bio_chain = bio;
-		submit_bio(rw | (1 << BIO_RW_SYNC), bio);
+		submit_bio(bio_rw, bio);
 	}
 	return 0;
 }

kernel/power/user.c

@@ -95,15 +95,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 		data->swap = swsusp_resume_device ?
 			swap_type_of(swsusp_resume_device, 0, NULL) : -1;
 		data->mode = O_RDONLY;
-		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
-		if (error)
-			pm_notifier_call_chain(PM_POST_RESTORE);
-	} else {
-		data->swap = -1;
-		data->mode = O_WRONLY;
 		error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
 		if (error)
 			pm_notifier_call_chain(PM_POST_HIBERNATION);
+	} else {
+		data->swap = -1;
+		data->mode = O_WRONLY;
+		error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+		if (error)
+			pm_notifier_call_chain(PM_POST_RESTORE);
 	}
 	if (error)
 		atomic_inc(&snapshot_device_available);

kernel/printk.c

@@ -73,7 +73,6 @@ EXPORT_SYMBOL(oops_in_progress);
  * driver system.
  */
 static DECLARE_MUTEX(console_sem);
-static DECLARE_MUTEX(secondary_console_sem);
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
@@ -891,12 +890,14 @@ void suspend_console(void)
 	printk("Suspending console(s) (use no_console_suspend to debug)\n");
 	acquire_console_sem();
 	console_suspended = 1;
+	up(&console_sem);
 }
 
 void resume_console(void)
 {
 	if (!console_suspend_enabled)
 		return;
+	down(&console_sem);
 	console_suspended = 0;
 	release_console_sem();
 }
@@ -912,11 +913,9 @@ void resume_console(void)
 void acquire_console_sem(void)
 {
 	BUG_ON(in_interrupt());
-	if (console_suspended) {
-		down(&secondary_console_sem);
-		return;
-	}
 	down(&console_sem);
+	if (console_suspended)
+		return;
 	console_locked = 1;
 	console_may_schedule = 1;
 }
@@ -926,6 +925,10 @@ int try_acquire_console_sem(void)
 {
 	if (down_trylock(&console_sem))
 		return -1;
+	if (console_suspended) {
+		up(&console_sem);
+		return -1;
+	}
 	console_locked = 1;
 	console_may_schedule = 0;
 	return 0;
@@ -979,7 +982,7 @@ void release_console_sem(void)
 	unsigned wake_klogd = 0;
 
 	if (console_suspended) {
-		up(&secondary_console_sem);
+		up(&console_sem);
 		return;
 	}
 

kernel/sched.c

@@ -6939,20 +6939,26 @@ static void free_rootdomain(struct root_domain *rd)
 
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
+	struct root_domain *old_rd = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&rq->lock, flags);
 
 	if (rq->rd) {
-		struct root_domain *old_rd = rq->rd;
+		old_rd = rq->rd;
 
 		if (cpumask_test_cpu(rq->cpu, old_rd->online))
 			set_rq_offline(rq);
 
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
-		if (atomic_dec_and_test(&old_rd->refcount))
-			free_rootdomain(old_rd);
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
 	}
 
 	atomic_inc(&rd->refcount);
@@ -6963,6 +6969,9 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
+
+	if (old_rd)
+		free_rootdomain(old_rd);
 }
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)

kernel/trace/Kconfig

@@ -52,6 +52,7 @@ config FUNCTION_TRACER
 	depends on HAVE_FUNCTION_TRACER
 	depends on DEBUG_KERNEL
 	select FRAME_POINTER
+	select KALLSYMS
 	select TRACING
 	select CONTEXT_SWITCH_TRACER
 	help
@@ -238,6 +239,7 @@ config STACK_TRACER
 	depends on DEBUG_KERNEL
 	select FUNCTION_TRACER
 	select STACKTRACE
+	select KALLSYMS
 	help
 	  This special tracer records the maximum stack footprint of the
 	  kernel and displays it in debugfs/tracing/stack_trace.
@@ -302,4 +304,27 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config MMIOTRACE
+	bool "Memory mapped IO tracing"
+	depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+	select TRACING
+	help
+	  Mmiotrace traces Memory Mapped I/O access and is meant for
+	  debugging and reverse engineering. It is called from the ioremap
+	  implementation and works via page faults. Tracing is disabled by
+	  default and can be enabled at run-time.
+
+	  See Documentation/tracers/mmiotrace.txt.
+	  If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+	tristate "Test module for mmiotrace"
+	depends on MMIOTRACE && m
+	help
+	  This is a dumb module for testing mmiotrace. It is very dangerous
+	  as it will write garbage to IO memory starting at a given address.
+	  However, it should be safe to use on e.g. unused portion of VRAM.
+
+	  Say N, unless you absolutely know what you are doing.
+
 endmenu

kernel/trace/ftrace.c

@@ -2033,7 +2033,7 @@ free:
 static int start_graph_tracing(void)
 {
 	struct ftrace_ret_stack **ret_stack_list;
-	int ret;
+	int ret, cpu;
 
 	ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
 				sizeof(struct ftrace_ret_stack *),
@@ -2042,6 +2042,10 @@ static int start_graph_tracing(void)
 	if (!ret_stack_list)
 		return -ENOMEM;
 
+	/* The cpu_boot init_task->ret_stack will never be freed */
+	for_each_online_cpu(cpu)
+		ftrace_graph_init_task(idle_task(cpu));
+
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);

kernel/trace/trace_mmiotrace.c

@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <asm/atomic.h>
 
 #include "trace.h"
 
@@ -19,6 +20,7 @@ struct header_iter {
 static struct trace_array *mmio_trace_array;
 static bool overrun_detected;
 static unsigned long prev_overruns;
+static atomic_t dropped_count;
 
 static void mmio_reset_data(struct trace_array *tr)
 {
@@ -121,11 +123,11 @@ static void mmio_close(struct trace_iterator *iter)
 
 static unsigned long count_overruns(struct trace_iterator *iter)
 {
-	unsigned long cnt = 0;
+	unsigned long cnt = atomic_xchg(&dropped_count, 0);
 	unsigned long over = ring_buffer_overruns(iter->tr->buffer);
 
 	if (over > prev_overruns)
-		cnt = over - prev_overruns;
+		cnt += over - prev_overruns;
 	prev_overruns = over;
 	return cnt;
 }
@@ -310,8 +312,10 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 
 	event	= ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					   &irq_flags);
-	if (!event)
+	if (!event) {
+		atomic_inc(&dropped_count);
 		return;
+	}
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, preempt_count());
 	entry->ent.type			= TRACE_MMIO_RW;
@@ -338,8 +342,10 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 
 	event	= ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					   &irq_flags);
-	if (!event)
+	if (!event) {
+		atomic_inc(&dropped_count);
 		return;
+	}
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, preempt_count());
 	entry->ent.type			= TRACE_MMIO_MAP;

kernel/trace/trace_selftest.c

@@ -23,10 +23,20 @@ static int trace_test_buffer_cpu(struct trace_array *tr, int cpu)
 {
 	struct ring_buffer_event *event;
 	struct trace_entry *entry;
+	unsigned int loops = 0;
 
 	while ((event = ring_buffer_consume(tr->buffer, cpu, NULL))) {
 		entry = ring_buffer_event_data(event);
 
+		/*
+		 * The ring buffer is a size of trace_buf_size, if
+		 * we loop more than the size, there's something wrong
+		 * with the ring buffer.
+		 */
+		if (loops++ > trace_buf_size) {
+			printk(KERN_CONT ".. bad ring buffer ");
+			goto failed;
+		}
 		if (!trace_valid_entry(entry)) {
 			printk(KERN_CONT ".. invalid entry %d ",
 				entry->type);
@@ -57,11 +67,20 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 
 	cnt = ring_buffer_entries(tr->buffer);
 
+	/*
+	 * The trace_test_buffer_cpu runs a while loop to consume all data.
+	 * If the calling tracer is broken, and is constantly filling
+	 * the buffer, this will run forever, and hard lock the box.
+	 * We disable the ring buffer while we do this test to prevent
+	 * a hard lock up.
+	 */
+	tracing_off();
 	for_each_possible_cpu(cpu) {
 		ret = trace_test_buffer_cpu(tr, cpu);
 		if (ret)
 			break;
 	}
+	tracing_on();
 	__raw_spin_unlock(&ftrace_max_lock);
 	local_irq_restore(flags);