Merge commit 'v2.6.36-rc3' into x86/memblock

Conflicts:
	arch/x86/kernel/trampoline.c
	mm/memblock.c

Merge reason: Resolve the conflicts, update to latest upstream.

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

32 files changed, 2369 insertions, 1520 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 123bcef13e5..eaa4a5bbe06 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include <trace/events/writeback.h>
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
@@ -49,8 +50,6 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
-static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
-
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -65,31 +64,25 @@ static void bdi_debug_init(void)
 static int bdi_debug_stats_show(struct seq_file *m, void *v)
 {
 	struct backing_dev_info *bdi = m->private;
-	struct bdi_writeback *wb;
+	struct bdi_writeback *wb = &bdi->wb;
 	unsigned long background_thresh;
 	unsigned long dirty_thresh;
 	unsigned long bdi_thresh;
 	unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
 	struct inode *inode;
 
-	/*
-	 * inode lock is enough here, the bdi->wb_list is protected by
-	 * RCU on the reader side
-	 */
 	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
 	spin_lock(&inode_lock);
-	list_for_each_entry(wb, &bdi->wb_list, list) {
-		nr_wb++;
-		list_for_each_entry(inode, &wb->b_dirty, i_list)
-			nr_dirty++;
-		list_for_each_entry(inode, &wb->b_io, i_list)
-			nr_io++;
-		list_for_each_entry(inode, &wb->b_more_io, i_list)
-			nr_more_io++;
-	}
+	list_for_each_entry(inode, &wb->b_dirty, i_list)
+		nr_dirty++;
+	list_for_each_entry(inode, &wb->b_io, i_list)
+		nr_io++;
+	list_for_each_entry(inode, &wb->b_more_io, i_list)
+		nr_more_io++;
 	spin_unlock(&inode_lock);
 
-	get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
+	global_dirty_limits(&background_thresh, &dirty_thresh);
+	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
@@ -98,19 +91,16 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "BdiDirtyThresh:   %8lu kB\n"
 		   "DirtyThresh:      %8lu kB\n"
 		   "BackgroundThresh: %8lu kB\n"
-		   "WritebackThreads: %8lu\n"
 		   "b_dirty:          %8lu\n"
 		   "b_io:             %8lu\n"
 		   "b_more_io:        %8lu\n"
 		   "bdi_list:         %8u\n"
-		   "state:            %8lx\n"
-		   "wb_list:          %8u\n",
+		   "state:            %8lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
 		   K(bdi_thresh), K(dirty_thresh),
-		   K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io,
-		   !list_empty(&bdi->bdi_list), bdi->state,
-		   !list_empty(&bdi->wb_list));
+		   K(background_thresh), nr_dirty, nr_io, nr_more_io,
+		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
 	return 0;
@@ -247,7 +237,6 @@ static int __init default_bdi_init(void)
 	sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
 	BUG_ON(IS_ERR(sync_supers_tsk));
 
-	init_timer(&sync_supers_timer);
 	setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
 	bdi_arm_supers_timer();
 
@@ -259,77 +248,6 @@ static int __init default_bdi_init(void)
 }
 subsys_initcall(default_bdi_init);
 
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
-{
-	memset(wb, 0, sizeof(*wb));
-
-	wb->bdi = bdi;
-	wb->last_old_flush = jiffies;
-	INIT_LIST_HEAD(&wb->b_dirty);
-	INIT_LIST_HEAD(&wb->b_io);
-	INIT_LIST_HEAD(&wb->b_more_io);
-}
-
-static void bdi_task_init(struct backing_dev_info *bdi,
-			  struct bdi_writeback *wb)
-{
-	struct task_struct *tsk = current;
-
-	spin_lock(&bdi->wb_lock);
-	list_add_tail_rcu(&wb->list, &bdi->wb_list);
-	spin_unlock(&bdi->wb_lock);
-
-	tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
-	set_freezable();
-
-	/*
-	 * Our parent may run at a different priority, just set us to normal
-	 */
-	set_user_nice(tsk, 0);
-}
-
-static int bdi_start_fn(void *ptr)
-{
-	struct bdi_writeback *wb = ptr;
-	struct backing_dev_info *bdi = wb->bdi;
-	int ret;
-
-	/*
-	 * Add us to the active bdi_list
-	 */
-	spin_lock_bh(&bdi_lock);
-	list_add_rcu(&bdi->bdi_list, &bdi_list);
-	spin_unlock_bh(&bdi_lock);
-
-	bdi_task_init(bdi, wb);
-
-	/*
-	 * Clear pending bit and wakeup anybody waiting to tear us down
-	 */
-	clear_bit(BDI_pending, &bdi->state);
-	smp_mb__after_clear_bit();
-	wake_up_bit(&bdi->state, BDI_pending);
-
-	ret = bdi_writeback_task(wb);
-
-	/*
-	 * Remove us from the list
-	 */
-	spin_lock(&bdi->wb_lock);
-	list_del_rcu(&wb->list);
-	spin_unlock(&bdi->wb_lock);
-
-	/*
-	 * Flush any work that raced with us exiting. No new work
-	 * will be added, since this bdi isn't discoverable anymore.
-	 */
-	if (!list_empty(&bdi->work_list))
-		wb_do_writeback(wb, 1);
-
-	wb->task = NULL;
-	return ret;
-}
-
 int bdi_has_dirty_io(struct backing_dev_info *bdi)
 {
 	return wb_has_dirty_io(&bdi->wb);
@@ -348,10 +266,10 @@ static void bdi_flush_io(struct backing_dev_info *bdi)
 }
 
 /*
- * kupdated() used to do this. We cannot do it from the bdi_forker_task()
+ * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
  * or we risk deadlocking on ->s_umount. The longer term solution would be
  * to implement sync_supers_bdi() or similar and simply do it from the
- * bdi writeback tasks individually.
+ * bdi writeback thread individually.
  */
 static int bdi_sync_supers(void *unused)
 {
@@ -387,144 +305,198 @@ static void sync_supers_timer_fn(unsigned long unused)
 	bdi_arm_supers_timer();
 }
 
-static int bdi_forker_task(void *ptr)
+static void wakeup_timer_fn(unsigned long data)
+{
+	struct backing_dev_info *bdi = (struct backing_dev_info *)data;
+
+	spin_lock_bh(&bdi->wb_lock);
+	if (bdi->wb.task) {
+		trace_writeback_wake_thread(bdi);
+		wake_up_process(bdi->wb.task);
+	} else {
+		/*
+		 * When bdi tasks are inactive for long time, they are killed.
+		 * In this case we have to wake-up the forker thread which
+		 * should create and run the bdi thread.
+		 */
+		trace_writeback_wake_forker_thread(bdi);
+		wake_up_process(default_backing_dev_info.wb.task);
+	}
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
+/*
+ * This function is used when the first inode for this bdi is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ */
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+{
+	unsigned long timeout;
+
+	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+	mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
+}
+
+/*
+ * Calculate the longest interval (jiffies) bdi threads are allowed to be
+ * inactive.
+ */
+static unsigned long bdi_longest_inactive(void)
+{
+	unsigned long interval;
+
+	interval = msecs_to_jiffies(dirty_writeback_interval * 10);
+	return max(5UL * 60 * HZ, interval);
+}
+
+static int bdi_forker_thread(void *ptr)
 {
 	struct bdi_writeback *me = ptr;
 
-	bdi_task_init(me->bdi, me);
+	current->flags |= PF_FLUSHER | PF_SWAPWRITE;
+	set_freezable();
+
+	/*
+	 * Our parent may run at a different priority, just set us to normal
+	 */
+	set_user_nice(current, 0);
 
 	for (;;) {
-		struct backing_dev_info *bdi, *tmp;
-		struct bdi_writeback *wb;
+		struct task_struct *task = NULL;
+		struct backing_dev_info *bdi;
+		enum {
+			NO_ACTION,   /* Nothing to do */
+			FORK_THREAD, /* Fork bdi thread */
+			KILL_THREAD, /* Kill inactive bdi thread */
+		} action = NO_ACTION;
 
 		/*
 		 * Temporary measure, we want to make sure we don't see
 		 * dirty data on the default backing_dev_info
 		 */
-		if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+		if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {
+			del_timer(&me->wakeup_timer);
 			wb_do_writeback(me, 0);
+		}
 
 		spin_lock_bh(&bdi_lock);
+		set_current_state(TASK_INTERRUPTIBLE);
 
-		/*
-		 * Check if any existing bdi's have dirty data without
-		 * a thread registered. If so, set that up.
-		 */
-		list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
-			if (bdi->wb.task)
-				continue;
-			if (list_empty(&bdi->work_list) &&
-			    !bdi_has_dirty_io(bdi))
+		list_for_each_entry(bdi, &bdi_list, bdi_list) {
+			bool have_dirty_io;
+
+			if (!bdi_cap_writeback_dirty(bdi) ||
+			     bdi_cap_flush_forker(bdi))
 				continue;
 
-			bdi_add_default_flusher_task(bdi);
-		}
+			WARN(!test_bit(BDI_registered, &bdi->state),
+			     "bdi %p/%s is not registered!\n", bdi, bdi->name);
 
-		set_current_state(TASK_INTERRUPTIBLE);
+			have_dirty_io = !list_empty(&bdi->work_list) ||
+					wb_has_dirty_io(&bdi->wb);
 
-		if (list_empty(&bdi_pending_list)) {
-			unsigned long wait;
+			/*
+			 * If the bdi has work to do, but the thread does not
+			 * exist - create it.
+			 */
+			if (!bdi->wb.task && have_dirty_io) {
+				/*
+				 * Set the pending bit - if someone will try to
+				 * unregister this bdi - it'll wait on this bit.
+				 */
+				set_bit(BDI_pending, &bdi->state);
+				action = FORK_THREAD;
+				break;
+			}
+
+			spin_lock(&bdi->wb_lock);
+
+			/*
+			 * If there is no work to do and the bdi thread was
+			 * inactive long enough - kill it. The wb_lock is taken
+			 * to make sure no-one adds more work to this bdi and
+			 * wakes the bdi thread up.
+			 */
+			if (bdi->wb.task && !have_dirty_io &&
+			    time_after(jiffies, bdi->wb.last_active +
+						bdi_longest_inactive())) {
+				task = bdi->wb.task;
+				bdi->wb.task = NULL;
+				spin_unlock(&bdi->wb_lock);
+				set_bit(BDI_pending, &bdi->state);
+				action = KILL_THREAD;
+				break;
+			}
+			spin_unlock(&bdi->wb_lock);
+		}
+		spin_unlock_bh(&bdi_lock);
 
-			spin_unlock_bh(&bdi_lock);
-			wait = msecs_to_jiffies(dirty_writeback_interval * 10);
-			if (wait)
-				schedule_timeout(wait);
+		/* Keep working if default bdi still has things to do */
+		if (!list_empty(&me->bdi->work_list))
+			__set_current_state(TASK_RUNNING);
+
+		switch (action) {
+		case FORK_THREAD:
+			__set_current_state(TASK_RUNNING);
+			task = kthread_run(bdi_writeback_thread, &bdi->wb, "flush-%s",
+					   dev_name(bdi->dev));
+			if (IS_ERR(task)) {
+				/*
+				 * If thread creation fails, force writeout of
+				 * the bdi from the thread.
+				 */
+				bdi_flush_io(bdi);
+			} else {
+				/*
+				 * The spinlock makes sure we do not lose
+				 * wake-ups when racing with 'bdi_queue_work()'.
+				 */
+				spin_lock_bh(&bdi->wb_lock);
+				bdi->wb.task = task;
+				spin_unlock_bh(&bdi->wb_lock);
+			}
+			break;
+
+		case KILL_THREAD:
+			__set_current_state(TASK_RUNNING);
+			kthread_stop(task);
+			break;
+
+		case NO_ACTION:
+			if (!wb_has_dirty_io(me) || !dirty_writeback_interval)
+				/*
+				 * There are no dirty data. The only thing we
+				 * should now care about is checking for
+				 * inactive bdi threads and killing them. Thus,
+				 * let's sleep for longer time, save energy and
+				 * be friendly for battery-driven devices.
+				 */
+				schedule_timeout(bdi_longest_inactive());
 			else
-				schedule();
+				schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
 			try_to_freeze();
+			/* Back to the main loop */
 			continue;
 		}
 
-		__set_current_state(TASK_RUNNING);
-
-		/*
-		 * This is our real job - check for pending entries in
-		 * bdi_pending_list, and create the tasks that got added
-		 */
-		bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
-				 bdi_list);
-		list_del_init(&bdi->bdi_list);
-		spin_unlock_bh(&bdi_lock);
-
-		wb = &bdi->wb;
-		wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
-					dev_name(bdi->dev));
 		/*
-		 * If task creation fails, then readd the bdi to
-		 * the pending list and force writeout of the bdi
-		 * from this forker thread. That will free some memory
-		 * and we can try again.
+		 * Clear pending bit and wakeup anybody waiting to tear us down.
 		 */
-		if (IS_ERR(wb->task)) {
-			wb->task = NULL;
-
-			/*
-			 * Add this 'bdi' to the back, so we get
-			 * a chance to flush other bdi's to free
-			 * memory.
-			 */
-			spin_lock_bh(&bdi_lock);
-			list_add_tail(&bdi->bdi_list, &bdi_pending_list);
-			spin_unlock_bh(&bdi_lock);
-
-			bdi_flush_io(bdi);
-		}
+		clear_bit(BDI_pending, &bdi->state);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&bdi->state, BDI_pending);
 	}
 
 	return 0;
 }
 
-static void bdi_add_to_pending(struct rcu_head *head)
-{
-	struct backing_dev_info *bdi;
-
-	bdi = container_of(head, struct backing_dev_info, rcu_head);
-	INIT_LIST_HEAD(&bdi->bdi_list);
-
-	spin_lock(&bdi_lock);
-	list_add_tail(&bdi->bdi_list, &bdi_pending_list);
-	spin_unlock(&bdi_lock);
-
-	/*
-	 * We are now on the pending list, wake up bdi_forker_task()
-	 * to finish the job and add us back to the active bdi_list
-	 */
-	wake_up_process(default_backing_dev_info.wb.task);
-}
-
-/*
- * Add the default flusher task that gets created for any bdi
- * that has dirty data pending writeout
- */
-void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
-{
-	if (!bdi_cap_writeback_dirty(bdi))
-		return;
-
-	if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
-		printk(KERN_ERR "bdi %p/%s is not registered!\n",
-							bdi, bdi->name);
-		return;
-	}
-
-	/*
-	 * Check with the helper whether to proceed adding a task. Will only
-	 * abort if we two or more simultanous calls to
-	 * bdi_add_default_flusher_task() occured, further additions will block
-	 * waiting for previous additions to finish.
-	 */
-	if (!test_and_set_bit(BDI_pending, &bdi->state)) {
-		list_del_rcu(&bdi->bdi_list);
-
-		/*
-		 * We must wait for the current RCU period to end before
-		 * moving to the pending list. So schedule that operation
-		 * from an RCU callback.
-		 */
-		call_rcu(&bdi->rcu_head, bdi_add_to_pending);
-	}
-}
-
 /*
  * Remove bdi from bdi_list, and ensure that it is no longer visible
  */
@@ -541,23 +513,16 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
 {
 	va_list args;
-	int ret = 0;
 	struct device *dev;
 
 	if (bdi->dev)	/* The driver needs to use separate queues per device */
-		goto exit;
+		return 0;
 
 	va_start(args, fmt);
 	dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
 	va_end(args);
-	if (IS_ERR(dev)) {
-		ret = PTR_ERR(dev);
-		goto exit;
-	}
-
-	spin_lock_bh(&bdi_lock);
-	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
-	spin_unlock_bh(&bdi_lock);
+	if (IS_ERR(dev))
+		return PTR_ERR(dev);
 
 	bdi->dev = dev;
 
@@ -569,21 +534,21 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 	if (bdi_cap_flush_forker(bdi)) {
 		struct bdi_writeback *wb = &bdi->wb;
 
-		wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
+		wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s",
 						dev_name(dev));
-		if (IS_ERR(wb->task)) {
-			wb->task = NULL;
-			ret = -ENOMEM;
-
-			bdi_remove_from_list(bdi);
-			goto exit;
-		}
+		if (IS_ERR(wb->task))
+			return PTR_ERR(wb->task);
 	}
 
 	bdi_debug_register(bdi, dev_name(dev));
 	set_bit(BDI_registered, &bdi->state);
-exit:
-	return ret;
+
+	spin_lock_bh(&bdi_lock);
+	list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+	spin_unlock_bh(&bdi_lock);
+
+	trace_writeback_bdi_register(bdi);
+	return 0;
 }
 EXPORT_SYMBOL(bdi_register);
 
@@ -598,31 +563,29 @@ EXPORT_SYMBOL(bdi_register_dev);
  */
 static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 {
-	struct bdi_writeback *wb;
-
 	if (!bdi_cap_writeback_dirty(bdi))
 		return;
 
 	/*
-	 * If setup is pending, wait for that to complete first
+	 * Make sure nobody finds us on the bdi_list anymore
 	 */
-	wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
-			TASK_UNINTERRUPTIBLE);
+	bdi_remove_from_list(bdi);
 
 	/*
-	 * Make sure nobody finds us on the bdi_list anymore
+	 * If setup is pending, wait for that to complete first
 	 */
-	bdi_remove_from_list(bdi);
+	wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+			TASK_UNINTERRUPTIBLE);
 
 	/*
-	 * Finally, kill the kernel threads. We don't need to be RCU
+	 * Finally, kill the kernel thread. We don't need to be RCU
 	 * safe anymore, since the bdi is gone from visibility. Force
 	 * unfreeze of the thread before calling kthread_stop(), otherwise
 	 * it would never exet if it is currently stuck in the refrigerator.
 	 */
-	list_for_each_entry(wb, &bdi->wb_list, list) {
-		thaw_process(wb->task);
-		kthread_stop(wb->task);
+	if (bdi->wb.task) {
+		thaw_process(bdi->wb.task);
+		kthread_stop(bdi->wb.task);
 	}
 }
 
@@ -644,7 +607,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
+		del_timer_sync(&bdi->wb.wakeup_timer);
 
 		if (!bdi_cap_flush_forker(bdi))
 			bdi_wb_shutdown(bdi);
@@ -655,6 +620,18 @@ void bdi_unregister(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_unregister);
 
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+	memset(wb, 0, sizeof(*wb));
+
+	wb->bdi = bdi;
+	wb->last_old_flush = jiffies;
+	INIT_LIST_HEAD(&wb->b_dirty);
+	INIT_LIST_HEAD(&wb->b_io);
+	INIT_LIST_HEAD(&wb->b_more_io);
+	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+}
+
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -665,9 +642,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = PROP_FRAC_BASE;
 	spin_lock_init(&bdi->wb_lock);
-	INIT_RCU_HEAD(&bdi->rcu_head);
 	INIT_LIST_HEAD(&bdi->bdi_list);
-	INIT_LIST_HEAD(&bdi->wb_list);
 	INIT_LIST_HEAD(&bdi->work_list);
 
 	bdi_wb_init(&bdi->wb, bdi);
diff --git a/mm/filemap.c b/mm/filemap.c
index 20e5642e9f9..3d4df44e422 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2238,14 +2238,12 @@ static ssize_t generic_perform_write(struct file *file,
 
 	do {
 		struct page *page;
-		pgoff_t index;		/* Pagecache index for current page */
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 		void *fsdata;
 
 		offset = (pos & (PAGE_CACHE_SIZE - 1));
-		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
 						iov_iter_count(i));
 
diff --git a/mm/highmem.c b/mm/highmem.c
index 66baa20f78f..7a0aa1be499 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -26,6 +26,7 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
+#include <linux/kgdb.h>
 #include <asm/tlbflush.h>
 
 /*
@@ -470,6 +471,12 @@ void debug_kmap_atomic(enum km_type type)
 			warn_count--;
 		}
 	}
+#ifdef CONFIG_KGDB_KDB
+	if (unlikely(type == KM_KDB && atomic_read(&kgdb_active) == -1)) {
+		WARN_ON(1);
+		warn_count--;
+	}
+#endif /* CONFIG_KGDB_KDB */
 }
 
 #endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 54d42b009db..cc5be788a39 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -18,6 +18,9 @@
 #include <linux/bootmem.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -220,6 +223,12 @@ static pgoff_t vma_hugecache_offset(struct hstate *h,
 			(vma->vm_pgoff >> huge_page_order(h));
 }
 
+pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
+				     unsigned long address)
+{
+	return vma_hugecache_offset(hstate_vma(vma), vma, address);
+}
+
 /*
  * Return the size of the pages allocated when backing a VMA. In the majority
  * cases this will be same size as used by the page table entries.
@@ -552,6 +561,7 @@ static void free_huge_page(struct page *page)
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
+	BUG_ON(page_mapcount(page));
 	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
@@ -605,6 +615,8 @@ int PageHuge(struct page *page)
 	return dtor == free_huge_page;
 }
 
+EXPORT_SYMBOL_GPL(PageHuge);
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
@@ -2129,6 +2141,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
+			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
 		spin_unlock(&src->page_table_lock);
@@ -2140,6 +2153,19 @@ nomem:
 	return -ENOMEM;
 }
 
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
+		return 1;
+	} else
+		return 0;
+}
+
 void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end, struct page *ref_page)
 {
@@ -2198,6 +2224,12 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		if (huge_pte_none(pte))
 			continue;
 
+		/*
+		 * HWPoisoned hugepage is already unmapped and dropped reference
+		 */
+		if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+			continue;
+
 		page = pte_page(pte);
 		if (pte_dirty(pte))
 			set_page_dirty(page);
@@ -2207,6 +2239,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	flush_tlb_range(vma, start, end);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	list_for_each_entry_safe(page, tmp, &page_list, lru) {
+		page_remove_rmap(page);
 		list_del(&page->lru);
 		put_page(page);
 	}
@@ -2272,6 +2305,9 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	return 1;
 }
 
+/*
+ * Hugetlb_cow() should be called with page lock of the original hugepage held.
+ */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
 			struct page *pagecache_page)
@@ -2286,8 +2322,13 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 retry_avoidcopy:
 	/* If no-one else is actually using this page, avoid the copy
 	 * and just make the page writable */
-	avoidcopy = (page_count(old_page) == 1);
+	avoidcopy = (page_mapcount(old_page) == 1);
 	if (avoidcopy) {
+		if (!trylock_page(old_page)) {
+			if (PageAnon(old_page))
+				page_move_anon_rmap(old_page, vma, address);
+		} else
+			unlock_page(old_page);
 		set_huge_ptep_writable(vma, address, ptep);
 		return 0;
 	}
@@ -2338,6 +2379,13 @@ retry_avoidcopy:
 		return -PTR_ERR(new_page);
 	}
 
+	/*
+	 * When the original hugepage is shared one, it does not have
+	 * anon_vma prepared.
+	 */
+	if (unlikely(anon_vma_prepare(vma)))
+		return VM_FAULT_OOM;
+
 	copy_huge_page(new_page, old_page, address, vma);
 	__SetPageUptodate(new_page);
 
@@ -2349,11 +2397,19 @@ retry_avoidcopy:
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		/* Break COW */
+		mmu_notifier_invalidate_range_start(mm,
+			address & huge_page_mask(h),
+			(address & huge_page_mask(h)) + huge_page_size(h));
 		huge_ptep_clear_flush(vma, address, ptep);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
+		page_remove_rmap(old_page);
+		hugepage_add_anon_rmap(new_page, vma, address);
 		/* Make the old page be freed below */
 		new_page = old_page;
+		mmu_notifier_invalidate_range_end(mm,
+			address & huge_page_mask(h),
+			(address & huge_page_mask(h)) + huge_page_size(h));
 	}
 	page_cache_release(new_page);
 	page_cache_release(old_page);
@@ -2452,10 +2508,29 @@ retry:
 			spin_lock(&inode->i_lock);
 			inode->i_blocks += blocks_per_huge_page(h);
 			spin_unlock(&inode->i_lock);
+			page_dup_rmap(page);
 		} else {
 			lock_page(page);
-			page->mapping = HUGETLB_POISON;
+			if (unlikely(anon_vma_prepare(vma))) {
+				ret = VM_FAULT_OOM;
+				goto backout_unlocked;
+			}
+			hugepage_add_new_anon_rmap(page, vma, address);
 		}
+	} else {
+		page_dup_rmap(page);
+	}
+
+	/*
+	 * Since memory error handler replaces pte into hwpoison swap entry
+	 * at the time of error handling, a process which reserved but not have
+	 * the mapping to the error hugepage does not have hwpoison swap entry.
+	 * So we need to block accesses from such a process by checking
+	 * PG_hwpoison bit here.
+	 */
+	if (unlikely(PageHWPoison(page))) {
+		ret = VM_FAULT_HWPOISON;
+		goto backout_unlocked;
 	}
 
 	/*
@@ -2507,10 +2582,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *ptep;
 	pte_t entry;
 	int ret;
+	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
 
+	ptep = huge_pte_offset(mm, address);
+	if (ptep) {
+		entry = huge_ptep_get(ptep);
+		if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+			return VM_FAULT_HWPOISON;
+	}
+
 	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
 	if (!ptep)
 		return VM_FAULT_OOM;
@@ -2548,6 +2631,11 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 								vma, address);
 	}
 
+	if (!pagecache_page) {
+		page = pte_page(entry);
+		lock_page(page);
+	}
+
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (unlikely(!pte_same(entry, h