Merge branch 'master' into pm-sleep

* master: (848 commits)
  SELinux: Fix RCU deref check warning in sel_netport_insert()
  binary_sysctl(): fix memory leak
  mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
  ipmi_watchdog: restore settings when BMC reset
  oom: fix integer overflow of points in oom_badness
  memcg: keep root group unchanged if creation fails
  nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
  nilfs2: unbreak compat ioctl
  cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
  evm: prevent racing during tfm allocation
  evm: key must be set once during initialization
  mmc: vub300: fix type of firmware_rom_wait_states module parameter
  Revert "mmc: enable runtime PM by default"
  mmc: sdhci: remove "state" argument from sdhci_suspend_host
  x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
  IB/qib: Correct sense on freectxts increment and decrement
  RDMA/cma: Verify private data length
  cgroups: fix a css_set not found bug in cgroup_attach_proc
  oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
  Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
  ...

Conflicts:
	kernel/cgroup_freezer.c

15 files changed, 431 insertions, 219 deletions

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 98ab240072e5..704a2ba08ea8 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -64,6 +64,8 @@ struct btrfs_worker_thread {
 	int idle;
 };
 
+static int __btrfs_start_workers(struct btrfs_workers *workers);
+
 /*
  * btrfs_start_workers uses kthread_run, which can block waiting for memory
  * for a very long time.  It will actually throttle on page writeback,
@@ -88,27 +90,10 @@ static void start_new_worker_func(struct btrfs_work *work)
 {
 	struct worker_start *start;
 	start = container_of(work, struct worker_start, work);
-	btrfs_start_workers(start->queue, 1);
+	__btrfs_start_workers(start->queue);
 	kfree(start);
 }
 
-static int start_new_worker(struct btrfs_workers *queue)
-{
-	struct worker_start *start;
-	int ret;
-
-	start = kzalloc(sizeof(*start), GFP_NOFS);
-	if (!start)
-		return -ENOMEM;
-
-	start->work.func = start_new_worker_func;
-	start->queue = queue;
-	ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
-	if (ret)
-		kfree(start);
-	return ret;
-}
-
 /*
  * helper function to move a thread onto the idle list after it
  * has finished some requests.
@@ -153,12 +138,20 @@ static void check_busy_worker(struct btrfs_worker_thread *worker)
 static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
 {
 	struct btrfs_workers *workers = worker->workers;
+	struct worker_start *start;
 	unsigned long flags;
 
 	rmb();
 	if (!workers->atomic_start_pending)
 		return;
 
+	start = kzalloc(sizeof(*start), GFP_NOFS);
+	if (!start)
+		return;
+
+	start->work.func = start_new_worker_func;
+	start->queue = workers;
+
 	spin_lock_irqsave(&workers->lock, flags);
 	if (!workers->atomic_start_pending)
 		goto out;
@@ -170,10 +163,11 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
 
 	workers->num_workers_starting += 1;
 	spin_unlock_irqrestore(&workers->lock, flags);
-	start_new_worker(workers);
+	btrfs_queue_worker(workers->atomic_worker_start, &start->work);
 	return;
 
 out:
+	kfree(start);
 	spin_unlock_irqrestore(&workers->lock, flags);
 }
 
@@ -331,7 +325,7 @@ again:
 			run_ordered_completions(worker->workers, work);
 
 			check_pending_worker_creates(worker);
-
+			cond_resched();
 		}
 
 		spin_lock_irq(&worker->lock);
@@ -462,56 +456,55 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
  * starts new worker threads.  This does not enforce the max worker
  * count in case you need to temporarily go past it.
  */
-static int __btrfs_start_workers(struct btrfs_workers *workers,
-				 int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers)
 {
 	struct btrfs_worker_thread *worker;
 	int ret = 0;
-	int i;
 
-	for (i = 0; i < num_workers; i++) {
-		worker = kzalloc(sizeof(*worker), GFP_NOFS);
-		if (!worker) {
-			ret = -ENOMEM;
-			goto fail;
-		}
+	worker = kzalloc(sizeof(*worker), GFP_NOFS);
+	if (!worker) {
+		ret = -ENOMEM;
+		goto fail;
+	}
 
-		INIT_LIST_HEAD(&worker->pending);
-		INIT_LIST_HEAD(&worker->prio_pending);
-		INIT_LIST_HEAD(&worker->worker_list);
-		spin_lock_init(&worker->lock);
-
-		atomic_set(&worker->num_pending, 0);
-		atomic_set(&worker->refs, 1);
-		worker->workers = workers;
-		worker->task = kthread_run(worker_loop, worker,
-					   "btrfs-%s-%d", workers->name,
-					   workers->num_workers + i);
-		if (IS_ERR(worker->task)) {
-			ret = PTR_ERR(worker->task);
-			kfree(worker);
-			goto fail;
-		}
-		spin_lock_irq(&workers->lock);
-		list_add_tail(&worker->worker_list, &workers->idle_list);
-		worker->idle = 1;
-		workers->num_workers++;
-		workers->num_workers_starting--;
-		WARN_ON(workers->num_workers_starting < 0);
-		spin_unlock_irq(&workers->lock);
+	INIT_LIST_HEAD(&worker->pending);
+	INIT_LIST_HEAD(&worker->prio_pending);
+	INIT_LIST_HEAD(&worker->worker_list);
+	spin_lock_init(&worker->lock);
+
+	atomic_set(&worker->num_pending, 0);
+	atomic_set(&worker->refs, 1);
+	worker->workers = workers;
+	worker->task = kthread_run(worker_loop, worker,
+				   "btrfs-%s-%d", workers->name,
+				   workers->num_workers + 1);
+	if (IS_ERR(worker->task)) {
+		ret = PTR_ERR(worker->task);
+		kfree(worker);
+		goto fail;
 	}
+	spin_lock_irq(&workers->lock);
+	list_add_tail(&worker->worker_list, &workers->idle_list);
+	worker->idle = 1;
+	workers->num_workers++;
+	workers->num_workers_starting--;
+	WARN_ON(workers->num_workers_starting < 0);
+	spin_unlock_irq(&workers->lock);
+
 	return 0;
 fail:
-	btrfs_stop_workers(workers);
+	spin_lock_irq(&workers->lock);
+	workers->num_workers_starting--;
+	spin_unlock_irq(&workers->lock);
 	return ret;
 }
 
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+int btrfs_start_workers(struct btrfs_workers *workers)
 {
 	spin_lock_irq(&workers->lock);
-	workers->num_workers_starting += num_workers;
+	workers->num_workers_starting++;
 	spin_unlock_irq(&workers->lock);
-	return __btrfs_start_workers(workers, num_workers);
+	return __btrfs_start_workers(workers);
 }
 
 /*
@@ -568,6 +561,7 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
 	struct btrfs_worker_thread *worker;
 	unsigned long flags;
 	struct list_head *fallback;
+	int ret;
 
 again:
 	spin_lock_irqsave(&workers->lock, flags);
@@ -584,7 +578,9 @@ again:
 			workers->num_workers_starting++;
 			spin_unlock_irqrestore(&workers->lock, flags);
 			/* we're below the limit, start another worker */
-			__btrfs_start_workers(workers, 1);
+			ret = __btrfs_start_workers(workers);
+			if (ret)
+				goto fallback;
 			goto again;
 		}
 	}
@@ -665,7 +661,7 @@ void btrfs_set_work_high_prio(struct btrfs_work *work)
 /*
  * places a struct btrfs_work into the pending queue of one of the kthreads
  */
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
 {
 	struct btrfs_worker_thread *worker;
 	unsigned long flags;
@@ -673,7 +669,7 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
 
 	/* don't requeue something already on a list */
 	if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
-		goto out;
+		return;
 
 	worker = find_worker(workers);
 	if (workers->ordered) {
@@ -712,7 +708,4 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
 	if (wake)
 		wake_up_process(worker->task);
 	spin_unlock_irqrestore(&worker->lock, flags);
-
-out:
-	return 0;
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 5077746cf85e..f34cc31fa3c9 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -109,8 +109,8 @@ struct btrfs_workers {
 	char *name;
 };
 
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
+int btrfs_start_workers(struct btrfs_workers *workers);
 int btrfs_stop_workers(struct btrfs_workers *workers);
 void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
 			struct btrfs_workers *async_starter);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 04a5dfcee5a1..67385033323d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2369,6 +2369,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
 int btrfs_block_rsv_refill(struct btrfs_root *root,
 			  struct btrfs_block_rsv *block_rsv,
 			  u64 min_reserved);
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+				   struct btrfs_block_rsv *block_rsv,
+				   u64 min_reserved);
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 			    struct btrfs_block_rsv *dst_rsv,
 			    u64 num_bytes);
@@ -2689,7 +2692,8 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
 int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode, int flags);
+int btrfs_dirty_inode(struct inode *inode);
+int btrfs_update_time(struct file *file);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 5b163572e0ca..9c1eccc2c503 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -640,8 +640,8 @@ static int btrfs_delayed_inode_reserve_metadata(
 	 * Now if src_rsv == delalloc_block_rsv we'll let it just steal since
 	 * we're accounted for.
 	 */
-	if (!trans->bytes_reserved &&
-	    src_rsv != &root->fs_info->delalloc_block_rsv) {
+	if (!src_rsv || (!trans->bytes_reserved &&
+	    src_rsv != &root->fs_info->delalloc_block_rsv)) {
 		ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
 		/*
 		 * Since we're under a transaction reserve_metadata_bytes could
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b09175901521..f99a099a7747 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2190,19 +2190,27 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->endio_meta_write_workers.idle_thresh = 2;
 	fs_info->readahead_workers.idle_thresh = 2;
 
-	btrfs_start_workers(&fs_info->workers, 1);
-	btrfs_start_workers(&fs_info->generic_worker, 1);
-	btrfs_start_workers(&fs_info->submit_workers, 1);
-	btrfs_start_workers(&fs_info->delalloc_workers, 1);
-	btrfs_start_workers(&fs_info->fixup_workers, 1);
-	btrfs_start_workers(&fs_info->endio_workers, 1);
-	btrfs_start_workers(&fs_info->endio_meta_workers, 1);
-	btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
-	btrfs_start_workers(&fs_info->endio_write_workers, 1);
-	btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
-	btrfs_start_workers(&fs_info->delayed_workers, 1);
-	btrfs_start_workers(&fs_info->caching_workers, 1);
-	btrfs_start_workers(&fs_info->readahead_workers, 1);
+	/*
+	 * btrfs_start_workers can really only fail because of ENOMEM so just
+	 * return -ENOMEM if any of these fail.
+	 */
+	ret = btrfs_start_workers(&fs_info->workers);
+	ret |= btrfs_start_workers(&fs_info->generic_worker);
+	ret |= btrfs_start_workers(&fs_info->submit_workers);
+	ret |= btrfs_start_workers(&fs_info->delalloc_workers);
+	ret |= btrfs_start_workers(&fs_info->fixup_workers);
+	ret |= btrfs_start_workers(&fs_info->endio_workers);
+	ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
+	ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
+	ret |= btrfs_start_workers(&fs_info->endio_write_workers);
+	ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
+	ret |= btrfs_start_workers(&fs_info->delayed_workers);
+	ret |= btrfs_start_workers(&fs_info->caching_workers);
+	ret |= btrfs_start_workers(&fs_info->readahead_workers);
+	if (ret) {
+		ret = -ENOMEM;
+		goto fail_sb_buffer;
+	}
 
 	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
 	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 930ae8949737..f5fbe576d2ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2822,7 +2822,7 @@ out_free:
 	btrfs_release_path(path);
 out:
 	spin_lock(&block_group->lock);
-	if (!ret)
+	if (!ret && dcs == BTRFS_DC_SETUP)
 		block_group->cache_generation = trans->transid;
 	block_group->disk_cache_state = dcs;
 	spin_unlock(&block_group->lock);
@@ -3888,9 +3888,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
 	return ret;
 }
 
-int btrfs_block_rsv_refill(struct btrfs_root *root,
-			  struct btrfs_block_rsv *block_rsv,
-			  u64 min_reserved)
+static inline int __btrfs_block_rsv_refill(struct btrfs_root *root,
+					   struct btrfs_block_rsv *block_rsv,
+					   u64 min_reserved, int flush)
 {
 	u64 num_bytes = 0;
 	int ret = -ENOSPC;
@@ -3909,7 +3909,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 	if (!ret)
 		return 0;
 
-	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1);
+	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
 	if (!ret) {
 		block_rsv_add_bytes(block_rsv, num_bytes, 0);
 		return 0;
@@ -3918,6 +3918,20 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 	return ret;
 }
 
+int btrfs_block_rsv_refill(struct btrfs_root *root,
+			   struct btrfs_block_rsv *block_rsv,
+			   u64 min_reserved)
+{
+	return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 1);
+}
+
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+				   struct btrfs_block_rsv *block_rsv,
+				   u64 min_reserved)
+{
+	return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 0);
+}
+
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 			    struct btrfs_block_rsv *dst_rsv,
 			    u64 num_bytes)
@@ -4190,12 +4204,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
 	u64 to_reserve = 0;
+	u64 csum_bytes;
 	unsigned nr_extents = 0;
+	int extra_reserve = 0;
 	int flush = 1;
 	int ret;
 
+	/* Need to be holding the i_mutex here if we aren't free space cache */
 	if (btrfs_is_free_space_inode(root, inode))
 		flush = 0;
+	else
+		WARN_ON(!mutex_is_locked(&inode->i_mutex));
 
 	if (flush && btrfs_transaction_in_commit(root->fs_info))
 		schedule_timeout(1);
@@ -4206,11 +4225,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	BTRFS_I(inode)->outstanding_extents++;
 
 	if (BTRFS_I(inode)->outstanding_extents >
-	    BTRFS_I(inode)->reserved_extents) {
+	    BTRFS_I(inode)->reserved_extents)
 		nr_extents = BTRFS_I(inode)->outstanding_extents -
 			BTRFS_I(inode)->reserved_extents;
-		BTRFS_I(inode)->reserved_extents += nr_extents;
-	}
 
 	/*
 	 * Add an item to reserve for updating the inode when we complete the
@@ -4218,11 +4235,12 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	 */
 	if (!BTRFS_I(inode)->delalloc_meta_reserved) {
 		nr_extents++;
-		BTRFS_I(inode)->delalloc_meta_reserved = 1;
+		extra_reserve = 1;
 	}
 
 	to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
 	to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+	csum_bytes = BTRFS_I(inode)->csum_bytes;
 	spin_unlock(&BTRFS_I(inode)->lock);
 
 	ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
@@ -4232,22 +4250,35 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 		spin_lock(&BTRFS_I(inode)->lock);
 		dropped = drop_outstanding_extent(inode);
-		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
-		spin_unlock(&BTRFS_I(inode)->lock);
-		to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
 		/*
-		 * Somebody could have come in and twiddled with the
-		 * reservation, so if we have to free more than we would have
-		 * reserved from this reservation go ahead and release those
-		 * bytes.
+		 * If the inodes csum_bytes is the same as the original
+		 * csum_bytes then we know we haven't raced with any free()ers
+		 * so we can just reduce our inodes csum bytes and carry on.
+		 * Otherwise we have to do the normal free thing to account for
+		 * the case that the free side didn't free up its reserve
+		 * because of this outstanding reservation.
 		 */
-		to_free -= to_reserve;
+		if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+			calc_csum_metadata_size(inode, num_bytes, 0);
+		else
+			to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+		spin_unlock(&BTRFS_I(inode)->lock);
+		if (dropped)
+			to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
 		if (to_free)
 			btrfs_block_rsv_release(root, block_rsv, to_free);
 		return ret;
 	}
 
+	spin_lock(&BTRFS_I(inode)->lock);
+	if (extra_reserve) {
+		BTRFS_I(inode)->delalloc_meta_reserved = 1;
+		nr_extents--;
+	}
+	BTRFS_I(inode)->reserved_extents += nr_extents;
+	spin_unlock(&BTRFS_I(inode)->lock);
+
 	block_rsv_add_bytes(block_rsv, to_reserve, 1);
 
 	return 0;
@@ -5093,11 +5124,11 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_root *root = orig_root->fs_info->extent_root;
 	struct btrfs_free_cluster *last_ptr = NULL;
 	struct btrfs_block_group_cache *block_group = NULL;
+	struct btrfs_block_group_cache *used_block_group;
 	int empty_cluster = 2 * 1024 * 1024;
 	int allowed_chunk_alloc = 0;
 	int done_chunk_alloc = 0;
 	struct btrfs_space_info *space_info;
-	int last_ptr_loop = 0;
 	int loop = 0;
 	int index = 0;
 	int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
@@ -5159,6 +5190,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 ideal_cache:
 		block_group = btrfs_lookup_block_group(root->fs_info,
 						       search_start);
+		used_block_group = block_group;
 		/*
 		 * we don't want to use the block group if it doesn't match our
 		 * allocation bits, or if its not cached.
@@ -5196,6 +5228,7 @@ search:
 		u64 offset;
 		int cached;
 
+		used_block_group = block_group;
 		btrfs_get_block_group(block_group);
 		search_start = block_group->key.objectid;
 
@@ -5265,84 +5298,73 @@ alloc:
 		spin_lock(&block_group->free_space_ctl->tree_lock);
 		if (cached &&
 		    block_group->free_space_ctl->free_space <
-		    num_bytes + empty_size) {
+		    num_bytes + empty_cluster + empty_size) {
 			spin_unlock(&block_group->free_space_ctl->tree_lock);
 			goto loop;
 		}
 		spin_unlock(&block_group->free_space_ctl->tree_lock);
 
 		/*
-		 * Ok we want to try and use the cluster allocator, so lets look
-		 * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
-		 * have tried the cluster allocator plenty of times at this
-		 * point and not have found anything, so we are likely way too
-		 * fragmented for the clustering stuff to find anything, so lets
-		 * just skip it and let the allocator find whatever block it can
-		 * find
+		 * Ok we want to try and use the cluster allocator, so
+		 * lets look there
 		 */
-		if (last_ptr && loop < LOOP_NO_EMPTY_SIZE) {
+		if (last_ptr) {
 			/*
 			 * the refill lock keeps out other
 			 * people trying to start a new cluster
 			 */
 			spin_lock(&last_ptr->refill_lock);
-			if (last_ptr->block_group &&
-			    (last_ptr->block_group->ro ||
-			    !block_group_bits(last_ptr->block_group, data))) {
-				offset = 0;
+			used_block_group = last_ptr->block_group;
+			if (used_block_group != block_group &&
+			    (!used_block_group ||
+			     used_block_group->ro ||
+			     !block_group_bits(used_block_group, data))) {
+				used_block_group = block_group;
 				goto refill_cluster;
 			}
 
-			offset = btrfs_alloc_from_cluster(block_group, last_ptr,
-						 num_bytes, search_start);
+			if (used_block_group != block_group)
+				btrfs_get_block_group(used_block_group);
+
+			offset = btrfs_alloc_from_cluster(used_block_group,
+			  last_ptr, num_bytes, used_block_group->key.objectid);
 			if (offset) {
 				/* we have a block, we're done */
 				spin_unlock(&last_ptr->refill_lock);
 				goto checks;
 			}
 
-			spin_lock(&last_ptr->lock);
-			/*
-			 * whoops, this cluster doesn't actually point to
-			 * this block group.  Get a ref on the block
-			 * group is does point to and try again
-			 */
-			if (!last_ptr_loop && last_ptr->block_group &&
-			    last_ptr->block_group != block_group &&
-			    index <=
-				 get_block_group_index(last_ptr->block_group)) {
-
-				btrfs_put_block_group(block_group);
-				block_group = last_ptr->block_group;
-				btrfs_get_block_group(block_group);
-				spin_unlock(&last_ptr->lock);
-				spin_unlock(&last_ptr->refill_lock);
-
-				last_ptr_loop = 1;
-				search_start = block_group->key.objectid;
-				/*
-				 * we know this block group is properly
-				 * in the list because
-				 * btrfs_remove_block_group, drops the
-				 * cluster before it removes the block
-				 * group from the list
-				 */
-				goto have_block_group;
+			WARN_ON(last_ptr->block_group != used_block_group);
+			if (used_block_group != block_group) {
+				btrfs_put_block_group(used_block_group);
+				used_block_group = block_group;
 			}
-			spin_unlock(&last_ptr->lock);
 refill_cluster:
+			BUG_ON(used_block_group != block_group);
+			/* If we are on LOOP_NO_EMPTY_SIZE, we can't
+			 * set up a new clusters, so lets just skip it
+			 * and let the allocator find whatever block
+			 * it can find.  If we reach this point, we
+			 * will have tried the cluster allocator
+			 * plenty of times and not have found
+			 * anything, so we are likely way too
+			 * fragmented for the clustering stuff to find
+			 * anything.  */
+			if (loop >= LOOP_NO_EMPTY_SIZE) {
+				spin_unlock(&last_ptr->refill_lock);
+				goto unclustered_alloc;
+			}
+
 			/*
 			 * this cluster didn't work out, free it and
 			 * start over
 			 */
 			btrfs_return_cluster_to_free_space(NULL, last_ptr);
 
-			last_ptr_loop = 0;
-
 			/* allocate a cluster in this block group */
 			ret = btrfs_find_space_cluster(trans, root,
 					       block_group, last_ptr,
-					       offset, num_bytes,
+					       search_start, num_bytes,
 					       empty_cluster + empty_size);
 			if (ret == 0) {
 				/*
@@ -5378,6 +5400,7 @@ refill_cluster:
 			goto loop;
 		}
 
+unclustered_alloc:
 		offset = btrfs_find_space_for_alloc(block_group, search_start,
 						    num_bytes, empty_size);
 		/*
@@ -5404,14 +5427,14 @@ checks:
 		search_start = stripe_align(root, offset);
 		/* move on to the next group */
 		if (search_start + num_bytes >= search_end) {
-			btrfs_add_free_space(block_group, offset, num_bytes);
+			btrfs_add_free_space(used_block_group, offset, num_bytes);
 			goto loop;
 		}
 
 		/* move on to the next group */
 		if (search_start + num_bytes >
-		    block_group->key.objectid + block_group->key.offset) {
-			btrfs_add_free_space(block_group, offset, num_bytes);
+		    used_block_group->key.objectid + used_block_group->key.offset) {
+			btrfs_add_free_space(used_block_group, offset, num_bytes);
 			goto loop;
 		}
 
@@ -5419,14 +5442,14 @@ checks:
 		ins->offset = num_bytes;
 
 		if (offset < search_start)
-			btrfs_add_free_space(block_group, offset,
+			btrfs_add_free_space(used_block_group, offset,
 					     search_start - offset);
 		BUG_ON(offset > search_start);
 
-		ret = btrfs_update_reserved_bytes(block_group, num_bytes,
+		ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
 						  alloc_type);
 		if (ret == -EAGAIN) {
-			btrfs_add_free_space(block_group, offset, num_bytes);
+			btrfs_add_free_space(used_block_group, offset, num_bytes);
 			goto loop;
 		}
 
@@ -5435,15 +5458,19 @@ checks:
 		ins->offset = num_bytes;
 
 		if (offset < search_start)
-			btrfs_add_free_space(block_group, offset,
+			btrfs_add_free_space(used_block_group, offset,
 					     search_start - offset);
 		BUG_ON(offset > search_start);
+		if (used_block_group != block_group)
+			btrfs_put_block_group(used_block_group);
 		btrfs_put_block_group(block_group);
 		break;
 loop:
 		failed_cluster_refill = false;
 		failed_alloc = false;
 		BUG_ON(index != get_block_group_index(block_group));
+		if (used_block_group != block_group)
+			btrfs_put_block_group(used_block_group);
 		btrfs_put_block_group(block_group);
 	}
 	up_read(&space_info->groups_sem);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9472d3de5e52..49f3c9dc09f4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -935,8 +935,10 @@ again:
 	node = tree_search(tree, start);
 	if (!node) {
 		prealloc = alloc_extent_state_atomic(prealloc);
-		if (!prealloc)
-			return -ENOMEM;
+		if (!prealloc) {
+			err = -ENOMEM;
+			goto out;
+		}
 		err = insert_state(tree, prealloc, start, end, &bits);
 		prealloc = NULL;
 		BUG_ON(err == -EEXIST);
@@ -992,8 +994,10 @@ hit_next:
 	 */
 	if (state->start < start) {
 		prealloc = alloc_extent_state_atomic(prealloc);
-		if (!prealloc)
-			return -ENOMEM;
+		if (!prealloc) {
+			err = -ENOMEM;
+			goto out;
+		}
 		err = split_state(tree, state, prealloc, start);
 		BUG_ON(err == -EEXIST);
 		prealloc = NULL;
@@ -1024,8 +1028,10 @@ hit_next:
 			this_end = last_start - 1;
 
 		prealloc = alloc_extent_state_atomic(prealloc);
-		if (!prealloc)
-			return -ENOMEM;
+		if (!prealloc) {
+			err = -ENOMEM;
+			goto out;
+		}
 
 		/*
 		 * Avoid to free 'prealloc' if it can be merged with
@@ -1051,8 +1057,10 @@ hit_next:
 	 */
 	if (state->start <= end && state->end > end) {
 		prealloc = alloc_extent_state_atomic(prealloc);
-		if (!prealloc)
-			return -ENOMEM;
+		if (!prealloc) {
+			err = -ENOMEM;
+			goto out;
+		}
 
 		err = split_state(tree, state, prealloc, end + 1);
 		BUG_ON(err == -EEXIST);
@@ -2287,14 +2295,20 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 		if (!uptodate) {
 			int failed_mirror;
 			failed_mirror = (int)(unsigned long)bio->bi_bdev;
-			if (tree->ops && tree->ops->readpage_io_failed_hook)
-				ret = tree->ops->readpage_io_failed_hook(
-						bio, page, start, end,
-						failed_mirror, state);
-			else
-				ret = bio_readpage_error(bio, page, start, end,
-							 failed_mirror, NULL);
+			/*
+			 * The generic bio_readpage_error handles errors the
+			 * following way: If possible, new read requests are
+			 * created and submitted and will end up in
+			 * end_bio_extent_readpage as well (if we're lucky, not
+			 * in the !uptodate case). In that case it returns 0 and
+			 * we just go on with the next page in our bio. If it
+			 * can't handle the error it will return -EIO and we
+			 * remain responsible for that page.
+			 */
+			ret = bio_readpage_error(bio, page, start, end,
+							failed_mirror, NULL);
 			if (ret == 0) {
+error_handled:
 				uptodate =
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
@@ -2302,6 +2316,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 				uncache_state(&cached);
 				continue;
 			}
+			if (tree->ops && tree->ops->readpage_io_failed_hook) {
+				ret = tree->ops->readpage_io_failed_hook(
+							bio, page, start, end,
+							failed_mirror, state);
+				if (ret == 0)
+					goto error_handled;
+			}
 		}
 
 		if (uptodate) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index dafdfa059bf6..97fbe939c050 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1167,6 +1167,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
 		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
 		     (sizeof(struct page *)));
+	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
+	nrptrs = max(nrptrs, 8);
 	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
@@ -1387,7 +1389,11 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		goto out;
 	}
 
-	file_update_time(file);
+	err = btrfs_update_time(file);
+	if (err) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
 	BTRFS_I(inode)->sequence++;
 
 	start_pos = round_down(pos, root->sectorsize);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6e5b7e463698..ec23d43d0c35 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1470,6 +1470,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 {
 	info->offset = offset_to_bitmap(ctl, offset);
 	info->bytes = 0;
+	INIT_LIST_HEAD(&info->list);
 	link_free_space(ctl, info);
 	ctl->total_bitmaps++;
 
@@ -2319,6 +2320,7 @@ again:
 
 	if (!found) {
 		start = i;
+		cluster->max_size = 0;
 		found = true;
 	}
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 526dd51a1966..0a6b928813a4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -38,6 +38,7 @@
 #include <linux/falloc.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
+#include <linux/mount.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -2031,7 +2032,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	/* insert an orphan item to track this unlinked/truncated file */
 	if (insert >= 1) {
 		ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
-		BUG_ON(ret);
+		BUG_ON(ret && ret != -EEXIST);
 	}
 
 	/* insert an orphan item to track subvolume contains orphan files */
@@ -2158,6 +2159,38 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		if (ret && ret != -ESTALE)
 			goto out;
 
+		if (ret == -ESTALE && root == root->fs_info->tree_root) {
+			struct btrfs_root *dead_root;
+			struct btrfs_fs_info *fs_info = root->fs_info;
+			int is_dead_root = 0;
+
+			/*
+			 * this is an orphan in the tree root. Currently these
+			 * could come from 2 sources:
+			 *  a) a snapshot deletion in progress
+			 *  b) a free space cache inode
+			 * We need to distinguish those two, as the snapshot
+			 * orphan must not get deleted.
+			 * find_dead_roots already ran before us, so if this
+			 * is a snapshot deletion, we should find the root
+			 * in the dead_roots list
+			 */
+			spin_lock(&fs_info->trans_lock);
+			list_for_each_entry(dead_root, &fs_info->dead_roots,
+					    root_list) {
+				if (dead_root->root_key.objectid ==
+				    found_key.objectid) {
+					is_dead_root = 1;
+					break;
+				}
+			}
+			spin_unlock(&fs_info->trans_lock);
+			if (is_dead_root) {
+				/* prevent this orphan from being found again */
+				key.offset = found_key.objectid - 1;
+				continue;
+			}
+		}
 		/*
 		 * Inode is already gone but the orphan item is still there,
 		 * kill the orphan item.
@@ -2191,7 +2224,14 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				continue;
 			}
 			nr_truncate++;
+			/*
+			 * Need to hold the imutex for reservation purposes, not
+			 * a huge deal here but I have a WARN_ON in
+			 * btrfs_delalloc_reserve_space to catch offenders.
+			 */
+			mutex_lock(&inode->i_mutex);
 			ret = btrfs_truncate(inode);
+			mutex_unlock(&inode->i_mutex);
 		} else {
 			nr_unlink++;
 		}
@@ -3327,7 +3367,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 			u64 hint_byte = 0;
 			hole_size = last_byte - cur_offset;
 
-			trans = btrfs_start_transaction(root, 2);
+			trans = btrfs_start_transaction(root, 3);
 			if (IS_ERR(trans)) {
 				err = PTR_ERR(trans);
 				break;
@@ -3337,6 +3377,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 						 cur_offset + hole_size,
 						 &hint_byte, 1);
 			if (err) {
+				btrfs_update_inode(trans, root, inode);
 				btrfs_end_transaction(trans, root);
 				break;
 			}
@@ -3346,6 +3387,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 					0, hole_size, 0, hole_size,
 					0, 0, 0);
 			if (err) {
+				btrfs_update_inode(trans, root, inode);
 				btrfs_end_transaction(trans, root);
 				break;
 			}
@@ -3353,6 +3395,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 			btrfs_drop_extent_cache(inode, hole_start,
 					last_byte - 1, 0);
 
+			btrfs_update_inode(trans, root, inode);
 			btrfs_end_transaction(trans, root);
 		}
 		free_extent_map(em);
@@ -3370,6 +3413,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 
 static int btrfs_setsize(struct inode *inode, loff_t newsize)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_trans_handle *trans;
 	loff_t oldsize = i_size_read(inode);
 	int ret;
 
@@ -3377,16 +3422,19 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
 		return 0;
 
 	if (newsize > oldsize) {
-		i_size_write(inode, newsize);
-		btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
 		truncate_pagecache(inode, oldsize, newsize);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
-		if (ret) {
-			btrfs_setsize(inode, oldsize);
+		if (ret)
 			return ret;
-		}
 
-		mark_inode_dirty(inode);
+		trans = btrfs_start_transaction(root, 1);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
+
+		i_size_write(inode, newsize);
+		btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+		ret = btrfs_update_inode(trans, root, inode);
+		btrfs_end_transaction_throttle(trans, root);
 	} else {
 
 		/*
@@ -3426,9 +3474,9 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (attr->ia_valid) {
 		setattr_copy(inode, attr);
-		mark_inode_dirty(inode);
+		err = btrfs_dirty_inode(inode);
 
-		if (attr->ia_valid & ATTR_MODE)
+		if (!err && attr->ia_valid & ATTR_MODE)
 			err = btrfs_acl_chmod(inode);
 	}
 
@@ -3490,7 +3538,7 @@ void btrfs_evict_inode(struct inode *inode)
 	 * doing the truncate.
 	 */
 	while (1) {
-		ret = btrfs_block_rsv_refill(root, rsv, min_size);
+		ret = btrfs_block_rsv_refill_noflush(root, rsv, min_size);
 
 		/*
 		 * Try and steal from the global reserve since we will
@@ -4204,42 +4252,80 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
  * FIXME, needs more benchmarking...there are no reasons other than performance
  * to keep or drop this code.
  */
-void btrfs_dirty_inode(struct inode *inode, int flags)
+int btrfs_dirty_inode(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	int ret;
 
 	if (BTRFS_I(inode)->dummy_inode)
-		return;
+		return 0;
 
 	trans = btrfs_join_transaction(root);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret && ret == -ENOSPC) {
 		/* whoops, lets try again with the full transaction */
 		btrfs_end_transaction(trans, root);
 		trans = btrfs_start_transaction(root, 1);
-		if (IS_ERR(trans)) {
-			printk_ratelimited(KERN_ERR "btrfs: fail to "
-				       "dirty  inode %llu error %ld\n",
-				       (unsigned long long)btrfs_ino(inode),
-				       PTR_ERR(trans));
-			return;
-		}
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
 
 		ret = btrfs_update_inode(trans, root, inode);
-		if (ret) {
-			printk_ratelimited(KERN_ERR "btrfs: fail to "
-				       "dirty  inode %llu error %d\n",
-				       (unsigned long long)btrfs_ino(inode),
-				       ret);
-		}
 	}
 	btrfs_end_transaction(trans, root);
 	if (BTRFS_I(inode)->delayed_node)
 		btrfs_balance_delayed_items(root);
+
+	return ret;
+}
+
+/*
+ * This is a copy of file_update_time.  We need this so we can return error on
+ * ENOSPC for updating the inode in the case of file write and mmap writes.
+ */
+int btrfs_update_time(struct file *file)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct timespec now;
+	int ret;
+	enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+
+	/* First try to exhaust all avenues to not sync */
+	if (IS_NOCMTIME(inode))
+		return 0;
+
+	now = current_fs_time(inode->i_sb);
+	if (!timespec_equal(&inode->i_mtime, &now))
+		sync_it = S_MTIME;
+
+	if (!timespec_equal(&inode->i_ctime, &now))
+		sync_it |= S_CTIME;
+
+	if (IS_I_VERSION(inode))
+		sync_it |= S_VERSION;
+
+	if (!sync_it)
+		return 0;
+
+	/* Finally allowed to write? Takes lock. */
+	if (mnt_want_write_file(file))
+		return 0;
+
+	/* Only change inode inside the lock region */
+	if (sync_it & S_VERSION)
+		inode_inc_iversion(inode);
+	if (sync_it & S_CTIME)
+		inode->i_ctime = now;
+	if (sync_it & S_MTIME)
+		inode->i_mtime = now;
+	ret = btrfs_dirty_inode(inode);
+	if (!ret)
+		mark_inode_dirty_sync(inode);
+	mnt_drop_write(file->f_path.mnt);
+	return ret;
 }
 
 /*
@@ -4555,11 +4641,18 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
+	/*
+	* If the active LSM wants to access the inode during
+	* d_instantiate it needs these. Smack checks to see
+	* if the filesystem supports xattrs by looking at the
+	* ops vector.
+	*/
+
+	inode->i_op = &btrfs_special_inode_operations;
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
 	else {
-		inode->i_op = &btrfs_special_inode_operations;
 		init_special_inode(inode, inode->i_mode, rdev);
 		btrfs_update_inode(trans, root, inode);
 	}
@@ -4613,14 +4706,21 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
+	/*
+	* If the active LSM wants to access the inode during
+	* d_instantiate it needs these. Smack checks to see
+	* if the filesystem supports xattrs by looking at the
+	* ops vector.
+	*/
+	inode->i_fop = &btrfs_file_operations;
+	inode->i_op = &btrfs_file_inode_operations;
+
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
 	else {
 		inode->i_mapping->a_ops = &btrfs_aops;
 		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
-		inode->i_fop = &btrfs_file_operations;
-		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
 out_unlock:
@@ -6303,7 +6403,12 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	u64 page_start;
 	u64 page_end;
 
+	/* Need this to keep space reservations serialized */
+	mutex_lock(&inode->i_mutex);
 	ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+	mutex_unlock(&inode->i_mutex);
+	if (!ret)
+		ret = btrfs_update_time(vma->vm_file);
 	if (ret) {
 		if (ret == -ENOMEM)
 			ret = VM_FAULT_OOM;
@@ -6515,8 +6620,9 @@ static int btrfs_truncate(struct inode *inode)
 			/* Just need the 1 for updating the inode */
 			trans = btrfs_start_transaction(root, 1);
 			if (IS_ERR(trans)) {
-				err = PTR_ERR(trans);
-				goto out;
+				ret = err = PTR_ERR(trans);
+				trans = NULL;
+				break;
 			}
 		}
 
@@ -7076,14 +7182,21 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 	}
 
+	/*
+	* If the active LSM wants to access the inode during
+	* d_instantiate it needs these. Smack checks to see
+	* if the filesystem supports xattrs by looking at the
+	* ops vector.
+	*/
+	inode->i_fop = &btrfs_file_operations;
+	inode->i_op = &btrfs_file_inode_operations;
+
 	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
 	if (err)
 		drop_inode = 1;
 	else {
 		inode->i_mapping->a_ops = &btrfs_aops;
 		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
-		inode->i_fop = &btrfs_file_operations;
-		inode->i_op = &btrfs_file_inode_operations;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	}
 	if (drop_inode)
@@ -7353,6 +7466,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
 	.getattr	= btrfs_getattr,
+	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
 	.setxattr	= btrfs_setxattr,
 	.getxattr	= btrfs_getxattr,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a90e749ed6d2..c04f02c7d5bb 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -252,11 +252,11 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	trans = btrfs_join_transaction(root);
 	BUG_ON(IS_ERR(trans));
 
+	btrfs_update_iflags(inode);
+	inode->i_ctime = CURRENT_TIME;
 	ret = btrfs_update_inode(trans, root, inode);
 	BUG_ON(ret);
 
-	btrfs_update_iflags(inode);
-	inode->i_ctime = CURRENT_TIME;
 	btrfs_end_transaction(trans, root);
 
 	mnt_drop_write(file->f_path.mnt);
@@ -858,8 +858,10 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		return 0;
 	file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
 
+	mutex_lock(&inode->i_mutex);
 	ret = btrfs_delalloc_reserve_space(inode,
 					   num_pages << PAGE_CACHE_SHIFT);
+	mutex_unlock(&inode->i_mutex);
 	if (ret)
 		return ret;
 again:
@@ -1278,7 +1280,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		}
 		ret = btrfs_grow_device(trans, device, new_size);
 		btrfs_commit_transaction(trans, root);
-	} else {
+	} else if (new_size < old_size) {
 		ret = btrfs_shrink_device(device, new_size);
 	}
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index dff29d5e151a..cfb55434a469 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2947,7 +2947,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
 	last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
 	while (index <= last_index) {
+		mutex_lock(&inode->i_mutex);
 		ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+		mutex_unlock(&inode->i_mutex);
 		if (ret)
 			goto out;
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fab420db5121..ddf2c90d3fc0 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -256,6 +256,11 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
 	btrfs_release_path(swarn->path);
 
 	ipath = init_ipath(4096, local_root, swarn->path);
+	if (IS_ERR(ipath)) {
+		ret = PTR_ERR(ipath);
+		ipath = NULL;
+		goto err;
+	}
 	ret = paths_from_inode(inum, ipath);
 
 	if (ret < 0)
@@ -1530,18 +1535,22 @@ static noinline_for_stack int scrub_supers(struct scrub_dev *sdev)
 static noinline_for_stack int scrub_workers_get(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret = 0;
 
 	mutex_lock(&fs_info->scrub_lock);
 	if (fs_info->scrub_workers_refcnt == 0) {
 		btrfs_init_workers(&fs_info->scrub_workers, "scrub",
 			   fs_info->thread_pool_size, &fs_info->generic_worker);
 		fs_info->scrub_workers.idle_thresh = 4;
-		btrfs_start_workers(&fs_info->scrub_workers, 1);
+		ret = btrfs_start_workers(&fs_info->scrub_workers);
+		if (ret)
+			goto out;
 	}
 	++fs_info->scrub_workers_refcnt;
+out:
 	mutex_unlock(&fs_info->scrub_lock);
 
-	return 0;
+	return ret;
 }
 
 static noinline_for_stack void scrub_workers_put(struct btrfs_root *root)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 17ee7fc5e64e..200f63bc6675 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -41,6 +41,7 @@
 #include <linux/slab.h>
 #include <linux/cleancache.h>
 #include <linux/mnt_namespace.h>
+#include <linux/ratelimit.h>
 #include "compat.h"
 #include "delayed-inode.h"
 #include "ctree.h"
@@ -1053,11 +1054,11 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	u64 avail_space;
 	u64 used_space;
 	u64 min_stripe_size;
-	int min_stripes = 1;
+	int min_stripes = 1, num_stripes = 1;
 	int i = 0, nr_devices;
 	int ret;
 
-	nr_devices = fs_info->fs_devices->rw_devices;
+	nr_devices = fs_info->fs_devices->open_devices;
 	BUG_ON(!nr_devices);
 
 	devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
@@ -1067,20 +1068,24 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 
 	/* calc min stripe number for data space alloction */
 	type = btrfs_get_alloc_profile(root, 1);
-	if (type & BTRFS_BLOCK_GROUP_RAID0)
+	if (type & BTRFS_BLOCK_GROUP_RAID0) {
 		min_stripes = 2;
-	else if (type & BTRFS_BLOCK_GROUP_RAID1)
+		num_stripes = nr_devices;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID1) {
 		min_stripes = 2;
-	else if (type & BTRFS_BLOCK_GROUP_RAID10)
+		num_stripes = 2;
+	} else if (type & BTRFS_BLOCK_GROUP_RAID10) {
 		min_stripes = 4;
+		num_stripes = 4;
+	}
 
 	if (type & BTRFS_BLOCK_GROUP_DUP)
 		min_stripe_size = 2 * BTRFS_STRIPE_LEN;
 	else
 		min_stripe_size = BTRFS_STRIPE_LEN;
 
-	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
-		if (!device->in_fs_metadata)
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		if (!device->in_fs_metadata || !device->bdev)
 			continue;
 
 		avail_space = device->total_bytes - device->bytes_used;
@@ -1141,13 +1146,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	i = nr_devices - 1;
 	avail_space = 0;
 	while (nr_devices >= min_stripes) {
+		if (num_stripes > nr_devices)
+			num_stripes = nr_devices;
+
 		if (devices_info[i].max_avail >= min_stripe_size) {
 			int j;
 			u64 alloc_size;
 
-			avail_space += devices_info[i].max_avail * min_stripes;
+			avail_space += devices_info[i].max_avail * num_stripes;
 			alloc_size = devices_info[i].max_avail;
-			for (j = i + 1 - min_stripes; j <= i; j++)
+			for (j = i + 1 - num_stripes; j <= i; j++)
 				devices_info[j].max_avail -= alloc_size;
 		}
 		i--;
@@ -1264,6 +1272,16 @@ static int btrfs_unfreeze(struct super_block *sb)
 	return 0;
 }
 
+static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
+{
+	int ret;
+
+	ret = btrfs_dirty_inode(inode);
+	if (ret)
+		printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
+				   "error %d\n", btrfs_ino(inode), ret);
+}
+
 static const struct super_operations btrfs_super_ops = {
 	.drop_inode	= btrfs_drop_inode,
 	.evict_inode	= btrfs_evict_inode,
@@ -1271,7 +1289,7 @@ static const struct super_operations btrfs_super_ops = {
 	.sync_fs	= btrfs_sync_fs,
 	.show_options	= btrfs_show_options,
 	.write_inode	= btrfs_write_inode,
-	.dirty_inode	= btrfs_dirty_inode,
+	.dirty_inode	= btrfs_fs_dirty_inode,
 	.alloc_inode	= btrfs_alloc_inode,
 	.destroy_inode	= btrfs_destroy_inode,
 	.statfs		= btrfs_statfs,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c37433d3cd82..f4b839fd3c9d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -295,6 +295,12 @@ loop_lock:
 			btrfs_requeue_work(&device->work);
 			goto done;
 		}
+		/* unplug every 64 requests just for good measure */
+		if (batch_run % 64 == 0) {
+			blk_finish_plug(&plug);
+			blk_start_plug(&plug);
+			sync_pending = 0;
+		}
 	}
 
 	cond_resched();
@@ -1611,7 +1617,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
 		return -EINVAL;
 
-	bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
 				  root->fs_info->bdev_holder);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
@@ -3258,7 +3264,7 @@ static void btrfs_end_bio(struct bio *bio, int err)
 		 */
 		if (atomic_read(&bbio->error) > bbio->max_errors) {
 			err = -EIO;
-		} else if (err) {
+		} else {
 			/*
 			 * this bio is actually up to date, we didn't
 			 * go over the max number of errors