Merge branch 'nfs-rdma' of git://git.linux-nfs.org/projects/anna/nfs-rdma into linux-next

* 'nfs-rdma' of git://git.linux-nfs.org/projects/anna/nfs-rdma: (916 commits)
  xprtrdma: Handle additional connection events
  xprtrdma: Remove RPCRDMA_PERSISTENT_REGISTRATION macro
  xprtrdma: Make rpcrdma_ep_disconnect() return void
  xprtrdma: Schedule reply tasklet once per upcall
  xprtrdma: Allocate each struct rpcrdma_mw separately
  xprtrdma: Rename frmr_wr
  xprtrdma: Disable completions for LOCAL_INV Work Requests
  xprtrdma: Disable completions for FAST_REG_MR Work Requests
  xprtrdma: Don't post a LOCAL_INV in rpcrdma_register_frmr_external()
  xprtrdma: Reset FRMRs after a flushed LOCAL_INV Work Request
  xprtrdma: Reset FRMRs when FAST_REG_MR is flushed by a disconnect
  xprtrdma: Properly handle exhaustion of the rb_mws list
  xprtrdma: Chain together all MWs in same buffer pool
  xprtrdma: Back off rkey when FAST_REG_MR fails
  xprtrdma: Unclutter struct rpcrdma_mr_seg
  xprtrdma: Don't invalidate FRMRs if registration fails
  xprtrdma: On disconnect, don't ignore pending CQEs
  xprtrdma: Update rkeys after transport reconnect
  xprtrdma: Limit data payload size for ALLPHYSICAL
  xprtrdma: Protect ia->ri_id when unmapping/invalidating MRs
  ...

68 files changed, 842 insertions, 363 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 4f078c0..1c9c5f0 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -830,16 +830,20 @@ void exit_aio(struct mm_struct *mm)
 static void put_reqs_available(struct kioctx *ctx, unsigned nr)
 {
 	struct kioctx_cpu *kcpu;
+	unsigned long flags;
 
 	preempt_disable();
 	kcpu = this_cpu_ptr(ctx->cpu);
 
+	local_irq_save(flags);
 	kcpu->reqs_available += nr;
+
 	while (kcpu->reqs_available >= ctx->req_batch * 2) {
 		kcpu->reqs_available -= ctx->req_batch;
 		atomic_add(ctx->req_batch, &ctx->reqs_available);
 	}
 
+	local_irq_restore(flags);
 	preempt_enable();
 }
 
@@ -847,10 +851,12 @@ static bool get_reqs_available(struct kioctx *ctx)
 {
 	struct kioctx_cpu *kcpu;
 	bool ret = false;
+	unsigned long flags;
 
 	preempt_disable();
 	kcpu = this_cpu_ptr(ctx->cpu);
 
+	local_irq_save(flags);
 	if (!kcpu->reqs_available) {
 		int old, avail = atomic_read(&ctx->reqs_available);
 
@@ -869,6 +875,7 @@ static bool get_reqs_available(struct kioctx *ctx)
 	ret = true;
 	kcpu->reqs_available--;
 out:
+	local_irq_restore(flags);
 	preempt_enable();
 	return ret;
 }
@@ -1021,6 +1028,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 
 	/* everything turned out well, dispose of the aiocb. */
 	kiocb_free(iocb);
+	put_reqs_available(ctx, 1);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1062,6 +1070,9 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	if (head == tail)
 		goto out;
 
+	head %= ctx->nr_events;
+	tail %= ctx->nr_events;
+
 	while (ret < nr) {
 		long avail;
 		struct io_event *ev;
@@ -1100,8 +1111,6 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	flush_dcache_page(ctx->ring_pages[0]);
 
 	pr_debug("%li  h%u t%u\n", ret, head, tail);
-
-	put_reqs_available(ctx, ret);
 out:
 	mutex_unlock(&ctx->ring_lock);
 
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index d7bd395..1c55388 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -210,7 +210,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	int pipefd;
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
-	int pgrp;
+	int pgrp = 0;
 	bool pgrp_set = false;
 	int ret = -EINVAL;
 
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 92371c4..1daea0b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -821,7 +821,7 @@ static void free_workspace(int type, struct list_head *workspace)
 
 	spin_lock(workspace_lock);
 	if (*num_workspace < num_online_cpus()) {
-		list_add_tail(workspace, idle_workspace);
+		list_add(workspace, idle_workspace);
 		(*num_workspace)++;
 		spin_unlock(workspace_lock);
 		goto wake;
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 2af6e66..eea26e1 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -36,6 +36,7 @@
 #include "check-integrity.h"
 #include "rcu-string.h"
 #include "dev-replace.h"
+#include "sysfs.h"
 
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 				       int scrub_ret);
@@ -562,6 +563,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 
+	/* replace the sysfs entry */
+	btrfs_kobj_rm_device(fs_info, src_device);
+	btrfs_kobj_add_device(fs_info, tgt_device);
+
 	btrfs_rm_dev_replace_blocked(fs_info);
 
 	btrfs_rm_dev_replace_srcdev(fs_info, src_device);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8bb4aa1..08e65e9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -369,7 +369,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 out:
 	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
 			     &cached_state, GFP_NOFS);
-	btrfs_tree_read_unlock_blocking(eb);
+	if (need_lock)
+		btrfs_tree_read_unlock_blocking(eb);
 	return ret;
 }
 
@@ -2904,7 +2905,9 @@ retry_root_backup:
 		if (ret)
 			goto fail_qgroup;
 
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			printk(KERN_WARNING
 			       "BTRFS: failed to recover relocation\n");
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 99c2539..813537f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5678,7 +5678,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	struct btrfs_caching_control *next;
 	struct btrfs_caching_control *caching_ctl;
 	struct btrfs_block_group_cache *cache;
-	struct btrfs_space_info *space_info;
 
 	down_write(&fs_info->commit_root_sem);
 
@@ -5701,9 +5700,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 
 	up_write(&fs_info->commit_root_sem);
 
-	list_for_each_entry_rcu(space_info, &fs_info->space_info, list)
-		percpu_counter_set(&space_info->total_bytes_pinned, 0);
-
 	update_global_block_rsv(fs_info);
 }
 
@@ -5741,6 +5737,7 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 		spin_lock(&cache->lock);
 		cache->pinned -= len;
 		space_info->bytes_pinned -= len;
+		percpu_counter_add(&space_info->total_bytes_pinned, -len);
 		if (cache->ro) {
 			space_info->bytes_readonly += len;
 			readonly = true;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0d321c2..47aceb4 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -136,19 +136,22 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 void btrfs_update_iflags(struct inode *inode)
 {
 	struct btrfs_inode *ip = BTRFS_I(inode);
-
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	unsigned int new_fl = 0;
 
 	if (ip->flags & BTRFS_INODE_SYNC)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (ip->flags & BTRFS_INODE_IMMUTABLE)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (ip->flags & BTRFS_INODE_APPEND)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (ip->flags & BTRFS_INODE_NOATIME)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (ip->flags & BTRFS_INODE_DIRSYNC)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+
+	set_mask_bits(&inode->i_flags,
+		      S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC,
+		      new_fl);
 }
 
 /*
@@ -3139,7 +3142,6 @@ out:
 static void clone_update_extent_map(struct inode *inode,
 				    const struct btrfs_trans_handle *trans,
 				    const struct btrfs_path *path,
-				    struct btrfs_file_extent_item *fi,
 				    const u64 hole_offset,
 				    const u64 hole_len)
 {
@@ -3154,7 +3156,11 @@ static void clone_update_extent_map(struct inode *inode,
 		return;
 	}
 
-	if (fi) {
+	if (path) {
+		struct btrfs_file_extent_item *fi;
+
+		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				    struct btrfs_file_extent_item);
 		btrfs_extent_item_to_extent_map(inode, path, fi, false, em);
 		em->generation = -1;
 		if (btrfs_file_extent_type(path->nodes[0], fi) ==
@@ -3508,18 +3514,15 @@ process_slot:
 					    btrfs_item_ptr_offset(leaf, slot),
 					    size);
 				inode_add_bytes(inode, datal);
-				extent = btrfs_item_ptr(leaf, slot,
-						struct btrfs_file_extent_item);
 			}
 
 			/* If we have an implicit hole (NO_HOLES feature). */
 			if (drop_start < new_key.offset)
 				clone_update_extent_map(inode, trans,
-						path, NULL, drop_start,
+						NULL, drop_start,
 						new_key.offset - drop_start);
 
-			clone_update_extent_map(inode, trans, path,
-						extent, 0, 0);
+			clone_update_extent_map(inode, trans, path, 0, 0);
 
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
@@ -3562,12 +3565,10 @@ process_slot:
 			btrfs_end_transaction(trans, root);
 			goto out;
 		}
+		clone_update_extent_map(inode, trans, NULL, last_dest_end,
+					destoff + len - last_dest_end);
 		ret = clone_finish_inode_update(trans, inode, destoff + len,
 						destoff, olen);
-		if (ret)
-			goto out;
-		clone_update_extent_map(inode, trans, path, NULL, last_dest_end,
-					destoff + len - last_dest_end);
 	}
 
 out:
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index e12441c..7187b14 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -484,8 +484,19 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 					   log_list);
 		list_del_init(&ordered->log_list);
 		spin_unlock_irq(&log->log_extents_lock[index]);
+
+		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
+		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
+			struct inode *inode = ordered->inode;
+			u64 start = ordered->file_offset;
+			u64 end = ordered->file_offset + ordered->len - 1;
+
+			WARN_ON(!inode);
+			filemap_fdatawrite_range(inode->i_mapping, start, end);
+		}
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
+
 		btrfs_put_ordered_extent(ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 6efd70d..9626b4a 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -54,7 +54,7 @@ static void print_extent_data_ref(struct extent_buffer *eb,
 	       btrfs_extent_data_ref_count(eb, ref));
 }
 
-static void print_extent_item(struct extent_buffer *eb, int slot)
+static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 {
 	struct btrfs_extent_item *ei;
 	struct btrfs_extent_inline_ref *iref;
@@ -63,7 +63,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot)
 	struct btrfs_disk_key key;
 	unsigned long end;
 	unsigned long ptr;
-	int type;
 	u32 item_size = btrfs_item_size_nr(eb, slot);
 	u64 flags;
 	u64 offset;
@@ -88,7 +87,8 @@ static void print_extent_item(struct extent_buffer *eb, int slot)
 	       btrfs_extent_refs(eb, ei), btrfs_extent_generation(eb, ei),
 	       flags);
 
-	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+	if ((type == BTRFS_EXTENT_ITEM_KEY) &&
+	    flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		struct btrfs_tree_block_info *info;
 		info = (struct btrfs_tree_block_info *)(ei + 1);
 		btrfs_tree_block_key(eb, info, &key);
@@ -223,7 +223,8 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 				btrfs_disk_root_refs(l, ri));
 			break;
 		case BTRFS_EXTENT_ITEM_KEY:
-			print_extent_item(l, i);
+		case BTRFS_METADATA_ITEM_KEY:
+			print_extent_item(l, i, type);
 			break;
 		case BTRFS_TREE_BLOCK_REF_KEY:
 			printk(KERN_INFO "\t\ttree block backref\n");
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4055291..4a88f07 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1956,9 +1956,10 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	 * pages are going to be uptodate.
 	 */
 	for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
-		if (rbio->faila == stripe ||
-		    rbio->failb == stripe)
+		if (rbio->faila == stripe || rbio->failb == stripe) {
+			atomic_inc(&rbio->bbio->error);
 			continue;
+		}
 
 		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
 			struct page *p;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 4662d92..8e16bca 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -522,9 +522,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_ssd_spread:
 			btrfs_set_and_info(root, SSD_SPREAD,
 					   "use spread ssd allocation scheme");
+			btrfs_set_opt(info->mount_opt, SSD);
 			break;
 		case Opt_nossd:
-			btrfs_clear_and_info(root, NOSSD,
+			btrfs_set_and_info(root, NOSSD,
 					     "not using ssd allocation scheme");
 			btrfs_clear_opt(info->mount_opt, SSD);
 			break;
@@ -1467,7 +1468,9 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 
 		/* recover relocation */
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret)
 			goto restore;
 
@@ -1808,6 +1811,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 		list_for_each_entry(dev, head, dev_list) {
 			if (dev->missing)
 				continue;
+			if (!dev->name)
+				continue;
 			if (!first_dev || dev->devid < first_dev->devid)
 				first_dev = dev;
 		}
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index df39458..7869936 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -605,14 +605,37 @@ static void init_feature_attrs(void)
 	}
 }
 
-static int add_device_membership(struct btrfs_fs_info *fs_info)
+int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device)
+{
+	struct hd_struct *disk;
+	struct kobject *disk_kobj;
+
+	if (!fs_info->device_dir_kobj)
+		return -EINVAL;
+
+	if (one_device) {
+		disk = one_device->bdev->bd_part;
+		disk_kobj = &part_to_dev(disk)->kobj;
+
+		sysfs_remove_link(fs_info->device_dir_kobj,
+						disk_kobj->name);
+	}
+
+	return 0;
+}
+
+int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device)
 {
 	int error = 0;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *dev;
 
-	fs_info->device_dir_kobj = kobject_create_and_add("devices",
+	if (!fs_info->device_dir_kobj)
+		fs_info->device_dir_kobj = kobject_create_and_add("devices",
 						&fs_info->super_kobj);
+
 	if (!fs_info->device_dir_kobj)
 		return -ENOMEM;
 
@@ -623,6 +646,9 @@ static int add_device_membership(struct btrfs_fs_info *fs_info)
 		if (!dev->bdev)
 			continue;
 
+		if (one_device && one_device != dev)
+			continue;
+
 		disk = dev->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
@@ -666,7 +692,7 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info)
 	if (error)
 		goto failure;
 
-	error = add_device_membership(fs_info);
+	error = btrfs_kobj_add_device(fs_info, NULL);
 	if (error)
 		goto failure;
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 9ab5763..ac46df3 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -66,4 +66,8 @@ char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
 extern const char * const btrfs_feature_set_names[3];
 extern struct kobj_type space_info_ktype;
 extern struct kobj_type btrfs_raid_ktype;
+int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device);
+int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
+                struct btrfs_device *one_device);
 #endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 511839c..5f379af 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -386,11 +386,13 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type,
 	bool reloc_reserved = false;
 	int ret;
 
+	/* Send isn't supposed to start transactions. */
+	ASSERT(current->journal_info != (void *)BTRFS_SEND_TRANS_STUB);
+
 	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
 		return ERR_PTR(-EROFS);
 
-	if (current->journal_info &&
-	    current->journal_info != (void *)BTRFS_SEND_TRANS_STUB) {
+	if (current->journal_info) {
 		WARN_ON(type & TRANS_EXTWRITERS);
 		h = current->journal_info;
 		h->use_count++;
@@ -491,6 +493,7 @@ again:
 	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
 	    may_wait_transaction(root, type)) {
+		current->journal_info = h;
 		btrfs_commit_transaction(h, root);
 		goto again;
 	}
@@ -1615,11 +1618,6 @@ static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = btrfs_run_delayed_items(trans, root);
-	/*
-	 * running the delayed items may have added new refs. account
-	 * them now so that they hinder processing of more delayed refs
-	 * as little as possible.
-	 */
 	if (ret)
 		return ret;
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c83b242..6cb82f6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -40,6 +40,7 @@
 #include "rcu-string.h"
 #include "math.h"
 #include "dev-replace.h"
+#include "sysfs.h"
 
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
@@ -554,12 +555,14 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		 * This is ok to do without rcu read locked because we hold the
 		 * uuid mutex so nothing we touch in here is going to disappear.
 		 */
-		name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
-		if (!name) {
-			kfree(device);
-			goto error;
+		if (orig_dev->name) {
+			name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+			if (!name) {
+				kfree(device);
+				goto error;
+			}
+			rcu_assign_pointer(device->name, name);
 		}
-		rcu_assign_pointer(device->name, name);
 
 		list_add(&device->dev_list, &fs_devices->devices);
 		device->fs_devices = fs_devices;
@@ -1677,8 +1680,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->bdev == root->fs_info->fs_devices->latest_bdev)
 		root->fs_info->fs_devices->latest_bdev = next_device->bdev;
 
-	if (device->bdev)
+	if (device->bdev) {
 		device->fs_devices->open_devices--;
+		/* remove sysfs entry */
+		btrfs_kobj_rm_device(root->fs_info, device);
+	}
 
 	call_rcu(&device->rcu, free_device);
 
@@ -2143,9 +2149,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	total_bytes = btrfs_super_num_devices(root->fs_info->super_copy);
 	btrfs_set_super_num_devices(root->fs_info->super_copy,
 				    total_bytes + 1);
+
+	/* add sysfs device entry */
+	btrfs_kobj_add_device(root->fs_info, device);
+
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
+		char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
 		ret = init_first_rw_device(trans, root, device);
 		if (ret) {
 			btrfs_abort_transaction(trans, root, ret);
@@ -2156,6 +2167,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 			btrfs_abort_transaction(trans, root, ret);
 			goto error_trans;
 		}
+
+		/* Sprouting would change fsid of the mounted root,
+		 * so rename the fsid on the sysfs
+		 */
+		snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
+						root->fs_info->fsid);
+		if (kobject_rename(&root->fs_info->super_kobj, fsid_buf))
+			goto error_trans;
 	} else {
 		ret = btrfs_add_device(trans, root, device);
 		if (ret) {
@@ -2205,6 +2224,7 @@ error_trans:
 	unlock_chunks(root);
 	btrfs_end_transaction(trans, root);
 	rcu_string_free(device->name);
+	btrfs_kobj_rm_device(root->fs_info, device);
 	kfree(device);
 error:
 	blkdev_put(bdev, FMODE_EXCL);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 4f19631..b67d8fc 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -136,7 +136,7 @@ static int zlib_compress_pages(struct list_head *ws,
 		if (workspace->def_strm.total_in > 8192 &&
 		    workspace->def_strm.total_in <
 		    workspace->def_strm.total_out) {
-			ret = -EIO;
+			ret = -E2BIG;
 			goto out;
 		}
 		/* we need another page for writing out.  Test this
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0227b45..15e9505 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -290,7 +290,8 @@ int
 cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		 const struct nls_table *cp, int mapChars)
 {
-	int i, j, charlen;
+	int i, charlen;
+	int j = 0;
 	char src_char;
 	__le16 dst_char;
 	wchar_t tmp;
@@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	if (!mapChars)
 		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
 
-	for (i = 0, j = 0; i < srclen; j++) {
+	for (i = 0; i < srclen; j++) {
 		src_char = source[i];
 		charlen = 1;
 		switch (src_char) {
 		case 0:
-			put_unaligned(0, &target[j]);
 			goto ctoUTF16_out;
 		case ':':
 			dst_char = cpu_to_le16(UNI_COLON);
@@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	}
 
 ctoUTF16_out:
+	put_unaligned(0, &target[j]); /* Null terminate target unicode string */
 	return j;
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 2c90d07..8883980 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -725,6 +725,19 @@ out_nls:
 	goto out;
 }
 
+static ssize_t
+cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	ssize_t rc;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	rc = cifs_revalidate_mapping(inode);
+	if (rc)
+		return rc;
+
+	return generic_file_read_iter(iocb, iter);
+}
+
 static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -881,7 +894,7 @@ const struct inode_operations cifs_symlink_inode_ops = {
 const struct file_operations cifs_file_ops = {
 	.read = new_sync_read,
 	.write = new_sync_write,
-	.read_iter = generic_file_read_iter,
+	.read_iter = cifs_loose_read_iter,
 	.write_iter = cifs_file_write_iter,
 	.open = cifs_open,
 	.release = cifs_close,
@@ -939,7 +952,7 @@ const struct file_operations cifs_file_direct_ops = {
 const struct file_operations cifs_file_nobrl_ops = {
 	.read = new_sync_read,
 	.write = new_sync_write,
-	.read_iter = generic_file_read_iter,
+	.read_iter = cifs_loose_read_iter,
 	.write_iter = cifs_file_write_iter,
 	.open = cifs_open,
 	.release = cifs_close,
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 264ece7..68559fd 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -374,7 +374,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	oparms.cifs_sb = cifs_sb;
 	oparms.desired_access = GENERIC_WRITE;
 	oparms.create_options = create_options;
-	oparms.disposition = FILE_OPEN;
+	oparms.disposition = FILE_CREATE;
 	oparms.path = path;
 	oparms.fid = &fid;
 	oparms.reconnect = false;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 0762d14..fca3820 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -194,7 +194,16 @@ static void ext4_init_block_bitmap(struct super_block *sb,
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
 		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
@@ -359,6 +368,7 @@ static void ext4_validate_block_bitmap(struct super_block *sb,
 {
 	ext4_fsblk_t	blk;
 	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (buffer_verified(bh))
 		return;
@@ -369,6 +379,9 @@ static void ext4_validate_block_bitmap(struct super_block *sb,
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
 			   block_group, blk);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
@@ -376,6 +389,9 @@ static void ext4_validate_block_bitmap(struct super_block *sb,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 3f5c188..0b7e28e 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -966,10 +966,10 @@ retry:
 			continue;
 		}
 
-		if (ei->i_es_lru_nr == 0 || ei == locked_ei)
+		if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
+		    !write_trylock(&ei->i_es_lock))
 			continue;
 
-		write_lock(&ei->i_es_lock);
 		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
 		if (ei->i_es_lru_nr == 0)
 			list_del_init(&ei->i_es_lru);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 0ee59a6..5b87fc3 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -71,6 +71,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
 				       struct ext4_group_desc *gdp)
 {
 	struct ext4_group_info *grp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
 	/* If checksum is bad mark all blocks and inodes use to prevent
@@ -78,7 +79,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
 		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return 0;
 	}
@@ -116,6 +126,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	struct buffer_head *bh = NULL;
 	ext4_fsblk_t bitmap_blk;
 	struct ext4_group_info *grp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	desc = ext4_get_group_desc(sb, block_group, NULL);
 	if (!desc)
@@ -185,6 +196,12 @@ verify:
 		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
 			   "inode_bitmap = %llu", block_group, bitmap_blk);
 		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, desc);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return NULL;
 	}
@@ -321,6 +338,12 @@ out:
 			fatal = err;
 	} else {
 		ext4_error(sb, "bit already cleared for inode %lu", ino);
+		if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 	}
 
@@ -851,6 +874,13 @@ got:
 		goto out;
 	}
 
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (ext4_has_group_desc_csum(sb) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
@@ -887,13 +917,6 @@ got:
 		}
 	}
 
-	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, group_desc_bh);
-	if (err) {
-		ext4_std_error(sb, err);
-		goto out;
-	}
-
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 8a57e9f..fd69da1 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -389,7 +389,13 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 	return 0;
 failed:
 	for (; i >= 0; i--) {
-		if (i != indirect_blks && branch[i].bh)
+		/*
+		 * We want to ext4_forget() only freshly allocated indirect
+		 * blocks.  Buffer for new_blocks[i-1] is at branch[i].bh and
+		 * buffer at branch[0].bh is indirect block / inode already
+		 * existing before ext4_alloc_branch() was called.
+		 */
+		if (i > 0 && i != indirect_blks && branch[i].bh)
 			ext4_forget(handle, 1, inode, branch[i].bh,
 				    branch[i].bh->b_blocknr);
 		ext4_free_blocks(handle, inode, NULL, new_blocks[i],
@@ -1310,16 +1316,24 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		blk = *i_data;
 		if (level > 0) {
 			ext4_lblk_t first2;
+			ext4_lblk_t count2;
+
 			bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
 			if (!bh) {
 				EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
 						       "Read failure");
 				return -EIO;
 			}
-			first2 = (first > offset) ? first - offset : 0;
+			if (first > offset) {
+				first2 = first - offset;
+				count2 = count;
+			} else {
+				first2 = 0;
+				count2 = count - (offset - first);
+			}
 			ret = free_hole_blocks(handle, inode, bh,
 					       (__le32 *)bh->b_data, level - 1,
-					       first2, count - offset,
+					       first2, count2,
 					       inode->i_sb->s_blocksize >> 2);
 			if (ret) {
 				brelse(bh);
@@ -1329,8 +1343,8 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		if (level == 0 ||
 		    (bh && all_zeroes((__le32 *)bh->b_data,
 				      (__le32 *)bh->b_data + addr_per_block))) {
-			ext4_free_data(handle, inode, parent_bh, &blk, &blk+1);
-			*i_data = 0;
+			ext4_free_data(handle, inode, parent_bh,
+				       i_data, i_data + 1);
 		}
 		brelse(bh);
 		bh = NULL;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 59e3162..2dcb936 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -722,6 +722,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 				void *buddy, void *bitmap, ext4_group_t group)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
 	ext4_grpblk_t i = 0;
 	ext4_grpblk_t first;
@@ -751,14 +752,17 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 
 	if (free != grp->bb_free) {
 		ext4_grp_locked_error(sb, group, 0, 0,
-				      "%u clusters in bitmap, %u in gd; "
-				      "block bitmap corrupt.",
+				      "block bitmap and bg descriptor "
+				      "inconsistent: %u vs %u free clusters",
 				      free, grp->bb_free);
 		/*
 		 * If we intend to continue, we consider group descriptor
 		 * corrupt and update bb_free using bitmap value
 		 */
 		grp->bb_free = free;
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 	}
 	mb_set_largest_free_order(sb, grp);
@@ -1431,6 +1435,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap);
 
 	if (unlikely(block != -1)) {
+		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		ext4_fsblk_t blocknr;
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
@@ -1441,6 +1446,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 				      "freeing already freed block "
 				      "(bit %u); block bitmap corrupt.",
 				      block);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   e4b->bd_info->bb_free);
 		/* Mark the block group as corrupt. */
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
 			&e4b->bd_info->bb_state);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b9b9aab..6df7bc6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1525,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
 	} else if (token == Opt_max_batch_time) {
-		if (arg == 0)
-			arg = EXT4_DEF_MAX_BATCH_TIME;
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
 		sbi->s_min_batch_time = arg;
@@ -2809,10 +2807,11 @@ static void print_daily_error_info(unsigned long arg)
 	es = sbi->s_es;
 
 	if (es->s_error_count)
-		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+		/* fsck newer than v1.41.13 is needed to clean this condition. */
+		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
@@ -2826,7 +2825,7 @@ static void print_daily_error_info(unsigned long arg)
 		printk("\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
@@ -3880,38 +3879,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-
-	/*
-	 * set up enough so that it can read an inode,
-	 * and create new inode for buddy allocator
-	 */
-	sbi->s_gdb_count = db_count;
-	if (!test_opt(sb, NOLOAD) &&
-	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
-		sb->s_op = &ext4_sops;
-	else
-		sb->s_op = &ext4_nojournal_sops;
-
-	ext4_ext_init(sb);
-	err = ext4_mb_init(sb);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
-			 err);
-		goto failed_mount2;
-	}
-
 	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
-		goto failed_mount2a;
+		goto failed_mount2;
 	}
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		if (!ext4_fill_flex_info(sb)) {
 			ext4_msg(sb, KERN_ERR,
 			       "unable to initialize "
 			       "flex_bg meta info!");
-			goto failed_mount2a;
+			goto failed_mount2;
 		}
 
+	sbi->s_gdb_count = db_count;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 	spin_lock_init(&sbi->s_next_gen_lock);
 
@@ -3946,6 +3926,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 	sbi->s_extent_max_zeroout_kb = 32;
 
+	/*
+	 * set up enough so that it can read an inode
+	 */
+	if (!test_opt(sb, NOLOAD) &&
+	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		sb->s_op = &ext4_sops;
+	else
+		sb->s_op = &ext4_nojournal_sops;
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
 #ifdef CONFIG_QUOTA
@@ -4135,13 +4123,21 @@ no_journal:
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
 			 "reserved pool", ext4_calculate_resv_clusters(sb));
-		goto failed_mount5;
+		goto failed_mount4a;
 	}
 
 	err = ext4_setup_system_zone(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize system "
 			 "zone (%d)", err);
+		goto failed_mount4a;
+	}
+
+	ext4_ext_init(sb);
+	err = ext4_mb_init(sb);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
+			 err);
 		goto failed_mount5;
 	}
 
@@ -4218,8 +4214,11 @@ failed_mount8:
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
-	ext4_release_system_zone(sb);
+	ext4_mb_release(sb);
 failed_mount5:
+	ext4_ext_release(sb);
+	ext4_release_system_zone(sb);
+failed_mount4a:
 	dput(sb->s_root);
 	sb->s_root = NULL;
 failed_mount4:
@@ -4243,14 +4242,11 @@ failed_mount3:
 	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
-failed_mount2a:
-	ext4_mb_release(sb);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
 	ext4_kvfree(sbi->s_group_desc);
 failed_mount:
-	ext4_ext_release(sb);
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	if (sbi->s_proc) {
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0924521..f8cf619 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -608,8 +608,8 @@ static int __allocate_data_block(struct dnode_of_data *dn)
  *     b. do not use extent cache for better performance
  *     c. give the block addresses to blockdev
  */
-static int get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create)
+static int __get_data_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create, bool fiemap)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	unsigned int blkbits = inode->i_sb->s_blocksize_bits;
@@ -637,7 +637,7 @@ static int get_data_block(struct inode *inode, sector_t iblock,
 			err = 0;
 		goto unlock_out;
 	}
-	if (dn.data_blkaddr == NEW_ADDR)
+	if (dn.data_blkaddr == NEW_ADDR && !fiemap)
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
@@ -671,7 +671,7 @@ get_next:
 				err = 0;
 			goto unlock_out;
 		}
-		if (dn.data_blkaddr == NEW_ADDR)
+		if (dn.data_blkaddr == NEW_ADDR && !fiemap)
 			goto put_out;
 
 		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
@@ -708,10 +708,23 @@ out:
 	return err;
 }
 
+static int get_data_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create)
+{
+	return __get_data_block(inode, iblock, bh_result, create, false);
+}
+
+static int get_data_block_fiemap(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create)
+{
+	return __get_data_block(inode, iblock, bh_result, create, true);
+}
+
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len)
 {
-	return generic_block_fiemap(inode, fieinfo, start, len, get_data_block);
+	return generic_block_fiemap(inode, fieinfo,
+				start, len, get_data_block_fiemap);
 }
 
 static int f2fs_read_data_page(struct file *file, struct page *page)
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 966acb0..a4addd7 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -376,11 +376,11 @@ static struct page *init_inode_metadata(struct inode *inode,
 
 put_error:
 	f2fs_put_page(page, 1);
+error:
 	/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_blocks(inode, 0);
 	remove_dirty_dir_inode(inode);
-error:
 	remove_inode_page(inode);
 	return ERR_PTR(err);
 }
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e51c732..58df97e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -342,9 +342,6 @@ struct f2fs_sm_info {
 	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
 	struct curseg_info *curseg_array;	/* active segment information */
 
-	struct list_head wblist_head;	/* list of under-writeback pages */
-	spinlock_t wblist_lock;		/* lock for checkpoint */
-
 	block_t seg0_blkaddr;		/* block address of 0'th segment */
 	block_t main_blkaddr;		/* start block address of main area */
 	block_t ssa_blkaddr;		/* start block address of SSA area */
@@ -644,7 +641,8 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
  */
 static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	WARN_ON((nid >= NM_I(sbi)->max_nid));
+	if (unlikely(nid < F2FS_ROOT_INO(sbi)))
+		return -EINVAL;
 	if (unlikely(nid >= NM_I(sbi)->max_nid))
 		return -EINVAL;
 	return 0;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index c58e330..7d8b962 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -659,16 +659,19 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	off_start = offset & (PAGE_CACHE_SIZE - 1);
 	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
 
+	f2fs_lock_op(sbi);
+
 	for (index = pg_start; index <= pg_end; index++) {
 		struct dnode_of_data dn;
 
-		f2fs_lock_op(sbi);
+		if (index == pg_end && !off_end)
+			goto noalloc;
+
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 		ret = f2fs_reserve_block(&dn, index);
-		f2fs_unlock_op(sbi);
 		if (ret)
 			break;
-
+noalloc:
 		if (pg_start == pg_end)
 			new_size = offset + len;
 		else if (index == pg_start && off_start)
@@ -683,8 +686,9 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 		i_size_read(inode) < new_size) {
 		i_size_write(inode, new_size);
 		mark_inode_dirty(inode);
-		f2fs_write_inode(inode, NULL);
+		update_inode_page(inode);
 	}
+	f2fs_unlock_op(sbi);
 
 	return ret;
 }
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index adc622c..2cf6962 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -78,6 +78,7 @@ static int do_read_inode(struct inode *inode)
 	if (check_nid_range(sbi, inode->i_ino)) {
 		f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
 			 (unsigned long) inode->i_ino);
+		WARN_ON(1);
 		return -EINVAL;
 	}
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 9138c32..a6bdddc 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -417,9 +417,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 
 		f2fs_set_link(new_dir, new_entry, new_page, old_inode);
-		down_write(&F2FS_I(old_inode)->i_sem);
-		F2FS_I(old_inode)->i_pino = new_dir->i_ino;
-		up_write(&F2FS_I(old_inode)->i_sem);
 
 		new_inode->i_ctime = CURRENT_TIME;
 		down_write(&F2FS_I(new_inode)->i_sem);
@@ -448,6 +445,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
+	down_write(&F2FS_I(old_inode)->i_sem);
+	file_lost_pino(old_inode);
+	up_write(&F2FS_I(old_inode)->i_sem);
+
 	old_inode->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(old_inode);
 
@@ -457,9 +458,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (old_dir != new_dir) {
 			f2fs_set_link(old_inode, old_dir_entry,
 						old_dir_page, new_dir);
-			down_write(&F2FS_I(old_inode)->i_sem);
-			F2FS_I(old_inode)->i_pino = new_dir->i_ino;
-			up_write(&F2FS_I(old_inode)->i_sem);
 			update_inode_page(old_inode);
 		} else {
 			kunmap(old_dir_page);
@@ -474,7 +472,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return 0;
 
 put_out_dir:
-	f2fs_put_page(new_page, 1);
+	kunmap(new_page);
+	f2fs_put_page(new_page, 0);
 out_dir:
 	if (old_dir_entry) {
 		kunmap(old_dir_page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9dfb9a0..4b697cc 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -42,6 +42,8 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
 		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
 	} else if (type == DIRTY_DENTS) {
+		if (sbi->sb->s_bdi->dirty_exceeded)
+			return false;
 		mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
 		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
 	}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f25f0e0..d04613d 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -272,14 +272,15 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 	spin_lock_init(&fcc->issue_lock);
 	init_waitqueue_head(&fcc->flush_wait_queue);
+	sbi->sm_info->cmd_control_info = fcc;
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
 		err = PTR_ERR(fcc->f2fs_issue_flush);
 		kfree(fcc);
+		sbi->sm_info->cmd_control_info = NULL;
 		return err;
 	}
-	sbi->sm_info->cmd_control_info = fcc;
 
 	return err;
 }
@@ -1885,8 +1886,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 
 	/* init sm info */
 	sbi->sm_info = sm_info;
-	INIT_LIST_HEAD(&sm_info->wblist_head);
-	spin_lock_init(&sm_info->wblist_lock);
 	sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
 	sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
 	sm_info->segment_count = le32_to_cpu(raw_super->segment_count);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b2b1863..8f96d93 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -689,9 +689,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
 
-	if (unlikely(ino < F2FS_ROOT_INO(sbi)))
-		return ERR_PTR(-ESTALE);
-	if (unlikely(ino >= NM_I(sbi)->max_nid))
+	if (check_nid_range(sbi, ino))
 		return ERR_PTR(-ESTALE);
 
 	/*
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 098f97b..ca88731 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -643,9 +643,8 @@ struct fuse_copy_state {
 	unsigned long seglen;
 	unsigned long addr;
 	struct page *pg;
-	void *mapaddr;
-	void *buf;
 	unsigned len;
+	unsigned offset;
 	unsigned move_pages:1;
 };
 
@@ -666,23 +665,17 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
 	if (cs->currbuf) {
 		struct pipe_buffer *buf = cs->currbuf;
 
-		if (!cs->write) {
-			kunmap_atomic(cs->mapaddr);
-		} else {
-			kunmap_atomic(cs->mapaddr);
+		if (cs->write)
 			buf->len = PAGE_SIZE - cs->len;
-		}
 		cs->currbuf = NULL;
-		cs->mapaddr = NULL;
-	} else if (cs->mapaddr) {
-		kunmap_atomic(cs->mapaddr);
+	} else if (cs->pg) {
 		if (cs->write) {
 			flush_dcache_page(cs->pg);
 			set_page_dirty_lock(cs->pg);
 		}
 		put_page(cs->pg);
-		cs->mapaddr = NULL;
 	}
+	cs->pg = NULL;
 }
 
 /*
@@ -691,7 +684,7 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
  */
 static int fuse_copy_fill(struct fuse_copy_state *cs)
 {
-	unsigned long offset;
+	struct page *page;
 	int err;
 
 	unlock_request(cs->fc, cs->req);
@@ -706,14 +699,12 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 
 			BUG_ON(!cs->nr_segs);
 			cs->currbuf = buf;
-			cs->mapaddr = kmap_atomic(buf->page);
+			cs->pg = buf->page;
+			cs->offset = buf->offset;
 			cs->len = buf->len;
-			cs->buf = cs->mapaddr + buf->offset;
 			cs->pipebufs++;
 			cs->nr_segs--;
 		} else {
-			struct page *page;
-
 			if (cs->nr_segs == cs->pipe->buffers)
 				return -EIO;
 
@@ -726,8 +717,8 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 			buf->len = 0;
 
 			cs->currbuf = buf;
-			cs->mapaddr = kmap_atomic(page);
-			cs->buf = cs->mapaddr;
+			cs->pg = page;
+			cs->offset = 0;
 			cs->len = PAGE_SIZE;
 			cs->pipebufs++;
 			cs->nr_segs++;
@@ -740,14 +731,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 			cs->iov++;
 			cs->nr_segs--;
 		}
-		err = get_user_pages_fast(cs->addr, 1, cs->write, &cs->pg);
+		err = get_user_pages_fast(cs->addr, 1, cs->write, &page);
 		if (err < 0)
 			return err;
 		BUG_ON(err != 1);
-		offset = cs->addr % PAGE_SIZE;
-		cs->mapaddr = kmap_atomic(cs->pg);
-		cs->buf = cs->mapaddr + offset;
-		cs->len = min(PAGE_SIZE - offset, cs->seglen);
+		cs->pg = page;
+		cs->offset = cs->addr % PAGE_SIZE;
+		cs->len = min(PAGE_SIZE - cs->offset, cs->seglen);
 		cs->seglen -= cs->len;
 		cs->addr += cs->len;
 	}
@@ -760,15 +750,20 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
 {
 	unsigned ncpy = min(*size, cs->len);
 	if (val) {
+		void *pgaddr = kmap_atomic(cs->pg);
+		void *buf = pgaddr + cs->offset;
+
 		if (cs->write)
-			memcpy(cs->buf, *val, ncpy);
+			memcpy(buf, *val, ncpy);
 		else
-			memcpy(*val, cs->buf, ncpy);
+			memcpy(*val, buf, ncpy);
+
+		kunmap_atomic(pgaddr);
 		*val += ncpy;
 	}
 	*size -= ncpy;
 	cs->len -= ncpy;
-	cs->buf += ncpy;
+	cs->offset += ncpy;
 	return ncpy;
 }
 
@@ -874,8 +869,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 out_fallback_unlock:
 	unlock_page(newpage);
 out_fallback:
-	cs->mapaddr = kmap_atomic(buf->page);
-	cs->buf = cs->mapaddr + buf->offset;
+	cs->pg = buf->page;
+	cs->offset = buf->offset;
 
 	err = lock_request(cs->fc, cs->req);
 	if (err)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 4219835..0c60482 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -198,7 +198,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 	inode = ACCESS_ONCE(entry->d_inode);
 	if (inode && is_bad_inode(inode))
 		goto invalid;
-	else if (fuse_dentry_time(entry) < get_jiffies_64()) {
+	else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
+		 (flags & LOOKUP_REVAL)) {
 		int err;
 		struct fuse_entry_out outarg;
 		struct fuse_req *req;
@@ -814,13 +815,6 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent,
 	return err;
 }
 
-static int fuse_rename(struct inode *olddir, struct dentry *oldent,
-		       struct inode *newdir, struct dentry *newent)
-{
-	return fuse_rename_common(olddir, oldent, newdir, newent, 0,
-				  FUSE_RENAME, sizeof(struct fuse_rename_in));
-}
-
 static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
 			struct inode *newdir, struct dentry *newent,
 			unsigned int flags)
@@ -831,17 +825,30 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
 		return -EINVAL;
 
-	if (fc->no_rename2 || fc->minor < 23)
-		return -EINVAL;
+	if (flags) {
+		if (fc->no_rename2 || fc->minor < 23)
+			return -EINVAL;
 
-	err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
-				 FUSE_RENAME2, sizeof(struct fuse_rename2_in));
-	if (err == -ENOSYS) {
-		fc->no_rename2 = 1;
-		err = -EINVAL;
+		err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
+					 FUSE_RENAME2,
+					 sizeof(struct fuse_rename2_in));
+		if (err == -ENOSYS) {
+			fc->no_rename2 = 1;
+			err = -EINVAL;
+		}
+	} else {
+		err = fuse_rename_common(olddir, oldent, newdir, newent, 0,
+					 FUSE_RENAME,
+					 sizeof(struct fuse_rename_in));
 	}
+
 	return err;
+}
 
+static int fuse_rename(struct inode *olddir, struct dentry *oldent,
+		       struct inode *newdir, struct dentry *newent)
+{
+	return fuse_rename2(olddir, oldent, newdir, newent, 0);
 }
 
 static int fuse_link(struct dentry *entry, struct inode *newdir,
@@ -985,7 +992,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
 	int err;
 	bool r;
 
-	if (fi->i_time < get_jiffies_64()) {
+	if (time_before64(fi->i_time, get_jiffies_64())) {
 		r = true;
 		err = fuse_do_getattr(inode, stat, file);
 	} else {
@@ -1171,7 +1178,7 @@ static int fuse_permission(struct inode *inode, int mask)
 	    ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
 		struct fuse_inode *fi = get_fuse_inode(inode);
 
-		if (fi->i_time < get_jiffies_64()) {
+		if (time_before64(fi->i_time, get_jiffies_64())) {
 			refreshed = true;
 
 			err = fuse_perm_getattr(inode, mask);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 6e16dad..40ac262 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1687,7 +1687,7 @@ static int fuse_writepage_locked(struct page *page)
 	error = -EIO;
 	req->ff = fuse_write_file_get(fc, fi);
 	if (!req->ff)
-		goto err_free;
+		goto err_nofile;
 
 	fuse_write_fill(req, req->ff, page_offset(page), 0);
 
@@ -1715,6 +1715,8 @@ static int fuse_writepage_locked(struct page *page)
 
 	return 0;
 
+err_nofile:
+	__free_page(tmp_page);
 err_free:
 	fuse_request_free(req);
 err:
@@ -1955,8 +1957,8 @@ static int fuse_writepages(struct address_space *mapping,
 	data.ff = NULL;
 
 	err = -ENOMEM;
-	data.orig_pages = kzalloc(sizeof(struct page *) *
-				  FUSE_MAX_PAGES_PER_REQ,
+	data.orig_pages = kcalloc(FUSE_MAX_PAGES_PER_REQ,
+				  sizeof(struct page *),
 				  GFP_NOFS);
 	if (!data.orig_pages)
 		goto out;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 754dcf2..8474028 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -478,6 +478,17 @@ static const match_table_t tokens = {
 	{OPT_ERR,			NULL}
 };
 
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+	int err = -ENOMEM;
+	char *buf = match_strdup(s);
+	if (buf) {
+		err = kstrtouint(buf, 10, res);
+		kfree(buf);
+	}
+	return err;
+}
+
 static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 {
 	char *p;
@@ -488,6 +499,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 	while ((p = strsep(&opt, ",")) != NULL) {
 		int token;
 		int value;
+		unsigned uv;
 		substring_t args[MAX_OPT_ARGS];
 		if (!*p)
 			continue;
@@ -511,18 +523,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 			break;
 
 		case OPT_USER_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->user_id = make_kuid(current_user_ns(), value);
+			d->user_id = make_kuid(current_user_ns(), uv);
 			if (!uid_valid(d->user_id))
 				return 0;
 			d->user_id_present = 1;
 			break;
 
 		case OPT_GROUP_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->group_id = make_kgid(current_user_ns(), value);
+			d->group_id = make_kgid(current_user_ns(), uv);
 			if (!gid_valid(d->group_id))
 				return 0;
 			d->group_id_present = 1;
@@ -1006,7 +1018,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION);
 
-	if (!parse_fuse_opt((char *) data, &d, is_bdev))
+	if (!parse_fuse_opt(data, &d, is_bdev))
 		goto err;
 
 	if (is_bdev) {
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4fc3a30..26b3f95 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -981,7 +981,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	int error = 0;
 
 	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT;
 
 	mutex_lock(&fp->f_fl_mutex);
 
@@ -991,7 +991,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 			goto out;
 		flock_lock_file_wait(file,
 				     &(struct file_lock){.fl_type = F_UNLCK});
-		gfs2_glock_dq_wait(fl_gh);
+		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
 		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c355f73..ee4e04f 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -731,14 +731,14 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		cachep = gfs2_glock_aspace_cachep;
 	else
 		cachep = gfs2_glock_cachep;
-	gl = kmem_cache_alloc(cachep, GFP_KERNEL);
+	gl = kmem_cache_alloc(cachep, GFP_NOFS);
 	if (!gl)
 		return -ENOMEM;
 
 	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
 
 	if (glops->go_flags & GLOF_LVB) {
-		gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_KERNEL);
+		gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS);
 		if (!gl->gl_lksb.sb_lvbptr) {
 			kmem_cache_free(cachep, gl);
 			return -ENOMEM;
@@ -1404,12 +1404,16 @@ __acquires(&lru_lock)
 		gl = list_entry(list->next, struct gfs2_glock, gl_lru);
 		list_del_init(&gl->gl_lru);
 		if (!spin_trylock(&gl->gl_spin)) {
+add_back_to_lru:
 			list_add(&gl->gl_lru, &lru_list);
 			atomic_inc(&lru_count);
 			continue;
 		}
+		if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+			spin_unlock(&gl->gl_spin);
+			goto add_back_to_lru;
+		}
 		clear_bit(GLF_LRU, &gl->gl_flags);
-		spin_unlock(&lru_lock);
 		gl->gl_lockref.count++;
 		if (demote_ok(gl))
 			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
@@ -1417,7 +1421,7 @@ __acquires(&lru_lock)
 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 			gl->gl_lockref.count--;
 		spin_unlock(&gl->gl_spin);
-		spin_lock(&lru_lock);
+		cond_resched_lock(&lru_lock);
 	}
 }
 
@@ -1442,7 +1446,7 @@ static long gfs2_scan_glock_lru(int nr)
 		gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
 
 		/* Test for being demotable */
-		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+		if (!test_bit(GLF_LOCK, &gl->gl_flags)) {
 			list_move(&gl->gl_lru, &dispose);
 			atomic_dec(&lru_count);
 			freed++;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index fc11007..2ffc67d 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -234,8 +234,8 @@ static void inode_go_sync(struct gfs2_glock *gl)
  * inode_go_inval - prepare a inode glock to be released
  * @gl: the glock
  * @flags:
- * 
- * Normally we invlidate everything, but if we are moving into
+ *
+ * Normally we invalidate everything, but if we are moving into
  * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
  * can keep hold of the metadata, since it won't have changed.
  *
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 91f274d..4fafea1 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1036,8 +1036,8 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots,
 
 	new_size = old_size + RECOVER_SIZE_INC;
 
-	submit = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS);
-	result = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS);
+	submit = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS);
+	result = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS);
 	if (!submit || !result) {
 		kfree(submit);
 		kfree(result);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index db629d1..f4cb9c0 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -337,7 +337,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le
 
 /**
  * gfs2_free_extlen - Return extent length of free blocks
- * @rbm: Starting position
+ * @rrbm: Starting position
  * @len: Max length to check
  *
  * Starting at the block specified by the rbm, see how many free blocks
@@ -2522,7 +2522,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state)
 
 /**
  * gfs2_rlist_free - free a resource group list
- * @list: the list of resource groups
+ * @rlist: the list of resource groups
  *
  */
 
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 38cfcf5..6f0f590 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1588,9 +1588,12 @@ int jbd2_journal_stop(handle_t *handle)
 	 * to perform a synchronous write.  We do this to detect the
 	 * case where a single process is doing a stream of sync
 	 * writes.  No point in waiting for joiners in that case.
+	 *
+	 * Setting max_batch_time to 0 disables this completely.
 	 */
 	pid = current->pid;
-	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+	if (handle->h_sync && journal->j_last_sync_writer != pid &&
+	    journal->j_max_batch_time) {
 		u64 commit_time, trans_time;
 
 		journal->j_last_sync_writer = pid;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e3d37f6..d895b4b 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -39,6 +39,19 @@ struct kernfs_open_node {
 	struct list_head	files; /* goes through kernfs_open_file.list */
 };
 
+/*
+ * kernfs_notify() may be called from any context and bounces notifications
+ * through a work item.  To minimize space overhead in kernfs_node, the
+ * pending queue is implemented as a singly linked list of kernfs_nodes.
+ * The list is terminated with the self pointer so that whether a
+ * kernfs_node is on the list or not can be determined by testing the next
+ * pointer for NULL.
+ */
+#define KERNFS_NOTIFY_EOL			((void *)&kernfs_notify_list)
+
+static DEFINE_SPINLOCK(kernfs_notify_lock);
+static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;
+
 static struct kernfs_open_file *kernfs_of(struct file *file)
 {
 	return ((struct seq_file *)file->private_data)->private;
@@ -783,24 +796,25 @@ static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
 	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
 }
 
-/**
- * kernfs_notify - notify a kernfs file
- * @kn: file to notify
- *
- * Notify @kn such that poll(2) on @kn wakes up.
- */
-void kernfs_notify(struct kernfs_node *kn)
+static void kernfs_notify_workfn(struct work_struct *work)
 {
-	struct kernfs_root *root = kernfs_root(kn);
+	struct kernfs_node *kn;
 	struct kernfs_open_node *on;
 	struct kernfs_super_info *info;
-	unsigned long flags;
-
-	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
+repeat:
+	/* pop one off the notify_list */
+	spin_lock_irq(&kernfs_notify_lock);
+	kn = kernfs_notify_list;
+	if (kn == KERNFS_NOTIFY_EOL) {
+		spin_unlock_irq(&kernfs_notify_lock);
 		return;
+	}
+	kernfs_notify_list = kn->attr.notify_next;
+	kn->attr.notify_next = NULL;
+	spin_unlock_irq(&kernfs_notify_lock);
 
 	/* kick poll */
-	spin_lock_irqsave(&kernfs_open_node_lock, flags);
+	spin_lock_irq(&kernfs_open_node_lock);
 
 	on = kn->attr.open;
 	if (on) {
@@ -808,12 +822,12 @@ void kernfs_notify(struct kernfs_node *kn)
 		wake_up_interruptible(&on->poll);
 	}
 
-	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
+	spin_unlock_irq(&kernfs_open_node_lock);
 
 	/* kick fsnotify */
 	mutex_lock(&kernfs_mutex);
 
-	list_for_each_entry(info, &root->supers, node) {
+	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
 		struct inode *inode;
 		struct dentry *dentry;
 
@@ -833,6 +847,33 @@ void kernfs_notify(struct kernfs_node *kn)
 	}
 
 	mutex_unlock(&kernfs_mutex);
+	kernfs_put(kn);
+	goto repeat;
+}
+
+/**
+ * kernfs_notify - notify a kernfs file
+ * @kn: file to notify
+ *
+ * Notify @kn such that poll(2) on @kn wakes up.  Maybe be called from any
+ * context.
+ */
+void kernfs_notify(struct kernfs_node *kn)
+{
+	static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn);
+	unsigned long flags;
+
+	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
+		return;
+
+	spin_lock_irqsave(&kernfs_notify_lock, flags);
+	if (!kn->attr.notify_next) {
+		kernfs_get(kn);
+		kn->attr.notify_next = kernfs_notify_list;
+		kernfs_notify_list = kn;
+		schedule_work(&kernfs_notify_work);
+	}
+	spin_unlock_irqrestore(&kernfs_notify_lock, flags);
 }
 EXPORT_SYMBOL_GPL(kernfs_notify);
 
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d171b98..f973ae9 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -211,6 +211,36 @@ void kernfs_kill_sb(struct super_block *sb)
 	kernfs_put(root_kn);
 }
 
+/**
+ * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
+ * @kernfs_root: the kernfs_root in question
+ * @ns: the namespace tag
+ *
+ * Pin the superblock so the superblock won't be destroyed in subsequent
+ * operations.  This can be used to block ->kill_sb() which may be useful
+ * for kernfs users which dynamically manage superblocks.
+ *
+ * Returns NULL if there's no superblock associated to this kernfs_root, or
+ * -EINVAL if the superblock is being freed.
+ */
+struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
+{
+	struct kernfs_super_info *info;
+	struct super_block *sb = NULL;
+
+	mutex_lock(&kernfs_mutex);
+	list_for_each_entry(info, &root->supers, node) {
+		if (info->ns == ns) {
+			sb = info->sb;
+			if (!atomic_inc_not_zero(&info->sb->s_active))
+				sb = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	mutex_unlock(&kernfs_mutex);
+	return sb;
+}
+
 void __init kernfs_init(void)
 {
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
diff --git a/fs/mbcache.c b/fs/mbcache.c
index bf166e3..187477d 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -73,6 +73,7 @@
 #include <linux/mbcache.h>
 #include <linux/init.h>
 #include <linux/blockgroup_lock.h>
+#include <linux/log2.h>
 
 #ifdef MB_CACHE_DEBUG
 # define mb_debug(f...) do { \
@@ -93,7 +94,7 @@
 
 #define MB_CACHE_WRITER ((unsigned short)~0U >> 1)
 
-#define MB_CACHE_ENTRY_LOCK_BITS	__builtin_log2(NR_BG_LOCKS)
+#define MB_CACHE_ENTRY_LOCK_BITS	ilog2(NR_BG_LOCKS)
 #define	MB_CACHE_ENTRY_LOCK_INDEX(ce)			\
 	(hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS))
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6851b00..8f029db 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -617,15 +617,6 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	switch (create->cr_type) {
 	case NF4LNK:
-		/* ugh! we have to null-terminate the linktext, or
-		 * vfs_symlink() will choke.  it is always safe to
-		 * null-terminate by brute force, since at worst we
-		 * will overwrite the first byte of the create namelen
-		 * in the XDR buffer, which has already been extracted
-		 * during XDR decode.
-		 */
-		create->cr_linkname[create->cr_linklen] = 0;
-
 		status = nfsd_symlink(rqstp, &cstate->current_fh,
 				      create->cr_name, create->cr_namelen,
 				      create->cr_linkname, create->cr_linklen,
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 83baf2b..b56b1cc0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -600,7 +600,18 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 		READ_BUF(4);
 		create->cr_linklen = be32_to_cpup(p++);
 		READ_BUF(create->cr_linklen);
-		SAVEMEM(create->cr_linkname, create->cr_linklen);
+		/*
+		 * The VFS will want a null-terminated string, and
+		 * null-terminating in place isn't safe since this might
+		 * end on a page boundary:
+		 */
+		create->cr_linkname =
+				kmalloc(create->cr_linklen + 1, GFP_KERNEL);
+		if (!create->cr_linkname)
+			return nfserr_jukebox;
+		memcpy(create->cr_linkname, p, create->cr_linklen);
+		create->cr_linkname[create->cr_linklen] = '\0';
+		defer_free(argp, kfree, create->cr_linkname);
 		break;
 	case NF4BLK:
 	case NF4CHR:
@@ -2630,7 +2641,7 @@ nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr)
 {
 	__be32 *p;
 
-	p = xdr_reserve_space(xdr, 6);
+	p = xdr_reserve_space(xdr, 20);
 	if (!p)
 		return NULL;
 	*p++ = htonl(2);
@@ -3267,7 +3278,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
 
 	wire_count = htonl(maxcount);
 	write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4);
-	xdr_truncate_encode(xdr, length_offset + 4 + maxcount);
+	xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4));
 	if (maxcount & 3)
 		write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount,
 						&zero, 4 - (maxcount&3));
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index a106b3f..fae17c6 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -331,6 +331,7 @@ struct dlm_lock_resource
 	u16 state;
 	char lvb[DLM_LVB_LEN];
 	unsigned int inflight_locks;
+	unsigned int inflight_assert_workers;
 	unsigned long refmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
 };
 
@@ -910,6 +911,9 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
 void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
 				   struct dlm_lock_resource *res);
 
+void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res);
+
 void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 3087a21..82abf0c 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -581,6 +581,7 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 	atomic_set(&res->asts_reserved, 0);
 	res->migration_pending = 0;
 	res->inflight_locks = 0;
+	res->inflight_assert_workers = 0;
 
 	res->dlm = dlm;
 
@@ -683,6 +684,43 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
 	wake_up(&res->wq);
 }
 
+void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
+	res->inflight_assert_workers++;
+	mlog(0, "%s:%.*s: inflight assert worker++: now %u\n",
+			dlm->name, res->lockname.len, res->lockname.name,
+			res->inflight_assert_workers);
+}
+
+static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	spin_lock(&res->spinlock);
+	__dlm_lockres_grab_inflight_worker(dlm, res);
+	spin_unlock(&res->spinlock);
+}
+
+static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
+	BUG_ON(res->inflight_assert_workers == 0);
+	res->inflight_assert_workers--;
+	mlog(0, "%s:%.*s: inflight assert worker--: now %u\n",
+			dlm->name, res->lockname.len, res->lockname.name,
+			res->inflight_assert_workers);
+}
+
+static void dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	spin_lock(&res->spinlock);
+	__dlm_lockres_drop_inflight_worker(dlm, res);
+	spin_unlock(&res->spinlock);
+}
+
 /*
  * lookup a lock resource by name.
  * may already exist in the hashtable.
@@ -1603,7 +1641,8 @@ send_response:
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
-		}
+		} else
+			dlm_lockres_grab_inflight_worker(dlm, res);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
@@ -2118,6 +2157,8 @@ static void dlm_assert_master_worker(struct dlm_work_item *item, void *data)
 	dlm_lockres_release_ast(dlm, res);
 
 put:
+	dlm_lockres_drop_inflight_worker(dlm, res);
+
 	dlm_lockres_put(res);
 
 	mlog(0, "finished with dlm_assert_master_worker\n");
@@ -3088,11 +3129,15 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 			/* remove it so that only one mle will be found */
 			__dlm_unlink_mle(dlm, tmp);
 			__dlm_mle_detach_hb_events(dlm, tmp);
-			ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
-			mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
-			    "telling master to get ref for cleared out mle "
-			    "during migration\n", dlm->name, namelen, name,
-			    master, new_master);
+			if (tmp->type == DLM_MLE_MASTER) {
+				ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
+				mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
+						"telling master to get ref "
+						"for cleared out mle during "
+						"migration\n", dlm->name,
+						namelen, name, master,
+						new_master);
+			}
 		}
 		spin_unlock(&tmp->spinlock);
 	}
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 5de0194..45067fa 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1708,7 +1708,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				mlog_errno(-ENOMEM);
 				/* retry!? */
 				BUG();
-			}
+			} else
+				__dlm_lockres_grab_inflight_worker(dlm, res);
 		} else /* put.. incase we are not the master */
 			dlm_lockres_put(res);
 		spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 9db869d..69aac6f 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -259,12 +259,15 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
 		 * refs on it. */
 		unused = __dlm_lockres_unused(lockres);
 		if (!unused ||
-		    (lockres->state & DLM_LOCK_RES_MIGRATING)) {
+		    (lockres->state & DLM_LOCK_RES_MIGRATING) ||
+		    (lockres->inflight_assert_workers != 0)) {
 			mlog(0, "%s: res %.*s is in use or being remastered, "
-			     "used %d, state %d\n", dlm->name,
-			     lockres->lockname.len, lockres->lockname.name,
-			     !unused, lockres->state);
-			list_move_tail(&dlm->purge_list, &lockres->purge);
+			     "used %d, state %d, assert master workers %u\n",
+			     dlm->name, lockres->lockname.len,
+			     lockres->lockname.name,
+			     !unused, lockres->state,
+			     lockres->inflight_assert_workers);
+			list_move_tail(&lockres->purge, &dlm->purge_list);
 			spin_unlock(&lockres->spinlock);
 			continue;
 		}
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 5698b52..2e3c9db 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -191,7 +191,9 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 				     DLM_UNLOCK_CLEAR_CONVERT_TYPE);
 		} else if (status == DLM_RECOVERING ||
 			   status == DLM_MIGRATING ||
-			   status == DLM_FORWARD) {
+			   status == DLM_FORWARD ||
+			   status == DLM_NOLOCKMGR
+			   ) {
 			/* must clear the actions because this unlock
 			 * is about to be retried.  cannot free or do
 			 * any list manipulation. */
@@ -200,7 +202,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 			     res->lockname.name,
 			     status==DLM_RECOVERING?"recovering":
 			     (status==DLM_MIGRATING?"migrating":
-			      "forward"));
+				(status == DLM_FORWARD ? "forward" :
+						"nolockmanager")));
 			actions = 0;
 		}
 		if (flags & LKM_CANCEL)
@@ -364,7 +367,10 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
 			 * updated state to the recovery master.  this thread
 			 * just needs to finish out the operation and call
 			 * the unlockast. */
-			ret = DLM_NORMAL;
+			if (dlm_is_node_dead(dlm, owner))
+				ret = DLM_NORMAL;
+			else
+				ret = DLM_NOLOCKMGR;
 		} else {
 			/* something bad.  this will BUG in ocfs2 */
 			ret = dlm_err_to_dlm_status(tmpret);
@@ -638,7 +644,9 @@ retry:
 
 	if (status == DLM_RECOVERING ||
 	    status == DLM_MIGRATING ||
-	    status == DLM_FORWARD) {
+	    status == DLM_FORWARD ||
+	    status == DLM_NOLOCKMGR) {
+
 		/* We want to go away for a tiny bit to allow recovery
 		 * / migration to complete on this resource. I don't
 		 * know of any wait queue we could sleep on as this
@@ -650,7 +658,7 @@ retry:
 		msleep(50);
 
 		mlog(0, "retrying unlock due to pending recovery/"
-		     "migration/in-progress\n");
+		     "migration/in-progress/reconnect\n");
 		goto retry;
 	}
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 2060fc3..8add6f1 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -205,6 +205,21 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
 	return inode;
 }
 
+static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb,
+		struct dentry *dentry, struct inode *inode)
+{
+	struct ocfs2_dentry_lock *dl = dentry->d_fsdata;
+
+	ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
+	ocfs2_lock_res_free(&dl->dl_lockres);
+	BUG_ON(dl->dl_count != 1);
+	spin_lock(&dentry_attach_lock);
+	dentry->d_fsdata = NULL;
+	spin_unlock(&dentry_attach_lock);
+	kfree(dl);
+	iput(inode);
+}
+
 static int ocfs2_mknod(struct inode *dir,
 		       struct dentry *dentry,
 		       umode_t mode,
@@ -231,6 +246,7 @@ static int ocfs2_mknod(struct inode *dir,
 	sigset_t oldset;
 	int did_block_signals = 0;
 	struct posix_acl *default_acl = NULL, *acl = NULL;
+	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
 			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
@@ -423,6 +439,8 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
+	dl = dentry->d_fsdata;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
 				 &lookup);
@@ -469,6 +487,9 @@ leave:
 	 * ocfs2_delete_inode will mutex_lock again.
 	 */
 	if ((status < 0) && inode) {
+		if (dl)
+			ocfs2_cleanup_add_entry_failure(osb, dentry, inode);
+
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
@@ -991,6 +1012,65 @@ leave:
 	return status;
 }
 
+static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
+		u64 src_inode_no, u64 dest_inode_no)
+{
+	int ret = 0, i = 0;
+	u64 parent_inode_no = 0;
+	u64 child_inode_no = src_inode_no;
+	struct inode *child_inode;
+
+#define MAX_LOOKUP_TIMES 32
+	while (1) {
+		child_inode = ocfs2_iget(osb, child_inode_no, 0, 0);
+		if (IS_ERR(child_inode)) {
+			ret = PTR_ERR(child_inode);
+			break;
+		}
+
+		ret = ocfs2_inode_lock(child_inode, NULL, 0);
+		if (ret < 0) {
+			iput(child_inode);
+			if (ret != -ENOENT)
+				mlog_errno(ret);
+			break;
+		}
+
+		ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2,
+				&parent_inode_no);
+		ocfs2_inode_unlock(child_inode, 0);
+		iput(child_inode);
+		if (ret < 0) {
+			ret = -ENOENT;
+			break;
+		}
+
+		if (parent_inode_no == dest_inode_no) {
+			ret = 1;
+			break;
+		}
+
+		if (parent_inode_no == osb->root_inode->i_ino) {
+			ret = 0;
+			break;
+		}
+
+		child_inode_no = parent_inode_no;
+
+		if (++i >= MAX_LOOKUP_TIMES) {
+			mlog(ML_NOTICE, "max lookup times reached, filesystem "
+					"may have nested directories, "
+					"src inode: %llu, dest inode: %llu.\n",
+					(unsigned long long)src_inode_no,
+					(unsigned long long)dest_inode_no);
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The only place this should be used is rename!
  * if they have the same id, then the 1st one is the only one locked.
@@ -1002,6 +1082,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 			     struct inode *inode2)
 {
 	int status;
+	int inode1_is_ancestor, inode2_is_ancestor;
 	struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
 	struct ocfs2_inode_info *oi2 = OCFS2_I(inode2);
 	struct buffer_head **tmpbh;
@@ -1015,9 +1096,26 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	if (*bh2)
 		*bh2 = NULL;
 
-	/* we always want to lock the one with the lower lockid first. */
+	/* we always want to lock the one with the lower lockid first.
+	 * and if they are nested, we lock ancestor first */
 	if (oi1->ip_blkno != oi2->ip_blkno) {
-		if (oi1->ip_blkno < oi2->ip_blkno) {
+		inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno,
+				oi1->ip_blkno);
+		if (inode1_is_ancestor < 0) {
+			status = inode1_is_ancestor;
+			goto bail;
+		}
+
+		inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno,
+				oi2->ip_blkno);
+		if (inode2_is_ancestor < 0) {
+			status = inode2_is_ancestor;
+			goto bail;
+		}
+
+		if ((inode1_is_ancestor == 1) ||
+				(oi1->ip_blkno < oi2->ip_blkno &&
+				inode2_is_ancestor == 0)) {
 			/* switch id1 and id2 around */
 			tmpbh = bh2;
 			bh2 = bh1;
@@ -1098,6 +1196,7 @@ static int ocfs2_rename(struct inode *old_dir,
 	struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, };
 	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
 	struct ocfs2_dir_lookup_result target_insert = { NULL, };
+	bool should_add_orphan = false;
 
 	/* At some point it might be nice to break this function up a
 	 * bit. */
@@ -1134,6 +1233,21 @@ static int ocfs2_rename(struct inode *old_dir,
 			goto bail;
 		}
 		rename_lock = 1;
+
+		/* here we cannot guarantee the inodes haven't just been
+		 * changed, so check if they are nested again */
+		status = ocfs2_check_if_ancestor(osb, new_dir->i_ino,
+				old_inode->i_ino);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		} else if (status == 1) {
+			status = -EPERM;
+			trace_ocfs2_rename_not_permitted(
+					(unsigned long long)old_inode->i_ino,
+					(unsigned long long)new_dir->i_ino);
+			goto bail;
+		}
 	}
 
 	/* if old and new are the same, this'll just do one lock. */
@@ -1304,6 +1418,7 @@ static int ocfs2_rename(struct inode *old_dir,
 				mlog_errno(status);
 				goto bail;
 			}
+			should_add_orphan = true;
 		}
 	} else {
 		BUG_ON(new_dentry->d_parent->d_inode != new_dir);
@@ -1348,17 +1463,6 @@ static int ocfs2_rename(struct inode *old_dir,
 			goto bail;
 		}
 
-		if (S_ISDIR(new_inode->i_mode) ||
-		    (ocfs2_read_links_count(newfe) == 1)) {
-			status = ocfs2_orphan_add(osb, handle, new_inode,
-						  newfe_bh, orphan_name,
-						  &orphan_insert, orphan_dir);
-			if (status < 0) {
-				mlog_errno(status);
-				goto bail;
-			}
-		}
-
 		/* change the dirent to point to the correct inode */
 		status = ocfs2_update_entry(new_dir, handle, &target_lookup_res,
 					    old_inode);
@@ -1373,6 +1477,15 @@ static int ocfs2_rename(struct inode *old_dir,
 		else
 			ocfs2_add_links_count(newfe, -1);
 		ocfs2_journal_dirty(handle, newfe_bh);
+		if (should_add_orphan) {
+			status = ocfs2_orphan_add(osb, handle, new_inode,
+					newfe_bh, orphan_name,
+					&orphan_insert, orphan_dir);
+			if (status < 0) {
+				mlog_errno(status);
+				goto bail;
+			}
+		}
 	} else {
 		/* if the name was not found in new_dir, add it now */
 		status = ocfs2_add_entry(handle, new_dentry, old_inode,
@@ -1642,6 +1755,7 @@ static int ocfs2_symlink(struct inode *dir,
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 	sigset_t oldset;
 	int did_block_signals = 0;
+	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_symlink_begin(dir, dentry, symname,
 				  dentry->d_name.len, dentry->d_name.name);
@@ -1830,6 +1944,8 @@ static int ocfs2_symlink(struct inode *dir,
 		goto bail;
 	}
 
+	dl = dentry->d_fsdata;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
 				 &lookup);
@@ -1864,6 +1980,9 @@ bail:
 	if (xattr_ac)
 		ocfs2_free_alloc_context(xattr_ac);
 	if ((status < 0) && inode) {
+		if (dl)
+			ocfs2_cleanup_add_entry_failure(osb, dentry, inode);
+
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 1b60c62..6cb019b 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2292,6 +2292,8 @@ TRACE_EVENT(ocfs2_rename,
 		  __entry->new_len, __get_str(new_name))
 );
 
+DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_rename_not_permitted);
+
 TRACE_EVENT(ocfs2_rename_target_exists,
 	TP_PROTO(int new_len, const char *new_name),
 	TP_ARGS(new_len, new_name),
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 714e53b..636aab6 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4288,9 +4288,16 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 		goto out;
 	}
 
+	error = ocfs2_rw_lock(inode, 1);
+	if (error) {
+		mlog_errno(error);
+		goto out;
+	}
+
 	error = ocfs2_inode_lock(inode, &old_bh, 1);
 	if (error) {
 		mlog_errno(error);
+		ocfs2_rw_unlock(inode, 1);
 		goto out;
 	}
 
@@ -4302,6 +4309,7 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 	up_write(&OCFS2_I(inode)->ip_xattr_sem);
 
 	ocfs2_inode_unlock(inode, 1);
+	ocfs2_rw_unlock(inode, 1);
 	brelse(old_bh);
 
 	if (error) {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c7a89cea..ddb662b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1925,15 +1925,11 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	ocfs2_shutdown_local_alloc(osb);
 
+	ocfs2_truncate_log_shutdown(osb);
+
 	/* This will disable recovery and flush any recovery work. */
 	ocfs2_recovery_exit(osb);
 
-	/*
-	 * During dismount, when it recovers another node it will call
-	 * ocfs2_recover_orphans and queue delayed work osb_truncate_log_wq.
-	 */
-	ocfs2_truncate_log_shutdown(osb);
-
 	ocfs2_journal_shutdown(osb);
 
 	ocfs2_sync_blockdev(sb);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 9d231e9..bf2d03f 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -184,29 +184,11 @@ static int show_stat(struct seq_file *p, void *v)
 
 static int stat_open(struct inode *inode, struct file *file)
 {
-	size_t size = 1024 + 128 * num_possible_cpus();
-	char *buf;
-	struct seq_file *m;
-	int res;
+	size_t size = 1024 + 128 * num_online_cpus();
 
 	/* minimum size to display an interrupt count : 2 bytes */
 	size += 2 * nr_irqs;
-
-	/* don't ask for more than the kmalloc() max size */
-	if (size > KMALLOC_MAX_SIZE)
-		size = KMALLOC_MAX_SIZE;
-	buf = kmalloc(size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	res = single_open(file, show_stat, NULL);
-	if (!res) {
-		m = file->private_data;
-		m->buf = buf;
-		m->size = ksize(buf);
-	} else
-		kfree(buf);
-	return res;
+	return single_open_size(file, show_stat, NULL, size);
 }
 
 static const struct file_operations proc_stat_operations = {
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 9cd5f63..7f30bdc 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -702,6 +702,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	struct dquot *dquot;
 	unsigned long freed = 0;
 
+	spin_lock(&dq_list_lock);
 	head = free_dquots.prev;
 	while (head != &free_dquots && sc->nr_to_scan) {
 		dquot = list_entry(head, struct dquot, dq_free);
@@ -713,6 +714,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		freed++;
 		head = free_dquots.prev;
 	}
+	spin_unlock(&dq_list_lock);
 	return freed;
 }
 
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 1d641bb..3857b72 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -8,8 +8,10 @@
 #include <linux/fs.h>
 #include <linux/export.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/cred.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -30,6 +32,16 @@ static void seq_set_overflow(struct seq_file *m)
 	m->count = m->size;
 }
 
+static void *seq_buf_alloc(unsigned long size)
+{
+	void *buf;
+
+	buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	if (!buf && size > PAGE_SIZE)
+		buf = vmalloc(size);
+	return buf;
+}
+
 /**
  *	seq_open -	initialize sequential file
  *	@file: file we initialize
@@ -96,7 +108,7 @@ static int traverse(struct seq_file *m, loff_t offset)
 		return 0;
 	}
 	if (!m->buf) {
-		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
 		if (!m->buf)
 			return -ENOMEM;
 	}
@@ -135,9 +147,9 @@ static int traverse(struct seq_file *m, loff_t offset)
 
 Eoverflow:
 	m->op->stop(m, p);
-	kfree(m->buf);
+	kvfree(m->buf);
 	m->count = 0;
-	m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+	m->buf = seq_buf_alloc(m->size <<= 1);
 	return !m->buf ? -ENOMEM : -EAGAIN;
 }
 
@@ -192,7 +204,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 
 	/* grab buffer if we didn't have one */
 	if (!m->buf) {
-		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
 		if (!m->buf)
 			goto Enomem;
 	}
@@ -232,9 +244,9 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 		if (m->count < m->size)
 			goto Fill;
 		m->op->stop(m, p);
-		kfree(m->buf);
+		kvfree(m->buf);
 		m->count = 0;
-		m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size <<= 1);
 		if (!m->buf)
 			goto Enomem;
 		m->version = 0;
@@ -350,7 +362,7 @@ EXPORT_SYMBOL(seq_lseek);
 int seq_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = file->private_data;
-	kfree(m->buf);
+	kvfree(m->buf);
 	kfree(m);
 	return 0;
 }
@@ -605,13 +617,13 @@ EXPORT_SYMBOL(single_open);
 int single_open_size(struct file *file, int (*show)(struct seq_file *, void *),
 		void *data, size_t size)
 {
-	char *buf = kmalloc(size, GFP_KERNEL);
+	char *buf = seq_buf_alloc(size);
 	int ret;
 	if (!buf)
 		return -ENOMEM;
 	ret = single_open(file, show, data);
 	if (ret) {
-		kfree(buf);
+		kvfree(buf);
 		return ret;
 	}
 	((struct seq_file *)file->private_data)->buf = buf;
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 96175df..75c3fe5 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -4298,8 +4298,8 @@ xfs_bmapi_delay(
 }
 
 
-int
-__xfs_bmapi_allocate(
+static int
+xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
 {
 	struct xfs_mount	*mp = bma->ip->i_mount;
@@ -4578,9 +4578,6 @@ xfs_bmapi_write(
 	bma.flist = flist;
 	bma.firstblock = firstblock;
 
-	if (flags & XFS_BMAPI_STACK_SWITCH)
-		bma.stack_switch = 1;
-
 	while (bno < end && n < *nmap) {
 		inhole = eof || bma.got.br_startoff > bno;
 		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 38ba36e..b879ca5 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -77,7 +77,6 @@ typedef	struct xfs_bmap_free
  * from written to unwritten, otherwise convert from unwritten to written.
  */
 #define XFS_BMAPI_CONVERT	0x040
-#define XFS_BMAPI_STACK_SWITCH	0x080
 
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
@@ -86,8 +85,7 @@ typedef	struct xfs_bmap_free
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
 	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
-	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
-	{ XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" }
+	{ XFS_BMAPI_CONVERT,	"CONVERT" }
 
 
 static inline int xfs_bmapi_aflag(int w)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 703b3ec..64731ef 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -249,59 +249,6 @@ xfs_bmap_rtalloc(
 }
 
 /*
- * Stack switching interfaces for allocation
- */
-static void
-xfs_bmapi_allocate_worker(
-	struct work_struct	*work)
-{
-	struct xfs_bmalloca	*args = container_of(work,
-						struct xfs_bmalloca, work);
-	unsigned long		pflags;
-	unsigned long		new_pflags = PF_FSTRANS;
-
-	/*
-	 * we are in a transaction context here, but may also be doing work
-	 * in kswapd context, and hence we may need to inherit that state
-	 * temporarily to ensure that we don't block waiting for memory reclaim
-	 * in any way.
-	 */
-	if (args->kswapd)
-		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
-
-	current_set_flags_nested(&pflags, new_pflags);
-
-	args->result = __xfs_bmapi_allocate(args);
-	complete(args->done);
-
-	current_restore_flags_nested(&pflags, new_pflags);
-}
-
-/*
- * Some allocation requests often come in with little stack to work on. Push
- * them off to a worker thread so there is lots of stack to use. Otherwise just
- * call directly to avoid the context switch overhead here.
- */
-int
-xfs_bmapi_allocate(
-	struct xfs_bmalloca	*args)
-{
-	DECLARE_COMPLETION_ONSTACK(done);
-
-	if (!args->stack_switch)
-		return __xfs_bmapi_allocate(args);
-
-
-	args->done = &done;
-	args->kswapd = current_is_kswapd();
-	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
-	queue_work(xfs_alloc_wq, &args->work);
-	wait_for_completion(&done);
-	destroy_work_on_stack(&args->work);
-	return args->result;
-}
-
-/*
  * Check if the endoff is outside the last extent. If so the caller will grow
  * the allocation to a stripe unit boundary.  All offsets are considered outside
  * the end of file for an empty fork, so 1 is returned in *eof in that case.
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 075f722..2fdb72d 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -55,8 +55,6 @@ struct xfs_bmalloca {
 	bool			userdata;/* set if is user data */
 	bool			aeof;	/* allocated space at eof */
 	bool			conv;	/* overwriting unwritten extents */
-	bool			stack_switch;
-	bool			kswapd;	/* allocation in kswapd context */
 	int			flags;
 	struct completion	*done;
 	struct work_struct	work;
@@ -66,8 +64,6 @@ struct xfs_bmalloca {
 int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
 			int *committed);
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
-int	xfs_bmapi_allocate(struct xfs_bmalloca *args);
-int	__xfs_bmapi_allocate(struct xfs_bmalloca *args);
 int	xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
 		     int whichfork, int *eof);
 int	xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index bf810c6..cf893bc 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -33,6 +33,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_alloc.h"
 
 /*
  * Cursor allocation zone.
@@ -2323,7 +2324,7 @@ error1:
  * record (to be inserted into parent).
  */
 STATIC int					/* error */
-xfs_btree_split(
+__xfs_btree_split(
 	struct xfs_btree_cur	*cur,
 	int			level,
 	union xfs_btree_ptr	*ptrp,
@@ -2503,6 +2504,85 @@ error0:
 	return error;
 }
 
+struct xfs_btree_split_args {
+	struct xfs_btree_cur	*cur;
+	int			level;
+	union xfs_btree_ptr	*ptrp;
+	union xfs_btree_key	*key;
+	struct xfs_btree_cur	**curp;
+	int			*stat;		/* success/failure */
+	int			result;
+	bool			kswapd;	/* allocation in kswapd context */
+	struct completion	*done;
+	struct work_struct	work;
+};
+
+/*
+ * Stack switching interfaces for allocation
+ */
+static void
+xfs_btree_split_worker(
+	struct work_struct	*work)
+{
+	struct xfs_btree_split_args	*args = container_of(work,
+						struct xfs_btree_split_args, work);
+	unsigned long		pflags;
+	unsigned long		new_pflags = PF_FSTRANS;
+
+	/*
+	 * we are in a transaction context here, but may also be doing work
+	 * in kswapd context, and hence we may need to inherit that state
+	 * temporarily to ensure that we don't block waiting for memory reclaim
+	 * in any way.
+	 */
+	if (args->kswapd)
+		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+	current_set_flags_nested(&pflags, new_pflags);
+
+	args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
+					 args->key, args->curp, args->stat);
+	complete(args->done);
+
+	current_restore_flags_nested(&pflags, new_pflags);
+}
+
+/*
+ * BMBT split requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. For the other
+ * btree types, just call directly to avoid the context switch overhead here.
+ */
+STATIC int					/* error */
+xfs_btree_split(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	union xfs_btree_ptr	*ptrp,
+	union xfs_btree_key	*key,
+	struct xfs_btree_cur	**curp,
+	int			*stat)		/* success/failure */
+{
+	struct xfs_btree_split_args	args;
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	if (cur->bc_btnum != XFS_BTNUM_BMAP)
+		return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
+
+	args.cur = cur;
+	args.level = level;
+	args.ptrp = ptrp;
+	args.key = key;
+	args.curp = curp;
+	args.stat = stat;
+	args.done = &done;
+	args.kswapd = current_is_kswapd();
+	INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker);
+	queue_work(xfs_alloc_wq, &args.work);
+	wait_for_completion(&done);
+	destroy_work_on_stack(&args.work);
+	return args.result;
+}
+
+
 /*
  * Copy the old inode root contents into a real block and make the
  * broot point to it.
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 6c5eb4c..6d3ec2b 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -749,8 +749,7 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb,
-						XFS_BMAPI_STACK_SWITCH,
+						count_fsb, 0,
 						&first_block, 1,
 						imap, &nimaps, &free_list);
 			if (error)
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index c3453b1..7703fa6 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -483,10 +483,16 @@ xfs_sb_quota_to_disk(
 	}
 
 	/*
-	 * GQUOTINO and PQUOTINO cannot be used together in versions
-	 * of superblock that do not have pquotino. from->sb_flags
-	 * tells us which quota is active and should be copied to
-	 * disk.
+	 * GQUOTINO and PQUOTINO cannot be used together in versions of
+	 * superblock that do not have pquotino. from->sb_flags tells us which
+	 * quota is active and should be copied to disk. If neither are active,
+	 * make sure we write NULLFSINO to the sb_gquotino field as a quota
+	 * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature
+	 * bit is set.
+	 *
+	 * Note that we don't need to handle the sb_uquotino or sb_pquotino here
+	 * as they do not require any translation. Hence the main sb field loop
+	 * will write them appropriately from the in-core superblock.
 	 */
 	if ((*fields & XFS_SB_GQUOTINO) &&
 				(from->sb_qflags & XFS_GQUOTA_ACCT))
@@ -494,6 +500,17 @@ xfs_sb_quota_to_disk(
 	else if ((*fields & XFS_SB_PQUOTINO) &&
 				(from->sb_qflags & XFS_PQUOTA_ACCT))
 		to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
+	else {
+		/*
+		 * We can't rely on just the fields being logged to tell us
+		 * that it is safe to write NULLFSINO - we should only do that
+		 * if quotas are not actually enabled. Hence only write
+		 * NULLFSINO if both in-core quota inodes are NULL.
+		 */
+		if (from->sb_gquotino == NULLFSINO &&
+		    from->sb_pquotino == NULLFSINO)
+			to->sb_gquotino = cpu_to_be64(NULLFSINO);
+	}
 
 	*fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO);
 }