Merge branch 'for-3.7' of git://git.infradead.org/users/dedekind/l2-mtd

Conflicts:
	drivers/mtd/nand/nand_base.c

144 files changed, 3398 insertions, 1724 deletions

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 392c5dac1981..d934f04e7736 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -184,10 +184,20 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 			v9ses->afid = option;
 			break;
 		case Opt_uname:
-			match_strlcpy(v9ses->uname, &args[0], PATH_MAX);
+			kfree(v9ses->uname);
+			v9ses->uname = match_strdup(&args[0]);
+			if (!v9ses->uname) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
 			break;
 		case Opt_remotename:
-			match_strlcpy(v9ses->aname, &args[0], PATH_MAX);
+			kfree(v9ses->aname);
+			v9ses->aname = match_strdup(&args[0]);
+			if (!v9ses->aname) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
 			break;
 		case Opt_nodevmap:
 			v9ses->nodev = 1;
@@ -287,21 +297,21 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	struct p9_fid *fid;
 	int rc;
 
-	v9ses->uname = __getname();
+	v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL);
 	if (!v9ses->uname)
 		return ERR_PTR(-ENOMEM);
 
-	v9ses->aname = __getname();
+	v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL);
 	if (!v9ses->aname) {
-		__putname(v9ses->uname);
+		kfree(v9ses->uname);
 		return ERR_PTR(-ENOMEM);
 	}
 	init_rwsem(&v9ses->rename_sem);
 
 	rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
 	if (rc) {
-		__putname(v9ses->aname);
-		__putname(v9ses->uname);
+		kfree(v9ses->aname);
+		kfree(v9ses->uname);
 		return ERR_PTR(rc);
 	}
 
@@ -309,8 +319,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	list_add(&v9ses->slist, &v9fs_sessionlist);
 	spin_unlock(&v9fs_sessionlist_lock);
 
-	strcpy(v9ses->uname, V9FS_DEFUSER);
-	strcpy(v9ses->aname, V9FS_DEFANAME);
 	v9ses->uid = ~0;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
@@ -412,8 +420,8 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 		kfree(v9ses->cachetag);
 	}
 #endif
-	__putname(v9ses->uname);
-	__putname(v9ses->aname);
+	kfree(v9ses->uname);
+	kfree(v9ses->aname);
 
 	bdi_destroy(&v9ses->bdi);
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index cbf9dbb1b2a2..890bed538f9b 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -1276,12 +1276,12 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	}
 
 	/* copy extension buffer into buffer */
-	strncpy(buffer, st->extension, buflen);
+	retval = min(strlen(st->extension)+1, (size_t)buflen);
+	memcpy(buffer, st->extension, retval);
 
-	p9_debug(P9_DEBUG_VFS, "%s -> %s (%s)\n",
-		 dentry->d_name.name, st->extension, buffer);
+	p9_debug(P9_DEBUG_VFS, "%s -> %s (%.*s)\n",
+		 dentry->d_name.name, st->extension, buflen, buffer);
 
-	retval = strnlen(buffer, buflen);
 done:
 	p9stat_free(st);
 	kfree(st);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index e7396cfdb109..91b11650722e 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -392,10 +392,12 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 		ino->flags |= AUTOFS_INF_PENDING;
 		spin_unlock(&sbi->fs_lock);
 		status = autofs4_mount_wait(dentry);
-		if (status)
-			return ERR_PTR(status);
 		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_PENDING;
+		if (status) {
+			spin_unlock(&sbi->fs_lock);
+			return ERR_PTR(status);
+		}
 	}
 done:
 	if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index e800dec958c3..fbd9f60bd763 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -36,7 +36,6 @@
 #include <asm/uaccess.h>
 #include <asm/param.h>
 #include <asm/page.h>
-#include <asm/exec.h>
 
 #ifndef user_long_t
 #define user_long_t long
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 262db114ff01..a46049154107 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -39,7 +39,6 @@
 #include <asm/uaccess.h>
 #include <asm/param.h>
 #include <asm/pgalloc.h>
-#include <asm/exec.h>
 
 typedef char *elf_caddr_t;
 
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index e85c04b9f61c..a3f28f331b2b 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -70,23 +70,25 @@ static inline int use_bip_pool(unsigned int idx)
 }
 
 /**
- * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio
+ * bio_integrity_alloc - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
  * @gfp_mask:	Memory allocation mask
  * @nr_vecs:	Number of integrity metadata scatter-gather elements
- * @bs:		bio_set to allocate from
  *
  * Description: This function prepares a bio for attaching integrity
  * metadata.  nr_vecs specifies the maximum number of pages containing
  * integrity metadata that can be attached.
  */
-struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
-							 gfp_t gfp_mask,
-							 unsigned int nr_vecs,
-							 struct bio_set *bs)
+struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
+						  gfp_t gfp_mask,
+						  unsigned int nr_vecs)
 {
 	struct bio_integrity_payload *bip;
 	unsigned int idx = vecs_to_idx(nr_vecs);
+	struct bio_set *bs = bio->bi_pool;
+
+	if (!bs)
+		bs = fs_bio_set;
 
 	BUG_ON(bio == NULL);
 	bip = NULL;
@@ -114,37 +116,22 @@ struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
 
 	return bip;
 }
-EXPORT_SYMBOL(bio_integrity_alloc_bioset);
-
-/**
- * bio_integrity_alloc - Allocate integrity payload and attach it to bio
- * @bio:	bio to attach integrity metadata to
- * @gfp_mask:	Memory allocation mask
- * @nr_vecs:	Number of integrity metadata scatter-gather elements
- *
- * Description: This function prepares a bio for attaching integrity
- * metadata.  nr_vecs specifies the maximum number of pages containing
- * integrity metadata that can be attached.
- */
-struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
-						  gfp_t gfp_mask,
-						  unsigned int nr_vecs)
-{
-	return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set);
-}
 EXPORT_SYMBOL(bio_integrity_alloc);
 
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
- * @bs:		bio_set this bio was allocated from
  *
  * Description: Used to free the integrity portion of a bio. Usually
  * called from bio_free().
  */
-void bio_integrity_free(struct bio *bio, struct bio_set *bs)
+void bio_integrity_free(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio->bi_integrity;
+	struct bio_set *bs = bio->bi_pool;
+
+	if (!bs)
+		bs = fs_bio_set;
 
 	BUG_ON(bip == NULL);
 
@@ -730,19 +717,18 @@ EXPORT_SYMBOL(bio_integrity_split);
  * @bio:	New bio
  * @bio_src:	Original bio
  * @gfp_mask:	Memory allocation mask
- * @bs:		bio_set to allocate bip from
  *
  * Description:	Called to allocate a bip when cloning a bio
  */
 int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
-			gfp_t gfp_mask, struct bio_set *bs)
+			gfp_t gfp_mask)
 {
 	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
+	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
 
 	if (bip == NULL)
 		return -EIO;
diff --git a/fs/bio.c b/fs/bio.c
index 71072ab99128..b96fc6ce4855 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -55,6 +55,7 @@ static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
  * IO code that does not need private memory pools.
  */
 struct bio_set *fs_bio_set;
+EXPORT_SYMBOL(fs_bio_set);
 
 /*
  * Our slab pool management
@@ -74,6 +75,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
 	unsigned int sz = sizeof(struct bio) + extra_size;
 	struct kmem_cache *slab = NULL;
 	struct bio_slab *bslab, *new_bio_slabs;
+	unsigned int new_bio_slab_max;
 	unsigned int i, entry = -1;
 
 	mutex_lock(&bio_slab_lock);
@@ -96,12 +98,13 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
 		goto out_unlock;
 
 	if (bio_slab_nr == bio_slab_max && entry == -1) {
-		bio_slab_max <<= 1;
+		new_bio_slab_max = bio_slab_max << 1;
 		new_bio_slabs = krealloc(bio_slabs,
-					 bio_slab_max * sizeof(struct bio_slab),
+					 new_bio_slab_max * sizeof(struct bio_slab),
 					 GFP_KERNEL);
 		if (!new_bio_slabs)
 			goto out_unlock;
+		bio_slab_max = new_bio_slab_max;
 		bio_slabs = new_bio_slabs;
 	}
 	if (entry == -1)
@@ -233,26 +236,37 @@ fallback:
 	return bvl;
 }
 
-void bio_free(struct bio *bio, struct bio_set *bs)
+static void __bio_free(struct bio *bio)
 {
+	bio_disassociate_task(bio);
+
+	if (bio_integrity(bio))
+		bio_integrity_free(bio);
+}
+
+static void bio_free(struct bio *bio)
+{
+	struct bio_set *bs = bio->bi_pool;
 	void *p;
 
-	if (bio_has_allocated_vec(bio))
-		bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
+	__bio_free(bio);
 
-	if (bio_integrity(bio))
-		bio_integrity_free(bio, bs);
+	if (bs) {
+		if (bio_has_allocated_vec(bio))
+			bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
 
-	/*
-	 * If we have front padding, adjust the bio pointer before freeing
-	 */
-	p = bio;
-	if (bs->front_pad)
+		/*
+		 * If we have front padding, adjust the bio pointer before freeing
+		 */
+		p = bio;
 		p -= bs->front_pad;
 
-	mempool_free(p, bs->bio_pool);
+		mempool_free(p, bs->bio_pool);
+	} else {
+		/* Bio was allocated by bio_kmalloc() */
+		kfree(bio);
+	}
 }
-EXPORT_SYMBOL(bio_free);
 
 void bio_init(struct bio *bio)
 {
@@ -263,48 +277,85 @@ void bio_init(struct bio *bio)
 EXPORT_SYMBOL(bio_init);
 
 /**
+ * bio_reset - reinitialize a bio
+ * @bio:	bio to reset
+ *
+ * Description:
+ *   After calling bio_reset(), @bio will be in the same state as a freshly
+ *   allocated bio returned bio bio_alloc_bioset() - the only fields that are
+ *   preserved are the ones that are initialized by bio_alloc_bioset(). See
+ *   comment in struct bio.
+ */
+void bio_reset(struct bio *bio)
+{
+	unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);
+
+	__bio_free(bio);
+
+	memset(bio, 0, BIO_RESET_BYTES);
+	bio->bi_flags = flags|(1 << BIO_UPTODATE);
+}
+EXPORT_SYMBOL(bio_reset);
+
+/**
  * bio_alloc_bioset - allocate a bio for I/O
  * @gfp_mask:   the GFP_ mask given to the slab allocator
  * @nr_iovecs:	number of iovecs to pre-allocate
  * @bs:		the bio_set to allocate from.
  *
  * Description:
- *   bio_alloc_bioset will try its own mempool to satisfy the allocation.
- *   If %__GFP_WAIT is set then we will block on the internal pool waiting
- *   for a &struct bio to become free.
+ *   If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
+ *   backed by the @bs's mempool.
  *
- *   Note that the caller must set ->bi_destructor on successful return
- *   of a bio, to do the appropriate freeing of the bio once the reference
- *   count drops to zero.
- **/
+ *   When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
+ *   able to allocate a bio. This is due to the mempool guarantees. To make this
+ *   work, callers must never allocate more than 1 bio at a time from this pool.
+ *   Callers that need to allocate more than 1 bio must always submit the
+ *   previously allocated bio for IO before attempting to allocate a new one.
+ *   Failure to do so can cause deadlocks under memory pressure.
+ *
+ *   RETURNS:
+ *   Pointer to new bio on success, NULL on failure.
+ */
 struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 {
+	unsigned front_pad;
+	unsigned inline_vecs;
 	unsigned long idx = BIO_POOL_NONE;
 	struct bio_vec *bvl = NULL;
 	struct bio *bio;
 	void *p;
 
-	p = mempool_alloc(bs->bio_pool, gfp_mask);
+	if (!bs) {
+		if (nr_iovecs > UIO_MAXIOV)
+			return NULL;
+
+		p = kmalloc(sizeof(struct bio) +
+			    nr_iovecs * sizeof(struct bio_vec),
+			    gfp_mask);
+		front_pad = 0;
+		inline_vecs = nr_iovecs;
+	} else {
+		p = mempool_alloc(bs->bio_pool, gfp_mask);
+		front_pad = bs->front_pad;
+		inline_vecs = BIO_INLINE_VECS;
+	}
+
 	if (unlikely(!p))
 		return NULL;
-	bio = p + bs->front_pad;
 
+	bio = p + front_pad;
 	bio_init(bio);
 
-	if (unlikely(!nr_iovecs))
-		goto out_set;
-
-	if (nr_iovecs <= BIO_INLINE_VECS) {
-		bvl = bio->bi_inline_vecs;
-		nr_iovecs = BIO_INLINE_VECS;
-	} else {
+	if (nr_iovecs > inline_vecs) {
 		bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
 		if (unlikely(!bvl))
 			goto err_free;
-
-		nr_iovecs = bvec_nr_vecs(idx);
+	} else if (nr_iovecs) {
+		bvl = bio->bi_inline_vecs;
 	}
-out_set:
+
+	bio->bi_pool = bs;
 	bio->bi_flags |= idx << BIO_POOL_OFFSET;
 	bio->bi_max_vecs = nr_iovecs;
 	bio->bi_io_vec = bvl;
@@ -316,80 +367,6 @@ err_free:
 }
 EXPORT_SYMBOL(bio_alloc_bioset);
 
-static void bio_fs_destructor(struct bio *bio)
-{
-	bio_free(bio, fs_bio_set);
-}
-
-/**
- *	bio_alloc - allocate a new bio, memory pool backed
- *	@gfp_mask: allocation mask to use
- *	@nr_iovecs: number of iovecs
- *
- *	bio_alloc will allocate a bio and associated bio_vec array that can hold
- *	at least @nr_iovecs entries. Allocations will be done from the
- *	fs_bio_set. Also see @bio_alloc_bioset and @bio_kmalloc.
- *
- *	If %__GFP_WAIT is set, then bio_alloc will always be able to allocate
- *	a bio. This is due to the mempool guarantees. To make this work, callers
- *	must never allocate more than 1 bio at a time from this pool. Callers
- *	that need to allocate more than 1 bio must always submit the previously
- *	allocated bio for IO before attempting to allocate a new one. Failure to
- *	do so can cause livelocks under memory pressure.
- *
- *	RETURNS:
- *	Pointer to new bio on success, NULL on failure.
- */
-struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
-	struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
-
-	if (bio)
-		bio->bi_destructor = bio_fs_destructor;
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_alloc);
-
-static void bio_kmalloc_destructor(struct bio *bio)
-{
-	if (bio_integrity(bio))
-		bio_integrity_free(bio, fs_bio_set);
-	kfree(bio);
-}
-
-/**
- * bio_kmalloc - allocate a bio for I/O using kmalloc()
- * @gfp_mask:   the GFP_ mask given to the slab allocator
- * @nr_iovecs:	number of iovecs to pre-allocate
- *
- * Description:
- *   Allocate a new bio with @nr_iovecs bvecs.  If @gfp_mask contains
- *   %__GFP_WAIT, the allocation is guaranteed to succeed.
- *
- **/
-struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
-{
-	struct bio *bio;
-
-	if (nr_iovecs > UIO_MAXIOV)
-		return NULL;
-
-	bio = kmalloc(sizeof(struct bio) + nr_iovecs * sizeof(struct bio_vec),
-		      gfp_mask);
-	if (unlikely(!bio))
-		return NULL;
-
-	bio_init(bio);
-	bio->bi_flags |= BIO_POOL_NONE << BIO_POOL_OFFSET;
-	bio->bi_max_vecs = nr_iovecs;
-	bio->bi_io_vec = bio->bi_inline_vecs;
-	bio->bi_destructor = bio_kmalloc_destructor;
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_kmalloc);
-
 void zero_fill_bio(struct bio *bio)
 {
 	unsigned long flags;
@@ -420,11 +397,8 @@ void bio_put(struct bio *bio)
 	/*
 	 * last put frees it
 	 */
-	if (atomic_dec_and_test(&bio->bi_cnt)) {
-		bio_disassociate_task(bio);
-		bio->bi_next = NULL;
-		bio->bi_destructor(bio);
-	}
+	if (atomic_dec_and_test(&bio->bi_cnt))
+		bio_free(bio);
 }
 EXPORT_SYMBOL(bio_put);
 
@@ -466,26 +440,28 @@ void __bio_clone(struct bio *bio, struct bio *bio_src)
 EXPORT_SYMBOL(__bio_clone);
 
 /**
- *	bio_clone	-	clone a bio
+ *	bio_clone_bioset -	clone a bio
  *	@bio: bio to clone
  *	@gfp_mask: allocation priority
+ *	@bs: bio_set to allocate from
  *
  * 	Like __bio_clone, only also allocates the returned bio
  */
-struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
+struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
+			     struct bio_set *bs)
 {
-	struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
+	struct bio *b;
 
+	b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, bs);
 	if (!b)
 		return NULL;
 
-	b->bi_destructor = bio_fs_destructor;
 	__bio_clone(b, bio);
 
 	if (bio_integrity(bio)) {
 		int ret;
 
-		ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
+		ret = bio_integrity_clone(b, bio, gfp_mask);
 
 		if (ret < 0) {
 			bio_put(b);
@@ -495,7 +471,7 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
 
 	return b;
 }
-EXPORT_SYMBOL(bio_clone);
+EXPORT_SYMBOL(bio_clone_bioset);
 
 /**
  *	bio_get_nr_vecs		- return approx number of vecs
@@ -1501,7 +1477,7 @@ struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 	trace_block_split(bdev_get_queue(bi->bi_bdev), bi,
 				bi->bi_sector + first_sectors);
 
-	BUG_ON(bi->bi_vcnt != 1);
+	BUG_ON(bi->bi_vcnt != 1 && bi->bi_vcnt != 0);
 	BUG_ON(bi->bi_idx != 0);
 	atomic_set(&bp->cnt, 3);
 	bp->error = 0;
@@ -1511,17 +1487,22 @@ struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 	bp->bio2.bi_size -= first_sectors << 9;
 	bp->bio1.bi_size = first_sectors << 9;
 
-	bp->bv1 = bi->bi_io_vec[0];
-	bp->bv2 = bi->bi_io_vec[0];
-	bp->bv2.bv_offset += first_sectors << 9;
-	bp->bv2.bv_len -= first_sectors << 9;
-	bp->bv1.bv_len = first_sectors << 9;
+	if (bi->bi_vcnt != 0) {
+		bp->bv1 = bi->bi_io_vec[0];
+		bp->bv2 = bi->bi_io_vec[0];
+
+		if (bio_is_rw(bi)) {
+			bp->bv2.bv_offset += first_sectors << 9;
+			bp->bv2.bv_len -= first_sectors << 9;
+			bp->bv1.bv_len = first_sectors << 9;
+		}
 
-	bp->bio1.bi_io_vec = &bp->bv1;
-	bp->bio2.bi_io_vec = &bp->bv2;
+		bp->bio1.bi_io_vec = &bp->bv1;
+		bp->bio2.bi_io_vec = &bp->bv2;
 
-	bp->bio1.bi_max_vecs = 1;
-	bp->bio2.bi_max_vecs = 1;
+		bp->bio1.bi_max_vecs = 1;
+		bp->bio2.bi_max_vecs = 1;
+	}
 
 	bp->bio1.bi_end_io = bio_pair_end_1;
 	bp->bio2.bi_end_io = bio_pair_end_2;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 38e721b35d45..1a1e5e3b1eaf 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -116,6 +116,8 @@ EXPORT_SYMBOL(invalidate_bdev);
 
 int set_blocksize(struct block_device *bdev, int size)
 {
+	struct address_space *mapping;
+
 	/* Size must be a power of two, and between 512 and PAGE_SIZE */
 	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
 		return -EINVAL;
@@ -124,6 +126,19 @@ int set_blocksize(struct block_device *bdev, int size)
 	if (size < bdev_logical_block_size(bdev))
 		return -EINVAL;
 
+	/* Prevent starting I/O or mapping the device */
+	percpu_down_write(&bdev->bd_block_size_semaphore);
+
+	/* Check that the block device is not memory mapped */
+	mapping = bdev->bd_inode->i_mapping;
+	mutex_lock(&mapping->i_mmap_mutex);
+	if (mapping_mapped(mapping)) {
+		mutex_unlock(&mapping->i_mmap_mutex);
+		percpu_up_write(&bdev->bd_block_size_semaphore);
+		return -EBUSY;
+	}
+	mutex_unlock(&mapping->i_mmap_mutex);
+
 	/* Don't change the size if it is same as current */
 	if (bdev->bd_block_size != size) {
 		sync_blockdev(bdev);
@@ -131,6 +146,9 @@ int set_blocksize(struct block_device *bdev, int size)
 		bdev->bd_inode->i_blkbits = blksize_bits(size);
 		kill_bdev(bdev);
 	}
+
+	percpu_up_write(&bdev->bd_block_size_semaphore);
+
 	return 0;
 }
 
@@ -441,6 +459,12 @@ static struct inode *bdev_alloc_inode(struct super_block *sb)
 	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
+
+	if (unlikely(percpu_init_rwsem(&ei->bdev.bd_block_size_semaphore))) {
+		kmem_cache_free(bdev_cachep, ei);
+		return NULL;
+	}
+
 	return &ei->vfs_inode;
 }
 
@@ -449,6 +473,8 @@ static void bdev_i_callback(struct rcu_head *head)
 	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct bdev_inode *bdi = BDEV_I(inode);
 
+	percpu_free_rwsem(&bdi->bdev.bd_block_size_semaphore);
+
 	kmem_cache_free(bdev_cachep, bdi);
 }
 
@@ -1567,6 +1593,22 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
+ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
+			unsigned long nr_segs, loff_t pos)
+{
+	ssize_t ret;
+	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+
+	percpu_down_read(&bdev->bd_block_size_semaphore);
+
+	ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+	percpu_up_read(&bdev->bd_block_size_semaphore);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_aio_read);
+
 /*
  * Write data to the block device.  Only intended for the block device itself
  * and the raw driver which basically is a fake block device.
@@ -1578,12 +1620,16 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 unsigned long nr_segs, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	struct blk_plug plug;
 	ssize_t ret;
 
 	BUG_ON(iocb->ki_pos != pos);
 
 	blk_start_plug(&plug);
+
+	percpu_down_read(&bdev->bd_block_size_semaphore);
+
 	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
 	if (ret > 0 || ret == -EIOCBQUEUED) {
 		ssize_t err;
@@ -1592,11 +1638,62 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err < 0 && ret > 0)
 			ret = err;
 	}
+
+	percpu_up_read(&bdev->bd_block_size_semaphore);
+
 	blk_finish_plug(&plug);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkdev_aio_write);
 
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int ret;
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+
+	percpu_down_read(&bdev->bd_block_size_semaphore);
+
+	ret = generic_file_mmap(file, vma);
+
+	percpu_up_read(&bdev->bd_block_size_semaphore);
+
+	return ret;
+}
+
+static ssize_t blkdev_splice_read(struct file *file, loff_t *ppos,
+				  struct pipe_inode_info *pipe, size_t len,
+				  unsigned int flags)
+{
+	ssize_t ret;
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+
+	percpu_down_read(&bdev->bd_block_size_semaphore);
+
+	ret = generic_file_splice_read(file, ppos, pipe, len, flags);
+
+	percpu_up_read(&bdev->bd_block_size_semaphore);
+
+	return ret;
+}
+
+static ssize_t blkdev_splice_write(struct pipe_inode_info *pipe,
+				   struct file *file, loff_t *ppos, size_t len,
+				   unsigned int flags)
+{
+	ssize_t ret;
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+
+	percpu_down_read(&bdev->bd_block_size_semaphore);
+
+	ret = generic_file_splice_write(pipe, file, ppos, len, flags);
+
+	percpu_up_read(&bdev->bd_block_size_semaphore);
+
+	return ret;
+}
+
+
 /*
  * Try to release a page associated with block device when the system
  * is under memory pressure.
@@ -1627,16 +1724,16 @@ const struct file_operations def_blk_fops = {
 	.llseek		= block_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
-  	.aio_read	= generic_file_aio_read,
+  	.aio_read	= blkdev_aio_read,
 	.aio_write	= blkdev_aio_write,
-	.mmap		= generic_file_mmap,
+	.mmap		= blkdev_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= compat_blkdev_ioctl,
 #endif
-	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_read	= blkdev_splice_read,
+	.splice_write	= blkdev_splice_write,
 };
 
 int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index f3187938e081..208d8aa5b07e 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -283,9 +283,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 		goto out;
 	}
 
-	rcu_read_lock();
-	root_level = btrfs_header_level(root->node);
-	rcu_read_unlock();
+	root_level = btrfs_old_root_level(root, time_seq);
 
 	if (root_level + 1 == level)
 		goto out;
@@ -1177,16 +1175,15 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
 	return ret;
 }
 
-static char *ref_to_path(struct btrfs_root *fs_root,
-			 struct btrfs_path *path,
-			 u32 name_len, unsigned long name_off,
-			 struct extent_buffer *eb_in, u64 parent,
-			 char *dest, u32 size)
+char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
+			u32 name_len, unsigned long name_off,
+			struct extent_buffer *eb_in, u64 parent,
+			char *dest, u32 size)
 {
 	int slot;
 	u64 next_inum;
 	int ret;
-	s64 bytes_left = size - 1;
+	s64 bytes_left = ((s64)size) - 1;
 	struct extent_buffer *eb = eb_in;
 	struct btrfs_key found_key;
 	int leave_spinning = path->leave_spinning;
@@ -1266,10 +1263,10 @@ char *btrfs_iref_to_path(struct btrfs_root *fs_root,
 			 struct extent_buffer *eb_in, u64 parent,
 			 char *dest, u32 size)
 {
-	return ref_to_path(fs_root, path,
-			   btrfs_inode_ref_name_len(eb_in, iref),
-			   (unsigned long)(iref + 1),
-			   eb_in, parent, dest, size);
+	return btrfs_ref_to_path(fs_root, path,
+				 btrfs_inode_ref_name_len(eb_in, iref),
+				 (unsigned long)(iref + 1),
+				 eb_in, parent, dest, size);
 }
 
 /*
@@ -1715,9 +1712,8 @@ static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off,
 					ipath->fspath->bytes_left - s_ptr : 0;
 
 	fspath_min = (char *)ipath->fspath->val + (i + 1) * s_ptr;
-	fspath = ref_to_path(ipath->fs_root, ipath->btrfs_path, name_len,
-			     name_off, eb, inum, fspath_min,
-			     bytes_left);
+	fspath = btrfs_ref_to_path(ipath->fs_root, ipath->btrfs_path, name_len,
+				   name_off, eb, inum, fspath_min, bytes_left);
 	if (IS_ERR(fspath))
 		return PTR_ERR(fspath);
 
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index e75533043a5f..d61feca79455 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -62,6 +62,10 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 char *btrfs_iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			 struct btrfs_inode_ref *iref, struct extent_buffer *eb,
 			 u64 parent, char *dest, u32 size);
+char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
+			u32 name_len, unsigned long name_off,
+			struct extent_buffer *eb_in, u64 parent,
+			char *dest, u32 size);
 
 struct btrfs_data_container *init_data_container(u32 total_bytes);
 struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index b33436211000..cdfb4c49a806 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -596,6 +596,11 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 	if (tree_mod_dont_log(fs_info, eb))
 		return 0;
 
+	/*
+	 * When we override something during the move, we log these removals.
+	 * This can only happen when we move towards the beginning of the
+	 * buffer, i.e. dst_slot < src_slot.
+	 */
 	for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
 		ret = tree_mod_log_insert_key_locked(fs_info, eb, i + dst_slot,
 					      MOD_LOG_KEY_REMOVE_WHILE_MOVING);
@@ -647,8 +652,6 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 	if (tree_mod_dont_log(fs_info, NULL))
 		return 0;
 
-	__tree_mod_log_free_eb(fs_info, old_root);
-
 	ret = tree_mod_alloc(fs_info, flags, &tm);
 	if (ret < 0)
 		goto out;
@@ -926,12 +929,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			ret = btrfs_dec_ref(trans, root, buf, 1, 1);
 			BUG_ON(ret); /* -ENOMEM */
 		}
-		/*
-		 * don't log freeing in case we're freeing the root node, this
-		 * is done by tree_mod_log_set_root_pointer later
-		 */
-		if (buf != root->node && btrfs_header_level(buf) != 0)
-			tree_mod_log_free_eb(root->fs_info, buf);
+		tree_mod_log_free_eb(root->fs_info, buf);
 		clean_tree_block(trans, root, buf);
 		*last_ref = 1;
 	}
@@ -1225,6 +1223,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 	free_extent_buffer(eb);
 
 	__tree_mod_log_rewind(eb_rewin, time_seq, tm);
+	WARN_ON(btrfs_header_nritems(eb_rewin) >
+		BTRFS_NODEPTRS_PER_BLOCK(fs_info->fs_root));
 
 	return eb_rewin;
 }
@@ -1241,9 +1241,11 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 {
 	struct tree_mod_elem *tm;
 	struct extent_buffer *eb;
+	struct extent_buffer *old;
 	struct tree_mod_root *old_root = NULL;
 	u64 old_generation = 0;
 	u64 logical;
+	u32 blocksize;
 
 	eb = btrfs_read_lock_root_node(root);
 	tm = __tree_mod_log_oldest_root(root->fs_info, root, time_seq);
@@ -1259,14 +1261,32 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	}
 
 	tm = tree_mod_log_search(root->fs_info, logical, time_seq);
-	if (old_root)
+	if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
+		btrfs_tree_read_unlock(root->node);
+		free_extent_buffer(root->node);
+		blocksize = btrfs_level_size(root, old_root->level);
+		old = read_tree_block(root, logical, blocksize, 0);
+		if (!old) {
+			pr_warn("btrfs: failed to read tree block %llu from get_old_root\n",
+				logical);
+			WARN_ON(1);
+		} else {
+			eb = btrfs_clone_extent_buffer(old);
+			free_extent_buffer(old);
+		}
+	} else if (old_root) {
+		btrfs_tree_read_unlock(root->node);
+		free_extent_buffer(root->node);
 		eb = alloc_dummy_extent_buffer(logical, root->nodesize);
-	else
+	} else {
 		eb = btrfs_clone_extent_buffer(root->node);
-	btrfs_tree_read_unlock(root->node);
-	free_extent_buffer(root->node);
+		btrfs_tree_read_unlock(root->node);
+		free_extent_buffer(root->node);
+	}
+
 	if (!eb)
 		return NULL;
+	extent_buffer_get(eb);
 	btrfs_tree_read_lock(eb);
 	if (old_root) {
 		btrfs_set_header_bytenr(eb, eb->start);
@@ -1279,11 +1299,28 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 		__tree_mod_log_rewind(eb, time_seq, tm);
 	else
 		WARN_ON(btrfs_header_level(eb) != 0);
-	extent_buffer_get(eb);
+	WARN_ON(btrfs_header_nritems(eb) > BTRFS_NODEPTRS_PER_BLOCK(root));
 
 	return eb;
 }
 
+int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq)
+{
+	struct tree_mod_elem *tm;
+	int level;
+
+	tm = __tree_mod_log_oldest_root(root->fs_info, root, time_seq);
+	if (tm && tm->op == MOD_LOG_ROOT_REPLACE) {
+		level = tm->old_root.level;
+	} else {
+		rcu_read_lock();
+		level = btrfs_header_level(root->node);
+		rcu_read_unlock();
+	}
+
+	return level;
+}
+
 static inline int should_cow_block(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct extent_buffer *buf)
@@ -1725,6 +1762,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			goto enospc;
 		}
 
+		tree_mod_log_free_eb(root->fs_info, root->node);
 		tree_mod_log_set_root_pointer(root, child);
 		rcu_assign_pointer(root->node, child);
 
@@ -2970,8 +3008,10 @@ static int push_node_left(struct btrfs_trans_handle *trans,
 			   push_items * sizeof(struct btrfs_key_ptr));
 
 	if (push_items < src_nritems) {
-		tree_mod_log_eb_move(root->fs_info, src, 0, push_items,
-				     src_nritems - push_items);
+		/*
+		 * don't call tree_mod_log_eb_move here, key removal was already
+		 * fully logged by tree_mod_log_eb_copy above.
+		 */
 		memmove_extent_buffer(src, btrfs_node_key_ptr_offset(0),
 				      btrfs_node_key_ptr_offset(push_items),
 				      (src_nritems - push_items) *
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 926c9ffc66d9..c72ead869507 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3120,6 +3120,7 @@ static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
 {
 	return atomic_inc_return(&fs_info->tree_mod_seq);
 }
+int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
 
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
@@ -3338,6 +3339,8 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct inode *inode);
+int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root, struct inode *inode);
 int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);
 int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 8036d3a84853..472873a94d96 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4110,8 +4110,8 @@ struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len)
 
 	return eb;
 err:
-	for (i--; i >= 0; i--)
-		__free_page(eb->pages[i]);
+	for (; i > 0; i--)
+		__free_page(eb->pages[i - 1]);
 	__free_extent_buffer(eb);
 	return NULL;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 85a1e5053fe6..95542a1b3dfc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -94,8 +94,6 @@ static noinline int cow_file_range(struct inode *inode,
 				   struct page *locked_page,
 				   u64 start, u64 end, int *page_started,
 				   unsigned long *nr_written, int unlock);
-static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, struct inode *inode);
 
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 				     struct inode *inode,  struct inode *dir,
@@ -2746,8 +2744,9 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	return btrfs_update_inode_item(trans, root, inode);
 }
 
-static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, struct inode *inode)
+noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
+					 struct btrfs_root *root,
+					 struct inode *inode)
 {
 	int ret;
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e568c472f807..8fcf9a59c28d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -343,7 +343,8 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 		return -EOPNOTSUPP;
 	if (copy_from_user(&range, arg, sizeof(range)))
 		return -EFAULT;
-	if (range.start > total_bytes)
+	if (range.start > total_bytes ||
+	    range.len < fs_info->sb->s_blocksize)
 		return -EINVAL;
 
 	range.len = min(range.len, total_bytes - range.start);
@@ -570,7 +571,8 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
 		ret = btrfs_commit_transaction(trans,
 					       root->fs_info->extent_root);
 	}
-	BUG_ON(ret);
+	if (ret)
+		goto fail;
 
 	ret = pending_snapshot->error;
 	if (ret)
@@ -638,7 +640,7 @@ static int btrfs_may_delete(struct inode *dir,struct dentry *victim,int isdir)
 		return -ENOENT;
 
 	BUG_ON(victim->d_parent->d_inode != dir);
-	audit_inode_child(victim, dir);
+	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
 	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
 	if (error)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5039686df6ae..fe9d02c45f8e 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -790,8 +790,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	}
 
 	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		ret = -ENOMEM;
+		goto out_free_root;
+	}
 
 	key.objectid = 0;
 	key.type = BTRFS_QGROUP_STATUS_KEY;
@@ -800,7 +802,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	ret = btrfs_insert_empty_item(trans, quota_root, path, &key,
 				      sizeof(*ptr));
 	if (ret)
-		goto out;
+		goto out_free_path;
 
 	leaf = path->nodes[0];
 	ptr = btrfs_item_ptr(leaf, path->slots[0],
@@ -818,8 +820,15 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	fs_info->quota_root = quota_root;
 	fs_info->pending_quota_state = 1;
 	spin_unlock(&fs_info->qgroup_lock);
-out:
+out_free_path:
 	btrfs_free_path(path);
+out_free_root:
+	if (ret) {
+		free_extent_buffer(quota_root->node);
+		free_extent_buffer(quota_root->commit_root);
+		kfree(quota_root);
+	}
+out:
 	return ret;
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index c7beb543a4a8..e78b297b0b00 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -745,31 +745,36 @@ typedef int (*iterate_inode_ref_t)(int num, u64 dir, int index,
 				   void *ctx);
 
 /*
- * Helper function to iterate the entries in ONE btrfs_inode_ref.
+ * Helper function to iterate the entries in ONE btrfs_inode_ref or
+ * btrfs_inode_extref.
  * The iterate callback may return a non zero value to stop iteration. This can
  * be a negative value for error codes or 1 to simply stop it.
  *
- * path must point to the INODE_REF when called.
+ * path must point to the INODE_REF or INODE_EXTREF when called.
  */
 static int iterate_inode_ref(struct send_ctx *sctx,
 			     struct btrfs_root *root, struct btrfs_path *path,
 			     struct btrfs_key *found_key, int resolve,
 			     iterate_inode_ref_t iterate, void *ctx)
 {
-	struct extent_buffer *eb;
+	struct extent_buffer *eb = path->nodes[0];
 	struct btrfs_item *item;
 	struct btrfs_inode_ref *iref;
+	struct btrfs_inode_extref *extref;
 	struct btrfs_path *tmp_path;
 	struct fs_path *p;
-	u32 cur;
-	u32 len;
+	u32 cur = 0;
 	u32 total;
-	int slot;
+	int slot = path->slots[0];
 	u32 name_len;
 	char *start;
 	int ret = 0;
-	int num;
+	int num = 0;
 	int index;
+	u64 dir;
+	unsigned long name_off;
+	unsigned long elem_size;
+	unsigned long ptr;
 
 	p = fs_path_alloc_reversed(sctx);
 	if (!p)
@@ -781,24 +786,40 @@ static int iterate_inode_ref(struct send_ctx *sctx,
 		return -ENOMEM;
 	}
 
-	eb = path->nodes[0];
-	slot = path->slots[0];
-	item = btrfs_item_nr(eb, slot);
-	iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
-	cur = 0;
-	len = 0;
-	total = btrfs_item_size(eb, item);
 
-	num = 0;
+	if (found_key->type == BTRFS_INODE_REF_KEY) {
+		ptr = (unsigned long)btrfs_item_ptr(eb, slot,
+						    struct btrfs_inode_ref);
+		item = btrfs_item_nr(eb, slot);
+		total = btrfs_item_size(eb, item);
+		elem_size = sizeof(*iref);
+	} else {
+		ptr = btrfs_item_ptr_offset(eb, slot);
+		total = btrfs_item_size_nr(eb, slot);
+		elem_size = sizeof(*extref);
+	}
+
 	while (cur < total) {
 		fs_path_reset(p);
 
-		name_len = btrfs_inode_ref_name_len(eb, iref);
-		index = btrfs_inode_ref_index(eb, iref);
+		if (found_key->type == BTRFS_INODE_REF_KEY) {
+			iref = (struct btrfs_inode_ref *)(ptr + cur);
+			name_len = btrfs_inode_ref_name_len(eb, iref);
+			name_off = (unsigned long)(iref + 1);
+			index = btrfs_inode_ref_index(eb, iref);
+			dir = found_key->offset;
+		} else {
+			extref = (struct btrfs_inode_extref *)(ptr + cur);
+			name_len = btrfs_inode_extref_name_len(eb, extref);
+			name_off = (unsigned long)&extref->name;
+			index = btrfs_inode_extref_index(eb, extref);
+			dir = btrfs_inode_extref_parent(eb, extref);
+		}
+
 		if (resolve) {
-			start = btrfs_iref_to_path(root, tmp_path, iref, eb,
-						found_key->offset, p->buf,
-						p->buf_len);
+			start = btrfs_ref_to_path(root, tmp_path, name_len,
+						  name_off, eb, dir,
+						  p->buf, p->buf_len);
 			if (IS_ERR(start)) {
 				ret = PTR_ERR(start);
 				goto out;
@@ -809,9 +830,10 @@ static int iterate_inode_ref(struct send_ctx *sctx,
 						p->buf_len + p->buf - start);
 				if (ret < 0)
 					goto out;
-				start = btrfs_iref_to_path(root, tmp_path, iref,
-						eb, found_key->offset, p->buf,
-						p->buf_len);
+				start = btrfs_ref_to_path(root, tmp_path,
+							  name_len, name_off,
+							  eb, dir,
+							  p->buf, p->buf_len);
 				if (IS_ERR(start)) {
 					ret = PTR_ERR(start);
 					goto out;
@@ -820,21 +842,16 @@ static int iterate_inode_ref(struct send_ctx *sctx,
 			}
 			p->start = start;
 		} else {
-			ret = fs_path_add_from_extent_buffer(p, eb,
-					(unsigned long)(iref + 1), name_len);
+			ret = fs_path_add_from_extent_buffer(p, eb, name_off,
+							     name_len);
 			if (ret < 0)
 				goto out;
 		}
 
-
-		len = sizeof(*iref) + name_len;
-		iref = (struct btrfs_inode_ref *)((char *)iref + len);
-		cur += len;
-
-		ret = iterate(num, found_key->offset, index, p, ctx);
+		cur += elem_size + name_len;
+		ret = iterate(num, dir, index, p, ctx);
 		if (ret)
 			goto out;
-
 		num++;
 	}
 
@@ -998,7 +1015,8 @@ static int get_inode_path(struct send_ctx *sctx, struct btrfs_root *root,
 	}
 	btrfs_item_key_to_cpu(p->nodes[0], &found_key, p->slots[0]);
 	if (found_key.objectid != ino ||
-		found_key.type != BTRFS_INODE_REF_KEY) {
+	    (found_key.type != BTRFS_INODE_REF_KEY &&
+	     found_key.type != BTRFS_INODE_EXTREF_KEY)) {
 		ret = -ENOENT;
 		goto out;
 	}
@@ -1551,8 +1569,8 @@ static int get_first_ref(struct send_ctx *sctx,
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 	struct btrfs_path *path;
-	struct btrfs_inode_ref *iref;
 	int len;
+	u64 parent_dir;
 
 	path = alloc_path_for_send();
 	if (!path)
@@ -1568,27 +1586,41 @@ static int get_first_ref(struct send_ctx *sctx,
 	if (!ret)
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key,
 				path->slots[0]);
-	if (ret || found_key.objectid != key.objectid ||
-	    found_key.type != key.type) {
+	if (ret || found_key.objectid != ino ||
+	    (found_key.type != BTRFS_INODE_REF_KEY &&
+	     found_key.type != BTRFS_INODE_EXTREF_KEY)) {
 		ret = -ENOENT;
 		goto out;
 	}
 
-	iref = btrfs_item_ptr(path->nodes[0], path->slots[0],
-			struct btrfs_inode_ref);
-	len = btrfs_inode_ref_name_len(path->nodes[0], iref);
-	ret = fs_path_add_from_extent_buffer(name, path->nodes[0],
-			(unsigned long)(iref + 1), len);
+	if (key.type == BTRFS_INODE_REF_KEY) {
+		struct btrfs_inode_ref *iref;
+		iref = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				      struct btrfs_inode_ref);
+		len = btrfs_inode_ref_name_len(path->nodes[0], iref);
+		ret = fs_path_add_from_extent_buffer(name, path->nodes[0],
+						     (unsigned long)(iref + 1),
+						     len);
+		parent_dir = found_key.offset;
+	} else {
+		struct btrfs_inode_extref *extref;
+		extref = btrfs_item_ptr(path->nodes[0], path->slots[0],
+					struct btrfs_inode_extref);
+		len = btrfs_inode_extref_name_len(path->nodes[0], extref);
+		ret = fs_path_add_from_extent_buffer(name, path->nodes[0],
+					(unsigned long)&extref->name, len);
+		parent_dir = btrfs_inode_extref_parent(path->nodes[0], extref);
+	}
 	if (ret < 0)
 		goto out;
 	btrfs_release_path(path);
 
-	ret = get_inode_info(root, found_key.offset, NULL, dir_gen, NULL, NULL,
+	ret = get_inode_info(root, parent_dir, NULL, dir_gen, NULL, NULL,
 			NULL, NULL);
 	if (ret < 0)
 		goto out;
 
-	*dir = found_key.offset;
+	*dir = parent_dir;
 
 out:
 	btrfs_free_path(path);
@@ -2430,7 +2462,8 @@ verbose_printk("btrfs: send_create_inode %llu\n", ino);
 		TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH_LINK, p);
 	} else if (S_ISCHR(mode) || S_ISBLK(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
-		TLV_PUT_U64(sctx, BTRFS_SEND_A_RDEV, rdev);
+		TLV_PUT_U64(sctx, BTRFS_SEND_A_RDEV, new_encode_dev(rdev));
+		TLV_PUT_U64(sctx, BTRFS_SEND_A_MODE, mode);
 	}
 
 	ret = send_cmd(sctx);
@@ -3226,7 +3259,8 @@ static int process_all_refs(struct send_ctx *sctx,
 		btrfs_item_key_to_cpu(eb, &found_key, slot);
 
 		if (found_key.objectid != key.objectid ||
-		    found_key.type != key.type)
+		    (found_key.type != BTRFS_INODE_REF_KEY &&
+		     found_key.type != BTRFS_INODE_EXTREF_KEY))
 			break;
 
 		ret = iterate_inode_ref(sctx, root, path, &found_key, 0, cb,
@@ -3987,7 +4021,7 @@ static int process_recorded_refs_if_needed(struct send_ctx *sctx, int at_end)
 	if (sctx->cur_ino == 0)
 		goto out;
 	if (!at_end && sctx->cur_ino == sctx->cmp_key->objectid &&
-	    sctx->cmp_key->type <= BTRFS_INODE_REF_KEY)
+	    sctx->cmp_key->type <= BTRFS_INODE_EXTREF_KEY)
 		goto out;
 	if (list_empty(&sctx->new_refs) && list_empty(&sctx->deleted_refs))
 		goto out;
@@ -4033,22 +4067,21 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	if (ret < 0)
 		goto out;
 
-	if (!S_ISLNK(sctx->cur_inode_mode)) {
-		if (!sctx->parent_root || sctx->cur_inode_new) {
+	if (!sctx->parent_root || sctx->cur_inode_new) {
+		need_chown = 1;
+		if (!S_ISLNK(sctx->cur_inode_mode))
 			need_chmod = 1;
-			need_chown = 1;
-		} else {
-			ret = get_inode_info(sctx->parent_root, sctx->cur_ino,
-					NULL, NULL, &right_mode, &right_uid,
-					&right_gid, NULL);
-			if (ret < 0)
-				goto out;
+	} else {
+		ret = get_inode_info(sctx->parent_root, sctx->cur_ino,
+				NULL, NULL, &right_mode, &right_uid,
+				&right_gid, NULL);
+		if (ret < 0)
+			goto out;
 
-			if (left_uid != right_uid || left_gid != right_gid)
-				need_chown = 1;
-			if (left_mode != right_mode)
-				need_chmod = 1;
-		}
+		if (left_uid != right_uid || left_gid != right_gid)
+			need_chown = 1;
+		if (!S_ISLNK(sctx->cur_inode_mode) && left_mode != right_mode)
+			need_chmod = 1;
 	}
 
 	if (S_ISREG(sctx->cur_inode_mode)) {
@@ -4335,7 +4368,8 @@ static int changed_cb(struct btrfs_root *left_root,
 
 	if (key->type == BTRFS_INODE_ITEM_KEY)
 		ret = changed_inode(sctx, result);
-	else if (key->type == BTRFS_INODE_REF_KEY)
+	else if (key->type == BTRFS_INODE_REF_KEY ||
+		 key->type == BTRFS_INODE_EXTREF_KEY)
 		ret = changed_ref(sctx, result);
 	else if (key->type == BTRFS_XATTR_ITEM_KEY)
 		ret = changed_xattr(sctx, result);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 77db875b5116..04bbfb1052eb 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1200,7 +1200,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_i_size_write(parent_inode, parent_inode->i_size +
 					 dentry->d_name.len * 2);
 	parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
-	ret = btrfs_update_inode(trans, parent_root, parent_inode);
+	ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 fail:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index e9ebb472b28b..81e407d9677a 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2952,8 +2952,8 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 			    struct btrfs_inode_item *item,
 			    struct inode *inode, int log_inode_only)
 {
-	btrfs_set_inode_uid(leaf, item, inode->i_uid);
-	btrfs_set_inode_gid(leaf, item, inode->i_gid);
+	btrfs_set_inode_uid(leaf, item, i_uid_read(inode));
+	btrfs_set_inode_gid(leaf, item, i_gid_read(inode));
 	btrfs_set_inode_mode(leaf, item, inode->i_mode);
 	btrfs_set_inode_nlink(leaf, item, inode->i_nlink);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 029b903a4ae3..0f5ebb72a5ea 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1819,6 +1819,13 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 				    "Failed to relocate sys chunks after "
 				    "device initialization. This can be fixed "
 				    "using the \"btrfs balance\" command.");
+		trans = btrfs_attach_transaction(root);
+		if (IS_ERR(trans)) {
+			if (PTR_ERR(trans) == -ENOENT)
+				return 0;
+			return PTR_ERR(trans);
+		}
+		ret = btrfs_commit_transaction(trans, root);
 	}
 
 	return ret;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 8e1b60e557b6..9349bb37a2fe 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -90,6 +90,8 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 		*max_len = handle_length;
 		type = 255;
 	}
+	if (dentry)
+		dput(dentry);
 	return type;
 }
 
@@ -99,7 +101,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
  * FIXME: we should try harder by querying the mds for the ino.
  */
 static struct dentry *__fh_to_dentry(struct super_block *sb,
-				     struct ceph_nfs_fh *fh)
+				     struct ceph_nfs_fh *fh, int fh_len)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -107,6 +109,9 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
+	if (fh_len < sizeof(*fh) / 4)
+		return ERR_PTR(-ESTALE);
+
 	dout("__fh_to_dentry %llx\n", fh->ino);
 	vino.ino = fh->ino;
 	vino.snap = CEPH_NOSNAP;
@@ -150,7 +155,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
  * convert connectable fh to dentry
  */
 static struct dentry *__cfh_to_dentry(struct super_block *sb,
-				      struct ceph_nfs_confh *cfh)
+				      struct ceph_nfs_confh *cfh, int fh_len)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
 	struct inode *inode;
@@ -158,6 +163,9 @@ static struct dentry *__cfh_to_dentry(struct super_block *sb,
 	struct ceph_vino vino;
 	int err;
 
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
+
 	dout("__cfh_to_dentry %llx (%llx/%x)\n",
 	     cfh->ino, cfh->parent_ino, cfh->parent_name_hash);
 
@@ -207,9 +215,11 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb, struct fid *fid,
 					int fh_len, int fh_type)
 {
 	if (fh_type == 1)
-		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw);
+		return __fh_to_dentry(sb, (struct ceph_nfs_fh *)fid->raw,
+								fh_len);
 	else
-		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw);
+		return __cfh_to_dentry(sb, (struct ceph_nfs_confh *)fid->raw,
+								fh_len);
 }
 
 /*
@@ -230,6 +240,8 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 
 	if (fh_type == 1)
 		return ERR_PTR(-ESTALE);
+	if (fh_len < sizeof(*cfh) / 4)
+		return ERR_PTR(-ESTALE);
 
 	pr_debug("fh_to_parent %llx/%d\n", cfh->parent_ino,
 		 cfh->parent_name_hash);
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 3f152b92a94a..afc2bb691780 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -471,9 +471,19 @@ static int exact_lock(dev_t dev, void *data)
  */
 int cdev_add(struct cdev *p, dev_t dev, unsigned count)
 {
+	int error;
+
 	p->dev = dev;
 	p->count = count;
-	return kobj_map(cdev_map, dev, count, NULL, exact_match, exact_lock, p);
+
+	error = kobj_map(cdev_map, dev, count, NULL,
+			 exact_match, exact_lock, p);
+	if (error)
+		return error;
+
+	kobject_get(p->kobj.parent);
+
+	return 0;
 }
 
 static void cdev_unmap(dev_t dev, unsigned count)
@@ -498,14 +508,20 @@ void cdev_del(struct cdev *p)
 static void cdev_default_release(struct kobject *kobj)
 {
 	struct cdev *p = container_of(kobj, struct cdev, kobj);
+	struct kobject *parent = kobj->parent;
+
 	cdev_purge(p);
+	kobject_put(parent);
 }
 
 static void cdev_dynamic_release(struct kobject *kobj)
 {
 	struct cdev *p = container_of(kobj, struct cdev, kobj);
+	struct kobject *parent = kobj->parent;
+
 	cdev_purge(p);
 	kfree(p);
+	kobject_put(parent);
 }
 
 static struct kobj_type ktype_cdev_default = {
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index e622863b292f..086f381d6489 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -31,18 +31,18 @@
 
 /* create a new cifs key */
 static int
-cifs_spnego_key_instantiate(struct key *key, const void *data, size_t datalen)
+cifs_spnego_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	char *payload;
 	int ret;
 
 	ret = -ENOMEM;
-	payload = kmalloc(datalen, GFP_KERNEL);
+	payload = kmalloc(prep->datalen, GFP_KERNEL);
 	if (!payload)
 		goto error;
 
 	/* attach the data */
-	memcpy(payload, data, datalen);
+	memcpy(payload, prep->data, prep->datalen);
 	key->payload.data = payload;
 	ret = 0;
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 2ee5c54797fa..fc783e264420 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -167,17 +167,17 @@ static struct shrinker cifs_shrinker = {
 };
 
 static int
-cifs_idmap_key_instantiate(struct key *key, const void *data, size_t datalen)
+cifs_idmap_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	char *payload;
 
-	payload = kmalloc(datalen, GFP_KERNEL);
+	payload = kmalloc(prep->datalen, GFP_KERNEL);
 	if (!payload)
 		return -ENOMEM;
 
-	memcpy(payload, data, datalen);
+	memcpy(payload, prep->data, prep->datalen);
 	key->payload.data = payload;
-	key->datalen = datalen;
+	key->datalen = prep->datalen;
 	return 0;
 }
 
diff --git a/fs/compat.c b/fs/compat.c
index b7a24d0ca30d..015e1e1f87c6 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -776,16 +776,16 @@ asmlinkage long compat_sys_mount(const char __user * dev_name,
 	char *kernel_type;
 	unsigned long data_page;
 	char *kernel_dev;
-	char *dir_page;
+	struct filename *dir;
 	int retval;
 
 	retval = copy_mount_string(type, &kernel_type);
 	if (retval < 0)
 		goto out;
 
-	dir_page = getname(dir_name);
-	retval = PTR_ERR(dir_page);
-	if (IS_ERR(dir_page))
+	dir = getname(dir_name);
+	retval = PTR_ERR(dir);
+	if (IS_ERR(dir))
 		goto out1;
 
 	retval = copy_mount_string(dev_name, &kernel_dev);
@@ -807,7 +807,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name,
 		}
 	}
 
-	retval = do_mount(kernel_dev, dir_page, kernel_type,
+	retval = do_mount(kernel_dev, dir->name, kernel_type,
 			flags, (void*)data_page);
 
  out4:
@@ -815,7 +815,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name,
  out3:
 	kfree(kernel_dev);
  out2:
-	putname(dir_page);
+	putname(dir);
  out1:
 	kfree(kernel_type);
  out:
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index f5054025f9da..4c6285fff598 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -210,6 +210,8 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd,
 
 	err  = get_user(palp, &up->palette);
 	err |= get_user(length, &up->length);
+	if (err)
+		return -EFAULT;
 
 	up_native = compat_alloc_user_space(sizeof(struct video_spu_palette));
 	err  = put_user(compat_ptr(palp), &up_native->palette);
diff --git a/fs/coredump.c b/fs/coredump.c
index fd37facac8dc..ce47379bfa61 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -450,11 +450,12 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
 
 	cp->file = files[1];
 
-	replace_fd(0, files[0], 0);
+	err = replace_fd(0, files[0], 0);
+	fput(files[0]);
 	/* and disallow core files too */
 	current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
 
-	return 0;
+	return err;
 }
 
 void do_coredump(siginfo_t *siginfo, struct pt_regs *regs)
diff --git a/fs/exec.c b/fs/exec.c
index 4f2bebc276c5..0039055b1fc6 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -59,7 +59,6 @@
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/tlb.h>
-#include <asm/exec.h>
 
 #include <trace/events/task.h>
 #include "internal.h"
@@ -106,7 +105,7 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
 SYSCALL_DEFINE1(uselib, const char __user *, library)
 {
 	struct file *file;
-	char *tmp = getname(library);
+	struct filename *tmp = getname(library);
 	int error = PTR_ERR(tmp);
 	static const struct open_flags uselib_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
@@ -392,7 +391,7 @@ struct user_arg_ptr {
 	union {
 		const char __user *const __user *native;
 #ifdef CONFIG_COMPAT
-		compat_uptr_t __user *compat;
+		const compat_uptr_t __user *compat;
 #endif
 	} ptr;
 };
@@ -752,13 +751,14 @@ struct file *open_exec(const char *name)
 {
 	struct file *file;
 	int err;
+	struct filename tmp = { .name = name };
 	static const struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC | MAY_OPEN,
 		.intent = LOOKUP_OPEN
 	};
 
-	file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
+	file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags, LOOKUP_FOLLOW);
 	if (IS_ERR(file))
 		goto out;
 
@@ -1083,7 +1083,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 	bprm->mm = NULL;		/* We're using it now */
 
 	set_fs(USER_DS);
-	current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD);
+	current->flags &=
+		~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE);
 	flush_thread();
 	current->personality &= ~bprm->per_clear;
 
@@ -1574,9 +1575,9 @@ int do_execve(const char *filename,
 }
 
 #ifdef CONFIG_COMPAT
-int compat_do_execve(char *filename,
-	compat_uptr_t __user *__argv,
-	compat_uptr_t __user *__envp,
+int compat_do_execve(const char *filename,
+	const compat_uptr_t __user *__argv,
+	const compat_uptr_t __user *__envp,
 	struct pt_regs *regs)
 {
 	struct user_arg_ptr argv = {
@@ -1658,3 +1659,56 @@ int get_dumpable(struct mm_struct *mm)
 {
 	return __get_dumpable(mm->flags);
 }
+
+#ifdef __ARCH_WANT_SYS_EXECVE
+SYSCALL_DEFINE3(execve,
+		const char __user *, filename,
+		const char __user *const __user *, argv,
+		const char __user *const __user *, envp)
+{
+	struct filename *path = getname(filename);
+	int error = PTR_ERR(path);
+	if (!IS_ERR(path)) {
+		error = do_execve(path->name, argv, envp, current_pt_regs());
+		putname(path);
+	}
+	return error;
+}
+#ifdef CONFIG_COMPAT
+asmlinkage long compat_sys_execve(const char __user * filename,
+	const compat_uptr_t __user * argv,
+	const compat_uptr_t __user * envp)
+{
+	struct filename *path = getname(filename);
+	int error = PTR_ERR(path);
+	if (!IS_ERR(path)) {
+		error = compat_do_execve(path->name, argv, envp,
+							current_pt_regs());
+		putname(path);
+	}
+	return error;
+}
+#endif
+#endif
+
+#ifdef __ARCH_WANT_KERNEL_EXECVE
+int kernel_execve(const char *filename,
+		  const char *const argv[],
+		  const char *const envp[])
+{
+	struct pt_regs *p = current_pt_regs();
+	int ret;
+
+	ret = do_execve(filename,
+			(const char __user *const __user *)argv,
+			(const char __user *const __user *)envp, p);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We were successful.  We won't be returning to our caller, but
+	 * instead to user space by manipulating the kernel stack.
+	 */
+	ret_from_kernel_execve(p);
+}
+#endif
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 1585db1aa365..f936cb50dc0d 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -814,8 +814,8 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 			struct bio *bio;
 
 			if (per_dev != master_dev) {
-				bio = bio_kmalloc(GFP_KERNEL,
-						  master_dev->bio->bi_max_vecs);
+				bio = bio_clone_kmalloc(master_dev->bio,
+							GFP_KERNEL);
 				if (unlikely(!bio)) {
 					ORE_DBGMSG(
 					      "Failed to allocate BIO size=%u\n",
@@ -824,7 +824,6 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 					goto out;
 				}
 
-				__bio_clone(bio, master_dev->bio);
 				bio->bi_bdev = NULL;
 				bio->bi_next = NULL;
 				per_dev->offset = master_dev->offset;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 59e3bbfac0b1..5e59280d42d7 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -389,8 +389,6 @@ static int exofs_sync_fs(struct super_block *sb, int wait)
 	if (unlikely(ret))
 		goto out;
 
-	lock_super(sb);
-
 	ios->length = offsetof(struct exofs_fscb, s_dev_table_oid);
 	memset(fscb, 0, ios->length);
 	fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
@@ -406,8 +404,6 @@ static int exofs_sync_fs(struct super_block *sb, int wait)
 	if (unlikely(ret))
 		EXOFS_ERR("%s: ore_write failed.\n", __func__);
 
-
-	unlock_super(sb);
 out:
 	EXOFS_DBGMSG("s_nextid=0x%llx ret=%d\n", _LLU(sbi->s_nextid), ret);
 	ore_put_io_state(ios);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 6c205d0c565b..fa04d023177e 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -469,7 +469,7 @@ static int parse_options(char *options, struct super_block *sb)
 			uid = make_kuid(current_user_ns(), option);
 			if (!uid_valid(uid)) {
 				ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option);
-				return -1;
+				return 0;
 
 			}
 			sbi->s_resuid = uid;
@@ -480,7 +480,7 @@ static int parse_options(char *options, struct super_block *sb)
 			gid = make_kgid(current_user_ns(), option);
 			if (!gid_valid(gid)) {
 				ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option);
-				return -1;
+				return 0;
 			}
 			sbi->s_resgid = gid;
 			break;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 8f4fddac01a6..890b8947c546 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -46,8 +46,7 @@ static struct buffer_head *ext3_append(handle_t *handle,
 
 	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
 
-	bh = ext3_bread(handle, inode, *block, 1, err);
-	if (bh) {
+	if ((bh = ext3_dir_bread(handle, inode, *block, 1, err))) {
 		inode->i_size += inode->i_sb->s_blocksize;
 		EXT3_I(inode)->i_disksize = inode->i_size;
 		*err = ext3_journal_get_write_access(handle, bh);
@@ -339,8 +338,10 @@ dx_probe(struct qstr *entry, struct inode *dir,
 	u32 hash;
 
 	frame->bh = NULL;
-	if (!(bh = ext3_bread (NULL,dir, 0, 0, err)))
+	if (!(bh = ext3_dir_bread(NULL, dir, 0, 0, err))) {
+		*err = ERR_BAD_DX_DIR;
 		goto fail;
+	}
 	root = (struct dx_root *) bh->b_data;
 	if (root->info.hash_version != DX_HASH_TEA &&
 	    root->info.hash_version != DX_HASH_HALF_MD4 &&
@@ -436,8 +437,10 @@ dx_probe(struct qstr *entry, struct inode *dir,
 		frame->entries = entries;
 		frame->at = at;
 		if (!indirect--) return frame;
-		if (!(bh = ext3_bread (NULL,dir, dx_get_block(at), 0, err)))
+		if (!(bh = ext3_dir_bread(NULL, dir, dx_get_block(at), 0, err))) {
+			*err = ERR_BAD_DX_DIR;
 			goto fail2;
+		}
 		at = entries = ((struct dx_node *) bh->b_data)->entries;
 		if (dx_get_limit(entries) != dx_node_limit (dir)) {
 			ext3_warning(dir->i_sb, __func__,
@@ -535,8 +538,8 @@ static int ext3_htree_next_block(struct inode *dir, __u32 hash,
 	 * block so no check is necessary
 	 */
 	while (num_frames--) {
-		if (!(bh = ext3_bread(NULL, dir, dx_get_block(p->at),
-				      0, &err)))
+		if (!(bh = ext3_dir_bread(NULL, dir, dx_get_block(p->at),
+					  0, &err)))
 			return err; /* Failure */
 		p++;
 		brelse (p->bh);
@@ -559,10 +562,11 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 {
 	struct buffer_head *bh;
 	struct ext3_dir_entry_2 *de, *top;
-	int err, count = 0;
+	int err = 0, count = 0;
 
 	dxtrace(printk("In htree dirblock_to_tree: block %d\n", block));
-	if (!(bh = ext3_bread (NULL, dir, block, 0, &err)))
+
+	if (!(bh = ext3_dir_bread(NULL, dir, block, 0, &err)))
 		return err;
 
 	de = (struct ext3_dir_entry_2 *) bh->b_data;
@@ -976,7 +980,7 @@ static struct buffer_head * ext3_dx_find_entry(struct inode *dir,
 		return NULL;
 	do {
 		block = dx_get_block(frame->at);
-		if (!(bh = ext3_bread (NULL,dir, block, 0, err)))
+		if (!(bh = ext3_dir_bread (NULL, dir, block, 0, err)))
 			goto errout;
 
 		retval = search_dirblock(bh, dir, entry,
@@ -1458,9 +1462,9 @@ static int ext3_add_entry (handle_t *handle, struct dentry *dentry,
 	}
 	blocks = dir->i_size >> sb->s_blocksize_bits;
 	for (block = 0; block < blocks; block++) {
-		bh = ext3_bread(handle, dir, block, 0, &retval);
-		if(!bh)
+		if (!(bh = ext3_dir_bread(handle, dir, block, 0, &retval)))
 			return retval;
+
 		retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
 		if (retval != -ENOSPC)
 			return retval;
@@ -1500,7 +1504,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	entries = frame->entries;
 	at = frame->at;
 
-	if (!(bh = ext3_bread(handle,dir, dx_get_block(frame->at), 0, &err)))
+	if (!(bh = ext3_dir_bread(handle, dir, dx_get_block(frame->at), 0, &err)))
 		goto cleanup;
 
 	BUFFER_TRACE(bh, "get_write_access");
@@ -1790,8 +1794,7 @@ retry:
 	inode->i_op = &ext3_dir_inode_operations;
 	inode->i_fop = &ext3_dir_operations;
 	inode->i_size = EXT3_I(inode)->i_disksize = inode->i_sb->s_blocksize;
-	dir_block = ext3_bread (handle, inode, 0, 1, &err);
-	if (!dir_block)
+	if (!(dir_block = ext3_dir_bread(handle, inode, 0, 1, &err)))
 		goto out_clear_inode;
 
 	BUFFER_TRACE(dir_block, "get_write_access");
@@ -1859,7 +1862,7 @@ static int empty_dir (struct inode * inode)
 
 	sb = inode->i_sb;
 	if (inode->i_size < EXT3_DIR_REC_LEN(1) + EXT3_DIR_REC_LEN(2) ||
-	    !(bh = ext3_bread (NULL, inode, 0, 0, &err))) {
+	    !(bh = ext3_dir_bread(NULL, inode, 0, 0, &err))) {
 		if (err)
 			ext3_error(inode->i_sb, __func__,
 				   "error %d reading directory #%lu offset 0",
@@ -1890,9 +1893,8 @@ static int empty_dir (struct inode * inode)
 			(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
 			err = 0;
 			brelse (bh);
-			bh = ext3_bread (NULL, inode,
-				offset >> EXT3_BLOCK_SIZE_BITS(sb), 0, &err);
-			if (!bh) {
+			if (!(bh = ext3_dir_bread (NULL, inode,
+				offset >> EXT3_BLOCK_SIZE_BITS(sb), 0, &err))) {
 				if (err)
 					ext3_error(sb, __func__,
 						   "error %d reading directory"
@@ -2388,7 +2390,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 				goto end_rename;
 		}
 		retval = -EIO;
-		dir_bh = ext3_bread (handle, old_inode, 0, 0, &retval);
+		dir_bh = ext3_dir_bread(handle, old_inode, 0, 0, &retval);
 		if (!dir_bh)
 			goto end_rename;
 		if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
diff --git a/fs/ext3/namei.h b/fs/ext3/namei.h
index f2ce2b0065c9..46304d8c9f0a 100644
--- a/fs/ext3/namei.h
+++ b/fs/ext3/namei.h
@@ -6,3 +6,22 @@
 */
 
 extern struct dentry *ext3_get_parent(struct dentry *child);
+
+static inline struct buffer_head *ext3_dir_bread(handle_t *handle,
+						 struct inode *inode,
+						 int block, int create,
+						 int *err)
+{
+	struct buffer_head *bh;
+
+	bh = ext3_bread(handle, inode, block, create, err);
+
+	if (!bh && !(*err)) {
+		*err = -EIO;
+		ext3_error(inode->i_sb, __func__,
+			   "Directory hole detected on inode %lu\n",
+			   inode->i_ino);
+		return NULL;
+	}
+	return bh;
+}
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 17ae5c83d234..5366393528df 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1001,7 +1001,7 @@ static int parse_options (char *options, struct super_block *sb,
 			uid = make_kuid(current_user_ns(), option);
 			if (!uid_valid(uid)) {
 				ext3_msg(sb, KERN_ERR, "Invalid uid value %d", option);
-				return -1;
+				return 0;
 
 			}
 			sbi->s_resuid = uid;
@@ -1012,7 +1012,7 @@ static int parse_options (char *options, struct super_block *sb,
 			gid = make_kgid(current_user_ns(), option);
 			if (!gid_valid(gid)) {
 				ext3_msg(sb, KERN_ERR, "Invalid gid value %d", option);
-				return -1;
+				return 0;
 			}
 			sbi->s_resgid = gid;
 			break;
@@ -2578,11 +2578,9 @@ out:
 static int ext3_unfreeze(struct super_block *sb)
 {
 	if (!(sb->s_flags & MS_RDONLY)) {
-		lock_super(sb);
 		/* Reser the needs_recovery flag before the fs is unlocked. */
 		EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
 		ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
-		unlock_super(sb);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
 	}
 	return 0;
@@ -2602,7 +2600,6 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 #endif
 
 	/* Store the original options */
-	lock_super(sb);
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
 	old_opts.s_resuid = sbi->s_resuid;
@@ -2708,8 +2705,6 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
 		    old_opts.s_qf_names[i] != sbi->s_qf_names[i])
 			kfree(old_opts.s_qf_names[i]);
 #endif
-	unlock_super(sb);
-
 	if (enable_quota)
 		dquot_resume(sb, -1);
 	return 0;
@@ -2728,7 +2723,6 @@ restore_opts:
 		sbi->s_qf_names[i] = old_opts.s_qf_names[i];
 	}
 #endif
-	unlock_super(sb);
 	return err;
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1b5089067d01..cf1821784a16 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -174,8 +174,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		ext4_free_inodes_set(sb, gdp, 0);
 		ext4_itable_unused_set(sb, gdp, 0);
 		memset(bh->b_data, 0xff, sb->s_blocksize);
-		ext4_block_bitmap_csum_set(sb, block_group, gdp, bh,
-					   EXT4_BLOCKS_PER_GROUP(sb) / 8);
+		ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
 		return;
 	}
 	memset(bh->b_data, 0, sb->s_blocksize);
@@ -212,8 +211,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	 */
 	ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group),
 			     sb->s_blocksize * 8, bh->b_data);
-	ext4_block_bitmap_csum_set(sb, block_group, gdp, bh,
-				   EXT4_BLOCKS_PER_GROUP(sb) / 8);
+	ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
 	ext4_group_desc_csum_set(sb, block_group, gdp);
 }
 
@@ -350,7 +348,7 @@ void ext4_validate_block_bitmap(struct super_block *sb,
 		return;
 	}
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
-			desc, bh, EXT4_BLOCKS_PER_GROUP(sb) / 8))) {
+			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
 		return;
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index 5c2d1813ebe9..3285aa5a706a 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -58,11 +58,12 @@ void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 
 int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 				  struct ext4_group_desc *gdp,
-				  struct buffer_head *bh, int sz)
+				  struct buffer_head *bh)
 {
 	__u32 hi;
 	__u32 provided, calculated;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
 
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 					EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -84,8 +85,9 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 
 void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 				struct ext4_group_desc *gdp,
-				struct buffer_head *bh, int sz)
+				struct buffer_head *bh)
 {
+	int sz = EXT4_CLUSTERS_PER_GROUP(sb) / 8;
 	__u32 csum;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3ab2539b7b2e..3c20de1d59d0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1882,10 +1882,10 @@ int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 				  struct buffer_head *bh, int sz);
 void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 				struct ext4_group_desc *gdp,
-				struct buffer_head *bh, int sz);
+				struct buffer_head *bh);
 int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 				  struct ext4_group_desc *gdp,
-				  struct buffer_head *bh, int sz);
+				  struct buffer_head *bh);
 
 /* balloc.c */
 extern void ext4_validate_block_bitmap(struct super_block *sb,
@@ -2063,8 +2063,7 @@ extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
 extern int ext4_calculate_overhead(struct super_block *sb);
 extern int ext4_superblock_csum_verify(struct super_block *sb,
 				       struct ext4_super_block *es);
-extern void ext4_superblock_csum_set(struct super_block *sb,
-				     struct ext4_super_block *es);
+extern void ext4_superblock_csum_set(struct super_block *sb);
 extern void *ext4_kvmalloc(size_t size, gfp_t flags);
 extern void *ext4_kvzalloc(size_t size, gfp_t flags);
 extern void ext4_kvfree(void *ptr);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index bfa65b49d424..b4323ba846b5 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -143,17 +143,13 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
 	struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
 	int err = 0;
 
+	ext4_superblock_csum_set(sb);
 	if (ext4_handle_valid(handle)) {
-		ext4_superblock_csum_set(sb,
-				(struct ext4_super_block *)bh->b_data);
 		err = jbd2_journal_dirty_metadata(handle, bh);
 		if (err)
 			ext4_journal_abort_handle(where, line, __func__,
 						  bh, handle, err);
-	} else {
-		ext4_superblock_csum_set(sb,
-				(struct ext4_super_block *)bh->b_data);
+	} else
 		mark_buffer_dirty(bh);
-	}
 	return err;
 }
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 1c94cca35ed1..7011ac967208 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -52,6 +52,9 @@
 #define EXT4_EXT_MARK_UNINIT1	0x2  /* mark first half uninitialized */
 #define EXT4_EXT_MARK_UNINIT2	0x4  /* mark second half uninitialized */
 
+#define EXT4_EXT_DATA_VALID1	0x8  /* first half contains valid data */
+#define EXT4_EXT_DATA_VALID2	0x10 /* second half contains valid data */
+
 static __le32 ext4_extent_block_csum(struct inode *inode,
 				     struct ext4_extent_header *eh)
 {
@@ -2914,6 +2917,9 @@ static int ext4_split_extent_at(handle_t *handle,
 	unsigned int ee_len, depth;
 	int err = 0;
 
+	BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) ==
+	       (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2));
+
 	ext_debug("ext4_split_extents_at: inode %lu, logical"
 		"block %llu\n", inode->i_ino, (unsigned long long)split);
 
@@ -2972,7 +2978,14 @@ static int ext4_split_extent_at(handle_t *handle,
 
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
-		err = ext4_ext_zeroout(inode, &orig_ex);
+		if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
+			if (split_flag & EXT4_EXT_DATA_VALID1)
+				err = ext4_ext_zeroout(inode, ex2);
+			else
+				err = ext4_ext_zeroout(inode, ex);
+		} else
+			err = ext4_ext_zeroout(inode, &orig_ex);
+
 		if (err)
 			goto fix_extent_len;
 		/* update the extent length and mark as initialized */
@@ -3025,12 +3038,13 @@ static int ext4_split_extent(handle_t *handle,
 	uninitialized = ext4_ext_is_uninitialized(ex);
 
 	if (map->m_lblk + map->m_len < ee_block + ee_len) {
-		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
-			      EXT4_EXT_MAY_ZEROOUT : 0;
+		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
 		flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
 		if (uninitialized)
 			split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
 				       EXT4_EXT_MARK_UNINIT2;
+		if (split_flag & EXT4_EXT_DATA_VALID2)
+			split_flag1 |= EXT4_EXT_DATA_VALID1;
 		err = ext4_split_extent_at(handle, inode, path,
 				map->m_lblk + map->m_len, split_flag1, flags1);
 		if (err)
@@ -3043,8 +3057,8 @@ static int ext4_split_extent(handle_t *handle,
 		return PTR_ERR(path);
 
 	if (map->m_lblk >= ee_block) {
-		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ?
-			      EXT4_EXT_MAY_ZEROOUT : 0;
+		split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT |
+					    EXT4_EXT_DATA_VALID2);
 		if (uninitialized)
 			split_flag1 |= EXT4_EXT_MARK_UNINIT1;
 		if (split_flag & EXT4_EXT_MARK_UNINIT2)
@@ -3323,26 +3337,47 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 
 	split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
 	split_flag |= EXT4_EXT_MARK_UNINIT2;
-
+	if (flags & EXT4_GET_BLOCKS_CONVERT)
+		split_flag |= EXT4_EXT_DATA_VALID2;
 	flags |= EXT4_GET_BLOCKS_PRE_IO;
 	return ext4_split_extent(handle, inode, path, map, split_flag, flags);
 }
 
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
-					      struct inode *inode,
-					      struct ext4_ext_path *path)
+						struct inode *inode,
+						struct ext4_map_blocks *map,
+						struct ext4_ext_path *path)
 {
 	struct ext4_extent *ex;
+	ext4_lblk_t ee_block;
+	unsigned int ee_len;
 	int depth;
 	int err = 0;
 
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
+	ee_block = le32_to_cpu(ex->ee_block);
+	ee_len = ext4_ext_get_actual_len(ex);
 
 	ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
-		(unsigned long long)le32_to_cpu(ex->ee_block),
-		ext4_ext_get_actual_len(ex));
+		  (unsigned long long)ee_block, ee_len);
+
+	/* If extent is larger than requested then split is required */
+	if (ee_block != map->m_lblk || ee_len > map->m_len) {
+		err = ext4_split_unwritten_extents(handle, inode, map, path,
+						   EXT4_GET_BLOCKS_CONVERT);
+		if (err < 0)
+			goto out;
+		ext4_ext_drop_refs(path);
+		path = ext4_ext_find_extent(inode, map->m_lblk, path);
+		if (IS_ERR(path)) {
+			err = PTR_ERR(path);
+			goto out;
+		}
+		depth = ext_depth(inode);
+		ex = path[depth].p_ext;
+	}
 
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
@@ -3652,7 +3687,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	}
 	/* IO end_io complete, convert the filled extent to written */
 	if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
-		ret = ext4_convert_unwritten_extents_endio(handle, inode,
+		ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
 							path);
 		if (ret >= 0) {
 			ext4_update_inode_fsync_trans(handle, inode, 1);
@@ -4428,6 +4463,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	 */
 	if (len <= EXT_UNINIT_MAX_LEN << blkbits)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
+
+	/* Prevent race condition between unwritten */
+	ext4_flush_unwritten_io(inode);
 retry:
 	while (ret >= 0 && ret < max_blocks) {
 		map.m_lblk = map.m_lblk + ret;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index fa36372f3fdf..3a100e7a62a8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -725,6 +725,10 @@ repeat_in_this_group:
 				   "inode=%lu", ino + 1);
 			continue;
 		}
+		BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
+		err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
+		if (err)
+			goto fail;
 		ext4_lock_group(sb, group);
 		ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data);
 		ext4_unlock_group(sb, group);
@@ -738,6 +742,11 @@ repeat_in_this_group:
 	goto out;
 
 got:
+	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
+	if (err)
+		goto fail;
+
 	/* 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)) {
@@ -762,9 +771,7 @@ got:
 			ext4_free_group_clusters_set(sb, gdp,
 				ext4_free_clusters_after_init(sb, group, gdp));
 			ext4_block_bitmap_csum_set(sb, group, gdp,
-						   block_bitmap_bh,
-						   EXT4_BLOCKS_PER_GROUP(sb) /
-						   8);
+						   block_bitmap_bh);
 			ext4_group_desc_csum_set(sb, group, gdp);
 		}
 		ext4_unlock_group(sb, group);
@@ -773,11 +780,6 @@ got:
 			goto fail;
 	}
 
-	BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
-	if (err)
-		goto fail;
-
 	BUFFER_TRACE(group_desc_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, group_desc_bh);
 	if (err)
@@ -825,11 +827,6 @@ got:
 	}
 	ext4_unlock_group(sb, group);
 
-	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh);
-	if (err)
-		goto fail;
-
 	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);
 	if (err)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f8b27bf80aca..526e55358606 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2805,8 +2805,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	}
 	len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len;
 	ext4_free_group_clusters_set(sb, gdp, len);
-	ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh,
-				   EXT4_BLOCKS_PER_GROUP(sb) / 8);
+	ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh);
 	ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp);
 
 	ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
@@ -4666,8 +4665,7 @@ do_more:
 
 	ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
 	ext4_free_group_clusters_set(sb, gdp, ret);
-	ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
-				   EXT4_BLOCKS_PER_GROUP(sb) / 8);
+	ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh);
 	ext4_group_desc_csum_set(sb, block_group, gdp);
 	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
@@ -4811,8 +4809,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	mb_free_blocks(NULL, &e4b, bit, count);
 	blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc);
 	ext4_free_group_clusters_set(sb, desc, blk_free_count);
-	ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh,
-				   EXT4_BLOCKS_PER_GROUP(sb) / 8);
+	ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh);
 	ext4_group_desc_csum_set(sb, block_group, desc);
 	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeclusters_counter,
@@ -4993,8 +4990,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	minlen = EXT4_NUM_B2C(EXT4_SB(sb),
 			      range->minlen >> sb->s_blocksize_bits);
 
-	if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) ||
-	    unlikely(start >= max_blks))
+	if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) ||
+	    start >= max_blks ||
+	    range->len < sb->s_blocksize)
 		return -EINVAL;
 	if (end >= max_blks)
 		end = max_blks - 1;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 7a75e1086961..47bf06a2765d 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1212,8 +1212,7 @@ static int ext4_set_bitmap_checksums(struct super_block *sb,
 	bh = ext4_get_bitmap(sb, group_data->block_bitmap);
 	if (!bh)
 		return -EIO;
-	ext4_block_bitmap_csum_set(sb, group, gdp, bh,
-				   EXT4_BLOCKS_PER_GROUP(sb) / 8);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bh);
 	brelse(bh);
 
 	return 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7265a0367476..80928f716850 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -143,9 +143,10 @@ int ext4_superblock_csum_verify(struct super_block *sb,
 	return es->s_checksum == ext4_superblock_csum(sb, es);
 }
 
-void ext4_superblock_csum_set(struct super_block *sb,
-			      struct ext4_super_block *es)
+void ext4_superblock_csum_set(struct super_block *sb)
 {
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 		EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
 		return;
@@ -1963,7 +1964,7 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
-	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+	groups_per_flex = 1U << sbi->s_log_groups_per_flex;
 
 	err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
 	if (err)
@@ -4381,7 +4382,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 		cpu_to_le32(percpu_counter_sum_positive(
 				&EXT4_SB(sb)->s_freeinodes_counter));
 	BUFFER_TRACE(sbh, "marking dirty");
-	ext4_superblock_csum_set(sb, es);
+	ext4_superblock_csum_set(sb);
 	mark_buffer_dirty(sbh);
 	if (sync) {
 		error = sync_dirty_buffer(sbh);
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index bca6d0a1255e..2a182342442e 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -571,7 +571,7 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
 	int short_len = 0, fill_len = 0;
 	int ret = 0;
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 
 	cpos = filp->f_pos;
 	/* Fake . and .. for the root directory. */
@@ -693,7 +693,7 @@ fill_failed:
 	if (unicode)
 		__putname(unicode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	return ret;
 }
 
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index ca7e8f8bad7c..623f36f0423b 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -71,8 +71,9 @@ struct msdos_sb_info {
 	unsigned long root_cluster;   /* first cluster of the root directory */
 	unsigned long fsinfo_sector;  /* sector number of FAT32 fsinfo */
 	struct mutex fat_lock;
-	unsigned int prev_free;       /* previously allocated cluster number */
-	unsigned int free_clusters;   /* -1 if undefined */
+	struct mutex s_lock;
+	unsigned int prev_free;      /* previously allocated cluster number */
+	unsigned int free_clusters;  /* -1 if undefined */
 	unsigned int free_clus_valid; /* is free_clusters valid? */
 	struct fat_mount_options options;
 	struct nls_table *nls_disk;   /* Codepage used on disk */
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 76f60c642c06..5bafaad00530 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -673,9 +673,9 @@ static int fat_write_inode(struct inode *inode, struct writeback_control *wbc)
 	if (inode->i_ino == MSDOS_FSINFO_INO) {
 		struct super_block *sb = inode->i_sb;
 
-		lock_super(sb);
+		mutex_lock(&MSDOS_SB(sb)->s_lock);
 		err = fat_clusters_flush(sb);
-		unlock_super(sb);
+		mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	} else
 		err = __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
 
@@ -1268,6 +1268,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		b = (struct fat_boot_sector *) bh->b_data;
 	}
 
+	mutex_init(&sbi->s_lock);
 	sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus;
 	sbi->cluster_bits = ffs(sbi->cluster_size) - 1;
 	sbi->fats = b->fats;
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index c1055e778fff..e2cfda94a28d 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -208,7 +208,7 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 	err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
 	switch (err) {
 	case -ENOENT:
@@ -221,7 +221,7 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
 	default:
 		inode = ERR_PTR(err);
 	}
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	return d_splice_alias(inode, dentry);
 }
 
@@ -273,7 +273,7 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	unsigned char msdos_name[MSDOS_NAME];
 	int err, is_hid;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	err = msdos_format_name(dentry->d_name.name, dentry->d_name.len,
 				msdos_name, &MSDOS_SB(sb)->options);
@@ -302,7 +302,7 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	d_instantiate(dentry, inode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	if (!err)
 		err = fat_flush_inodes(sb, dir, inode);
 	return err;
@@ -316,7 +316,7 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 	/*
 	 * Check whether the directory is not in use, then check
 	 * whether it is empty.
@@ -337,7 +337,7 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 	inode->i_ctime = CURRENT_TIME_SEC;
 	fat_detach(inode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	if (!err)
 		err = fat_flush_inodes(sb, dir, inode);
 
@@ -354,7 +354,7 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct timespec ts;
 	int err, is_hid, cluster;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	err = msdos_format_name(dentry->d_name.name, dentry->d_name.len,
 				msdos_name, &MSDOS_SB(sb)->options);
@@ -392,14 +392,14 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	d_instantiate(dentry, inode);
 
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	fat_flush_inodes(sb, dir, inode);
 	return 0;
 
 out_free:
 	fat_free_clusters(dir, cluster);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	return err;
 }
 
@@ -411,7 +411,7 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 	err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
 	if (err)
 		goto out;
@@ -423,7 +423,7 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry)
 	inode->i_ctime = CURRENT_TIME_SEC;
 	fat_detach(inode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	if (!err)
 		err = fat_flush_inodes(sb, dir, inode);
 
@@ -606,7 +606,7 @@ static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry,
 	unsigned char old_msdos_name[MSDOS_NAME], new_msdos_name[MSDOS_NAME];
 	int err, is_hid;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	err = msdos_format_name(old_dentry->d_name.name,
 				old_dentry->d_name.len, old_msdos_name,
@@ -625,7 +625,7 @@ static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry,
 	err = do_msdos_rename(old_dir, old_msdos_name, old_dentry,
 			      new_dir, new_msdos_name, new_dentry, is_hid);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	if (!err)
 		err = fat_flush_inodes(sb, old_dir, new_dir);
 	return err;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index e535dd75b986..ac959d655e7d 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -721,7 +721,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 	struct dentry *alias;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	err = vfat_find(dir, &dentry->d_name, &sinfo);
 	if (err) {
@@ -752,13 +752,13 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 		if (!S_ISDIR(inode->i_mode))
 			d_move(alias, dentry);
 		iput(inode);
-		unlock_super(sb);
+		mutex_unlock(&MSDOS_SB(sb)->s_lock);
 		return alias;
 	} else
 		dput(alias);
 
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	dentry->d_time = dentry->d_parent->d_inode->i_version;
 	dentry = d_splice_alias(inode, dentry);
 	if (dentry)
@@ -766,7 +766,7 @@ out:
 	return dentry;
 
 error:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	return ERR_PTR(err);
 }
 
@@ -779,7 +779,7 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	struct timespec ts;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	ts = CURRENT_TIME_SEC;
 	err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo);
@@ -800,7 +800,7 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	dentry->d_time = dentry->d_parent->d_inode->i_version;
 	d_instantiate(dentry, inode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	return err;
 }
 
@@ -811,7 +811,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	err = fat_dir_empty(inode);
 	if (err)
@@ -829,7 +829,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
 	inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC;
 	fat_detach(inode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 
 	return err;
 }
@@ -841,7 +841,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry)
 	struct fat_slot_info sinfo;
 	int err;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	err = vfat_find(dir, &dentry->d_name, &sinfo);
 	if (err)
@@ -854,7 +854,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry)
 	inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC;
 	fat_detach(inode);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 
 	return err;
 }
@@ -867,7 +867,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct timespec ts;
 	int err, cluster;
 
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 
 	ts = CURRENT_TIME_SEC;
 	cluster = fat_alloc_new_dir(dir, &ts);
@@ -896,13 +896,13 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	dentry->d_time = dentry->d_parent->d_inode->i_version;
 	d_instantiate(dentry, inode);
 
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	return 0;
 
 out_free:
 	fat_free_clusters(dir, cluster);
 out:
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 	return err;
 }
 
@@ -921,7 +921,7 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
 	old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
 	old_inode = old_dentry->d_inode;
 	new_inode = new_dentry->d_inode;
-	lock_super(sb);
+	mutex_lock(&MSDOS_SB(sb)->s_lock);
 	err = vfat_find(old_dir, &old_dentry->d_name, &old_sinfo);
 	if (err)
 		goto out;
@@ -996,7 +996,7 @@ out:
 	brelse(sinfo.bh);
 	brelse(dotdot_bh);
 	brelse(old_sinfo.bh);
-	unlock_super(sb);
+	mutex_unlock(&MSDOS_SB(sb)->s_lock);
 
 	return err;
 
diff --git a/fs/file.c b/fs/file.c
index 0f1bda4bebfa..708d997a7748 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -900,7 +900,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 		return __close_fd(files, fd);
 
 	if (fd >= rlimit(RLIMIT_NOFILE))
-		return -EMFILE;
+		return -EBADF;
 
 	spin_lock(&files->file_lock);
 	err = expand_files(files, fd);
@@ -922,8 +922,11 @@ SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
 	if ((flags & ~O_CLOEXEC) != 0)
 		return -EINVAL;
 
+	if (unlikely(oldfd == newfd))
+		return -EINVAL;
+
 	if (newfd >= rlimit(RLIMIT_NOFILE))
-		return -EMFILE;
+		return -EBADF;
 
 	spin_lock(&files->file_lock);
 	err = expand_files(files, newfd);
diff --git a/fs/file_table.c b/fs/file_table.c
index dac67923330f..a72bf9ddd0d2 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -36,7 +36,7 @@ struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-DEFINE_LGLOCK(files_lglock);
+DEFINE_STATIC_LGLOCK(files_lglock);
 
 /* SLAB cache for file structures */
 static struct kmem_cache *filp_cachep __read_mostly;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 96f24286667a..da165f6adcbf 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -124,7 +124,7 @@ EXPORT_SYMBOL(unregister_filesystem);
 static int fs_index(const char __user * __name)
 {
 	struct file_system_type * tmp;
-	char * name;
+	struct filename *name;
 	int err, index;
 
 	name = getname(__name);
@@ -135,7 +135,7 @@ static int fs_index(const char __user * __name)
 	err = -EINVAL;
 	read_lock(&file_systems_lock);
 	for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) {
-		if (strcmp(tmp->name,name) == 0) {
+		if (strcmp(tmp->name, name->name) == 0) {
 			err = index;
 			break;
 		}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 401b6c6248ae..51ea267d444c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -249,7 +249,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
 }
 
 /*
- * Move expired (dirtied after work->older_than_this) dirty inodes from
+ * Move expired (dirtied before work->older_than_this) dirty inodes from
  * @delaying_queue to @dispatch_queue.
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index e8ed6d4a6181..4767774a5f3e 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -161,6 +161,8 @@ static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,
 	case GFS2_SMALL_FH_SIZE:
 	case GFS2_LARGE_FH_SIZE:
 	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_SMALL_FH_SIZE)
+			return NULL;
 		this.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32;
 		this.no_formal_ino |= be32_to_cpu(fh[1]);
 		this.no_addr = ((u64)be32_to_cpu(fh[2])) << 32;
@@ -180,6 +182,8 @@ static struct dentry *gfs2_fh_to_parent(struct super_block *sb, struct fid *fid,
 	switch (fh_type) {
 	case GFS2_LARGE_FH_SIZE:
 	case GFS2_OLD_FH_SIZE:
+		if (fh_len < GFS2_LARGE_FH_SIZE)
+			return NULL;
 		parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32;
 		parent.no_formal_ino |= be32_to_cpu(fh[5]);
 		parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32;
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index 1fe731337f07..9c88da0e855a 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -1,7 +1,7 @@
 #ifndef __UM_FS_HOSTFS
 #define __UM_FS_HOSTFS
 
-#include "os.h"
+#include <os.h>
 
 /*
  * These are exactly the same definitions as in fs.h, but the names are
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 6c9f3a9d5e21..457addc5c91f 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -16,8 +16,8 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include "hostfs.h"
-#include "init.h"
-#include "kern.h"
+#include <init.h>
+#include <kern.h>
 
 struct hostfs_inode_info {
 	int fd;
@@ -848,9 +848,11 @@ int hostfs_setattr(struct dentry *dentry, struct iattr *attr)
 	    attr->ia_size != i_size_read(inode)) {
 		int error;
 
-		error = vmtruncate(inode, attr->ia_size);
-		if (err)
-			return err;
+		error = inode_newsize_ok(inode, attr->ia_size);
+		if (error)
+			return error;
+
+		truncate_setsize(inode, attr->ia_size);
 	}
 
 	setattr_copy(inode, attr);
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index a74ad0d371c2..67838f3aa20a 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -15,7 +15,6 @@
 #include <sys/types.h>
 #include <sys/vfs.h>
 #include "hostfs.h"
-#include "os.h"
 #include <utime.h>
 
 static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index bc28bf077a6a..a3076228523d 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -398,7 +398,6 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
 	*flags |= MS_NOATIME;
 	
 	hpfs_lock(s);
-	lock_super(s);
 	uid = sbi->sb_uid; gid = sbi->sb_gid;
 	umask = 0777 & ~sbi->sb_mode;
 	lowercase = sbi->sb_lowercase;
@@ -431,12 +430,10 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
 
 	replace_mount_options(s, new_opts);
 
-	unlock_super(s);
 	hpfs_unlock(s);
 	return 0;
 
 out_err:
-	unlock_super(s);
 	hpfs_unlock(s);
 	kfree(new_opts);
 	return -EINVAL;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index c1dffe47fde2..78f21f8dc2ec 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -18,7 +18,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/namei.h>
 #include <asm/uaccess.h>
-#include "os.h"
+#include <os.h>
 
 static struct inode *get_inode(struct super_block *, struct dentry *);
 
@@ -674,7 +674,7 @@ static struct inode *get_inode(struct super_block *sb, struct dentry *dentry)
 
 	if (!inode) {
 		dput(dentry);
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 	}
 
 	if (S_ISDIR(dentry->d_inode->i_mode)) {
diff --git a/fs/internal.h b/fs/internal.h
index 371bcc4b1697..916b7cbf3e3e 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -97,8 +97,8 @@ struct open_flags {
 	int acc_mode;
 	int intent;
 };
-extern struct file *do_filp_open(int dfd, const char *pathname,
-		const struct open_flags *op, int lookup_flags);
+extern struct file *do_filp_open(int dfd, struct filename *pathname,
+		const struct open_flags *op, int flags);
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *, int lookup_flags);
 
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index 1d3804492aa7..2b4f2358eadb 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -175,7 +175,7 @@ static struct dentry *isofs_fh_to_parent(struct super_block *sb,
 {
 	struct isofs_fid *ifid = (struct isofs_fid *)fid;
 
-	if (fh_type != 2)
+	if (fh_len < 2 || fh_type != 2)
 		return NULL;
 
 	return isofs_export_iget(sb,
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 60ef3fb707ff..1506673c087e 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -138,33 +138,39 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	struct page *pg;
 	struct inode *inode = mapping->host;
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
+	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
+	struct jffs2_raw_inode ri;
+	uint32_t alloc_len = 0;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	uint32_t pageofs = index << PAGE_CACHE_SHIFT;
 	int ret = 0;
 
+	jffs2_dbg(1, "%s()\n", __func__);
+
+	if (pageofs > inode->i_size) {
+		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
+					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
+		if (ret)
+			return ret;
+	}
+
+	mutex_lock(&f->sem);
 	pg = grab_cache_page_write_begin(mapping, index, flags);
-	if (!pg)
+	if (!pg) {
+		if (alloc_len)
+			jffs2_complete_reservation(c);
+		mutex_unlock(&f->sem);
 		return -ENOMEM;
+	}
 	*pagep = pg;
 
-	jffs2_dbg(1, "%s()\n", __func__);
-
-	if (pageofs > inode->i_size) {
+	if (alloc_len) {
 		/* Make new hole frag from old EOF to new page */
-		struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-		struct jffs2_raw_inode ri;
 		struct jffs2_full_dnode *fn;
-		uint32_t alloc_len;
 
 		jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n",
 			  (unsigned int)inode->i_size, pageofs);
 
-		ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len,
-					  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
-		if (ret)
-			goto out_page;
-
-		mutex_lock(&f->sem);
 		memset(&ri, 0, sizeof(ri));
 
 		ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK);
@@ -191,7 +197,6 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		if (IS_ERR(fn)) {
 			ret = PTR_ERR(fn);
 			jffs2_complete_reservation(c);
-			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		ret = jffs2_add_full_dnode_to_inode(c, f, fn);
@@ -206,12 +211,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			jffs2_mark_node_obsolete(c, fn->raw);
 			jffs2_free_full_dnode(fn);
 			jffs2_complete_reservation(c);
-			mutex_unlock(&f->sem);
 			goto out_page;
 		}
 		jffs2_complete_reservation(c);
 		inode->i_size = pageofs;
-		mutex_unlock(&f->sem);
 	}
 
 	/*
@@ -220,18 +223,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * case of a short-copy.
 	 */
 	if (!PageUptodate(pg)) {
-		mutex_lock(&f->sem);
 		ret = jffs2_do_readpage_nolock(inode, pg);
-		mutex_unlock(&f->sem);
 		if (ret)
 			goto out_page;
 	}
+	mutex_unlock(&f->sem);
 	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
 	return ret;
 
 out_page:
 	unlock_page(pg);
 	page_cache_release(pg);
+	mutex_unlock(&f->sem);
 	return ret;
 }
 
diff --git a/fs/jfs/jfs_discard.c b/fs/jfs/jfs_discard.c
index 9947563e4175..dfcd50304559 100644
--- a/fs/jfs/jfs_discard.c
+++ b/fs/jfs/jfs_discard.c
@@ -83,7 +83,7 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range)
 	struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap;
 	struct super_block *sb = ipbmap->i_sb;
 	int agno, agno_end;
-	s64 start, end, minlen;
+	u64 start, end, minlen;
 	u64 trimmed = 0;
 
 	/**
@@ -93,15 +93,19 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range)
 	 * minlen:	minimum extent length in Bytes
 	 */
 	start = range->start >> sb->s_blocksize_bits;
-	if (start < 0)
-		start = 0;
 	end = start + (range->len >> sb->s_blocksize_bits) - 1;
-	if (end >= bmp->db_mapsize)
-		end = bmp->db_mapsize - 1;
 	minlen = range->minlen >> sb->s_blocksize_bits;
-	if (minlen <= 0)
+	if (minlen == 0)
 		minlen = 1;
 
+	if (minlen > bmp->db_agsize ||
+	    start >= bmp->db_mapsize ||
+	    range->len < sb->s_blocksize)
+		return -EINVAL;
+
+	if (end >= bmp->db_mapsize)
+		end = bmp->db_mapsize - 1;
+
 	/**
 	 * we trim all ag's within the range
 	 */
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index d269ada7670e..982d2676e1f8 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -223,7 +223,7 @@ static void encode_nlm_stat(struct xdr_stream *xdr,
 {
 	__be32 *p;
 
-	BUG_ON(be32_to_cpu(stat) > NLM_LCK_DENIED_GRACE_PERIOD);
+	WARN_ON_ONCE(be32_to_cpu(stat) > NLM_LCK_DENIED_GRACE_PERIOD);
 	p = xdr_reserve_space(xdr, 4);
 	*p = stat;
 }
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 7ef14b3c5bee..3d7e09bcc0e9 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/utsname.h>
 #include <linux/kernel.h>
 #include <linux/ktime.h>
 #include <linux/slab.h>
@@ -19,6 +18,8 @@
 
 #include <asm/unaligned.h>
 
+#include "netns.h"
+
 #define NLMDBG_FACILITY		NLMDBG_MONITOR
 #define NSM_PROGRAM		100024
 #define NSM_VERSION		1
@@ -40,6 +41,7 @@ struct nsm_args {
 	u32			proc;
 
 	char			*mon_name;
+	char			*nodename;
 };
 
 struct nsm_res {
@@ -70,7 +72,7 @@ static struct rpc_clnt *nsm_create(struct net *net)
 	};
 	struct rpc_create_args args = {
 		.net			= net,
-		.protocol		= XPRT_TRANSPORT_UDP,
+		.protocol		= XPRT_TRANSPORT_TCP,
 		.address		= (struct sockaddr *)&sin,
 		.addrsize		= sizeof(sin),
 		.servername		= "rpc.statd",
@@ -83,10 +85,61 @@ static struct rpc_clnt *nsm_create(struct net *net)
 	return rpc_create(&args);
 }
 
+static struct rpc_clnt *nsm_client_set(struct lockd_net *ln,
+		struct rpc_clnt *clnt)
+{
+	spin_lock(&ln->nsm_clnt_lock);
+	if (ln->nsm_users == 0) {
+		if (clnt == NULL)
+			goto out;
+		ln->nsm_clnt = clnt;
+	}
+	clnt = ln->nsm_clnt;
+	ln->nsm_users++;
+out:
+	spin_unlock(&ln->nsm_clnt_lock);
+	return clnt;
+}
+
+static struct rpc_clnt *nsm_client_get(struct net *net)
+{
+	struct rpc_clnt	*clnt, *new;
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+
+	clnt = nsm_client_set(ln, NULL);
+	if (clnt != NULL)
+		goto out;
+
+	clnt = new = nsm_create(net);
+	if (IS_ERR(clnt))
+		goto out;
+
+	clnt = nsm_client_set(ln, new);
+	if (clnt != new)
+		rpc_shutdown_client(new);
+out:
+	return clnt;
+}
+
+static void nsm_client_put(struct net *net)
+{
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
+	struct rpc_clnt	*clnt = NULL;
+
+	spin_lock(&ln->nsm_clnt_lock);
+	ln->nsm_users--;
+	if (ln->nsm_users == 0) {
+		clnt = ln->nsm_clnt;
+		ln->nsm_clnt = NULL;
+	}
+	spin_unlock(&ln->nsm_clnt_lock);
+	if (clnt != NULL)
+		rpc_shutdown_client(clnt);
+}
+
 static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
-			 struct net *net)
+			 struct rpc_clnt *clnt)
 {
-	struct rpc_clnt	*clnt;
 	int		status;
 	struct nsm_args args = {
 		.priv		= &nsm->sm_priv,
@@ -94,31 +147,24 @@ static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res,
 		.vers		= 3,
 		.proc		= NLMPROC_NSM_NOTIFY,
 		.mon_name	= nsm->sm_mon_name,
+		.nodename	= clnt->cl_nodename,
 	};
 	struct rpc_message msg = {
 		.rpc_argp	= &args,
 		.rpc_resp	= res,
 	};
 
-	clnt = nsm_create(net);
-	if (IS_ERR(clnt)) {
-		status = PTR_ERR(clnt);
-		dprintk("lockd: failed to create NSM upcall transport, "
-				"status=%d\n", status);
-		goto out;
-	}
+	BUG_ON(clnt == NULL);
 
 	memset(res, 0, sizeof(*res));
 
 	msg.rpc_proc = &clnt->cl_procinfo[proc];
-	status = rpc_call_sync(clnt, &msg, 0);
+	status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
 	if (status < 0)
 		dprintk("lockd: NSM upcall RPC failed, status=%d\n",
 				status);
 	else
 		status = 0;
-	rpc_shutdown_client(clnt);
- out:
 	return status;
 }
 
@@ -138,6 +184,7 @@ int nsm_monitor(const struct nlm_host *host)
 	struct nsm_handle *nsm = host->h_nsmhandle;
 	struct nsm_res	res;
 	int		status;
+	struct rpc_clnt *clnt;
 
 	dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
 
@@ -150,7 +197,15 @@ int nsm_monitor(const struct nlm_host *host)
 	 */
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, host->net);
+	clnt = nsm_client_get(host->net);
+	if (IS_ERR(clnt)) {
+		status = PTR_ERR(clnt);
+		dprintk("lockd: failed to create NSM upcall transport, "
+				"status=%d, net=%p\n", status, host->net);
+		return status;
+	}
+
+	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res, clnt);
 	if (unlikely(res.status != 0))
 		status = -EIO;
 	if (unlikely(status < 0)) {
@@ -182,9 +237,11 @@ void nsm_unmonitor(const struct nlm_host *host)
 
 	if (atomic_read(&nsm->sm_count) == 1
 	 && nsm->sm_monitored && !nsm->sm_sticky) {
+		struct lockd_net *ln = net_generic(host->net, lockd_net_id);
+
 		dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
 
-		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, host->net);
+		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res, ln->nsm_clnt);
 		if (res.status != 0)
 			status = -EIO;
 		if (status < 0)
@@ -192,6 +249,8 @@ void nsm_unmonitor(const struct nlm_host *host)
 					nsm->sm_name);
 		else
 			nsm->sm_monitored = 0;
+
+		nsm_client_put(host->net);
 	}
 }
 
@@ -430,7 +489,7 @@ static void encode_my_id(struct xdr_stream *xdr, const struct nsm_args *argp)
 {
 	__be32 *p;
 
-	encode_nsm_string(xdr, utsname()->nodename);
+	encode_nsm_string(xdr, argp->nodename);
 	p = xdr_reserve_space(xdr, 4 + 4 + 4);
 	*p++ = cpu_to_be32(argp->prog);
 	*p++ = cpu_to_be32(argp->vers);
diff --git a/fs/lockd/netns.h b/fs/lockd/netns.h
index 4eee248ba96e..5010b55628b4 100644
--- a/fs/lockd/netns.h
+++ b/fs/lockd/netns.h
@@ -12,6 +12,10 @@ struct lockd_net {
 	struct delayed_work grace_period_end;
 	struct lock_manager lockd_manager;
 	struct list_head grace_list;
+
+	spinlock_t nsm_clnt_lock;
+	unsigned int nsm_users;
+	struct rpc_clnt *nsm_clnt;
 };
 
 extern int lockd_net_id;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 31a63f87b806..a2aa97d45670 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -126,7 +126,7 @@ static void restart_grace(void)
 static int
 lockd(void *vrqstp)
 {
-	int		err = 0, preverr = 0;
+	int		err = 0;
 	struct svc_rqst *rqstp = vrqstp;
 
 	/* try_to_freeze() is called from svc_recv() */
@@ -165,21 +165,8 @@ lockd(void *vrqstp)
 		 * recvfrom routine.
 		 */
 		err = svc_recv(rqstp, timeout);
-		if (err == -EAGAIN || err == -EINTR) {
-			preverr = err;
+		if (err == -EAGAIN || err == -EINTR)
 			continue;
-		}
-		if (err < 0) {
-			if (err != preverr) {
-				printk(KERN_WARNING "%s: unexpected error "
-					"from svc_recv (%d)\n", __func__, err);
-				preverr = err;
-			}
-			schedule_timeout_interruptible(HZ);
-			continue;
-		}
-		preverr = err;
-
 		dprintk("lockd: request from %s\n",
 				svc_print_addr(rqstp, buf, sizeof(buf)));
 
@@ -596,6 +583,7 @@ static int lockd_init_net(struct net *net)
 
 	INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
 	INIT_LIST_HEAD(&ln->grace_list);
+	spin_lock_init(&ln->nsm_clnt_lock);
 	return 0;
 }
 
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 3009a365e082..21171f0c6477 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -68,7 +68,8 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 	/* Obtain file pointer. Not used by FREE_ALL call. */
 	if (filp != NULL) {
-		if ((error = nlm_lookup_file(rqstp, &file, &lock->fh)) != 0)
+		error = cast_status(nlm_lookup_file(rqstp, &file, &lock->fh));
+		if (error != 0)
 			goto no_locks;
 		*filp = file;
 
diff --git a/fs/locks.c b/fs/locks.c
index abc7dc6c490b..a94e331a52a2 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1289,7 +1289,7 @@ EXPORT_SYMBOL(__break_lease);
 void lease_get_mtime(struct inode *inode, struct timespec *time)
 {
 	struct file_lock *flock = inode->i_flock;
-	if (flock && IS_LEASE(flock) && (flock->fl_type & F_WRLCK))
+	if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
 		*time = current_fs_time(inode->i_sb);
 	else
 		*time = inode->i_mtime;
@@ -2185,8 +2185,8 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 	} else {
 		seq_printf(f, "%s ",
 			       (lease_breaking(fl))
-			       ? (fl->fl_type & F_UNLCK) ? "UNLCK" : "READ "
-			       : (fl->fl_type & F_WRLCK) ? "WRITE" : "READ ");
+			       ? (fl->fl_type == F_UNLCK) ? "UNLCK" : "READ "
+			       : (fl->fl_type == F_WRLCK) ? "WRITE" : "READ ");
 	}
 	if (inode) {
 #ifdef WE_CAN_BREAK_LSLK_NOW
diff --git a/fs/namei.c b/fs/namei.c
index aa30d19e9edd..937f9d50c84b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -117,18 +117,70 @@
  * POSIX.1 2.4: an empty pathname is invalid (ENOENT).
  * PATH_MAX includes the nul terminator --RR.
  */
-static char *getname_flags(const char __user *filename, int flags, int *empty)
+void final_putname(struct filename *name)
 {
-	char *result = __getname(), *err;
+	if (name->separate) {
+		__putname(name->name);
+		kfree(name);
+	} else {
+		__putname(name);
+	}
+}
+
+#define EMBEDDED_NAME_MAX	(PATH_MAX - sizeof(struct filename))
+
+static struct filename *
+getname_flags(const char __user *filename, int flags, int *empty)
+{
+	struct filename *result, *err;
 	int len;
+	long max;
+	char *kname;
 
+	result = audit_reusename(filename);
+	if (result)
+		return result;
+
+	result = __getname();
 	if (unlikely(!result))
 		return ERR_PTR(-ENOMEM);
 
-	len = strncpy_from_user(result, filename, PATH_MAX);
-	err = ERR_PTR(len);
-	if (unlikely(len < 0))
+	/*
+	 * First, try to embed the struct filename inside the names_cache
+	 * allocation
+	 */
+	kname = (char *)result + sizeof(*result);
+	result->name = kname;
+	result->separate = false;
+	max = EMBEDDED_NAME_MAX;
+
+recopy:
+	len = strncpy_from_user(kname, filename, max);
+	if (unlikely(len < 0)) {
+		err = ERR_PTR(len);
 		goto error;
+	}
+
+	/*
+	 * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
+	 * separate struct filename so we can dedicate the entire
+	 * names_cache allocation for the pathname, and re-do the copy from
+	 * userland.
+	 */
+	if (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) {
+		kname = (char *)result;
+
+		result = kzalloc(sizeof(*result), GFP_KERNEL);
+		if (!result) {
+			err = ERR_PTR(-ENOMEM);
+			result = (struct filename *)kname;
+			goto error;
+		}
+		result->name = kname;
+		result->separate = true;
+		max = PATH_MAX;
+		goto recopy;
+	}
 
 	/* The empty path is special. */
 	if (unlikely(!len)) {
@@ -140,30 +192,32 @@ static char *getname_flags(const char __user *filename, int flags, int *empty)
 	}
 
 	err = ERR_PTR(-ENAMETOOLONG);
-	if (likely(len < PATH_MAX)) {
-		audit_getname(result);
-		return result;
-	}
+	if (unlikely(len >= PATH_MAX))
+		goto error;
+
+	result->uptr = filename;
+	audit_getname(result);
+	return result;
 
 error:
-	__putname(result);
+	final_putname(result);
 	return err;
 }
 
-char *getname(const char __user * filename)
+struct filename *
+getname(const char __user * filename)
 {
 	return getname_flags(filename, 0, NULL);
 }
+EXPORT_SYMBOL(getname);
 
 #ifdef CONFIG_AUDITSYSCALL
-void putname(const char *name)
+void putname(struct filename *name)
 {
 	if (unlikely(!audit_dummy_context()))
-		audit_putname(name);
-	else
-		__putname(name);
+		return audit_putname(name);
+	final_putname(name);
 }
-EXPORT_SYMBOL(putname);
 #endif
 
 static int check_acl(struct inode *inode, int mask)
@@ -651,8 +705,8 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki
 	path_put(link);
 }
 
-int sysctl_protected_symlinks __read_mostly = 1;
-int sysctl_protected_hardlinks __read_mostly = 1;
+int sysctl_protected_symlinks __read_mostly = 0;
+int sysctl_protected_hardlinks __read_mostly = 0;
 
 /**
  * may_follow_link - Check symlink following for unsafe situations
@@ -692,9 +746,9 @@ static inline int may_follow_link(struct path *link, struct nameidata *nd)
 	if (uid_eq(parent->i_uid, inode->i_uid))
 		return 0;
 
+	audit_log_link_denied("follow_link", link);
 	path_put_conditional(link, nd);
 	path_put(&nd->path);
-	audit_log_link_denied("follow_link", link);
 	return -EACCES;
 }
 
@@ -810,6 +864,7 @@ follow_link(struct path *link, struct nameidata *nd, void **p)
 	return error;
 
 out_put_nd_path:
+	*p = NULL;
 	path_put(&nd->path);
 	path_put(link);
 	return error;
@@ -1962,24 +2017,29 @@ static int path_lookupat(int dfd, const char *name,
 	return err;
 }
 
-static int do_path_lookup(int dfd, const char *name,
+static int filename_lookup(int dfd, struct filename *name,
 				unsigned int flags, struct nameidata *nd)
 {
-	int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+	int retval = path_lookupat(dfd, name->name, flags | LOOKUP_RCU, nd);
 	if (unlikely(retval == -ECHILD))
-		retval = path_lookupat(dfd, name, flags, nd);
+		retval = path_lookupat(dfd, name->name, flags, nd);
 	if (unlikely(retval == -ESTALE))
-		retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
+		retval = path_lookupat(dfd, name->name,
+						flags | LOOKUP_REVAL, nd);
 
-	if (likely(!retval)) {
-		if (unlikely(!audit_dummy_context())) {
-			if (nd->path.dentry && nd->inode)
-				audit_inode(name, nd->path.dentry);
-		}
-	}
+	if (likely(!retval))
+		audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
 	return retval;
 }
 
+static int do_path_lookup(int dfd, const char *name,
+				unsigned int flags, struct nameidata *nd)
+{
+	struct filename filename = { .name = name };
+
+	return filename_lookup(dfd, &filename, flags, nd);
+}
+
 /* does lookup, returns the object with parent locked */
 struct dentry *kern_path_locked(const char *name, struct path *path)
 {
@@ -2097,13 +2157,13 @@ int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
 	struct nameidata nd;
-	char *tmp = getname_flags(name, flags, empty);
+	struct filename *tmp = getname_flags(name, flags, empty);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
 		BUG_ON(flags & LOOKUP_PARENT);
 
-		err = do_path_lookup(dfd, tmp, flags, &nd);
+		err = filename_lookup(dfd, tmp, flags, &nd);
 		putname(tmp);
 		if (!err)
 			*path = nd.path;
@@ -2117,22 +2177,28 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 	return user_path_at_empty(dfd, name, flags, path, NULL);
 }
 
-static int user_path_parent(int dfd, const char __user *path,
-			struct nameidata *nd, char **name)
+/*
+ * NB: most callers don't do anything directly with the reference to the
+ *     to struct filename, but the nd->last pointer points into the name string
+ *     allocated by getname. So we must hold the reference to it until all
+ *     path-walking is complete.
+ */
+static struct filename *
+user_path_parent(int dfd, const char __user *path, struct nameidata *nd)
 {
-	char *s = getname(path);
+	struct filename *s = getname(path);
 	int error;
 
 	if (IS_ERR(s))
-		return PTR_ERR(s);
+		return s;
 
-	error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd);
-	if (error)
+	error = filename_lookup(dfd, s, LOOKUP_PARENT, nd);
+	if (error) {
 		putname(s);
-	else
-		*name = s;
+		return ERR_PTR(error);
+	}
 
-	return error;
+	return s;
 }
 
 /*
@@ -2179,7 +2245,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
 		return -ENOENT;
 
 	BUG_ON(victim->d_parent->d_inode != dir);
-	audit_inode_child(victim, dir);
+	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
 	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
 	if (error)
@@ -2624,7 +2690,7 @@ out_dput:
  */
 static int do_last(struct nameidata *nd, struct path *path,
 		   struct file *file, const struct open_flags *op,
-		   int *opened, const char *pathname)
+		   int *opened, struct filename *name)
 {
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
@@ -2651,7 +2717,7 @@ static int do_last(struct nameidata *nd, struct path *path,
 		error = complete_walk(nd);
 		if (error)
 			return error;
-		audit_inode(pathname, nd->path.dentry);
+		audit_inode(name, nd->path.dentry, 0);
 		if (open_flag & O_CREAT) {
 			error = -EISDIR;
 			goto out;
@@ -2661,7 +2727,7 @@ static int do_last(struct nameidata *nd, struct path *path,
 		error = complete_walk(nd);
 		if (error)
 			return error;
-		audit_inode(pathname, dir);
+		audit_inode(name, dir, 0);
 		goto finish_open;
 	}
 
@@ -2690,7 +2756,7 @@ static int do_last(struct nameidata *nd, struct path *path,
 		if (error)
 			return error;
 
-		audit_inode(pathname, dir);
+		audit_inode(name, dir, 0);
 		error = -EISDIR;
 		/* trailing slashes? */
 		if (nd->last.name[nd->last.len])
@@ -2720,7 +2786,7 @@ retry_lookup:
 		    !S_ISREG(file->f_path.dentry->d_inode->i_mode))
 			will_truncate = false;
 
-		audit_inode(pathname, file->f_path.dentry);
+		audit_inode(name, file->f_path.dentry, 0);
 		goto opened;
 	}
 
@@ -2737,7 +2803,7 @@ retry_lookup:
 	 * create/update audit record if it already exists.
 	 */
 	if (path->dentry->d_inode)
-		audit_inode(pathname, path->dentry);
+		audit_inode(name, path->dentry, 0);
 
 	/*
 	 * If atomic_open() acquired write access it is dropped now due to
@@ -2802,7 +2868,7 @@ finish_lookup:
 	error = -ENOTDIR;
 	if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup)
 		goto out;
-	audit_inode(pathname, nd->path.dentry);
+	audit_inode(name, nd->path.dentry, 0);
 finish_open:
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = false;
@@ -2870,7 +2936,7 @@ stale_open:
 	goto retry_lookup;
 }
 
-static struct file *path_openat(int dfd, const char *pathname,
+static struct file *path_openat(int dfd, struct filename *pathname,
 		struct nameidata *nd, const struct open_flags *op, int flags)
 {
 	struct file *base = NULL;
@@ -2885,12 +2951,12 @@ static struct file *path_openat(int dfd, const char *pathname,
 
 	file->f_flags = op->open_flag;
 
-	error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
+	error = path_init(dfd, pathname->name, flags | LOOKUP_PARENT, nd, &base);
 	if (unlikely(error))
 		goto out;
 
 	current->total_link_count = 0;
-	error = link_path_walk(pathname, nd);
+	error = link_path_walk(pathname->name, nd);
 	if (unlikely(error))
 		goto out;
 
@@ -2936,7 +3002,7 @@ out:
 	return file;
 }
 
-struct file *do_filp_open(int dfd, const char *pathname,
+struct file *do_filp_open(int dfd, struct filename *pathname,
 		const struct open_flags *op, int flags)
 {
 	struct nameidata nd;
@@ -2955,6 +3021,7 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 {
 	struct nameidata nd;
 	struct file *file;
+	struct filename filename = { .name = name };
 
 	nd.root.mnt = mnt;
 	nd.root.dentry = dentry;
@@ -2964,11 +3031,11 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
 		return ERR_PTR(-ELOOP);
 
-	file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU);
+	file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_RCU);
 	if (unlikely(file == ERR_PTR(-ECHILD)))
-		file = path_openat(-1, name, &nd, op, flags);
+		file = path_openat(-1, &filename, &nd, op, flags);
 	if (unlikely(file == ERR_PTR(-ESTALE)))
-		file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL);
+		file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_REVAL);
 	return file;
 }
 
@@ -3043,11 +3110,11 @@ EXPORT_SYMBOL(done_path_create);
 
 struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir)
 {
-	char *tmp = getname(pathname);
+	struct filename *tmp = getname(pathname);
 	struct dentry *res;
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	res = kern_path_create(dfd, tmp, path, is_dir);
+	res = kern_path_create(dfd, tmp->name, path, is_dir);
 	putname(tmp);
 	return res;
 }
@@ -3252,13 +3319,13 @@ out:
 static long do_rmdir(int dfd, const char __user *pathname)
 {
 	int error = 0;
-	char * name;
+	struct filename *name;
 	struct dentry *dentry;
 	struct nameidata nd;
 
-	error = user_path_parent(dfd, pathname, &nd, &name);
-	if (error)
-		return error;
+	name = user_path_parent(dfd, pathname, &nd);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 
 	switch(nd.last_type) {
 	case LAST_DOTDOT:
@@ -3347,14 +3414,14 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
 static long do_unlinkat(int dfd, const char __user *pathname)
 {
 	int error;
-	char *name;
+	struct filename *name;
 	struct dentry *dentry;
 	struct nameidata nd;
 	struct inode *inode = NULL;
 
-	error = user_path_parent(dfd, pathname, &nd, &name);
-	if (error)
-		return error;
+	name = user_path_parent(dfd, pathname, &nd);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 
 	error = -EISDIR;
 	if (nd.last_type != LAST_NORM)
@@ -3438,7 +3505,7 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 		int, newdfd, const char __user *, newname)
 {
 	int error;
-	char *from;
+	struct filename *from;
 	struct dentry *dentry;
 	struct path path;
 
@@ -3451,9 +3518,9 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 	if (IS_ERR(dentry))
 		goto out_putname;
 
-	error = security_path_symlink(&path, dentry, from);
+	error = security_path_symlink(&path, dentry, from->name);
 	if (!error)
-		error = vfs_symlink(path.dentry->d_inode, dentry, from);
+		error = vfs_symlink(path.dentry->d_inode, dentry, from->name);
 	done_path_create(&path, dentry);
 out_putname:
 	putname(from);
@@ -3733,17 +3800,21 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	struct dentry *old_dentry, *new_dentry;
 	struct dentry *trap;
 	struct nameidata oldnd, newnd;
-	char *from;
-	char *to;
+	struct filename *from;
+	struct filename *to;
 	int error;
 
-	error = user_path_parent(olddfd, oldname, &oldnd, &from);
-	if (error)
+	from = user_path_parent(olddfd, oldname, &oldnd);
+	if (IS_ERR(from)) {
+		error = PTR_ERR(from);
 		goto exit;
+	}
 
-	error = user_path_parent(newdfd, newname, &newnd, &to);
-	if (error)
+	to = user_path_parent(newdfd, newname, &newnd);
+	if (IS_ERR(to)) {
+		error = PTR_ERR(to);
 		goto exit1;
+	}
 
 	error = -EXDEV;
 	if (oldnd.path.mnt != newnd.path.mnt)
@@ -3967,7 +4038,6 @@ EXPORT_SYMBOL(follow_down_one);
 EXPORT_SYMBOL(follow_down);
 EXPORT_SYMBOL(follow_up);
 EXPORT_SYMBOL(get_write_access); /* nfsd */
-EXPORT_SYMBOL(getname);
 EXPORT_SYMBOL(lock_rename);
 EXPORT_SYMBOL(lookup_one_len);
 EXPORT_SYMBOL(page_follow_link_light);
diff --git a/fs/namespace.c b/fs/namespace.c
index 7bdf7907413f..24960626bb6b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1640,7 +1640,7 @@ static int do_change_type(struct path *path, int flag)
 /*
  * do loopback mount.
  */
-static int do_loopback(struct path *path, char *old_name,
+static int do_loopback(struct path *path, const char *old_name,
 				int recurse)
 {
 	LIST_HEAD(umount_list);
@@ -1764,7 +1764,7 @@ static inline int tree_contains_unbindable(struct mount *mnt)
 	return 0;
 }
 
-static int do_move_mount(struct path *path, char *old_name)
+static int do_move_mount(struct path *path, const char *old_name)
 {
 	struct path old_path, parent_path;
 	struct mount *p;
@@ -1917,8 +1917,8 @@ unlock:
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
  */
-static int do_new_mount(struct path *path, char *type, int flags,
-			int mnt_flags, char *name, void *data)
+static int do_new_mount(struct path *path, const char *type, int flags,
+			int mnt_flags, const char *name, void *data)
 {
 	struct vfsmount *mnt;
 	int err;
@@ -2191,8 +2191,8 @@ int copy_mount_string(const void __user *data, char **where)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-long do_mount(char *dev_name, char *dir_name, char *type_page,
-		  unsigned long flags, void *data_page)
+long do_mount(const char *dev_name, const char *dir_name,
+		const char *type_page, unsigned long flags, void *data_page)
 {
 	struct path path;
 	int retval = 0;
@@ -2408,7 +2408,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 {
 	int ret;
 	char *kernel_type;
-	char *kernel_dir;
+	struct filename *kernel_dir;
 	char *kernel_dev;
 	unsigned long data_page;
 
@@ -2430,7 +2430,7 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 	if (ret < 0)
 		goto out_data;
 
-	ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags,
+	ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags,
 		(void *) data_page);
 
 	free_page(data_page);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index db7ad719628a..13ca196385f5 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -95,8 +95,8 @@ config NFS_SWAP
 	  This option enables swapon to work on files located on NFS mounts.
 
 config NFS_V4_1
-	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
-	depends on NFS_V4 && EXPERIMENTAL
+	bool "NFS client support for NFSv4.1"
+	depends on NFS_V4
 	select SUNRPC_BACKCHANNEL
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index dd392ed5f2e2..f1027b06a1a9 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -37,6 +37,7 @@
 #include <linux/bio.h>		/* struct bio */
 #include <linux/buffer_head.h>	/* various write calls */
 #include <linux/prefetch.h>
+#include <linux/pagevec.h>
 
 #include "../pnfs.h"
 #include "../internal.h"
@@ -162,25 +163,39 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
 	return bio;
 }
 
-static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
+static struct bio *do_add_page_to_bio(struct bio *bio, int npg, int rw,
 				      sector_t isect, struct page *page,
 				      struct pnfs_block_extent *be,
 				      void (*end_io)(struct bio *, int err),
-				      struct parallel_io *par)
+				      struct parallel_io *par,
+				      unsigned int offset, int len)
 {
+	isect = isect + (offset >> SECTOR_SHIFT);
+	dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
+		npg, rw, (unsigned long long)isect, offset, len);
 retry:
 	if (!bio) {
 		bio = bl_alloc_init_bio(npg, isect, be, end_io, par);
 		if (!bio)
 			return ERR_PTR(-ENOMEM);
 	}
-	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+	if (bio_add_page(bio, page, len, offset) < len) {
 		bio = bl_submit_bio(rw, bio);
 		goto retry;
 	}
 	return bio;
 }
 
+static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
+				      sector_t isect, struct page *page,
+				      struct pnfs_block_extent *be,
+				      void (*end_io)(struct bio *, int err),
+				      struct parallel_io *par)
+{
+	return do_add_page_to_bio(bio, npg, rw, isect, page, be,
+				  end_io, par, 0, PAGE_CACHE_SIZE);
+}
+
 /* This is basically copied from mpage_end_io_read */
 static void bl_end_io_read(struct bio *bio, int err)
 {
@@ -228,14 +243,6 @@ bl_end_par_io_read(void *data, int unused)
 	schedule_work(&rdata->task.u.tk_work);
 }
 
-static bool
-bl_check_alignment(u64 offset, u32 len, unsigned long blkmask)
-{
-	if ((offset & blkmask) || (len & blkmask))
-		return false;
-	return true;
-}
-
 static enum pnfs_try_status
 bl_read_pagelist(struct nfs_read_data *rdata)
 {
@@ -246,15 +253,15 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 	sector_t isect, extent_length = 0;
 	struct parallel_io *par;
 	loff_t f_offset = rdata->args.offset;
+	size_t bytes_left = rdata->args.count;
+	unsigned int pg_offset, pg_len;
 	struct page **pages = rdata->args.pages;
 	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
+	const bool is_dio = (header->dreq != NULL);
 
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
 	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
 
-	if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK))
-		goto use_mds;
-
 	par = alloc_parallel(rdata);
 	if (!par)
 		goto use_mds;
@@ -284,36 +291,53 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 				extent_length = min(extent_length, cow_length);
 			}
 		}
+
+		if (is_dio) {
+			pg_offset = f_offset & ~PAGE_CACHE_MASK;
+			if (pg_offset + bytes_left > PAGE_CACHE_SIZE)
+				pg_len = PAGE_CACHE_SIZE - pg_offset;
+			else
+				pg_len = bytes_left;
+
+			f_offset += pg_len;
+			bytes_left -= pg_len;
+			isect += (pg_offset >> SECTOR_SHIFT);
+		} else {
+			pg_offset = 0;
+			pg_len = PAGE_CACHE_SIZE;
+		}
+
 		hole = is_hole(be, isect);
 		if (hole && !cow_read) {
 			bio = bl_submit_bio(READ, bio);
 			/* Fill hole w/ zeroes w/o accessing device */
 			dprintk("%s Zeroing page for hole\n", __func__);
-			zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
+			zero_user_segment(pages[i], pg_offset, pg_len);
 			print_page(pages[i]);
 			SetPageUptodate(pages[i]);
 		} else {
 			struct pnfs_block_extent *be_read;
 
 			be_read = (hole && cow_read) ? cow_read : be;
-			bio = bl_add_page_to_bio(bio, rdata->pages.npages - i,
+			bio = do_add_page_to_bio(bio, rdata->pages.npages - i,
 						 READ,
 						 isect, pages[i], be_read,
-						 bl_end_io_read, par);
+						 bl_end_io_read, par,
+						 pg_offset, pg_len);
 			if (IS_ERR(bio)) {
 				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
 				goto out;
 			}
 		}
-		isect += PAGE_CACHE_SECTORS;
+		isect += (pg_len >> SECTOR_SHIFT);
 		extent_length -= PAGE_CACHE_SECTORS;
 	}
 	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
 		rdata->res.eof = 1;
-		rdata->res.count = header->inode->i_size - f_offset;
+		rdata->res.count = header->inode->i_size - rdata->args.offset;
 	} else {
-		rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
+		rdata->res.count = (isect << SECTOR_SHIFT) - rdata->args.offset;
 	}
 out:
 	bl_put_extent(be);
@@ -461,6 +485,106 @@ map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be)
 	return;
 }
 
+static void
+bl_read_single_end_io(struct bio *bio, int error)
+{
+	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+	struct page *page = bvec->bv_page;
+
+	/* Only one page in bvec */
+	unlock_page(page);
+}
+
+static int
+bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
+		    unsigned int offset, unsigned int len)
+{
+	struct bio *bio;
+	struct page *shadow_page;
+	sector_t isect;
+	char *kaddr, *kshadow_addr;
+	int ret = 0;
+
+	dprintk("%s: offset %u len %u\n", __func__, offset, len);
+
+	shadow_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+	if (shadow_page == NULL)
+		return -ENOMEM;
+
+	bio = bio_alloc(GFP_NOIO, 1);
+	if (bio == NULL)
+		return -ENOMEM;
+
+	isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
+		(offset / SECTOR_SIZE);
+
+	bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+	bio->bi_bdev = be->be_mdev;
+	bio->bi_end_io = bl_read_single_end_io;
+
+	lock_page(shadow_page);
+	if (bio_add_page(bio, shadow_page,
+			 SECTOR_SIZE, round_down(offset, SECTOR_SIZE)) == 0) {
+		unlock_page(shadow_page);
+		bio_put(bio);
+		return -EIO;
+	}
+
+	submit_bio(READ, bio);
+	wait_on_page_locked(shadow_page);
+	if (unlikely(!test_bit(BIO_UPTODATE, &bio->bi_flags))) {
+		ret = -EIO;
+	} else {
+		kaddr = kmap_atomic(page);
+		kshadow_addr = kmap_atomic(shadow_page);
+		memcpy(kaddr + offset, kshadow_addr + offset, len);
+		kunmap_atomic(kshadow_addr);
+		kunmap_atomic(kaddr);
+	}
+	__free_page(shadow_page);
+	bio_put(bio);
+
+	return ret;
+}
+
+static int
+bl_read_partial_page_sync(struct page *page, struct pnfs_block_extent *be,
+			  unsigned int dirty_offset, unsigned int dirty_len,
+			  bool full_page)
+{
+	int ret = 0;
+	unsigned int start, end;
+
+	if (full_page) {
+		start = 0;
+		end = PAGE_CACHE_SIZE;
+	} else {
+		start = round_down(dirty_offset, SECTOR_SIZE);
+		end = round_up(dirty_offset + dirty_len, SECTOR_SIZE);
+	}
+
+	dprintk("%s: offset %u len %d\n", __func__, dirty_offset, dirty_len);
+	if (!be) {
+		zero_user_segments(page, start, dirty_offset,
+				   dirty_offset + dirty_len, end);
+		if (start == 0 && end == PAGE_CACHE_SIZE &&
+		    trylock_page(page)) {
+			SetPageUptodate(page);
+			unlock_page(page);
+		}
+		return ret;
+	}
+
+	if (start != dirty_offset)
+		ret = bl_do_readpage_sync(page, be, start, dirty_offset - start);
+
+	if (!ret && (dirty_offset + dirty_len < end))
+		ret = bl_do_readpage_sync(page, be, dirty_offset + dirty_len,
+					  end - dirty_offset - dirty_len);
+
+	return ret;
+}
+
 /* Given an unmapped page, zero it or read in page for COW, page is locked
  * by caller.
  */
@@ -494,7 +618,6 @@ init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read)
 	SetPageUptodate(page);
 
 cleanup:
-	bl_put_extent(cow_read);
 	if (bh)
 		free_buffer_head(bh);
 	if (ret) {
@@ -566,6 +689,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	struct parallel_io *par = NULL;
 	loff_t offset = wdata->args.offset;
 	size_t count = wdata->args.count;
+	unsigned int pg_offset, pg_len, saved_len;
 	struct page **pages = wdata->args.pages;
 	struct page *page;
 	pgoff_t index;
@@ -574,10 +698,13 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
-	/* Check for alignment first */
-	if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK))
-		goto out_mds;
 
+	if (header->dreq != NULL &&
+	    (!IS_ALIGNED(offset, NFS_SERVER(header->inode)->pnfs_blksize) ||
+	     !IS_ALIGNED(count, NFS_SERVER(header->inode)->pnfs_blksize))) {
+		dprintk("pnfsblock nonblock aligned DIO writes. Resend MDS\n");
+		goto out_mds;
+	}
 	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
 	 * We want to write each, and if there is an error set pnfs_error
 	 * to have it redone using nfs.
@@ -674,10 +801,11 @@ next_page:
 		if (!extent_length) {
 			/* We've used up the previous extent */
 			bl_put_extent(be);
+			bl_put_extent(cow_read);
 			bio = bl_submit_bio(WRITE, bio);
 			/* Get the next one */
 			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
-					     isect, NULL);
+					     isect, &cow_read);
 			if (!be || !is_writable(be, isect)) {
 				header->pnfs_error = -EINVAL;
 				goto out;
@@ -694,7 +822,26 @@ next_page:
 			extent_length = be->be_length -
 			    (isect - be->be_f_offset);
 		}
-		if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
+
+		dprintk("%s offset %lld count %Zu\n", __func__, offset, count);
+		pg_offset = offset & ~PAGE_CACHE_MASK;
+		if (pg_offset + count > PAGE_CACHE_SIZE)
+			pg_len = PAGE_CACHE_SIZE - pg_offset;
+		else
+			pg_len = count;
+
+		saved_len = pg_len;
+		if (be->be_state == PNFS_BLOCK_INVALID_DATA &&
+		    !bl_is_sector_init(be->be_inval, isect)) {
+			ret = bl_read_partial_page_sync(pages[i], cow_read,
+							pg_offset, pg_len, true);
+			if (ret) {
+				dprintk("%s bl_read_partial_page_sync fail %d\n",
+					__func__, ret);
+				header->pnfs_error = ret;
+				goto out;
+			}
+
 			ret = bl_mark_sectors_init(be->be_inval, isect,
 						       PAGE_CACHE_SECTORS);
 			if (unlikely(ret)) {
@@ -703,15 +850,35 @@ next_page:
 				header->pnfs_error = ret;
 				goto out;
 			}
+
+			/* Expand to full page write */
+			pg_offset = 0;
+			pg_len = PAGE_CACHE_SIZE;
+		} else if  ((pg_offset & (SECTOR_SIZE - 1)) ||
+			    (pg_len & (SECTOR_SIZE - 1))){
+			/* ahh, nasty case. We have to do sync full sector
+			 * read-modify-write cycles.
+			 */
+			unsigned int saved_offset = pg_offset;
+			ret = bl_read_partial_page_sync(pages[i], be, pg_offset,
+							pg_len, false);
+			pg_offset = round_down(pg_offset, SECTOR_SIZE);
+			pg_len = round_up(saved_offset + pg_len, SECTOR_SIZE)
+				 - pg_offset;
 		}
-		bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
+
+
+		bio = do_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
 					 isect, pages[i], be,
-					 bl_end_io_write, par);
+					 bl_end_io_write, par,
+					 pg_offset, pg_len);
 		if (IS_ERR(bio)) {
 			header->pnfs_error = PTR_ERR(bio);
 			bio = NULL;
 			goto out;
 		}
+		offset += saved_len;
+		count -= saved_len;
 		isect += PAGE_CACHE_SECTORS;
 		last_isect = isect;
 		extent_length -= PAGE_CACHE_SECTORS;
@@ -729,17 +896,16 @@ next_page:
 	}
 
 write_done:
-	wdata->res.count = (last_isect << SECTOR_SHIFT) - (offset);
-	if (count < wdata->res.count) {
-		wdata->res.count = count;
-	}
+	wdata->res.count = wdata->args.count;
 out:
 	bl_put_extent(be);
+	bl_put_extent(cow_read);
 	bl_submit_bio(WRITE, bio);
 	put_parallel(par);
 	return PNFS_ATTEMPTED;
 out_mds:
 	bl_put_extent(be);
+	bl_put_extent(cow_read);
 	kfree(par);
 	return PNFS_NOT_ATTEMPTED;
 }
@@ -874,7 +1040,7 @@ static void free_blk_mountid(struct block_mount_id *mid)
 	}
 }
 
-/* This is mostly copied from the filelayout's get_device_info function.
+/* This is mostly copied from the filelayout_get_device_info function.
  * It seems much of this should be at the generic pnfs level.
  */
 static struct pnfs_block_dev *
@@ -1011,33 +1177,95 @@ bl_clear_layoutdriver(struct nfs_server *server)
 	return 0;
 }
 
+static bool
+is_aligned_req(struct nfs_page *req, unsigned int alignment)
+{
+	return IS_ALIGNED(req->wb_offset, alignment) &&
+	       IS_ALIGNED(req->wb_bytes, alignment);
+}
+
 static void
 bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, SECTOR_SIZE))
 		nfs_pageio_reset_read_mds(pgio);
 	else
 		pnfs_generic_pg_init_read(pgio, req);
 }
 
+static bool
+bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		struct nfs_page *req)
+{
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, SECTOR_SIZE))
+		return false;
+
+	return pnfs_generic_pg_test(pgio, prev, req);
+}
+
+/*
+ * Return the number of contiguous bytes for a given inode
+ * starting at page frame idx.
+ */
+static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t end;
+
+	/* Optimize common case that writes from 0 to end of file */
+	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
+	if (end != NFS_I(inode)->npages) {
+		rcu_read_lock();
+		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		rcu_read_unlock();
+	}
+
+	if (!end)
+		return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT);
+	else
+		return (end - idx) << PAGE_CACHE_SHIFT;
+}
+
 static void
 bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
-	if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK))
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, PAGE_CACHE_SIZE)) {
 		nfs_pageio_reset_write_mds(pgio);
-	else
-		pnfs_generic_pg_init_write(pgio, req);
+	} else {
+		u64 wb_size;
+		if (pgio->pg_dreq == NULL)
+			wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
+						      req->wb_index);
+		else
+			wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+		pnfs_generic_pg_init_write(pgio, req, wb_size);
+	}
+}
+
+static bool
+bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+		 struct nfs_page *req)
+{
+	if (pgio->pg_dreq != NULL &&
+	    !is_aligned_req(req, PAGE_CACHE_SIZE))
+		return false;
+
+	return pnfs_generic_pg_test(pgio, prev, req);
 }
 
 static const struct nfs_pageio_ops bl_pg_read_ops = {
 	.pg_init = bl_pg_init_read,
-	.pg_test = pnfs_generic_pg_test,
+	.pg_test = bl_pg_test_read,
 	.pg_doio = pnfs_generic_pg_readpages,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
 	.pg_init = bl_pg_init_write,
-	.pg_test = pnfs_generic_pg_test,
+	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
 };
 
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 03350690118e..f4891bde8851 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -41,6 +41,7 @@
 
 #define PAGE_CACHE_SECTORS (PAGE_CACHE_SIZE >> SECTOR_SHIFT)
 #define PAGE_CACHE_SECTOR_SHIFT (PAGE_CACHE_SHIFT - SECTOR_SHIFT)
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
 
 struct block_mount_id {
 	spinlock_t			bm_lock;    /* protects list */
@@ -172,7 +173,6 @@ struct bl_msg_hdr {
 /* blocklayoutdev.c */
 ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
-struct block_device *nfs4_blkdev_get(dev_t dev);
 int nfs4_blkdev_put(struct block_device *bdev);
 struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
 						struct pnfs_device *dev);
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index c96554245ccf..a86c5bdad9e3 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -53,22 +53,6 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
 	return 0;
 }
 
-/* Open a block_device by device number. */
-struct block_device *nfs4_blkdev_get(dev_t dev)
-{
-	struct block_device *bd;
-
-	dprintk("%s enter\n", __func__);
-	bd = blkdev_get_by_dev(dev, FMODE_READ, NULL);
-	if (IS_ERR(bd))
-		goto fail;
-	return bd;
-fail:
-	dprintk("%s failed to open device : %ld\n",
-			__func__, PTR_ERR(bd));
-	return NULL;
-}
-
 /*
  * Release the block device
  */
@@ -172,11 +156,12 @@ nfs4_blk_decode_device(struct nfs_server *server,
 		goto out;
 	}
 
-	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
+	bd = blkdev_get_by_dev(MKDEV(reply->major, reply->minor),
+			       FMODE_READ, NULL);
 	if (IS_ERR(bd)) {
-		rc = PTR_ERR(bd);
-		dprintk("%s failed to open device : %d\n", __func__, rc);
-		rv = ERR_PTR(rc);
+		dprintk("%s failed to open device : %ld\n", __func__,
+			PTR_ERR(bd));
+		rv = ERR_CAST(bd);
 		goto out;
 	}
 
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 1f9a6032796b..9c3e117c3ed1 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -683,8 +683,7 @@ encode_pnfs_block_layoutupdate(struct pnfs_block_layout *bl,
 		p = xdr_encode_hyper(p, lce->bse_length << SECTOR_SHIFT);
 		p = xdr_encode_hyper(p, 0LL);
 		*p++ = cpu_to_be32(PNFS_BLOCK_READWRITE_DATA);
-		list_del(&lce->bse_node);
-		list_add_tail(&lce->bse_node, &bl->bl_committing);
+		list_move_tail(&lce->bse_node, &bl->bl_committing);
 		bl->bl_count--;
 		count++;
 	}
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 4c8459e5bdee..5088b57b078a 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -12,6 +12,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
+#include <linux/errno.h>
 #include <linux/mutex.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
@@ -23,6 +24,7 @@
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "internal.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
@@ -37,7 +39,32 @@ static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1];
 static DEFINE_MUTEX(nfs_callback_mutex);
 static struct svc_program nfs4_callback_program;
 
-unsigned short nfs_callback_tcpport6;
+static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net)
+{
+	int ret;
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	ret = svc_create_xprt(serv, "tcp", net, PF_INET,
+				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+	if (ret <= 0)
+		goto out_err;
+	nn->nfs_callback_tcpport = ret;
+	dprintk("NFS: Callback listener port = %u (af %u, net %p)\n",
+			nn->nfs_callback_tcpport, PF_INET, net);
+
+	ret = svc_create_xprt(serv, "tcp", net, PF_INET6,
+				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
+	if (ret > 0) {
+		nn->nfs_callback_tcpport6 = ret;
+		dprintk("NFS: Callback listener port = %u (af %u, net %p)\n",
+				nn->nfs_callback_tcpport6, PF_INET6, net);
+	} else if (ret != -EAFNOSUPPORT)
+		goto out_err;
+	return 0;
+
+out_err:
+	return (ret) ? ret : -ENOMEM;
+}
 
 /*
  * This is the NFSv4 callback kernel thread.
@@ -45,7 +72,7 @@ unsigned short nfs_callback_tcpport6;
 static int
 nfs4_callback_svc(void *vrqstp)
 {
-	int err, preverr = 0;
+	int err;
 	struct svc_rqst *rqstp = vrqstp;
 
 	set_freezable();
@@ -55,20 +82,8 @@ nfs4_callback_svc(void *vrqstp)
 		 * Listen for a request on the socket
 		 */
 		err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT);
-		if (err == -EAGAIN || err == -EINTR) {
-			preverr = err;
-			continue;
-		}
-		if (err < 0) {
-			if (err != preverr) {
-				printk(KERN_WARNING "NFS: %s: unexpected error "
-					"from svc_recv (%d)\n", __func__, err);
-				preverr = err;
-			}
-			schedule_timeout_uninterruptible(HZ);
+		if (err == -EAGAIN || err == -EINTR)
 			continue;
-		}
-		preverr = err;
 		svc_process(rqstp);
 	}
 	return 0;
@@ -78,38 +93,23 @@ nfs4_callback_svc(void *vrqstp)
  * Prepare to bring up the NFSv4 callback service
  */
 static struct svc_rqst *
-nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
+nfs4_callback_up(struct svc_serv *serv)
 {
-	int ret;
-
-	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
-				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
-	if (ret <= 0)
-		goto out_err;
-	nfs_callback_tcpport = ret;
-	dprintk("NFS: Callback listener port = %u (af %u)\n",
-			nfs_callback_tcpport, PF_INET);
-
-	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
-				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
-	if (ret > 0) {
-		nfs_callback_tcpport6 = ret;
-		dprintk("NFS: Callback listener port = %u (af %u)\n",
-				nfs_callback_tcpport6, PF_INET6);
-	} else if (ret == -EAFNOSUPPORT)
-		ret = 0;
-	else
-		goto out_err;
-
 	return svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE);
-
-out_err:
-	if (ret == 0)
-		ret = -ENOMEM;
-	return ERR_PTR(ret);
 }
 
 #if defined(CONFIG_NFS_V4_1)
+static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
+{
+	/*
+	 * Create an svc_sock for the back channel service that shares the
+	 * fore channel connection.
+	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
+	 */
+	return svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0,
+			      SVC_SOCK_ANONYMOUS);
+}
+
 /*
  * The callback service for NFSv4.1 callbacks
  */
@@ -149,28 +149,9 @@ nfs41_callback_svc(void *vrqstp)
  * Bring up the NFSv4.1 callback service
  */
 static struct svc_rqst *
-nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
+nfs41_callback_up(struct svc_serv *serv)
 {
 	struct svc_rqst *rqstp;
-	int ret;
-
-	/*
-	 * Create an svc_sock for the back channel service that shares the
-	 * fore channel connection.
-	 * Returns the input port (0) and sets the svc_serv bc_xprt on success
-	 */
-	ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0,
-			      SVC_SOCK_ANONYMOUS);
-	if (ret < 0) {
-		rqstp = ERR_PTR(ret);
-		goto out;
-	}
-
-	/*
-	 * Save the svc_serv in the transport so that it can
-	 * be referenced when the session backchannel is initialized
-	 */
-	xprt->bc_serv = serv;
 
 	INIT_LIST_HEAD(&serv->sv_cb_list);
 	spin_lock_init(&serv->sv_cb_lock);
@@ -180,90 +161,74 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt)
 		svc_xprt_put(serv->sv_bc_xprt);
 		serv->sv_bc_xprt = NULL;
 	}
-out:
 	dprintk("--> %s return %ld\n", __func__,
 		IS_ERR(rqstp) ? PTR_ERR(rqstp) : 0);
 	return rqstp;
 }
 
-static inline int nfs_minorversion_callback_svc_setup(u32 minorversion,
-		struct svc_serv *serv, struct rpc_xprt *xprt,
+static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv,
 		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
 {
-	if (minorversion) {
-		*rqstpp = nfs41_callback_up(serv, xprt);
-		*callback_svc = nfs41_callback_svc;
-	}
-	return minorversion;
+	*rqstpp = nfs41_callback_up(serv);
+	*callback_svc = nfs41_callback_svc;
 }
 
 static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
-		struct nfs_callback_data *cb_info)
+		struct svc_serv *serv)
 {
 	if (minorversion)
-		xprt->bc_serv = cb_info->serv;
+		/*
+		 * Save the svc_serv in the transport so that it can
+		 * be referenced when the session backchannel is initialized
+		 */
+		xprt->bc_serv = serv;
 }
 #else
-static inline int nfs_minorversion_callback_svc_setup(u32 minorversion,
-		struct svc_serv *serv, struct rpc_xprt *xprt,
-		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
+static int nfs41_callback_up_net(struct svc_serv *serv, struct net *net)
 {
 	return 0;
 }
 
+static void nfs_minorversion_callback_svc_setup(struct svc_serv *serv,
+		struct svc_rqst **rqstpp, int (**callback_svc)(void *vrqstp))
+{
+	*rqstpp = ERR_PTR(-ENOTSUPP);
+	*callback_svc = ERR_PTR(-ENOTSUPP);
+}
+
 static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
-		struct nfs_callback_data *cb_info)
+		struct svc_serv *serv)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-/*
- * Bring up the callback thread if it is not already up.
- */
-int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
+static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt,
+				  struct svc_serv *serv)
 {
-	struct svc_serv *serv = NULL;
 	struct svc_rqst *rqstp;
 	int (*callback_svc)(void *vrqstp);
 	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
 	char svc_name[12];
-	int ret = 0;
-	int minorversion_setup;
-	struct net *net = &init_net;
+	int ret;
 
-	mutex_lock(&nfs_callback_mutex);
-	if (cb_info->users++ || cb_info->task != NULL) {
-		nfs_callback_bc_serv(minorversion, xprt, cb_info);
-		goto out;
-	}
-	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
-	if (!serv) {
-		ret = -ENOMEM;
-		goto out_err;
-	}
-	/* As there is only one thread we need to over-ride the
-	 * default maximum of 80 connections
-	 */
-	serv->sv_maxconn = 1024;
+	nfs_callback_bc_serv(minorversion, xprt, serv);
 
-	ret = svc_bind(serv, net);
-	if (ret < 0) {
-		printk(KERN_WARNING "NFS: bind callback service failed\n");
-		goto out_err;
-	}
+	if (cb_info->task)
+		return 0;
 
-	minorversion_setup =  nfs_minorversion_callback_svc_setup(minorversion,
-					serv, xprt, &rqstp, &callback_svc);
-	if (!minorversion_setup) {
+	switch (minorversion) {
+	case 0:
 		/* v4.0 callback setup */
-		rqstp = nfs4_callback_up(serv, xprt);
+		rqstp = nfs4_callback_up(serv);
 		callback_svc = nfs4_callback_svc;
+		break;
+	default:
+		nfs_minorversion_callback_svc_setup(serv,
+				&rqstp, &callback_svc);
 	}
 
-	if (IS_ERR(rqstp)) {
-		ret = PTR_ERR(rqstp);
-		goto out_err;
-	}
+	if (IS_ERR(rqstp))
+		return PTR_ERR(rqstp);
 
 	svc_sock_update_bufs(serv);
 
@@ -276,41 +241,165 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
 		svc_exit_thread(cb_info->rqst);
 		cb_info->rqst = NULL;
 		cb_info->task = NULL;
-		goto out_err;
+		return ret;
+	}
+	dprintk("nfs_callback_up: service started\n");
+	return 0;
+}
+
+static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	if (--nn->cb_users[minorversion])
+		return;
+
+	dprintk("NFS: destroy per-net callback data; net=%p\n", net);
+	svc_shutdown_net(serv, net);
+}
+
+static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	int ret;
+
+	if (nn->cb_users[minorversion]++)
+		return 0;
+
+	dprintk("NFS: create per-net callback data; net=%p\n", net);
+
+	ret = svc_bind(serv, net);
+	if (ret < 0) {
+		printk(KERN_WARNING "NFS: bind callback service failed\n");
+		goto err_bind;
+	}
+
+	switch (minorversion) {
+		case 0:
+			ret = nfs4_callback_up_net(serv, net);
+			break;
+		case 1:
+			ret = nfs41_callback_up_net(serv, net);
+			break;
+		default:
+			printk(KERN_ERR "NFS: unknown callback version: %d\n",
+					minorversion);
+			ret = -EINVAL;
+			break;
+	}
+
+	if (ret < 0) {
+		printk(KERN_ERR "NFS: callback service start failed\n");
+		goto err_socks;
+	}
+	return 0;
+
+err_socks:
+	svc_rpcb_cleanup(serv, net);
+err_bind:
+	dprintk("NFS: Couldn't create callback socket: err = %d; "
+			"net = %p\n", ret, net);
+	return ret;
+}
+
+static struct svc_serv *nfs_callback_create_svc(int minorversion)
+{
+	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
+	struct svc_serv *serv;
+
+	/*
+	 * Check whether we're already up and running.
+	 */
+	if (cb_info->task) {
+		/*
+		 * Note: increase service usage, because later in case of error
+		 * svc_destroy() will be called.
+		 */
+		svc_get(cb_info->serv);
+		return cb_info->serv;
+	}
+
+	/*
+	 * Sanity check: if there's no task,
+	 * we should be the first user ...
+	 */
+	if (cb_info->users)
+		printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n",
+			cb_info->users);
+
+	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
+	if (!serv) {
+		printk(KERN_ERR "nfs_callback_create_svc: create service failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	/* As there is only one thread we need to over-ride the
+	 * default maximum of 80 connections
+	 */
+	serv->sv_maxconn = 1024;
+	dprintk("nfs_callback_create_svc: service created\n");
+	return serv;
+}
+
+/*
+ * Bring up the callback thread if it is not already up.
+ */
+int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt)
+{
+	struct svc_serv *serv;
+	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
+	int ret;
+	struct net *net = xprt->xprt_net;
+
+	mutex_lock(&nfs_callback_mutex);
+
+	serv = nfs_callback_create_svc(minorversion);
+	if (IS_ERR(serv)) {
+		ret = PTR_ERR(serv);
+		goto err_create;
 	}
-out:
+
+	ret = nfs_callback_up_net(minorversion, serv, net);
+	if (ret < 0)
+		goto err_net;
+
+	ret = nfs_callback_start_svc(minorversion, xprt, serv);
+	if (ret < 0)
+		goto err_start;
+
+	cb_info->users++;
 	/*
 	 * svc_create creates the svc_serv with sv_nrthreads == 1, and then
 	 * svc_prepare_thread increments that. So we need to call svc_destroy
 	 * on both success and failure so that the refcount is 1 when the
 	 * thread exits.
 	 */
-	if (serv)
-		svc_destroy(serv);
+err_net:
+	svc_destroy(serv);
+err_create:
 	mutex_unlock(&nfs_callback_mutex);
 	return ret;
-out_err:
-	dprintk("NFS: Couldn't create callback socket or server thread; "
-		"err = %d\n", ret);
-	cb_info->users--;
-	if (serv)
-		svc_shutdown_net(serv, net);
-	goto out;
+
+err_start:
+	nfs_callback_down_net(minorversion, serv, net);
+	dprintk("NFS: Couldn't create server thread; err = %d\n", ret);
+	goto err_net;
 }
 
 /*
  * Kill the callback thread if it's no longer being used.
  */
-void nfs_callback_down(int minorversion)
+void nfs_callback_down(int minorversion, struct net *net)
 {
 	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
 
 	mutex_lock(&nfs_callback_mutex);
+	nfs_callback_down_net(minorversion, cb_info->serv, net);
 	cb_info->users--;
 	if (cb_info->users == 0 && cb_info->task != NULL) {
 		kthread_stop(cb_info->task);
-		svc_shutdown_net(cb_info->serv, &init_net);
+		dprintk("nfs_callback_down: service stopped\n");
 		svc_exit_thread(cb_info->rqst);
+		dprintk("nfs_callback_down: service destroyed\n");
 		cb_info->serv = NULL;
 		cb_info->rqst = NULL;
 		cb_info->task = NULL;
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index b44d7b128b71..4251c2ae06ad 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -194,7 +194,7 @@ extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
 				   struct cb_process_state *cps);
 #if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
-extern void nfs_callback_down(int minorversion);
+extern void nfs_callback_down(int minorversion, struct net *net);
 extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation,
 					    const nfs4_stateid *stateid);
 extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
@@ -209,6 +209,5 @@ extern int nfs4_set_callback_sessionid(struct nfs_client *clp);
 
 extern unsigned int nfs_callback_set_tcpport;
 extern unsigned short nfs_callback_tcpport;
-extern unsigned short nfs_callback_tcpport6;
 
 #endif /* __LINUX_FS_NFS_CALLBACK_H */
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 1b5d809a105e..76b4a7a3e559 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -122,7 +122,15 @@ static struct pnfs_layout_hdr * get_layout_by_fh_locked(struct nfs_client *clp,
 			ino = igrab(lo->plh_inode);
 			if (!ino)
 				continue;
-			get_layout_hdr(lo);
+			spin_lock(&ino->i_lock);
+			/* Is this layout in the process of being freed? */
+			if (NFS_I(ino)->layout != lo) {
+				spin_unlock(&ino->i_lock);
+				iput(ino);
+				continue;
+			}
+			pnfs_get_layout_hdr(lo);
+			spin_unlock(&ino->i_lock);
 			return lo;
 		}
 	}
@@ -158,7 +166,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	ino = lo->plh_inode;
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
-	    mark_matching_lsegs_invalid(lo, &free_me_list,
+	    pnfs_mark_matching_lsegs_invalid(lo, &free_me_list,
 					&args->cbl_range))
 		rv = NFS4ERR_DELAY;
 	else
@@ -166,7 +174,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	pnfs_set_layout_stateid(lo, &args->cbl_stateid, true);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&free_me_list);
-	put_layout_hdr(lo);
+	pnfs_put_layout_hdr(lo);
 	iput(ino);
 	return rv;
 }
@@ -196,9 +204,18 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 			continue;
 
 		list_for_each_entry(lo, &server->layouts, plh_layouts) {
-			if (!igrab(lo->plh_inode))
+			ino = igrab(lo->plh_inode);
+			if (ino)
+				continue;
+			spin_lock(&ino->i_lock);
+			/* Is this layout in the process of being freed? */
+			if (NFS_I(ino)->layout != lo) {
+				spin_unlock(&ino->i_lock);
+				iput(ino);
 				continue;
-			get_layout_hdr(lo);
+			}
+			pnfs_get_layout_hdr(lo);
+			spin_unlock(&ino->i_lock);
 			BUG_ON(!list_empty(&lo->plh_bulk_recall));
 			list_add(&lo->plh_bulk_recall, &recall_list);
 		}
@@ -211,12 +228,12 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 		ino = lo->plh_inode;
 		spin_lock(&ino->i_lock);
 		set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (mark_matching_lsegs_invalid(lo, &free_me_list, &range))
+		if (pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, &range))
 			rv = NFS4ERR_DELAY;
 		list_del_init(&lo->plh_bulk_recall);
 		spin_unlock(&ino->i_lock);
 		pnfs_free_lseg_list(&free_me_list);
-		put_layout_hdr(lo);
+		pnfs_put_layout_hdr(lo);
 		iput(ino);
 	}
 	return rv;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 99694442b93f..8b39a42ac35e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -93,10 +93,10 @@ static struct nfs_subversion *find_nfs_version(unsigned int version)
 			spin_unlock(&nfs_version_lock);
 			return nfs;
 		}
-	};
+	}
 
 	spin_unlock(&nfs_version_lock);
-	return ERR_PTR(-EPROTONOSUPPORT);;
+	return ERR_PTR(-EPROTONOSUPPORT);
 }
 
 struct nfs_subversion *get_nfs_version(unsigned int version)
@@ -498,7 +498,8 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 			return nfs_found_client(cl_init, clp);
 		}
 		if (new) {
-			list_add(&new->cl_share_link, &nn->nfs_client_list);
+			list_add_tail(&new->cl_share_link,
+					&nn->nfs_client_list);
 			spin_unlock(&nn->nfs_client_lock);
 			new->cl_flags = cl_init->init_flags;
 			return rpc_ops->init_client(new, timeparms, ip_addr,
@@ -668,7 +669,8 @@ int nfs_init_server_rpcclient(struct nfs_server *server,
 {
 	struct nfs_client *clp = server->nfs_client;
 
-	server->client = rpc_clone_client(clp->cl_rpcclient);
+	server->client = rpc_clone_client_set_auth(clp->cl_rpcclient,
+							pseudoflavour);
 	if (IS_ERR(server->client)) {
 		dprintk("%s: couldn't create rpc_client!\n", __func__);
 		return PTR_ERR(server->client);
@@ -678,16 +680,6 @@ int nfs_init_server_rpcclient(struct nfs_server *server,
 			timeo,
 			sizeof(server->client->cl_timeout_default));
 	server->client->cl_timeout = &server->client->cl_timeout_default;
-
-	if (pseudoflavour != clp->cl_rpcclient->cl_auth->au_flavor) {
-		struct rpc_auth *auth;
-
-		auth = rpcauth_create(pseudoflavour, server->client);
-		if (IS_ERR(auth)) {
-			dprintk("%s: couldn't create credcache!\n", __func__);
-			return PTR_ERR(auth);
-		}
-	}
 	server->client->cl_softrtry = 0;
 	if (server->flags & NFS_MOUNT_SOFT)
 		server->client->cl_softrtry = 1;
@@ -761,6 +753,8 @@ static int nfs_init_server(struct nfs_server *server,
 			data->timeo, data->retrans);
 	if (data->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+	if (server->options & NFS_OPTION_MIGRATION)
+		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX);
@@ -855,7 +849,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
 	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	server->pnfs_blksize = fsinfo->blksize;
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 627f108ede23..ce8cb926526b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2072,7 +2072,7 @@ found:
 	nfs_access_free_entry(entry);
 }
 
-static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 {
 	struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
 	if (cache == NULL)
@@ -2098,6 +2098,20 @@ static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *s
 		spin_unlock(&nfs_access_lru_lock);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_access_add_cache);
+
+void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
+{
+	entry->mask = 0;
+	if (access_result & NFS4_ACCESS_READ)
+		entry->mask |= MAY_READ;
+	if (access_result &
+	    (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
+		entry->mask |= MAY_WRITE;
+	if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
+		entry->mask |= MAY_EXEC;
+}
+EXPORT_SYMBOL_GPL(nfs_access_set_mask);
 
 static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 {
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 1ba385b7c90d..cae26cbd59ee 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -46,6 +46,7 @@
 #include <linux/kref.h>
 #include <linux/slab.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/module.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
@@ -78,6 +79,7 @@ struct nfs_direct_req {
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
 	ssize_t			count,		/* bytes actually processed */
+				bytes_left,	/* bytes left to be sent */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
@@ -190,6 +192,12 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq)
 	kref_put(&dreq->kref, nfs_direct_req_free);
 }
 
+ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq)
+{
+	return dreq->bytes_left;
+}
+EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left);
+
 /*
  * Collects and returns the final error value/byte-count.
  */
@@ -390,6 +398,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 			user_addr += req_len;
 			pos += req_len;
 			count -= req_len;
+			dreq->bytes_left -= req_len;
 		}
 		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
@@ -450,23 +459,28 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
+	struct nfs_lock_context *l_ctx;
 
 	dreq = nfs_direct_req_alloc();
 	if (dreq == NULL)
 		goto out;
 
 	dreq->inode = inode;
+	dreq->bytes_left = iov_length(iov, nr_segs);
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
-	dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
-	if (dreq->l_ctx == NULL)
+	l_ctx = nfs_get_lock_context(dreq->ctx);
+	if (IS_ERR(l_ctx)) {
+		result = PTR_ERR(l_ctx);
 		goto out_release;
+	}
+	dreq->l_ctx = l_ctx;
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
+	NFS_I(inode)->read_io += iov_length(iov, nr_segs);
 	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
 	if (!result)
 		result = nfs_direct_wait(dreq);
-	NFS_I(inode)->read_io += result;
 out_release:
 	nfs_direct_req_release(dreq);
 out:
@@ -706,6 +720,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
 			user_addr += req_len;
 			pos += req_len;
 			count -= req_len;
+			dreq->bytes_left -= req_len;
 		}
 		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
@@ -814,6 +829,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 	get_dreq(dreq);
 	atomic_inc(&inode->i_dio_count);
 
+	NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs);
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
 		result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
@@ -825,7 +841,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 		pos += vec->iov_len;
 	}
 	nfs_pageio_complete(&desc);
-	NFS_I(dreq->inode)->write_io += desc.pg_bytes_written;
 
 	/*
 	 * If no bytes were started, return the error, and let the
@@ -849,16 +864,21 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
+	struct nfs_lock_context *l_ctx;
 
 	dreq = nfs_direct_req_alloc();
 	if (!dreq)
 		goto out;
 
 	dreq->inode = inode;
+	dreq->bytes_left = count;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
-	dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
-	if (dreq->l_ctx == NULL)
+	l_ctx = nfs_get_lock_context(dreq->ctx);
+	if (IS_ERR(l_ctx)) {
+		result = PTR_ERR(l_ctx);
 		goto out_release;
+	}
+	dreq->l_ctx = l_ctx;
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index 31c26c4dcc23..ca4b11ec87a2 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -217,7 +217,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 {
 	char buf1[NFS_DNS_HOSTNAME_MAXLEN+1];
 	struct nfs_dns_ent key, *item;
-	unsigned long ttl;
+	unsigned int ttl;
 	ssize_t len;
 	int ret = -EINVAL;
 
@@ -240,7 +240,8 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 	key.namelen = len;
 	memset(&key.h, 0, sizeof(key.h));
 
-	ttl = get_expiry(&buf);
+	if (get_uint(&buf, &ttl) < 0)
+		goto out;
 	if (ttl == 0)
 		goto out;
 	key.h.expiry_time = ttl + seconds_since_boot();
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index f692be97676d..582bb8866131 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -259,7 +259,7 @@ nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 	struct dentry *dentry = file->f_path.dentry;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = dentry->d_inode;
-	int have_error, status;
+	int have_error, do_resend, status;
 	int ret = 0;
 
 	dprintk("NFS: fsync file(%s/%s) datasync %d\n",
@@ -267,15 +267,23 @@ nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync)
 			datasync);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
+	do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
 	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	status = nfs_commit_inode(inode, FLUSH_SYNC);
-	if (status >= 0 && ret < 0)
-		status = ret;
 	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
-	if (have_error)
+	if (have_error) {
 		ret = xchg(&ctx->error, 0);
-	if (!ret && status < 0)
+		if (ret)
+			goto out;
+	}
+	if (status < 0) {
 		ret = status;
+		goto out;
+	}
+	do_resend |= test_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags);
+	if (do_resend)
+		ret = -EAGAIN;
+out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nfs_file_fsync_commit);
@@ -286,13 +294,22 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct inode *inode = file->f_path.dentry->d_inode;
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret != 0)
-		goto out;
-	mutex_lock(&inode->i_mutex);
-	ret = nfs_file_fsync_commit(file, start, end, datasync);
-	mutex_unlock(&inode->i_mutex);
-out:
+	do {
+		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+		if (ret != 0)
+			break;
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_file_fsync_commit(file, start, end, datasync);
+		mutex_unlock(&inode->i_mutex);
+		/*
+		 * If nfs_file_fsync_commit detected a server reboot, then
+		 * resend all dirty pages that might have been covered by
+		 * the NFS_CONTEXT_RESEND_WRITES flag
+		 */
+		start = 0;
+		end = LLONG_MAX;
+	} while (ret == -EAGAIN);
+
 	return ret;
 }
 
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 4654ced096a6..033803c36644 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -32,6 +32,8 @@
 
 #include <asm/uaccess.h>
 
+#include "internal.h"
+
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 /*
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index a850079467d8..9cc4a3fbf4b0 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -55,18 +55,19 @@
 static const struct cred *id_resolver_cache;
 static struct key_type key_type_id_resolver_legacy;
 
-struct idmap {
-	struct rpc_pipe		*idmap_pipe;
-	struct key_construction	*idmap_key_cons;
-	struct mutex		idmap_mutex;
-};
-
 struct idmap_legacy_upcalldata {
 	struct rpc_pipe_msg pipe_msg;
 	struct idmap_msg idmap_msg;
+	struct key_construction	*key_cons;
 	struct idmap *idmap;
 };
 
+struct idmap {
+	struct rpc_pipe		*idmap_pipe;
+	struct idmap_legacy_upcalldata *idmap_upcall_data;
+	struct mutex		idmap_mutex;
+};
+
 /**
  * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields
  * @fattr: fully initialised struct nfs_fattr
@@ -158,7 +159,7 @@ static int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *re
 		return 0;
 	memcpy(buf, name, namelen);
 	buf[namelen] = '\0';
-	if (strict_strtoul(buf, 0, &val) != 0)
+	if (kstrtoul(buf, 0, &val) != 0)
 		return 0;
 	*res = val;
 	return 1;
@@ -330,7 +331,6 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
 		ret = nfs_idmap_request_key(&key_type_id_resolver_legacy,
 					    name, namelen, type, data,
 					    data_size, idmap);
-		idmap->idmap_key_cons = NULL;
 		mutex_unlock(&idmap->idmap_mutex);
 	}
 	return ret;
@@ -364,7 +364,7 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ
 	if (data_size <= 0) {
 		ret = -EINVAL;
 	} else {
-		ret = strict_strtol(id_str, 10, &id_long);
+		ret = kstrtol(id_str, 10, &id_long);
 		*id = (__u32)id_long;
 	}
 	return ret;
@@ -465,8 +465,6 @@ nfs_idmap_new(struct nfs_client *clp)
 	struct rpc_pipe *pipe;
 	int error;
 
-	BUG_ON(clp->cl_idmap != NULL);
-
 	idmap = kzalloc(sizeof(*idmap), GFP_KERNEL);
 	if (idmap == NULL)
 		return -ENOMEM;
@@ -510,7 +508,6 @@ static int __rpc_pipefs_event(struct nfs_client *clp, unsigned long event,
 
 	switch (event) {
 	case RPC_PIPEFS_MOUNT:
-		BUG_ON(clp->cl_rpcclient->cl_dentry == NULL);
 		err = __nfs_idmap_register(clp->cl_rpcclient->cl_dentry,
 						clp->cl_idmap,
 						clp->cl_idmap->idmap_pipe);
@@ -632,9 +629,6 @@ static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap,
 	substring_t substr;
 	int token, ret;
 
-	memset(im,  0, sizeof(*im));
-	memset(msg, 0, sizeof(*msg));
-
 	im->im_type = IDMAP_TYPE_GROUP;
 	token = match_token(desc, nfs_idmap_tokens, &substr);
 
@@ -665,6 +659,35 @@ out:
 	return ret;
 }
 
+static bool
+nfs_idmap_prepare_pipe_upcall(struct idmap *idmap,
+		struct idmap_legacy_upcalldata *data)
+{
+	if (idmap->idmap_upcall_data != NULL) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
+	idmap->idmap_upcall_data = data;
+	return true;
+}
+
+static void
+nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret)
+{
+	struct key_construction *cons = idmap->idmap_upcall_data->key_cons;
+
+	kfree(idmap->idmap_upcall_data);
+	idmap->idmap_upcall_data = NULL;
+	complete_request_key(cons, ret);
+}
+
+static void
+nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret)
+{
+	if (idmap->idmap_upcall_data != NULL)
+		nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+}
+
 static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 				   const char *op,
 				   void *aux)
@@ -677,29 +700,28 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 	int ret = -ENOMEM;
 
 	/* msg and im are freed in idmap_pipe_destroy_msg */
-	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		goto out1;
 
 	msg = &data->pipe_msg;
 	im = &data->idmap_msg;
 	data->idmap = idmap;
+	data->key_cons = cons;
 
 	ret = nfs_idmap_prepare_message(key->description, idmap, im, msg);
 	if (ret < 0)
 		goto out2;
 
-	BUG_ON(idmap->idmap_key_cons != NULL);
-	idmap->idmap_key_cons = cons;
+	ret = -EAGAIN;
+	if (!nfs_idmap_prepare_pipe_upcall(idmap, data))
+		goto out2;
 
 	ret = rpc_queue_upcall(idmap->idmap_pipe, msg);
 	if (ret < 0)
-		goto out3;
+		nfs_idmap_abort_pipe_upcall(idmap, ret);
 
 	return ret;
-
-out3:
-	idmap->idmap_key_cons = NULL;
 out2:
 	kfree(data);
 out1:
@@ -714,21 +736,32 @@ static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *dat
 					authkey);
 }
 
-static int nfs_idmap_read_message(struct idmap_msg *im, struct key *key, struct key *authkey)
+static int nfs_idmap_read_and_verify_message(struct idmap_msg *im,
+		struct idmap_msg *upcall,
+		struct key *key, struct key *authkey)
 {
 	char id_str[NFS_UINT_MAXLEN];
-	int ret = -EINVAL;
+	int ret = -ENOKEY;
 
+	/* ret = -ENOKEY */
+	if (upcall->im_type != im->im_type || upcall->im_conv != im->im_conv)
+		goto out;
 	switch (im->im_conv) {
 	case IDMAP_CONV_NAMETOID:
+		if (strcmp(upcall->im_name, im->im_name) != 0)
+			break;
 		sprintf(id_str, "%d", im->im_id);
 		ret = nfs_idmap_instantiate(key, authkey, id_str);
 		break;
 	case IDMAP_CONV_IDTONAME:
+		if (upcall->im_id != im->im_id)
+			break;
 		ret = nfs_idmap_instantiate(key, authkey, im->im_name);
 		break;
+	default:
+		ret = -EINVAL;
 	}
-
+out:
 	return ret;
 }
 
@@ -740,14 +773,16 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	struct key_construction *cons;
 	struct idmap_msg im;
 	size_t namelen_in;
-	int ret;
+	int ret = -ENOKEY;
 
 	/* If instantiation is successful, anyone waiting for key construction
 	 * will have been woken up and someone else may now have used
 	 * idmap_key_cons - so after this point we may no longer touch it.
 	 */
-	cons = ACCESS_ONCE(idmap->idmap_key_cons);
-	idmap->idmap_key_cons = NULL;
+	if (idmap->idmap_upcall_data == NULL)
+		goto out_noupcall;
+
+	cons = idmap->idmap_upcall_data->key_cons;
 
 	if (mlen != sizeof(im)) {
 		ret = -ENOSPC;
@@ -768,16 +803,19 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	if (namelen_in == 0 || namelen_in == IDMAP_NAMESZ) {
 		ret = -EINVAL;
 		goto out;
-	}
+}
 
-	ret = nfs_idmap_read_message(&im, cons->key, cons->authkey);
+	ret = nfs_idmap_read_and_verify_message(&im,
+			&idmap->idmap_upcall_data->idmap_msg,
+			cons->key, cons->authkey);
 	if (ret >= 0) {
 		key_set_timeout(cons->key, nfs_idmap_cache_timeout);
 		ret = mlen;
 	}
 
 out:
-	complete_request_key(cons, ret);
+	nfs_idmap_complete_pipe_upcall_locked(idmap, ret);
+out_noupcall:
 	return ret;
 }
 
@@ -788,14 +826,9 @@ idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 			struct idmap_legacy_upcalldata,
 			pipe_msg);
 	struct idmap *idmap = data->idmap;
-	struct key_construction *cons;
-	if (msg->errno) {
-		cons = ACCESS_ONCE(idmap->idmap_key_cons);
-		idmap->idmap_key_cons = NULL;
-		complete_request_key(cons, msg->errno);
-	}
-	/* Free memory allocated in nfs_idmap_legacy_upcall() */
-	kfree(data);
+
+	if (msg->errno)
+		nfs_idmap_abort_pipe_upcall(idmap, msg->errno);
 }
 
 static void
@@ -803,7 +836,8 @@ idmap_release_pipe(struct inode *inode)
 {
 	struct rpc_inode *rpci = RPC_I(inode);
 	struct idmap *idmap = (struct idmap *)rpci->private;
-	idmap->idmap_key_cons = NULL;
+
+	nfs_idmap_abort_pipe_upcall(idmap, -EPIPE);
 }
 
 int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index e4c716d374a8..6fa01aea2488 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -547,8 +547,8 @@ EXPORT_SYMBOL_GPL(nfs_getattr);
 static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
 {
 	atomic_set(&l_ctx->count, 1);
-	l_ctx->lockowner = current->files;
-	l_ctx->pid = current->tgid;
+	l_ctx->lockowner.l_owner = current->files;
+	l_ctx->lockowner.l_pid = current->tgid;
 	INIT_LIST_HEAD(&l_ctx->list);
 }
 
@@ -557,9 +557,9 @@ static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context
 	struct nfs_lock_context *pos;
 
 	list_for_each_entry(pos, &ctx->lock_context.list, list) {
-		if (pos->lockowner != current->files)
+		if (pos->lockowner.l_owner != current->files)
 			continue;
-		if (pos->pid != current->tgid)
+		if (pos->lockowner.l_pid != current->tgid)
 			continue;
 		atomic_inc(&pos->count);
 		return pos;
@@ -578,7 +578,7 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
 		spin_unlock(&inode->i_lock);
 		new = kmalloc(sizeof(*new), GFP_KERNEL);
 		if (new == NULL)
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		nfs_init_lock_context(new);
 		spin_lock(&inode->i_lock);
 		res = __nfs_find_lock_context(ctx);
@@ -685,7 +685,10 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	if (ctx->cred != NULL)
 		put_rpccred(ctx->cred);
 	dput(ctx->dentry);
-	nfs_sb_deactive(sb);
+	if (is_sync)
+		nfs_sb_deactive(sb);
+	else
+		nfs_sb_deactive_async(sb);
 	kfree(ctx->mdsthreshold);
 	kfree(ctx);
 }
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 31fdb03225cd..05521cadac2e 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -101,11 +101,11 @@ struct nfs_client_initdata {
  */
 struct nfs_parsed_mount_data {
 	int			flags;
-	int			rsize, wsize;
-	int			timeo, retrans;
-	int			acregmin, acregmax,
+	unsigned int		rsize, wsize;
+	unsigned int		timeo, retrans;
+	unsigned int		acregmin, acregmax,
 				acdirmin, acdirmax;
-	int			namlen;
+	unsigned int		namlen;
 	unsigned int		options;
 	unsigned int		bsize;
 	unsigned int		auth_flavor_len;
@@ -351,10 +351,12 @@ extern int __init register_nfs_fs(void);
 extern void __exit unregister_nfs_fs(void);
 extern void nfs_sb_active(struct super_block *sb);
 extern void nfs_sb_deactive(struct super_block *sb);
+extern void nfs_sb_deactive_async(struct super_block *sb);
 
 /* namespace.c */
+#define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
-		      char *buffer, ssize_t buflen);
+		      char *buffer, ssize_t buflen, unsigned flags);
 extern struct vfsmount *nfs_d_automount(struct path *path);
 struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *,
 			      struct nfs_fh *, struct nfs_fattr *);
@@ -464,6 +466,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 {
 	inode_dio_wait(inode);
 }
+extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_read_data *);
@@ -483,6 +486,12 @@ extern int _nfs4_call_sync_session(struct rpc_clnt *clnt,
 				   struct nfs4_sequence_args *args,
 				   struct nfs4_sequence_res *res,
 				   int cache_reply);
+extern int nfs40_walk_client_list(struct nfs_client *clp,
+				struct nfs_client **result,
+				struct rpc_cred *cred);
+extern int nfs41_walk_client_list(struct nfs_client *clp,
+				struct nfs_client **result,
+				struct rpc_cred *cred);
 
 /*
  * Determine the device name as a string
@@ -491,7 +500,7 @@ static inline char *nfs_devname(struct dentry *dentry,
 				char *buffer, ssize_t buflen)
 {
 	char *dummy;
-	return nfs_path(&dummy, dentry, buffer, buflen);
+	return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL);
 }
 
 /*
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 8e65c7f1f87c..015f71f8f62c 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -181,7 +181,7 @@ int nfs_mount(struct nfs_mount_request *info)
 	else
 		msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT];
 
-	status = rpc_call_sync(mnt_clnt, &msg, 0);
+	status = rpc_call_sync(mnt_clnt, &msg, RPC_TASK_SOFT|RPC_TASK_TIMEOUT);
 	rpc_shutdown_client(mnt_clnt);
 
 	if (status < 0)
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 655925373b91..dd057bc6b65b 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -33,6 +33,7 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  * @dentry - pointer to dentry
  * @buffer - result buffer
  * @buflen - length of buffer
+ * @flags - options (see below)
  *
  * Helper function for constructing the server pathname
  * by arbitrary hashed dentry.
@@ -40,8 +41,14 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  * This is mainly for use in figuring out the path on the
  * server side when automounting on top of an existing partition
  * and in generating /proc/mounts and friends.
+ *
+ * Supported flags:
+ * NFS_PATH_CANONICAL: ensure there is exactly one slash after
+ *		       the original device (export) name
+ *		       (if unset, the original name is returned verbatim)
  */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen)
+char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
+	       unsigned flags)
 {
 	char *end;
 	int namelen;
@@ -74,7 +81,7 @@ rename_retry:
 		rcu_read_unlock();
 		goto rename_retry;
 	}
-	if (*end != '/') {
+	if ((flags & NFS_PATH_CANONICAL) && *end != '/') {
 		if (--buflen < 0) {
 			spin_unlock(&dentry->d_lock);
 			rcu_read_unlock();
@@ -91,9 +98,11 @@ rename_retry:
 		return end;
 	}
 	namelen = strlen(base);
-	/* Strip off excess slashes in base string */
-	while (namelen > 0 && base[namelen - 1] == '/')
-		namelen--;
+	if (flags & NFS_PATH_CANONICAL) {
+		/* Strip off excess slashes in base string */
+		while (namelen > 0 && base[namelen - 1] == '/')
+			namelen--;
+	}
 	buflen -= namelen;
 	if (buflen < 0) {
 		spin_unlock(&dentry->d_lock);
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index 0539de1b8d1f..8ee1fab83268 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -5,6 +5,7 @@
 #ifndef __NFS_NETNS_H__
 #define __NFS_NETNS_H__
 
+#include <linux/nfs4.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -22,6 +23,9 @@ struct nfs_net {
 	struct list_head nfs_volume_list;
 #if IS_ENABLED(CONFIG_NFS_V4)
 	struct idr cb_ident_idr; /* Protected by nfs_client_lock */
+	unsigned short nfs_callback_tcpport;
+	unsigned short nfs_callback_tcpport6;
+	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
 #endif
 	spinlock_t nfs_client_lock;
 	struct timespec boot_time;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index da0618aeeadb..a525fdefccde 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -132,8 +132,8 @@ struct nfs4_lock_owner {
 struct nfs4_lock_state {
 	struct list_head	ls_locks;	/* Other lock stateids */
 	struct nfs4_state *	ls_state;	/* Pointer to open state */
-#define NFS_LOCK_INITIALIZED 1
-	int			ls_flags;
+#define NFS_LOCK_INITIALIZED 0
+	unsigned long		ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
 	nfs4_stateid		ls_stateid;
 	atomic_t		ls_count;
@@ -191,6 +191,8 @@ struct nfs4_state_recovery_ops {
 	int (*establish_clid)(struct nfs_client *, struct rpc_cred *);
 	struct rpc_cred * (*get_clid_cred)(struct nfs_client *);
 	int (*reclaim_complete)(struct nfs_client *);
+	int (*detect_trunking)(struct nfs_client *, struct nfs_client **,
+		struct rpc_cred *);
 };
 
 struct nfs4_state_maintenance_ops {
@@ -223,7 +225,7 @@ extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
 extern int nfs4_destroy_clientid(struct nfs_client *clp);
 extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
-extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
+extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait);
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
 				  struct nfs4_fs_locations *, struct page *);
@@ -320,9 +322,15 @@ extern void nfs4_renew_state(struct work_struct *);
 /* nfs4state.c */
 struct rpc_cred *nfs4_get_setclientid_cred(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
+int nfs4_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **);
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **, struct rpc_cred *);
 #if defined(CONFIG_NFS_V4_1)
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
+int nfs41_discover_server_trunking(struct nfs_client *clp,
+			struct nfs_client **, struct rpc_cred *);
 extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 #else
 static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
@@ -351,7 +359,7 @@ extern void nfs41_handle_server_scope(struct nfs_client *,
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
 extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
-		fmode_t, fl_owner_t, pid_t);
+		fmode_t, const struct nfs_lockowner *);
 
 extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
 extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -372,6 +380,9 @@ extern bool nfs4_disable_idmapping;
 extern unsigned short max_session_slots;
 extern unsigned short send_implementation_id;
 
+#define NFS4_CLIENT_ID_UNIQ_LEN		(64)
+extern char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN];
+
 /* nfs4sysctl.c */
 #ifdef CONFIG_SYSCTL
 int nfs4_register_sysctl(void);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 24eb663f8ed5..6bacfde1319a 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -84,7 +84,7 @@ error:
 static void nfs4_destroy_callback(struct nfs_client *clp)
 {
 	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down(clp->cl_mvops->minor_version);
+		nfs_callback_down(clp->cl_mvops->minor_version, clp->cl_net);
 }
 
 static void nfs4_shutdown_client(struct nfs_client *clp)
@@ -185,6 +185,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 				    rpc_authflavor_t authflavour)
 {
 	char buf[INET6_ADDRSTRLEN + 1];
+	struct nfs_client *old;
 	int error;
 
 	if (clp->cl_cons_state == NFS_CS_READY) {
@@ -230,6 +231,17 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 
 	if (!nfs4_has_session(clp))
 		nfs_mark_client_ready(clp, NFS_CS_READY);
+
+	error = nfs4_discover_server_trunking(clp, &old);
+	if (error < 0)
+		goto error;
+	if (clp != old) {
+		clp->cl_preserve_clid = true;
+		nfs_put_client(clp);
+		clp = old;
+		atomic_inc(&clp->cl_count);
+	}
+
 	return clp;
 
 error:
@@ -239,6 +251,248 @@ error:
 	return ERR_PTR(error);
 }
 
+/*
+ * SETCLIENTID just did a callback update with the callback ident in
+ * "drop," but server trunking discovery claims "drop" and "keep" are
+ * actually the same server.  Swap the callback IDs so that "keep"
+ * will continue to use the callback ident the server now knows about,
+ * and so that "keep"'s original callback ident is destroyed when
+ * "drop" is freed.
+ */
+static void nfs4_swap_callback_idents(struct nfs_client *keep,
+				      struct nfs_client *drop)
+{
+	struct nfs_net *nn = net_generic(keep->cl_net, nfs_net_id);
+	unsigned int save = keep->cl_cb_ident;
+
+	if (keep->cl_cb_ident == drop->cl_cb_ident)
+		return;
+
+	dprintk("%s: keeping callback ident %u and dropping ident %u\n",
+		__func__, keep->cl_cb_ident, drop->cl_cb_ident);
+
+	spin_lock(&nn->nfs_client_lock);
+
+	idr_replace(&nn->cb_ident_idr, keep, drop->cl_cb_ident);
+	keep->cl_cb_ident = drop->cl_cb_ident;
+
+	idr_replace(&nn->cb_ident_idr, drop, save);
+	drop->cl_cb_ident = save;
+
+	spin_unlock(&nn->nfs_client_lock);
+}
+
+/**
+ * nfs40_walk_client_list - Find server that recognizes a client ID
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs40_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+int nfs40_walk_client_list(struct nfs_client *new,
+			   struct nfs_client **result,
+			   struct rpc_cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *n, *prev = NULL;
+	struct nfs4_setclientid_res clid = {
+		.clientid	= new->cl_clientid,
+		.confirm	= new->cl_confirm,
+	};
+	int status;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+		/* If "pos" isn't marked ready, we can't trust the
+		 * remaining fields in "pos" */
+		if (pos->cl_cons_state < NFS_CS_READY)
+			continue;
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
+		if (pos->cl_clientid != new->cl_clientid)
+			continue;
+
+		atomic_inc(&pos->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+
+		if (prev)
+			nfs_put_client(prev);
+
+		status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
+		if (status == 0) {
+			nfs4_swap_callback_idents(pos, new);
+
+			nfs_put_client(pos);
+			*result = pos;
+			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
+				__func__, pos, atomic_read(&pos->cl_count));
+			return 0;
+		}
+		if (status != -NFS4ERR_STALE_CLIENTID) {
+			nfs_put_client(pos);
+			dprintk("NFS: <-- %s status = %d, no result\n",
+				__func__, status);
+			return status;
+		}
+
+		spin_lock(&nn->nfs_client_lock);
+		prev = pos;
+	}
+
+	/*
+	 * No matching nfs_client found.  This should be impossible,
+	 * because the new nfs_client has already been added to
+	 * nfs_client_list by nfs_get_client().
+	 *
+	 * Don't BUG(), since the caller is holding a mutex.
+	 */
+	if (prev)
+		nfs_put_client(prev);
+	spin_unlock(&nn->nfs_client_lock);
+	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
+	return -NFS4ERR_STALE_CLIENTID;
+}
+
+#ifdef CONFIG_NFS_V4_1
+/*
+ * Returns true if the client IDs match
+ */
+static bool nfs4_match_clientids(struct nfs_client *a, struct nfs_client *b)
+{
+	if (a->cl_clientid != b->cl_clientid) {
+		dprintk("NFS: --> %s client ID %llx does not match %llx\n",
+			__func__, a->cl_clientid, b->cl_clientid);
+		return false;
+	}
+	dprintk("NFS: --> %s client ID %llx matches %llx\n",
+		__func__, a->cl_clientid, b->cl_clientid);
+	return true;
+}
+
+/*
+ * Returns true if the server owners match
+ */
+static bool
+nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b)
+{
+	struct nfs41_server_owner *o1 = a->cl_serverowner;
+	struct nfs41_server_owner *o2 = b->cl_serverowner;
+
+	if (o1->minor_id != o2->minor_id) {
+		dprintk("NFS: --> %s server owner minor IDs do not match\n",
+			__func__);
+		return false;
+	}
+
+	if (o1->major_id_sz != o2->major_id_sz)
+		goto out_major_mismatch;
+	if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
+		goto out_major_mismatch;
+
+	dprintk("NFS: --> %s server owners match\n", __func__);
+	return true;
+
+out_major_mismatch:
+	dprintk("NFS: --> %s server owner major IDs do not match\n",
+		__func__);
+	return false;
+}
+
+/**
+ * nfs41_walk_client_list - Find nfs_client that matches a client/server owner
+ *
+ * @new: nfs_client with client ID to test
+ * @result: OUT: found nfs_client, or new
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in "result."
+ *
+ * NB: nfs41_walk_client_list() relies on the new nfs_client being
+ *     the last nfs_client on the list.
+ */
+int nfs41_walk_client_list(struct nfs_client *new,
+			   struct nfs_client **result,
+			   struct rpc_cred *cred)
+{
+	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
+	struct nfs_client *pos, *n, *prev = NULL;
+	int error;
+
+	spin_lock(&nn->nfs_client_lock);
+	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+		/* If "pos" isn't marked ready, we can't trust the
+		 * remaining fields in "pos", especially the client
+		 * ID and serverowner fields.  Wait for CREATE_SESSION
+		 * to finish. */
+		if (pos->cl_cons_state < NFS_CS_READY) {
+			atomic_inc(&pos->cl_count);
+			spin_unlock(&nn->nfs_client_lock);
+
+			if (prev)
+				nfs_put_client(prev);
+			prev = pos;
+
+			error = nfs_wait_client_init_complete(pos);
+			if (error < 0) {
+				nfs_put_client(pos);
+				spin_lock(&nn->nfs_client_lock);
+				continue;
+			}
+
+			spin_lock(&nn->nfs_client_lock);
+		}
+
+		if (pos->rpc_ops != new->rpc_ops)
+			continue;
+
+		if (pos->cl_proto != new->cl_proto)
+			continue;
+
+		if (pos->cl_minorversion != new->cl_minorversion)
+			continue;
+
+		if (!nfs4_match_clientids(pos, new))
+			continue;
+
+		if (!nfs4_match_serverowners(pos, new))
+			continue;
+
+		spin_unlock(&nn->nfs_client_lock);
+		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
+			__func__, pos, atomic_read(&pos->cl_count));
+
+		*result = pos;
+		return 0;
+	}
+
+	/*
+	 * No matching nfs_client found.  This should be impossible,
+	 * because the new nfs_client has already been added to
+	 * nfs_client_list by nfs_get_client().
+	 *
+	 * Don't BUG(), since the caller is holding a mutex.
+	 */
+	spin_unlock(&nn->nfs_client_lock);
+	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
+	return -NFS4ERR_STALE_CLIENTID;
+}
+#endif	/* CONFIG_NFS_V4_1 */
+
 static void nfs4_destroy_server(struct nfs_server *server)
 {
 	nfs_server_return_all_delegations(server);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index eb5eb8eef4d3..afddd6639afb 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -95,16 +95,25 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct inode *inode = file->f_path.dentry->d_inode;
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret != 0)
-		goto out;
-	mutex_lock(&inode->i_mutex);
-	ret = nfs_file_fsync_commit(file, start, end, datasync);
-	if (!ret && !datasync)
-		/* application has asked for meta-data sync */
-		ret = pnfs_layoutcommit_inode(inode, true);
-	mutex_unlock(&inode->i_mutex);
-out:
+	do {
+		ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+		if (ret != 0)
+			break;
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_file_fsync_commit(file, start, end, datasync);
+		if (!ret && !datasync)
+			/* application has asked for meta-data sync */
+			ret = pnfs_layoutcommit_inode(inode, true);
+		mutex_unlock(&inode->i_mutex);
+		/*
+		 * If nfs_file_fsync_commit detected a server reboot, then
+		 * resend all dirty pages that might have been covered by
+		 * the NFS_CONTEXT_RESEND_WRITES flag
+		 */
+		start = 0;
+		end = LLONG_MAX;
+	} while (ret == -EAGAIN);
+
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 53f94d915bd1..2e45fd9c02a3 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -122,12 +122,21 @@ static void filelayout_reset_read(struct nfs_read_data *data)
 	}
 }
 
+static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
+{
+	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return;
+	clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
+	pnfs_return_layout(inode);
+}
+
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
 					 struct pnfs_layout_segment *lseg)
 {
-	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct pnfs_layout_hdr *lo = lseg->pls_layout;
+	struct inode *inode = lo->plh_inode;
 	struct nfs_server *mds_server = NFS_SERVER(inode);
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs_client *mds_client = mds_server->nfs_client;
@@ -190,8 +199,6 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		 * i/o and all i/o waiting on the slot table to the MDS until
 		 * layout is destroyed and a new valid layout is obtained.
 		 */
-		set_bit(NFS_LAYOUT_INVALID,
-				&NFS_I(inode)->layout->plh_flags);
 		pnfs_destroy_layout(NFS_I(inode));
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		goto reset;
@@ -205,11 +212,9 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -EPIPE:
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
-		filelayout_mark_devid_invalid(devid);
-		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
-		_pnfs_return_layout(inode);
+		nfs4_mark_deviceid_unavailable(devid);
+		set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		nfs4_ds_disconnect(clp);
 		/* fall through */
 	default:
 reset:
@@ -269,6 +274,21 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
 
+bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node)
+{
+	return filelayout_test_devid_invalid(node) ||
+		nfs4_test_deviceid_unavailable(node);
+}
+
+static bool
+filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
+{
+	struct nfs4_deviceid_node *node = FILELAYOUT_DEVID_NODE(lseg);
+
+	return filelayout_test_devid_unavailable(node);
+}
+
 /*
  * Call ops for the async read/write cases
  * In the case of dense layouts, the offset needs to be reset to its
@@ -318,7 +338,9 @@ static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 static void filelayout_read_release(void *data)
 {
 	struct nfs_read_data *rdata = data;
+	struct pnfs_layout_hdr *lo = rdata->header->lseg->pls_layout;
 
+	filelayout_fenceme(lo->plh_inode, lo);
 	nfs_put_client(rdata->ds_clp);
 	rdata->header->mds_ops->rpc_release(data);
 }
@@ -416,7 +438,9 @@ static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 static void filelayout_write_release(void *data)
 {
 	struct nfs_write_data *wdata = data;
+	struct pnfs_layout_hdr *lo = wdata->header->lseg->pls_layout;
 
+	filelayout_fenceme(lo->plh_inode, lo);
 	nfs_put_client(wdata->ds_clp);
 	wdata->header->mds_ops->rpc_release(data);
 }
@@ -453,7 +477,7 @@ static void filelayout_commit_release(void *calldata)
 	struct nfs_commit_data *data = calldata;
 
 	data->completion_ops->completion(data);
-	put_lseg(data->lseg);
+	pnfs_put_lseg(data->lseg);
 	nfs_put_client(data->ds_clp);
 	nfs_commitdata_release(data);
 }
@@ -608,13 +632,13 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
 				   NFS_SERVER(lo->plh_inode)->nfs_client, id);
 	if (d == NULL) {
-		dsaddr = get_device_info(lo->plh_inode, id, gfp_flags);
+		dsaddr = filelayout_get_device_info(lo->plh_inode, id, gfp_flags);
 		if (dsaddr == NULL)
 			goto out;
 	} else
 		dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
-	/* Found deviceid is being reaped */
-	if (test_bit(NFS_DEVICEID_INVALID, &dsaddr->id_node.flags))
+	/* Found deviceid is unavailable */
+	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
 			goto out_put;
 
 	fl->dsaddr = dsaddr;
@@ -726,7 +750,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		goto out_err;
 
 	if (fl->num_fh > 0) {
-		fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *),
+		fl->fh_array = kcalloc(fl->num_fh, sizeof(fl->fh_array[0]),
 				       gfp_flags);
 		if (!fl->fh_array)
 			goto out_err;
@@ -931,7 +955,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
 	status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
 	if (status < 0) {
-		put_lseg(pgio->pg_lseg);
+		pnfs_put_lseg(pgio->pg_lseg);
 		pgio->pg_lseg = NULL;
 		goto out_mds;
 	}
@@ -985,7 +1009,7 @@ filelayout_clear_request_commit(struct nfs_page *req,
 out:
 	nfs_request_remove_commit_list(req, cinfo);
 	spin_unlock(cinfo->lock);
-	put_lseg(freeme);
+	pnfs_put_lseg(freeme);
 }
 
 static struct list_head *
@@ -1018,7 +1042,7 @@ filelayout_choose_commit_list(struct nfs_page *req,
 		 * off due to a rewrite, in which case it will be done in
 		 * filelayout_clear_request_commit
 		 */
-		buckets[i].wlseg = get_lseg(lseg);
+		buckets[i].wlseg = pnfs_get_lseg(lseg);
 	}
 	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
 	cinfo->ds->nwritten++;
@@ -1128,7 +1152,7 @@ filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 		if (list_empty(src))
 			bucket->wlseg = NULL;
 		else
-			get_lseg(bucket->clseg);
+			pnfs_get_lseg(bucket->clseg);
 	}
 	return ret;
 }
@@ -1159,12 +1183,12 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
 
 	/* NOTE cinfo->lock is NOT held, relying on fact that this is
 	 * only called on single thread per dreq.
-	 * Can't take the lock because need to do put_lseg
+	 * Can't take the lock because need to do pnfs_put_lseg
 	 */
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
 		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
 			BUG_ON(!list_empty(&b->written));
-			put_lseg(b->wlseg);
+			pnfs_put_lseg(b->wlseg);
 			b->wlseg = NULL;
 		}
 	}
@@ -1200,7 +1224,7 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
 		if (list_empty(&bucket->committing))
 			continue;
 		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
-		put_lseg(bucket->clseg);
+		pnfs_put_lseg(bucket->clseg);
 		bucket->clseg = NULL;
 	}
 	/* Caller will clean up entries put on list */
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 43fe802dd678..8c07241fe52b 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -129,23 +129,13 @@ filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
 }
 
 static inline bool
-filelayout_test_layout_invalid(struct pnfs_layout_hdr *lo)
-{
-	return test_bit(NFS_LAYOUT_INVALID, &lo->plh_flags);
-}
-
-static inline bool
 filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
 {
 	return test_bit(NFS_DEVICEID_INVALID, &node->flags);
 }
 
-static inline bool
-filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
-{
-	return filelayout_test_devid_invalid(FILELAYOUT_DEVID_NODE(lseg)) ||
-		filelayout_test_layout_invalid(lseg->pls_layout);
-}
+extern bool
+filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
 
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
@@ -158,7 +148,6 @@ struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
 extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 struct nfs4_file_layout_dsaddr *
-get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
-void nfs4_ds_disconnect(struct nfs_client *clp);
+filelayout_get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
 
 #endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index f81231f30d94..a8eaa9b7bb0f 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -149,28 +149,6 @@ _data_server_lookup_locked(const struct list_head *dsaddrs)
 }
 
 /*
- * Lookup DS by nfs_client pointer. Zero data server client pointer
- */
-void nfs4_ds_disconnect(struct nfs_client *clp)
-{
-	struct nfs4_pnfs_ds *ds;
-	struct nfs_client *found = NULL;
-
-	dprintk("%s clp %p\n", __func__, clp);
-	spin_lock(&nfs4_ds_cache_lock);
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
-		if (ds->ds_clp && ds->ds_clp == clp) {
-			found = ds->ds_clp;
-			ds->ds_clp = NULL;
-		}
-	spin_unlock(&nfs4_ds_cache_lock);
-	if (found) {
-		set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
-		nfs_put_client(clp);
-	}
-}
-
-/*
  * Create an rpc connection to the nfs4_pnfs_ds data server
  * Currently only supports IPv4 and IPv6 addresses
  */
@@ -690,7 +668,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
  * of available devices, and return it.
  */
 struct nfs4_file_layout_dsaddr *
-get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags)
+filelayout_get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags)
 {
 	struct pnfs_device *pdev = NULL;
 	u32 max_resp_sz;
@@ -804,13 +782,14 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 
-	if (filelayout_test_devid_invalid(devid))
+	if (filelayout_test_devid_unavailable(devid))
 		return NULL;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
-		goto mark_dev_invalid;
+		filelayout_mark_devid_invalid(devid);
+		return NULL;
 	}
 
 	if (!ds->ds_clp) {
@@ -818,14 +797,12 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		int err;
 
 		err = nfs4_ds_connect(s, ds);
-		if (err)
-			goto mark_dev_invalid;
+		if (err) {
+			nfs4_mark_deviceid_unavailable(devid);
+			return NULL;
+		}
 	}
 	return ds;
-
-mark_dev_invalid:
-	filelayout_mark_devid_invalid(devid);
-	return NULL;
 }
 
 module_param(dataserver_retrans, uint, 0644);
diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c
index 6a83780e0ce6..549462e5b9b0 100644
--- a/fs/nfs/nfs4getroot.c
+++ b/fs/nfs/nfs4getroot.c
@@ -5,6 +5,7 @@
 
 #include <linux/nfs_fs.h>
 #include "nfs4_fs.h"
+#include "internal.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 017b4b01a69c..1e09eb78543b 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -81,7 +81,8 @@ static char *nfs_path_component(const char *nfspath, const char *end)
 static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen)
 {
 	char *limit;
-	char *path = nfs_path(&limit, dentry, buffer, buflen);
+	char *path = nfs_path(&limit, dentry, buffer, buflen,
+			      NFS_PATH_CANONICAL);
 	if (!IS_ERR(path)) {
 		char *path_component = nfs_path_component(path, limit);
 		if (path_component)
@@ -192,25 +193,13 @@ out:
 struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode,
 					struct qstr *name)
 {
-	struct rpc_clnt *clone;
-	struct rpc_auth *auth;
 	rpc_authflavor_t flavor;
 
 	flavor = nfs4_negotiate_security(inode, name);
 	if ((int)flavor < 0)
-		return ERR_PTR(flavor);
+		return ERR_PTR((int)flavor);
 
-	clone = rpc_clone_client(clnt);
-	if (IS_ERR(clone))
-		return clone;
-
-	auth = rpcauth_create(flavor, clone);
-	if (!auth) {
-		rpc_shutdown_client(clone);
-		clone = ERR_PTR(-EIO);
-	}
-
-	return clone;
+	return rpc_clone_client_set_auth(clnt, flavor);
 }
 
 static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1e50326d00dd..5eec4429970c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -104,6 +104,8 @@ static int nfs4_map_errors(int err)
 		return -EACCES;
 	case -NFS4ERR_MINOR_VERS_MISMATCH:
 		return -EPROTONOSUPPORT;
+	case -NFS4ERR_ACCESS:
+		return -EACCES;
 	default:
 		dprintk("%s could not handle NFSv4 error %d\n",
 				__func__, -err);
@@ -150,6 +152,12 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
 	FATTR4_WORD2_MDSTHRESHOLD
 };
 
+static const u32 nfs4_open_noattr_bitmap[3] = {
+	FATTR4_WORD0_TYPE
+	| FATTR4_WORD0_CHANGE
+	| FATTR4_WORD0_FILEID,
+};
+
 const u32 nfs4_statfs_bitmap[2] = {
 	FATTR4_WORD0_FILES_AVAIL
 	| FATTR4_WORD0_FILES_FREE
@@ -331,8 +339,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
 			nfs4_schedule_session_recovery(clp->cl_session, errorcode);
-			exception->retry = 1;
-			break;
+			goto wait_on_recovery;
 #endif /* defined(CONFIG_NFS_V4_1) */
 		case -NFS4ERR_FILE_OPEN:
 			if (exception->timeout > HZ) {
@@ -832,6 +839,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 	p->o_res.seqid = p->o_arg.seqid;
 	p->c_res.seqid = p->c_arg.seqid;
 	p->o_res.server = p->o_arg.server;
+	p->o_res.access_request = p->o_arg.access;
 	nfs_fattr_init(&p->f_attr);
 	nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name);
 }
@@ -860,6 +868,14 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	p->o_arg.fh = NFS_FH(dir);
 	p->o_arg.open_flags = flags;
 	p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
+	/* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS
+	 * will return permission denied for all bits until close */
+	if (!(flags & O_EXCL)) {
+		/* ask server to check for all possible rights as results
+		 * are cached */
+		p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY |
+				  NFS4_ACCESS_EXTEND | NFS4_ACCESS_EXECUTE;
+	}
 	p->o_arg.clientid = server->nfs_client->cl_clientid;
 	p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time);
 	p->o_arg.id.uniquifier = sp->so_seqid.owner_id;
@@ -1115,11 +1131,80 @@ out_return_state:
 	return state;
 }
 
-static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
+static void
+nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state)
+{
+	struct nfs_client *clp = NFS_SERVER(state->inode)->nfs_client;
+	struct nfs_delegation *delegation;
+	int delegation_flags = 0;
+
+	rcu_read_lock();
+	delegation = rcu_dereference(NFS_I(state->inode)->delegation);
+	if (delegation)
+		delegation_flags = delegation->flags;
+	rcu_read_unlock();
+	if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
+		pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
+				   "returning a delegation for "
+				   "OPEN(CLAIM_DELEGATE_CUR)\n",
+				   clp->cl_hostname);
+	} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
+		nfs_inode_set_delegation(state->inode,
+					 data->owner->so_cred,
+					 &data->o_res);
+	else
+		nfs_inode_reclaim_delegation(state->inode,
+					     data->owner->so_cred,
+					     &data->o_res);
+}
+
+/*
+ * Check the inode attributes against the CLAIM_PREVIOUS returned attributes
+ * and update the nfs4_state.
+ */
+static struct nfs4_state *
+_nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
+{
+	struct inode *inode = data->state->inode;
+	struct nfs4_state *state = data->state;
+	int ret;
+
+	if (!data->rpc_done) {
+		ret = data->rpc_status;
+		goto err;
+	}
+
+	ret = -ESTALE;
+	if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) ||
+	    !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) ||
+	    !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE))
+		goto err;
+
+	ret = -ENOMEM;
+	state = nfs4_get_open_state(inode, data->owner);
+	if (state == NULL)
+		goto err;
+
+	ret = nfs_refresh_inode(inode, &data->f_attr);
+	if (ret)
+		goto err;
+
+	if (data->o_res.delegation_type != 0)
+		nfs4_opendata_check_deleg(data, state);
+	update_open_stateid(state, &data->o_res.stateid, NULL,
+			    data->o_arg.fmode);
+
+	return state;
+err:
+	return ERR_PTR(ret);
+
+}
+
+static struct nfs4_state *
+_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
 {
 	struct inode *inode;
 	struct nfs4_state *state = NULL;
-	struct nfs_delegation *delegation;
 	int ret;
 
 	if (!data->rpc_done) {
@@ -1138,30 +1223,8 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
 	state = nfs4_get_open_state(inode, data->owner);
 	if (state == NULL)
 		goto err_put_inode;
-	if (data->o_res.delegation_type != 0) {
-		struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
-		int delegation_flags = 0;
-
-		rcu_read_lock();
-		delegation = rcu_dereference(NFS_I(inode)->delegation);
-		if (delegation)
-			delegation_flags = delegation->flags;
-		rcu_read_unlock();
-		if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
-			pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
-					"returning a delegation for "
-					"OPEN(CLAIM_DELEGATE_CUR)\n",
-					clp->cl_hostname);
-		} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
-			nfs_inode_set_delegation(state->inode,
-					data->owner->so_cred,
-					&data->o_res);
-		else
-			nfs_inode_reclaim_delegation(state->inode,
-					data->owner->so_cred,
-					&data->o_res);
-	}
-
+	if (data->o_res.delegation_type != 0)
+		nfs4_opendata_check_deleg(data, state);
 	update_open_stateid(state, &data->o_res.stateid, NULL,
 			data->o_arg.fmode);
 	iput(inode);
@@ -1173,6 +1236,14 @@ err:
 	return ERR_PTR(ret);
 }
 
+static struct nfs4_state *
+nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
+{
+	if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS)
+		return _nfs4_opendata_reclaim_to_nfs4_state(data);
+	return _nfs4_opendata_to_nfs4_state(data);
+}
+
 static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
@@ -1494,14 +1565,17 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 	data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
 	if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
+		data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
 		nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
 	}
 	data->timestamp = jiffies;
 	if (nfs4_setup_sequence(data->o_arg.server,
 				&data->o_arg.seq_args,
-				&data->o_res.seq_res, task))
-		return;
-	rpc_call_start(task);
+				&data->o_res.seq_res,
+				task) != 0)
+		nfs_release_seqid(data->o_arg.seqid);
+	else
+		rpc_call_start(task);
 	return;
 unlock_no_action:
 	rcu_read_unlock();
@@ -1526,7 +1600,8 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 		return;
 
 	if (task->tk_status == 0) {
-		switch (data->o_res.f_attr->mode & S_IFMT) {
+		if (data->o_res.f_attr->valid & NFS_ATTR_FATTR_TYPE) {
+			switch (data->o_res.f_attr->mode & S_IFMT) {
 			case S_IFREG:
 				break;
 			case S_IFLNK:
@@ -1537,6 +1612,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 				break;
 			default:
 				data->rpc_status = -ENOTDIR;
+			}
 		}
 		renew_lease(data->o_res.server, data->timestamp);
 		if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM))
@@ -1643,6 +1719,39 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 	return status;
 }
 
+static int nfs4_opendata_access(struct rpc_cred *cred,
+				struct nfs4_opendata *opendata,
+				struct nfs4_state *state, fmode_t fmode)
+{
+	struct nfs_access_entry cache;
+	u32 mask;
+
+	/* access call failed or for some reason the server doesn't
+	 * support any access modes -- defer access call until later */
+	if (opendata->o_res.access_supported == 0)
+		return 0;
+
+	mask = 0;
+	/* don't check MAY_WRITE - a newly created file may not have
+	 * write mode bits, but POSIX allows the creating process to write */
+	if (fmode & FMODE_READ)
+		mask |= MAY_READ;
+	if (fmode & FMODE_EXEC)
+		mask |= MAY_EXEC;
+
+	cache.cred = cred;
+	cache.jiffies = jiffies;
+	nfs_access_set_mask(&cache, opendata->o_res.access_result);
+	nfs_access_add_cache(state->inode, &cache);
+
+	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
+		return 0;
+
+	/* even though OPEN succeeded, access is denied. Close the file */
+	nfs4_close_state(state, fmode);
+	return -EACCES;
+}
+
 /*
  * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
  */
@@ -1774,7 +1883,11 @@ static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
 		 * informs us the stateid is unrecognized. */
 		if (status != -NFS4ERR_BAD_STATEID)
 			nfs41_free_stateid(server, stateid);
+		nfs_remove_bad_delegation(state->inode);
 
+		write_seqlock(&state->seqlock);
+		nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+		write_sequnlock(&state->seqlock);
 		clear_bit(NFS_DELEGATED_STATE, &state->flags);
 	}
 }
@@ -1790,7 +1903,7 @@ static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
 static int nfs41_check_open_stateid(struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
-	nfs4_stateid *stateid = &state->stateid;
+	nfs4_stateid *stateid = &state->open_stateid;
 	int status;
 
 	/* If a state reset has been done, test_stateid is unneeded */
@@ -1896,6 +2009,10 @@ static int _nfs4_do_open(struct inode *dir,
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 
+	status = nfs4_opendata_access(cred, opendata, state, fmode);
+	if (status != 0)
+		goto err_opendata_put;
+
 	if (opendata->o_arg.open_flags & O_EXCL) {
 		nfs4_exclusive_attrset(opendata, sattr);
 
@@ -1941,7 +2058,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
 	struct nfs4_state *res;
 	int status;
 
-	fmode &= FMODE_READ|FMODE_WRITE;
+	fmode &= FMODE_READ|FMODE_WRITE|FMODE_EXEC;
 	do {
 		status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred,
 				       &res, ctx_th);
@@ -2013,8 +2130,12 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 	nfs_fattr_init(fattr);
 
 	if (state != NULL) {
+		struct nfs_lockowner lockowner = {
+			.l_owner = current->files,
+			.l_pid = current->tgid,
+		};
 		nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
-				current->files, current->tgid);
+				&lockowner);
 	} else if (nfs4_copy_delegation_stateid(&arg.stateid, inode,
 				FMODE_WRITE)) {
 		/* Use that stateid */
@@ -2076,7 +2197,7 @@ static void nfs4_free_closedata(void *data)
 	nfs4_put_open_state(calldata->state);
 	nfs_free_seqid(calldata->arg.seqid);
 	nfs4_put_state_owner(sp);
-	nfs_sb_deactive(sb);
+	nfs_sb_deactive_async(sb);
 	kfree(calldata);
 }
 
@@ -2133,6 +2254,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
+	struct inode *inode = calldata->inode;
 	int call_close = 0;
 
 	dprintk("%s: begin!\n", __func__);
@@ -2166,21 +2288,19 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	if (calldata->arg.fmode == 0) {
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
 		if (calldata->roc &&
-		    pnfs_roc_drain(calldata->inode, &calldata->roc_barrier)) {
-			rpc_sleep_on(&NFS_SERVER(calldata->inode)->roc_rpcwaitq,
-				     task, NULL);
+		    pnfs_roc_drain(inode, &calldata->roc_barrier, task))
 			goto out;
-		}
 	}
 
 	nfs_fattr_init(calldata->res.fattr);
 	calldata->timestamp = jiffies;
-	if (nfs4_setup_sequence(NFS_SERVER(calldata->inode),
+	if (nfs4_setup_sequence(NFS_SERVER(inode),
 				&calldata->arg.seq_args,
 				&calldata->res.seq_res,
-				task))
-		goto out;
-	rpc_call_start(task);
+				task) != 0)
+		nfs_release_seqid(calldata->arg.seqid);
+	else
+		rpc_call_start(task);
 out:
 	dprintk("%s: done!\n", __func__);
 }
@@ -2202,7 +2322,7 @@ static const struct rpc_call_ops nfs4_close_ops = {
  *
  * NOTE: Caller must be holding the sp->so_owner semaphore!
  */
-int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
+int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs4_closedata *calldata;
@@ -2238,7 +2358,7 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
 	calldata->res.fattr = &calldata->fattr;
 	calldata->res.seqid = calldata->arg.seqid;
 	calldata->res.server = server;
-	calldata->roc = roc;
+	calldata->roc = pnfs_roc(state->inode);
 	nfs_sb_active(calldata->inode->i_sb);
 
 	msg.rpc_argp = &calldata->arg;
@@ -2255,8 +2375,6 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc)
 out_free_calldata:
 	kfree(calldata);
 out:
-	if (roc)
-		pnfs_roc_release(state->inode);
 	nfs4_put_open_state(state);
 	nfs4_put_state_owner(sp);
 	return status;
@@ -2399,7 +2517,7 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl
 	int ret;
 
 	auth = rpcauth_create(flavor, server->client);
-	if (!auth) {
+	if (IS_ERR(auth)) {
 		ret = -EIO;
 		goto out;
 	}
@@ -2767,13 +2885,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
 	if (!status) {
-		entry->mask = 0;
-		if (res.access & NFS4_ACCESS_READ)
-			entry->mask |= MAY_READ;
-		if (res.access & (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
-			entry->mask |= MAY_WRITE;
-		if (res.access & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
-			entry->mask |= MAY_EXEC;
+		nfs_access_set_mask(entry, res.access);
 		nfs_refresh_inode(inode, res.fattr);
 	}
 	nfs_free_fattr(res.fattr);
@@ -3362,8 +3474,11 @@ static int nfs4_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, s
 
 	nfs_fattr_init(fsinfo->fattr);
 	error = nfs4_do_fsinfo(server, fhandle, fsinfo);
-	if (error == 0)
+	if (error == 0) {
+		/* block layout checks this! */
+		server->pnfs_blksize = fsinfo->blksize;
 		set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype);
+	}
 
 	return error;
 }
@@ -4007,6 +4122,36 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
+static unsigned int
+nfs4_init_nonuniform_client_string(const struct nfs_client *clp,
+				   char *buf, size_t len)
+{
+	unsigned int result;
+
+	rcu_read_lock();
+	result = scnprintf(buf, len, "Linux NFSv4.0 %s/%s %s",
+				clp->cl_ipaddr,
+				rpc_peeraddr2str(clp->cl_rpcclient,
+							RPC_DISPLAY_ADDR),
+				rpc_peeraddr2str(clp->cl_rpcclient,
+							RPC_DISPLAY_PROTO));
+	rcu_read_unlock();
+	return result;
+}
+
+static unsigned int
+nfs4_init_uniform_client_string(const struct nfs_client *clp,
+				char *buf, size_t len)
+{
+	char *nodename = clp->cl_rpcclient->cl_nodename;
+
+	if (nfs4_client_id_uniquifier[0] != '\0')
+		nodename = nfs4_client_id_uniquifier;
+	return scnprintf(buf, len, "Linux NFSv%u.%u %s",
+				clp->rpc_ops->version, clp->cl_minorversion,
+				nodename);
+}
+
 /**
  * nfs4_proc_setclientid - Negotiate client ID
  * @clp: state data structure
@@ -4037,15 +4182,18 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 
 	/* nfs_client_id4 */
 	nfs4_init_boot_verifier(clp, &sc_verifier);
-	rcu_read_lock();
-	setclientid.sc_name_len = scnprintf(setclientid.sc_name,
-			sizeof(setclientid.sc_name), "%s/%s %s",
-			clp->cl_ipaddr,
-			rpc_peeraddr2str(clp->cl_rpcclient,
-						RPC_DISPLAY_ADDR),
-			rpc_peeraddr2str(clp->cl_rpcclient,
-						RPC_DISPLAY_PROTO));
+	if (test_bit(NFS_CS_MIGRATION, &clp->cl_flags))
+		setclientid.sc_name_len =
+				nfs4_init_uniform_client_string(clp,
+						setclientid.sc_name,
+						sizeof(setclientid.sc_name));
+	else
+		setclientid.sc_name_len =
+				nfs4_init_nonuniform_client_string(clp,
+						setclientid.sc_name,
+						sizeof(setclientid.sc_name));
 	/* cb_client4 */
+	rcu_read_lock();
 	setclientid.sc_netid_len = scnprintf(setclientid.sc_netid,
 				sizeof(setclientid.sc_netid),
 				rpc_peeraddr2str(clp->cl_rpcclient,
@@ -4383,6 +4531,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data)
 			if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN)
 				rpc_restart_call_prepare(task);
 	}
+	nfs_release_seqid(calldata->arg.seqid);
 }
 
 static void nfs4_locku_prepare(struct rpc_task *task, void *data)
@@ -4391,7 +4540,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 
 	if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
 		return;
-	if ((calldata->lsp->ls_flags & NFS_LOCK_INITIALIZED) == 0) {
+	if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) {
 		/* Note: exit _without_ running nfs4_locku_done */
 		task->tk_action = NULL;
 		return;
@@ -4399,9 +4548,11 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 	calldata->timestamp = jiffies;
 	if (nfs4_setup_sequence(calldata->server,
 				&calldata->arg.seq_args,
-				&calldata->res.seq_res, task))
-		return;
-	rpc_call_start(task);
+				&calldata->res.seq_res,
+				task) != 0)
+		nfs_release_seqid(calldata->arg.seqid);
+	else
+		rpc_call_start(task);
 }
 
 static const struct rpc_call_ops nfs4_locku_ops = {
@@ -4546,7 +4697,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 	/* Do we need to do an open_to_lock_owner? */
 	if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
 		if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0)
-			return;
+			goto out_release_lock_seqid;
 		data->arg.open_stateid = &state->stateid;
 		data->arg.new_lock_owner = 1;
 		data->res.open_seqid = data->arg.open_seqid;
@@ -4555,10 +4706,15 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 	data->timestamp = jiffies;
 	if (nfs4_setup_sequence(data->server,
 				&data->arg.seq_args,
-				&data->res.seq_res, task))
+				&data->res.seq_res,
+				task) == 0) {
+		rpc_call_start(task);
 		return;
-	rpc_call_start(task);
-	dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
+	}
+	nfs_release_seqid(data->arg.open_seqid);
+out_release_lock_seqid:
+	nfs_release_seqid(data->arg.lock_seqid);
+	dprintk("%s: done!, ret = %d\n", __func__, task->tk_status);
 }
 
 static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata)
@@ -4585,7 +4741,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
 	}
 	if (data->rpc_status == 0) {
 		nfs4_stateid_copy(&data->lsp->ls_stateid, &data->res.stateid);
-		data->lsp->ls_flags |= NFS_LOCK_INITIALIZED;
+		set_bit(NFS_LOCK_INITIALIZED, &data->lsp->ls_flags);
 		renew_lease(NFS_SERVER(data->ctx->dentry->d_inode), data->timestamp);
 	}
 out:
@@ -4632,7 +4788,7 @@ static void nfs4_handle_setlk_error(struct nfs_server *server, struct nfs4_lock_
 	case -NFS4ERR_BAD_STATEID:
 		lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
 		if (new_lock_owner != 0 ||
-		   (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
+		   test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0)
 			nfs4_schedule_stateid_recovery(server, lsp->ls_state);
 		break;
 	case -NFS4ERR_STALE_STATEID:
@@ -4756,7 +4912,7 @@ static int nfs41_check_expired_locks(struct nfs4_state *state)
 	struct nfs_server *server = NFS_SERVER(state->inode);
 
 	list_for_each_entry(lsp, &state->lock_states, ls_locks) {
-		if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+		if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
 			status = nfs41_test_stateid(server, &lsp->ls_stateid);
 			if (status != NFS_OK) {
 				/* Free the stateid unless the server
@@ -4764,7 +4920,7 @@ static int nfs41_check_expired_locks(struct nfs4_state *state)
 				if (status != -NFS4ERR_BAD_STATEID)
 					nfs41_free_stateid(server,
 							&lsp->ls_stateid);
-				lsp->ls_flags &= ~NFS_LOCK_INITIALIZED;
+				clear_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
 				ret = status;
 			}
 		}
@@ -5267,10 +5423,8 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	};
 
 	nfs4_init_boot_verifier(clp, &verifier);
-	args.id_len = scnprintf(args.id, sizeof(args.id),
-				"%s/%s",
-				clp->cl_ipaddr,
-				clp->cl_rpcclient->cl_nodename);
+	args.id_len = nfs4_init_uniform_client_string(clp, args.id,
+							sizeof(args.id));
 	dprintk("NFS call  exchange_id auth=%s, '%.*s'\n",
 		clp->cl_rpcclient->cl_auth->au_ops->au_name,
 		args.id_len, args.id);
@@ -5391,6 +5545,8 @@ int nfs4_destroy_clientid(struct nfs_client *clp)
 		goto out;
 	if (clp->cl_exchange_flags == 0)
 		goto out;
+	if (clp->cl_preserve_clid)
+		goto out;
 	cred = nfs4_get_exchange_id_cred(clp);
 	ret = nfs4_proc_destroy_clientid(clp, cred);
 	if (cred)
@@ -5521,7 +5677,7 @@ static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl,
 		tbl->slots = new;
 		tbl->max_slots = max_slots;
 	}
-	tbl->highest_used_slotid = -1;	/* no slot is currently used */
+	tbl->highest_used_slotid = NFS4_NO_SLOT;
 	for (i = 0; i < tbl->max_slots; i++)
 		tbl->slots[i].seq_nr = ivalue;
 	spin_unlock(&tbl->slot_tbl_lock);
@@ -6196,26 +6352,44 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
-	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	struct inode *inode = lgp->args.inode;
+	struct nfs_server *server = NFS_SERVER(inode);
+	struct pnfs_layout_hdr *lo;
+	struct nfs4_state *state = NULL;
 
 	dprintk("--> %s\n", __func__);
 
 	if (!nfs4_sequence_done(task, &lgp->res.seq_res))
-		return;
+		goto out;
 
 	switch (task->tk_status) {
 	case 0:
-		break;
+		goto out;
 	case -NFS4ERR_LAYOUTTRYLATER:
 	case -NFS4ERR_RECALLCONFLICT:
 		task->tk_status = -NFS4ERR_DELAY;
-		/* Fall through */
-	default:
-		if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
-			rpc_restart_call_prepare(task);
-			return;
+		break;
+	case -NFS4ERR_EXPIRED:
+	case -NFS4ERR_BAD_STATEID:
+		spin_lock(&inode->i_lock);
+		lo = NFS_I(inode)->layout;
+		if (!lo || list_empty(&lo->plh_segs)) {
+			spin_unlock(&inode->i_lock);
+			/* If the open stateid was bad, then recover it. */
+			state = lgp->args.ctx->state;
+		} else {
+			LIST_HEAD(head);
+
+			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+			spin_unlock(&inode->i_lock);
+			/* Mark the bad layout state as invalid, then
+			 * retry using the open stateid. */
+			pnfs_free_lseg_list(&head);
 		}
 	}
+	if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+		rpc_restart_call_prepare(task);
+out:
 	dprintk("<-- %s\n", __func__);
 }
 
@@ -6282,7 +6456,8 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
 	.rpc_release = nfs4_layoutget_release,
 };
 
-void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
+struct pnfs_layout_segment *
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 {
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
 	size_t max_pages = max_response_pages(server);
@@ -6299,6 +6474,7 @@ void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 		.callback_data = lgp,
 		.flags = RPC_TASK_ASYNC,
 	};
+	struct pnfs_layout_segment *lseg = NULL;
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
@@ -6306,7 +6482,7 @@ void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
 	if (!lgp->args.layout.pages) {
 		nfs4_layoutget_release(lgp);
-		return;
+		return ERR_PTR(-ENOMEM);
 	}
 	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
 
@@ -6315,15 +6491,17 @@ void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 	nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
-		return;
+		return ERR_CAST(task);
 	status = nfs4_wait_for_completion_rpc_task(task);
 	if (status == 0)
 		status = task->tk_status;
 	if (status == 0)
-		status = pnfs_layout_process(lgp);
+		lseg = pnfs_layout_process(lgp);
 	rpc_put_task(task);
 	dprintk("<-- %s status=%d\n", __func__, status);
-	return;
+	if (status)
+		return ERR_PTR(status);
+	return lseg;
 }
 
 static void
@@ -6342,7 +6520,6 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutreturn *lrp = calldata;
 	struct nfs_server *server;
-	struct pnfs_layout_hdr *lo = lrp->args.layout;
 
 	dprintk("--> %s\n", __func__);
 
@@ -6354,20 +6531,21 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
 		rpc_restart_call_prepare(task);
 		return;
 	}
-	spin_lock(&lo->plh_inode->i_lock);
-	if (task->tk_status == 0 && lrp->res.lrs_present)
-		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
-	lo->plh_block_lgets--;
-	spin_unlock(&lo->plh_inode->i_lock);
 	dprintk("<-- %s\n", __func__);
 }
 
 static void nfs4_layoutreturn_release(void *calldata)
 {
 	struct nfs4_layoutreturn *lrp = calldata;
+	struct pnfs_layout_hdr *lo = lrp->args.layout;
 
 	dprintk("--> %s\n", __func__);
-	put_layout_hdr(lrp->args.layout);
+	spin_lock(&lo->plh_inode->i_lock);
+	if (lrp->res.lrs_present)
+		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	lo->plh_block_lgets--;
+	spin_unlock(&lo->plh_inode->i_lock);
+	pnfs_put_layout_hdr(lrp->args.layout);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
 }
@@ -6541,7 +6719,7 @@ static void nfs4_layoutcommit_release(void *calldata)
 		list_del_init(&lseg->pls_lc_list);
 		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
 				       &lseg->pls_flags))
-			put_lseg(lseg);
+			pnfs_put_lseg(lseg);
 	}
 
 	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
@@ -6800,6 +6978,7 @@ static const struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = {
 	.recover_lock	= nfs4_lock_reclaim,
 	.establish_clid = nfs4_init_clientid,
 	.get_clid_cred	= nfs4_get_setclientid_cred,
+	.detect_trunking = nfs40_discover_server_trunking,
 };
 
 #if defined(CONFIG_NFS_V4_1)
@@ -6811,6 +6990,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
 	.establish_clid = nfs41_init_clientid,
 	.get_clid_cred	= nfs4_get_exchange_id_cred,
 	.reclaim_complete = nfs41_proc_reclaim_complete,
+	.detect_trunking = nfs41_discover_server_trunking,
 };
 #endif /* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 55148def5540..c351e6b39838 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -51,18 +51,21 @@
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
 
+#include <linux/sunrpc/clnt.h>
+
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
 #include "internal.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_STATE
 
 #define OPENOWNER_POOL_SIZE	8
 
 const nfs4_stateid zero_stateid;
-
+static DEFINE_MUTEX(nfs_clid_init_mutex);
 static LIST_HEAD(nfs4_clientid_list);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
@@ -73,12 +76,13 @@ int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 	};
 	unsigned short port;
 	int status;
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 
 	if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
 		goto do_confirm;
-	port = nfs_callback_tcpport;
+	port = nn->nfs_callback_tcpport;
 	if (clp->cl_addr.ss_family == AF_INET6)
-		port = nfs_callback_tcpport6;
+		port = nn->nfs_callback_tcpport6;
 
 	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
 	if (status != 0)
@@ -96,6 +100,56 @@ out:
 	return status;
 }
 
+/**
+ * nfs40_discover_server_trunking - Detect server IP address trunking (mv0)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns zero, a negative errno, or a negative NFS4ERR status.
+ * If zero is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs40_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   struct rpc_cred *cred)
+{
+	struct nfs4_setclientid_res clid = {
+		.clientid = clp->cl_clientid,
+		.confirm = clp->cl_confirm,
+	};
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+	unsigned short port;
+	int status;
+
+	port = nn->nfs_callback_tcpport;
+	if (clp->cl_addr.ss_family == AF_INET6)
+		port = nn->nfs_callback_tcpport6;
+
+	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
+	if (status != 0)
+		goto out;
+	clp->cl_clientid = clid.clientid;
+	clp->cl_confirm = clid.confirm;
+
+	status = nfs40_walk_client_list(clp, result, cred);
+	switch (status) {
+	case -NFS4ERR_STALE_CLIENTID:
+		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	case 0:
+		/* Sustain the lease, even if it's empty.  If the clientid4
+		 * goes stale it's of no use for trunking discovery. */
+		nfs4_schedule_state_renewal(*result);
+		break;
+	}
+
+out:
+	return status;
+}
+
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
 {
 	struct rpc_cred *cred = NULL;
@@ -275,6 +329,33 @@ out:
 	return status;
 }
 
+/**
+ * nfs41_discover_server_trunking - Detect server IP address trunking (mv1)
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ * @cred: credential to use for trunking test
+ *
+ * Returns NFS4_OK, a negative errno, or a negative NFS4ERR status.
+ * If NFS4_OK is returned, an nfs_client pointer is planted in
+ * "result".
+ *
+ * Note: The returned client may not yet be marked ready.
+ */
+int nfs41_discover_server_trunking(struct nfs_client *clp,
+				   struct nfs_client **result,
+				   struct rpc_cred *cred)
+{
+	int status;
+
+	status = nfs4_proc_exchange_id(clp, cred);
+	if (status != NFS4_OK)
+		return status;
+	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+
+	return nfs41_walk_client_list(clp, result, cred);
+}
+
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
@@ -729,11 +810,8 @@ static void __nfs4_close(struct nfs4_state *state,
 	if (!call_close) {
 		nfs4_put_open_state(state);
 		nfs4_put_state_owner(owner);
-	} else {
-		bool roc = pnfs_roc(state->inode);
-
-		nfs4_do_close(state, gfp_mask, wait, roc);
-	}
+	} else
+		nfs4_do_close(state, gfp_mask, wait);
 }
 
 void nfs4_close_state(struct nfs4_state *state, fmode_t fmode)
@@ -865,7 +943,7 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
 	if (list_empty(&state->lock_states))
 		clear_bit(LK_STATE_IN_USE, &state->flags);
 	spin_unlock(&state->state_lock);
-	if (lsp->ls_flags & NFS_LOCK_INITIALIZED) {
+	if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
 		if (nfs4_release_lockowner(lsp) == 0)
 			return;
 	}
@@ -911,17 +989,25 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 }
 
 static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state,
-		fl_owner_t fl_owner, pid_t fl_pid)
+		const struct nfs_lockowner *lockowner)
 {
 	struct nfs4_lock_state *lsp;
+	fl_owner_t fl_owner;
+	pid_t fl_pid;
 	bool ret = false;
 
+
+	if (lockowner == NULL)
+		goto out;
+
 	if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
 		goto out;
 
+	fl_owner = lockowner->l_owner;
+	fl_pid = lockowner->l_pid;
 	spin_lock(&state->state_lock);
 	lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
-	if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0) {
+	if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
 		nfs4_stateid_copy(dst, &lsp->ls_stateid);
 		ret = true;
 	}
@@ -946,11 +1032,11 @@ static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
  * requests.
  */
 void nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
-		fmode_t fmode, fl_owner_t fl_owner, pid_t fl_pid)
+		fmode_t fmode, const struct nfs_lockowner *lockowner)
 {
 	if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
 		return;
-	if (nfs4_copy_lock_stateid(dst, state, fl_owner, fl_pid))
+	if (nfs4_copy_lock_stateid(dst, state, lockowner))
 		return;
 	nfs4_copy_open_stateid(dst, state);
 }
@@ -1289,7 +1375,7 @@ restart:
 			if (status >= 0) {
 				spin_lock(&state->state_lock);
 				list_for_each_entry(lock, &state->lock_states, ls_locks) {
-					if (!(lock->ls_flags & NFS_LOCK_INITIALIZED))
+					if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
 						pr_warn_ratelimited("NFS: "
 							"%s: Lock reclaim "
 							"failed!\n", __func__);
@@ -1361,7 +1447,7 @@ static void nfs4_clear_open_state(struct nfs4_state *state)
 	spin_lock(&state->state_lock);
 	list_for_each_entry(lock, &state->lock_states, ls_locks) {
 		lock->ls_seqid.flags = 0;
-		lock->ls_flags &= ~NFS_LOCK_INITIALIZED;
+		clear_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags);
 	}
 	spin_unlock(&state->state_lock);
 }
@@ -1595,8 +1681,8 @@ out:
 	return nfs4_recovery_handle_error(clp, status);
 }
 
-/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
- * on EXCHANGE_ID for v4.1
+/* Set NFS4CLNT_LEASE_EXPIRED and reclaim reboot state for all v4.0 errors
+ * and for recoverable errors on EXCHANGE_ID for v4.1
  */
 static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 {
@@ -1606,8 +1692,12 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 			return -ESERVERFAULT;
 		/* Lease confirmation error: retry after purging the lease */
 		ssleep(1);
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		break;
 	case -NFS4ERR_STALE_CLIENTID:
 		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		nfs4_state_clear_reclaim_reboot(clp);
+		nfs4_state_start_reclaim_reboot(clp);
 		break;
 	case -NFS4ERR_CLID_INUSE:
 		pr_err("NFS: Server %s reports our clientid is in use\n",
@@ -1698,6 +1788,109 @@ static int nfs4_purge_lease(struct nfs_client *clp)
 	return 0;
 }
 
+/**
+ * nfs4_discover_server_trunking - Detect server IP address trunking
+ *
+ * @clp: nfs_client under test
+ * @result: OUT: found nfs_client, or clp
+ *
+ * Returns zero or a negative errno.  If zero is returned,
+ * an nfs_client pointer is planted in "result".
+ *
+ * Note: since we are invoked in process context, and
+ * not from inside the state manager, we cannot use
+ * nfs4_handle_reclaim_lease_error().
+ */
+int nfs4_discover_server_trunking(struct nfs_client *clp,
+				  struct nfs_client **result)
+{
+	const struct nfs4_state_recovery_ops *ops =
+				clp->cl_mvops->reboot_recovery_ops;
+	rpc_authflavor_t *flavors, flav, save;
+	struct rpc_clnt *clnt;
+	struct rpc_cred *cred;
+	int i, len, status;
+
+	dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname);
+
+	len = NFS_MAX_SECFLAVORS;
+	flavors = kcalloc(len, sizeof(*flavors), GFP_KERNEL);
+	if (flavors == NULL) {
+		status = -ENOMEM;
+		goto out;
+	}
+	len = rpcauth_list_flavors(flavors, len);
+	if (len < 0) {
+		status = len;
+		goto out_free;
+	}
+	clnt = clp->cl_rpcclient;
+	save = clnt->cl_auth->au_flavor;
+	i = 0;
+
+	mutex_lock(&nfs_clid_init_mutex);
+	status  = -ENOENT;
+again:
+	cred = ops->get_clid_cred(clp);
+	if (cred == NULL)
+		goto out_unlock;
+
+	status = ops->detect_trunking(clp, result, cred);
+	put_rpccred(cred);
+	switch (status) {
+	case 0:
+		break;
+
+	case -EACCES:
+		if (clp->cl_machine_cred == NULL)
+			break;
+		/* Handle case where the user hasn't set up machine creds */
+		nfs4_clear_machine_cred(clp);
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EAGAIN:
+		ssleep(1);
+		dprintk("NFS: %s after status %d, retrying\n",
+			__func__, status);
+		goto again;
+
+	case -NFS4ERR_CLID_INUSE:
+	case -NFS4ERR_WRONGSEC:
+		status = -EPERM;
+		if (i >= len)
+			break;
+
+		flav = flavors[i++];
+		if (flav == save)
+			flav = flavors[i++];
+		clnt = rpc_clone_client_set_auth(clnt, flav);
+		if (IS_ERR(clnt)) {
+			status = PTR_ERR(clnt);
+			break;
+		}
+		clp->cl_rpcclient = clnt;
+		goto again;
+
+	case -NFS4ERR_MINOR_VERS_MISMATCH:
+		status = -EPROTONOSUPPORT;
+		break;
+
+	case -EKEYEXPIRED:
+		nfs4_warn_keyexpired(clp->cl_hostname);
+	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
+				 * in nfs4_exchange_id */
+		status = -EKEYEXPIRED;
+	}
+
+out_unlock:
+	mutex_unlock(&nfs_clid_init_mutex);
+out_free:
+	kfree(flavors);
+out:
+	dprintk("NFS: %s: status = %d\n", __func__, status);
+	return status;
+}
+
 #ifdef CONFIG_NFS_V4_1
 void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
@@ -2008,6 +2201,7 @@ out_error:
 	pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s"
 			" with error %d\n", section_sep, section,
 			clp->cl_hostname, -status);
+	ssleep(1);
 	nfs4_end_drain_session(clp);
 	nfs4_clear_state_manager_bit(clp);
 }
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 5729bc8aa75d..2628d921b7e3 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -9,6 +9,7 @@
 #include <linux/nfs_idmap.h>
 #include <linux/nfs_fs.h>
 
+#include "nfs4_fs.h"
 #include "callback.h"
 
 static const int nfs_set_port_min = 0;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 8dba6bd48557..40836ee5dc3a 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -447,12 +447,14 @@ static int nfs4_stat_to_errno(int);
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_open_maxsz + \
+				encode_access_maxsz + \
 				encode_getfh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_open_sz        (compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_open_maxsz + \
+				decode_access_maxsz + \
 				decode_getfh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_open_confirm_sz \
@@ -467,11 +469,13 @@ static int nfs4_stat_to_errno(int);
 					encode_sequence_maxsz + \
 					encode_putfh_maxsz + \
 					encode_open_maxsz + \
+					encode_access_maxsz + \
 					encode_getattr_maxsz)
 #define NFS4_dec_open_noattr_sz	(compound_decode_hdr_maxsz + \
 					decode_sequence_maxsz + \
 					decode_putfh_maxsz + \
 					decode_open_maxsz + \
+					decode_access_maxsz + \
 					decode_getattr_maxsz)
 #define NFS4_enc_open_downgrade_sz \
 				(compound_encode_hdr_maxsz + \
@@ -1509,8 +1513,12 @@ static void encode_open_stateid(struct xdr_stream *xdr,
 	nfs4_stateid stateid;
 
 	if (ctx->state != NULL) {
+		const struct nfs_lockowner *lockowner = NULL;
+
+		if (l_ctx != NULL)
+			lockowner = &l_ctx->lockowner;
 		nfs4_select_rw_stateid(&stateid, ctx->state,
-				fmode, l_ctx->lockowner, l_ctx->pid);
+				fmode, lockowner);
 		if (zero_seqid)
 			stateid.seqid = 0;
 		encode_nfs4_stateid(xdr, &stateid);
@@ -2216,6 +2224,8 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_open(xdr, args, &hdr);
 	encode_getfh(xdr, &hdr);
+	if (args->access)
+		encode_access(xdr, args->access, &hdr);
 	encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr);
 	encode_nops(&hdr);
 }
@@ -2252,7 +2262,9 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_open(xdr, args, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
+	if (args->access)
+		encode_access(xdr, args->access, &hdr);
+	encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -4095,7 +4107,7 @@ out_overflow:
 	return -EIO;
 }
 
-static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access)
+static int decode_access(struct xdr_stream *xdr, u32 *supported, u32 *access)
 {
 	__be32 *p;
 	uint32_t supp, acc;
@@ -4109,8 +4121,8 @@ static int decode_access(struct xdr_stream *xdr, struct nfs4_accessres *access)
 		goto out_overflow;
 	supp = be32_to_cpup(p++);
 	acc = be32_to_cpup(p);
-	access->supported = supp;
-	access->access = acc;
+	*supported = supp;
+	*access = acc;
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -5642,7 +5654,8 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr,
 	 * and places the remaining xdr data in xdr_buf->tail
 	 */
 	pdev->mincount = be32_to_cpup(p);
-	xdr_read_pages(xdr, pdev->mincount); /* include space for the length */
+	if (xdr_read_pages(xdr, pdev->mincount) != pdev->mincount)
+		goto out_overflow;
 
 	/* Parse notification bitmap, verifying that it is zero. */
 	p = xdr_inline_decode(xdr, 4);
@@ -5887,7 +5900,7 @@ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status != 0)
 		goto out;
-	status = decode_access(xdr, res);
+	status = decode_access(xdr, &res->supported, &res->access);
 	if (status != 0)
 		goto out;
 	decode_getfattr(xdr, res->fattr, res->server);
@@ -6228,6 +6241,8 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_getfh(xdr, &res->fh);
 	if (status)
 		goto out;
+	if (res->access_request)
+		decode_access(xdr, &res->access_supported, &res->access_result);
 	decode_getfattr(xdr, res->f_attr, res->server);
 out:
 	return status;
@@ -6276,6 +6291,8 @@ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp,
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
+	if (res->access_request)
+		decode_access(xdr, &res->access_supported, &res->access_result);
 	decode_getfattr(xdr, res->f_attr, res->server);
 out:
 	return status;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index ea6d111b03e9..c6f990656f89 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -41,6 +41,7 @@
 #include <scsi/osd_ore.h>
 
 #include "objlayout.h"
+#include "../internal.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
@@ -368,7 +369,7 @@ void objio_free_result(struct objlayout_io_res *oir)
 	kfree(objios);
 }
 
-enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
+static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
 {
 	switch (oep) {
 	case OSD_ERR_PRI_NO_ERROR:
@@ -573,7 +574,7 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
 			(unsigned long)pgio->pg_layout_private;
 }
 
-void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	pnfs_generic_pg_init_read(pgio, req);
 	if (unlikely(pgio->pg_lseg == NULL))
@@ -603,11 +604,17 @@ static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
 	return false;
 }
 
-void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	unsigned long stripe_end = 0;
+	u64 wb_size;
 
-	pnfs_generic_pg_init_write(pgio, req);
+	if (pgio->pg_dreq == NULL)
+		wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
+	else
+		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+	pnfs_generic_pg_init_write(pgio, req, wb_size);
 	if (unlikely(pgio->pg_lseg == NULL))
 		return; /* Not pNFS */
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 311a79681e2b..e56e846e9d2d 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -102,6 +102,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 		   unsigned int offset, unsigned int count)
 {
 	struct nfs_page		*req;
+	struct nfs_lock_context *l_ctx;
 
 	/* try to allocate the request struct */
 	req = nfs_page_alloc();
@@ -109,11 +110,12 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 		return ERR_PTR(-ENOMEM);
 
 	/* get lock context early so we can deal with alloc failures */
-	req->wb_lock_context = nfs_get_lock_context(ctx);
-	if (req->wb_lock_context == NULL) {
+	l_ctx = nfs_get_lock_context(ctx);
+	if (IS_ERR(l_ctx)) {
 		nfs_page_free(req);
-		return ERR_PTR(-ENOMEM);
+		return ERR_CAST(l_ctx);
 	}
+	req->wb_lock_context = l_ctx;
 
 	/* Initialize the request struct. Initially, we assume a
 	 * long write-back delay. This will be adjusted in
@@ -290,7 +292,9 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 {
 	if (req->wb_context->cred != prev->wb_context->cred)
 		return false;
-	if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
+	if (req->wb_lock_context->lockowner.l_owner != prev->wb_lock_context->lockowner.l_owner)
+		return false;
+	if (req->wb_lock_context->lockowner.l_pid != prev->wb_lock_context->lockowner.l_pid)
 		return false;
 	if (req->wb_context->state != prev->wb_context->state)
 		return false;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 2e00feacd4be..2878f97bd78d 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -35,6 +35,7 @@
 #include "iostat.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
+#define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
 
 /* Locking:
  *
@@ -190,7 +191,7 @@ EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);
 
 /* Need to hold i_lock if caller does not already hold reference */
 void
-get_layout_hdr(struct pnfs_layout_hdr *lo)
+pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo)
 {
 	atomic_inc(&lo->plh_refcount);
 }
@@ -199,43 +200,107 @@ static struct pnfs_layout_hdr *
 pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags)
 {
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
-	return ld->alloc_layout_hdr ? ld->alloc_layout_hdr(ino, gfp_flags) :
-		kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags);
+	return ld->alloc_layout_hdr(ino, gfp_flags);
 }
 
 static void
 pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
 {
-	struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld;
+	struct nfs_server *server = NFS_SERVER(lo->plh_inode);
+	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
+
+	if (!list_empty(&lo->plh_layouts)) {
+		struct nfs_client *clp = server->nfs_client;
+
+		spin_lock(&clp->cl_lock);
+		list_del_init(&lo->plh_layouts);
+		spin_unlock(&clp->cl_lock);
+	}
 	put_rpccred(lo->plh_lc_cred);
-	return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo);
+	return ld->free_layout_hdr(lo);
 }
 
 static void
-destroy_layout_hdr(struct pnfs_layout_hdr *lo)
+pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo)
 {
+	struct nfs_inode *nfsi = NFS_I(lo->plh_inode);
 	dprintk("%s: freeing layout cache %p\n", __func__, lo);
-	BUG_ON(!list_empty(&lo->plh_layouts));
-	NFS_I(lo->plh_inode)->layout = NULL;
-	pnfs_free_layout_hdr(lo);
+	nfsi->layout = NULL;
+	/* Reset MDS Threshold I/O counters */
+	nfsi->write_io = 0;
+	nfsi->read_io = 0;
+}
+
+void
+pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	struct inode *inode = lo->plh_inode;
+
+	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
+		pnfs_detach_layout_hdr(lo);
+		spin_unlock(&inode->i_lock);
+		pnfs_free_layout_hdr(lo);
+	}
+}
+
+static int
+pnfs_iomode_to_fail_bit(u32 iomode)
+{
+	return iomode == IOMODE_RW ?
+		NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
 }
 
 static void
-put_layout_hdr_locked(struct pnfs_layout_hdr *lo)
+pnfs_layout_set_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
 {
-	if (atomic_dec_and_test(&lo->plh_refcount))
-		destroy_layout_hdr(lo);
+	lo->plh_retry_timestamp = jiffies;
+	if (test_and_set_bit(fail_bit, &lo->plh_flags))
+		atomic_inc(&lo->plh_refcount);
 }
 
-void
-put_layout_hdr(struct pnfs_layout_hdr *lo)
+static void
+pnfs_layout_clear_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
+{
+	if (test_and_clear_bit(fail_bit, &lo->plh_flags))
+		atomic_dec(&lo->plh_refcount);
+}
+
+static void
+pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
 {
 	struct inode *inode = lo->plh_inode;
+	struct pnfs_layout_range range = {
+		.iomode = iomode,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+	LIST_HEAD(head);
 
-	if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
-		destroy_layout_hdr(lo);
-		spin_unlock(&inode->i_lock);
+	spin_lock(&inode->i_lock);
+	pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+	pnfs_mark_matching_lsegs_invalid(lo, &head, &range);
+	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&head);
+	dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
+			iomode == IOMODE_RW ?  "RW" : "READ");
+}
+
+static bool
+pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode)
+{
+	unsigned long start, end;
+	int fail_bit = pnfs_iomode_to_fail_bit(iomode);
+
+	if (test_bit(fail_bit, &lo->plh_flags) == 0)
+		return false;
+	end = jiffies;
+	start = end - PNFS_LAYOUTGET_RETRY_TIMEOUT;
+	if (!time_in_range(lo->plh_retry_timestamp, start, end)) {
+		/* It is time to retry the failed layoutgets */
+		pnfs_layout_clear_fail_bit(lo, fail_bit);
+		return false;
 	}
+	return true;
 }
 
 static void
@@ -249,33 +314,32 @@ init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
 	lseg->pls_layout = lo;
 }
 
-static void free_lseg(struct pnfs_layout_segment *lseg)
+static void pnfs_free_lseg(struct pnfs_layout_segment *lseg)
 {
 	struct inode *ino = lseg->pls_layout->plh_inode;
 
 	NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
-	/* Matched by get_layout_hdr in pnfs_insert_layout */
-	put_layout_hdr(NFS_I(ino)->layout);
 }
 
 static void
-put_lseg_common(struct pnfs_layout_segment *lseg)
+pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
+		struct pnfs_layout_segment *lseg)
 {
-	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct inode *inode = lo->plh_inode;
 
 	WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 	list_del_init(&lseg->pls_list);
-	if (list_empty(&lseg->pls_layout->plh_segs)) {
-		set_bit(NFS_LAYOUT_DESTROYED, &lseg->pls_layout->plh_flags);
-		/* Matched by initial refcount set in alloc_init_layout_hdr */
-		put_layout_hdr_locked(lseg->pls_layout);
-	}
+	/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
+	atomic_dec(&lo->plh_refcount);
+	if (list_empty(&lo->plh_segs))
+		clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
 void
-put_lseg(struct pnfs_layout_segment *lseg)
+pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
+	struct pnfs_layout_hdr *lo;
 	struct inode *inode;
 
 	if (!lseg)
@@ -284,17 +348,17 @@ put_lseg(struct pnfs_layout_segment *lseg)
 	dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
 		atomic_read(&lseg->pls_refcount),
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
-	inode = lseg->pls_layout->plh_inode;
+	lo = lseg->pls_layout;
+	inode = lo->plh_inode;
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
-		LIST_HEAD(free_me);
-
-		put_lseg_common(lseg);
-		list_add(&lseg->pls_list, &free_me);
+		pnfs_get_layout_hdr(lo);
+		pnfs_layout_remove_lseg(lo, lseg);
 		spin_unlock(&inode->i_lock);
-		pnfs_free_lseg_list(&free_me);
+		pnfs_free_lseg(lseg);
+		pnfs_put_layout_hdr(lo);
 	}
 }
-EXPORT_SYMBOL_GPL(put_lseg);
+EXPORT_SYMBOL_GPL(pnfs_put_lseg);
 
 static inline u64
 end_offset(u64 start, u64 len)
@@ -378,7 +442,7 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 		dprintk("%s: lseg %p ref %d\n", __func__, lseg,
 			atomic_read(&lseg->pls_refcount));
 		if (atomic_dec_and_test(&lseg->pls_refcount)) {
-			put_lseg_common(lseg);
+			pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
 			list_add(&lseg->pls_list, tmp_list);
 			rv = 1;
 		}
@@ -390,7 +454,7 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
  * after call.
  */
 int
-mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 			    struct list_head *tmp_list,
 			    struct pnfs_layout_range *recall_range)
 {
@@ -399,14 +463,8 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 
 	dprintk("%s:Begin lo %p\n", __func__, lo);
 
-	if (list_empty(&lo->plh_segs)) {
-		/* Reset MDS Threshold I/O counters */
-		NFS_I(lo->plh_inode)->write_io = 0;
-		NFS_I(lo->plh_inode)->read_io = 0;
-		if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags))
-			put_layout_hdr_locked(lo);
+	if (list_empty(&lo->plh_segs))
 		return 0;
-	}
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
 		if (!recall_range ||
 		    should_free_lseg(&lseg->pls_range, recall_range)) {
@@ -426,25 +484,13 @@ void
 pnfs_free_lseg_list(struct list_head *free_me)
 {
 	struct pnfs_layout_segment *lseg, *tmp;
-	struct pnfs_layout_hdr *lo;
 
 	if (list_empty(free_me))
 		return;
 
-	lo = list_first_entry(free_me, struct pnfs_layout_segment,
-			      pls_list)->pls_layout;
-
-	if (test_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags)) {
-		struct nfs_client *clp;
-
-		clp = NFS_SERVER(lo->plh_inode)->nfs_client;
-		spin_lock(&clp->cl_lock);
-		list_del_init(&lo->plh_layouts);
-		spin_unlock(&clp->cl_lock);
-	}
 	list_for_each_entry_safe(lseg, tmp, free_me, pls_list) {
 		list_del(&lseg->pls_list);
-		free_lseg(lseg);
+		pnfs_free_lseg(lseg);
 	}
 }
 
@@ -458,10 +504,15 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	lo = nfsi->layout;
 	if (lo) {
 		lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-		mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
-	}
-	spin_unlock(&nfsi->vfs_inode.i_lock);
-	pnfs_free_lseg_list(&tmp_list);
+		pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+		pnfs_get_layout_hdr(lo);
+		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
+		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
+		spin_unlock(&nfsi->vfs_inode.i_lock);
+		pnfs_free_lseg_list(&tmp_list);
+		pnfs_put_layout_hdr(lo);
+	} else
+		spin_unlock(&nfsi->vfs_inode.i_lock);
 }
 EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
 
@@ -498,46 +549,54 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
 	}
 }
 
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+	return (s32)s1 - (s32)s2 > 0;
+}
+
 /* update lo->plh_stateid with new if is more recent */
 void
 pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
 			bool update_barrier)
 {
-	u32 oldseq, newseq;
+	u32 oldseq, newseq, new_barrier;
+	int empty = list_empty(&lo->plh_segs);
 
 	oldseq = be32_to_cpu(lo->plh_stateid.seqid);
 	newseq = be32_to_cpu(new->seqid);
-	if ((int)(newseq - oldseq) > 0) {
+	if (empty || pnfs_seqid_is_newer(newseq, oldseq)) {
 		nfs4_stateid_copy(&lo->plh_stateid, new);
 		if (update_barrier) {
-			u32 new_barrier = be32_to_cpu(new->seqid);
-
-			if ((int)(new_barrier - lo->plh_barrier))
-				lo->plh_barrier = new_barrier;
+			new_barrier = be32_to_cpu(new->seqid);
 		} else {
 			/* Because of wraparound, we want to keep the barrier
-			 * "close" to the current seqids.  It needs to be
-			 * within 2**31 to count as "behind", so if it
-			 * gets too near that limit, give us a litle leeway
-			 * and bring it to within 2**30.
-			 * NOTE - and yes, this is all unsigned arithmetic.
+			 * "close" to the current seqids.
 			 */
-			if (unlikely((newseq - lo->plh_barrier) > (3 << 29)))
-				lo->plh_barrier = newseq - (1 << 30);
+			new_barrier = newseq - atomic_read(&lo->plh_outstanding);
 		}
+		if (empty || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+			lo->plh_barrier = new_barrier;
 	}
 }
 
+static bool
+pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
+		const nfs4_stateid *stateid)
+{
+	u32 seqid = be32_to_cpu(stateid->seqid);
+
+	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
+}
+
 /* lget is set to 1 if called from inside send_layoutget call chain */
 static bool
-pnfs_layoutgets_blocked(struct pnfs_layout_hdr *lo, nfs4_stateid *stateid,
-			int lget)
+pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, int lget)
 {
-	if ((stateid) &&
-	    (int)(lo->plh_barrier - be32_to_cpu(stateid->seqid)) >= 0)
-		return true;
 	return lo->plh_block_lgets ||
-		test_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags) ||
 		test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 		(list_empty(&lo->plh_segs) &&
 		 (atomic_read(&lo->plh_outstanding) > lget));
@@ -551,7 +610,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
-	if (pnfs_layoutgets_blocked(lo, NULL, 1)) {
+	if (pnfs_layoutgets_blocked(lo, 1)) {
 		status = -EAGAIN;
 	} else if (list_empty(&lo->plh_segs)) {
 		int seq;
@@ -582,7 +641,7 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	struct inode *ino = lo->plh_inode;
 	struct nfs_server *server = NFS_SERVER(ino);
 	struct nfs4_layoutget *lgp;
-	struct pnfs_layout_segment *lseg = NULL;
+	struct pnfs_layout_segment *lseg;
 
 	dprintk("--> %s\n", __func__);
 
@@ -599,16 +658,22 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	lgp->args.type = server->pnfs_curr_ld->id;
 	lgp->args.inode = ino;
 	lgp->args.ctx = get_nfs_open_context(ctx);
-	lgp->lsegpp = &lseg;
 	lgp->gfp_flags = gfp_flags;
 
 	/* Synchronously retrieve layout information from server and
 	 * store in lseg.
 	 */
-	nfs4_proc_layoutget(lgp, gfp_flags);
-	if (!lseg) {
-		/* remember that LAYOUTGET failed and suspend trying */
-		set_bit(lo_fail_bit(range->iomode), &lo->plh_flags);
+	lseg = nfs4_proc_layoutget(lgp, gfp_flags);
+	if (IS_ERR(lseg)) {
+		switch (PTR_ERR(lseg)) {
+		case -ENOMEM:
+		case -ERESTARTSYS:
+			break;
+		default:
+			/* remember that LAYOUTGET failed and suspend trying */
+			pnfs_layout_io_set_failed(lo, range->iomode);
+		}
+		return NULL;
 	}
 
 	return lseg;
@@ -636,25 +701,24 @@ _pnfs_return_layout(struct inode *ino)
 
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
-	if (!lo || pnfs_test_layout_returned(lo)) {
+	if (!lo) {
 		spin_unlock(&ino->i_lock);
 		dprintk("NFS: %s no layout to return\n", __func__);
 		goto out;
 	}
 	stateid = nfsi->layout->plh_stateid;
 	/* Reference matched in nfs4_layoutreturn_release */
-	get_layout_hdr(lo);
+	pnfs_get_layout_hdr(lo);
 	empty = list_empty(&lo->plh_segs);
-	mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+	pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
 		spin_unlock(&ino->i_lock);
-		put_layout_hdr(lo);
+		pnfs_put_layout_hdr(lo);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
 		goto out;
 	}
 	lo->plh_block_lgets++;
-	pnfs_mark_layout_returned(lo);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
@@ -663,10 +727,10 @@ _pnfs_return_layout(struct inode *ino)
 	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
 	if (unlikely(lrp == NULL)) {
 		status = -ENOMEM;
-		set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags);
-		set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags);
-		pnfs_clear_layout_returned(lo);
-		put_layout_hdr(lo);
+		spin_lock(&ino->i_lock);
+		lo->plh_block_lgets--;
+		spin_unlock(&ino->i_lock);
+		pnfs_put_layout_hdr(lo);
 		goto out;
 	}
 
@@ -703,7 +767,7 @@ bool pnfs_roc(struct inode *ino)
 	if (!found)
 		goto out_nolayout;
 	lo->plh_block_lgets++;
-	get_layout_hdr(lo); /* matched in pnfs_roc_release */
+	pnfs_get_layout_hdr(lo); /* matched in pnfs_roc_release */
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 	return true;
@@ -720,8 +784,12 @@ void pnfs_roc_release(struct inode *ino)
 	spin_lock(&ino->i_lock);
 	lo = NFS_I(ino)->layout;
 	lo->plh_block_lgets--;
-	put_layout_hdr_locked(lo);
-	spin_unlock(&ino->i_lock);
+	if (atomic_dec_and_test(&lo->plh_refcount)) {
+		pnfs_detach_layout_hdr(lo);
+		spin_unlock(&ino->i_lock);
+		pnfs_free_layout_hdr(lo);
+	} else
+		spin_unlock(&ino->i_lock);
 }
 
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
@@ -730,32 +798,34 @@ void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 
 	spin_lock(&ino->i_lock);
 	lo = NFS_I(ino)->layout;
-	if ((int)(barrier - lo->plh_barrier) > 0)
+	if (pnfs_seqid_is_newer(barrier, lo->plh_barrier))
 		lo->plh_barrier = barrier;
 	spin_unlock(&ino->i_lock);
 }
 
-bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 {
 	struct nfs_inode *nfsi = NFS_I(ino);
+	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg;
+	u32 current_seqid;
 	bool found = false;
 
 	spin_lock(&ino->i_lock);
 	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
 		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
+			rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
 			found = true;
-			break;
+			goto out;
 		}
-	if (!found) {
-		struct pnfs_layout_hdr *lo = nfsi->layout;
-		u32 current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
+	lo = nfsi->layout;
+	current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
 
-		/* Since close does not return a layout stateid for use as
-		 * a barrier, we choose the worst-case barrier.
-		 */
-		*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
-	}
+	/* Since close does not return a layout stateid for use as
+	 * a barrier, we choose the worst-case barrier.
+	 */
+	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
+out:
 	spin_unlock(&ino->i_lock);
 	return found;
 }
@@ -786,14 +856,13 @@ cmp_layout(struct pnfs_layout_range *l1,
 }
 
 static void
-pnfs_insert_layout(struct pnfs_layout_hdr *lo,
+pnfs_layout_insert_lseg(struct pnfs_layout_hdr *lo,
 		   struct pnfs_layout_segment *lseg)
 {
 	struct pnfs_layout_segment *lp;
 
 	dprintk("%s:Begin\n", __func__);
 
-	assert_spin_locked(&lo->plh_inode->i_lock);
 	list_for_each_entry(lp, &lo->plh_segs, pls_list) {
 		if (cmp_layout(&lseg->pls_range, &lp->pls_range) > 0)
 			continue;
@@ -813,7 +882,7 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
 		__func__, lseg, lseg->pls_range.iomode,
 		lseg->pls_range.offset, lseg->pls_range.length);
 out:
-	get_layout_hdr(lo);
+	pnfs_get_layout_hdr(lo);
 
 	dprintk("%s:Return\n", __func__);
 }
@@ -847,21 +916,19 @@ pnfs_find_alloc_layout(struct inode *ino,
 
 	dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout);
 
-	assert_spin_locked(&ino->i_lock);
-	if (nfsi->layout) {
-		if (test_bit(NFS_LAYOUT_DESTROYED, &nfsi->layout->plh_flags))
-			return NULL;
-		else
-			return nfsi->layout;
-	}
+	if (nfsi->layout != NULL)
+		goto out_existing;
 	spin_unlock(&ino->i_lock);
 	new = alloc_init_layout_hdr(ino, ctx, gfp_flags);
 	spin_lock(&ino->i_lock);
 
-	if (likely(nfsi->layout == NULL))	/* Won the race? */
+	if (likely(nfsi->layout == NULL)) {	/* Won the race? */
 		nfsi->layout = new;
-	else
+		return new;
+	} else if (new != NULL)
 		pnfs_free_layout_hdr(new);
+out_existing:
+	pnfs_get_layout_hdr(nfsi->layout);
 	return nfsi->layout;
 }
 
@@ -904,11 +971,10 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
 
 	dprintk("%s:Begin\n", __func__);
 
-	assert_spin_locked(&lo->plh_inode->i_lock);
 	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
 		    is_matching_lseg(&lseg->pls_range, range)) {
-			ret = get_lseg(lseg);
+			ret = pnfs_get_lseg(lseg);
 			break;
 		}
 		if (lseg->pls_range.offset > range->offset)
@@ -1013,7 +1079,6 @@ pnfs_update_layout(struct inode *ino,
 		.length = count,
 	};
 	unsigned pg_offset;
-	struct nfs_inode *nfsi = NFS_I(ino);
 	struct nfs_server *server = NFS_SERVER(ino);
 	struct nfs_client *clp = server->nfs_client;
 	struct pnfs_layout_hdr *lo;
@@ -1021,16 +1086,16 @@ pnfs_update_layout(struct inode *ino,
 	bool first = false;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
-		return NULL;
+		goto out;
 
 	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
-		return NULL;
+		goto out;
 
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
-		dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__);
-		goto out_unlock;
+		spin_unlock(&ino->i_lock);
+		goto out;
 	}
 
 	/* Do we even need to bother with this? */
@@ -1040,7 +1105,7 @@ pnfs_update_layout(struct inode *ino,
 	}
 
 	/* if LAYOUTGET already failed once we don't try again */
-	if (test_bit(lo_fail_bit(iomode), &nfsi->layout->plh_flags))
+	if (pnfs_layout_io_test_failed(lo, iomode))
 		goto out_unlock;
 
 	/* Check to see if the layout for the given range already exists */
@@ -1048,17 +1113,13 @@ pnfs_update_layout(struct inode *ino,
 	if (lseg)
 		goto out_unlock;
 
-	if (pnfs_layoutgets_blocked(lo, NULL, 0))
+	if (pnfs_layoutgets_blocked(lo, 0))
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
 
-	get_layout_hdr(lo);
 	if (list_empty(&lo->plh_segs))
 		first = true;
 
-	/* Enable LAYOUTRETURNs */
-	pnfs_clear_layout_returned(lo);
-
 	spin_unlock(&ino->i_lock);
 	if (first) {
 		/* The lo must be on the clp list if there is any
@@ -1079,24 +1140,26 @@ pnfs_update_layout(struct inode *ino,
 		arg.length = PAGE_CACHE_ALIGN(arg.length);
 
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
-	if (!lseg && first) {
-		spin_lock(&clp->cl_lock);
-		list_del_init(&lo->plh_layouts);
-		spin_unlock(&clp->cl_lock);
-	}
 	atomic_dec(&lo->plh_outstanding);
-	put_layout_hdr(lo);
+out_put_layout_hdr:
+	pnfs_put_layout_hdr(lo);
 out:
-	dprintk("%s end, state 0x%lx lseg %p\n", __func__,
-		nfsi->layout ? nfsi->layout->plh_flags : -1, lseg);
+	dprintk("%s: inode %s/%llu pNFS layout segment %s for "
+			"(%s, offset: %llu, length: %llu)\n",
+			__func__, ino->i_sb->s_id,
+			(unsigned long long)NFS_FILEID(ino),
+			lseg == NULL ? "not found" : "found",
+			iomode==IOMODE_RW ?  "read/write" : "read-only",
+			(unsigned long long)pos,
+			(unsigned long long)count);
 	return lseg;
 out_unlock:
 	spin_unlock(&ino->i_lock);
-	goto out;
+	goto out_put_layout_hdr;
 }
 EXPORT_SYMBOL_GPL(pnfs_update_layout);
 
-int
+struct pnfs_layout_segment *
 pnfs_layout_process(struct nfs4_layoutget *lgp)
 {
 	struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout;
@@ -1123,25 +1186,29 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget_reply;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, &res->stateid, 1)) {
+	if (pnfs_layoutgets_blocked(lo, 1) ||
+	    pnfs_layout_stateid_blocked(lo, &res->stateid)) {
 		dprintk("%s forget reply due to state\n", __func__);
 		goto out_forget_reply;
 	}
+
+	/* Done processing layoutget. Set the layout stateid */
+	pnfs_set_layout_stateid(lo, &res->stateid, false);
+
 	init_lseg(lo, lseg);
 	lseg->pls_range = res->range;
-	*lgp->lsegpp = get_lseg(lseg);
-	pnfs_insert_layout(lo, lseg);
+	pnfs_get_lseg(lseg);
+	pnfs_layout_insert_lseg(lo, lseg);
 
 	if (res->return_on_close) {
 		set_bit(NFS_LSEG_ROC, &lseg->pls_flags);
 		set_bit(NFS_LAYOUT_ROC, &lo->plh_flags);
 	}
 
-	/* Done processing layoutget. Set the layout stateid */
-	pnfs_set_layout_stateid(lo, &res->stateid, false);
 	spin_unlock(&ino->i_lock);
+	return lseg;
 out:
-	return status;
+	return ERR_PTR(status);
 
 out_forget_reply:
 	spin_unlock(&ino->i_lock);
@@ -1153,16 +1220,24 @@ out_forget_reply:
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
+	u64 rd_size = req->wb_bytes;
+
 	BUG_ON(pgio->pg_lseg != NULL);
 
 	if (req->wb_offset != req->wb_pgbase) {
 		nfs_pageio_reset_read_mds(pgio);
 		return;
 	}
+
+	if (pgio->pg_dreq == NULL)
+		rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
+	else
+		rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
-					   req->wb_bytes,
+					   rd_size,
 					   IOMODE_READ,
 					   GFP_KERNEL);
 	/* If no lseg, fall back to read through mds */
@@ -1173,7 +1248,8 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_read);
 
 void
-pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			   struct nfs_page *req, u64 wb_size)
 {
 	BUG_ON(pgio->pg_lseg != NULL);
 
@@ -1181,10 +1257,11 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 		nfs_pageio_reset_write_mds(pgio);
 		return;
 	}
+
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
-					   req->wb_bytes,
+					   wb_size,
 					   IOMODE_RW,
 					   GFP_NOFS);
 	/* If no lseg, fall back to write through mds */
@@ -1362,12 +1439,12 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he
 		if (trypnfs == PNFS_NOT_ATTEMPTED)
 			pnfs_write_through_mds(desc, data);
 	}
-	put_lseg(lseg);
+	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 {
-	put_lseg(hdr->lseg);
+	pnfs_put_lseg(hdr->lseg);
 	nfs_writehdr_free(hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
@@ -1382,17 +1459,17 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 	whdr = nfs_writehdr_alloc();
 	if (!whdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 		return -ENOMEM;
 	}
 	hdr = &whdr->header;
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
-	hdr->lseg = get_lseg(desc->pg_lseg);
+	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	atomic_inc(&hdr->refcnt);
 	ret = nfs_generic_flush(desc, hdr);
 	if (ret != 0) {
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 	} else
 		pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags);
@@ -1517,12 +1594,12 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea
 		if (trypnfs == PNFS_NOT_ATTEMPTED)
 			pnfs_read_through_mds(desc, data);
 	}
-	put_lseg(lseg);
+	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 {
-	put_lseg(hdr->lseg);
+	pnfs_put_lseg(hdr->lseg);
 	nfs_readhdr_free(hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
@@ -1538,17 +1615,17 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 	if (!rhdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
 		ret = -ENOMEM;
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 		return ret;
 	}
 	hdr = &rhdr->header;
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
-	hdr->lseg = get_lseg(desc->pg_lseg);
+	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	atomic_inc(&hdr->refcnt);
 	ret = nfs_generic_pagein(desc, hdr);
 	if (ret != 0) {
-		put_lseg(desc->pg_lseg);
+		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 	} else
 		pnfs_do_multiple_reads(desc, &hdr->rpc_list);
@@ -1574,13 +1651,7 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
 {
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
+	pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode);
 }
 EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
 
@@ -1601,7 +1672,7 @@ pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 	}
 	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) {
 		/* references matched in nfs4_layoutcommit_release */
-		get_lseg(hdr->lseg);
+		pnfs_get_lseg(hdr->lseg);
 	}
 	if (end_pos > nfsi->layout->plh_lwb)
 		nfsi->layout->plh_lwb = end_pos;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 745aa1b39e7c..dbf7bba52da0 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -62,9 +62,7 @@ enum {
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
-	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
-	NFS_LAYOUT_INVALID,		/* layout is being destroyed */
-	NFS_LAYOUT_RETURNED,		/* layout has already been returned */
+	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
 };
 
 enum layoutdriver_policy_flags {
@@ -140,6 +138,7 @@ struct pnfs_layout_hdr {
 	atomic_t		plh_outstanding; /* number of RPCs out */
 	unsigned long		plh_block_lgets; /* block LAYOUTGET if >0 */
 	u32			plh_barrier; /* ignore lower seqids */
+	unsigned long		plh_retry_timestamp;
 	unsigned long		plh_flags;
 	loff_t			plh_lwb; /* last write byte for layoutcommit */
 	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
@@ -172,12 +171,12 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server,
 				   struct pnfs_devicelist *devlist);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
 				   struct pnfs_device *dev);
-extern void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
+extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
 extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 
 /* pnfs.c */
-void get_layout_hdr(struct pnfs_layout_hdr *lo);
-void put_lseg(struct pnfs_layout_segment *lseg);
+void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
+void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
 
 void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
 			   const struct nfs_pgio_completion_ops *);
@@ -188,28 +187,29 @@ void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
-void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
+void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			        struct nfs_page *req, u64 wb_size);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
-int pnfs_layout_process(struct nfs4_layoutget *lgp);
+struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
 void pnfs_destroy_all_layouts(struct nfs_client *);
-void put_layout_hdr(struct pnfs_layout_hdr *lo);
+void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     const nfs4_stateid *new,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
 				  struct nfs4_state *open_state);
-int mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
+int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,
 				struct pnfs_layout_range *recall_range);
 bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
-bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
+bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
 void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
@@ -233,6 +233,7 @@ struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 /* nfs4_deviceid_flags */
 enum {
 	NFS_DEVICEID_INVALID = 0,       /* set when MDS clientid recalled */
+	NFS_DEVICEID_UNAVAILABLE,	/* device temporarily unavailable */
 };
 
 /* pnfs_dev.c */
@@ -242,6 +243,7 @@ struct nfs4_deviceid_node {
 	const struct pnfs_layoutdriver_type *ld;
 	const struct nfs_client		*nfs_client;
 	unsigned long 			flags;
+	unsigned long			timestamp_unavailable;
 	struct nfs4_deviceid		deviceid;
 	atomic_t			ref;
 };
@@ -254,34 +256,12 @@ void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
 			     const struct nfs4_deviceid *);
 struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
 bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
+void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
+bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
-static inline void
-pnfs_mark_layout_returned(struct pnfs_layout_hdr *lo)
-{
-	set_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
-}
-
-static inline void
-pnfs_clear_layout_returned(struct pnfs_layout_hdr *lo)
-{
-	clear_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
-}
-
-static inline bool
-pnfs_test_layout_returned(struct pnfs_layout_hdr *lo)
-{
-	return test_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags);
-}
-
-static inline int lo_fail_bit(u32 iomode)
-{
-	return iomode == IOMODE_RW ?
-			 NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
-}
-
 static inline struct pnfs_layout_segment *
-get_lseg(struct pnfs_layout_segment *lseg)
+pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	if (lseg) {
 		atomic_inc(&lseg->pls_refcount);
@@ -406,12 +386,12 @@ static inline void pnfs_destroy_layout(struct nfs_inode *nfsi)
 }
 
 static inline struct pnfs_layout_segment *
-get_lseg(struct pnfs_layout_segment *lseg)
+pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	return NULL;
 }
 
-static inline void put_lseg(struct pnfs_layout_segment *lseg)
+static inline void pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {
 }
 
@@ -443,7 +423,7 @@ pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
 }
 
 static inline bool
-pnfs_roc_drain(struct inode *ino, u32 *barrier)
+pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 {
 	return false;
 }
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index 73f701f1f4d3..d35b62e83ea6 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -40,6 +40,8 @@
 #define NFS4_DEVICE_ID_HASH_SIZE	(1 << NFS4_DEVICE_ID_HASH_BITS)
 #define NFS4_DEVICE_ID_HASH_MASK	(NFS4_DEVICE_ID_HASH_SIZE - 1)
 
+#define PNFS_DEVICE_RETRY_TIMEOUT (120*HZ)
+
 static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
 static DEFINE_SPINLOCK(nfs4_deviceid_lock);
 
@@ -218,6 +220,30 @@ nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
 }
 EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node);
 
+void
+nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node)
+{
+	node->timestamp_unavailable = jiffies;
+	set_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+}
+EXPORT_SYMBOL_GPL(nfs4_mark_deviceid_unavailable);
+
+bool
+nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node)
+{
+	if (test_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags)) {
+		unsigned long start, end;
+
+		end = jiffies;
+		start = end - PNFS_DEVICE_RETRY_TIMEOUT;
+		if (time_in_range(node->timestamp_unavailable, start, end))
+			return true;
+		clear_bit(NFS_DEVICEID_UNAVAILABLE, &node->flags);
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(nfs4_test_deviceid_unavailable);
+
 static void
 _deviceid_purge_client(const struct nfs_client *clp, long hash)
 {
@@ -276,3 +302,4 @@ nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
 	}
 	rcu_read_unlock();
 }
+
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index d2c7f5db0847..652d3f7176a9 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -54,6 +54,7 @@
 #include <linux/parser.h>
 #include <linux/nsproxy.h>
 #include <linux/rcupdate.h>
+#include <linux/kthread.h>
 
 #include <asm/uaccess.h>
 
@@ -88,6 +89,7 @@ enum {
 	Opt_sharecache, Opt_nosharecache,
 	Opt_resvport, Opt_noresvport,
 	Opt_fscache, Opt_nofscache,
+	Opt_migration, Opt_nomigration,
 
 	/* Mount options that take integer arguments */
 	Opt_port,
@@ -147,6 +149,8 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_noresvport, "noresvport" },
 	{ Opt_fscache, "fsc" },
 	{ Opt_nofscache, "nofsc" },
+	{ Opt_migration, "migration" },
+	{ Opt_nomigration, "nomigration" },
 
 	{ Opt_port, "port=%s" },
 	{ Opt_rsize, "rsize=%s" },
@@ -412,6 +416,54 @@ void nfs_sb_deactive(struct super_block *sb)
 }
 EXPORT_SYMBOL_GPL(nfs_sb_deactive);
 
+static int nfs_deactivate_super_async_work(void *ptr)
+{
+	struct super_block *sb = ptr;
+
+	deactivate_super(sb);
+	module_put_and_exit(0);
+	return 0;
+}
+
+/*
+ * same effect as deactivate_super, but will do final unmount in kthread
+ * context
+ */
+static void nfs_deactivate_super_async(struct super_block *sb)
+{
+	struct task_struct *task;
+	char buf[INET6_ADDRSTRLEN + 1];
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_client *clp = server->nfs_client;
+
+	if (!atomic_add_unless(&sb->s_active, -1, 1)) {
+		rcu_read_lock();
+		snprintf(buf, sizeof(buf),
+			rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
+		rcu_read_unlock();
+
+		__module_get(THIS_MODULE);
+		task = kthread_run(nfs_deactivate_super_async_work, sb,
+				"%s-deactivate-super", buf);
+		if (IS_ERR(task)) {
+			pr_err("%s: kthread_run: %ld\n",
+				__func__, PTR_ERR(task));
+			/* make synchronous call and hope for the best */
+			deactivate_super(sb);
+			module_put(THIS_MODULE);
+		}
+	}
+}
+
+void nfs_sb_deactive_async(struct super_block *sb)
+{
+	struct nfs_server *server = NFS_SB(sb);
+
+	if (atomic_dec_and_test(&server->active))
+		nfs_deactivate_super_async(sb);
+}
+EXPORT_SYMBOL_GPL(nfs_sb_deactive_async);
+
 /*
  * Deliver file system statistics to userspace
  */
@@ -676,6 +728,9 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	if (nfss->options & NFS_OPTION_FSCACHE)
 		seq_printf(m, ",fsc");
 
+	if (nfss->options & NFS_OPTION_MIGRATION)
+		seq_printf(m, ",migration");
+
 	if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
 		if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
 			seq_printf(m, ",lookupcache=none");
@@ -765,7 +820,7 @@ int nfs_show_devname(struct seq_file *m, struct dentry *root)
 	int err = 0;
 	if (!page)
 		return -ENOMEM;
-	devname = nfs_path(&dummy, root, page, PAGE_SIZE);
+	devname = nfs_path(&dummy, root, page, PAGE_SIZE, 0);
 	if (IS_ERR(devname))
 		err = PTR_ERR(devname);
 	else
@@ -1106,7 +1161,7 @@ static int nfs_get_option_ul(substring_t args[], unsigned long *option)
 	string = match_strdup(args);
 	if (string == NULL)
 		return -ENOMEM;
-	rc = strict_strtoul(string, 10, option);
+	rc = kstrtoul(string, 10, option);
 	kfree(string);
 
 	return rc;
@@ -1243,6 +1298,12 @@ static int nfs_parse_mount_options(char *raw,
 			kfree(mnt->fscache_uniq);
 			mnt->fscache_uniq = NULL;
 			break;
+		case Opt_migration:
+			mnt->options |= NFS_OPTION_MIGRATION;
+			break;
+		case Opt_nomigration:
+			mnt->options &= NFS_OPTION_MIGRATION;
+			break;
 
 		/*
 		 * options that take numeric values
@@ -1535,6 +1596,10 @@ static int nfs_parse_mount_options(char *raw,
 	if (mnt->minorversion && mnt->version != 4)
 		goto out_minorversion_mismatch;
 
+	if (mnt->options & NFS_OPTION_MIGRATION &&
+	    mnt->version != 4 && mnt->minorversion != 0)
+		goto out_migration_misuse;
+
 	/*
 	 * verify that any proto=/mountproto= options match the address
 	 * families in the addr=/mountaddr= options.
@@ -1572,6 +1637,10 @@ out_minorversion_mismatch:
 	printk(KERN_INFO "NFS: mount option vers=%u does not support "
 			 "minorversion=%u\n", mnt->version, mnt->minorversion);
 	return 0;
+out_migration_misuse:
+	printk(KERN_INFO
+		"NFS: 'migration' not supported for this NFS version\n");
+	return 0;
 out_nomem:
 	printk(KERN_INFO "NFS: not enough memory to parse option\n");
 	return 0;
@@ -2494,7 +2563,7 @@ EXPORT_SYMBOL_GPL(nfs_kill_super);
 /*
  * Clone an NFS2/3/4 server record on xdev traversal (FSID-change)
  */
-struct dentry *
+static struct dentry *
 nfs_xdev_mount(struct file_system_type *fs_type, int flags,
 		const char *dev_name, void *raw_data)
 {
@@ -2642,6 +2711,7 @@ unsigned int nfs_idmap_cache_timeout = 600;
 bool nfs4_disable_idmapping = true;
 unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE;
 unsigned short send_implementation_id = 1;
+char nfs4_client_id_uniquifier[NFS4_CLIENT_ID_UNIQ_LEN] = "";
 
 EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport);
 EXPORT_SYMBOL_GPL(nfs_callback_tcpport);
@@ -2649,6 +2719,7 @@ EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout);
 EXPORT_SYMBOL_GPL(nfs4_disable_idmapping);
 EXPORT_SYMBOL_GPL(max_session_slots);
 EXPORT_SYMBOL_GPL(send_implementation_id);
+EXPORT_SYMBOL_GPL(nfs4_client_id_uniquifier);
 
 #define NFS_CALLBACK_MAXPORTNR (65535U)
 
@@ -2659,7 +2730,7 @@ static int param_set_portnr(const char *val, const struct kernel_param *kp)
 
 	if (!val)
 		return -EINVAL;
-	ret = strict_strtoul(val, 0, &num);
+	ret = kstrtoul(val, 0, &num);
 	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
 		return -EINVAL;
 	*((unsigned int *)kp->arg) = num;
@@ -2674,6 +2745,8 @@ static struct kernel_param_ops param_ops_portnr = {
 module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 module_param(nfs_idmap_cache_timeout, int, 0644);
 module_param(nfs4_disable_idmapping, bool, 0644);
+module_param_string(nfs4_unique_id, nfs4_client_id_uniquifier,
+			NFS4_CLIENT_ID_UNIQ_LEN, 0600);
 MODULE_PARM_DESC(nfs4_disable_idmapping,
 		"Turn off NFSv4 idmapping when using 'sec=sys'");
 module_param(max_session_slots, ushort, 0644);
@@ -2682,6 +2755,7 @@ MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 "
 module_param(send_implementation_id, ushort, 0644);
 MODULE_PARM_DESC(send_implementation_id,
 		"Send implementation ID with NFSv4.1 exchange_id");
+MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string");
 MODULE_ALIAS("nfs4");
 
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 13cea637eff8..3f79c77153b8 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -95,7 +95,7 @@ static void nfs_async_unlink_release(void *calldata)
 
 	nfs_dec_sillycount(data->dir);
 	nfs_free_unlinkdata(data);
-	nfs_sb_deactive(sb);
+	nfs_sb_deactive_async(sb);
 }
 
 static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e3b55372726c..9347ab7c9574 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -846,6 +846,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 int nfs_flush_incompatible(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
+	struct nfs_lock_context *l_ctx;
 	struct nfs_page	*req;
 	int do_flush, status;
 	/*
@@ -860,9 +861,12 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		req = nfs_page_find_request(page);
 		if (req == NULL)
 			return 0;
-		do_flush = req->wb_page != page || req->wb_context != ctx ||
-			req->wb_lock_context->lockowner != current->files ||
-			req->wb_lock_context->pid != current->tgid;
+		l_ctx = req->wb_lock_context;
+		do_flush = req->wb_page != page || req->wb_context != ctx;
+		if (l_ctx) {
+			do_flush |= l_ctx->lockowner.l_owner != current->files
+				|| l_ctx->lockowner.l_pid != current->tgid;
+		}
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
@@ -1576,6 +1580,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		/* We have a mismatch. Write the page again */
 		dprintk(" mismatch\n");
 		nfs_mark_request_dirty(req);
+		set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	next:
 		nfs_unlock_and_release_request(req);
 	}
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 6aa5590c3679..b314888825d5 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -218,8 +218,7 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
  * There must be an encoding function for void results so svc_process
  * will work properly.
  */
-int
-nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 9095f3c21df9..97d90d1c8608 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -247,7 +247,7 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
 	/* Now create the file and set attributes */
 	nfserr = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len,
 				attr, newfhp,
-				argp->createmode, argp->verf, NULL, NULL);
+				argp->createmode, (u32 *)argp->verf, NULL, NULL);
 
 	RETURN_STATUS(nfserr);
 }
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 4c7bd35b1876..bdf29c96e4cd 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1028,7 +1028,6 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
 	cb->cb_msg.rpc_cred = callback_cred;
 
 	cb->cb_ops = &nfsd4_cb_recall_ops;
-	dp->dl_retries = 1;
 
 	INIT_LIST_HEAD(&cb->cb_per_client);
 	cb->cb_done = true;
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index fdc91a6fc9c4..a1f10c0a6255 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -478,7 +478,7 @@ nfsd_idmap_init(struct net *net)
 		goto destroy_idtoname_cache;
 	nn->nametoid_cache = cache_create_net(&nametoid_cache_template, net);
 	if (IS_ERR(nn->nametoid_cache)) {
-		rv = PTR_ERR(nn->idtoname_cache);
+		rv = PTR_ERR(nn->nametoid_cache);
 		goto unregister_idtoname_cache;
 	}
 	rv = cache_register_net(nn->nametoid_cache, net);
@@ -598,7 +598,7 @@ numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namel
 	/* Just to make sure it's null-terminated: */
 	memcpy(buf, name, namelen);
 	buf[namelen] = '\0';
-	ret = kstrtouint(name, 10, id);
+	ret = kstrtouint(buf, 10, id);
 	return ret == 0;
 }
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index c9c1c0a25417..6c9a4b291dba 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -370,7 +370,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			break;
 		case NFS4_OPEN_CLAIM_PREVIOUS:
 			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
-			status = nfs4_check_open_reclaim(&open->op_clientid);
+			status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion);
 			if (status)
 				goto out;
 		case NFS4_OPEN_CLAIM_FH:
@@ -1054,8 +1054,8 @@ struct nfsd4_operation {
 	char *op_name;
 	/* Try to get response size before operation */
 	nfsd4op_rsize op_rsize_bop;
-	stateid_setter op_get_currentstateid;
-	stateid_getter op_set_currentstateid;
+	stateid_getter op_get_currentstateid;
+	stateid_setter op_set_currentstateid;
 };
 
 static struct nfsd4_operation nfsd4_ops[];
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 48a1bad37334..d0237f872cc4 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -758,7 +758,7 @@ static void nfsd4_put_drc_mem(int slotsize, int num)
 	spin_unlock(&nfsd_drc_lock);
 }
 
-static struct nfsd4_session *alloc_session(int slotsize, int numslots)
+static struct nfsd4_session *__alloc_session(int slotsize, int numslots)
 {
 	struct nfsd4_session *new;
 	int mem, i;
@@ -852,35 +852,28 @@ static int nfsd4_register_conn(struct nfsd4_conn *conn)
 	return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user);
 }
 
-static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses, u32 dir)
+static void nfsd4_init_conn(struct svc_rqst *rqstp, struct nfsd4_conn *conn, struct nfsd4_session *ses)
 {
-	struct nfsd4_conn *conn;
 	int ret;
 
-	conn = alloc_conn(rqstp, dir);
-	if (!conn)
-		return nfserr_jukebox;
 	nfsd4_hash_conn(conn, ses);
 	ret = nfsd4_register_conn(conn);
 	if (ret)
 		/* oops; xprt is already down: */
 		nfsd4_conn_lost(&conn->cn_xpt_user);
-	if (ses->se_client->cl_cb_state == NFSD4_CB_DOWN &&
-		dir & NFS4_CDFC4_BACK) {
+	if (conn->cn_flags & NFS4_CDFC4_BACK) {
 		/* callback channel may be back up */
 		nfsd4_probe_callback(ses->se_client);
 	}
-	return nfs_ok;
 }
 
-static __be32 nfsd4_new_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_session *ses)
+static struct nfsd4_conn *alloc_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_create_session *cses)
 {
 	u32 dir = NFS4_CDFC4_FORE;
 
-	if (ses->se_flags & SESSION4_BACK_CHAN)
+	if (cses->flags & SESSION4_BACK_CHAN)
 		dir |= NFS4_CDFC4_BACK;
-
-	return nfsd4_new_conn(rqstp, ses, dir);
+	return alloc_conn(rqstp, dir);
 }
 
 /* must be called under client_lock */
@@ -903,20 +896,21 @@ static void nfsd4_del_conns(struct nfsd4_session *s)
 	spin_unlock(&clp->cl_lock);
 }
 
+static void __free_session(struct nfsd4_session *ses)
+{
+	nfsd4_put_drc_mem(slot_bytes(&ses->se_fchannel), ses->se_fchannel.maxreqs);
+	free_session_slots(ses);
+	kfree(ses);
+}
+
 static void free_session(struct kref *kref)
 {
 	struct nfsd4_session *ses;
-	int mem;
 
 	lockdep_assert_held(&client_lock);
 	ses = container_of(kref, struct nfsd4_session, se_ref);
 	nfsd4_del_conns(ses);
-	spin_lock(&nfsd_drc_lock);
-	mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel);
-	nfsd_drc_mem_used -= mem;
-	spin_unlock(&nfsd_drc_lock);
-	free_session_slots(ses);
-	kfree(ses);
+	__free_session(ses);
 }
 
 void nfsd4_put_session(struct nfsd4_session *ses)
@@ -926,14 +920,10 @@ void nfsd4_put_session(struct nfsd4_session *ses)
 	spin_unlock(&client_lock);
 }
 
-static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses)
+static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fchan)
 {
 	struct nfsd4_session *new;
-	struct nfsd4_channel_attrs *fchan = &cses->fore_channel;
 	int numslots, slotsize;
-	__be32 status;
-	int idx;
-
 	/*
 	 * Note decreasing slot size below client's request may
 	 * make it difficult for client to function correctly, whereas
@@ -946,12 +936,18 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	if (numslots < 1)
 		return NULL;
 
-	new = alloc_session(slotsize, numslots);
+	new = __alloc_session(slotsize, numslots);
 	if (!new) {
 		nfsd4_put_drc_mem(slotsize, fchan->maxreqs);
 		return NULL;
 	}
 	init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize);
+	return new;
+}
+
+static struct nfsd4_session *init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
+{
+	int idx;
 
 	new->se_client = clp;
 	gen_sessionid(new);
@@ -970,14 +966,6 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 	spin_unlock(&clp->cl_lock);
 	spin_unlock(&client_lock);
 
-	status = nfsd4_new_conn_from_crses(rqstp, new);
-	/* whoops: benny points out, status is ignored! (err, or bogus) */
-	if (status) {
-		spin_lock(&client_lock);
-		free_session(&new->se_ref);
-		spin_unlock(&client_lock);
-		return NULL;
-	}
 	if (cses->flags & SESSION4_BACK_CHAN) {
 		struct sockaddr *sa = svc_addr(rqstp);
 		/*
@@ -990,7 +978,6 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n
 		rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa);
 		clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa);
 	}
-	nfsd4_probe_callback(clp);
 	return new;
 }
 
@@ -1131,7 +1118,7 @@ unhash_client_locked(struct nfs4_client *clp)
 }
 
 static void
-expire_client(struct nfs4_client *clp)
+destroy_client(struct nfs4_client *clp)
 {
 	struct nfs4_openowner *oo;
 	struct nfs4_delegation *dp;
@@ -1165,6 +1152,12 @@ expire_client(struct nfs4_client *clp)
 	spin_unlock(&client_lock);
 }
 
+static void expire_client(struct nfs4_client *clp)
+{
+	nfsd4_client_record_remove(clp);
+	destroy_client(clp);
+}
+
 static void copy_verf(struct nfs4_client *target, nfs4_verifier *source)
 {
 	memcpy(target->cl_verifier.data, source->data,
@@ -1223,10 +1216,26 @@ static bool groups_equal(struct group_info *g1, struct group_info *g2)
 	return true;
 }
 
+/*
+ * RFC 3530 language requires clid_inuse be returned when the
+ * "principal" associated with a requests differs from that previously
+ * used.  We use uid, gid's, and gss principal string as our best
+ * approximation.  We also don't want to allow non-gss use of a client
+ * established using gss: in theory cr_principal should catch that
+ * change, but in practice cr_principal can be null even in the gss case
+ * since gssd doesn't always pass down a principal string.
+ */
+static bool is_gss_cred(struct svc_cred *cr)
+{
+	/* Is cr_flavor one of the gss "pseudoflavors"?: */
+	return (cr->cr_flavor > RPC_AUTH_MAXFLAVOR);
+}
+
+
 static bool
 same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
 {
-	if ((cr1->cr_flavor != cr2->cr_flavor)
+	if ((is_gss_cred(cr1) != is_gss_cred(cr2))
 		|| (cr1->cr_uid != cr2->cr_uid)
 		|| (cr1->cr_gid != cr2->cr_gid)
 		|| !groups_equal(cr1->cr_group_info, cr2->cr_group_info))
@@ -1340,13 +1349,15 @@ move_to_confirmed(struct nfs4_client *clp)
 }
 
 static struct nfs4_client *
-find_confirmed_client(clientid_t *clid)
+find_confirmed_client(clientid_t *clid, bool sessions)
 {
 	struct nfs4_client *clp;
 	unsigned int idhashval = clientid_hashval(clid->cl_id);
 
 	list_for_each_entry(clp, &conf_id_hashtbl[idhashval], cl_idhash) {
 		if (same_clid(&clp->cl_clientid, clid)) {
+			if ((bool)clp->cl_minorversion != sessions)
+				return NULL;
 			renew_client(clp);
 			return clp;
 		}
@@ -1355,14 +1366,17 @@ find_confirmed_client(clientid_t *clid)
 }
 
 static struct nfs4_client *
-find_unconfirmed_client(clientid_t *clid)
+find_unconfirmed_client(clientid_t *clid, bool sessions)
 {
 	struct nfs4_client *clp;
 	unsigned int idhashval = clientid_hashval(clid->cl_id);
 
 	list_for_each_entry(clp, &unconf_id_hashtbl[idhashval], cl_idhash) {
-		if (same_clid(&clp->cl_clientid, clid))
+		if (same_clid(&clp->cl_clientid, clid)) {
+			if ((bool)clp->cl_minorversion != sessions)
+				return NULL;
 			return clp;
+		}
 	}
 	return NULL;
 }
@@ -1651,6 +1665,7 @@ out_new:
 		status = nfserr_jukebox;
 		goto out;
 	}
+	new->cl_minorversion = 1;
 
 	gen_clid(new);
 	add_to_unconfirmed(new, strhashval);
@@ -1743,67 +1758,71 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 	struct sockaddr *sa = svc_addr(rqstp);
 	struct nfs4_client *conf, *unconf;
 	struct nfsd4_session *new;
+	struct nfsd4_conn *conn;
 	struct nfsd4_clid_slot *cs_slot = NULL;
-	bool confirm_me = false;
 	__be32 status = 0;
 
 	if (cr_ses->flags & ~SESSION4_FLAG_MASK_A)
 		return nfserr_inval;
+	if (check_forechannel_attrs(cr_ses->fore_channel))
+		return nfserr_toosmall;
+	new = alloc_session(&cr_ses->fore_channel);
+	if (!new)
+		return nfserr_jukebox;
+	status = nfserr_jukebox;
+	conn = alloc_conn_from_crses(rqstp, cr_ses);
+	if (!conn)
+		goto out_free_session;
 
 	nfs4_lock_state();
-	unconf = find_unconfirmed_client(&cr_ses->clientid);
-	conf = find_confirmed_client(&cr_ses->clientid);
+	unconf = find_unconfirmed_client(&cr_ses->clientid, true);
+	conf = find_confirmed_client(&cr_ses->clientid, true);
 
 	if (conf) {
 		cs_slot = &conf->cl_cs_slot;
 		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
 		if (status == nfserr_replay_cache) {
 			status = nfsd4_replay_create_session(cr_ses, cs_slot);
-			goto out;
+			goto out_free_conn;
 		} else if (cr_ses->seqid != cs_slot->sl_seqid + 1) {
 			status = nfserr_seq_misordered;
-			goto out;
+			goto out_free_conn;
 		}
 	} else if (unconf) {
+		unsigned int hash;
+		struct nfs4_client *old;
 		if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
 		    !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
 			status = nfserr_clid_inuse;
-			goto out;
+			goto out_free_conn;
 		}
 		cs_slot = &unconf->cl_cs_slot;
 		status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0);
 		if (status) {
 			/* an unconfirmed replay returns misordered */
 			status = nfserr_seq_misordered;
-			goto out;
+			goto out_free_conn;
 		}
-		confirm_me = true;
+		hash = clientstr_hashval(unconf->cl_recdir);
+		old = find_confirmed_client_by_str(unconf->cl_recdir, hash);
+		if (old)
+			expire_client(old);
+		move_to_confirmed(unconf);
 		conf = unconf;
 	} else {
 		status = nfserr_stale_clientid;
-		goto out;
+		goto out_free_conn;
 	}
-
-	/*
-	 * XXX: we should probably set this at creation time, and check
-	 * for consistent minorversion use throughout:
-	 */
-	conf->cl_minorversion = 1;
+	status = nfs_ok;
 	/*
 	 * We do not support RDMA or persistent sessions
 	 */
 	cr_ses->flags &= ~SESSION4_PERSIST;
 	cr_ses->flags &= ~SESSION4_RDMA;
 
-	status = nfserr_toosmall;
-	if (check_forechannel_attrs(cr_ses->fore_channel))
-		goto out;
+	init_session(rqstp, new, conf, cr_ses);
+	nfsd4_init_conn(rqstp, conn, new);
 
-	status = nfserr_jukebox;
-	new = alloc_init_session(rqstp, conf, cr_ses);
-	if (!new)
-		goto out;
-	status = nfs_ok;
 	memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
 	       NFS4_MAX_SESSIONID_LEN);
 	memcpy(&cr_ses->fore_channel, &new->se_fchannel,
@@ -1813,18 +1832,15 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 
 	/* cache solo and embedded create sessions under the state lock */
 	nfsd4_cache_create_session(cr_ses, cs_slot, status);
-	if (confirm_me) {
-		unsigned int hash = clientstr_hashval(unconf->cl_recdir);
-		struct nfs4_client *old =
-			find_confirmed_client_by_str(conf->cl_recdir, hash);
-		if (old)
-			expire_client(old);
-		move_to_confirmed(conf);
-	}
 out:
 	nfs4_unlock_state();
 	dprintk("%s returns %d\n", __func__, ntohl(status));
 	return status;
+out_free_conn:
+	free_conn(conn);
+out_free_session:
+	__free_session(new);
+	goto out;
 }
 
 static bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
@@ -1854,6 +1870,7 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
 		     struct nfsd4_bind_conn_to_session *bcts)
 {
 	__be32 status;
+	struct nfsd4_conn *conn;
 
 	if (!nfsd4_last_compound_op(rqstp))
 		return nfserr_not_only_op;
@@ -1870,9 +1887,13 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
 		return nfserr_badsession;
 
 	status = nfsd4_map_bcts_dir(&bcts->dir);
-	if (!status)
-		nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
-	return status;
+	if (status)
+		return status;
+	conn = alloc_conn(rqstp, bcts->dir);
+	if (!conn)
+		return nfserr_jukebox;
+	nfsd4_init_conn(rqstp, conn, cstate->session);
+	return nfs_ok;
 }
 
 static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4_sessionid *sid)
@@ -2085,8 +2106,8 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
 	__be32 status = 0;
 
 	nfs4_lock_state();
-	unconf = find_unconfirmed_client(&dc->clientid);
-	conf = find_confirmed_client(&dc->clientid);
+	unconf = find_unconfirmed_client(&dc->clientid, true);
+	conf = find_confirmed_client(&dc->clientid, true);
 
 	if (conf) {
 		clp = conf;
@@ -2200,10 +2221,6 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		copy_clid(new, conf);
 	else /* case 4 (new client) or cases 2, 3 (client reboot): */
 		gen_clid(new);
-	/*
-	 * XXX: we should probably set this at creation time, and check
-	 * for consistent minorversion use throughout:
-	 */
 	new->cl_minorversion = 0;
 	gen_callback(new, setclid, rqstp);
 	add_to_unconfirmed(new, strhashval);
@@ -2232,8 +2249,8 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		return nfserr_stale_clientid;
 	nfs4_lock_state();
 
-	conf = find_confirmed_client(clid);
-	unconf = find_unconfirmed_client(clid);
+	conf = find_confirmed_client(clid, false);
+	unconf = find_unconfirmed_client(clid, false);
 	/*
 	 * We try hard to give out unique clientid's, so if we get an
 	 * attempt to confirm the same clientid with a different cred,
@@ -2262,10 +2279,8 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		unsigned int hash = clientstr_hashval(unconf->cl_recdir);
 
 		conf = find_confirmed_client_by_str(unconf->cl_recdir, hash);
-		if (conf) {
-			nfsd4_client_record_remove(conf);
+		if (conf)
 			expire_client(conf);
-		}
 		move_to_confirmed(unconf);
 		nfsd4_probe_callback(unconf);
 	}
@@ -2447,16 +2462,20 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner,
 }
 
 static struct nfs4_openowner *
-find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open)
+find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, bool sessions)
 {
 	struct nfs4_stateowner *so;
 	struct nfs4_openowner *oo;
+	struct nfs4_client *clp;
 
 	list_for_each_entry(so, &ownerstr_hashtbl[hashval], so_strhash) {
 		if (!so->so_is_open_owner)
 			continue;
 		if (same_owner_str(so, &open->op_owner, &open->op_clientid)) {
 			oo = openowner(so);
+			clp = oo->oo_owner.so_client;
+			if ((bool)clp->cl_minorversion != sessions)
+				return NULL;
 			renew_client(oo->oo_owner.so_client);
 			return oo;
 		}
@@ -2600,10 +2619,10 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
 		return nfserr_jukebox;
 
 	strhashval = ownerstr_hashval(clientid->cl_id, &open->op_owner);
-	oo = find_openstateowner_str(strhashval, open);
+	oo = find_openstateowner_str(strhashval, open, cstate->minorversion);
 	open->op_openowner = oo;
 	if (!oo) {
-		clp = find_confirmed_client(clientid);
+		clp = find_confirmed_client(clientid, cstate->minorversion);
 		if (clp == NULL)
 			return nfserr_expired;
 		goto new_owner;
@@ -2705,11 +2724,6 @@ nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_ol_st
 	return nfs_ok;
 }
 
-static void nfs4_free_stateid(struct nfs4_ol_stateid *s)
-{
-	kmem_cache_free(stateid_slab, s);
-}
-
 static inline int nfs4_access_to_access(u32 nfs4_access)
 {
 	int flags = 0;
@@ -3087,7 +3101,7 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
 	if (open->op_file)
 		nfsd4_free_file(open->op_file);
 	if (open->op_stp)
-		nfs4_free_stateid(open->op_stp);
+		free_generic_stateid(open->op_stp);
 }
 
 __be32
@@ -3104,7 +3118,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	status = nfserr_stale_clientid;
 	if (STALE_CLIENTID(clid, nn))
 		goto out;
-	clp = find_confirmed_client(clid);
+	clp = find_confirmed_client(clid, cstate->minorversion);
 	status = nfserr_expired;
 	if (clp == NULL) {
 		/* We assume the client took too long to RENEW. */
@@ -3180,7 +3194,6 @@ nfs4_laundromat(void)
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
 		dprintk("NFSD: purging unused client (clientid %08x)\n",
 			clp->cl_clientid.cl_id);
-		nfsd4_client_record_remove(clp);
 		expire_client(clp);
 	}
 	spin_lock(&recall_lock);
@@ -3372,7 +3385,7 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	return nfs_ok;
 }
 
-static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s)
+static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, bool sessions)
 {
 	struct nfs4_client *cl;
 	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
@@ -3381,7 +3394,7 @@ static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask, s
 		return nfserr_bad_stateid;
 	if (STALE_STATEID(stateid, nn))
 		return nfserr_stale_stateid;
-	cl = find_confirmed_client(&stateid->si_opaque.so_clid);
+	cl = find_confirmed_client(&stateid->si_opaque.so_clid, sessions);
 	if (!cl)
 		return nfserr_expired;
 	*s = find_stateid_by_type(cl, stateid, typemask);
@@ -3414,7 +3427,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
 		return check_special_stateids(net, current_fh, stateid, flags);
 
-	status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s);
+	status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, &s, cstate->minorversion);
 	if (status)
 		return status;
 	status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
@@ -3564,7 +3577,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
 		seqid, STATEID_VAL(stateid));
 
 	*stpp = NULL;
-	status = nfsd4_lookup_stateid(stateid, typemask, &s);
+	status = nfsd4_lookup_stateid(stateid, typemask, &s, cstate->minorversion);
 	if (status)
 		return status;
 	*stpp = openlockstateid(s);
@@ -3765,6 +3778,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
 	nfsd4_close_open_stateid(stp);
+	release_last_closed_stateid(oo);
 	oo->oo_last_closed_stid = stp;
 
 	if (list_empty(&oo->oo_owner.so_stateids)) {
@@ -3801,7 +3815,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	inode = cstate->current_fh.fh_dentry->d_inode;
 
 	nfs4_lock_state();
-	status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s);
+	status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s, cstate->minorversion);
 	if (status)
 		goto out;
 	dp = delegstateid(s);
@@ -4045,8 +4059,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfs4_lockowner *lock_sop = NULL;
 	struct nfs4_ol_stateid *lock_stp;
 	struct file *filp = NULL;
-	struct file_lock file_lock;
-	struct file_lock conflock;
+	struct file_lock *file_lock = NULL;
+	struct file_lock *conflock = NULL;
 	__be32 status = 0;
 	bool new_state = false;
 	int lkflg;
@@ -4116,21 +4130,28 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (!locks_in_grace(SVC_NET(rqstp)) && lock->lk_reclaim)
 		goto out;
 
-	locks_init_lock(&file_lock);
+	file_lock = locks_alloc_lock();
+	if (!file_lock) {
+		dprintk("NFSD: %s: unable to allocate lock!\n", __func__);
+		status = nfserr_jukebox;
+		goto out;
+	}
+
+	locks_init_lock(file_lock);
 	switch (lock->lk_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
 			filp = find_readable_file(lock_stp->st_file);
 			if (filp)
 				get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ);
-			file_lock.fl_type = F_RDLCK;
+			file_lock->fl_type = F_RDLCK;
 			break;
 		case NFS4_WRITE_LT:
 		case NFS4_WRITEW_LT:
 			filp = find_writeable_file(lock_stp->st_file);
 			if (filp)
 				get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE);
-			file_lock.fl_type = F_WRLCK;
+			file_lock->fl_type = F_WRLCK;
 			break;
 		default:
 			status = nfserr_inval;
@@ -4140,22 +4161,23 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_openmode;
 		goto out;
 	}
-	file_lock.fl_owner = (fl_owner_t)lock_sop;
-	file_lock.fl_pid = current->tgid;
-	file_lock.fl_file = filp;
-	file_lock.fl_flags = FL_POSIX;
-	file_lock.fl_lmops = &nfsd_posix_mng_ops;
-
-	file_lock.fl_start = lock->lk_offset;
-	file_lock.fl_end = last_byte_offset(lock->lk_offset, lock->lk_length);
-	nfs4_transform_lock_offset(&file_lock);
-
-	/*
-	* Try to lock the file in the VFS.
-	* Note: locks.c uses the BKL to protect the inode's lock list.
-	*/
+	file_lock->fl_owner = (fl_owner_t)lock_sop;
+	file_lock->fl_pid = current->tgid;
+	file_lock->fl_file = filp;
+	file_lock->fl_flags = FL_POSIX;
+	file_lock->fl_lmops = &nfsd_posix_mng_ops;
+	file_lock->fl_start = lock->lk_offset;
+	file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length);
+	nfs4_transform_lock_offset(file_lock);
+
+	conflock = locks_alloc_lock();
+	if (!conflock) {
+		dprintk("NFSD: %s: unable to allocate lock!\n", __func__);
+		status = nfserr_jukebox;
+		goto out;
+	}
 
-	err = vfs_lock_file(filp, F_SETLK, &file_lock, &conflock);
+	err = vfs_lock_file(filp, F_SETLK, file_lock, conflock);
 	switch (-err) {
 	case 0: /* success! */
 		update_stateid(&lock_stp->st_stid.sc_stateid);
@@ -4166,7 +4188,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	case (EAGAIN):		/* conflock holds conflicting lock */
 		status = nfserr_denied;
 		dprintk("NFSD: nfsd4_lock: conflicting lock found!\n");
-		nfs4_set_lock_denied(&conflock, &lock->lk_denied);
+		nfs4_set_lock_denied(conflock, &lock->lk_denied);
 		break;
 	case (EDEADLK):
 		status = nfserr_deadlock;
@@ -4181,6 +4203,10 @@ out:
 		release_lockowner(lock_sop);
 	if (!cstate->replay_owner)
 		nfs4_unlock_state();
+	if (file_lock)
+		locks_free_lock(file_lock);
+	if (conflock)
+		locks_free_lock(conflock);
 	return status;
 }
 
@@ -4209,7 +4235,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	    struct nfsd4_lockt *lockt)
 {
 	struct inode *inode;
-	struct file_lock file_lock;
+	struct file_lock *file_lock = NULL;
 	struct nfs4_lockowner *lo;
 	__be32 status;
 	struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
@@ -4230,15 +4256,21 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		goto out;
 
 	inode = cstate->current_fh.fh_dentry->d_inode;
-	locks_init_lock(&file_lock);
+	file_lock = locks_alloc_lock();
+	if (!file_lock) {
+		dprintk("NFSD: %s: unable to allocate lock!\n", __func__);
+		status = nfserr_jukebox;
+		goto out;
+	}
+	locks_init_lock(file_lock);
 	switch (lockt->lt_type) {
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
-			file_lock.fl_type = F_RDLCK;
+			file_lock->fl_type = F_RDLCK;
 		break;
 		case NFS4_WRITE_LT:
 		case NFS4_WRITEW_LT:
-			file_lock.fl_type = F_WRLCK;
+			file_lock->fl_type = F_WRLCK;
 		break;
 		default:
 			dprintk("NFSD: nfs4_lockt: bad lock type!\n");
@@ -4248,25 +4280,27 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	lo = find_lockowner_str(inode, &lockt->lt_clientid, &lockt->lt_owner);
 	if (lo)
-		file_lock.fl_owner = (fl_owner_t)lo;
-	file_lock.fl_pid = current->tgid;
-	file_lock.fl_flags = FL_POSIX;
+		file_lock->fl_owner = (fl_owner_t)lo;
+	file_lock->fl_pid = current->tgid;
+	file_lock->fl_flags = FL_POSIX;
 
-	file_lock.fl_start = lockt->lt_offset;
-	file_lock.fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length);
+	file_lock->fl_start = lockt->lt_offset;
+	file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length);
 
-	nfs4_transform_lock_offset(&file_lock);
+	nfs4_transform_lock_offset(file_lock);
 
-	status = nfsd_test_lock(rqstp, &cstate->current_fh, &file_lock);
+	status = nfsd_test_lock(rqstp, &cstate->current_fh, file_lock);
 	if (status)
 		goto out;
 
-	if (file_lock.fl_type != F_UNLCK) {
+	if (file_lock->fl_type != F_UNLCK) {
 		status = nfserr_denied;
-		nfs4_set_lock_denied(&file_lock, &lockt->lt_denied);
+		nfs4_set_lock_denied(file_lock, &lockt->lt_denied);
 	}
 out:
 	nfs4_unlock_state();
+	if (file_lock)
+		locks_free_lock(file_lock);
 	return status;
 }
 
@@ -4276,7 +4310,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	struct nfs4_ol_stateid *stp;
 	struct file *filp = NULL;
-	struct file_lock file_lock;
+	struct file_lock *file_lock = NULL;
 	__be32 status;
 	int err;
 						        
@@ -4298,23 +4332,29 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_lock_range;
 		goto out;
 	}
-	BUG_ON(!filp);
-	locks_init_lock(&file_lock);
-	file_lock.fl_type = F_UNLCK;
-	file_lock.fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
-	file_lock.fl_pid = current->tgid;
-	file_lock.fl_file = filp;
-	file_lock.fl_flags = FL_POSIX; 
-	file_lock.fl_lmops = &nfsd_posix_mng_ops;
-	file_lock.fl_start = locku->lu_offset;
-
-	file_lock.fl_end = last_byte_offset(locku->lu_offset, locku->lu_length);
-	nfs4_transform_lock_offset(&file_lock);
+	file_lock = locks_alloc_lock();
+	if (!file_lock) {
+		dprintk("NFSD: %s: unable to allocate lock!\n", __func__);
+		status = nfserr_jukebox;
+		goto out;
+	}
+	locks_init_lock(file_lock);
+	file_lock->fl_type = F_UNLCK;
+	file_lock->fl_owner = (fl_owner_t)lockowner(stp->st_stateowner);
+	file_lock->fl_pid = current->tgid;
+	file_lock->fl_file = filp;
+	file_lock->fl_flags = FL_POSIX;
+	file_lock->fl_lmops = &nfsd_posix_mng_ops;
+	file_lock->fl_start = locku->lu_offset;
+
+	file_lock->fl_end = last_byte_offset(locku->lu_offset,
+						locku->lu_length);
+	nfs4_transform_lock_offset(file_lock);
 
 	/*
 	*  Try to unlock the file in the VFS.
 	*/
-	err = vfs_lock_file(filp, F_SETLK, &file_lock, NULL);
+	err = vfs_lock_file(filp, F_SETLK, file_lock, NULL);
 	if (err) {
 		dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n");
 		goto out_nfserr;
@@ -4328,6 +4368,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 out:
 	if (!cstate->replay_owner)
 		nfs4_unlock_state();
+	if (file_lock)
+		locks_free_lock(file_lock);
 	return status;
 
 out_nfserr:
@@ -4501,12 +4543,12 @@ nfsd4_find_reclaim_client(struct nfs4_client *clp)
 * Called from OPEN. Look for clientid in reclaim list.
 */
 __be32
-nfs4_check_open_reclaim(clientid_t *clid)
+nfs4_check_open_reclaim(clientid_t *clid, bool sessions)
 {
 	struct nfs4_client *clp;
 
 	/* find clientid in conf_id_hashtbl */
-	clp = find_confirmed_client(clid);
+	clp = find_confirmed_client(clid, sessions);
 	if (clp == NULL)
 		return nfserr_reclaim_bad;
 
@@ -4522,7 +4564,6 @@ void nfsd_forget_clients(u64 num)
 
 	nfs4_lock_state();
 	list_for_each_entry_safe(clp, next, &client_lru, cl_lru) {
-		nfsd4_client_record_remove(clp);
 		expire_client(clp);
 		if (++count == num)
 			break;
@@ -4582,7 +4623,7 @@ void nfsd_forget_openowners(u64 num)
 	printk(KERN_INFO "NFSD: Forgot %d open owners", count);
 }
 
-int nfsd_process_n_delegations(u64 num, struct list_head *list)
+static int nfsd_process_n_delegations(u64 num, struct list_head *list)
 {
 	int i, count = 0;
 	struct nfs4_file *fp, *fnext;
@@ -4747,11 +4788,11 @@ __nfs4_state_shutdown(void)
 	for (i = 0; i < CLIENT_HASH_SIZE; i++) {
 		while (!list_empty(&conf_id_hashtbl[i])) {
 			clp = list_entry(conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
-			expire_client(clp);
+			destroy_client(clp);
 		}
 		while (!list_empty(&unconf_str_hashtbl[i])) {
 			clp = list_entry(unconf_str_hashtbl[i].next, struct nfs4_client, cl_strhash);
-			expire_client(clp);
+			destroy_client(clp);
 		}
 	}
 	INIT_LIST_HEAD(&reaplist);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 6322df36031f..fd548d155088 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2659,7 +2659,7 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
 		RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8);
 		WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
 		WRITE32(bcts->dir);
-		/* XXX: ? */
+		/* Sorry, we do not yet support RDMA over 4.1: */
 		WRITE32(0);
 		ADJUST_ARGS();
 	}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index fa49cff5ee65..dab350dfc376 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -406,7 +406,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 			return rv;
 		if (newthreads < 0)
 			return -EINVAL;
-		rv = nfsd_svc(NFS_PORT, newthreads);
+		rv = nfsd_svc(newthreads);
 		if (rv < 0)
 			return rv;
 	} else
@@ -683,25 +683,6 @@ static ssize_t __write_ports_addfd(char *buf)
 }
 
 /*
- * A '-' followed by the 'name' of a socket means we close the socket.
- */
-static ssize_t __write_ports_delfd(char *buf)
-{
-	char *toclose;
-	int len = 0;
-
-	toclose = kstrdup(buf + 1, GFP_KERNEL);
-	if (toclose == NULL)
-		return -ENOMEM;
-
-	if (nfsd_serv != NULL)
-		len = svc_sock_names(nfsd_serv, buf,
-					SIMPLE_TRANSACTION_LIMIT, toclose);
-	kfree(toclose);
-	return len;
-}
-
-/*
  * A transport listener is added by writing it's transport name and
  * a port number.
  */
@@ -712,7 +693,7 @@ static ssize_t __write_ports_addxprt(char *buf)
 	int port, err;
 	struct net *net = &init_net;
 
-	if (sscanf(buf, "%15s %4u", transport, &port) != 2)
+	if (sscanf(buf, "%15s %5u", transport, &port) != 2)
 		return -EINVAL;
 
 	if (port < 1 || port > USHRT_MAX)
@@ -746,31 +727,6 @@ out_err:
 	return err;
 }
 
-/*
- * A transport listener is removed by writing a "-", it's transport
- * name, and it's port number.
- */
-static ssize_t __write_ports_delxprt(char *buf)
-{
-	struct svc_xprt *xprt;
-	char transport[16];
-	int port;
-
-	if (sscanf(&buf[1], "%15s %4u", transport, &port) != 2)
-		return -EINVAL;
-
-	if (port < 1 || port > USHRT_MAX || nfsd_serv == NULL)
-		return -EINVAL;
-
-	xprt = svc_find_xprt(nfsd_serv, transport, &init_net, AF_UNSPEC, port);
-	if (xprt == NULL)
-		return -ENOTCONN;
-
-	svc_close_xprt(xprt);
-	svc_xprt_put(xprt);
-	return 0;
-}
-
 static ssize_t __write_ports(struct file *file, char *buf, size_t size)
 {
 	if (size == 0)
@@ -779,15 +735,9 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
 	if (isdigit(buf[0]))
 		return __write_ports_addfd(buf);
 
-	if (buf[0] == '-' && isdigit(buf[1]))
-		return __write_ports_delfd(buf);
-
 	if (isalpha(buf[0]))
 		return __write_ports_addxprt(buf);
 
-	if (buf[0] == '-' && isalpha(buf[1]))
-		return __write_ports_delxprt(buf);
-
 	return -EINVAL;
 }
 
@@ -825,21 +775,6 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
  * OR
  *
  * Input:
- *			buf:		C string containing a "-" followed
- *					by an integer value representing a
- *					previously passed in socket file
- *					descriptor
- *			size:		non-zero length of C string in @buf
- * Output:
- *	On success:	NFS service no longer listens on that socket;
- *			passed-in buffer filled with a '\n'-terminated C
- *			string containing a unique name of the listener;
- *			return code is the size in bytes of the string
- *	On error:	return code is a negative errno value
- *
- * OR
- *
- * Input:
  *			buf:		C string containing a transport
  *					name and an unsigned integer value
  *					representing the port to listen on,
@@ -848,19 +783,6 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
  * Output:
  *	On success:	returns zero; NFS service is started
  *	On error:	return code is a negative errno value
- *
- * OR
- *
- * Input:
- *			buf:		C string containing a "-" followed
- *					by a transport name and an unsigned
- *					integer value representing the port
- *					to listen on, separated by whitespace
- *			size:		non-zero length of C string in @buf
- * Output:
- *	On success:	returns zero; NFS service no longer listens
- *			on that transport
- *	On error:	return code is a negative errno value
  */
 static ssize_t write_ports(struct file *file, char *buf, size_t size)
 {
@@ -1008,8 +930,6 @@ static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
 	return nfsd4_write_time(file, buf, size, &nfsd4_grace);
 }
 
-extern char *nfs4_recoverydir(void);
-
 static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
 {
 	char *mesg = buf;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 2244222368ab..80d5ce40aadb 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -65,7 +65,7 @@ extern const struct seq_operations nfs_exports_op;
 /*
  * Function prototypes.
  */
-int		nfsd_svc(unsigned short port, int nrservs);
+int		nfsd_svc(int nrservs);
 int		nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp);
 
 int		nfsd_nrthreads(void);
@@ -124,6 +124,7 @@ int nfs4_state_start(void);
 void nfs4_state_shutdown(void);
 void nfs4_reset_lease(time_t leasetime);
 int nfs4_reset_recoverydir(char *recdir);
+char * nfs4_recoverydir(void);
 #else
 static inline void nfs4_state_init(void) { }
 static inline int nfsd4_init_slabs(void) { return 0; }
@@ -132,6 +133,7 @@ static inline int nfs4_state_start(void) { return 0; }
 static inline void nfs4_state_shutdown(void) { }
 static inline void nfs4_reset_lease(time_t leasetime) { }
 static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
+static inline char * nfs4_recoverydir(void) {return NULL; }
 #endif
 
 /*
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 240473cb708f..2013aa001dab 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -183,18 +183,18 @@ int nfsd_nrthreads(void)
 	return rv;
 }
 
-static int nfsd_init_socks(int port)
+static int nfsd_init_socks(void)
 {
 	int error;
 	if (!list_empty(&nfsd_serv->sv_permsocks))
 		return 0;
 
-	error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, port,
+	error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, NFS_PORT,
 					SVC_SOCK_DEFAULTS);
 	if (error < 0)
 		return error;
 
-	error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, port,
+	error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, NFS_PORT,
 					SVC_SOCK_DEFAULTS);
 	if (error < 0)
 		return error;
@@ -204,7 +204,7 @@ static int nfsd_init_socks(int port)
 
 static bool nfsd_up = false;
 
-static int nfsd_startup(unsigned short port, int nrservs)
+static int nfsd_startup(int nrservs)
 {
 	int ret;
 
@@ -218,7 +218,7 @@ static int nfsd_startup(unsigned short port, int nrservs)
 	ret = nfsd_racache_init(2*nrservs);
 	if (ret)
 		return ret;
-	ret = nfsd_init_socks(port);
+	ret = nfsd_init_socks();
 	if (ret)
 		goto out_racache;
 	ret = lockd_up(&init_net);
@@ -436,7 +436,7 @@ int nfsd_set_nrthreads(int n, int *nthreads)
  * this is the first time nrservs is nonzero.
  */
 int
-nfsd_svc(unsigned short port, int nrservs)
+nfsd_svc(int nrservs)
 {
 	int	error;
 	bool	nfsd_up_before;
@@ -458,7 +458,7 @@ nfsd_svc(unsigned short port, int nrservs)
 
 	nfsd_up_before = nfsd_up;
 
-	error = nfsd_startup(port, nrservs);
+	error = nfsd_startup(nrservs);
 	if (error)
 		goto out_destroy;
 	error = svc_set_num_threads(nfsd_serv, NULL, nrservs);
@@ -487,7 +487,7 @@ static int
 nfsd(void *vrqstp)
 {
 	struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
-	int err, preverr = 0;
+	int err;
 
 	/* Lock module and set up kernel thread */
 	mutex_lock(&nfsd_mutex);
@@ -534,16 +534,6 @@ nfsd(void *vrqstp)
 			;
 		if (err == -EINTR)
 			break;
-		else if (err < 0) {
-			if (err != preverr) {
-				printk(KERN_WARNING "%s: unexpected error "
-					"from svc_recv (%d)\n", __func__, -err);
-				preverr = err;
-			}
-			schedule_timeout_uninterruptible(HZ);
-			continue;
-		}
-
 		validate_process_creds();
 		svc_process(rqstp);
 		validate_process_creds();
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 22bd0a66c356..e036894bce57 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -373,11 +373,7 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
 	return container_of(so, struct nfs4_lockowner, lo_owner);
 }
 
-/*
-*  nfs4_file: a file opened by some number of (open) nfs4_stateowners.
-*    o fi_perfile list is used to search for conflicting 
-*      share_acces, share_deny on the file.
-*/
+/* nfs4_file: a file opened by some number of (open) nfs4_stateowners. */
 struct nfs4_file {
 	atomic_t		fi_ref;
 	struct list_head        fi_hash;    /* hash by "struct inode *" */
@@ -459,7 +455,7 @@ extern void nfs4_unlock_state(void);
 extern int nfs4_in_grace(void);
 extern void nfs4_release_reclaim(void);
 extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(struct nfs4_client *crp);
-extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
+extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions);
 extern void nfs4_free_openowner(struct nfs4_openowner *);
 extern void nfs4_free_lockowner(struct nfs4_lockowner *);
 extern int set_callback_cred(void);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 3f67b8e12251..c120b48ec305 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1581,7 +1581,7 @@ nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
 	 */
 
 	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = inode->i_op->readlink(path.dentry, buf, *lenp);
+	host_err = inode->i_op->readlink(path.dentry, (char __user *)buf, *lenp);
 	set_fs(oldfs);
 
 	if (host_err < 0)
diff --git a/fs/open.c b/fs/open.c
index 44da0feeca2c..59071f55bf7f 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -478,7 +478,7 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
 
 	file = fget(fd);
 	if (file) {
-		audit_inode(NULL, file->f_path.dentry);
+		audit_inode(NULL, file->f_path.dentry, 0);
 		err = chmod_common(&file->f_path, mode);
 		fput(file);
 	}
@@ -588,7 +588,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	error = mnt_want_write_file(f.file);
 	if (error)
 		goto out_fput;
-	audit_inode(NULL, f.file->f_path.dentry);
+	audit_inode(NULL, f.file->f_path.dentry, 0);
 	error = chown_common(&f.file->f_path, user, group);
 	mnt_drop_write_file(f.file);
 out_fput:
@@ -859,6 +859,24 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 }
 
 /**
+ * file_open_name - open file and return file pointer
+ *
+ * @name:	struct filename containing path to open
+ * @flags:	open flags as per the open(2) second argument
+ * @mode:	mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to.  But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *file_open_name(struct filename *name, int flags, umode_t mode)
+{
+	struct open_flags op;
+	int lookup = build_open_flags(flags, mode, &op);
+	return do_filp_open(AT_FDCWD, name, &op, lookup);
+}
+
+/**
  * filp_open - open file and return file pointer
  *
  * @filename:	path to open
@@ -871,9 +889,8 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
  */
 struct file *filp_open(const char *filename, int flags, umode_t mode)
 {
-	struct open_flags op;
-	int lookup = build_open_flags(flags, mode, &op);
-	return do_filp_open(AT_FDCWD, filename, &op, lookup);
+	struct filename name = {.name = filename};
+	return file_open_name(&name, flags, mode);
 }
 EXPORT_SYMBOL(filp_open);
 
@@ -895,7 +912,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
 	int lookup = build_open_flags(flags, mode, &op);
-	char *tmp = getname(filename);
+	struct filename *tmp = getname(filename);
 	int fd = PTR_ERR(tmp);
 
 	if (!IS_ERR(tmp)) {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ef5c84be66f9..144a96732dd7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2258,7 +2258,8 @@ static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
 	pid_t tgid = task_tgid_nr_ns(current, ns);
 	char *name = ERR_PTR(-ENOENT);
 	if (tgid) {
-		name = __getname();
+		/* 11 for max length of signed int in decimal + NULL term */
+		name = kmalloc(12, GFP_KERNEL);
 		if (!name)
 			name = ERR_PTR(-ENOMEM);
 		else
@@ -2273,7 +2274,7 @@ static void proc_self_put_link(struct dentry *dentry, struct nameidata *nd,
 {
 	char *s = nd_get_link(nd);
 	if (!IS_ERR(s))
-		__putname(s);
+		kfree(s);
 }
 
 static const struct inode_operations proc_self_inode_operations = {
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index cceaab07ad54..43973b084abf 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -12,6 +12,7 @@
 #include <linux/sched.h>
 #include <linux/proc_fs.h>
 struct  ctl_table_header;
+struct  mempolicy;
 
 extern struct proc_dir_entry proc_root;
 #ifdef CONFIG_PROC_SYSCTL
@@ -74,6 +75,9 @@ struct proc_maps_private {
 #ifdef CONFIG_MMU
 	struct vm_area_struct *tail_vma;
 #endif
+#ifdef CONFIG_NUMA
+	struct mempolicy *task_mempolicy;
+#endif
 };
 
 void proc_init_inodecache(void);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 64c3b3172367..e296572c73ed 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -45,10 +45,13 @@ static cputime64_t get_iowait_time(int cpu)
 
 static u64 get_idle_time(int cpu)
 {
-	u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL);
+	u64 idle, idle_time = -1ULL;
+
+	if (cpu_online(cpu))
+		idle_time = get_cpu_idle_time_us(cpu, NULL);
 
 	if (idle_time == -1ULL)
-		/* !NO_HZ so we can rely on cpustat.idle */
+		/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
 		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	else
 		idle = usecs_to_cputime64(idle_time);
@@ -58,10 +61,13 @@ static u64 get_idle_time(int cpu)
 
 static u64 get_iowait_time(int cpu)
 {
-	u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+	u64 iowait, iowait_time = -1ULL;
+
+	if (cpu_online(cpu))
+		iowait_time = get_cpu_iowait_time_us(cpu, NULL);
 
 	if (iowait_time == -1ULL)
-		/* !NO_HZ so we can rely on cpustat.iowait */
+		/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
 		iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	else
 		iowait = usecs_to_cputime64(iowait_time);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 79827ce03e3b..90c63f9392a5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -90,10 +90,55 @@ static void pad_len_spaces(struct seq_file *m, int len)
 	seq_printf(m, "%*c", len, ' ');
 }
 
+#ifdef CONFIG_NUMA
+/*
+ * These functions are for numa_maps but called in generic **maps seq_file
+ * ->start(), ->stop() ops.
+ *
+ * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
+ * Each mempolicy object is controlled by reference counting. The problem here
+ * is how to avoid accessing dead mempolicy object.
+ *
+ * Because we're holding mmap_sem while reading seq_file, it's safe to access
+ * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
+ *
+ * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
+ * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
+ * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
+ * gurantee the task never exits under us. But taking task_lock() around
+ * get_vma_plicy() causes lock order problem.
+ *
+ * To access task->mempolicy without lock, we hold a reference count of an
+ * object pointed by task->mempolicy and remember it. This will guarantee
+ * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
+ */
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+	struct task_struct *task = priv->task;
+
+	task_lock(task);
+	priv->task_mempolicy = task->mempolicy;
+	mpol_get(priv->task_mempolicy);
+	task_unlock(task);
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+	mpol_put(priv->task_mempolicy);
+}
+#else
+static void hold_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+static void release_task_mempolicy(struct proc_maps_private *priv)
+{
+}
+#endif
+
 static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
 {
 	if (vma && vma != priv->tail_vma) {
 		struct mm_struct *mm = vma->vm_mm;
+		release_task_mempolicy(priv);
 		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
@@ -132,7 +177,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	tail_vma = get_gate_vma(priv->task->mm);
 	priv->tail_vma = tail_vma;
-
+	hold_task_mempolicy(priv);
 	/* Start with last addr hint */
 	vma = find_vma(mm, last_addr);
 	if (last_addr && vma) {
@@ -159,6 +204,7 @@ out:
 	if (vma)
 		return vma;
 
+	release_task_mempolicy(priv);
 	/* End of vmas has been reached */
 	m->version = (tail_vma != NULL)? 0: -1UL;
 	up_read(&mm->mmap_sem);
@@ -1158,6 +1204,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	struct vm_area_struct *vma = v;
 	struct numa_maps *md = &numa_priv->md;
 	struct file *file = vma->vm_file;
+	struct task_struct *task = proc_priv->task;
 	struct mm_struct *mm = vma->vm_mm;
 	struct mm_walk walk = {};
 	struct mempolicy *pol;
@@ -1177,7 +1224,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	walk.private = md;
 	walk.mm = mm;
 
-	pol = get_vma_policy(proc_priv->task, vma, vma->vm_start);
+	pol = get_vma_policy(task, vma, vma->vm_start);
 	mpol_to_str(buffer, sizeof(buffer), pol, 0);
 	mpol_cond_put(pol);
 
@@ -1189,7 +1236,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_printf(m, " heap");
 	} else {
-		pid_t tid = vm_is_stack(proc_priv->task, vma, is_pid);
+		pid_t tid = vm_is_stack(task, vma, is_pid);
 		if (tid != 0) {
 			/*
 			 * Thread stack in /proc/PID/task/TID/maps or
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 557a9c20a215..05ae3c97f7a5 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1160,6 +1160,8 @@ static int need_print_warning(struct dquot_warn *warn)
 			return uid_eq(current_fsuid(), warn->w_dq_id.uid);
 		case GRPQUOTA:
 			return in_group_p(warn->w_dq_id.gid);
+		case PRJQUOTA:	/* Never taken... Just make gcc happy */
+			return 0;
 	}
 	return 0;
 }
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index ff0135d6bc51..af1661f7a54f 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -331,11 +331,11 @@ static struct super_block *quotactl_block(const char __user *special, int cmd)
 #ifdef CONFIG_BLOCK
 	struct block_device *bdev;
 	struct super_block *sb;
-	char *tmp = getname(special);
+	struct filename *tmp = getname(special);
 
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	bdev = lookup_bdev(tmp);
+	bdev = lookup_bdev(tmp->name);
 	putname(tmp);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 46485557cdc6..f27f01a98aa2 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1573,8 +1573,10 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 			reiserfs_warning(sb, "reiserfs-13077",
 				"nfsd/reiserfs, fhtype=%d, len=%d - odd",
 				fh_type, fh_len);
-		fh_type = 5;
+		fh_type = fh_len;
 	}
+	if (fh_len < 2)
+		return NULL;
 
 	return reiserfs_get_dentry(sb, fid->raw[0], fid->raw[1],
 		(fh_type == 3 || fh_type >= 5) ? fid->raw[2] : 0);
@@ -1583,6 +1585,8 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid,
 		int fh_len, int fh_type)
 {
+	if (fh_type > fh_len)
+		fh_type = fh_len;
 	if (fh_type < 4)
 		return NULL;
 
diff --git a/fs/super.c b/fs/super.c
index a3bc935069d9..12f123712161 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -186,15 +186,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		spin_lock_init(&s->s_inode_lru_lock);
 		INIT_LIST_HEAD(&s->s_mounts);
 		init_rwsem(&s->s_umount);
-		mutex_init(&s->s_lock);
 		lockdep_set_class(&s->s_umount, &type->s_umount_key);
 		/*
-		 * The locking rules for s_lock are up to the
-		 * filesystem. For example ext3fs has different
-		 * lock ordering than usbfs:
-		 */
-		lockdep_set_class(&s->s_lock, &type->s_lock_key);
-		/*
 		 * sget() can have s_umount recursion.
 		 *
 		 * When it cannot find a suitable sb, it allocates a new
@@ -394,22 +387,6 @@ bool grab_super_passive(struct super_block *sb)
 	return false;
 }
 
-/*
- * Superblock locking.  We really ought to get rid of these two.
- */
-void lock_super(struct super_block * sb)
-{
-	mutex_lock(&sb->s_lock);
-}
-
-void unlock_super(struct super_block * sb)
-{
-	mutex_unlock(&sb->s_lock);
-}
-
-EXPORT_SYMBOL(lock_super);
-EXPORT_SYMBOL(unlock_super);
-
 /**
  *	generic_shutdown_super	-	common helper for ->kill_sb()
  *	@sb: superblock to kill
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 6b0bb00d4d2b..2fbdff6be25c 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -485,20 +485,18 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 /**
  *	sysfs_pathname - return full path to sysfs dirent
  *	@sd: sysfs_dirent whose path we want
- *	@path: caller allocated buffer
+ *	@path: caller allocated buffer of size PATH_MAX
  *
  *	Gives the name "/" to the sysfs_root entry; any path returned
  *	is relative to wherever sysfs is mounted.
- *
- *	XXX: does no error checking on @path size
  */
 static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
 {
 	if (sd->s_parent) {
 		sysfs_pathname(sd->s_parent, path);
-		strcat(path, "/");
+		strlcat(path, "/", PATH_MAX);
 	}
-	strcat(path, sd->s_name);
+	strlcat(path, sd->s_name, PATH_MAX);
 	return path;
 }
 
@@ -531,9 +529,11 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 		char *path = kzalloc(PATH_MAX, GFP_KERNEL);
 		WARN(1, KERN_WARNING
 		     "sysfs: cannot create duplicate filename '%s'\n",
-		     (path == NULL) ? sd->s_name :
-		     strcat(strcat(sysfs_pathname(acxt->parent_sd, path), "/"),
-		            sd->s_name));
+		     (path == NULL) ? sd->s_name
+				    : (sysfs_pathname(acxt->parent_sd, path),
+				       strlcat(path, "/", PATH_MAX),
+				       strlcat(path, sd->s_name, PATH_MAX),
+				       path));
 		kfree(path);
 	}
 
diff --git a/fs/sysv/balloc.c b/fs/sysv/balloc.c
index 9a6ad96acf27..921c053fc052 100644
--- a/fs/sysv/balloc.c
+++ b/fs/sysv/balloc.c
@@ -60,12 +60,12 @@ void sysv_free_block(struct super_block * sb, sysv_zone_t nr)
 		return;
 	}
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 	count = fs16_to_cpu(sbi, *sbi->s_bcache_count);
 
 	if (count > sbi->s_flc_size) {
 		printk("sysv_free_block: flc_count > flc_size\n");
-		unlock_super(sb);
+		mutex_unlock(&sbi->s_lock);
 		return;
 	}
 	/* If the free list head in super-block is full, it is copied
@@ -77,7 +77,7 @@ void sysv_free_block(struct super_block * sb, sysv_zone_t nr)
 		bh = sb_getblk(sb, block);
 		if (!bh) {
 			printk("sysv_free_block: getblk() failed\n");
-			unlock_super(sb);
+			mutex_unlock(&sbi->s_lock);
 			return;
 		}
 		memset(bh->b_data, 0, sb->s_blocksize);
@@ -93,7 +93,7 @@ void sysv_free_block(struct super_block * sb, sysv_zone_t nr)
 	*sbi->s_bcache_count = cpu_to_fs16(sbi, count);
 	fs32_add(sbi, sbi->s_free_blocks, 1);
 	dirty_sb(sb);
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 }
 
 sysv_zone_t sysv_new_block(struct super_block * sb)
@@ -104,7 +104,7 @@ sysv_zone_t sysv_new_block(struct super_block * sb)
 	struct buffer_head * bh;
 	unsigned count;
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 	count = fs16_to_cpu(sbi, *sbi->s_bcache_count);
 
 	if (count == 0) /* Applies only to Coherent FS */
@@ -147,11 +147,11 @@ sysv_zone_t sysv_new_block(struct super_block * sb)
 	/* Now the free list head in the superblock is valid again. */
 	fs32_add(sbi, sbi->s_free_blocks, -1);
 	dirty_sb(sb);
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	return nr;
 
 Enospc:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	return 0;
 }
 
@@ -173,7 +173,7 @@ unsigned long sysv_count_free_blocks(struct super_block * sb)
 	if (sbi->s_type == FSTYPE_AFS)
 		return 0;
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 	sb_count = fs32_to_cpu(sbi, *sbi->s_free_blocks);
 
 	if (0)
@@ -211,7 +211,7 @@ unsigned long sysv_count_free_blocks(struct super_block * sb)
 	if (count != sb_count)
 		goto Ecount;
 done:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	return count;
 
 Einval:
diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c
index 8233b02eccae..f9db4eb31db4 100644
--- a/fs/sysv/ialloc.c
+++ b/fs/sysv/ialloc.c
@@ -118,7 +118,7 @@ void sysv_free_inode(struct inode * inode)
 		       "%s\n", inode->i_sb->s_id);
 		return;
 	}
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 	count = fs16_to_cpu(sbi, *sbi->s_sb_fic_count);
 	if (count < sbi->s_fic_size) {
 		*sv_sb_fic_inode(sb,count++) = cpu_to_fs16(sbi, ino);
@@ -128,7 +128,7 @@ void sysv_free_inode(struct inode * inode)
 	dirty_sb(sb);
 	memset(raw_inode, 0, sizeof(struct sysv_inode));
 	mark_buffer_dirty(bh);
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	brelse(bh);
 }
 
@@ -147,13 +147,13 @@ struct inode * sysv_new_inode(const struct inode * dir, umode_t mode)
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 	count = fs16_to_cpu(sbi, *sbi->s_sb_fic_count);
 	if (count == 0 || (*sv_sb_fic_inode(sb,count-1) == 0)) {
 		count = refill_free_cache(sb);
 		if (count == 0) {
 			iput(inode);
-			unlock_super(sb);
+			mutex_unlock(&sbi->s_lock);
 			return ERR_PTR(-ENOSPC);
 		}
 	}
@@ -174,7 +174,7 @@ struct inode * sysv_new_inode(const struct inode * dir, umode_t mode)
 	sysv_write_inode(inode, &wbc);	/* ensure inode not allocated again */
 	mark_inode_dirty(inode);	/* cleared by sysv_write_inode() */
 	/* That's it. */
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	return inode;
 }
 
@@ -185,7 +185,7 @@ unsigned long sysv_count_free_inodes(struct super_block * sb)
 	struct sysv_inode * raw_inode;
 	int ino, count, sb_count;
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 
 	sb_count = fs16_to_cpu(sbi, *sbi->s_sb_total_free_inodes);
 
@@ -213,7 +213,7 @@ unsigned long sysv_count_free_inodes(struct super_block * sb)
 	if (count != sb_count)
 		goto Einval;
 out:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	return count;
 
 Einval:
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index d33e506c1eac..c327d4ee1235 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -36,7 +36,7 @@ static int sysv_sync_fs(struct super_block *sb, int wait)
 	struct sysv_sb_info *sbi = SYSV_SB(sb);
 	unsigned long time = get_seconds(), old_time;
 
-	lock_super(sb);
+	mutex_lock(&sbi->s_lock);
 
 	/*
 	 * If we are going to write out the super block,
@@ -51,7 +51,7 @@ static int sysv_sync_fs(struct super_block *sb, int wait)
 		mark_buffer_dirty(sbi->s_bh2);
 	}
 
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 
 	return 0;
 }
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index 7491c33b6468..a38e87bdd78d 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -368,6 +368,7 @@ static int sysv_fill_super(struct super_block *sb, void *data, int silent)
 
 	sbi->s_sb = sb;
 	sbi->s_block_base = 0;
+	mutex_init(&sbi->s_lock);
 	sb->s_fs_info = sbi;
 
 	sb_set_blocksize(sb, BLOCK_SIZE);
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 0bc35fdc58e2..69d488986cce 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -58,6 +58,7 @@ struct sysv_sb_info {
 	u32            s_nzones;	/* same as s_sbd->s_fsize */
 	u16	       s_namelen;       /* max length of dir entry */
 	int	       s_forced_ro;
+	struct mutex s_lock;
 };
 
 /*
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 1b3e410bf334..a7ea492ae660 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -54,7 +54,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 	if (ufs_fragnum(fragment) + count > uspi->s_fpg)
 		ufs_error (sb, "ufs_free_fragments", "internal error");
 	
-	lock_super(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 	cgno = ufs_dtog(uspi, fragment);
 	bit = ufs_dtogd(uspi, fragment);
@@ -118,12 +118,12 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	ufs_mark_sb_dirty(sb);
 	
-	unlock_super (sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed:
-	unlock_super (sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return;
 }
@@ -155,7 +155,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count)
 		goto failed;
 	}
 
-	lock_super(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 do_more:
 	overflow = 0;
@@ -215,12 +215,12 @@ do_more:
 	}
 
 	ufs_mark_sb_dirty(sb);
-	unlock_super (sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed_unlock:
-	unlock_super (sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 failed:
 	UFSD("EXIT (FAILED)\n");
 	return;
@@ -361,7 +361,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	usb1 = ubh_get_usb_first(uspi);
 	*err = -ENOSPC;
 
-	lock_super (sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	tmp = ufs_data_ptr_to_cpu(sb, p);
 
 	if (count + ufs_fragnum(fragment) > uspi->s_fpb) {
@@ -382,19 +382,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 				  "fragment %llu, tmp %llu\n",
 				  (unsigned long long)fragment,
 				  (unsigned long long)tmp);
-			unlock_super(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return INVBLOCK;
 		}
 		if (fragment < UFS_I(inode)->i_lastfrag) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_super (sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
 	else {
 		if (tmp) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_super(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
@@ -403,7 +403,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	 * There is not enough space for user on the device
 	 */
 	if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) {
-		unlock_super (sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT (FAILED)\n");
 		return 0;
 	}
@@ -428,7 +428,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 			ufs_clear_frags(inode, result + oldcount,
 					newcount - oldcount, locked_page != NULL);
 		}
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -443,7 +443,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 						fragment + count);
 		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
 				locked_page != NULL);
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -481,7 +481,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		if (newcount < request)
 			ufs_free_fragments (inode, result + newcount, request - newcount);
 		ufs_free_fragments (inode, tmp, oldcount);
@@ -489,7 +489,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		return result;
 	}
 
-	unlock_super(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return 0;
 }		
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index e84cbe21b986..d0426d74817b 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -71,11 +71,11 @@ void ufs_free_inode (struct inode * inode)
 	
 	ino = inode->i_ino;
 
-	lock_super (sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) {
 		ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino);
-		unlock_super (sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	
@@ -83,7 +83,7 @@ void ufs_free_inode (struct inode * inode)
 	bit = ufs_inotocgoff (ino);
 	ucpi = ufs_load_cylinder (sb, cg);
 	if (!ucpi) {
-		unlock_super (sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	ucg = ubh_get_ucg(UCPI_UBH(ucpi));
@@ -117,7 +117,7 @@ void ufs_free_inode (struct inode * inode)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	
 	ufs_mark_sb_dirty(sb);
-	unlock_super (sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 }
 
@@ -197,7 +197,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode)
 	uspi = sbi->s_uspi;
 	usb1 = ubh_get_usb_first(uspi);
 
-	lock_super (sb);
+	mutex_lock(&sbi->s_lock);
 
 	/*
 	 * Try to place the inode in its parent directory
@@ -333,20 +333,20 @@ cg_found:
 		brelse(bh);
 	}
 
-	unlock_super (sb);
+	mutex_unlock(&sbi->s_lock);
 
 	UFSD("allocating inode %lu\n", inode->i_ino);
 	UFSD("EXIT\n");
 	return inode;
 
 fail_remove_inode:
-	unlock_super(sb);
+	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
 	iput(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
-	unlock_super (sb);
+	mutex_unlock(&sbi->s_lock);
 	make_bad_inode(inode);
 	iput (inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index f7cfecfe1cab..dc8e3a861d0f 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -699,7 +699,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	unsigned flags;
 
 	lock_ufs(sb);
-	lock_super(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	UFSD("ENTER\n");
 
@@ -717,7 +717,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	ufs_put_cstotal(sb);
 
 	UFSD("EXIT\n");
-	unlock_super(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 
 	return 0;
@@ -805,6 +805,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 #endif
 	mutex_init(&sbi->mutex);
+	mutex_init(&sbi->s_lock);
 	spin_lock_init(&sbi->work_lock);
 	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
 	/*
@@ -1280,7 +1281,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	unsigned flags;
 
 	lock_ufs(sb);
-	lock_super(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	uspi = UFS_SB(sb)->s_uspi;
 	flags = UFS_SB(sb)->s_flags;
 	usb1 = ubh_get_usb_first(uspi);
@@ -1294,7 +1295,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	new_mount_opt = 0;
 	ufs_set_opt (new_mount_opt, ONERROR_LOCK);
 	if (!ufs_parse_options (data, &new_mount_opt)) {
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
@@ -1302,14 +1303,14 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		new_mount_opt |= ufstype;
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
 		printk("ufstype can't be changed during remount\n");
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
 
 	if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		UFS_SB(sb)->s_mount_opt = new_mount_opt;
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return 0;
 	}
@@ -1334,7 +1335,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 #ifndef CONFIG_UFS_FS_WRITE
 		printk("ufs was compiled with read-only support, "
 		"can't be mounted as read-write\n");
-		unlock_super(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 #else
@@ -1344,13 +1345,13 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		    ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
 			printk("this ufstype is read-only supported\n");
-			unlock_super(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
 			printk("failed during remounting\n");
-			unlock_super(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EPERM;
 		}
@@ -1358,7 +1359,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 #endif
 	}
 	UFS_SB(sb)->s_mount_opt = new_mount_opt;
-	unlock_super(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 	return 0;
 }
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 343e6fc571e5..ff2c15ab81aa 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -24,6 +24,7 @@ struct ufs_sb_info {
 	int work_queued; /* non-zero if the delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
 	spinlock_t work_lock; /* protects sync_work and work_queued */
+	struct mutex s_lock;
 };
 
 struct ufs_inode_info {
diff --git a/fs/xattr.c b/fs/xattr.c
index 1780f062dbaf..e21c119f4f99 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -412,7 +412,7 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 	if (!f.file)
 		return error;
 	dentry = f.file->f_path.dentry;
-	audit_inode(NULL, dentry);
+	audit_inode(NULL, dentry, 0);
 	error = mnt_want_write_file(f.file);
 	if (!error) {
 		error = setxattr(dentry, name, value, size, flags);
@@ -507,7 +507,7 @@ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
 
 	if (!f.file)
 		return error;
-	audit_inode(NULL, f.file->f_path.dentry);
+	audit_inode(NULL, f.file->f_path.dentry, 0);
 	error = getxattr(f.file->f_path.dentry, name, value, size);
 	fdput(f);
 	return error;
@@ -586,7 +586,7 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
 
 	if (!f.file)
 		return error;
-	audit_inode(NULL, f.file->f_path.dentry);
+	audit_inode(NULL, f.file->f_path.dentry, 0);
 	error = listxattr(f.file->f_path.dentry, list, size);
 	fdput(f);
 	return error;
@@ -655,7 +655,7 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 	if (!f.file)
 		return error;
 	dentry = f.file->f_path.dentry;
-	audit_inode(NULL, dentry);
+	audit_inode(NULL, dentry, 0);
 	error = mnt_want_write_file(f.file);
 	if (!error) {
 		error = removexattr(dentry, name);
@@ -846,7 +846,7 @@ static int __simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 			      const void *value, size_t size, int flags)
 {
 	struct simple_xattr *xattr;
-	struct simple_xattr *uninitialized_var(new_xattr);
+	struct simple_xattr *new_xattr = NULL;
 	int err = 0;
 
 	/* value == NULL means remove */
diff --git a/fs/xattr_acl.c b/fs/xattr_acl.c
index 11efd830b5f5..9fbea87fdb6e 100644
--- a/fs/xattr_acl.c
+++ b/fs/xattr_acl.c
@@ -45,7 +45,7 @@ static void posix_acl_fix_xattr_userns(
 			break;
 		case ACL_GROUP:
 			gid = make_kgid(from, le32_to_cpu(entry->e_id));
-			entry->e_id = cpu_to_le32(from_kuid(to, uid));
+			entry->e_id = cpu_to_le32(from_kgid(to, gid));
 			break;
 		default:
 			break;
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 42679223a0fd..8c6d1d70278c 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -189,6 +189,9 @@ xfs_fs_fh_to_parent(struct super_block *sb, struct fid *fid,
 	struct xfs_fid64	*fid64 = (struct xfs_fid64 *)fid;
 	struct inode		*inode = NULL;
 
+	if (fh_len < xfs_fileid_length(fileid_type))
+		return NULL;
+
 	switch (fileid_type) {
 	case FILEID_INO32_GEN_PARENT:
 		inode = xfs_nfs_get_inode(sb, fid->i32.parent_ino,