Merge tag 'v4.3-rc4' into locking/core, to pick up fixes before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

28 files changed, 420 insertions, 157 deletions

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 81220b2203c6..0ef5cc13fae2 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -44,8 +44,6 @@
 #define BTRFS_INODE_IN_DELALLOC_LIST		9
 #define BTRFS_INODE_READDIO_NEED_LOCK		10
 #define BTRFS_INODE_HAS_PROPS		        11
-/* DIO is ready to submit */
-#define BTRFS_INODE_DIO_READY		        12
 /*
  * The following 3 bits are meant only for the btree inode.
  * When any of them is set, it means an error happened while writing an
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0d98aee34fee..295795aebe0b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3765,9 +3765,7 @@ void close_ctree(struct btrfs_root *root)
 		 * block groups queued for removal, the deletion will be
 		 * skipped when we quit the cleaner thread.
 		 */
-		mutex_lock(&root->fs_info->cleaner_mutex);
 		btrfs_delete_unused_bgs(root->fs_info);
-		mutex_unlock(&root->fs_info->cleaner_mutex);
 
 		ret = btrfs_commit_super(root);
 		if (ret)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5411f0ab5683..9f9604201333 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3742,10 +3742,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->bytes_reserved = 0;
 	found->bytes_readonly = 0;
 	found->bytes_may_use = 0;
-	if (total_bytes > 0)
-		found->full = 0;
-	else
-		found->full = 1;
+	found->full = 0;
 	found->force_alloc = CHUNK_ALLOC_NO_FORCE;
 	found->chunk_alloc = 0;
 	found->flush = 0;
@@ -8668,7 +8665,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	}
 
 	if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) {
-		btrfs_drop_and_free_fs_root(tree_root->fs_info, root);
+		btrfs_add_dropped_root(trans, root);
 	} else {
 		free_extent_buffer(root->node);
 		free_extent_buffer(root->commit_root);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f1018cfbfefa..e2357e31609a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2798,7 +2798,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			      bio_end_io_t end_io_func,
 			      int mirror_num,
 			      unsigned long prev_bio_flags,
-			      unsigned long bio_flags)
+			      unsigned long bio_flags,
+			      bool force_bio_submit)
 {
 	int ret = 0;
 	struct bio *bio;
@@ -2814,6 +2815,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			contig = bio_end_sector(bio) == sector;
 
 		if (prev_bio_flags != bio_flags || !contig ||
+		    force_bio_submit ||
 		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
 			ret = submit_one_bio(rw, bio, mirror_num,
@@ -2910,7 +2912,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 			 get_extent_t *get_extent,
 			 struct extent_map **em_cached,
 			 struct bio **bio, int mirror_num,
-			 unsigned long *bio_flags, int rw)
+			 unsigned long *bio_flags, int rw,
+			 u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
 	u64 start = page_offset(page);
@@ -2958,6 +2961,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 	}
 	while (cur <= end) {
 		unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+		bool force_bio_submit = false;
 
 		if (cur >= last_byte) {
 			char *userpage;
@@ -3008,6 +3012,49 @@ static int __do_readpage(struct extent_io_tree *tree,
 		block_start = em->block_start;
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			block_start = EXTENT_MAP_HOLE;
+
+		/*
+		 * If we have a file range that points to a compressed extent
+		 * and it's followed by a consecutive file range that points to
+		 * to the same compressed extent (possibly with a different
+		 * offset and/or length, so it either points to the whole extent
+		 * or only part of it), we must make sure we do not submit a
+		 * single bio to populate the pages for the 2 ranges because
+		 * this makes the compressed extent read zero out the pages
+		 * belonging to the 2nd range. Imagine the following scenario:
+		 *
+		 *  File layout
+		 *  [0 - 8K]                     [8K - 24K]
+		 *    |                               |
+		 *    |                               |
+		 * points to extent X,         points to extent X,
+		 * offset 4K, length of 8K     offset 0, length 16K
+		 *
+		 * [extent X, compressed length = 4K uncompressed length = 16K]
+		 *
+		 * If the bio to read the compressed extent covers both ranges,
+		 * it will decompress extent X into the pages belonging to the
+		 * first range and then it will stop, zeroing out the remaining
+		 * pages that belong to the other range that points to extent X.
+		 * So here we make sure we submit 2 bios, one for the first
+		 * range and another one for the third range. Both will target
+		 * the same physical extent from disk, but we can't currently
+		 * make the compressed bio endio callback populate the pages
+		 * for both ranges because each compressed bio is tightly
+		 * coupled with a single extent map, and each range can have
+		 * an extent map with a different offset value relative to the
+		 * uncompressed data of our extent and different lengths. This
+		 * is a corner case so we prioritize correctness over
+		 * non-optimal behavior (submitting 2 bios for the same extent).
+		 */
+		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
+		    prev_em_start && *prev_em_start != (u64)-1 &&
+		    *prev_em_start != em->orig_start)
+			force_bio_submit = true;
+
+		if (prev_em_start)
+			*prev_em_start = em->orig_start;
+
 		free_extent_map(em);
 		em = NULL;
 
@@ -3057,7 +3104,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 					 bdev, bio, pnr,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
-					 this_bio_flag);
+					 this_bio_flag,
+					 force_bio_submit);
 		if (!ret) {
 			nr++;
 			*bio_flags = this_bio_flag;
@@ -3089,6 +3137,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	struct inode *inode;
 	struct btrfs_ordered_extent *ordered;
 	int index;
+	u64 prev_em_start = (u64)-1;
 
 	inode = pages[0]->mapping->host;
 	while (1) {
@@ -3104,7 +3153,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, rw);
+			      mirror_num, bio_flags, rw, &prev_em_start);
 		page_cache_release(pages[index]);
 	}
 }
@@ -3172,7 +3221,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	}
 
 	ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
-			    bio_flags, rw);
+			    bio_flags, rw, NULL);
 	return ret;
 }
 
@@ -3198,7 +3247,7 @@ int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
 	int ret;
 
 	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-				      &bio_flags, READ);
+			    &bio_flags, READ, NULL);
 	if (bio)
 		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
 	return ret;
@@ -3451,7 +3500,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 						 sector, iosize, pg_offset,
 						 bdev, &epd->bio, max_nr,
 						 end_bio_extent_writepage,
-						 0, 0, 0);
+						 0, 0, 0, false);
 			if (ret)
 				SetPageError(page);
 		}
@@ -3754,7 +3803,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
 					 PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
 					 -1, end_bio_extent_buffer_writepage,
-					 0, epd->bio_flags, bio_flags);
+					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
 		if (ret) {
 			set_btree_ioerr(p);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a0fa7253a2d7..611b66d73e80 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5084,7 +5084,8 @@ void btrfs_evict_inode(struct inode *inode)
 		goto no_delete;
 	}
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
-	btrfs_wait_ordered_range(inode, 0, (u64)-1);
+	if (!special_file(inode->i_mode))
+		btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
 	btrfs_free_io_failure_record(inode, 0, (u64)-1);
 
@@ -7408,6 +7409,10 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 	return em;
 }
 
+struct btrfs_dio_data {
+	u64 outstanding_extents;
+	u64 reserve;
+};
 
 static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -7415,10 +7420,10 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	struct extent_map *em;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_state *cached_state = NULL;
+	struct btrfs_dio_data *dio_data = NULL;
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
-	u64 *outstanding_extents = NULL;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
@@ -7436,7 +7441,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		 * that anything that needs to check if there's a transction doesn't get
 		 * confused.
 		 */
-		outstanding_extents = current->journal_info;
+		dio_data = current->journal_info;
 		current->journal_info = NULL;
 	}
 
@@ -7568,17 +7573,18 @@ unlock:
 		 * within our reservation, otherwise we need to adjust our inode
 		 * counter appropriately.
 		 */
-		if (*outstanding_extents) {
-			(*outstanding_extents)--;
+		if (dio_data->outstanding_extents) {
+			(dio_data->outstanding_extents)--;
 		} else {
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
-		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
-		set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags);
+		WARN_ON(dio_data->reserve < len);
+		dio_data->reserve -= len;
+		current->journal_info = dio_data;
 	}
 
 	/*
@@ -7601,8 +7607,8 @@ unlock:
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
-	if (outstanding_extents)
-		current->journal_info = outstanding_extents;
+	if (dio_data)
+		current->journal_info = dio_data;
 	return ret;
 }
 
@@ -8329,7 +8335,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	u64 outstanding_extents = 0;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_dio_data dio_data = { 0 };
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8367,7 +8374,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
-		outstanding_extents = div64_u64(count +
+		dio_data.outstanding_extents = div64_u64(count +
 						BTRFS_MAX_EXTENT_SIZE - 1,
 						BTRFS_MAX_EXTENT_SIZE);
 
@@ -8376,7 +8383,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 		 * do the accounting properly if we go over the number we
 		 * originally calculated.  Abuse current->journal_info for this.
 		 */
-		current->journal_info = &outstanding_extents;
+		dio_data.reserve = round_up(count, root->sectorsize);
+		current->journal_info = &dio_data;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_end(inode);
@@ -8391,16 +8399,9 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
-			/*
-			 * If the error comes from submitting stage,
-			 * btrfs_get_blocsk_direct() has free'd data space,
-			 * and metadata space will be handled by
-			 * finish_ordered_fn, don't do that again to make
-			 * sure bytes_may_use is correct.
-			 */
-			if (!test_and_clear_bit(BTRFS_INODE_DIO_READY,
-				     &BTRFS_I(inode)->runtime_flags))
-				btrfs_delalloc_release_space(inode, count);
+			if (dio_data.reserve)
+				btrfs_delalloc_release_space(inode,
+							dio_data.reserve);
 		} else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode,
 						     count - (size_t)ret);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2b07b3581781..11d1eab9234d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1658,9 +1658,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		 * groups on disk until we're mounted read-write again
 		 * unless we clean them up here.
 		 */
-		mutex_lock(&root->fs_info->cleaner_mutex);
 		btrfs_delete_unused_bgs(fs_info);
-		mutex_unlock(&root->fs_info->cleaner_mutex);
 
 		btrfs_dev_replace_suspend_for_unmount(fs_info);
 		btrfs_scrub_cancel(fs_info);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8f259b3a66b3..74bc3338418b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -117,6 +117,18 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans,
 			btrfs_unpin_free_ino(root);
 		clear_btree_io_tree(&root->dirty_log_pages);
 	}
+
+	/* We can free old roots now. */
+	spin_lock(&trans->dropped_roots_lock);
+	while (!list_empty(&trans->dropped_roots)) {
+		root = list_first_entry(&trans->dropped_roots,
+					struct btrfs_root, root_list);
+		list_del_init(&root->root_list);
+		spin_unlock(&trans->dropped_roots_lock);
+		btrfs_drop_and_free_fs_root(fs_info, root);
+		spin_lock(&trans->dropped_roots_lock);
+	}
+	spin_unlock(&trans->dropped_roots_lock);
 	up_write(&fs_info->commit_root_sem);
 }
 
@@ -255,11 +267,13 @@ loop:
 	INIT_LIST_HEAD(&cur_trans->pending_ordered);
 	INIT_LIST_HEAD(&cur_trans->dirty_bgs);
 	INIT_LIST_HEAD(&cur_trans->io_bgs);
+	INIT_LIST_HEAD(&cur_trans->dropped_roots);
 	mutex_init(&cur_trans->cache_write_mutex);
 	cur_trans->num_dirty_bgs = 0;
 	spin_lock_init(&cur_trans->dirty_bgs_lock);
 	INIT_LIST_HEAD(&cur_trans->deleted_bgs);
 	spin_lock_init(&cur_trans->deleted_bgs_lock);
+	spin_lock_init(&cur_trans->dropped_roots_lock);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
 			     fs_info->btree_inode->i_mapping);
@@ -336,6 +350,24 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 }
 
 
+void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root)
+{
+	struct btrfs_transaction *cur_trans = trans->transaction;
+
+	/* Add ourselves to the transaction dropped list */
+	spin_lock(&cur_trans->dropped_roots_lock);
+	list_add_tail(&root->root_list, &cur_trans->dropped_roots);
+	spin_unlock(&cur_trans->dropped_roots_lock);
+
+	/* Make sure we don't try to update the root at commit time */
+	spin_lock(&root->fs_info->fs_roots_radix_lock);
+	radix_tree_tag_clear(&root->fs_info->fs_roots_radix,
+			     (unsigned long)root->root_key.objectid,
+			     BTRFS_ROOT_TRANS_TAG);
+	spin_unlock(&root->fs_info->fs_roots_radix_lock);
+}
+
 int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
 {
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index edc2fbc262d7..87964bf8892d 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -65,6 +65,7 @@ struct btrfs_transaction {
 	struct list_head switch_commits;
 	struct list_head dirty_bgs;
 	struct list_head io_bgs;
+	struct list_head dropped_roots;
 	u64 num_dirty_bgs;
 
 	/*
@@ -76,6 +77,7 @@ struct btrfs_transaction {
 	spinlock_t dirty_bgs_lock;
 	struct list_head deleted_bgs;
 	spinlock_t deleted_bgs_lock;
+	spinlock_t dropped_roots_lock;
 	struct btrfs_delayed_ref_root delayed_refs;
 	int aborted;
 	int dirty_bg_run;
@@ -216,5 +218,6 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info);
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
 void btrfs_put_transaction(struct btrfs_transaction *transaction);
 void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info);
-
+void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root);
 #endif
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index aa0dc2573374..afa09fce8151 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -444,6 +444,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	return 0;
 }
 
+/* Server has provided av pairs/target info in the type 2 challenge
+ * packet and we have plucked it and stored within smb session.
+ * We parse that blob here to find the server given timestamp
+ * as part of ntlmv2 authentication (or local current time as
+ * default in case of failure)
+ */
+static __le64
+find_timestamp(struct cifs_ses *ses)
+{
+	unsigned int attrsize;
+	unsigned int type;
+	unsigned int onesize = sizeof(struct ntlmssp2_name);
+	unsigned char *blobptr;
+	unsigned char *blobend;
+	struct ntlmssp2_name *attrptr;
+
+	if (!ses->auth_key.len || !ses->auth_key.response)
+		return 0;
+
+	blobptr = ses->auth_key.response;
+	blobend = blobptr + ses->auth_key.len;
+
+	while (blobptr + onesize < blobend) {
+		attrptr = (struct ntlmssp2_name *) blobptr;
+		type = le16_to_cpu(attrptr->type);
+		if (type == NTLMSSP_AV_EOL)
+			break;
+		blobptr += 2; /* advance attr type */
+		attrsize = le16_to_cpu(attrptr->length);
+		blobptr += 2; /* advance attr size */
+		if (blobptr + attrsize > blobend)
+			break;
+		if (type == NTLMSSP_AV_TIMESTAMP) {
+			if (attrsize == sizeof(u64))
+				return *((__le64 *)blobptr);
+		}
+		blobptr += attrsize; /* advance attr value */
+	}
+
+	return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+}
+
 static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 			    const struct nls_table *nls_cp)
 {
@@ -641,6 +683,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	struct ntlmv2_resp *ntlmv2;
 	char ntlmv2_hash[16];
 	unsigned char *tiblob = NULL; /* target info blob */
+	__le64 rsp_timestamp;
 
 	if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) {
 		if (!ses->domainName) {
@@ -659,6 +702,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 		}
 	}
 
+	/* Must be within 5 minutes of the server (or in range +/-2h
+	 * in case of Mac OS X), so simply carry over server timestamp
+	 * (as Windows 7 does)
+	 */
+	rsp_timestamp = find_timestamp(ses);
+
 	baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp);
 	tilen = ses->auth_key.len;
 	tiblob = ses->auth_key.response;
@@ -675,8 +724,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 			(ses->auth_key.response + CIFS_SESS_KEY_SIZE);
 	ntlmv2->blob_signature = cpu_to_le32(0x00000101);
 	ntlmv2->reserved = 0;
-	/* Must be within 5 minutes of the server */
-	ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+	ntlmv2->time = rsp_timestamp;
+
 	get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal));
 	ntlmv2->reserved2 = 0;
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index df91bcf56d67..18da19f4f811 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server)
 		break;
 	default:
 		server->echoes = true;
-		server->oplocks = true;
+		if (enable_oplocks) {
+			server->oplocks = true;
+			server->oplock_credits = 1;
+		} else
+			server->oplocks = false;
+
 		server->echo_credits = 1;
-		server->oplock_credits = 1;
 	}
 	server->credits -= server->echo_credits + server->oplock_credits;
 	return 0;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 070fb2ad85ce..ce83e2edbe0a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -46,6 +46,7 @@
 #include "smb2status.h"
 #include "smb2glob.h"
 #include "cifspdu.h"
+#include "cifs_spnego.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -486,19 +487,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "missing security blob on negprot\n");
 
 	rc = cifs_enable_signing(server, ses->sign);
-#ifdef CONFIG_SMB2_ASN1  /* BB REMOVEME when updated asn1.c ready */
 	if (rc)
 		goto neg_exit;
-	if (blob_length)
+	if (blob_length) {
 		rc = decode_negTokenInit(security_blob, blob_length, server);
-	if (rc == 1)
-		rc = 0;
-	else if (rc == 0) {
-		rc = -EIO;
-		goto neg_exit;
+		if (rc == 1)
+			rc = 0;
+		else if (rc == 0)
+			rc = -EIO;
 	}
-#endif
-
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -592,7 +589,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	__le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
 	struct TCP_Server_Info *server = ses->server;
 	u16 blob_length = 0;
-	char *security_blob;
+	struct key *spnego_key = NULL;
+	char *security_blob = NULL;
 	char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 
@@ -620,7 +618,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	ses->ntlmssp->sesskey_per_smbsess = true;
 
 	/* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */
-	ses->sectype = RawNTLMSSP;
+	if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
+		ses->sectype = RawNTLMSSP;
 
 ssetup_ntlmssp_authenticate:
 	if (phase == NtLmChallenge)
@@ -649,7 +648,48 @@ ssetup_ntlmssp_authenticate:
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field and 1 for pad */
 	iov[0].iov_len = get_rfc1002_length(req) + 4 - 1;
-	if (phase == NtLmNegotiate) {
+
+	if (ses->sectype == Kerberos) {
+#ifdef CONFIG_CIFS_UPCALL
+		struct cifs_spnego_msg *msg;
+
+		spnego_key = cifs_get_spnego_key(ses);
+		if (IS_ERR(spnego_key)) {
+			rc = PTR_ERR(spnego_key);
+			spnego_key = NULL;
+			goto ssetup_exit;
+		}
+
+		msg = spnego_key->payload.data;
+		/*
+		 * check version field to make sure that cifs.upcall is
+		 * sending us a response in an expected form
+		 */
+		if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
+			cifs_dbg(VFS,
+				  "bad cifs.upcall version. Expected %d got %d",
+				  CIFS_SPNEGO_UPCALL_VERSION, msg->version);
+			rc = -EKEYREJECTED;
+			goto ssetup_exit;
+		}
+		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
+						 GFP_KERNEL);
+		if (!ses->auth_key.response) {
+			cifs_dbg(VFS,
+				"Kerberos can't allocate (%u bytes) memory",
+				msg->sesskey_len);
+			rc = -ENOMEM;
+			goto ssetup_exit;
+		}
+		ses->auth_key.len = msg->sesskey_len;
+		blob_length = msg->secblob_len;
+		iov[1].iov_base = msg->data + msg->sesskey_len;
+		iov[1].iov_len = blob_length;
+#else
+		rc = -EOPNOTSUPP;
+		goto ssetup_exit;
+#endif /* CONFIG_CIFS_UPCALL */
+	} else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */
 		ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
 				       GFP_KERNEL);
 		if (ntlmssp_blob == NULL) {
@@ -672,6 +712,8 @@ ssetup_ntlmssp_authenticate:
 			/* with raw NTLMSSP we don't encapsulate in SPNEGO */
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
 		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
@@ -699,6 +741,8 @@ ssetup_ntlmssp_authenticate:
 		} else {
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else {
 		cifs_dbg(VFS, "illegal ntlmssp phase\n");
 		rc = -EIO;
@@ -710,8 +754,6 @@ ssetup_ntlmssp_authenticate:
 				cpu_to_le16(sizeof(struct smb2_sess_setup_req) -
 					    1 /* pad */ - 4 /* rfc1001 len */);
 	req->SecurityBufferLength = cpu_to_le16(blob_length);
-	iov[1].iov_base = security_blob;
-	iov[1].iov_len = blob_length;
 
 	inc_rfc1001_len(req, blob_length - 1 /* pad */);
 
@@ -722,6 +764,7 @@ ssetup_ntlmssp_authenticate:
 
 	kfree(security_blob);
 	rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base;
+	ses->Suid = rsp->hdr.SessionId;
 	if (resp_buftype != CIFS_NO_BUFFER &&
 	    rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) {
 		if (phase != NtLmNegotiate) {
@@ -739,7 +782,6 @@ ssetup_ntlmssp_authenticate:
 		/* NTLMSSP Negotiate sent now processing challenge (response) */
 		phase = NtLmChallenge; /* process ntlmssp challenge */
 		rc = 0; /* MORE_PROCESSING is not an error here but expected */
-		ses->Suid = rsp->hdr.SessionId;
 		rc = decode_ntlmssp_challenge(rsp->Buffer,
 				le16_to_cpu(rsp->SecurityBufferLength), ses);
 	}
@@ -796,6 +838,10 @@ keygen_exit:
 		kfree(ses->auth_key.response);
 		ses->auth_key.response = NULL;
 	}
+	if (spnego_key) {
+		key_invalidate(spnego_key);
+		key_put(spnego_key);
+	}
 	kfree(ses->ntlmssp);
 
 	return rc;
@@ -876,6 +922,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	if (tcon && tcon->bad_network_name)
 		return -ENOENT;
 
+	if ((tcon->seal) &&
+	    ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
+		cifs_dbg(VFS, "encryption requested but no server support");
+		return -EOPNOTSUPP;
+	}
+
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -955,6 +1007,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
 	init_copy_chunk_defaults(tcon);
+	if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)
+		cifs_dbg(VFS, "Encrypted shares not supported");
 	if (tcon->ses->server->ops->validate_negotiate)
 		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
diff --git a/fs/dax.c b/fs/dax.c
index 7ae6df7ea1d2..bcfb14bfc1e4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -569,8 +569,20 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
+	sector = bh.b_blocknr << (blkbits - 9);
+
 	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
 		int i;
+
+		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
+						bh.b_size);
+		if (length < 0) {
+			result = VM_FAULT_SIGBUS;
+			goto out;
+		}
+		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+			goto fallback;
+
 		for (i = 0; i < PTRS_PER_PMD; i++)
 			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
 		wmb_pmem();
@@ -623,7 +635,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		result = VM_FAULT_NOPAGE;
 		spin_unlock(ptl);
 	} else {
-		sector = bh.b_blocknr << (blkbits - 9);
 		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
 						bh.b_size);
 		if (length < 0) {
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 2714ef835bdd..be806ead7f4d 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -113,7 +113,8 @@ out:
 	return status;
 }
 
-static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_opens(struct inode *inode,
+		const nfs4_stateid *stateid, fmode_t type)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *ctx;
@@ -140,7 +141,7 @@ again:
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
 		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
-		err = nfs4_open_delegation_recall(ctx, state, stateid);
+		err = nfs4_open_delegation_recall(ctx, state, stateid, type);
 		if (!err)
 			err = nfs_delegation_claim_locks(ctx, state, stateid);
 		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -411,7 +412,8 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 	do {
 		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
 			break;
-		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
+		err = nfs_delegation_claim_opens(inode, &delegation->stateid,
+				delegation->type);
 		if (!issync || err != -EAGAIN)
 			break;
 		/*
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index a44829173e57..333063e032f0 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -54,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 
 /* NFSv4 delegation-related procedures */
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
 int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
 bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 38678d9a5cc4..4b1d08f56aba 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -166,8 +166,11 @@ nfs_direct_select_verf(struct nfs_direct_req *dreq,
 	struct nfs_writeverf *verfp = &dreq->verf;
 
 #ifdef CONFIG_NFS_V4_1
-	if (ds_clp) {
-		/* pNFS is in use, use the DS verf */
+	/*
+	 * pNFS is in use, use the DS verf except commit_through_mds is set
+	 * for layout segment where nbuckets is zero.
+	 */
+	if (ds_clp && dreq->ds_cinfo.nbuckets > 0) {
 		if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
 			verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf;
 		else
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index b34f2e228601..02ec07973bc4 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -629,23 +629,18 @@ out_put:
 	goto out;
 }
 
-static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
+static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
 {
 	int i;
 
-	for (i = 0; i < fl->num_fh; i++) {
-		if (!fl->fh_array[i])
-			break;
-		kfree(fl->fh_array[i]);
+	if (fl->fh_array) {
+		for (i = 0; i < fl->num_fh; i++) {
+			if (!fl->fh_array[i])
+				break;
+			kfree(fl->fh_array[i]);
+		}
+		kfree(fl->fh_array);
 	}
-	kfree(fl->fh_array);
-	fl->fh_array = NULL;
-}
-
-static void
-_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
-{
-	filelayout_free_fh_array(fl);
 	kfree(fl);
 }
 
@@ -716,21 +711,21 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		/* Do we want to use a mempool here? */
 		fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags);
 		if (!fl->fh_array[i])
-			goto out_err_free;
+			goto out_err;
 
 		p = xdr_inline_decode(&stream, 4);
 		if (unlikely(!p))
-			goto out_err_free;
+			goto out_err;
 		fl->fh_array[i]->size = be32_to_cpup(p++);
 		if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
 			printk(KERN_ERR "NFS: Too big fh %d received %d\n",
 			       i, fl->fh_array[i]->size);
-			goto out_err_free;
+			goto out_err;
 		}
 
 		p = xdr_inline_decode(&stream, fl->fh_array[i]->size);
 		if (unlikely(!p))
-			goto out_err_free;
+			goto out_err;
 		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
 		dprintk("DEBUG: %s: fh len %d\n", __func__,
 			fl->fh_array[i]->size);
@@ -739,8 +734,6 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	__free_page(scratch);
 	return 0;
 
-out_err_free:
-	filelayout_free_fh_array(fl);
 out_err:
 	__free_page(scratch);
 	return -EIO;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index d731bbf974aa..0f020e4d8421 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -175,10 +175,12 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
-	int err;
+	loff_t err;
 
 	do {
 		err = _nfs42_proc_llseek(filep, offset, whence);
+		if (err >= 0)
+			break;
 		if (err == -ENOTSUPP)
 			return -EOPNOTSUPP;
 		err = nfs4_handle_exception(server, err, &exception);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 693b903b48bd..f93b9cdb4934 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1127,6 +1127,21 @@ static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task)
 	return ret;
 }
 
+static bool nfs4_mode_match_open_stateid(struct nfs4_state *state,
+		fmode_t fmode)
+{
+	switch(fmode & (FMODE_READ|FMODE_WRITE)) {
+	case FMODE_READ|FMODE_WRITE:
+		return state->n_rdwr != 0;
+	case FMODE_WRITE:
+		return state->n_wronly != 0;
+	case FMODE_READ:
+		return state->n_rdonly != 0;
+	}
+	WARN_ON_ONCE(1);
+	return false;
+}
+
 static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode)
 {
 	int ret = 0;
@@ -1571,17 +1586,13 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context
 	return opendata;
 }
 
-static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res)
+static int nfs4_open_recover_helper(struct nfs4_opendata *opendata,
+		fmode_t fmode)
 {
 	struct nfs4_state *newstate;
 	int ret;
 
-	if ((opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR ||
-	     opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEG_CUR_FH) &&
-	    (opendata->o_arg.u.delegation_type & fmode) != fmode)
-		/* This mode can't have been delegated, so we must have
-		 * a valid open_stateid to cover it - not need to reclaim.
-		 */
+	if (!nfs4_mode_match_open_stateid(opendata->state, fmode))
 		return 0;
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
@@ -1597,14 +1608,14 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
 	newstate = nfs4_opendata_to_nfs4_state(opendata);
 	if (IS_ERR(newstate))
 		return PTR_ERR(newstate);
+	if (newstate != opendata->state)
+		ret = -ESTALE;
 	nfs4_close_state(newstate, fmode);
-	*res = newstate;
-	return 0;
+	return ret;
 }
 
 static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state)
 {
-	struct nfs4_state *newstate;
 	int ret;
 
 	/* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
@@ -1615,27 +1626,15 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
 	clear_bit(NFS_DELEGATED_STATE, &state->flags);
 	clear_bit(NFS_OPEN_STATE, &state->flags);
 	smp_rmb();
-	if (state->n_rdwr != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
-	if (state->n_wronly != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
-	if (state->n_rdonly != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
+	ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
+	if (ret != 0)
+		return ret;
+	ret = nfs4_open_recover_helper(opendata, FMODE_WRITE);
+	if (ret != 0)
+		return ret;
+	ret = nfs4_open_recover_helper(opendata, FMODE_READ);
+	if (ret != 0)
+		return ret;
 	/*
 	 * We may have performed cached opens for all three recoveries.
 	 * Check if we need to update the current stateid.
@@ -1759,18 +1758,32 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 	return err;
 }
 
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
+		struct nfs4_state *state, const nfs4_stateid *stateid,
+		fmode_t type)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs4_opendata *opendata;
-	int err;
+	int err = 0;
 
 	opendata = nfs4_open_recoverdata_alloc(ctx, state,
 			NFS4_OPEN_CLAIM_DELEG_CUR_FH);
 	if (IS_ERR(opendata))
 		return PTR_ERR(opendata);
 	nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
-	err = nfs4_open_recover(opendata, state);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+	switch (type & (FMODE_READ|FMODE_WRITE)) {
+	case FMODE_READ|FMODE_WRITE:
+	case FMODE_WRITE:
+		err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
+		if (err)
+			break;
+		err = nfs4_open_recover_helper(opendata, FMODE_WRITE);
+		if (err)
+			break;
+	case FMODE_READ:
+		err = nfs4_open_recover_helper(opendata, FMODE_READ);
+	}
 	nfs4_opendata_put(opendata);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, err);
 }
@@ -2645,6 +2658,15 @@ out:
 	return err;
 }
 
+static bool
+nfs4_wait_on_layoutreturn(struct inode *inode, struct rpc_task *task)
+{
+	if (inode == NULL || !nfs_have_layout(inode))
+		return false;
+
+	return pnfs_wait_on_layoutreturn(inode, task);
+}
+
 struct nfs4_closedata {
 	struct inode *inode;
 	struct nfs4_state *state;
@@ -2763,6 +2785,11 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_no_action;
 	}
 
+	if (nfs4_wait_on_layoutreturn(inode, task)) {
+		nfs_release_seqid(calldata->arg.seqid);
+		goto out_wait;
+	}
+
 	if (calldata->arg.fmode == 0)
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
 	if (calldata->roc)
@@ -5308,6 +5335,9 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 
 	d_data = (struct nfs4_delegreturndata *)data;
 
+	if (nfs4_wait_on_layoutreturn(d_data->inode, task))
+		return;
+
 	if (d_data->roc)
 		pnfs_roc_get_barrier(d_data->inode, &d_data->roc_barrier);
 
@@ -7800,39 +7830,46 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 			dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
 				__func__, delay);
 			rpc_delay(task, delay);
-			task->tk_status = 0;
-			rpc_restart_call_prepare(task);
-			goto out; /* Do not call nfs4_async_handle_error() */
+			/* Do not call nfs4_async_handle_error() */
+			goto out_restart;
 		}
 		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)) {
+		if (nfs4_stateid_match(&lgp->args.stateid,
+					&lgp->args.ctx->state->stateid)) {
 			spin_unlock(&inode->i_lock);
 			/* If the open stateid was bad, then recover it. */
 			state = lgp->args.ctx->state;
-		} else {
+			break;
+		}
+		lo = NFS_I(inode)->layout;
+		if (lo && nfs4_stateid_match(&lgp->args.stateid,
+					&lo->plh_stateid)) {
 			LIST_HEAD(head);
 
 			/*
 			 * Mark the bad layout state as invalid, then retry
 			 * with the current stateid.
 			 */
+			set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
 			pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
 			spin_unlock(&inode->i_lock);
 			pnfs_free_lseg_list(&head);
-	
-			task->tk_status = 0;
-			rpc_restart_call_prepare(task);
-		}
+		} else
+			spin_unlock(&inode->i_lock);
+		goto out_restart;
 	}
 	if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
-		rpc_restart_call_prepare(task);
+		goto out_restart;
 out:
 	dprintk("<-- %s\n", __func__);
 	return;
+out_restart:
+	task->tk_status = 0;
+	rpc_restart_call_prepare(task);
+	return;
 out_overflow:
 	task->tk_status = -EOVERFLOW;
 	goto out;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index da73bc443238..5db324635e92 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1481,7 +1481,7 @@ restart:
 					spin_unlock(&state->state_lock);
 				}
 				nfs4_put_open_state(state);
-				clear_bit(NFS4CLNT_RECLAIM_NOGRACE,
+				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
 					&state->flags);
 				spin_lock(&sp->so_lock);
 				goto restart;
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 7c5718ba625e..fe3ddd20ff89 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -508,7 +508,7 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 	 * for it without upsetting the slab allocator.
 	 */
 	if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
-			sizeof(struct page) > PAGE_SIZE)
+			sizeof(struct page *) > PAGE_SIZE)
 		return 0;
 
 	return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index ba1246433794..8abe27165ad0 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1104,20 +1104,15 @@ bool pnfs_roc(struct inode *ino)
 			mark_lseg_invalid(lseg, &tmp_list);
 			found = true;
 		}
-	/* pnfs_prepare_layoutreturn() grabs lo ref and it will be put
-	 * in pnfs_roc_release(). We don't really send a layoutreturn but
-	 * still want others to view us like we are sending one!
-	 *
-	 * If pnfs_prepare_layoutreturn() fails, it means someone else is doing
-	 * LAYOUTRETURN, so we proceed like there are no layouts to return.
-	 *
-	 * ROC in three conditions:
+	/* ROC in two conditions:
 	 * 1. there are ROC lsegs
 	 * 2. we don't send layoutreturn
-	 * 3. no others are sending layoutreturn
 	 */
-	if (found && !layoutreturn && pnfs_prepare_layoutreturn(lo))
+	if (found && !layoutreturn) {
+		/* lo ref dropped in pnfs_roc_release() */
+		pnfs_get_layout_hdr(lo);
 		roc = true;
+	}
 
 out_noroc:
 	spin_unlock(&ino->i_lock);
@@ -1172,6 +1167,26 @@ void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier)
 	spin_unlock(&ino->i_lock);
 }
 
+bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
+{
+	struct nfs_inode *nfsi = NFS_I(ino);
+        struct pnfs_layout_hdr *lo;
+        bool sleep = false;
+
+	/* we might not have grabbed lo reference. so need to check under
+	 * i_lock */
+        spin_lock(&ino->i_lock);
+        lo = nfsi->layout;
+        if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+                sleep = true;
+        spin_unlock(&ino->i_lock);
+
+        if (sleep)
+                rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+
+        return sleep;
+}
+
 /*
  * Compare two layout segments for sorting into layout cache.
  * We want to preferentially return RW over RO layouts, so ensure those
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 78c9351ff117..d1990e90e7a0 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -270,6 +270,7 @@ bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier);
+bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task);
 void pnfs_set_layoutcommit(struct inode *, struct pnfs_layout_segment *, loff_t);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
@@ -639,6 +640,12 @@ pnfs_roc_get_barrier(struct inode *ino, u32 *barrier)
 {
 }
 
+static inline bool
+pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
+{
+	return false;
+}
+
 static inline void set_pnfs_layoutdriver(struct nfs_server *s,
 					 const struct nfs_fh *mntfh, u32 id)
 {
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index ae0ff7a11b40..01b8cc8e8cfc 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -72,6 +72,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
 
+	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
+		pgio->pg_ops->pg_cleanup(pgio);
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
 
 	/* read path should never have more than one mirror */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 388f48079c43..72624dc4a623 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1351,6 +1351,9 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
 
+	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
+		pgio->pg_ops->pg_cleanup(pgio);
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
 
 	nfs_pageio_stop_mirroring(pgio);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 46b8b2bbc95a..ee5aa4daaea0 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int found, ret;
 	int set_maybe;
 	int dispatch_assert = 0;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm))
 		return DLM_MASTER_RESP_NO;
@@ -1658,15 +1659,18 @@ send_response:
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
-		} else
+		} else {
+			dispatched = 1;
 			__dlm_lockres_grab_inflight_worker(dlm, res);
+		}
 		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
 	}
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return response;
 }
 
@@ -2090,7 +2094,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
 
 
 	/* queue up work for dlm_assert_master_worker */
-	dlm_grab(dlm);  /* get an extra ref for the work item */
 	dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL);
 	item->u.am.lockres = res; /* already have a ref */
 	/* can optionally ignore node numbers higher than this node */
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index ce12e0b1a31f..3d90ad7ff91f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	unsigned int hash;
 	int master = DLM_LOCK_RES_OWNER_UNKNOWN;
 	u32 flags = DLM_ASSERT_MASTER_REQUERY;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm)) {
 		/* since the domain has gone away on this
@@ -1719,8 +1720,10 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				dlm_put(dlm);
 				/* sender will take care of this and retry */
 				return ret;
-			} else
+			} else {
+				dispatched = 1;
 				__dlm_lockres_grab_inflight_worker(dlm, res);
+			}
 			spin_unlock(&res->spinlock);
 		} else {
 			/* put.. incase we are not the master */
@@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 	spin_unlock(&dlm->spinlock);
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return master;
 }
 
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 96f3448b6eb4..fd65b3f1923c 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -652,11 +652,8 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode,
 {
 	int err;
 
-	mutex_lock(&inode->i_mutex);
 	err = security_inode_init_security(inode, dentry, qstr,
 					   &init_xattrs, 0);
-	mutex_unlock(&inode->i_mutex);
-
 	if (err) {
 		struct ubifs_info *c = dentry->i_sb->s_fs_info;
 		ubifs_err(c, "cannot initialize security for inode %lu, error %d",
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f9aeb40a7197..50311703135b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -467,8 +467,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * the fault_*wqh.
 	 */
 	spin_lock(&ctx->fault_pending_wqh.lock);
-	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0, &range);
-	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, &range);
+	__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
+	__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	wake_up_poll(&ctx->fd_wqh, POLLHUP);
@@ -650,10 +650,10 @@ static void __wake_userfault(struct userfaultfd_ctx *ctx,
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/* wake all in the range and autoremove */
 	if (waitqueue_active(&ctx->fault_pending_wqh))
-		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, 0,
+		__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
 				     range);
 	if (waitqueue_active(&ctx->fault_wqh))
-		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, 0, range);
+		__wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, range);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 }