Merge branch 'linux-3.4.57' into rel-17

Bug 1348440

Change-Id: If25c49f027dc2a69642f7ed4733e965962b2a5a2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>

77 files changed, 714 insertions, 397 deletions

diff --git a/fs/aio.c b/fs/aio.c
index e7f2fad7b4ce..cdc8dc493ed9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1094,9 +1094,9 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
 	spin_unlock(&info->ring_lock);
 
 out:
-	kunmap_atomic(ring);
 	dprintk("leaving aio_read_evt: %d  h%lu t%lu\n", ret,
 		 (unsigned long)ring->head, (unsigned long)ring->tail);
+	kunmap_atomic(ring);
 	return ret;
 }
 
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1feb68ecef95..b1cdb0ae5ca6 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -61,15 +61,6 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 		/* This is an autofs submount, we can't expire it */
 		if (autofs_type_indirect(sbi->type))
 			goto done;
-
-		/*
-		 * Otherwise it's an offset mount and we need to check
-		 * if we can umount its mount, if there is one.
-		 */
-		if (!d_mountpoint(path.dentry)) {
-			status = 0;
-			goto done;
-		}
 	}
 
 	/* Update the expiry counter if fs is busy */
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 2790c7e1912e..575796ae3d84 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -42,7 +42,6 @@ static int load_em86(struct linux_binprm *bprm,struct pt_regs *regs)
 			return -ENOEXEC;
 	}
 
-	bprm->recursion_depth++; /* Well, the bang-shell is implicit... */
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index e1724392d050..87fa90d5863b 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -117,10 +117,6 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (!enabled)
 		goto _ret;
 
-	retval = -ENOEXEC;
-	if (bprm->recursion_depth > BINPRM_MAX_RECURSION)
-		goto _ret;
-
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
 	fmt = check_file(bprm);
@@ -200,8 +196,6 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (retval < 0)
 		goto _error;
 
-	bprm->recursion_depth++;
-
 	retval = search_binary_handler (bprm, regs);
 	if (retval < 0)
 		goto _error;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index df49d486b0c0..8ae4be199fb4 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -22,15 +22,13 @@ static int load_script(struct linux_binprm *bprm,struct pt_regs *regs)
 	char interp[BINPRM_BUF_SIZE];
 	int retval;
 
-	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!') ||
-	    (bprm->recursion_depth > BINPRM_MAX_RECURSION))
+	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
 		return -ENOEXEC;
 	/*
 	 * This section does the #! interpretation.
 	 * Sorta complicated, but hopefully it will work.  -TYT
 	 */
 
-	bprm->recursion_depth++;
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b3be92c980ee..319d9c74c4d3 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -57,17 +57,24 @@ static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
 	struct backing_dev_info *old = inode->i_data.backing_dev_info;
+	bool wakeup_bdi = false;
 
 	if (unlikely(dst == old))		/* deadlock avoidance */
 		return;
 	bdi_lock_two(&old->wb, &dst->wb);
 	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
-	if (inode->i_state & I_DIRTY)
+	if (inode->i_state & I_DIRTY) {
+		if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
+			wakeup_bdi = true;
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	}
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&old->wb.list_lock);
 	spin_unlock(&dst->wb.list_lock);
+
+	if (wakeup_bdi)
+		bdi_wakeup_thread_delayed(dst);
 }
 
 sector_t blkdev_max_block(struct block_device *bdev)
@@ -604,6 +611,7 @@ struct block_device *bdgrab(struct block_device *bdev)
 	ihold(bdev->bd_inode);
 	return bdev;
 }
+EXPORT_SYMBOL(bdgrab);
 
 long nr_blockdev_pages(void)
 {
@@ -1086,7 +1094,9 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 {
 	unsigned bsize = bdev_logical_block_size(bdev);
 
-	bdev->bd_inode->i_size = size;
+	mutex_lock(&bdev->bd_inode->i_mutex);
+	i_size_write(bdev->bd_inode, size);
+	mutex_unlock(&bdev->bd_inode->i_mutex);
 	while (bsize < PAGE_CACHE_SIZE) {
 		if (size & bsize)
 			break;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 49fd7b66d57b..c4f0a9936f88 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4217,7 +4217,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	spin_lock(&sinfo->lock);
 	spin_lock(&block_rsv->lock);
 
-	block_rsv->size = num_bytes;
+	block_rsv->size = min_t(u64, num_bytes, 512 * 1024 * 1024);
 
 	num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
 		    sinfo->bytes_reserved + sinfo->bytes_readonly +
@@ -4486,14 +4486,49 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		 * If the inodes csum_bytes is the same as the original
 		 * csum_bytes then we know we haven't raced with any free()ers
 		 * so we can just reduce our inodes csum bytes and carry on.
-		 * Otherwise we have to do the normal free thing to account for
-		 * the case that the free side didn't free up its reserve
-		 * because of this outstanding reservation.
 		 */
-		if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+		if (BTRFS_I(inode)->csum_bytes == csum_bytes) {
 			calc_csum_metadata_size(inode, num_bytes, 0);
-		else
-			to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+		} else {
+			u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes;
+			u64 bytes;
+
+			/*
+			 * This is tricky, but first we need to figure out how much we
+			 * free'd from any free-ers that occured during this
+			 * reservation, so we reset ->csum_bytes to the csum_bytes
+			 * before we dropped our lock, and then call the free for the
+			 * number of bytes that were freed while we were trying our
+			 * reservation.
+			 */
+			bytes = csum_bytes - BTRFS_I(inode)->csum_bytes;
+			BTRFS_I(inode)->csum_bytes = csum_bytes;
+			to_free = calc_csum_metadata_size(inode, bytes, 0);
+
+
+			/*
+			 * Now we need to see how much we would have freed had we not
+			 * been making this reservation and our ->csum_bytes were not
+			 * artificially inflated.
+			 */
+			BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes;
+			bytes = csum_bytes - orig_csum_bytes;
+			bytes = calc_csum_metadata_size(inode, bytes, 0);
+
+			/*
+			 * Now reset ->csum_bytes to what it should be.  If bytes is
+			 * more than to_free then we would have free'd more space had we
+			 * not had an artificially high ->csum_bytes, so we need to free
+			 * the remainder.  If bytes is the same or less then we don't
+			 * need to do anything, the other free-ers did the correct
+			 * thing.
+			 */
+			BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes;
+			if (bytes > to_free)
+				to_free = bytes - to_free;
+			else
+				to_free = 0;
+		}
 		spin_unlock(&BTRFS_I(inode)->lock);
 		if (dropped)
 			to_free += btrfs_calc_trans_metadata_size(root, dropped);
@@ -6811,6 +6846,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	int err = 0;
 	int ret;
 	int level;
+	bool root_dropped = false;
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -6868,6 +6904,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		while (1) {
 			btrfs_tree_lock(path->nodes[level]);
 			btrfs_set_lock_blocking(path->nodes[level]);
+			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 
 			ret = btrfs_lookup_extent_info(trans, root,
 						path->nodes[level]->start,
@@ -6884,6 +6921,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 				break;
 
 			btrfs_tree_unlock(path->nodes[level]);
+			path->locks[level] = 0;
 			WARN_ON(wc->refs[level] != 1);
 			level--;
 		}
@@ -6979,12 +7017,22 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		free_extent_buffer(root->commit_root);
 		kfree(root);
 	}
+	root_dropped = true;
 out_end_trans:
 	btrfs_end_transaction_throttle(trans, tree_root);
 out_free:
 	kfree(wc);
 	btrfs_free_path(path);
 out:
+	/*
+	 * So if we need to stop dropping the snapshot for whatever reason we
+	 * need to make sure to add it back to the dead root list so that we
+	 * keep trying to do the work later.  This also cleans up roots if we
+	 * don't have it in the radix (like when we recover after a power fail
+	 * or unmount) so we don't leak memory.
+	 */
+	if (root_dropped == false)
+		btrfs_add_dead_root(root);
 	if (err)
 		btrfs_std_error(root->fs_info, err);
 	return err;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c9018a05036e..d64fda541483 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1238,6 +1238,39 @@ int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 				GFP_NOFS);
 }
 
+int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+	unsigned long index = start >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		BUG_ON(!page); /* Pages should be in the extent_io_tree */
+		clear_page_dirty_for_io(page);
+		page_cache_release(page);
+		index++;
+	}
+	return 0;
+}
+
+int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+	unsigned long index = start >> PAGE_CACHE_SHIFT;
+	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		BUG_ON(!page); /* Pages should be in the extent_io_tree */
+		account_page_redirty(page);
+		__set_page_dirty_nobuffers(page);
+		page_cache_release(page);
+		index++;
+	}
+	return 0;
+}
+
 /*
  * helper function to set both pages and extents in the tree writeback
  */
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index b516c3b8dec6..2edf9120aae5 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -312,6 +312,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
 		      unsigned long *map_len);
 int extent_range_uptodate(struct extent_io_tree *tree,
 			  u64 start, u64 end);
+int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
+int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
 int extent_clear_unlock_delalloc(struct inode *inode,
 				struct extent_io_tree *tree,
 				u64 start, u64 end, struct page *locked_page,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0df0d1fd4fee..9e51325828bc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -349,6 +349,7 @@ static noinline int compress_file_range(struct inode *inode,
 	int i;
 	int will_compress;
 	int compress_type = root->fs_info->compress_type;
+	int redirty = 0;
 
 	/* if this is a small write inside eof, kick off a defrag */
 	if ((end - start + 1) < 16 * 1024 &&
@@ -411,6 +412,17 @@ again:
 		if (BTRFS_I(inode)->force_compress)
 			compress_type = BTRFS_I(inode)->force_compress;
 
+		/*
+		 * we need to call clear_page_dirty_for_io on each
+		 * page in the range.  Otherwise applications with the file
+		 * mmap'd can wander in and change the page contents while
+		 * we are compressing them.
+		 *
+		 * If the compression fails for any reason, we set the pages
+		 * dirty again later on.
+		 */
+		extent_range_clear_dirty_for_io(inode, start, end);
+		redirty = 1;
 		ret = btrfs_compress_pages(compress_type,
 					   inode->i_mapping, start,
 					   total_compressed, pages,
@@ -552,6 +564,8 @@ cleanup_and_bail_uncompressed:
 			__set_page_dirty_nobuffers(locked_page);
 			/* unlocked later on in the async handlers */
 		}
+		if (redirty)
+			extent_range_redirty_for_io(inode, start, end);
 		add_async_extent(async_cow, start, end - start + 1,
 				 0, NULL, 0, BTRFS_COMPRESS_NONE);
 		*num_added += 1;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 14f8e1faa46e..3a65f4343416 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1653,7 +1653,11 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 		item_off = btrfs_item_ptr_offset(leaf, i);
 		item_len = btrfs_item_size_nr(leaf, i);
 
-		if (item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
+		btrfs_item_key_to_cpu(leaf, key, i);
+		if (!key_in_sk(key, sk))
+			continue;
+
+		if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
 			item_len = 0;
 
 		if (sizeof(sh) + item_len + *sk_offset >
@@ -1662,10 +1666,6 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 			goto overflow;
 		}
 
-		btrfs_item_key_to_cpu(leaf, key, i);
-		if (!key_in_sk(key, sk))
-			continue;
-
 		sh.objectid = key->objectid;
 		sh.offset = key->offset;
 		sh.type = key->type;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2f3d6f917fb3..682e5da3143a 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -383,7 +383,6 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 	eb = path->nodes[0];
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
-	btrfs_release_path(path);
 
 	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
@@ -398,7 +397,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 				ret < 0 ? -1 : ref_level,
 				ret < 0 ? -1 : ref_root);
 		} while (ret != 1);
+		btrfs_release_path(path);
 	} else {
+		btrfs_release_path(path);
 		swarn.path = path;
 		iterate_extent_inodes(fs_info, found_key.objectid,
 					extent_item_pos, 1,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index dce89da9c863..3ef7f386e265 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -315,6 +315,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 	unsigned long src_ptr;
 	unsigned long dst_ptr;
 	int overwrite_root = 0;
+	bool inode_item = key->type == BTRFS_INODE_ITEM_KEY;
 
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 		overwrite_root = 1;
@@ -324,6 +325,9 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 
 	/* look for the key in the destination tree */
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+
 	if (ret == 0) {
 		char *src_copy;
 		char *dst_copy;
@@ -365,6 +369,30 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
 			return 0;
 		}
 
+		/*
+		 * We need to load the old nbytes into the inode so when we
+		 * replay the extents we've logged we get the right nbytes.
+		 */
+		if (inode_item) {
+			struct btrfs_inode_item *item;
+			u64 nbytes;
+
+			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+					      struct btrfs_inode_item);
+			nbytes = btrfs_inode_nbytes(path->nodes[0], item);
+			item = btrfs_item_ptr(eb, slot,
+					      struct btrfs_inode_item);
+			btrfs_set_inode_nbytes(eb, item, nbytes);
+		}
+	} else if (inode_item) {
+		struct btrfs_inode_item *item;
+
+		/*
+		 * New inode, set nbytes to 0 so that the nbytes comes out
+		 * properly when we replay the extents.
+		 */
+		item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
+		btrfs_set_inode_nbytes(eb, item, 0);
 	}
 insert:
 	btrfs_release_path(path);
@@ -486,7 +514,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	u64 extent_end;
 	u64 alloc_hint;
 	u64 start = key->offset;
-	u64 saved_nbytes;
+	u64 nbytes = 0;
 	struct btrfs_file_extent_item *item;
 	struct inode *inode = NULL;
 	unsigned long size;
@@ -496,10 +524,19 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	found_type = btrfs_file_extent_type(eb, item);
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
-	    found_type == BTRFS_FILE_EXTENT_PREALLOC)
-		extent_end = start + btrfs_file_extent_num_bytes(eb, item);
-	else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
+	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+		nbytes = btrfs_file_extent_num_bytes(eb, item);
+		extent_end = start + nbytes;
+
+		/*
+		 * We don't add to the inodes nbytes if we are prealloc or a
+		 * hole.
+		 */
+		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
+			nbytes = 0;
+	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size = btrfs_file_extent_inline_len(eb, item);
+		nbytes = btrfs_file_extent_ram_bytes(eb, item);
 		extent_end = (start + size + mask) & ~mask;
 	} else {
 		ret = 0;
@@ -548,7 +585,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	saved_nbytes = inode_get_bytes(inode);
 	/* drop any overlapping extents */
 	ret = btrfs_drop_extents(trans, inode, start, extent_end,
 				 &alloc_hint, 1);
@@ -636,7 +672,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		BUG_ON(ret);
 	}
 
-	inode_set_bytes(inode, saved_nbytes);
+	inode_add_bytes(inode, nbytes);
 	btrfs_update_inode(trans, root, inode);
 out:
 	if (inode)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1411b99555a4..06744f1e91f4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -557,6 +557,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		new_device->writeable = 0;
 		new_device->in_fs_metadata = 0;
 		new_device->can_discard = 0;
+		spin_lock_init(&new_device->io_lock);
 		list_replace_rcu(&device->dev_list, &new_device->dev_list);
 
 		call_rcu(&device->rcu, free_device);
@@ -590,6 +591,12 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 		__btrfs_close_devices(fs_devices);
 		free_fs_devices(fs_devices);
 	}
+	/*
+	 * Wait for rcu kworkers under __btrfs_close_devices
+	 * to finish all blkdev_puts so device is really
+	 * free when umount is done.
+	 */
+	rcu_barrier();
 	return ret;
 }
 
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 80576d05d687..bb5fb3d46e8f 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -191,27 +191,23 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 }
 
 /**
- * Encode the flock and fcntl locks for the given inode into the pagelist.
- * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
- * sequential flock locks.
- * Must be called with lock_flocks() already held.
- * If we encounter more of a specific lock type than expected,
- * we return the value 1.
+ * Encode the flock and fcntl locks for the given inode into the ceph_filelock
+ * array. Must be called with lock_flocks() already held.
+ * If we encounter more of a specific lock type than expected, return -ENOSPC.
  */
-int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
-		      int num_fcntl_locks, int num_flock_locks)
+int ceph_encode_locks_to_buffer(struct inode *inode,
+				struct ceph_filelock *flocks,
+				int num_fcntl_locks, int num_flock_locks)
 {
 	struct file_lock *lock;
-	struct ceph_filelock cephlock;
 	int err = 0;
 	int seen_fcntl = 0;
 	int seen_flock = 0;
+	int l = 0;
 
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
-	err = ceph_pagelist_append(pagelist, &num_fcntl_locks, sizeof(u32));
-	if (err)
-		goto fail;
+
 	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
 		if (lock->fl_flags & FL_POSIX) {
 			++seen_fcntl;
@@ -219,19 +215,12 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 				err = -ENOSPC;
 				goto fail;
 			}
-			err = lock_to_ceph_filelock(lock, &cephlock);
+			err = lock_to_ceph_filelock(lock, &flocks[l]);
 			if (err)
 				goto fail;
-			err = ceph_pagelist_append(pagelist, &cephlock,
-					   sizeof(struct ceph_filelock));
+			++l;
 		}
-		if (err)
-			goto fail;
 	}
-
-	err = ceph_pagelist_append(pagelist, &num_flock_locks, sizeof(u32));
-	if (err)
-		goto fail;
 	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
 		if (lock->fl_flags & FL_FLOCK) {
 			++seen_flock;
@@ -239,19 +228,51 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
 				err = -ENOSPC;
 				goto fail;
 			}
-			err = lock_to_ceph_filelock(lock, &cephlock);
+			err = lock_to_ceph_filelock(lock, &flocks[l]);
 			if (err)
 				goto fail;
-			err = ceph_pagelist_append(pagelist, &cephlock,
-					   sizeof(struct ceph_filelock));
+			++l;
 		}
-		if (err)
-			goto fail;
 	}
 fail:
 	return err;
 }
 
+/**
+ * Copy the encoded flock and fcntl locks into the pagelist.
+ * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
+ * sequential flock locks.
+ * Returns zero on success.
+ */
+int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+			   struct ceph_pagelist *pagelist,
+			   int num_fcntl_locks, int num_flock_locks)
+{
+	int err = 0;
+	__le32 nlocks;
+
+	nlocks = cpu_to_le32(num_fcntl_locks);
+	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+	if (err)
+		goto out_fail;
+
+	err = ceph_pagelist_append(pagelist, flocks,
+				   num_fcntl_locks * sizeof(*flocks));
+	if (err)
+		goto out_fail;
+
+	nlocks = cpu_to_le32(num_flock_locks);
+	err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+	if (err)
+		goto out_fail;
+
+	err = ceph_pagelist_append(pagelist,
+				   &flocks[num_fcntl_locks],
+				   num_flock_locks * sizeof(*flocks));
+out_fail:
+	return err;
+}
+
 /*
  * Given a pointer to a lock, convert it to a ceph filelock
  */
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 3fd08ad5c478..cf1b9e043b08 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -335,9 +335,9 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
 	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
 	if (atomic_dec_and_test(&s->s_ref)) {
 		if (s->s_auth.authorizer)
-		     s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
-			     s->s_mdsc->fsc->client->monc.auth,
-			     s->s_auth.authorizer);
+			ceph_auth_destroy_authorizer(
+				s->s_mdsc->fsc->client->monc.auth,
+				s->s_auth.authorizer);
 		kfree(s);
 	}
 }
@@ -2455,39 +2455,44 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 
 	if (recon_state->flock) {
 		int num_fcntl_locks, num_flock_locks;
-		struct ceph_pagelist_cursor trunc_point;
-
-		ceph_pagelist_set_cursor(pagelist, &trunc_point);
-		do {
-			lock_flocks();
-			ceph_count_locks(inode, &num_fcntl_locks,
-					 &num_flock_locks);
-			rec.v2.flock_len = (2*sizeof(u32) +
-					    (num_fcntl_locks+num_flock_locks) *
-					    sizeof(struct ceph_filelock));
-			unlock_flocks();
-
-			/* pre-alloc pagelist */
-			ceph_pagelist_truncate(pagelist, &trunc_point);
-			err = ceph_pagelist_append(pagelist, &rec, reclen);
-			if (!err)
-				err = ceph_pagelist_reserve(pagelist,
-							    rec.v2.flock_len);
-
-			/* encode locks */
-			if (!err) {
-				lock_flocks();
-				err = ceph_encode_locks(inode,
-							pagelist,
-							num_fcntl_locks,
-							num_flock_locks);
-				unlock_flocks();
-			}
-		} while (err == -ENOSPC);
+		struct ceph_filelock *flocks;
+
+encode_again:
+		lock_flocks();
+		ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
+		unlock_flocks();
+		flocks = kmalloc((num_fcntl_locks+num_flock_locks) *
+				 sizeof(struct ceph_filelock), GFP_NOFS);
+		if (!flocks) {
+			err = -ENOMEM;
+			goto out_free;
+		}
+		lock_flocks();
+		err = ceph_encode_locks_to_buffer(inode, flocks,
+						  num_fcntl_locks,
+						  num_flock_locks);
+		unlock_flocks();
+		if (err) {
+			kfree(flocks);
+			if (err == -ENOSPC)
+				goto encode_again;
+			goto out_free;
+		}
+		/*
+		 * number of encoded locks is stable, so copy to pagelist
+		 */
+		rec.v2.flock_len = cpu_to_le32(2*sizeof(u32) +
+				    (num_fcntl_locks+num_flock_locks) *
+				    sizeof(struct ceph_filelock));
+		err = ceph_pagelist_append(pagelist, &rec, reclen);
+		if (!err)
+			err = ceph_locks_to_pagelist(flocks, pagelist,
+						     num_fcntl_locks,
+						     num_flock_locks);
+		kfree(flocks);
 	} else {
 		err = ceph_pagelist_append(pagelist, &rec, reclen);
 	}
-
 out_free:
 	kfree(path);
 out_dput:
@@ -3414,13 +3419,17 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
 	struct ceph_auth_handshake *auth = &s->s_auth;
 
 	if (force_new && auth->authorizer) {
-		if (ac->ops && ac->ops->destroy_authorizer)
-			ac->ops->destroy_authorizer(ac, auth->authorizer);
+		ceph_auth_destroy_authorizer(ac, auth->authorizer);
 		auth->authorizer = NULL;
 	}
-	if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) {
-		int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
-							auth);
+	if (!auth->authorizer) {
+		int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
+						      auth);
+		if (ret)
+			return ERR_PTR(ret);
+	} else {
+		int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_MDS,
+						      auth);
 		if (ret)
 			return ERR_PTR(ret);
 	}
@@ -3436,7 +3445,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
-	return ac->ops->verify_authorizer_reply(ac, s->s_auth.authorizer, len);
+	return ceph_auth_verify_authorizer_reply(ac, s->s_auth.authorizer, len);
 }
 
 static int invalidate_authorizer(struct ceph_connection *con)
@@ -3445,8 +3454,7 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	struct ceph_mds_client *mdsc = s->s_mdsc;
 	struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
-	if (ac->ops->invalidate_authorizer)
-		ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
+	ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
 
 	return ceph_monc_validate_auth(&mdsc->fsc->client->monc);
 }
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index f36391815461..f4fa5cf0cdf1 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -70,8 +70,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	/*
 	 * express utilization in terms of large blocks to avoid
 	 * overflow on 32-bit machines.
+	 *
+	 * NOTE: for the time being, we make bsize == frsize to humor
+	 * not-yet-ancient versions of glibc that are broken.
+	 * Someday, we will probably want to report a real block
+	 * size...  whatever that may mean for a network file system!
 	 */
 	buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
+	buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
 	buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
 	buf->f_bfree = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
 	buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
@@ -79,7 +85,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = le64_to_cpu(st.num_objects);
 	buf->f_ffree = -1;
 	buf->f_namelen = NAME_MAX;
-	buf->f_frsize = PAGE_CACHE_SIZE;
 
 	/* leave fsid little-endian, regardless of host endianness */
 	fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fc35036d258d..d2e01a61f9d2 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -21,7 +21,7 @@
 
 /* large granularity for statfs utilization stats to facilitate
  * large volume sizes on 32-bit machines. */
-#define CEPH_BLOCK_SHIFT   20  /* 1 MB */
+#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
 #define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
@@ -847,8 +847,13 @@ extern const struct export_operations ceph_export_ops;
 extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
 extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
 extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
-extern int ceph_encode_locks(struct inode *i, struct ceph_pagelist *p,
-			     int p_locks, int f_locks);
+extern int ceph_encode_locks_to_buffer(struct inode *inode,
+				       struct ceph_filelock *flocks,
+				       int num_fcntl_locks,
+				       int num_flock_locks);
+extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+				  struct ceph_pagelist *pagelist,
+				  int num_fcntl_locks, int num_flock_locks);
 extern int lock_to_ceph_filelock(struct file_lock *fl, struct ceph_filelock *c);
 
 /* debugfs.c */
diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index cfd1ce34e0bc..1d36db114772 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -614,53 +614,10 @@ decode_negTokenInit(unsigned char *security_blob, int length,
 		}
 	}
 
-	/* mechlistMIC */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		/* Check if we have reached the end of the blob, but with
-		   no mechListMic (e.g. NTLMSSP instead of KRB5) */
-		if (ctx.error == ASN1_ERR_DEC_EMPTY)
-			goto decode_negtoken_exit;
-		cFYI(1, "Error decoding last part negTokenInit exit3");
-		return 0;
-	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		/* tag = 3 indicating mechListMIC */
-		cFYI(1, "Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-
-	/* sequence */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit5");
-		return 0;
-	} else if ((cls != ASN1_UNI) || (con != ASN1_CON)
-		   || (tag != ASN1_SEQ)) {
-		cFYI(1, "cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-	}
-
-	/* sequence of */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit 7");
-		return 0;
-	} else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
-		cFYI(1, "Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-
-	/* general string */
-	if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
-		cFYI(1, "Error decoding last part negTokenInit exit9");
-		return 0;
-	} else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
-		   || (tag != ASN1_GENSTR)) {
-		cFYI(1, "Exit10 cls = %d con = %d tag = %d end = %p (%d)",
-			cls, con, tag, end, *end);
-		return 0;
-	}
-	cFYI(1, "Need to call asn1_octets_decode() function for %s",
-		ctx.pointer);	/* is this UTF-8 or ASCII? */
-decode_negtoken_exit:
+	/*
+	 * We currently ignore anything at the end of the SPNEGO blob after
+	 * the mechTypes have been parsed, since none of that info is
+	 * used at the moment.
+	 */
 	return 1;
 }
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 22631445a4ac..d0e5fc57bfa8 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/vfs.h>
 #include <linux/fs.h>
+#include <linux/inet.h>
 #include "cifsglob.h"
 #include "cifsproto.h"
 #include "cifsfs.h"
@@ -150,7 +151,8 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 	 * assuming that we have 'unc=' and 'ip=' in
 	 * the original sb_mountdata
 	 */
-	md_len = strlen(sb_mountdata) + rc + strlen(ref->node_name) + 12;
+	md_len = strlen(sb_mountdata) + rc + strlen(ref->node_name) + 12 +
+			INET6_ADDRSTRLEN;
 	mountdata = kzalloc(md_len+1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		rc = -ENOMEM;
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index a513a546700b..f2b2ffd452c8 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -323,14 +323,14 @@ UniToupper(register wchar_t uc)
 /*
  * UniStrupr:  Upper case a unicode string
  */
-static inline wchar_t *
-UniStrupr(register wchar_t *upin)
+static inline __le16 *
+UniStrupr(register __le16 *upin)
 {
-	register wchar_t *up;
+	register __le16 *up;
 
 	up = upin;
 	while (*up) {		/* For all characters */
-		*up = UniToupper(*up);
+		*up = cpu_to_le16(UniToupper(le16_to_cpu(*up)));
 		up++;
 	}
 	return upin;		/* Return input pointer */
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 63c460e503b6..6d0c62a529a0 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -394,7 +394,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 	int rc = 0;
 	int len;
 	char nt_hash[CIFS_NTHASH_SIZE];
-	wchar_t *user;
+	__le16 *user;
 	wchar_t *domain;
 	wchar_t *server;
 
@@ -419,7 +419,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 		return rc;
 	}
 
-	/* convert ses->user_name to unicode and uppercase */
+	/* convert ses->user_name to unicode */
 	len = ses->user_name ? strlen(ses->user_name) : 0;
 	user = kmalloc(2 + (len * 2), GFP_KERNEL);
 	if (user == NULL) {
@@ -429,7 +429,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 	}
 
 	if (len) {
-		len = cifs_strtoUTF16((__le16 *)user, ses->user_name, len, nls_cp);
+		len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp);
 		UniStrupr(user);
 	} else {
 		memset(user, '\0', 2);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 541ef81f6ae8..d7561e03870c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -557,6 +557,11 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 			dentry = ERR_PTR(-ENOENT);
 			break;
 		}
+		if (!S_ISDIR(dir->i_mode)) {
+			dput(dentry);
+			dentry = ERR_PTR(-ENOTDIR);
+			break;
+		}
 
 		/* skip separators */
 		while (*s == sep)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index f771e9f98f9f..9cc574cb00d1 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1576,14 +1576,24 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 			}
 			break;
 		case Opt_blank_pass:
-			vol->password = NULL;
-			break;
-		case Opt_pass:
 			/* passwords have to be handled differently
 			 * to allow the character used for deliminator
 			 * to be passed within them
 			 */
 
+			/*
+			 * Check if this is a case where the  password
+			 * starts with a delimiter
+			 */
+			tmp_end = strchr(data, '=');
+			tmp_end++;
+			if (!(tmp_end < end && tmp_end[1] == delim)) {
+				/* No it is not. Set the password to NULL */
+				vol->password = NULL;
+				break;
+			}
+			/* Yes it is. Drop down to Opt_pass below.*/
+		case Opt_pass:
 			/* Obtain the value string */
 			value = strchr(data, '=');
 			value++;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 745da3d0653e..43944c6d7b41 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -173,7 +173,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 
 	if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
 		inode->i_flags |= S_AUTOMOUNT;
-	cifs_set_ops(inode);
+	if (inode->i_state & I_NEW)
+		cifs_set_ops(inode);
 }
 
 void
@@ -548,6 +549,11 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 			fattr->cf_mode &= ~(S_IWUGO);
 
 		fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
+		if (fattr->cf_nlink < 1) {
+			cFYI(1, "replacing bogus file nlink value %u\n",
+			     fattr->cf_nlink);
+			fattr->cf_nlink = 1;
+		}
 	}
 
 	fattr->cf_uid = cifs_sb->mnt_uid;
diff --git a/fs/compat.c b/fs/compat.c
index 2b371b38911d..56acdcb84fb0 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -558,6 +558,10 @@ ssize_t compat_rw_copy_check_uvector(int type,
 	}
 	*ret_pointer = iov;
 
+	ret = -EFAULT;
+	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+		goto out;
+
 	/*
 	 * Single unix specification:
 	 * We should -EINVAL if an element length is not >= 0 and fitting an
@@ -1089,17 +1093,12 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	if (!file->f_op)
 		goto out;
 
-	ret = -EFAULT;
-	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs,
+	ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
 					       UIO_FASTIOV, iovstack, &iov, 1);
-	if (tot_len == 0) {
-		ret = 0;
+	if (ret <= 0)
 		goto out;
-	}
 
+	tot_len = ret;
 	ret = rw_verify_area(type, file, pos, tot_len);
 	if (ret < 0)
 		goto out;
diff --git a/fs/dcache.c b/fs/dcache.c
index f104945dcc7d..e498de23bdcc 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1238,8 +1238,10 @@ void shrink_dcache_parent(struct dentry * parent)
 	LIST_HEAD(dispose);
 	int found;
 
-	while ((found = select_parent(parent, &dispose)) != 0)
+	while ((found = select_parent(parent, &dispose)) != 0) {
 		shrink_dentry_list(&dispose);
+		cond_resched();
+	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);
 
diff --git a/fs/exec.c b/fs/exec.c
index c136a5e750fc..0ea0b4c476d8 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -627,7 +627,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * when the old and new regions overlap clear from new_end.
 		 */
 		free_pgd_range(&tlb, new_end, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : TASK_SIZE);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	} else {
 		/*
 		 * otherwise, clean from old_start; this is done to not touch
@@ -636,7 +636,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * for the others its just a little faster.
 		 */
 		free_pgd_range(&tlb, old_start, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : TASK_SIZE);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
 	tlb_finish_mmu(&tlb, new_end, old_end);
 
@@ -1163,13 +1163,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 			set_dumpable(current->mm, suid_dumpable);
 	}
 
-	/*
-	 * Flush performance counters when crossing a
-	 * security domain:
-	 */
-	if (!get_dumpable(current->mm))
-		perf_event_exit_task(current);
-
 	/* An exec changes our domain. We are no longer part of the thread
 	   group */
 
@@ -1233,6 +1226,15 @@ void install_exec_creds(struct linux_binprm *bprm)
 
 	commit_creds(bprm->cred);
 	bprm->cred = NULL;
+
+	/*
+	 * Disable monitoring for regular users
+	 * when executing setuid binaries. Must
+	 * wait until new credentials are committed
+	 * by commit_creds() above
+	 */
+	if (get_dumpable(current->mm) != SUID_DUMP_USER)
+		perf_event_exit_task(current);
 	/*
 	 * cred_guard_mutex must be held at least to this point to prevent
 	 * ptrace_attach() from altering our determination of the task's
@@ -1389,6 +1391,10 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 	struct linux_binfmt *fmt;
 	pid_t old_pid, old_vpid;
 
+	/* This allows 4 levels of binfmt rewrites before failing hard. */
+	if (depth > 5)
+		return -ELOOP;
+
 	retval = security_bprm_check(bprm);
 	if (retval)
 		return retval;
@@ -1413,12 +1419,8 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 			if (!try_module_get(fmt->module))
 				continue;
 			read_unlock(&binfmt_lock);
+			bprm->recursion_depth = depth + 1;
 			retval = fn(bprm, regs);
-			/*
-			 * Restore the depth counter to its starting value
-			 * in this call, so we don't have to rely on every
-			 * load_binary function to restore it on return.
-			 */
 			bprm->recursion_depth = depth;
 			if (retval >= 0) {
 				if (depth == 0) {
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 075281734fcb..aad0f3989e52 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -218,7 +218,8 @@ void ext3_evict_inode (struct inode *inode)
 	 */
 	if (inode->i_nlink && ext3_should_journal_data(inode) &&
 	    EXT3_SB(inode->i_sb)->s_journal &&
-	    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+	    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+	    inode->i_ino != EXT3_JOURNAL_INO) {
 		tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
 		journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
 
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index d7940b24cf68..fbb9b82b59cc 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -573,11 +573,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 		if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
 					(block<<EXT3_BLOCK_SIZE_BITS(dir->i_sb))
 						+((char *)de - bh->b_data))) {
-			/* On error, skip the f_pos to the next block. */
-			dir_file->f_pos = (dir_file->f_pos |
-					(dir->i_sb->s_blocksize - 1)) + 1;
-			brelse (bh);
-			return count;
+			/* silently ignore the rest of the block */
+			break;
 		}
 		ext3fs_dirhash(de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index cf0b5921cf0f..ef4c812c7a63 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -364,7 +364,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
 	return bdev;
 
 fail:
-	ext3_msg(sb, "error: failed to open journal device %s: %ld",
+	ext3_msg(sb, KERN_ERR, "error: failed to open journal device %s: %ld",
 		__bdevname(dev, b), PTR_ERR(bdev));
 
 	return NULL;
@@ -891,7 +891,7 @@ static ext3_fsblk_t get_sb_block(void **data, struct super_block *sb)
 	/*todo: use simple_strtoll with >32bit ext3 */
 	sb_block = simple_strtoul(options, &options, 0);
 	if (*options && *options != ',') {
-		ext3_msg(sb, "error: invalid sb specification: %s",
+		ext3_msg(sb, KERN_ERR, "error: invalid sb specification: %s",
 		       (char *) *data);
 		return 1;
 	}
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 9ed1bb1f319f..5459168d9db0 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -82,4 +82,5 @@ config EXT4_DEBUG
 	  Enables run-time debugging support for the ext4 filesystem.
 
 	  If you select Y here, then you will be able to turn on debugging
-	  with a command such as "echo 1 > /sys/kernel/debug/ext4/mballoc-debug"
+	  with a command such as:
+		echo 1 > /sys/module/ext4/parameters/mballoc_debug
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 3e1018ace702..d33733eaa1b0 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -600,7 +600,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 	brelse(bitmap_bh);
 	printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
 	       ", computed = %llu, %llu\n",
-	       EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
+	       EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
 	       desc_count, bitmap_count);
 	return bitmap_count;
 #else
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 47d1c8cda0cb..d918b55f009c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -316,9 +316,9 @@ struct ext4_group_desc
  */
 
 struct flex_groups {
-	atomic_t free_inodes;
-	atomic_t free_clusters;
-	atomic_t used_dirs;
+	atomic64_t	free_clusters;
+	atomic_t	free_inodes;
+	atomic_t	used_dirs;
 };
 
 #define EXT4_BG_INODE_UNINIT	0x0001 /* Inode table/bitmap not in use */
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 83b20fcf9400..6b23a96e8095 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -164,16 +164,20 @@ static inline void ext4_journal_callback_add(handle_t *handle,
  * ext4_journal_callback_del: delete a registered callback
  * @handle: active journal transaction handle on which callback was registered
  * @jce: registered journal callback entry to unregister
+ * Return true if object was sucessfully removed
  */
-static inline void ext4_journal_callback_del(handle_t *handle,
+static inline bool ext4_journal_callback_try_del(handle_t *handle,
 					     struct ext4_journal_cb_entry *jce)
 {
+	bool deleted;
 	struct ext4_sb_info *sbi =
 			EXT4_SB(handle->h_transaction->t_journal->j_private);
 
 	spin_lock(&sbi->s_md_lock);
+	deleted = !list_empty(&jce->jce_list);
 	list_del_init(&jce->jce_list);
 	spin_unlock(&sbi->s_md_lock);
+	return deleted;
 }
 
 int
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 852d4c257ace..b9a3726ea048 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2959,6 +2959,7 @@ static int ext4_split_extent(handle_t *handle,
 	int err = 0;
 	int uninitialized;
 	int split_flag1, flags1;
+	int allocated = map->m_len;
 
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
@@ -2978,6 +2979,8 @@ static int ext4_split_extent(handle_t *handle,
 				map->m_lblk + map->m_len, split_flag1, flags1);
 		if (err)
 			goto out;
+	} else {
+		allocated = ee_len - (map->m_lblk - ee_block);
 	}
 
 	ext4_ext_drop_refs(path);
@@ -3000,7 +3003,7 @@ static int ext4_split_extent(handle_t *handle,
 
 	ext4_ext_show_leaf(inode, path);
 out:
-	return err ? err : map->m_len;
+	return err ? err : allocated;
 }
 
 #define EXT4_EXT_ZERO_LEN 7
@@ -3668,6 +3671,7 @@ out:
 					allocated - map->m_len);
 		allocated = map->m_len;
 	}
+	map->m_len = allocated;
 
 	/*
 	 * If we have done fallocate with the offset that is already
@@ -4709,7 +4713,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
 		error = ext4_get_inode_loc(inode, &iloc);
 		if (error)
 			return error;
-		physical = iloc.bh->b_blocknr << blockbits;
+		physical = (__u64)iloc.bh->b_blocknr << blockbits;
 		offset = EXT4_GOOD_OLD_INODE_SIZE +
 				EXT4_I(inode)->i_extra_isize;
 		physical += offset;
@@ -4717,7 +4721,7 @@ static int ext4_xattr_fiemap(struct inode *inode,
 		flags |= FIEMAP_EXTENT_DATA_INLINE;
 		brelse(iloc.bh);
 	} else { /* external block */
-		physical = EXT4_I(inode)->i_file_acl << blockbits;
+		physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
 		length = inode->i_sb->s_blocksize;
 	}
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 902544e7ee5c..e42b4687dbf0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -305,8 +305,8 @@ error_return:
 }
 
 struct orlov_stats {
+	__u64 free_clusters;
 	__u32 free_inodes;
-	__u32 free_clusters;
 	__u32 used_dirs;
 };
 
@@ -323,7 +323,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
 
 	if (flex_size > 1) {
 		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
+		stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
 		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
 		return;
 	}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a0d7e2617fda..98bff01eed6e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -144,7 +144,8 @@ void ext4_evict_inode(struct inode *inode)
 		 * don't use page cache.
 		 */
 		if (ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+		    inode->i_ino != EXT4_JOURNAL_INO) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -4220,7 +4221,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		 struct kstat *stat)
 {
 	struct inode *inode;
-	unsigned long delalloc_blocks;
+	unsigned long long delalloc_blocks;
 
 	inode = dentry->d_inode;
 	generic_fillattr(inode, stat);
@@ -4237,7 +4238,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	 */
 	delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks;
 
-	stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+	stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
 	return 0;
 }
 
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 3122ece15147..878484256a6f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1980,7 +1980,11 @@ repeat:
 		group = ac->ac_g_ex.fe_group;
 
 		for (i = 0; i < ngroups; group++, i++) {
-			if (group == ngroups)
+			/*
+			 * Artificially restricted ngroups for non-extent
+			 * files makes group > ngroups possible on first loop.
+			 */
+			if (group >= ngroups)
 				group = 0;
 
 			/* This now checks without needing the buddy page */
@@ -2813,8 +2817,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi,
 							  ac->ac_b_ex.fe_group);
-		atomic_sub(ac->ac_b_ex.fe_len,
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_sub(ac->ac_b_ex.fe_len,
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -3433,7 +3437,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 			win = offs;
 
 		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
-			EXT4_B2C(sbi, win);
+			EXT4_NUM_B2C(sbi, win);
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
 		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
 	}
@@ -4436,11 +4440,11 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_prev(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(entry, new_entry)) {
+		if (can_merge(entry, new_entry) &&
+		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
 			new_entry->efd_start_cluster = entry->efd_start_cluster;
 			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			ext4_journal_callback_del(handle, &entry->efd_jce);
 			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
@@ -4448,10 +4452,10 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_next(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(new_entry, entry)) {
+		if (can_merge(new_entry, entry) &&
+		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
 			new_entry->efd_count += entry->efd_count;
 			rb_erase(node, &(db->bb_free_root));
-			ext4_journal_callback_del(handle, &entry->efd_jce);
 			kmem_cache_free(ext4_free_data_cachep, entry);
 		}
 	}
@@ -4577,7 +4581,7 @@ do_more:
 			EXT4_BLOCKS_PER_GROUP(sb);
 		count -= overflow;
 	}
-	count_clusters = EXT4_B2C(sbi, count);
+	count_clusters = EXT4_NUM_B2C(sbi, count);
 	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
 	if (!bitmap_bh) {
 		err = -EIO;
@@ -4635,11 +4639,16 @@ do_more:
 		 * blocks being freed are metadata. these blocks shouldn't
 		 * be used until this transaction is committed
 		 */
+	retry:
 		new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
 		if (!new_entry) {
-			ext4_mb_unload_buddy(&e4b);
-			err = -ENOMEM;
-			goto error_return;
+			/*
+			 * We use a retry loop because
+			 * ext4_free_blocks() is not allowed to fail.
+			 */
+			cond_resched();
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			goto retry;
 		}
 		new_entry->efd_start_cluster = bit;
 		new_entry->efd_group = block_group;
@@ -4667,8 +4676,8 @@ do_more:
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(count_clusters,
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(count_clusters,
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
@@ -4808,12 +4817,12 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
 	ext4_unlock_group(sb, block_group);
 	percpu_counter_add(&sbi->s_freeclusters_counter,
-			   EXT4_B2C(sbi, blocks_freed));
+			   EXT4_NUM_B2C(sbi, blocks_freed));
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
-		atomic_add(EXT4_B2C(sbi, blocks_freed),
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed),
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index ac769399b141..9fb3fae4898a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -585,11 +585,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
 				(block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
 					 + ((char *)de - bh->b_data))) {
-			/* On error, skip the f_pos to the next block. */
-			dir_file->f_pos = (dir_file->f_pos |
-					(dir->i_sb->s_blocksize - 1)) + 1;
-			brelse(bh);
-			return count;
+			/* silently ignore the rest of the block */
+			break;
 		}
 		ext4fs_dirhash(de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 0dbeb39f79ef..c299dde3f6ec 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1112,7 +1112,7 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb,
 		ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap);
 		ext4_inode_table_set(sb, gdp, group_data->inode_table);
 		ext4_free_group_clusters_set(sb, gdp,
-					     EXT4_B2C(sbi, group_data->free_blocks_count));
+			EXT4_NUM_B2C(sbi, group_data->free_blocks_count));
 		ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
 		gdp->bg_flags = cpu_to_le16(*bg_flags);
 		gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
@@ -1202,6 +1202,8 @@ static void ext4_update_super(struct super_block *sb,
 
 	/* Update the global fs size fields */
 	sbi->s_groups_count += flex_gd->count;
+	sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count,
+			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 
 	/* Update the reserved block counts only once the new group is
 	 * active. */
@@ -1210,7 +1212,7 @@ static void ext4_update_super(struct super_block *sb,
 
 	/* Update the free space counts */
 	percpu_counter_add(&sbi->s_freeclusters_counter,
-			   EXT4_B2C(sbi, free_blocks));
+			   EXT4_NUM_B2C(sbi, free_blocks));
 	percpu_counter_add(&sbi->s_freeinodes_counter,
 			   EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
 
@@ -1219,8 +1221,8 @@ static void ext4_update_super(struct super_block *sb,
 	    sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
 		flex_group = ext4_flex_group(sbi, group_data[0].group);
-		atomic_add(EXT4_B2C(sbi, free_blocks),
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
 			   &sbi->s_flex_groups[flex_group].free_inodes);
 	}
@@ -1628,6 +1630,10 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 		return 0;
 
 	ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset);
+	if (n_group > (0xFFFFFFFFUL / EXT4_INODES_PER_GROUP(sb))) {
+		ext4_warning(sb, "resize would cause inodes_count overflow");
+		return -EINVAL;
+	}
 	ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset);
 
 	n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) /
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 94dc725a1bb8..0edd29412912 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -437,10 +437,13 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	struct super_block		*sb = journal->j_private;
 	struct ext4_sb_info		*sbi = EXT4_SB(sb);
 	int				error = is_journal_aborted(journal);
-	struct ext4_journal_cb_entry	*jce, *tmp;
+	struct ext4_journal_cb_entry	*jce;
 
+	BUG_ON(txn->t_state == T_FINISHED);
 	spin_lock(&sbi->s_md_lock);
-	list_for_each_entry_safe(jce, tmp, &txn->t_private_list, jce_list) {
+	while (!list_empty(&txn->t_private_list)) {
+		jce = list_entry(txn->t_private_list.next,
+				 struct ext4_journal_cb_entry, jce_list);
 		list_del_init(&jce->jce_list);
 		spin_unlock(&sbi->s_md_lock);
 		jce->jce_func(sb, jce, error);
@@ -1907,8 +1910,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 		flex_group = ext4_flex_group(sbi, i);
 		atomic_add(ext4_free_inodes_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].free_inodes);
-		atomic_add(ext4_free_group_clusters(sb, gdp),
-			   &sbi->s_flex_groups[flex_group].free_clusters);
+		atomic64_add(ext4_free_group_clusters(sb, gdp),
+			     &sbi->s_flex_groups[flex_group].free_clusters);
 		atomic_add(ext4_used_dirs_count(sb, gdp),
 			   &sbi->s_flex_groups[flex_group].used_dirs);
 	}
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index d403f76c5a68..fe6d34000454 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1237,6 +1237,19 @@ static int fat_read_root(struct inode *inode)
 	return 0;
 }
 
+static unsigned long calc_fat_clusters(struct super_block *sb)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+
+	/* Divide first to avoid overflow */
+	if (sbi->fat_bits != 12) {
+		unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits;
+		return ent_per_sec * sbi->fat_length;
+	}
+
+	return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
+}
+
 /*
  * Read the super block of an MS-DOS FS.
  */
@@ -1442,7 +1455,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12;
 
 	/* check that FAT table does not overflow */
-	fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
+	fat_clusters = calc_fat_clusters(sb);
 	total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT);
 	if (total_clusters > MAX_FAT(sb)) {
 		if (!silent)
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190d537f..73c0bd7f7424 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -276,5 +276,5 @@ const struct file_operations fscache_stats_fops = {
 	.open		= fscache_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release        = single_release,
 };
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 5849e3ef35cc..32b12e5e33c9 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -517,7 +517,7 @@ void hfsplus_file_truncate(struct inode *inode)
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page;
 		void *fsdata;
-		u32 size = inode->i_size;
+		loff_t size = inode->i_size;
 
 		res = pagecache_write_begin(NULL, mapping, size, 0,
 						AOP_FLAG_UNINTERRUPTIBLE,
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index a790821366a7..ea3d1ca43e19 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -17,7 +17,8 @@ unsigned int *hpfs_map_bitmap(struct super_block *s, unsigned bmp_block,
 			 struct quad_buffer_head *qbh, char *id)
 {
 	secno sec;
-	if (hpfs_sb(s)->sb_chk) if (bmp_block * 16384 > hpfs_sb(s)->sb_fs_size) {
+	unsigned n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14;
+	if (hpfs_sb(s)->sb_chk) if (bmp_block >= n_bands) {
 		hpfs_error(s, "hpfs_map_bitmap called with bad parameter: %08x at %s", bmp_block, id);
 		return NULL;
 	}
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 54f6eccb79d9..0bf578dbfce7 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -552,7 +552,13 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
 	sbi->sb_cp_table = NULL;
 	sbi->sb_c_bitmap = -1;
 	sbi->sb_max_fwd_alloc = 0xffffff;
-	
+
+	if (sbi->sb_fs_size >= 0x80000000) {
+		hpfs_error(s, "invalid size in superblock: %08x",
+			(unsigned)sbi->sb_fs_size);
+		goto bail4;
+	}
+
 	/* Load bitmap directory */
 	if (!(sbi->sb_bmp_dir = hpfs_load_bitmap_directory(s, le32_to_cpu(superblock->bitmaps))))
 		goto bail4;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 001ef01d2fe2..36ad5b4aae62 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -927,9 +927,13 @@ static int can_do_hugetlb_shm(void)
 	return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
 }
 
-struct file *hugetlb_file_setup(const char *name, unsigned long addr,
-				size_t size, vm_flags_t acctflag,
-				struct user_struct **user, int creat_flags)
+/*
+ * Note that size should be aligned to proper hugepage size in caller side,
+ * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
+ */
+struct file *hugetlb_file_setup(const char *name, size_t size,
+				vm_flags_t acctflag, struct user_struct **user,
+				int creat_flags)
 {
 	int error = -ENOMEM;
 	struct file *file;
@@ -937,8 +941,6 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 	struct path path;
 	struct dentry *root;
 	struct qstr quick_string;
-	struct hstate *hstate;
-	unsigned long num_pages;
 
 	*user = NULL;
 	if (!hugetlbfs_vfsmount)
@@ -972,12 +974,10 @@ struct file *hugetlb_file_setup(const char *name, unsigned long addr,
 	if (!inode)
 		goto out_dentry;
 
-	hstate = hstate_inode(inode);
-	size += addr & ~huge_page_mask(hstate);
-	num_pages = ALIGN(size, huge_page_size(hstate)) >>
-			huge_page_shift(hstate);
 	error = -ENOMEM;
-	if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
+	if (hugetlb_reserve_pages(inode, 0,
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
 		goto out_inode;
 
 	d_instantiate(path.dentry, inode);
diff --git a/fs/inode.c b/fs/inode.c
index 9f4f5fecc096..8de457e8ed09 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -705,7 +705,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
 		 * inode to the back of the list so we don't spin on it.
 		 */
 		if (!spin_trylock(&inode->i_lock)) {
-			list_move_tail(&inode->i_lru, &sb->s_inode_lru);
+			list_move(&inode->i_lru, &sb->s_inode_lru);
 			continue;
 		}
 
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index 516eb21895c6..fd88add6ca46 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -135,6 +135,7 @@ isofs_export_encode_fh(struct dentry *dentry,
 	len = 3;
 	fh32[0] = ei->i_iget5_block;
  	fh16[2] = (__u16)ei->i_iget5_offset;  /* fh16 [sic] */
+	fh16[3] = 0;  /* avoid leaking uninitialized data */
 	fh32[2] = inode->i_generation;
 	if (connectable && !S_ISDIR(inode->i_mode)) {
 		struct inode *parent;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 840f70f50792..a0dcbd62b180 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -325,7 +325,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	int space_left = 0;
 	int first_tag = 0;
 	int tag_flag;
-	int i, to_free = 0;
+	int i;
 	int tag_bytes = journal_tag_bytes(journal);
 	struct buffer_head *cbh = NULL; /* For transactional checksums */
 	__u32 crc32_sum = ~0;
@@ -1044,7 +1044,7 @@ restart_loop:
 	journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
 	spin_unlock(&journal->j_history_lock);
 
-	commit_transaction->t_state = T_FINISHED;
+	commit_transaction->t_state = T_COMMIT_CALLBACK;
 	J_ASSERT(commit_transaction == journal->j_committing_transaction);
 	journal->j_commit_sequence = commit_transaction->t_tid;
 	journal->j_committing_transaction = NULL;
@@ -1059,38 +1059,44 @@ restart_loop:
 				journal->j_average_commit_time*3) / 4;
 	else
 		journal->j_average_commit_time = commit_time;
+
 	write_unlock(&journal->j_state_lock);
 
-	if (commit_transaction->t_checkpoint_list == NULL &&
-	    commit_transaction->t_checkpoint_io_list == NULL) {
-		__jbd2_journal_drop_transaction(journal, commit_transaction);
-		to_free = 1;
+	if (journal->j_checkpoint_transactions == NULL) {
+		journal->j_checkpoint_transactions = commit_transaction;
+		commit_transaction->t_cpnext = commit_transaction;
+		commit_transaction->t_cpprev = commit_transaction;
 	} else {
-		if (journal->j_checkpoint_transactions == NULL) {
-			journal->j_checkpoint_transactions = commit_transaction;
-			commit_transaction->t_cpnext = commit_transaction;
-			commit_transaction->t_cpprev = commit_transaction;
-		} else {
-			commit_transaction->t_cpnext =
-				journal->j_checkpoint_transactions;
-			commit_transaction->t_cpprev =
-				commit_transaction->t_cpnext->t_cpprev;
-			commit_transaction->t_cpnext->t_cpprev =
-				commit_transaction;
-			commit_transaction->t_cpprev->t_cpnext =
+		commit_transaction->t_cpnext =
+			journal->j_checkpoint_transactions;
+		commit_transaction->t_cpprev =
+			commit_transaction->t_cpnext->t_cpprev;
+		commit_transaction->t_cpnext->t_cpprev =
+			commit_transaction;
+		commit_transaction->t_cpprev->t_cpnext =
 				commit_transaction;
-		}
 	}
 	spin_unlock(&journal->j_list_lock);
-
+	/* Drop all spin_locks because commit_callback may be block.
+	 * __journal_remove_checkpoint() can not destroy transaction
+	 * under us because it is not marked as T_FINISHED yet */
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
-	if (to_free)
-		jbd2_journal_free_transaction(commit_transaction);
 
+	write_lock(&journal->j_state_lock);
+	spin_lock(&journal->j_list_lock);
+	commit_transaction->t_state = T_FINISHED;
+	/* Recheck checkpoint lists after j_list_lock was dropped */
+	if (commit_transaction->t_checkpoint_list == NULL &&
+	    commit_transaction->t_checkpoint_io_list == NULL) {
+		__jbd2_journal_drop_transaction(journal, commit_transaction);
+		jbd2_journal_free_transaction(commit_transaction);
+	}
+	spin_unlock(&journal->j_list_lock);
+	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
 }
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index de8b4cb7c31e..f5671271b5ba 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -500,10 +500,10 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
 		   &transaction->t_outstanding_credits);
 	if (atomic_dec_and_test(&transaction->t_updates))
 		wake_up(&journal->j_wait_updates);
+	tid = transaction->t_tid;
 	spin_unlock(&transaction->t_handle_lock);
 
 	jbd_debug(2, "restarting handle %p\n", handle);
-	tid = transaction->t_tid;
 	need_to_start = !tid_geq(journal->j_commit_request, tid);
 	read_unlock(&journal->j_state_lock);
 	if (need_to_start)
@@ -1047,9 +1047,12 @@ out:
 void jbd2_journal_set_triggers(struct buffer_head *bh,
 			       struct jbd2_buffer_trigger_type *type)
 {
-	struct journal_head *jh = bh2jh(bh);
+	struct journal_head *jh = jbd2_journal_grab_journal_head(bh);
 
+	if (WARN_ON(!jh))
+		return;
 	jh->b_triggers = type;
+	jbd2_journal_put_journal_head(jh);
 }
 
 void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data,
@@ -1101,17 +1104,18 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal = transaction->t_journal;
-	struct journal_head *jh = bh2jh(bh);
+	struct journal_head *jh;
 	int ret = 0;
 
-	jbd_debug(5, "journal_head %p\n", jh);
-	JBUFFER_TRACE(jh, "entry");
 	if (is_handle_aborted(handle))
 		goto out;
-	if (!buffer_jbd(bh)) {
+	jh = jbd2_journal_grab_journal_head(bh);
+	if (!jh) {
 		ret = -EUCLEAN;
 		goto out;
 	}
+	jbd_debug(5, "journal_head %p\n", jh);
+	JBUFFER_TRACE(jh, "entry");
 
 	jbd_lock_bh_state(bh);
 
@@ -1202,6 +1206,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	spin_unlock(&journal->j_list_lock);
 out_unlock_bh:
 	jbd_unlock_bh_state(bh);
+	jbd2_journal_put_journal_head(jh);
 out:
 	JBUFFER_TRACE(jh, "exit");
 	WARN_ON(ret);	/* All errors are bugs, so dump the stack */
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 77b69b27f825..13fc88561da3 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -125,7 +125,7 @@ int jfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	int wait = wbc->sync_mode == WB_SYNC_ALL;
 
-	if (test_cflag(COMMIT_Nolink, inode))
+	if (inode->i_nlink == 0)
 		return 0;
 	/*
 	 * If COMMIT_DIRTY is not set, the inode isn't really dirty.
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 2eb952c41a69..cbe48ea9318e 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1058,7 +1058,8 @@ static int lmLogSync(struct jfs_log * log, int hard_sync)
  */
 void jfs_syncpt(struct jfs_log *log, int hard_sync)
 {	LOG_LOCK(log);
-	lmLogSync(log, hard_sync);
+	if (!test_bit(log_QUIESCE, &log->flag))
+		lmLogSync(log, hard_sync);
 	LOG_UNLOCK(log);
 }
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index ca0a08001449..193f04cc97ba 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -144,6 +144,9 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
 			timeout);
 	if (ret < 0)
 		return -ERESTARTSYS;
+	/* Reset the lock status after a server reboot so we resend */
+	if (block->b_status == nlm_lck_denied_grace_period)
+		block->b_status = nlm_lck_blocked;
 	req->a_res.status = block->b_status;
 	return 0;
 }
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index a3a09877ea62..8392cb85bd54 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -551,9 +551,6 @@ again:
 		status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT);
 		if (status < 0)
 			break;
-		/* Resend the blocking lock request after a server reboot */
-		if (resp->status ==  nlm_lck_denied_grace_period)
-			continue;
 		if (resp->status != nlm_lck_blocked)
 			break;
 	}
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e46353f41a42..aff1c616aedf 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -941,6 +941,7 @@ nlmsvc_retry_blocked(void)
 	unsigned long	timeout = MAX_SCHEDULE_TIMEOUT;
 	struct nlm_block *block;
 
+	spin_lock(&nlm_blocked_lock);
 	while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
 		block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
 
@@ -950,6 +951,7 @@ nlmsvc_retry_blocked(void)
 			timeout = block->b_when - jiffies;
 			break;
 		}
+		spin_unlock(&nlm_blocked_lock);
 
 		dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
 			block, block->b_when);
@@ -959,7 +961,9 @@ nlmsvc_retry_blocked(void)
 			retry_deferred_block(block);
 		} else
 			nlmsvc_grant_blocked(block);
+		spin_lock(&nlm_blocked_lock);
 	}
+	spin_unlock(&nlm_blocked_lock);
 
 	return timeout;
 }
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index 737d839bc17b..6fc7b5cae92b 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -55,7 +55,8 @@ static void dev_remove(struct net *net, dev_t dev)
 
 	bl_pipe_msg.bl_wq = &nn->bl_wq;
 	memset(msg, 0, sizeof(*msg));
-	msg->data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+	msg->len = sizeof(bl_msg) + bl_msg.totallen;
+	msg->data = kzalloc(msg->len, GFP_NOFS);
 	if (!msg->data)
 		goto out;
 
@@ -66,7 +67,6 @@ static void dev_remove(struct net *net, dev_t dev)
 	memcpy(msg->data, &bl_msg, sizeof(bl_msg));
 	dataptr = (uint8_t *) msg->data;
 	memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
-	msg->len = sizeof(bl_msg) + bl_msg.totallen;
 
 	add_wait_queue(&nn->bl_wq, &wq);
 	if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 30351877aee2..d121c67f87d0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1053,7 +1053,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 	struct nfs4_state *state = opendata->state;
 	struct nfs_inode *nfsi = NFS_I(state->inode);
 	struct nfs_delegation *delegation;
-	int open_mode = opendata->o_arg.open_flags & (O_EXCL|O_TRUNC);
+	int open_mode = opendata->o_arg.open_flags;
 	fmode_t fmode = opendata->o_arg.fmode;
 	nfs4_stateid stateid;
 	int ret = -EAGAIN;
@@ -1362,6 +1362,12 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 			case -ENOMEM:
 				err = 0;
 				goto out;
+			case -NFS4ERR_DELAY:
+			case -NFS4ERR_GRACE:
+				set_bit(NFS_DELEGATED_STATE, &state->flags);
+				ssleep(1);
+				err = -EAGAIN;
+				goto out;
 		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 3210a03342f9..2781563ed542 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -336,20 +336,14 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 	struct inode *old_dir = data->old_dir;
 	struct inode *new_dir = data->new_dir;
 	struct dentry *old_dentry = data->old_dentry;
-	struct dentry *new_dentry = data->new_dentry;
 
 	if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
 		rpc_restart_call_prepare(task);
 		return;
 	}
 
-	if (task->tk_status != 0) {
+	if (task->tk_status != 0)
 		nfs_cancel_async_unlink(old_dentry);
-		return;
-	}
-
-	d_drop(old_dentry);
-	d_drop(new_dentry);
 }
 
 /**
@@ -550,6 +544,18 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 	error = rpc_wait_for_completion_task(task);
 	if (error == 0)
 		error = task->tk_status;
+	switch (error) {
+	case 0:
+		/* The rename succeeded */
+		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+		d_move(dentry, sdentry);
+		break;
+	case -ERESTARTSYS:
+		/* The result of the rename is unknown. Play it safe by
+		 * forcing a new lookup */
+		d_drop(dentry);
+		d_drop(sdentry);
+	}
 	rpc_put_task(task);
 out_dput:
 	dput(sdentry);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index dd0308d65f66..64198ed1d64a 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -270,6 +270,7 @@ static __be32
 do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
 {
 	__be32 status;
+	int accmode = 0;
 
 	/* We don't know the target directory, and therefore can not
 	* set the change info
@@ -283,9 +284,19 @@ do_open_fhandle(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_
 
 	open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
 		(open->op_iattr.ia_size == 0);
+	/*
+	 * In the delegation case, the client is telling us about an
+	 * open that it *already* performed locally, some time ago.  We
+	 * should let it succeed now if possible.
+	 *
+	 * In the case of a CLAIM_FH open, on the other hand, the client
+	 * may be counting on us to enforce permissions (the Linux 4.1
+	 * client uses this for normal opens, for example).
+	 */
+	if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH)
+		accmode = NFSD_MAY_OWNER_OVERRIDE;
 
-	status = do_open_permission(rqstp, current_fh, open,
-				    NFSD_MAY_OWNER_OVERRIDE);
+	status = do_open_permission(rqstp, current_fh, open, accmode);
 
 	return status;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index abd785e5fd2d..f90b197ceffa 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -213,13 +213,7 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 {
 	if (atomic_dec_and_test(&fp->fi_access[oflag])) {
 		nfs4_file_put_fd(fp, oflag);
-		/*
-		 * It's also safe to get rid of the RDWR open *if*
-		 * we no longer have need of the other kind of access
-		 * or if we already have the other kind of open:
-		 */
-		if (fp->fi_fds[1-oflag]
-			|| atomic_read(&fp->fi_access[1 - oflag]) == 0)
+		if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
 			nfs4_file_put_fd(fp, O_RDWR);
 	}
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 967d68eef282..cb997b1bb398 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -161,8 +161,8 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
 	 */
 	memcpy(p, argp->p, avail);
 	/* step to next page */
-	argp->p = page_address(argp->pagelist[0]);
 	argp->pagelist++;
+	argp->p = page_address(argp->pagelist[0]);
 	if (argp->pagelen < PAGE_SIZE) {
 		argp->end = argp->p + (argp->pagelen>>2);
 		argp->pagelen = 0;
@@ -263,7 +263,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		iattr->ia_valid |= ATTR_SIZE;
 	}
 	if (bmval[0] & FATTR4_WORD0_ACL) {
-		int nace;
+		u32 nace;
 		struct nfs4_ace *ace;
 
 		READ_BUF(4); len += 4;
@@ -343,10 +343,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ32(dummy32);
-			if (dummy32)
-				return nfserr_inval;
-			READ32(iattr->ia_atime.tv_sec);
+			READ64(iattr->ia_atime.tv_sec);
 			READ32(iattr->ia_atime.tv_nsec);
 			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
@@ -369,10 +366,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ32(dummy32);
-			if (dummy32)
-				return nfserr_inval;
-			READ32(iattr->ia_mtime.tv_sec);
+			READ64(iattr->ia_mtime.tv_sec);
 			READ32(iattr->ia_mtime.tv_nsec);
 			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
@@ -2371,8 +2365,7 @@ out_acl:
 	if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.atime.tv_sec);
+		WRITE64((s64)stat.atime.tv_sec);
 		WRITE32(stat.atime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
@@ -2385,15 +2378,13 @@ out_acl:
 	if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.ctime.tv_sec);
+		WRITE64((s64)stat.ctime.tv_sec);
 		WRITE32(stat.ctime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
 		if ((buflen -= 12) < 0)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(stat.mtime.tv_sec);
+		WRITE64((s64)stat.mtime.tv_sec);
 		WRITE32(stat.mtime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 8f7b95ac1f7e..aa526bebee3f 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -195,13 +195,32 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
 
 static int nilfs_set_page_dirty(struct page *page)
 {
-	int ret = __set_page_dirty_buffers(page);
+	int ret = __set_page_dirty_nobuffers(page);
 
-	if (ret) {
+	if (page_has_buffers(page)) {
 		struct inode *inode = page->mapping->host;
-		unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
+		unsigned nr_dirty = 0;
+		struct buffer_head *bh, *head;
 
-		nilfs_set_file_dirty(inode, nr_dirty);
+		/*
+		 * This page is locked by callers, and no other thread
+		 * concurrently marks its buffers dirty since they are
+		 * only dirtied through routines in fs/buffer.c in
+		 * which call sites of mark_buffer_dirty are protected
+		 * by page lock.
+		 */
+		bh = head = page_buffers(page);
+		do {
+			/* Do not mark hole blocks dirty */
+			if (buffer_dirty(bh) || !buffer_mapped(bh))
+				continue;
+
+			set_buffer_dirty(bh);
+			nr_dirty++;
+		} while (bh = bh->b_this_page, bh != head);
+
+		if (nr_dirty)
+			nilfs_set_file_dirty(inode, nr_dirty);
 	}
 	return ret;
 }
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 3568c8a8b138..48bc91d60fce 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -120,6 +120,7 @@ static int fill_event_metadata(struct fsnotify_group *group,
 	metadata->event_len = FAN_EVENT_METADATA_LEN;
 	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata->vers = FANOTIFY_METADATA_VERSION;
+	metadata->reserved = 0;
 	metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
 	metadata->pid = pid_vnr(event->tgid);
 	if (unlikely(event->mask & FAN_Q_OVERFLOW))
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 6f292dd53c6d..f255d372a5df 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -577,7 +577,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	int add = (arg & IN_MASK_ADD);
 	int ret;
 
-	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
@@ -628,7 +627,6 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	struct idr *idr = &group->inotify_data.idr;
 	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
 
-	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 
 	tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
@@ -757,6 +755,10 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	int ret, fput_needed;
 	unsigned flags = 0;
 
+	/* don't allow invalid bits: we don't want flags set */
+	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
+		return -EINVAL;
+
 	filp = fget_light(fd, &fput_needed);
 	if (unlikely(!filp))
 		return -EBADF;
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 2f5b92ef0e53..7eb1c0c7c166 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -791,7 +791,7 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 						 &hole_size, &rec, &is_last);
 		if (ret) {
 			mlog_errno(ret);
-			goto out;
+			goto out_unlock;
 		}
 
 		if (rec.e_blkno == 0ULL) {
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 2e3ea308c144..5b8d94436105 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -6499,6 +6499,16 @@ static int ocfs2_reflink_xattr_inline(struct ocfs2_xattr_reflink *args)
 	}
 
 	new_oi = OCFS2_I(args->new_inode);
+	/*
+	 * Adjust extent record count to reserve space for extended attribute.
+	 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+	 */
+	if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+	    !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
+		struct ocfs2_extent_list *el = &new_di->id2.i_list;
+		le16_add_cpu(&el->l_count, -(inline_size /
+					sizeof(struct ocfs2_extent_rec)));
+	}
 	spin_lock(&new_oi->ip_lock);
 	new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
 	new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);
diff --git a/fs/pipe.c b/fs/pipe.c
index fec5e4ad071a..1667e6fe0416 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -860,6 +860,9 @@ pipe_rdwr_open(struct inode *inode, struct file *filp)
 {
 	int ret = -ENOENT;
 
+	if (!(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
+		return -EINVAL;
+
 	mutex_lock(&inode->i_mutex);
 
 	if (inode->i_pipe) {
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 46fc1c20a6b1..048d9900910c 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -187,8 +187,8 @@ fill_with_dentries(void *buf, const char *name, int namelen, loff_t offset,
 	if (dbuf->count == ARRAY_SIZE(dbuf->dentries))
 		return -ENOSPC;
 
-	if (name[0] == '.' && (name[1] == '\0' ||
-			       (name[1] == '.' && name[2] == '\0')))
+	if (name[0] == '.' && (namelen < 2 ||
+			       (namelen == 2 && name[1] == '.')))
 		return 0;
 
 	dentry = lookup_one_len(name, dbuf->xadir, namelen);
diff --git a/fs/super.c b/fs/super.c
index cf001775617f..3c520a5ed715 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -298,19 +298,19 @@ EXPORT_SYMBOL(deactivate_super);
  *	and want to turn it into a full-blown active reference.  grab_super()
  *	is called with sb_lock held and drops it.  Returns 1 in case of
  *	success, 0 if we had failed (superblock contents was already dead or
- *	dying when grab_super() had been called).
+ *	dying when grab_super() had been called).  Note that this is only
+ *	called for superblocks not in rundown mode (== ones still on ->fs_supers
+ *	of their type), so increment of ->s_count is OK here.
  */
 static int grab_super(struct super_block *s) __releases(sb_lock)
 {
-	if (atomic_inc_not_zero(&s->s_active)) {
-		spin_unlock(&sb_lock);
-		return 1;
-	}
-	/* it's going away */
 	s->s_count++;
 	spin_unlock(&sb_lock);
-	/* wait for it to die */
 	down_write(&s->s_umount);
+	if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) {
+		put_super(s);
+		return 1;
+	}
 	up_write(&s->s_umount);
 	put_super(s);
 	return 0;
@@ -440,11 +440,6 @@ retry:
 				destroy_super(s);
 				s = NULL;
 			}
-			down_write(&old->s_umount);
-			if (unlikely(!(old->s_flags & MS_BORN))) {
-				deactivate_locked_super(old);
-				goto retry;
-			}
 			return old;
 		}
 	}
@@ -677,10 +672,10 @@ restart:
 		if (hlist_unhashed(&sb->s_instances))
 			continue;
 		if (sb->s_bdev == bdev) {
-			if (grab_super(sb)) /* drops sb_lock */
-				return sb;
-			else
+			if (!grab_super(sb))
 				goto restart;
+			up_write(&sb->s_umount);
+			return sb;
 		}
 	}
 	spin_unlock(&sb_lock);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index a545d819b495..9a5f07d962ab 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -994,6 +994,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	enum kobj_ns_type type;
 	const void *ns;
 	ino_t ino;
+	loff_t off;
 
 	type = sysfs_ns_type(parent_sd);
 	ns = sysfs_info(dentry->d_sb)->ns[type];
@@ -1002,6 +1003,8 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		ino = parent_sd->s_ino;
 		if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
+		else
+			return 0;
 	}
 	if (filp->f_pos == 1) {
 		if (parent_sd->s_parent)
@@ -1010,8 +1013,11 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 			ino = parent_sd->s_ino;
 		if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
 			filp->f_pos++;
+		else
+			return 0;
 	}
 	mutex_lock(&sysfs_mutex);
+	off = filp->f_pos;
 	for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
 	     pos;
 	     pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) {
@@ -1023,27 +1029,43 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 		len = strlen(name);
 		ino = pos->s_ino;
 		type = dt_type(pos);
-		filp->f_pos = pos->s_hash;
+		off = filp->f_pos = pos->s_hash;
 		filp->private_data = sysfs_get(pos);
 
 		mutex_unlock(&sysfs_mutex);
-		ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+		ret = filldir(dirent, name, len, off, ino, type);
 		mutex_lock(&sysfs_mutex);
 		if (ret < 0)
 			break;
 	}
 	mutex_unlock(&sysfs_mutex);
-	if ((filp->f_pos > 1) && !pos) { /* EOF */
-		filp->f_pos = INT_MAX;
+
+	/* don't reference last entry if its refcount is dropped */
+	if (!pos) {
 		filp->private_data = NULL;
+
+		/* EOF and not changed as 0 or 1 in read/write path */
+		if (off == filp->f_pos && off > 1)
+			filp->f_pos = INT_MAX;
 	}
 	return 0;
 }
 
+static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	loff_t ret;
+
+	mutex_lock(&inode->i_mutex);
+	ret = generic_file_llseek(file, offset, whence);
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
 
 const struct file_operations sysfs_dir_operations = {
 	.read		= generic_read_dir,
 	.readdir	= sysfs_readdir,
 	.release	= sysfs_dir_release,
-	.llseek		= generic_file_llseek,
+	.llseek		= sysfs_dir_llseek,
 };
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 8640a12f0650..25c472bb8ab5 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -357,31 +357,50 @@ static unsigned int vfs_dent_type(uint8_t type)
 static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 {
 	int err, over = 0;
+	loff_t pos = file->f_pos;
 	struct qstr nm;
 	union ubifs_key key;
 	struct ubifs_dent_node *dent;
 	struct inode *dir = file->f_path.dentry->d_inode;
 	struct ubifs_info *c = dir->i_sb->s_fs_info;
 
-	dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, file->f_pos);
+	dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, pos);
 
-	if (file->f_pos > UBIFS_S_KEY_HASH_MASK || file->f_pos == 2)
+	if (pos > UBIFS_S_KEY_HASH_MASK || pos == 2)
 		/*
 		 * The directory was seek'ed to a senseless position or there
 		 * are no more entries.
 		 */
 		return 0;
 
+	if (file->f_version == 0) {
+		/*
+		 * The file was seek'ed, which means that @file->private_data
+		 * is now invalid. This may also be just the first
+		 * 'ubifs_readdir()' invocation, in which case
+		 * @file->private_data is NULL, and the below code is
+		 * basically a no-op.
+		 */
+		kfree(file->private_data);
+		file->private_data = NULL;
+	}
+
+	/*
+	 * 'generic_file_llseek()' unconditionally sets @file->f_version to
+	 * zero, and we use this for detecting whether the file was seek'ed.
+	 */
+	file->f_version = 1;
+
 	/* File positions 0 and 1 correspond to "." and ".." */
-	if (file->f_pos == 0) {
+	if (pos == 0) {
 		ubifs_assert(!file->private_data);
 		over = filldir(dirent, ".", 1, 0, dir->i_ino, DT_DIR);
 		if (over)
 			return 0;
-		file->f_pos = 1;
+		file->f_pos = pos = 1;
 	}
 
-	if (file->f_pos == 1) {
+	if (pos == 1) {
 		ubifs_assert(!file->private_data);
 		over = filldir(dirent, "..", 2, 1,
 			       parent_ino(file->f_path.dentry), DT_DIR);
@@ -397,7 +416,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 			goto out;
 		}
 
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 	}
 
@@ -405,17 +424,16 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 	if (!dent) {
 		/*
 		 * The directory was seek'ed to and is now readdir'ed.
-		 * Find the entry corresponding to @file->f_pos or the
-		 * closest one.
+		 * Find the entry corresponding to @pos or the closest one.
 		 */
-		dent_key_init_hash(c, &key, dir->i_ino, file->f_pos);
+		dent_key_init_hash(c, &key, dir->i_ino, pos);
 		nm.name = NULL;
 		dent = ubifs_tnc_next_ent(c, &key, &nm);
 		if (IS_ERR(dent)) {
 			err = PTR_ERR(dent);
 			goto out;
 		}
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 	}
 
@@ -427,7 +445,7 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 			     ubifs_inode(dir)->creat_sqnum);
 
 		nm.len = le16_to_cpu(dent->nlen);
-		over = filldir(dirent, dent->name, nm.len, file->f_pos,
+		over = filldir(dirent, dent->name, nm.len, pos,
 			       le64_to_cpu(dent->inum),
 			       vfs_dent_type(dent->type));
 		if (over)
@@ -443,9 +461,17 @@ static int ubifs_readdir(struct file *file, void *dirent, filldir_t filldir)
 		}
 
 		kfree(file->private_data);
-		file->f_pos = key_hash_flash(c, &dent->key);
+		file->f_pos = pos = key_hash_flash(c, &dent->key);
 		file->private_data = dent;
 		cond_resched();
+
+		if (file->f_version == 0)
+			/*
+			 * The file was seek'ed meanwhile, lets return and start
+			 * reading direntries from the new position on the next
+			 * invocation.
+			 */
+			return 0;
 	}
 
 out:
@@ -456,15 +482,13 @@ out:
 
 	kfree(file->private_data);
 	file->private_data = NULL;
+	/* 2 is a special value indicating that there are no more direntries */
 	file->f_pos = 2;
 	return 0;
 }
 
-/* If a directory is seeked, we have to free saved readdir() state */
 static loff_t ubifs_dir_llseek(struct file *file, loff_t offset, int origin)
 {
-	kfree(file->private_data);
-	file->private_data = NULL;
 	return generic_file_llseek(file, offset, origin);
 }
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 76e4e0566ad6..d867bd97bc60 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1582,6 +1582,12 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 	c->remounting_rw = 1;
 	c->ro_mount = 0;
 
+	if (c->space_fixup) {
+		err = ubifs_fixup_free_space(c);
+		if (err)
+			return err;
+	}
+
 	err = check_free_space(c);
 	if (err)
 		goto out;
@@ -1698,12 +1704,6 @@ static int ubifs_remount_rw(struct ubifs_info *c)
 		err = dbg_check_space_info(c);
 	}
 
-	if (c->space_fixup) {
-		err = ubifs_fixup_free_space(c);
-		if (err)
-			goto out;
-	}
-
 	mutex_unlock(&c->umount_mutex);
 	return err;
 
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 38de8f234b94..78bff11169ea 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1280,6 +1280,7 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp,
 	*lenp = 3;
 	fid->udf.block = location.logicalBlockNum;
 	fid->udf.partref = location.partitionReferenceNum;
+	fid->udf.parent_partref = 0;
 	fid->udf.generation = inode->i_generation;
 
 	if (connectable && !S_ISDIR(inode->i_mode)) {
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 42ad69ac9576..9e8e08ef246b 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -82,7 +82,7 @@ struct udf_virtual_data {
 struct udf_bitmap {
 	__u32			s_extLength;
 	__u32			s_extPosition;
-	__u16			s_nr_groups;
+	int			s_nr_groups;
 	struct buffer_head 	**s_block_bitmap;
 };
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 3011b879f850..23c79cab08de 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -457,6 +457,28 @@ xfs_vn_getattr(
 	return 0;
 }
 
+static void
+xfs_setattr_mode(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct iattr		*iattr)
+{
+	struct inode	*inode = VFS_I(ip);
+	umode_t		mode = iattr->ia_mode;
+
+	ASSERT(tp);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+		mode &= ~S_ISGID;
+
+	ip->i_d.di_mode &= S_IFMT;
+	ip->i_d.di_mode |= mode & ~S_IFMT;
+
+	inode->i_mode &= S_IFMT;
+	inode->i_mode |= mode & ~S_IFMT;
+}
+
 int
 xfs_setattr_nonsize(
 	struct xfs_inode	*ip,
@@ -608,18 +630,8 @@ xfs_setattr_nonsize(
 	/*
 	 * Change file access modes.
 	 */
-	if (mask & ATTR_MODE) {
-		umode_t mode = iattr->ia_mode;
-
-		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
-			mode &= ~S_ISGID;
-
-		ip->i_d.di_mode &= S_IFMT;
-		ip->i_d.di_mode |= mode & ~S_IFMT;
-
-		inode->i_mode &= S_IFMT;
-		inode->i_mode |= mode & ~S_IFMT;
-	}
+	if (mask & ATTR_MODE)
+		xfs_setattr_mode(tp, ip, iattr);
 
 	/*
 	 * Change file access or modified times.
@@ -716,9 +728,8 @@ xfs_setattr_size(
 		return XFS_ERROR(error);
 
 	ASSERT(S_ISREG(ip->i_d.di_mode));
-	ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
-			ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
-			ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+	ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+			ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
 	lock_flags = XFS_ILOCK_EXCL;
 	if (!(flags & XFS_ATTR_NOLOCK))
@@ -861,6 +872,12 @@ xfs_setattr_size(
 		xfs_iflags_set(ip, XFS_ITRUNCATED);
 	}
 
+	/*
+	 * Change file access modes.
+	 */
+	if (mask & ATTR_MODE)
+		xfs_setattr_mode(tp, ip, iattr);
+
 	if (mask & ATTR_CTIME) {
 		inode->i_ctime = iattr->ia_ctime;
 		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;