Merge v3.9-rc5 into driver-core-next

We want the fixes in here.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

31 files changed, 416 insertions, 89 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index ecd25a1b4e5..ca9d8f1a3bb 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -651,6 +651,8 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 	if (tree_mod_dont_log(fs_info, NULL))
 		return 0;
 
+	__tree_mod_log_free_eb(fs_info, old_root);
+
 	ret = tree_mod_alloc(fs_info, flags, &tm);
 	if (ret < 0)
 		goto out;
@@ -736,7 +738,7 @@ tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq)
 static noinline void
 tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
 		     struct extent_buffer *src, unsigned long dst_offset,
-		     unsigned long src_offset, int nr_items)
+		     unsigned long src_offset, int nr_items, int log_removal)
 {
 	int ret;
 	int i;
@@ -750,10 +752,12 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
 	}
 
 	for (i = 0; i < nr_items; i++) {
-		ret = tree_mod_log_insert_key_locked(fs_info, src,
-						     i + src_offset,
-						     MOD_LOG_KEY_REMOVE);
-		BUG_ON(ret < 0);
+		if (log_removal) {
+			ret = tree_mod_log_insert_key_locked(fs_info, src,
+							i + src_offset,
+							MOD_LOG_KEY_REMOVE);
+			BUG_ON(ret < 0);
+		}
 		ret = tree_mod_log_insert_key_locked(fs_info, dst,
 						     i + dst_offset,
 						     MOD_LOG_KEY_ADD);
@@ -927,7 +931,6 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			ret = btrfs_dec_ref(trans, root, buf, 1, 1);
 			BUG_ON(ret); /* -ENOMEM */
 		}
-		tree_mod_log_free_eb(root->fs_info, buf);
 		clean_tree_block(trans, root, buf);
 		*last_ref = 1;
 	}
@@ -1046,6 +1049,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		btrfs_set_node_ptr_generation(parent, parent_slot,
 					      trans->transid);
 		btrfs_mark_buffer_dirty(parent);
+		tree_mod_log_free_eb(root->fs_info, buf);
 		btrfs_free_tree_block(trans, root, buf, parent_start,
 				      last_ref);
 	}
@@ -1750,7 +1754,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			goto enospc;
 		}
 
-		tree_mod_log_free_eb(root->fs_info, root->node);
 		tree_mod_log_set_root_pointer(root, child);
 		rcu_assign_pointer(root->node, child);
 
@@ -2995,7 +2998,7 @@ static int push_node_left(struct btrfs_trans_handle *trans,
 		push_items = min(src_nritems - 8, push_items);
 
 	tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0,
-			     push_items);
+			     push_items, 1);
 	copy_extent_buffer(dst, src,
 			   btrfs_node_key_ptr_offset(dst_nritems),
 			   btrfs_node_key_ptr_offset(0),
@@ -3066,7 +3069,7 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 				      sizeof(struct btrfs_key_ptr));
 
 	tree_mod_log_eb_copy(root->fs_info, dst, src, 0,
-			     src_nritems - push_items, push_items);
+			     src_nritems - push_items, push_items, 1);
 	copy_extent_buffer(dst, src,
 			   btrfs_node_key_ptr_offset(0),
 			   btrfs_node_key_ptr_offset(src_nritems - push_items),
@@ -3218,12 +3221,18 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	int mid;
 	int ret;
 	u32 c_nritems;
+	int tree_mod_log_removal = 1;
 
 	c = path->nodes[level];
 	WARN_ON(btrfs_header_generation(c) != trans->transid);
 	if (c == root->node) {
 		/* trying to split the root, lets make a new one */
 		ret = insert_new_root(trans, root, path, level + 1);
+		/*
+		 * removal of root nodes has been logged by
+		 * tree_mod_log_set_root_pointer due to locking
+		 */
+		tree_mod_log_removal = 0;
 		if (ret)
 			return ret;
 	} else {
@@ -3261,7 +3270,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 			    (unsigned long)btrfs_header_chunk_tree_uuid(split),
 			    BTRFS_UUID_SIZE);
 
-	tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid);
+	tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid,
+			     tree_mod_log_removal);
 	copy_extent_buffer(split, c,
 			   btrfs_node_key_ptr_offset(0),
 			   btrfs_node_key_ptr_offset(mid),
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7d84651e850..6d19a0a554a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1291,6 +1291,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 				      0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
+		leaf = NULL;
 		goto fail;
 	}
 
@@ -1334,11 +1335,16 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 
 	btrfs_tree_unlock(leaf);
 
+	return root;
+
 fail:
-	if (ret)
-		return ERR_PTR(ret);
+	if (leaf) {
+		btrfs_tree_unlock(leaf);
+		free_extent_buffer(leaf);
+	}
+	kfree(root);
 
-	return root;
+	return ERR_PTR(ret);
 }
 
 static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
@@ -3253,7 +3259,7 @@ void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
 	if (btrfs_root_refs(&root->root_item) == 0)
 		synchronize_srcu(&fs_info->subvol_srcu);
 
-	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
 		btrfs_free_log(NULL, root);
 		btrfs_free_log_root_tree(NULL, fs_info);
 	}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9ac2eca681e..3d551231cab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -257,7 +257,8 @@ static int exclude_super_stripes(struct btrfs_root *root,
 		cache->bytes_super += stripe_len;
 		ret = add_excluded_extent(root, cache->key.objectid,
 					  stripe_len);
-		BUG_ON(ret); /* -ENOMEM */
+		if (ret)
+			return ret;
 	}
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
@@ -265,13 +266,17 @@ static int exclude_super_stripes(struct btrfs_root *root,
 		ret = btrfs_rmap_block(&root->fs_info->mapping_tree,
 				       cache->key.objectid, bytenr,
 				       0, &logical, &nr, &stripe_len);
-		BUG_ON(ret); /* -ENOMEM */
+		if (ret)
+			return ret;
 
 		while (nr--) {
 			cache->bytes_super += stripe_len;
 			ret = add_excluded_extent(root, logical[nr],
 						  stripe_len);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret) {
+				kfree(logical);
+				return ret;
+			}
 		}
 
 		kfree(logical);
@@ -4438,7 +4443,7 @@ 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 +
@@ -4793,14 +4798,49 @@ out_fail:
 	 * 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);
@@ -7947,7 +7987,17 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 		 * info has super bytes accounted for, otherwise we'll think
 		 * we have more space than we actually do.
 		 */
-		exclude_super_stripes(root, cache);
+		ret = exclude_super_stripes(root, cache);
+		if (ret) {
+			/*
+			 * We may have excluded something, so call this just in
+			 * case.
+			 */
+			free_excluded_extents(root, cache);
+			kfree(cache->free_space_ctl);
+			kfree(cache);
+			goto error;
+		}
 
 		/*
 		 * check for two cases, either we are full, and therefore
@@ -8089,7 +8139,17 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
-	exclude_super_stripes(root, cache);
+	ret = exclude_super_stripes(root, cache);
+	if (ret) {
+		/*
+		 * We may have excluded something, so call this just in
+		 * case.
+		 */
+		free_excluded_extents(root, cache);
+		kfree(cache->free_space_ctl);
+		kfree(cache);
+		return ret;
+	}
 
 	add_new_free_space(cache, root->fs_info, chunk_offset,
 			   chunk_offset + size);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f173c5af646..cdee391fc7b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1257,6 +1257,39 @@ 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 6068a198556..258c9215685 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -325,6 +325,8 @@ 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/file-item.c b/fs/btrfs/file-item.c
index ec160202be3..c4628a201cb 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -118,9 +118,11 @@ struct btrfs_csum_item *btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 		csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]);
 		csums_in_item /= csum_size;
 
-		if (csum_offset >= csums_in_item) {
+		if (csum_offset == csums_in_item) {
 			ret = -EFBIG;
 			goto fail;
+		} else if (csum_offset > csums_in_item) {
+			goto fail;
 		}
 	}
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
@@ -728,7 +730,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 		return -ENOMEM;
 
 	sector_sum = sums->sums;
-	trans->adding_csums = 1;
 again:
 	next_offset = (u64)-1;
 	found_next = 0;
@@ -899,7 +900,6 @@ next_sector:
 		goto again;
 	}
 out:
-	trans->adding_csums = 0;
 	btrfs_free_path(path);
 	return ret;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 5b4ea5f55b8..ade03e6f7bd 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2142,6 +2142,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 cur_offset;
 	u64 last_byte;
 	u64 alloc_start;
@@ -2169,6 +2170,11 @@ static long btrfs_fallocate(struct file *file, int mode,
 	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
 	if (ret)
 		return ret;
+	if (root->fs_info->quota_enabled) {
+		ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start);
+		if (ret)
+			goto out_reserve_fail;
+	}
 
 	/*
 	 * wait for ordered IO before we have any locks.  We'll loop again
@@ -2272,6 +2278,9 @@ static long btrfs_fallocate(struct file *file, int mode,
 			     &cached_state, GFP_NOFS);
 out:
 	mutex_unlock(&inode->i_mutex);
+	if (root->fs_info->quota_enabled)
+		btrfs_qgroup_free(root, alloc_end - alloc_start);
+out_reserve_fail:
 	/* Let go of our reservation. */
 	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
 	return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ca1b767d51f..09c58a35b42 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -353,6 +353,7 @@ 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 &&
@@ -415,6 +416,17 @@ 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,
@@ -554,6 +566,8 @@ 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;
@@ -1743,8 +1757,10 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 	struct btrfs_ordered_sum *sum;
 
 	list_for_each_entry(sum, list, list) {
+		trans->adding_csums = 1;
 		btrfs_csum_file_blocks(trans,
 		       BTRFS_I(inode)->root->fs_info->csum_root, sum);
+		trans->adding_csums = 0;
 	}
 	return 0;
 }
@@ -3679,11 +3695,9 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir,
 	 * 1 for the dir item
 	 * 1 for the dir index
 	 * 1 for the inode ref
-	 * 1 for the inode ref in the tree log
-	 * 2 for the dir entries in the log
 	 * 1 for the inode
 	 */
-	trans = btrfs_start_transaction(root, 8);
+	trans = btrfs_start_transaction(root, 5);
 	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
 		return trans;
 
@@ -8127,7 +8141,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * inodes.  So 5 * 2 is 10, plus 1 for the new link, so 11 total items
 	 * should cover the worst case number of items we'll modify.
 	 */
-	trans = btrfs_start_transaction(root, 20);
+	trans = btrfs_start_transaction(root, 11);
 	if (IS_ERR(trans)) {
                 ret = PTR_ERR(trans);
                 goto out_notrans;
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index dc08d77b717..005c45db699 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -557,6 +557,7 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
 	INIT_LIST_HEAD(&splice);
 	INIT_LIST_HEAD(&works);
 
+	mutex_lock(&root->fs_info->ordered_operations_mutex);
 	spin_lock(&root->fs_info->ordered_extent_lock);
 	list_splice_init(&root->fs_info->ordered_extents, &splice);
 	while (!list_empty(&splice)) {
@@ -600,6 +601,7 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
 
 		cond_resched();
 	}
+	mutex_unlock(&root->fs_info->ordered_operations_mutex);
 }
 
 /*
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5471e47d655..b44124dd237 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1153,7 +1153,7 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_find_all_roots(trans, fs_info, node->bytenr,
 				   sgn > 0 ? node->seq - 1 : node->seq, &roots);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
@@ -1275,7 +1275,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
 	ret = 0;
 unlock:
 	spin_unlock(&fs_info->qgroup_lock);
-out:
 	ulist_free(roots);
 	ulist_free(tmp);
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 53c3501fa4c..85e072b956d 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -542,7 +542,6 @@ 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 (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
@@ -558,7 +557,9 @@ 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;
 		swarn.dev = dev;
 		iterate_extent_inodes(fs_info, found_key.objectid,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index f7a8b861058..c85e7c6b459 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3945,12 +3945,10 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 		    found_key.type != key.type) {
 			key.offset += right_len;
 			break;
-		} else {
-			if (found_key.offset != key.offset + right_len) {
-				/* Should really not happen */
-				ret = -EIO;
-				goto out;
-			}
+		}
+		if (found_key.offset != key.offset + right_len) {
+			ret = 0;
+			goto out;
 		}
 		key = found_key;
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5989a92236f..2854c824ab6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4935,7 +4935,18 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 	em = lookup_extent_mapping(em_tree, chunk_start, 1);
 	read_unlock(&em_tree->lock);
 
-	BUG_ON(!em || em->start != chunk_start);
+	if (!em) {
+		printk(KERN_ERR "btrfs: couldn't find em for chunk %Lu\n",
+		       chunk_start);
+		return -EIO;
+	}
+
+	if (em->start != chunk_start) {
+		printk(KERN_ERR "btrfs: bad chunk start, em=%Lu, wanted=%Lu\n",
+		       em->start, chunk_start);
+		free_extent_map(em);
+		return -EIO;
+	}
 	map = (struct map_lookup *)em->bdev;
 
 	length = em->len;
diff --git a/fs/dcache.c b/fs/dcache.c
index fbfae008ba4..e8bc3420d63 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2542,7 +2542,6 @@ static int prepend_path(const struct path *path,
 	bool slash = false;
 	int error = 0;
 
-	br_read_lock(&vfsmount_lock);
 	while (dentry != root->dentry || vfsmnt != root->mnt) {
 		struct dentry * parent;
 
@@ -2572,8 +2571,6 @@ static int prepend_path(const struct path *path,
 	if (!error && !slash)
 		error = prepend(buffer, buflen, "/", 1);
 
-out:
-	br_read_unlock(&vfsmount_lock);
 	return error;
 
 global_root:
@@ -2590,7 +2587,7 @@ global_root:
 		error = prepend(buffer, buflen, "/", 1);
 	if (!error)
 		error = is_mounted(vfsmnt) ? 1 : 2;
-	goto out;
+	return error;
 }
 
 /**
@@ -2617,9 +2614,11 @@ char *__d_path(const struct path *path,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	error = prepend_path(path, root, &res, &buflen);
 	write_sequnlock(&rename_lock);
+	br_read_unlock(&vfsmount_lock);
 
 	if (error < 0)
 		return ERR_PTR(error);
@@ -2636,9 +2635,11 @@ char *d_absolute_path(const struct path *path,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	error = prepend_path(path, &root, &res, &buflen);
 	write_sequnlock(&rename_lock);
+	br_read_unlock(&vfsmount_lock);
 
 	if (error > 1)
 		error = -EINVAL;
@@ -2702,11 +2703,13 @@ char *d_path(const struct path *path, char *buf, int buflen)
 		return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
 	get_fs_root(current->fs, &root);
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	error = path_with_deleted(path, &root, &res, &buflen);
+	write_sequnlock(&rename_lock);
+	br_read_unlock(&vfsmount_lock);
 	if (error < 0)
 		res = ERR_PTR(error);
-	write_sequnlock(&rename_lock);
 	path_put(&root);
 	return res;
 }
@@ -2830,6 +2833,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 	get_fs_root_and_pwd(current->fs, &root, &pwd);
 
 	error = -ENOENT;
+	br_read_lock(&vfsmount_lock);
 	write_seqlock(&rename_lock);
 	if (!d_unlinked(pwd.dentry)) {
 		unsigned long len;
@@ -2839,6 +2843,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 		prepend(&cwd, &buflen, "\0", 1);
 		error = prepend_path(&pwd, &root, &cwd, &buflen);
 		write_sequnlock(&rename_lock);
+		br_read_unlock(&vfsmount_lock);
 
 		if (error < 0)
 			goto out;
@@ -2859,6 +2864,7 @@ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
 		}
 	} else {
 		write_sequnlock(&rename_lock);
+		br_read_unlock(&vfsmount_lock);
 	}
 
 out:
diff --git a/fs/internal.h b/fs/internal.h
index 507141fceb9..4be78237d89 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,3 +125,8 @@ extern int invalidate_inodes(struct super_block *, bool);
  * dcache.c
  */
 extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
+
+/*
+ * read_write.c
+ */
+extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
diff --git a/fs/namespace.c b/fs/namespace.c
index 50ca17d3cb4..d581e45c0a9 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -798,6 +798,10 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	}
 
 	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	/* Don't allow unprivileged users to change mount flags */
+	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
+		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_sb = sb;
 	mnt->mnt.mnt_root = dget(root);
@@ -1713,6 +1717,9 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 	if (readonly_request == __mnt_is_readonly(mnt))
 		return 0;
 
+	if (mnt->mnt_flags & MNT_LOCK_READONLY)
+		return -EPERM;
+
 	if (readonly_request)
 		error = mnt_make_readonly(real_mount(mnt));
 	else
@@ -2339,7 +2346,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	/* First pass: copy the tree topology */
 	copy_flags = CL_COPY_ALL | CL_EXPIRE;
 	if (user_ns != mnt_ns->user_ns)
-		copy_flags |= CL_SHARED_TO_SLAVE;
+		copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED;
 	new = copy_tree(old, old->mnt.mnt_root, copy_flags);
 	if (IS_ERR(new)) {
 		up_write(&namespace_sem);
@@ -2732,6 +2739,51 @@ bool our_mnt(struct vfsmount *mnt)
 	return check_mnt(real_mount(mnt));
 }
 
+bool current_chrooted(void)
+{
+	/* Does the current process have a non-standard root */
+	struct path ns_root;
+	struct path fs_root;
+	bool chrooted;
+
+	/* Find the namespace root */
+	ns_root.mnt = &current->nsproxy->mnt_ns->root->mnt;
+	ns_root.dentry = ns_root.mnt->mnt_root;
+	path_get(&ns_root);
+	while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root))
+		;
+
+	get_fs_root(current->fs, &fs_root);
+
+	chrooted = !path_equal(&fs_root, &ns_root);
+
+	path_put(&fs_root);
+	path_put(&ns_root);
+
+	return chrooted;
+}
+
+void update_mnt_policy(struct user_namespace *userns)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mount *mnt;
+
+	down_read(&namespace_sem);
+	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		switch (mnt->mnt.mnt_sb->s_magic) {
+		case SYSFS_MAGIC:
+			userns->may_mount_sysfs = true;
+			break;
+		case PROC_SUPER_MAGIC:
+			userns->may_mount_proc = true;
+			break;
+		}
+		if (userns->may_mount_sysfs && userns->may_mount_proc)
+			break;
+	}
+	up_read(&namespace_sem);
+}
+
 static void *mntns_get(struct task_struct *task)
 {
 	struct mnt_namespace *ns = NULL;
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index 737d839bc17..6fc7b5cae92 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/idmap.c b/fs/nfs/idmap.c
index dc0f98dfa71..c516da5873f 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -726,9 +726,9 @@ out1:
 	return ret;
 }
 
-static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data)
+static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data, size_t datalen)
 {
-	return key_instantiate_and_link(key, data, strlen(data) + 1,
+	return key_instantiate_and_link(key, data, datalen,
 					id_resolver_cache->thread_keyring,
 					authkey);
 }
@@ -738,6 +738,7 @@ static int nfs_idmap_read_and_verify_message(struct idmap_msg *im,
 		struct key *key, struct key *authkey)
 {
 	char id_str[NFS_UINT_MAXLEN];
+	size_t len;
 	int ret = -ENOKEY;
 
 	/* ret = -ENOKEY */
@@ -747,13 +748,15 @@ static int nfs_idmap_read_and_verify_message(struct idmap_msg *im,
 	case IDMAP_CONV_NAMETOID:
 		if (strcmp(upcall->im_name, im->im_name) != 0)
 			break;
-		sprintf(id_str, "%d", im->im_id);
-		ret = nfs_idmap_instantiate(key, authkey, id_str);
+		/* Note: here we store the NUL terminator too */
+		len = sprintf(id_str, "%d", im->im_id) + 1;
+		ret = nfs_idmap_instantiate(key, authkey, id_str, len);
 		break;
 	case IDMAP_CONV_IDTONAME:
 		if (upcall->im_id != im->im_id)
 			break;
-		ret = nfs_idmap_instantiate(key, authkey, im->im_name);
+		len = strlen(im->im_name);
+		ret = nfs_idmap_instantiate(key, authkey, im->im_name, len);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 49eeb044c10..4fb234d3aef 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -129,7 +129,6 @@ static void filelayout_fenceme(struct inode *inode, struct pnfs_layout_hdr *lo)
 {
 	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
 		return;
-	clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
 	pnfs_return_layout(inode);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b2671cb0f90..26431cf62dd 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2632,7 +2632,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	int status;
 
 	if (pnfs_ld_layoutret_on_setattr(inode))
-		pnfs_return_layout(inode);
+		pnfs_commit_and_return_layout(inode);
 
 	nfs_fattr_init(fattr);
 	
@@ -6416,22 +6416,8 @@ nfs4_layoutcommit_done(struct rpc_task *task, void *calldata)
 static void nfs4_layoutcommit_release(void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
-	struct pnfs_layout_segment *lseg, *tmp;
-	unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
 
 	pnfs_cleanup_layoutcommit(data);
-	/* Matched by references in pnfs_set_layoutcommit */
-	list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
-		list_del_init(&lseg->pls_lc_list);
-		if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
-				       &lseg->pls_flags))
-			pnfs_put_lseg(lseg);
-	}
-
-	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
-	smp_mb__after_clear_bit();
-	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
-
 	put_rpccred(data->cred);
 	kfree(data);
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 48ac5aad625..4bdffe0ba02 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -417,6 +417,16 @@ should_free_lseg(struct pnfs_layout_range *lseg_range,
 	       lo_seg_intersecting(lseg_range, recall_range);
 }
 
+static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
+		struct list_head *tmp_list)
+{
+	if (!atomic_dec_and_test(&lseg->pls_refcount))
+		return false;
+	pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
+	list_add(&lseg->pls_list, tmp_list);
+	return true;
+}
+
 /* Returns 1 if lseg is removed from list, 0 otherwise */
 static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 			     struct list_head *tmp_list)
@@ -430,11 +440,8 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 		 */
 		dprintk("%s: lseg %p ref %d\n", __func__, lseg,
 			atomic_read(&lseg->pls_refcount));
-		if (atomic_dec_and_test(&lseg->pls_refcount)) {
-			pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
-			list_add(&lseg->pls_list, tmp_list);
+		if (pnfs_lseg_dec_and_remove_zero(lseg, tmp_list))
 			rv = 1;
-		}
 	}
 	return rv;
 }
@@ -777,6 +784,21 @@ send_layoutget(struct pnfs_layout_hdr *lo,
 	return lseg;
 }
 
+static void pnfs_clear_layoutcommit(struct inode *inode,
+		struct list_head *head)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct pnfs_layout_segment *lseg, *tmp;
+
+	if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+		return;
+	list_for_each_entry_safe(lseg, tmp, &nfsi->layout->plh_segs, pls_list) {
+		if (!test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+			continue;
+		pnfs_lseg_dec_and_remove_zero(lseg, head);
+	}
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.
@@ -808,6 +830,7 @@ _pnfs_return_layout(struct inode *ino)
 	/* Reference matched in nfs4_layoutreturn_release */
 	pnfs_get_layout_hdr(lo);
 	empty = list_empty(&lo->plh_segs);
+	pnfs_clear_layoutcommit(ino, &tmp_list);
 	pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
@@ -820,8 +843,6 @@ _pnfs_return_layout(struct inode *ino)
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
-	WARN_ON(test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags));
-
 	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
 	if (unlikely(lrp == NULL)) {
 		status = -ENOMEM;
@@ -845,6 +866,33 @@ out:
 }
 EXPORT_SYMBOL_GPL(_pnfs_return_layout);
 
+int
+pnfs_commit_and_return_layout(struct inode *inode)
+{
+	struct pnfs_layout_hdr *lo;
+	int ret;
+
+	spin_lock(&inode->i_lock);
+	lo = NFS_I(inode)->layout;
+	if (lo == NULL) {
+		spin_unlock(&inode->i_lock);
+		return 0;
+	}
+	pnfs_get_layout_hdr(lo);
+	/* Block new layoutgets and read/write to ds */
+	lo->plh_block_lgets++;
+	spin_unlock(&inode->i_lock);
+	filemap_fdatawait(inode->i_mapping);
+	ret = pnfs_layoutcommit_inode(inode, true);
+	if (ret == 0)
+		ret = _pnfs_return_layout(inode);
+	spin_lock(&inode->i_lock);
+	lo->plh_block_lgets--;
+	spin_unlock(&inode->i_lock);
+	pnfs_put_layout_hdr(lo);
+	return ret;
+}
+
 bool pnfs_roc(struct inode *ino)
 {
 	struct pnfs_layout_hdr *lo;
@@ -1458,7 +1506,6 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
 	dprintk("pnfs write error = %d\n", hdr->pnfs_error);
 	if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
 	    PNFS_LAYOUTRET_ON_ERROR) {
-		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
 		pnfs_return_layout(hdr->inode);
 	}
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
@@ -1613,7 +1660,6 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
 	dprintk("pnfs read error = %d\n", hdr->pnfs_error);
 	if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
 	    PNFS_LAYOUTRET_ON_ERROR) {
-		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
 		pnfs_return_layout(hdr->inode);
 	}
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
@@ -1746,11 +1792,27 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 
 	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
 		if (lseg->pls_range.iomode == IOMODE_RW &&
-		    test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+		    test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
 			list_add(&lseg->pls_lc_list, listp);
 	}
 }
 
+static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp)
+{
+	struct pnfs_layout_segment *lseg, *tmp;
+	unsigned long *bitlock = &NFS_I(inode)->flags;
+
+	/* Matched by references in pnfs_set_layoutcommit */
+	list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) {
+		list_del_init(&lseg->pls_lc_list);
+		pnfs_put_lseg(lseg);
+	}
+
+	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+	smp_mb__after_clear_bit();
+	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+}
+
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
 {
 	pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode);
@@ -1795,6 +1857,7 @@ void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
 
 	if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
 		nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
+	pnfs_list_write_lseg_done(data->args.inode, &data->lseg_list);
 }
 
 /*
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 94ba8041774..f5f8a470a64 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -219,6 +219,7 @@ void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
+int pnfs_commit_and_return_layout(struct inode *);
 void pnfs_ld_write_done(struct nfs_write_data *);
 void pnfs_ld_read_done(struct nfs_read_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
@@ -407,6 +408,11 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
+static inline int pnfs_commit_and_return_layout(struct inode *inode)
+{
+	return 0;
+}
+
 static inline bool
 pnfs_ld_layoutret_on_setattr(struct inode *inode)
 {
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 62c1ee128ae..ca05f6dc354 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -102,7 +102,8 @@ nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
 {
 	if (rp->c_type == RC_REPLBUFF)
 		kfree(rp->c_replvec.iov_base);
-	hlist_del(&rp->c_hash);
+	if (!hlist_unhashed(&rp->c_hash))
+		hlist_del(&rp->c_hash);
 	list_del(&rp->c_lru);
 	--num_drc_entries;
 	kmem_cache_free(drc_slab, rp);
@@ -118,6 +119,10 @@ nfsd_reply_cache_free(struct svc_cacherep *rp)
 
 int nfsd_reply_cache_init(void)
 {
+	INIT_LIST_HEAD(&lru_head);
+	max_drc_entries = nfsd_cache_size_limit();
+	num_drc_entries = 0;
+
 	register_shrinker(&nfsd_reply_cache_shrinker);
 	drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
 					0, 0, NULL);
@@ -128,10 +133,6 @@ int nfsd_reply_cache_init(void)
 	if (!cache_hash)
 		goto out_nomem;
 
-	INIT_LIST_HEAD(&lru_head);
-	max_drc_entries = nfsd_cache_size_limit();
-	num_drc_entries = 0;
-
 	return 0;
 out_nomem:
 	printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2a7eb536de0..2b2e2396a86 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1013,6 +1013,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	int			host_err;
 	int			stable = *stablep;
 	int			use_wgather;
+	loff_t			pos = offset;
 
 	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
@@ -1025,7 +1026,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 
 	/* Write the data. */
 	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
+	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
 	set_fs(oldfs);
 	if (host_err < 0)
 		goto out_nfserr;
diff --git a/fs/pnode.c b/fs/pnode.c
index 3e000a51ac0..8b29d2164da 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -9,6 +9,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/mount.h>
 #include <linux/fs.h>
+#include <linux/nsproxy.h>
 #include "internal.h"
 #include "pnode.h"
 
@@ -220,6 +221,7 @@ static struct mount *get_source(struct mount *dest,
 int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry,
 		    struct mount *source_mnt, struct list_head *tree_list)
 {
+	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	struct mount *m, *child;
 	int ret = 0;
 	struct mount *prev_dest_mnt = dest_mnt;
@@ -237,6 +239,10 @@ int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry,
 
 		source =  get_source(m, prev_dest_mnt, prev_src_mnt, &type);
 
+		/* Notice when we are propagating across user namespaces */
+		if (m->mnt_ns->user_ns != user_ns)
+			type |= CL_UNPRIVILEGED;
+
 		child = copy_tree(source, source->mnt.mnt_root, type);
 		if (IS_ERR(child)) {
 			ret = PTR_ERR(child);
diff --git a/fs/pnode.h b/fs/pnode.h
index 19b853a3445..a0493d5ebfb 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -23,6 +23,7 @@
 #define CL_MAKE_SHARED 		0x08
 #define CL_PRIVATE 		0x10
 #define CL_SHARED_TO_SLAVE	0x20
+#define CL_UNPRIVILEGED		0x40
 
 static inline void set_mnt_shared(struct mount *mnt)
 {
diff --git a/fs/proc/root.c b/fs/proc/root.c
index c6e9fac26ba..9c7fab1d23f 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
+#include <linux/user_namespace.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
@@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	} else {
 		ns = task_active_pid_ns(current);
 		options = data;
+
+		if (!current_user_ns()->may_mount_proc)
+			return ERR_PTR(-EPERM);
 	}
 
 	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
diff --git a/fs/read_write.c b/fs/read_write.c
index a698eff457f..e6ddc8dceb9 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -17,6 +17,7 @@
 #include <linux/splice.h>
 #include <linux/compat.h>
 #include "read_write.h"
+#include "internal.h"
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -417,6 +418,33 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 
 EXPORT_SYMBOL(do_sync_write);
 
+ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
+{
+	mm_segment_t old_fs;
+	const char __user *p;
+	ssize_t ret;
+
+	if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	p = (__force const char __user *)buf;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	if (file->f_op->write)
+		ret = file->f_op->write(file, p, count, pos);
+	else
+		ret = do_sync_write(file, p, count, pos);
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_modify(file);
+		add_wchar(current, ret);
+	}
+	inc_syscw(current);
+	return ret;
+}
+
 ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
 {
 	ssize_t ret;
diff --git a/fs/splice.c b/fs/splice.c
index 718bd005638..29e394e49dd 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -31,6 +31,7 @@
 #include <linux/security.h>
 #include <linux/gfp.h>
 #include <linux/socket.h>
+#include "internal.h"
 
 /*
  * Attempt to steal a page from a pipe buffer. This should perhaps go into
@@ -1048,9 +1049,10 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 {
 	int ret;
 	void *data;
+	loff_t tmp = sd->pos;
 
 	data = buf->ops->map(pipe, buf, 0);
-	ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
 	buf->ops->unmap(pipe, buf, data);
 
 	return ret;
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 7f968ede20d..c6f54abe985 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -1007,6 +1007,8 @@ 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)
@@ -1015,6 +1017,8 @@ 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);
 	for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
@@ -1045,10 +1049,21 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 	return 0;
 }
 
+static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file_inode(file);
+	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/sysfs/mount.c b/fs/sysfs/mount.c
index 8d924b5ec73..afd83273e6c 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/user_namespace.h>
 
 #include "sysfs.h"
 
@@ -111,6 +112,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	struct super_block *sb;
 	int error;
 
+	if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
+		return ERR_PTR(-EPERM);
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);