Merge tag 'v4.9.137' into v4.9-rt

This is the 4.9.137 stable release

18 files changed, 139 insertions, 48 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6661116c47d9..163b61a92b59 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8263,6 +8263,19 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	if (IS_ERR(buf))
 		return buf;
 
+	/*
+	 * Extra safety check in case the extent tree is corrupted and extent
+	 * allocator chooses to use a tree block which is already used and
+	 * locked.
+	 */
+	if (buf->lock_owner == current->pid) {
+		btrfs_err_rl(root->fs_info,
+"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected",
+			buf->start, btrfs_header_owner(buf), current->pid);
+		free_extent_buffer(buf);
+		return ERR_PTR(-EUCLEAN);
+	}
+
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
@@ -9100,15 +9113,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 	if (eb == root->node) {
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = eb->start;
-		else
-			BUG_ON(root->root_key.objectid !=
-			       btrfs_header_owner(eb));
+		else if (root->root_key.objectid != btrfs_header_owner(eb))
+			goto owner_mismatch;
 	} else {
 		if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = path->nodes[level + 1]->start;
-		else
-			BUG_ON(root->root_key.objectid !=
-			       btrfs_header_owner(path->nodes[level + 1]));
+		else if (root->root_key.objectid !=
+			 btrfs_header_owner(path->nodes[level + 1]))
+			goto owner_mismatch;
 	}
 
 	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
@@ -9116,6 +9128,11 @@ out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;
 	return 0;
+
+owner_mismatch:
+	btrfs_err_rl(root->fs_info, "unexpected tree owner, have %llu expect %llu",
+		     btrfs_header_owner(eb), root->root_key.objectid);
+	return -EUCLEAN;
 }
 
 static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
@@ -9169,6 +9186,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
 			ret = walk_up_proc(trans, root, path, wc);
 			if (ret > 0)
 				return 0;
+			if (ret < 0)
+				return ret;
 
 			if (path->locks[level]) {
 				btrfs_tree_unlock_rw(path->nodes[level],
@@ -9933,6 +9952,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 
 		block_group = btrfs_lookup_first_block_group(info, last);
 		while (block_group) {
+			wait_block_group_cache_done(block_group);
 			spin_lock(&block_group->lock);
 			if (block_group->iref)
 				break;
@@ -10332,7 +10352,7 @@ error:
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *root)
 {
-	struct btrfs_block_group_cache *block_group, *tmp;
+	struct btrfs_block_group_cache *block_group;
 	struct btrfs_root *extent_root = root->fs_info->extent_root;
 	struct btrfs_block_group_item item;
 	struct btrfs_key key;
@@ -10340,7 +10360,10 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 	bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
 
 	trans->can_flush_pending_bgs = false;
-	list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+	while (!list_empty(&trans->new_bgs)) {
+		block_group = list_first_entry(&trans->new_bgs,
+					       struct btrfs_block_group_cache,
+					       bg_list);
 		if (ret)
 			goto next;
 
@@ -11052,6 +11075,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 
 	*trimmed = 0;
 
+	/* Discard not supported = nothing to do. */
+	if (!blk_queue_discard(bdev_get_queue(device->bdev)))
+		return 0;
+
 	/* Not writeable = nothing to do. */
 	if (!device->writeable)
 		return 0;
@@ -11174,8 +11201,8 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
 	}
 
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
-	devices = &root->fs_info->fs_devices->alloc_list;
-	list_for_each_entry(device, devices, dev_alloc_list) {
+	devices = &root->fs_info->fs_devices->devices;
+	list_for_each_entry(device, devices, dev_list) {
 		ret = btrfs_trim_free_extents(device, range->minlen,
 					      &group_trimmed);
 		if (ret)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index c56253a1e5b4..5ca0dbb9074d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1693,6 +1693,8 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 	bitmap_clear(info->bitmap, start, count);
 
 	info->bytes -= bytes;
+	if (info->max_extent_size > ctl->unit)
+		info->max_extent_size = 0;
 }
 
 static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
@@ -1776,6 +1778,13 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl,
 	return -1;
 }
 
+static inline u64 get_max_extent_size(struct btrfs_free_space *entry)
+{
+	if (entry->bitmap)
+		return entry->max_extent_size;
+	return entry->bytes;
+}
+
 /* Cache the size of the max extent in bytes */
 static struct btrfs_free_space *
 find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
@@ -1797,8 +1806,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
 	for (node = &entry->offset_index; node; node = rb_next(node)) {
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 		if (entry->bytes < *bytes) {
-			if (entry->bytes > *max_extent_size)
-				*max_extent_size = entry->bytes;
+			*max_extent_size = max(get_max_extent_size(entry),
+					       *max_extent_size);
 			continue;
 		}
 
@@ -1816,8 +1825,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
 		}
 
 		if (entry->bytes < *bytes + align_off) {
-			if (entry->bytes > *max_extent_size)
-				*max_extent_size = entry->bytes;
+			*max_extent_size = max(get_max_extent_size(entry),
+					       *max_extent_size);
 			continue;
 		}
 
@@ -1829,8 +1838,10 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
 				*offset = tmp;
 				*bytes = size;
 				return entry;
-			} else if (size > *max_extent_size) {
-				*max_extent_size = size;
+			} else {
+				*max_extent_size =
+					max(get_max_extent_size(entry),
+					    *max_extent_size);
 			}
 			continue;
 		}
@@ -2689,8 +2700,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 
 	err = search_bitmap(ctl, entry, &search_start, &search_bytes, true);
 	if (err) {
-		if (search_bytes > *max_extent_size)
-			*max_extent_size = search_bytes;
+		*max_extent_size = max(get_max_extent_size(entry),
+				       *max_extent_size);
 		return 0;
 	}
 
@@ -2727,8 +2738,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 
 	entry = rb_entry(node, struct btrfs_free_space, offset_index);
 	while (1) {
-		if (entry->bytes < bytes && entry->bytes > *max_extent_size)
-			*max_extent_size = entry->bytes;
+		if (entry->bytes < bytes)
+			*max_extent_size = max(get_max_extent_size(entry),
+					       *max_extent_size);
 
 		if (entry->bytes < bytes ||
 		    (!entry->bitmap && entry->offset < min_start)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5ebdb58079e1..17e143d91fa9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -489,6 +489,7 @@ again:
 		pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 		if (!pages) {
 			/* just bail out to the uncompressed code */
+			nr_pages = 0;
 			goto cont;
 		}
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 9afad8c14220..f25233093d68 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2498,6 +2498,7 @@ qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info)
 		qgroup->rfer_cmpr = 0;
 		qgroup->excl = 0;
 		qgroup->excl_cmpr = 0;
+		qgroup_dirty(fs_info, qgroup);
 	}
 	spin_unlock(&fs_info->qgroup_lock);
 }
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 9140aede5869..b0c3a6afe664 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1325,7 +1325,7 @@ static void __del_reloc_root(struct btrfs_root *root)
 	struct mapping_node *node = NULL;
 	struct reloc_control *rc = root->fs_info->reloc_ctl;
 
-	if (rc) {
+	if (rc && root->node) {
 		spin_lock(&rc->reloc_root_tree.lock);
 		rb_node = tree_search(&rc->reloc_root_tree.rb_root,
 				      root->node->start);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 44966fd00790..47d11a30bee7 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3016,9 +3016,12 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 	};
 
 	ret = walk_log_tree(trans, log, &wc);
-	/* I don't think this can happen but just in case */
-	if (ret)
-		btrfs_abort_transaction(trans, ret);
+	if (ret) {
+		if (trans)
+			btrfs_abort_transaction(trans, ret);
+		else
+			btrfs_handle_fs_error(log->fs_info, ret, NULL);
+	}
 
 	while (1) {
 		ret = find_first_extent_bit(&log->dirty_log_pages,
@@ -5370,9 +5373,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 
 			dir_inode = btrfs_iget(root->fs_info->sb, &inode_key,
 					       root, NULL);
-			/* If parent inode was deleted, skip it. */
-			if (IS_ERR(dir_inode))
-				continue;
+			/*
+			 * If the parent inode was deleted, return an error to
+			 * fallback to a transaction commit. This is to prevent
+			 * getting an inode that was moved from one parent A to
+			 * a parent B, got its former parent A deleted and then
+			 * it got fsync'ed, from existing at both parents after
+			 * a log replay (and the old parent still existing).
+			 * Example:
+			 *
+			 * mkdir /mnt/A
+			 * mkdir /mnt/B
+			 * touch /mnt/B/bar
+			 * sync
+			 * mv /mnt/B/bar /mnt/A/bar
+			 * mv -T /mnt/A /mnt/B
+			 * fsync /mnt/B/bar
+			 * <power fail>
+			 *
+			 * If we ignore the old parent B which got deleted,
+			 * after a log replay we would have file bar linked
+			 * at both parents and the old parent B would still
+			 * exist.
+			 */
+			if (IS_ERR(dir_inode)) {
+				ret = PTR_ERR(dir_inode);
+				goto out;
+			}
 
 			if (ctx)
 				ctx->log_new_dentries = false;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index e06468f8e041..98fc77dd7b45 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -284,6 +284,9 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
 #endif /* CONFIG_CIFS_STATS2 */
+		atomic_set(&tcpSesReconnectCount, 0);
+		atomic_set(&tconInfoReconnectCount, 0);
+
 		spin_lock(&GlobalMid_Lock);
 		GlobalMaxActiveXid = 0;
 		GlobalCurrentXid = 0;
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index b611fc2e8984..7f01c6e60791 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -147,8 +147,10 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo)
 		sprintf(dp, ";sec=krb5");
 	else if (server->sec_mskerberos)
 		sprintf(dp, ";sec=mskrb5");
-	else
-		goto out;
+	else {
+		cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n");
+		sprintf(dp, ";sec=krb5");
+	}
 
 	dp = description + strlen(description);
 	sprintf(dp, ";uid=0x%x",
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 77a18fe10805..57c938ffeb6e 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -768,7 +768,15 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 	} else if (rc == -EREMOTE) {
 		cifs_create_dfs_fattr(&fattr, sb);
 		rc = 0;
-	} else if (rc == -EACCES && backup_cred(cifs_sb)) {
+	} else if ((rc == -EACCES) && backup_cred(cifs_sb) &&
+		   (strcmp(server->vals->version_string, SMB1_VERSION_STRING)
+		      == 0)) {
+			/*
+			 * For SMB2 and later the backup intent flag is already
+			 * sent if needed on open and there is no path based
+			 * FindFirst operation to use to retry with
+			 */
+
 			srchinf = kzalloc(sizeof(struct cifs_search_info),
 						GFP_KERNEL);
 			if (srchinf == NULL) {
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 7919967488cb..011c6f53dcda 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -186,7 +186,8 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 			continue;
 		blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_SHIFT;
 		blk_offset += offset;
-		if (blk_offset + len > BUFFER_SIZE)
+		if (blk_offset > BUFFER_SIZE ||
+		    blk_offset + len > BUFFER_SIZE)
 			continue;
 		return read_buffers[i] + blk_offset;
 	}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 6779a9f1de3b..d06cfe372609 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -860,7 +860,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping,
 	handle_t *handle;
 	struct page *page;
 	struct ext4_iloc iloc;
-	int retries;
+	int retries = 0;
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bf5ae8ebbc97..2880e017cd0a 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -345,7 +345,9 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 	}
 	brelse(iloc.bh);
 
-	dquot_initialize(inode);
+	err = dquot_initialize(inode);
+	if (err)
+		return err;
 
 	handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
 		EXT4_QUOTA_INIT_BLOCKS(sb) +
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 578f8c33fb44..c4434bdeeea7 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -526,9 +526,13 @@ mext_check_arguments(struct inode *orig_inode,
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
-	if (orig_eof < orig_start + *len - 1)
+	if (orig_eof <= orig_start)
+		*len = 0;
+	else if (orig_eof < orig_start + *len - 1)
 		*len = orig_eof - orig_start;
-	if (donor_eof < donor_start + *len - 1)
+	if (donor_eof <= donor_start)
+		*len = 0;
+	else if (donor_eof < donor_start + *len - 1)
 		*len = donor_eof - donor_start;
 	if (!*len) {
 		ext4_debug("ext4 move extent: len should not be 0 "
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index ff72ac6439c8..6d7f66816319 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1355,6 +1355,9 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type,
 	struct path path;
 	int error;
 
+	if (!dev_name || !*dev_name)
+		return ERR_PTR(-EINVAL);
+
 	error = kern_path(dev_name, LOOKUP_FOLLOW, &path);
 	if (error) {
 		pr_warn("path_lookup on %s returned error %d\n",
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 684996c8a3a4..4d5a5a4cc017 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -254,8 +254,8 @@ restart:
 		bh = jh2bh(jh);
 
 		if (buffer_locked(bh)) {
-			spin_unlock(&journal->j_list_lock);
 			get_bh(bh);
+			spin_unlock(&journal->j_list_lock);
 			wait_on_buffer(bh);
 			/* the journal_head may have gone by now */
 			BUFFER_TRACE(bh, "brelse");
@@ -336,8 +336,8 @@ restart2:
 		jh = transaction->t_checkpoint_io_list;
 		bh = jh2bh(jh);
 		if (buffer_locked(bh)) {
-			spin_unlock(&journal->j_list_lock);
 			get_bh(bh);
+			spin_unlock(&journal->j_list_lock);
 			wait_on_buffer(bh);
 			/* the journal_head may have gone by now */
 			BUFFER_TRACE(bh, "brelse");
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 59c019a148f6..79b0de846f21 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -285,10 +285,8 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_fs_info = c;
 
 	ret = jffs2_parse_options(c, data);
-	if (ret) {
-		kfree(c);
+	if (ret)
 		return -EINVAL;
-	}
 
 	/* Initialize JFFS2 superblock locks, the further initialization will
 	 * be done later */
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index d716c9993a26..c7eb47f2fb6c 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -340,7 +340,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp,
 	};
 	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
-	dprintk("lockd: %s(host='%*s', vers=%u, proto=%s)\n", __func__,
+	dprintk("lockd: %s(host='%.*s', vers=%u, proto=%s)\n", __func__,
 			(int)hostname_len, hostname, rqstp->rq_vers,
 			(rqstp->rq_prot == IPPROTO_UDP ? "udp" : "tcp"));
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index f6b0848cc831..43f42cc30a60 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -988,10 +988,10 @@ EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
 
 /*
  * Session has been established, and the client marked ready.
- * Set the mount rsize and wsize with negotiated fore channel
- * attributes which will be bound checked in nfs_server_set_fsinfo.
+ * Limit the mount rsize, wsize and dtsize using negotiated fore
+ * channel attributes.
  */
-static void nfs4_session_set_rwsize(struct nfs_server *server)
+static void nfs4_session_limit_rwsize(struct nfs_server *server)
 {
 #ifdef CONFIG_NFS_V4_1
 	struct nfs4_session *sess;
@@ -1004,9 +1004,11 @@ static void nfs4_session_set_rwsize(struct nfs_server *server)
 	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
 	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
 
-	if (!server->rsize || server->rsize > server_resp_sz)
+	if (server->dtsize > server_resp_sz)
+		server->dtsize = server_resp_sz;
+	if (server->rsize > server_resp_sz)
 		server->rsize = server_resp_sz;
-	if (!server->wsize || server->wsize > server_rqst_sz)
+	if (server->wsize > server_rqst_sz)
 		server->wsize = server_rqst_sz;
 #endif /* CONFIG_NFS_V4_1 */
 }
@@ -1053,12 +1055,12 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 			(unsigned long long) server->fsid.minor);
 	nfs_display_fhandle(mntfh, "Pseudo-fs root FH");
 
-	nfs4_session_set_rwsize(server);
-
 	error = nfs_probe_fsinfo(server, mntfh, fattr);
 	if (error < 0)
 		goto out;
 
+	nfs4_session_limit_rwsize(server);
+
 	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
 		server->namelen = NFS4_MAXNAMLEN;