Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "Almost all of these are bug fixes.  Dave Sterba's documentation update
  is the big exception because he removed our promises to set any
  machine running Btrfs on fire"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Documentation: filesystems: update btrfs tools section
  Documentation: filesystems: add new btrfs mount options
  btrfs: update kconfig help text
  btrfs: fix bio_size_ok() for max_sectors > 0xffff
  btrfs: Use trace condition for get_extent tracepoint
  btrfs: fix typo in the log message
  Btrfs: fix list delete warning when removing ordered root from the list
  Btrfs: print bytenr instead of page pointer in check-int
  Btrfs: remove dead codes from ctree.h
  Btrfs: don't wait for ordered data outside desired range
  Btrfs: fix lockdep error in async commit
  Btrfs: avoid heavy operations in btrfs_commit_super
  Btrfs: fix __btrfs_start_workers retval
  Btrfs: disable online raid-repair on ro mounts
  Btrfs: do not inc uncorrectable_errors counter on ro scrubs
  Btrfs: only drop modified extents if we logged the whole inode
  Btrfs: make sure to copy everything if we rename
  Btrfs: don't BUG_ON() if we get an error walking backrefs

Documentation/filesystems/btrfs.txt

@@ -70,6 +70,12 @@ Unless otherwise specified, all options default to off.
 
 	See comments at the top of fs/btrfs/check-integrity.c for more info.
 
+  commit=<seconds>
+	Set the interval of periodic commit, 30 seconds by default. Higher
+	values defer data being synced to permanent storage with obvious
+	consequences when the system crashes. The upper bound is not forced,
+	but a warning is printed if it's more than 300 seconds (5 minutes).
+
   compress
   compress=<type>
   compress-force
@@ -154,7 +160,11 @@ Unless otherwise specified, all options default to off.
 	Currently this scans a list of several previous tree roots and tries to 
 	use the first readable.
 
- skip_balance
+  rescan_uuid_tree
+	Force check and rebuild procedure of the UUID tree. This should not
+	normally be needed.
+
+  skip_balance
 	Skip automatic resume of interrupted balance operation after mount.
 	May be resumed with "btrfs balance resume."
 
@@ -234,24 +244,14 @@ available from the git repository at the following location:
 
 These include the following tools:
 
-mkfs.btrfs: create a filesystem
-
-btrfsctl: control program to create snapshots and subvolumes:
+* mkfs.btrfs: create a filesystem
 
-	mount /dev/sda2 /mnt
-	btrfsctl -s new_subvol_name /mnt
-	btrfsctl -s snapshot_of_default /mnt/default
-	btrfsctl -s snapshot_of_new_subvol /mnt/new_subvol_name
-	btrfsctl -s snapshot_of_a_snapshot /mnt/snapshot_of_new_subvol
-	ls /mnt
-	default snapshot_of_a_snapshot snapshot_of_new_subvol
-	new_subvol_name snapshot_of_default
+* btrfs: a single tool to manage the filesystems, refer to the manpage for more details
 
-	Snapshots and subvolumes cannot be deleted right now, but you can
-	rm -rf all the files and directories inside them.
+* 'btrfsck' or 'btrfs check': do a consistency check of the filesystem
 
-btrfsck: do a limited check of the FS extent trees.
+Other tools for specific tasks:
 
-btrfs-debug-tree: print all of the FS metadata in text form.  Example:
+* btrfs-convert: in-place conversion from ext2/3/4 filesystems
 
-	btrfs-debug-tree /dev/sda2 >& big_output_file
+* btrfs-image: dump filesystem metadata for debugging

fs/btrfs/Kconfig

@@ -9,12 +9,17 @@ config BTRFS_FS
 	select XOR_BLOCKS
 
 	help
-	  Btrfs is a new filesystem with extents, writable snapshotting,
-	  support for multiple devices and many more features.
+	  Btrfs is a general purpose copy-on-write filesystem with extents,
+	  writable snapshotting, support for multiple devices and many more
+	  features focused on fault tolerance, repair and easy administration.
 
-	  Btrfs is highly experimental, and THE DISK FORMAT IS NOT YET
-	  FINALIZED.  You should say N here unless you are interested in
-	  testing Btrfs with non-critical data.
+	  The filesystem disk format is no longer unstable, and it's not
+	  expected to change unless there are strong reasons to do so. If there
+	  is a format change, file systems with a unchanged format will
+	  continue to be mountable and usable by newer kernels.
+
+	  For more information, please see the web pages at
+	  http://btrfs.wiki.kernel.org.
 
 	  To compile this file system support as a module, choose M here. The
 	  module will be called btrfs.

fs/btrfs/async-thread.c

@@ -495,6 +495,7 @@ static int __btrfs_start_workers(struct btrfs_workers *workers)
 	spin_lock_irq(&workers->lock);
 	if (workers->stopping) {
 		spin_unlock_irq(&workers->lock);
+		ret = -EINVAL;
 		goto fail_kthread;
 	}
 	list_add_tail(&worker->worker_list, &workers->idle_list);

fs/btrfs/check-integrity.c

@@ -77,6 +77,15 @@
  * the integrity of (super)-block write requests, do not
  * enable the config option BTRFS_FS_CHECK_INTEGRITY to
  * include and compile the integrity check tool.
+ *
+ * Expect millions of lines of information in the kernel log with an
+ * enabled check_int_print_mask. Therefore set LOG_BUF_SHIFT in the
+ * kernel config to at least 26 (which is 64MB). Usually the value is
+ * limited to 21 (which is 2MB) in init/Kconfig. The file needs to be
+ * changed like this before LOG_BUF_SHIFT can be set to a high value:
+ * config LOG_BUF_SHIFT
+ *       int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
+ *       range 12 30
  */
 
 #include <linux/sched.h>
@@ -124,6 +133,7 @@
 #define BTRFSIC_PRINT_MASK_INITIAL_DATABASE			0x00000400
 #define BTRFSIC_PRINT_MASK_NUM_COPIES				0x00000800
 #define BTRFSIC_PRINT_MASK_TREE_WITH_ALL_MIRRORS		0x00001000
+#define BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE		0x00002000
 
 struct btrfsic_dev_state;
 struct btrfsic_state;
@@ -3015,6 +3025,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 	    (rw & WRITE) && NULL != bio->bi_io_vec) {
 		unsigned int i;
 		u64 dev_bytenr;
+		u64 cur_bytenr;
 		int bio_is_patched;
 		char **mapped_datav;
 
@@ -3033,6 +3044,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 				       GFP_NOFS);
 		if (!mapped_datav)
 			goto leave;
+		cur_bytenr = dev_bytenr;
 		for (i = 0; i < bio->bi_vcnt; i++) {
 			BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE);
 			mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page);
@@ -3044,16 +3056,13 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
 				kfree(mapped_datav);
 				goto leave;
 			}
-			if ((BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
-			     BTRFSIC_PRINT_MASK_VERBOSE) ==
-			    (dev_state->state->print_mask &
-			     (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
-			      BTRFSIC_PRINT_MASK_VERBOSE)))
+			if (dev_state->state->print_mask &
+			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
 				printk(KERN_INFO
-				       "#%u: page=%p, len=%u, offset=%u\n",
-				       i, bio->bi_io_vec[i].bv_page,
-				       bio->bi_io_vec[i].bv_len,
+				       "#%u: bytenr=%llu, len=%u, offset=%u\n",
+				       i, cur_bytenr, bio->bi_io_vec[i].bv_len,
 				       bio->bi_io_vec[i].bv_offset);
+			cur_bytenr += bio->bi_io_vec[i].bv_len;
 		}
 		btrfsic_process_written_block(dev_state, dev_bytenr,
 					      mapped_datav, bio->bi_vcnt,

fs/btrfs/ctree.h

@@ -3613,9 +3613,6 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_ordered_sum *sums);
 int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		       struct bio *bio, u64 file_start, int contig);
-int btrfs_csum_truncate(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root, struct btrfs_path *path,
-			u64 isize);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
 /* inode.c */
@@ -3744,9 +3741,6 @@ void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
 void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
 			     int skip_pinned);
-int btrfs_replace_extent_cache(struct inode *inode, struct extent_map *replace,
-			       u64 start, u64 end, int skip_pinned,
-			       int modified);
 extern const struct file_operations btrfs_file_operations;
 int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root, struct inode *inode,

fs/btrfs/dev-replace.c

@@ -366,7 +366,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	dev_replace->tgtdev = tgt_device;
 
 	printk_in_rcu(KERN_INFO
-		      "btrfs: dev_replace from %s (devid %llu) to %s) started\n",
+		      "btrfs: dev_replace from %s (devid %llu) to %s started\n",
 		      src_device->missing ? "<missing disk>" :
 		        rcu_str_deref(src_device->name),
 		      src_device->devid,

fs/btrfs/disk-io.c

@@ -3517,7 +3517,6 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 int btrfs_commit_super(struct btrfs_root *root)
 {
 	struct btrfs_trans_handle *trans;
-	int ret;
 
 	mutex_lock(&root->fs_info->cleaner_mutex);
 	btrfs_run_delayed_iputs(root);
@@ -3531,25 +3530,7 @@ int btrfs_commit_super(struct btrfs_root *root)
 	trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
-	ret = btrfs_commit_transaction(trans, root);
-	if (ret)
-		return ret;
-	/* run commit again to drop the original snapshot */
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-	ret = btrfs_commit_transaction(trans, root);
-	if (ret)
-		return ret;
-	ret = btrfs_write_and_wait_transaction(NULL, root);
-	if (ret) {
-		btrfs_error(root->fs_info, ret,
-			    "Failed to sync btree inode to disk.");
-		return ret;
-	}
-
-	ret = write_ctree_super(NULL, root, 0);
-	return ret;
+	return btrfs_commit_transaction(trans, root);
 }
 
 int close_ctree(struct btrfs_root *root)

fs/btrfs/extent_io.c

@@ -1980,6 +1980,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
 	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
 	int ret;
 
+	ASSERT(!(fs_info->sb->s_flags & MS_RDONLY));
 	BUG_ON(!mirror_num);
 
 	/* we can't repair anything in raid56 yet */
@@ -2036,6 +2037,9 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
 	unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
 	int ret = 0;
 
+	if (root->fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = extent_buffer_page(eb, i);
 		ret = repair_io_failure(root->fs_info, start, PAGE_CACHE_SIZE,
@@ -2057,12 +2061,12 @@ static int clean_io_failure(u64 start, struct page *page)
 	u64 private;
 	u64 private_failure;
 	struct io_failure_record *failrec;
-	struct btrfs_fs_info *fs_info;
+	struct inode *inode = page->mapping->host;
+	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct extent_state *state;
 	int num_copies;
 	int did_repair = 0;
 	int ret;
-	struct inode *inode = page->mapping->host;
 
 	private = 0;
 	ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
@@ -2085,6 +2089,8 @@ static int clean_io_failure(u64 start, struct page *page)
 		did_repair = 1;
 		goto out;
 	}
+	if (fs_info->sb->s_flags & MS_RDONLY)
+		goto out;
 
 	spin_lock(&BTRFS_I(inode)->io_tree.lock);
 	state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree,
@@ -2094,7 +2100,6 @@ static int clean_io_failure(u64 start, struct page *page)
 
 	if (state && state->start <= failrec->start &&
 	    state->end >= failrec->start + failrec->len - 1) {
-		fs_info = BTRFS_I(inode)->root->fs_info;
 		num_copies = btrfs_num_copies(fs_info, failrec->logical,
 					      failrec->len);
 		if (num_copies > 1)  {

fs/btrfs/inode.c

@@ -2129,7 +2129,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path,
 						  old->extent_offset, fs_info,
 						  path, record_one_backref,
 						  old);
-		BUG_ON(ret < 0 && ret != -ENOENT);
+		if (ret < 0 && ret != -ENOENT)
+			return false;
 
 		/* no backref to be processed for this extent */
 		if (!old->count) {
@@ -6186,8 +6187,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	write_unlock(&em_tree->lock);
 out:
 
-	if (em)
-		trace_btrfs_get_extent(root, em);
+	trace_btrfs_get_extent(root, em);
 
 	if (path)
 		btrfs_free_path(path);

fs/btrfs/ordered-data.c

@@ -638,6 +638,7 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 			WARN_ON(nr < 0);
 		}
 	}
+	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 }
 
@@ -803,7 +804,7 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}
-		if (ordered->file_offset + ordered->len < start) {
+		if (ordered->file_offset + ordered->len <= start) {
 			btrfs_put_ordered_extent(ordered);
 			break;
 		}

fs/btrfs/scrub.c

@@ -938,8 +938,10 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 				BTRFS_DEV_STAT_CORRUPTION_ERRS);
 	}
 
-	if (sctx->readonly && !sctx->is_dev_replace)
-		goto did_not_correct_error;
+	if (sctx->readonly) {
+		ASSERT(!sctx->is_dev_replace);
+		goto out;
+	}
 
 	if (!is_metadata && !have_csum) {
 		struct scrub_fixup_nodatasum *fixup_nodatasum;

fs/btrfs/transaction.c

@@ -1480,7 +1480,7 @@ static void do_async_commit(struct work_struct *work)
 	 * We've got freeze protection passed with the transaction.
 	 * Tell lockdep about it.
 	 */
-	if (ac->newtrans->type < TRANS_JOIN_NOLOCK)
+	if (ac->newtrans->type & __TRANS_FREEZABLE)
 		rwsem_acquire_read(
 		     &ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
 		     0, 1, _THIS_IP_);
@@ -1521,7 +1521,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	 * Tell lockdep we've released the freeze rwsem, since the
 	 * async commit thread will be the one to unlock it.
 	 */
-	if (trans->type < TRANS_JOIN_NOLOCK)
+	if (ac->newtrans->type & __TRANS_FREEZABLE)
 		rwsem_release(
 			&root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
 			1, _THIS_IP_);

fs/btrfs/tree-log.c

@@ -3697,7 +3697,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			ret = btrfs_truncate_inode_items(trans, log,
 							 inode, 0, 0);
 		} else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING,
-					      &BTRFS_I(inode)->runtime_flags)) {
+					      &BTRFS_I(inode)->runtime_flags) ||
+			   inode_only == LOG_INODE_EXISTS) {
 			if (inode_only == LOG_INODE_ALL)
 				fast_search = true;
 			max_key.type = BTRFS_XATTR_ITEM_KEY;
@@ -3801,7 +3802,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			err = ret;
 			goto out_unlock;
 		}
-	} else {
+	} else if (inode_only == LOG_INODE_ALL) {
 		struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree;
 		struct extent_map *em, *n;
 

fs/btrfs/volumes.c

@@ -5394,7 +5394,7 @@ static int bio_size_ok(struct block_device *bdev, struct bio *bio,
 {
 	struct bio_vec *prev;
 	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned short max_sectors = queue_max_sectors(q);
+	unsigned int max_sectors = queue_max_sectors(q);
 	struct bvec_merge_data bvm = {
 		.bi_bdev = bdev,
 		.bi_sector = sector,

include/trace/events/btrfs.h

@@ -162,12 +162,14 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 		{ EXTENT_FLAG_LOGGING,	 	"LOGGING" 	},	\
 		{ EXTENT_FLAG_FILLING,	 	"FILLING" 	})
 
-TRACE_EVENT(btrfs_get_extent,
+TRACE_EVENT_CONDITION(btrfs_get_extent,
 
 	TP_PROTO(struct btrfs_root *root, struct extent_map *map),
 
 	TP_ARGS(root, map),
 
+	TP_CONDITION(map),
+
 	TP_STRUCT__entry(
 		__field(	u64,  root_objectid	)
 		__field(	u64,  start		)