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

Pull btrfs update from Chris Mason:
 "This is a large pull, with the bulk of the updates coming from:

   - Hole punching

   - send/receive fixes

   - fsync performance

   - Disk format extension allowing more hardlinks inside a single
     directory (btrfs-progs patch required to enable the compat bit for
     this one)

  I'm cooking more unrelated RAID code, but I wanted to make sure this
  original batch makes it in.  The largest updates here are relatively
  old and have been in testing for some time."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (121 commits)
  btrfs: init ref_index to zero in add_inode_ref
  Btrfs: remove repeated eb->pages check in, disk-io.c/csum_dirty_buffer
  Btrfs: fix page leakage
  Btrfs: do not warn_on when we cannot alloc a page for an extent buffer
  Btrfs: don't bug on enomem in readpage
  Btrfs: cleanup pages properly when ENOMEM in compression
  Btrfs: make filesystem read-only when submitting barrier fails
  Btrfs: detect corrupted filesystem after write I/O errors
  Btrfs: make compress and nodatacow mount options mutually exclusive
  btrfs: fix message printing
  Btrfs: don't bother committing delayed inode updates when fsyncing
  btrfs: move inline function code to header file
  Btrfs: remove unnecessary IS_ERR in bio_readpage_error()
  btrfs: remove unused function btrfs_insert_some_items()
  Btrfs: don't commit instead of overcommitting
  Btrfs: confirmation of value is added before trace_btrfs_get_extent() is called
  Btrfs: be smarter about dropping things from the tree log
  Btrfs: don't lookup csums for prealloc extents
  Btrfs: cache extent state when writing out dirty metadata pages
  Btrfs: do not hold the file extent leaf locked when adding extent item
  ...

1 files changed, 56 insertions, 44 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 47127c1bd290..e568c472f807 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -181,6 +181,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	int ret;
 	u64 ip_oldflags;
 	unsigned int i_oldflags;
+	umode_t mode;
 
 	if (btrfs_root_readonly(root))
 		return -EROFS;
@@ -203,6 +204,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 
 	ip_oldflags = ip->flags;
 	i_oldflags = inode->i_flags;
+	mode = inode->i_mode;
 
 	flags = btrfs_mask_flags(inode->i_mode, flags);
 	oldflags = btrfs_flags_to_ioctl(ip->flags);
@@ -237,10 +239,31 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		ip->flags |= BTRFS_INODE_DIRSYNC;
 	else
 		ip->flags &= ~BTRFS_INODE_DIRSYNC;
-	if (flags & FS_NOCOW_FL)
-		ip->flags |= BTRFS_INODE_NODATACOW;
-	else
-		ip->flags &= ~BTRFS_INODE_NODATACOW;
+	if (flags & FS_NOCOW_FL) {
+		if (S_ISREG(mode)) {
+			/*
+			 * It's safe to turn csums off here, no extents exist.
+			 * Otherwise we want the flag to reflect the real COW
+			 * status of the file and will not set it.
+			 */
+			if (inode->i_size == 0)
+				ip->flags |= BTRFS_INODE_NODATACOW
+					   | BTRFS_INODE_NODATASUM;
+		} else {
+			ip->flags |= BTRFS_INODE_NODATACOW;
+		}
+	} else {
+		/*
+		 * Revert back under same assuptions as above
+		 */
+		if (S_ISREG(mode)) {
+			if (inode->i_size == 0)
+				ip->flags &= ~(BTRFS_INODE_NODATACOW
+				             | BTRFS_INODE_NODATASUM);
+		} else {
+			ip->flags &= ~BTRFS_INODE_NODATACOW;
+		}
+	}
 
 	/*
 	 * The COMPRESS flag can only be changed by users, while the NOCOMPRESS
@@ -516,7 +539,8 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
 	if (!pending_snapshot)
 		return -ENOMEM;
 
-	btrfs_init_block_rsv(&pending_snapshot->block_rsv);
+	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
+			     BTRFS_BLOCK_RSV_TEMP);
 	pending_snapshot->dentry = dentry;
 	pending_snapshot->root = root;
 	pending_snapshot->readonly = readonly;
@@ -525,7 +549,7 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
 		*inherit = NULL;	/* take responsibility to free it */
 	}
 
-	trans = btrfs_start_transaction(root->fs_info->extent_root, 5);
+	trans = btrfs_start_transaction(root->fs_info->extent_root, 6);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		goto fail;
@@ -1022,8 +1046,8 @@ again:
 			 page_start, page_end - 1, 0, &cached_state);
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
 			  page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
-			  EXTENT_DO_ACCOUNTING, 0, 0, &cached_state,
-			  GFP_NOFS);
+			  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
+			  &cached_state, GFP_NOFS);
 
 	if (i_done != page_cnt) {
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -1034,8 +1058,8 @@ again:
 	}
 
 
-	btrfs_set_extent_delalloc(inode, page_start, page_end - 1,
-				  &cached_state);
+	set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
+			  &cached_state, GFP_NOFS);
 
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 			     page_start, page_end - 1, &cached_state,
@@ -2351,7 +2375,6 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	int ret;
 	u64 len = olen;
 	u64 bs = root->fs_info->sb->s_blocksize;
-	u64 hint_byte;
 
 	/*
 	 * TODO:
@@ -2456,13 +2479,13 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	   another, and lock file content */
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
-		lock_extent(&BTRFS_I(src)->io_tree, off, off+len);
-		ordered = btrfs_lookup_first_ordered_extent(src, off+len);
+		lock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
+		ordered = btrfs_lookup_first_ordered_extent(src, off + len - 1);
 		if (!ordered &&
-		    !test_range_bit(&BTRFS_I(src)->io_tree, off, off+len,
-				   EXTENT_DELALLOC, 0, NULL))
+		    !test_range_bit(&BTRFS_I(src)->io_tree, off, off + len - 1,
+				    EXTENT_DELALLOC, 0, NULL))
 			break;
-		unlock_extent(&BTRFS_I(src)->io_tree, off, off+len);
+		unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
 		btrfs_wait_ordered_range(src, off, len);
@@ -2536,7 +2559,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 			btrfs_release_path(path);
 
 			if (key.offset + datal <= off ||
-			    key.offset >= off+len)
+			    key.offset >= off + len - 1)
 				goto next;
 
 			memcpy(&new_key, &key, sizeof(new_key));
@@ -2574,10 +2597,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 					datal -= off - key.offset;
 				}
 
-				ret = btrfs_drop_extents(trans, inode,
+				ret = btrfs_drop_extents(trans, root, inode,
 							 new_key.offset,
 							 new_key.offset + datal,
-							 &hint_byte, 1);
+							 1);
 				if (ret) {
 					btrfs_abort_transaction(trans, root,
 								ret);
@@ -2637,8 +2660,8 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 					new_key.offset += skip;
 				}
 
-				if (key.offset + datal > off+len)
-					trim = key.offset + datal - (off+len);
+				if (key.offset + datal > off + len)
+					trim = key.offset + datal - (off + len);
 
 				if (comp && (skip || trim)) {
 					ret = -EINVAL;
@@ -2648,10 +2671,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 				size -= skip + trim;
 				datal -= skip + trim;
 
-				ret = btrfs_drop_extents(trans, inode,
+				ret = btrfs_drop_extents(trans, root, inode,
 							 new_key.offset,
 							 new_key.offset + datal,
-							 &hint_byte, 1);
+							 1);
 				if (ret) {
 					btrfs_abort_transaction(trans, root,
 								ret);
@@ -2715,7 +2738,7 @@ next:
 	ret = 0;
 out:
 	btrfs_release_path(path);
-	unlock_extent(&BTRFS_I(src)->io_tree, off, off+len);
+	unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
 out_unlock:
 	mutex_unlock(&src->i_mutex);
 	mutex_unlock(&inode->i_mutex);
@@ -2850,8 +2873,8 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 	return 0;
 }
 
-static void get_block_group_info(struct list_head *groups_list,
-				 struct btrfs_ioctl_space_info *space)
+void btrfs_get_block_group_info(struct list_head *groups_list,
+				struct btrfs_ioctl_space_info *space)
 {
 	struct btrfs_block_group_cache *block_group;
 
@@ -2959,8 +2982,8 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 		down_read(&info->groups_sem);
 		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
 			if (!list_empty(&info->block_groups[c])) {
-				get_block_group_info(&info->block_groups[c],
-						     &space);
+				btrfs_get_block_group_info(
+					&info->block_groups[c], &space);
 				memcpy(dest, &space, sizeof(space));
 				dest++;
 				space_args.total_spaces++;
@@ -3208,11 +3231,9 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 {
 	int ret = 0;
 	int size;
-	u64 extent_item_pos;
 	struct btrfs_ioctl_logical_ino_args *loi;
 	struct btrfs_data_container *inodes = NULL;
 	struct btrfs_path *path = NULL;
-	struct btrfs_key key;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -3230,7 +3251,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 		goto out;
 	}
 
-	size = min_t(u32, loi->size, 4096);
+	size = min_t(u32, loi->size, 64 * 1024);
 	inodes = init_data_container(size);
 	if (IS_ERR(inodes)) {
 		ret = PTR_ERR(inodes);
@@ -3238,22 +3259,13 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 		goto out;
 	}
 
-	ret = extent_from_logical(root->fs_info, loi->logical, path, &key);
-	btrfs_release_path(path);
-
-	if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
+	ret = iterate_inodes_from_logical(loi->logical, root->fs_info, path,
+					  build_ino_list, inodes);
+	if (ret == -EINVAL)
 		ret = -ENOENT;
 	if (ret < 0)
 		goto out;
 
-	extent_item_pos = loi->logical - key.objectid;
-	ret = iterate_extent_inodes(root->fs_info, key.objectid,
-					extent_item_pos, 0, build_ino_list,
-					inodes);
-
-	if (ret < 0)
-		goto out;
-
 	ret = copy_to_user((void *)(unsigned long)loi->inodes,
 			   (void *)(unsigned long)inodes, size);
 	if (ret)
@@ -3261,7 +3273,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 
 out:
 	btrfs_free_path(path);
-	kfree(inodes);
+	vfree(inodes);
 	kfree(loi);
 
 	return ret;