summaryrefslogtreecommitdiff
path: root/fs/btrfs/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/inode.c')
-rw-r--r--fs/btrfs/inode.c84
1 files changed, 62 insertions, 22 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d2c3edb50702..92415b8ac5a3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -926,7 +926,7 @@ static noinline int cow_file_range(struct inode *inode,
u64 alloc_hint = 0;
u64 num_bytes;
unsigned long ram_size;
- u64 disk_num_bytes;
+ u64 min_alloc_size;
u64 cur_alloc_size;
u64 blocksize = root->sectorsize;
struct btrfs_key ins;
@@ -942,7 +942,6 @@ static noinline int cow_file_range(struct inode *inode,
num_bytes = ALIGN(end - start + 1, blocksize);
num_bytes = max(blocksize, num_bytes);
- disk_num_bytes = num_bytes;
/* if this is a small write inside eof, kick off defrag */
if (num_bytes < 64 * 1024 &&
@@ -969,18 +968,33 @@ static noinline int cow_file_range(struct inode *inode,
}
}
- BUG_ON(disk_num_bytes >
- btrfs_super_total_bytes(root->fs_info->super_copy));
+ BUG_ON(num_bytes > btrfs_super_total_bytes(root->fs_info->super_copy));
alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
- while (disk_num_bytes > 0) {
+ /*
+ * Relocation relies on the relocated extents to have exactly the same
+ * size as the original extents. Normally writeback for relocation data
+ * extents follows a NOCOW path because relocation preallocates the
+ * extents. However, due to an operation such as scrub turning a block
+ * group to RO mode, it may fallback to COW mode, so we must make sure
+ * an extent allocated during COW has exactly the requested size and can
+ * not be split into smaller extents, otherwise relocation breaks and
+ * fails during the stage where it updates the bytenr of file extent
+ * items.
+ */
+ if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
+ min_alloc_size = num_bytes;
+ else
+ min_alloc_size = root->sectorsize;
+
+ while (num_bytes > 0) {
unsigned long op;
- cur_alloc_size = disk_num_bytes;
+ cur_alloc_size = num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size,
- root->sectorsize, 0, alloc_hint,
+ min_alloc_size, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
goto out_unlock;
@@ -1033,7 +1047,7 @@ static noinline int cow_file_range(struct inode *inode,
goto out_drop_extent_cache;
}
- if (disk_num_bytes < cur_alloc_size)
+ if (num_bytes < cur_alloc_size)
break;
/* we're not doing compressed IO, don't unlock the first
@@ -1050,8 +1064,10 @@ static noinline int cow_file_range(struct inode *inode,
start + ram_size - 1, locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC,
op);
- disk_num_bytes -= cur_alloc_size;
- num_bytes -= cur_alloc_size;
+ if (num_bytes < cur_alloc_size)
+ num_bytes = 0;
+ else
+ num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
start += cur_alloc_size;
}
@@ -5354,11 +5370,13 @@ no_delete:
}
/*
- * this returns the key found in the dir entry in the location pointer.
+ * Return the key found in the dir entry in the location pointer, fill @type
+ * with BTRFS_FT_*, and return 0.
+ *
* If no dir entries were found, location->objectid is 0.
*/
static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
- struct btrfs_key *location)
+ struct btrfs_key *location, u8 *type)
{
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
@@ -5380,6 +5398,8 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
goto out_err;
btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
+ if (!ret)
+ *type = btrfs_dir_type(path->nodes[0], di);
out:
btrfs_free_path(path);
return ret;
@@ -5506,7 +5526,6 @@ static void inode_tree_del(struct inode *inode)
spin_unlock(&root->inode_lock);
if (empty && btrfs_root_refs(&root->root_item) == 0) {
- synchronize_srcu(&root->fs_info->subvol_srcu);
spin_lock(&root->inode_lock);
empty = RB_EMPTY_ROOT(&root->inode_tree);
spin_unlock(&root->inode_lock);
@@ -5666,19 +5685,25 @@ static struct inode *new_simple_dir(struct super_block *s,
return inode;
}
+static inline u8 btrfs_inode_type(struct inode *inode)
+{
+ return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT];
+}
+
struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
{
struct inode *inode;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *sub_root = root;
struct btrfs_key location;
+ u8 di_type = 0;
int index;
int ret = 0;
if (dentry->d_name.len > BTRFS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
- ret = btrfs_inode_by_name(dir, dentry, &location);
+ ret = btrfs_inode_by_name(dir, dentry, &location, &di_type);
if (ret < 0)
return ERR_PTR(ret);
@@ -5687,6 +5712,18 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
if (location.type == BTRFS_INODE_ITEM_KEY) {
inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+ if (IS_ERR(inode))
+ return inode;
+
+ /* Do extra check against inode mode with di_type */
+ if (btrfs_inode_type(inode) != di_type) {
+ btrfs_crit(root->fs_info,
+"inode mode mismatch with dir: inode mode=0%o btrfs type=%u dir type=%u",
+ inode->i_mode, btrfs_inode_type(inode),
+ di_type);
+ iput(inode);
+ return ERR_PTR(-EUCLEAN);
+ }
return inode;
}
@@ -6300,11 +6337,6 @@ fail:
return ERR_PTR(ret);
}
-static inline u8 btrfs_inode_type(struct inode *inode)
-{
- return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT];
-}
-
/*
* utility function to add 'inode' into 'parent_inode' with
* a give name and a given sequence number.
@@ -6896,6 +6928,14 @@ again:
extent_start = found_key.offset;
if (found_type == BTRFS_FILE_EXTENT_REG ||
found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+ /* Only regular file could have regular/prealloc extent */
+ if (!S_ISREG(inode->i_mode)) {
+ err = -EUCLEAN;
+ btrfs_crit(root->fs_info,
+ "regular/prealloc extent found for non-regular inode %llu",
+ btrfs_ino(inode));
+ goto out;
+ }
extent_end = extent_start +
btrfs_file_extent_num_bytes(leaf, item);
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
@@ -8302,7 +8342,6 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
- atomic_inc(&dip->pending_bios);
while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
if (map_length < submit_len + bvec->bv_len ||
@@ -8359,7 +8398,8 @@ submit:
if (!ret)
return 0;
- bio_put(bio);
+ if (bio != orig_bio)
+ bio_put(bio);
out_err:
dip->errors = 1;
/*
@@ -8406,7 +8446,7 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
io_bio->bi_private = dip;
dip->orig_bio = io_bio;
dip->dio_bio = dio_bio;
- atomic_set(&dip->pending_bios, 0);
+ atomic_set(&dip->pending_bios, 1);
btrfs_bio = btrfs_io_bio(io_bio);
btrfs_bio->logical = file_offset;
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-23 01:04:10 +0000