summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-04 20:13:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-04 20:13:46 -0700
commit9daee913dc8d15eb65e0ff560803ab1c28bb480b (patch)
tree389d943ccf6c280176365e3b09f9e87a105f0733
parentfa9db655d0e112c108fe838809608caf759bdf5e (diff)
parentd95efb14c0b81b684deb32ba10cdb78b4178ae5b (diff)
downloadlinux-9daee913dc8d15eb65e0ff560803ab1c28bb480b.tar.gz
linux-9daee913dc8d15eb65e0ff560803ab1c28bb480b.tar.bz2
linux-9daee913dc8d15eb65e0ff560803ab1c28bb480b.zip
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o: "Add new ioctls to set and get the file system UUID in the ext4 superblock and improved the performance of the online resizing of file systems with bigalloc enabled. Fixed a lot of bugs, in particular for the inline data feature, potential races when creating and deleting inodes with shared extended attribute blocks, and the handling of directory blocks which are corrupted" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (37 commits) ext4: add ioctls to get/set the ext4 superblock uuid ext4: avoid resizing to a partial cluster size ext4: reduce computation of overhead during resize jbd2: fix assertion 'jh->b_frozen_data == NULL' failure when journal aborted ext4: block range must be validated before use in ext4_mb_clear_bb() mbcache: automatically delete entries from cache on freeing mbcache: Remove mb_cache_entry_delete() ext2: avoid deleting xattr block that is being reused ext2: unindent codeblock in ext2_xattr_set() ext2: factor our freeing of xattr block reference ext4: fix race when reusing xattr blocks ext4: unindent codeblock in ext4_xattr_block_set() ext4: remove EA inode entry from mbcache on inode eviction mbcache: add functions to delete entry if unused mbcache: don't reclaim used entries ext4: make sure ext4_append() always allocates new block ext4: check if directory block is within i_size ext4: reflect mb_optimize_scan value in options file ext4: avoid remove directory when directory is corrupted ext4: aligned '*' in comments ...
-rw-r--r--Documentation/filesystems/ext4/blockmap.rst2
-rw-r--r--fs/ext2/xattr.c170
-rw-r--r--fs/ext4/balloc.c2
-rw-r--r--fs/ext4/ext4.h16
-rw-r--r--fs/ext4/ext4_jbd2.c3
-rw-r--r--fs/ext4/fast_commit.c44
-rw-r--r--fs/ext4/indirect.c4
-rw-r--r--fs/ext4/inline.c33
-rw-r--r--fs/ext4/inode.c26
-rw-r--r--fs/ext4/ioctl.c105
-rw-r--r--fs/ext4/mballoc.c31
-rw-r--r--fs/ext4/migrate.c4
-rw-r--r--fs/ext4/namei.c30
-rw-r--r--fs/ext4/orphan.c24
-rw-r--r--fs/ext4/resize.c39
-rw-r--r--fs/ext4/super.c13
-rw-r--r--fs/ext4/symlink.c15
-rw-r--r--fs/ext4/xattr.c168
-rw-r--r--fs/ext4/xattr.h16
-rw-r--r--fs/jbd2/checkpoint.c6
-rw-r--r--fs/jbd2/commit.c32
-rw-r--r--fs/jbd2/journal.c41
-rw-r--r--fs/jbd2/recovery.c30
-rw-r--r--fs/jbd2/revoke.c8
-rw-r--r--fs/jbd2/transaction.c40
-rw-r--r--fs/mbcache.c123
-rw-r--r--include/linux/jbd2.h6
-rw-r--r--include/linux/mbcache.h33
28 files changed, 678 insertions, 386 deletions
diff --git a/Documentation/filesystems/ext4/blockmap.rst b/Documentation/filesystems/ext4/blockmap.rst
index 2bd990402a5c..cc596541ce79 100644
--- a/Documentation/filesystems/ext4/blockmap.rst
+++ b/Documentation/filesystems/ext4/blockmap.rst
@@ -1,7 +1,7 @@
.. SPDX-License-Identifier: GPL-2.0
+---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-| i.i_block Offset | Where It Points |
+| i.i_block Offset | Where It Points |
+=====================+==============================================================================================================================================================================================================================+
| 0 to 11 | Direct map to file blocks 0 to 11. |
+---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 841fa6d9d744..641abfa4b718 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -517,36 +517,36 @@ bad_block:
/* Here we know that we can set the new attribute. */
if (header) {
- /* assert(header == HDR(bh)); */
+ int offset;
+
lock_buffer(bh);
if (header->h_refcount == cpu_to_le32(1)) {
__u32 hash = le32_to_cpu(header->h_hash);
+ struct mb_cache_entry *oe;
- ea_bdebug(bh, "modifying in-place");
+ oe = mb_cache_entry_delete_or_get(EA_BLOCK_CACHE(inode),
+ hash, bh->b_blocknr);
+ if (!oe) {
+ ea_bdebug(bh, "modifying in-place");
+ goto update_block;
+ }
/*
- * This must happen under buffer lock for
- * ext2_xattr_set2() to reliably detect modified block
+ * Someone is trying to reuse the block, leave it alone
*/
- mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
- bh->b_blocknr);
-
- /* keep the buffer locked while modifying it. */
- } else {
- int offset;
-
- unlock_buffer(bh);
- ea_bdebug(bh, "cloning");
- header = kmemdup(HDR(bh), bh->b_size, GFP_KERNEL);
- error = -ENOMEM;
- if (header == NULL)
- goto cleanup;
- header->h_refcount = cpu_to_le32(1);
-
- offset = (char *)here - bh->b_data;
- here = ENTRY((char *)header + offset);
- offset = (char *)last - bh->b_data;
- last = ENTRY((char *)header + offset);
+ mb_cache_entry_put(EA_BLOCK_CACHE(inode), oe);
}
+ unlock_buffer(bh);
+ ea_bdebug(bh, "cloning");
+ header = kmemdup(HDR(bh), bh->b_size, GFP_KERNEL);
+ error = -ENOMEM;
+ if (header == NULL)
+ goto cleanup;
+ header->h_refcount = cpu_to_le32(1);
+
+ offset = (char *)here - bh->b_data;
+ here = ENTRY((char *)header + offset);
+ offset = (char *)last - bh->b_data;
+ last = ENTRY((char *)header + offset);
} else {
/* Allocate a buffer where we construct the new block. */
header = kzalloc(sb->s_blocksize, GFP_KERNEL);
@@ -559,6 +559,7 @@ bad_block:
last = here = ENTRY(header+1);
}
+update_block:
/* Iff we are modifying the block in-place, bh is locked here. */
if (not_found) {
@@ -651,6 +652,55 @@ cleanup:
return error;
}
+static void ext2_xattr_release_block(struct inode *inode,
+ struct buffer_head *bh)
+{
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
+
+retry_ref:
+ lock_buffer(bh);
+ if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
+ __u32 hash = le32_to_cpu(HDR(bh)->h_hash);
+ struct mb_cache_entry *oe;
+
+ /*
+ * This must happen under buffer lock to properly
+ * serialize with ext2_xattr_set() reusing the block.
+ */
+ oe = mb_cache_entry_delete_or_get(ea_block_cache, hash,
+ bh->b_blocknr);
+ if (oe) {
+ /*
+ * Someone is trying to reuse the block. Wait
+ * and retry.
+ */
+ unlock_buffer(bh);
+ mb_cache_entry_wait_unused(oe);
+ mb_cache_entry_put(ea_block_cache, oe);
+ goto retry_ref;
+ }
+
+ /* Free the old block. */
+ ea_bdebug(bh, "freeing");
+ ext2_free_blocks(inode, bh->b_blocknr, 1);
+ /* We let our caller release bh, so we
+ * need to duplicate the buffer before. */
+ get_bh(bh);
+ bforget(bh);
+ unlock_buffer(bh);
+ } else {
+ /* Decrement the refcount only. */
+ le32_add_cpu(&HDR(bh)->h_refcount, -1);
+ dquot_free_block(inode, 1);
+ mark_buffer_dirty(bh);
+ unlock_buffer(bh);
+ ea_bdebug(bh, "refcount now=%d",
+ le32_to_cpu(HDR(bh)->h_refcount));
+ if (IS_SYNC(inode))
+ sync_dirty_buffer(bh);
+ }
+}
+
/*
* Second half of ext2_xattr_set(): Update the file system.
*/
@@ -747,34 +797,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
* If there was an old block and we are no longer using it,
* release the old block.
*/
- lock_buffer(old_bh);
- if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) {
- __u32 hash = le32_to_cpu(HDR(old_bh)->h_hash);
-
- /*
- * This must happen under buffer lock for
- * ext2_xattr_set2() to reliably detect freed block
- */
- mb_cache_entry_delete(ea_block_cache, hash,
- old_bh->b_blocknr);
- /* Free the old block. */
- ea_bdebug(old_bh, "freeing");
- ext2_free_blocks(inode, old_bh->b_blocknr, 1);
- mark_inode_dirty(inode);
- /* We let our caller release old_bh, so we
- * need to duplicate the buffer before. */
- get_bh(old_bh);
- bforget(old_bh);
- } else {
- /* Decrement the refcount only. */
- le32_add_cpu(&HDR(old_bh)->h_refcount, -1);
- dquot_free_block_nodirty(inode, 1);
- mark_inode_dirty(inode);
- mark_buffer_dirty(old_bh);
- ea_bdebug(old_bh, "refcount now=%d",
- le32_to_cpu(HDR(old_bh)->h_refcount));
- }
- unlock_buffer(old_bh);
+ ext2_xattr_release_block(inode, old_bh);
}
cleanup:
@@ -828,30 +851,7 @@ ext2_xattr_delete_inode(struct inode *inode)
EXT2_I(inode)->i_file_acl);
goto cleanup;
}
- lock_buffer(bh);
- if (HDR(bh)->h_refcount == cpu_to_le32(1)) {
- __u32 hash = le32_to_cpu(HDR(bh)->h_hash);
-
- /*
- * This must happen under buffer lock for ext2_xattr_set2() to
- * reliably detect freed block
- */
- mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
- bh->b_blocknr);
- ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
- get_bh(bh);
- bforget(bh);
- unlock_buffer(bh);
- } else {
- le32_add_cpu(&HDR(bh)->h_refcount, -1);
- ea_bdebug(bh, "refcount now=%d",
- le32_to_cpu(HDR(bh)->h_refcount));
- unlock_buffer(bh);
- mark_buffer_dirty(bh);
- if (IS_SYNC(inode))
- sync_dirty_buffer(bh);
- dquot_free_block_nodirty(inode, 1);
- }
+ ext2_xattr_release_block(inode, bh);
EXT2_I(inode)->i_file_acl = 0;
cleanup:
@@ -943,7 +943,7 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
-again:
+
ce = mb_cache_entry_find_first(ea_block_cache, hash);
while (ce) {
struct buffer_head *bh;
@@ -955,22 +955,8 @@ again:
inode->i_ino, (unsigned long) ce->e_value);
} else {
lock_buffer(bh);
- /*
- * We have to be careful about races with freeing or
- * rehashing of xattr block. Once we hold buffer lock
- * xattr block's state is stable so we can check
- * whether the block got freed / rehashed or not.
- * Since we unhash mbcache entry under buffer lock when
- * freeing / rehashing xattr block, checking whether
- * entry is still hashed is reliable.
- */
- if (hlist_bl_unhashed(&ce->e_hash_list)) {
- mb_cache_entry_put(ea_block_cache, ce);
- unlock_buffer(bh);
- brelse(bh);
- goto again;
- } else if (le32_to_cpu(HDR(bh)->h_refcount) >
- EXT2_XATTR_REFCOUNT_MAX) {
+ if (le32_to_cpu(HDR(bh)->h_refcount) >
+ EXT2_XATTR_REFCOUNT_MAX) {
ea_idebug(inode, "block %ld refcount %d>%d",
(unsigned long) ce->e_value,
le32_to_cpu(HDR(bh)->h_refcount),
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 78ee3ef795ae..8ff4b9192a9f 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -666,7 +666,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
* it's possible we've just missed a transaction commit here,
* so ignore the returned status
*/
- jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
+ ext4_debug("%s: retrying operation after ENOSPC\n", sb->s_id);
(void) jbd2_journal_force_commit_nested(sbi->s_journal);
return 1;
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 29fc575a4eb6..9bca5565547b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -724,6 +724,8 @@ enum {
#define EXT4_IOC_GETSTATE _IOW('f', 41, __u32)
#define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap)
#define EXT4_IOC_CHECKPOINT _IOW('f', 43, __u32)
+#define EXT4_IOC_GETFSUUID _IOR('f', 44, struct fsuuid)
+#define EXT4_IOC_SETFSUUID _IOW('f', 44, struct fsuuid)
#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
@@ -753,6 +755,15 @@ enum {
EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \
EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
+/*
+ * Structure for EXT4_IOC_GETFSUUID/EXT4_IOC_SETFSUUID
+ */
+struct fsuuid {
+ __u32 fsu_len;
+ __u32 fsu_flags;
+ __u8 fsu_uuid[];
+};
+
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
@@ -3016,7 +3027,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns,
struct dentry *dentry, struct fileattr *fa);
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
extern void ext4_reset_inode_seed(struct inode *inode);
-int ext4_update_overhead(struct super_block *sb);
+int ext4_update_overhead(struct super_block *sb, bool force);
/* migrate.c */
extern int ext4_ext_migrate(struct inode *);
@@ -3583,6 +3594,7 @@ extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
extern int ext4_inline_data_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
int *has_inline, __u64 start, __u64 len);
+extern void *ext4_read_inline_link(struct inode *inode);
struct iomap;
extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
@@ -3799,7 +3811,7 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
extern int ext4_resize_begin(struct super_block *sb);
-extern void ext4_resize_end(struct super_block *sb);
+extern int ext4_resize_end(struct super_block *sb, bool update_backups);
static inline void ext4_set_io_unwritten_flag(struct inode *inode,
struct ext4_io_end *io_end)
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 3477a16d08ae..8e1fb18f465e 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -267,8 +267,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
trace_ext4_forget(inode, is_metadata, blocknr);
BUFFER_TRACE(bh, "enter");
- jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
- "data mode %x\n",
+ ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n",
bh, is_metadata, inode->i_mode,
test_opt(inode->i_sb, DATA_FLAGS));
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index eb4c8ad1bb61..2af962cbb835 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -917,8 +917,8 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc)
mutex_unlock(&ei->i_fc_lock);
cur_lblk_off = old_blk_size;
- jbd_debug(1, "%s: will try writing %d to %d for inode %ld\n",
- __func__, cur_lblk_off, new_blk_size, inode->i_ino);
+ ext4_debug("will try writing %d to %d for inode %ld\n",
+ cur_lblk_off, new_blk_size, inode->i_ino);
while (cur_lblk_off <= new_blk_size) {
map.m_lblk = cur_lblk_off;
@@ -1168,7 +1168,7 @@ static void ext4_fc_update_stats(struct super_block *sb, int status,
{
struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats;
- jbd_debug(1, "Fast commit ended with status = %d for tid %u",
+ ext4_debug("Fast commit ended with status = %d for tid %u",
status, commit_tid);
if (status == EXT4_FC_STATUS_OK) {
stats->fc_num_commits++;
@@ -1375,14 +1375,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl,
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode %d not found", darg.ino);
+ ext4_debug("Inode %d not found", darg.ino);
return 0;
}
old_parent = ext4_iget(sb, darg.parent_ino,
EXT4_IGET_NORMAL);
if (IS_ERR(old_parent)) {
- jbd_debug(1, "Dir with inode %d not found", darg.parent_ino);
+ ext4_debug("Dir with inode %d not found", darg.parent_ino);
iput(inode);
return 0;
}
@@ -1407,21 +1407,21 @@ static int ext4_fc_replay_link_internal(struct super_block *sb,
dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL);
if (IS_ERR(dir)) {
- jbd_debug(1, "Dir with inode %d not found.", darg->parent_ino);
+ ext4_debug("Dir with inode %d not found.", darg->parent_ino);
dir = NULL;
goto out;
}
dentry_dir = d_obtain_alias(dir);
if (IS_ERR(dentry_dir)) {
- jbd_debug(1, "Failed to obtain dentry");
+ ext4_debug("Failed to obtain dentry");
dentry_dir = NULL;
goto out;
}
dentry_inode = d_alloc(dentry_dir, &qstr_dname);
if (!dentry_inode) {
- jbd_debug(1, "Inode dentry not created.");
+ ext4_debug("Inode dentry not created.");
ret = -ENOMEM;
goto out;
}
@@ -1434,7 +1434,7 @@ static int ext4_fc_replay_link_internal(struct super_block *sb,
* could complete.
*/
if (ret && ret != -EEXIST) {
- jbd_debug(1, "Failed to link\n");
+ ext4_debug("Failed to link\n");
goto out;
}
@@ -1468,7 +1468,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl,
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode not found.");
+ ext4_debug("Inode not found.");
return 0;
}
@@ -1576,7 +1576,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
/* Given that we just wrote the inode on disk, this SHOULD succeed. */
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode not found.");
+ ext4_debug("Inode not found.");
return -EFSCORRUPTED;
}
@@ -1630,7 +1630,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl,
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "inode %d not found.", darg.ino);
+ ext4_debug("inode %d not found.", darg.ino);
inode = NULL;
ret = -EINVAL;
goto out;
@@ -1643,7 +1643,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl,
*/
dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
if (IS_ERR(dir)) {
- jbd_debug(1, "Dir %d not found.", darg.ino);
+ ext4_debug("Dir %d not found.", darg.ino);
goto out;
}
ret = ext4_init_new_dir(NULL, dir, inode);
@@ -1727,7 +1727,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode not found.");
+ ext4_debug("Inode not found.");
return 0;
}
@@ -1741,7 +1741,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
cur = start;
remaining = len;
- jbd_debug(1, "ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n",
+ ext4_debug("ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n",
start, start_pblk, len, ext4_ext_is_unwritten(ex),
inode->i_ino);
@@ -1802,7 +1802,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
}
/* Range is mapped and needs a state change */
- jbd_debug(1, "Converting from %ld to %d %lld",
+ ext4_debug("Converting from %ld to %d %lld",
map.m_flags & EXT4_MAP_UNWRITTEN,
ext4_ext_is_unwritten(ex), map.m_pblk);
ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
@@ -1845,7 +1845,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino));
+ ext4_debug("Inode %d not found", le32_to_cpu(lrange.fc_ino));
return 0;
}
@@ -1853,7 +1853,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
if (ret)
goto out;
- jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
+ ext4_debug("DEL_RANGE, inode %ld, lblk %d, len %d\n",
inode->i_ino, le32_to_cpu(lrange.fc_lblk),
le32_to_cpu(lrange.fc_len));
while (remaining > 0) {
@@ -1902,7 +1902,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
inode = ext4_iget(sb, state->fc_modified_inodes[i],
EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode %d not found.",
+ ext4_debug("Inode %d not found.",
state->fc_modified_inodes[i]);
continue;
}
@@ -2031,7 +2031,7 @@ static int ext4_fc_replay_scan(journal_t *journal,
for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) {
memcpy(&tl, cur, sizeof(tl));
val = cur + sizeof(tl);
- jbd_debug(3, "Scan phase, tag:%s, blk %lld\n",
+ ext4_debug("Scan phase, tag:%s, blk %lld\n",
tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr);
switch (le16_to_cpu(tl.fc_tag)) {
case EXT4_FC_TAG_ADD_RANGE:
@@ -2126,7 +2126,7 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
sbi->s_mount_state |= EXT4_FC_REPLAY;
}
if (!sbi->s_fc_replay_state.fc_replay_num_tags) {
- jbd_debug(1, "Replay stops\n");
+ ext4_debug("Replay stops\n");
ext4_fc_set_bitmaps_and_counters(sb);
return 0;
}
@@ -2150,7 +2150,7 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
ext4_fc_set_bitmaps_and_counters(sb);
break;
}
- jbd_debug(3, "Replay phase, tag:%s\n",
+ ext4_debug("Replay phase, tag:%s\n",
tag2str(le16_to_cpu(tl.fc_tag)));
state->fc_replay_num_tags--;
switch (le16_to_cpu(tl.fc_tag)) {
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 07a8c75b65ed..860fc5119009 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -460,7 +460,7 @@ static int ext4_splice_branch(handle_t *handle,
* the new i_size. But that is not done here - it is done in
* generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
*/
- jbd_debug(5, "splicing indirect only\n");
+ ext4_debug("splicing indirect only\n");
BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, ar->inode, where->bh);
if (err)
@@ -472,7 +472,7 @@ static int ext4_splice_branch(handle_t *handle,
err = ext4_mark_inode_dirty(handle, ar->inode);
if (unlikely(err))
goto err_out;
- jbd_debug(5, "splicing direct\n");
+ ext4_debug("splicing direct\n");
}
return err;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index cff52ff6549d..a4fbe825694b 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -6,6 +6,7 @@
#include <linux/iomap.h>
#include <linux/fiemap.h>
+#include <linux/namei.h>
#include <linux/iversion.h>
#include <linux/sched/mm.h>
@@ -35,6 +36,9 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
struct ext4_inode *raw_inode;
int free, min_offs;
+ if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
+ return 0;
+
min_offs = EXT4_SB(inode->i_sb)->s_inode_size -
EXT4_GOOD_OLD_INODE_SIZE -
EXT4_I(inode)->i_extra_isize -
@@ -1588,6 +1592,35 @@ out:
return ret;
}
+void *ext4_read_inline_link(struct inode *inode)
+{
+ struct ext4_iloc iloc;
+ int ret, inline_size;
+ void *link;
+
+ ret = ext4_get_inode_loc(inode, &iloc);
+ if (ret)
+ return ERR_PTR(ret);
+
+ ret = -ENOMEM;
+ inline_size = ext4_get_inline_size(inode);
+ link = kmalloc(inline_size + 1, GFP_NOFS);
+ if (!link)
+ goto out;
+
+ ret = ext4_read_inline_data(inode, link, inline_size, &iloc);
+ if (ret < 0) {
+ kfree(link);
+ goto out;
+ }
+ nd_terminate_link(link, inode->i_size, ret);
+out:
+ if (ret < 0)
+ link = ERR_PTR(ret);
+ brelse(iloc.bh);
+ return link;
+}
+
struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
struct ext4_dir_entry_2 **parent_de,
int *retval)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9fd60fc8ba4c..601214453c3a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -177,6 +177,8 @@ void ext4_evict_inode(struct inode *inode)
trace_ext4_evict_inode(inode);
+ if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
+ ext4_evict_ea_inode(inode);
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
@@ -1571,7 +1573,14 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
ext4_lblk_t start, last;
start = index << (PAGE_SHIFT - inode->i_blkbits);
last = end << (PAGE_SHIFT - inode->i_blkbits);
+
+ /*
+ * avoid racing with extent status tree scans made by
+ * ext4_insert_delayed_block()
+ */
+ down_write(&EXT4_I(inode)->i_data_sem);
ext4_es_remove_extent(inode, start, last - start + 1);
+ up_write(&EXT4_I(inode)->i_data_sem);
}
folio_batch_init(&fbatch);
@@ -3142,13 +3151,15 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
journal_t *journal;
+ sector_t ret = 0;
int err;
+ inode_lock_shared(inode);
/*
* We can get here for an inline file via the FIBMAP ioctl
*/
if (ext4_has_inline_data(inode))
- return 0;
+ goto out;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
test_opt(inode->i_sb, DELALLOC)) {
@@ -3187,10 +3198,14 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
jbd2_journal_unlock_updates(journal);
if (err)
- return 0;
+ goto out;
}
- return iomap_bmap(mapping, block, &ext4_iomap_ops);
+ ret = iomap_bmap(mapping, block, &ext4_iomap_ops);
+
+out:
+ inode_unlock_shared(inode);
+ return ret;
}
static int ext4_read_folio(struct file *file, struct folio *folio)
@@ -4687,8 +4702,7 @@ static inline int ext4_iget_extra_inode(struct inode *inode,
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
- if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
- EXT4_INODE_SIZE(inode->i_sb) &&
+ if (EXT4_INODE_HAS_XATTR_SPACE(inode) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
return ext4_find_inline_data_nolock(inode);
@@ -5215,7 +5229,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
if (EXT4_SB(inode->i_sb)->s_journal) {
if (ext4_journal_current_handle()) {
- jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
+ ext4_debug("called recursively, non-PF_MEMALLOC!\n");
dump_stack();
return -EIO;
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index cb01c1da0f9d..3cf3ec4b1c21 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -20,6 +20,7 @@
#include <linux/delay.h>
#include <linux/iversion.h>
#include <linux/fileattr.h>
+#include <linux/uuid.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include <linux/fsmap.h>
@@ -41,6 +42,15 @@ static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg)
memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX);
}
+/*
+ * Superblock modification callback function for changing file system
+ * UUID.
+ */
+static void ext4_sb_setuuid(struct ext4_super_block *es, const void *arg)
+{
+ memcpy(es->s_uuid, (__u8 *)arg, UUID_SIZE);
+}
+
static
int ext4_update_primary_sb(struct super_block *sb, handle_t *handle,
ext4_update_sb_callback func,
@@ -944,7 +954,9 @@ static long ext4_ioctl_group_add(struct file *file,
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input->group);
group_add_out:
- ext4_resize_end(sb);
+ err2 = ext4_resize_end(sb, false);
+ if (err == 0)
+ err = err2;
return err;
}
@@ -1131,6 +1143,73 @@ static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label
return 0;
}
+static int ext4_ioctl_getuuid(struct ext4_sb_info *sbi,
+ struct fsuuid __user *ufsuuid)
+{
+ struct fsuuid fsuuid;
+ __u8 uuid[UUID_SIZE];
+
+ if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid)))
+ return -EFAULT;
+
+ if (fsuuid.fsu_len == 0) {
+ fsuuid.fsu_len = UUID_SIZE;
+ if (copy_to_user(ufsuuid, &fsuuid, sizeof(fsuuid.fsu_len)))
+ return -EFAULT;
+ return -EINVAL;
+ }
+
+ if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0)
+ return -EINVAL;
+
+ lock_buffer(sbi->s_sbh);
+ memcpy(uuid, sbi->s_es->s_uuid, UUID_SIZE);
+ unlock_buffer(sbi->s_sbh);
+
+ if (copy_to_user(&ufsuuid->fsu_uuid[0], uuid, UUID_SIZE))
+ return -EFAULT;
+ return 0;
+}
+
+static int ext4_ioctl_setuuid(struct file *filp,
+ const struct fsuuid __user *ufsuuid)
+{
+ int ret = 0;
+ struct super_block *sb = file_inode(filp)->i_sb;
+ struct fsuuid fsuuid;
+ __u8 uuid[UUID_SIZE];
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /*
+ * If any checksums (group descriptors or metadata) are being used
+ * then the checksum seed feature is required to change the UUID.
+ */
+ if (((ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb))
+ && !ext4_has_feature_csum_seed(sb))
+ || ext4_has_feature_stable_inodes(sb))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid)))
+ return -EFAULT;
+
+ if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0)
+ return -EINVAL;
+
+ if (copy_from_user(uuid, &ufsuuid->fsu_uuid[0], UUID_SIZE))
+ return -EFAULT;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ ret = ext4_update_superblocks_fn(sb, ext4_sb_setuuid, &uu