ext4: Allow ext4 to run without a journal
A few weeks ago I posted a patch for discussion that allowed ext4 to run
without a journal. Since that time I've integrated the excellent
comments from Andreas and fixed several serious bugs. We're currently
running with this patch and generating some performance numbers against
both ext2 (with backported reservations code) and ext4 with and without
a journal. It just so happens that running without a journal is
slightly faster for most everything.
We did
iozone -T -t 4 s 2g -r 256k -T -I -i0 -i1 -i2
which creates 4 threads, each of which create and do reads and writes on
a 2G file, with a buffer size of 256K, using O_DIRECT for all file opens
to bypass the page cache. Results:
ext2 ext4, default ext4, no journal
initial writes 13.0 MB/s 15.4 MB/s 15.7 MB/s
rewrites 13.1 MB/s 15.6 MB/s 15.9 MB/s
reads 15.2 MB/s 16.9 MB/s 17.2 MB/s
re-reads 15.3 MB/s 16.9 MB/s 17.2 MB/s
random readers 5.6 MB/s 5.6 MB/s 5.7 MB/s
random writers 5.1 MB/s 5.3 MB/s 5.4 MB/s
So it seems that, so far, this was a useful exercise.
Signed-off-by: Frank Mayhar <fmayhar@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 35f5f9a..31ebeb5 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -531,11 +531,11 @@
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
- ret = ext4_journal_dirty_metadata(handle, gd_bh);
+ ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
if (!err) err = ret;
*pdquot_freed_blocks += group_freed;
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index c75384b..ad13a84 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -7,53 +7,96 @@
int __ext4_journal_get_undo_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
- int err = jbd2_journal_get_undo_access(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_get_undo_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_get_write_access(const char *where, handle_t *handle,
struct buffer_head *bh)
{
- int err = jbd2_journal_get_write_access(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_get_write_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_forget(const char *where, handle_t *handle,
struct buffer_head *bh)
{
- int err = jbd2_journal_forget(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_forget(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_revoke(const char *where, handle_t *handle,
ext4_fsblk_t blocknr, struct buffer_head *bh)
{
- int err = jbd2_journal_revoke(handle, blocknr, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_revoke(handle, blocknr, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
int __ext4_journal_get_create_access(const char *where,
handle_t *handle, struct buffer_head *bh)
{
- int err = jbd2_journal_get_create_access(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_get_create_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ }
return err;
}
-int __ext4_journal_dirty_metadata(const char *where,
- handle_t *handle, struct buffer_head *bh)
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
+ struct inode *inode, struct buffer_head *bh)
{
- int err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, __func__, bh, handle, err);
+ int err = 0;
+
+ if (ext4_handle_valid(handle)) {
+ err = jbd2_journal_dirty_metadata(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __func__, bh,
+ handle, err);
+ } else {
+ mark_buffer_dirty(bh);
+ if (inode && inode_needs_sync(inode)) {
+ sync_dirty_buffer(bh);
+ if (buffer_req(bh) && !buffer_uptodate(bh)) {
+ ext4_error(inode->i_sb, __func__,
+ "IO error syncing inode, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long) bh->b_blocknr);
+ err = -EIO;
+ }
+ }
+ }
return err;
}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index b455c68..663197a 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -122,12 +122,6 @@
* been done yet.
*/
-static inline void ext4_journal_release_buffer(handle_t *handle,
- struct buffer_head *bh)
-{
- jbd2_journal_release_buffer(handle, bh);
-}
-
void ext4_journal_abort_handle(const char *caller, const char *err_fn,
struct buffer_head *bh, handle_t *handle, int err);
@@ -146,8 +140,8 @@
int __ext4_journal_get_create_access(const char *where,
handle_t *handle, struct buffer_head *bh);
-int __ext4_journal_dirty_metadata(const char *where,
- handle_t *handle, struct buffer_head *bh);
+int __ext4_handle_dirty_metadata(const char *where, handle_t *handle,
+ struct inode *inode, struct buffer_head *bh);
#define ext4_journal_get_undo_access(handle, bh) \
__ext4_journal_get_undo_access(__func__, (handle), (bh))
@@ -157,14 +151,57 @@
__ext4_journal_revoke(__func__, (handle), (blocknr), (bh))
#define ext4_journal_get_create_access(handle, bh) \
__ext4_journal_get_create_access(__func__, (handle), (bh))
-#define ext4_journal_dirty_metadata(handle, bh) \
- __ext4_journal_dirty_metadata(__func__, (handle), (bh))
#define ext4_journal_forget(handle, bh) \
__ext4_journal_forget(__func__, (handle), (bh))
+#define ext4_handle_dirty_metadata(handle, inode, bh) \
+ __ext4_handle_dirty_metadata(__func__, (handle), (inode), (bh))
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
int __ext4_journal_stop(const char *where, handle_t *handle);
+#define EXT4_NOJOURNAL_HANDLE ((handle_t *) 0x1)
+
+static inline int ext4_handle_valid(handle_t *handle)
+{
+ if (handle == EXT4_NOJOURNAL_HANDLE)
+ return 0;
+ return 1;
+}
+
+static inline void ext4_handle_sync(handle_t *handle)
+{
+ if (ext4_handle_valid(handle))
+ handle->h_sync = 1;
+}
+
+static inline void ext4_handle_release_buffer(handle_t *handle,
+ struct buffer_head *bh)
+{
+ if (ext4_handle_valid(handle))
+ jbd2_journal_release_buffer(handle, bh);
+}
+
+static inline int ext4_handle_is_aborted(handle_t *handle)
+{
+ if (ext4_handle_valid(handle))
+ return is_handle_aborted(handle);
+ return 0;
+}
+
+static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+{
+ if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
+ return 0;
+ return 1;
+}
+
+static inline void ext4_journal_release_buffer(handle_t *handle,
+ struct buffer_head *bh)
+{
+ if (ext4_handle_valid(handle))
+ jbd2_journal_release_buffer(handle, bh);
+}
+
static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
{
return ext4_journal_start_sb(inode->i_sb, nblocks);
@@ -180,27 +217,37 @@
static inline int ext4_journal_extend(handle_t *handle, int nblocks)
{
- return jbd2_journal_extend(handle, nblocks);
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_extend(handle, nblocks);
+ return 0;
}
static inline int ext4_journal_restart(handle_t *handle, int nblocks)
{
- return jbd2_journal_restart(handle, nblocks);
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_restart(handle, nblocks);
+ return 0;
}
static inline int ext4_journal_blocks_per_page(struct inode *inode)
{
- return jbd2_journal_blocks_per_page(inode);
+ if (EXT4_JOURNAL(inode) != NULL)
+ return jbd2_journal_blocks_per_page(inode);
+ return 0;
}
static inline int ext4_journal_force_commit(journal_t *journal)
{
- return jbd2_journal_force_commit(journal);
+ if (journal)
+ return jbd2_journal_force_commit(journal);
+ return 0;
}
static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
- return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+ return 0;
}
/* super.c */
@@ -208,6 +255,8 @@
static inline int ext4_should_journal_data(struct inode *inode)
{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return 0;
if (!S_ISREG(inode->i_mode))
return 1;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -219,6 +268,8 @@
static inline int ext4_should_order_data(struct inode *inode)
{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return 0;
if (!S_ISREG(inode->i_mode))
return 0;
if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
@@ -230,6 +281,8 @@
static inline int ext4_should_writeback_data(struct inode *inode)
{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return 0;
if (!S_ISREG(inode->i_mode))
return 0;
if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0917be5..743e3fe 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -97,6 +97,8 @@
{
int err;
+ if (!ext4_handle_valid(handle))
+ return 0;
if (handle->h_buffer_credits > needed)
return 0;
err = ext4_journal_extend(handle, needed);
@@ -134,7 +136,7 @@
int err;
if (path->p_bh) {
/* path points to block */
- err = ext4_journal_dirty_metadata(handle, path->p_bh);
+ err = ext4_handle_dirty_metadata(handle, inode, path->p_bh);
} else {
/* path points to leaf/index in inode body */
err = ext4_mark_inode_dirty(handle, inode);
@@ -780,7 +782,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
@@ -859,7 +861,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto cleanup;
brelse(bh);
@@ -955,7 +957,7 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto out;
@@ -2947,7 +2949,7 @@
* transaction synchronous.
*/
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
out_stop:
up_write(&EXT4_I(inode)->i_data_sem);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 6e60528..9dd21b7 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -253,12 +253,12 @@
spin_unlock(sb_bgl_lock(sbi, flex_group));
}
}
- BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh2);
+ BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bh2);
if (!fatal) fatal = err;
}
- BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ BUFFER_TRACE(bitmap_bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
sb->s_dirt = 1;
@@ -656,15 +656,16 @@
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
- "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle,
+ "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle,
+ inode,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
- jbd2_journal_release_buffer(handle, bitmap_bh);
+ ext4_handle_release_buffer(handle, bitmap_bh);
if (++ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
@@ -726,7 +727,8 @@
/* Don't need to dirty bitmap block if we didn't change it */
if (free) {
BUFFER_TRACE(block_bh, "dirty block bitmap");
- err = ext4_journal_dirty_metadata(handle, block_bh);
+ err = ext4_handle_dirty_metadata(handle,
+ NULL, block_bh);
}
brelse(block_bh);
@@ -771,8 +773,8 @@
}
gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
spin_unlock(sb_bgl_lock(sbi, group));
- BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh2);
+ BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, NULL, bh2);
if (err) goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
@@ -825,7 +827,7 @@
ext4_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
if (insert_inode_locked(inode) < 0) {
err = -EINVAL;
goto fail_drop;
@@ -1028,4 +1030,3 @@
}
return count;
}
-
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c77a7ac..45d0f70 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -72,12 +72,17 @@
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
+ *
+ * If the handle isn't valid we're not journaling so there's nothing to do.
*/
int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr)
{
int err;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
might_sleep();
BUFFER_TRACE(bh, "enter");
@@ -170,7 +175,9 @@
*/
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
- if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+ if (!ext4_handle_valid(handle))
+ return 0;
+ if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
return 0;
if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
return 0;
@@ -184,6 +191,7 @@
*/
static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
{
+ BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
return ext4_journal_restart(handle, blocks_for_truncate(inode));
}
@@ -216,7 +224,7 @@
}
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
@@ -233,7 +241,7 @@
* enough credits left in the handle to remove the inode from
* the orphan list and set the dtime field.
*/
- if (handle->h_buffer_credits < 3) {
+ if (!ext4_handle_has_enough_credits(handle, 3)) {
err = ext4_journal_extend(handle, 3);
if (err > 0)
err = ext4_journal_restart(handle, 3);
@@ -717,8 +725,8 @@
set_buffer_uptodate(bh);
unlock_buffer(bh);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto failed;
}
@@ -800,8 +808,8 @@
* generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
*/
jbd_debug(5, "splicing indirect only\n");
- BUFFER_TRACE(where->bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, where->bh);
+ BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, where->bh);
if (err)
goto err_out;
} else {
@@ -1229,8 +1237,8 @@
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
if (!fatal)
fatal = err;
} else {
@@ -1395,7 +1403,7 @@
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
- return ext4_journal_dirty_metadata(handle, bh);
+ return ext4_handle_dirty_metadata(handle, NULL, bh);
}
/*
@@ -2762,7 +2770,10 @@
filemap_write_and_wait(mapping);
}
- if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ BUG_ON(!EXT4_JOURNAL(inode) &&
+ EXT4_I(inode)->i_state & EXT4_STATE_JDATA);
+
+ if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
/*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
@@ -3033,7 +3044,10 @@
if (offset == 0)
ClearPageChecked(page);
- jbd2_journal_invalidatepage(journal, page, offset);
+ if (journal)
+ jbd2_journal_invalidatepage(journal, page, offset);
+ else
+ block_invalidatepage(page, offset);
}
static int ext4_releasepage(struct page *page, gfp_t wait)
@@ -3043,7 +3057,10 @@
WARN_ON(PageChecked(page));
if (!page_has_buffers(page))
return 0;
- return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ if (journal)
+ return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ else
+ return try_to_free_buffers(page);
}
/*
@@ -3315,7 +3332,7 @@
err = 0;
if (ext4_should_journal_data(inode)) {
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
} else {
if (ext4_should_order_data(inode))
err = ext4_jbd2_file_inode(handle, inode);
@@ -3439,8 +3456,8 @@
__le32 *p;
if (try_to_extend_transaction(handle, inode)) {
if (bh) {
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, inode, bh);
}
ext4_mark_inode_dirty(handle, inode);
ext4_journal_test_restart(handle, inode);
@@ -3540,7 +3557,7 @@
count, block_to_free_p, p);
if (this_bh) {
- BUFFER_TRACE(this_bh, "call ext4_journal_dirty_metadata");
+ BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
/*
* The buffer head should have an attached journal head at this
@@ -3549,7 +3566,7 @@
* the block was cleared. Check for this instead of OOPSing.
*/
if (bh2jh(this_bh))
- ext4_journal_dirty_metadata(handle, this_bh);
+ ext4_handle_dirty_metadata(handle, inode, this_bh);
else
ext4_error(inode->i_sb, __func__,
"circular indirect block detected, "
@@ -3579,7 +3596,7 @@
ext4_fsblk_t nr;
__le32 *p;
- if (is_handle_aborted(handle))
+ if (ext4_handle_is_aborted(handle))
return;
if (depth--) {
@@ -3649,7 +3666,7 @@
* will merely complain about releasing a free block,
* rather than leaking blocks.
*/
- if (is_handle_aborted(handle))
+ if (ext4_handle_is_aborted(handle))
return;
if (try_to_extend_transaction(handle, inode)) {
ext4_mark_inode_dirty(handle, inode);
@@ -3668,9 +3685,10 @@
parent_bh)){
*p = 0;
BUFFER_TRACE(parent_bh,
- "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle,
- parent_bh);
+ "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle,
+ inode,
+ parent_bh);
}
}
}
@@ -3858,7 +3876,7 @@
* synchronous
*/
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
out_stop:
/*
* If this was a simple ftruncate(), and the file will remain alive
@@ -4357,8 +4375,8 @@
EXT4_SET_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
sb->s_dirt = 1;
- handle->h_sync = 1;
- err = ext4_journal_dirty_metadata(handle,
+ ext4_handle_sync(handle);
+ err = ext4_handle_dirty_metadata(handle, inode,
EXT4_SB(sb)->s_sbh);
}
}
@@ -4385,9 +4403,8 @@
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
-
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- rc = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ rc = ext4_handle_dirty_metadata(handle, inode, bh);
if (!err)
err = rc;
ei->i_state &= ~EXT4_STATE_NEW;
@@ -4450,6 +4467,25 @@
return ext4_force_commit(inode->i_sb);
}
+int __ext4_write_dirty_metadata(struct inode *inode, struct buffer_head *bh)
+{
+ int err = 0;
+
+ mark_buffer_dirty(bh);
+ if (inode && inode_needs_sync(inode)) {
+ sync_dirty_buffer(bh);
+ if (buffer_req(bh) && !buffer_uptodate(bh)) {
+ ext4_error(inode->i_sb, __func__,
+ "IO error syncing inode, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long)bh->b_blocknr);
+ err = -EIO;
+ }
+ }
+ return err;
+}
+
/*
* ext4_setattr()
*
@@ -4754,16 +4790,15 @@
ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc)
{
- int err = 0;
- if (handle) {
- err = ext4_get_inode_loc(inode, iloc);
- if (!err) {
- BUFFER_TRACE(iloc->bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, iloc->bh);
- if (err) {
- brelse(iloc->bh);
- iloc->bh = NULL;
- }
+ int err;
+
+ err = ext4_get_inode_loc(inode, iloc);
+ if (!err) {
+ BUFFER_TRACE(iloc->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, iloc->bh);
+ if (err) {
+ brelse(iloc->bh);
+ iloc->bh = NULL;
}
}
ext4_std_error(inode->i_sb, err);
@@ -4835,7 +4870,8 @@
might_sleep();
err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+ if (ext4_handle_valid(handle) &&
+ EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
!(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
/*
* We need extra buffer credits since we may write into EA block
@@ -4887,6 +4923,11 @@
handle_t *current_handle = ext4_journal_current_handle();
handle_t *handle;
+ if (!ext4_handle_valid(current_handle)) {
+ ext4_mark_inode_dirty(current_handle, inode);
+ return;
+ }
+
handle = ext4_journal_start(inode, 2);
if (IS_ERR(handle))
goto out;
@@ -4924,8 +4965,9 @@
BUFFER_TRACE(iloc.bh, "get_write_access");
err = jbd2_journal_get_write_access(handle, iloc.bh);
if (!err)
- err = ext4_journal_dirty_metadata(handle,
- iloc.bh);
+ err = ext4_handle_dirty_metadata(handle,
+ inode,
+ iloc.bh);
brelse(iloc.bh);
}
}
@@ -4951,6 +4993,8 @@
*/
journal = EXT4_JOURNAL(inode);
+ if (!journal)
+ return 0;
if (is_journal_aborted(journal))
return -EROFS;
@@ -4980,7 +5024,7 @@
return PTR_ERR(handle);
err = ext4_mark_inode_dirty(handle, inode);
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
ext4_journal_stop(handle);
ext4_std_error(inode->i_sb, err);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index dc99b47..42dc83f 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -99,7 +99,7 @@
goto flags_out;
}
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7beab71..edb512b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2553,7 +2553,8 @@
ext4_mb_init_per_dev_proc(sb);
ext4_mb_history_init(sb);
- sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+ if (sbi->s_journal)
+ sbi->s_journal->j_commit_callback = release_blocks_on_commit;
printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
return 0;
@@ -2854,7 +2855,7 @@
mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group),
bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
err = -EAGAIN;
goto out_err;
@@ -2901,10 +2902,10 @@
spin_unlock(sb_bgl_lock(sbi, flex_group));
}
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (err)
goto out_err;
- err = ext4_journal_dirty_metadata(handle, gdp_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
out_err:
sb->s_dirt = 1;
@@ -4414,7 +4415,7 @@
struct rb_node **n = &db->bb_free_root.rb_node, *node;
struct rb_node *parent = NULL, *new_node;
-
+ BUG_ON(!ext4_handle_valid(handle));
BUG_ON(e4b->bd_bitmap_page == NULL);
BUG_ON(e4b->bd_buddy_page == NULL);
@@ -4600,7 +4601,7 @@
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
- err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (ac) {
ac->ac_b_ex.fe_group = block_group;
@@ -4609,7 +4610,7 @@
ext4_mb_store_history(ac);
}
- if (metadata) {
+ if (metadata && ext4_handle_valid(handle)) {
/* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed */
ext4_mb_free_metadata(handle, &e4b, block_group, bit, count);
@@ -4639,7 +4640,7 @@
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
- ret = ext4_journal_dirty_metadata(handle, gd_bh);
+ ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
if (!err)
err = ret;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index f2a9cf4..e7cd488 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -59,7 +59,8 @@
/*
* Make sure the credit we accumalated is not really high
*/
- if (needed && handle->h_buffer_credits >= EXT4_RESERVE_TRANS_BLOCKS) {
+ if (needed && ext4_handle_has_enough_credits(handle,
+ EXT4_RESERVE_TRANS_BLOCKS)) {
retval = ext4_journal_restart(handle, needed);
if (retval)
goto err_out;
@@ -229,7 +230,7 @@
{
int retval = 0, needed;
- if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+ if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
return 0;
/*
* We are freeing a blocks. During this we touch
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 84a68ae..08873e9 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1233,10 +1233,10 @@
de = de2;
}
dx_insert_block(frame, hash2 + continued, newblock);
- err = ext4_journal_dirty_metadata(handle, bh2);
+ err = ext4_handle_dirty_metadata(handle, dir, bh2);
if (err)
goto journal_error;
- err = ext4_journal_dirty_metadata(handle, frame->bh);
+ err = ext4_handle_dirty_metadata(handle, dir, frame->bh);
if (err)
goto journal_error;
brelse(bh2);
@@ -1340,8 +1340,8 @@
ext4_update_dx_flag(dir);
dir->i_version++;
ext4_mark_inode_dirty(handle, dir);
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- err = ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ err = ext4_handle_dirty_metadata(handle, dir, bh);
if (err)
ext4_std_error(dir->i_sb, err);
brelse(bh);
@@ -1581,7 +1581,7 @@
dxtrace(dx_show_index("node", frames[1].entries));
dxtrace(dx_show_index("node",
((struct dx_node *) bh2->b_data)->entries));
- err = ext4_journal_dirty_metadata(handle, bh2);
+ err = ext4_handle_dirty_metadata(handle, inode, bh2);
if (err)
goto journal_error;
brelse (bh2);
@@ -1607,7 +1607,7 @@
if (err)
goto journal_error;
}
- ext4_journal_dirty_metadata(handle, frames[0].bh);
+ ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
}
de = do_split(handle, dir, &bh, frame, &hinfo, &err);
if (!de)
@@ -1653,8 +1653,8 @@
else
de->inode = 0;
dir->i_version++;
- BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, bh);
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, dir, bh);
return 0;
}
i += ext4_rec_len_from_disk(de->rec_len);
@@ -1732,7 +1732,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode (handle, dir, mode);
err = PTR_ERR(inode);
@@ -1766,7 +1766,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, mode);
err = PTR_ERR(inode);
@@ -1802,7 +1802,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFDIR | mode);
err = PTR_ERR(inode);
@@ -1831,8 +1831,8 @@
strcpy(de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
inode->i_nlink = 2;
- BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, dir_block);
+ BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, dir, dir_block);
brelse(dir_block);
ext4_mark_inode_dirty(handle, inode);
err = ext4_add_entry(handle, dentry, inode);
@@ -1944,6 +1944,9 @@
struct ext4_iloc iloc;
int err = 0, rc;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
lock_super(sb);
if (!list_empty(&EXT4_I(inode)->i_orphan))
goto out_unlock;
@@ -1972,7 +1975,7 @@
/* Insert this inode at the head of the on-disk orphan list... */
NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
- err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, inode, EXT4_SB(sb)->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -2010,6 +2013,9 @@
struct ext4_iloc iloc;
int err = 0;
+ if (!ext4_handle_valid(handle))
+ return 0;
+
lock_super(inode->i_sb);
if (list_empty(&ei->i_orphan)) {
unlock_super(inode->i_sb);
@@ -2028,7 +2034,7 @@
* transaction handle with which to update the orphan list on
* disk, but we still need to remove the inode from the linked
* list in memory. */
- if (!handle)
+ if (sbi->s_journal && !handle)
goto out;
err = ext4_reserve_inode_write(handle, inode, &iloc);
@@ -2042,7 +2048,7 @@
if (err)
goto out_brelse;
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
- err = ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, inode, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
@@ -2093,7 +2099,7 @@
goto end_rmdir;
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = dentry->d_inode;
@@ -2147,7 +2153,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de);
@@ -2204,7 +2210,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO);
err = PTR_ERR(inode);
@@ -2267,7 +2273,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
inode->i_ctime = ext4_current_time(inode);
ext4_inc_count(handle, inode);
@@ -2316,7 +2322,7 @@
return PTR_ERR(handle);
if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de);
/*
@@ -2370,8 +2376,8 @@
new_dir->i_ctime = new_dir->i_mtime =
ext4_current_time(new_dir);
ext4_mark_inode_dirty(handle, new_dir);
- BUFFER_TRACE(new_bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, new_bh);
+ BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, new_dir, new_bh);
brelse(new_bh);
new_bh = NULL;
}
@@ -2421,8 +2427,8 @@
BUFFER_TRACE(dir_bh, "get_write_access");
ext4_journal_get_write_access(handle, dir_bh);
PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
- BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata");
- ext4_journal_dirty_metadata(handle, dir_bh);
+ BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
+ ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
ext4_dec_count(handle, old_dir);
if (new_inode) {
/* checked empty_dir above, can't have another parent,
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index d448eb1..1665aa1 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -149,7 +149,7 @@
{
int err;
- if (handle->h_buffer_credits >= thresh)
+ if (ext4_handle_has_enough_credits(handle, thresh))
return 0;
err = ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA);
@@ -232,7 +232,7 @@
memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, gdb->b_size);
set_buffer_uptodate(gdb);
unlock_buffer(gdb);
- ext4_journal_dirty_metadata(handle, gdb);
+ ext4_handle_dirty_metadata(handle, NULL, gdb);
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -251,7 +251,7 @@
err = PTR_ERR(bh);
goto exit_bh;
}
- ext4_journal_dirty_metadata(handle, gdb);
+ ext4_handle_dirty_metadata(handle, NULL, gdb);
ext4_set_bit(bit, bh->b_data);
brelse(gdb);
}
@@ -276,7 +276,7 @@
err = PTR_ERR(it);
goto exit_bh;
}
- ext4_journal_dirty_metadata(handle, it);
+ ext4_handle_dirty_metadata(handle, NULL, it);
brelse(it);
ext4_set_bit(bit, bh->b_data);
}
@@ -286,7 +286,7 @@
mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb),
bh->b_data);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
/* Mark unused entries in inode bitmap used */
@@ -299,7 +299,7 @@
mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
bh->b_data);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
exit_bh:
brelse(bh);
@@ -486,12 +486,12 @@
* reserved inode, and will become GDT blocks (primary and backup).
*/
data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
- ext4_journal_dirty_metadata(handle, dind);
+ ext4_handle_dirty_metadata(handle, NULL, dind);
brelse(dind);
inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
ext4_mark_iloc_dirty(handle, inode, &iloc);
memset((*primary)->b_data, 0, sb->s_blocksize);
- ext4_journal_dirty_metadata(handle, *primary);
+ ext4_handle_dirty_metadata(handle, NULL, *primary);
o_group_desc = EXT4_SB(sb)->s_group_desc;
memcpy(n_group_desc, o_group_desc,
@@ -502,7 +502,7 @@
kfree(o_group_desc);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
return 0;
@@ -618,7 +618,7 @@
primary[i]->b_blocknr, gdbackups,
blk + primary[i]->b_blocknr); */
data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
- err2 = ext4_journal_dirty_metadata(handle, primary[i]);
+ err2 = ext4_handle_dirty_metadata(handle, NULL, primary[i]);
if (!err)
err = err2;
}
@@ -676,7 +676,8 @@
struct buffer_head *bh;
/* Out of journal space, and can't get more - abort - so sad */
- if (handle->h_buffer_credits == 0 &&
+ if (ext4_handle_valid(handle) &&
+ handle->h_buffer_credits == 0 &&
ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
(err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
break;
@@ -696,7 +697,7 @@
memset(bh->b_data + size, 0, rest);
set_buffer_uptodate(bh);
unlock_buffer(bh);
- ext4_journal_dirty_metadata(handle, bh);
+ ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
}
if ((err2 = ext4_journal_stop(handle)) && !err)
@@ -916,7 +917,7 @@
/* Update the global fs size fields */
sbi->s_groups_count++;
- ext4_journal_dirty_metadata(handle, primary);
+ ext4_handle_dirty_metadata(handle, NULL, primary);
/* Update the reserved block counts only once the new group is
* active. */
@@ -938,7 +939,7 @@
EXT4_INODES_PER_GROUP(sb);
}
- ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
sb->s_dirt = 1;
exit_journal:
@@ -1072,7 +1073,7 @@
goto exit_put;
}
ext4_blocks_count_set(es, o_blocks_count + add);
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
sb->s_dirt = 1;
unlock_super(sb);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8a0ae88..9b9076d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -136,13 +136,19 @@
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, __func__,
- "Detected aborted journal");
- return ERR_PTR(-EROFS);
+ if (journal) {
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, __func__,
+ "Detected aborted journal");
+ return ERR_PTR(-EROFS);
+ }
+ return jbd2_journal_start(journal, nblocks);
}
-
- return jbd2_journal_start(journal, nblocks);
+ /*
+ * We're not journaling, return the appropriate indication.
+ */
+ current->journal_info = EXT4_NOJOURNAL_HANDLE;
+ return current->journal_info;
}
/*
@@ -157,6 +163,14 @@
int err;
int rc;
+ if (!ext4_handle_valid(handle)) {
+ /*
+ * Do this here since we don't call jbd2_journal_stop() in
+ * no-journal mode.
+ */
+ current->journal_info = NULL;
+ return 0;
+ }
sb = handle->h_transaction->t_journal->j_private;
err = handle->h_err;
rc = jbd2_journal_stop(handle);
@@ -174,6 +188,8 @@
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
+ BUG_ON(!ext4_handle_valid(handle));
+
if (bh)
BUFFER_TRACE(bh, "abort");
@@ -448,11 +464,13 @@
ext4_mb_release(sb);
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
- err = jbd2_journal_destroy(sbi->s_journal);
- sbi->s_journal = NULL;
- if (err < 0)
- ext4_abort(sb, __func__, "Couldn't clean up the journal");
-
+ if (sbi->s_journal) {
+ err = jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ if (err < 0)
+ ext4_abort(sb, __func__,
+ "Couldn't clean up the journal");
+ }
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -522,6 +540,11 @@
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
+ /*
+ * Note: We can be called before EXT4_SB(sb)->s_journal is set,
+ * therefore it can be null here. Don't check it, just initialize
+ * jinode.
+ */
jbd2_journal_init_jbd_inode(&ei->jinode, &ei->vfs_inode);
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
@@ -588,7 +611,8 @@
}
#endif
ext4_discard_preallocations(inode);
- jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
+ if (EXT4_JOURNAL(inode))
+ jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
&EXT4_I(inode)->jinode);
}
@@ -1406,20 +1430,15 @@
printk(KERN_WARNING
"EXT4-fs warning: checktime reached, "
"running e2fsck is recommended\n");
-#if 0
- /* @@@ We _will_ want to clear the valid bit if we find
- * inconsistencies, to force a fsck at reboot. But for
- * a plain journaled filesystem we can keep it set as
- * valid forever! :)
- */
- es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
-#endif
+ if (!sbi->s_journal)
+ es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
es->s_mtime = cpu_to_le32(get_seconds());
ext4_update_dynamic_rev(sb);
- EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ if (sbi->s_journal)
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
ext4_commit_super(sb, es, 1);
if (test_opt(sb, DEBUG))
@@ -1431,9 +1450,13 @@
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt);
- printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
- sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
- "external", EXT4_SB(sb)->s_journal->j_devname);
+ if (EXT4_SB(sb)->s_journal) {
+ printk(KERN_INFO "EXT4 FS on %s, %s journal on %s\n",
+ sb->s_id, EXT4_SB(sb)->s_journal->j_inode ? "internal" :
+ "external", EXT4_SB(sb)->s_journal->j_devname);
+ } else {
+ printk(KERN_INFO "EXT4 FS on %s, no journal\n", sb->s_id);
+ }
return res;
}
@@ -1867,6 +1890,7 @@
unsigned long def_mount_opts;
struct inode *root;
char *cp;
+ const char *descr;
int ret = -EINVAL;
int blocksize;
int db_count;
@@ -2278,21 +2302,23 @@
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
ext4_commit_super(sb, es, 1);
- printk(KERN_CRIT
- "EXT4-fs (device %s): mount failed\n",
- sb->s_id);
goto failed_mount4;
}
}
} else if (journal_inum) {
if (ext4_create_journal(sb, es, journal_inum))
goto failed_mount3;
+ } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
+ EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+ printk(KERN_ERR "EXT4-fs: required journal recovery "
+ "suppressed and not mounted read-only\n");
+ goto failed_mount4;
} else {
- if (!silent)
- printk(KERN_ERR
- "ext4: No journal on filesystem on %s\n",
- sb->s_id);
- goto failed_mount3;
+ clear_opt(sbi->s_mount_opt, DATA_FLAGS);
+ set_opt(sbi->s_mount_opt, WRITEBACK_DATA);
+ sbi->s_journal = NULL;
+ needs_recovery = 0;
+ goto no_journal;
}
if (ext4_blocks_count(es) > 0xffffffffULL &&
@@ -2344,6 +2370,8 @@
break;
}
+no_journal:
+
if (test_opt(sb, NOBH)) {
if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - "
@@ -2428,13 +2456,22 @@
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
- if (needs_recovery)
+ if (needs_recovery) {
printk(KERN_INFO "EXT4-fs: recovery complete.\n");
- ext4_mark_recovery_complete(sb, es);
- printk(KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
- test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
- test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
- "writeback");
+ ext4_mark_recovery_complete(sb, es);
+ }
+ if (EXT4_SB(sb)->s_journal) {
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ descr = " journalled data mode";
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ descr = " ordered data mode";
+ else
+ descr = " writeback data mode";
+ } else
+ descr = "out journal";
+
+ printk(KERN_INFO "EXT4-fs: mounted filesystem %s with%s\n",
+ sb->s_id, descr);
lock_kernel();
return 0;
@@ -2446,8 +2483,11 @@
goto failed_mount;
failed_mount4:
- jbd2_journal_destroy(sbi->s_journal);
- sbi->s_journal = NULL;
+ printk(KERN_ERR "EXT4-fs (device %s): mount failed\n", sb->s_id);
+ if (sbi->s_journal) {
+ jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
+ }
failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
@@ -2508,6 +2548,8 @@
struct inode *journal_inode;
journal_t *journal;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
/* First, test for the existence of a valid inode on disk. Bad
* things happen if we iget() an unused inode, as the subsequent
* iput() will try to delete it. */
@@ -2556,6 +2598,8 @@
struct ext4_super_block *es;
struct block_device *bdev;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
bdev = ext4_blkdev_get(j_dev);
if (bdev == NULL)
return NULL;
@@ -2643,6 +2687,8 @@
int err = 0;
int really_read_only;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
if (journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
printk(KERN_INFO "EXT4-fs: external journal device major/minor "
@@ -2817,6 +2863,10 @@
{
journal_t *journal = EXT4_SB(sb)->s_journal;
+ if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+ BUG_ON(journal != NULL);
+ return;
+ }
jbd2_journal_lock_updates(journal);
if (jbd2_journal_flush(journal) < 0)
goto out;
@@ -2846,6 +2896,8 @@
int j_errno;
const char *errstr;
+ BUG_ON(!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL));
+
journal = EXT4_SB(sb)->s_journal;
/*
@@ -2878,14 +2930,17 @@
int ext4_force_commit(struct super_block *sb)
{
journal_t *journal;
- int ret;
+ int ret = 0;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
- sb->s_dirt = 0;
- ret = ext4_journal_force_commit(journal);
+ if (journal) {
+ sb->s_dirt = 0;
+ ret = ext4_journal_force_commit(journal);
+ }
+
return ret;
}
@@ -2897,9 +2952,13 @@
*/
static void ext4_write_super(struct super_block *sb)
{
- if (mutex_trylock(&sb->s_lock) != 0)
- BUG();
- sb->s_dirt = 0;
+ if (EXT4_SB(sb)->s_journal) {
+ if (mutex_trylock(&sb->s_lock) != 0)
+ BUG();
+ sb->s_dirt = 0;
+ } else {
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
+ }
}
static int ext4_sync_fs(struct super_block *sb, int wait)
@@ -2908,10 +2967,14 @@
trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
sb->s_dirt = 0;
- if (wait)
- ret = ext4_force_commit(sb);
- else
- jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+ if (EXT4_SB(sb)->s_journal) {
+ if (wait)
+ ret = ext4_force_commit(sb);
+ else
+ jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+ } else {
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, wait);
+ }
return ret;
}
@@ -2926,15 +2989,17 @@
if (!(sb->s_flags & MS_RDONLY)) {
journal_t *journal = EXT4_SB(sb)->s_journal;
- /* Now we set up the journal barrier. */
- jbd2_journal_lock_updates(journal);
+ if (journal) {
+ /* Now we set up the journal barrier. */
+ jbd2_journal_lock_updates(journal);
- /*
- * We don't want to clear needs_recovery flag when we failed
- * to flush the journal.
- */
- if (jbd2_journal_flush(journal) < 0)
- return;
+ /*
+ * We don't want to clear needs_recovery flag when we
+ * failed to flush the journal.
+ */
+ if (jbd2_journal_flush(journal) < 0)
+ return;
+ }
/* Journal blocked and flushed, clear needs_recovery flag. */
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -2948,7 +3013,7 @@
*/
static void ext4_unlockfs(struct super_block *sb)
{
- if (!(sb->s_flags & MS_RDONLY)) {
+ if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {
lock_super(sb);
/* Reser the needs_recovery flag before the fs is unlocked. */
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
@@ -2999,7 +3064,8 @@
es = sbi->s_es;
- ext4_init_journal_params(sb, sbi->s_journal);
+ if (sbi->s_journal)
+ ext4_init_journal_params(sb, sbi->s_journal);
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
n_blocks_count > ext4_blocks_count(es)) {
@@ -3028,9 +3094,11 @@
* We have to unlock super so that we can wait for
* transactions.
*/
- unlock_super(sb);
- ext4_mark_recovery_complete(sb, es);
- lock_super(sb);
+ if (sbi->s_journal) {
+ unlock_super(sb);
+ ext4_mark_recovery_complete(sb, es);
+ lock_super(sb);
+ }
} else {
__le32 ret;
if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
@@ -3084,7 +3152,8 @@
* been changed by e2fsck since we originally mounted
* the partition.)
*/
- ext4_clear_journal_err(sb, es);
+ if (sbi->s_journal)
+ ext4_clear_journal_err(sb, es);
sbi->s_mount_state = le16_to_cpu(es->s_state);
if ((err = ext4_group_extend(sb, es, n_blocks_count)))
goto restore_opts;
@@ -3092,6 +3161,9 @@
sb->s_flags &= ~MS_RDONLY;
}
}
+ if (sbi->s_journal == NULL)
+ ext4_commit_super(sb, es, 1);
+
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
@@ -3368,7 +3440,8 @@
* When we journal data on quota file, we have to flush journal to see
* all updates to the file when we bypass pagecache...
*/
- if (ext4_should_journal_data(path.dentry->d_inode)) {
+ if (EXT4_SB(sb)->s_journal &&
+ ext4_should_journal_data(path.dentry->d_inode)) {
/*
* We don't need to lock updates but journal_flush() could
* otherwise be livelocked...
@@ -3442,7 +3515,7 @@
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
- if (!handle) {
+ if (EXT4_SB(sb)->s_journal && !handle) {
printk(KERN_WARNING "EXT4-fs: Quota write (off=%llu, len=%llu)"
" cancelled because transaction is not started.\n",
(unsigned long long)off, (unsigned long long)len);
@@ -3467,7 +3540,7 @@
flush_dcache_page(bh->b_page);
unlock_buffer(bh);
if (journal_quota)
- err = ext4_journal_dirty_metadata(handle, bh);
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
else {
/* Always do at least ordered writes for quotas */
err = ext4_jbd2_file_inode(handle, inode);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 9b4a368..157ce65 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -457,7 +457,7 @@
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
sb->s_dirt = 1;
- ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
}
}
@@ -487,9 +487,9 @@
ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
} else {
le32_add_cpu(&BHDR(bh)->h_refcount, -1);
- error = ext4_journal_dirty_metadata(handle, bh);
+ error = ext4_handle_dirty_metadata(handle, inode, bh);
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
DQUOT_FREE_BLOCK(inode, 1);
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
@@ -724,8 +724,9 @@
if (error == -EIO)
goto bad_block;
if (!error)
- error = ext4_journal_dirty_metadata(handle,
- bs->bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode,
+ bs->bh);
if (error)
goto cleanup;
goto inserted;
@@ -794,8 +795,9 @@
ea_bdebug(new_bh, "reusing; refcount now=%d",
le32_to_cpu(BHDR(new_bh)->h_refcount));
unlock_buffer(new_bh);
- error = ext4_journal_dirty_metadata(handle,
- new_bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode,
+ new_bh);
if (error)
goto cleanup_dquot;
}
@@ -833,7 +835,8 @@
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
ext4_xattr_cache_insert(new_bh);
- error = ext4_journal_dirty_metadata(handle, new_bh);
+ error = ext4_handle_dirty_metadata(handle,
+ inode, new_bh);
if (error)
goto cleanup;
}
@@ -1040,7 +1043,7 @@
*/
is.iloc.bh = NULL;
if (IS_SYNC(inode))
- handle->h_sync = 1;
+ ext4_handle_sync(handle);
}
cleanup: