summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-03-22 20:36:55 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-22 20:36:55 +0300
commit9b03992f0c88baef524842e411fbdc147780dd5d (patch)
tree4fe0ccfee6f9ef0931e294f1aa951696af3ea70a /fs/ext4
parent14705fda8f6273501930dfe1d679ad4bec209f52 (diff)
parent919adbfec29d5b89b3e45620653cbeeb0d42e6fd (diff)
downloadlinux-9b03992f0c88baef524842e411fbdc147780dd5d.tar.xz
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o: "Fix some bugs in converting ext4 to use the new mount API, as well as more bug fixes and clean ups in the ext4 fast_commit feature (most notably, in the tracepoints). In the jbd2 layer, the t_handle_lock spinlock has been removed, with the last place where it was actually needed replaced with an atomic cmpxchg" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (35 commits) ext4: fix kernel doc warnings ext4: fix remaining two trace events to use same printk convention ext4: add commit tid info in ext4_fc_commit_start/stop trace events ext4: add commit_tid info in jbd debug log ext4: add transaction tid info in fc_track events ext4: add new trace event in ext4_fc_cleanup ext4: return early for non-eligible fast_commit track events ext4: do not call FC trace event in ext4_fc_commit() if FS does not support FC ext4: convert ext4_fc_track_dentry type events to use event class ext4: fix ext4_fc_stats trace point ext4: remove unused enum EXT4_FC_COMMIT_FAILED ext4: warn when dirtying page w/o buffers in data=journal mode doc: fixed a typo in ext4 documentation ext4: make mb_optimize_scan performance mount option work with extents ext4: make mb_optimize_scan option work with set/unset mount cmd ext4: don't BUG if someone dirty pages without asking ext4 first ext4: remove redundant assignment to variable split_flag1 ext4: fix underflow in ext4_max_bitmap_size() ext4: fix ext4_mb_clear_bb() kernel-doc comment ext4: fix fs corruption when tring to remove a non-empty directory with IO error ...
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c1
-rw-r--r--fs/ext4/block_validity.c26
-rw-r--r--fs/ext4/ext4.h7
-rw-r--r--fs/ext4/extents.c1
-rw-r--r--fs/ext4/fast_commit.c173
-rw-r--r--fs/ext4/fast_commit.h2
-rw-r--r--fs/ext4/inline.c9
-rw-r--r--fs/ext4/inode.c35
-rw-r--r--fs/ext4/ioctl.c6
-rw-r--r--fs/ext4/mballoc.c345
-rw-r--r--fs/ext4/namei.c25
-rw-r--r--fs/ext4/resize.c7
-rw-r--r--fs/ext4/super.c99
13 files changed, 472 insertions, 264 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index a0fb0c4bdc7c..78ee3ef795ae 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -411,6 +411,7 @@ verified:
* ext4_read_block_bitmap_nowait()
* @sb: super block
* @block_group: given block group
+ * @ignore_locked: ignore locked buffers
*
* Read the bitmap for a given block_group,and validate the
* bits for block/inode/inode tables are set in the bitmaps
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 4666b55b736e..5504f72bbbbe 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -292,15 +292,10 @@ void ext4_release_system_zone(struct super_block *sb)
call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
}
-/*
- * Returns 1 if the passed-in block region (start_blk,
- * start_blk+count) is valid; 0 if some part of the block region
- * overlaps with some other filesystem metadata blocks.
- */
-int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
- unsigned int count)
+int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+ ext4_fsblk_t start_blk, unsigned int count)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_system_blocks *system_blks;
struct ext4_system_zone *entry;
struct rb_node *n;
@@ -329,7 +324,9 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
else if (start_blk >= (entry->start_blk + entry->count))
n = n->rb_right;
else {
- ret = (entry->ino == inode->i_ino);
+ ret = 0;
+ if (inode)
+ ret = (entry->ino == inode->i_ino);
break;
}
}
@@ -338,6 +335,17 @@ out_rcu:
return ret;
}
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with some other filesystem metadata blocks.
+ */
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
+ unsigned int count)
+{
+ return ext4_sb_block_valid(inode->i_sb, inode, start_blk, count);
+}
+
int ext4_check_blockref(const char *function, unsigned int line,
struct inode *inode, __le32 *p, unsigned int max)
{
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index bcd3b9bf8069..3f87cca49f0c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1046,6 +1046,8 @@ struct ext4_inode_info {
/* Fast commit related info */
+ /* For tracking dentry create updates */
+ struct list_head i_fc_dilist;
struct list_head i_fc_list; /*
* inodes that need fast commit
* protected by sbi->s_fc_lock.
@@ -1279,7 +1281,7 @@ struct ext4_inode_info {
#define ext4_find_next_zero_bit find_next_zero_bit_le
#define ext4_find_next_bit find_next_bit_le
-extern void ext4_set_bits(void *bm, int cur, int len);
+extern void mb_set_bits(void *bm, int cur, int len);
/*
* Maximal mount counts between two filesystem checks
@@ -3707,6 +3709,9 @@ extern int ext4_inode_block_valid(struct inode *inode,
unsigned int count);
extern int ext4_check_blockref(const char *, unsigned int,
struct inode *, __le32 *, unsigned int);
+extern int ext4_sb_block_valid(struct super_block *sb, struct inode *inode,
+ ext4_fsblk_t start_blk, unsigned int count);
+
/* extents.c */
struct ext4_ext_path;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index c0f3f83e0c1b..0d98cf402282 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3368,7 +3368,6 @@ static int ext4_split_extent(handle_t *handle,
return -EFSCORRUPTED;
}
unwritten = ext4_ext_is_unwritten(ex);
- split_flag1 = 0;
if (map->m_lblk >= ee_block) {
split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 7964ee34e322..3d72565ec6e8 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -199,6 +199,7 @@ void ext4_fc_init_inode(struct inode *inode)
ext4_fc_reset_inode(inode);
ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
INIT_LIST_HEAD(&ei->i_fc_list);
+ INIT_LIST_HEAD(&ei->i_fc_dilist);
init_waitqueue_head(&ei->i_fc_wait);
atomic_set(&ei->i_fc_updates, 0);
}
@@ -279,6 +280,8 @@ void ext4_fc_stop_update(struct inode *inode)
void ext4_fc_del(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_fc_dentry_update *fc_dentry;
if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
@@ -286,7 +289,7 @@ void ext4_fc_del(struct inode *inode)
restart:
spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- if (list_empty(&ei->i_fc_list)) {
+ if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) {
spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
return;
}
@@ -295,8 +298,33 @@ restart:
ext4_fc_wait_committing_inode(inode);
goto restart;
}
- list_del_init(&ei->i_fc_list);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+
+ if (!list_empty(&ei->i_fc_list))
+ list_del_init(&ei->i_fc_list);
+
+ /*
+ * Since this inode is getting removed, let's also remove all FC
+ * dentry create references, since it is not needed to log it anyways.
+ */
+ if (list_empty(&ei->i_fc_dilist)) {
+ spin_unlock(&sbi->s_fc_lock);
+ return;
+ }
+
+ fc_dentry = list_first_entry(&ei->i_fc_dilist, struct ext4_fc_dentry_update, fcd_dilist);
+ WARN_ON(fc_dentry->fcd_op != EXT4_FC_TAG_CREAT);
+ list_del_init(&fc_dentry->fcd_list);
+ list_del_init(&fc_dentry->fcd_dilist);
+
+ WARN_ON(!list_empty(&ei->i_fc_dilist));
+ spin_unlock(&sbi->s_fc_lock);
+
+ if (fc_dentry->fcd_name.name &&
+ fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
+ kfree(fc_dentry->fcd_name.name);
+ kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
+
+ return;
}
/*
@@ -351,13 +379,6 @@ static int ext4_fc_track_template(
tid_t tid = 0;
int ret;
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
- return -EOPNOTSUPP;
-
- if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
- return -EINVAL;
-
tid = handle->h_transaction->t_tid;
mutex_lock(&ei->i_fc_lock);
if (tid == ei->i_sync_tid) {
@@ -427,7 +448,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
node->fcd_name.name = node->fcd_iname;
}
node->fcd_name.len = dentry->d_name.len;
-
+ INIT_LIST_HEAD(&node->fcd_dilist);
spin_lock(&sbi->s_fc_lock);
if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING)
@@ -435,6 +456,20 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
&sbi->s_fc_dentry_q[FC_Q_STAGING]);
else
list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]);
+
+ /*
+ * This helps us keep a track of all fc_dentry updates which is part of
+ * this ext4 inode. So in case the inode is getting unlinked, before
+ * even we get a chance to fsync, we could remove all fc_dentry
+ * references while evicting the inode in ext4_fc_del().
+ * Also with this, we don't need to loop over all the inodes in
+ * sbi->s_fc_q to get the corresponding inode in
+ * ext4_fc_commit_dentry_updates().
+ */
+ if (dentry_update->op == EXT4_FC_TAG_CREAT) {
+ WARN_ON(!list_empty(&ei->i_fc_dilist));
+ list_add_tail(&node->fcd_dilist, &ei->i_fc_dilist);
+ }
spin_unlock(&sbi->s_fc_lock);
mutex_lock(&ei->i_fc_lock);
@@ -452,12 +487,22 @@ void __ext4_fc_track_unlink(handle_t *handle,
ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
- trace_ext4_fc_track_unlink(inode, dentry, ret);
+ trace_ext4_fc_track_unlink(handle, inode, dentry, ret);
}
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
{
- __ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+ struct inode *inode = d_inode(dentry);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
+ __ext4_fc_track_unlink(handle, inode, dentry);
}
void __ext4_fc_track_link(handle_t *handle,
@@ -471,12 +516,22 @@ void __ext4_fc_track_link(handle_t *handle,
ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
- trace_ext4_fc_track_link(inode, dentry, ret);
+ trace_ext4_fc_track_link(handle, inode, dentry, ret);
}
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
{
- __ext4_fc_track_link(handle, d_inode(dentry), dentry);
+ struct inode *inode = d_inode(dentry);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
+ __ext4_fc_track_link(handle, inode, dentry);
}
void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
@@ -490,12 +545,22 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
(void *)&args, 0);
- trace_ext4_fc_track_create(inode, dentry, ret);
+ trace_ext4_fc_track_create(handle, inode, dentry, ret);
}
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
{
- __ext4_fc_track_create(handle, d_inode(dentry), dentry);
+ struct inode *inode = d_inode(dentry);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
+ __ext4_fc_track_create(handle, inode, dentry);
}
/* __track_fn for inode tracking */
@@ -511,6 +576,7 @@ static int __track_inode(struct inode *inode, void *arg, bool update)
void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
if (S_ISDIR(inode->i_mode))
@@ -522,8 +588,15 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
return;
}
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
- trace_ext4_fc_track_inode(inode, ret);
+ trace_ext4_fc_track_inode(handle, inode, ret);
}
struct __track_range_args {
@@ -561,18 +634,26 @@ static int __track_range(struct inode *inode, void *arg, bool update)
void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct __track_range_args args;
int ret;
if (S_ISDIR(inode->i_mode))
return;
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (sbi->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
args.start = start;
args.end = end;
ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1);
- trace_ext4_fc_track_range(inode, start, end, ret);
+ trace_ext4_fc_track_range(handle, inode, start, end, ret);
}
static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
@@ -954,7 +1035,7 @@ __releases(&sbi->s_fc_lock)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_fc_dentry_update *fc_dentry, *fc_dentry_n;
struct inode *inode;
- struct ext4_inode_info *ei, *ei_n;
+ struct ext4_inode_info *ei;
int ret;
if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN]))
@@ -970,21 +1051,16 @@ __releases(&sbi->s_fc_lock)
spin_lock(&sbi->s_fc_lock);
continue;
}
-
- inode = NULL;
- list_for_each_entry_safe(ei, ei_n, &sbi->s_fc_q[FC_Q_MAIN],
- i_fc_list) {
- if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) {
- inode = &ei->vfs_inode;
- break;
- }
- }
/*
- * If we don't find inode in our list, then it was deleted,
- * in which case, we don't need to record it's create tag.
+ * With fcd_dilist we need not loop in sbi->s_fc_q to get the
+ * corresponding inode pointer
*/
- if (!inode)
- continue;
+ WARN_ON(list_empty(&fc_dentry->fcd_dilist));
+ ei = list_first_entry(&fc_dentry->fcd_dilist,
+ struct ext4_inode_info, i_fc_dilist);
+ inode = &ei->vfs_inode;
+ WARN_ON(inode->i_ino != fc_dentry->fcd_ino);
+
spin_unlock(&sbi->s_fc_lock);
/*
@@ -1088,11 +1164,12 @@ out:
}
static void ext4_fc_update_stats(struct super_block *sb, int status,
- u64 commit_time, int nblks)
+ u64 commit_time, int nblks, tid_t commit_tid)
{
struct ext4_fc_stats *stats = &EXT4_SB(sb)->s_fc_stats;
- jbd_debug(1, "Fast commit ended with status = %d", status);
+ jbd_debug(1, "Fast commit ended with status = %d for tid %u",
+ status, commit_tid);
if (status == EXT4_FC_STATUS_OK) {
stats->fc_num_commits++;
stats->fc_numblks += nblks;
@@ -1110,7 +1187,7 @@ static void ext4_fc_update_stats(struct super_block *sb, int status,
} else {
stats->fc_skipped_commits++;
}
- trace_ext4_fc_commit_stop(sb, nblks, status);
+ trace_ext4_fc_commit_stop(sb, nblks, status, commit_tid);
}
/*
@@ -1128,13 +1205,13 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
int status = EXT4_FC_STATUS_OK, fc_bufs_before = 0;
ktime_t start_time, commit_time;
- trace_ext4_fc_commit_start(sb);
-
- start_time = ktime_get();
-
if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
return jbd2_complete_transaction(journal, commit_tid);
+ trace_ext4_fc_commit_start(sb, commit_tid);
+
+ start_time = ktime_get();
+
restart_fc:
ret = jbd2_fc_begin_commit(journal, commit_tid);
if (ret == -EALREADY) {
@@ -1142,14 +1219,16 @@ restart_fc:
if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
commit_tid > journal->j_commit_sequence)
goto restart_fc;
- ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0);
+ ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0,
+ commit_tid);
return 0;
} else if (ret) {
/*
* Commit couldn't start. Just update stats and perform a
* full commit.
*/
- ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0);
+ ext4_fc_update_stats(sb, EXT4_FC_STATUS_FAILED, 0, 0,
+ commit_tid);
return jbd2_complete_transaction(journal, commit_tid);
}
@@ -1181,12 +1260,12 @@ restart_fc:
* don't react too strongly to vast changes in the commit time
*/
commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
- ext4_fc_update_stats(sb, status, commit_time, nblks);
+ ext4_fc_update_stats(sb, status, commit_time, nblks, commit_tid);
return ret;
fallback:
ret = jbd2_fc_end_commit_fallback(journal);
- ext4_fc_update_stats(sb, status, 0, 0);
+ ext4_fc_update_stats(sb, status, 0, 0, commit_tid);
return ret;
}
@@ -1204,6 +1283,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
if (full && sbi->s_fc_bh)
sbi->s_fc_bh = NULL;
+ trace_ext4_fc_cleanup(journal, full, tid);
jbd2_fc_release_bufs(journal);
spin_lock(&sbi->s_fc_lock);
@@ -1228,6 +1308,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
struct ext4_fc_dentry_update,
fcd_list);
list_del_init(&fc_dentry->fcd_list);
+ list_del_init(&fc_dentry->fcd_dilist);
spin_unlock(&sbi->s_fc_lock);
if (fc_dentry->fcd_name.name &&
@@ -1875,8 +1956,8 @@ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk)
if (state->fc_regions[i].ino == 0 ||
state->fc_regions[i].len == 0)
continue;
- if (blk >= state->fc_regions[i].pblk &&
- blk < state->fc_regions[i].pblk + state->fc_regions[i].len)
+ if (in_range(blk, state->fc_regions[i].pblk,
+ state->fc_regions[i].len))
return true;
}
return false;
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 083ad1cb705a..80414dcba6e1 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -93,7 +93,6 @@ enum {
EXT4_FC_REASON_RENAME_DIR,
EXT4_FC_REASON_FALLOC_RANGE,
EXT4_FC_REASON_INODE_JOURNAL_DATA,
- EXT4_FC_COMMIT_FAILED,
EXT4_FC_REASON_MAX
};
@@ -109,6 +108,7 @@ struct ext4_fc_dentry_update {
struct qstr fcd_name; /* Dirent name */
unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */
struct list_head fcd_list;
+ struct list_head fcd_dilist;
};
struct ext4_fc_stats {
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index e42941803605..9c076262770d 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1783,19 +1783,20 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
void *inline_pos;
unsigned int offset;
struct ext4_dir_entry_2 *de;
- bool ret = true;
+ bool ret = false;
err = ext4_get_inode_loc(dir, &iloc);
if (err) {
EXT4_ERROR_INODE_ERR(dir, -err,
"error %d getting inode %lu block",
err, dir->i_ino);
- return true;
+ return false;
}
down_read(&EXT4_I(dir)->xattr_sem);
if (!ext4_has_inline_data(dir)) {
*has_inline_data = 0;
+ ret = true;
goto out;
}
@@ -1804,7 +1805,6 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - no `..'",
dir->i_ino);
- ret = true;
goto out;
}
@@ -1823,16 +1823,15 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
dir->i_ino, le32_to_cpu(de->inode),
le16_to_cpu(de->rec_len), de->name_len,
inline_size);
- ret = true;
goto out;
}
if (le32_to_cpu(de->inode)) {
- ret = false;
goto out;
}
offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
}
+ ret = true;
out:
up_read(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4cf55ef54193..3d0ca48d20c8 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1993,6 +1993,15 @@ static int ext4_writepage(struct page *page,
else
len = PAGE_SIZE;
+ /* Should never happen but for bugs in other kernel subsystems */
+ if (!page_has_buffers(page)) {
+ ext4_warning_inode(inode,
+ "page %lu does not have buffers attached", page->index);
+ ClearPageDirty(page);
+ unlock_page(page);
+ return 0;
+ }
+
page_bufs = page_buffers(page);
/*
* We cannot do block allocation or other extent handling in this
@@ -2594,6 +2603,22 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
+ /*
+ * Should never happen but for buggy code in
+ * other subsystems that call
+ * set_page_dirty() without properly warning
+ * the file system first. See [1] for more
+ * information.
+ *
+ * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz
+ */
+ if (!page_has_buffers(page)) {
+ ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index);
+ ClearPageDirty(page);
+ unlock_page(page);
+ continue;
+ }
+
if (mpd->map.m_len == 0)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
@@ -3548,10 +3573,11 @@ const struct iomap_ops ext4_iomap_report_ops = {
};
/*
- * Pages can be marked dirty completely asynchronously from ext4's journalling
- * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do
- * much here because ->set_page_dirty is called under VFS locks. The page is
- * not necessarily locked.
+ * Whenever the page is being dirtied, corresponding buffers should already be
+ * attached to the transaction (we take care of this in ext4_page_mkwrite() and
+ * ext4_write_begin()). However we cannot move buffers to dirty transaction
+ * lists here because ->set_page_dirty is called under VFS locks and the page
+ * is not necessarily locked.
*
* We cannot just dirty the page and leave attached buffers clean, because the
* buffers' dirty state is "definitive". We cannot just set the buffers dirty
@@ -3562,6 +3588,7 @@ const struct iomap_ops ext4_iomap_report_ops = {
*/
static int ext4_journalled_set_page_dirty(struct page *page)
{
+ WARN_ON_ONCE(!page_has_buffers(page));
SetPageChecked(page);
return __set_page_dirty_nobuffers(page);
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index a8022c2c6a58..992229ca2d83 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -269,7 +269,7 @@ out:
return err ? err : 0;
}
-/**
+/*
* Swap memory between @a and @b for @len bytes.
*
* @a: pointer to first memory area
@@ -290,7 +290,7 @@ static void memswap(void *a, void *b, size_t len)
}
}
-/**
+/*
* Swap i_data and associated attributes between @inode1 and @inode2.
* This function is used for the primary swap between inode1 and inode2
* and also to revert this primary swap in case of errors.
@@ -344,7 +344,7 @@ void ext4_reset_inode_seed(struct inode *inode)
ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, sizeof(gen));
}
-/**
+/*
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 67ac95c4cd9b..252c168454c7 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1000,7 +1000,7 @@ static inline int should_optimize_scan(struct ext4_allocation_context *ac)
return 0;
if (ac->ac_criteria >= 2)
return 0;
- if (ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))
+ if (!ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))
return 0;
return 1;
}
@@ -1689,7 +1689,7 @@ static int mb_test_and_clear_bits(void *bm, int cur, int len)
return zero_bit;
}
-void ext4_set_bits(void *bm, int cur, int len)
+void mb_set_bits(void *bm, int cur, int len)
{
__u32 *addr;
@@ -1996,7 +1996,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info);
- ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
+ mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
mb_check_buddy(e4b);
return ret;
@@ -3825,7 +3825,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
* We leak some of the blocks here.
*/
ext4_lock_group(sb, ac->ac_b_ex.fe_group);
- ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -3844,7 +3844,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
}
}
#endif
- ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+ mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
if (ext4_has_group_desc_csum(sb) &&
(gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
@@ -3899,69 +3899,103 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i, clen, err;
+ int i, err;
int already;
+ unsigned int clen, clen_changed, thisgrp_len;
- clen = EXT4_B2C(sbi, len);
+ while (len > 0) {
+ ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
- ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
- bitmap_bh = ext4_read_block_bitmap(sb, group);
- if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- bitmap_bh = NULL;
- goto out_err;
- }
+ /*
+ * Check to see if we are freeing blocks across a group
+ * boundary.
+ * In case of flex_bg, this can happen that (block, len) may
+ * span across more than one group. In that case we need to
+ * get the corresponding group metadata to work with.
+ * For this we have goto again loop.
+ */
+ thisgrp_len = min_t(unsigned int, (unsigned int)len,
+ EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
+ clen = EXT4_NUM_B2C(sbi, thisgrp_len);
+
+ if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) {
+ ext4_error(sb, "Marking blocks in system zone - "
+ "Block = %llu, len = %u",
+ block, thisgrp_len);
+ bitmap_bh = NULL;
+ break;
+ }
- err = -EIO;
- gdp = ext4_get_group_desc(sb, group, &gdp_bh);
- if (!gdp)
- goto out_err;
+ bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (IS_ERR(bitmap_bh)) {
+ err = PTR_ERR(bitmap_bh);
+ bitmap_bh = NULL;
+ break;
+ }
- ext4_lock_group(sb, group);
- already = 0;
- for (i = 0; i < clen; i++)
- if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
- already++;
+ err = -EIO;
+ gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+ if (!gdp)
+ break;
- if (state)
- ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
- else
- mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
- if (ext4_has_group_desc_csum(sb) &&
- (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
- gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_group_clusters_set(sb, gdp,
- ext4_free_clusters_after_init(sb,
- group, gdp));
- }
- if (state)
- clen = ext4_free_group_clusters(sb, gdp) - clen + already;
- else
- clen = ext4_free_group_clusters(sb, gdp) + clen - already;
+ ext4_lock_group(sb, group);
+ already = 0;
+ for (i = 0; i < clen; i++)
+ if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) ==
+ !state)
+ already++;
+
+ clen_changed = clen - already;
+ if (state)
+ mb_set_bits(bitmap_bh->b_data, blkoff, clen);
+ else
+ mb_clear_bits(bitmap_bh->b_data, blkoff, clen);
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_clusters_after_init(sb, group, gdp));
+ }
+ if (state)
+ clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
+ else
+ clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
- ext4_free_group_clusters_set(sb, gdp, clen);
- ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
- ext4_group_desc_csum_set(sb, group, gdp);
+ ext4_free_group_clusters_set(sb, gdp, clen);
+ ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
- ext4_unlock_group(sb, group);
+ ext4_unlock_group(sb, group);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t flex_group = ext4_flex_group(sbi, group);
+ if (sbi->s_log_groups_per_flex) {
+ ext4_group_t flex_group = ext4_flex_group(sbi, group);
+ struct flex_groups *fg = sbi_array_rcu_deref(sbi,
+ s_flex_groups, flex_group);
- atomic64_sub(len,
- &sbi_array_rcu_deref(sbi, s_flex_groups,
- flex_group)->free_clusters);
+ if (state)
+ atomic64_sub(clen_changed, &fg->free_clusters);
+ else
+ atomic64_add(clen_changed, &fg->free_clusters);
+
+ }
+
+ err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+ if (err)
+ break;
+ sync_dirty_buffer(bitmap_bh);
+ err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+ sync_dirty_buffer(gdp_bh);
+ if (err)
+ break;
+
+ block += thisgrp_len;
+ len -= thisgrp_len;
+ brelse(bitmap_bh);
+ BUG_ON(len < 0);
}
- err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
if (err)
- goto out_err;
- sync_dirty_buffer(bitmap_bh);
- err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
- sync_dirty_buffer(gdp_bh);
-
-out_err:
- brelse(bitmap_bh);
+ brelse(bitmap_bh);
}
/*
@@ -4433,7 +4467,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
while (n) {
entry = rb_entry(n, struct ext4_free_data, efd_node);
- ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
+ mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
n = rb_next(n);
}
return;
@@ -4474,7 +4508,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
if (unlikely(len == 0))
continue;
BUG_ON(groupnr != group);
- ext4_set_bits(bitmap, start, len);
+ mb_set_bits(bitmap, start, len);
preallocated += len;
}
mb_debug(sb, "preallocated %d for group %u\n", preallocated, group);
@@ -5846,17 +5880,17 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
}
/**
- * ext4_free_blocks() -- Free given blocks and update quota
+ * ext4_mb_clear_bb() -- helper function for freeing blocks.
+ * Used by ext4_free_blocks()
* @handle: handle for this transaction
* @inode: inode
- * @bh: optional buffer of the block to be freed
* @block: starting physical block to be freed
* @count: number of blocks to be freed
* @flags: flags used by ext4_free_blocks
*/
-void ext4_free_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *bh, ext4_fsblk_t block,
- unsigned long count, int flags)
+static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t block, unsigned long count,
+ int flags)
{
struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
@@ -5873,80 +5907,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
sbi = EXT4_SB(sb);
- if (sbi->s_mount_state & EXT4_FC_REPLAY) {
- ext4_free_blocks_simple(inode, block, count);
- return;
- }
-
- might_sleep();
- if (bh) {
- if (block)
- BUG_ON(block != bh->b_blocknr);
- else
- block = bh->b_blocknr;
- }
-
- if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
- !ext4_inode_block_valid(inode, block, count)) {
- ext4_error(sb, "Freeing blocks not in datazone - "
- "block = %llu, count = %lu", block, count);
- goto error_return;
- }
-
- ext4_debug("freeing block %llu\n", block);
- trace_ext4_free_blocks(inode, block, count, flags);
-
- if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
- BUG_ON(count > 1);
-
- ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
- inode, bh, block);
- }
-
- /*
- * If the extent to be freed does not begin on a cluster
- * boundary, we need to deal with partial clusters at the
- * beginning and end of the extent. Normally we will free
- * blocks at the beginning or the end unless we are explicitly
- * requested to avoid doing so.
- */
- overflow = EXT4_PBLK_COFF(sbi, block);
- if (overflow) {
- if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
- overflow = sbi->s_cluster_ratio - overflow;
- block += overflow;
- if (count > overflow)
- count -= overflow;
- else
- return;
- } else {
- block -= overflow;
- count += overflow;
- }
- }
- overflow = EXT4_LBLK_COFF(sbi, count);
- if (overflow) {
- if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
- if (count > overflow)
- count -= overflow;
- else
- return;
- } else
- count += sbi->s_cluster_ratio - overflow;
- }
-
- if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
- int i;
- int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
-
- for (i = 0; i < count; i++) {
- cond_resched();
- if (is_metadata)
- bh = sb_find_get_block(inode->i_sb, block + i);
- ext4_forget(handle, is_metadata, inode, bh, block + i);
- }
- }
-
do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -5977,13 +5937,7 @@ do_more:
goto error_return;
}
- if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
- in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
- in_range(block, ext4_inode_table(sb, gdp),
- sbi->s_itb_per_group) ||
- in_range(block + count - 1, ext4_inode_table(sb, gdp),
- sbi->s_itb_per_group)) {
-
+ if (!ext4_inode_block_valid(inode, block, count)) {
ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
/* err = 0. ext4_std_error should be a no op */
@@ -6054,7 +6008,7 @@ do_more:
NULL);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
- " group:%d block:%d count:%lu failed"
+ " group:%u block:%d count:%lu failed"
" with %d", block_group, bit, count,
err);
} else
@@ -6115,6 +6069,103 @@ error_return:
}
/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle: handle for this transaction
+ * @inode: inode
+ * @bh: optional buffer of the block to be freed
+ * @block: starting physical block to be freed
+ * @count: number of blocks to be freed
+ * @flags: flags used by ext4_free_blocks
+ */
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block,
+ unsigned long count, int flags)
+{
+ struct super_block *sb = inode->i_sb;
+ unsigned int overflow;
+ struct ext4_sb_info *sbi;
+
+ sbi = EXT4_SB(sb);
+
+ if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+ ext4_free_blocks_simple(inode, block, count);
+ return;
+ }
+
+ might_sleep();
+ if (bh) {
+ if (block)
+ BUG_ON(block != bh->b_blocknr);
+ else
+ block = bh->b_blocknr;
+ }
+
+ if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
+ !ext4_inode_block_valid(inode, block, count)) {
+ ext4_error(sb, "Freeing blocks not in datazone - "
+ "block = %llu, count = %lu", block, count);
+ return;
+ }
+
+ ext4_debug("freeing block %llu\n", block);
+ trace_ext4_free_blocks(inode, block, count, flags);
+
+ if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
+ BUG_ON(count > 1);
+
+ ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
+ inode, bh, block);
+ }
+
+ /*
+ * If the extent to be freed does not begin on a cluster
+ * boundary, we need to deal with partial clusters at the
+ * beginning and end of the extent. Normally we will free
+ * blocks at the beginning or the end unless we are explicitly
+ * requested to avoid doing so.
+ */
+ overflow = EXT4_PBLK_COFF(sbi, block);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
+ overflow = sbi->s_cluster_ratio - overflow;
+ block += overflow;
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else {
+ block -= overflow;
+ count += overflow;
+ }
+ }
+ overflow = EXT4_LBLK_COFF(sbi, count);
+ if (overflow) {
+ if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
+ if (count > overflow)
+ count -= overflow;
+ else
+ return;
+ } else
+ count += sbi->s_cluster_ratio - overflow;
+ }
+
+ if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
+ int i;
+ int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
+
+ for (i = 0; i < count; i++) {
+ cond_resched();
+ if (is_metadata)
+ bh = sb_find_get_block(inode->i_sb, block + i);
+ ext4_forget(handle, is_metadata, inode, bh, block + i);
+ }
+ }
+
+ ext4_mb_clear_bb(handle, inode, block, count, flags);
+ return;
+}
+
+/**
* ext4_group_add_blocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
@@ -6170,11 +6221,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
goto error_return;
}
- if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
- in_range(ext4_inode_bitmap(sb, desc), block, count) ||
- in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
- in_range(block + count - 1, ext4_inode_table(sb, desc),
- sbi->s_itb_per_group)) {
+ if (!ext4_sb_block_valid(sb, NULL, block, count)) {
ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 8cf0a924a49b..e37da8d5cd0c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2997,14 +2997,14 @@ bool ext4_empty_dir(struct inode *inode)
if (inode->i_size < ext4_dir_rec_len(1, NULL) +
ext4_dir_rec_len(2, NULL)) {
EXT4_ERROR_INODE(inode, "invalid size");
- return true;
+ return false;
}
/* The first directory block must not be a hole,
* so treat it as DIRENT_HTREE
*/
bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
if (IS_ERR(bh))
- return true;
+ return false;
de = (struct ext4_dir_entry_2 *) bh->b_data;
if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
@@ -3012,7 +3012,7 @@ bool ext4_empty_dir(struct inode *inode)
le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) {
ext4_warning_inode(inode, "directory missing '.'");
brelse(bh);
- return true;
+ return false;
}
offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
de = ext4_next_entry(de, sb->s_blocksize);
@@ -3021,7 +3021,7 @@ bool ext4_empty_dir(struct inode *inode)
le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) {
ext4_warning_inode(inode, "directory missing '..'");
brelse(bh);
- return true;
+ return false;
}
offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
while (offset < inode->i_size) {
@@ -3035,7 +3035,7 @@ bool ext4_empty_dir(struct inode *inode)
continue;
}
if (IS_ERR(bh))
- return true;
+ return false;
}
de = (struct ext4_dir_entry_2 *) (bh->b_data +
(offset & (sb->s_blocksize - 1)));
@@ -3891,12 +3891,19 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
ext4_fc_mark_ineligible(old.inode->i_sb,
EXT4_FC_REASON_RENAME_DIR, handle);
} else {
+ struct super_block *sb = old.inode->i_sb;
+
if (new.inode)
ext4_fc_track_unlink(handle, new.dentry);
- __ext4_fc_track_link(handle, old.inode, new.dentry);
- __ext4_fc_track_unlink(handle, old.inode, old.dentry);
- if (whiteout)
- __ext4_fc_track_create(handle, whiteout, old.dentry);
+ if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+ !(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+ !(ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE))) {
+ __ext4_fc_track_link(handle, old.inode, new.dentry);
+ __ext4_fc_track_unlink(handle, old.inode, old.dentry);
+ if (whiteout)
+ __ext4_fc_track_create(handle, whiteout,
+ old.dentry);
+ }
}
if (new.inode) {
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index ee8f02f406cb..90a941d20dff 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -14,6 +14,7 @@
#include <linux/errno.h>
#include <linux/slab.h>
+#include <linux/jiffies.h>
#include "ext4_jbd2.h"
@@ -483,7 +484,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
}
ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n",
first_cluster, first_cluster - start, count2);
- ext4_set_bits(bh->b_data, first_cluster - start, count2);
+ mb_set_bits(bh->b_data, first_cluster - start, count2);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
@@ -632,7 +633,7 @@ handle_bb:
if (overhead != 0) {
ext4_debug("mark backup superblock %#04llx (+0)\n",
start);
- ext4_set_bits(bh->b_data, 0,
+ mb_set_bits(bh->b_data, 0,
EXT4_NUM_B2C(sbi, overhead));
}
ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count),
@@ -2100,7 +2101,7 @@ retry:
*/
while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
flexbg_size)) {
- if (jiffies - last_update_time > HZ * 10) {
+ if (time_is_before_jiffies(last_update_time + HZ * 10)) {
if (last_update_time)
ext4_msg(sb, KERN_INFO,
"resized to %llu blocks",
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c5021ca0a28a..4120a743be52 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2021,12 +2021,12 @@ static int ext4_set_test_dummy_encryption(struct super_block *sb, char *arg)
#define EXT4_SPEC_s_commit_interval (1 << 16)
#define EXT4_SPEC_s_fc_debug_max_replay (1 << 17)
#define EXT4_SPEC_s_sb_block (1 << 18)
+#define EXT4_SPEC_mb_optimize_scan (1 << 19)
struct ext4_fs_context {
char *s_qf_names[EXT4_MAXQUOTAS];
char *test_dummy_enc_arg;
int s_jquota_fmt; /* Format of quota to use */
- int mb_optimize_scan;
#ifdef CONFIG_EXT4_DEBUG
int s_fc_debug_max_replay;
#endif
@@ -2045,8 +2045,8 @@ struct ext4_fs_context {
unsigned int mask_s_mount_opt;
unsigned int vals_s_mount_opt2;
unsigned int mask_s_mount_opt2;
- unsigned int vals_s_mount_flags;
- unsigned int mask_s_mount_flags;
+ unsigned long vals_s_mount_flags;
+ unsigned long mask_s_mount_flags;
unsigned int opt_flags; /* MOPT flags */
unsigned int spec;
u32 s_max_batch_time;
@@ -2149,23 +2149,36 @@ static inline void ctx_set_##name(struct ext4_fs_context *ctx, \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name |= flag; \
-} \
+}
+
+#define EXT4_CLEAR_CTX(name) \
static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \
unsigned long flag) \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name &= ~flag; \
-} \
+}
+
+#define EXT4_TEST_CTX(name) \
static inline unsigned long \
ctx_test_##name(struct ext4_fs_context *ctx, unsigned long flag) \
{ \
return (ctx->vals_s_##name & flag); \
-} \
+}
-EXT4_SET_CTX(flags);
+EXT4_SET_CTX(flags); /* set only */
EXT4_SET_CTX(mount_opt);
+EXT4_CLEAR_CTX(mount_opt);
+EXT4_TEST_CTX(mount_opt);
EXT4_SET_CTX(mount_opt2);
-EXT4_SET_CTX(mount_flags);
+EXT4_CLEAR_CTX(mount_opt2);
+EXT4_TEST_CTX(mount_opt2);
+
+static inline void ctx_set_mount_flag(struct ext4_fs_context *ctx, int bit)
+{
+ set_bit(bit, &ctx->mask_s_mount_flags);
+ set_bit(bit, &ctx->vals_s_mount_flags);
+}
static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
@@ -2235,7 +2248,7 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
param->key);
return 0;
case Opt_abort:
- ctx_set_mount_flags(ctx, EXT4_MF_FS_ABORTED);
+ ctx_set_mount_flag(ctx, EXT4_MF_FS_ABORTED);
return 0;
case Opt_i_version:
ext4_msg(NULL, KERN_WARNING, deprecated_msg, param->key, "5.20");
@@ -2451,12 +2464,17 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
ctx_clear_mount_opt(ctx, m->mount_opt);
return 0;
case Opt_mb_optimize_scan:
- if (result.int_32 != 0 && result.int_32 != 1) {
+ if (result.int_32 == 1) {
+ ctx_set_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
+ ctx->spec |= EXT4_SPEC_mb_optimize_scan;
+ } else if (result.int_32 == 0) {
+ ctx_clear_mount_opt2(ctx, EXT4_MOUNT2_MB_OPTIMIZE_SCAN);
+ ctx->spec |= EXT4_SPEC_mb_optimize_scan;
+ } else {
ext4_msg(NULL, KERN_WARNING,
"mb_optimize_scan should be set to 0 or 1.");
return -EINVAL;
}
- ctx->mb_optimize_scan = result.int_32;
return 0;
}
@@ -3468,8 +3486,9 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files)
*/
static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
{
- unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS;
+ loff_t upper_limit, res = EXT4_NDIR_BLOCKS;
int meta_blocks;
+ unsigned int ppb = 1 << (bits - 2);
/*
* This is calculated to be the largest file size for a dense, block
@@ -3501,27 +3520,42 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files)
}
+ /* Compute how many blocks we can address by block tree */
+ res += ppb;
+ res += ppb * ppb;
+ res += ((loff_t)ppb) * ppb * ppb;
+ /* Compute how many metadata blocks are needed */
+ meta_blocks = 1;
+ meta_blocks += 1 + ppb;
+ meta_blocks += 1 + ppb + ppb * ppb;
+ /* Does block tree limit file size? */
+ if (res + meta_blocks <= upper_limit)
+ goto check_lfs;
+
+ res = upper_limit;
+ /* How many metadata blocks are needed for addressing upper_limit? */
+ upper_limit -= EXT4_NDIR_BLOCKS;
/* indirect blocks */
meta_blocks = 1;
+ upper_limit -= ppb;
/* double indirect blocks */
- meta_blocks += 1 + (1LL << (bits-2));
- /* tripple indirect blocks */
- meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
-
- upper_limit -= meta_blocks;
- upper_limit <<= bits;
-
- res += 1LL << (bits-2);
- res += 1LL << (2*(bits-2));
- res += 1LL << (3*(bits-2));
+ if (upper_limit < ppb * ppb) {
+ meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb);
+ res -= meta_blocks;
+ goto check_lfs;
+ }
+ meta_blocks += 1 + ppb;
+ upper_limit -= ppb * ppb;
+ /* tripple indirect blocks for the rest */
+ meta_blocks += 1 + DIV_ROUND_UP_ULL(upper_limit, ppb) +
+ DIV_ROUND_UP_ULL(upper_limit, ppb*ppb);
+ res -= meta_blocks;
+check_lfs:
res <<= bits;
- if (res > upper_limit)
- res = upper_limit;
-
if (res > MAX_LFS_FILESIZE)
res = MAX_LFS_FILESIZE;
- return (loff_t)res;
+ return res;
}
static ext4_fsblk_t descriptor_loc(struct super_block *sb,
@@ -4369,7 +4403,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
/* Set defaults for the variables that will be set during parsing */
ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
- ctx->mb_optimize_scan = DEFAULT_MB_OPTIMIZE_SCAN;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sectors_written_start =
@@ -5320,12 +5353,12 @@ no_journal:
* turned off by passing "mb_optimize_scan=0". This can also be
* turned on forcefully by passing "mb_optimize_scan=1".
*/
- if (ctx->mb_optimize_scan == 1)
- set_opt2(sb, MB_OPTIMIZE_SCAN);
- else if (ctx->mb_optimize_scan == 0)
- clear_opt2(sb, MB_OPTIMIZE_SCAN);
- else if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
- set_opt2(sb, MB_OPTIMIZE_SCAN);
+ if (!(ctx->spec & EXT4_SPEC_mb_optimize_scan)) {
+ if (sbi->s_groups_count >= MB_DEFAULT_LINEAR_SCAN_THRESHOLD)
+ set_opt2(sb, MB_OPTIMIZE_SCAN);
+ else
+ clear_opt2(sb, MB_OPTIMIZE_SCAN);
+ }
err = ext4_mb_init(sb);
if (err) {