aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h18
-rw-r--r--fs/ext4/extents.c47
-rw-r--r--fs/ext4/extents_status.c4
-rw-r--r--fs/ext4/fast_commit.c170
-rw-r--r--fs/ext4/fast_commit.h19
-rw-r--r--fs/ext4/fsmap.h4
-rw-r--r--fs/ext4/ialloc.c17
-rw-r--r--fs/ext4/inline.c11
-rw-r--r--fs/ext4/inode.c10
-rw-r--r--fs/ext4/ioctl.c80
-rw-r--r--fs/ext4/mballoc.c2
-rw-r--r--fs/ext4/mmp.c28
-rw-r--r--fs/ext4/namei.c8
-rw-r--r--fs/ext4/resize.c9
-rw-r--r--fs/ext4/super.c68
-rw-r--r--fs/ext4/sysfs.c9
-rw-r--r--fs/ext4/xattr.c26
-rw-r--r--fs/ext4/xattr.h6
18 files changed, 291 insertions, 245 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 37002663d521..3c51e243450d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -720,6 +720,7 @@ enum {
#define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40)
#define EXT4_IOC_GETSTATE _IOW('f', 41, __u32)
#define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap)
+#define EXT4_IOC_CHECKPOINT _IOW('f', 43, __u32)
#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
@@ -741,6 +742,14 @@ enum {
#define EXT4_STATE_FLAG_NEWENTRY 0x00000004
#define EXT4_STATE_FLAG_DA_ALLOC_CLOSE 0x00000008
+/* flags for ioctl EXT4_IOC_CHECKPOINT */
+#define EXT4_IOC_CHECKPOINT_FLAG_DISCARD 0x1
+#define EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT 0x2
+#define EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN 0x4
+#define EXT4_IOC_CHECKPOINT_FLAG_VALID (EXT4_IOC_CHECKPOINT_FLAG_DISCARD | \
+ EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \
+ EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
+
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
@@ -1477,7 +1486,7 @@ struct ext4_sb_info {
unsigned int s_inode_goal;
u32 s_hash_seed[4];
int s_def_hash_version;
- int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */
+ int s_hash_unsigned; /* 3 if hash should be unsigned, 0 if not */
struct percpu_counter s_freeclusters_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
@@ -1488,6 +1497,7 @@ struct ext4_sb_info {
struct kobject s_kobj;
struct completion s_kobj_unregister;
struct super_block *s_sb;
+ struct buffer_head *s_mmp_bh;
/* Journaling */
struct journal_s *s_journal;
@@ -3614,6 +3624,7 @@ extern const struct inode_operations ext4_symlink_inode_operations;
extern const struct inode_operations ext4_fast_symlink_inode_operations;
/* sysfs.c */
+extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi);
extern int ext4_register_sysfs(struct super_block *sb);
extern void ext4_unregister_sysfs(struct super_block *sb);
extern int __init ext4_init_sysfs(void);
@@ -3720,6 +3731,9 @@ extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
/* mmp.c */
extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
+/* mmp.c */
+extern void ext4_stop_mmpd(struct ext4_sb_info *sbi);
+
/* verity.c */
extern const struct fsverity_operations ext4_verityops;
@@ -3784,7 +3798,7 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh)
* have to read the block because we may read the old data
* successfully.
*/
- if (!buffer_uptodate(bh) && buffer_write_io_error(bh))
+ if (buffer_write_io_error(bh))
set_buffer_uptodate(bh);
return buffer_uptodate(bh);
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 77c84d6f1af6..92ad64b89d9b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -825,6 +825,7 @@ void ext4_ext_tree_init(handle_t *handle, struct inode *inode)
eh->eh_entries = 0;
eh->eh_magic = EXT4_EXT_MAGIC;
eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
+ eh->eh_generation = 0;
ext4_mark_inode_dirty(handle, inode);
}
@@ -1090,6 +1091,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0));
neh->eh_magic = EXT4_EXT_MAGIC;
neh->eh_depth = 0;
+ neh->eh_generation = 0;
/* move remainder of path[depth] to the new leaf */
if (unlikely(path[depth].p_hdr->eh_entries !=
@@ -1167,6 +1169,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
neh->eh_magic = EXT4_EXT_MAGIC;
neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0));
neh->eh_depth = cpu_to_le16(depth - i);
+ neh->eh_generation = 0;
fidx = EXT_FIRST_INDEX(neh);
fidx->ei_block = border;
ext4_idx_store_pblock(fidx, oldblock);
@@ -1306,6 +1309,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
neh->eh_magic = EXT4_EXT_MAGIC;
ext4_extent_block_csum_set(inode, neh);
set_buffer_uptodate(bh);
+ set_buffer_verified(bh);
unlock_buffer(bh);
err = ext4_handle_dirty_metadata(handle, inode, bh);
@@ -3206,7 +3210,10 @@ static int ext4_split_extent_at(handle_t *handle,
ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
- if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ if (err != -ENOSPC && err != -EDQUOT)
+ goto out;
+
+ if (EXT4_EXT_MAY_ZEROOUT & split_flag) {
if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
if (split_flag & EXT4_EXT_DATA_VALID1) {
err = ext4_ext_zeroout(inode, ex2);
@@ -3232,25 +3239,22 @@ static int ext4_split_extent_at(handle_t *handle,
ext4_ext_pblock(&orig_ex));
}
- if (err)
- goto fix_extent_len;
- /* update the extent length and mark as initialized */
- ex->ee_len = cpu_to_le16(ee_len);
- ext4_ext_try_to_merge(handle, inode, path, ex);
- err = ext4_ext_dirty(handle, inode, path + path->p_depth);
- if (err)
- goto fix_extent_len;
-
- /* update extent status tree */
- err = ext4_zeroout_es(inode, &zero_ex);
-
- goto out;
- } else if (err)
- goto fix_extent_len;
-
-out:
- ext4_ext_show_leaf(inode, path);
- return err;
+ if (!err) {
+ /* update the extent length and mark as initialized */
+ ex->ee_len = cpu_to_le16(ee_len);
+ ext4_ext_try_to_merge(handle, inode, path, ex);
+ err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+ if (!err)
+ /* update extent status tree */
+ err = ext4_zeroout_es(inode, &zero_ex);
+ /* If we failed at this point, we don't know in which
+ * state the extent tree exactly is so don't try to fix
+ * length of the original extent as it may do even more
+ * damage.
+ */
+ goto out;
+ }
+ }
fix_extent_len:
ex->ee_len = orig_ex.ee_len;
@@ -3260,6 +3264,9 @@ fix_extent_len:
*/
ext4_ext_dirty(handle, inode, path + path->p_depth);
return err;
+out:
+ ext4_ext_show_leaf(inode, path);
+ return err;
}
/*
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 0a729027322d..9a3a8996aacf 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -1574,11 +1574,9 @@ static unsigned long ext4_es_scan(struct shrinker *shrink,
ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret);
- if (!nr_to_scan)
- return ret;
-
nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL);
+ ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt);
trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret);
return nr_shrunk;
}
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f98ca4f37ef6..e8195229c252 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1288,28 +1288,29 @@ struct dentry_info_args {
};
static inline void tl_to_darg(struct dentry_info_args *darg,
- struct ext4_fc_tl *tl)
+ struct ext4_fc_tl *tl, u8 *val)
{
- struct ext4_fc_dentry_info *fcd;
+ struct ext4_fc_dentry_info fcd;
- fcd = (struct ext4_fc_dentry_info *)ext4_fc_tag_val(tl);
+ memcpy(&fcd, val, sizeof(fcd));
- darg->parent_ino = le32_to_cpu(fcd->fc_parent_ino);
- darg->ino = le32_to_cpu(fcd->fc_ino);
- darg->dname = fcd->fc_dname;
- darg->dname_len = ext4_fc_tag_len(tl) -
- sizeof(struct ext4_fc_dentry_info);
+ darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino);
+ darg->ino = le32_to_cpu(fcd.fc_ino);
+ darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname);
+ darg->dname_len = le16_to_cpu(tl->fc_len) -
+ sizeof(struct ext4_fc_dentry_info);
}
/* Unlink replay function */
-static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
struct inode *inode, *old_parent;
struct qstr entry;
struct dentry_info_args darg;
int ret = 0;
- tl_to_darg(&darg, tl);
+ tl_to_darg(&darg, tl, val);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino,
darg.parent_ino, darg.dname_len);
@@ -1399,13 +1400,14 @@ out:
}
/* Link replay function */
-static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
struct inode *inode;
struct dentry_info_args darg;
int ret = 0;
- tl_to_darg(&darg, tl);
+ tl_to_darg(&darg, tl, val);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino,
darg.parent_ino, darg.dname_len);
@@ -1450,9 +1452,10 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
/*
* Inode replay function
*/
-static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
- struct ext4_fc_inode *fc_inode;
+ struct ext4_fc_inode fc_inode;
struct ext4_inode *raw_inode;
struct ext4_inode *raw_fc_inode;
struct inode *inode = NULL;
@@ -1460,9 +1463,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag);
struct ext4_extent_header *eh;
- fc_inode = (struct ext4_fc_inode *)ext4_fc_tag_val(tl);
+ memcpy(&fc_inode, val, sizeof(fc_inode));
- ino = le32_to_cpu(fc_inode->fc_ino);
+ ino = le32_to_cpu(fc_inode.fc_ino);
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
@@ -1474,12 +1477,13 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
ext4_fc_record_modified_inode(sb, ino);
- raw_fc_inode = (struct ext4_inode *)fc_inode->fc_raw_inode;
+ raw_fc_inode = (struct ext4_inode *)
+ (val + offsetof(struct ext4_fc_inode, fc_raw_inode));
ret = ext4_get_fc_inode_loc(sb, ino, &iloc);
if (ret)
goto out;
- inode_len = ext4_fc_tag_len(tl) - sizeof(struct ext4_fc_inode);
+ inode_len = le16_to_cpu(tl->fc_len) - sizeof(struct ext4_fc_inode);
raw_inode = ext4_raw_inode(&iloc);
memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block));
@@ -1547,14 +1551,15 @@ out:
* inode for which we are trying to create a dentry here, should already have
* been replayed before we start here.
*/
-static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
+static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
int ret = 0;
struct inode *inode = NULL;
struct inode *dir = NULL;
struct dentry_info_args darg;
- tl_to_darg(&darg, tl);
+ tl_to_darg(&darg, tl, val);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino,
darg.parent_ino, darg.dname_len);
@@ -1633,9 +1638,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino,
/* Replay add range tag */
static int ext4_fc_replay_add_range(struct super_block *sb,
- struct ext4_fc_tl *tl)
+ struct ext4_fc_tl *tl, u8 *val)
{
- struct ext4_fc_add_range *fc_add_ex;
+ struct ext4_fc_add_range fc_add_ex;
struct ext4_extent newex, *ex;
struct inode *inode;
ext4_lblk_t start, cur;
@@ -1645,15 +1650,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
struct ext4_ext_path *path = NULL;
int ret;
- fc_add_ex = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
- ex = (struct ext4_extent *)&fc_add_ex->fc_ex;
+ memcpy(&fc_add_ex, val, sizeof(fc_add_ex));
+ ex = (struct ext4_extent *)&fc_add_ex.fc_ex;
trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE,
- le32_to_cpu(fc_add_ex->fc_ino), le32_to_cpu(ex->ee_block),
+ le32_to_cpu(fc_add_ex.fc_ino), le32_to_cpu(ex->ee_block),
ext4_ext_get_actual_len(ex));
- inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
- EXT4_IGET_NORMAL);
+ inode = ext4_iget(sb, le32_to_cpu(fc_add_ex.fc_ino), EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
@@ -1762,32 +1766,33 @@ next:
/* Replay DEL_RANGE tag */
static int
-ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
+ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
+ u8 *val)
{
struct inode *inode;
- struct ext4_fc_del_range *lrange;
+ struct ext4_fc_del_range lrange;
struct ext4_map_blocks map;
ext4_lblk_t cur, remaining;
int ret;
- lrange = (struct ext4_fc_del_range *)ext4_fc_tag_val(tl);
- cur = le32_to_cpu(lrange->fc_lblk);
- remaining = le32_to_cpu(lrange->fc_len);
+ memcpy(&lrange, val, sizeof(lrange));
+ cur = le32_to_cpu(lrange.fc_lblk);
+ remaining = le32_to_cpu(lrange.fc_len);
trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE,
- le32_to_cpu(lrange->fc_ino), cur, remaining);
+ le32_to_cpu(lrange.fc_ino), cur, remaining);
- inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
+ inode = ext4_iget(sb, le32_to_cpu(lrange.fc_ino), EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
- jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
+ jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange.fc_ino));
return 0;
}
ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
- inode->i_ino, le32_to_cpu(lrange->fc_lblk),
- le32_to_cpu(lrange->fc_len));
+ inode->i_ino, le32_to_cpu(lrange.fc_lblk),
+ le32_to_cpu(lrange.fc_len));
while (remaining > 0) {
map.m_lblk = cur;
map.m_len = remaining;
@@ -1808,8 +1813,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
}
ret = ext4_punch_hole(inode,
- le32_to_cpu(lrange->fc_lblk) << sb->s_blocksize_bits,
- le32_to_cpu(lrange->fc_len) << sb->s_blocksize_bits);
+ le32_to_cpu(lrange.fc_lblk) << sb->s_blocksize_bits,
+ le32_to_cpu(lrange.fc_len) << sb->s_blocksize_bits);
if (ret)
jbd_debug(1, "ext4_punch_hole returned %d", ret);
ext4_ext_replay_shrink_inode(inode,
@@ -1925,11 +1930,11 @@ static int ext4_fc_replay_scan(journal_t *journal,
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_fc_replay_state *state;
int ret = JBD2_FC_REPLAY_CONTINUE;
- struct ext4_fc_add_range *ext;
- struct ext4_fc_tl *tl;
- struct ext4_fc_tail *tail;
- __u8 *start, *end;
- struct ext4_fc_head *head;
+ struct ext4_fc_add_range ext;
+ struct ext4_fc_tl tl;
+ struct ext4_fc_tail tail;
+ __u8 *start, *end, *cur, *val;
+ struct ext4_fc_head head;
struct ext4_extent *ex;
state = &sbi->s_fc_replay_state;
@@ -1956,15 +1961,17 @@ static int ext4_fc_replay_scan(journal_t *journal,
}
state->fc_replay_expected_off++;
- fc_for_each_tl(start, end, tl) {
+ for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) {
+ memcpy(&tl, cur, sizeof(tl));
+ val = cur + sizeof(tl);
jbd_debug(3, "Scan phase, tag:%s, blk %lld\n",
- tag2str(le16_to_cpu(tl->fc_tag)), bh->b_blocknr);
- switch (le16_to_cpu(tl->fc_tag)) {
+ tag2str(le16_to_cpu(tl.fc_tag)), bh->b_blocknr);
+ switch (le16_to_cpu(tl.fc_tag)) {
case EXT4_FC_TAG_ADD_RANGE:
- ext = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
- ex = (struct ext4_extent *)&ext->fc_ex;
+ memcpy(&ext, val, sizeof(ext));
+ ex = (struct ext4_extent *)&ext.fc_ex;
ret = ext4_fc_record_regions(sb,
- le32_to_cpu(ext->fc_ino),
+ le32_to_cpu(ext.fc_ino),
le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex),
ext4_ext_get_actual_len(ex));
if (ret < 0)
@@ -1978,18 +1985,18 @@ static int ext4_fc_replay_scan(journal_t *journal,
case EXT4_FC_TAG_INODE:
case EXT4_FC_TAG_PAD:
state->fc_cur_tag++;
- state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
- sizeof(*tl) + ext4_fc_tag_len(tl));
+ state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur,
+ sizeof(tl) + le16_to_cpu(tl.fc_len));
break;
case EXT4_FC_TAG_TAIL:
state->fc_cur_tag++;
- tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
- state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
- sizeof(*tl) +
+ memcpy(&tail, val, sizeof(tail));
+ state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur,
+ sizeof(tl) +
offsetof(struct ext4_fc_tail,
fc_crc));
- if (le32_to_cpu(tail->fc_tid) == expected_tid &&
- le32_to_cpu(tail->fc_crc) == state->fc_crc) {
+ if (le32_to_cpu(tail.fc_tid) == expected_tid &&
+ le32_to_cpu(tail.fc_crc) == state->fc_crc) {
state->fc_replay_num_tags = state->fc_cur_tag;
state->fc_regions_valid =
state->fc_regions_used;
@@ -2000,19 +2007,19 @@ static int ext4_fc_replay_scan(journal_t *journal,
state->fc_crc = 0;
break;
case EXT4_FC_TAG_HEAD:
- head = (struct ext4_fc_head *)ext4_fc_tag_val(tl);
- if (le32_to_cpu(head->fc_features) &
+ memcpy(&head, val, sizeof(head));
+ if (le32_to_cpu(head.fc_features) &
~EXT4_FC_SUPPORTED_FEATURES) {
ret = -EOPNOTSUPP;
break;
}
- if (le32_to_cpu(head->fc_tid) != expected_tid) {
+ if (le32_to_cpu(head.fc_tid) != expected_tid) {
ret = JBD2_FC_REPLAY_STOP;
break;
}
state->fc_cur_tag++;
- state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
- sizeof(*tl) + ext4_fc_tag_len(tl));
+ state->fc_crc = ext4_chksum(sbi, state->fc_crc, cur,
+ sizeof(tl) + le16_to_cpu(tl.fc_len));
break;
default:
ret = state->fc_replay_num_tags ?
@@ -2036,11 +2043,11 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_fc_tl *tl;
- __u8 *start, *end;
+ struct ext4_fc_tl tl;
+ __u8 *start, *end, *cur, *val;
int ret = JBD2_FC_REPLAY_CONTINUE;
struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state;
- struct ext4_fc_tail *tail;
+ struct ext4_fc_tail tail;
if (pass == PASS_SCAN) {
state->fc_current_pass = PASS_SCAN;
@@ -2067,49 +2074,52 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
start = (u8 *)bh->b_data;
end = (__u8 *)bh->b_data + journal->j_blocksize - 1;
- fc_for_each_tl(start, end, tl) {
+ for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) {
+ memcpy(&tl, cur, sizeof(tl));
+ val = cur + sizeof(tl);
+
if (state->fc_replay_num_tags == 0) {
ret = JBD2_FC_REPLAY_STOP;
ext4_fc_set_bitmaps_and_counters(sb);
break;
}
jbd_debug(3, "Replay phase, tag:%s\n",
- tag2str(le16_to_cpu(tl->fc_tag)));
+ tag2str(le16_to_cpu(tl.fc_tag)));
state->fc_replay_num_tags--;
- switch (le16_to_cpu(tl->fc_tag)) {
+ switch (le16_to_cpu(tl.fc_tag)) {
case EXT4_FC_TAG_LINK:
- ret = ext4_fc_replay_link(sb, tl);
+ ret = ext4_fc_replay_link(sb, &tl, val);
break;
case EXT4_FC_TAG_UNLINK:
- ret = ext4_fc_replay_unlink(sb, tl);
+ ret = ext4_fc_replay_unlink(sb, &tl, val);
break;
case EXT4_FC_TAG_ADD_RANGE:
- ret = ext4_fc_replay_add_range(sb, tl);
+ ret = ext4_fc_replay_add_range(sb, &tl, val);
break;
case EXT4_FC_TAG_CREAT:
- ret = ext4_fc_replay_create(sb, tl);
+ ret = ext4_fc_replay_create(sb, &tl, val);
break;
case EXT4_FC_TAG_DEL_RANGE:
- ret = ext4_fc_replay_del_range(sb, tl);
+ ret = ext4_fc_replay_del_range(sb, &tl, val);
break;
case EXT4_FC_TAG_INODE:
- ret = ext4_fc_replay_inode(sb, tl);
+ ret = ext4_fc_replay_inode(sb, &tl, val);
break;
case EXT4_FC_TAG_PAD:
trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0,
- ext4_fc_tag_len(tl), 0);
+ le16_to_cpu(tl.fc_len), 0);
break;
case EXT4_FC_TAG_TAIL:
trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0,
- ext4_fc_tag_len(tl), 0);
- tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
- WARN_ON(le32_to_cpu(tail->fc_tid) != expected_tid);
+ le16_to_cpu(tl.fc_len), 0);
+ memcpy(&tail, val, sizeof(tail));
+ WARN_ON(le32_to_cpu(tail.fc_tid) != expected_tid);
break;
case EXT4_FC_TAG_HEAD:
break;
default:
- trace_ext4_fc_replay(sb, le16_to_cpu(tl->fc_tag), 0,
- ext4_fc_tag_len(tl), 0);
+ trace_ext4_fc_replay(sb, le16_to_cpu(tl.fc_tag), 0,
+ le16_to_cpu(tl.fc_len), 0);
ret = -ECANCELED;
break;
}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index b77f70f55a62..937c381b4c85 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -153,13 +153,6 @@ struct ext4_fc_replay_state {
#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
#endif
-#define fc_for_each_tl(__start, __end, __tl) \
- for (tl = (struct ext4_fc_tl *)(__start); \
- (__u8 *)tl < (__u8 *)(__end); \
- tl = (struct ext4_fc_tl *)((__u8 *)tl + \
- sizeof(struct ext4_fc_tl) + \
- + le16_to_cpu(tl->fc_len)))
-
static inline const char *tag2str(__u16 tag)
{
switch (tag) {
@@ -186,16 +179,4 @@ static inline const char *tag2str(__u16 tag)
}
}
-/* Get length of a particular tlv */
-static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
-{
- return le16_to_cpu(tl->fc_len);
-}
-
-/* Get a pointer to "value" of a tlv */
-static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
-{
- return (__u8 *)tl + sizeof(*tl);
-}
-
#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/fsmap.h b/fs/ext4/fsmap.h
index 68c8001fee85..ac642be2302e 100644
--- a/fs/ext4/fsmap.h
+++ b/fs/ext4/fsmap.h
@@ -50,7 +50,7 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
#define EXT4_FMR_OWN_INODES FMR_OWNER('X', 5) /* inodes */
#define EXT4_FMR_OWN_GDT FMR_OWNER('f', 1) /* group descriptors */
#define EXT4_FMR_OWN_RESV_GDT FMR_OWNER('f', 2) /* reserved gdt blocks */
-#define EXT4_FMR_OWN_BLKBM FMR_OWNER('f', 3) /* inode bitmap */
-#define EXT4_FMR_OWN_INOBM FMR_OWNER('f', 4) /* block bitmap */
+#define EXT4_FMR_OWN_BLKBM FMR_OWNER('f', 3) /* block bitmap */
+#define EXT4_FMR_OWN_INOBM FMR_OWNER('f', 4) /* inode bitmap */
#endif /* __EXT4_FSMAP_H__ */
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 81a17a3cd80e..e89fc0f770b0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -322,14 +322,16 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
if (is_directory) {
count = ext4_used_dirs_count(sb, gdp) - 1;
ext4_used_dirs_set(sb, gdp, count);
- percpu_counter_dec(&sbi->s_dirs_counter);
+ if (percpu_counter_initialized(&sbi->s_dirs_counter))
+ percpu_counter_dec(&sbi->s_dirs_counter);
}
ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh,
EXT4_INODES_PER_GROUP(sb) / 8);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
- percpu_counter_inc(&sbi->s_freeinodes_counter);
+ if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
+ percpu_counter_inc(&sbi->s_freeinodes_counter);
if (sbi->s_log_groups_per_flex) {
struct flex_groups *fg;
@@ -400,7 +402,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
*
* We always try to spread first-level directories.
*
- * If there are blockgroups with both free inodes and free blocks counts
+ * If there are blockgroups with both free inodes and free clusters counts
* not worse than average we return one with smallest directory count.
* Otherwise we simply return a random group.
*
@@ -409,7 +411,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
* It's OK to put directory into a group unless
* it has too many directories already (max_dirs) or
* it has too few free inodes left (min_inodes) or
- * it has too few free blocks left (min_blocks) or
+ * it has too few free clusters left (min_clusters) or
* Parent's group is preferred, if it doesn't satisfy these
* conditions we search cyclically through the rest. If none
* of the groups look good we just look for a group with more
@@ -425,7 +427,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
ext4_group_t real_ngroups = ext4_get_groups_count(sb);
int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
unsigned int freei, avefreei, grp_free;
- ext4_fsblk_t freeb, avefreec;
+ ext4_fsblk_t freec, avefreec;
unsigned int ndirs;
int max_dirs, min_inodes;
ext4_grpblk_t min_clusters;
@@ -444,9 +446,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
avefreei = freei / ngroups;
- freeb = EXT4_C2B(sbi,
- percpu_counter_read_positive(&sbi->s_freeclusters_counter));
- avefreec = freeb;
+ freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter);
+ avefreec = freec;
do_div(avefreec, ngroups);
ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 3cf01629010d..70cb64db33f7 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -204,7 +204,7 @@ out:
/*
* write the buffer to the inline inode.
* If 'create' is set, we don't need to do the extra copy in the xattr
- * value since it is already handled by ext4_xattr_ibody_inline_set.
+ * value since it is already handled by ext4_xattr_ibody_set.
* That saves us one memcpy.
*/
static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
@@ -286,7 +286,7 @@ static int ext4_create_inline_data(handle_t *handle,
BUG_ON(!is.s.not_found);
- error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
if (error) {
if (error == -ENOSPC)
ext4_clear_inode_state(inode,
@@ -358,7 +358,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
i.value = value;
i.value_len = len;
- error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
if (error)
goto out;
@@ -431,7 +431,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
if (error)
goto out;
- error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
if (error)
goto out;
@@ -1925,8 +1925,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
i.value = value;
i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
- err = ext4_xattr_ibody_inline_set(handle, inode,
- &i, &is);
+ err = ext4_xattr_ibody_set(handle, inode, &i, &is);
if (err)
goto out_error;
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index fe6045a46599..d8de607849df 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -374,7 +374,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
ei->i_reserved_data_blocks -= used;
percpu_counter_sub(&sbi->s_dirtyclusters_counter, used);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+ spin_unlock(&ei->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
if (quota_claim)
@@ -3223,7 +3223,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
ext4_clear_inode_state(inode, EXT4_STATE_JDATA);
journal = EXT4_JOURNAL(inode);
jbd2_journal_lock_updates(journal);
- err = jbd2_journal_flush(journal);
+ err = jbd2_journal_flush(journal, 0);
jbd2_journal_unlock_updates(journal);
if (err)
@@ -3418,7 +3418,7 @@ retry:
* i_disksize out to i_size. This could be beyond where direct I/O is
* happening and thus expose allocated blocks to direct I/O reads.
*/
- else if ((map->m_lblk * (1 << blkbits)) >= i_size_read(inode))
+ else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode))
m_flags = EXT4_GET_BLOCKS_CREATE;
else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
@@ -3701,7 +3701,7 @@ static const struct address_space_operations ext4_da_aops = {
static const struct address_space_operations ext4_dax_aops = {
.writepages = ext4_dax_writepages,
.direct_IO = noop_direct_IO,
- .set_page_dirty = noop_set_page_dirty,
+ .set_page_dirty = __set_page_dirty_no_writeback,
.bmap = ext4_bmap,
.invalidatepage = noop_invalidatepage,
.swap_activate = ext4_iomap_swap_activate,
@@ -6005,7 +6005,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
if (val)
ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
else {
- err = jbd2_journal_flush(journal);
+ err = jbd2_journal_flush(journal, 0);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
percpu_up_write(&sbi->s_writepages_rwsem);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 31627f7dc5cd..e27f34bceb8d 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -659,10 +659,9 @@ static int ext4_ioc_getfsmap(struct super_block *sb,
info.gi_sb = sb;
info.gi_data = arg;
error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info);
- if (error == EXT4_QUERY_RANGE_ABORT) {
- error = 0;
+ if (error == EXT4_QUERY_RANGE_ABORT)
aborted = true;
- } else if (error)
+ else if (error)
return error;
/* If we didn't abort, set the "last" flag in the last fmx */
@@ -693,13 +692,6 @@ static long ext4_ioctl_group_add(struct file *file,
if (err)
return err;
- if (ext4_has_feature_bigalloc(sb)) {
- ext4_msg(sb, KERN_ERR,
- "Online resizing not supported with bigalloc");
- err = -EOPNOTSUPP;
- goto group_add_out;
- }
-
err = mnt_want_write_file(file);
if (err)
goto group_add_out;
@@ -707,7 +699,7 @@ static long ext4_ioctl_group_add(struct file *file,
err = ext4_group_add(sb, input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
- err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
@@ -800,6 +792,57 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg)
return error;
}
+static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg)
+{
+ int err = 0;
+ __u32 flags = 0;
+ unsigned int flush_flags = 0;
+ struct super_block *sb = file_inode(filp)->i_sb;
+ struct request_queue *q;
+
+ if (copy_from_user(&flags, (__u32 __user *)arg,
+ sizeof(__u32)))
+ return -EFAULT;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /* check for invalid bits set */
+ if ((flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) ||
+ ((flags & JBD2_JOURNAL_FLUSH_DISCARD) &&
+ (flags & JBD2_JOURNAL_FLUSH_ZEROOUT)))
+ return -EINVAL;
+
+ if (!EXT4_SB(sb)->s_journal)
+ return -ENODEV;
+
+ if (flags & ~JBD2_JOURNAL_FLUSH_VALID)
+ return -EINVAL;
+
+ q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev);
+ if (!q)
+ return -ENXIO;
+ if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN)
+ return 0;
+
+ if (flags & EXT4_IOC_CHECKPOINT_FLAG_DISCARD)
+ flush_flags |= JBD2_JOURNAL_FLUSH_DISCARD;
+
+ if (flags & EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT) {
+ flush_flags |= JBD2_JOURNAL_FLUSH_ZEROOUT;
+ pr_info_ratelimited("warning: checkpointing journal with EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT can be slow");
+ }
+
+ jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+ err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, flush_flags);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+
+ return err;
+}
+
static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -871,13 +914,6 @@ setversion_out:
goto group_extend_out;
}
- if (ext4_has_feature_bigalloc(sb)) {
- ext4_msg(sb, KERN_ERR,
- "Online resizing not supported with bigalloc");
- err = -EOPNOTSUPP;
- goto group_extend_out;
- }
-
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
@@ -885,7 +921,7 @@ setversion_out:
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
- err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
@@ -1028,7 +1064,7 @@ mext_out:
if (EXT4_SB(sb)->s_journal) {
ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
- err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
@@ -1211,6 +1247,9 @@ resizefs_out:
return fsverity_ioctl_read_metadata(filp,
(const void __user *)arg);
+ case EXT4_IOC_CHECKPOINT:
+ return ext4_ioctl_checkpoint(filp, arg);
+
default:
return -ENOTTY;
}
@@ -1291,6 +1330,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC_CLEAR_ES_CACHE:
case EXT4_IOC_GETSTATE:
case EXT4_IOC_GET_ES_CACHE:
+ case EXT4_IOC_CHECKPOINT:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 3239e6669e84..c2c22c2baac0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3217,7 +3217,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
*/
if (sbi->s_es->s_log_groups_per_flex >= 32) {
ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group");
- goto err_freesgi;
+ goto err_freebuddy;
}
sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex,
BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 68fbeedd627b..6cb598b549ca 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -127,9 +127,9 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp,
*/
static int kmmpd(void *data)
{
- struct super_block *sb = ((struct mmpd_data *) data)->sb;
- struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
+ struct super_block *sb = (struct super_block *) data;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh;
struct mmp_struct *mmp;
ext4_fsblk_t mmp_block;
u32 seq = 0;
@@ -245,12 +245,18 @@ static int kmmpd(void *data)
retval = write_mmp_block(sb, bh);
exit_thread:
- EXT4_SB(sb)->s_mmp_tsk = NULL;
- kfree(data);
- brelse(bh);
return retval;
}
+void ext4_stop_mmpd(struct ext4_sb_info *sbi)
+{
+ if (sbi->s_mmp_tsk) {
+ kthread_stop(sbi->s_mmp_tsk);
+ brelse(sbi->s_mmp_bh);
+ sbi->s_mmp_tsk = NULL;
+ }
+}
+
/*
* Get a random new sequence number but make sure it is not greater than
* EXT4_MMP_SEQ_MAX.
@@ -275,7 +281,6 @@ int ext4_multi_mount_protect(struct super_block *sb,
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct buffer_head *bh = NULL;
struct mmp_struct *mmp = NULL;
- struct mmpd_data *mmpd_data;
u32 seq;
unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
unsigned int wait_time = 0;
@@ -364,24 +369,17 @@ skip:
goto failed;
}
- mmpd_data = kmalloc(sizeof(*mmpd_data), GFP_KERNEL);
- if (!mmpd_data) {
- ext4_warning(sb, "not enough memory for mmpd_data");
- goto failed;
- }
- mmpd_data->sb = sb;
- mmpd_data->bh = bh;
+ EXT4_SB(sb)->s_mmp_bh = bh;
/*
* Start a kernel thread to update the MMP block periodically.
*/
- EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s",
+ EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
(int)sizeof(mmp->mmp_bdevname),
bdevname(bh->b_bdev,
mmp->mmp_bdevname));
if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
EXT4_SB(sb)->s_mmp_tsk = NULL;
- kfree(mmpd_data);
ext4_warning(sb, "Unable to create kmmpd thread for %s.",
sb->s_id);
goto failed;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index afb9d05a99ba..5fd56f616cf0 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1376,7 +1376,8 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
struct dx_hash_info *hinfo = &name->hinfo;
int len;
- if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) {
+ if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding ||
+ (IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) {
cf_name->name = NULL;
return 0;
}
@@ -1427,7 +1428,8 @@ static bool ext4_match(struct inode *parent,
#endif
#ifdef CONFIG_UNICODE
- if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent)) {
+ if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
+ (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
if (fname->cf_name.name) {
struct qstr cf = {.name = fname->cf_name.name,
.len = fname->cf_name.len};
@@ -2497,7 +2499,7 @@ again:
/* Which index block gets the new entry? */
if (at - entries >= icount1) {
- frame->at = at = at - entries - icount1 + entries2;
+ frame->at = at - entries - icount1 + entries2;
frame->entries = entries = entries2;
swap(frame->bh, bh2);
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index bd0d185654f3..fc885914c88a 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -74,6 +74,15 @@ int ext4_resize_begin(struct super_block *sb)
return -EPERM;
}
+ if (ext4_has_feature_bigalloc(sb)) {
+ ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc");
+ return -EOPNOTSUPP;
+ }
+ if (ext4_has_feature_sparse_super2(sb)) {
+ ext4_msg(sb, KERN_ERR, "Online resizing not supported with sparse_super2");
+ return -EOPNOTSUPP;
+ }
+
if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING,
&EXT4_SB(sb)->s_ext4_flags))
ret = -EBUSY;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7dc94f3e18e6..20344633bdd9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -718,6 +718,7 @@ static void flush_stashed_error_work(struct work_struct *work)
goto write_directly;
}
jbd2_journal_stop(handle);
+ ext4_notify_error_sysfs(sbi);
return;
}
write_directly:
@@ -726,6 +727,7 @@ write_directly:
* out and hope for the best.
*/
ext4_commit_super(sbi->s_sb);
+ ext4_notify_error_sysfs(sbi);
}
#define ext4_error_ratelimit(sb) \
@@ -1174,6 +1176,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_unregister_sysfs(sb);
if (sbi->s_journal) {
+ jbd2_journal_unregister_shrinker(sbi->s_journal);
aborted = is_journal_aborted(sbi->s_journal);
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
@@ -1245,8 +1248,8 @@ static void ext4_put_super(struct super_block *sb)
ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
sbi->s_ea_block_cache = NULL;
- if (sbi->s_mmp_tsk)
- kthread_stop(sbi->s_mmp_tsk);
+ ext4_stop_mmpd(sbi);
+
brelse(sbi->s_sbh);
sb->s_fs_info = NULL;
/*
@@ -1441,26 +1444,6 @@ static int ext4_nfs_commit_metadata(struct inode *inode)
return ext4_write_inode(inode, &wbc);
}
-/*
- * Try to release metadata pages (indirect blocks, directories) which are
- * mapped via the block device. Since these pages could have journal heads
- * which would prevent try_to_free_buffers() from freeing them, we must use
- * jbd2 layer's try_to_free_buffers() function to release them.
- */
-static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
- gfp_t wait)
-{
- journal_t *journal = EXT4_SB(sb)->s_journal;
-
- WARN_ON(PageChecked(page));
- if (!page_has_buffers(page))
- return 0;
- if (journal)
- return jbd2_journal_try_to_free_buffers(journal, page);
-
- return try_to_free_buffers(page);
-}
-
#ifdef CONFIG_FS_ENCRYPTION
static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
{
@@ -1655,7 +1638,6 @@ static const struct super_operations ext4_sops = {
.quota_write = ext4_quota_write,
.get_dquots = ext4_get_dquots,
#endif
- .bdev_try_to_free_page = bdev_try_to_free_page,
};
static const struct export_operations ext4_export_ops = {
@@ -3101,8 +3083,15 @@ static void ext4_orphan_cleanup(struct super_block *sb,
inode_lock(inode);
truncate_inode_pages(inode->i_mapping, inode->i_size);
ret = ext4_truncate(inode);
- if (ret)
+ if (ret) {
+ /*
+ * We need to clean up the in-core orphan list
+ * manually if ext4_truncate() failed to get a
+ * transaction handle.
+ */
+ ext4_orphan_del(NULL, inode);
ext4_std_error(inode->i_sb, ret);
+ }
inode_unlock(inode);
nr_truncates++;
} else {
@@ -4462,14 +4451,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (sb->s_blocksize != blocksize) {
+ /*
+ * bh must be released before kill_bdev(), otherwise
+ * it won't be freed and its page also. kill_bdev()
+ * is called by sb_set_blocksize().
+ */
+ brelse(bh);
/* Validate the filesystem blocksize */
if (!sb_set_blocksize(sb, blocksize)) {
ext4_msg(sb, KERN_ERR, "bad block size %d",
blocksize);
+ bh = NULL;
goto failed_mount;
}
- brelse(bh);
logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
offset = do_div(logical_sb_block, blocksize);
bh = ext4_sb_bread_unmovable(sb, logical_sb_block);
@@ -5052,6 +5047,7 @@ no_journal:
ext4_msg(sb, KERN_ERR,
"unable to initialize "
"flex_bg meta info!");
+ ret = -ENOMEM;
goto failed_mount6;
}
@@ -5172,6 +5168,7 @@ failed_mount_wq:
sbi->s_ea_block_cache = NULL;
if (sbi->s_journal) {
+ jbd2_journal_unregister_shrinker(sbi->s_journal);
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
@@ -5180,8 +5177,7 @@ failed_mount3a:
failed_mount3:
flush_work(&sbi->s_error_work);
del_timer_sync(&sbi->s_err_report);
- if (sbi->s_mmp_tsk)
- kthread_stop(sbi->s_mmp_tsk);
+ ext4_stop_mmpd(sbi);
failed_mount2:
rcu_read_lock();
group_desc = rcu_dereference(sbi->s_group_desc);
@@ -5202,8 +5198,9 @@ failed_mount:
kfree(get_qf_name(sb, sbi, i));
#endif
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
- ext4_blkdev_remove(sbi);
+ /* ext4_blkdev_remove() calls kill_bdev(), release bh before it. */
brelse(bh);
+ ext4_blkdev_remove(sbi);
out_fail:
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
@@ -5497,6 +5494,12 @@ static int ext4_load_journal(struct super_block *sb,
ext4_commit_super(sb);
}
+ err = jbd2_journal_register_shrinker(journal);
+ if (err) {
+ EXT4_SB(sb)->s_journal = NULL;
+ goto err_out;
+ }
+
return 0;
err_out:
@@ -5639,7 +5642,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
return 0;
}
jbd2_journal_lock_updates(journal);
- err = jbd2_journal_flush(journal);
+ err = jbd2_journal_flush(journal, 0);
if (err < 0)
goto out;
@@ -5781,7 +5784,7 @@ static int ext4_freeze(struct super_block *sb)
* Don't clear the needs_recovery flag if we failed to
* flush the journal.
*/
- error = jbd2_journal_flush(journal);
+ error = jbd2_journal_flush(journal, 0);
if (error < 0)
goto out;
@@ -5982,8 +5985,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
*/
ext4_mark_recovery_complete(sb, es);
}
- if (sbi->s_mmp_tsk)
- kthread_stop(sbi->s_mmp_tsk);
+ ext4_stop_mmpd(sbi);
} else {
/* Make sure we can mount this feature set readwrite */
if (ext4_has_feature_readonly(sb) ||
@@ -6376,7 +6378,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
* otherwise be livelocked...
*/
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
- err = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
if (err)
return err;
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 6f825dedc3d4..2314f7446592 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -315,7 +315,9 @@ EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
EXT4_ATTR_FEATURE(fast_commit);
+#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
EXT4_ATTR_FEATURE(encrypted_casefold);
+#endif
static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(lazy_itable_init),
@@ -333,7 +335,9 @@ static struct attribute *ext4_feat_attrs[] = {
#endif
ATTR_LIST(metadata_csum_seed),
ATTR_LIST(fast_commit),
+#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
ATTR_LIST(encrypted_casefold),
+#endif
NULL,
};
ATTRIBUTE_GROUPS(ext4_feat);
@@ -502,6 +506,11 @@ static struct kobj_type ext4_feat_ktype = {
.release = (void (*)(struct kobject *))kfree,
};
+void ext4_notify_error_sysfs(struct ext4_sb_info *sbi)
+{
+ sysfs_notify(&sbi->s_kobj, NULL, "errors_count");
+}
+
static struct kobject *ext4_root;
static struct kobject *ext4_feat;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 10ba4b24a0aa..6dd5c05c444a 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2190,31 +2190,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
return 0;
}
-int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
- struct ext4_xattr_info *i,
- struct ext4_xattr_ibody_find *is)
-{
- struct ext4_xattr_ibody_header *header;
- struct ext4_xattr_search *s = &is->s;
- int error;
-
- if (EXT4_I(inode)->i_extra_isize == 0)
- return -ENOSPC;
- error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
- if (error)
- return error;
- header = IHDR(inode, ext4_raw_inode(&is->iloc));
- if (!IS_LAST_ENTRY(s->first)) {
- header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
- ext4_set_inode_state(inode, EXT4_STATE_XATTR);
- } else {
- header->h_magic = cpu_to_le32(0);
- ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
- }
- return 0;
-}
-
-static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is)
{
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 730b91fa0dd7..77efb9a627ad 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -186,9 +186,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
extern int ext4_xattr_ibody_get(struct inode *inode, int name_index,
const char *name,
void *buffer, size_t buffer_size);
-extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
- struct ext4_xattr_info *i,
- struct ext4_xattr_ibody_find *is);
+extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+ struct ext4_xattr_info *i,
+ struct ext4_xattr_ibody_find *is);
extern struct mb_cache *ext4_xattr_create_cache(void);
extern void ext4_xattr_destroy_cache(struct mb_cache *);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.