(raw_inode)->xtime = cpu_to_le32(clamp_t(int32_t, (ts).tv_sec, S32_MIN, S32_MAX)); \
} while (0)
-#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \
- EXT4_INODE_SET_XTIME_VAL(xtime, inode, raw_inode, (inode)->xtime)
+#define EXT4_INODE_SET_ATIME(inode, raw_inode) \
+ EXT4_INODE_SET_XTIME_VAL(i_atime, inode, raw_inode, inode_get_atime(inode))
-#define EXT4_INODE_SET_CTIME(inode, raw_inode) \
+#define EXT4_INODE_SET_MTIME(inode, raw_inode) \
+ EXT4_INODE_SET_XTIME_VAL(i_mtime, inode, raw_inode, inode_get_mtime(inode))
+
+#define EXT4_INODE_SET_CTIME(inode, raw_inode) \
EXT4_INODE_SET_XTIME_VAL(i_ctime, inode, raw_inode, inode_get_ctime(inode))
#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \
.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime) \
})
-#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \
+#define EXT4_INODE_GET_ATIME(inode, raw_inode) \
+do { \
+ inode_set_atime_to_ts(inode, \
+ EXT4_INODE_GET_XTIME_VAL(i_atime, inode, raw_inode)); \
+} while (0)
+
+#define EXT4_INODE_GET_MTIME(inode, raw_inode) \
do { \
- (inode)->xtime = EXT4_INODE_GET_XTIME_VAL(xtime, inode, raw_inode); \
+ inode_set_mtime_to_ts(inode, \
+ EXT4_INODE_GET_XTIME_VAL(i_mtime, inode, raw_inode)); \
} while (0)
#define EXT4_INODE_GET_CTIME(inode, raw_inode) \
loff_t s_bitmap_maxbytes; /* max bytes for bitmap files */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block *s_es; /* Pointer to the super block in the buffer */
+ /* Array of bh's for the block group descriptors */
struct buffer_head * __rcu *s_group_desc;
unsigned int s_mount_opt;
unsigned int s_mount_opt2;
unsigned long s_commit_interval;
u32 s_max_batch_time;
u32 s_min_batch_time;
- struct block_device *s_journal_bdev;
+ struct bdev_handle *s_journal_bdev_handle;
#ifdef CONFIG_QUOTA
/* Names of quota files with journalled quota */
char __rcu *s_qf_names[EXT4_MAXQUOTAS];
unsigned int *s_mb_maxs;
unsigned int s_group_info_size;
unsigned int s_mb_free_pending;
- struct list_head s_freed_data_list; /* List of blocks to be freed
+ struct list_head s_freed_data_list[2]; /* List of blocks to be freed
after commit completed */
struct list_head s_discard_list;
struct work_struct s_discard_work;
/*
* Barrier between writepages ops and changing any inode's JOURNAL_DATA
- * or EXTENTS flag.
+ * or EXTENTS flag or between writepages ops and changing DELALLOC or
+ * DIOREAD_NOLOCK mount options on remount.
*/
struct percpu_rw_semaphore s_writepages_rwsem;
struct dax_device *s_daxdev;
extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
- int len, int state);
+ int len, bool state);
static inline bool ext4_mb_cr_expensive(enum criteria cr)
{
return cr >= CR_GOAL_LEN_SLOW;
ix = curp->p_idx;
}
+ if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
+ EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
+ return -EFSCORRUPTED;
+ }
+
len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1;
BUG_ON(len < 0);
if (len > 0) {
memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx));
}
- if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) {
- EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!");
- return -EFSCORRUPTED;
- }
-
ix->ei_block = cpu_to_le32(logical);
ext4_idx_store_pblock(ix, ptr);
le16_add_cpu(&curp->p_hdr->eh_entries, 1);
if (epos > new_size)
epos = new_size;
if (ext4_update_inode_size(inode, epos) & 0x1)
- inode->i_mtime = inode_get_ctime(inode);
+ inode_set_mtime_to_ts(inode,
+ inode_get_ctime(inode));
}
ret2 = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
/* Now release the pages and zero block aligned part of pages */
truncate_pagecache_range(inode, start, end - 1);
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
flags);
goto out_mutex;
}
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
if (new_size)
ext4_update_inode_size(inode, new_size);
ret = ext4_mark_inode_dirty(handle, inode);
up_write(&EXT4_I(inode)->i_data_sem);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
ret = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
/* Expand file to avoid data loss if there is error while shifting */
inode->i_size += len;
EXT4_I(inode)->i_disksize += len;
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
ret = ext4_mark_inode_dirty(handle, inode);
if (ret)
goto out_stop;
for (j = 0; j < path->p_depth; j++) {
ext4_mb_mark_bb(inode->i_sb,
- path[j].p_block, 1, 0);
+ path[j].p_block, 1, false);
ext4_fc_record_regions(inode->i_sb, inode->i_ino,
0, path[j].p_block, 1, 1);
}
ext4_free_ext_path(path);
}
- ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+ ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false);
ext4_fc_record_regions(inode->i_sb, inode->i_ino,
map.m_lblk, map.m_pblk, map.m_len, 1);
}
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
+ int ret = 0;
+
ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
inode->i_ino, create);
- return _ext4_get_block(inode, iblock, bh_result,
+ ret = _ext4_get_block(inode, iblock, bh_result,
EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT);
+
+ /*
+ * If the buffer is marked unwritten, mark it as new to make sure it is
+ * zeroed out correctly in case of partial writes. Otherwise, there is
+ * a chance of stale data getting exposed.
+ */
+ if (ret == 0 && buffer_unwritten(bh_result))
+ set_buffer_new(bh_result);
+
+ return ret;
}
/* Maximum number of blocks we map for direct IO at once. */
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
ret2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(ret2))
ret = ret2;
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
err2 = ext4_mark_inode_dirty(handle, inode);
if (unlikely(err2 && !err))
err = err2;
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
EXT4_INODE_SET_CTIME(inode, raw_inode);
- EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
- EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
+ EXT4_INODE_SET_MTIME(inode, raw_inode);
+ EXT4_INODE_SET_ATIME(inode, raw_inode);
EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
}
EXT4_INODE_GET_CTIME(inode, raw_inode);
- EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode);
- EXT4_INODE_GET_XTIME(i_atime, inode, raw_inode);
+ EXT4_INODE_GET_ATIME(inode, raw_inode);
+ EXT4_INODE_GET_MTIME(inode, raw_inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
spin_lock(&ei->i_raw_lock);
EXT4_INODE_SET_CTIME(inode, raw_inode);
- EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
- EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
+ EXT4_INODE_SET_MTIME(inode, raw_inode);
+ EXT4_INODE_SET_ATIME(inode, raw_inode);
ext4_inode_csum_set(inode, raw_inode, ei);
spin_unlock(&ei->i_raw_lock);
trace_ext4_other_inode_update_time(inode, orig_ino);
* update c/mtime in shrink case below
*/
if (!shrink)
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode,
+ inode_set_ctime_current(inode));
if (shrink)
ext4_fc_track_range(handle, inode,
* happen is that the times are slightly out of date
* and/or different from the directory change time.
*/
- dir->i_mtime = inode_set_ctime_current(dir);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
ext4_update_dx_flag(dir);
inode_inc_iversion(dir);
err2 = ext4_mark_inode_dirty(handle, dir);
top = data2 + len;
while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) {
if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len,
- (data2 + (blocksize - csum_size) -
- (char *) de))) {
+ (char *)de - data2)) {
brelse(bh2);
brelse(bh);
return -EFSCORRUPTED;
* recovery. */
inode->i_size = 0;
ext4_orphan_add(handle, inode);
- dir->i_mtime = inode_set_ctime_current(dir);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
inode_set_ctime_current(inode);
retval = ext4_mark_inode_dirty(handle, inode);
if (retval)
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
goto out_handle;
- dir->i_mtime = inode_set_ctime_current(dir);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
ext4_update_dx_flag(dir);
retval = ext4_mark_inode_dirty(handle, dir);
if (retval)
if (ext4_has_feature_filetype(ent->dir->i_sb))
ent->de->file_type = file_type;
inode_inc_iversion(ent->dir);
- ent->dir->i_mtime = inode_set_ctime_current(ent->dir);
+ inode_set_mtime_to_ts(ent->dir, inode_set_ctime_current(ent->dir));
retval = ext4_mark_inode_dirty(handle, ent->dir);
BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
if (!ent->inlined) {
ext4_dec_count(new.inode);
inode_set_ctime_current(new.inode);
}
- old.dir->i_mtime = inode_set_ctime_current(old.dir);
+ inode_set_mtime_to_ts(old.dir, inode_set_ctime_current(old.dir));
ext4_update_dx_flag(old.dir);
if (old.dir_bh) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
*/
if (!sb_rdonly(sbi->s_sb) && journal) {
struct buffer_head *sbh = sbi->s_sbh;
- bool call_notify_err;
+ bool call_notify_err = false;
+
handle = jbd2_journal_start(journal, 1);
if (IS_ERR(handle))
goto write_directly;
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
- if (sbi->s_journal_bdev) {
+ if (sbi->s_journal_bdev_handle) {
/*
* Invalidate the journal device's buffers. We don't want them
* floating about in memory - the physical journal device may
* hotswapped, and it breaks the `ro-after' testing code.
*/
- sync_blockdev(sbi->s_journal_bdev);
- invalidate_bdev(sbi->s_journal_bdev);
+ sync_blockdev(sbi->s_journal_bdev_handle->bdev);
+ invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
}
ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
* Add the internal journal blocks whether the journal has been
* loaded or not
*/
- if (sbi->s_journal && !sbi->s_journal_bdev)
+ if (sbi->s_journal && !sbi->s_journal_bdev_handle)
overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
/* j_inum for internal journal is non-zero */
#endif
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
brelse(sbi->s_sbh);
- if (sbi->s_journal_bdev) {
- invalidate_bdev(sbi->s_journal_bdev);
- blkdev_put(sbi->s_journal_bdev, sb);
+ if (sbi->s_journal_bdev_handle) {
+ invalidate_bdev(sbi->s_journal_bdev_handle->bdev);
+ bdev_release(sbi->s_journal_bdev_handle);
}
out_fail:
invalidate_bdev(sb->s_bdev);
return journal;
}
-static struct block_device *ext4_get_journal_blkdev(struct super_block *sb,
+static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
dev_t j_dev, ext4_fsblk_t *j_start,
ext4_fsblk_t *j_len)
{
struct buffer_head *bh;
struct block_device *bdev;
+ struct bdev_handle *bdev_handle;
int hblock, blocksize;
ext4_fsblk_t sb_block;
unsigned long offset;
/* see get_tree_bdev why this is needed and safe */
up_write(&sb->s_umount);
- bdev = blkdev_get_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb,
- &fs_holder_ops);
+ bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
+ sb, &fs_holder_ops);
down_write(&sb->s_umount);
- if (IS_ERR(bdev)) {
+ if (IS_ERR(bdev_handle)) {
ext4_msg(sb, KERN_ERR,
"failed to open journal device unknown-block(%u,%u) %ld",
- MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev));
- return ERR_CAST(bdev);
+ MAJOR(j_dev), MINOR(j_dev), PTR_ERR(bdev_handle));
+ return bdev_handle;
}
+ bdev = bdev_handle->bdev;
blocksize = sb->s_blocksize;
hblock = bdev_logical_block_size(bdev);
if (blocksize < hblock) {
*j_start = sb_block + 1;
*j_len = ext4_blocks_count(es);
brelse(bh);
- return bdev;
+ return bdev_handle;
out_bh:
brelse(bh);
out_bdev:
- blkdev_put(bdev, sb);
+ bdev_release(bdev_handle);
return ERR_PTR(errno);
}
journal_t *journal;
ext4_fsblk_t j_start;
ext4_fsblk_t j_len;
- struct block_device *journal_bdev;
+ struct bdev_handle *bdev_handle;
int errno = 0;
- journal_bdev = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
- if (IS_ERR(journal_bdev))
- return ERR_CAST(journal_bdev);
+ bdev_handle = ext4_get_journal_blkdev(sb, j_dev, &j_start, &j_len);
+ if (IS_ERR(bdev_handle))
+ return ERR_CAST(bdev_handle);
- journal = jbd2_journal_init_dev(journal_bdev, sb->s_bdev, j_start,
+ journal = jbd2_journal_init_dev(bdev_handle->bdev, sb->s_bdev, j_start,
j_len, sb->s_blocksize);
if (IS_ERR(journal)) {
ext4_msg(sb, KERN_ERR, "failed to create device journal");
goto out_journal;
}
journal->j_private = sb;
- EXT4_SB(sb)->s_journal_bdev = journal_bdev;
+ EXT4_SB(sb)->s_journal_bdev_handle = bdev_handle;
ext4_init_journal_params(sb, journal);
return journal;
out_journal:
jbd2_journal_destroy(journal);
out_bdev:
- blkdev_put(journal_bdev, sb);
+ bdev_release(bdev_handle);
return ERR_PTR(errno);
}
struct ext4_mount_options old_opts;
ext4_group_t g;
int err = 0;
+ int alloc_ctx;
#ifdef CONFIG_QUOTA
int enable_quota = 0;
int i, j;
}
+ /*
+ * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause
+ * two calls to ext4_should_dioread_nolock() to return inconsistent
+ * values, triggering WARN_ON in ext4_add_complete_io(). we grab
+ * here s_writepages_rwsem to avoid race between writepages ops and
+ * remount.
+ */
+ alloc_ctx = ext4_writepages_down_write(sb);
ext4_apply_options(fc, sb);
+ ext4_writepages_up_write(sb, alloc_ctx);
if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
test_opt(sb, JOURNAL_CHECKSUM)) {
if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) &&
sb_any_quota_suspended(sb))
dquot_resume(sb, -1);
+
+ alloc_ctx = ext4_writepages_down_write(sb);
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
sbi->s_mount_opt2 = old_opts.s_mount_opt2;
sbi->s_commit_interval = old_opts.s_commit_interval;
sbi->s_min_batch_time = old_opts.s_min_batch_time;
sbi->s_max_batch_time = old_opts.s_max_batch_time;
+ ext4_writepages_up_write(sb, alloc_ctx);
+
if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
ext4_release_system_zone(sb);
#ifdef CONFIG_QUOTA
}
EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL);
inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
err = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
out_unlock:
static void ext4_kill_sb(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct block_device *journal_bdev = sbi ? sbi->s_journal_bdev : NULL;
+ struct bdev_handle *handle = sbi ? sbi->s_journal_bdev_handle : NULL;
kill_block_super(sb);
- if (journal_bdev)
- blkdev_put(journal_bdev, sb);
+ if (handle)
+ bdev_release(handle);
}
static struct file_system_type ext4_fs_type = {
projects / linux.git / commitdiff