aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--fs/ext4/balloc.c30
-rw-r--r--fs/ext4/ext4.h43
-rw-r--r--fs/ext4/ext4_extents.h1
-rw-r--r--fs/ext4/extents.c23
-rw-r--r--fs/ext4/file.c2
-rw-r--r--fs/ext4/ialloc.c30
-rw-r--r--fs/ext4/inline.c58
-rw-r--r--fs/ext4/inode.c93
-rw-r--r--fs/ext4/mballoc.c13
-rw-r--r--fs/ext4/mmp.c13
-rw-r--r--fs/ext4/move_extent.c4
-rw-r--r--fs/ext4/namei.c1
-rw-r--r--fs/ext4/readpage.c5
-rw-r--r--fs/ext4/super.c171
-rw-r--r--fs/ext4/sysfs.c38
-rw-r--r--fs/ext4/truncate.h4
-rw-r--r--fs/ext4/xattr.c42
17 files changed, 373 insertions, 198 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index b00481c475cb..e5d6ee61ff48 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -184,7 +184,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
unsigned int bit, bit_max;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
- int flex_bg = 0;
J_ASSERT_BH(bh, buffer_locked(bh));
@@ -207,22 +206,19 @@ static int ext4_init_block_bitmap(struct super_block *sb,
start = ext4_group_first_block_no(sb, block_group);
- if (ext4_has_feature_flex_bg(sb))
- flex_bg = 1;
-
/* Set bits for block and inode bitmaps, and inode table */
tmp = ext4_block_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ if (ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
tmp = ext4_inode_bitmap(sb, gdp);
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ if (ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
tmp = ext4_inode_table(sb, gdp);
for (; tmp < ext4_inode_table(sb, gdp) +
sbi->s_itb_per_group; tmp++) {
- if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+ if (ext4_block_in_group(sb, tmp, block_group))
ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
}
@@ -372,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
return -EFSCORRUPTED;
ext4_lock_group(sb, block_group);
+ if (buffer_verified(bh))
+ goto verified;
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
desc, bh))) {
ext4_unlock_group(sb, block_group);
@@ -390,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
return -EFSCORRUPTED;
}
set_buffer_verified(bh);
+verified:
ext4_unlock_group(sb, block_group);
return 0;
}
@@ -427,9 +426,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
}
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, "Cannot get buffer for block bitmap - "
- "block_group = %u, block_bitmap = %llu",
- block_group, bitmap_blk);
+ ext4_warning(sb, "Cannot get buffer for block bitmap - "
+ "block_group = %u, block_bitmap = %llu",
+ block_group, bitmap_blk);
return ERR_PTR(-ENOMEM);
}
@@ -442,7 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
goto verify;
}
ext4_lock_group(sb, block_group);
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+ if (block_group == 0) {
+ ext4_unlock_group(sb, block_group);
+ unlock_buffer(bh);
+ ext4_error(sb, "Block bitmap for bg 0 marked "
+ "uninitialized");
+ err = -EFSCORRUPTED;
+ goto out;
+ }
err = ext4_init_block_bitmap(sb, bh, block_group, desc);
set_bitmap_uptodate(bh);
set_buffer_uptodate(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0b127853c584..0f0edd1cd0cd 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -789,17 +789,16 @@ struct move_extent {
* affected filesystem before 2242.
*/
-static inline __le32 ext4_encode_extra_time(struct timespec *time)
+static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
{
- u32 extra = sizeof(time->tv_sec) > 4 ?
- ((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+ u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
}
-static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
+static inline void ext4_decode_extra_time(struct timespec64 *time,
+ __le32 extra)
{
- if (unlikely(sizeof(time->tv_sec) > 4 &&
- (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+ if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) {
#if 1
/* Handle legacy encoding of pre-1970 dates with epoch
@@ -821,9 +820,8 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
do { \
(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {\
- struct timespec ts = timespec64_to_timespec((inode)->xtime); \
(raw_inode)->xtime ## _extra = \
- ext4_encode_extra_time(&ts); \
+ ext4_encode_extra_time(&(inode)->xtime); \
} \
} while (0)
@@ -840,10 +838,8 @@ do { \
do { \
(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \
if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \
- struct timespec ts = timespec64_to_timespec((inode)->xtime); \
- ext4_decode_extra_time(&ts, \
+ ext4_decode_extra_time(&(inode)->xtime, \
raw_inode->xtime ## _extra); \
- (inode)->xtime = timespec_to_timespec64(ts); \
} \
else \
(inode)->xtime.tv_nsec = 0; \
@@ -993,9 +989,9 @@ struct ext4_inode_info {
/*
* File creation time. Its function is same as that of
- * struct timespec i_{a,c,m}time in the generic inode.
+ * struct timespec64 i_{a,c,m}time in the generic inode.
*/
- struct timespec i_crtime;
+ struct timespec64 i_crtime;
/* mballoc */
struct list_head i_prealloc_list;
@@ -1114,6 +1110,7 @@ struct ext4_inode_info {
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
@@ -1298,7 +1295,14 @@ struct ext4_super_block {
__le32 s_lpf_ino; /* Location of the lost+found inode */
__le32 s_prj_quota_inum; /* inode for tracking project quota */
__le32 s_checksum_seed; /* crc32c(uuid) if csum_seed set */
- __le32 s_reserved[98]; /* Padding to the end of the block */
+ __u8 s_wtime_hi;
+ __u8 s_mtime_hi;
+ __u8 s_mkfs_time_hi;
+ __u8 s_lastcheck_hi;
+ __u8 s_first_error_time_hi;
+ __u8 s_last_error_time_hi;
+ __u8 s_pad[2];
+ __le32 s_reserved[96]; /* Padding to the end of the block */
__le32 s_checksum; /* crc32c(superblock) */
};
@@ -1507,11 +1511,6 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
{
return ino == EXT4_ROOT_INO ||
- ino == EXT4_USR_QUOTA_INO ||
- ino == EXT4_GRP_QUOTA_INO ||
- ino == EXT4_BOOT_LOADER_INO ||
- ino == EXT4_JOURNAL_INO ||
- ino == EXT4_RESIZE_INO ||
(ino >= EXT4_FIRST_INO(sb) &&
ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
}
@@ -2460,6 +2459,7 @@ extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
extern int ext4_inode_attach_jinode(struct inode *inode);
extern int ext4_can_truncate(struct inode *inode);
extern int ext4_truncate(struct inode *);
+extern int ext4_break_layouts(struct inode *);
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
extern void ext4_set_inode_flags(struct inode *);
@@ -3018,9 +3018,6 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
struct iomap;
extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
-extern int ext4_try_to_evict_inline_data(handle_t *handle,
- struct inode *inode,
- int needed);
extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
extern int ext4_convert_inline_data(struct inode *inode);
@@ -3065,7 +3062,7 @@ static inline void ext4_set_de_type(struct super_block *sb,
/* readpages.c */
extern int ext4_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
- unsigned nr_pages);
+ unsigned nr_pages, bool is_readahead);
/* symlink.c */
extern const struct inode_operations ext4_encrypted_symlink_inode_operations;
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 98fb0c119c68..adf6668b596f 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -91,6 +91,7 @@ struct ext4_extent_header {
};
#define EXT4_EXT_MAGIC cpu_to_le16(0xf30a)
+#define EXT4_MAX_EXTENT_DEPTH 5
#define EXT4_EXTENT_TAIL_OFFSET(hdr) \
(sizeof(struct ext4_extent_header) + \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0057fe3f248d..72a361d5ef74 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -869,6 +869,12 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
+ if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) {
+ EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d",
+ depth);
+ ret = -EFSCORRUPTED;
+ goto err;
+ }
if (path) {
ext4_ext_drop_refs(path);
@@ -4820,6 +4826,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* released from page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
+
+ ret = ext4_break_layouts(inode);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ goto out_mutex;
+ }
+
ret = ext4_update_disksize_before_punch(inode, offset, len);
if (ret) {
up_write(&EXT4_I(inode)->i_mmap_sem);
@@ -5493,6 +5506,11 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
* page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
+
+ ret = ext4_break_layouts(inode);
+ if (ret)
+ goto out_mmap;
+
/*
* Need to round down offset to be aligned with page size boundary
* for page size > block size.
@@ -5641,6 +5659,11 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
* page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
+
+ ret = ext4_break_layouts(inode);
+ if (ret)
+ goto out_mmap;
+
/*
* Need to round down to align start offset to page size boundary
* for page size > block size.
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 7f8023340eb8..69d65d49837b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -374,7 +374,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
- vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+ vma->vm_flags |= VM_HUGEPAGE;
} else {
vma->vm_ops = &ext4_file_vm_ops;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f525f909b559..2addcb8730e1 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
return -EFSCORRUPTED;
ext4_lock_group(sb, block_group);
+ if (buffer_verified(bh))
+ goto verified;
blk = ext4_inode_bitmap(sb, desc);
if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
EXT4_INODES_PER_GROUP(sb) / 8)) {
@@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
return -EFSBADCRC;
}
set_buffer_verified(bh);
+verified:
ext4_unlock_group(sb, block_group);
return 0;
}
@@ -135,9 +138,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
}
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
- ext4_error(sb, "Cannot read inode bitmap - "
- "block_group = %u, inode_bitmap = %llu",
- block_group, bitmap_blk);
+ ext4_warning(sb, "Cannot read inode bitmap - "
+ "block_group = %u, inode_bitmap = %llu",
+ block_group, bitmap_blk);
return ERR_PTR(-ENOMEM);
}
if (bitmap_uptodate(bh))
@@ -150,7 +153,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
}
ext4_lock_group(sb, block_group);
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
+ if (block_group == 0) {
+ ext4_unlock_group(sb, block_group);
+ unlock_buffer(bh);
+ ext4_error(sb, "Inode bitmap for bg 0 marked "
+ "uninitialized");
+ err = -EFSCORRUPTED;
+ goto out;
+ }
memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
sb->s_blocksize * 8, bh->b_data);
@@ -994,7 +1006,8 @@ got:
/* recheck and clear flag under lock if we still need to */
ext4_lock_group(sb, group);
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ 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));
@@ -1073,7 +1086,7 @@ got:
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
- ei->i_crtime = timespec64_to_timespec(inode->i_mtime);
+ ei->i_crtime = inode->i_mtime;
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
@@ -1375,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
ext4_itable_unused_count(sb, gdp)),
sbi->s_inodes_per_block);
- if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+ if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
+ ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
+ ext4_itable_unused_count(sb, gdp)) <
+ EXT4_FIRST_INO(sb)))) {
ext4_error(sb, "Something is wrong with group %u: "
"used itable blocks: %d; "
"itable unused count: %u",
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 285ed1588730..3543fe80a3c4 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -437,6 +437,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
+ memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE);
if (ext4_has_feature_extents(inode->i_sb)) {
if (S_ISDIR(inode->i_mode) ||
@@ -681,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
goto convert;
}
+ ret = ext4_journal_get_write_access(handle, iloc.bh);
+ if (ret)
+ goto out;
+
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, 0, flags);
@@ -709,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
out_up_read:
up_read(&EXT4_I(inode)->xattr_sem);
out:
- if (handle)
+ if (handle && (ret != 1))
ext4_journal_stop(handle);
brelse(iloc.bh);
return ret;
@@ -751,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
ext4_write_unlock_xattr(inode, &no_expand);
brelse(iloc.bh);
+ mark_inode_dirty(inode);
out:
return copied;
}
@@ -886,18 +892,17 @@ retry_journal:
flags |= AOP_FLAG_NOFS;
if (ret == -ENOSPC) {
+ ext4_journal_stop(handle);
ret = ext4_da_convert_inline_data_to_extent(mapping,
inode,
flags,
fsdata);
- ext4_journal_stop(handle);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_journal;
goto out;
}
-
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page) {
ret = -ENOMEM;
@@ -915,6 +920,9 @@ retry_journal:
if (ret < 0)
goto out_release_page;
}
+ ret = ext4_journal_get_write_access(handle, iloc.bh);
+ if (ret)
+ goto out_release_page;
up_read(&EXT4_I(inode)->xattr_sem);
*pagep = page;
@@ -935,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
unsigned len, unsigned copied,
struct page *page)
{
- int i_size_changed = 0;
int ret;
ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
@@ -953,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
* But it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
- if (pos+copied > inode->i_size) {
+ if (pos+copied > inode->i_size)
i_size_write(inode, pos+copied);
- i_size_changed = 1;
- }
unlock_page(page);
put_page(page);
@@ -966,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
* ordering of page lock and transaction start for journaling
* filesystems.
*/
- if (i_size_changed)
- mark_inode_dirty(inode);
+ mark_inode_dirty(inode);
return copied;
}
@@ -1890,42 +1894,6 @@ out:
return (error < 0 ? error : 0);
}
-/*
- * Called during xattr set, and if we can sparse space 'needed',
- * just create the extent tree evict the data to the outer block.
- *
- * We use jbd2 instead of page cache to move data to the 1st block
- * so that the whole transaction can be committed as a whole and
- * the data isn't lost because of the delayed page cache write.
- */
-int ext4_try_to_evict_inline_data(handle_t *handle,
- struct inode *inode,
- int needed)
-{
- int error;
- struct ext4_xattr_entry *entry;
- struct ext4_inode *raw_inode;
- struct ext4_iloc iloc;
-
- error = ext4_get_inode_loc(inode, &iloc);
- if (error)
- return error;
-
- raw_inode = ext4_raw_inode(&iloc);
- entry = (struct ext4_xattr_entry *)((void *)raw_inode +
- EXT4_I(inode)->i_inline_off);
- if (EXT4_XATTR_LEN(entry->e_name_len) +
- EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
- error = -ENOSPC;
- goto out;
- }
-
- error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-out:
- brelse(iloc.bh);
- return error;
-}
-
int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
handle_t *handle;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2ea07efbe016..d0dd585add6a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -317,7 +317,7 @@ stop_handle:
* (Well, we could do this if we need to, but heck - it works)
*/
ext4_orphan_del(handle, inode);
- EXT4_I(inode)->i_dtime = get_seconds();
+ EXT4_I(inode)->i_dtime = (__u32)ktime_get_real_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
@@ -402,9 +402,9 @@ static int __check_block_validity(struct inode *inode, const char *func,
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
- "lblock %lu mapped to illegal pblock "
+ "lblock %lu mapped to illegal pblock %llu "
"(length %d)", (unsigned long) map->m_lblk,
- map->m_len);
+ map->m_pblk, map->m_len);
return -EFSCORRUPTED;
}
return 0;
@@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file,
loff_t old_size = inode->i_size;
int ret = 0, ret2;
int i_size_changed = 0;
+ int inline_data = ext4_has_inline_data(inode);
trace_ext4_write_end(inode, pos, len, copied);
- if (ext4_has_inline_data(inode)) {
+ if (inline_data) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0) {
@@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file,
* ordering of page lock and transaction start for journaling
* filesystems.
*/
- if (i_size_changed)
+ if (i_size_changed || inline_data)
ext4_mark_inode_dirty(handle, inode);
if (pos + len > inode->i_size && ext4_can_truncate(inode))
@@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file,
int partial = 0;
unsigned from, to;
int size_changed = 0;
+ int inline_data = ext4_has_inline_data(inode);
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_SIZE - 1);
@@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file,
BUG_ON(!ext4_handle_valid(handle));
- if (ext4_has_inline_data(inode)) {
+ if (inline_data) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0) {
@@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file,
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
- if (size_changed) {
+ if (size_changed || inline_data) {
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
@@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page,
}
if (inline_data) {
- BUFFER_TRACE(inode_bh, "get write access");
- ret = ext4_journal_get_write_access(handle, inode_bh);
-
- err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
-
+ ret = ext4_mark_inode_dirty(handle, inode);
} else {
ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
@@ -3327,7 +3325,8 @@ static int ext4_readpage(struct file *file, struct page *page)
ret = ext4_readpage_inline(inode, page);
if (ret == -EAGAIN)
- return ext4_mpage_readpages(page->mapping, NULL, page, 1);
+ return ext4_mpage_readpages(page->mapping, NULL, page, 1,
+ false);
return ret;
}
@@ -3342,7 +3341,7 @@ ext4_readpages(struct file *file, struct address_space *mapping,
if (ext4_has_inline_data(inode))
return 0;
- return ext4_mpage_readpages(mapping, pages, NULL, nr_pages);
+ return ext4_mpage_readpages(mapping, pages, NULL, nr_pages, true);
}
static void ext4_invalidatepage(struct page *page, unsigned int offset,
@@ -4193,6 +4192,39 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
return 0;
}
+static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
+{
+ *did_unlock = true;
+ up_write(&ei->i_mmap_sem);
+ schedule();
+ down_write(&ei->i_mmap_sem);
+}
+
+int ext4_break_layouts(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct page *page;
+ bool retry;
+ int error;
+
+ if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+ return -EINVAL;
+
+ do {
+ retry = false;
+ page = dax_layout_busy_page(inode->i_mapping);
+ if (!page)
+ return 0;
+
+ error = ___wait_var_event(&page->_refcount,
+ atomic_read(&page->_refcount) == 1,
+ TASK_INTERRUPTIBLE, 0, 0,
+ ext4_wait_dax_page(ei, &retry));
+ } while (error == 0 && retry);
+
+ return error;
+}
+
/*
* ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
@@ -4266,6 +4298,11 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
* page cache.
*/
down_write(&EXT4_I(inode)->i_mmap_sem);
+
+ ret = ext4_break_layouts(inode);
+ if (ret)
+ goto out_dio;
+
first_block_offset = round_up(offset, sb->s_blocksize);
last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
@@ -4506,7 +4543,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
int inodes_per_block, inode_offset;
iloc->bh = NULL;
- if (!ext4_valid_inum(sb, inode->i_ino))
+ if (inode->i_ino < EXT4_ROOT_INO ||
+ inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return -EFSCORRUPTED;
iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
@@ -4945,17 +4983,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ret = -EFSCORRUPTED;
goto bad_inode;
} else if (!ext4_has_inline_data(inode)) {
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- (S_ISLNK(inode->i_mode) &&
- !ext4_inode_is_fast_symlink(inode))))
- /* Validate extent which is part of inode */
+ /* validate the block references in the inode */
+ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ (S_ISLNK(inode->i_mode) &&
+ !ext4_inode_is_fast_symlink(inode))) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_check_inode(inode);
- } else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- (S_ISLNK(inode->i_mode) &&
- !ext4_inode_is_fast_symlink(inode))) {
- /* Validate block references which are part of inode */
- ret = ext4_ind_check_inode(inode);
+ else
+ ret = ext4_ind_check_inode(inode);
}
}
if (ret)
@@ -5554,6 +5589,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
ext4_wait_for_tail_page_commit(inode);
}
down_write(&EXT4_I(inode)->i_mmap_sem);
+
+ rc = ext4_break_layouts(inode);
+ if (rc) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ error = rc;
+ goto err_out;
+ }
+
/*
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 6eae2b91aafa..e29fce2fbf25 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -14,6 +14,7 @@
#include <linux/log2.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/nospec.h>
#include <linux/backing-dev.h>
#include <trace/events/ext4.h>
@@ -2140,7 +2141,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
* This should tell if fe_len is exactly power of 2
*/
if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0)
- ac->ac_2order = i - 1;
+ ac->ac_2order = array_index_nospec(i - 1,
+ sb->s_blocksize_bits + 2);
}
/* if stream allocation is enabled, use global goal */
@@ -2423,7 +2425,8 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
* initialize bb_free to be able to skip
* empty groups without initialization
*/
- if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ if (ext4_has_group_desc_csum(sb) &&
+ (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
meta_group_info[i]->bb_free =
ext4_free_clusters_after_init(sb, group, desc);
} else {
@@ -2989,7 +2992,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
#endif
ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
ac->ac_b_ex.fe_len);
- if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+ 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,
@@ -3797,7 +3801,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
ext4_group_t group;
ext4_grpblk_t bit;
unsigned long long grp_blk_start;
- int err = 0;
int free = 0;
BUG_ON(pa->pa_deleted == 0);
@@ -3838,7 +3841,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
}
atomic_add(free, &sbi->s_mb_discarded);
- return err;
+ return 0;
}
static noinline_for_stack int
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 27b9a76a0dfa..39b07c2d3384 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -147,7 +147,7 @@ static int kmmpd(void *data)
mmp_block = le64_to_cpu(es->s_mmp_block);
mmp = (struct mmp_struct *)(bh->b_data);
- mmp->mmp_time = cpu_to_le64(get_seconds());
+ mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
/*
* Start with the higher mmp_check_interval and reduce it if
* the MMP block is being updated on time.
@@ -165,7 +165,7 @@ static int kmmpd(void *data)
seq = 1;
mmp->mmp_seq = cpu_to_le32(seq);
- mmp->mmp_time = cpu_to_le64(get_seconds());
+ mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
last_update_time = jiffies;
retval = write_mmp_block(sb, bh);
@@ -186,11 +186,8 @@ static int kmmpd(void *data)
goto exit_thread;
}
- if (sb_rdonly(sb)) {
- ext4_warning(sb, "kmmpd being stopped since filesystem "
- "has been remounted as readonly.");
- goto exit_thread;
- }
+ if (sb_rdonly(sb))
+ break;
diff = jiffies - last_update_time;
if (diff < mmp_update_interval * HZ)
@@ -244,7 +241,7 @@ static int kmmpd(void *data)
* Unmount seems to be clean.
*/
mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
- mmp->mmp_time = cpu_to_le64(get_seconds());
+ mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
retval = write_mmp_block(sb, bh);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 8e17efdcbf11..a409ff70d67b 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -134,9 +134,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
mapping[0] = inode1->i_mapping;
mapping[1] = inode2->i_mapping;
} else {
- pgoff_t tmp = index1;
- index1 = index2;
- index2 = tmp;
+ swap(index1, index2);
mapping[0] = inode2->i_mapping;
mapping[1] = inode1->i_mapping;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2a4c25c4681d..116ff68c5bd4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1398,6 +1398,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
goto cleanup_and_exit;
dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
"falling back\n"));
+ ret = NULL;
}
nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
if (!nblocks) {
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 19b87a8de6ff..f461d75ac049 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -98,7 +98,7 @@ static void mpage_end_io(struct bio *bio)
int ext4_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
- unsigned nr_pages)
+ unsigned nr_pages, bool is_readahead)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
@@ -259,7 +259,8 @@ int ext4_mpage_readpages(struct address_space *mapping,
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
bio->bi_private = ctx;
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
+ bio_set_op_attrs(bio, REQ_OP_READ,
+ is_readahead ? REQ_RAHEAD : 0);
}
length = first_hole << blkbits;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0c4c2201b3aa..5863fd22e90b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -312,6 +312,24 @@ void ext4_itable_unused_set(struct super_block *sb,
bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}
+static void __ext4_update_tstamp(__le32 *lo, __u8 *hi)
+{
+ time64_t now = ktime_get_real_seconds();
+
+ now = clamp_val(now, 0, (1ull << 40) - 1);
+
+ *lo = cpu_to_le32(lower_32_bits(now));
+ *hi = upper_32_bits(now);
+}
+
+static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
+{
+ return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
+}
+#define ext4_update_tstamp(es, tstamp) \
+ __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
+#define ext4_get_tstamp(es, tstamp) \
+ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
static void __save_error_info(struct super_block *sb, const char *func,
unsigned int line)
@@ -322,11 +340,12 @@ static void __save_error_info(struct super_block *sb, const char *func,
if (bdev_read_only(sb->s_bdev))
return;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- es->s_last_error_time = cpu_to_le32(get_seconds());
+ ext4_update_tstamp(es, s_last_error_time);
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
es->s_last_error_line = cpu_to_le32(line);
if (!es->s_first_error_time) {
es->s_first_error_time = es->s_last_error_time;
+ es->s_first_error_time_hi = es->s_last_error_time_hi;
strncpy(es->s_first_error_func, func,
sizeof(es->s_first_error_func));
es->s_first_error_line = cpu_to_le32(line);
@@ -405,6 +424,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
static void ext4_handle_error(struct super_block *sb)
{
+ if (test_opt(sb, WARN_ON_ERROR))
+ WARN_ON_ONCE(1);
+
if (sb_rdonly(sb))
return;
@@ -740,6 +762,9 @@ __acquires(bitlock)
va_end(args);
}
+ if (test_opt(sb, WARN_ON_ERROR))
+ WARN_ON_ONCE(1);
+
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
return;
@@ -770,26 +795,26 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+ int ret;
- if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) &&
- !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) {
- percpu_counter_sub(&sbi->s_freeclusters_counter,
- grp->bb_free);
- set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
- &grp->bb_state);
+ if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) {
+ ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+ &grp->bb_state);
+ if (!ret)
+ percpu_counter_sub(&sbi->s_freeclusters_counter,
+ grp->bb_free);
}
- if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) &&
- !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
- if (gdp) {
+ if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) {
+ ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
+ &grp->bb_state);
+ if (!ret && gdp) {
int count;
count = ext4_free_inodes_count(sb, gdp);
percpu_counter_sub(&sbi->s_freeinodes_counter,
count);
}
- set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
- &grp->bb_state);
}
}
@@ -1371,7 +1396,8 @@ enum {
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
- Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+ Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
+ Opt_nowarn_on_error, Opt_mblk_io_submit,
Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
@@ -1438,6 +1464,8 @@ static const match_table_t tokens = {
{Opt_dax, "dax"},
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
+ {Opt_warn_on_error, "warn_on_error"},
+ {Opt_nowarn_on_error, "nowarn_on_error"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
@@ -1602,6 +1630,8 @@ static const struct mount_opts {
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_CLEAR},
+ {Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
+ {Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
@@ -2163,8 +2193,8 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
"warning: maximal mount count reached, "
"running e2fsck is recommended");
else if (le32_to_cpu(es->s_checkinterval) &&
- (le32_to_cpu(es->s_lastcheck) +
- le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+ (ext4_get_tstamp(es, s_lastcheck) +
+ le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds()))
ext4_msg(sb, KERN_WARNING,
"warning: checktime reached, "
"running e2fsck is recommended");
@@ -2173,7 +2203,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
le16_add_cpu(&es->s_mnt_count, 1);
- es->s_mtime = cpu_to_le32(get_seconds());
+ ext4_update_tstamp(es, s_mtime);
ext4_update_dynamic_rev(sb);
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
@@ -2331,6 +2361,7 @@ static int ext4_check_descriptors(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
ext4_fsblk_t last_block;
+ ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0);
ext4_fsblk_t block_bitmap;
ext4_fsblk_t inode_bitmap;
ext4_fsblk_t inode_table;
@@ -2363,6 +2394,14 @@ static int ext4_check_descriptors(struct super_block *sb,
if (!sb_rdonly(sb))
return 0;
}
+ if (block_bitmap >= sb_block + 1 &&
+ block_bitmap <= last_bg_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Block bitmap for group %u overlaps "
+ "block group descriptors", i);
+ if (!sb_rdonly(sb))
+ return 0;
+ }
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
@@ -2377,6 +2416,14 @@ static int ext4_check_descriptors(struct super_block *sb,
if (!sb_rdonly(sb))
return 0;
}
+ if (inode_bitmap >= sb_block + 1 &&
+ inode_bitmap <= last_bg_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode bitmap for group %u overlaps "
+ "block group descriptors", i);
+ if (!sb_rdonly(sb))
+ return 0;
+ }
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
@@ -2391,6 +2438,14 @@ static int ext4_check_descriptors(struct super_block *sb,
if (!sb_rdonly(sb))
return 0;
}
+ if (inode_table >= sb_block + 1 &&
+ inode_table <= last_bg_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode table for group %u overlaps "
+ "block group descriptors", i);
+ if (!sb_rdonly(sb))
+ return 0;
+ }
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -2839,8 +2894,9 @@ static void print_daily_error_info(struct timer_list *t)
ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
- sb->s_id, le32_to_cpu(es->s_first_error_time),
+ printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d",
+ sb->s_id,
+ ext4_get_tstamp(es, s_first_error_time),
(int) sizeof(es->s_first_error_func),
es->s_first_error_func,
le32_to_cpu(es->s_first_error_line));
@@ -2853,8 +2909,9 @@ static void print_daily_error_info(struct timer_list *t)
printk(KERN_CONT "\n");
}
if (es->s_last_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
- sb->s_id, le32_to_cpu(es->s_last_error_time),
+ printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d",
+ sb->s_id,
+ ext4_get_tstamp(es, s_last_error_time),
(int) sizeof(es->s_last_error_func),
es->s_last_error_func,
le32_to_cpu(es->s_last_error_line));
@@ -3097,6 +3154,9 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
struct ext4_group_desc *gdp = NULL;
+ if (!ext4_has_group_desc_csum(sb))
+ return ngroups;
+
for (group = 0; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp)
@@ -3469,7 +3529,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_sb_block = sb_block;
if (sb->s_bdev->bd_part)
sbi->s_sectors_written_start =
- part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+ part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
/* Cleanup superblock name */
strreplace(sb->s_id, '/', '!');
@@ -3742,6 +3802,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
le32_to_cpu(es->s_log_block_size));
goto failed_mount;
}
+ if (le32_to_cpu(es->s_log_cluster_size) >
+ (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+ ext4_msg(sb, KERN_ERR,
+ "Invalid log cluster size: %u",
+ le32_to_cpu(es->s_log_cluster_size));
+ goto failed_mount;
+ }
if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
ext4_msg(sb, KERN_ERR,
@@ -3806,6 +3873,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
} else {
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+ if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
+ ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
+ sbi->s_first_ino);
+ goto failed_mount;
+ }
if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
(!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
@@ -3882,13 +3954,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"block size (%d)", clustersize, blocksize);
goto failed_mount;
}
- if (le32_to_cpu(es->s_log_cluster_size) >
- (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
- ext4_msg(sb, KERN_ERR,
- "Invalid log cluster size: %u",
- le32_to_cpu(es->s_log_cluster_size));
- goto failed_mount;
- }
sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
le32_to_cpu(es->s_log_block_size);
sbi->s_clusters_per_group =
@@ -3909,10 +3974,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
} else {
if (clustersize != blocksize) {
- ext4_warning(sb, "fragment/cluster size (%d) != "
- "block size (%d)", clustersize,
- blocksize);
- clustersize = blocksize;
+ ext4_msg(sb, KERN_ERR,
+ "fragment/cluster size (%d) != "
+ "block size (%d)", clustersize, blocksize);
+ goto failed_mount;
}
if (sbi->s_blocks_per_group > blocksize * 8) {
ext4_msg(sb, KERN_ERR,
@@ -3966,6 +4031,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ext4_blocks_count(es));
goto failed_mount;
}
+ if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) &&
+ (sbi->s_cluster_ratio == 1)) {
+ ext4_msg(sb, KERN_WARNING, "bad geometry: first data "
+ "block is 0 with a 1k block and cluster size");
+ goto failed_mount;
+ }
+
blocks_count = (ext4_blocks_count(es) -
le32_to_cpu(es->s_first_data_block) +
EXT4_BLOCKS_PER_GROUP(sb) - 1);
@@ -4001,6 +4073,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ret = -ENOMEM;
goto failed_mount;
}
+ if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+ le32_to_cpu(es->s_inodes_count)) {
+ ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+ le32_to_cpu(es->s_inodes_count),
+ ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+ ret = -EINVAL;
+ goto failed_mount;
+ }
bgl_lock_init(sbi->s_blockgroup_lock);
@@ -4020,14 +4100,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount2;
}
}
+ sbi->s_gdb_count = db_count;
if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
}
- sbi->s_gdb_count = db_count;
-
timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
/* Register extent status tree shrinker */
@@ -4736,6 +4815,14 @@ static int ext4_commit_super(struct super_block *sb, int sync)
if (!sbh || block_device_ejected(sb))
return error;
+
+ /*
+ * The superblock bh should be mapped, but it might not be if the
+ * device was hot-removed. Not much we can do but fail the I/O.
+ */
+ if (!buffer_mapped(sbh))
+ return error;
+
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
@@ -4747,11 +4834,12 @@ static int ext4_commit_super(struct super_block *sb, int sync)
* to complain and force a full file system check.
*/
if (!(sb->s_flags & SB_RDONLY))
- es->s_wtime = cpu_to_le32(get_seconds());
+ ext4_update_tstamp(es, s_wtime);
if (sb->s_bdev->bd_part)
es->s_kbytes_written =
cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
- ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+ ((part_stat_read(sb->s_bdev->bd_part,
+ sectors[STAT_WRITE]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1));
else
es->s_kbytes_written =
@@ -5014,6 +5102,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
#endif
char *orig_data = kstrdup(data, GFP_KERNEL);
+ if (data && !orig_data)
+ return -ENOMEM;
+
/* Store the original options */
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
@@ -5140,6 +5231,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_journal)
ext4_mark_recovery_complete(sb, es);
+ if (sbi->s_mmp_tsk)
+ kthread_stop(sbi->s_mmp_tsk);
} else {
/* Make sure we can mount this feature set readwrite */
if (ext4_has_feature_readonly(sb) ||
@@ -5597,13 +5690,13 @@ static int ext4_enable_quotas(struct super_block *sb)
DQUOT_USAGE_ENABLED |
(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
if (err) {
- for (type--; type >= 0; type--)
- dquot_quota_off(sb, type);
-
ext4_warning(sb,
"Failed to enable quota tracking "
"(type=%d, err=%d). Please run "
"e2fsck to fix.", type, err);
+ for (type--; type >= 0; type--)
+ dquot_quota_off(sb, type);
+
return err;
}
}
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f34da0bb8f17..9212a026a1f1 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -25,6 +25,8 @@ typedef enum {
attr_reserved_clusters,
attr_inode_readahead,
attr_trigger_test_error,
+ attr_first_error_time,
+ attr_last_error_time,
attr_feature,
attr_pointer_ui,
attr_pointer_atomic,
@@ -56,7 +58,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
if (!sb->s_bdev->bd_part)
return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%lu\n",
- (part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+ (part_stat_read(sb->s_bdev->bd_part,
+ sectors[STAT_WRITE]) -
sbi->s_sectors_written_start) >> 1);
}
@@ -68,7 +71,8 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)(sbi->s_kbytes_written +
- ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+ ((part_stat_read(sb->s_bdev->bd_part,
+ sectors[STAT_WRITE]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
@@ -182,8 +186,8 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
-EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
-EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
+EXT4_ATTR(first_error_time, 0444, first_error_time);
+EXT4_ATTR(last_error_time, 0444, last_error_time);
static unsigned int old_bump_val = 128;
EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -249,6 +253,15 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
return NULL;
}
+static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
+{
+ return snprintf(buf, PAGE_SIZE, "%lld",
+ ((time64_t)hi << 32) + le32_to_cpu(lo));
+}
+
+#define print_tstamp(buf, es, tstamp) \
+ __print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi)
+
static ssize_t ext4_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
@@ -274,8 +287,12 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
case attr_pointer_ui:
if (!ptr)
return 0;
- return snprintf(buf, PAGE_SIZE, "%u\n",
- *((unsigned int *) ptr));
+ if (a->attr_ptr == ptr_ext4_super_block_offset)
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ le32_to_cpup(ptr));
+ else
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ *((unsigned int *) ptr));
case attr_pointer_atomic:
if (!ptr)
return 0;
@@ -283,6 +300,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
atomic_read((atomic_t *) ptr));
case attr_feature:
return snprintf(buf, PAGE_SIZE, "supported\n");
+ case attr_first_error_time:
+ return print_tstamp(buf, sbi->s_es, s_first_error_time);
+ case attr_last_error_time:
+ return print_tstamp(buf, sbi->s_es, s_last_error_time);
}
return 0;
@@ -308,7 +329,10 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret)
return ret;
- *((unsigned int *) ptr) = t;
+ if (a->attr_ptr == ptr_ext4_super_block_offset)
+ *((__le32 *) ptr) = cpu_to_le32(t);
+ else
+ *((unsigned int *) ptr) = t;
return len;
case attr_inode_readahead:
return inode_readahead_blks_store(sbi, buf, len);
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 0cb13badf473..bcbe3668c1d4 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,6 +11,10 @@
*/
static inline void ext4_truncate_failed_write(struct inode *inode)
{
+ /*
+ * We don't need to call ext4_break_layouts() because the blocks we
+ * are truncating were never visible to userspace.
+ */
down_write(&EXT4_I(inode)->i_mmap_sem);
truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fc4ced59c565..f36fc5d5b257 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -190,6 +190,8 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
if ((void *)next >= end)
return -EFSCORRUPTED;
+ if (strnlen(e->e_name, e->e_name_len) != e->e_name_len)
+ return -EFSCORRUPTED;
e = next;
}
@@ -230,12 +232,12 @@ __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh,
{
int error = -EFSCORRUPTED;
- if (buffer_verified(bh))
- return 0;
-
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1))
goto errout;
+ if (buffer_verified(bh))
+ return 0;
+
error = -EFSBADCRC;
if (!ext4_xattr_block_csum_verify(inode, bh))
goto errout;
@@ -1560,7 +1562,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
handle_t *handle, struct inode *inode,
bool is_block)
{
- struct ext4_xattr_entry *last;
+ struct ext4_xattr_entry *last, *next;
struct ext4_xattr_entry *here = s->here;
size_t min_offs = s->end - s->base, name_len = strlen(i->name);
int in_inode = i->in_inode;
@@ -1595,7 +1597,13 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
/* Compute min_offs and last. */
last = s->first;
- for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ for (; !IS_LAST_ENTRY(last); last = next) {
+ next = EXT4_XATTR_NEXT(last);
+ if ((void *)next >= s->end) {
+ EXT4_ERROR_INODE(inode, "corrupted xattr entries");
+ ret = -EFSCORRUPTED;
+ goto out;
+ }
if (!last->e_value_inum && last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < min_offs)
@@ -2206,23 +2214,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
if (EXT4_I(inode)->i_extra_isize == 0)
return -ENOSPC;
error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
- if (error) {
- if (error == -ENOSPC &&
- ext4_has_inline_data(inode)) {
- error = ext4_try_to_evict_inline_data(handle, inode,
- EXT4_XATTR_LEN(strlen(i->name) +
- EXT4_XATTR_SIZE(i->value_len)));
- if (error)
- return error;
- error = ext4_xattr_ibody_find(inode, i, is);
- if (error)
- return error;
- error = ext4_xattr_set_entry(i, s, handle, inode,
- false /* is_block */);
- }
- if (error)
- return error;
- }
+ 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);
@@ -2651,6 +2644,11 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
last = IFIRST(header);
/* Find the entry best suited to be pushed into EA block */
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ /* never move system.data out of the inode */
+ if ((last->e_name_len == 4) &&
+ (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) &&
+ !memcmp(last->e_name, "data", 4))
+ continue;
total_size = EXT4_XATTR_LEN(last->e_name_len);
if (!last->e_value_inum)
total_size += EXT4_XATTR_SIZE(
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.