aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/acl.h5
-rw-r--r--fs/ext4/balloc.c25
-rw-r--r--fs/ext4/ext4.h8
-rw-r--r--fs/ext4/extents.c10
-rw-r--r--fs/ext4/fsmap.c10
-rw-r--r--fs/ext4/indirect.c17
-rw-r--r--fs/ext4/inline.c26
-rw-r--r--fs/ext4/inode.c78
-rw-r--r--fs/ext4/ioctl.c16
-rw-r--r--fs/ext4/mballoc.c217
-rw-r--r--fs/ext4/namei.c42
-rw-r--r--fs/ext4/page-io.c11
-rw-r--r--fs/ext4/resize.c25
-rw-r--r--fs/ext4/super.c94
-rw-r--r--fs/ext4/sysfs.c7
-rw-r--r--fs/ext4/xattr.c278
-rw-r--r--fs/ext4/xattr.h7
17 files changed, 537 insertions, 339 deletions
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 9b63f5416a2f..7f3b25b3fa6d 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -67,6 +67,11 @@ extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
static inline int
ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
{
+ /* usually, the umask is applied by posix_acl_create(), but if
+ ext4 ACL support is disabled at compile time, we need to do
+ it here, because posix_acl_create() will never be called */
+ inode->i_mode &= ~current_umask();
+
return 0;
}
#endif /* CONFIG_EXT4_FS_POSIX_ACL */
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f9645de9d04c..9761aeb4b224 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -303,6 +303,22 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
return desc;
}
+static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb,
+ ext4_group_t block_group,
+ struct buffer_head *bh)
+{
+ ext4_grpblk_t next_zero_bit;
+ unsigned long bitmap_size = sb->s_blocksize * 8;
+ unsigned int offset = num_clusters_in_group(sb, block_group);
+
+ if (bitmap_size <= offset)
+ return 0;
+
+ next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset);
+
+ return (next_zero_bit < bitmap_size ? next_zero_bit : 0);
+}
+
/*
* Return the block number which was discovered to be invalid, or 0 if
* the block bitmap is valid.
@@ -395,6 +411,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
return -EFSCORRUPTED;
}
+ blk = ext4_valid_block_bitmap_padding(sb, block_group, bh);
+ if (unlikely(blk != 0)) {
+ ext4_unlock_group(sb, block_group);
+ ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set",
+ block_group, blk);
+ ext4_mark_group_bitmap_corrupted(sb, block_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+ return -EFSCORRUPTED;
+ }
set_buffer_verified(bh);
verified:
ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6938dff9f04b..fa2579abea7d 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -503,7 +503,7 @@ enum {
*
* It's not paranoia if the Murphy's Law really *is* out to get you. :-)
*/
-#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG))
+#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG))
#define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG))
static inline void ext4_check_flag_values(void)
@@ -929,11 +929,13 @@ do { \
* where the second inode has larger inode number
* than the first
* I_DATA_SEM_QUOTA - Used for quota inodes only
+ * I_DATA_SEM_EA - Used for ea_inodes only
*/
enum {
I_DATA_SEM_NORMAL = 0,
I_DATA_SEM_OTHER,
I_DATA_SEM_QUOTA,
+ I_DATA_SEM_EA
};
@@ -1410,7 +1412,7 @@ struct ext4_sb_info {
unsigned long s_commit_interval;
u32 s_max_batch_time;
u32 s_min_batch_time;
- struct block_device *journal_bdev;
+ struct block_device *s_journal_bdev;
#ifdef CONFIG_QUOTA
/* Names of quota files with journalled quota */
char __rcu *s_qf_names[EXT4_MAXQUOTAS];
@@ -1498,7 +1500,7 @@ struct ext4_sb_info {
struct task_struct *s_mmp_tsk;
/* record the last minlen when FITRIM is called. */
- atomic_t s_last_trim_minblks;
+ unsigned long s_last_trim_minblks;
/* Reference to checksum algorithm driver via cryptoapi */
struct crypto_shash *s_chksum_driver;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 6c492fca60c4..d931252b7d0d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -997,6 +997,11 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
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) {
@@ -1006,11 +1011,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
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);
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 6f3f245f3a80..69c76327792e 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
keys[0].fmr_physical = bofs;
if (keys[1].fmr_physical >= eofs)
keys[1].fmr_physical = eofs - 1;
+ if (keys[1].fmr_physical < keys[0].fmr_physical)
+ return 0;
start_fsb = keys[0].fmr_physical;
end_fsb = keys[1].fmr_physical;
@@ -574,8 +576,8 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb,
if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev))
return true;
- if (EXT4_SB(sb)->journal_bdev &&
- fm->fmr_device == new_encode_dev(EXT4_SB(sb)->journal_bdev->bd_dev))
+ if (EXT4_SB(sb)->s_journal_bdev &&
+ fm->fmr_device == new_encode_dev(EXT4_SB(sb)->s_journal_bdev->bd_dev))
return true;
return false;
}
@@ -645,9 +647,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
memset(handlers, 0, sizeof(handlers));
handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev);
handlers[0].gfd_fn = ext4_getfsmap_datadev;
- if (EXT4_SB(sb)->journal_bdev) {
+ if (EXT4_SB(sb)->s_journal_bdev) {
handlers[1].gfd_dev = new_encode_dev(
- EXT4_SB(sb)->journal_bdev->bd_dev);
+ EXT4_SB(sb)->s_journal_bdev->bd_dev);
handlers[1].gfd_fn = ext4_getfsmap_logdev;
}
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index a5442528a60d..9bf711d63368 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -148,6 +148,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
struct super_block *sb = inode->i_sb;
Indirect *p = chain;
struct buffer_head *bh;
+ unsigned int key;
int ret = -EIO;
*err = 0;
@@ -156,7 +157,13 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
if (!p->key)
goto no_block;
while (--depth) {
- bh = sb_getblk(sb, le32_to_cpu(p->key));
+ key = le32_to_cpu(p->key);
+ if (key > ext4_blocks_count(EXT4_SB(sb)->s_es)) {
+ /* the block was out of range */
+ ret = -EFSCORRUPTED;
+ goto failure;
+ }
+ bh = sb_getblk(sb, key);
if (unlikely(!bh)) {
ret = -ENOMEM;
goto failure;
@@ -635,6 +642,14 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
ext4_update_inode_fsync_trans(handle, inode, 1);
count = ar.len;
+
+ /*
+ * Update reserved blocks/metadata blocks after successful block
+ * allocation which had been deferred till now.
+ */
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ ext4_da_update_reserve_space(inode, count, 1);
+
got_it:
map->m_flags |= EXT4_MAP_MAPPED;
map->m_pblk = le32_to_cpu(chain[depth-1].key);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index b1c6b9398eef..71bb3cfc5933 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -32,6 +32,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
struct ext4_xattr_ibody_header *header;
struct ext4_xattr_entry *entry;
struct ext4_inode *raw_inode;
+ void *end;
int free, min_offs;
if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
@@ -55,14 +56,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
raw_inode = ext4_raw_inode(iloc);
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
+ end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
/* Compute min_offs. */
- for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+ while (!IS_LAST_ENTRY(entry)) {
+ void *next = EXT4_XATTR_NEXT(entry);
+
+ if (next >= end) {
+ EXT4_ERROR_INODE(inode,
+ "corrupt xattr in inline inode");
+ return 0;
+ }
if (!entry->e_value_inum && entry->e_value_size) {
size_t offs = le16_to_cpu(entry->e_value_offs);
if (offs < min_offs)
min_offs = offs;
}
+ entry = next;
}
free = min_offs -
((void *)entry - (void *)IFIRST(header)) - sizeof(__u32);
@@ -157,7 +167,6 @@ int ext4_find_inline_data_nolock(struct inode *inode)
(void *)ext4_raw_inode(&is.iloc));
EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
le32_to_cpu(is.s.here->e_value_size);
- ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
}
out:
brelse(is.iloc.bh);
@@ -207,7 +216,7 @@ 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,
@@ -289,7 +298,7 @@ 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,
@@ -349,7 +358,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
value, len);
- if (error == -ENODATA)
+ if (error < 0)
goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
@@ -361,7 +370,7 @@ 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;
@@ -434,7 +443,7 @@ 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;
@@ -1978,8 +1987,7 @@ 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 95139c992a54..646285fbc9fc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -207,6 +207,8 @@ void ext4_evict_inode(struct inode *inode)
trace_ext4_evict_inode(inode);
+ if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
+ ext4_evict_ea_inode(inode);
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
@@ -666,16 +668,6 @@ found:
*/
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
-
- /*
- * Update reserved blocks/metadata blocks after successful
- * block allocation which had been deferred till now. We don't
- * support fallocate for non extent files. So we can update
- * reserve space here.
- */
- if ((retval > 0) &&
- (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
- ext4_da_update_reserve_space(inode, retval, 1);
}
if (retval > 0) {
@@ -1426,7 +1418,8 @@ static int ext4_write_end(struct file *file,
int inline_data = ext4_has_inline_data(inode);
trace_ext4_write_end(inode, pos, len, copied);
- if (inline_data) {
+ if (inline_data &&
+ ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0) {
@@ -4549,7 +4542,7 @@ int ext4_truncate(struct inode *inode)
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
- return 0;
+ goto out_trace;
ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
@@ -4560,16 +4553,15 @@ int ext4_truncate(struct inode *inode)
int has_inline = 1;
err = ext4_inline_data_truncate(inode, &has_inline);
- if (err)
- return err;
- if (has_inline)
- return 0;
+ if (err || has_inline)
+ goto out_trace;
}
/* If we zero-out tail of the page, we have to create jinode for jbd2 */
if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
- if (ext4_inode_attach_jinode(inode) < 0)
- return 0;
+ err = ext4_inode_attach_jinode(inode);
+ if (err)
+ goto out_trace;
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
@@ -4578,8 +4570,10 @@ int ext4_truncate(struct inode *inode)
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto out_trace;
+ }
if (inode->i_size & (inode->i_sb->s_blocksize - 1))
ext4_block_truncate_page(handle, mapping, inode->i_size);
@@ -4628,6 +4622,7 @@ out_stop:
ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
+out_trace:
trace_ext4_truncate_exit(inode);
return err;
}
@@ -4663,9 +4658,17 @@ static int __ext4_get_inode_loc(struct inode *inode,
inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
inode_offset = ((inode->i_ino - 1) %
EXT4_INODES_PER_GROUP(sb));
- block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
+ block = ext4_inode_table(sb, gdp);
+ if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) ||
+ (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) {
+ ext4_error(sb, "Invalid inode table block %llu in "
+ "block_group %u", block, iloc->block_group);
+ return -EFSCORRUPTED;
+ }
+ block += (inode_offset / inodes_per_block);
+
bh = sb_getblk(sb, block);
if (unlikely(!bh))
return -ENOMEM;
@@ -4853,8 +4856,13 @@ static inline int ext4_iget_extra_inode(struct inode *inode,
if (EXT4_INODE_HAS_XATTR_SPACE(inode) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ int err;
+
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
- return ext4_find_inline_data_nolock(inode);
+ err = ext4_find_inline_data_nolock(inode);
+ if (!err && ext4_has_inline_data(inode))
+ ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+ return err;
} else
EXT4_I(inode)->i_inline_off = 0;
return 0;
@@ -4930,13 +4938,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
goto bad_inode;
raw_inode = ext4_raw_inode(&iloc);
- if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) {
- ext4_error_inode(inode, function, line, 0,
- "iget: root inode unallocated");
- ret = -EFSCORRUPTED;
- goto bad_inode;
- }
-
if ((flags & EXT4_IGET_HANDLE) &&
(raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) {
ret = -ESTALE;
@@ -5007,11 +5008,16 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0) {
- if ((inode->i_mode == 0 ||
+ if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
ino != EXT4_BOOT_LOADER_INO) {
- /* this inode is deleted */
- ret = -ESTALE;
+ /* this inode is deleted or unallocated */
+ if (flags & EXT4_IGET_SPECIAL) {
+ ext4_error_inode(inode, function, line, 0,
+ "iget: special inode unallocated");
+ ret = -EFSCORRUPTED;
+ } else
+ ret = -ESTALE;
goto bad_inode;
}
/* The only unlinked inodes we let through here have
@@ -6033,6 +6039,14 @@ static int __ext4_expand_extra_isize(struct inode *inode,
return 0;
}
+ /*
+ * We may need to allocate external xattr block so we need quotas
+ * initialized. Here we can be called with various locks held so we
+ * cannot affort to initialize quotas ourselves. So just bail.
+ */
+ if (dquot_initialize_needed(inode))
+ return -EAGAIN;
+
/* try to expand with EAs present */
error = ext4_expand_extra_isize_ea(inode, new_extra_isize,
raw_inode, handle);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 484cb68c34d9..43e036f0b661 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -169,7 +169,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
- if (inode_bl->i_nlink == 0) {
+ if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
@@ -178,6 +178,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
ei_bl->i_flags = 0;
inode_set_iversion(inode_bl, 1);
i_size_write(inode_bl, 0);
+ EXT4_I(inode_bl)->i_disksize = inode_bl->i_size;
inode_bl->i_mode = S_IFREG;
if (ext4_has_feature_extents(sb)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
@@ -449,6 +450,10 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
if (ext4_is_quota_file(inode))
return err;
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+
err = ext4_get_inode_loc(inode, &iloc);
if (err)
return err;
@@ -464,10 +469,6 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
brelse(iloc.bh);
}
- err = dquot_initialize(inode);
- if (err)
- return err;
-
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
EXT4_QUOTA_INIT_BLOCKS(sb) +
EXT4_QUOTA_DEL_BLOCKS(sb) + 3);
@@ -560,6 +561,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
__u32 flags;
+ struct super_block *ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -578,7 +580,9 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg)
switch (flags) {
case EXT4_GOING_FLAGS_DEFAULT:
- freeze_bdev(sb->s_bdev);
+ ret = freeze_bdev(sb->s_bdev);
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
thaw_bdev(sb->s_bdev, sb);
break;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4ea4fe92eb8c..8875fac9f958 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -16,6 +16,7 @@
#include <linux/slab.h>
#include <linux/nospec.h>
#include <linux/backing-dev.h>
+#include <linux/freezer.h>
#include <trace/events/ext4.h>
#ifdef CONFIG_EXT4_DEBUG
@@ -3089,6 +3090,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
struct ext4_allocation_request *ar)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+ struct ext4_super_block *es = sbi->s_es;
int bsbits, max;
ext4_lblk_t end;
loff_t size, start_off;
@@ -3179,6 +3181,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
start = max(start, rounddown(ac->ac_o_ex.fe_logical,
(ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb)));
+ /* avoid unnecessary preallocation that may trigger assertions */
+ if (start + size > EXT_MAX_BLOCKS)
+ size = EXT_MAX_BLOCKS - start;
+
/* don't cover already allocated blocks in selected range */
if (ar->pleft && start <= ar->lleft) {
size -= ar->lleft + 1 - start;
@@ -3269,18 +3275,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size);
/* define goal start in order to merge */
- if (ar->pright && (ar->lright == (start + size))) {
+ if (ar->pright && (ar->lright == (start + size)) &&
+ ar->pright >= size &&
+ ar->pright - size >= le32_to_cpu(es->s_first_data_block)) {
/* merge to the right */
ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size,
- &ac->ac_f_ex.fe_group,
- &ac->ac_f_ex.fe_start);
+ &ac->ac_g_ex.fe_group,
+ &ac->ac_g_ex.fe_start);
ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
}
- if (ar->pleft && (ar->lleft + 1 == start)) {
+ if (ar->pleft && (ar->lleft + 1 == start) &&
+ ar->pleft + 1 < ext4_blocks_count(es)) {
/* merge to the left */
ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1,
- &ac->ac_f_ex.fe_group,
- &ac->ac_f_ex.fe_start);
+ &ac->ac_g_ex.fe_group,
+ &ac->ac_g_ex.fe_start);
ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
}
@@ -3372,6 +3381,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
BUG_ON(start < pa->pa_pstart);
BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len));
BUG_ON(pa->pa_free < len);
+ BUG_ON(ac->ac_b_ex.fe_len <= 0);
pa->pa_free -= len;
mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa);
@@ -3676,10 +3686,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
return -ENOMEM;
if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) {
- int winl;
- int wins;
- int win;
- int offs;
+ int new_bex_start;
+ int new_bex_end;
/* we can't allocate as much as normalizer wants.
* so, found space must get proper lstart
@@ -3687,26 +3695,40 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
- /* we're limited by original request in that
- * logical block must be covered any way
- * winl is window we can move our chunk within */
- winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
+ /*
+ * Use the below logic for adjusting best extent as it keeps
+ * fragmentation in check while ensuring logical range of best
+ * extent doesn't overflow out of goal extent:
+ *
+ * 1. Check if best ex can be kept at end of goal and still
+ * cover original start
+ * 2. Else, check if best ex can be kept at start of goal and
+ * still cover original start
+ * 3. Else, keep the best ex at start of original request.
+ */
+ new_bex_end = ac->ac_g_ex.fe_logical +
+ EXT4_C2B(sbi, ac->ac_g_ex.fe_len);
+ new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+ if (ac->ac_o_ex.fe_logical >= new_bex_start)
+ goto adjust_bex;
- /* also, we should cover whole original request */
- wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len);
+ new_bex_start = ac->ac_g_ex.fe_logical;
+ new_bex_end =
+ new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
+ if (ac->ac_o_ex.fe_logical < new_bex_end)
+ goto adjust_bex;
- /* the smallest one defines real window */
- win = min(winl, wins);
+ new_bex_start = ac->ac_o_ex.fe_logical;
+ new_bex_end =
+ new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
- offs = ac->ac_o_ex.fe_logical %
- EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
- if (offs && offs < win)
- win = offs;
+adjust_bex:
+ ac->ac_b_ex.fe_logical = new_bex_start;
- ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
- EXT4_NUM_B2C(sbi, win);
BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
+ BUG_ON(new_bex_end > (ac->ac_g_ex.fe_logical +
+ EXT4_C2B(sbi, ac->ac_g_ex.fe_len)));
}
/* preallocation can change ac_b_ex, thus we store actually
@@ -3893,7 +3915,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
trace_ext4_mb_release_group_pa(sb, pa);
BUG_ON(pa->pa_deleted == 0);
ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
- BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
+ if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
+ ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
+ e4b->bd_group, group, pa->pa_pstart);
+ return 0;
+ }
mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
@@ -4927,8 +4953,8 @@ do_more:
* them with group lock_held
*/
if (test_opt(sb, DISCARD)) {
- err = ext4_issue_discard(sb, block_group, bit, count,
- NULL);
+ err = ext4_issue_discard(sb, block_group, bit,
+ count_clusters, NULL);
if (err && err != -EOPNOTSUPP)
ext4_msg(sb, KERN_WARNING, "discard request in"
" group:%d block:%d count:%lu failed"
@@ -5128,19 +5154,19 @@ error_return:
* @sb: super block for the file system
* @start: starting block of the free extent in the alloc. group
* @count: number of blocks to TRIM
- * @group: alloc. group we are working with
* @e4b: ext4 buddy for the group
*
* Trim "count" blocks starting at "start" in the "group". To assure that no
* one will allocate those blocks, mark it as used in buddy bitmap. This must
* be called with under the group lock.
*/
-static int ext4_trim_extent(struct super_block *sb, int start, int count,
- ext4_group_t group, struct ext4_buddy *e4b)
+static int ext4_trim_extent(struct super_block *sb,
+ int start, int count, struct ext4_buddy *e4b)
__releases(bitlock)
__acquires(bitlock)
{
struct ext4_free_extent ex;
+ ext4_group_t group = e4b->bd_group;
int ret = 0;
trace_ext4_trim_extent(sb, group, start, count);
@@ -5163,6 +5189,71 @@ __acquires(bitlock)
return ret;
}
+static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,
+ ext4_group_t grp)
+{
+ if (grp < ext4_get_groups_count(sb))
+ return EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+ return (ext4_blocks_count(EXT4_SB(sb)->s_es) -
+ ext4_group_first_block_no(sb, grp) - 1) >>
+ EXT4_CLUSTER_BITS(sb);
+}
+
+static bool ext4_trim_interrupted(void)
+{
+ return fatal_signal_pending(current) || freezing(current);
+}
+
+static int ext4_try_to_trim_range(struct super_block *sb,
+ struct ext4_buddy *e4b, ext4_grpblk_t start,
+ ext4_grpblk_t max, ext4_grpblk_t minblocks)
+{
+ ext4_grpblk_t next, count, free_count;
+ bool set_trimmed = false;
+ void *bitmap;
+
+ bitmap = e4b->bd_bitmap;
+ if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group))
+ set_trimmed = true;
+ start = max(e4b->bd_info->bb_first_free, start);
+ count = 0;
+ free_count = 0;
+
+ while (start <= max) {
+ start = mb_find_next_zero_bit(bitmap, max + 1, start);
+ if (start > max)
+ break;
+ next = mb_find_next_bit(bitmap, max + 1, start);
+
+ if ((next - start) >= minblocks) {
+ int ret = ext4_trim_extent(sb, start, next - start, e4b);
+
+ if (ret && ret != -EOPNOTSUPP)
+ return count;
+ count += next - start;
+ }
+ free_count += next - start;
+ start = next + 1;
+
+ if (ext4_trim_interrupted())
+ return count;
+
+ if (need_resched()) {
+ ext4_unlock_group(sb, e4b->bd_group);
+ cond_resched();
+ ext4_lock_group(sb, e4b->bd_group);
+ }
+
+ if ((e4b->bd_info->bb_free - free_count) < minblocks)
+ break;
+ }
+
+ if (set_trimmed)
+ EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info);
+
+ return count;
+}
+
/**
* ext4_trim_all_free -- function to trim all free space in alloc. group
* @sb: super block for file system
@@ -5186,10 +5277,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_grpblk_t start, ext4_grpblk_t max,
ext4_grpblk_t minblocks)
{
- void *bitmap;
- ext4_grpblk_t next, count = 0, free_count = 0;
struct ext4_buddy e4b;
- int ret = 0;
+ int ret;
trace_ext4_trim_all_free(sb, group, start, max);
@@ -5199,58 +5288,20 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ret, group);
return ret;
}
- bitmap = e4b.bd_bitmap;
ext4_lock_group(sb, group);
- if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) &&
- minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks))
- goto out;
- start = (e4b.bd_info->bb_first_free > start) ?
- e4b.bd_info->bb_first_free : start;
-
- while (start <= max) {
- start = mb_find_next_zero_bit(bitmap, max + 1, start);
- if (start > max)
- break;
- next = mb_find_next_bit(bitmap, max + 1, start);
-
- if ((next - start) >= minblocks) {
- ret = ext4_trim_extent(sb, start,
- next - start, group, &e4b);
- if (ret && ret != -EOPNOTSUPP)
- break;
- ret = 0;
- count += next - start;
- }
- free_count += next - start;
- start = next + 1;
-
- if (fatal_signal_pending(current)) {
- count = -ERESTARTSYS;
- break;
- }
-
- if (need_resched()) {
- ext4_unlock_group(sb, group);
- cond_resched();
- ext4_lock_group(sb, group);
- }
-
- if ((e4b.bd_info->bb_free - free_count) < minblocks)
- break;
- }
+ if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
+ minblocks < EXT4_SB(sb)->s_last_trim_minblks)
+ ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
+ else
+ ret = 0;
- if (!ret) {
- ret = count;
- EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
- }
-out:
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
ext4_debug("trimmed %d blocks in the group %d\n",
- count, group);
+ ret, group);
return ret;
}
@@ -5295,7 +5346,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
if (minlen > EXT4_CLUSTERS_PER_GROUP(sb))
goto out;
}
- if (end >= max_blks)
+ if (end >= max_blks - 1)
end = max_blks - 1;
if (end <= first_data_blk)
goto out;
@@ -5312,6 +5363,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
for (group = first_group; group <= last_group; group++) {
+ if (ext4_trim_interrupted())
+ break;
grp = ext4_get_group_info(sb, group);
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
@@ -5328,10 +5381,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
*/
if (group == last_group)
end = last_cluster;
-
if (grp->bb_free >= minlen) {
cnt = ext4_trim_all_free(sb, group, first_cluster,
- end, minlen);
+ end, minlen);
if (cnt < 0) {
ret = cnt;
break;
@@ -5347,7 +5399,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
}
if (!ret)
- atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
+ EXT4_SB(sb)->s_last_trim_minblks = minlen;
out:
range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits;
@@ -5376,8 +5428,7 @@ ext4_mballoc_query_range(
ext4_lock_group(sb, group);
- start = (e4b.bd_info->bb_first_free > start) ?
- e4b.bd_info->bb_first_free : start;
+ start = max(e4b.bd_info->bb_first_free, start);
if (end >= EXT4_CLUSTERS_PER_GROUP(sb))
end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a878b9a8d9ea..93d392576c12 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -322,17 +322,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
struct ext4_dir_entry *de)
{
struct ext4_dir_entry_tail *t;
+ int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
#ifdef PARANOID
struct ext4_dir_entry *d, *top;
d = de;
top = (struct ext4_dir_entry *)(((void *)de) +
- (EXT4_BLOCK_SIZE(inode->i_sb) -
- sizeof(struct ext4_dir_entry_tail)));
- while (d < top && d->rec_len)
+ (blocksize - sizeof(struct ext4_dir_entry_tail)));
+ while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize))
d = (struct ext4_dir_entry *)(((void *)d) +
- le16_to_cpu(d->rec_len));
+ ext4_rec_len_from_disk(d->rec_len, blocksize));
if (d != top)
return NULL;
@@ -343,7 +343,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
#endif
if (t->det_reserved_zero1 ||
- le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) ||
+ (ext4_rec_len_from_disk(t->det_rec_len, blocksize) !=
+ sizeof(struct ext4_dir_entry_tail)) ||
t->det_reserved_zero2 ||
t->det_reserved_ft != EXT4_FT_DIR_CSUM)
return NULL;
@@ -425,13 +426,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode,
struct ext4_dir_entry *dp;
struct dx_root_info *root;
int count_offset;
+ int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
+ unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize);
- if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb))
+ if (rlen == blocksize)
count_offset = 8;
- else if (le16_to_cpu(dirent->rec_len) == 12) {
+ else if (rlen == 12) {
dp = (struct ext4_dir_entry *)(((void *)dirent) + 12);
- if (le16_to_cpu(dp->rec_len) !=
- EXT4_BLOCK_SIZE(inode->i_sb) - 12)
+ if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12)
return NULL;
root = (struct dx_root_info *)(((void *)dp + 12));
if (root->reserved_zero ||
@@ -1244,6 +1246,7 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
unsigned int buflen = bh->b_size;
char *base = bh->b_data;
struct dx_hash_info h = *hinfo;
+ int blocksize = EXT4_BLOCK_SIZE(dir->i_sb);
if (ext4_has_metadata_csum(dir->i_sb))
buflen -= sizeof(struct ext4_dir_entry_tail);
@@ -1257,11 +1260,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
map_tail--;
map_tail->hash = h.hash;
map_tail->offs = ((char *) de - base)>>2;
- map_tail->size = le16_to_cpu(de->rec_len);
+ map_tail->size = ext4_rec_len_from_disk(de->rec_len,
+ blocksize);
count++;
cond_resched();
}
- de = ext4_next_entry(de, dir->i_sb->s_blocksize);
+ de = ext4_next_entry(de, blocksize);
}
return count;
}
@@ -1419,11 +1423,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
int has_inline_data = 1;
ret = ext4_find_inline_entry(dir, fname, res_dir,
&has_inline_data);
- if (has_inline_data) {
- if (inlined)
- *inlined = 1;
+ if (inlined)
+ *inlined = has_inline_data;
+ if (has_inline_data)
goto cleanup_and_exit;
- }
}
if ((namelen <= 2) && (name[0] == '.') &&
@@ -3515,7 +3518,8 @@ static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
* so the old->de may no longer valid and need to find it again
* before reset old inode info.
*/
- old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de,
+ &old.inlined);
if (IS_ERR(old.bh))
retval = PTR_ERR(old.bh);
if (!old.bh)
@@ -3677,7 +3681,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
return retval;
}
- old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de,
+ &old.inlined);
if (IS_ERR(old.bh))
return PTR_ERR(old.bh);
/*
@@ -3870,6 +3875,9 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
retval = dquot_initialize(old.dir);
if (retval)
return retval;
+ retval = dquot_initialize(old.inode);
+ if (retval)
+ return retval;
retval = dquot_initialize(new.dir);
if (retval)
return retval;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 838d9f4fc554..391308566035 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -386,7 +386,8 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
static int io_submit_add_bh(struct ext4_io_submit *io,
struct inode *inode,
- struct page *page,
+ struct page *pagecache_page,
+ struct page *bounce_page,
struct buffer_head *bh)
{
int ret;
@@ -401,10 +402,11 @@ submit_and_retry:
return ret;
io->io_bio->bi_write_hint = inode->i_write_hint;
}
- ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
+ ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page,
+ bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
- wbc_account_io(io->io_wbc, page, bh->b_size);
+ wbc_account_io(io->io_wbc, pagecache_page, bh->b_size);
io->io_next_block++;
return 0;
}
@@ -512,8 +514,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
do {
if (!buffer_async_write(bh))
continue;
- ret = io_submit_add_bh(io, inode,
- data_page ? data_page : page, bh);
+ ret = io_submit_add_bh(io, inode, page, data_page, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 8737d1bcdb6e..f4b3d450dead 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -572,13 +572,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
if (meta_bg == 0 && !ext4_bg_has_super(sb, group))
goto handle_itb;
- if (meta_bg == 1) {
- ext4_group_t first_group;
- first_group = ext4_meta_bg_first_group(sb, group);
- if (first_group != group + 1 &&
- first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1)
- goto handle_itb;
- }
+ if (meta_bg == 1)
+ goto handle_itb;
block = start + ext4_bg_has_super(sb, group);
/* Copy all of the GDT blocks into the backup in this group */
@@ -1565,10 +1560,12 @@ exit_journal:
int gdb_num_end = ((group + flex_gd->count - 1) /
EXT4_DESC_PER_BLOCK(sb));
int meta_bg = ext4_has_feature_meta_bg(sb);
+ sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr -
+ ext4_group_first_block_no(sb, 0);
sector_t old_gdb = 0;
- update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
- sizeof(struct ext4_super_block), 0);
+ update_backups(sb, ext4_group_first_block_no(sb, 0),
+ (char *)es, sizeof(struct ext4_super_block), 0);
for (; gdb_num <= gdb_num_end; gdb_num++) {
struct buffer_head *gdb_bh;
@@ -1576,8 +1573,8 @@ exit_journal:
gdb_num);
if (old_gdb == gdb_bh->b_blocknr)
continue;
- update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
- gdb_bh->b_size, meta_bg);
+ update_backups(sb, gdb_bh->b_blocknr - padding_blocks,
+ gdb_bh->b_data, gdb_bh->b_size, meta_bg);
old_gdb = gdb_bh->b_blocknr;
}
}
@@ -1775,7 +1772,7 @@ errout:
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
"blocks\n", ext4_blocks_count(es));
- update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr,
+ update_backups(sb, ext4_group_first_block_no(sb, 0),
(char *)es, sizeof(struct ext4_super_block), 0);
}
return err;
@@ -1940,9 +1937,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
errout:
ret = ext4_journal_stop(handle);
- if (!err)
- err = ret;
- return ret;
+ return err ? err : ret;
invalid_resize_inode:
ext4_error(sb, "corrupted/inconsistent resize inode");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f00cc301da36..926063a6d232 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -905,10 +905,16 @@ static void ext4_blkdev_put(struct block_device *bdev)
static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
struct block_device *bdev;
- bdev = sbi->journal_bdev;
+ bdev = sbi->s_journal_bdev;
if (bdev) {
+ /*
+ * 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.
+ */
+ invalidate_bdev(bdev);
ext4_blkdev_put(bdev);
- sbi->journal_bdev = NULL;
+ sbi->s_journal_bdev = NULL;
}
}
@@ -1032,14 +1038,8 @@ static void ext4_put_super(struct super_block *sb)
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
- if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
- /*
- * 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->journal_bdev);
- invalidate_bdev(sbi->journal_bdev);
+ if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) {
+ sync_blockdev(sbi->s_journal_bdev);
ext4_blkdev_remove(sbi);
}
if (sbi->s_ea_inode_cache) {
@@ -1081,6 +1081,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
return NULL;
inode_set_iversion(&ei->vfs_inode, 1);
+ ei->i_flags = 0;
spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
@@ -2422,11 +2423,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
crc = crc16(crc, (__u8 *)gdp, offset);
offset += sizeof(gdp->bg_checksum); /* skip checksum */
/* for checksum of struct ext4_group_desc do the rest...*/
- if (ext4_has_feature_64bit(sb) &&
- offset < le16_to_cpu(sbi->s_es->s_desc_size))
+ if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size)
crc = crc16(crc, (__u8 *)gdp + offset,
- le16_to_cpu(sbi->s_es->s_desc_size) -
- offset);
+ sbi->s_desc_size - offset);
out:
return cpu_to_le16(crc);
@@ -3538,7 +3537,7 @@ int ext4_calculate_overhead(struct super_block *sb)
* Add the internal journal blocks whether the journal has been
* loaded or not
*/
- if (sbi->s_journal && !sbi->journal_bdev)
+ if (sbi->s_journal && !sbi->s_journal_bdev)
overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
/* j_inum for internal journal is non-zero */
@@ -4302,30 +4301,31 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
ext4_has_feature_journal_needs_recovery(sb)) {
ext4_msg(sb, KERN_ERR, "required journal recovery "
"suppressed and not mounted read-only");
- goto failed_mount_wq;
+ goto failed_mount3a;
} else {
/* Nojournal mode, all journal mount options are illegal */
- if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) {
- ext4_msg(sb, KERN_ERR, "can't mount with "
- "journal_checksum, fs mounted w/o journal");
- goto failed_mount_wq;
- }
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"journal_async_commit, fs mounted w/o journal");
- goto failed_mount_wq;
+ goto failed_mount3a;
+ }
+
+ if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "journal_checksum, fs mounted w/o journal");
+ goto failed_mount3a;
}
if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"commit=%lu, fs mounted w/o journal",
sbi->s_commit_interval / HZ);
- goto failed_mount_wq;
+ goto failed_mount3a;
}
if (EXT4_MOUNT_DATA_FLAGS &
(sbi->s_mount_opt ^ sbi->s_def_mount_opt)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"data=, fs mounted w/o journal");
- goto failed_mount_wq;
+ goto failed_mount3a;
}
sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
clear_opt(sb, JOURNAL_CHECKSUM);
@@ -4673,6 +4673,7 @@ failed_mount:
ext4_blkdev_remove(sbi);
brelse(bh);
out_fail:
+ invalidate_bdev(sb->s_bdev);
sb->s_fs_info = NULL;
kfree(sbi->s_blockgroup_lock);
out_free_base:
@@ -4731,7 +4732,7 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
jbd_debug(2, "Journal inode found at %p: %lld bytes\n",
journal_inode, journal_inode->i_size);
- if (!S_ISREG(journal_inode->i_mode)) {
+ if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) {
ext4_msg(sb, KERN_ERR, "invalid journal inode");
iput(journal_inode);
return NULL;
@@ -4848,7 +4849,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
be32_to_cpu(journal->j_superblock->s_nr_users));
goto out_journal;
}
- EXT4_SB(sb)->journal_bdev = bdev;
+ EXT4_SB(sb)->s_journal_bdev = bdev;
ext4_init_journal_params(sb, journal);
return journal;
@@ -5501,9 +5502,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
#ifdef CONFIG_QUOTA
- /* Release old quota file names */
- for (i = 0; i < EXT4_MAXQUOTAS; i++)
- kfree(old_opts.s_qf_names[i]);
if (enable_quota) {
if (sb_any_quota_suspended(sb))
dquot_resume(sb, -1);
@@ -5513,6 +5511,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
}
+ /* Release old quota file names */
+ for (i = 0; i < EXT4_MAXQUOTAS; i++)
+ kfree(old_opts.s_qf_names[i]);
#endif
if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
ext4_release_system_zone(sb);
@@ -5529,6 +5530,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
return 0;
restore_opts:
+ /*
+ * If there was a failing r/w to ro transition, we may need to
+ * re-enable quota
+ */
+ if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) &&
+ sb_any_quota_suspended(sb))
+ dquot_resume(sb, -1);
sb->s_flags = old_sb_flags;
sbi->s_mount_opt = old_opts.s_mount_opt;
sbi->s_mount_opt2 = old_opts.s_mount_opt2;
@@ -5839,6 +5847,20 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
return err;
}
+static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum)
+{
+ switch (type) {
+ case USRQUOTA:
+ return qf_inum == EXT4_USR_QUOTA_INO;
+ case GRPQUOTA:
+ return qf_inum == EXT4_GRP_QUOTA_INO;
+ case PRJQUOTA:
+ return qf_inum >= EXT4_GOOD_OLD_FIRST_INO;
+ default:
+ BUG();
+ }
+}
+
static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
unsigned int flags)
{
@@ -5855,9 +5877,16 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
if (!qf_inums[type])
return -EPERM;
+ if (!ext4_check_quota_inum(type, qf_inums[type])) {
+ ext4_error(sb, "Bad quota inum: %lu, type: %d",
+ qf_inums[type], type);
+ return -EUCLEAN;
+ }
+
qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL);
if (IS_ERR(qf_inode)) {
- ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]);
+ ext4_error(sb, "Bad quota inode: %lu, type: %d",
+ qf_inums[type], type);
return PTR_ERR(qf_inode);
}
@@ -5896,8 +5925,9 @@ static int ext4_enable_quotas(struct super_block *sb)
if (err) {
ext4_warning(sb,
"Failed to enable quota tracking "
- "(type=%d, err=%d). Please run "
- "e2fsck to fix.", type, err);
+ "(type=%d, err=%d, ino=%lu). "
+ "Please run e2fsck to fix.", type,
+ err, qf_inums[type]);
for (type--; type >= 0; type--) {
struct inode *inode;
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 9212a026a1f1..74722ce7206c 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -349,6 +349,11 @@ static void ext4_sb_release(struct kobject *kobj)
complete(&sbi->s_kobj_unregister);
}
+static void ext4_feat_release(struct kobject *kobj)
+{
+ kfree(kobj);
+}
+
static const struct sysfs_ops ext4_attr_ops = {
.show = ext4_attr_show,
.store = ext4_attr_store,
@@ -363,7 +368,7 @@ static struct kobj_type ext4_sb_ktype = {
static struct kobj_type ext4_feat_ktype = {
.default_attrs = ext4_feat_attrs,
.sysfs_ops = &ext4_attr_ops,
- .release = (void (*)(struct kobject *))kfree,
+ .release = ext4_feat_release,
};
static struct kobject *ext4_root;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 497649c69bba..88bdb2714e51 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -121,7 +121,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
#ifdef CONFIG_LOCKDEP
void ext4_xattr_inode_set_class(struct inode *ea_inode)
{
+ struct ext4_inode_info *ei = EXT4_I(ea_inode);
+
lockdep_set_subclass(&ea_inode->i_rwsem, 1);
+ (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */
+ lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA);
}
#endif
@@ -384,6 +388,17 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
struct inode *inode;
int err;
+ /*
+ * We have to check for this corruption early as otherwise
+ * iget_locked() could wait indefinitely for the state of our
+ * parent inode.
+ */
+ if (parent->i_ino == ea_ino) {
+ ext4_error(parent->i_sb,
+ "Parent and EA inode have the same ino %lu", ea_ino);
+ return -EFSCORRUPTED;
+ }
+
inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
@@ -434,6 +449,21 @@ error:
return err;
}
+/* Remove entry from mbcache when EA inode is getting evicted */
+void ext4_evict_ea_inode(struct inode *inode)
+{
+ struct mb_cache_entry *oe;
+
+ if (!EA_INODE_CACHE(inode))
+ return;
+ /* Wait for entry to get unused so that we can remove it */
+ while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode),
+ ext4_xattr_inode_get_hash(inode), inode->i_ino))) {
+ mb_cache_entry_wait_unused(oe);
+ mb_cache_entry_put(EA_INODE_CACHE(inode), oe);
+ }
+}
+
static int
ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
struct ext4_xattr_entry *entry, void *buffer,
@@ -1019,10 +1049,8 @@ static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
int ref_change)
{
- struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode);
struct ext4_iloc iloc;
s64 ref_count;
- u32 hash;
int ret;
inode_lock(ea_inode);
@@ -1047,14 +1075,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
set_nlink(ea_inode, 1);
ext4_orphan_del(handle, ea_inode);
-
- if (ea_inode_cache) {
- hash = ext4_xattr_inode_get_hash(ea_inode);
- mb_cache_entry_create(ea_inode_cache,
- GFP_NOFS, hash,
- ea_inode->i_ino,
- true /* reusable */);
- }
}
} else {
WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
@@ -1067,12 +1087,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
clear_nlink(ea_inode);
ext4_orphan_add(handle, ea_inode);
-
- if (ea_inode_cache) {
- hash = ext4_xattr_inode_get_hash(ea_inode);
- mb_cache_entry_delete(ea_inode_cache, hash,
- ea_inode->i_ino);
- }
}
}
@@ -1253,6 +1267,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
if (error)
goto out;
+retry_ref:
lock_buffer(bh);
hash = le32_to_cpu(BHDR(bh)->h_hash);
ref = le32_to_cpu(BHDR(bh)->h_refcount);
@@ -1262,9 +1277,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect freed block
*/
- if (ea_block_cache)
- mb_cache_entry_delete(ea_block_cache, hash,
- bh->b_blocknr);
+ if (ea_block_cache) {
+ struct mb_cache_entry *oe;
+
+ oe = mb_cache_entry_delete_or_get(ea_block_cache, hash,
+ bh->b_blocknr);
+ if (oe) {
+ unlock_buffer(bh);
+ mb_cache_entry_wait_unused(oe);
+ mb_cache_entry_put(ea_block_cache, oe);
+ goto retry_ref;
+ }
+ }
get_bh(bh);
unlock_buffer(bh);
@@ -1288,7 +1312,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
ce = mb_cache_entry_get(ea_block_cache, hash,
bh->b_blocknr);
if (ce) {
- ce->e_reusable = 1;
+ set_bit(MBE_REUSABLE_B, &ce->e_flags);
mb_cache_entry_put(ea_block_cache, ce);
}
}
@@ -1427,6 +1451,13 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle,
uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) };
int err;
+ if (inode->i_sb->s_root == NULL) {
+ ext4_warning(inode->i_sb,
+ "refuse to create EA inode when umounting");
+ WARN_ON(1);
+ return ERR_PTR(-EINVAL);
+ }
+
/*
* Let the next inode be the goal, so we try and allocate the EA inode
* in the same group, or nearby one.
@@ -1446,6 +1477,9 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle,
if (!err)
err = ext4_inode_attach_jinode(ea_inode);
if (err) {
+ if (ext4_xattr_inode_dec_ref(handle, ea_inode))
+ ext4_warning_inode(ea_inode,
+ "cleanup dec ref error %d", err);
iput(ea_inode);
return ERR_PTR(err);
}
@@ -1733,6 +1767,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
memmove(here, (void *)here + size,
(void *)last - (void *)here + sizeof(__u32));
memset(last, 0, size);
+
+ /*
+ * Update i_inline_off - moved ibody region might contain
+ * system.data attribute. Handling a failure here won't
+ * cause other complications for setting an xattr.
+ */
+ if (!is_block && ext4_has_inline_data(inode)) {
+ ret = ext4_find_inline_data_nolock(inode);
+ if (ret) {
+ ext4_warning_inode(inode,
+ "unable to update i_inline_off");
+ goto out;
+ }
+ }
} else if (s->not_found) {
/* Insert new name. */
size_t size = EXT4_XATTR_LEN(name_len);
@@ -1872,6 +1920,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
#define header(x) ((struct ext4_xattr_header *)(x))
if (s->base) {
+ int offset = (char *)s->here - bs->bh->b_data;
+
BUFFER_TRACE(bs->bh, "get_write_access");
error = ext4_journal_get_write_access(handle, bs->bh);
if (error)
@@ -1886,9 +1936,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
* ext4_xattr_block_set() to reliably detect modified
* block
*/
- if (ea_block_cache)
- mb_cache_entry_delete(ea_block_cache, hash,
- bs->bh->b_blocknr);
+ if (ea_block_cache) {
+ struct mb_cache_entry *oe;
+
+ oe = mb_cache_entry_delete_or_get(ea_block_cache,
+ hash, bs->bh->b_blocknr);
+ if (oe) {
+ /*
+ * Xattr block is getting reused. Leave
+ * it alone.
+ */
+ mb_cache_entry_put(ea_block_cache, oe);
+ goto clone_block;
+ }
+ }
ea_bdebug(bs->bh, "modifying in-place");
error = ext4_xattr_set_entry(i, s, handle, inode,
true /* is_block */);
@@ -1903,50 +1964,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
if (error)
goto cleanup;
goto inserted;
- } else {
- int offset = (char *)s->here - bs->bh->b_data;
+ }
+clone_block:
+ unlock_buffer(bs->bh);
+ ea_bdebug(bs->bh, "cloning");
+ s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS);
+ error = -ENOMEM;
+ if (s->base == NULL)
+ goto cleanup;
+ s->first = ENTRY(header(s->base)+1);
+ header(s->base)->h_refcount = cpu_to_le32(1);
+ s->here = ENTRY(s->base + offset);
+ s->end = s->base + bs->bh->b_size;
- unlock_buffer(bs->bh);
- ea_bdebug(bs->bh, "cloning");
- s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
- error = -ENOMEM;
- if (s->base == NULL)
+ /*
+ * If existing entry points to an xattr inode, we need
+ * to prevent ext4_xattr_set_entry() from decrementing
+ * ref count on it because the reference belongs to the
+ * original block. In this case, make the entry look
+ * like it has an empty value.
+ */
+ if (!s->not_found && s->here->e_value_inum) {
+ ea_ino = le32_to_cpu(s->here->e_value_inum);
+ error = ext4_xattr_inode_iget(inode, ea_ino,
+ le32_to_cpu(s->here->e_hash),
+ &tmp_inode);
+ if (error)
goto cleanup;
- memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
- s->first = ENTRY(header(s->base)+1);
- header(s->base)->h_refcount = cpu_to_le32(1);
- s->here = ENTRY(s->base + offset);
- s->end = s->base + bs->bh->b_size;
-
- /*
- * If existing entry points to an xattr inode, we need
- * to prevent ext4_xattr_set_entry() from decrementing
- * ref count on it because the reference belongs to the
- * original block. In this case, make the entry look
- * like it has an empty value.
- */
- if (!s->not_found && s->here->e_value_inum) {
- ea_ino = le32_to_cpu(s->here->e_value_inum);
- error = ext4_xattr_inode_iget(inode, ea_ino,
- le32_to_cpu(s->here->e_hash),
- &tmp_inode);
- if (error)
- goto cleanup;
-
- if (!ext4_test_inode_state(tmp_inode,
- EXT4_STATE_LUSTRE_EA_INODE)) {
- /*
- * Defer quota free call for previous
- * inode until success is guaranteed.
- */
- old_ea_inode_quota = le32_to_cpu(
- s->here->e_value_size);
- }
- iput(tmp_inode);
- s->here->e_value_inum = 0;
- s->here->e_value_size = 0;
+ if (!ext4_test_inode_state(tmp_inode,
+ EXT4_STATE_LUSTRE_EA_INODE)) {
+ /*
+ * Defer quota free call for previous
+ * inode until success is guaranteed.
+ */
+ old_ea_inode_quota = le32_to_cpu(
+ s->here->e_value_size);
}
+ iput(tmp_inode);
+
+ s->here->e_value_inum = 0;
+ s->here->e_value_size = 0;
}
} else {
/* Allocate a buffer where we construct the new block. */
@@ -1997,8 +2055,9 @@ inserted:
else {
u32 ref;
+#ifdef EXT4_XATTR_DEBUG
WARN_ON_ONCE(dquot_initialize_needed(inode));
-
+#endif
/* The old block is released after updating
the inode. */
error = dquot_alloc_block(inode,
@@ -2013,18 +2072,13 @@ inserted:
lock_buffer(new_bh);
/*
* We have to be careful about races with
- * freeing, rehashing or adding references to
- * xattr block. Once we hold buffer lock xattr
- * block's state is stable so we can check
- * whether the block got freed / rehashed or
- * not. Since we unhash mbcache entry under
- * buffer lock when freeing / rehashing xattr
- * block, checking whether entry is still
- * hashed is reliable. Same rules hold for
- * e_reusable handling.
+ * adding references to xattr block. Once we
+ * hold buffer lock xattr block's state is
+ * stable so we can check the additional
+ * reference fits.
*/
- if (hlist_bl_unhashed(&ce->e_hash_list) ||
- !ce->e_reusable) {
+ ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
+ if (ref > EXT4_XATTR_REFCOUNT_MAX) {
/*
* Undo everything and check mbcache
* again.
@@ -2039,10 +2093,9 @@ inserted:
new_bh = NULL;
goto inserted;
}
- ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
- if (ref >= EXT4_XATTR_REFCOUNT_MAX)
- ce->e_reusable = 0;
+ if (ref == EXT4_XATTR_REFCOUNT_MAX)
+ clear_bit(MBE_REUSABLE_B, &ce->e_flags);
ea_bdebug(new_bh, "reusing; refcount now=%d",
ref);
ext4_xattr_block_csum_set(inode, new_bh);
@@ -2066,23 +2119,16 @@ inserted:
/* We need to allocate a new block */
ext4_fsblk_t goal, block;
+#ifdef EXT4_XATTR_DEBUG
WARN_ON_ONCE(dquot_initialize_needed(inode));
-
+#endif
goal = ext4_group_first_block_no(sb,
EXT4_I(inode)->i_block_group);
-
- /* non-extent files can't have physical blocks past 2^32 */
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
-
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
if (error)
goto cleanup;
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
-
ea_idebug(inode, "creating block %llu",
(unsigned long long)block);
@@ -2210,7 +2256,7 @@ 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,
+int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is)
{
@@ -2235,30 +2281,6 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
return 0;
}
-static int ext4_xattr_ibody_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_value_same(struct ext4_xattr_search *s,
struct ext4_xattr_info *i)
{
@@ -2571,13 +2593,13 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
.in_inode = !!entry->e_value_inum,
};
struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
+ int needs_kvfree = 0;
int error;
is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
- buffer = kmalloc(value_size, GFP_NOFS);
b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
- if (!is || !bs || !buffer || !b_entry_name) {
+ if (!is || !bs || !b_entry_name) {
error = -ENOMEM;
goto out;
}
@@ -2589,12 +2611,18 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
/* Save the entry name and the entry value */
if (entry->e_value_inum) {
+ buffer = kvmalloc(value_size, GFP_NOFS);
+ if (!buffer) {
+ error = -ENOMEM;
+ goto out;
+ }
+ needs_kvfree = 1;
error = ext4_xattr_inode_get(inode, entry, buffer, value_size);
if (error)
goto out;
} else {
size_t value_offs = le16_to_cpu(entry->e_value_offs);
- memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size);
+ buffer = (void *)IFIRST(header) + value_offs;
}
memcpy(b_entry_name, entry->e_name, entry->e_name_len);
@@ -2609,25 +2637,26 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
if (error)
goto out;
- /* Remove the chosen entry from the inode */
- error = ext4_xattr_ibody_set(handle, inode, &i, is);
- if (error)
- goto out;
-
i.value = buffer;
i.value_len = value_size;
error = ext4_xattr_block_find(inode, &i, bs);
if (error)
goto out;
- /* Add entry which was removed from the inode into the block */
+ /* Move ea entry from the inode into the block */
error = ext4_xattr_block_set(handle, inode, &i, bs);
if (error)
goto out;
- error = 0;
+
+ /* Remove the chosen entry from the inode */
+ i.value = NULL;
+ i.value_len = 0;
+ error = ext4_xattr_ibody_set(handle, inode, &i, is);
+
out:
kfree(b_entry_name);
- kfree(buffer);
+ if (needs_kvfree && buffer)
+ kvfree(buffer);
if (is)
brelse(is->iloc.bh);
if (bs)
@@ -2802,6 +2831,9 @@ shift:
(void *)header, total_ino);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
+ if (ext4_has_inline_data(inode))
+ error = ext4_find_inline_data_nolock(inode);
+
cleanup:
if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) {
ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.",
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 990084e00374..66911f8a11f8 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -190,6 +190,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array);
extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
struct ext4_inode *raw_inode, handle_t *handle);
+extern void ext4_evict_ea_inode(struct inode *inode);
extern const struct xattr_handler *ext4_xattr_handlers[];
@@ -198,9 +199,9 @@ 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 *);
generated by cgit (git 2.34.1) at 2024-06-02 08:30:49 +0000