summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/acl.c4
-rw-r--r--fs/ext4/acl.h2
-rw-r--r--fs/ext4/ext4.h19
-rw-r--r--fs/ext4/extents.c2
-rw-r--r--fs/ext4/fast_commit.c44
-rw-r--r--fs/ext4/file.c36
-rw-r--r--fs/ext4/fsmap.c2
-rw-r--r--fs/ext4/ialloc.c6
-rw-r--r--fs/ext4/inline.c1
-rw-r--r--fs/ext4/inode.c135
-rw-r--r--fs/ext4/ioctl.c24
-rw-r--r--fs/ext4/move_extent.c46
-rw-r--r--fs/ext4/namei.c64
-rw-r--r--fs/ext4/page-io.c11
-rw-r--r--fs/ext4/readpage.c3
-rw-r--r--fs/ext4/super.c118
-rw-r--r--fs/ext4/symlink.c4
-rw-r--r--fs/ext4/sysfs.c11
-rw-r--r--fs/ext4/verity.c6
-rw-r--r--fs/ext4/xattr.c175
-rw-r--r--fs/ext4/xattr_hurd.c2
-rw-r--r--fs/ext4/xattr_security.c2
-rw-r--r--fs/ext4/xattr_trusted.c2
-rw-r--r--fs/ext4/xattr_user.c2
24 files changed, 427 insertions, 294 deletions
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index a9f89539aeee..27fcbddfb148 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -225,7 +225,7 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
}
int
-ext4_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
struct posix_acl *acl, int type)
{
handle_t *handle;
@@ -249,7 +249,7 @@ retry:
return PTR_ERR(handle);
if ((type == ACL_TYPE_ACCESS) && acl) {
- error = posix_acl_update_mode(mnt_userns, inode, &mode, &acl);
+ error = posix_acl_update_mode(idmap, inode, &mode, &acl);
if (error)
goto out_stop;
if (mode != inode->i_mode)
diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h
index 09c4a8a3b716..0c5a79c3b5d4 100644
--- a/fs/ext4/acl.h
+++ b/fs/ext4/acl.h
@@ -56,7 +56,7 @@ static inline int ext4_acl_count(size_t size)
/* acl.c */
struct posix_acl *ext4_get_acl(struct inode *inode, int type, bool rcu);
-int ext4_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+int ext4_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
struct posix_acl *acl, int type);
extern int ext4_init_acl(handle_t *, struct inode *, struct inode *);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 140e1eb300d1..08b29c289da4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1387,7 +1387,7 @@ struct ext4_super_block {
__le32 s_first_meta_bg; /* First metablock block group */
__le32 s_mkfs_time; /* When the filesystem was created */
__le32 s_jnl_blocks[17]; /* Backup of the journal inode */
- /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+ /* 64bit support valid if EXT4_FEATURE_INCOMPAT_64BIT */
/*150*/ __le32 s_blocks_count_hi; /* Blocks count */
__le32 s_r_blocks_count_hi; /* Reserved blocks count */
__le32 s_free_blocks_count_hi; /* Free blocks count */
@@ -1529,6 +1529,7 @@ struct ext4_sb_info {
unsigned int s_mount_opt2;
unsigned long s_mount_flags;
unsigned int s_def_mount_opt;
+ unsigned int s_def_mount_opt2;
ext4_fsblk_t s_sb_block;
atomic64_t s_resv_clusters;
kuid_t s_resuid;
@@ -2845,7 +2846,7 @@ extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
/* ialloc.c */
extern int ext4_mark_inode_used(struct super_block *sb, int ino);
-extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *,
+extern struct inode *__ext4_new_inode(struct mnt_idmap *, handle_t *,
struct inode *, umode_t,
const struct qstr *qstr, __u32 goal,
uid_t *owner, __u32 i_flags,
@@ -2853,11 +2854,11 @@ extern struct inode *__ext4_new_inode(struct user_namespace *, handle_t *,
int nblocks);
#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
- __ext4_new_inode(&init_user_ns, (handle), (dir), (mode), (qstr), \
+ __ext4_new_inode(&nop_mnt_idmap, (handle), (dir), (mode), (qstr), \
(goal), (owner), i_flags, 0, 0, 0)
-#define ext4_new_inode_start_handle(mnt_userns, dir, mode, qstr, goal, owner, \
+#define ext4_new_inode_start_handle(idmap, dir, mode, qstr, goal, owner, \
type, nblocks) \
- __ext4_new_inode((mnt_userns), NULL, (dir), (mode), (qstr), (goal), (owner), \
+ __ext4_new_inode((idmap), NULL, (dir), (mode), (qstr), (goal), (owner), \
0, (type), __LINE__, (nblocks))
@@ -2976,14 +2977,14 @@ extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
__ext4_iget((sb), (ino), (flags), __func__, __LINE__)
extern int ext4_write_inode(struct inode *, struct writeback_control *);
-extern int ext4_setattr(struct user_namespace *, struct dentry *,
+extern int ext4_setattr(struct mnt_idmap *, struct dentry *,
struct iattr *);
extern u32 ext4_dio_alignment(struct inode *inode);
-extern int ext4_getattr(struct user_namespace *, const struct path *,
+extern int ext4_getattr(struct mnt_idmap *, const struct path *,
struct kstat *, u32, unsigned int);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
-extern int ext4_file_getattr(struct user_namespace *, const struct path *,
+extern int ext4_file_getattr(struct mnt_idmap *, const struct path *,
struct kstat *, u32, unsigned int);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
@@ -3024,7 +3025,7 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
-int ext4_fileattr_set(struct user_namespace *mnt_userns,
+int ext4_fileattr_set(struct mnt_idmap *idmap,
struct dentry *dentry, struct fileattr *fa);
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
extern void ext4_reset_inode_seed(struct inode *inode);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 9de1c9d1a13d..3559ea6b0781 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3251,7 +3251,7 @@ static int ext4_split_extent_at(handle_t *handle,
ext4_ext_mark_unwritten(ex2);
err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags);
- if (err != -ENOSPC && err != -EDQUOT)
+ if (err != -ENOSPC && err != -EDQUOT && err != -ENOMEM)
goto out;
if (EXT4_EXT_MAY_ZEROOUT & split_flag) {
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 4594b62f147b..b06de728b3b6 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1332,8 +1332,14 @@ struct dentry_info_args {
char *dname;
};
+/* Same as struct ext4_fc_tl, but uses native endianness fields */
+struct ext4_fc_tl_mem {
+ u16 fc_tag;
+ u16 fc_len;
+};
+
static inline void tl_to_darg(struct dentry_info_args *darg,
- struct ext4_fc_tl *tl, u8 *val)
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
struct ext4_fc_dentry_info fcd;
@@ -1345,16 +1351,18 @@ static inline void tl_to_darg(struct dentry_info_args *darg,
darg->dname_len = tl->fc_len - sizeof(struct ext4_fc_dentry_info);
}
-static inline void ext4_fc_get_tl(struct ext4_fc_tl *tl, u8 *val)
+static inline void ext4_fc_get_tl(struct ext4_fc_tl_mem *tl, u8 *val)
{
- memcpy(tl, val, EXT4_FC_TAG_BASE_LEN);
- tl->fc_len = le16_to_cpu(tl->fc_len);
- tl->fc_tag = le16_to_cpu(tl->fc_tag);
+ struct ext4_fc_tl tl_disk;
+
+ memcpy(&tl_disk, val, EXT4_FC_TAG_BASE_LEN);
+ tl->fc_len = le16_to_cpu(tl_disk.fc_len);
+ tl->fc_tag = le16_to_cpu(tl_disk.fc_tag);
}
/* Unlink replay function */
-static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl,
- u8 *val)
+static int ext4_fc_replay_unlink(struct super_block *sb,
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
struct inode *inode, *old_parent;
struct qstr entry;
@@ -1451,8 +1459,8 @@ out:
}
/* Link replay function */
-static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl,
- u8 *val)
+static int ext4_fc_replay_link(struct super_block *sb,
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
struct inode *inode;
struct dentry_info_args darg;
@@ -1506,8 +1514,8 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
/*
* Inode replay function
*/
-static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
- u8 *val)
+static int ext4_fc_replay_inode(struct super_block *sb,
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
struct ext4_fc_inode fc_inode;
struct ext4_inode *raw_inode;
@@ -1609,8 +1617,8 @@ out:
* inode for which we are trying to create a dentry here, should already have
* been replayed before we start here.
*/
-static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl,
- u8 *val)
+static int ext4_fc_replay_create(struct super_block *sb,
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
int ret = 0;
struct inode *inode = NULL;
@@ -1708,7 +1716,7 @@ int ext4_fc_record_regions(struct super_block *sb, int ino,
/* Replay add range tag */
static int ext4_fc_replay_add_range(struct super_block *sb,
- struct ext4_fc_tl *tl, u8 *val)
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
struct ext4_fc_add_range fc_add_ex;
struct ext4_extent newex, *ex;
@@ -1828,8 +1836,8 @@ out:
/* Replay DEL_RANGE tag */
static int
-ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
- u8 *val)
+ext4_fc_replay_del_range(struct super_block *sb,
+ struct ext4_fc_tl_mem *tl, u8 *val)
{
struct inode *inode;
struct ext4_fc_del_range lrange;
@@ -2025,7 +2033,7 @@ static int ext4_fc_replay_scan(journal_t *journal,
struct ext4_fc_replay_state *state;
int ret = JBD2_FC_REPLAY_CONTINUE;
struct ext4_fc_add_range ext;
- struct ext4_fc_tl tl;
+ struct ext4_fc_tl_mem tl;
struct ext4_fc_tail tail;
__u8 *start, *end, *cur, *val;
struct ext4_fc_head head;
@@ -2144,7 +2152,7 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_fc_tl tl;
+ struct ext4_fc_tl_mem tl;
__u8 *start, *end, *cur, *val;
int ret = JBD2_FC_REPLAY_CONTINUE;
struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 7ac0a81bd371..0b8b4499e5ca 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,8 +202,9 @@ ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
return false;
}
-/* Is IO overwriting allocated and initialized blocks? */
-static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
+/* Is IO overwriting allocated or initialized blocks? */
+static bool ext4_overwrite_io(struct inode *inode,
+ loff_t pos, loff_t len, bool *unwritten)
{
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
@@ -217,12 +218,15 @@ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
blklen = map.m_len;
err = ext4_map_blocks(NULL, inode, &map, 0);
+ if (err != blklen)
+ return false;
/*
* 'err==len' means that all of the blocks have been preallocated,
- * regardless of whether they have been initialized or not. To exclude
- * unwritten extents, we need to check m_flags.
+ * regardless of whether they have been initialized or not. We need to
+ * check m_flags to distinguish the unwritten extents.
*/
- return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
+ *unwritten = !(map.m_flags & EXT4_MAP_MAPPED);
+ return true;
}
static ssize_t ext4_generic_write_checks(struct kiocb *iocb,
@@ -431,11 +435,16 @@ static const struct iomap_dio_ops ext4_dio_write_ops = {
* - For extending writes case we don't take the shared lock, since it requires
* updating inode i_disksize and/or orphan handling with exclusive lock.
*
- * - shared locking will only be true mostly with overwrites. Otherwise we will
- * switch to exclusive i_rwsem lock.
+ * - shared locking will only be true mostly with overwrites, including
+ * initialized blocks and unwritten blocks. For overwrite unwritten blocks
+ * we protect splitting extents by i_data_sem in ext4_inode_info, so we can
+ * also release exclusive i_rwsem lock.
+ *
+ * - Otherwise we will switch to exclusive i_rwsem lock.
*/
static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
- bool *ilock_shared, bool *extend)
+ bool *ilock_shared, bool *extend,
+ bool *unwritten)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
@@ -459,7 +468,7 @@ restart:
* in file_modified().
*/
if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
- !ext4_overwrite_io(inode, offset, count))) {
+ !ext4_overwrite_io(inode, offset, count, unwritten))) {
if (iocb->ki_flags & IOCB_NOWAIT) {
ret = -EAGAIN;
goto out;
@@ -491,7 +500,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
loff_t offset = iocb->ki_pos;
size_t count = iov_iter_count(from);
const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
- bool extend = false, unaligned_io = false;
+ bool extend = false, unaligned_io = false, unwritten = false;
bool ilock_shared = true;
/*
@@ -534,7 +543,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
return ext4_buffered_write_iter(iocb, from);
}
- ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend);
+ ret = ext4_dio_write_checks(iocb, from,
+ &ilock_shared, &extend, &unwritten);
if (ret <= 0)
return ret;
@@ -582,7 +592,7 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
ext4_journal_stop(handle);
}
- if (ilock_shared)
+ if (ilock_shared && !unwritten)
iomap_ops = &ext4_iomap_overwrite_ops;
ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
(unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
@@ -801,7 +811,7 @@ 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_HUGEPAGE;
+ vm_flags_set(vma, VM_HUGEPAGE);
} else {
vma->vm_ops = &ext4_file_vm_ops;
}
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 4493ef0c715e..cdf9bfe10137 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;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 63f9bb6e8851..157663031f8c 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -921,7 +921,7 @@ static int ext4_xattr_credits_for_new_inode(struct inode *dir, mode_t mode,
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
-struct inode *__ext4_new_inode(struct user_namespace *mnt_userns,
+struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
handle_t *handle, struct inode *dir,
umode_t mode, const struct qstr *qstr,
__u32 goal, uid_t *owner, __u32 i_flags,
@@ -972,10 +972,10 @@ struct inode *__ext4_new_inode(struct user_namespace *mnt_userns,
i_gid_write(inode, owner[1]);
} else if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
- inode_fsuid_set(inode, mnt_userns);
+ inode_fsuid_set(inode, idmap);
inode->i_gid = dir->i_gid;
} else
- inode_init_owner(mnt_userns, inode, dir, mode);
+ inode_init_owner(idmap, inode, dir, mode);
if (ext4_has_feature_project(sb) &&
ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT))
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 2b42ececa46d..1602d74b5eeb 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -159,7 +159,6 @@ 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);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9d9f414f99fe..bf0b7dea4900 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -786,11 +786,10 @@ static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
* once we get rid of using bh as a container for mapping information
* to pass to / from get_block functions, this can go away.
*/
+ old_state = READ_ONCE(bh->b_state);
do {
- old_state = READ_ONCE(bh->b_state);
new_state = (old_state & ~EXT4_MAP_FLAGS) | flags;
- } while (unlikely(
- cmpxchg(&bh->b_state, old_state, new_state) != old_state));
+ } while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state)));
}
static int _ext4_get_block(struct inode *inode, sector_t iblock,
@@ -1136,7 +1135,8 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
for (i = 0; i < nr_wait; i++) {
int err2;
- err2 = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+ err2 = fscrypt_decrypt_pagecache_blocks(page_folio(page),
+ blocksize,
bh_offset(wait[i]));
if (err2) {
clear_buffer_uptodate(wait[i]);
@@ -2595,8 +2595,8 @@ static bool ext4_page_nomap_can_writeout(struct page *page)
static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
{
struct address_space *mapping = mpd->inode->i_mapping;
- struct pagevec pvec;
- unsigned int nr_pages;
+ struct folio_batch fbatch;
+ unsigned int nr_folios;
long left = mpd->wbc->nr_to_write;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
@@ -2610,18 +2610,17 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
-
- pagevec_init(&pvec);
+ folio_batch_init(&fbatch);
mpd->map.m_len = 0;
mpd->next_page = index;
while (index <= end) {
- nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
- tag);
- if (nr_pages == 0)
+ nr_folios = filemap_get_folios_tag(mapping, &index, end,
+ tag, &fbatch);
+ if (nr_folios == 0)
break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
+ for (i = 0; i < nr_folios; i++) {
+ struct folio *folio = fbatch.folios[i];
/*
* Accumulated enough dirty pages? This doesn't apply
@@ -2635,10 +2634,10 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
goto out;
/* If we can't merge this page, we are done. */
- if (mpd->map.m_len > 0 && mpd->next_page != page->index)
+ if (mpd->map.m_len > 0 && mpd->next_page != folio->index)
goto out;
- lock_page(page);
+ folio_lock(folio);
/*
* If the page is no longer dirty, or its mapping no
* longer corresponds to inode we are writing (which
@@ -2646,16 +2645,16 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
* page is already under writeback and we are not doing
* a data integrity writeback, skip the page
*/
- if (!PageDirty(page) ||
- (PageWriteback(page) &&
+ if (!folio_test_dirty(folio) ||
+ (folio_test_writeback(folio) &&
(mpd->wbc->sync_mode == WB_SYNC_NONE)) ||
- unlikely(page->mapping != mapping)) {
- unlock_page(page);
+ unlikely(folio->mapping != mapping)) {
+ folio_unlock(folio);
continue;
}
- wait_on_page_writeback(page);
- BUG_ON(PageWriteback(page));
+ folio_wait_writeback(folio);
+ BUG_ON(folio_test_writeback(folio));
/*
* Should never happen but for buggy code in
@@ -2666,56 +2665,56 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
*
* [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz
*/
- if (!page_has_buffers(page)) {
- ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index);
- ClearPageDirty(page);
- unlock_page(page);
+ if (!folio_buffers(folio)) {
+ ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", folio->index);
+ folio_clear_dirty(folio);
+ folio_unlock(folio);
continue;
}
if (mpd->map.m_len == 0)
- mpd->first_page = page->index;
- mpd->next_page = page->index + 1;
+ mpd->first_page = folio->index;
+ mpd->next_page = folio->index + folio_nr_pages(folio);
/*
* Writeout for transaction commit where we cannot
* modify metadata is simple. Just submit the page.
*/
if (!mpd->can_map) {
- if (ext4_page_nomap_can_writeout(page)) {
- err = mpage_submit_page(mpd, page);
+ if (ext4_page_nomap_can_writeout(&folio->page)) {
+ err = mpage_submit_page(mpd, &folio->page);
if (err < 0)
goto out;
} else {
- unlock_page(page);
- mpd->first_page++;
+ folio_unlock(folio);
+ mpd->first_page += folio_nr_pages(folio);
}
} else {
/* Add all dirty buffers to mpd */
- lblk = ((ext4_lblk_t)page->index) <<
+ lblk = ((ext4_lblk_t)folio->index) <<
(PAGE_SHIFT - blkbits);
- head = page_buffers(page);
+ head = folio_buffers(folio);
err = mpage_process_page_bufs(mpd, head, head,
- lblk);
+ lblk);
if (err <= 0)
goto out;
err = 0;
}
- left--;
+ left -= folio_nr_pages(folio);
}
- pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
cond_resched();
}
mpd->scanned_until_end = 1;
return 0;
out:
- pagevec_release(&pvec);
+ folio_batch_release(&fbatch);
return err;
}
-static int ext4_writepage_cb(struct page *page, struct writeback_control *wbc,
+static int ext4_writepage_cb(struct folio *folio, struct writeback_control *wbc,
void *data)
{
- return ext4_writepage(page, wbc);
+ return ext4_writepage(&folio->page, wbc);
}
static int ext4_do_writepages(struct mpage_da_data *mpd)
@@ -3858,7 +3857,8 @@ static int __ext4_block_zero_page_range(handle_t *handle,
if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
- err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+ err = fscrypt_decrypt_pagecache_blocks(page_folio(page),
+ blocksize,
bh_offset(bh));
if (err) {
clear_buffer_uptodate(bh);
@@ -4797,8 +4797,13 @@ 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;
@@ -4872,13 +4877,6 @@ 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;
@@ -4951,11 +4949,16 @@ 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
@@ -5434,7 +5437,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
*
* Called with inode->i_rwsem down.
*/
-int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
+int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
@@ -5454,7 +5457,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
- error = setattr_prepare(mnt_userns, dentry, attr);
+ error = setattr_prepare(idmap, dentry, attr);
if (error)
return error;
@@ -5466,14 +5469,14 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (error)
return error;
- if (is_quota_modification(mnt_userns, inode, attr)) {
+ if (is_quota_modification(idmap, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
- if (i_uid_needs_update(mnt_userns, attr, inode) ||
- i_gid_needs_update(mnt_userns, attr, inode)) {
+ if (i_uid_needs_update(idmap, attr, inode) ||
+ i_gid_needs_update(idmap, attr, inode)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
@@ -5490,7 +5493,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
- error = dquot_transfer(mnt_userns, inode, attr);
+ error = dquot_transfer(idmap, inode, attr);
up_read(&EXT4_I(inode)->xattr_sem);
if (error) {
@@ -5499,8 +5502,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
}
/* Update corresponding info in inode so that everything is in
* one transaction */
- i_uid_update(mnt_userns, attr, inode);
- i_gid_update(mnt_userns, attr, inode);
+ i_uid_update(idmap, attr, inode);
+ i_gid_update(idmap, attr, inode);
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
if (unlikely(error)) {
@@ -5630,7 +5633,7 @@ out_mmap_sem:
if (!error) {
if (inc_ivers)
inode_inc_iversion(inode);
- setattr_copy(mnt_userns, inode, attr);
+ setattr_copy(idmap, inode, attr);
mark_inode_dirty(inode);
}
@@ -5642,7 +5645,7 @@ out_mmap_sem:
ext4_orphan_del(NULL, inode);
if (!error && (ia_valid & ATTR_MODE))
- rc = posix_acl_chmod(mnt_userns, dentry, inode->i_mode);
+ rc = posix_acl_chmod(idmap, dentry, inode->i_mode);
err_out:
if (error)
@@ -5668,7 +5671,7 @@ u32 ext4_dio_alignment(struct inode *inode)
return 1; /* use the iomap defaults */
}
-int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
+int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
@@ -5725,18 +5728,18 @@ int ext4_getattr(struct user_namespace *mnt_userns, const struct path *path,
STATX_ATTR_NODUMP |
STATX_ATTR_VERITY);
- generic_fillattr(mnt_userns, inode, stat);
+ generic_fillattr(idmap, inode, stat);
return 0;
}
-int ext4_file_getattr(struct user_namespace *mnt_userns,
+int ext4_file_getattr(struct mnt_idmap *idmap,
const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
u64 delalloc_blocks;
- ext4_getattr(mnt_userns, path, stat, request_mask, query_flags);
+ ext4_getattr(idmap, path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
@@ -5788,7 +5791,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
int gdpblocks;
int idxblocks;
- int ret = 0;
+ int ret;
/*
* How many index blocks need to touch to map @lblocks logical blocks
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 8067ccda34e4..f9a430152063 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -155,9 +155,6 @@ static int ext4_update_backup_sb(struct super_block *sb,
set_buffer_uptodate(bh);
unlock_buffer(bh);
- if (err)
- goto out_bh;
-
if (handle) {
err = ext4_handle_dirty_metadata(handle, NULL, bh);
if (err)
@@ -358,12 +355,12 @@ void ext4_reset_inode_seed(struct inode *inode)
* important fields of the inodes.
*
* @sb: the super block of the filesystem
- * @mnt_userns: user namespace of the mount the inode was found from
+ * @idmap: idmap of the mount the inode was found from
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
struct inode *inode)
{
handle_t *handle;
@@ -393,7 +390,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
}
if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
- !inode_owner_or_capable(mnt_userns, inode) ||
+ !inode_owner_or_capable(idmap, inode) ||
!capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto journal_err_out;
@@ -434,6 +431,7 @@ 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);
@@ -979,7 +977,7 @@ int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
return 0;
}
-int ext4_fileattr_set(struct user_namespace *mnt_userns,
+int ext4_fileattr_set(struct mnt_idmap *idmap,
struct dentry *dentry, struct fileattr *fa)
{
struct inode *inode = d_inode(dentry);
@@ -1217,7 +1215,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
- struct user_namespace *mnt_userns = file_mnt_user_ns(filp);
+ struct mnt_idmap *idmap = file_mnt_idmap(filp);
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
@@ -1234,7 +1232,7 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
__u32 generation;
int err;
- if (!inode_owner_or_capable(mnt_userns, inode))
+ if (!inode_owner_or_capable(idmap, inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
@@ -1376,7 +1374,7 @@ mext_out:
case EXT4_IOC_MIGRATE:
{
int err;
- if (!inode_owner_or_capable(mnt_userns, inode))
+ if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
err = mnt_want_write_file(filp);
@@ -1398,7 +1396,7 @@ mext_out:
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
- if (!inode_owner_or_capable(mnt_userns, inode))
+ if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
err = mnt_want_write_file(filp);
@@ -1417,7 +1415,7 @@ mext_out:
err = mnt_want_write_file(filp);
if (err)
return err;
- err = swap_inode_boot_loader(sb, mnt_userns, inode);
+ err = swap_inode_boot_loader(sb, idmap, inode);
mnt_drop_write_file(filp);
return err;
}
@@ -1542,7 +1540,7 @@ resizefs_out:
case EXT4_IOC_CLEAR_ES_CACHE:
{
- if (!inode_owner_or_capable(mnt_userns, inode))
+ if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
ext4_clear_inode_es(inode);
return 0;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 8dbb87edf24c..2de9829aed63 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -110,22 +110,23 @@ out:
}
/**
- * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2
+ * mext_folio_double_lock - Grab and lock folio on both @inode1 and @inode2
*
* @inode1: the inode structure
* @inode2: the inode structure
- * @index1: page index
- * @index2: page index
- * @page: result page vector
+ * @index1: folio index
+ * @index2: folio index
+ * @folio: result folio vector
*
- * Grab two locked pages for inode's by inode order
+ * Grab two locked folio for inode's by inode order
*/
static int
-mext_page_double_lock(struct inode *inode1, struct inode *inode2,
- pgoff_t index1, pgoff_t index2, struct page *page[2])
+mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
+ pgoff_t index1, pgoff_t index2, struct folio *folio[2])
{
struct address_space *mapping[2];
unsigned int flags;
+ unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
BUG_ON(!inode1 || !inode2);
if (inode1 < inode2) {
@@ -138,28 +139,30 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
}
flags = memalloc_nofs_save();
- page[0] = grab_cache_page_write_begin(mapping[0], index1);
- if (!page[0]) {
+ folio[0] = __filemap_get_folio(mapping[0], index1, fgp_flags,
+ mapping_gfp_mask(mapping[0]));
+ if (!folio[0]) {
memalloc_nofs_restore(flags);
return -ENOMEM;
}
- page[1] = grab_cache_page_write_begin(mapping[1], index2);
+ folio[1] = __filemap_get_folio(mapping[1], index2, fgp_flags,
+ mapping_gfp_mask(mapping[1]));
memalloc_nofs_restore(flags);
- if (!page[1]) {
- unlock_page(page[0]);
- put_page(page[0]);
+ if (!folio[1]) {
+ folio_unlock(folio[0]);
+ folio_put(folio[0]);
return -ENOMEM;
}
/*
- * grab_cache_page_write_begin() may not wait on page's writeback if
+ * __filemap_get_folio() may not wait on folio's writeback if
* BDI not demand that. But it is reasonable to be very conservative
- * here and explicitly wait on page's writeback
+ * here and explicitly wait on folio's writeback
*/
- wait_on_page_writeback(page[0]);
- wait_on_page_writeback(page[1]);
+ folio_wait_writeback(folio[0]);
+ folio_wait_writeback(folio[1]);
if (inode1 > inode2)
- swap(page[0], page[1]);
+ swap(folio[0], folio[1]);
return 0;
}
@@ -252,7 +255,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
int block_len_in_page, int unwritten, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
- struct page *pagep[2] = {NULL, NULL};
struct folio *folio[2] = {NULL, NULL};
handle_t *handle;
ext4_lblk_t orig_blk_offset, donor_blk_offset;
@@ -303,8 +305,8 @@ again:
replaced_size = data_size;
- *err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset,
- donor_page_offset, pagep);
+ *err = mext_folio_double_lock(orig_inode, donor_inode, orig_page_offset,
+ donor_page_offset, folio);
if (unlikely(*err < 0))
goto stop_journal;
/*
@@ -314,8 +316,6 @@ again:
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
- folio[0] = page_folio(pagep[0]);
- folio[1] = page_folio(pagep[1]);
VM_BUG_ON_FOLIO(folio_test_large(folio[0]), folio[0]);
VM_BUG_ON_FOLIO(folio_test_large(folio[1]), folio[1]);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index dd28453d6ea3..a5010b5b8a8c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1595,11 +1595,10 @@ 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] == '.') &&
@@ -2792,7 +2791,7 @@ static int ext4_add_nondir(handle_t *handle,
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_create(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
handle_t *handle;
@@ -2806,7 +2805,7 @@ static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir,
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
+ inode = ext4_new_inode_start_handle(idmap, dir, mode, &dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
@@ -2827,7 +2826,7 @@ retry:
return err;
}
-static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_mknod(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t rdev)
{
handle_t *handle;
@@ -2841,7 +2840,7 @@ static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir,
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
+ inode = ext4_new_inode_start_handle(idmap, dir, mode, &dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
@@ -2861,7 +2860,7 @@ retry:
return err;
}
-static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
struct file *file, umode_t mode)
{
handle_t *handle;
@@ -2873,7 +2872,7 @@ static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
return err;
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, mode,
+ inode = ext4_new_inode_start_handle(idmap, dir, mode,
NULL, 0, NULL,
EXT4_HT_DIR,
EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
@@ -2972,7 +2971,7 @@ out:
return err;
}
-static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_mkdir(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
handle_t *handle;
@@ -2989,7 +2988,7 @@ static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFDIR | mode,
+ inode = ext4_new_inode_start_handle(idmap, dir, S_IFDIR | mode,
&dentry->d_name,
0, NULL, EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
@@ -3339,7 +3338,7 @@ out:
return err;
}
-static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
+static int ext4_symlink(struct mnt_idmap *idmap, struct inode *dir,
struct dentry *dentry, const char *symname)
{
handle_t *handle;
@@ -3370,7 +3369,7 @@ static int ext4_symlink(struct user_namespace *mnt_userns, struct inode *dir,
credits = EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3;
retry:
- inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFLNK|S_IRWXUGO,
+ inode = ext4_new_inode_start_handle(idmap, dir, S_IFLNK|S_IRWXUGO,
&dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
handle = ext4_journal_current_handle();
@@ -3646,7 +3645,8 @@ 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)
@@ -3720,7 +3720,7 @@ static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
}
}
-static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns,
+static struct inode *ext4_whiteout_for_rename(struct mnt_idmap *idmap,
struct ext4_renament *ent,
int credits, handle_t **h)
{
@@ -3735,7 +3735,7 @@ static struct inode *ext4_whiteout_for_rename(struct user_namespace *mnt_userns,
credits += (EXT4_MAXQUOTAS_TRANS_BLOCKS(ent->dir->i_sb) +
EXT4_XATTR_TRANS_BLOCKS + 4);
retry:
- wh = ext4_new_inode_start_handle(mnt_userns, ent->dir,
+ wh = ext4_new_inode_start_handle(idmap, ent->dir,
S_IFCHR | WHITEOUT_MODE,
&ent->dentry->d_name, 0, NULL,
EXT4_HT_DIR, credits);
@@ -3763,7 +3763,7 @@ retry:
* while new_{dentry,inode) refers to the destination dentry/inode
* This comes from rename(const char *oldpath, const char *newpath)
*/
-static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
+static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
struct dentry *old_dentry, struct inode *new_dir,
struct dentry *new_dentry, unsigned int flags)
{
@@ -3813,9 +3813,20 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
return retval;
}
- old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
- if (IS_ERR(old.bh))
- return PTR_ERR(old.bh);
+ /*
+ * We need to protect against old.inode directory getting converted
+ * from inline directory format into a normal one.
+ */
+ if (S_ISDIR(old.inode->i_mode))
+ inode_lock_nested(old.inode, I_MUTEX_NONDIR2);
+
+ 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);
+ goto unlock_moved_dir;
+ }
+
/*
* Check for inode number is _not_ due to possible IO errors.
* We might rmdir the source, keep it as pwd of some process
@@ -3851,7 +3862,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
goto release_bh;
}
} else {
- whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
+ whiteout = ext4_whiteout_for_rename(idmap, &old, credits, &handle);
if (IS_ERR(whiteout)) {
retval = PTR_ERR(whiteout);
goto release_bh;
@@ -4010,6 +4021,11 @@ release_bh:
brelse(old.dir_bh);
brelse(old.bh);
brelse(new.bh);
+
+unlock_moved_dir:
+ if (S_ISDIR(old.inode->i_mode))
+ inode_unlock(old.inode);
+
return retval;
}
@@ -4158,7 +4174,7 @@ end_rename:
return retval;
}
-static int ext4_rename2(struct user_namespace *mnt_userns,
+static int ext4_rename2(struct mnt_idmap *idmap,
struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
@@ -4181,7 +4197,7 @@ static int ext4_rename2(struct user_namespace *mnt_userns,
new_dir, new_dentry);
}
- return ext4_rename(mnt_userns, old_dir, old_dentry, new_dir, new_dentry, flags);
+ return ext4_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags);
}
/*
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index beaec6d81074..1e4db96a04e6 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -409,7 +409,8 @@ static void io_submit_init_bio(struct ext4_io_submit *io,
static void 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;
@@ -421,10 +422,11 @@ submit_and_retry:
}
if (io->io_bio == NULL)
io_submit_init_bio(io, bh);
- 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_cgroup_owner(io->io_wbc, page, bh->b_size);
+ wbc_account_cgroup_owner(io->io_wbc, pagecache_page, bh->b_size);
io->io_next_block++;
}
@@ -561,8 +563,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
do {
if (!buffer_async_write(bh))
continue;
- io_submit_add_bh(io, inode,
- bounce_page ? bounce_page : page, bh);
+ io_submit_add_bh(io, inode, page, bounce_page, bh);
} while ((bh = bh->b_this_page) != head);
unlock:
unlock_page(page);
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index d5266932ce6c..c61dc8a7c014 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -211,8 +211,7 @@ static void ext4_set_bio_post_read_ctx(struct bio *bio,
static inline loff_t ext4_readpage_limit(struct inode *inode)
{
- if (IS_ENABLED(CONFIG_FS_VERITY) &&
- (IS_VERITY(inode) || ext4_verity_in_progress(inode)))
+ if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
return inode->i_sb->s_maxbytes;
return i_size_read(inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 260c1b3e3ef2..f43e526112ae 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -482,7 +482,7 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
*
* However, we may have to redirty a page (see below.)
*/
-static int ext4_journalled_writepage_callback(struct page *page,
+static int ext4_journalled_writepage_callback(struct folio *folio,
struct writeback_control *wbc,
void *data)
{
@@ -490,7 +490,7 @@ static int ext4_journalled_writepage_callback(struct page *page,
struct buffer_head *bh, *head;
struct journal_head *jh;
- bh = head = page_buffers(page);
+ bh = head = folio_buffers(folio);
do {
/*
* We have to redirty a page in these cases:
@@ -509,7 +509,7 @@ static int ext4_journalled_writepage_callback(struct page *page,
if (buffer_dirty(bh) ||
(jh && (jh->b_transaction != transaction ||
jh->b_next_transaction))) {
- redirty_page_for_writepage(wbc, page);
+ folio_redirty_for_writepage(wbc, folio);
goto out;
}
} while ((bh = bh->b_this_page) != head);
@@ -2146,7 +2146,7 @@ static int ext4_parse_param(struct fs_context *fc, struct fs_parameter *param)
return 0;
case Opt_commit:
if (result.uint_32 == 0)
- ctx->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE;
+ result.uint_32 = JBD2_DEFAULT_MAX_COMMIT_AGE;
else if (result.uint_32 > INT_MAX / HZ) {
ext4_msg(NULL, KERN_ERR,
"Invalid commit interval %d, "
@@ -2635,7 +2635,6 @@ static int ext4_check_test_dummy_encryption(const struct fs_context *fc,
{
const struct ext4_fs_context *ctx = fc->fs_private;
const struct ext4_sb_info *sbi = EXT4_SB(sb);
- int err;
if (!fscrypt_is_dummy_policy_set(&ctx->dummy_enc_policy))
return 0;
@@ -2668,17 +2667,7 @@ static int ext4_check_test_dummy_encryption(const struct fs_context *fc,
"Conflicting test_dummy_encryption options");
return -EINVAL;
}
- /*
- * fscrypt_add_test_dummy_key() technically changes the super_block, so
- * technically it should be delayed until ext4_apply_options() like the
- * other changes. But since we never get here for remounts (see above),
- * and this is the last chance to report errors, we do it here.
- */
- err = fscrypt_add_test_dummy_key(sb, &ctx->dummy_enc_policy);
- if (err)
- ext4_msg(NULL, KERN_WARNING,
- "Error adding test dummy encryption key [%d]", err);
- return err;
+ return 0;
}
static void ext4_apply_test_dummy_encryption(struct ext4_fs_context *ctx,
@@ -2894,7 +2883,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
- int def_errors, def_mount_opt = sbi->s_def_mount_opt;
+ int def_errors;
const struct mount_opts *m;
char sep = nodefs ? '\n' : ',';
@@ -2906,15 +2895,28 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
for (m = ext4_mount_opts; m->token != Opt_err; m++) {
int want_set = m->flags & MOPT_SET;
+ int opt_2 = m->flags & MOPT_2;
+ unsigned int mount_opt, def_mount_opt;
+
if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
m->flags & MOPT_SKIP)
continue;
- if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
- continue; /* skip if same as the default */
+
+ if (opt_2) {
+ mount_opt = sbi->s_mount_opt2;
+ def_mount_opt = sbi->s_def_mount_opt2;
+ } else {
+ mount_opt = sbi->s_mount_opt;
+ def_mount_opt = sbi->s_def_mount_opt;
+ }
+ /* skip if same as the default */
+ if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt)))
+ continue;
+ /* select Opt_noFoo vs Opt_Foo */
if ((want_set &&
- (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) ||
- (!want_set && (sbi->s_mount_opt & m->mount_opt)))
- continue; /* select Opt_noFoo vs Opt_Foo */
+ (mount_opt & m->mount_opt) != m->mount_opt) ||
+ (!want_set && (mount_opt & m->mount_opt)))
+ continue;
SEQ_OPTS_PRINT("%s", token2str(m->token));
}
@@ -2942,7 +2944,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
if (nodefs || sbi->s_stripe)
SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
if (nodefs || EXT4_MOUNT_DATA_FLAGS &
- (sbi->s_mount_opt ^ def_mount_opt)) {
+ (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) {
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
SEQ_OPTS_PUTS("data=journal");
else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
@@ -4738,7 +4740,6 @@ static int ext4_group_desc_init(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned int db_count;
ext4_fsblk_t block;
- int ret;
int i;
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
@@ -4778,8 +4779,7 @@ static int ext4_group_desc_init(struct super_block *sb,
ext4_msg(sb, KERN_ERR,
"can't read group descriptor %d", i);
sbi->s_gdb_count = i;
- ret = PTR_ERR(bh);
- goto out;
+ return PTR_ERR(bh);
}
rcu_read_lock();
rcu_dereference(sbi->s_group_desc)[i] = bh;
@@ -4788,13 +4788,10 @@ static int ext4_group_desc_init(struct super_block *sb,
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 out;
+ return -EFSCORRUPTED;
}
+
return 0;
-out:
- ext4_group_desc_free(sbi);
- return ret;
}
static int ext4_load_and_init_journal(struct super_block *sb,
@@ -5086,6 +5083,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
goto failed_mount;
sbi->s_def_mount_opt = sbi->s_mount_opt;
+ sbi->s_def_mount_opt2 = sbi->s_mount_opt2;
err = ext4_check_opt_consistency(fc, sb);
if (err < 0)
@@ -5220,14 +5218,14 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
if (ext4_geometry_check(sb, es))
goto failed_mount;
- err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed);
- if (err)
- goto failed_mount;
-
timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
spin_lock_init(&sbi->s_error_lock);
INIT_WORK(&sbi->s_error_work, flush_stashed_error_work);
+ err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed);
+ if (err)
+ goto failed_mount3;
+
/* Register extent status tree shrinker */
if (ext4_es_register_shrinker(sbi))
goto failed_mount3;
@@ -5336,11 +5334,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
}
}
- if (ext4_has_feature_verity(sb) && sb->s_blocksize != PAGE_SIZE) {
- ext4_msg(sb, KERN_ERR, "Unsupported blocksize for fs-verity");
- goto failed_mount_wq;
- }
-
/*
* Get the # of file system overhead blocks from the
* superblock if present.
@@ -5733,6 +5726,28 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
return journal_inode;
}
+static int ext4_journal_bmap(journal_t *journal, sector_t *block)
+{
+ struct ext4_map_blocks map;
+ int ret;
+
+ if (journal->j_inode == NULL)
+ return 0;
+
+ map.m_lblk = *block;
+ map.m_len = 1;
+ ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0);
+ if (ret <= 0) {
+ ext4_msg(journal->j_inode->i_sb, KERN_CRIT,
+ "journal bmap failed: block %llu ret %d\n",
+ *block, ret);
+ jbd2_journal_abort(journal, ret ? ret : -EIO);
+ return ret;
+ }
+ *block = map.m_pblk;
+ return 0;
+}
+
static journal_t *ext4_get_journal(struct super_block *sb,
unsigned int journal_inum)
{
@@ -5753,6 +5768,7 @@ static journal_t *ext4_get_journal(struct super_block *sb,
return NULL;
}
journal->j_private = sb;
+ journal->j_bmap = ext4_journal_bmap;
ext4_init_journal_params(sb, journal);
return journal;
}
@@ -5927,6 +5943,7 @@ static int ext4_load_journal(struct super_block *sb,
err = jbd2_journal_wipe(journal, !really_read_only);
if (!err) {
char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
+
if (save)
memcpy(save, ((char *) es) +
EXT4_S_ERR_START, EXT4_S_ERR_LEN);
@@ -5935,6 +5952,14 @@ static int ext4_load_journal(struct super_block *sb,
memcpy(((char *) es) + EXT4_S_ERR_START,
save, EXT4_S_ERR_LEN);
kfree(save);
+ es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state &
+ EXT4_ERROR_FS);
+ /* Write out restored error information to the superblock */
+ if (!bdev_read_only(sb->s_bdev)) {
+ int err2;
+ err2 = ext4_commit_super(sb);
+ err = err ? : err2;
+ }
}
if (err) {
@@ -5953,8 +5978,11 @@ static int ext4_load_journal(struct super_block *sb,
if (!really_read_only && journal_devnum &&
journal_devnum != le32_to_cpu(es->s_journal_dev)) {
es->s_journal_dev = cpu_to_le32(journal_devnum);
-
- /* Make sure we flush the recovery flag to disk. */
+ ext4_commit_super(sb);
+ }
+ if (!really_read_only && journal_inum &&
+ journal_inum != le32_to_cpu(es->s_journal_inum)) {
+ es->s_journal_inum = cpu_to_le32(journal_inum);
ext4_commit_super(sb);
}
@@ -6161,11 +6189,13 @@ static int ext4_clear_journal_err(struct super_block *sb,
errstr = ext4_decode_error(sb, j_errno, nbuf);
ext4_warning(sb, "Filesystem error recorded "
"from previous mount: %s", errstr);
- ext4_warning(sb, "Marking fs in need of filesystem check.");
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb);
+ j_errno = ext4_commit_super(sb);
+ if (j_errno)
+ return j_errno;
+ ext4_warning(sb, "Marked fs in need of filesystem check.");
jbd2_journal_clear_err(journal);
jbd2_journal_update_sb_errno(journal);
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 3d3ed3c38f56..75bf1f88843c 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -55,12 +55,12 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
return paddr;
}
-static int ext4_encrypted_symlink_getattr(struct user_namespace *mnt_userns,
+static int ext4_encrypted_symlink_getattr(struct mnt_idmap *idmap,
const struct path *path,
struct kstat *stat, u32 request_mask,
unsigned int query_flags)
{
- ext4_getattr(mnt_userns, path, stat, request_mask, query_flags);
+ ext4_getattr(idmap, path, stat, request_mask, query_flags);
return fscrypt_symlink_getattr(path, stat);
}
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index d233c24ea342..12d6252e3e22 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -491,21 +491,26 @@ 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,
};
-static struct kobj_type ext4_sb_ktype = {
+static const struct kobj_type ext4_sb_ktype = {
.default_groups = ext4_groups,
.sysfs_ops = &ext4_attr_ops,
.release = ext4_sb_release,
};
-static struct kobj_type ext4_feat_ktype = {
+static const struct kobj_type ext4_feat_ktype = {
.default_groups = ext4_feat_groups,
.sysfs_ops = &ext4_attr_ops,
- .release = (void (*)(struct kobject *))kfree,
+ .release = ext4_feat_release,
};
void ext4_notify_error_sysfs(struct ext4_sb_info *sbi)
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index 30e3b65798b5..e4da1704438e 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -381,11 +381,11 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
}
static int ext4_write_merkle_tree_block(struct inode *inode, const void *buf,
- u64 index, int log_blocksize)
+ u64 pos, unsigned int size)
{
- loff_t pos = ext4_verity_metadata_pos(inode) + (index << log_blocksize);
+ pos += ext4_verity_metadata_pos(inode);
- return pagecache_write(inode, buf, 1 << log_blocksize, pos);
+ return pagecache_write(inode, buf, size, pos);
}
const struct fsverity_operations ext4_verityops = {
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index a2f04a3808db..767454d74cd6 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -184,27 +184,73 @@ ext4_xattr_handler(int name_index)
}
static int
-ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
- void *value_start)
+check_xattrs(struct inode *inode, struct buffer_head *bh,
+ struct ext4_xattr_entry *entry, void *end, void *value_start,
+ const char *function, unsigned int line)
{
struct ext4_xattr_entry *e = entry;
+ int err = -EFSCORRUPTED;
+ char *err_str;
+
+ if (bh) {
+ if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
+ BHDR(bh)->h_blocks != cpu_to_le32(1)) {
+ err_str = "invalid header";
+ goto errout;
+ }
+ if (buffer_verified(bh))
+ return 0;
+ if (!ext4_xattr_block_csum_verify(inode, bh)) {
+ err = -EFSBADCRC;
+ err_str = "invalid checksum";
+ goto errout;
+ }
+ } else {
+ struct ext4_xattr_ibody_header *header = value_start;
+
+ header -= 1;
+ if (end - (void *)header < sizeof(*header) + sizeof(u32)) {
+ err_str = "in-inode xattr block too small";
+ goto errout;
+ }
+ if (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ err_str = "bad magic number in in-inode xattr";
+ goto errout;
+ }
+ }
/* Find the end of the names list */
while (!IS_LAST_ENTRY(e)) {
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;
+ if ((void *)next >= end) {
+ err_str = "e_name out of bounds";
+ goto errout;
+ }
+ if (strnlen(e->e_name, e->e_name_len) != e->e_name_len) {
+ err_str = "bad e_name length";
+ goto errout;
+ }
e = next;
}
/* Check the values */
while (!IS_LAST_ENTRY(entry)) {
u32 size = le32_to_cpu(entry->e_value_size);
+ unsigned long ea_ino = le32_to_cpu(entry->e_value_inum);
- if (size > EXT4_XATTR_SIZE_MAX)
- return -EFSCORRUPTED;
+ if (!ext4_has_feature_ea_inode(inode->i_sb) && ea_ino) {
+ err_str = "ea_inode specified without ea_inode feature enabled";
+ goto errout;
+ }
+ if (ea_ino && ((ea_ino == EXT4_ROOT_INO) ||
+ !ext4_valid_inum(inode->i_sb, ea_ino))) {
+ err_str = "invalid ea_ino";
+ goto errout;
+ }
+ if (size > EXT4_XATTR_SIZE_MAX) {
+ err_str = "e_value size too large";
+ goto errout;
+ }
if (size != 0 && entry->e_value_inum == 0) {
u16 offs = le16_to_cpu(entry->e_value_offs);
@@ -216,66 +262,54 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
* the padded and unpadded sizes, since the size may
* overflow to 0 when adding padding.
*/
- if (offs > end - value_start)
- return -EFSCORRUPTED;
+ if (offs > end - value_start) {
+ err_str = "e_value out of bounds";
+ goto errout;
+ }
value = value_start + offs;
if (value < (void *)e + sizeof(u32) ||
size > end - value ||
- EXT4_XATTR_SIZE(size) > end - value)
- return -EFSCORRUPTED;
+ EXT4_XATTR_SIZE(size) > end - value) {
+ err_str = "overlapping e_value ";
+ goto errout;
+ }
}
entry = EXT4_XATTR_NEXT(entry);
}
-
+ if (bh)
+ set_buffer_verified(bh);
return 0;
+
+errout:
+ if (bh)
+ __ext4_error_inode(inode, function, line, 0, -err,
+ "corrupted xattr block %llu: %s",
+ (unsigned long long) bh->b_blocknr,
+ err_str);
+ else
+ __ext4_error_inode(inode, function, line, 0, -err,
+ "corrupted in-inode xattr: %s", err_str);
+ return err;
}
static inline int
__ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh,
const char *function, unsigned int line)
{
- int error = -EFSCORRUPTED;
-
- 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;
- error = ext4_xattr_check_entries(BFIRST(bh), bh->b_data + bh->b_size,
- bh->b_data);
-errout:
- if (error)
- __ext4_error_inode(inode, function, line, 0, -error,
- "corrupted xattr block %llu",
- (unsigned long long) bh->b_blocknr);
- else
- set_buffer_verified(bh);
- return error;
+ return check_xattrs(inode, bh, BFIRST(bh), bh->b_data + bh->b_size,
+ bh->b_data, function, line);
}
#define ext4_xattr_check_block(inode, bh) \
__ext4_xattr_check_block((inode), (bh), __func__, __LINE__)
-static int
+static inline int
__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
void *end, const char *function, unsigned int line)
{
- int error = -EFSCORRUPTED;
-
- if (end - (void *)header < sizeof(*header) + sizeof(u32) ||
- (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
- goto errout;
- error = ext4_xattr_check_entries(IFIRST(header), end, IFIRST(header));
-errout:
- if (error)
- __ext4_error_inode(inode, function, line, 0, -error,
- "corrupted in-inode xattr");
- return error;
+ return check_xattrs(inode, NULL, IFIRST(header), end, IFIRST(header),
+ function, line);
}
#define xattr_check_inode(inode, header, end) \
@@ -388,6 +422,17 @@ 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);
@@ -1438,6 +1483,13 @@ 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.
@@ -2567,9 +2619,8 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
- buffer = kvmalloc(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;
}
@@ -2581,12 +2632,18 @@ 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;
+ }
+
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);
@@ -2601,25 +2658,26 @@ 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);
- kvfree(buffer);
+ if (entry->e_value_inum && buffer)
+ kvfree(buffer);
if (is)
brelse(is->iloc.bh);
if (bs)
@@ -2794,6 +2852,9 @@ 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_hurd.c b/fs/ext4/xattr_hurd.c
index c78df5790377..8a5842e4cd95 100644
--- a/fs/ext4/xattr_hurd.c
+++ b/fs/ext4/xattr_hurd.c
@@ -32,7 +32,7 @@ ext4_xattr_hurd_get(const struct xattr_handler *handler,
static int
ext4_xattr_hurd_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 8213f66f7b2d..776cf11d24ca 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -23,7 +23,7 @@ ext4_xattr_security_get(const struct xattr_handler *handler,
static int
ext4_xattr_security_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index 7c21ffb26d25..9811eb0ab276 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -30,7 +30,7 @@ ext4_xattr_trusted_get(const struct xattr_handler *handler,
static int
ext4_xattr_trusted_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index 2fe7ff0a479c..4b70bf4e7626 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -31,7 +31,7 @@ ext4_xattr_user_get(const struct xattr_handler *handler,
static int
ext4_xattr_user_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
+ struct mnt_idmap *idmap,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-23 08:39:32 +0000