summaryrefslogtreecommitdiff
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c123
1 files changed, 87 insertions, 36 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 18aa2ef963ad..2ea07efbe016 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2716,12 +2716,6 @@ static int ext4_writepages(struct address_space *mapping,
percpu_down_read(&sbi->s_journal_flag_rwsem);
trace_ext4_writepages(inode, wbc);
- if (dax_mapping(mapping)) {
- ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
- wbc);
- goto out_writepages;
- }
-
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
@@ -2942,6 +2936,27 @@ out_writepages:
return ret;
}
+static int ext4_dax_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ int ret;
+ long nr_to_write = wbc->nr_to_write;
+ struct inode *inode = mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
+ percpu_down_read(&sbi->s_journal_flag_rwsem);
+ trace_ext4_writepages(inode, wbc);
+
+ ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+ trace_ext4_writepages_result(inode, wbc, ret,
+ nr_to_write - wbc->nr_to_write);
+ percpu_up_read(&sbi->s_journal_flag_rwsem);
+ return ret;
+}
+
static int ext4_nonda_switch(struct super_block *sb)
{
s64 free_clusters, dirty_clusters;
@@ -3845,10 +3860,6 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (ext4_has_inline_data(inode))
return 0;
- /* DAX uses iomap path now */
- if (WARN_ON_ONCE(IS_DAX(inode)))
- return 0;
-
trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
if (iov_iter_rw(iter) == READ)
ret = ext4_direct_IO_read(iocb, iter);
@@ -3934,6 +3945,13 @@ static const struct address_space_operations ext4_da_aops = {
.error_remove_page = generic_error_remove_page,
};
+static const struct address_space_operations ext4_dax_aops = {
+ .writepages = ext4_dax_writepages,
+ .direct_IO = noop_direct_IO,
+ .set_page_dirty = noop_set_page_dirty,
+ .invalidatepage = noop_invalidatepage,
+};
+
void ext4_set_aops(struct inode *inode)
{
switch (ext4_inode_journal_mode(inode)) {
@@ -3946,7 +3964,9 @@ void ext4_set_aops(struct inode *inode)
default:
BUG();
}
- if (test_opt(inode->i_sb, DELALLOC))
+ if (IS_DAX(inode))
+ inode->i_mapping->a_ops = &ext4_dax_aops;
+ else if (test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else
inode->i_mapping->a_ops = &ext4_aops;
@@ -4278,28 +4298,28 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
EXT4_BLOCK_SIZE_BITS(sb);
stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
- /* If there are no blocks to remove, return now */
- if (first_block >= stop_block)
- goto out_stop;
+ /* If there are blocks to remove, do it */
+ if (stop_block > first_block) {
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_discard_preallocations(inode);
- ret = ext4_es_remove_extent(inode, first_block,
- stop_block - first_block);
- if (ret) {
- up_write(&EXT4_I(inode)->i_data_sem);
- goto out_stop;
- }
+ ret = ext4_es_remove_extent(inode, first_block,
+ stop_block - first_block);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ret = ext4_ext_remove_space(inode, first_block,
- stop_block - 1);
- else
- ret = ext4_ind_remove_space(handle, inode, first_block,
- stop_block);
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ ret = ext4_ext_remove_space(inode, first_block,
+ stop_block - 1);
+ else
+ ret = ext4_ind_remove_space(handle, inode, first_block,
+ stop_block);
- up_write(&EXT4_I(inode)->i_data_sem);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ }
if (IS_SYNC(inode))
ext4_handle_sync(handle);
@@ -4681,19 +4701,21 @@ static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
}
}
-static inline void ext4_iget_extra_inode(struct inode *inode,
+static inline int ext4_iget_extra_inode(struct inode *inode,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
{
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
+
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
EXT4_INODE_SIZE(inode->i_sb) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
- ext4_find_inline_data_nolock(inode);
+ return ext4_find_inline_data_nolock(inode);
} else
EXT4_I(inode)->i_inline_off = 0;
+ return 0;
}
int ext4_get_projid(struct inode *inode, kprojid_t *projid)
@@ -4704,6 +4726,26 @@ int ext4_get_projid(struct inode *inode, kprojid_t *projid)
return 0;
}
+/*
+ * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of
+ * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag
+ * set.
+ */
+static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val)
+{
+ if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+ inode_set_iversion_raw(inode, val);
+ else
+ inode_set_iversion_queried(inode, val);
+}
+static inline u64 ext4_inode_peek_iversion(const struct inode *inode)
+{
+ if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+ return inode_peek_iversion_raw(inode);
+ else
+ return inode_peek_iversion(inode);
+}
+
struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
{
struct ext4_iloc iloc;
@@ -4873,7 +4915,9 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ei->i_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
} else {
- ext4_iget_extra_inode(inode, raw_inode, ei);
+ ret = ext4_iget_extra_inode(inode, raw_inode, ei);
+ if (ret)
+ goto bad_inode;
}
}
@@ -4890,7 +4934,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ivers |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
- inode_set_iversion_queried(inode, ivers);
+ ext4_inode_set_iversion_queried(inode, ivers);
}
ret = 0;
@@ -4925,6 +4969,13 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
+ /* VFS does not allow setting these so must be corruption */
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+ EXT4_ERROR_INODE(inode,
+ "immutable or append flags not allowed on symlinks");
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
if (ext4_encrypted_inode(inode)) {
inode->i_op = &ext4_encrypted_symlink_inode_operations;
ext4_set_aops(inode);
@@ -5024,12 +5075,12 @@ static int other_inode_match(struct inode * inode, unsigned long ino,
if ((inode->i_ino != ino) ||
(inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
- I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
+ I_DIRTY_INODE)) ||
((inode->i_state & I_DIRTY_TIME) == 0))
return 0;
spin_lock(&inode->i_lock);
if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
- I_DIRTY_SYNC | I_DIRTY_DATASYNC)) == 0) &&
+ I_DIRTY_INODE)) == 0) &&
(inode->i_state & I_DIRTY_TIME)) {
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -5176,7 +5227,7 @@ static int ext4_do_update_inode(handle_t *handle,
}
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
- u64 ivers = inode_peek_iversion(inode);
+ u64 ivers = ext4_inode_peek_iversion(inode);
raw_inode->i_disk_version = cpu_to_le32(ivers);
if (ei->i_extra_isize) {
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-17 10:59:11 +0300