struct ext4_inode_info *ei)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- __u16 csum_lo;
- __u16 csum_hi = 0;
__u32 csum;
+ __u16 dummy_csum = 0;
+ int offset = offsetof(struct ext4_inode, i_checksum_lo);
+ unsigned int csum_size = sizeof(dummy_csum);
- csum_lo = le16_to_cpu(raw->i_checksum_lo);
- raw->i_checksum_lo = 0;
- if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
- EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
- csum_hi = le16_to_cpu(raw->i_checksum_hi);
- raw->i_checksum_hi = 0;
- }
+ csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, offset);
+ csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, csum_size);
+ offset += csum_size;
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+ EXT4_GOOD_OLD_INODE_SIZE - offset);
- csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw,
- EXT4_INODE_SIZE(inode->i_sb));
-
- raw->i_checksum_lo = cpu_to_le16(csum_lo);
- if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
- EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi))
- raw->i_checksum_hi = cpu_to_le16(csum_hi);
+ if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+ offset = offsetof(struct ext4_inode, i_checksum_hi);
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw +
+ EXT4_GOOD_OLD_INODE_SIZE,
+ offset - EXT4_GOOD_OLD_INODE_SIZE);
+ if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) {
+ csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum,
+ csum_size);
+ offset += csum_size;
+ }
+ csum = ext4_chksum(sbi, csum, (__u8 *)raw + offset,
+ EXT4_INODE_SIZE(inode->i_sb) - offset);
+ }
return csum;
}
* Note that directories do not have this problem because they
* don't use page cache.
*/
- if (ext4_should_journal_data(inode) &&
- (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
- inode->i_ino != EXT4_JOURNAL_INO) {
+ if (inode->i_ino != EXT4_JOURNAL_INO &&
+ ext4_should_journal_data(inode) &&
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
- * On success, it returns the number of blocks being mapped or allocated.
- * if create==0 and the blocks are pre-allocated and unwritten block,
- * the result buffer head is unmapped. If the create ==1, it will make sure
- * the buffer head is mapped.
+ * On success, it returns the number of blocks being mapped or allocated. if
+ * create==0 and the blocks are pre-allocated and unwritten, the resulting @map
+ * is marked as unwritten. If the create == 1, it will mark @map as mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
- * that case, buffer head is unmapped
+ * that case, @map is returned as unmapped but we still do fill map->m_len to
+ * indicate the length of a hole starting at map->m_lblk.
*
* It returns the error in case of allocation failure.
*/
retval = map->m_len;
map->m_len = retval;
} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
+ map->m_pblk = 0;
+ retval = es.es_len - (map->m_lblk - es.es_lblk);
+ if (retval > map->m_len)
+ retval = map->m_len;
+ map->m_len = retval;
retval = 0;
} else {
BUG_ON(1);
return retval;
}
+/*
+ * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages
+ * we have to be careful as someone else may be manipulating b_state as well.
+ */
+static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags)
+{
+ unsigned long old_state;
+ unsigned long new_state;
+
+ flags &= EXT4_MAP_FLAGS;
+
+ /* Dummy buffer_head? Set non-atomically. */
+ if (!bh->b_page) {
+ bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags;
+ return;
+ }
+ /*
+ * Someone else may be modifying b_state. Be careful! This is ugly but
+ * once we get rid of using bh as a container for mapping information
+ * to pass to / from get_block functions, this can go away.
+ */
+ 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));
+}
+
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
ext4_io_end_t *io_end = ext4_inode_aio(inode);
map_bh(bh, inode->i_sb, map.m_pblk);
- bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+ ext4_update_bh_state(bh, map.m_flags);
if (IS_DAX(inode) && buffer_unwritten(bh)) {
/*
* dgc: I suspect unwritten conversion on ext4+DAX is
if (ext4_has_inline_data(inode)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
- if (ret < 0)
+ if (ret < 0) {
+ unlock_page(page);
+ put_page(page);
goto errout;
+ }
copied = ret;
} else
copied = block_write_end(file, mapping, pos,
* set the buffer to be dirty, since in data=journalled mode we need
* to call ext4_handle_dirty_metadata() instead.
*/
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+ struct page *page,
+ unsigned from, unsigned to)
{
unsigned int block_start = 0, block_end;
struct buffer_head *head, *bh;
size = min(to, block_end) - start;
zero_user(page, start, size);
- set_buffer_uptodate(bh);
+ write_end_fn(handle, bh);
}
clear_buffer_new(bh);
}
BUG_ON(!ext4_handle_valid(handle));
- if (ext4_has_inline_data(inode))
- copied = ext4_write_inline_data_end(inode, pos, len,
- copied, page);
- else {
- if (copied < len) {
- if (!PageUptodate(page))
- copied = 0;
- zero_new_buffers(page, from+copied, to);
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_write_inline_data_end(inode, pos, len,
+ copied, page);
+ if (ret < 0) {
+ unlock_page(page);
+ put_page(page);
+ goto errout;
}
-
+ copied = ret;
+ } else if (unlikely(copied < len) && !PageUptodate(page)) {
+ copied = 0;
+ ext4_journalled_zero_new_buffers(handle, page, from, to);
+ } else {
+ if (unlikely(copied < len))
+ ext4_journalled_zero_new_buffers(handle, page,
+ from + copied, to);
ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
- to, &partial, write_end_fn);
+ from + copied, &partial,
+ write_end_fn);
if (!partial)
SetPageUptodate(page);
}
*/
ext4_orphan_add(handle, inode);
+errout:
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
return ret;
map_bh(bh, inode->i_sb, map.m_pblk);
- bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+ ext4_update_bh_state(bh, map.m_flags);
if (buffer_unwritten(bh)) {
/* A delayed write to unwritten bh should be marked
done = true;
}
}
- ext4_journal_stop(handle);
+ /*
+ * Caution: If the handle is synchronous,
+ * ext4_journal_stop() can wait for transaction commit
+ * to finish which may depend on writeback of pages to
+ * complete or on page lock to be released. In that
+ * case, we have to wait until after after we have
+ * submitted all the IO, released page locks we hold,
+ * and dropped io_end reference (for extent conversion
+ * to be able to complete) before stopping the handle.
+ */
+ if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+ ext4_journal_stop(handle);
+ handle = NULL;
+ }
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
- /* Drop our io_end reference we got from init */
- ext4_put_io_end(mpd.io_submit.io_end);
+ /*
+ * Drop our io_end reference we got from init. We have
+ * to be careful and use deferred io_end finishing if
+ * we are still holding the transaction as we can
+ * release the last reference to io_end which may end
+ * up doing unwritten extent conversion.
+ */
+ if (handle) {
+ ext4_put_io_end_defer(mpd.io_submit.io_end);
+ ext4_journal_stop(handle);
+ } else
+ ext4_put_io_end(mpd.io_submit.io_end);
if (ret == -ENOSPC && sbi->s_journal) {
/*
unsigned blocksize;
struct inode *inode = mapping->host;
+ /* If we are processing an encrypted inode during orphan list handling */
+ if (ext4_encrypted_inode(inode) && !ext4_has_encryption_key(inode))
+ return 0;
+
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
}
/*
- * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * We have to make sure i_disksize gets properly updated before we truncate
+ * page cache due to hole punching or zero range. Otherwise i_disksize update
+ * can get lost as it may have been postponed to submission of writeback but
+ * that will never happen after we truncate page cache.
+ */
+int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
+ loff_t len)
+{
+ handle_t *handle;
+ loff_t size = i_size_read(inode);
+
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
+ if (offset > size || offset + len < size)
+ return 0;
+
+ if (EXT4_I(inode)->i_disksize >= size)
+ return 0;
+
+ handle = ext4_journal_start(inode, EXT4_HT_MISC, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ext4_update_i_disksize(inode, size);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+ return 0;
+}
+
+/*
+ * ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
*
* @inode: File inode
* Write out all dirty pages to avoid race conditions
* Then release them.
*/
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
ret = filemap_write_and_wait_range(mapping, offset,
offset + length - 1);
if (ret)
}
+ /* Wait all existing dio workers, newcomers will block on i_mutex */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
+ /*
+ * Prevent page faults from reinstantiating pages we have released from
+ * page cache.
+ */
+ down_write(&EXT4_I(inode)->i_mmap_sem);
first_block_offset = round_up(offset, sb->s_blocksize);
last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
/* Now release the pages and zero block aligned part of pages*/
- if (last_block_offset > first_block_offset)
+ if (last_block_offset > first_block_offset) {
+ ret = ext4_update_disksize_before_punch(inode, offset, length);
+ if (ret)
+ goto out_dio;
truncate_pagecache_range(inode, first_block_offset,
last_block_offset);
-
- /* Wait all existing dio workers, newcomers will block on i_mutex */
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
+ }
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- /* Now release the pages again to reduce race window */
- if (last_block_offset > first_block_offset)
- truncate_pagecache_range(inode, first_block_offset,
- last_block_offset);
-
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
out_stop:
ext4_journal_stop(handle);
out_dio:
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
out_mutex:
mutex_unlock(&inode->i_mutex);
struct inode *inode;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
+ loff_t size;
int block;
uid_t i_uid;
gid_t i_gid;
ei->i_file_acl |=
((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
inode->i_size = ext4_isize(raw_inode);
+ if ((size = i_size_read(inode)) < 0) {
+ EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size);
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
ei->i_disksize = inode->i_size;
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
- if (!ei->i_dtime) {
+ if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+ raw_inode->i_uid_high = 0;
+ raw_inode->i_gid_high = 0;
+ } else {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(i_gid));
- } else {
- raw_inode->i_uid_high = 0;
- raw_inode->i_gid_high = 0;
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
} else
ext4_wait_for_tail_page_commit(inode);
}
+ down_write(&EXT4_I(inode)->i_mmap_sem);
/*
* Truncate pagecache after we've waited for commit
* in data=journal mode to make pages freeable.
truncate_pagecache(inode, inode->i_size);
if (shrink)
ext4_truncate(inode);
+ up_write(&EXT4_I(inode)->i_mmap_sem);
}
if (!rc) {
might_sleep();
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ return err;
if (ext4_handle_valid(handle) &&
EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
!ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) {
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
}
}
}
- if (!err)
- err = ext4_mark_iloc_dirty(handle, inode, &iloc);
- return err;
+ return ext4_mark_iloc_dirty(handle, inode, &iloc);
}
/*
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
+
+ down_read(&EXT4_I(inode)->i_mmap_sem);
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
!ext4_should_journal_data(inode) &&
out_ret:
ret = block_page_mkwrite_return(ret);
out:
+ up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
return ret;
}
+
+int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ int err;
+
+ down_read(&EXT4_I(inode)->i_mmap_sem);
+ err = filemap_fault(vma, vmf);
+ up_read(&EXT4_I(inode)->i_mmap_sem);
+
+ return err;
+}
+
+/*
+ * Find the first extent at or after @lblk in an inode that is not a hole.
+ * Search for @map_len blocks at most. The extent is returned in @result.
+ *
+ * The function returns 1 if we found an extent. The function returns 0 in
+ * case there is no extent at or after @lblk and in that case also sets
+ * @result->es_len to 0. In case of error, the error code is returned.
+ */
+int ext4_get_next_extent(struct inode *inode, ext4_lblk_t lblk,
+ unsigned int map_len, struct extent_status *result)
+{
+ struct ext4_map_blocks map;
+ struct extent_status es = {};
+ int ret;
+
+ map.m_lblk = lblk;
+ map.m_len = map_len;
+
+ /*
+ * For non-extent based files this loop may iterate several times since
+ * we do not determine full hole size.
+ */
+ while (map.m_len > 0) {
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret < 0)
+ return ret;
+ /* There's extent covering m_lblk? Just return it. */
+ if (ret > 0) {
+ int status;
+
+ ext4_es_store_pblock(result, map.m_pblk);
+ result->es_lblk = map.m_lblk;
+ result->es_len = map.m_len;
+ if (map.m_flags & EXT4_MAP_UNWRITTEN)
+ status = EXTENT_STATUS_UNWRITTEN;
+ else
+ status = EXTENT_STATUS_WRITTEN;
+ ext4_es_store_status(result, status);
+ return 1;
+ }
+ ext4_es_find_delayed_extent_range(inode, map.m_lblk,
+ map.m_lblk + map.m_len - 1,
+ &es);
+ /* Is delalloc data before next block in extent tree? */
+ if (es.es_len && es.es_lblk < map.m_lblk + map.m_len) {
+ ext4_lblk_t offset = 0;
+
+ if (es.es_lblk < lblk)
+ offset = lblk - es.es_lblk;
+ result->es_lblk = es.es_lblk + offset;
+ ext4_es_store_pblock(result,
+ ext4_es_pblock(&es) + offset);
+ result->es_len = es.es_len - offset;
+ ext4_es_store_status(result, ext4_es_status(&es));
+
+ return 1;
+ }
+ /* There's a hole at m_lblk, advance us after it */
+ map.m_lblk += map.m_len;
+ map_len -= map.m_len;
+ map.m_len = map_len;
+ cond_resched();
+ }
+ result->es_len = 0;
+ return 0;
+}
+