Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "A lot of bug fixes and cleanups for ext4, including:

   - Fix performance problems found in dioread_nolock now that it is the
     default, caused by transaction leaks.

   - Clean up fiemap handling in ext4

   - Clean up and refactor multiple block allocator (mballoc) code

   - Fix a problem with mballoc with a smaller file systems running out
     of blocks because they couldn't properly use blocks that had been
     reserved by inode preallocation.

   - Fixed a race in ext4_sync_parent() versus rename()

   - Simplify the error handling in the extent manipulation code

   - Make sure all metadata I/O errors are felected to
     ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers.

   - Avoid passing an error pointer to brelse in ext4_xattr_set()

   - Fix race which could result to freeing an inode on the dirty last
     in data=journal mode.

   - Fix refcount handling if ext4_iget() fails

   - Fix a crash in generic/019 caused by a corrupted extent node"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits)
  ext4: avoid unnecessary transaction starts during writeback
  ext4: don't block for O_DIRECT if IOCB_NOWAIT is set
  ext4: remove the access_ok() check in ext4_ioctl_get_es_cache
  fs: remove the access_ok() check in ioctl_fiemap
  fs: handle FIEMAP_FLAG_SYNC in fiemap_prep
  fs: move fiemap range validation into the file systems instances
  iomap: fix the iomap_fiemap prototype
  fs: move the fiemap definitions out of fs.h
  fs: mark __generic_block_fiemap static
  ext4: remove the call to fiemap_check_flags in ext4_fiemap
  ext4: split _ext4_fiemap
  ext4: fix fiemap size checks for bitmap files
  ext4: fix EXT4_MAX_LOGICAL_BLOCK macro
  add comment for ext4_dir_entry_2 file_type member
  jbd2: avoid leaking transaction credits when unreserving handle
  ext4: drop ext4_journal_free_reserved()
  ext4: mballoc: use lock for checking free blocks while retrying
  ext4: mballoc: refactor ext4_mb_good_group()
  ext4: mballoc: introduce pcpu seqcnt for freeing PA to improve ENOSPC handling
  ext4: mballoc: refactor ext4_mb_discard_preallocations()
  ...

1 files changed, 62 insertions, 46 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 52be85f96159..afffb75915dc 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -221,6 +221,16 @@ void ext4_evict_inode(struct inode *inode)
 	truncate_inode_pages_final(&inode->i_data);
 
 	/*
+	 * For inodes with journalled data, transaction commit could have
+	 * dirtied the inode. Flush worker is ignoring it because of I_FREEING
+	 * flag but we still need to remove the inode from the writeback lists.
+	 */
+	if (!list_empty_careful(&inode->i_io_list)) {
+		WARN_ON_ONCE(!ext4_should_journal_data(inode));
+		inode_io_list_del(inode);
+	}
+
+	/*
 	 * Protect us against freezing - iput() caller didn't have to have any
 	 * protection against it
 	 */
@@ -432,11 +442,9 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 	 */
 	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-		retval = ext4_ext_map_blocks(handle, inode, map, flags &
-					     EXT4_GET_BLOCKS_KEEP_SIZE);
+		retval = ext4_ext_map_blocks(handle, inode, map, 0);
 	} else {
-		retval = ext4_ind_map_blocks(handle, inode, map, flags &
-					     EXT4_GET_BLOCKS_KEEP_SIZE);
+		retval = ext4_ind_map_blocks(handle, inode, map, 0);
 	}
 	up_read((&EXT4_I(inode)->i_data_sem));
 
@@ -493,9 +501,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 #endif
 
 	map->m_flags = 0;
-	ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
-		  "logical block %lu\n", inode->i_ino, flags, map->m_len,
-		  (unsigned long) map->m_lblk);
+	ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n",
+		  flags, map->m_len, (unsigned long) map->m_lblk);
 
 	/*
 	 * ext4_map_blocks returns an int, and m_len is an unsigned int
@@ -541,11 +548,9 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 */
 	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-		retval = ext4_ext_map_blocks(handle, inode, map, flags &
-					     EXT4_GET_BLOCKS_KEEP_SIZE);
+		retval = ext4_ext_map_blocks(handle, inode, map, 0);
 	} else {
-		retval = ext4_ind_map_blocks(handle, inode, map, flags &
-					     EXT4_GET_BLOCKS_KEEP_SIZE);
+		retval = ext4_ind_map_blocks(handle, inode, map, 0);
 	}
 	if (retval > 0) {
 		unsigned int status;
@@ -726,6 +731,9 @@ out_sem:
 				return ret;
 		}
 	}
+
+	if (retval < 0)
+		ext_debug(inode, "failed with err %d\n", retval);
 	return retval;
 }
 
@@ -1296,7 +1304,7 @@ static int ext4_write_end(struct file *file,
 	 * filesystems.
 	 */
 	if (i_size_changed || inline_data)
-		ext4_mark_inode_dirty(handle, inode);
+		ret = ext4_mark_inode_dirty(handle, inode);
 
 	if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
@@ -1526,6 +1534,7 @@ struct mpage_da_data {
 	struct ext4_map_blocks map;
 	struct ext4_io_submit io_submit;	/* IO submission data */
 	unsigned int do_map:1;
+	unsigned int scanned_until_end:1;
 };
 
 static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@@ -1541,6 +1550,7 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
 	if (mpd->first_page >= mpd->next_page)
 		return;
 
+	mpd->scanned_until_end = 0;
 	index = mpd->first_page;
 	end   = mpd->next_page - 1;
 	if (invalidate) {
@@ -1681,8 +1691,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		invalid_block = ~0;
 
 	map->m_flags = 0;
-	ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
-		  "logical block %lu\n", inode->i_ino, map->m_len,
+	ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
 		  (unsigned long) map->m_lblk);
 
 	/* Lookup extent status tree firstly */
@@ -2078,7 +2087,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	return err;
 }
 
-#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
+#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay))
 
 /*
  * mballoc gives us at most this number of blocks...
@@ -2188,7 +2197,11 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 		if (err < 0)
 			return err;
 	}
-	return lblk < blocks;
+	if (lblk >= blocks) {
+		mpd->scanned_until_end = 1;
+		return 0;
+	}
+	return 1;
 }
 
 /*
@@ -2311,7 +2324,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
 			 * mapping, or maybe the page was submitted for IO.
 			 * So we return to call further extent mapping.
 			 */
-			if (err < 0 || map_bh == true)
+			if (err < 0 || map_bh)
 				goto out;
 			/* Page fully mapped - let IO run! */
 			err = mpage_submit_page(mpd, page);
@@ -2358,7 +2371,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	dioread_nolock = ext4_should_dioread_nolock(inode);
 	if (dioread_nolock)
 		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
-	if (map->m_flags & (1 << BH_Delay))
+	if (map->m_flags & BIT(BH_Delay))
 		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
 
 	err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
@@ -2546,7 +2559,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
 				tag);
 		if (nr_pages == 0)
-			goto out;
+			break;
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
@@ -2601,6 +2614,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 		pagevec_release(&pvec);
 		cond_resched();
 	}
+	mpd->scanned_until_end = 1;
 	return 0;
 out:
 	pagevec_release(&pvec);
@@ -2619,7 +2633,6 @@ static int ext4_writepages(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	int needed_blocks, rsv_blocks = 0, ret = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
-	bool done;
 	struct blk_plug plug;
 	bool give_up_on_write = false;
 
@@ -2705,7 +2718,6 @@ static int ext4_writepages(struct address_space *mapping,
 retry:
 	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
-	done = false;
 	blk_start_plug(&plug);
 
 	/*
@@ -2715,6 +2727,7 @@ retry:
 	 * started.
 	 */
 	mpd.do_map = 0;
+	mpd.scanned_until_end = 0;
 	mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
 	if (!mpd.io_submit.io_end) {
 		ret = -ENOMEM;
@@ -2730,7 +2743,7 @@ retry:
 	if (ret < 0)
 		goto unplug;
 
-	while (!done && mpd.first_page <= mpd.last_page) {
+	while (!mpd.scanned_until_end && wbc->nr_to_write > 0) {
 		/* For each extent of pages we use new io_end */
 		mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
 		if (!mpd.io_submit.io_end) {
@@ -2765,20 +2778,9 @@ retry:
 
 		trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
 		ret = mpage_prepare_extent_to_map(&mpd);
-		if (!ret) {
-			if (mpd.map.m_len)
-				ret = mpage_map_and_submit_extent(handle, &mpd,
+		if (!ret && mpd.map.m_len)
+			ret = mpage_map_and_submit_extent(handle, &mpd,
 					&give_up_on_write);
-			else {
-				/*
-				 * We scanned the whole range (or exhausted
-				 * nr_to_write), submitted what was mapped and
-				 * didn't find anything needing mapping. We are
-				 * done.
-				 */
-				done = true;
-			}
-		}
 		/*
 		 * Caution: If the handle is synchronous,
 		 * ext4_journal_stop() can wait for transaction commit
@@ -3077,7 +3079,7 @@ static int ext4_da_write_end(struct file *file,
 			 * new_i_size is less that inode->i_size
 			 * bu greater than i_disksize.(hint delalloc)
 			 */
-			ext4_mark_inode_dirty(handle, inode);
+			ret = ext4_mark_inode_dirty(handle, inode);
 		}
 	}
 
@@ -3094,7 +3096,7 @@ static int ext4_da_write_end(struct file *file,
 	if (ret2 < 0)
 		ret = ret2;
 	ret2 = ext4_journal_stop(handle);
-	if (!ret)
+	if (unlikely(ret2 && !ret))
 		ret = ret2;
 
 	return ret ? ret : copied;
@@ -3883,6 +3885,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 				      loff_t len)
 {
 	handle_t *handle;
+	int ret;
+
 	loff_t size = i_size_read(inode);
 
 	WARN_ON(!inode_is_locked(inode));
@@ -3896,10 +3900,10 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ext4_update_i_disksize(inode, size);
-	ext4_mark_inode_dirty(handle, inode);
+	ret = ext4_mark_inode_dirty(handle, inode);
 	ext4_journal_stop(handle);
 
-	return 0;
+	return ret;
 }
 
 static void ext4_wait_dax_page(struct ext4_inode_info *ei)
@@ -3951,7 +3955,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	loff_t first_block_offset, last_block_offset;
 	handle_t *handle;
 	unsigned int credits;
-	int ret = 0;
+	int ret = 0, ret2 = 0;
 
 	trace_ext4_punch_hole(inode, offset, length, 0);
 
@@ -4074,7 +4078,9 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 		ext4_handle_sync(handle);
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
+	ret2 = ext4_mark_inode_dirty(handle, inode);
+	if (unlikely(ret2))
+		ret = ret2;
 	if (ret >= 0)
 		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
@@ -4143,7 +4149,7 @@ int ext4_truncate(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int credits;
-	int err = 0;
+	int err = 0, err2;
 	handle_t *handle;
 	struct address_space *mapping = inode->i_mapping;
 
@@ -4231,7 +4237,9 @@ out_stop:
 		ext4_orphan_del(handle, inode);
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
+	err2 = ext4_mark_inode_dirty(handle, inode);
+	if (unlikely(err2 && !err))
+		err = err2;
 	ext4_journal_stop(handle);
 
 	trace_ext4_truncate_exit(inode);
@@ -5289,6 +5297,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			inode->i_gid = attr->ia_gid;
 		error = ext4_mark_inode_dirty(handle, inode);
 		ext4_journal_stop(handle);
+		if (unlikely(error))
+			return error;
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
@@ -5774,7 +5784,8 @@ out_unlock:
  * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
  * we start and wait on commits.
  */
-int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
+int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
+				const char *func, unsigned int line)
 {
 	struct ext4_iloc iloc;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -5784,13 +5795,18 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 	trace_ext4_mark_inode_dirty(inode, _RET_IP_);
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
 	if (err)
-		return err;
+		goto out;
 
 	if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize)
 		ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize,
 					       iloc, handle);
 
-	return ext4_mark_iloc_dirty(handle, inode, &iloc);
+	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+out:
+	if (unlikely(err))
+		ext4_error_inode_err(inode, func, line, 0, err,
+					"mark_inode_dirty error");
+	return err;
 }
 
 /*