Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Fix a number of ext4 bugs in fast_commit, inline data, and delayed
  allocation.

  Also fix error handling code paths in ext4_dx_readdir() and
  ext4_fill_super().

  Finally, avoid a grabbing a journal head in the delayed allocation
  write in the common cases where we are overwriting a pre-existing
  block or appending to an inode"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: recheck buffer uptodate bit under buffer lock
  ext4: fix potential infinite loop in ext4_dx_readdir()
  ext4: flush s_error_work before journal destroy in ext4_fill_super
  ext4: fix loff_t overflow in ext4_max_bitmap_size()
  ext4: fix reserved space counter leakage
  ext4: limit the number of blocks in one ADD_RANGE TLV
  ext4: enforce buffer head state assertion in ext4_da_map_blocks
  ext4: remove extent cache entries when truncating inline data
  ext4: drop unnecessary journal handle in delalloc write
  ext4: factor out write end code of inline file
  ext4: correct the error path of ext4_write_inline_data_end()
  ext4: check and update i_disksize properly
  ext4: add error checking to ext4_ext_replay_set_iblocks()

1 files changed, 59 insertions, 117 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d18852d6029c..0f06305167d5 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1284,22 +1284,14 @@ static int ext4_write_end(struct file *file,
 	loff_t old_size = inode->i_size;
 	int ret = 0, ret2;
 	int i_size_changed = 0;
-	int inline_data = ext4_has_inline_data(inode);
 	bool verity = ext4_verity_in_progress(inode);
 
 	trace_ext4_write_end(inode, pos, len, copied);
-	if (inline_data) {
-		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
-		copied = block_write_end(file, mapping, pos,
-					 len, copied, page, fsdata);
+
+	if (ext4_has_inline_data(inode))
+		return ext4_write_inline_data_end(inode, pos, len, copied, page);
+
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 	/*
 	 * it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
@@ -1320,7 +1312,7 @@ static int ext4_write_end(struct file *file,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed || inline_data)
+	if (i_size_changed)
 		ret = ext4_mark_inode_dirty(handle, inode);
 
 	if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
@@ -1329,7 +1321,7 @@ static int ext4_write_end(struct file *file,
 		 * inode->i_size. So truncate them
 		 */
 		ext4_orphan_add(handle, inode);
-errout:
+
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -1395,7 +1387,6 @@ static int ext4_journalled_write_end(struct file *file,
 	int partial = 0;
 	unsigned from, to;
 	int size_changed = 0;
-	int inline_data = ext4_has_inline_data(inode);
 	bool verity = ext4_verity_in_progress(inode);
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
@@ -1404,16 +1395,10 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (inline_data) {
-		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)) {
+	if (ext4_has_inline_data(inode))
+		return ext4_write_inline_data_end(inode, pos, len, copied, page);
+
+	if (unlikely(copied < len) && !PageUptodate(page)) {
 		copied = 0;
 		ext4_journalled_zero_new_buffers(handle, inode, page, from, to);
 	} else {
@@ -1436,7 +1421,7 @@ static int ext4_journalled_write_end(struct file *file,
 	if (old_size < pos && !verity)
 		pagecache_isize_extended(inode, old_size, pos);
 
-	if (size_changed || inline_data) {
+	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
@@ -1449,7 +1434,6 @@ static int ext4_journalled_write_end(struct file *file,
 		 */
 		ext4_orphan_add(handle, inode);
 
-errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -1644,6 +1628,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int ret;
 	bool allocated = false;
+	bool reserved = false;
 
 	/*
 	 * If the cluster containing lblk is shared with a delayed,
@@ -1660,6 +1645,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 		ret = ext4_da_reserve_space(inode);
 		if (ret != 0)   /* ENOSPC */
 			goto errout;
+		reserved = true;
 	} else {   /* bigalloc */
 		if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
 			if (!ext4_es_scan_clu(inode,
@@ -1672,6 +1658,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 					ret = ext4_da_reserve_space(inode);
 					if (ret != 0)   /* ENOSPC */
 						goto errout;
+					reserved = true;
 				} else {
 					allocated = true;
 				}
@@ -1682,6 +1669,8 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 	}
 
 	ret = ext4_es_insert_delayed_block(inode, lblk, allocated);
+	if (ret && reserved)
+		ext4_da_release_space(inode, 1);
 
 errout:
 	return ret;
@@ -1722,13 +1711,16 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		}
 
 		/*
-		 * Delayed extent could be allocated by fallocate.
-		 * So we need to check it.
+		 * the buffer head associated with a delayed and not unwritten
+		 * block found in the extent status cache must contain an
+		 * invalid block number and have its BH_New and BH_Delay bits
+		 * set, reflecting the state assigned when the block was
+		 * initially delayed allocated
 		 */
-		if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
-			map_bh(bh, inode->i_sb, invalid_block);
-			set_buffer_new(bh);
-			set_buffer_delay(bh);
+		if (ext4_es_is_delonly(&es)) {
+			BUG_ON(bh->b_blocknr != invalid_block);
+			BUG_ON(!buffer_new(bh));
+			BUG_ON(!buffer_delay(bh));
 			return 0;
 		}
 
@@ -2932,19 +2924,6 @@ static int ext4_nonda_switch(struct super_block *sb)
 	return 0;
 }
 
-/* We always reserve for an inode update; the superblock could be there too */
-static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
-{
-	if (likely(ext4_has_feature_large_file(inode->i_sb)))
-		return 1;
-
-	if (pos + len <= 0x7fffffffULL)
-		return 1;
-
-	/* We might need to update the superblock to set LARGE_FILE */
-	return 2;
-}
-
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       loff_t pos, unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
@@ -2953,7 +2932,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	struct page *page;
 	pgoff_t index;
 	struct inode *inode = mapping->host;
-	handle_t *handle;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
@@ -2979,41 +2957,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			return 0;
 	}
 
-	/*
-	 * grab_cache_page_write_begin() can take a long time if the
-	 * system is thrashing due to memory pressure, or if the page
-	 * is being written back.  So grab it first before we start
-	 * the transaction handle.  This also allows us to allocate
-	 * the page (if needed) without using GFP_NOFS.
-	 */
-retry_grab:
+retry:
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
-	unlock_page(page);
 
-	/*
-	 * With delayed allocation, we don't log the i_disksize update
-	 * if there is delayed block allocation. But we still need
-	 * to journalling the i_disksize update if writes to the end
-	 * of file which has an already mapped buffer.
-	 */
-retry_journal:
-	handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
-				ext4_da_write_credits(inode, pos, len));
-	if (IS_ERR(handle)) {
-		put_page(page);
-		return PTR_ERR(handle);
-	}
-
-	lock_page(page);
-	if (page->mapping != mapping) {
-		/* The page got truncated from under us */
-		unlock_page(page);
-		put_page(page);
-		ext4_journal_stop(handle);
-		goto retry_grab;
-	}
 	/* In case writeback began while the page was unlocked */
 	wait_for_stable_page(page);
 
@@ -3025,20 +2973,18 @@ retry_journal:
 #endif
 	if (ret < 0) {
 		unlock_page(page);
-		ext4_journal_stop(handle);
+		put_page(page);
 		/*
 		 * block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
-		 * i_size_read because we hold i_mutex.
+		 * i_size_read because we hold inode lock.
 		 */
 		if (pos + len > inode->i_size)
 			ext4_truncate_failed_write(inode);
 
 		if (ret == -ENOSPC &&
 		    ext4_should_retry_alloc(inode->i_sb, &retries))
-			goto retry_journal;
-
-		put_page(page);
+			goto retry;
 		return ret;
 	}
 
@@ -3075,8 +3021,6 @@ static int ext4_da_write_end(struct file *file,
 			     struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
-	int ret = 0, ret2;
-	handle_t *handle = ext4_journal_current_handle();
 	loff_t new_i_size;
 	unsigned long start, end;
 	int write_mode = (int)(unsigned long)fsdata;
@@ -3086,44 +3030,36 @@ static int ext4_da_write_end(struct file *file,
 				      len, copied, page, fsdata);
 
 	trace_ext4_da_write_end(inode, pos, len, copied);
+
+	if (write_mode != CONVERT_INLINE_DATA &&
+	    ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
+	    ext4_has_inline_data(inode))
+		return ext4_write_inline_data_end(inode, pos, len, copied, page);
+
 	start = pos & (PAGE_SIZE - 1);
 	end = start + copied - 1;
 
 	/*
-	 * generic_write_end() will run mark_inode_dirty() if i_size
-	 * changes.  So let's piggyback the i_disksize mark_inode_dirty
-	 * into that.
+	 * Since we are holding inode lock, we are sure i_disksize <=
+	 * i_size. We also know that if i_disksize < i_size, there are
+	 * delalloc writes pending in the range upto i_size. If the end of
+	 * the current write is <= i_size, there's no need to touch
+	 * i_disksize since writeback will push i_disksize upto i_size
+	 * eventually. If the end of the current write is > i_size and
+	 * inside an allocated block (ext4_da_should_update_i_disksize()
+	 * check), we need to update i_disksize here as neither
+	 * ext4_writepage() nor certain ext4_writepages() paths not
+	 * allocating blocks update i_disksize.
+	 *
+	 * Note that we defer inode dirtying to generic_write_end() /
+	 * ext4_da_write_inline_data_end().
 	 */
 	new_i_size = pos + copied;
-	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
-		if (ext4_has_inline_data(inode) ||
-		    ext4_da_should_update_i_disksize(page, end)) {
-			ext4_update_i_disksize(inode, new_i_size);
-			/* We need to mark inode dirty even if
-			 * new_i_size is less that inode->i_size
-			 * bu greater than i_disksize.(hint delalloc)
-			 */
-			ret = ext4_mark_inode_dirty(handle, inode);
-		}
-	}
+	if (copied && new_i_size > inode->i_size &&
+	    ext4_da_should_update_i_disksize(page, end))
+		ext4_update_i_disksize(inode, new_i_size);
 
-	if (write_mode != CONVERT_INLINE_DATA &&
-	    ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
-	    ext4_has_inline_data(inode))
-		ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied,
-						     page);
-	else
-		ret2 = generic_write_end(file, mapping, pos, len, copied,
-							page, fsdata);
-
-	copied = ret2;
-	if (ret2 < 0)
-		ret = ret2;
-	ret2 = ext4_journal_stop(handle);
-	if (unlikely(ret2 && !ret))
-		ret = ret2;
-
-	return ret ? ret : copied;
+	return generic_write_end(file, mapping, pos, len, copied, page, fsdata);
 }
 
 /*
@@ -4340,6 +4276,12 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
 		goto has_buffer;
 
 	lock_buffer(bh);
+	if (ext4_buffer_uptodate(bh)) {
+		/* Someone brought it uptodate while we waited */
+		unlock_buffer(bh);
+		goto has_buffer;
+	}
+
 	/*
 	 * If we have all information of the inode in memory and this
 	 * is the only valid inode in the block, we need not read the