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

Pull ext4 update from Ted Ts'o:
"Fixed regressions (two stability regressions and a performance
regression) introduced during the 3.10-rc1 merge window.

Also included is a bug fix relating to allocating blocks after
resizing an ext3 file system when using the ext4 file system driver"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
jbd,jbd2: fix oops in jbd2_journal_put_journal_head()
ext4: revert "ext4: use io_end for multiple bios"
ext4: limit group search loop for non-extent files
ext4: fix fio regression

fs/ext4/ext4.h

···
 	ssize_t			size;		/* size of the extent */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
-	atomic_t		count;		/* reference counter */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
···
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);
+extern void ext4_add_complete_io(ext4_io_end_t *io_end);
 extern void ext4_exit_pageio(void);
 extern void ext4_ioend_shutdown(struct inode *);
+extern void ext4_free_io_end(ext4_io_end_t *io);
 extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
-extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
-extern int ext4_put_io_end(ext4_io_end_t *io_end);
-extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
-extern void ext4_io_submit_init(struct ext4_io_submit *io,
-				struct writeback_control *wbc);
 extern void ext4_end_io_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,

fs/ext4/extents.c

···
 {
 	struct extent_status es;
 
-	ext4_es_find_delayed_extent(inode, lblk_start, &es);
+	ext4_es_find_delayed_extent_range(inode, lblk_start, lblk_end, &es);
 	if (es.es_len == 0)
 		return 0; /* there is no delay extent in this tree */
 	else if (es.es_lblk <= lblk_start &&
···
 	struct extent_status es;
 	ext4_lblk_t block, next_del;
 
-	ext4_es_find_delayed_extent(inode, newes->es_lblk, &es);
-
 	if (newes->es_pblk == 0) {
+		ext4_es_find_delayed_extent_range(inode, newes->es_lblk,
+				newes->es_lblk + newes->es_len - 1, &es);
+
 		/*
 		 * No extent in extent-tree contains block @newes->es_pblk,
 		 * then the block may stay in 1)a hole or 2)delayed-extent.
···
 	}
 
 	block = newes->es_lblk + newes->es_len;
-	ext4_es_find_delayed_extent(inode, block, &es);
+	ext4_es_find_delayed_extent_range(inode, block, EXT_MAX_BLOCKS, &es);
 	if (es.es_len == 0)
 		next_del = EXT_MAX_BLOCKS;
 	else

fs/ext4/extents_status.c

···
 }
 
 /*
- * ext4_es_find_delayed_extent: find the 1st delayed extent covering @es->lblk
- * if it exists, otherwise, the next extent after @es->lblk.
+ * ext4_es_find_delayed_extent_range: find the 1st delayed extent covering
+ * @es->lblk if it exists, otherwise, the next extent after @es->lblk.
  *
  * @inode: the inode which owns delayed extents
  * @lblk: the offset where we start to search
+ * @end: the offset where we stop to search
  * @es: delayed extent that we found
  */
-void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+void ext4_es_find_delayed_extent_range(struct inode *inode,
+				 ext4_lblk_t lblk, ext4_lblk_t end,
 				 struct extent_status *es)
 {
 	struct ext4_es_tree *tree = NULL;
···
 	struct rb_node *node;
 
 	BUG_ON(es == NULL);
-	trace_ext4_es_find_delayed_extent_enter(inode, lblk);
+	BUG_ON(end < lblk);
+	trace_ext4_es_find_delayed_extent_range_enter(inode, lblk);
 
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	tree = &EXT4_I(inode)->i_es_tree;
···
 	if (es1 && !ext4_es_is_delayed(es1)) {
 		while ((node = rb_next(&es1->rb_node)) != NULL) {
 			es1 = rb_entry(node, struct extent_status, rb_node);
+			if (es1->es_lblk > end) {
+				es1 = NULL;
+				break;
+			}
 			if (ext4_es_is_delayed(es1))
 				break;
 		}
···
 	read_unlock(&EXT4_I(inode)->i_es_lock);
 
 	ext4_es_lru_add(inode);
-	trace_ext4_es_find_delayed_extent_exit(inode, es);
+	trace_ext4_es_find_delayed_extent_range_exit(inode, es);
 }
 
 static struct extent_status *

fs/ext4/extents_status.h

···
 				 unsigned long long status);
 extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
 				 ext4_lblk_t len);
-extern void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+extern void ext4_es_find_delayed_extent_range(struct inode *inode,
+					ext4_lblk_t lblk, ext4_lblk_t end,
 					struct extent_status *es);
 extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 				 struct extent_status *es);

fs/ext4/file.c

···
 		 * If there is a delay extent at this offset,
 		 * it will be as a data.
 		 */
-		ext4_es_find_delayed_extent(inode, last, &es);
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
 		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
 			if (last != start)
 				dataoff = last << blkbits;
···
 		 * If there is a delay extent at this offset,
 		 * we will skip this extent.
 		 */
-		ext4_es_find_delayed_extent(inode, last, &es);
+		ext4_es_find_delayed_extent_range(inode, last, last, &es);
 		if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
 			last = es.es_lblk + es.es_len;
 			holeoff = last << blkbits;

fs/ext4/inode.c

···
 	struct ext4_io_submit io_submit;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
-	ext4_io_submit_init(&io_submit, mpd->wbc);
-	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
-	if (!io_submit.io_end)
-		return -ENOMEM;
+	memset(&io_submit, 0, sizeof(io_submit));
 	/*
 	 * We need to start from the first_page to the next_page - 1
 	 * to make sure we also write the mapped dirty buffer_heads.
···
 		pagevec_release(&pvec);
 	}
 	ext4_io_submit(&io_submit);
-	/* Drop io_end reference we got from init */
-	ext4_put_io_end_defer(io_submit.io_end);
 	return ret;
 }
 
···
 		 */
 		return __ext4_journalled_writepage(page, len);
 
-	ext4_io_submit_init(&io_submit, wbc);
-	io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS);
-	if (!io_submit.io_end) {
-		redirty_page_for_writepage(wbc, page);
-		return -ENOMEM;
-	}
+	memset(&io_submit, 0, sizeof(io_submit));
 	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
 	ext4_io_submit(&io_submit);
-	/* Drop io_end reference we got from init */
-	ext4_put_io_end_defer(io_submit.io_end);
 	return ret;
 }
 
···
 	struct inode *inode = file_inode(iocb->ki_filp);
         ext4_io_end_t *io_end = iocb->private;
 
-	/* if not async direct IO just return */
-	if (!io_end) {
-		inode_dio_done(inode);
-		if (is_async)
-			aio_complete(iocb, ret, 0);
-		return;
-	}
+	/* if not async direct IO or dio with 0 bytes write, just return */
+	if (!io_end || !size)
+		goto out;
 
 	ext_debug("ext4_end_io_dio(): io_end 0x%p "
 		  "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
···
 		  size);
 
 	iocb->private = NULL;
+
+	/* if not aio dio with unwritten extents, just free io and return */
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+out:
+		inode_dio_done(inode);
+		if (is_async)
+			aio_complete(iocb, ret, 0);
+		return;
+	}
+
 	io_end->offset = offset;
 	io_end->size = size;
 	if (is_async) {
 		io_end->iocb = iocb;
 		io_end->result = ret;
 	}
-	ext4_put_io_end_defer(io_end);
+
+	ext4_add_complete_io(io_end);
 }
 
 /*
···
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
 	loff_t final_size = offset + count;
-	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
 	if (rw != WRITE || final_size > inode->i_size)
···
 	iocb->private = NULL;
 	ext4_inode_aio_set(inode, NULL);
 	if (!is_sync_kiocb(iocb)) {
-		io_end = ext4_init_io_end(inode, GFP_NOFS);
+		ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS);
 		if (!io_end) {
 			ret = -ENOMEM;
 			goto retake_lock;
 		}
 		io_end->flag |= EXT4_IO_END_DIRECT;
-		/*
-		 * Grab reference for DIO. Will be dropped in ext4_end_io_dio()
-		 */
-		iocb->private = ext4_get_io_end(io_end);
+		iocb->private = io_end;
 		/*
 		 * we save the io structure for current async direct
 		 * IO, so that later ext4_map_blocks() could flag the
···
 				   NULL,
 				   dio_flags);
 
-	/*
-	 * Put our reference to io_end. This can free the io_end structure e.g.
-	 * in sync IO case or in case of error. It can even perform extent
-	 * conversion if all bios we submitted finished before we got here.
-	 * Note that in that case iocb->private can be already set to NULL
-	 * here.
-	 */
-	if (io_end) {
+	if (iocb->private)
 		ext4_inode_aio_set(inode, NULL);
-		ext4_put_io_end(io_end);
-		/*
-		 * In case of error or no write ext4_end_io_dio() was not
-		 * called so we have to put iocb's reference.
-		 */
-		if (ret <= 0 && ret != -EIOCBQUEUED) {
-			WARN_ON(iocb->private != io_end);
-			ext4_put_io_end(io_end);
-			iocb->private = NULL;
-		}
-	}
-	if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
+	/*
+	 * The io_end structure takes a reference to the inode, that
+	 * structure needs to be destroyed and the reference to the
+	 * inode need to be dropped, when IO is complete, even with 0
+	 * byte write, or failed.
+	 *
+	 * In the successful AIO DIO case, the io_end structure will
+	 * be destroyed and the reference to the inode will be dropped
+	 * after the end_io call back function is called.
+	 *
+	 * In the case there is 0 byte write, or error case, since VFS
+	 * direct IO won't invoke the end_io call back function, we
+	 * need to free the end_io structure here.
+	 */
+	if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
+		ext4_free_io_end(iocb->private);
+		iocb->private = NULL;
+	} else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
 		int err;
 		/*

fs/ext4/mballoc.c

···
 		group = ac->ac_g_ex.fe_group;
 
 		for (i = 0; i < ngroups; group++, i++) {
-			if (group == ngroups)
+			/*
+			 * Artificially restricted ngroups for non-extent
+			 * files makes group > ngroups possible on first loop.
+			 */
+			if (group >= ngroups)
 				group = 0;
 
 			/* This now checks without needing the buddy page */

fs/ext4/page-io.c

···
 		cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
 }
 
-static void ext4_release_io_end(ext4_io_end_t *io_end)
+void ext4_free_io_end(ext4_io_end_t *io)
 {
-	BUG_ON(!list_empty(&io_end->list));
-	BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
+	BUG_ON(!io);
+	BUG_ON(!list_empty(&io->list));
+	BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
 
-	if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
-		wake_up_all(ext4_ioend_wq(io_end->inode));
-	if (io_end->flag & EXT4_IO_END_DIRECT)
-		inode_dio_done(io_end->inode);
-	if (io_end->iocb)
-		aio_complete(io_end->iocb, io_end->result, 0);
-	kmem_cache_free(io_end_cachep, io_end);
-}
-
-static void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
-{
-	struct inode *inode = io_end->inode;
-
-	io_end->flag &= ~EXT4_IO_END_UNWRITTEN;
-	/* Wake up anyone waiting on unwritten extent conversion */
-	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
-		wake_up_all(ext4_ioend_wq(inode));
+	if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count))
+		wake_up_all(ext4_ioend_wq(io->inode));
+	kmem_cache_free(io_end_cachep, io);
 }
 
 /* check a range of space and convert unwritten extents to written. */
···
 			 "(inode %lu, offset %llu, size %zd, error %d)",
 			 inode->i_ino, offset, size, ret);
 	}
-	ext4_clear_io_unwritten_flag(io);
-	ext4_release_io_end(io);
+	/* Wake up anyone waiting on unwritten extent conversion */
+	if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
+		wake_up_all(ext4_ioend_wq(inode));
+	if (io->flag & EXT4_IO_END_DIRECT)
+		inode_dio_done(inode);
+	if (io->iocb)
+		aio_complete(io->iocb, io->result, 0);
 	return ret;
 }
 
···
 }
 
 /* Add the io_end to per-inode completed end_io list. */
-static void ext4_add_complete_io(ext4_io_end_t *io_end)
+void ext4_add_complete_io(ext4_io_end_t *io_end)
 {
 	struct ext4_inode_info *ei = EXT4_I(io_end->inode);
 	struct workqueue_struct *wq;
···
 		err = ext4_end_io(io);
 		if (unlikely(!ret && err))
 			ret = err;
+		io->flag &= ~EXT4_IO_END_UNWRITTEN;
+		ext4_free_io_end(io);
 	}
 	return ret;
 }
···
 		atomic_inc(&EXT4_I(inode)->i_ioend_count);
 		io->inode = inode;
 		INIT_LIST_HEAD(&io->list);
-		atomic_set(&io->count, 1);
 	}
 	return io;
-}
-
-void ext4_put_io_end_defer(ext4_io_end_t *io_end)
-{
-	if (atomic_dec_and_test(&io_end->count)) {
-		if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
-			ext4_release_io_end(io_end);
-			return;
-		}
-		ext4_add_complete_io(io_end);
-	}
-}
-
-int ext4_put_io_end(ext4_io_end_t *io_end)
-{
-	int err = 0;
-
-	if (atomic_dec_and_test(&io_end->count)) {
-		if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
-			err = ext4_convert_unwritten_extents(io_end->inode,
-						io_end->offset, io_end->size);
-			ext4_clear_io_unwritten_flag(io_end);
-		}
-		ext4_release_io_end(io_end);
-	}
-	return err;
-}
-
-ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
-{
-	atomic_inc(&io_end->count);
-	return io_end;
 }
 
 /*
···
 			     bi_sector >> (inode->i_blkbits - 9));
 	}
 
-	ext4_put_io_end_defer(io_end);
+	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		ext4_free_io_end(io_end);
+		return;
+	}
+
+	ext4_add_complete_io(io_end);
 }
 
 void ext4_io_submit(struct ext4_io_submit *io)
···
 		bio_put(io->io_bio);
 	}
 	io->io_bio = NULL;
-}
-
-void ext4_io_submit_init(struct ext4_io_submit *io,
-			 struct writeback_control *wbc)
-{
-	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
-	io->io_bio = NULL;
+	io->io_op = 0;
 	io->io_end = NULL;
 }
 
-static int io_submit_init_bio(struct ext4_io_submit *io,
-			      struct buffer_head *bh)
+static int io_submit_init(struct ext4_io_submit *io,
+			  struct inode *inode,
+			  struct writeback_control *wbc,
+			  struct buffer_head *bh)
 {
+	ext4_io_end_t *io_end;
+	struct page *page = bh->b_page;
 	int nvecs = bio_get_nr_vecs(bh->b_bdev);
 	struct bio *bio;
 
+	io_end = ext4_init_io_end(inode, GFP_NOFS);
+	if (!io_end)
+		return -ENOMEM;
 	bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
 	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
+	bio->bi_private = io->io_end = io_end;
 	bio->bi_end_io = ext4_end_bio;
-	bio->bi_private = ext4_get_io_end(io->io_end);
-	if (!io->io_end->size)
-		io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT)
-				     + bh_offset(bh);
+
+	io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
+
 	io->io_bio = bio;
+	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 	io->io_next_block = bh->b_blocknr;
 	return 0;
 }
 
 static int io_submit_add_bh(struct ext4_io_submit *io,
 			    struct inode *inode,
+			    struct writeback_control *wbc,
 			    struct buffer_head *bh)
 {
 	ext4_io_end_t *io_end;
···
 		ext4_io_submit(io);
 	}
 	if (io->io_bio == NULL) {
-		ret = io_submit_init_bio(io, bh);
+		ret = io_submit_init(io, inode, wbc, bh);
 		if (ret)
 			return ret;
 	}
-	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
-	if (ret != bh->b_size)
-		goto submit_and_retry;
 	io_end = io->io_end;
 	if (test_clear_buffer_uninit(bh))
 		ext4_set_io_unwritten_flag(inode, io_end);
-	io_end->size += bh->b_size;
+	io->io_end->size += bh->b_size;
 	io->io_next_block++;
+	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+	if (ret != bh->b_size)
+		goto submit_and_retry;
 	return 0;
 }
 
···
 	do {
 		if (!buffer_async_write(bh))
 			continue;
-		ret = io_submit_add_bh(io, inode, bh);
+		ret = io_submit_add_bh(io, inode, wbc, bh);
 		if (ret) {
 			/*
 			 * We only get here on ENOMEM.  Not much else

include/linux/journal-head.h

···
 
 	/*
 	 * Journalling list for this buffer [jbd_lock_bh_state()]
+	 * NOTE: We *cannot* combine this with b_modified into a bitfield
+	 * as gcc would then (which the C standard allows but which is
+	 * very unuseful) make 64-bit accesses to the bitfield and clobber
+	 * b_jcount if its update races with bitfield modification.
 	 */
-	unsigned b_jlist:4;
+	unsigned b_jlist;
 
 	/*
 	 * This flag signals the buffer has been modified by
 	 * the currently running transaction
 	 * [jbd_lock_bh_state()]
 	 */
-	unsigned b_modified:1;
+	unsigned b_modified;
 
 	/*
 	 * Copy of the buffer data frozen for writing to the log.

include/trace/events/ext4.h

···
 		  __entry->lblk, __entry->len)
 );
 
-TRACE_EVENT(ext4_es_find_delayed_extent_enter,
+TRACE_EVENT(ext4_es_find_delayed_extent_range_enter,
 	TP_PROTO(struct inode *inode, ext4_lblk_t lblk),
 
 	TP_ARGS(inode, lblk),
···
 		  (unsigned long) __entry->ino, __entry->lblk)
 );
 
-TRACE_EVENT(ext4_es_find_delayed_extent_exit,
+TRACE_EVENT(ext4_es_find_delayed_extent_range_exit,
 	TP_PROTO(struct inode *inode, struct extent_status *es),
 
 	TP_ARGS(inode, es),