Merge: fs: replace ll_rw_block()

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1885

Bugzilla: https://bugzilla.redhat.com/2160719

Tested: xfstests

ll_rw_block() is not safe for the sync read path because it cannot
guarantee that submitting read IO if the buffer has been locked. We
could get false positive EIO after wait_on_buffer() if the buffer
has been locked by others.

ll_rw_block() is being used by multiple file systems (gfs2, isofs,
jbd2, ntfs3, ocfs2, reiserfs, udf, ufs) not all of which are shipped
by Red Hat so we only backport changes for gfs2, isofs, jbd2, and udf.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>

Approved-by: Pavel Reichl <preichl@redhat.com>
Approved-by: Andreas Gruenbacher <agruenba@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

fs/buffer.c

@@ -152,7 +152,7 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
 
 /*
  * Default synchronous end-of-IO handler..  Just mark it up-to-date and
- * unlock the buffer. This is what ll_rw_block uses too.
+ * unlock the buffer.
  */
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
 {
@@ -491,8 +491,8 @@ int inode_has_buffers(struct inode *inode)
  * all already-submitted IO to complete, but does not queue any new
  * writes to the disk.
  *
- * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as
- * you dirty the buffers, and then use osync_inode_buffers to wait for
+ * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer
+ * as you dirty the buffers, and then use osync_inode_buffers to wait for
  * completion.  Any other dirty buffers which are not yet queued for
  * write will not be flushed to disk by the osync.
  */
@@ -562,7 +562,7 @@ void write_boundary_block(struct block_device *bdev,
 	struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
 	if (bh) {
 		if (buffer_dirty(bh))
-			ll_rw_block(REQ_OP_WRITE, 1, &bh);
+			write_dirty_buffer(bh, 0);
 		put_bh(bh);
 	}
 }
@@ -1342,23 +1342,12 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 {
 	struct buffer_head *bh = __getblk(bdev, block, size);
 	if (likely(bh)) {
-		ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
+		bh_readahead(bh, REQ_RAHEAD);
 		brelse(bh);
 	}
 }
 EXPORT_SYMBOL(__breadahead);
 
-void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size,
-		      gfp_t gfp)
-{
-	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
-	if (likely(bh)) {
-		ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
-		brelse(bh);
-	}
-}
-EXPORT_SYMBOL(__breadahead_gfp);
-
 /**
  *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
@@ -1817,7 +1806,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
 		/*
 		 * The page was marked dirty, but the buffers were
 		 * clean.  Someone wrote them back by hand with
-		 * ll_rw_block/submit_bh.  A rare case.
+		 * write_dirty_buffer/submit_bh.  A rare case.
 		 */
 		end_page_writeback(page);
 
@@ -2033,7 +2022,7 @@ int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 		if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
 		    !buffer_unwritten(bh) &&
 		     (block_start < from || block_end > to)) {
-			ll_rw_block(REQ_OP_READ, 1, &bh);
+			bh_read_nowait(bh, 0);
 			*wait_bh++=bh;
 		}
 	}
@@ -2920,11 +2909,9 @@ int block_truncate_page(struct address_space *mapping,
 		set_buffer_uptodate(bh);
 
 	if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
-		err = -EIO;
-		ll_rw_block(REQ_OP_READ, 1, &bh);
-		wait_on_buffer(bh);
+		err = bh_read(bh, 0);
 		/* Uhhuh. Read error. Complain and punt. */
-		if (!buffer_uptodate(bh))
+		if (err < 0)
 			goto unlock;
 	}
 
@@ -3053,61 +3040,6 @@ int submit_bh(blk_opf_t opf, struct buffer_head *bh)
 }
 EXPORT_SYMBOL(submit_bh);
 
-/**
- * ll_rw_block: low-level access to block devices (DEPRECATED)
- * @opf: block layer request operation and flags.
- * @nr: number of &struct buffer_heads in the array
- * @bhs: array of pointers to &struct buffer_head
- *
- * ll_rw_block() takes an array of pointers to &struct buffer_heads, and
- * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
- * @opf contains flags modifying the detailed I/O behavior, most notably
- * %REQ_RAHEAD.
- *
- * This function drops any buffer that it cannot get a lock on (with the
- * BH_Lock state bit), any buffer that appears to be clean when doing a write
- * request, and any buffer that appears to be up-to-date when doing read
- * request.  Further it marks as clean buffers that are processed for
- * writing (the buffer cache won't assume that they are actually clean
- * until the buffer gets unlocked).
- *
- * ll_rw_block sets b_end_io to simple completion handler that marks
- * the buffer up-to-date (if appropriate), unlocks the buffer and wakes
- * any waiters. 
- *
- * All of the buffers must be for the same device, and must also be a
- * multiple of the current approved size for the device.
- */
-void ll_rw_block(const blk_opf_t opf, int nr, struct buffer_head *bhs[])
-{
-	const enum req_op op = opf & REQ_OP_MASK;
-	int i;
-
-	for (i = 0; i < nr; i++) {
-		struct buffer_head *bh = bhs[i];
-
-		if (!trylock_buffer(bh))
-			continue;
-		if (op == REQ_OP_WRITE) {
-			if (test_clear_buffer_dirty(bh)) {
-				bh->b_end_io = end_buffer_write_sync;
-				get_bh(bh);
-				submit_bh(opf, bh);
-				continue;
-			}
-		} else {
-			if (!buffer_uptodate(bh)) {
-				bh->b_end_io = end_buffer_read_sync;
-				get_bh(bh);
-				submit_bh(opf, bh);
-				continue;
-			}
-		}
-		unlock_buffer(bh);
-	}
-}
-EXPORT_SYMBOL(ll_rw_block);
-
 void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
 {
 	lock_buffer(bh);
@@ -3356,29 +3288,69 @@ int bh_uptodate_or_lock(struct buffer_head *bh)
 EXPORT_SYMBOL(bh_uptodate_or_lock);
 
 /**
- * bh_submit_read - Submit a locked buffer for reading
+ * __bh_read - Submit read for a locked buffer
  * @bh: struct buffer_head
+ * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ
+ * @wait: wait until reading finish
  *
- * Returns zero on success and -EIO on error.
+ * Returns zero on success or don't wait, and -EIO on error.
  */
-int bh_submit_read(struct buffer_head *bh)
+int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
 {
-	BUG_ON(!buffer_locked(bh));
+	int ret = 0;
 
-	if (buffer_uptodate(bh)) {
-		unlock_buffer(bh);
-		return 0;
-	}
+	BUG_ON(!buffer_locked(bh));
 
 	get_bh(bh);
 	bh->b_end_io = end_buffer_read_sync;
-	submit_bh(REQ_OP_READ, bh);
-	wait_on_buffer(bh);
-	if (buffer_uptodate(bh))
-		return 0;
-	return -EIO;
+	submit_bh(REQ_OP_READ | op_flags, bh);
+	if (wait) {
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh))
+			ret = -EIO;
+	}
+	return ret;
+}
+EXPORT_SYMBOL(__bh_read);
+
+/**
+ * __bh_read_batch - Submit read for a batch of unlocked buffers
+ * @nr: entry number of the buffer batch
+ * @bhs: a batch of struct buffer_head
+ * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ
+ * @force_lock: force to get a lock on the buffer if set, otherwise drops any
+ *              buffer that cannot lock.
+ *
+ * Returns zero on success or don't wait, and -EIO on error.
+ */
+void __bh_read_batch(int nr, struct buffer_head *bhs[],
+		     blk_opf_t op_flags, bool force_lock)
+{
+	int i;
+
+	for (i = 0; i < nr; i++) {
+		struct buffer_head *bh = bhs[i];
+
+		if (buffer_uptodate(bh))
+			continue;
+
+		if (force_lock)
+			lock_buffer(bh);
+		else
+			if (!trylock_buffer(bh))
+				continue;
+
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			continue;
+		}
+
+		bh->b_end_io = end_buffer_read_sync;
+		get_bh(bh);
+		submit_bh(REQ_OP_READ | op_flags, bh);
+	}
 }
-EXPORT_SYMBOL(bh_submit_read);
+EXPORT_SYMBOL(__bh_read_batch);
 
 void __init buffer_init(void)
 {

fs/ext2/balloc.c

@@ -128,6 +128,7 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 	struct ext2_group_desc * desc;
 	struct buffer_head * bh = NULL;
 	ext2_fsblk_t bitmap_blk;
+	int ret;
 
 	desc = ext2_get_group_desc(sb, block_group, NULL);
 	if (!desc)
@@ -141,10 +142,10 @@ read_block_bitmap(struct super_block *sb, unsigned int block_group)
 			    block_group, le32_to_cpu(desc->bg_block_bitmap));
 		return NULL;
 	}
-	if (likely(bh_uptodate_or_lock(bh)))
+	ret = bh_read(bh, 0);
+	if (ret > 0)
 		return bh;
-
-	if (bh_submit_read(bh) < 0) {
+	if (ret < 0) {
 		brelse(bh);
 		ext2_error(sb, __func__,
 			    "Cannot read block bitmap - "

fs/gfs2/meta_io.c

@@ -525,18 +525,15 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 
 	if (buffer_uptodate(first_bh))
 		goto out;
-	if (!buffer_locked(first_bh))
-		ll_rw_block(REQ_OP_READ | REQ_META | REQ_PRIO, 1, &first_bh);
+	bh_read_nowait(first_bh, REQ_META | REQ_PRIO);
 
 	dblock++;
 	extlen--;
 
 	while (extlen) {
 		bh = gfs2_getbuf(gl, dblock, CREATE);
 
-		if (!buffer_uptodate(bh) && !buffer_locked(bh))
-			ll_rw_block(REQ_OP_READ | REQ_RAHEAD | REQ_META |
-				    REQ_PRIO, 1, &bh);
+		bh_readahead(bh, REQ_RAHEAD | REQ_META | REQ_PRIO);
 		brelse(bh);
 		dblock++;
 		extlen--;

fs/gfs2/quota.c

@@ -733,12 +733,8 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
 		}
 		if (PageUptodate(page))
 			set_buffer_uptodate(bh);
-		if (!buffer_uptodate(bh)) {
-			ll_rw_block(REQ_OP_READ | REQ_META | REQ_PRIO, 1, &bh);
-			wait_on_buffer(bh);
-			if (!buffer_uptodate(bh))
-				goto unlock_out;
-		}
+		if (bh_read(bh, REQ_META | REQ_PRIO) < 0)
+			goto unlock_out;
 		if (gfs2_is_jdata(ip))
 			gfs2_trans_add_data(ip->i_gl, bh);
 		else

fs/isofs/compress.c

@@ -82,7 +82,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
 		return 0;
 	}
 	haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
-	ll_rw_block(REQ_OP_READ, haveblocks, bhs);
+	bh_read_batch(haveblocks, bhs);
 
 	curbh = 0;
 	curpage = 0;

fs/jbd2/journal.c

@@ -1897,19 +1897,16 @@ static int journal_get_superblock(journal_t *journal)
 {
 	struct buffer_head *bh;
 	journal_superblock_t *sb;
-	int err = -EIO;
+	int err;
 
 	bh = journal->j_sb_buffer;
 
 	J_ASSERT(bh != NULL);
-	if (!buffer_uptodate(bh)) {
-		ll_rw_block(REQ_OP_READ, 1, &bh);
-		wait_on_buffer(bh);
-		if (!buffer_uptodate(bh)) {
-			printk(KERN_ERR
-				"JBD2: IO error reading journal superblock\n");
-			goto out;
-		}
+	err = bh_read(bh, 0);
+	if (err < 0) {
+		printk(KERN_ERR
+			"JBD2: IO error reading journal superblock\n");
+		goto out;
 	}
 
 	if (buffer_verified(bh))

fs/jbd2/recovery.c

@@ -100,7 +100,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
 		if (!buffer_uptodate(bh) && !buffer_locked(bh)) {
 			bufs[nbufs++] = bh;
 			if (nbufs == MAXBUF) {
-				ll_rw_block(REQ_OP_READ, nbufs, bufs);
+				bh_readahead_batch(nbufs, bufs, 0);
 				journal_brelse_array(bufs, nbufs);
 				nbufs = 0;
 			}
@@ -109,7 +109,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
 	}
 
 	if (nbufs)
-		ll_rw_block(REQ_OP_READ, nbufs, bufs);
+		bh_readahead_batch(nbufs, bufs, 0);
 	err = 0;
 
 failed:
@@ -152,9 +152,14 @@ static int jread(struct buffer_head **bhp, journal_t *journal,
 		return -ENOMEM;
 
 	if (!buffer_uptodate(bh)) {
-		/* If this is a brand new buffer, start readahead.
-                   Otherwise, we assume we are already reading it.  */
-		if (!buffer_req(bh))
+		/*
+		 * If this is a brand new buffer, start readahead.
+		 * Otherwise, we assume we are already reading it.
+		 */
+		bool need_readahead = !buffer_req(bh);
+
+		bh_read_nowait(bh, 0);
+		if (need_readahead)
 			do_readahead(journal, offset);
 		wait_on_buffer(bh);
 	}
@@ -688,7 +693,6 @@ static int do_one_pass(journal_t *journal,
 					mark_buffer_dirty(nbh);
 					BUFFER_TRACE(nbh, "marking uptodate");
 					++info->nr_replays;
-					/* ll_rw_block(WRITE, 1, &nbh); */
 					unlock_buffer(nbh);
 					brelse(obh);
 					brelse(nbh);

fs/udf/dir.c

@@ -114,7 +114,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 					brelse(tmp);
 			}
 			if (num) {
-				ll_rw_block(REQ_OP_READ | REQ_RAHEAD, num, bha);
+				bh_readahead_batch(num, bha, REQ_RAHEAD);
 				for (i = 0; i < num; i++)
 					brelse(bha[i]);
 			}

fs/udf/directory.c

@@ -89,7 +89,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
 					brelse(tmp);
 			}
 			if (num) {
-				ll_rw_block(REQ_OP_READ | REQ_RAHEAD, num, bha);
+				bh_readahead_batch(num, bha, REQ_RAHEAD);
 				for (i = 0; i < num; i++)
 					brelse(bha[i]);
 			}