btrfs: use bios instead of buffer_heads from super block writeout

Similar to the superblock read path, change the write path to using bios
and pages instead of buffer_heads. This allows us to skip over the
buffer_head code, for writing the superblock to disk.

This is based on a patch originally authored by Nikolay Borisov.
Co-developed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/disk-io.c

@@ -7,7 +7,6 @@
 #include <linux/blkdev.h>
 #include <linux/radix-tree.h>
 #include <linux/writeback.h>
-#include <linux/buffer_head.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
@@ -3395,25 +3394,34 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 }
 ALLOW_ERROR_INJECTION(open_ctree, ERRNO);
 
-static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
+static void btrfs_end_super_write(struct bio *bio)
 {
-	if (uptodate) {
-		set_buffer_uptodate(bh);
-	} else {
-		struct btrfs_device *device = (struct btrfs_device *)
-			bh->b_private;
+	struct btrfs_device *device = bio->bi_private;
+	struct bio_vec *bvec;
+	struct bvec_iter_all iter_all;
+	struct page *page;
 
+	bio_for_each_segment_all(bvec, bio, iter_all) {
+		page = bvec->bv_page;
+
+		if (bio->bi_status) {
 			btrfs_warn_rl_in_rcu(device->fs_info,
-				"lost page write due to IO error on %s",
-					  rcu_str_deref(device->name));
-		/* note, we don't set_buffer_write_io_error because we have
-		 * our own ways of dealing with the IO errors
-		 */
-		clear_buffer_uptodate(bh);
-		btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS);
+				"lost page write due to IO error on %s (%d)",
+				rcu_str_deref(device->name),
+				blk_status_to_errno(bio->bi_status));
+			ClearPageUptodate(page);
+			SetPageError(page);
+			btrfs_dev_stat_inc_and_print(device,
+						     BTRFS_DEV_STAT_WRITE_ERRS);
+		} else {
+			SetPageUptodate(page);
 		}
-	unlock_buffer(bh);
-	put_bh(bh);
+
+		put_page(page);
+		unlock_page(page);
+	}
+
+	bio_put(bio);
 }
 
 struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
@@ -3473,25 +3481,23 @@ struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev)
 
 /*
  * Write superblock @sb to the @device. Do not wait for completion, all the
- * buffer heads we write are pinned.
+ * pages we use for writing are locked.
  *
  * Write @max_mirrors copies of the superblock, where 0 means default that fit
  * the expected device size at commit time. Note that max_mirrors must be
  * same for write and wait phases.
  *
- * Return number of errors when buffer head is not found or submission fails.
+ * Return number of errors when page is not found or submission fails.
  */
 static int write_dev_supers(struct btrfs_device *device,
 			    struct btrfs_super_block *sb, int max_mirrors)
 {
 	struct btrfs_fs_info *fs_info = device->fs_info;
+	struct address_space *mapping = device->bdev->bd_inode->i_mapping;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
-	struct buffer_head *bh;
 	int i;
-	int ret;
 	int errors = 0;
 	u64 bytenr;
-	int op_flags;
 
 	if (max_mirrors == 0)
 		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
@@ -3499,6 +3505,10 @@ static int write_dev_supers(struct btrfs_device *device,
 	shash->tfm = fs_info->csum_shash;
 
 	for (i = 0; i < max_mirrors; i++) {
+		struct page *page;
+		struct bio *bio;
+		struct btrfs_super_block *disk_super;
+
 		bytenr = btrfs_sb_offset(i);
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
 		    device->commit_total_bytes)
@@ -3511,37 +3521,45 @@ static int write_dev_supers(struct btrfs_device *device,
 				    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
 		crypto_shash_final(shash, sb->csum);
 
-		/* One reference for us, and we leave it for the caller */
-		bh = __getblk(device->bdev, bytenr / BTRFS_BDEV_BLOCKSIZE,
-			      BTRFS_SUPER_INFO_SIZE);
-		if (!bh) {
+		page = find_or_create_page(mapping, bytenr >> PAGE_SHIFT,
+					   GFP_NOFS);
+		if (!page) {
 			btrfs_err(device->fs_info,
-			    "couldn't get super buffer head for bytenr %llu",
+			    "couldn't get super block page for bytenr %llu",
 			    bytenr);
 			errors++;
 			continue;
 		}
 
-		memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE);
+		/* Bump the refcount for wait_dev_supers() */
+		get_page(page);
 
-		/* one reference for submit_bh */
-		get_bh(bh);
+		disk_super = page_address(page);
+		memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE);
 
-		set_buffer_uptodate(bh);
-		lock_buffer(bh);
-		bh->b_end_io = btrfs_end_buffer_write_sync;
-		bh->b_private = device;
+		/*
+		 * Directly use bios here instead of relying on the page cache
+		 * to do I/O, so we don't lose the ability to do integrity
+		 * checking.
+		 */
+		bio = bio_alloc(GFP_NOFS, 1);
+		bio_set_dev(bio, device->bdev);
+		bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT;
+		bio->bi_private = device;
+		bio->bi_end_io = btrfs_end_super_write;
+		__bio_add_page(bio, page, BTRFS_SUPER_INFO_SIZE,
+			       offset_in_page(bytenr));
 
 		/*
-		 * we fua the first super.  The others we allow
-		 * to go down lazy.
+		 * We FUA only the first super block.  The others we allow to
+		 * go down lazy and there's a short window where the on-disk
+		 * copies might still contain the older version.
 		 */
-		op_flags = REQ_SYNC | REQ_META | REQ_PRIO;
+		bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO;
 		if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER))
-			op_flags |= REQ_FUA;
-		ret = btrfsic_submit_bh(REQ_OP_WRITE, op_flags, bh);
-		if (ret)
-			errors++;
+			bio->bi_opf |= REQ_FUA;
+
+		btrfsic_submit_bio(bio);
 	}
 	return errors < i ? 0 : -1;
 }
@@ -3550,12 +3568,11 @@ static int write_dev_supers(struct btrfs_device *device,
  * Wait for write completion of superblocks done by write_dev_supers,
  * @max_mirrors same for write and wait phases.
  *
- * Return number of errors when buffer head is not found or not marked up to
+ * Return number of errors when page is not found or not marked up to
  * date.
  */
 static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 {
-	struct buffer_head *bh;
 	int i;
 	int errors = 0;
 	bool primary_failed = false;
@@ -3565,32 +3582,34 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
 
 	for (i = 0; i < max_mirrors; i++) {
+		struct page *page;
+
 		bytenr = btrfs_sb_offset(i);
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
 		    device->commit_total_bytes)
 			break;
 
-		bh = __find_get_block(device->bdev,
-				      bytenr / BTRFS_BDEV_BLOCKSIZE,
-				      BTRFS_SUPER_INFO_SIZE);
-		if (!bh) {
+		page = find_get_page(device->bdev->bd_inode->i_mapping,
+				     bytenr >> PAGE_SHIFT);
+		if (!page) {
 			errors++;
 			if (i == 0)
 				primary_failed = true;
 			continue;
 		}
-		wait_on_buffer(bh);
-		if (!buffer_uptodate(bh)) {
+		/* Page is submitted locked and unlocked once the IO completes */
+		wait_on_page_locked(page);
+		if (PageError(page)) {
 			errors++;
 			if (i == 0)
 				primary_failed = true;
 		}
 
-		/* drop our reference */
-		brelse(bh);
+		/* Drop our reference */
+		put_page(page);
 
-		/* drop the reference from the writing run */
-		brelse(bh);
+		/* Drop the reference from the writing run */
+		put_page(page);
 	}
 
 	/* log error, force error return */