1 files changed, 93 insertions, 59 deletions

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 0123d2728923..531312efee8d 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -261,7 +261,7 @@ static int init_scrub_stripe(struct btrfs_fs_info *fs_info,
 	atomic_set(&stripe->pending_io, 0);
 	spin_lock_init(&stripe->write_error_lock);
 
-	ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages, 0);
+	ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages, false);
 	if (ret < 0)
 		goto error;
 
@@ -838,7 +838,7 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe,
 			     bbio->bio.bi_iter.bi_size >= blocksize)) {
 			ASSERT(bbio->bio.bi_iter.bi_size);
 			atomic_inc(&stripe->pending_io);
-			btrfs_submit_bio(bbio, mirror);
+			btrfs_submit_bbio(bbio, mirror);
 			if (wait)
 				wait_scrub_stripe_io(stripe);
 			bbio = NULL;
@@ -857,7 +857,7 @@ static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe,
 	if (bbio) {
 		ASSERT(bbio->bio.bi_iter.bi_size);
 		atomic_inc(&stripe->pending_io);
-		btrfs_submit_bio(bbio, mirror);
+		btrfs_submit_bbio(bbio, mirror);
 		if (wait)
 			wait_scrub_stripe_io(stripe);
 	}
@@ -1012,6 +1012,7 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work)
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	int num_copies = btrfs_num_copies(fs_info, stripe->bg->start,
 					  stripe->bg->length);
+	unsigned long repaired;
 	int mirror;
 	int i;
 
@@ -1078,16 +1079,15 @@ out:
 	 * Submit the repaired sectors.  For zoned case, we cannot do repair
 	 * in-place, but queue the bg to be relocated.
 	 */
-	if (btrfs_is_zoned(fs_info)) {
-		if (!bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors))
+	bitmap_andnot(&repaired, &stripe->init_error_bitmap, &stripe->error_bitmap,
+		      stripe->nr_sectors);
+	if (!sctx->readonly && !bitmap_empty(&repaired, stripe->nr_sectors)) {
+		if (btrfs_is_zoned(fs_info)) {
 			btrfs_repair_one_zone(fs_info, sctx->stripes[0].bg->start);
-	} else if (!sctx->readonly) {
-		unsigned long repaired;
-
-		bitmap_andnot(&repaired, &stripe->init_error_bitmap,
-			      &stripe->error_bitmap, stripe->nr_sectors);
-		scrub_write_sectors(sctx, stripe, repaired, false);
-		wait_scrub_stripe_io(stripe);
+		} else {
+			scrub_write_sectors(sctx, stripe, repaired, false);
+			wait_scrub_stripe_io(stripe);
+		}
 	}
 
 	scrub_stripe_report_errors(sctx, stripe);
@@ -1390,8 +1390,15 @@ static int find_first_extent_item(struct btrfs_root *extent_root,
 	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
+	if (ret == 0) {
+		/*
+		 * Key with offset -1 found, there would have to exist an extent
+		 * item with such offset, but this is out of the valid range.
+		 */
+		btrfs_release_path(path);
+		return -EUCLEAN;
+	}
 
-	ASSERT(ret > 0);
 	/*
 	 * Here we intentionally pass 0 as @min_objectid, as there could be
 	 * an extent item starting before @search_start.
@@ -1534,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
 	u64 extent_gen;
 	int ret;
 
+	if (unlikely(!extent_root)) {
+		btrfs_err(fs_info, "no valid extent root for scrub");
+		return -EUCLEAN;
+	}
 	memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) *
 				   stripe->nr_sectors);
 	scrub_stripe_reset_bitmaps(stripe);
@@ -1641,14 +1652,19 @@ static void scrub_reset_stripe(struct scrub_stripe *stripe)
 	}
 }
 
-static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
-					    struct scrub_stripe *stripe)
+static u32 stripe_length(const struct scrub_stripe *stripe)
+{
+	ASSERT(stripe->bg);
+
+	return min(BTRFS_STRIPE_LEN,
+		   stripe->bg->start + stripe->bg->length - stripe->logical);
+}
+
+static void scrub_submit_extent_sector_read(struct scrub_stripe *stripe)
 {
 	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
 	struct btrfs_bio *bbio = NULL;
-	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
-				      stripe->bg->length - stripe->logical) >>
-				  fs_info->sectorsize_bits;
+	unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
 	u64 stripe_len = BTRFS_STRIPE_LEN;
 	int mirror = stripe->mirror_num;
 	int i;
@@ -1670,7 +1686,7 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 		     bbio->bio.bi_iter.bi_size >= stripe_len)) {
 			ASSERT(bbio->bio.bi_iter.bi_size);
 			atomic_inc(&stripe->pending_io);
-			btrfs_submit_bio(bbio, mirror);
+			btrfs_submit_bbio(bbio, mirror);
 			bbio = NULL;
 		}
 
@@ -1681,20 +1697,34 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 					    (i << fs_info->sectorsize_bits);
 			int err;
 
-			bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
-					       fs_info, scrub_read_endio, stripe);
-			bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT;
-
-			io_stripe.is_scrub = true;
+			io_stripe.rst_search_commit_root = true;
+			stripe_len = (nr_sectors - i) << fs_info->sectorsize_bits;
+			/*
+			 * For RST cases, we need to manually split the bbio to
+			 * follow the RST boundary.
+			 */
 			err = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
-					      &stripe_len, &bioc, &io_stripe,
-					      &mirror);
+					      &stripe_len, &bioc, &io_stripe, &mirror);
 			btrfs_put_bioc(bioc);
-			if (err) {
-				btrfs_bio_end_io(bbio,
-						 errno_to_blk_status(err));
-				return;
+			if (err < 0) {
+				if (err != -ENODATA) {
+					/*
+					 * Earlier btrfs_get_raid_extent_offset()
+					 * returned -ENODATA, which means there's
+					 * no entry for the corresponding range
+					 * in the stripe tree.  But if it's in
+					 * the extent tree, then it's a preallocated
+					 * extent and not an error.
+					 */
+					set_bit(i, &stripe->io_error_bitmap);
+					set_bit(i, &stripe->error_bitmap);
+				}
+				continue;
 			}
+
+			bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
+					       fs_info, scrub_read_endio, stripe);
+			bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT;
 		}
 
 		__bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
@@ -1703,7 +1733,7 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 	if (bbio) {
 		ASSERT(bbio->bio.bi_iter.bi_size);
 		atomic_inc(&stripe->pending_io);
-		btrfs_submit_bio(bbio, mirror);
+		btrfs_submit_bbio(bbio, mirror);
 	}
 
 	if (atomic_dec_and_test(&stripe->pending_io)) {
@@ -1718,9 +1748,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct btrfs_bio *bbio;
-	unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
-				      stripe->bg->length - stripe->logical) >>
-				  fs_info->sectorsize_bits;
+	unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
 	int mirror = stripe->mirror_num;
 
 	ASSERT(stripe->bg);
@@ -1728,7 +1756,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 	ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state));
 
 	if (btrfs_need_stripe_tree_update(fs_info, stripe->bg->flags)) {
-		scrub_submit_extent_sector_read(sctx, stripe);
+		scrub_submit_extent_sector_read(stripe);
 		return;
 	}
 
@@ -1761,7 +1789,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 
 		mirror = calc_next_mirror(mirror, num_copies);
 	}
-	btrfs_submit_bio(bbio, mirror);
+	btrfs_submit_bbio(bbio, mirror);
 }
 
 static bool stripe_has_metadata_error(struct scrub_stripe *stripe)
@@ -1860,6 +1888,9 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)
 		stripe = &sctx->stripes[i];
 
 		wait_scrub_stripe_io(stripe);
+		spin_lock(&sctx->stat_lock);
+		sctx->stat.last_physical = stripe->physical + stripe_length(stripe);
+		spin_unlock(&sctx->stat_lock);
 		scrub_reset_stripe(stripe);
 	}
 out:
@@ -1936,7 +1967,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 	ASSERT(sctx->raid56_data_stripes);
 
 	/*
-	 * For data stripe search, we cannot re-use the same extent/csum paths,
+	 * For data stripe search, we cannot reuse the same extent/csum paths,
 	 * as the data stripe bytenr may be smaller than previous extent.  Thus
 	 * we have to use our own extent/csum paths.
 	 */
@@ -2085,7 +2116,6 @@ out:
  */
 static int scrub_simple_mirror(struct scrub_ctx *sctx,
 			       struct btrfs_block_group *bg,
-			       struct btrfs_chunk_map *map,
 			       u64 logical_start, u64 logical_length,
 			       struct btrfs_device *device,
 			       u64 physical, int mirror_num)
@@ -2093,7 +2123,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	const u64 logical_end = logical_start + logical_length;
 	u64 cur_logical = logical_start;
-	int ret;
+	int ret = 0;
 
 	/* The range must be inside the bg */
 	ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length);
@@ -2128,7 +2158,9 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
 					 cur_physical, &found_logical);
 		if (ret > 0) {
 			/* No more extent, just update the accounting */
+			spin_lock(&sctx->stat_lock);
 			sctx->stat.last_physical = physical + logical_length;
+			spin_unlock(&sctx->stat_lock);
 			ret = 0;
 			break;
 		}
@@ -2202,7 +2234,7 @@ static int scrub_simple_stripe(struct scrub_ctx *sctx,
 		 * just RAID1, so we can reuse scrub_simple_mirror() to scrub
 		 * this stripe.
 		 */
-		ret = scrub_simple_mirror(sctx, bg, map, cur_logical,
+		ret = scrub_simple_mirror(sctx, bg, cur_logical,
 					  BTRFS_STRIPE_LEN, device, cur_physical,
 					  mirror_num);
 		if (ret)
@@ -2236,7 +2268,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	/* Offset inside the chunk */
 	u64 offset;
 	u64 stripe_logical;
-	int stop_loop = 0;
 
 	/* Extent_path should be released by now. */
 	ASSERT(sctx->extent_path.nodes[0] == NULL);
@@ -2287,7 +2318,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 		 * Only @physical and @mirror_num needs to calculated using
 		 * @stripe_index.
 		 */
-		ret = scrub_simple_mirror(sctx, bg, map, bg->start, bg->length,
+		ret = scrub_simple_mirror(sctx, bg, bg->start, bg->length,
 				scrub_dev, map->stripes[stripe_index].physical,
 				stripe_index + 1);
 		offset = 0;
@@ -2325,6 +2356,10 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 			stripe_logical += chunk_logical;
 			ret = scrub_raid56_parity_stripe(sctx, scrub_dev, bg,
 							 map, stripe_logical);
+			spin_lock(&sctx->stat_lock);
+			sctx->stat.last_physical = min(physical + BTRFS_STRIPE_LEN,
+						       physical_end);
+			spin_unlock(&sctx->stat_lock);
 			if (ret)
 				goto out;
 			goto next;
@@ -2338,7 +2373,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 		 * We can reuse scrub_simple_mirror() here, as the repair part
 		 * is still based on @mirror_num.
 		 */
-		ret = scrub_simple_mirror(sctx, bg, map, logical, BTRFS_STRIPE_LEN,
+		ret = scrub_simple_mirror(sctx, bg, logical, BTRFS_STRIPE_LEN,
 					  scrub_dev, physical, 1);
 		if (ret < 0)
 			goto out;
@@ -2346,14 +2381,8 @@ next:
 		logical += increment;
 		physical += BTRFS_STRIPE_LEN;
 		spin_lock(&sctx->stat_lock);
-		if (stop_loop)
-			sctx->stat.last_physical =
-				map->stripes[stripe_index].physical + dev_stripe_len;
-		else
-			sctx->stat.last_physical = physical;
+		sctx->stat.last_physical = physical;
 		spin_unlock(&sctx->stat_lock);
-		if (stop_loop)
-			break;
 	}
 out:
 	ret2 = flush_scrub_stripes(sctx);
@@ -2430,19 +2459,15 @@ static int finish_extent_writes_for_zoned(struct btrfs_root *root,
 					  struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct btrfs_trans_handle *trans;
 
 	if (!btrfs_is_zoned(fs_info))
 		return 0;
 
 	btrfs_wait_block_group_reservations(cache);
 	btrfs_wait_nocow_writers(cache);
-	btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start, cache->length);
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, cache);
 
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-	return btrfs_commit_transaction(trans);
+	return btrfs_commit_current_transaction(root);
 }
 
 static noinline_for_stack
@@ -2673,8 +2698,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 */
 		if (sctx->is_dev_replace) {
 			btrfs_wait_nocow_writers(cache);
-			btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start,
-					cache->length);
+			btrfs_wait_ordered_roots(fs_info, U64_MAX, cache);
 		}
 
 		scrub_pause_off(fs_info);
@@ -2805,7 +2829,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
 		gen = btrfs_get_last_trans_committed(fs_info);
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
-		bytenr = btrfs_sb_offset(i);
+		ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr);
+		if (ret == -ENOENT)
+			break;
+
+		if (ret) {
+			spin_lock(&sctx->stat_lock);
+			sctx->stat.super_errors++;
+			spin_unlock(&sctx->stat_lock);
+			continue;
+		}
+
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >
 		    scrub_dev->commit_total_bytes)
 			break;