1 files changed, 55 insertions, 40 deletions

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6776e6ab8d10..4691d0bdb2e8 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -113,7 +113,7 @@ enum {
 	/* Which blocks are covered by extent items. */
 	scrub_bitmap_nr_has_extent = 0,
 
-	/* Which blocks are meteadata. */
+	/* Which blocks are metadata. */
 	scrub_bitmap_nr_is_metadata,
 
 	/*
@@ -130,7 +130,7 @@ enum {
 	scrub_bitmap_nr_last,
 };
 
-#define SCRUB_STRIPE_PAGES		(BTRFS_STRIPE_LEN / PAGE_SIZE)
+#define SCRUB_STRIPE_MAX_FOLIOS		(BTRFS_STRIPE_LEN / PAGE_SIZE)
 
 /*
  * Represent one contiguous range with a length of BTRFS_STRIPE_LEN.
@@ -139,7 +139,7 @@ struct scrub_stripe {
 	struct scrub_ctx *sctx;
 	struct btrfs_block_group *bg;
 
-	struct page *pages[SCRUB_STRIPE_PAGES];
+	struct folio *folios[SCRUB_STRIPE_MAX_FOLIOS];
 	struct scrub_sector_verification *sectors;
 
 	struct btrfs_device *dev;
@@ -206,7 +206,7 @@ struct scrub_ctx {
 	ktime_t			throttle_deadline;
 	u64			throttle_sent;
 
-	int			is_dev_replace;
+	bool			is_dev_replace;
 	u64			write_pointer;
 
 	struct mutex            wr_lock;
@@ -339,10 +339,10 @@ static void release_scrub_stripe(struct scrub_stripe *stripe)
 	if (!stripe)
 		return;
 
-	for (int i = 0; i < SCRUB_STRIPE_PAGES; i++) {
-		if (stripe->pages[i])
-			__free_page(stripe->pages[i]);
-		stripe->pages[i] = NULL;
+	for (int i = 0; i < SCRUB_STRIPE_MAX_FOLIOS; i++) {
+		if (stripe->folios[i])
+			folio_put(stripe->folios[i]);
+		stripe->folios[i] = NULL;
 	}
 	kfree(stripe->sectors);
 	kfree(stripe->csums);
@@ -355,6 +355,7 @@ static void release_scrub_stripe(struct scrub_stripe *stripe)
 static int init_scrub_stripe(struct btrfs_fs_info *fs_info,
 			     struct scrub_stripe *stripe)
 {
+	const u32 min_folio_shift = PAGE_SHIFT + fs_info->block_min_order;
 	int ret;
 
 	memset(stripe, 0, sizeof(*stripe));
@@ -367,7 +368,9 @@ 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, false);
+	ASSERT(BTRFS_STRIPE_LEN >> min_folio_shift <= SCRUB_STRIPE_MAX_FOLIOS);
+	ret = btrfs_alloc_folio_array(BTRFS_STRIPE_LEN >> min_folio_shift,
+				      fs_info->block_min_order, stripe->folios);
 	if (ret < 0)
 		goto error;
 
@@ -446,7 +449,7 @@ static void scrub_put_ctx(struct scrub_ctx *sctx)
 }
 
 static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
-		struct btrfs_fs_info *fs_info, int is_dev_replace)
+		struct btrfs_fs_info *fs_info, bool is_dev_replace)
 {
 	struct scrub_ctx *sctx;
 	int		i;
@@ -585,7 +588,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
 				       bool is_super, u64 logical, u64 physical)
 {
 	struct btrfs_fs_info *fs_info = dev->fs_info;
-	struct btrfs_path *path;
+	BTRFS_PATH_AUTO_FREE(path);
 	struct btrfs_key found_key;
 	struct extent_buffer *eb;
 	struct btrfs_extent_item *ei;
@@ -612,7 +615,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
 	ret = extent_from_logical(fs_info, swarn.logical, path, &found_key,
 				  &flags);
 	if (ret < 0)
-		goto out;
+		return;
 
 	swarn.extent_item_size = found_key.offset;
 
@@ -658,9 +661,6 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
 
 		iterate_extent_inodes(&ctx, true, scrub_print_warning_inode, &swarn);
 	}
-
-out:
-	btrfs_free_path(path);
 }
 
 static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical)
@@ -687,13 +687,30 @@ static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical)
 
 static void *scrub_stripe_get_kaddr(struct scrub_stripe *stripe, int sector_nr)
 {
-	u32 offset = (sector_nr << stripe->bg->fs_info->sectorsize_bits);
-	const struct page *page = stripe->pages[offset >> PAGE_SHIFT];
+	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
+	const u32 min_folio_shift = PAGE_SHIFT + fs_info->block_min_order;
+	u32 offset = (sector_nr << fs_info->sectorsize_bits);
+	const struct folio *folio = stripe->folios[offset >> min_folio_shift];
 
-	/* stripe->pages[] is allocated by us and no highmem is allowed. */
-	ASSERT(page);
-	ASSERT(!PageHighMem(page));
-	return page_address(page) + offset_in_page(offset);
+	/* stripe->folios[] is allocated by us and no highmem is allowed. */
+	ASSERT(folio);
+	ASSERT(!folio_test_partial_kmap(folio));
+	return folio_address(folio) + offset_in_folio(folio, offset);
+}
+
+static phys_addr_t scrub_stripe_get_paddr(struct scrub_stripe *stripe, int sector_nr)
+{
+	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
+	const u32 min_folio_shift = PAGE_SHIFT + fs_info->block_min_order;
+	u32 offset = (sector_nr << fs_info->sectorsize_bits);
+	const struct folio *folio = stripe->folios[offset >> min_folio_shift];
+
+	/* stripe->folios[] is allocated by us and no highmem is allowed. */
+	ASSERT(folio);
+	ASSERT(!folio_test_partial_kmap(folio));
+	/* And the range must be contained inside the folio. */
+	ASSERT(offset_in_folio(folio, offset) + fs_info->sectorsize <= folio_size(folio));
+	return page_to_phys(folio_page(folio, 0)) + offset_in_folio(folio, offset);
 }
 
 static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr)
@@ -788,7 +805,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
 	struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
 	struct scrub_sector_verification *sector = &stripe->sectors[sector_nr];
 	const u32 sectors_per_tree = fs_info->nodesize >> fs_info->sectorsize_bits;
-	void *kaddr = scrub_stripe_get_kaddr(stripe, sector_nr);
+	phys_addr_t paddr = scrub_stripe_get_paddr(stripe, sector_nr);
 	u8 csum_buf[BTRFS_CSUM_SIZE];
 	int ret;
 
@@ -833,7 +850,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
 		return;
 	}
 
-	ret = btrfs_check_sector_csum(fs_info, kaddr, csum_buf, sector->csum);
+	ret = btrfs_check_block_csum(fs_info, paddr, csum_buf, sector->csum);
 	if (ret < 0) {
 		scrub_bitmap_set_bit_csum_error(stripe, sector_nr);
 		scrub_bitmap_set_bit_error(stripe, sector_nr);
@@ -1369,8 +1386,7 @@ static void scrub_throttle_dev_io(struct scrub_ctx *sctx, struct btrfs_device *d
 	 * Slice is divided into intervals when the IO is submitted, adjust by
 	 * bwlimit and maximum of 64 intervals.
 	 */
-	div = max_t(u32, 1, (u32)(bwlimit / (16 * 1024 * 1024)));
-	div = min_t(u32, 64, div);
+	div = clamp(bwlimit / (16 * 1024 * 1024), 1, 64);
 
 	/* Start new epoch, set deadline */
 	now = ktime_get();
@@ -1513,7 +1529,7 @@ 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) {
+	if (unlikely(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.
@@ -1859,6 +1875,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct btrfs_bio *bbio;
+	const u32 min_folio_shift = PAGE_SHIFT + fs_info->block_min_order;
 	unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
 	int mirror = stripe->mirror_num;
 
@@ -1871,7 +1888,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
 		return;
 	}
 
-	bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
+	bbio = btrfs_bio_alloc(BTRFS_STRIPE_LEN >> min_folio_shift, REQ_OP_READ, fs_info,
 			       scrub_read_endio, stripe);
 
 	bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT;
@@ -1970,7 +1987,7 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)
 		 * metadata, we should immediately abort.
 		 */
 		for (int i = 0; i < nr_stripes; i++) {
-			if (stripe_has_metadata_error(&sctx->stripes[i])) {
+			if (unlikely(stripe_has_metadata_error(&sctx->stripes[i]))) {
 				ret = -EIO;
 				goto out;
 			}
@@ -2164,7 +2181,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 		 * As we may hit an empty data stripe while it's missing.
 		 */
 		bitmap_and(&error, &error, &has_extent, stripe->nr_sectors);
-		if (!bitmap_empty(&error, stripe->nr_sectors)) {
+		if (unlikely(!bitmap_empty(&error, stripe->nr_sectors))) {
 			btrfs_err(fs_info,
 "scrub: unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl",
 				  full_stripe_start, i, stripe->nr_sectors,
@@ -2202,7 +2219,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 	for (int i = 0; i < data_stripes; i++) {
 		stripe = &sctx->raid56_data_stripes[i];
 
-		raid56_parity_cache_data_pages(rbio, stripe->pages,
+		raid56_parity_cache_data_folios(rbio, stripe->folios,
 				full_stripe_start + (i << BTRFS_STRIPE_LEN_SHIFT));
 	}
 	raid56_parity_submit_scrub_rbio(rbio);
@@ -2586,7 +2603,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			   struct btrfs_device *scrub_dev, u64 start, u64 end)
 {
 	struct btrfs_dev_extent *dev_extent = NULL;
-	struct btrfs_path *path;
+	BTRFS_PATH_AUTO_FREE(path);
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct btrfs_root *root = fs_info->dev_root;
 	u64 chunk_offset;
@@ -2858,8 +2875,8 @@ skip_unfreeze:
 		btrfs_put_block_group(cache);
 		if (ret)
 			break;
-		if (sctx->is_dev_replace &&
-		    atomic64_read(&dev_replace->num_write_errors) > 0) {
+		if (unlikely(sctx->is_dev_replace &&
+			     atomic64_read(&dev_replace->num_write_errors) > 0)) {
 			ret = -EIO;
 			break;
 		}
@@ -2872,8 +2889,6 @@ skip:
 		btrfs_release_path(path);
 	}
 
-	btrfs_free_path(path);
-
 	return ret;
 }
 
@@ -2889,13 +2904,13 @@ static int scrub_one_super(struct scrub_ctx *sctx, struct btrfs_device *dev,
 	if (ret < 0)
 		return ret;
 	ret = btrfs_check_super_csum(fs_info, sb);
-	if (ret != 0) {
+	if (unlikely(ret != 0)) {
 		btrfs_err_rl(fs_info,
 		  "scrub: super block at physical %llu devid %llu has bad csum",
 			physical, dev->devid);
 		return -EIO;
 	}
-	if (btrfs_super_generation(sb) != generation) {
+	if (unlikely(btrfs_super_generation(sb) != generation)) {
 		btrfs_err_rl(fs_info,
 "scrub: super block at physical %llu devid %llu has bad generation %llu expect %llu",
 			     physical, dev->devid,
@@ -3013,7 +3028,7 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info)
 
 int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		    u64 end, struct btrfs_scrub_progress *progress,
-		    int readonly, int is_dev_replace)
+		    bool readonly, bool is_dev_replace)
 {
 	struct btrfs_dev_lookup_args args = { .devid = devid };
 	struct scrub_ctx *sctx;
@@ -3065,8 +3080,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	}
 
 	mutex_lock(&fs_info->scrub_lock);
-	if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
-	    test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &dev->dev_state)) {
+	if (unlikely(!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
+		     test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &dev->dev_state))) {
 		mutex_unlock(&fs_info->scrub_lock);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		ret = -EIO;