btrfs: make btrfs_csum_one_bio() handle bs > ps without large folios

For bs > ps cases, all folios passed into btrfs_csum_one_bio() are
ensured to be backed by large folios.  But that requirement excludes
features like direct IO and encoded writes.

To support bs > ps without large folios, enhance btrfs_csum_one_bio()
by:

- Split btrfs_calculate_block_csum() into two versions
  * btrfs_calculate_block_csum_folio()
    For call sites where a fs block is always backed by a large folio.

    This will do extra checks on the folio size, build a paddrs[] array,
    and pass it into the newer btrfs_calculate_block_csum_pages()
    helper.

    For now btrfs_check_block_csum() is still using this version.

  * btrfs_calculate_block_csum_pages()
    For call sites that may hit a fs block backed by noncontiguous pages.
    The pages are represented by paddrs[] array, which includes the
    offset inside the page.

    This function will do the proper sub-block handling.

- Make btrfs_csum_one_bio() to use btrfs_calculate_block_csum_pages()
  This means we will need to build a local paddrs[] array, and after
  filling a fs block, do the checksum calculation.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

Author: adam900710

fs/btrfs/btrfs_inode.h

@@ -543,8 +543,10 @@ static inline void btrfs_set_inode_mapping_order(struct btrfs_inode *inode)
 #endif
 }
 
-void btrfs_calculate_block_csum(struct btrfs_fs_info *fs_info, phys_addr_t paddr,
-				u8 *dest);
+void btrfs_calculate_block_csum_folio(struct btrfs_fs_info *fs_info,
+				      const phys_addr_t paddr, u8 *dest);
+void btrfs_calculate_block_csum_pages(struct btrfs_fs_info *fs_info,
+				      const phys_addr_t paddrs[], u8 *dest);
 int btrfs_check_block_csum(struct btrfs_fs_info *fs_info, phys_addr_t paddr, u8 *csum,
 			   const u8 * const csum_expected);
 bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev,

fs/btrfs/file-item.c

@@ -775,13 +775,22 @@ static void csum_one_bio(struct btrfs_bio *bbio, struct bvec_iter *src)
 	struct bvec_iter iter = *src;
 	phys_addr_t paddr;
 	const u32 blocksize = fs_info->sectorsize;
+	const u32 step = min(blocksize, PAGE_SIZE);
+	const u32 nr_steps = blocksize / step;
+	phys_addr_t paddrs[BTRFS_MAX_BLOCKSIZE / PAGE_SIZE];
+	u32 offset = 0;
 	int index = 0;
 
 	shash->tfm = fs_info->csum_shash;
 
-	btrfs_bio_for_each_block(paddr, bio, &iter, blocksize) {
-		btrfs_calculate_block_csum(fs_info, paddr, sums->sums + index);
-		index += fs_info->csum_size;
+	btrfs_bio_for_each_block(paddr, bio, &iter, step) {
+		paddrs[(offset / step) % nr_steps] = paddr;
+		offset += step;
+
+		if (IS_ALIGNED(offset, blocksize)) {
+			btrfs_calculate_block_csum_pages(fs_info, paddrs, sums->sums + index);
+			index += fs_info->csum_size;
+		}
 	}
 }
 

fs/btrfs/inode.c

@@ -3343,36 +3343,67 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered)
 	return btrfs_finish_one_ordered(ordered);
 }
 
-void btrfs_calculate_block_csum(struct btrfs_fs_info *fs_info, phys_addr_t paddr,
-				u8 *dest)
+/*
+ * Calculate the checksum of an fs block at physical memory address @paddr,
+ * and save the result to @dest.
+ *
+ * The folio containing @paddr must be large enough to contain a full fs block.
+ */
+void btrfs_calculate_block_csum_folio(struct btrfs_fs_info *fs_info,
+				      const phys_addr_t paddr, u8 *dest)
 {
 	struct folio *folio = page_folio(phys_to_page(paddr));
 	const u32 blocksize = fs_info->sectorsize;
-	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
+	const u32 step = min(blocksize, PAGE_SIZE);
+	const u32 nr_steps = blocksize / step;
+	phys_addr_t paddrs[BTRFS_MAX_BLOCKSIZE / PAGE_SIZE];
 
-	shash->tfm = fs_info->csum_shash;
 	/* The full block must be inside the folio. */
 	ASSERT(offset_in_folio(folio, paddr) + blocksize <= folio_size(folio));
 
-	if (folio_test_partial_kmap(folio)) {
-		size_t cur = paddr;
+	for (int i = 0; i < nr_steps; i++) {
+		u32 pindex = offset_in_folio(folio, paddr + i * step) >> PAGE_SHIFT;
 
-		crypto_shash_init(shash);
-		while (cur < paddr + blocksize) {
-			void *kaddr;
-			size_t len = min(paddr + blocksize - cur,
-					 PAGE_SIZE - offset_in_page(cur));
+		/*
+		 * For bs <= ps cases, we will only run the loop once, so the offset
+		 * inside the page will only added to paddrs[0].
+		 *
+		 * For bs > ps cases, the block must be page aligned, thus offset
+		 * inside the page will always be 0.
+		 */
+		paddrs[i] = page_to_phys(folio_page(folio, pindex)) + offset_in_page(paddr);
+	}
+	return btrfs_calculate_block_csum_pages(fs_info, paddrs, dest);
+}
 
-			kaddr = kmap_local_folio(folio, offset_in_folio(folio, cur));
-			crypto_shash_update(shash, kaddr, len);
-			kunmap_local(kaddr);
-			cur += len;
-		}
-		crypto_shash_final(shash, dest);
-	} else {
-		crypto_shash_digest(shash, phys_to_virt(paddr), blocksize, dest);
+/*
+ * Calculate the checksum of a fs block backed by multiple noncontiguous pages
+ * at @paddrs[] and save the result to @dest.
+ *
+ * The folio containing @paddr must be large enough to contain a full fs block.
+ */
+void btrfs_calculate_block_csum_pages(struct btrfs_fs_info *fs_info,
+				      const phys_addr_t paddrs[], u8 *dest)
+{
+	const u32 blocksize = fs_info->sectorsize;
+	const u32 step = min(blocksize, PAGE_SIZE);
+	const u32 nr_steps = blocksize / step;
+	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
+
+	shash->tfm = fs_info->csum_shash;
+	crypto_shash_init(shash);
+	for (int i = 0; i < nr_steps; i++) {
+		const phys_addr_t paddr = paddrs[i];
+		void *kaddr;
+
+		ASSERT(offset_in_page(paddr) + step <= PAGE_SIZE);
+		kaddr = kmap_local_page(phys_to_page(paddr)) + offset_in_page(paddr);
+		crypto_shash_update(shash, kaddr, step);
+		kunmap_local(kaddr);
 	}
+	crypto_shash_final(shash, dest);
 }
+
 /*
  * Verify the checksum for a single sector without any extra action that depend
  * on the type of I/O.
@@ -3382,7 +3413,7 @@ void btrfs_calculate_block_csum(struct btrfs_fs_info *fs_info, phys_addr_t paddr
 int btrfs_check_block_csum(struct btrfs_fs_info *fs_info, phys_addr_t paddr, u8 *csum,
 			   const u8 * const csum_expected)
 {
-	btrfs_calculate_block_csum(fs_info, paddr, csum);
+	btrfs_calculate_block_csum_folio(fs_info, paddr, csum);
 	if (unlikely(memcmp(csum, csum_expected, fs_info->csum_size) != 0))
 		return -EIO;
 	return 0;