btrfs: use precalculated sectorsize_bits from fs_info

We do a lot of calculations where we divide or multiply by sectorsize.
We also know and make sure that sectorsize is a power of two, so this
means all divisions can be turned to shifts and avoid eg. expensive
u64/u32 divisions.

The type is u32 as it's more register friendly on x86_64 compared to u8
and the resulting assembly is smaller (movzbl vs movl).

There's also superblock s_blocksize_bits but it's usually one more
pointer dereference farther than fs_info.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

8 files changed, 17 insertions, 13 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b1b6d9a69b99..2bfad194bf06 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -935,6 +935,8 @@ struct btrfs_fs_info {
 	/* Cached block sizes */
 	u32 nodesize;
 	u32 sectorsize;
+	/* ilog2 of sectorsize, use to avoid 64bit division */
+	u32 sectorsize_bits;
 	u32 stripesize;
 
 	/* Block groups and devices containing active swapfiles. */
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index ad526aa5312a..25889a2362e2 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2814,6 +2814,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	/* Usable values until the real ones are cached from the superblock */
 	fs_info->nodesize = 4096;
 	fs_info->sectorsize = 4096;
+	fs_info->sectorsize_bits = ilog2(4096);
 	fs_info->stripesize = 4096;
 
 	spin_lock_init(&fs_info->swapfile_pins_lock);
@@ -3078,6 +3079,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	/* Cache block sizes */
 	fs_info->nodesize = nodesize;
 	fs_info->sectorsize = sectorsize;
+	fs_info->sectorsize_bits = ilog2(sectorsize);
 	fs_info->stripesize = stripesize;
 
 	/*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bac1eb17e498..14d5aaa28399 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2145,7 +2145,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes)
 	csum_size = BTRFS_MAX_ITEM_SIZE(fs_info);
 	num_csums_per_leaf = div64_u64(csum_size,
 			(u64)btrfs_super_csum_size(fs_info->super_copy));
-	num_csums = div64_u64(csum_bytes, fs_info->sectorsize);
+	num_csums = csum_bytes >> fs_info->sectorsize_bits;
 	num_csums += num_csums_per_leaf - 1;
 	num_csums = div64_u64(num_csums, num_csums_per_leaf);
 	return num_csums;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 816f57d52fc9..81a318a92418 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -369,7 +369,7 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 		 * a single leaf so it will also fit inside a u32
 		 */
 		diff = disk_bytenr - item_start_offset;
-		diff = diff / fs_info->sectorsize;
+		diff = diff >> fs_info->sectorsize_bits;
 		diff = diff * csum_size;
 		count = min_t(int, nblocks, (item_last_offset - disk_bytenr) >>
 					    inode->i_sb->s_blocksize_bits);
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 6b9faf3b0e96..84eb1a3ffaca 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -416,7 +416,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize);
+	nrbits = block_group->length >> block_group->fs_info->sectorsize_bits;
 	start_bit = find_next_bit_le(bitmap, nrbits, 0);
 
 	while (start_bit < nrbits) {
@@ -540,8 +540,8 @@ static void free_space_set_bits(struct btrfs_block_group *block_group,
 		end = found_end;
 
 	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
-	first = div_u64(*start - found_start, fs_info->sectorsize);
-	last = div_u64(end - found_start, fs_info->sectorsize);
+	first = (*start - found_start) >> fs_info->sectorsize_bits;
+	last = (end - found_start) >> fs_info->sectorsize_bits;
 	if (bit)
 		extent_buffer_bitmap_set(leaf, ptr, first, last - first);
 	else
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 87bac9ecdf4c..c6534daa40cd 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -868,7 +868,6 @@ int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset,
 	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
 	unsigned long num_sectors;
 	unsigned long i;
-	u32 sectorsize = btrfs_inode_sectorsize(inode);
 	const u8 blocksize_bits = inode->vfs_inode.i_sb->s_blocksize_bits;
 	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 	int index = 0;
@@ -890,7 +889,7 @@ int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset,
 			index += (int)num_sectors * csum_size;
 			if (index == len)
 				goto out;
-			disk_bytenr += num_sectors * sectorsize;
+			disk_bytenr += num_sectors * fs_info->sectorsize;
 		}
 	}
 out:
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 04351b55dd14..c307f25c4846 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2300,7 +2300,7 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 	u64 offset;
 	u64 nsectors64;
 	u32 nsectors;
-	int sectorsize = sparity->sctx->fs_info->sectorsize;
+	u32 sectorsize_bits = sparity->sctx->fs_info->sectorsize_bits;
 
 	if (len >= sparity->stripe_len) {
 		bitmap_set(bitmap, 0, sparity->nsectors);
@@ -2309,8 +2309,8 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 
 	start -= sparity->logic_start;
 	start = div64_u64_rem(start, sparity->stripe_len, &offset);
-	offset = div_u64(offset, sectorsize);
-	nsectors64 = div_u64(len, sectorsize);
+	offset = offset >> sectorsize_bits;
+	nsectors64 = len >> sectorsize_bits;
 
 	ASSERT(nsectors64 < UINT_MAX);
 	nsectors = (u32)nsectors64;
@@ -2386,10 +2386,10 @@ static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum)
 	if (!sum)
 		return 0;
 
-	index = div_u64(logical - sum->bytenr, sctx->fs_info->sectorsize);
+	index = (logical - sum->bytenr) >> sctx->fs_info->sectorsize_bits;
 	ASSERT(index < UINT_MAX);
 
-	num_sectors = sum->len / sctx->fs_info->sectorsize;
+	num_sectors = sum->len >> sctx->fs_info->sectorsize_bits;
 	memcpy(csum, sum->sums + index * sctx->csum_size, sctx->csum_size);
 	if (index == num_sectors - 1) {
 		list_del(&sum->list);
@@ -2776,7 +2776,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	int extent_mirror_num;
 	int stop_loop = 0;
 
-	nsectors = div_u64(map->stripe_len, fs_info->sectorsize);
+	nsectors = map->stripe_len >> fs_info->sectorsize_bits;
 	bitmap_len = scrub_calc_parity_bitmap_len(nsectors);
 	sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len,
 			  GFP_NOFS);
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 999c14e5d0bd..b36e88753f1f 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -134,6 +134,7 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
 
 	fs_info->nodesize = nodesize;
 	fs_info->sectorsize = sectorsize;
+	fs_info->sectorsize_bits = ilog2(sectorsize);
 	set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
 
 	test_mnt->mnt_sb->s_fs_info = fs_info;