btrfs: reduce div64 calls by limiting the number of stripes of a chunk to u32

There are quite some div64 calls inside btrfs_map_block() and its
variants.

Such calls are for @stripe_nr, where @stripe_nr is the number of
stripes before our logical bytenr inside a chunk.

However we can eliminate such div64 calls by just reducing the width of
@stripe_nr from 64 to 32.

This can be done because our chunk size limit is already 10G, with fixed
stripe length 64K.
Thus a U32 is definitely enough to contain the number of stripes.

With such width reduction, we can get rid of slower div64, and extra
warning for certain 32bit arch.

This patch would do:

- Add a new tree-checker chunk validation on chunk length
  Make sure no chunk can reach 256G, which can also act as a bitflip
  checker.

- Reduce the width from u64 to u32 for @stripe_nr variables

- Replace unnecessary div64 calls with regular modulo and division
  32bit division and modulo are much faster than 64bit operations, and
  we are finally free of the div64 fear at least in those involved
  functions.

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

1 files changed, 36 insertions, 29 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d2b8b8a8bd89..9f80ff74101f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5970,15 +5970,15 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 	struct btrfs_discard_stripe *stripes;
 	u64 length = *length_ret;
 	u64 offset;
-	u64 stripe_nr;
-	u64 stripe_nr_end;
+	u32 stripe_nr;
+	u32 stripe_nr_end;
+	u32 stripe_cnt;
 	u64 stripe_end_offset;
-	u64 stripe_cnt;
 	u64 stripe_offset;
 	u32 stripe_index;
 	u32 factor = 0;
 	u32 sub_stripes = 0;
-	u64 stripes_per_dev = 0;
+	u32 stripes_per_dev = 0;
 	u32 remaining_stripes = 0;
 	u32 last_stripe = 0;
 	int ret;
@@ -6031,18 +6031,19 @@ struct btrfs_discard_stripe *btrfs_map_discard(struct btrfs_fs_info *fs_info,
 		factor = map->num_stripes / sub_stripes;
 		*num_stripes = min_t(u64, map->num_stripes,
 				    sub_stripes * stripe_cnt);
-		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
+		stripe_index = stripe_nr % factor;
+		stripe_nr /= factor;
 		stripe_index *= sub_stripes;
-		stripes_per_dev = div_u64_rem(stripe_cnt, factor,
-					      &remaining_stripes);
-		div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
-		last_stripe *= sub_stripes;
+
+		remaining_stripes = stripe_cnt % factor;
+		stripes_per_dev = stripe_cnt / factor;
+		last_stripe = ((stripe_nr_end - 1) % factor) * sub_stripes;
 	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID1_MASK |
 				BTRFS_BLOCK_GROUP_DUP)) {
 		*num_stripes = map->num_stripes;
 	} else {
-		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
-					&stripe_index);
+		stripe_index = stripe_nr % map->num_stripes;
+		stripe_nr /= map->num_stripes;
 	}
 
 	stripes = kcalloc(*num_stripes, sizeof(*stripes), GFP_NOFS);
@@ -6298,7 +6299,7 @@ static bool need_full_stripe(enum btrfs_map_op op)
 }
 
 static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
-			    u64 offset, u64 *stripe_nr, u64 *stripe_offset,
+			    u64 offset, u32 *stripe_nr, u64 *stripe_offset,
 			    u64 *full_stripe_start)
 {
 	ASSERT(op != BTRFS_MAP_DISCARD);
@@ -6346,7 +6347,7 @@ static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
 }
 
 static void set_io_stripe(struct btrfs_io_stripe *dst, const struct map_lookup *map,
-		          u32 stripe_index, u64 stripe_offset, u64 stripe_nr)
+			  u32 stripe_index, u64 stripe_offset, u32 stripe_nr)
 {
 	dst->dev = map->stripes[stripe_index].dev;
 	dst->physical = map->stripes[stripe_index].physical +
@@ -6363,7 +6364,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	struct map_lookup *map;
 	u64 map_offset;
 	u64 stripe_offset;
-	u64 stripe_nr;
+	u32 stripe_nr;
 	u32 stripe_index;
 	int data_stripes;
 	int i;
@@ -6422,8 +6423,8 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	num_stripes = 1;
 	stripe_index = 0;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
-		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
-				&stripe_index);
+		stripe_index = stripe_nr % map->num_stripes;
+		stripe_nr /= map->num_stripes;
 		if (!need_full_stripe(op))
 			mirror_num = 1;
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1_MASK) {
@@ -6449,8 +6450,8 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
 		u32 factor = map->num_stripes / map->sub_stripes;
 
-		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
-		stripe_index *= map->sub_stripes;
+		stripe_index = (stripe_nr % factor) * map->sub_stripes;
+		stripe_nr /= factor;
 
 		if (need_full_stripe(op))
 			num_stripes = map->sub_stripes;
@@ -6466,9 +6467,16 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		if (need_raid_map && (need_full_stripe(op) || mirror_num > 1)) {
-			/* push stripe_nr back to the start of the full stripe */
-			stripe_nr = div64_u64(raid56_full_stripe_start,
-					      data_stripes << BTRFS_STRIPE_LEN_SHIFT);
+			/*
+			 * Push stripe_nr back to the start of the full stripe
+			 * For those cases needing a full stripe, @stripe_nr
+			 * is the full stripe number.
+			 *
+			 * Originally we go raid56_full_stripe_start / full_stripe_len,
+			 * but that can be expensive.  Here we just divide
+			 * @stripe_nr with @data_stripes.
+			 */
+			stripe_nr /= data_stripes;
 
 			/* RAID[56] write or recovery. Return all stripes */
 			num_stripes = map->num_stripes;
@@ -6486,25 +6494,24 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 			 * Mirror #2 is RAID5 parity block.
 			 * Mirror #3 is RAID6 Q block.
 			 */
-			stripe_nr = div_u64_rem(stripe_nr,
-					data_stripes, &stripe_index);
+			stripe_index = stripe_nr % data_stripes;
+			stripe_nr /= data_stripes;
 			if (mirror_num > 1)
 				stripe_index = data_stripes + mirror_num - 2;
 
 			/* We distribute the parity blocks across stripes */
-			div_u64_rem(stripe_nr + stripe_index, map->num_stripes,
-					&stripe_index);
+			stripe_index = (stripe_nr + stripe_index) % map->num_stripes;
 			if (!need_full_stripe(op) && mirror_num <= 1)
 				mirror_num = 1;
 		}
 	} else {
 		/*
-		 * after this, stripe_nr is the number of stripes on this
+		 * After this, stripe_nr is the number of stripes on this
 		 * device we have to walk to find the data, and stripe_index is
 		 * the number of our device in the stripe array
 		 */
-		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
-				&stripe_index);
+		stripe_index = stripe_nr % map->num_stripes;
+		stripe_nr /= map->num_stripes;
 		mirror_num = stripe_index + 1;
 	}
 	if (stripe_index >= map->num_stripes) {
@@ -6566,7 +6573,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		unsigned rot;
 
 		/* Work out the disk rotation on this stripe-set */
-		div_u64_rem(stripe_nr, num_stripes, &rot);
+		rot = stripe_nr % num_stripes;
 
 		/* Fill in the logical address of each stripe */
 		tmp = stripe_nr * data_stripes;