[PATCH 3/6] blk-merge: split bio by max_segment_size, not PAGE_SIZE

From: Hannes Reinecke <hare@kernel.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: Matthew Wilcox <willy@infradead.org>,
	Luis Chamberlain <mcgrof@kernel.org>,
	Pankaj Raghav <p.raghav@samsung.com>,
	linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
	Hannes Reinecke <hare@kernel.org>
Subject: [PATCH 3/6] blk-merge: split bio by max_segment_size, not PAGE_SIZE
Date: Tue, 14 May 2024 19:38:57 +0200	[thread overview]
Message-ID: <20240514173900.62207-4-hare@kernel.org> (raw)
In-Reply-To: <20240514173900.62207-1-hare@kernel.org>

Bvecs can be larger than a page, and the block layer handles
this just fine. So do not split by PAGE_SIZE but rather by
the max_segment_size if that happens to be larger.

Signed-off-by: Hannes Reinecke <hare@kernel.org>
---
 block/blk-merge.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4e3483a16b75..570573d7a34f 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -278,6 +278,7 @@ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned nsegs = 0, bytes = 0;
+	unsigned bv_seg_lim = max(PAGE_SIZE, lim->max_segment_size);
 
 	bio_for_each_bvec(bv, bio, iter) {
 		/*
@@ -289,7 +290,7 @@ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
 
 		if (nsegs < lim->max_segments &&
 		    bytes + bv.bv_len <= max_bytes &&
-		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+		    bv.bv_offset + bv.bv_len <= bv_seg_lim) {
 			nsegs++;
 			bytes += bv.bv_len;
 		} else {
-- 
2.35.3


