linux-kernel - [PATCH 2/7] md/raid5: make sure max_sectors is not less than io

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251121051406.1316884-4-yukuai@fnnas.com>
Date: Fri, 21 Nov 2025 13:14:01 +0800
From: Yu Kuai <yukuai@...as.com>
To: song@...nel.org,
	yukuai@...as.com
Cc: linux-raid@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linan122@...wei.com,
	xni@...hat.com
Subject: [PATCH 2/7] md/raid5: make sure max_sectors is not less than io_opt

Otherwise, even if user issue IO by io_opt, such IO will be split
by max_sectors before they are submitted to raid5. For consequence,
full stripe IO is impossible.

BTW, dm-raid5 is not affected and still have such problem.

Signed-off-by: Yu Kuai <yukuai@...as.com>
---
 drivers/md/raid5.c | 35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0ccb5907cd20..dc7bdbdb04b7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -773,14 +773,14 @@ struct stripe_request_ctx {
 	/* last sector in the request */
 	sector_t last_sector;
 
+	/* the request had REQ_PREFLUSH, cleared after the first stripe_head */
+	bool do_flush;
+
 	/*
 	 * bitmap to track stripe sectors that have been added to stripes
 	 * add one to account for unaligned requests
 	 */
-	DECLARE_BITMAP(sectors_to_do, RAID5_MAX_REQ_STRIPES + 1);
-
-	/* the request had REQ_PREFLUSH, cleared after the first stripe_head */
-	bool do_flush;
+	unsigned long sectors_to_do[];
 };
 
 /*
@@ -7732,6 +7732,24 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
 	return 0;
 }
 
+static int raid5_create_ctx_pool(struct r5conf *conf)
+{
+	struct stripe_request_ctx *ctx;
+	int size;
+
+	if (mddev_is_dm(conf->mddev))
+		size = BITS_TO_LONGS(RAID5_MAX_REQ_STRIPES);
+	else
+		size = BITS_TO_LONGS(
+			queue_max_hw_sectors(conf->mddev->gendisk->queue) >>
+			RAID5_STRIPE_SHIFT(conf));
+
+	conf->ctx_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS,
+				struct_size(ctx, sectors_to_do, size));
+
+	return conf->ctx_pool ? 0 : -ENOMEM;
+}
+
 static int raid5_set_limits(struct mddev *mddev)
 {
 	struct r5conf *conf = mddev->private;
@@ -7788,6 +7806,8 @@ static int raid5_set_limits(struct mddev *mddev)
 	 * Limit the max sectors based on this.
 	 */
 	lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+	if ((lim.max_hw_sectors << 9) < lim.io_opt)
+		lim.max_hw_sectors = lim.io_opt >> 9;
 
 	/* No restrictions on the number of segments in the request */
 	lim.max_segments = USHRT_MAX;
@@ -8060,12 +8080,9 @@ static int raid5_run(struct mddev *mddev)
 			goto abort;
 	}
 
-	conf->ctx_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS,
-					sizeof(struct stripe_request_ctx));
-	if (!conf->ctx_pool) {
-		ret = -ENOMEM;
+	ret = raid5_create_ctx_pool(conf);
+	if (ret)
 		goto abort;
-	}
 
 	if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
 		goto abort;
-- 
2.51.0