linux-kernel - [PATCH md-6.9 v4 08/11] md/raid1: factor out choose_slow_rdev() from read

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: <20240229095714.926789-9-yukuai1@huaweicloud.com>
Date: Thu, 29 Feb 2024 17:57:11 +0800
From: Yu Kuai <yukuai1@...weicloud.com>
To: xni@...hat.com,
	paul.e.luse@...ux.intel.com,
	song@...nel.org,
	neilb@...e.com,
	shli@...com
Cc: linux-raid@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	yukuai3@...wei.com,
	yukuai1@...weicloud.com,
	yi.zhang@...wei.com,
	yangerkun@...wei.com
Subject: [PATCH md-6.9 v4 08/11] md/raid1: factor out choose_slow_rdev() from read_balance()

From: Yu Kuai <yukuai3@...wei.com>

read_balance() is hard to understand because there are too many status
and branches, and it's overlong.

This patch factor out the case to read the slow rdev from
read_balance(), there are no functional changes.

Co-developed-by: Paul Luse <paul.e.luse@...ux.intel.com>
Signed-off-by: Paul Luse <paul.e.luse@...ux.intel.com>
Signed-off-by: Yu Kuai <yukuai3@...wei.com>
Reviewed-by: Xiao Ni <xni@...hat.com>
---
 drivers/md/raid1.c | 69 ++++++++++++++++++++++++++++++++++------------
 1 file changed, 52 insertions(+), 17 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 3149f22f1155..09b7e93a54b5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -620,6 +620,53 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 	return -1;
 }
 
+static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			    int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int bb_disk = -1;
+	int bb_read_len = 0;
+	int disk;
+
+	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+		struct md_rdev *rdev;
+		int len;
+		int read_len;
+
+		if (r1_bio->bios[disk] == IO_BLOCKED)
+			continue;
+
+		rdev = conf->mirrors[disk].rdev;
+		if (!rdev || test_bit(Faulty, &rdev->flags) ||
+		    !test_bit(WriteMostly, &rdev->flags))
+			continue;
+
+		/* there are no bad blocks, we can use this disk */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len == r1_bio->sectors) {
+			update_read_sectors(conf, disk, this_sector, read_len);
+			return disk;
+		}
+
+		/*
+		 * there are partial bad blocks, choose the rdev with largest
+		 * read length.
+		 */
+		if (read_len > bb_read_len) {
+			bb_disk = disk;
+			bb_read_len = read_len;
+		}
+	}
+
+	if (bb_disk != -1) {
+		*max_sectors = bb_read_len;
+		update_read_sectors(conf, bb_disk, this_sector, bb_read_len);
+	}
+
+	return bb_disk;
+}
+
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -673,23 +720,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		if (!test_bit(In_sync, &rdev->flags) &&
 		    rdev->recovery_offset < this_sector + sectors)
 			continue;
-		if (test_bit(WriteMostly, &rdev->flags)) {
-			/* Don't balance among write-mostly, just
-			 * use the first as a last resort */
-			if (best_dist_disk < 0) {
-				if (is_badblock(rdev, this_sector, sectors,
-						&first_bad, &bad_sectors)) {
-					if (first_bad <= this_sector)
-						/* Cannot use this */
-						continue;
-					best_good_sectors = first_bad - this_sector;
-				} else
-					best_good_sectors = sectors;
-				best_dist_disk = disk;
-				best_pending_disk = disk;
-			}
+		if (test_bit(WriteMostly, &rdev->flags))
 			continue;
-		}
 		/* This is a reasonable device to use.  It might
 		 * even be best.
 		 */
@@ -808,7 +840,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	}
 	*max_sectors = sectors;
 
-	return best_disk;
+	if (best_disk >= 0)
+		return best_disk;
+
+	return choose_slow_rdev(conf, r1_bio, max_sectors);
 }
 
 static void wake_up_barrier(struct r1conf *conf)
-- 
2.39.2