linux-kernel - [PATCH md-6.9 v2 08/10] md/raid1: factor out choose_bb_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: <20240227120327.1432511-9-yukuai1@huaweicloud.com>
Date: Tue, 27 Feb 2024 20:03:25 +0800
From: Yu Kuai <yukuai1@...weicloud.com>
To: xni@...hat.com,
	paul.e.luse@...ux.intel.com,
	song@...nel.org,
	shli@...com,
	neilb@...e.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 v2 08/10] md/raid1: factor out choose_bb_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 rdev with bad blocks 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 | 79 ++++++++++++++++++++++++++++------------------
 1 file changed, 48 insertions(+), 31 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 407e2bf5c322..76bb59ad1485 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -620,6 +620,44 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 	return -1;
 }
 
+static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+			  int *max_sectors)
+{
+	sector_t this_sector = r1_bio->sector;
+	int best_disk = -1;
+	int best_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;
+
+		/* keep track of the disk with the most readable sectors. */
+		len = r1_bio->sectors;
+		read_len = raid1_check_read_range(rdev, this_sector, &len);
+		if (read_len > best_len) {
+			best_disk = disk;
+			best_len = read_len;
+		}
+	}
+
+	if (best_disk != -1) {
+		*max_sectors = best_len;
+		update_read_sectors(conf, best_disk, this_sector, best_len);
+	}
+
+	return best_disk;
+}
+
 static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 			    int *max_sectors)
 {
@@ -708,8 +746,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
 		sector_t dist;
-		sector_t first_bad;
-		int bad_sectors;
 		unsigned int pending;
 
 		rdev = conf->mirrors[disk].rdev;
@@ -722,36 +758,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 			continue;
 		if (test_bit(WriteMostly, &rdev->flags))
 			continue;
-		/* This is a reasonable device to use.  It might
-		 * even be best.
-		 */
-		if (is_badblock(rdev, this_sector, sectors,
-				&first_bad, &bad_sectors)) {
-			if (best_dist < MaxSector)
-				/* already have a better device */
-				continue;
-			if (first_bad <= this_sector) {
-				/* cannot read here. If this is the 'primary'
-				 * device, then we must not read beyond
-				 * bad_sectors from another device..
-				 */
-				bad_sectors -= (this_sector - first_bad);
-				if (best_good_sectors > sectors)
-					best_good_sectors = sectors;
-
-			} else {
-				sector_t good_sectors = first_bad - this_sector;
-				if (good_sectors > best_good_sectors) {
-					best_good_sectors = good_sectors;
-					best_disk = disk;
-				}
-			}
+		if (rdev_has_badblock(rdev, this_sector, sectors))
 			continue;
-		} else {
-			if ((sectors > best_good_sectors) && (best_disk >= 0))
-				best_disk = -1;
-			best_good_sectors = sectors;
-		}
 
 		if (best_disk >= 0)
 			/* At least two disks to choose from so failfast is OK */
@@ -843,6 +851,15 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	if (best_disk >= 0)
 		return best_disk;
 
+	/*
+	 * If we are here it means we didn't find a perfectly good disk so
+	 * now spend a bit more time trying to find one with the most good
+	 * sectors.
+	 */
+	disk = choose_bb_rdev(conf, r1_bio, max_sectors);
+	if (disk >= 0)
+		return disk;
+
 	return choose_slow_rdev(conf, r1_bio, max_sectors);
 }
 
-- 
2.39.2