[PATCH 1/2] md/linear: add fault-tolerant mode for unraid-like setups

[Yu Kuai]

From: Yu Kuai <yukuai@xxxxxxxxx>

Add a module parameter 'fault_tolerant' that changes how md-linear
handles disk failures. When enabled:

- Disk failures are isolated instead of failing the entire array
- I/O to failed disks returns -EIO while healthy disks continue
- The array remains operational with reduced capacity
- Failed disk count is tracked and shown in /proc/mdstat

This enables unraid-like functionality where individual disk failures
don't bring down the entire array, allowing continued access to data
on healthy disks.

The fault_tolerant parameter can be set at module load time or
dynamically via /sys/module/md_linear/parameters/fault_tolerant.

Signed-off-by: Yu Kuai <yukuai@xxxxxxxxx>
---
 drivers/md/md-linear.c | 63 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 55 insertions(+), 8 deletions(-)

diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 8d7b82c4a723..8afc6665cfde 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -2,6 +2,10 @@
 /*
  * linear.c : Multiple Devices driver for Linux Copyright (C) 1994-96 Marc
  * ZYNGIER <zyngier@xxxxxxxxxxxxxxxxxx> or <maz@xxxxxxxxxxxxx>
+ *
+ * Fault-tolerant mode added for unraid-like setups.
+ * When fault_tolerant=1, disk failures are isolated - I/O to failed disks
+ * returns -EIO while healthy disks continue operating normally.
  */

 #include <linux/blkdev.h>
@@ -21,9 +25,15 @@ struct linear_conf {
 	sector_t                array_sectors;
 	/* a copy of mddev->raid_disks */
 	int                     raid_disks;
+	atomic_t		failed_disks;	/* count of failed disks */
 	struct dev_info         disks[] __counted_by(raid_disks);
 };

+static bool fault_tolerant;
+module_param(fault_tolerant, bool, 0644);
+MODULE_PARM_DESC(fault_tolerant,
+	"Enable fault-tolerant mode: isolate disk failures instead of failing array (default: false)");
+
 /*
  * find which device holds a particular offset
  */
@@ -96,6 +106,8 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 	if (!conf)
 		return ERR_PTR(-ENOMEM);

+	atomic_set(&conf->failed_disks, 0);
+
 	/*
 	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
 	 * keep a copy of mddev->raid_disks in struct linear_conf is,
@@ -251,7 +263,8 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)
 		     bio_sector < start_sector))
 		goto out_of_bounds;

-	if (unlikely(is_rdev_broken(tmp_dev->rdev))) {
+	if (unlikely(is_rdev_broken(tmp_dev->rdev) ||
+		     test_bit(Faulty, &tmp_dev->rdev->flags))) {
 		md_error(mddev, tmp_dev->rdev);
 		bio_io_error(bio);
 		return true;
@@ -296,16 +309,47 @@ static bool linear_make_request(struct mddev *mddev, struct bio *bio)

 static void linear_status(struct seq_file *seq, struct mddev *mddev)
 {
+	struct linear_conf *conf = mddev->private;
+
 	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
+	if (fault_tolerant) {
+		int failed = atomic_read(&conf->failed_disks);
+
+		seq_puts(seq, " fault-tolerant");
+		if (failed)
+			seq_printf(seq, " [%d failed]", failed);
+	}
 }

 static void linear_error(struct mddev *mddev, struct md_rdev *rdev)
 {
-	if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
-		char *md_name = mdname(mddev);
-
-		pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
-			md_name, rdev->bdev);
+	char *md_name = mdname(mddev);
+
+	if (fault_tolerant) {
+		/*
+		 * Fault-tolerant mode: isolate the failed disk instead of
+		 * failing the entire array. I/O to this disk will return -EIO
+		 * but other disks continue operating normally.
+		 */
+		if (!test_and_set_bit(Faulty, &rdev->flags)) {
+			struct linear_conf *conf = mddev->private;
+
+			atomic_inc(&conf->failed_disks);
+			pr_warn("md/linear%s: Disk failure on %pg detected, isolating device (fault-tolerant mode).\n",
+				md_name, rdev->bdev);
+			pr_warn("md/linear%s: %d disk(s) now failed, array continues with reduced capacity.\n",
+				md_name, atomic_read(&conf->failed_disks));
+			/* Notify userspace about the state change */
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
+		}
+	} else {
+		/*
+		 * Standard mode: fail the entire array on any disk failure.
+		 */
+		if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) {
+			pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n",
+				md_name, rdev->bdev);
+		}
 	}
 }

@@ -344,7 +388,7 @@ static void linear_exit(void)
 module_init(linear_init);
 module_exit(linear_exit);
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
+MODULE_DESCRIPTION("Linear device concatenation personality for MD with optional fault-tolerant mode");
 MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
 MODULE_ALIAS("md-linear");
 MODULE_ALIAS("md-level--1");
--
2.43.0