From: NeilBrown <neilb@suse.de>
Date: Thu, 1 Mar 2007 04:11:18 +0000 (-0800)
Subject: [PATCH] md: fix raid10 recovery problem.
X-Git-Tag: v2.6.21-rc3~193
X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=64a742bc61f9115b0bb270fa081e5b5b9c35dcd0;p=linux-2.6

[PATCH] md: fix raid10 recovery problem.

There are two errors that can lead to recovery problems with raid10
when used in 'far' more (not the default).

Due to a '>' instead of '>=' the wrong block is located which would result in
garbage being written to some random location, quite possible outside the
range of the device, causing the newly reconstructed device to fail.

The device size calculation had some rounding errors (it didn't round when it
should) and so recovery would go a few blocks too far which would again cause
a write to a random block address and probably a device error.

The code for working with device sizes was fairly confused and spread out, so
this has been tided up a bit.

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index a9401c017e..82249a6901 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -429,7 +429,7 @@ static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
 		if (dev < 0)
 			dev += conf->raid_disks;
 	} else {
-		while (sector > conf->stride) {
+		while (sector >= conf->stride) {
 			sector -= conf->stride;
 			if (dev < conf->near_copies)
 				dev += conf->raid_disks - conf->near_copies;
@@ -1801,6 +1801,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 						for (k=0; k<conf->copies; k++)
 							if (r10_bio->devs[k].devnum == i)
 								break;
+						BUG_ON(k == conf->copies);
 						bio = r10_bio->devs[1].bio;
 						bio->bi_next = biolist;
 						biolist = bio;
@@ -2021,19 +2022,30 @@ static int run(mddev_t *mddev)
 	if (!conf->tmppage)
 		goto out_free_conf;
 
+	conf->mddev = mddev;
+	conf->raid_disks = mddev->raid_disks;
 	conf->near_copies = nc;
 	conf->far_copies = fc;
 	conf->copies = nc*fc;
 	conf->far_offset = fo;
 	conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
 	conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
+	size = mddev->size >> (conf->chunk_shift-1);
+	sector_div(size, fc);
+	size = size * conf->raid_disks;
+	sector_div(size, nc);
+	/* 'size' is now the number of chunks in the array */
+	/* calculate "used chunks per device" in 'stride' */
+	stride = size * conf->copies;
+	sector_div(stride, conf->raid_disks);
+	mddev->size = stride  << (conf->chunk_shift-1);
+
 	if (fo)
-		conf->stride = 1 << conf->chunk_shift;
-	else {
-		stride = mddev->size >> (conf->chunk_shift-1);
+		stride = 1;
+	else
 		sector_div(stride, fc);
-		conf->stride = stride << conf->chunk_shift;
-	}
+	conf->stride = stride << conf->chunk_shift;
+
 	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
 						r10bio_pool_free, conf);
 	if (!conf->r10bio_pool) {
@@ -2063,8 +2075,6 @@ static int run(mddev_t *mddev)
 
 		disk->head_position = 0;
 	}
-	conf->raid_disks = mddev->raid_disks;
-	conf->mddev = mddev;
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
 
@@ -2106,16 +2116,8 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	if (conf->far_offset) {
-		size = mddev->size >> (conf->chunk_shift-1);
-		size *= conf->raid_disks;
-		size <<= conf->chunk_shift;
-		sector_div(size, conf->far_copies);
-	} else
-		size = conf->stride * conf->raid_disks;
-	sector_div(size, conf->near_copies);
-	mddev->array_size = size/2;
-	mddev->resync_max_sectors = size;
+	mddev->array_size = size << (conf->chunk_shift-1);
+	mddev->resync_max_sectors = size << conf->chunk_shift;
 
 	mddev->queue->unplug_fn = raid10_unplug;
 	mddev->queue->issue_flush_fn = raid10_issue_flush;