X-Git-Url: http://pilppa.org/gitweb/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid1.c;h=46677d7d9980521802dc71355bb9c6478a103383;hb=f6dff381af01006ffae3c23cd2e07e30584de0ec;hp=97ee870b265d866ffa818bdf83dc7f551cd40d7b;hpb=4285431fb658263e98942ce2320b0b26eddcc06d;p=linux-2.6-omap-h63xx.git

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 97ee870b265..46677d7d998 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -271,21 +271,25 @@ static int raid1_end_read_request(struct bio *bio, unsigned int bytes_done, int
 	 */
 	update_head_pos(mirror, r1_bio);
 
-	if (uptodate || (conf->raid_disks - conf->mddev->degraded) <= 1) {
-		/*
-		 * Set R1BIO_Uptodate in our master bio, so that
-		 * we will return a good error code for to the higher
-		 * levels even if IO on some other mirrored buffer fails.
-		 *
-		 * The 'master' represents the composite IO operation to
-		 * user-side. So if something waits for IO, then it will
-		 * wait for the 'master' bio.
+	if (uptodate)
+		set_bit(R1BIO_Uptodate, &r1_bio->state);
+	else {
+		/* If all other devices have failed, we want to return
+		 * the error upwards rather than fail the last device.
+		 * Here we redefine "uptodate" to mean "Don't want to retry"
 		 */
-		if (uptodate)
-			set_bit(R1BIO_Uptodate, &r1_bio->state);
+		unsigned long flags;
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (r1_bio->mddev->degraded == conf->raid_disks ||
+		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
+		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+			uptodate = 1;
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+	}
 
+	if (uptodate)
 		raid_end_bio_io(r1_bio);
-	} else {
+	else {
 		/*
 		 * oops, read error:
 		 */
@@ -992,13 +996,14 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		unsigned long flags;
 		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
+		set_bit(Faulty, &rdev->flags);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 		/*
 		 * if recovery is running, make sure it aborts.
 		 */
 		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
-	}
-	set_bit(Faulty, &rdev->flags);
+	} else
+		set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device. \n"
 		"	Operation continuing on %d devices\n",
@@ -1235,17 +1240,24 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 			}
 		r1_bio->read_disk = primary;
 		for (i=0; i<mddev->raid_disks; i++)
-			if (r1_bio->bios[i]->bi_end_io == end_sync_read &&
-			    test_bit(BIO_UPTODATE, &r1_bio->bios[i]->bi_flags)) {
+			if (r1_bio->bios[i]->bi_end_io == end_sync_read) {
 				int j;
 				int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
 				struct bio *pbio = r1_bio->bios[primary];
 				struct bio *sbio = r1_bio->bios[i];
-				for (j = vcnt; j-- ; )
-					if (memcmp(page_address(pbio->bi_io_vec[j].bv_page),
-						   page_address(sbio->bi_io_vec[j].bv_page),
-						   PAGE_SIZE))
-						break;
+
+				if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+					for (j = vcnt; j-- ; ) {
+						struct page *p, *s;
+						p = pbio->bi_io_vec[j].bv_page;
+						s = sbio->bi_io_vec[j].bv_page;
+						if (memcmp(page_address(p),
+							   page_address(s),
+							   PAGE_SIZE))
+							break;
+					}
+				} else
+					j = 0;
 				if (j >= 0)
 					mddev->resync_mismatches += r1_bio->sectors;
 				if (j < 0 || test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {