X-Git-Url: https://git.stricted.de/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid1.c;h=a8315aaba9fee33b844049f3fe8fb99f26e5aff1;hb=HEAD;hp=6e17f8181c4b923eb4044838d5bfc9dbb6d625fd;hpb=e00c7f1fad21ff81ac0a8dfbbb7cc3b7c806fa73;p=GitHub%2Fmt8127%2Fandroid_kernel_alcatel_ttab.git

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6e17f8181c4b..a8315aaba9fe 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -94,6 +94,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	struct pool_info *pi = data;
 	struct r1bio *r1_bio;
 	struct bio *bio;
+	int need_pages;
 	int i, j;
 
 	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
@@ -116,15 +117,15 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * RESYNC_PAGES for each bio.
 	 */
 	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
-		j = pi->raid_disks;
+		need_pages = pi->raid_disks;
 	else
-		j = 1;
-	while(j--) {
+		need_pages = 1;
+	for (j = 0; j < need_pages; j++) {
 		bio = r1_bio->bios[j];
 		bio->bi_vcnt = RESYNC_PAGES;
 
 		if (bio_alloc_pages(bio, gfp_flags))
-			goto out_free_bio;
+			goto out_free_pages;
 	}
 	/* If not user-requests, copy the page pointers to all bios */
 	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
@@ -138,6 +139,14 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 
 	return r1_bio;
 
+out_free_pages:
+	while (--j >= 0) {
+		struct bio_vec *bv;
+
+		bio_for_each_segment_all(bv, r1_bio->bios[j], i)
+			__free_page(bv->bv_page);
+	}
+
 out_free_bio:
 	while (++j < pi->raid_disks)
 		bio_put(r1_bio->bios[j]);
@@ -318,7 +327,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		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)))
+		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
@@ -548,16 +557,17 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 		if (test_bit(WriteMostly, &rdev->flags)) {
 			/* Don't balance among write-mostly, just
 			 * use the first as a last resort */
-			if (best_disk < 0) {
+			if (best_dist_disk < 0) {
 				if (is_badblock(rdev, this_sector, sectors,
 						&first_bad, &bad_sectors)) {
-					if (first_bad < this_sector)
+					if (first_bad <= this_sector)
 						/* Cannot use this */
 						continue;
 					best_good_sectors = first_bad - this_sector;
 				} else
 					best_good_sectors = sectors;
-				best_disk = disk;
+				best_dist_disk = disk;
+				best_pending_disk = disk;
 			}
 			continue;
 		}
@@ -1372,6 +1382,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1391,18 +1402,17 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		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_INTR, &mddev->recovery);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
+	/*
+	 * if recovery is running, make sure it aborts.
+	 */
+	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
@@ -1456,7 +1466,10 @@ static int raid1_spare_active(struct mddev *mddev)
 	 * Find all failed disks within the RAID1 configuration 
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1479,13 +1492,13 @@ static int raid1_spare_active(struct mddev *mddev)
 			}
 		}
 		if (rdev
+		    && rdev->recovery_offset == MaxSector
 		    && !test_bit(Faulty, &rdev->flags)
 		    && !test_and_set_bit(In_sync, &rdev->flags)) {
 			count++;
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
@@ -1848,6 +1861,40 @@ static int process_checks(struct r1bio *r1_bio)
 	int i;
 	int vcnt;
 
+	/* Fix variable parts of all bios */
+	vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
+	for (i = 0; i < conf->raid_disks * 2; i++) {
+		int j;
+		int size;
+		int uptodate;
+		struct bio *b = r1_bio->bios[i];
+		if (b->bi_end_io != end_sync_read)
+			continue;
+		/* fixup the bio for reuse, but preserve BIO_UPTODATE */
+		uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+		bio_reset(b);
+		if (!uptodate)
+			clear_bit(BIO_UPTODATE, &b->bi_flags);
+		b->bi_vcnt = vcnt;
+		b->bi_size = r1_bio->sectors << 9;
+		b->bi_sector = r1_bio->sector +
+			conf->mirrors[i].rdev->data_offset;
+		b->bi_bdev = conf->mirrors[i].rdev->bdev;
+		b->bi_end_io = end_sync_read;
+		b->bi_private = r1_bio;
+
+		size = b->bi_size;
+		for (j = 0; j < vcnt ; j++) {
+			struct bio_vec *bi;
+			bi = &b->bi_io_vec[j];
+			bi->bv_offset = 0;
+			if (size > PAGE_SIZE)
+				bi->bv_len = PAGE_SIZE;
+			else
+				bi->bv_len = size;
+			size -= PAGE_SIZE;
+		}
+	}
 	for (primary = 0; primary < conf->raid_disks * 2; primary++)
 		if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
 		    test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
@@ -1856,17 +1903,18 @@ static int process_checks(struct r1bio *r1_bio)
 			break;
 		}
 	r1_bio->read_disk = primary;
-	vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
 	for (i = 0; i < conf->raid_disks * 2; i++) {
 		int j;
 		struct bio *pbio = r1_bio->bios[primary];
 		struct bio *sbio = r1_bio->bios[i];
-		int size;
+		int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
 
 		if (sbio->bi_end_io != end_sync_read)
 			continue;
+		/* Now we can 'fixup' the BIO_UPTODATE flag */
+		set_bit(BIO_UPTODATE, &sbio->bi_flags);
 
-		if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+		if (uptodate) {
 			for (j = vcnt; j-- ; ) {
 				struct page *p, *s;
 				p = pbio->bi_io_vec[j].bv_page;
@@ -1881,33 +1929,12 @@ static int process_checks(struct r1bio *r1_bio)
 		if (j >= 0)
 			atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
 		if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
-			      && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+			      && uptodate)) {
 			/* No need to write to this device. */
 			sbio->bi_end_io = NULL;
 			rdev_dec_pending(conf->mirrors[i].rdev, mddev);
 			continue;
 		}
-		/* fixup the bio for reuse */
-		bio_reset(sbio);
-		sbio->bi_vcnt = vcnt;
-		sbio->bi_size = r1_bio->sectors << 9;
-		sbio->bi_sector = r1_bio->sector +
-			conf->mirrors[i].rdev->data_offset;
-		sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
-		sbio->bi_end_io = end_sync_read;
-		sbio->bi_private = r1_bio;
-
-		size = sbio->bi_size;
-		for (j = 0; j < vcnt ; j++) {
-			struct bio_vec *bi;
-			bi = &sbio->bi_io_vec[j];
-			bi->bv_offset = 0;
-			if (size > PAGE_SIZE)
-				bi->bv_len = PAGE_SIZE;
-			else
-				bi->bv_len = size;
-			size -= PAGE_SIZE;
-		}
 
 		bio_copy_data(sbio, pbio);
 	}
@@ -2027,7 +2054,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags))
+			    !test_bit(Faulty, &rdev->flags))
 				r1_sync_page_io(rdev, sect, s,
 						conf->tmppage, WRITE);
 		}
@@ -2039,7 +2066,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags)) {
+			    !test_bit(Faulty, &rdev->flags)) {
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
@@ -2120,7 +2147,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 		md_trim_bio(wbio, sector - r1_bio->sector, sectors);
 		wbio->bi_sector += rdev->data_offset;
 		wbio->bi_bdev = rdev->bdev;
-		if (submit_bio_wait(WRITE, wbio) == 0)
+		if (submit_bio_wait(WRITE, wbio) < 0)
 			/* failure! */
 			ok = rdev_set_badblocks(rdev, sector,
 						sectors, 0)