1 files changed, 47 insertions, 71 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index de9bccbe7337..408c26398321 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -127,10 +127,9 @@ static inline struct r1bio *get_resync_r1bio(struct bio *bio)
 	return get_resync_pages(bio)->raid_bio;
 }
 
-static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
+static void *r1bio_pool_alloc(gfp_t gfp_flags, struct r1conf *conf)
 {
-	struct pool_info *pi = data;
-	int size = offsetof(struct r1bio, bios[pi->raid_disks]);
+	int size = offsetof(struct r1bio, bios[conf->raid_disks * 2]);
 
 	/* allocate a r1bio with room for raid_disks entries in the bios array */
 	return kzalloc(size, gfp_flags);
@@ -145,18 +144,18 @@ static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
 
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 {
-	struct pool_info *pi = data;
+	struct r1conf *conf = data;
 	struct r1bio *r1_bio;
 	struct bio *bio;
 	int need_pages;
 	int j;
 	struct resync_pages *rps;
 
-	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
+	r1_bio = r1bio_pool_alloc(gfp_flags, conf);
 	if (!r1_bio)
 		return NULL;
 
-	rps = kmalloc_array(pi->raid_disks, sizeof(struct resync_pages),
+	rps = kmalloc_array(conf->raid_disks * 2, sizeof(struct resync_pages),
 			    gfp_flags);
 	if (!rps)
 		goto out_free_r1bio;
@@ -164,7 +163,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	/*
 	 * Allocate bios : 1 for reading, n-1 for writing
 	 */
-	for (j = pi->raid_disks ; j-- ; ) {
+	for (j = conf->raid_disks * 2; j-- ; ) {
 		bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
 		if (!bio)
 			goto out_free_bio;
@@ -177,11 +176,11 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
 	 * If this is a user-requested check/repair, allocate
 	 * RESYNC_PAGES for each bio.
 	 */
-	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
-		need_pages = pi->raid_disks;
+	if (test_bit(MD_RECOVERY_REQUESTED, &conf->mddev->recovery))
+		need_pages = conf->raid_disks * 2;
 	else
 		need_pages = 1;
-	for (j = 0; j < pi->raid_disks; j++) {
+	for (j = 0; j < conf->raid_disks * 2; j++) {
 		struct resync_pages *rp = &rps[j];
 
 		bio = r1_bio->bios[j];
@@ -207,7 +206,7 @@ out_free_pages:
 		resync_free_pages(&rps[j]);
 
 out_free_bio:
-	while (++j < pi->raid_disks) {
+	while (++j < conf->raid_disks * 2) {
 		bio_uninit(r1_bio->bios[j]);
 		kfree(r1_bio->bios[j]);
 	}
@@ -220,12 +219,12 @@ out_free_r1bio:
 
 static void r1buf_pool_free(void *__r1_bio, void *data)
 {
-	struct pool_info *pi = data;
+	struct r1conf *conf = data;
 	int i;
 	struct r1bio *r1bio = __r1_bio;
 	struct resync_pages *rp = NULL;
 
-	for (i = pi->raid_disks; i--; ) {
+	for (i = conf->raid_disks * 2; i--; ) {
 		rp = get_resync_pages(r1bio->bios[i]);
 		resync_free_pages(rp);
 		bio_uninit(r1bio->bios[i]);
@@ -255,7 +254,7 @@ static void free_r1bio(struct r1bio *r1_bio)
 	struct r1conf *conf = r1_bio->mddev->private;
 
 	put_all_bios(conf, r1_bio);
-	mempool_free(r1_bio, &conf->r1bio_pool);
+	mempool_free(r1_bio, conf->r1bio_pool);
 }
 
 static void put_buf(struct r1bio *r1_bio)
@@ -373,14 +372,16 @@ static void raid1_end_read_request(struct bio *bio)
 	 */
 	update_head_pos(r1_bio->read_disk, r1_bio);
 
-	if (uptodate)
+	if (uptodate) {
 		set_bit(R1BIO_Uptodate, &r1_bio->state);
-	else if (test_bit(FailFast, &rdev->flags) &&
-		 test_bit(R1BIO_FailFast, &r1_bio->state))
+	} else if (test_bit(FailFast, &rdev->flags) &&
+		 test_bit(R1BIO_FailFast, &r1_bio->state)) {
 		/* This was a fail-fast read so we definitely
 		 * want to retry */
 		;
-	else {
+	} else if (!raid1_should_handle_error(bio)) {
+		uptodate = 1;
+	} 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"
@@ -451,16 +452,15 @@ static void raid1_end_write_request(struct bio *bio)
 	struct bio *to_put = NULL;
 	int mirror = find_bio_disk(r1_bio, bio);
 	struct md_rdev *rdev = conf->mirrors[mirror].rdev;
-	bool discard_error;
 	sector_t lo = r1_bio->sector;
 	sector_t hi = r1_bio->sector + r1_bio->sectors;
-
-	discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
+	bool ignore_error = !raid1_should_handle_error(bio) ||
+		(bio->bi_status && bio_op(bio) == REQ_OP_DISCARD);
 
 	/*
 	 * 'one mirror IO has finished' event handler:
 	 */
-	if (bio->bi_status && !discard_error) {
+	if (bio->bi_status && !ignore_error) {
 		set_bit(WriteErrorSeen,	&rdev->flags);
 		if (!test_and_set_bit(WantReplacement, &rdev->flags))
 			set_bit(MD_RECOVERY_NEEDED, &
@@ -511,7 +511,7 @@ static void raid1_end_write_request(struct bio *bio)
 
 		/* Maybe we can clear some bad blocks. */
 		if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) &&
-		    !discard_error) {
+		    !ignore_error) {
 			r1_bio->bios[mirror] = IO_MADE_GOOD;
 			set_bit(R1BIO_MadeGood, &r1_bio->state);
 		}
@@ -1304,9 +1304,8 @@ alloc_r1bio(struct mddev *mddev, struct bio *bio)
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 
-	r1_bio = mempool_alloc(&conf->r1bio_pool, GFP_NOIO);
-	/* Ensure no bio records IO_BLOCKED */
-	memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
+	r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO);
+	memset(r1_bio, 0, offsetof(struct r1bio, bios[conf->raid_disks * 2]));
 	init_r1bio(r1_bio, mddev, bio);
 	return r1_bio;
 }
@@ -1398,7 +1397,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	}
 	read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp,
 				   &mddev->bio_set);
-
+	read_bio->bi_opf &= ~REQ_NOWAIT;
 	r1_bio->bios[rdisk] = read_bio;
 
 	read_bio->bi_iter.bi_sector = r1_bio->sector +
@@ -1648,6 +1647,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				wait_for_serialization(rdev, r1_bio);
 		}
 
+		mbio->bi_opf &= ~REQ_NOWAIT;
 		r1_bio->bios[i] = mbio;
 
 		mbio->bi_iter.bi_sector	= (r1_bio->sector + rdev->data_offset);
@@ -2382,7 +2382,6 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 
 		wbio->bi_end_io = end_sync_write;
 		atomic_inc(&r1_bio->remaining);
-		md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
 
 		submit_bio_noacct(wbio);
 	}
@@ -2746,7 +2745,7 @@ static int init_resync(struct r1conf *conf)
 	BUG_ON(mempool_initialized(&conf->r1buf_pool));
 
 	return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc,
-			    r1buf_pool_free, conf->poolinfo);
+			    r1buf_pool_free, conf);
 }
 
 static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
@@ -2756,7 +2755,7 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
 	struct bio *bio;
 	int i;
 
-	for (i = conf->poolinfo->raid_disks; i--; ) {
+	for (i = conf->raid_disks * 2; i--; ) {
 		bio = r1bio->bios[i];
 		rps = bio->bi_private;
 		bio_reset(bio, NULL, 0);
@@ -2821,7 +2820,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	}
 
 	if (mddev->bitmap == NULL &&
-	    mddev->recovery_cp == MaxSector &&
+	    mddev->resync_offset == MaxSector &&
 	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
 	    conf->fullsync == 0) {
 		*skipped = 1;
@@ -3055,7 +3054,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio = r1_bio->bios[i];
 			if (bio->bi_end_io == end_sync_read) {
 				read_targets--;
-				md_sync_acct_bio(bio, nr_sectors);
 				if (read_targets == 1)
 					bio->bi_opf &= ~MD_FAILFAST;
 				submit_bio_noacct(bio);
@@ -3064,7 +3062,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	} else {
 		atomic_set(&r1_bio->remaining, 1);
 		bio = r1_bio->bios[r1_bio->read_disk];
-		md_sync_acct_bio(bio, nr_sectors);
 		if (read_targets == 1)
 			bio->bi_opf &= ~MD_FAILFAST;
 		submit_bio_noacct(bio);
@@ -3086,6 +3083,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	int i;
 	struct raid1_info *disk;
 	struct md_rdev *rdev;
+	size_t r1bio_size;
 	int err = -ENOMEM;
 
 	conf = kzalloc(sizeof(struct r1conf), GFP_KERNEL);
@@ -3122,21 +3120,15 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 	if (!conf->tmppage)
 		goto abort;
 
-	conf->poolinfo = kzalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
-	if (!conf->poolinfo)
-		goto abort;
-	conf->poolinfo->raid_disks = mddev->raid_disks * 2;
-	err = mempool_init(&conf->r1bio_pool, NR_RAID_BIOS, r1bio_pool_alloc,
-			   rbio_pool_free, conf->poolinfo);
-	if (err)
+	r1bio_size = offsetof(struct r1bio, bios[mddev->raid_disks * 2]);
+	conf->r1bio_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS, r1bio_size);
+	if (!conf->r1bio_pool)
 		goto abort;
 
 	err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
 	if (err)
 		goto abort;
 
-	conf->poolinfo->mddev = mddev;
-
 	err = -EINVAL;
 	spin_lock_init(&conf->device_lock);
 	conf->raid_disks = mddev->raid_disks;
@@ -3199,10 +3191,9 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
  abort:
 	if (conf) {
-		mempool_exit(&conf->r1bio_pool);
+		mempool_destroy(conf->r1bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
-		kfree(conf->poolinfo);
 		kfree(conf->nr_pending);
 		kfree(conf->nr_waiting);
 		kfree(conf->nr_queued);
@@ -3283,9 +3274,9 @@ static int raid1_run(struct mddev *mddev)
 	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
-		mddev->recovery_cp = MaxSector;
+		mddev->resync_offset = MaxSector;
 
-	if (mddev->recovery_cp != MaxSector)
+	if (mddev->resync_offset != MaxSector)
 		pr_info("md/raid1:%s: not clean -- starting background reconstruction\n",
 			mdname(mddev));
 	pr_info("md/raid1:%s: active with %d out of %d mirrors\n",
@@ -3312,10 +3303,9 @@ static void raid1_free(struct mddev *mddev, void *priv)
 {
 	struct r1conf *conf = priv;
 
-	mempool_exit(&conf->r1bio_pool);
+	mempool_destroy(conf->r1bio_pool);
 	kfree(conf->mirrors);
 	safe_put_page(conf->tmppage);
-	kfree(conf->poolinfo);
 	kfree(conf->nr_pending);
 	kfree(conf->nr_waiting);
 	kfree(conf->nr_queued);
@@ -3346,8 +3336,8 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors)
 
 	md_set_array_sectors(mddev, newsize);
 	if (sectors > mddev->dev_sectors &&
-	    mddev->recovery_cp > mddev->dev_sectors) {
-		mddev->recovery_cp = mddev->dev_sectors;
+	    mddev->resync_offset > mddev->dev_sectors) {
+		mddev->resync_offset = mddev->dev_sectors;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
 	mddev->dev_sectors = sectors;
@@ -3368,17 +3358,13 @@ static int raid1_reshape(struct mddev *mddev)
 	 * At the same time, we "pack" the devices so that all the missing
 	 * devices have the higher raid_disk numbers.
 	 */
-	mempool_t newpool, oldpool;
-	struct pool_info *newpoolinfo;
+	mempool_t *newpool, *oldpool;
+	size_t new_r1bio_size;
 	struct raid1_info *newmirrors;
 	struct r1conf *conf = mddev->private;
 	int cnt, raid_disks;
 	unsigned long flags;
 	int d, d2;
-	int ret;
-
-	memset(&newpool, 0, sizeof(newpool));
-	memset(&oldpool, 0, sizeof(oldpool));
 
 	/* Cannot change chunk_size, layout, or level */
 	if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
@@ -3404,24 +3390,16 @@ static int raid1_reshape(struct mddev *mddev)
 			return -EBUSY;
 	}
 
-	newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL);
-	if (!newpoolinfo)
+	new_r1bio_size = offsetof(struct r1bio, bios[raid_disks * 2]);
+	newpool = mempool_create_kmalloc_pool(NR_RAID_BIOS, new_r1bio_size);
+	if (!newpool) {
 		return -ENOMEM;
-	newpoolinfo->mddev = mddev;
-	newpoolinfo->raid_disks = raid_disks * 2;
-
-	ret = mempool_init(&newpool, NR_RAID_BIOS, r1bio_pool_alloc,
-			   rbio_pool_free, newpoolinfo);
-	if (ret) {
-		kfree(newpoolinfo);
-		return ret;
 	}
 	newmirrors = kzalloc(array3_size(sizeof(struct raid1_info),
 					 raid_disks, 2),
 			     GFP_KERNEL);
 	if (!newmirrors) {
-		kfree(newpoolinfo);
-		mempool_exit(&newpool);
+		mempool_destroy(newpool);
 		return -ENOMEM;
 	}
 
@@ -3446,8 +3424,6 @@ static int raid1_reshape(struct mddev *mddev)
 	}
 	kfree(conf->mirrors);
 	conf->mirrors = newmirrors;
-	kfree(conf->poolinfo);
-	conf->poolinfo = newpoolinfo;
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded += (raid_disks - conf->raid_disks);
@@ -3461,7 +3437,7 @@ static int raid1_reshape(struct mddev *mddev)
 	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	md_wakeup_thread(mddev->thread);
 
-	mempool_exit(&oldpool);
+	mempool_destroy(oldpool);
 	return 0;
 }