Merge branch 'for-4.7/drivers' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "On top of the core pull request, this is the drivers pull request for
  this merge window.  This contains:

   - Switch drivers to the new write back cache API, and kill off the
     flush flags.  From me.

   - Kill the discard support for the STEC pci-e flash driver.  It's
     trivially broken, and apparently unmaintained, so it's safer to
     just remove it.  From Jeff Moyer.

   - A set of lightnvm updates from the usual suspects (Matias/Javier,
     and Simon), and fixes from Arnd, Jeff Mahoney, Sagi, and Wenwei
     Tao.

   - A set of updates for NVMe:

        - Turn the controller state management into a proper state
          machine.  From Christoph.

        - Shuffling of code in preparation for NVMe-over-fabrics, also
          from Christoph.

        - Cleanup of the command prep part from Ming Lin.

        - Rewrite of the discard support from Ming Lin.

        - Deadlock fix for namespace removal from Ming Lin.

        - Use the now exported blk-mq tag helper for IO termination.
          From Sagi.

        - Various little fixes from Christoph, Guilherme, Keith, Ming
          Lin, Wang Sheng-Hui.

   - Convert mtip32xx to use the now exported blk-mq tag iter function,
     from Keith"

* 'for-4.7/drivers' of git://git.kernel.dk/linux-block: (74 commits)
  lightnvm: reserved space calculation incorrect
  lightnvm: rename nr_pages to nr_ppas on nvm_rq
  lightnvm: add is_cached entry to struct ppa_addr
  lightnvm: expose gennvm_mark_blk to targets
  lightnvm: remove mgt targets on mgt removal
  lightnvm: pass dma address to hardware rather than pointer
  lightnvm: do not assume sequential lun alloc.
  nvme/lightnvm: Log using the ctrl named device
  lightnvm: rename dma helper functions
  lightnvm: enable metadata to be sent to device
  lightnvm: do not free unused metadata on rrpc
  lightnvm: fix out of bound ppa lun id on bb tbl
  lightnvm: refactor set_bb_tbl for accepting ppa list
  lightnvm: move responsibility for bad blk mgmt to target
  lightnvm: make nvm_set_rqd_ppalist() aware of vblks
  lightnvm: remove struct factory_blks
  lightnvm: refactor device ops->get_bb_tbl()
  lightnvm: introduce nvm_for_each_lun_ppa() macro
  lightnvm: refactor dev->online_target to global nvm_targets
  lightnvm: rename nvm_targets to nvm_tgt_type
  ...

Documentation/block/writeback_cache_control.txt

@@ -71,7 +71,7 @@ requests that have a payload.  For devices with volatile write caches the
 driver needs to tell the block layer that it supports flushing caches by
 doing:
 
-	blk_queue_flush(sdkp->disk->queue, REQ_FLUSH);
+	blk_queue_write_cache(sdkp->disk->queue, true, false);
 
 and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
 REQ_FLUSH requests with a payload are automatically turned into a sequence
@@ -79,7 +79,7 @@ of an empty REQ_FLUSH request followed by the actual write by the block
 layer.  For devices that also support the FUA bit the block layer needs
 to be told to pass through the REQ_FUA bit using:
 
-	blk_queue_flush(sdkp->disk->queue, REQ_FLUSH | REQ_FUA);
+	blk_queue_write_cache(sdkp->disk->queue, true, true);
 
 and the driver must handle write requests that have the REQ_FUA bit set
 in prep_fn/request_fn.  If the FUA bit is not natively supported the block

arch/um/drivers/ubd_kern.c

@@ -862,7 +862,7 @@ static int ubd_add(int n, char **error_out)
 		goto out;
 	}
 	ubd_dev->queue->queuedata = ubd_dev;
-	blk_queue_flush(ubd_dev->queue, REQ_FLUSH);
+	blk_queue_write_cache(ubd_dev->queue, true, false);
 
 	blk_queue_max_segments(ubd_dev->queue, MAX_SG);
 	err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, &ubd_gendisk[n]);

block/blk-core.c

@@ -1964,7 +1964,8 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
+	if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) &&
+	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
 		bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
 		if (!nr_sectors) {
 			err = 0;

block/blk-flush.c

@@ -95,17 +95,18 @@ enum {
 static bool blk_kick_flush(struct request_queue *q,
 			   struct blk_flush_queue *fq);
 
-static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
+static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
 {
 	unsigned int policy = 0;
 
 	if (blk_rq_sectors(rq))
 		policy |= REQ_FSEQ_DATA;
 
-	if (fflags & REQ_FLUSH) {
+	if (fflags & (1UL << QUEUE_FLAG_WC)) {
 		if (rq->cmd_flags & REQ_FLUSH)
 			policy |= REQ_FSEQ_PREFLUSH;
-		if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
+		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
+		    (rq->cmd_flags & REQ_FUA))
 			policy |= REQ_FSEQ_POSTFLUSH;
 	}
 	return policy;
@@ -384,7 +385,7 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 void blk_insert_flush(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	unsigned int fflags = q->flush_flags;	/* may change, cache */
+	unsigned long fflags = q->queue_flags;	/* may change, cache */
 	unsigned int policy = blk_flush_policy(fflags, rq);
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
 
@@ -393,7 +394,7 @@ void blk_insert_flush(struct request *rq)
 	 * REQ_FLUSH and FUA for the driver.
 	 */
 	rq->cmd_flags &= ~REQ_FLUSH;
-	if (!(fflags & REQ_FUA))
+	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*

block/blk-mq-tag.c

@@ -464,15 +464,14 @@ static void bt_tags_for_each(struct blk_mq_tags *tags,
 	}
 }
 
-void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
-		void *priv)
+static void blk_mq_all_tag_busy_iter(struct blk_mq_tags *tags,
+		busy_tag_iter_fn *fn, void *priv)
 {
 	if (tags->nr_reserved_tags)
 		bt_tags_for_each(tags, &tags->breserved_tags, 0, fn, priv, true);
 	bt_tags_for_each(tags, &tags->bitmap_tags, tags->nr_reserved_tags, fn, priv,
 			false);
 }
-EXPORT_SYMBOL(blk_mq_all_tag_busy_iter);
 
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv)

block/blk-settings.c

@@ -820,29 +820,14 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 
-/**
- * blk_queue_flush - configure queue's cache flush capability
- * @q:		the request queue for the device
- * @flush:	0, REQ_FLUSH or REQ_FLUSH | REQ_FUA
- *
- * Tell block layer cache flush capability of @q.  If it supports
- * flushing, REQ_FLUSH should be set.  If it supports bypassing
- * write cache for individual writes, REQ_FUA should be set.
- */
-void blk_queue_flush(struct request_queue *q, unsigned int flush)
-{
-	WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA));
-
-	if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA)))
-		flush &= ~REQ_FUA;
-
-	q->flush_flags = flush & (REQ_FLUSH | REQ_FUA);
-}
-EXPORT_SYMBOL_GPL(blk_queue_flush);
-
 void blk_queue_flush_queueable(struct request_queue *q, bool queueable)
 {
-	q->flush_not_queueable = !queueable;
+	spin_lock_irq(q->queue_lock);
+	if (queueable)
+		clear_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags);
+	else
+		set_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags);
+	spin_unlock_irq(q->queue_lock);
 }
 EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 
@@ -857,16 +842,13 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 {
 	spin_lock_irq(q->queue_lock);
-	if (wc) {
+	if (wc)
 		queue_flag_set(QUEUE_FLAG_WC, q);
-		q->flush_flags = REQ_FLUSH;
-	} else
+	else
 		queue_flag_clear(QUEUE_FLAG_WC, q);
-	if (fua) {
-		if (wc)
-			q->flush_flags |= REQ_FUA;
+	if (fua)
 		queue_flag_set(QUEUE_FLAG_FUA, q);
-	} else
+	else
 		queue_flag_clear(QUEUE_FLAG_FUA, q);
 	spin_unlock_irq(q->queue_lock);
 }

drivers/block/drbd/drbd_main.c

@@ -2761,7 +2761,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	q->backing_dev_info.congested_data = device;
 
 	blk_queue_make_request(q, drbd_make_request);
-	blk_queue_flush(q, REQ_FLUSH | REQ_FUA);
+	blk_queue_write_cache(q, true, true);
 	/* Setting the max_hw_sectors to an odd value of 8kibyte here
 	   This triggers a max_bio_size message upon first attach or connect */
 	blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);

drivers/block/loop.c

@@ -943,7 +943,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
-		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
+		blk_queue_write_cache(lo->lo_queue, true, false);
 
 	loop_update_dio(lo);
 	set_capacity(lo->lo_disk, size);

drivers/block/mtip32xx/mtip32xx.c

@@ -3000,14 +3000,14 @@ static int mtip_service_thread(void *data)
 					"Completion workers still active!");
 
 			spin_lock(dd->queue->queue_lock);
-			blk_mq_all_tag_busy_iter(*dd->tags.tags,
+			blk_mq_tagset_busy_iter(&dd->tags,
 							mtip_queue_cmd, dd);
 			spin_unlock(dd->queue->queue_lock);
 
 			set_bit(MTIP_PF_ISSUE_CMDS_BIT, &dd->port->flags);
 
 			if (mtip_device_reset(dd))
-				blk_mq_all_tag_busy_iter(*dd->tags.tags,
+				blk_mq_tagset_busy_iter(&dd->tags,
 							mtip_abort_cmd, dd);
 
 			clear_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags);
@@ -4023,12 +4023,6 @@ static int mtip_block_initialize(struct driver_data *dd)
 	blk_queue_io_min(dd->queue, 4096);
 	blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask);
 
-	/*
-	 * write back cache is not supported in the device. FUA depends on
-	 * write back cache support, hence setting flush support to zero.
-	 */
-	blk_queue_flush(dd->queue, 0);
-
 	/* Signal trim support */
 	if (dd->trim_supp == true) {
 		set_bit(QUEUE_FLAG_DISCARD, &dd->queue->queue_flags);
@@ -4174,7 +4168,7 @@ static int mtip_block_remove(struct driver_data *dd)
 
 	blk_mq_freeze_queue_start(dd->queue);
 	blk_mq_stop_hw_queues(dd->queue);
-	blk_mq_all_tag_busy_iter(dd->tags.tags[0], mtip_no_dev_cleanup, dd);
+	blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
 
 	/*
 	 * Delete our gendisk structure. This also removes the device

drivers/block/nbd.c

@@ -693,9 +693,9 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
 	if (nbd->flags & NBD_FLAG_SEND_TRIM)
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 	if (nbd->flags & NBD_FLAG_SEND_FLUSH)
-		blk_queue_flush(nbd->disk->queue, REQ_FLUSH);
+		blk_queue_write_cache(nbd->disk->queue, true, false);
 	else
-		blk_queue_flush(nbd->disk->queue, 0);
+		blk_queue_write_cache(nbd->disk->queue, false, false);
 }
 
 static int nbd_dev_dbg_init(struct nbd_device *nbd);

drivers/block/osdblk.c

@@ -437,7 +437,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev)
 	blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
 
 	blk_queue_prep_rq(q, blk_queue_start_tag);
-	blk_queue_flush(q, REQ_FLUSH);
+	blk_queue_write_cache(q, true, false);
 
 	disk->queue = q;
 

drivers/block/ps3disk.c

@@ -468,7 +468,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev)
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
 	blk_queue_logical_block_size(queue, dev->blk_size);
 
-	blk_queue_flush(queue, REQ_FLUSH);
+	blk_queue_write_cache(queue, true, false);
 
 	blk_queue_max_segments(queue, -1);
 	blk_queue_max_segment_size(queue, dev->bounce_size);

drivers/block/skd_main.c

@@ -133,7 +133,6 @@ MODULE_VERSION(DRV_VERSION "-" DRV_BUILD_ID);
 #define SKD_TIMER_MINUTES(minutes) ((minutes) * (60))
 
 #define INQ_STD_NBYTES 36
-#define SKD_DISCARD_CDB_LENGTH	24
 
 enum skd_drvr_state {
 	SKD_DRVR_STATE_LOAD,
@@ -212,7 +211,6 @@ struct skd_request_context {
 
 	struct request *req;
 	u8 flush_cmd;
-	u8 discard_page;
 
 	u32 timeout_stamp;
 	u8 sg_data_dir;
@@ -230,7 +228,6 @@ struct skd_request_context {
 };
 #define SKD_DATA_DIR_HOST_TO_CARD       1
 #define SKD_DATA_DIR_CARD_TO_HOST       2
-#define SKD_DATA_DIR_NONE		3	/* especially for DISCARD requests. */
 
 struct skd_special_context {
 	struct skd_request_context req;
@@ -540,31 +537,6 @@ skd_prep_zerosize_flush_cdb(struct skd_scsi_request *scsi_req,
 	scsi_req->cdb[9] = 0;
 }
 
-static void
-skd_prep_discard_cdb(struct skd_scsi_request *scsi_req,
-		     struct skd_request_context *skreq,
-		     struct page *page,
-		     u32 lba, u32 count)
-{
-	char *buf;
-	unsigned long len;
-	struct request *req;
-
-	buf = page_address(page);
-	len = SKD_DISCARD_CDB_LENGTH;
-
-	scsi_req->cdb[0] = UNMAP;
-	scsi_req->cdb[8] = len;
-
-	put_unaligned_be16(6 + 16, &buf[0]);
-	put_unaligned_be16(16, &buf[2]);
-	put_unaligned_be64(lba, &buf[8]);
-	put_unaligned_be32(count, &buf[16]);
-
-	req = skreq->req;
-	blk_add_request_payload(req, page, 0, len);
-}
-
 static void skd_request_fn_not_online(struct request_queue *q);
 
 static void skd_request_fn(struct request_queue *q)
@@ -575,7 +547,6 @@ static void skd_request_fn(struct request_queue *q)
 	struct skd_request_context *skreq;
 	struct request *req = NULL;
 	struct skd_scsi_request *scsi_req;
-	struct page *page;
 	unsigned long io_flags;
 	int error;
 	u32 lba;
@@ -669,7 +640,6 @@ static void skd_request_fn(struct request_queue *q)
 		skreq->flush_cmd = 0;
 		skreq->n_sg = 0;
 		skreq->sg_byte_count = 0;
-		skreq->discard_page = 0;
 
 		/*
 		 * OK to now dequeue request from q.
@@ -735,18 +705,7 @@ static void skd_request_fn(struct request_queue *q)
 		else
 			skreq->sg_data_dir = SKD_DATA_DIR_HOST_TO_CARD;
 
-		if (io_flags & REQ_DISCARD) {
-			page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
-			if (!page) {
-				pr_err("request_fn:Page allocation failed.\n");
-				skd_end_request(skdev, skreq, -ENOMEM);
-				break;
-			}
-			skreq->discard_page = 1;
-			req->completion_data = page;
-			skd_prep_discard_cdb(scsi_req, skreq, page, lba, count);
-
-		} else if (flush == SKD_FLUSH_ZERO_SIZE_FIRST) {
+		if (flush == SKD_FLUSH_ZERO_SIZE_FIRST) {
 			skd_prep_zerosize_flush_cdb(scsi_req, skreq);
 			SKD_ASSERT(skreq->flush_cmd == 1);
 
@@ -851,16 +810,6 @@ static void skd_request_fn(struct request_queue *q)
 static void skd_end_request(struct skd_device *skdev,
 			    struct skd_request_context *skreq, int error)
 {
-	struct request *req = skreq->req;
-	unsigned int io_flags = req->cmd_flags;
-
-	if ((io_flags & REQ_DISCARD) &&
-		(skreq->discard_page == 1)) {
-		pr_debug("%s:%s:%d, free the page!",
-			 skdev->name, __func__, __LINE__);
-		__free_page(req->completion_data);
-	}
-
 	if (unlikely(error)) {
 		struct request *req = skreq->req;
 		char *cmd = (rq_data_dir(req) == READ) ? "read" : "write";
@@ -4412,19 +4361,13 @@ static int skd_cons_disk(struct skd_device *skdev)
 	disk->queue = q;
 	q->queuedata = skdev;
 
-	blk_queue_flush(q, REQ_FLUSH | REQ_FUA);
+	blk_queue_write_cache(q, true, true);
 	blk_queue_max_segments(q, skdev->sgs_per_request);
 	blk_queue_max_hw_sectors(q, SKD_N_MAX_SECTORS);
 
 	/* set sysfs ptimal_io_size to 8K */
 	blk_queue_io_opt(q, 8192);
 
-	/* DISCARD Flag initialization. */
-	q->limits.discard_granularity = 8192;
-	q->limits.discard_alignment = 0;
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	q->limits.discard_zeroes_data = 1;
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q);
 

drivers/block/virtio_blk.c

@@ -493,11 +493,7 @@ static void virtblk_update_cache_mode(struct virtio_device *vdev)
 	u8 writeback = virtblk_get_cache_mode(vdev);
 	struct virtio_blk *vblk = vdev->priv;
 
-	if (writeback)
-		blk_queue_flush(vblk->disk->queue, REQ_FLUSH);
-	else
-		blk_queue_flush(vblk->disk->queue, 0);
-
+	blk_queue_write_cache(vblk->disk->queue, writeback, false);
 	revalidate_disk(vblk->disk);
 }
 

drivers/block/xen-blkback/xenbus.c

@@ -477,7 +477,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 		vbd->type |= VDISK_REMOVABLE;
 
 	q = bdev_get_queue(bdev);
-	if (q && q->flush_flags)
+	if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags))
 		vbd->flush_support = true;
 
 	if (q && blk_queue_secdiscard(q))

drivers/block/xen-blkfront.c

@@ -998,7 +998,8 @@ static const char *flush_info(unsigned int feature_flush)
 
 static void xlvbd_flush(struct blkfront_info *info)
 {
-	blk_queue_flush(info->rq, info->feature_flush);
+	blk_queue_write_cache(info->rq, info->feature_flush & REQ_FLUSH,
+				info->feature_flush & REQ_FUA);
 	pr_info("blkfront: %s: %s %s %s %s %s\n",
 		info->gd->disk_name, flush_info(info->feature_flush),
 		"persistent grants:", info->feature_persistent ?

drivers/ide/ide-disk.c

@@ -522,7 +522,7 @@ static int ide_do_setfeature(ide_drive_t *drive, u8 feature, u8 nsect)
 static void update_flush(ide_drive_t *drive)
 {
 	u16 *id = drive->id;
-	unsigned flush = 0;
+	bool wc = false;
 
 	if (drive->dev_flags & IDE_DFLAG_WCACHE) {
 		unsigned long long capacity;
@@ -546,12 +546,12 @@ static void update_flush(ide_drive_t *drive)
 		       drive->name, barrier ? "" : "not ");
 
 		if (barrier) {
-			flush = REQ_FLUSH;
+			wc = true;
 			blk_queue_prep_rq(drive->queue, idedisk_prep_fn);
 		}
 	}
 
-	blk_queue_flush(drive->queue, flush);
+	blk_queue_write_cache(drive->queue, wc, false);
 }
 
 ide_devset_get_flag(wcache, IDE_DFLAG_WCACHE);

drivers/lightnvm/core.c

@@ -30,23 +30,35 @@
 #include <linux/sched/sysctl.h>
 #include <uapi/linux/lightnvm.h>
 
-static LIST_HEAD(nvm_targets);
+static LIST_HEAD(nvm_tgt_types);
 static LIST_HEAD(nvm_mgrs);
 static LIST_HEAD(nvm_devices);
+static LIST_HEAD(nvm_targets);
 static DECLARE_RWSEM(nvm_lock);
 
+static struct nvm_target *nvm_find_target(const char *name)
+{
+	struct nvm_target *tgt;
+
+	list_for_each_entry(tgt, &nvm_targets, list)
+		if (!strcmp(name, tgt->disk->disk_name))
+			return tgt;
+
+	return NULL;
+}
+
 static struct nvm_tgt_type *nvm_find_target_type(const char *name)
 {
 	struct nvm_tgt_type *tt;
 
-	list_for_each_entry(tt, &nvm_targets, list)
+	list_for_each_entry(tt, &nvm_tgt_types, list)
 		if (!strcmp(name, tt->name))
 			return tt;
 
 	return NULL;
 }
 
-int nvm_register_target(struct nvm_tgt_type *tt)
+int nvm_register_tgt_type(struct nvm_tgt_type *tt)
 {
 	int ret = 0;
 
@@ -54,14 +66,14 @@ int nvm_register_target(struct nvm_tgt_type *tt)
 	if (nvm_find_target_type(tt->name))
 		ret = -EEXIST;
 	else
-		list_add(&tt->list, &nvm_targets);
+		list_add(&tt->list, &nvm_tgt_types);
 	up_write(&nvm_lock);
 
 	return ret;
 }
-EXPORT_SYMBOL(nvm_register_target);
+EXPORT_SYMBOL(nvm_register_tgt_type);
 
-void nvm_unregister_target(struct nvm_tgt_type *tt)
+void nvm_unregister_tgt_type(struct nvm_tgt_type *tt)
 {
 	if (!tt)
 		return;
@@ -70,20 +82,20 @@ void nvm_unregister_target(struct nvm_tgt_type *tt)
 	list_del(&tt->list);
 	up_write(&nvm_lock);
 }
-EXPORT_SYMBOL(nvm_unregister_target);
+EXPORT_SYMBOL(nvm_unregister_tgt_type);
 
 void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags,
 							dma_addr_t *dma_handler)
 {
-	return dev->ops->dev_dma_alloc(dev, dev->ppalist_pool, mem_flags,
+	return dev->ops->dev_dma_alloc(dev, dev->dma_pool, mem_flags,
 								dma_handler);
 }
 EXPORT_SYMBOL(nvm_dev_dma_alloc);
 
-void nvm_dev_dma_free(struct nvm_dev *dev, void *ppa_list,
+void nvm_dev_dma_free(struct nvm_dev *dev, void *addr,
 							dma_addr_t dma_handler)
 {
-	dev->ops->dev_dma_free(dev->ppalist_pool, ppa_list, dma_handler);
+	dev->ops->dev_dma_free(dev->dma_pool, addr, dma_handler);
 }
 EXPORT_SYMBOL(nvm_dev_dma_free);
 
@@ -214,8 +226,8 @@ void nvm_addr_to_generic_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	int i;
 
-	if (rqd->nr_pages > 1) {
-		for (i = 0; i < rqd->nr_pages; i++)
+	if (rqd->nr_ppas > 1) {
+		for (i = 0; i < rqd->nr_ppas; i++)
 			rqd->ppa_list[i] = dev_to_generic_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
@@ -228,8 +240,8 @@ void nvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
 	int i;
 
-	if (rqd->nr_pages > 1) {
-		for (i = 0; i < rqd->nr_pages; i++)
+	if (rqd->nr_ppas > 1) {
+		for (i = 0; i < rqd->nr_ppas; i++)
 			rqd->ppa_list[i] = generic_to_dev_addr(dev,
 							rqd->ppa_list[i]);
 	} else {
@@ -239,33 +251,36 @@ void nvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
 EXPORT_SYMBOL(nvm_generic_to_addr_mode);
 
 int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
-					struct ppa_addr *ppas, int nr_ppas)
+				struct ppa_addr *ppas, int nr_ppas, int vblk)
 {
 	int i, plane_cnt, pl_idx;
 
-	if (dev->plane_mode == NVM_PLANE_SINGLE && nr_ppas == 1) {
-		rqd->nr_pages = 1;
+	if ((!vblk || dev->plane_mode == NVM_PLANE_SINGLE) && nr_ppas == 1) {
+		rqd->nr_ppas = nr_ppas;
 		rqd->ppa_addr = ppas[0];
 
 		return 0;
 	}
 
-	plane_cnt = dev->plane_mode;
-	rqd->nr_pages = plane_cnt * nr_ppas;
-
-	if (dev->ops->max_phys_sect < rqd->nr_pages)
-		return -EINVAL;
-
+	rqd->nr_ppas = nr_ppas;
 	rqd->ppa_list = nvm_dev_dma_alloc(dev, GFP_KERNEL, &rqd->dma_ppa_list);
 	if (!rqd->ppa_list) {
 		pr_err("nvm: failed to allocate dma memory\n");
 		return -ENOMEM;
 	}
 
-	for (pl_idx = 0; pl_idx < plane_cnt; pl_idx++) {
+	if (!vblk) {
+		for (i = 0; i < nr_ppas; i++)
+			rqd->ppa_list[i] = ppas[i];
+	} else {
+		plane_cnt = dev->plane_mode;
+		rqd->nr_ppas *= plane_cnt;
+
 		for (i = 0; i < nr_ppas; i++) {
-			ppas[i].g.pl = pl_idx;
-			rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppas[i];
+			for (pl_idx = 0; pl_idx < plane_cnt; pl_idx++) {
+				ppas[i].g.pl = pl_idx;
+				rqd->ppa_list[(pl_idx * nr_ppas) + i] = ppas[i];
+			}
 		}
 	}
 
@@ -292,7 +307,7 @@ int nvm_erase_ppa(struct nvm_dev *dev, struct ppa_addr *ppas, int nr_ppas)
 
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
-	ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas);
+	ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
 	if (ret)
 		return ret;
 
@@ -322,11 +337,10 @@ static void nvm_end_io_sync(struct nvm_rq *rqd)
 	complete(waiting);
 }
 
-int nvm_submit_ppa(struct nvm_dev *dev, struct ppa_addr *ppa, int nr_ppas,
-				int opcode, int flags, void *buf, int len)
+int __nvm_submit_ppa(struct nvm_dev *dev, struct nvm_rq *rqd, int opcode,
+						int flags, void *buf, int len)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	struct nvm_rq rqd;
 	struct bio *bio;
 	int ret;
 	unsigned long hang_check;
@@ -335,23 +349,21 @@ int nvm_submit_ppa(struct nvm_dev *dev, struct ppa_addr *ppa, int nr_ppas,
 	if (IS_ERR_OR_NULL(bio))
 		return -ENOMEM;
 
-	memset(&rqd, 0, sizeof(struct nvm_rq));
-	ret = nvm_set_rqd_ppalist(dev, &rqd, ppa, nr_ppas);
+	nvm_generic_to_addr_mode(dev, rqd);
+
+	rqd->dev = dev;
+	rqd->opcode = opcode;
+	rqd->flags = flags;
+	rqd->bio = bio;
+	rqd->wait = &wait;
+	rqd->end_io = nvm_end_io_sync;
+
+	ret = dev->ops->submit_io(dev, rqd);
 	if (ret) {
 		bio_put(bio);
 		return ret;
 	}
 
-	rqd.opcode = opcode;
-	rqd.bio = bio;
-	rqd.wait = &wait;
-	rqd.dev = dev;
-	rqd.end_io = nvm_end_io_sync;
-	rqd.flags = flags;
-	nvm_generic_to_addr_mode(dev, &rqd);
-
-	ret = dev->ops->submit_io(dev, &rqd);
-
 	/* Prevent hang_check timer from firing at us during very long I/O */
 	hang_check = sysctl_hung_task_timeout_secs;
 	if (hang_check)
@@ -359,12 +371,113 @@ int nvm_submit_ppa(struct nvm_dev *dev, struct ppa_addr *ppa, int nr_ppas,
 	else
 		wait_for_completion_io(&wait);
 
+	return rqd->error;
+}
+
+/**
+ * nvm_submit_ppa_list - submit user-defined ppa list to device. The user must
+ *			 take to free ppa list if necessary.
+ * @dev:	device
+ * @ppa_list:	user created ppa_list
+ * @nr_ppas:	length of ppa_list
+ * @opcode:	device opcode
+ * @flags:	device flags
+ * @buf:	data buffer
+ * @len:	data buffer length
+ */
+int nvm_submit_ppa_list(struct nvm_dev *dev, struct ppa_addr *ppa_list,
+			int nr_ppas, int opcode, int flags, void *buf, int len)
+{
+	struct nvm_rq rqd;
+
+	if (dev->ops->max_phys_sect < nr_ppas)
+		return -EINVAL;
+
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+
+	rqd.nr_ppas = nr_ppas;
+	if (nr_ppas > 1)
+		rqd.ppa_list = ppa_list;
+	else
+		rqd.ppa_addr = ppa_list[0];
+
+	return __nvm_submit_ppa(dev, &rqd, opcode, flags, buf, len);
+}
+EXPORT_SYMBOL(nvm_submit_ppa_list);
+
+/**
+ * nvm_submit_ppa - submit PPAs to device. PPAs will automatically be unfolded
+ *		    as single, dual, quad plane PPAs depending on device type.
+ * @dev:	device
+ * @ppa:	user created ppa_list
+ * @nr_ppas:	length of ppa_list
+ * @opcode:	device opcode
+ * @flags:	device flags
+ * @buf:	data buffer
+ * @len:	data buffer length
+ */
+int nvm_submit_ppa(struct nvm_dev *dev, struct ppa_addr *ppa, int nr_ppas,
+				int opcode, int flags, void *buf, int len)
+{
+	struct nvm_rq rqd;
+	int ret;
+
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+	ret = nvm_set_rqd_ppalist(dev, &rqd, ppa, nr_ppas, 1);
+	if (ret)
+		return ret;
+
+	ret = __nvm_submit_ppa(dev, &rqd, opcode, flags, buf, len);
+
 	nvm_free_rqd_ppalist(dev, &rqd);
 
-	return rqd.error;
+	return ret;
 }
 EXPORT_SYMBOL(nvm_submit_ppa);
 
+/*
+ * folds a bad block list from its plane representation to its virtual
+ * block representation. The fold is done in place and reduced size is
+ * returned.
+ *
+ * If any of the planes status are bad or grown bad block, the virtual block
+ * is marked bad. If not bad, the first plane state acts as the block state.
+ */
+int nvm_bb_tbl_fold(struct nvm_dev *dev, u8 *blks, int nr_blks)
+{
+	int blk, offset, pl, blktype;
+
+	if (nr_blks != dev->blks_per_lun * dev->plane_mode)
+		return -EINVAL;
+
+	for (blk = 0; blk < dev->blks_per_lun; blk++) {
+		offset = blk * dev->plane_mode;
+		blktype = blks[offset];
+
+		/* Bad blocks on any planes take precedence over other types */
+		for (pl = 0; pl < dev->plane_mode; pl++) {
+			if (blks[offset + pl] &
+					(NVM_BLK_T_BAD|NVM_BLK_T_GRWN_BAD)) {
+				blktype = blks[offset + pl];
+				break;
+			}
+		}
+
+		blks[blk] = blktype;
+	}
+
+	return dev->blks_per_lun;
+}
+EXPORT_SYMBOL(nvm_bb_tbl_fold);
+
+int nvm_get_bb_tbl(struct nvm_dev *dev, struct ppa_addr ppa, u8 *blks)
+{
+	ppa = generic_to_dev_addr(dev, ppa);
+
+	return dev->ops->get_bb_tbl(dev, ppa, blks);
+}
+EXPORT_SYMBOL(nvm_get_bb_tbl);
+
 static int nvm_init_slc_tbl(struct nvm_dev *dev, struct nvm_id_group *grp)
 {
 	int i;
@@ -414,6 +527,7 @@ static int nvm_core_init(struct nvm_dev *dev)
 {
 	struct nvm_id *id = &dev->identity;
 	struct nvm_id_group *grp = &id->groups[0];
+	int ret;
 
 	/* device values */
 	dev->nr_chnls = grp->num_ch;
@@ -421,6 +535,8 @@ static int nvm_core_init(struct nvm_dev *dev)
 	dev->pgs_per_blk = grp->num_pg;
 	dev->blks_per_lun = grp->num_blk;
 	dev->nr_planes = grp->num_pln;
+	dev->fpg_size = grp->fpg_sz;
+	dev->pfpg_size = grp->fpg_sz * grp->num_pln;
 	dev->sec_size = grp->csecs;
 	dev->oob_size = grp->sos;
 	dev->sec_per_pg = grp->fpg_sz / grp->csecs;
@@ -430,33 +546,16 @@ static int nvm_core_init(struct nvm_dev *dev)
 	dev->plane_mode = NVM_PLANE_SINGLE;
 	dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size;
 
-	if (grp->mtype != 0) {
-		pr_err("nvm: memory type not supported\n");
-		return -EINVAL;
-	}
-
-	switch (grp->fmtype) {
-	case NVM_ID_FMTYPE_SLC:
-		if (nvm_init_slc_tbl(dev, grp))
-			return -ENOMEM;
-		break;
-	case NVM_ID_FMTYPE_MLC:
-		if (nvm_init_mlc_tbl(dev, grp))
-			return -ENOMEM;
-		break;
-	default:
-		pr_err("nvm: flash type not supported\n");
-		return -EINVAL;
-	}
-
-	if (!dev->lps_per_blk)
-		pr_info("nvm: lower page programming table missing\n");
-
 	if (grp->mpos & 0x020202)
 		dev->plane_mode = NVM_PLANE_DOUBLE;
 	if (grp->mpos & 0x040404)
 		dev->plane_mode = NVM_PLANE_QUAD;
 
+	if (grp->mtype != 0) {
+		pr_err("nvm: memory type not supported\n");
+		return -EINVAL;
+	}
+
 	/* calculated values */
 	dev->sec_per_pl = dev->sec_per_pg * dev->nr_planes;
 	dev->sec_per_blk = dev->sec_per_pl * dev->pgs_per_blk;
@@ -468,11 +567,73 @@ static int nvm_core_init(struct nvm_dev *dev)
 					sizeof(unsigned long), GFP_KERNEL);
 	if (!dev->lun_map)
 		return -ENOMEM;
-	INIT_LIST_HEAD(&dev->online_targets);
+
+	switch (grp->fmtype) {
+	case NVM_ID_FMTYPE_SLC:
+		if (nvm_init_slc_tbl(dev, grp)) {
+			ret = -ENOMEM;
+			goto err_fmtype;
+		}
+		break;
+	case NVM_ID_FMTYPE_MLC:
+		if (nvm_init_mlc_tbl(dev, grp)) {
+			ret = -ENOMEM;
+			goto err_fmtype;
+		}
+		break;
+	default:
+		pr_err("nvm: flash type not supported\n");
+		ret = -EINVAL;
+		goto err_fmtype;
+	}
+
 	mutex_init(&dev->mlock);
 	spin_lock_init(&dev->lock);
 
 	return 0;
+err_fmtype:
+	kfree(dev->lun_map);
+	return ret;
+}
+
+static void nvm_remove_target(struct nvm_target *t)
+{
+	struct nvm_tgt_type *tt = t->type;
+	struct gendisk *tdisk = t->disk;
+	struct request_queue *q = tdisk->queue;
+
+	lockdep_assert_held(&nvm_lock);
+
+	del_gendisk(tdisk);
+	blk_cleanup_queue(q);
+
+	if (tt->exit)
+		tt->exit(tdisk->private_data);
+
+	put_disk(tdisk);
+
+	list_del(&t->list);
+	kfree(t);
+}
+
+static void nvm_free_mgr(struct nvm_dev *dev)
+{
+	struct nvm_target *tgt, *tmp;
+
+	if (!dev->mt)
+		return;
+
+	down_write(&nvm_lock);
+	list_for_each_entry_safe(tgt, tmp, &nvm_targets, list) {
+		if (tgt->dev != dev)
+			continue;
+
+		nvm_remove_target(tgt);
+	}
+	up_write(&nvm_lock);
+
+	dev->mt->unregister_mgr(dev);
+	dev->mt = NULL;
 }
 
 static void nvm_free(struct nvm_dev *dev)
@@ -480,10 +641,10 @@ static void nvm_free(struct nvm_dev *dev)
 	if (!dev)
 		return;
 
-	if (dev->mt)
-		dev->mt->unregister_mgr(dev);
+	nvm_free_mgr(dev);
 
 	kfree(dev->lptbl);
+	kfree(dev->lun_map);
 }
 
 static int nvm_init(struct nvm_dev *dev)
@@ -530,8 +691,8 @@ static int nvm_init(struct nvm_dev *dev)
 
 static void nvm_exit(struct nvm_dev *dev)
 {
-	if (dev->ppalist_pool)
-		dev->ops->destroy_dma_pool(dev->ppalist_pool);
+	if (dev->dma_pool)
+		dev->ops->destroy_dma_pool(dev->dma_pool);
 	nvm_free(dev);
 
 	pr_info("nvm: successfully unloaded\n");
@@ -565,9 +726,9 @@ int nvm_register(struct request_queue *q, char *disk_name,
 	}
 
 	if (dev->ops->max_phys_sect > 1) {
-		dev->ppalist_pool = dev->ops->create_dma_pool(dev, "ppalist");
-		if (!dev->ppalist_pool) {
-			pr_err("nvm: could not create ppa pool\n");
+		dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist");
+		if (!dev->dma_pool) {
+			pr_err("nvm: could not create dma pool\n");
 			ret = -ENOMEM;
 			goto err_init;
 		}
@@ -613,7 +774,6 @@ void nvm_unregister(char *disk_name)
 	up_write(&nvm_lock);
 
 	nvm_exit(dev);
-	kfree(dev->lun_map);
 	kfree(dev);
 }
 EXPORT_SYMBOL(nvm_unregister);
@@ -645,12 +805,11 @@ static int nvm_create_target(struct nvm_dev *dev,
 		return -EINVAL;
 	}
 
-	list_for_each_entry(t, &dev->online_targets, list) {
-		if (!strcmp(create->tgtname, t->disk->disk_name)) {
-			pr_err("nvm: target name already exists.\n");
-			up_write(&nvm_lock);
-			return -EINVAL;
-		}
+	t = nvm_find_target(create->tgtname);
+	if (t) {
+		pr_err("nvm: target name already exists.\n");
+		up_write(&nvm_lock);
+		return -EINVAL;
 	}
 	up_write(&nvm_lock);
 
@@ -688,9 +847,10 @@ static int nvm_create_target(struct nvm_dev *dev,
 
 	t->type = tt;
 	t->disk = tdisk;
+	t->dev = dev;
 
 	down_write(&nvm_lock);
-	list_add_tail(&t->list, &dev->online_targets);
+	list_add_tail(&t->list, &nvm_targets);
 	up_write(&nvm_lock);
 
 	return 0;
@@ -703,26 +863,6 @@ static int nvm_create_target(struct nvm_dev *dev,
 	return -ENOMEM;
 }
 
-static void nvm_remove_target(struct nvm_target *t)
-{
-	struct nvm_tgt_type *tt = t->type;
-	struct gendisk *tdisk = t->disk;
-	struct request_queue *q = tdisk->queue;
-
-	lockdep_assert_held(&nvm_lock);
-
-	del_gendisk(tdisk);
-	blk_cleanup_queue(q);
-
-	if (tt->exit)
-		tt->exit(tdisk->private_data);
-
-	put_disk(tdisk);
-
-	list_del(&t->list);
-	kfree(t);
-}
-
 static int __nvm_configure_create(struct nvm_ioctl_create *create)
 {
 	struct nvm_dev *dev;
@@ -753,26 +893,19 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
 
 static int __nvm_configure_remove(struct nvm_ioctl_remove *remove)
 {
-	struct nvm_target *t = NULL;
-	struct nvm_dev *dev;
-	int ret = -1;
+	struct nvm_target *t;
 
 	down_write(&nvm_lock);
-	list_for_each_entry(dev, &nvm_devices, devices)
-		list_for_each_entry(t, &dev->online_targets, list) {
-			if (!strcmp(remove->tgtname, t->disk->disk_name)) {
-				nvm_remove_target(t);
-				ret = 0;
-				break;
-			}
-		}
-	up_write(&nvm_lock);
-
-	if (ret) {
+	t = nvm_find_target(remove->tgtname);
+	if (!t) {
 		pr_err("nvm: target \"%s\" doesn't exist.\n", remove->tgtname);
+		up_write(&nvm_lock);
 		return -EINVAL;
 	}
 
+	nvm_remove_target(t);
+	up_write(&nvm_lock);
+
 	return 0;
 }
 
@@ -921,7 +1054,7 @@ static long nvm_ioctl_info(struct file *file, void __user *arg)
 	info->version[2] = NVM_VERSION_PATCH;
 
 	down_write(&nvm_lock);
-	list_for_each_entry(tt, &nvm_targets, list) {
+	list_for_each_entry(tt, &nvm_tgt_types, list) {
 		struct nvm_ioctl_info_tgt *tgt = &info->tgts[tgt_iter];
 
 		tgt->version[0] = tt->version[0];
@@ -1118,10 +1251,7 @@ static long nvm_ioctl_dev_factory(struct file *file, void __user *arg)
 		return -EINVAL;
 	}
 
-	if (dev->mt) {
-		dev->mt->unregister_mgr(dev);
-		dev->mt = NULL;
-	}
+	nvm_free_mgr(dev);
 
 	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT)
 		return nvm_dev_factory(dev, fact.flags);

drivers/lightnvm/gennvm.c

@@ -129,27 +129,25 @@ static int gennvm_luns_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	return 0;
 }
 
-static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks,
-								void *private)
+static int gennvm_block_bb(struct gen_nvm *gn, struct ppa_addr ppa,
+							u8 *blks, int nr_blks)
 {
-	struct gen_nvm *gn = private;
 	struct nvm_dev *dev = gn->dev;
 	struct gen_lun *lun;
 	struct nvm_block *blk;
 	int i;
 
+	nr_blks = nvm_bb_tbl_fold(dev, blks, nr_blks);
+	if (nr_blks < 0)
+		return nr_blks;
+
 	lun = &gn->luns[(dev->luns_per_chnl * ppa.g.ch) + ppa.g.lun];
 
-	for (i = 0; i < nr_blocks; i++) {
+	for (i = 0; i < nr_blks; i++) {
 		if (blks[i] == 0)
 			continue;
 
 		blk = &lun->vlun.blocks[i];
-		if (!blk) {
-			pr_err("gennvm: BB data is out of bounds.\n");
-			return -EINVAL;
-		}
-
 		list_move_tail(&blk->list, &lun->bb_list);
 		lun->vlun.nr_bad_blocks++;
 		lun->vlun.nr_free_blocks--;
@@ -216,13 +214,21 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 	struct gen_lun *lun;
 	struct nvm_block *block;
 	sector_t lun_iter, blk_iter, cur_block_id = 0;
-	int ret;
+	int ret, nr_blks;
+	u8 *blks;
+
+	nr_blks = dev->blks_per_lun * dev->plane_mode;
+	blks = kmalloc(nr_blks, GFP_KERNEL);
+	if (!blks)
+		return -ENOMEM;
 
 	gennvm_for_each_lun(gn, lun, lun_iter) {
 		lun->vlun.blocks = vzalloc(sizeof(struct nvm_block) *
 							dev->blks_per_lun);
-		if (!lun->vlun.blocks)
+		if (!lun->vlun.blocks) {
+			kfree(blks);
 			return -ENOMEM;
+		}
 
 		for (blk_iter = 0; blk_iter < dev->blks_per_lun; blk_iter++) {
 			block = &lun->vlun.blocks[blk_iter];
@@ -246,14 +252,15 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 
 			ppa.ppa = 0;
 			ppa.g.ch = lun->vlun.chnl_id;
-			ppa.g.lun = lun->vlun.id;
-			ppa = generic_to_dev_addr(dev, ppa);
+			ppa.g.lun = lun->vlun.lun_id;
+
+			ret = nvm_get_bb_tbl(dev, ppa, blks);
+			if (ret)
+				pr_err("gennvm: could not get BB table\n");
 
-			ret = dev->ops->get_bb_tbl(dev, ppa,
-						dev->blks_per_lun,
-						gennvm_block_bb, gn);
+			ret = gennvm_block_bb(gn, ppa, blks, nr_blks);
 			if (ret)
-				pr_err("gennvm: could not read BB table\n");
+				pr_err("gennvm: BB table map failed\n");
 		}
 	}
 
@@ -266,6 +273,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn)
 		}
 	}
 
+	kfree(blks);
 	return 0;
 }
 
@@ -399,64 +407,60 @@ static void gennvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk)
 	spin_unlock(&vlun->lock);
 }
 
-static void gennvm_blk_set_type(struct nvm_dev *dev, struct ppa_addr *ppa,
-								int type)
+static void gennvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type)
 {
 	struct gen_nvm *gn = dev->mp;
 	struct gen_lun *lun;
 	struct nvm_block *blk;
 
-	if (unlikely(ppa->g.ch > dev->nr_chnls ||
-					ppa->g.lun > dev->luns_per_chnl ||
-					ppa->g.blk > dev->blks_per_lun)) {
+	pr_debug("gennvm: ppa  (ch: %u lun: %u blk: %u pg: %u) -> %u\n",
+			ppa.g.ch, ppa.g.lun, ppa.g.blk, ppa.g.pg, type);
+
+	if (unlikely(ppa.g.ch > dev->nr_chnls ||
+					ppa.g.lun > dev->luns_per_chnl ||
+					ppa.g.blk > dev->blks_per_lun)) {
 		WARN_ON_ONCE(1);
 		pr_err("gennvm: ppa broken (ch: %u > %u lun: %u > %u blk: %u > %u",
-				ppa->g.ch, dev->nr_chnls,
-				ppa->g.lun, dev->luns_per_chnl,
-				ppa->g.blk, dev->blks_per_lun);
+				ppa.g.ch, dev->nr_chnls,
+				ppa.g.lun, dev->luns_per_chnl,
+				ppa.g.blk, dev->blks_per_lun);
 		return;
 	}
 
-	lun = &gn->luns[ppa->g.lun * ppa->g.ch];
-	blk = &lun->vlun.blocks[ppa->g.blk];
+	lun = &gn->luns[ppa.g.lun * ppa.g.ch];
+	blk = &lun->vlun.blocks[ppa.g.blk];
 
 	/* will be moved to bb list on put_blk from target */
 	blk->state = type;
 }
 
-/* mark block bad. It is expected the target recover from the error. */
+/*
+ * mark block bad in gennvm. It is expected that the target recovers separately
+ */
 static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd)
 {
-	int i;
-
-	if (!dev->ops->set_bb_tbl)
-		return;
-
-	if (dev->ops->set_bb_tbl(dev, rqd, 1))
-		return;
+	int bit = -1;
+	int max_secs = dev->ops->max_phys_sect;
+	void *comp_bits = &rqd->ppa_status;
 
 	nvm_addr_to_generic_mode(dev, rqd);
 
 	/* look up blocks and mark them as bad */
-	if (rqd->nr_pages > 1)
-		for (i = 0; i < rqd->nr_pages; i++)
-			gennvm_blk_set_type(dev, &rqd->ppa_list[i],
-						NVM_BLK_ST_BAD);
-	else
-		gennvm_blk_set_type(dev, &rqd->ppa_addr, NVM_BLK_ST_BAD);
+	if (rqd->nr_ppas == 1) {
+		gennvm_mark_blk(dev, rqd->ppa_addr, NVM_BLK_ST_BAD);
+		return;
+	}
+
+	while ((bit = find_next_bit(comp_bits, max_secs, bit + 1)) < max_secs)
+		gennvm_mark_blk(dev, rqd->ppa_list[bit], NVM_BLK_ST_BAD);
 }
 
 static void gennvm_end_io(struct nvm_rq *rqd)
 {
 	struct nvm_tgt_instance *ins = rqd->ins;
 
-	switch (rqd->error) {
-	case NVM_RSP_SUCCESS:
-	case NVM_RSP_ERR_EMPTYPAGE:
-		break;
-	case NVM_RSP_ERR_FAILWRITE:
+	if (rqd->error == NVM_RSP_ERR_FAILWRITE)
 		gennvm_mark_blk_bad(rqd->dev, rqd);
-	}
 
 	ins->tt->end_io(rqd);
 }
@@ -539,6 +543,8 @@ static struct nvmm_type gennvm = {
 	.submit_io		= gennvm_submit_io,
 	.erase_blk		= gennvm_erase_blk,
 
+	.mark_blk		= gennvm_mark_blk,
+
 	.get_lun		= gennvm_get_lun,
 	.reserve_lun		= gennvm_reserve_lun,
 	.release_lun		= gennvm_release_lun,

drivers/lightnvm/rrpc.c

@@ -405,9 +405,8 @@ static void rrpc_block_gc(struct work_struct *work)
 									ws_gc);
 	struct rrpc *rrpc = gcb->rrpc;
 	struct rrpc_block *rblk = gcb->rblk;
+	struct rrpc_lun *rlun = rblk->rlun;
 	struct nvm_dev *dev = rrpc->dev;
-	struct nvm_lun *lun = rblk->parent->lun;
-	struct rrpc_lun *rlun = &rrpc->luns[lun->id - rrpc->lun_offset];
 
 	mempool_free(gcb, rrpc->gcb_pool);
 	pr_debug("nvm: block '%lu' being reclaimed\n", rblk->parent->id);
@@ -508,9 +507,9 @@ static void rrpc_gc_queue(struct work_struct *work)
 									ws_gc);
 	struct rrpc *rrpc = gcb->rrpc;
 	struct rrpc_block *rblk = gcb->rblk;
+	struct rrpc_lun *rlun = rblk->rlun;
 	struct nvm_lun *lun = rblk->parent->lun;
 	struct nvm_block *blk = rblk->parent;
-	struct rrpc_lun *rlun = &rrpc->luns[lun->id - rrpc->lun_offset];
 
 	spin_lock(&rlun->lock);
 	list_add_tail(&rblk->prio, &rlun->prio_list);
@@ -696,7 +695,7 @@ static void rrpc_end_io(struct nvm_rq *rqd)
 {
 	struct rrpc *rrpc = container_of(rqd->ins, struct rrpc, instance);
 	struct rrpc_rq *rrqd = nvm_rq_to_pdu(rqd);
-	uint8_t npages = rqd->nr_pages;
+	uint8_t npages = rqd->nr_ppas;
 	sector_t laddr = rrpc_get_laddr(rqd->bio) - npages;
 
 	if (bio_data_dir(rqd->bio) == WRITE)
@@ -711,8 +710,6 @@ static void rrpc_end_io(struct nvm_rq *rqd)
 
 	if (npages > 1)
 		nvm_dev_dma_free(rrpc->dev, rqd->ppa_list, rqd->dma_ppa_list);
-	if (rqd->metadata)
-		nvm_dev_dma_free(rrpc->dev, rqd->metadata, rqd->dma_metadata);
 
 	mempool_free(rqd, rrpc->rq_pool);
 }
@@ -886,7 +883,7 @@ static int rrpc_submit_io(struct rrpc *rrpc, struct bio *bio,
 	bio_get(bio);
 	rqd->bio = bio;
 	rqd->ins = &rrpc->instance;
-	rqd->nr_pages = nr_pages;
+	rqd->nr_ppas = nr_pages;
 	rrq->flags = flags;
 
 	err = nvm_submit_io(rrpc->dev, rqd);
@@ -895,7 +892,7 @@ static int rrpc_submit_io(struct rrpc *rrpc, struct bio *bio,
 		bio_put(bio);
 		if (!(flags & NVM_IOTYPE_GC)) {
 			rrpc_unlock_rq(rrpc, rqd);
-			if (rqd->nr_pages > 1)
+			if (rqd->nr_ppas > 1)
 				nvm_dev_dma_free(rrpc->dev,
 			rqd->ppa_list, rqd->dma_ppa_list);
 		}
@@ -1039,11 +1036,8 @@ static int rrpc_map_init(struct rrpc *rrpc)
 {
 	struct nvm_dev *dev = rrpc->dev;
 	sector_t i;
-	u64 slba;
 	int ret;
 
-	slba = rrpc->soffset >> (ilog2(dev->sec_size) - 9);
-
 	rrpc->trans_map = vzalloc(sizeof(struct rrpc_addr) * rrpc->nr_sects);
 	if (!rrpc->trans_map)
 		return -ENOMEM;
@@ -1065,8 +1059,8 @@ static int rrpc_map_init(struct rrpc *rrpc)
 		return 0;
 
 	/* Bring up the mapping table from device */
-	ret = dev->ops->get_l2p_tbl(dev, slba, rrpc->nr_sects, rrpc_l2p_update,
-									rrpc);
+	ret = dev->ops->get_l2p_tbl(dev, rrpc->soffset, rrpc->nr_sects,
+					rrpc_l2p_update, rrpc);
 	if (ret) {
 		pr_err("nvm: rrpc: could not read L2P table.\n");
 		return -EINVAL;
@@ -1207,10 +1201,6 @@ static int rrpc_luns_init(struct rrpc *rrpc, int lun_begin, int lun_end)
 
 		INIT_WORK(&rlun->ws_gc, rrpc_lun_gc);
 		spin_lock_init(&rlun->lock);
-
-		rrpc->total_blocks += dev->blks_per_lun;
-		rrpc->nr_sects += dev->sec_per_lun;
-
 	}
 
 	return 0;
@@ -1224,18 +1214,24 @@ static int rrpc_area_init(struct rrpc *rrpc, sector_t *begin)
 	struct nvm_dev *dev = rrpc->dev;
 	struct nvmm_type *mt = dev->mt;
 	sector_t size = rrpc->nr_sects * dev->sec_size;
+	int ret;
 
 	size >>= 9;
 
-	return mt->get_area(dev, begin, size);
+	ret = mt->get_area(dev, begin, size);
+	if (!ret)
+		*begin >>= (ilog2(dev->sec_size) - 9);
+
+	return ret;
 }
 
 static void rrpc_area_free(struct rrpc *rrpc)
 {
 	struct nvm_dev *dev = rrpc->dev;
 	struct nvmm_type *mt = dev->mt;
+	sector_t begin = rrpc->soffset << (ilog2(dev->sec_size) - 9);
 
-	mt->put_area(dev, rrpc->soffset);
+	mt->put_area(dev, begin);
 }
 
 static void rrpc_free(struct rrpc *rrpc)
@@ -1268,7 +1264,7 @@ static sector_t rrpc_capacity(void *private)
 	sector_t reserved, provisioned;
 
 	/* cur, gc, and two emergency blocks for each lun */
-	reserved = rrpc->nr_luns * dev->max_pages_per_blk * 4;
+	reserved = rrpc->nr_luns * dev->sec_per_blk * 4;
 	provisioned = rrpc->nr_sects - reserved;
 
 	if (reserved > rrpc->nr_sects) {
@@ -1388,6 +1384,8 @@ static void *rrpc_init(struct nvm_dev *dev, struct gendisk *tdisk,
 	INIT_WORK(&rrpc->ws_requeue, rrpc_requeue);
 
 	rrpc->nr_luns = lun_end - lun_begin + 1;
+	rrpc->total_blocks = (unsigned long)dev->blks_per_lun * rrpc->nr_luns;
+	rrpc->nr_sects = (unsigned long long)dev->sec_per_lun * rrpc->nr_luns;
 
 	/* simple round-robin strategy */
 	atomic_set(&rrpc->next_lun, -1);
@@ -1468,12 +1466,12 @@ static struct nvm_tgt_type tt_rrpc = {
 
 static int __init rrpc_module_init(void)
 {
-	return nvm_register_target(&tt_rrpc);
+	return nvm_register_tgt_type(&tt_rrpc);
 }
 
 static void rrpc_module_exit(void)
 {
-	nvm_unregister_target(&tt_rrpc);
+	nvm_unregister_tgt_type(&tt_rrpc);
 }
 
 module_init(rrpc_module_init);