Merge tag 'block-5.12-2021-03-12-v2' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Mostly just random fixes all over the map.

  The only odd-one-out change is finally getting the rename of
  BIO_MAX_PAGES to BIO_MAX_VECS done. This should've been done with the
  multipage bvec change, but it's been left.

  Do it now to avoid hassles around changes piling up for the next merge
  window.

  Summary:

   - NVMe pull request:
      - one more quirk (Dmitry Monakhov)
      - fix max_zone_append_sectors initialization (Chaitanya Kulkarni)
      - nvme-fc reset/create race fix (James Smart)
      - fix status code on aborts/resets (Hannes Reinecke)
      - fix the CSS check for ZNS namespaces (Chaitanya Kulkarni)
      - fix a use after free in a debug printk in nvme-rdma (Lv Yunlong)

   - Follow-up NVMe error fix for NULL 'id' (Christoph)

   - Fixup for the bd_size_lock being IRQ safe, now that the offending
     driver has been dropped (Damien).

   - rsxx probe failure error return (Jia-Ju)

   - umem probe failure error return (Wei)

   - s390/dasd unbind fixes (Stefan)

   - blk-cgroup stats summing fix (Xunlei)

   - zone reset handling fix (Damien)

   - Rename BIO_MAX_PAGES to BIO_MAX_VECS (Christoph)

   - Suppress uevent trigger for hidden devices (Daniel)

   - Fix handling of discard on busy device (Jan)

   - Fix stale cache issue with zone reset (Shin'ichiro)"

* tag 'block-5.12-2021-03-12-v2' of git://git.kernel.dk/linux-block:
  nvme: fix the nsid value to print in nvme_validate_or_alloc_ns
  block: Discard page cache of zone reset target range
  block: Suppress uevent for hidden device when removed
  block: rename BIO_MAX_PAGES to BIO_MAX_VECS
  nvme-pci: add the DISABLE_WRITE_ZEROES quirk for a Samsung PM1725a
  nvme-rdma: Fix a use after free in nvmet_rdma_write_data_done
  nvme-core: check ctrl css before setting up zns
  nvme-fc: fix racing controller reset and create association
  nvme-fc: return NVME_SC_HOST_ABORTED_CMD when a command has been aborted
  nvme-fc: set NVME_REQ_CANCELLED in nvme_fc_terminate_exchange()
  nvme: add NVME_REQ_CANCELLED flag in nvme_cancel_request()
  nvme: simplify error logic in nvme_validate_ns()
  nvme: set max_zone_append_sectors nvme_revalidate_zones
  block: rsxx: fix error return code of rsxx_pci_probe()
  block: Fix REQ_OP_ZONE_RESET_ALL handling
  umem: fix error return code in mm_pci_probe()
  blk-cgroup: Fix the recursive blkg rwstat
  s390/dasd: fix hanging IO request during DASD driver unbind
  s390/dasd: fix hanging DASD driver unbind
  block: Try to handle busy underlying device on discard

15 files changed, 46 insertions, 29 deletions

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 7d9cc433b758..5d9181382ce1 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1324,7 +1324,7 @@ struct bm_extent {
  * A followup commit may allow even bigger BIO sizes,
  * once we thought that through. */
 #define DRBD_MAX_BIO_SIZE (1U << 20)
-#if DRBD_MAX_BIO_SIZE > (BIO_MAX_PAGES << PAGE_SHIFT)
+#if DRBD_MAX_BIO_SIZE > (BIO_MAX_VECS << PAGE_SHIFT)
 #error Architecture not supported: DRBD_MAX_BIO_SIZE > BIO_MAX_SIZE
 #endif
 #define DRBD_MAX_BIO_SIZE_SAFE (1U << 12)       /* Works always = 4k */
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 5ac1881396af..227e1be4c6f9 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -871,6 +871,7 @@ static int rsxx_pci_probe(struct pci_dev *dev,
 	card->event_wq = create_singlethread_workqueue(DRIVER_NAME"_event");
 	if (!card->event_wq) {
 		dev_err(CARD_TO_DEV(card), "Failed card event setup.\n");
+		st = -ENOMEM;
 		goto failed_event_handler;
 	}
 
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 982732dbe82e..664280f23bee 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -877,6 +877,7 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (card->mm_pages[0].desc == NULL ||
 	    card->mm_pages[1].desc == NULL) {
 		dev_printk(KERN_ERR, &card->dev->dev, "alloc failed\n");
+		ret = -ENOMEM;
 		goto failed_alloc;
 	}
 	reset_page(&card->mm_pages[0]);
@@ -888,8 +889,10 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	spin_lock_init(&card->lock);
 
 	card->queue = blk_alloc_queue(NUMA_NO_NODE);
-	if (!card->queue)
+	if (!card->queue) {
+		ret = -ENOMEM;
 		goto failed_alloc;
+	}
 
 	tasklet_init(&card->tasklet, process_page, (unsigned long)card);
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 71691f32959b..03e1fe4de53d 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -965,7 +965,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
-	q->limits.max_segments		= BIO_MAX_PAGES;
+	q->limits.max_segments		= BIO_MAX_VECS;
 	blk_queue_max_discard_sectors(q, UINT_MAX);
 	q->limits.discard_granularity	= 512;
 	q->limits.io_min		= block_size;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 11c105ecd165..b0ab080f2567 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -229,7 +229,7 @@ static DEFINE_SPINLOCK(dm_crypt_clients_lock);
 static unsigned dm_crypt_clients_n = 0;
 static volatile unsigned long dm_crypt_pages_per_client;
 #define DM_CRYPT_MEMORY_PERCENT			2
-#define DM_CRYPT_MIN_PAGES_PER_CLIENT		(BIO_MAX_PAGES * 16)
+#define DM_CRYPT_MIN_PAGES_PER_CLIENT		(BIO_MAX_VECS * 16)
 
 static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
@@ -3246,7 +3246,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
 		      ARCH_KMALLOC_MINALIGN);
 
-	ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
+	ret = mempool_init(&cc->page_pool, BIO_MAX_VECS, crypt_page_alloc, crypt_page_free, cc);
 	if (ret) {
 		ti->error = "Cannot allocate page mempool";
 		goto bad;
@@ -3373,9 +3373,9 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	/*
 	 * Check if bio is too large, split as needed.
 	 */
-	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) &&
+	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_VECS << PAGE_SHIFT)) &&
 	    (bio_data_dir(bio) == WRITE || cc->on_disk_tag_size))
-		dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+		dm_accept_partial_bio(bio, ((BIO_MAX_VECS << PAGE_SHIFT) >> SECTOR_SHIFT));
 
 	/*
 	 * Ensure that bio is a multiple of internal sector encryption size
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 844c4be11768..4f72b6f66c3a 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -1892,10 +1892,10 @@ restart:
 			list_add(&g->lru, &wbl.list);
 			wbl.size++;
 			g->write_in_progress = true;
-			g->wc_list_contiguous = BIO_MAX_PAGES;
+			g->wc_list_contiguous = BIO_MAX_VECS;
 			f = g;
 			e->wc_list_contiguous++;
-			if (unlikely(e->wc_list_contiguous == BIO_MAX_PAGES)) {
+			if (unlikely(e->wc_list_contiguous == BIO_MAX_VECS)) {
 				if (unlikely(wc->writeback_all)) {
 					next_node = rb_next(&f->rb_node);
 					if (likely(next_node))
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 4337ae0e6af2..0b5dcaabbc15 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -735,7 +735,7 @@ static void r5l_submit_current_io(struct r5l_log *log)
 
 static struct bio *r5l_bio_alloc(struct r5l_log *log)
 {
-	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs);
+	struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &log->bs);
 
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	bio_set_dev(bio, log->rdev->bdev);
@@ -1634,7 +1634,7 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log,
 {
 	struct page *page;
 
-	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs);
+	ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_VECS, &log->bs);
 	if (!ctx->ra_bio)
 		return -ENOMEM;
 
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index e8c118e05dfd..3ddc2aa0b530 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -496,7 +496,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io)
 		if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) {
 			struct bio *prev = bio;
 
-			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
+			bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS,
 					       &ppl_conf->bs);
 			bio->bi_opf = prev->bi_opf;
 			bio->bi_write_hint = prev->bi_write_hint;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e68a8c4ac5a6..a5653892d773 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -380,6 +380,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 		return true;
 
 	nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
+	nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 	blk_mq_complete_request(req);
 	return true;
 }
@@ -1440,7 +1441,7 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 		goto out_free_id;
 	}
 
-	error = -ENODEV;
+	error = NVME_SC_INVALID_NS | NVME_SC_DNR;
 	if ((*id)->ncap == 0) /* namespace not allocated or attached */
 		goto out_free_id;
 
@@ -4038,7 +4039,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
 static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
 {
 	struct nvme_id_ns *id;
-	int ret = -ENODEV;
+	int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
 
 	if (test_bit(NVME_NS_DEAD, &ns->flags))
 		goto out;
@@ -4047,7 +4048,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
 	if (ret)
 		goto out;
 
-	ret = -ENODEV;
+	ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
 	if (!nvme_ns_ids_equal(&ns->head->ids, ids)) {
 		dev_err(ns->ctrl->device,
 			"identifiers changed for nsid %d\n", ns->head->ns_id);
@@ -4065,7 +4066,7 @@ out:
 	 *
 	 * TODO: we should probably schedule a delayed retry here.
 	 */
-	if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR)))
+	if (ret > 0 && (ret & NVME_SC_DNR))
 		nvme_ns_remove(ns);
 }
 
@@ -4095,6 +4096,12 @@ static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 				nsid);
 			break;
 		}
+		if (!nvme_multi_css(ctrl)) {
+			dev_warn(ctrl->device,
+				"command set not reported for nsid: %d\n",
+				nsid);
+			break;
+		}
 		nvme_alloc_ns(ctrl, nsid, &ids);
 		break;
 	default:
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 20dadd86e981..73d073748389 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1956,7 +1956,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
 				sizeof(op->rsp_iu), DMA_FROM_DEVICE);
 
 	if (opstate == FCPOP_STATE_ABORTED)
-		status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+		status = cpu_to_le16(NVME_SC_HOST_ABORTED_CMD << 1);
 	else if (freq->status) {
 		status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
 		dev_info(ctrl->ctrl.device,
@@ -2055,7 +2055,7 @@ done:
 		nvme_fc_complete_rq(rq);
 
 check_error:
-	if (terminate_assoc)
+	if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING)
 		queue_work(nvme_reset_wq, &ctrl->ioerr_work);
 }
 
@@ -2443,6 +2443,7 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 	struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
 
+	op->nreq.flags |= NVME_REQ_CANCELLED;
 	__nvme_fc_abort_op(ctrl, op);
 	return true;
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 17ab3320d28b..7249ae74f71f 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3246,6 +3246,7 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x144d, 0xa822),   /* Samsung PM1725a */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+				NVME_QUIRK_DISABLE_WRITE_ZEROES|
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1987, 0x5016),	/* Phison E16 */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index c7e3ec561ba0..bc2f344f0ae0 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -9,7 +9,13 @@
 
 int nvme_revalidate_zones(struct nvme_ns *ns)
 {
-	return blk_revalidate_disk_zones(ns->disk, NULL);
+	struct request_queue *q = ns->queue;
+	int ret;
+
+	ret = blk_revalidate_disk_zones(ns->disk, NULL);
+	if (!ret)
+		blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
+	return ret;
 }
 
 static int nvme_set_max_append(struct nvme_ctrl *ctrl)
@@ -107,7 +113,6 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
 	blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
-	blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
 free_data:
 	kfree(id);
 	return status;
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 26c587ccd152..2798944899b7 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -50,9 +50,9 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 
 	/*
 	 * nvmet_passthru_map_sg is limitted to using a single bio so limit
-	 * the mdts based on BIO_MAX_PAGES as well
+	 * the mdts based on BIO_MAX_VECS as well
 	 */
-	max_hw_sectors = min_not_zero(BIO_MAX_PAGES << (PAGE_SHIFT - 9),
+	max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9),
 				      max_hw_sectors);
 
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
@@ -191,7 +191,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
 	struct bio *bio;
 	int i;
 
-	if (req->sg_cnt > BIO_MAX_PAGES)
+	if (req->sg_cnt > BIO_MAX_VECS)
 		return -EINVAL;
 
 	if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) {
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 06b6b742bb21..6c1f3ab7649c 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -802,9 +802,8 @@ static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc)
 		nvmet_req_uninit(&rsp->req);
 		nvmet_rdma_release_rsp(rsp);
 		if (wc->status != IB_WC_WR_FLUSH_ERR) {
-			pr_info("RDMA WRITE for CQE 0x%p failed with status %s (%d).\n",
-				wc->wr_cqe, ib_wc_status_msg(wc->status),
-				wc->status);
+			pr_info("RDMA WRITE for CQE failed with status %s (%d).\n",
+				ib_wc_status_msg(wc->status), wc->status);
 			nvmet_rdma_error_comp(queue);
 		}
 		return;
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 28c04a4efa66..ba9ce4e0d30a 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3052,7 +3052,8 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx,
 
 	basedev = block->base;
 	spin_lock_irq(&dq->lock);
-	if (basedev->state < DASD_STATE_READY) {
+	if (basedev->state < DASD_STATE_READY ||
+	    test_bit(DASD_FLAG_OFFLINE, &basedev->flags)) {
 		DBF_DEV_EVENT(DBF_ERR, basedev,
 			      "device not ready for request %p", req);
 		rc = BLK_STS_IOERR;
@@ -3487,8 +3488,6 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	struct dasd_device *device;
 	struct dasd_block *block;
 
-	cdev->handler = NULL;
-
 	device = dasd_device_from_cdev(cdev);
 	if (IS_ERR(device)) {
 		dasd_remove_sysfs_files(cdev);
@@ -3507,6 +3506,7 @@ void dasd_generic_remove(struct ccw_device *cdev)
 	 * no quite down yet.
 	 */
 	dasd_set_target_state(device, DASD_STATE_NEW);
+	cdev->handler = NULL;
 	/* dasd_delete_device destroys the device reference. */
 	block = device->block;
 	dasd_delete_device(device);