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

Pull block fixes from Jens Axboe:
 "Small collection of fixes that would be nice to have in -rc1. This
  contains:

   - NVMe pull request form Christoph, mostly with fixes for nvme-pci,
     host memory buffer in particular.

   - Error handling fixup for cgwb_create(), in case allocation of 'wb'
     fails. From Christophe Jaillet.

   - Ensure that trace_block_getrq() gets the 'dev' in an appropriate
     fashion, to avoid a potential NULL deref. From Greg Thelen.

   - Regression fix for dm-mq with blk-mq, fixing a problem with
     stacking IO schedulers. From me.

   - string.h fixup, fixing an issue with memcpy_and_pad(). This
     original change came in through an NVMe dependency, which is why
     I'm including it here. From Martin Wilck.

   - Fix potential int overflow in __blkdev_sectors_to_bio_pages(), from
     Mikulas.

   - MBR enable fix for sed-opal, from Scott"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: directly insert blk-mq request from blk_insert_cloned_request()
  mm/backing-dev.c: fix an error handling path in 'cgwb_create()'
  string.h: un-fortify memcpy_and_pad
  nvme-pci: implement the HMB entry number and size limitations
  nvme-pci: propagate (some) errors from host memory buffer setup
  nvme-pci: use appropriate initial chunk size for HMB allocation
  nvme-pci: fix host memory buffer allocation fallback
  nvme: fix lightnvm check
  block: fix integer overflow in __blkdev_sectors_to_bio_pages()
  block: sed-opal: Set MBRDone on S3 resume path if TPER is MBREnabled
  block: tolerate tracing of NULL bio

block/blk-core.c

@@ -2342,7 +2342,12 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_sched_insert_request(rq, false, true, false, false);
+		/*
+		 * Since we have a scheduler attached on the top device,
+		 * bypass a potential scheduler on the bottom device for
+		 * insert.
+		 */
+		blk_mq_request_bypass_insert(rq);
 		return BLK_STS_OK;
 	}
 

block/blk-lib.c

@@ -269,9 +269,9 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
  */
 static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
 {
-	sector_t bytes = (nr_sects << 9) + PAGE_SIZE - 1;
+	sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512);
 
-	return min(bytes >> PAGE_SHIFT, (sector_t)BIO_MAX_PAGES);
+	return min(pages, (sector_t)BIO_MAX_PAGES);
 }
 
 /**

block/blk-mq.c

@@ -1401,6 +1401,22 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
+/*
+ * Should only be used carefully, when the caller knows we want to
+ * bypass a potential IO scheduler on the target device.
+ */
+void blk_mq_request_bypass_insert(struct request *rq)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+
+	spin_lock(&hctx->lock);
+	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+
+	blk_mq_run_hw_queue(hctx, false);
+}
+
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			    struct list_head *list)
 

block/blk-mq.h

@@ -54,6 +54,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
+void blk_mq_request_bypass_insert(struct request *rq);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 

block/opal_proto.h

@@ -46,6 +46,7 @@ enum opal_response_token {
 #define GENERIC_HOST_SESSION_NUM 0x41
 
 #define TPER_SYNC_SUPPORTED 0x01
+#define MBR_ENABLED_MASK 0x10
 
 #define TINY_ATOM_DATA_MASK 0x3F
 #define TINY_ATOM_SIGNED 0x40

block/sed-opal.c

@@ -80,6 +80,7 @@ struct parsed_resp {
 
 struct opal_dev {
 	bool supported;
+	bool mbr_enabled;
 
 	void *data;
 	sec_send_recv *send_recv;
@@ -283,6 +284,14 @@ static bool check_tper(const void *data)
 	return true;
 }
 
+static bool check_mbrenabled(const void *data)
+{
+	const struct d0_locking_features *lfeat = data;
+	u8 sup_feat = lfeat->supported_features;
+
+	return !!(sup_feat & MBR_ENABLED_MASK);
+}
+
 static bool check_sum(const void *data)
 {
 	const struct d0_single_user_mode *sum = data;
@@ -417,6 +426,7 @@ static int opal_discovery0_end(struct opal_dev *dev)
 	u32 hlen = be32_to_cpu(hdr->length);
 
 	print_buffer(dev->resp, hlen);
+	dev->mbr_enabled = false;
 
 	if (hlen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
 		pr_debug("Discovery length overflows buffer (%zu+%u)/%u\n",
@@ -442,6 +452,8 @@ static int opal_discovery0_end(struct opal_dev *dev)
 			check_geometry(dev, body);
 			break;
 		case FC_LOCKING:
+			dev->mbr_enabled = check_mbrenabled(body->features);
+			break;
 		case FC_ENTERPRISE:
 		case FC_DATASTORE:
 			/* some ignored properties */
@@ -2190,6 +2202,21 @@ static int __opal_lock_unlock(struct opal_dev *dev,
 	return next(dev);
 }
 
+static int __opal_set_mbr_done(struct opal_dev *dev, struct opal_key *key)
+{
+	u8 mbr_done_tf = 1;
+	const struct opal_step mbrdone_step [] = {
+		{ opal_discovery0, },
+		{ start_admin1LSP_opal_session, key },
+		{ set_mbr_done, &mbr_done_tf },
+		{ end_opal_session, },
+		{ NULL, }
+	};
+
+	dev->steps = mbrdone_step;
+	return next(dev);
+}
+
 static int opal_lock_unlock(struct opal_dev *dev,
 			    struct opal_lock_unlock *lk_unlk)
 {
@@ -2345,6 +2372,11 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 				 suspend->unlk.session.sum);
 			was_failure = true;
 		}
+		if (dev->mbr_enabled) {
+			ret = __opal_set_mbr_done(dev, &suspend->unlk.session.opal_key);
+			if (ret)
+				pr_debug("Failed to set MBR Done in S3 resume\n");
+		}
 	}
 	mutex_unlock(&dev->dev_lock);
 	return was_failure;

drivers/nvme/host/core.c

@@ -1897,6 +1897,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->cntlid = le16_to_cpu(id->cntlid);
 		ctrl->hmpre = le32_to_cpu(id->hmpre);
 		ctrl->hmmin = le32_to_cpu(id->hmmin);
+		ctrl->hmminds = le32_to_cpu(id->hmminds);
+		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
 	kfree(id);
@@ -2377,10 +2379,11 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	nvme_report_ns_ids(ctrl, ns->ns_id, id, ns->eui, ns->nguid, &ns->uuid);
 
-	if (nvme_nvm_ns_supported(ns, id) &&
-				nvme_nvm_register(ns, disk_name, node)) {
-		dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__);
-		goto out_free_id;
+	if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
+		if (nvme_nvm_register(ns, disk_name, node)) {
+			dev_warn(ctrl->device, "LightNVM init failure\n");
+			goto out_free_id;
+		}
 	}
 
 	disk = alloc_disk_node(0, node);

drivers/nvme/host/lightnvm.c

@@ -955,29 +955,3 @@ void nvme_nvm_unregister_sysfs(struct nvme_ns *ns)
 	sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
 					&nvm_dev_attr_group);
 }
-
-/* move to shared place when used in multiple places. */
-#define PCI_VENDOR_ID_CNEX 0x1d1d
-#define PCI_DEVICE_ID_CNEX_WL 0x2807
-#define PCI_DEVICE_ID_CNEX_QEMU 0x1f1f
-
-int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
-{
-	struct nvme_ctrl *ctrl = ns->ctrl;
-	/* XXX: this is poking into PCI structures from generic code! */
-	struct pci_dev *pdev = to_pci_dev(ctrl->dev);
-
-	/* QEMU NVMe simulator - PCI ID + Vendor specific bit */
-	if (pdev->vendor == PCI_VENDOR_ID_CNEX &&
-				pdev->device == PCI_DEVICE_ID_CNEX_QEMU &&
-							id->vs[0] == 0x1)
-		return 1;
-
-	/* CNEX Labs - PCI ID + Vendor specific bit */
-	if (pdev->vendor == PCI_VENDOR_ID_CNEX &&
-				pdev->device == PCI_DEVICE_ID_CNEX_WL &&
-							id->vs[0] == 0x1)
-		return 1;
-
-	return 0;
-}

drivers/nvme/host/nvme.h

@@ -75,6 +75,11 @@ enum nvme_quirks {
 	 * The deepest sleep state should not be used.
 	 */
 	NVME_QUIRK_NO_DEEPEST_PS		= (1 << 5),
+
+	/*
+	 * Supports the LighNVM command set if indicated in vs[1].
+	 */
+	NVME_QUIRK_LIGHTNVM			= (1 << 6),
 };
 
 /*
@@ -176,8 +181,11 @@ struct nvme_ctrl {
 	u64 ps_max_latency_us;
 	bool apst_enabled;
 
+	/* PCIe only: */
 	u32 hmpre;
 	u32 hmmin;
+	u32 hmminds;
+	u16 hmmaxd;
 
 	/* Fabrics only */
 	u16 sqsize;
@@ -320,7 +328,6 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
 
 #ifdef CONFIG_NVM
-int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id);
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);
 int nvme_nvm_register_sysfs(struct nvme_ns *ns);
@@ -339,10 +346,6 @@ static inline int nvme_nvm_register_sysfs(struct nvme_ns *ns)
 	return 0;
 }
 static inline void nvme_nvm_unregister_sysfs(struct nvme_ns *ns) {};
-static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
-{
-	return 0;
-}
 static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
 							unsigned long arg)
 {

drivers/nvme/host/pci.c

@@ -1612,21 +1612,23 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
 	dev->host_mem_descs = NULL;
 }
 
-static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
+static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred,
+		u32 chunk_size)
 {
 	struct nvme_host_mem_buf_desc *descs;
-	u32 chunk_size, max_entries, len;
+	u32 max_entries, len;
 	dma_addr_t descs_dma;
 	int i = 0;
 	void **bufs;
 	u64 size = 0, tmp;
 
-	/* start big and work our way down */
-	chunk_size = min(preferred, (u64)PAGE_SIZE << MAX_ORDER);
-retry:
 	tmp = (preferred + chunk_size - 1);
 	do_div(tmp, chunk_size);
 	max_entries = tmp;
+
+	if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries)
+		max_entries = dev->ctrl.hmmaxd;
+
 	descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs),
 			&descs_dma, GFP_KERNEL);
 	if (!descs)
@@ -1650,15 +1652,9 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 		i++;
 	}
 
-	if (!size || (min && size < min)) {
-		dev_warn(dev->ctrl.device,
-			"failed to allocate host memory buffer.\n");
+	if (!size)
 		goto out_free_bufs;
-	}
 
-	dev_info(dev->ctrl.device,
-		"allocated %lld MiB host memory buffer.\n",
-		size >> ilog2(SZ_1M));
 	dev->nr_host_mem_descs = i;
 	dev->host_mem_size = size;
 	dev->host_mem_descs = descs;
@@ -1679,29 +1675,43 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 	dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs,
 			descs_dma);
 out:
-	/* try a smaller chunk size if we failed early */
-	if (chunk_size >= PAGE_SIZE * 2 && (i == 0 || size < min)) {
-		chunk_size /= 2;
-		goto retry;
-	}
 	dev->host_mem_descs = NULL;
 	return -ENOMEM;
 }
 
-static void nvme_setup_host_mem(struct nvme_dev *dev)
+static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
+{
+	u32 chunk_size;
+
+	/* start big and work our way down */
+	for (chunk_size = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
+	     chunk_size >= max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
+	     chunk_size /= 2) {
+		if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
+			if (!min || dev->host_mem_size >= min)
+				return 0;
+			nvme_free_host_mem(dev);
+		}
+	}
+
+	return -ENOMEM;
+}
+
+static int nvme_setup_host_mem(struct nvme_dev *dev)
 {
 	u64 max = (u64)max_host_mem_size_mb * SZ_1M;
 	u64 preferred = (u64)dev->ctrl.hmpre * 4096;
 	u64 min = (u64)dev->ctrl.hmmin * 4096;
 	u32 enable_bits = NVME_HOST_MEM_ENABLE;
+	int ret = 0;
 
 	preferred = min(preferred, max);
 	if (min > max) {
 		dev_warn(dev->ctrl.device,
 			"min host memory (%lld MiB) above limit (%d MiB).\n",
 			min >> ilog2(SZ_1M), max_host_mem_size_mb);
 		nvme_free_host_mem(dev);
-		return;
+		return 0;
 	}
 
 	/*
@@ -1715,12 +1725,21 @@ static void nvme_setup_host_mem(struct nvme_dev *dev)
 	}
 
 	if (!dev->host_mem_descs) {
-		if (nvme_alloc_host_mem(dev, min, preferred))
-			return;
+		if (nvme_alloc_host_mem(dev, min, preferred)) {
+			dev_warn(dev->ctrl.device,
+				"failed to allocate host memory buffer.\n");
+			return 0; /* controller must work without HMB */
+		}
+
+		dev_info(dev->ctrl.device,
+			"allocated %lld MiB host memory buffer.\n",
+			dev->host_mem_size >> ilog2(SZ_1M));
 	}
 
-	if (nvme_set_host_mem(dev, enable_bits))
+	ret = nvme_set_host_mem(dev, enable_bits);
+	if (ret)
 		nvme_free_host_mem(dev);
+	return ret;
 }
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
@@ -2164,8 +2183,11 @@ static void nvme_reset_work(struct work_struct *work)
 				 "unable to allocate dma for dbbuf\n");
 	}
 
-	if (dev->ctrl.hmpre)
-		nvme_setup_host_mem(dev);
+	if (dev->ctrl.hmpre) {
+		result = nvme_setup_host_mem(dev);
+		if (result < 0)
+			goto out;
+	}
 
 	result = nvme_setup_io_queues(dev);
 	if (result)
@@ -2497,6 +2519,10 @@ 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, },
+	{ PCI_DEVICE(0x1d1d, 0x1f1f),	/* LighNVM qemu device */
+		.driver_data = NVME_QUIRK_LIGHTNVM, },
+	{ PCI_DEVICE(0x1d1d, 0x2807),	/* CNEX WL */
+		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },

include/linux/nvme.h

@@ -226,7 +226,9 @@ struct nvme_id_ctrl {
 	__le16			mntmt;
 	__le16			mxtmt;
 	__le32			sanicap;
-	__u8			rsvd332[180];
+	__le32			hmminds;
+	__le16			hmmaxd;
+	__u8			rsvd338[174];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;