block-5.11-2021-01-24

-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmANwMUQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpr1PEACPVkVvLlxH2YfnBNykDn+tV+goOs37oJkB
 0XR+flcZAHHycLvWnix4AVca4ebTU4diwrFMM4gB01mzzoPYhicHefNuhPV4abYO
 qq6SCcpZkBfbjYqfB+Fmo0823UXaGUqX/oaxbYwePjkMbFjW6kQEThEHGH07CmWA
 s5VfOSn695hXLUBpKwsj5m88NohP4tSZMm+VE2RvycdVt2uzJuga1aDDAFPfZFRA
 YHQyhIEUClYl3eC3Yo5E32nBezrRCJtumRZKmQHMCBXGQ2Z9OfgalD8wz4zBb/D0
 ypzr68M27coQIQ9qNBruHuOfnjvwy4jwB0Eci7bGHfKUiVwUDiLD8TVqnQzcwxR6
 VNm4RbCEazsfZ33ztk7iiKHijesJ5wHlaDNlL1xBxpNajqOVv3T65kmaETarhUAQ
 h/EgHUFzYrzy9Y9ZpuClAE3LSk9gV3EzFuWmgSvwSY99TPNCpkG6raXTdmRzj6fV
 ZFz8L7AlXnbBjREfK8x4lB3W1T16zAQpiPrGYIfQsSIAeBbbyxGIo/H5wdCZwQBj
 0k5+UoxWT8oYK2C6xdK7elDN6jT4BaC4p5IZBhlVXCIh+VUD5+Ol6/2pFRr6qRWt
 giXITDzuVMECTtj8gNhf/P209kG9eSglYfXFRr334GFirSMfN8a22BB3tabp+dDF
 GzCHw+zZuA==
 =Bblh
 -----END PGP SIGNATURE-----

Merge tag 'block-5.11-2021-01-24' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Christoph:
      - fix a status code in nvmet (Chaitanya Kulkarni)
      - avoid double completions in nvme-rdma/nvme-tcp (Chao Leng)
      - fix the CMB support to cope with NVMe 1.4 controllers (Klaus Jensen)
      - fix PRINFO handling in the passthrough ioctl (Revanth Rajashekar)
      - fix a double DMA unmap in nvme-pci

 - lightnvm error path leak fix (Pan)

 - MD pull request from Song:
      - Flush request fix (Xiao)

* tag 'block-5.11-2021-01-24' of git://git.kernel.dk/linux-block:
  lightnvm: fix memory leak when submit fails
  nvme-pci: fix error unwind in nvme_map_data
  nvme-pci: refactor nvme_unmap_data
  md: Set prev_flush_start and flush_bio in an atomic way
  nvmet: set right status on error in id-ns handler
  nvme-pci: allow use of cmb on v1.4 controllers
  nvme-tcp: avoid request double completion for concurrent nvme_tcp_timeout
  nvme-rdma: avoid request double completion for concurrent nvme_rdma_timeout
  nvme: check the PRINFO bit before deciding the host buffer length

drivers/lightnvm/core.c

@@ -844,11 +844,10 @@ static int nvm_bb_chunk_sense(struct nvm_dev *dev, struct ppa_addr ppa)
 	rqd.ppa_addr = generic_to_dev_addr(dev, ppa);
 
 	ret = nvm_submit_io_sync_raw(dev, &rqd);
+	__free_page(page);
 	if (ret)
 		return ret;
 
-	__free_page(page);
-
 	return rqd.error;
 }
 

drivers/md/md.c

@@ -639,8 +639,10 @@ static void md_submit_flush_data(struct work_struct *ws)
 	 * could wait for this and below md_handle_request could wait for those
 	 * bios because of suspend check
 	 */
+	spin_lock_irq(&mddev->lock);
 	mddev->prev_flush_start = mddev->start_flush;
 	mddev->flush_bio = NULL;
+	spin_unlock_irq(&mddev->lock);
 	wake_up(&mddev->sb_wait);
 
 	if (bio->bi_iter.bi_size == 0) {

drivers/nvme/host/core.c

@@ -1543,8 +1543,21 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	}
 
 	length = (io.nblocks + 1) << ns->lba_shift;
-	meta_len = (io.nblocks + 1) * ns->ms;
+
-	metadata = nvme_to_user_ptr(io.metadata);
+	if ((io.control & NVME_RW_PRINFO_PRACT) &&
+	    ns->ms == sizeof(struct t10_pi_tuple)) {
+		/*
+		 * Protection information is stripped/inserted by the
+		 * controller.
+		 */
+		if (nvme_to_user_ptr(io.metadata))
+			return -EINVAL;
+		meta_len = 0;
+		metadata = NULL;
+	} else {
+		meta_len = (io.nblocks + 1) * ns->ms;
+		metadata = nvme_to_user_ptr(io.metadata);
+	}
 
 	if (ns->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;

drivers/nvme/host/pci.c

@@ -23,6 +23,7 @@
 #include <linux/t10-pi.h>
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/sed-opal.h>
 #include <linux/pci-p2pdma.h>
 
@@ -542,50 +543,71 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
 	return true;
 }
 
-static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
+static void nvme_free_prps(struct nvme_dev *dev, struct request *req)
 {
-	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 	const int last_prp = NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1;
-	dma_addr_t dma_addr = iod->first_dma, next_dma_addr;
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	dma_addr_t dma_addr = iod->first_dma;
 	int i;
 
-	if (iod->dma_len) {
+	for (i = 0; i < iod->npages; i++) {
-		dma_unmap_page(dev->dev, dma_addr, iod->dma_len,
+		__le64 *prp_list = nvme_pci_iod_list(req)[i];
-			       rq_dma_dir(req));
+		dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]);
-		return;
+
+		dma_pool_free(dev->prp_page_pool, prp_list, dma_addr);
+		dma_addr = next_dma_addr;
 	}
 
-	WARN_ON_ONCE(!iod->nents);
+}
+
+static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
+{
+	const int last_sg = SGES_PER_PAGE - 1;
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	dma_addr_t dma_addr = iod->first_dma;
+	int i;
+
+	for (i = 0; i < iod->npages; i++) {
+		struct nvme_sgl_desc *sg_list = nvme_pci_iod_list(req)[i];
+		dma_addr_t next_dma_addr = le64_to_cpu((sg_list[last_sg]).addr);
+
+		dma_pool_free(dev->prp_page_pool, sg_list, dma_addr);
+		dma_addr = next_dma_addr;
+	}
+
+}
+
+static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
 	if (is_pci_p2pdma_page(sg_page(iod->sg)))
 		pci_p2pdma_unmap_sg(dev->dev, iod->sg, iod->nents,
 				    rq_dma_dir(req));
 	else
 		dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req));
+}
 
+static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
+{
+	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
-	if (iod->npages == 0)
+	if (iod->dma_len) {
-		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
+		dma_unmap_page(dev->dev, iod->first_dma, iod->dma_len,
-			dma_addr);
+			       rq_dma_dir(req));
-
+		return;
-	for (i = 0; i < iod->npages; i++) {
-		void *addr = nvme_pci_iod_list(req)[i];
-
-		if (iod->use_sgl) {
-			struct nvme_sgl_desc *sg_list = addr;
-
-			next_dma_addr =
-			    le64_to_cpu((sg_list[SGES_PER_PAGE - 1]).addr);
-		} else {
-			__le64 *prp_list = addr;
-
-			next_dma_addr = le64_to_cpu(prp_list[last_prp]);
-		}
-
-		dma_pool_free(dev->prp_page_pool, addr, dma_addr);
-		dma_addr = next_dma_addr;
 	}
 
+	WARN_ON_ONCE(!iod->nents);
+
+	nvme_unmap_sg(dev, req);
+	if (iod->npages == 0)
+		dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0],
+			      iod->first_dma);
+	else if (iod->use_sgl)
+		nvme_free_sgls(dev, req);
+	else
+		nvme_free_prps(dev, req);
 	mempool_free(iod->sg, dev->iod_mempool);
 }
 
@@ -661,7 +683,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 			__le64 *old_prp_list = prp_list;
 			prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma);
 			if (!prp_list)
-				return BLK_STS_RESOURCE;
+				goto free_prps;
 			list[iod->npages++] = prp_list;
 			prp_list[0] = old_prp_list[i - 1];
 			old_prp_list[i - 1] = cpu_to_le64(prp_dma);
@@ -681,14 +703,14 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev,
 		dma_addr = sg_dma_address(sg);
 		dma_len = sg_dma_len(sg);
 	}
-
 done:
 	cmnd->dptr.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
 	cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma);
-
 	return BLK_STS_OK;
-
+free_prps:
- bad_sgl:
+	nvme_free_prps(dev, req);
+	return BLK_STS_RESOURCE;
+bad_sgl:
 	WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
 			"Invalid SGL for payload:%d nents:%d\n",
 			blk_rq_payload_bytes(req), iod->nents);
@@ -760,7 +782,7 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
 
 			sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma);
 			if (!sg_list)
-				return BLK_STS_RESOURCE;
+				goto free_sgls;
 
 			i = 0;
 			nvme_pci_iod_list(req)[iod->npages++] = sg_list;
@@ -773,6 +795,9 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev,
 	} while (--entries > 0);
 
 	return BLK_STS_OK;
+free_sgls:
+	nvme_free_sgls(dev, req);
+	return BLK_STS_RESOURCE;
 }
 
 static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
@@ -841,7 +866,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 	sg_init_table(iod->sg, blk_rq_nr_phys_segments(req));
 	iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
 	if (!iod->nents)
-		goto out;
+		goto out_free_sg;
 
 	if (is_pci_p2pdma_page(sg_page(iod->sg)))
 		nr_mapped = pci_p2pdma_map_sg_attrs(dev->dev, iod->sg,
@@ -850,16 +875,21 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents,
 					     rq_dma_dir(req), DMA_ATTR_NO_WARN);
 	if (!nr_mapped)
-		goto out;
+		goto out_free_sg;
 
 	iod->use_sgl = nvme_pci_use_sgls(dev, req);
 	if (iod->use_sgl)
 		ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped);
 	else
 		ret = nvme_pci_setup_prps(dev, req, &cmnd->rw);
-out:
 	if (ret != BLK_STS_OK)
-		nvme_unmap_data(dev, req);
+		goto out_unmap_sg;
+	return BLK_STS_OK;
+
+out_unmap_sg:
+	nvme_unmap_sg(dev, req);
+out_free_sg:
+	mempool_free(iod->sg, dev->iod_mempool);
 	return ret;
 }
 
@@ -1795,6 +1825,9 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (dev->cmb_size)
 		return;
 
+	if (NVME_CAP_CMBS(dev->ctrl.cap))
+		writel(NVME_CMBMSC_CRE, dev->bar + NVME_REG_CMBMSC);
+
 	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
 	if (!dev->cmbsz)
 		return;
@@ -1808,6 +1841,16 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (offset > bar_size)
 		return;
 
+	/*
+	 * Tell the controller about the host side address mapping the CMB,
+	 * and enable CMB decoding for the NVMe 1.4+ scheme:
+	 */
+	if (NVME_CAP_CMBS(dev->ctrl.cap)) {
+		hi_lo_writeq(NVME_CMBMSC_CRE | NVME_CMBMSC_CMSE |
+			     (pci_bus_address(pdev, bar) + offset),
+			     dev->bar + NVME_REG_CMBMSC);
+	}
+
 	/*
 	 * Controllers may support a CMB size larger than their BAR,
 	 * for example, due to being behind a bridge. Reduce the CMB to

drivers/nvme/host/rdma.c

@@ -97,6 +97,7 @@ struct nvme_rdma_queue {
 	struct completion	cm_done;
 	bool			pi_support;
 	int			cq_size;
+	struct mutex		queue_lock;
 };
 
 struct nvme_rdma_ctrl {
@@ -579,6 +580,7 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
 	int ret;
 
 	queue = &ctrl->queues[idx];
+	mutex_init(&queue->queue_lock);
 	queue->ctrl = ctrl;
 	if (idx && ctrl->ctrl.max_integrity_segments)
 		queue->pi_support = true;
@@ -598,7 +600,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
 	if (IS_ERR(queue->cm_id)) {
 		dev_info(ctrl->ctrl.device,
 			"failed to create CM ID: %ld\n", PTR_ERR(queue->cm_id));
-		return PTR_ERR(queue->cm_id);
+		ret = PTR_ERR(queue->cm_id);
+		goto out_destroy_mutex;
 	}
 
 	if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
@@ -628,6 +631,8 @@ static int nvme_rdma_alloc_queue(struct nvme_rdma_ctrl *ctrl,
 out_destroy_cm_id:
 	rdma_destroy_id(queue->cm_id);
 	nvme_rdma_destroy_queue_ib(queue);
+out_destroy_mutex:
+	mutex_destroy(&queue->queue_lock);
 	return ret;
 }
 
@@ -639,9 +644,10 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
 
 static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
 {
-	if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags))
+	mutex_lock(&queue->queue_lock);
-		return;
+	if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags))
-	__nvme_rdma_stop_queue(queue);
+		__nvme_rdma_stop_queue(queue);
+	mutex_unlock(&queue->queue_lock);
 }
 
 static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
@@ -651,6 +657,7 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
 
 	nvme_rdma_destroy_queue_ib(queue);
 	rdma_destroy_id(queue->cm_id);
+	mutex_destroy(&queue->queue_lock);
 }
 
 static void nvme_rdma_free_io_queues(struct nvme_rdma_ctrl *ctrl)

drivers/nvme/host/tcp.c

@@ -76,6 +76,7 @@ struct nvme_tcp_queue {
 	struct work_struct	io_work;
 	int			io_cpu;
 
+	struct mutex		queue_lock;
 	struct mutex		send_mutex;
 	struct llist_head	req_list;
 	struct list_head	send_list;
@@ -1219,6 +1220,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 
 	sock_release(queue->sock);
 	kfree(queue->pdu);
+	mutex_destroy(&queue->queue_lock);
 }
 
 static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
@@ -1380,6 +1382,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
 	int ret, rcv_pdu_size;
 
+	mutex_init(&queue->queue_lock);
 	queue->ctrl = ctrl;
 	init_llist_head(&queue->req_list);
 	INIT_LIST_HEAD(&queue->send_list);
@@ -1398,7 +1401,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	if (ret) {
 		dev_err(nctrl->device,
 			"failed to create socket: %d\n", ret);
-		return ret;
+		goto err_destroy_mutex;
 	}
 
 	/* Single syn retry */
@@ -1507,6 +1510,8 @@ err_crypto:
 err_sock:
 	sock_release(queue->sock);
 	queue->sock = NULL;
+err_destroy_mutex:
+	mutex_destroy(&queue->queue_lock);
 	return ret;
 }
 
@@ -1534,9 +1539,10 @@ static void nvme_tcp_stop_queue(struct nvme_ctrl *nctrl, int qid)
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
 
-	if (!test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
+	mutex_lock(&queue->queue_lock);
-		return;
+	if (test_and_clear_bit(NVME_TCP_Q_LIVE, &queue->flags))
-	__nvme_tcp_stop_queue(queue);
+		__nvme_tcp_stop_queue(queue);
+	mutex_unlock(&queue->queue_lock);
 }
 
 static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)

drivers/nvme/target/admin-cmd.c

@@ -487,8 +487,10 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 
 	/* return an all zeroed buffer if we can't find an active namespace */
 	ns = nvmet_find_namespace(ctrl, req->cmd->identify.nsid);
-	if (!ns)
+	if (!ns) {
+		status = NVME_SC_INVALID_NS;
 		goto done;
+	}
 
 	nvmet_ns_revalidate(ns);
 
@@ -541,7 +543,9 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 		id->nsattr |= (1 << 0);
 	nvmet_put_namespace(ns);
 done:
-	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+	if (!status)
+		status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+
 	kfree(id);
 out:
 	nvmet_req_complete(req, status);

include/linux/nvme.h

@@ -116,6 +116,9 @@ enum {
 	NVME_REG_BPMBL	= 0x0048,	/* Boot Partition Memory Buffer
 					 * Location
 					 */
+	NVME_REG_CMBMSC = 0x0050,	/* Controller Memory Buffer Memory
+					 * Space Control
+					 */
 	NVME_REG_PMRCAP	= 0x0e00,	/* Persistent Memory Capabilities */
 	NVME_REG_PMRCTL	= 0x0e04,	/* Persistent Memory Region Control */
 	NVME_REG_PMRSTS	= 0x0e08,	/* Persistent Memory Region Status */
@@ -135,6 +138,7 @@ enum {
 #define NVME_CAP_CSS(cap)	(((cap) >> 37) & 0xff)
 #define NVME_CAP_MPSMIN(cap)	(((cap) >> 48) & 0xf)
 #define NVME_CAP_MPSMAX(cap)	(((cap) >> 52) & 0xf)
+#define NVME_CAP_CMBS(cap)	(((cap) >> 57) & 0x1)
 
 #define NVME_CMB_BIR(cmbloc)	((cmbloc) & 0x7)
 #define NVME_CMB_OFST(cmbloc)	(((cmbloc) >> 12) & 0xfffff)
@@ -192,6 +196,8 @@ enum {
 	NVME_CSTS_SHST_OCCUR	= 1 << 2,
 	NVME_CSTS_SHST_CMPLT	= 2 << 2,
 	NVME_CSTS_SHST_MASK	= 3 << 2,
+	NVME_CMBMSC_CRE		= 1 << 0,
+	NVME_CMBMSC_CMSE	= 1 << 1,
 };
 
 struct nvme_id_power_state {