6 files changed, 86 insertions, 80 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c49f1f8b2e57..c596dd3c58b1 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -336,7 +336,7 @@ static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
 
 	c.directive.opcode = nvme_admin_directive_recv;
 	c.directive.nsid = cpu_to_le32(nsid);
-	c.directive.numd = cpu_to_le32(sizeof(*s));
+	c.directive.numd = cpu_to_le32((sizeof(*s) >> 2) - 1);
 	c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
 	c.directive.dtype = NVME_DIR_STREAMS;
 
@@ -613,11 +613,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
 
 		if (!disk)
 			goto submit;
-		bio->bi_bdev = bdget_disk(disk, 0);
-		if (!bio->bi_bdev) {
-			ret = -ENODEV;
-			goto out_unmap;
-		}
+		bio->bi_disk = disk;
 
 		if (meta_buffer && meta_len) {
 			struct bio_integrity_payload *bip;
@@ -668,11 +664,8 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
  out_free_meta:
 	kfree(meta);
  out_unmap:
-	if (bio) {
-		if (disk && bio->bi_bdev)
-			bdput(bio->bi_bdev);
+	if (bio)
 		blk_rq_unmap_user(bio);
-	}
  out:
 	blk_mq_free_request(req);
 	return ret;
@@ -1509,7 +1502,7 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
 	blk_queue_write_cache(q, vwc, vwc);
 }
 
-static void nvme_configure_apst(struct nvme_ctrl *ctrl)
+static int nvme_configure_apst(struct nvme_ctrl *ctrl)
 {
 	/*
 	 * APST (Autonomous Power State Transition) lets us program a
@@ -1538,16 +1531,16 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 	 * then don't do anything.
 	 */
 	if (!ctrl->apsta)
-		return;
+		return 0;
 
 	if (ctrl->npss > 31) {
 		dev_warn(ctrl->device, "NPSS is invalid; not using APST\n");
-		return;
+		return 0;
 	}
 
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
 	if (!table)
-		return;
+		return 0;
 
 	if (!ctrl->apst_enabled || ctrl->ps_max_latency_us == 0) {
 		/* Turn off APST. */
@@ -1629,6 +1622,7 @@ static void nvme_configure_apst(struct nvme_ctrl *ctrl)
 		dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret);
 
 	kfree(table);
+	return ret;
 }
 
 static void nvme_set_latency_tolerance(struct device *dev, s32 val)
@@ -1835,13 +1829,16 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		 * In fabrics we need to verify the cntlid matches the
 		 * admin connect
 		 */
-		if (ctrl->cntlid != le16_to_cpu(id->cntlid))
+		if (ctrl->cntlid != le16_to_cpu(id->cntlid)) {
 			ret = -EINVAL;
+			goto out_free;
+		}
 
 		if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
 			dev_err(ctrl->device,
 				"keep-alive support is mandatory for fabrics\n");
 			ret = -EINVAL;
+			goto out_free;
 		}
 	} else {
 		ctrl->cntlid = le16_to_cpu(id->cntlid);
@@ -1856,11 +1853,20 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
 
-	nvme_configure_apst(ctrl);
-	nvme_configure_directives(ctrl);
+	ret = nvme_configure_apst(ctrl);
+	if (ret < 0)
+		return ret;
+
+	ret = nvme_configure_directives(ctrl);
+	if (ret < 0)
+		return ret;
 
 	ctrl->identified = true;
 
+	return 0;
+
+out_free:
+	kfree(id);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_identify);
@@ -2004,9 +2010,11 @@ static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
 	if (memchr_inv(ns->eui, 0, sizeof(ns->eui)))
 		return sprintf(buf, "eui.%8phN\n", ns->eui);
 
-	while (ctrl->serial[serial_len - 1] == ' ')
+	while (serial_len > 0 && (ctrl->serial[serial_len - 1] == ' ' ||
+				  ctrl->serial[serial_len - 1] == '\0'))
 		serial_len--;
-	while (ctrl->model[model_len - 1] == ' ')
+	while (model_len > 0 && (ctrl->model[model_len - 1] == ' ' ||
+				 ctrl->model[model_len - 1] == '\0'))
 		model_len--;
 
 	return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid,
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 2e582a240943..5f5cd306f76d 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -794,7 +794,8 @@ static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts,
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) {
-			if (opt_tokens[i].token & ~allowed_opts) {
+			if ((opt_tokens[i].token & opts->mask) &&
+			    (opt_tokens[i].token & ~allowed_opts)) {
 				pr_warn("invalid parameter '%s'\n",
 					opt_tokens[i].pattern);
 			}
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 5c2a08ef08ba..1438be649866 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2168,7 +2168,6 @@ static const struct blk_mq_ops nvme_fc_mq_ops = {
 	.complete	= nvme_fc_complete_rq,
 	.init_request	= nvme_fc_init_request,
 	.exit_request	= nvme_fc_exit_request,
-	.reinit_request	= nvme_fc_reinit_request,
 	.init_hctx	= nvme_fc_init_hctx,
 	.poll		= nvme_fc_poll,
 	.timeout	= nvme_fc_timeout,
@@ -2269,7 +2268,7 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
 
 	nvme_fc_init_io_queues(ctrl);
 
-	ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+	ret = blk_mq_reinit_tagset(&ctrl->tag_set, nvme_fc_reinit_request);
 	if (ret)
 		goto out_free_io_queues;
 
@@ -2655,7 +2654,6 @@ static const struct blk_mq_ops nvme_fc_admin_mq_ops = {
 	.complete	= nvme_fc_complete_rq,
 	.init_request	= nvme_fc_init_request,
 	.exit_request	= nvme_fc_exit_request,
-	.reinit_request	= nvme_fc_reinit_request,
 	.init_hctx	= nvme_fc_init_admin_hctx,
 	.timeout	= nvme_fc_timeout,
 };
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index be8541335e31..c1a28569e843 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -643,17 +643,9 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q,
 			vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma);
 		}
 
-		if (!disk)
-			goto submit;
-
-		bio->bi_bdev = bdget_disk(disk, 0);
-		if (!bio->bi_bdev) {
-			ret = -ENODEV;
-			goto err_meta;
-		}
+		bio->bi_disk = disk;
 	}
 
-submit:
 	blk_execute_rq(q, NULL, rq, 0);
 
 	if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
@@ -673,11 +665,8 @@ err_meta:
 	if (meta_buf && meta_len)
 		dma_pool_free(dev->dma_pool, metadata, metadata_dma);
 err_map:
-	if (bio) {
-		if (disk && bio->bi_bdev)
-			bdput(bio->bi_bdev);
+	if (bio)
 		blk_rq_unmap_user(bio);
-	}
 err_ppa:
 	if (ppa_buf && ppa_len)
 		dma_pool_free(dev->dma_pool, ppa_list, ppa_dma);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index cd888a47d0fc..ea892e732268 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -109,6 +109,7 @@ struct nvme_dev {
 	/* host memory buffer support: */
 	u64 host_mem_size;
 	u32 nr_host_mem_descs;
+	dma_addr_t host_mem_descs_dma;
 	struct nvme_host_mem_buf_desc *host_mem_descs;
 	void **host_mem_desc_bufs;
 };
@@ -801,6 +802,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
 		return;
 	}
 
+	nvmeq->cqe_seen = 1;
 	req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id);
 	nvme_end_request(req, cqe->status, cqe->result);
 }
@@ -830,10 +832,8 @@ static void nvme_process_cq(struct nvme_queue *nvmeq)
 		consumed++;
 	}
 
-	if (consumed) {
+	if (consumed)
 		nvme_ring_cq_doorbell(nvmeq);
-		nvmeq->cqe_seen = 1;
-	}
 }
 
 static irqreturn_t nvme_irq(int irq, void *data)
@@ -1558,26 +1558,18 @@ static inline void nvme_release_cmb(struct nvme_dev *dev)
 	if (dev->cmb) {
 		iounmap(dev->cmb);
 		dev->cmb = NULL;
-		if (dev->cmbsz) {
-			sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
-						     &dev_attr_cmb.attr, NULL);
-			dev->cmbsz = 0;
-		}
+		sysfs_remove_file_from_group(&dev->ctrl.device->kobj,
+					     &dev_attr_cmb.attr, NULL);
+		dev->cmbsz = 0;
 	}
 }
 
 static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
 {
-	size_t len = dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs);
+	u64 dma_addr = dev->host_mem_descs_dma;
 	struct nvme_command c;
-	u64 dma_addr;
 	int ret;
 
-	dma_addr = dma_map_single(dev->dev, dev->host_mem_descs, len,
-			DMA_TO_DEVICE);
-	if (dma_mapping_error(dev->dev, dma_addr))
-		return -ENOMEM;
-
 	memset(&c, 0, sizeof(c));
 	c.features.opcode	= nvme_admin_set_features;
 	c.features.fid		= cpu_to_le32(NVME_FEAT_HOST_MEM_BUF);
@@ -1594,7 +1586,6 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
 			 "failed to set host mem (err %d, flags %#x).\n",
 			 ret, bits);
 	}
-	dma_unmap_single(dev->dev, dma_addr, len, DMA_TO_DEVICE);
 	return ret;
 }
 
@@ -1612,7 +1603,9 @@ static void nvme_free_host_mem(struct nvme_dev *dev)
 
 	kfree(dev->host_mem_desc_bufs);
 	dev->host_mem_desc_bufs = NULL;
-	kfree(dev->host_mem_descs);
+	dma_free_coherent(dev->dev,
+			dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs),
+			dev->host_mem_descs, dev->host_mem_descs_dma);
 	dev->host_mem_descs = NULL;
 }
 
@@ -1620,6 +1613,7 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 {
 	struct nvme_host_mem_buf_desc *descs;
 	u32 chunk_size, max_entries, len;
+	dma_addr_t descs_dma;
 	int i = 0;
 	void **bufs;
 	u64 size = 0, tmp;
@@ -1630,7 +1624,8 @@ retry:
 	tmp = (preferred + chunk_size - 1);
 	do_div(tmp, chunk_size);
 	max_entries = tmp;
-	descs = kcalloc(max_entries, sizeof(*descs), GFP_KERNEL);
+	descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs),
+			&descs_dma, GFP_KERNEL);
 	if (!descs)
 		goto out;
 
@@ -1664,6 +1659,7 @@ retry:
 	dev->nr_host_mem_descs = i;
 	dev->host_mem_size = size;
 	dev->host_mem_descs = descs;
+	dev->host_mem_descs_dma = descs_dma;
 	dev->host_mem_desc_bufs = bufs;
 	return 0;
 
@@ -1677,7 +1673,8 @@ out_free_bufs:
 
 	kfree(bufs);
 out_free_descs:
-	kfree(descs);
+	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)) {
@@ -1953,16 +1950,14 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	/*
 	 * CMBs can currently only exist on >=1.2 PCIe devices. We only
-	 * populate sysfs if a CMB is implemented. Note that we add the
-	 * CMB attribute to the nvme_ctrl kobj which removes the need to remove
-	 * it on exit. Since nvme_dev_attrs_group has no name we can pass
-	 * NULL as final argument to sysfs_add_file_to_group.
+	 * populate sysfs if a CMB is implemented. Since nvme_dev_attrs_group
+	 * has no name we can pass NULL as final argument to
+	 * sysfs_add_file_to_group.
 	 */
 
 	if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2, 0)) {
 		dev->cmb = nvme_map_cmb(dev);
-
-		if (dev->cmbsz) {
+		if (dev->cmb) {
 			if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
 						    &dev_attr_cmb.attr, NULL))
 				dev_warn(dev->ctrl.device,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index da04df1af231..bf42d31484d4 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/atomic.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-rdma.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -463,14 +464,10 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	ibdev = queue->device->dev;
 
 	/*
-	 * The admin queue is barely used once the controller is live, so don't
-	 * bother to spread it out.
+	 * Spread I/O queues completion vectors according their queue index.
+	 * Admin queues can always go on completion vector 0.
 	 */
-	if (idx == 0)
-		comp_vector = 0;
-	else
-		comp_vector = idx % ibdev->num_comp_vectors;
-
+	comp_vector = idx == 0 ? idx : idx - 1;
 
 	/* +1 for ib_stop_cq */
 	queue->ib_cq = ib_alloc_cq(ibdev, queue,
@@ -611,10 +608,20 @@ out_free_queues:
 static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
 {
 	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	struct ib_device *ibdev = ctrl->device->dev;
 	unsigned int nr_io_queues;
 	int i, ret;
 
 	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+
+	/*
+	 * we map queues according to the device irq vectors for
+	 * optimal locality so we don't need more queues than
+	 * completion vectors.
+	 */
+	nr_io_queues = min_t(unsigned int, nr_io_queues,
+				ibdev->num_comp_vectors);
+
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
 		return ret;
@@ -704,14 +711,16 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_rdma_free_io_queues(ctrl);
 
-		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+		ret = blk_mq_reinit_tagset(&ctrl->tag_set,
+					   nvme_rdma_reinit_request);
 		if (ret)
 			goto requeue;
 	}
 
 	nvme_rdma_stop_and_free_queue(&ctrl->queues[0]);
 
-	ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set);
+	ret = blk_mq_reinit_tagset(&ctrl->admin_tag_set,
+				   nvme_rdma_reinit_request);
 	if (ret)
 		goto requeue;
 
@@ -920,7 +929,11 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue,
 	struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl;
 	int nr;
 
-	nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE);
+	/*
+	 * Align the MR to a 4K page size to match the ctrl page size and
+	 * the block virtual boundary.
+	 */
+	nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, SZ_4K);
 	if (nr < count) {
 		if (nr < 0)
 			return nr;
@@ -1498,15 +1511,22 @@ static void nvme_rdma_complete_rq(struct request *rq)
 	nvme_complete_rq(rq);
 }
 
+static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
+{
+	struct nvme_rdma_ctrl *ctrl = set->driver_data;
+
+	return blk_mq_rdma_map_queues(set, ctrl->device->dev, 0);
+}
+
 static const struct blk_mq_ops nvme_rdma_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
 	.init_request	= nvme_rdma_init_request,
 	.exit_request	= nvme_rdma_exit_request,
-	.reinit_request	= nvme_rdma_reinit_request,
 	.init_hctx	= nvme_rdma_init_hctx,
 	.poll		= nvme_rdma_poll,
 	.timeout	= nvme_rdma_timeout,
+	.map_queues	= nvme_rdma_map_queues,
 };
 
 static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
@@ -1514,7 +1534,6 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 	.complete	= nvme_rdma_complete_rq,
 	.init_request	= nvme_rdma_init_request,
 	.exit_request	= nvme_rdma_exit_request,
-	.reinit_request	= nvme_rdma_reinit_request,
 	.init_hctx	= nvme_rdma_init_admin_hctx,
 	.timeout	= nvme_rdma_timeout,
 };
@@ -1583,7 +1602,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl)
 		goto out_cleanup_queue;
 
 	ctrl->ctrl.max_hw_sectors =
-		(ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9);
+		(ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
 
 	error = nvme_init_identify(&ctrl->ctrl);
 	if (error)
@@ -1712,7 +1731,8 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 	}
 
 	if (ctrl->ctrl.queue_count > 1) {
-		ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+		ret = blk_mq_reinit_tagset(&ctrl->tag_set,
+					   nvme_rdma_reinit_request);
 		if (ret)
 			goto del_dead_ctrl;
 
@@ -1946,10 +1966,6 @@ static struct nvmf_transport_ops nvme_rdma_transport = {
 	.create_ctrl	= nvme_rdma_create_ctrl,
 };
 
-static void nvme_rdma_add_one(struct ib_device *ib_device)
-{
-}
-
 static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data)
 {
 	struct nvme_rdma_ctrl *ctrl;
@@ -1971,7 +1987,6 @@ static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data)
 
 static struct ib_client nvme_rdma_ib_client = {
 	.name   = "nvme_rdma",
-	.add = nvme_rdma_add_one,
 	.remove = nvme_rdma_remove_one
 };