Automatic affinity settings for nvme over rdma

index 41cd22a223dc..2a3c59e55dcf 100644
@@ -385,7 +385,7 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
 	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
+	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
 }
 
 static inline int mlx5e_get_wqe_mtt_sz(void)

index ea5d8d37a75c..e2c33c493b89 100644
@@ -575,7 +575,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		 name, pci_name(dev->pdev));
 
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
-	eq->irqn = priv->msix_arr[vecidx].vector;
+	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
 	err = request_irq(eq->irqn, handler, 0,

@@ -610,7 +610,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	return 0;
 
 err_irq:
-	free_irq(priv->msix_arr[vecidx].vector, eq);
+	free_irq(eq->irqn, eq);
 
 err_eq:
 	mlx5_cmd_destroy_eq(dev, eq->eqn);

@@ -651,11 +651,6 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 }
 EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq);
 
-u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx)
-{
-	return dev->priv.msix_arr[MLX5_EQ_VEC_ASYNC].vector;
-}
-
 int mlx5_eq_init(struct mlx5_core_dev *dev)
 {
 	int err;

index 2e34d95ea776..e9256b7017b6 100644
@@ -1592,7 +1592,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	synchronize_irq(mlx5_get_msix_vec(esw->dev, MLX5_EQ_VEC_ASYNC));
+	synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */

index d0515391d33b..8b38d5cfd4c5 100644
@@ -80,7 +80,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	u64 vector;
 
 	/* wait for pending handlers to complete */
-	synchronize_irq(dev->priv.msix_arr[MLX5_EQ_VEC_CMD].vector);
+	synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
 	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
 	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
 	if (!vector)

index 0c123d571b4c..f7a8650e1bac 100644
@@ -308,13 +308,12 @@ static void release_bar(struct pci_dev *pdev)
 	pci_release_regions(pdev);
 }
 
-static int mlx5_enable_msix(struct mlx5_core_dev *dev)
+static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
 	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
-	int i;
 
 	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
 	       MLX5_EQ_VEC_COMP_BASE;

@@ -322,17 +321,13 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
 		return -ENOMEM;
 
-	priv->msix_arr = kcalloc(nvec, sizeof(*priv->msix_arr), GFP_KERNEL);
-
 	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
-	if (!priv->msix_arr || !priv->irq_info)
+	if (!priv->irq_info)
 		goto err_free_msix;
 
-	for (i = 0; i < nvec; i++)
-		priv->msix_arr[i].entry = i;
-
-	nvec = pci_enable_msix_range(dev->pdev, priv->msix_arr,
-				     MLX5_EQ_VEC_COMP_BASE + 1, nvec);
+	nvec = pci_alloc_irq_vectors(dev->pdev,
+			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
+			PCI_IRQ_MSIX);
 	if (nvec < 0)
 		return nvec;
 

@@ -342,17 +337,15 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 
 err_free_msix:
 	kfree(priv->irq_info);
-	kfree(priv->msix_arr);
 	return -ENOMEM;
 }
 
-static void mlx5_disable_msix(struct mlx5_core_dev *dev)
+static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
-	pci_disable_msix(dev->pdev);
+	pci_free_irq_vectors(dev->pdev);
 	kfree(priv->irq_info);
-	kfree(priv->msix_arr);
 }
 
 struct mlx5_reg_host_endianess {

@@ -610,8 +603,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 {
 	struct mlx5_priv *priv  = &mdev->priv;
-	struct msix_entry *msix = priv->msix_arr;
-	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
+	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
 	int err;
 
 	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {

@@ -639,8 +631,7 @@ static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
 static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
 {
 	struct mlx5_priv *priv  = &mdev->priv;
-	struct msix_entry *msix = priv->msix_arr;
-	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
+	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
 
 	irq_set_affinity_hint(irq, NULL);
 	free_cpumask_var(priv->irq_info[i].mask);

@@ -763,8 +754,8 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 		}
 
 #ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(dev->rmap,
-				 dev->priv.msix_arr[i + MLX5_EQ_VEC_COMP_BASE].vector);
+		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev,
+				 MLX5_EQ_VEC_COMP_BASE + i));
 #endif
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
 		err = mlx5_create_map_eq(dev, eq,

@@ -1101,9 +1092,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_poll;
 	}
 
-	err = mlx5_enable_msix(dev);
+	err = mlx5_alloc_irq_vectors(dev);
 	if (err) {
-		dev_err(&pdev->dev, "enable msix failed\n");
+		dev_err(&pdev->dev, "alloc irq vectors failed\n");
 		goto err_cleanup_once;
 	}
 

@@ -1186,7 +1177,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_put_uars_page(dev, priv->uar);
 
 err_disable_msix:
-	mlx5_disable_msix(dev);
+	mlx5_free_irq_vectors(dev);
 
 err_cleanup_once:
 	if (boot)

@@ -1247,7 +1238,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	free_comp_eqs(dev);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
-	mlx5_disable_msix(dev);
+	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev);

index fbc6e9e9e305..521768c56073 100644
@@ -109,7 +109,6 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
-u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
 void mlx5_cq_tasklet_cb(unsigned long data);
 

index bcdf739ee41a..4843fab18b83 100644
@@ -590,7 +590,6 @@ struct mlx5_port_module_event_stats {
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
-	struct msix_entry	*msix_arr;
 	struct mlx5_irq_info	*irq_info;
 
 	/* pages stuff */

index 2a3c59e55dcf..ebfda1eae6b4 100644
@@ -1565,11 +1565,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
-}
-
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)

@@ -1718,11 +1713,11 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 {
 	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	int err;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kzalloc_node(sizeof(*c), GFP_KERNEL,
+		pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix));
 	if (!c)
 		return -ENOMEM;
 

@@ -1730,7 +1725,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->mdev     = priv->mdev;
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
-	c->cpu      = cpu;
+	c->cpu      = cpumask_first(pci_irq_get_affinity(priv->mdev->pdev,
+			MLX5_EQ_VEC_COMP_BASE + ix));
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);

120 lines not on this page · raw message

index 4843fab18b83..963e3d59d740 100644
@@ -527,7 +527,6 @@ struct mlx5_core_sriov {
 };
 
 struct mlx5_irq_info {
-	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
 };
 

index ba8314ec5768..2349143297c9 100644
@@ -2245,6 +2245,8 @@ struct ib_device {
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
 	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
+	const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
+						     int comp_vector);
 };
 
 struct ib_client {

@@ -3609,7 +3611,6 @@ static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr,
 
 	grh->dgid.global.interface_id = if_id;
 }
-
 static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr,
 				   union ib_gid *dgid, u32 flow_label,
 				   u8 sgid_index, u8 hop_limit,

@@ -3639,4 +3640,26 @@ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
 	else
 		return RDMA_AH_ATTR_TYPE_IB;
 }
+
+/**
+ * ib_get_vector_affinity - Get the affinity mappings of a given completion
+ *   vector
+ * @device:         the rdma device
+ * @comp_vector:    index of completion vector
+ *
+ * Returns NULL on failure, otherwise a corresponding cpu map of the
+ * completion vector (returns all-cpus map if the device driver doesn't
+ * implement get_vector_affinity).
+ */
+static inline const struct cpumask *
+ib_get_vector_affinity(struct ib_device *device, int comp_vector)
+{
+	if (comp_vector < 0 || comp_vector >= device->num_comp_vectors ||
+	    !device->get_vector_affinity)
+		return NULL;
+
+	return device->get_vector_affinity(device, comp_vector);
+
+}
+
 #endif /* IB_VERBS_H */

index d45772da0963..dc272ece106d 100644
@@ -3550,6 +3550,15 @@ static void mlx5_ib_free_rdma_netdev(struct net_device *netdev)
 	return mlx5_rdma_netdev_free(netdev);
 }
 
+const struct cpumask *mlx5_ib_get_vector_affinity(struct ib_device *ibdev,
+		int comp_vector)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+
+	return pci_irq_get_affinity(dev->mdev->pdev,
+			MLX5_EQ_VEC_COMP_BASE + comp_vector);
+}
+
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_dev *dev;

@@ -3682,6 +3691,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.get_dev_fw_str      = get_dev_fw_str;
 	dev->ib_dev.alloc_rdma_netdev	= mlx5_ib_alloc_rdma_netdev;
 	dev->ib_dev.free_rdma_netdev	= mlx5_ib_free_rdma_netdev;
+	dev->ib_dev.get_vector_affinity	= mlx5_ib_get_vector_affinity;
 	if (mlx5_core_is_pf(mdev)) {
 		dev->ib_dev.get_vf_config	= mlx5_ib_get_vf_config;
 		dev->ib_dev.set_vf_link_state	= mlx5_ib_set_vf_link_state;

54 lines not on this page · raw message

new file mode 100644
index 000000000000..b4ade198007d
@@ -0,0 +1,10 @@
+#ifndef _LINUX_BLK_MQ_RDMA_H
+#define _LINUX_BLK_MQ_RDMA_H
+
+struct blk_mq_tag_set;
+struct ib_device;
+
+int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+		struct ib_device *dev, int first_vec);
+
+#endif /* _LINUX_BLK_MQ_RDMA_H */

index 609b5a11b251..494ed3ce751d 100644
@@ -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>

@@ -469,14 +470,10 @@ 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,

@@ -616,10 +613,20 @@ static int nvme_rdma_connect_io_queues(struct nvme_rdma_ctrl *ctrl)
 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;

@@ -1506,6 +1513,13 @@ 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,

@@ -1515,6 +1529,7 @@ static const struct blk_mq_ops nvme_rdma_mq_ops = {
 	.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 = {