Expose cpu mapping hints to a nvme target port

index a358ecd93e11..095c2e6b4116 100644
@@ -17,12 +17,63 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/ctype.h>
+#include <linux/cpumask.h>
 
 #include "nvmet.h"
 
 static struct config_item_type nvmet_host_type;
 static struct config_item_type nvmet_subsys_type;
 
+static ssize_t nvmet_addr_cpulist_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return sprintf(page, "%*pbl\n", cpumask_pr_args(port->cpumask));
+}
+
+static ssize_t nvmet_addr_cpulist_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	cpumask_var_t cpumask;
+	int i, err;
+
+	if (port->enabled) {
+		pr_err("Cannot specify cpulist while enabled\n");
+		pr_err("Disable the port before changing cores\n");
+		return -EACCES;
+	}
+
+	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	err = cpulist_parse(page, cpumask);
+	if (err) {
+		pr_err("bad cpumask given (%d): %s\n", err, page);
+		return err;
+	}
+
+	if (!cpumask_intersects(cpumask, cpu_online_mask)) {
+		pr_err("cpulist consists of offline cpus: %s\n", page);
+		return err;
+	}
+
+	/* copy cpumask */
+	cpumask_copy(port->cpumask, cpumask);
+	free_cpumask_var(cpumask);
+
+	/* clear port cpulist */
+	port->nr_cpus = 0;
+	/* reset port cpulist */
+	for_each_cpu(i, cpumask)
+		port->cpus[port->nr_cpus++] = i;
+
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, addr_cpulist);
+
 /*
  * nvmet_port Generic ConfigFS definitions.
  * Used in any place in the ConfigFS tree that refers to an address.

@@ -821,6 +872,7 @@ static struct config_group *nvmet_referral_make(
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&port->entry);
+
 	config_group_init_type_name(&port->group, name, &nvmet_referral_type);
 
 	return &port->group;

@@ -842,6 +894,8 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	kfree(port->cpus);
+	free_cpumask_var(port->cpumask);
 	kfree(port);
 }
 

@@ -851,6 +905,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
+	&nvmet_attr_addr_cpulist,
 	NULL,
 };
 

@@ -869,6 +924,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 {
 	struct nvmet_port *port;
 	u16 portid;
+	int i;
 
 	if (kstrtou16(name, 0, &portid))
 		return ERR_PTR(-EINVAL);

@@ -881,6 +937,20 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
 
+	if (!alloc_cpumask_var(&port->cpumask, GFP_KERNEL))
+		goto err_free_port;
+
+	port->nr_cpus = num_possible_cpus();
+
+	port->cpus = kcalloc(sizeof(int), port->nr_cpus, GFP_KERNEL);
+	if (!port->cpus)
+		goto err_free_cpumask;
+
+	for_each_possible_cpu(i) {
+		cpumask_set_cpu(i, port->cpumask);
+		port->cpus[i] = i;
+	}
+
 	port->disc_addr.portid = cpu_to_le16(portid);
 	config_group_init_type_name(&port->group, name, &nvmet_port_type);
 

@@ -893,6 +963,11 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	configfs_add_default_group(&port->referrals_group, &port->group);
 
 	return &port->group;
+
+err_free_cpumask:
+	free_cpumask_var(port->cpumask);
+err_free_port:
+	return ERR_PTR(-ENOMEM);
 }
 
 static struct configfs_group_operations nvmet_ports_group_ops = {

index 747bbdb4f9c6..20ed676dc335 100644
@@ -97,6 +97,10 @@ struct nvmet_port {
 	struct list_head		referrals;
 	void				*priv;
 	bool				enabled;
+
+	int				nr_cpus;
+	cpumask_var_t			cpumask;
+	int				*cpus;
 };
 
 static inline struct nvmet_port *to_nvmet_port(struct config_item *item)

index 4792f5209ac2..f0dfb1ca952b 100644
@@ -2099,3 +2099,44 @@ void ib_drain_qp(struct ib_qp *qp)
 		ib_drain_rq(qp);
 }
 EXPORT_SYMBOL(ib_drain_qp);
+
+/**
+ * ib_find_cpu_vector() - Find the first completion vector mapped to a given cpu core
+ * @device:            rdma device
+ * @cpu:               cpu for the corresponding completion vector affinity
+ * @vector:            output target completion vector
+ *
+ * If the device expose vector affinity we will search each of the vectors
+ * and if we find one that gives us the desired cpu core we return true
+ * and assign @vector to the corresponding completion vector. Otherwise
+ * we return false. We stop at the first appropriate completion vector
+ * we find as we don't have any preference for multiple vectors with the
+ * same affinity.
+ */
+bool ib_find_cpu_vector(struct ib_device *device, unsigned int cpu,
+		unsigned int *vector)
+{
+	bool found = false;
+	unsigned int c;
+	int vec;
+
+	for (vec = 0; vec < device->num_comp_vectors; vec++) {
+		const struct cpumask *mask;
+
+		mask = ib_get_vector_affinity(device, vec);
+		if (!mask)
+			goto out;
+
+		for_each_cpu(c, mask) {
+			if (c == cpu) {
+				*vector = vec;
+				found = true;
+				goto out;
+			}
+		}
+	}
+
+out:
+	return found;
+}
+EXPORT_SYMBOL(ib_find_cpu_vector);

index 2349143297c9..8af48ef811f8 100644
@@ -3662,4 +3662,7 @@ ib_get_vector_affinity(struct ib_device *device, int comp_vector)
 
 }
 
+bool ib_find_cpu_vector(struct ib_device *device, unsigned int cpu,
+		unsigned int *vector);
+
 #endif /* IB_VERBS_H */

index 56a4cba690b5..a1725d3e174a 100644
@@ -889,27 +889,43 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 	return NULL;
 }
 
-static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
+static int nvmet_rdma_assign_vector(struct nvmet_rdma_queue *queue)
 {
-	struct ib_qp_init_attr qp_attr;
-	struct nvmet_rdma_device *ndev = queue->dev;
-	int comp_vector, nr_cqe, ret, i;
+	struct ib_device *dev = queue->dev->device;
+	struct nvmet_port *port = queue->port;
+	int vec, cpu;
 
 	/*
-	 * Spread the io queues across completion vectors,
-	 * but still keep all admin queues on vector 0.
+	 * Spread the io queues across port cpus,
+	 * but still keep all admin queues on cpu 0.
 	 */
-	comp_vector = !queue->host_qid ? 0 :
-		queue->idx % ndev->device->num_comp_vectors;
+	cpu = !queue->host_qid ? 0 : port->cpus[queue->idx % port->nr_cpus];
+
+	if (ib_find_cpu_vector(dev, cpu, &vec))
+		return vec;
+
+	pr_debug("device %s could not provide vector to match cpu %d\n",
+			dev->name, cpu);
+	/*
+	 * No corresponding vector affinity found, fallback to
+	 * the old behavior where we spread vectors all over...
+	 */
+	return !queue->host_qid ? 0 : queue->idx % dev->num_comp_vectors;
+}
+
+static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
+{
+	struct ib_qp_init_attr qp_attr;
+	struct nvmet_rdma_device *ndev = queue->dev;
+	int nr_cqe, ret, i;
 
 	/*
 	 * Reserve CQ slots for RECV + RDMA_READ/RDMA_WRITE + RDMA_SEND.
 	 */
 	nr_cqe = queue->recv_queue_size + 2 * queue->send_queue_size;
 
-	queue->cq = ib_alloc_cq(ndev->device, queue,
-			nr_cqe + 1, comp_vector,
-			IB_POLL_WORKQUEUE);
+	queue->cq = ib_alloc_cq(ndev->device, queue, nr_cqe + 1,
+			nvmet_rdma_assign_vector(queue), IB_POLL_WORKQUEUE);
 	if (IS_ERR(queue->cq)) {
 		ret = PTR_ERR(queue->cq);
 		pr_err("failed to create CQ cqe= %d ret= %d\n",

@@ -1080,6 +1096,7 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 	INIT_WORK(&queue->release_work, nvmet_rdma_release_queue_work);
 	queue->dev = ndev;
 	queue->cm_id = cm_id;
+	queue->port = cm_id->context;
 
 	spin_lock_init(&queue->state_lock);
 	queue->state = NVMET_RDMA_Q_CONNECTING;

@@ -1198,7 +1215,6 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
 		ret = -ENOMEM;
 		goto put_device;
 	}
-	queue->port = cm_id->context;
 
 	if (queue->host_qid == 0) {
 		/* Let inflight controller teardown complete */