Merge branch 'for-4.14/block' of git://git.kernel.dk/linux-block

[linux.git] / drivers / nvme / host / rdma.c

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index da04df1af231758cb4965735c417a215d736ec94..bf42d31484d40b732e59cd68858fe4ce71666c53 100644 (file)
--- 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 @@ 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;
@@ -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
 };