nvme-loop: handle cpu unplug when re-establishing the controller

If a cpu unplug event has occured, we need to take the minimum
of the provided nr_io_queues and the number of online cpus,
otherwise we won't be able to connect them as blk-mq mapping
won't dispatch to those queues.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 74e04a0855d452c3e15c966408a43b7d34202c70..22f7bc6bac7fa77dd48198cde3a31ef60ead531b 100644 (file)
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -223,8 +223,6 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx)
 static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl,
                struct nvme_loop_iod *iod, unsigned int queue_idx)
 {
-       BUG_ON(queue_idx >= ctrl->queue_count);
-
        iod->req.cmd = &iod->cmd;
        iod->req.rsp = &iod->rsp;
        iod->queue = &ctrl->queues[queue_idx];
@@ -314,6 +312,43 @@ free_ctrl:
        kfree(ctrl);
 }
 
+static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+       int i;
+
+       for (i = 1; i < ctrl->queue_count; i++)
+               nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+}
+
+static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+       struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+       unsigned int nr_io_queues;
+       int ret, i;
+
+       nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+       ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+       if (ret || !nr_io_queues)
+               return ret;
+
+       dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n", nr_io_queues);
+
+       for (i = 1; i <= nr_io_queues; i++) {
+               ctrl->queues[i].ctrl = ctrl;
+               ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
+               if (ret)
+                       goto out_destroy_queues;
+
+               ctrl->queue_count++;
+       }
+
+       return 0;
+
+out_destroy_queues:
+       nvme_loop_destroy_io_queues(ctrl);
+       return ret;
+}
+
 static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
        int error;
@@ -385,17 +420,13 @@ out_free_sq:
 
 static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
 {
-       int i;
-
        nvme_stop_keep_alive(&ctrl->ctrl);
 
        if (ctrl->queue_count > 1) {
                nvme_stop_queues(&ctrl->ctrl);
                blk_mq_tagset_busy_iter(&ctrl->tag_set,
                                        nvme_cancel_request, &ctrl->ctrl);
-
-               for (i = 1; i < ctrl->queue_count; i++)
-                       nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+               nvme_loop_destroy_io_queues(ctrl);
        }
 
        if (ctrl->ctrl.state == NVME_CTRL_LIVE)
@@ -467,19 +498,14 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
        if (ret)
                goto out_disable;
 
-       for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
-               ctrl->queues[i].ctrl = ctrl;
-               ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
-               if (ret)
-                       goto out_free_queues;
-
-               ctrl->queue_count++;
-       }
+       ret = nvme_loop_init_io_queues(ctrl);
+       if (ret)
+               goto out_destroy_admin;
 
-       for (i = 1; i <= ctrl->ctrl.opts->nr_io_queues; i++) {
+       for (i = 1; i < ctrl->queue_count; i++) {
                ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
                if (ret)
-                       goto out_free_queues;
+                       goto out_destroy_io;
        }
 
        changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
@@ -492,9 +518,9 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
 
        return;
 
-out_free_queues:
-       for (i = 1; i < ctrl->queue_count; i++)
-               nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+out_destroy_io:
+       nvme_loop_destroy_io_queues(ctrl);
+out_destroy_admin:
        nvme_loop_destroy_admin_queue(ctrl);
 out_disable:
        dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
@@ -533,25 +559,12 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 {
-       struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
        int ret, i;
 
-       ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
-       if (ret || !opts->nr_io_queues)
+       ret = nvme_loop_init_io_queues(ctrl);
+       if (ret)
                return ret;
 
-       dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
-               opts->nr_io_queues);
-
-       for (i = 1; i <= opts->nr_io_queues; i++) {
-               ctrl->queues[i].ctrl = ctrl;
-               ret = nvmet_sq_init(&ctrl->queues[i].nvme_sq);
-               if (ret)
-                       goto out_destroy_queues;
-
-               ctrl->queue_count++;
-       }
-
        memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
        ctrl->tag_set.ops = &nvme_loop_mq_ops;
        ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
@@ -575,7 +588,7 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
                goto out_free_tagset;
        }
 
-       for (i = 1; i <= opts->nr_io_queues; i++) {
+       for (i = 1; i < ctrl->queue_count; i++) {
                ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
                if (ret)
                        goto out_cleanup_connect_q;
@@ -588,8 +601,7 @@ out_cleanup_connect_q:
 out_free_tagset:
        blk_mq_free_tag_set(&ctrl->tag_set);
 out_destroy_queues:
-       for (i = 1; i < ctrl->queue_count; i++)
-               nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
+       nvme_loop_destroy_io_queues(ctrl);
        return ret;
 }