From mboxrd@z Thu Jan 1 00:00:00 1970 From: hare@suse.de (Hannes Reinecke) Date: Fri, 5 Oct 2018 11:29:14 +0200 Subject: [PATCH 1/2] nvme: NUMA locality information for fabrics In-Reply-To: <20181005092915.126636-1-hare@suse.de> References: <20181005092915.126636-1-hare@suse.de> Message-ID: <20181005092915.126636-2-hare@suse.de> From: Hannes Reinecke Add a new field 'node_id' to the nvme_ctrl structure to hold the NUMA locality information of the underlying hardware. With that we can allocate the memory structures on the same NUMA node as the underlying hardware. Signed-off-by: Hannes Reinecke --- drivers/nvme/host/core.c | 4 +++- drivers/nvme/host/fc.c | 5 +++-- drivers/nvme/host/multipath.c | 4 ++-- drivers/nvme/host/nvme.h | 1 + drivers/nvme/host/pci.c | 1 + drivers/nvme/host/rdma.c | 5 +++-- 6 files changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2db33a752e2b..21c1d317415a 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2766,6 +2766,7 @@ static ssize_t field##_show(struct device *dev, \ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); nvme_show_int_function(cntlid); +nvme_show_int_function(node_id); static ssize_t nvme_sysfs_delete(struct device *dev, struct device_attribute *attr, const char *buf, @@ -2845,6 +2846,7 @@ static struct attribute *nvme_dev_attrs[] = { &dev_attr_subsysnqn.attr, &dev_attr_address.attr, &dev_attr_state.attr, + &dev_attr_node_id.attr, NULL }; @@ -3055,7 +3057,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) struct gendisk *disk; struct nvme_id_ns *id; char disk_name[DISK_NAME_LEN]; - int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT; + int node = ctrl->node_id, flags = GENHD_FL_EXT_DEVT; ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 9d201b35397d..7f246dd04bc5 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2422,7 +2422,7 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) ctrl->tag_set.ops = &nvme_fc_mq_ops; ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; ctrl->tag_set.reserved_tags = 1; /* fabric connect */ - ctrl->tag_set.numa_node = NUMA_NO_NODE; + ctrl->tag_set.numa_node = ctrl->ctrl.node_id; ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ctrl->tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) + (SG_CHUNK_SIZE * @@ -2990,6 +2990,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->ctrl.opts = opts; ctrl->ctrl.nr_reconnects = 0; + ctrl->ctrl.node_id = dev_to_node(lport->dev); INIT_LIST_HEAD(&ctrl->ctrl_list); ctrl->lport = lport; ctrl->rport = rport; @@ -3028,7 +3029,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops; ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */ - ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; + ctrl->admin_tag_set.numa_node = ctrl->ctrl.node_id; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) + (SG_CHUNK_SIZE * sizeof(struct scatterlist)) + diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 52987052b7fc..8d456c6f0e02 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -141,7 +141,7 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) test_bit(NVME_NS_ANA_PENDING, &ns->flags)) continue; - distance = node_distance(node, dev_to_node(ns->ctrl->dev)); + distance = node_distance(node, ns->ctrl->node_id); switch (ns->ana_state) { case NVME_ANA_OPTIMIZED: @@ -276,7 +276,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) if (!(ctrl->subsys->cmic & (1 << 1)) || !multipath) return 0; - q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, NULL); + q = blk_alloc_queue_node(GFP_KERNEL, ctrl->node_id, NULL); if (!q) goto out; q->queuedata = head; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9fefba039d1e..55347a547d84 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -153,6 +153,7 @@ struct nvme_ctrl { struct request_queue *connect_q; struct device *dev; int instance; + int node_id; struct blk_mq_tag_set *tagset; struct blk_mq_tag_set *admin_tagset; struct list_head namespaces; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d668682f91df..b5d37aacf212 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2517,6 +2517,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev)); + dev->ctrl.node_id = node; nvme_get_ctrl(&dev->ctrl); async_schedule(nvme_async_probe, dev); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index dc042017c293..707e158561ba 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -686,7 +686,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set->ops = &nvme_rdma_admin_mq_ops; set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; set->reserved_tags = 2; /* connect + keep-alive */ - set->numa_node = NUMA_NO_NODE; + set->numa_node = nctrl->node_id; set->cmd_size = sizeof(struct nvme_rdma_request) + SG_CHUNK_SIZE * sizeof(struct scatterlist); set->driver_data = ctrl; @@ -699,7 +699,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set->ops = &nvme_rdma_mq_ops; set->queue_depth = nctrl->sqsize + 1; set->reserved_tags = 1; /* fabric connect */ - set->numa_node = NUMA_NO_NODE; + set->numa_node = nctrl->node_id; set->flags = BLK_MQ_F_SHOULD_MERGE; set->cmd_size = sizeof(struct nvme_rdma_request) + SG_CHUNK_SIZE * sizeof(struct scatterlist); @@ -755,6 +755,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, return error; ctrl->device = ctrl->queues[0].device; + ctrl->ctrl.node_id = dev_to_node(ctrl->device->dev->dma_device); ctrl->max_fr_pages = nvme_rdma_get_max_fr_pages(ctrl->device->dev); -- 2.16.4