[RFC PATCH 4/4] nvme: expose queue information via debugfs

[Nilay Shroff <nilay@linux.ibm.com>]

Add a new debugfs attribute "io_queue_info" to expose per-queue
information for NVMe controllers. For NVMe-TCP, this includes the
CPU handling each I/O queue and the associated TCP flow (source and
destination address/port).

This information can be useful for understanding and tuning the
interaction between NVMe-TCP I/O queues and network stack components,
such as IRQ affinity, RPS/RFS, XPS, or NIC flow steering (ntuple).

The data is exported using seq_file interfaces to allow iteration
over all controller queues.

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 drivers/nvme/host/core.c    |  3 +++
 drivers/nvme/host/debugfs.c | 53 ++++++++++++++++++++++++++++++++++++-
 drivers/nvme/host/nvme.h    |  2 ++
 drivers/nvme/host/tcp.c     | 52 ++++++++++++++++++++++++++++++++++++
 4 files changed, 109 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1e33af94c24b..1b0d13374d45 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4207,6 +4207,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
 		goto out_cleanup_ns_from_list;
 
+	nvme_debugfs_register(ns->disk);
+
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_add_ns_cdev(ns);
 
@@ -4285,6 +4287,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 
 	nvme_mpath_remove_sysfs_link(ns);
 
+	nvme_debugfs_unregister(ns->disk);
 	del_gendisk(ns->disk);
 
 	mutex_lock(&ns->ctrl->namespaces_lock);
diff --git a/drivers/nvme/host/debugfs.c b/drivers/nvme/host/debugfs.c
index ee86138487d0..68c40582fa97 100644
--- a/drivers/nvme/host/debugfs.c
+++ b/drivers/nvme/host/debugfs.c
@@ -22,6 +22,56 @@ struct nvme_debugfs_ctx {
 	struct nvme_debugfs_attr *attr;
 };
 
+static void *nvme_io_queue_info_start(struct seq_file *m, loff_t *pos)
+{
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns *ns = ctx->data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
+
+	nvme_get_ctrl(ctrl);
+	/*
+	 * IO queues starts at offset 1.
+	 */
+	return (++*pos < ctrl->queue_count) ? pos : NULL;
+}
+
+static void *nvme_io_queue_info_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns *ns = ctx->data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
+
+	return (++*pos < ctrl->queue_count) ? pos : NULL;
+}
+
+static void nvme_io_queue_info_stop(struct seq_file *m, void *v)
+{
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns *ns = ctx->data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
+
+	nvme_put_ctrl(ctrl);
+}
+
+static int nvme_io_queue_info_show(struct seq_file *m, void *v)
+{
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns *ns = ctx->data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
+
+	if (ctrl->ops->print_io_queue_info)
+		return ctrl->ops->print_io_queue_info(m, ctrl, *(loff_t *)v);
+
+	return 0;
+}
+
+const struct seq_operations nvme_io_queue_info_seq_ops = {
+	.start = nvme_io_queue_info_start,
+	.next = nvme_io_queue_info_next,
+	.stop = nvme_io_queue_info_stop,
+	.show = nvme_io_queue_info_show
+};
+
 static int nvme_debugfs_show(struct seq_file *m, void *v)
 {
 	struct nvme_debugfs_ctx *ctx = m->private;
@@ -90,7 +140,8 @@ static const struct file_operations nvme_debugfs_fops = {
 };
 
 static const struct nvme_debugfs_attr nvme_ns_debugfs_attrs[] = {
-	{},
+	{"io_queue_info", 0400, .seq_ops = &nvme_io_queue_info_seq_ops},
+	{}
 };
 
 static void nvme_debugfs_create_files(struct request_queue *q,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2f3f1d2d19b9..d7ff82971136 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -650,6 +650,8 @@ struct nvme_ctrl_ops {
 	void (*print_device_info)(struct nvme_ctrl *ctrl);
 	bool (*supports_pci_p2pdma)(struct nvme_ctrl *ctrl);
 	unsigned long (*get_virt_boundary)(struct nvme_ctrl *ctrl, bool is_admin);
+	int (*print_io_queue_info)(struct seq_file *m, struct nvme_ctrl *ctrl,
+			int qid);
 };
 
 /*
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 9239495122fc..6d06e984de47 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2723,6 +2723,57 @@ static void nvme_tcp_free_ctrl(struct nvme_ctrl *nctrl)
 	kfree(ctrl);
 }
 
+static int nvme_tcp_print_io_queue_info(struct seq_file *m,
+		struct nvme_ctrl *ctrl, int qid)
+{
+	int cpu;
+	struct sockaddr_storage src, dst;
+	struct nvme_tcp_ctrl *tctrl = to_tcp_ctrl(ctrl);
+	struct nvme_tcp_queue *queue = &tctrl->queues[qid];
+	int ret = -EINVAL;
+
+	if (!qid || qid >= ctrl->queue_count  ||
+			!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
+		return -EINVAL;
+
+	mutex_lock(&queue->queue_lock);
+	if (!queue->sock)
+		goto unlock;
+
+	ret = kernel_getsockname(queue->sock, (struct sockaddr *)&src);
+	if (ret <= 0)
+		goto unlock;
+
+	ret = kernel_getpeername(queue->sock, (struct sockaddr *)&dst);
+	if (ret <= 0)
+		goto unlock;
+
+	cpu = (queue->io_cpu == WORK_CPU_UNBOUND) ? -1 : queue->io_cpu;
+
+	if (src.ss_family == AF_INET) {
+		struct sockaddr_in *sip = (struct sockaddr_in *)&src;
+		struct sockaddr_in *dip = (struct sockaddr_in *)&dst;
+
+		seq_printf(m, "qid=%d cpu=%d src_ip=%pI4 src_port=%u dst_ip=%pI4 dst_port=%u\n",
+				qid, cpu,
+				&sip->sin_addr.s_addr, ntohs(sip->sin_port),
+				&dip->sin_addr.s_addr, ntohs(dip->sin_port));
+		ret = 0;
+	} else if (src.ss_family == AF_INET6) {
+		struct sockaddr_in6 *sip6 = (struct sockaddr_in6 *)&src;
+		struct sockaddr_in6 *dip6 = (struct sockaddr_in6 *)&dst;
+
+		seq_printf(m, "qid=%d cpu=%d src_ip=%pI6c src_port=%u dst_ip=%pI6c dst_port=%u\n",
+				qid, cpu,
+				&sip6->sin6_addr, ntohs(sip6->sin6_port),
+				&dip6->sin6_addr, ntohs(dip6->sin6_port));
+		ret = 0;
+	}
+unlock:
+	mutex_unlock(&queue->queue_lock);
+	return ret;
+}
+
 static void nvme_tcp_set_sg_null(struct nvme_command *c)
 {
 	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
@@ -3023,6 +3074,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = {
 	.get_address		= nvme_tcp_get_address,
 	.stop_ctrl		= nvme_tcp_stop_ctrl,
 	.get_virt_boundary	= nvmf_get_virt_boundary,
+	.print_io_queue_info	= nvme_tcp_print_io_queue_info,
 };
 
 static bool
-- 
2.53.0