[PATCH 2/2] nvme-tcp: support specifying the congestion-control

[Mingbao Sun]

From: Mingbao Sun <tyler.sun@xxxxxxxx>

congestion-control could have a noticeable impaction on the
performance of TCP-based communications. This is of course true
to NVMe_over_TCP.

Different congestion-controls (e.g., cubic, dctcp) are suitable for
different scenarios. Proper adoption of congestion control would benefit
the performance. On the contrary, the performance could be destroyed.

Though we can specify the congestion-control of NVMe_over_TCP via
writing '/proc/sys/net/ipv4/tcp_congestion_control', but this also
changes the congestion-control of all the future TCP sockets that
have not been explicitly assigned the congestion-control, thus bringing
potential impaction on their performance.

So it makes sense to make NVMe_over_TCP support specifying the
congestion-control. And this commit addresses the host side.

Implementation approach:
a new option called 'tcp_congestion' was created in fabrics opt_tokens
for 'nvme connect' command to passed in the congestion-control
specified by the user.
Then later in nvme_tcp_alloc_queue, the specified congestion-control
would be applied to the relevant sockets of the host side.

Signed-off-by: Mingbao Sun <tyler.sun@xxxxxxxx>
---
 drivers/nvme/host/fabrics.c | 24 ++++++++++++++++++++++++
 drivers/nvme/host/fabrics.h |  2 ++
 drivers/nvme/host/tcp.c     | 20 +++++++++++++++++++-
 3 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index ee79a6d639b4..6d946f758372 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -10,6 +10,7 @@
 #include <linux/mutex.h>
 #include <linux/parser.h>
 #include <linux/seq_file.h>
+#include <net/tcp.h>
 #include "nvme.h"
 #include "fabrics.h"
 
@@ -548,6 +549,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_TOS,			"tos=%d"		},
 	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
 	{ NVMF_OPT_DISCOVERY,		"discovery"		},
+	{ NVMF_OPT_TCP_CONGESTION,	"tcp_congestion=%s"	},
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -560,6 +562,8 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 	size_t nqnlen  = 0;
 	int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
 	uuid_t hostid;
+	bool ecn_ca;
+	u32 key;
 
 	/* Set defaults */
 	opts->queue_size = NVMF_DEF_QUEUE_SIZE;
@@ -829,6 +833,25 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 		case NVMF_OPT_DISCOVERY:
 			opts->discovery_nqn = true;
 			break;
+		case NVMF_OPT_TCP_CONGESTION:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			key = tcp_ca_get_key_by_name(NULL, p, &ecn_ca);
+			if (key == TCP_CA_UNSPEC) {
+				pr_err("congestion control %s not found.\n",
+				       p);
+				ret = -EINVAL;
+				kfree(p);
+				goto out;
+			}
+
+			kfree(opts->tcp_congestion);
+			opts->tcp_congestion = p;
+			break;
 		default:
 			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
 				p);
@@ -947,6 +970,7 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts)
 	kfree(opts->subsysnqn);
 	kfree(opts->host_traddr);
 	kfree(opts->host_iface);
+	kfree(opts->tcp_congestion);
 	kfree(opts);
 }
 EXPORT_SYMBOL_GPL(nvmf_free_options);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index c3203ff1c654..25fdc169949d 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -68,6 +68,7 @@ enum {
 	NVMF_OPT_FAIL_FAST_TMO	= 1 << 20,
 	NVMF_OPT_HOST_IFACE	= 1 << 21,
 	NVMF_OPT_DISCOVERY	= 1 << 22,
+	NVMF_OPT_TCP_CONGESTION	= 1 << 23,
 };
 
 /**
@@ -117,6 +118,7 @@ struct nvmf_ctrl_options {
 	unsigned int		nr_io_queues;
 	unsigned int		reconnect_delay;
 	bool			discovery_nqn;
+	const char		*tcp_congestion;
 	bool			duplicate_connect;
 	unsigned int		kato;
 	struct nvmf_host	*host;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 6cbcc8b4daaf..cb2c7d7371d4 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1403,6 +1403,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 {
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+	char ca_name[TCP_CA_NAME_MAX];
+	sockptr_t optval;
 	int ret, rcv_pdu_size;
 
 	mutex_init(&queue->queue_lock);
@@ -1447,6 +1449,21 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	if (nctrl->opts->tos >= 0)
 		ip_sock_set_tos(queue->sock->sk, nctrl->opts->tos);
 
+	if (nctrl->opts->mask & NVMF_OPT_TCP_CONGESTION) {
+		strncpy(ca_name, nctrl->opts->tcp_congestion,
+			TCP_CA_NAME_MAX-1);
+		optval = KERNEL_SOCKPTR(ca_name);
+		ret = sock_common_setsockopt(queue->sock, IPPROTO_TCP,
+					     TCP_CONGESTION, optval,
+					     strlen(ca_name));
+		if (ret) {
+			dev_err(nctrl->device,
+				"failed to set TCP congestion to %s: %d\n",
+				ca_name, ret);
+			goto err_sock;
+		}
+	}
+
 	/* Set 10 seconds timeout for icresp recvmsg */
 	queue->sock->sk->sk_rcvtimeo = 10 * HZ;
 
@@ -2611,7 +2628,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
 			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
 			  NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST |
 			  NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
-			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE,
+			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE |
+			  NVMF_OPT_TCP_CONGESTION,
 	.create_ctrl	= nvme_tcp_create_ctrl,
 };
 
-- 
2.26.2