nvme-tcp: Add TOS for tcp transport

TOS provide clients the ability to segregate traffic flows for
different type of data.
One of the TOS usage is bandwidth management which allows setting bandwidth
limits for QoS classes, e.g. 80% bandwidth to controllers at QoS class A
and 20% to controllers at QoS class B.

usage examples:
nvme connect --tos=0 --transport=tcp --traddr=10.0.1.1 --nqn=test-nvme

Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1ae985e..a9c3f28 100644 (file)
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1304,6 +1304,18 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
                goto err_sock;
        }
 
+       /* Set socket type of service */
+       if (nctrl->opts->tos >= 0) {
+               opt = nctrl->opts->tos;
+               ret = kernel_setsockopt(queue->sock, SOL_IP, IP_TOS,
+                               (char *)&opt, sizeof(opt));
+               if (ret) {
+                       dev_err(nctrl->device,
+                               "failed to set IP_TOS sock opt %d\n", ret);
+                       goto err_sock;
+               }
+       }
+
        queue->sock->sk->sk_allocation = GFP_ATOMIC;
        if (!qid)
                n = 0;
@@ -2344,7 +2356,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
        .allowed_opts   = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
                          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_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
+                         NVMF_OPT_TOS,
        .create_ctrl    = nvme_tcp_create_ctrl,
 };