summaryrefslogtreecommitdiff
path: root/drivers/nvme/target/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme/target/tcp.c')
-rw-r--r--drivers/nvme/target/tcp.c47
1 files changed, 41 insertions, 6 deletions
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index af674fc0bb1e..f0da04e960f4 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -19,6 +19,16 @@
#define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE)
+/* Define the socket priority to use for connections were it is desirable
+ * that the NIC consider performing optimized packet processing or filtering.
+ * A non-zero value being sufficient to indicate general consideration of any
+ * possible optimization. Making it a module param allows for alternative
+ * values that may be unique for some NIC implementations.
+ */
+static int so_priority;
+module_param(so_priority, int, 0644);
+MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority");
+
#define NVMET_TCP_RECV_BUDGET 8
#define NVMET_TCP_SEND_BUDGET 8
#define NVMET_TCP_IO_WORK_BUDGET 64
@@ -515,7 +525,7 @@ static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
return 1;
}
-static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
struct nvmet_tcp_queue *queue = cmd->queue;
int ret;
@@ -523,9 +533,15 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
while (cmd->cur_sg) {
struct page *page = sg_page(cmd->cur_sg);
u32 left = cmd->cur_sg->length - cmd->offset;
+ int flags = MSG_DONTWAIT;
+
+ if ((!last_in_batch && cmd->queue->send_list_len) ||
+ cmd->wbytes_done + left < cmd->req.transfer_len ||
+ queue->data_digest || !queue->nvme_sq.sqhd_disabled)
+ flags |= MSG_MORE;
ret = kernel_sendpage(cmd->queue->sock, page, cmd->offset,
- left, MSG_DONTWAIT | MSG_MORE);
+ left, flags);
if (ret <= 0)
return ret;
@@ -616,7 +632,7 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
return 1;
}
-static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
struct nvmet_tcp_queue *queue = cmd->queue;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
@@ -626,6 +642,9 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
};
int ret;
+ if (!last_in_batch && cmd->queue->send_list_len)
+ msg.msg_flags |= MSG_MORE;
+
ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
if (unlikely(ret <= 0))
return ret;
@@ -660,13 +679,13 @@ static int nvmet_tcp_try_send_one(struct nvmet_tcp_queue *queue,
}
if (cmd->state == NVMET_TCP_SEND_DATA) {
- ret = nvmet_try_send_data(cmd);
+ ret = nvmet_try_send_data(cmd, last_in_batch);
if (ret <= 0)
goto done_send;
}
if (cmd->state == NVMET_TCP_SEND_DDGST) {
- ret = nvmet_try_send_ddgst(cmd);
+ ret = nvmet_try_send_ddgst(cmd, last_in_batch);
if (ret <= 0)
goto done_send;
}
@@ -788,7 +807,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
icresp->hdr.pdo = 0;
icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
- icresp->maxdata = cpu_to_le32(0xffff); /* FIXME: support r2t */
+ icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
icresp->cpda = 0;
if (queue->hdr_digest)
icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@@ -1433,6 +1452,13 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue)
if (ret)
return ret;
+ if (so_priority > 0) {
+ ret = kernel_setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
+ (char *)&so_priority, sizeof(so_priority));
+ if (ret)
+ return ret;
+ }
+
/* Set socket type of service */
if (inet->rcv_tos > 0) {
int tos = inet->rcv_tos;
@@ -1622,6 +1648,15 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
goto err_sock;
}
+ if (so_priority > 0) {
+ ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_PRIORITY,
+ (char *)&so_priority, sizeof(so_priority));
+ if (ret) {
+ pr_err("failed to set SO_PRIORITY sock opt %d\n", ret);
+ goto err_sock;
+ }
+ }
+
ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
sizeof(port->addr));
if (ret) {