[PATCH net-next 1/2] net/smc: send cdc msg inline if qp has sufficient inline space

[Guangguan Wang]

As cdc msg's length is 44B, cdc msgs can be sent inline in
most rdma devices, which can help reducing sending latency.

In my test environment, which are 2 VMs running on the same
physical host and whose NICs(ConnectX-4Lx) are working on
SR-IOV mode, qperf shows 0.4us-0.7us improvement in latency.

Test command:
server: smc_run taskset -c 1 qperf
client: smc_run taskset -c 1 qperf <server ip> -oo \
		msg_size:1:2K:*2 -t 30 -vu tcp_lat

The results shown below:
msgsize     before       after
1B          11.9 us      11.2 us (-0.7 us)
2B          11.7 us      11.2 us (-0.5 us)
4B          11.7 us      11.3 us (-0.4 us)
8B          11.6 us      11.2 us (-0.4 us)
16B         11.7 us      11.3 us (-0.4 us)
32B         11.7 us      11.3 us (-0.4 us)
64B         11.7 us      11.2 us (-0.5 us)
128B        11.6 us      11.2 us (-0.4 us)
256B        11.8 us      11.2 us (-0.6 us)
512B        11.8 us      11.4 us (-0.4 us)
1KB         11.9 us      11.4 us (-0.5 us)
2KB         12.1 us      11.5 us (-0.6 us)

Signed-off-by: Guangguan Wang <guangguan.wang@xxxxxxxxxxxxxxxxx>
---
 net/smc/smc_ib.c | 1 +
 net/smc/smc_wr.c | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index a3e2d3b89568..1dcce9e4f4ca 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -671,6 +671,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk)
 			.max_recv_wr = SMC_WR_BUF_CNT * 3,
 			.max_send_sge = SMC_IB_MAX_SEND_SGE,
 			.max_recv_sge = sges_per_buf,
+			.max_inline_data = SMC_WR_TX_SIZE,
 		},
 		.sq_sig_type = IB_SIGNAL_REQ_WR,
 		.qp_type = IB_QPT_RC,
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 24be1d03fef9..8a2f9a561197 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -554,10 +554,11 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk)
 static void smc_wr_init_sge(struct smc_link *lnk)
 {
 	int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1;
+	bool send_inline = (lnk->qp_attr.cap.max_inline_data >= SMC_WR_TX_SIZE);
 	u32 i;
 
 	for (i = 0; i < lnk->wr_tx_cnt; i++) {
-		lnk->wr_tx_sges[i].addr =
+		lnk->wr_tx_sges[i].addr = send_inline ? (u64)(&lnk->wr_tx_bufs[i]) :
 			lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE;
 		lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE;
 		lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey;
@@ -575,6 +576,8 @@ static void smc_wr_init_sge(struct smc_link *lnk)
 		lnk->wr_tx_ibs[i].opcode = IB_WR_SEND;
 		lnk->wr_tx_ibs[i].send_flags =
 			IB_SEND_SIGNALED | IB_SEND_SOLICITED;
+		if (send_inline)
+			lnk->wr_tx_ibs[i].send_flags |= IB_SEND_INLINE;
 		lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE;
 		lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE;
 		lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list =
-- 
2.24.3 (Apple Git-128)