net/smc: use read semaphores to reduce unnecessary blocking in smc_buf_create() & smcr_buf_unuse()

Following is part of Off-CPU graph during frequent SMC-R short-lived
processing:

process_one_work				(51.19%)
smc_close_passive_work			(28.36%)
	smcr_buf_unuse				(28.34%)
	rwsem_down_write_slowpath		(28.22%)

smc_listen_work				(22.83%)
	smc_clc_wait_msg			(1.84%)
	smc_buf_create				(20.45%)
		smcr_buf_map_usable_links
		rwsem_down_write_slowpath	(20.43%)
	smcr_lgr_reg_rmbs			(0.53%)
		rwsem_down_write_slowpath	(0.43%)
		smc_llc_do_confirm_rkey		(0.08%)

We can clearly see that during the connection establishment time,
waiting time of connections is not on IO, but on llc_conf_mutex.

What is more important, the core critical area (smcr_buf_unuse() &
smc_buf_create()) only perfroms read semantics on links, we can
easily replace it with read semaphore.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/smc_core.c

@@ -1106,10 +1106,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
 		rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
 		if (!rc) {
 			/* protect against smc_llc_cli_rkey_exchange() */
-			down_write(&lgr->llc_conf_mutex);
+			down_read(&lgr->llc_conf_mutex);
 			smc_llc_do_delete_rkey(lgr, buf_desc);
 			buf_desc->is_conf_rkey = false;
-			up_write(&lgr->llc_conf_mutex);
+			up_read(&lgr->llc_conf_mutex);
 			smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
 		}
 	}
@@ -2247,7 +2247,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
 	int i, rc = 0, cnt = 0;
 
 	/* protect against parallel link reconfiguration */
-	down_write(&lgr->llc_conf_mutex);
+	down_read(&lgr->llc_conf_mutex);
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 		struct smc_link *lnk = &lgr->lnk[i];
 
@@ -2260,7 +2260,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
 		cnt++;
 	}
 out:
-	up_write(&lgr->llc_conf_mutex);
+	up_read(&lgr->llc_conf_mutex);
 	if (!rc && !cnt)
 		rc = -EINVAL;
 	return rc;