[PATCH v2] RDMA/cma: Make CM response timeout and # CM retries configurable

[HÃkon Bugge]

During certain workloads, the default CM response timeout is too
short, leading to excessive retries. Hence, make it configurable
through sysctl. While at it, also make number of CM retries
configurable.

The defaults are not changed.

Signed-off-by: HÃkon Bugge <haakon.bugge@xxxxxxxxxx>

---
v1 -> v2:
   * Added unregister_net_sysctl_table() in cma_cleanup()
---
 drivers/infiniband/core/cma.c | 52 ++++++++++++++++++++++++++++++-----
 1 file changed, 45 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 68c997be2429..50abce078ff1 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -43,6 +43,7 @@
 #include <linux/inetdevice.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/sysctl.h>
 #include <net/route.h>
 
 #include <net/net_namespace.h>
@@ -68,13 +69,46 @@ MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("Generic RDMA CM Agent");
 MODULE_LICENSE("Dual BSD/GPL");
 
-#define CMA_CM_RESPONSE_TIMEOUT 20
 #define CMA_QUERY_CLASSPORT_INFO_TIMEOUT 3000
-#define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
 
+#define CMA_DFLT_CM_RESPONSE_TIMEOUT 20
+static int cma_cm_response_timeout = CMA_DFLT_CM_RESPONSE_TIMEOUT;
+static int cma_cm_response_timeout_min = 8;
+static int cma_cm_response_timeout_max = 31;
+#undef CMA_DFLT_CM_RESPONSE_TIMEOUT
+
+#define CMA_DFLT_MAX_CM_RETRIES 15
+static int cma_max_cm_retries = CMA_DFLT_MAX_CM_RETRIES;
+static int cma_max_cm_retries_min = 1;
+static int cma_max_cm_retries_max = 100;
+#undef CMA_DFLT_MAX_CM_RETRIES
+
+static struct ctl_table_header *cma_ctl_table_hdr;
+static struct ctl_table cma_ctl_table[] = {
+	{
+		.procname	= "cma_cm_response_timeout",
+		.data		= &cma_cm_response_timeout,
+		.maxlen		= sizeof(cma_cm_response_timeout),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &cma_cm_response_timeout_min,
+		.extra2		= &cma_cm_response_timeout_max,
+	},
+	{
+		.procname	= "cma_max_cm_retries",
+		.data		= &cma_max_cm_retries,
+		.maxlen		= sizeof(cma_max_cm_retries),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &cma_max_cm_retries_min,
+		.extra2		= &cma_max_cm_retries_max,
+	},
+	{ }
+};
+
 static const char * const cma_events[] = {
 	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
 	[RDMA_CM_EVENT_ADDR_ERROR]	 = "address error",
@@ -3744,8 +3778,8 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 	req.path = id_priv->id.route.path_rec;
 	req.sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr;
 	req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv));
-	req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8);
-	req.max_cm_retries = CMA_MAX_CM_RETRIES;
+	req.timeout_ms = 1 << (cma_cm_response_timeout - 8);
+	req.max_cm_retries = cma_max_cm_retries;
 
 	ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req);
 	if (ret) {
@@ -3815,9 +3849,9 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
 	req.flow_control = conn_param->flow_control;
 	req.retry_count = min_t(u8, 7, conn_param->retry_count);
 	req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count);
-	req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT;
-	req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT;
-	req.max_cm_retries = CMA_MAX_CM_RETRIES;
+	req.remote_cm_response_timeout = cma_cm_response_timeout;
+	req.local_cm_response_timeout = cma_cm_response_timeout;
+	req.max_cm_retries = cma_max_cm_retries;
 	req.srq = id_priv->srq ? 1 : 0;
 
 	ret = ib_send_cm_req(id_priv->cm_id.ib, &req);
@@ -4700,6 +4734,9 @@ static int __init cma_init(void)
 		goto err;
 
 	cma_configfs_init();
+	cma_ctl_table_hdr = register_net_sysctl(&init_net, "net/rdma_cm", cma_ctl_table);
+	if (!cma_ctl_table_hdr)
+		pr_warn("rdma_cm: couldn't register sysctl path, using default values\n");
 
 	return 0;
 
@@ -4713,6 +4750,7 @@ static int __init cma_init(void)
 
 static void __exit cma_cleanup(void)
 {
+	unregister_net_sysctl_table(cma_ctl_table_hdr);
 	cma_configfs_exit();
 	ib_unregister_client(&cma_client);
 	unregister_netdevice_notifier(&cma_nb);
-- 
2.20.1