[openib-general] [PATCH v2] IB_CM: Limit CM message timeouts
Sean Hefty
sean.hefty at intel.com
Thu Oct 5 11:06:57 PDT 2006
Limit the timeout that the ib_cm will wait to receive a response to
a message, to avoid excessively large (on the order of hours) timeout
values. This prevents consuming resources tracking requests for
extended periods of time.
This helps correct for a bug in SRP Engenio target sending a large
value (>1 hour) as service timeout.
Signed-off-by: Sean Hefty <sean.hefty at intel.com>
---
Michael / Ishai, this is untested. Can you please let me know if it
works for you? I didn't change the packet life time, since that's
needed to configure the QP.
Index: cm.c
===================================================================
--- cm.c (revision 9713)
+++ cm.c (working copy)
@@ -54,6 +54,12 @@ MODULE_AUTHOR("Sean Hefty");
MODULE_DESCRIPTION("InfiniBand CM");
MODULE_LICENSE("Dual BSD/GPL");
+/*
+ * Limit CM msg timeouts to something reasonable.
+ * 8 seconds, with up to 15 retries, gives per msg timeout of 2 min.
+ */
+#define IB_CM_MAX_TIMEOUT 21
+
static void cm_add_one(struct ib_device *device);
static void cm_remove_one(struct ib_device *device);
@@ -891,12 +897,12 @@ static void cm_format_req(struct cm_req_
cm_req_set_resp_res(req_msg, param->responder_resources);
cm_req_set_init_depth(req_msg, param->initiator_depth);
cm_req_set_remote_resp_timeout(req_msg,
- param->remote_cm_response_timeout);
+ min((u8) IB_CM_MAX_TIMEOUT, param->remote_cm_response_timeout));
cm_req_set_qp_type(req_msg, param->qp_type);
cm_req_set_flow_ctrl(req_msg, param->flow_control);
cm_req_set_starting_psn(req_msg, cpu_to_be32(param->starting_psn));
cm_req_set_local_resp_timeout(req_msg,
- param->local_cm_response_timeout);
+ min((u8) IB_CM_MAX_TIMEOUT, param->local_cm_response_timeout));
cm_req_set_retry_count(req_msg, param->retry_count);
req_msg->pkey = param->primary_path->pkey;
cm_req_set_path_mtu(req_msg, param->primary_path->mtu);
@@ -1002,10 +1008,10 @@ int ib_send_cm_req(struct ib_cm_id *cm_i
}
cm_id->service_id = param->service_id;
cm_id->service_mask = __constant_cpu_to_be64(~0ULL);
- cm_id_priv->timeout_ms = cm_convert_to_ms(
- param->primary_path->packet_life_time) * 2 +
- cm_convert_to_ms(
- param->remote_cm_response_timeout);
+ cm_id_priv->timeout_ms =
+ min(IB_CM_MAX_TIMEOUT,
+ cm_convert_to_ms(param->primary_path->packet_life_time) * 2 +
+ cm_convert_to_ms(param->remote_cm_response_timeout));
cm_id_priv->max_cm_retries = param->max_cm_retries;
cm_id_priv->initiator_depth = param->initiator_depth;
cm_id_priv->responder_resources = param->responder_resources;
@@ -1404,8 +1410,9 @@ static int cm_req_handler(struct cm_work
}
}
cm_id_priv->tid = req_msg->hdr.tid;
- cm_id_priv->timeout_ms = cm_convert_to_ms(
- cm_req_get_local_resp_timeout(req_msg));
+ cm_id_priv->timeout_ms =
+ min(IB_CM_MAX_TIMEOUT,
+ cm_convert_to_ms(cm_req_get_local_resp_timeout(req_msg)));
cm_id_priv->max_cm_retries = cm_req_get_max_cm_retries(req_msg);
cm_id_priv->remote_qpn = cm_req_get_local_qpn(req_msg);
cm_id_priv->initiator_depth = cm_req_get_resp_res(req_msg);
@@ -2308,8 +2315,9 @@ static int cm_mra_handler(struct cm_work
work->cm_event.private_data = &mra_msg->private_data;
work->cm_event.param.mra_rcvd.service_timeout =
cm_mra_get_service_timeout(mra_msg);
- timeout = cm_convert_to_ms(cm_mra_get_service_timeout(mra_msg)) +
- cm_convert_to_ms(cm_id_priv->av.packet_life_time);
+ timeout = min(IB_CM_MAX_TIMEOUT,
+ cm_convert_to_ms(cm_mra_get_service_timeout(mra_msg)) +
+ cm_convert_to_ms(cm_id_priv->av.packet_life_time));
spin_lock_irqsave(&cm_id_priv->lock, flags);
switch (cm_id_priv->id.state) {
@@ -2701,7 +2709,7 @@ int ib_send_cm_sidr_req(struct ib_cm_id
cm_id->service_id = param->service_id;
cm_id->service_mask = __constant_cpu_to_be64(~0ULL);
- cm_id_priv->timeout_ms = param->timeout_ms;
+ cm_id_priv->timeout_ms = min(IB_CM_MAX_TIMEOUT, param->timeout_ms);
cm_id_priv->max_cm_retries = param->max_cm_retries;
ret = cm_alloc_msg(cm_id_priv, &msg);
if (ret)
More information about the general
mailing list