Skip to contentSkip to conversation

rdma cm typo + bug report

PATCH In review frank zago 2 participants 3 messages May 9, 2011 2 messages not in the archive InfiniBand

lore
Share & tools
lore

frank zago

author
#0 lore raw

PATCH 1/1 rdma cm typo + bug report

Hi Sean,

Here's a patch for a typo.

I also think there's a bug with ucma_create_cqs()/ucma_destroy_cqs() because ucma_destroy_cqs unconditionally destroys the CQs, even if they were given by the application. librdmacm should only destroy the CQs it created.

Regards,
Frank.

examples/rdma_server.c +1 -1
index 2831d0c..5b9e16d 100644
@@ -97,7 +97,7 @@ static int run(void)
 
 	ret = rdma_accept(id, NULL);
 	if (ret) {
-		printf("rdma_connect %d\n", errno);
+		printf("rdma_accept %d\n", errno);
 		return ret;
 	}

A message that is not in the archive (sent off-list or not yet received): 4DC861A7.5010005-klaOcWyJdxkshyMvu7JE4pqQE7yCjDx5@public.gmane.org

#2 lore raw
Quoted 1 line

Here's a patch for a typo.

Thanks - I added a patch for this.

Quoted 4 lines

I also think there's a bug with ucma_create_cqs()/ucma_destroy_cqs() because ucma_destroy_cqs unconditionally destroys the CQs, even if they were given by the application. librdmacm should only destroy the CQs it created.

I think we're okay here. ucma_create_cqs() only allocates a CQ if the user specified a CQ of NULL as part of the QP attributes. It stores the allocated CQ in id->send/recv_cq. ucma_destroy_cqs() checks for id->send/recv_cq and destroys them.

- Sean
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

A message that is not in the archive (sent off-list or not yet received): 1828884A29C6694DAF28B7E6B8A82373B942-P5GAC/[email protected]

author
#4 lore raw
Quoted 6 lines · Sean
Quoted 4 lines

I also think there's a bug with ucma_create_cqs()/ucma_destroy_cqs() because ucma_destroy_cqs unconditionally destroys the CQs, even if they were given by the application. librdmacm should only destroy the CQs it created.

I think we're okay here. ucma_create_cqs() only allocates a CQ if the user specified a CQ of NULL as part of the QP attributes. It stores the allocated CQ in id->send/recv_cq. ucma_destroy_cqs() checks for id->send/recv_cq and destroys them.

Indeed. Sorry.

Frank.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html