Re: [PATCH] RDMA/CMA: Use neigh_event_send() to initiate neighbour discovery.

Previous thread: 2.6.23-rc4-mm1: kgdboe link errors by Jiri Slaby on Wednesday, September 12, 2007 - 2:31 am. (6 messages)

Next thread: [Resend][PATCH -mm] Hibernation: Check if ACPI is enabled during restore in the right place by Rafael J. Wysocki on Wednesday, September 12, 2007 - 4:09 am. (1 message)
From: Steve Wise
Date: Wednesday, September 12, 2007 - 3:00 am

RDMA/CMA: Use neigh_event_send() to initiate neighbour discovery.

Calling arp_send() to initiate neighbour discovery (ND) doesn't do the
full ND protocol.  Namely, it doesn't handle retransmitting the arp
request if it is dropped. The function neigh_event_send() does all this.
Without doing full ND, rdma address resolution fails in the presence of
dropped arp bcast packets.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
---

 drivers/infiniband/core/addr.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index c5c33d3..5381c80 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -161,8 +161,7 @@ static void addr_send_arp(struct sockadd
 	if (ip_route_output_key(&rt, &fl))
 		return;
 
-	arp_send(ARPOP_REQUEST, ETH_P_ARP, rt->rt_gateway, rt->idev->dev,
-		 rt->rt_src, NULL, rt->idev->dev->dev_addr, NULL);
+	neigh_event_send(rt->u.dst.neighbour, NULL);
 	ip_rt_put(rt);
 }
 
-

From: Sean Hefty
Date: Wednesday, September 12, 2007 - 11:13 am

Acked-by: Sean Hefty <sean.hefty@intel.com>

Roland - can you please queue this up for 2.6.24?
-

From: Steve Wise
Date: Tuesday, September 18, 2007 - 10:23 am

Once this is applied upstream, I can pull it back in to ofed-1.2.5 and 
ofed-1.3.

Steve.

-

From: Roland Dreier
Date: Thursday, September 20, 2007 - 9:31 am

> Roland - can you please queue this up for 2.6.24?

Done, thanks.
-

From: Or Gerlitz
Date: Sunday, September 16, 2007 - 12:34 am

Jay,

Is there a way to deploy something similar for the gratuitous arp being 
sent by the bonding driver at bond_arp_send()?

We have seen rare situations where the skb was dropped by the stack and 
hence bonding fail-over was detected by the remote peer only when its 
neighboring subsystem probe failures dictated that a new arp must be issued.


-

Previous thread: 2.6.23-rc4-mm1: kgdboe link errors by Jiri Slaby on Wednesday, September 12, 2007 - 2:31 am. (6 messages)

Next thread: [Resend][PATCH -mm] Hibernation: Check if ACPI is enabled during restore in the right place by Rafael J. Wysocki on Wednesday, September 12, 2007 - 4:09 am. (1 message)