Re: [PATCH] opensm: Add the precreation of multicast groups

2011-10-27 Thread Hal Rosenstock
On 10/6/2011 8:13 PM, Ira Weiny wrote: > > Allow for the pre-creation of these groups on a partition by partition basis. This looks good to me and has been needed for some time now; Thanks for doing this! Just some minor comments below from scanning through the patch. I haven't tried it yet...

[PATCH] opensm/osm_link_mgr.c: Remove no longer needed memset

2011-10-27 Thread Hal Rosenstock
Since PortInfo attribute is now IB_SMP_DATA_SIZE (64 bytes), there is no remaining space at the end of the attribute as it now fills the entire SMP data size. Found-by: Leonid Keller Signed-off-by: Hal Rosenstock --- diff --git a/opensm/osm_link_mgr.c b/opensm/osm_link_mgr.c index aaefa78..e83

Re: REQ GID enforcement in the CM

2011-10-27 Thread Jason Gunthorpe
On Thu, Oct 27, 2011 at 04:14:07PM +0200, Or Gerlitz wrote: > Looking on that case, I noted that the CM code (SB) checks that the > GID in the incoming REQ is present in at least of one the ports of > the relevant device, but not specifically on the port this request > arrived to, is that followin

[PATCH] RDMA/nes: ip address print changes

2011-10-27 Thread Faisal Latif
Fix printing of ip addresses to use %pI4. Reported-by: Roland Dreier Signed-off-by: Tatyana Nikolova Signed-off-by: Faisal Latif --- drivers/infiniband/hw/nes/nes_cm.c | 96 +++- drivers/infiniband/hw/nes/nes_hw.c |6 +- 2 files changed, 54 insertions(+),

REQ GID enforcement in the CM

2011-10-27 Thread Or Gerlitz
Hi Sean, Looking on that case, I noted that the CM code (SB) checks that the GID in the incoming REQ is present in at least of one the ports of the relevant device, but not specifically on the port this request arrived to, is that following IBTA? I thought it could be problematic e.g in the ca