Re: [patch v3] infiniband: uverbs: handle large number of entries

2010-10-13 Thread Dan Carpenter
On Tue, Oct 12, 2010 at 03:01:18PM -0600, Jason Gunthorpe wrote: On Tue, Oct 12, 2010 at 01:31:17PM +0200, Dan Carpenter wrote: In the original code there was a potential integer overflow if you passed in a large cmd.ne. The calls to kmalloc() would allocate smaller buffers than intended,

[patch v4] infiniband: uverbs: handle large number of entries

2010-10-13 Thread Dan Carpenter
In the original code there was a potential integer overflow if you passed in a large cmd.ne. The calls to kmalloc() would allocate smaller buffers than intended, leading to memory corruption. There was also an information leak if resp wasn't all used. Documentation/infiniband/user_verbs.txt

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Eli Cohen
libmlx4 does not report the opcode of the operation if it completed with error. We will fix this and post a patch for review. On Tue, Oct 12, 2010 at 10:22 PM, Eli Cohen e...@dev.mellanox.co.il wrote: On Tue, Oct 12, 2010 at 08:58:59PM +0200, Bart Van Assche wrote: On Tue, Oct 12, 2010 at 8:50

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Or Gerlitz
Eli Cohen wrote: Completions with non-zero (error) status and a wr_id / opcode combination were received that were never queued by the application. In case of error the opcode of the completed operation is not provided. I am not sure why. Eli, there's nothing in the IB spec that mandates the

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Eli Cohen
On Wed, Oct 13, 2010 at 03:51:10PM +0200, Or Gerlitz wrote: Eli Cohen wrote: Completions with non-zero (error) status and a wr_id / opcode combination were received that were never queued by the application. In case of error the opcode of the completed operation is not provided. I am not

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Roland Dreier
If the status of the operation that generates the Work Completion is anything other than success, the contents of the Work Completion are undefined except as noted below. The contents of a Work Completion are: Yes, that is exactly right. And the noted below fields are the status and the

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Roland Dreier
I'm not clear on the problem observed here. A few notes: - If a QP transitions to error state, then *all* work requests, whether or not they were signaled, generate a completion with status flush. - If a work request completes with an error status, then the opcode field is not defined.

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Eli Cohen
On Wed, Oct 13, 2010 at 09:05:47AM -0700, Roland Dreier wrote: If the status of the operation that generates the Work Completion is anything other than success, the contents of the Work Completion are undefined except as noted below. The contents of a Work Completion are: Yes, that

Re: Work completions generated after a queue pair has made the transition to an error state

2010-10-13 Thread Bart Van Assche
On Wed, Oct 13, 2010 at 6:18 PM, Roland Dreier rdre...@cisco.com wrote: I'm not clear on the problem observed here.  A few notes:  - If a QP transitions to error state, then *all* work requests, whether   or not they were signaled, generate a completion with status flush.  - If a work

RE: Opensm crash with OFED 1.5

2010-10-13 Thread Suresh Shelvapille
I tried 1.5.2 and that did not help, same kernel oops. -Original Message- From: linux-rdma-ow...@vger.kernel.org [mailto:linux-rdma-ow...@vger.kernel.org] On Behalf Of Suresh Shelvapille Sent: Tuesday, October 12, 2010 7:22 PM To: 'Linux RDMA list' Subject: Opensm crash with