Re: [PATCH] mm: get_user_pages(write,force) refuse to COW in shared areas

2014-04-25 Thread Hugh Dickins
On Fri, 25 Apr 2014, Oleg Nesterov wrote: > > And I forgot to mention, there is another reason why I would like to > change uprobes to follow the same convention. I still think it would > be better to kill __replace_page() and use gup(FOLL_WRITE | FORCE) > in uprobe_write_opcode(). Oh, please ple

[PATCH] iw_cxgb4: Update Kconfig to include Chelsio T5 adapter.

2014-04-25 Thread Hariprasad Shenai
Signed-off-by: Hariprasad Shenai --- drivers/infiniband/hw/cxgb4/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/Kconfig b/drivers/infiniband/hw/cxgb4/Kconfig index d4e8983..23f38cf 100644 --- a/drivers/infiniband/hw/cxgb4/Kconfig +++

Re: [PATCH] mm: get_user_pages(write,force) refuse to COW in shared areas

2014-04-25 Thread Oleg Nesterov
On 04/24, Hugh Dickins wrote: > > On Thu, 24 Apr 2014, Oleg Nesterov wrote: > > > So, what do you think about the patch below? It is probably fine in any > > case, > > but is there any "strong" reason to follow the gup's behaviour and forbid > > the > > anon page in VM_MAYSHARE && !VM_MAYWRITE vm

Re: IB/cma: Make timeout dependent on the subnet timeout

2014-04-25 Thread Bart Van Assche
On 04/25/14 18:56, Hefty, Sean wrote: > Btw, up til now most of the requests regarding CM timeouts has been to > increase it. We need to make sure that we don't end up breaking that. > Even if we set this timeout to 0, the total timeout for a connection > request is 2 x packet lifetime x # retries

RE: IB/cma: Make timeout dependent on the subnet timeout

2014-04-25 Thread Hefty, Sean
> Another possible approach is to make the CM timeout configurable for > kernel clients only. How about creating two versions of struct > rdma_conn_param - the existing version for communication between user > space and kernel and a second version for in-kernel clients only ? In > that second versi

Re: IB/cma: Make timeout dependent on the subnet timeout

2014-04-25 Thread Bart Van Assche
On 04/25/14 04:59, Hefty, Sean wrote: >> Sean, can't we have CMA to follow the same practice used in the CM where >> we derive the RC QP timeout based on the packet life time retrieved in >> path queries? e.g base the cm response time out on this value too? > > We could. The timeout that's being

[PATCH] xprtrdma: Ensure ia->ri_id->qp is not NULL when reconnecting

2014-04-25 Thread Chuck Lever
Devesh Sharma reports that after a disconnect, his HCA is failing to create a fresh QP, leaving ia_ri->ri_id->qp set to NULL. But xprtrdma still allows RPCs to wake up and post LOCAL_INV as they exit, causing an oops. rpcrdma_ep_connect() is allowing the wake-up by leaking the QP creation error c

Re: [PATCH] svcrdma: refactor marshalling logic

2014-04-25 Thread Steve Wise
On 4/25/2014 8:24 AM, Chuck Lever wrote: Hi Bruce- On Apr 25, 2014, at 6:58 AM, J. Bruce Fields wrote: On Thu, Apr 10, 2014 at 01:37:23PM -0500, Steve Wise wrote: From: Tom Tucker This patch refactors the marshalling logic to remove the intermediary map structures. It also fixes an existi

Re: [PATCH] svcrdma: refactor marshalling logic

2014-04-25 Thread Chuck Lever
Hi Bruce- On Apr 25, 2014, at 6:58 AM, J. Bruce Fields wrote: > On Thu, Apr 10, 2014 at 01:37:23PM -0500, Steve Wise wrote: >> From: Tom Tucker >> >> This patch refactors the marshalling logic to remove the intermediary >> map structures. It also fixes an existing bug where the NFSRDMA server

Re: [PATCH] svcrdma: refactor marshalling logic

2014-04-25 Thread J. Bruce Fields
On Thu, Apr 10, 2014 at 01:37:23PM -0500, Steve Wise wrote: > From: Tom Tucker > > This patch refactors the marshalling logic to remove the intermediary > map structures. It also fixes an existing bug where the NFSRDMA server > was not minding the device fast register page list length limitation