[PATCH] IB/ipoib: optimized the function ipoib_mcast_alloc

ipoib_mcast_alloc is called only in atomic context, hence removing the extra check. Signed-off-by: Saurabh Sengar --- Hi, Even if in future, if there are some functions expected to call it in normal context(not atomic), we can pass the GFP_KERNEL or GFP_ATOMIC directly

Re: shrink struct ib_send_wr V4

On 10/29/2015 1:51 PM, Christoph Hellwig wrote: On Wed, Oct 28, 2015 at 10:57:59PM -0400, Doug Ledford wrote: > >I had to do a minor hand merge to get this to apply, but it has been > >pulled in for 4.4. > >This breaks all of the drivers in staging BTW. That will need fixed up >before the

Re: [PATCH v5 00/26] New fast registration API

On Thu, Oct 29, 2015 at 4:16 PM, Doug Ledford wrote: > On 10/29/2015 01:42 AM, Or Gerlitz wrote: >> On Thu, Oct 29, 2015 at 4:34 AM, Doug Ledford wrote: >>> Yes, I've pulled this in for 4.4. Thanks! >> >> Doug, we want to run regression over the 4.4

Re: shrink struct ib_send_wr V4

On Sun, Nov 01, 2015 at 02:10:48PM +0200, Or Gerlitz wrote: > On 10/29/2015 1:51 PM, Christoph Hellwig wrote: > >On Wed, Oct 28, 2015 at 10:57:59PM -0400, Doug Ledford wrote: > >I had to do a minor hand merge to get this to apply, but it has been > >pulled in for 4.4. > >>> > >>>This

Re: [PATCH v5 00/26] New fast registration API

hi On 11/1/2015 17:00, Or Gerlitz wrote: > On Thu, Oct 29, 2015 at 4:16 PM, Doug Ledford wrote: >> On 10/29/2015 01:42 AM, Or Gerlitz wrote: >>> On Thu, Oct 29, 2015 at 4:34 AM, Doug Ledford wrote: Yes, I've pulled this in for 4.4. Thanks! >>>

Re: [PATCH v5 00/26] New fast registration API

Hi, On Sun, 1 Nov 2015 17:00:22 +0200 Or Gerlitz wrote: > > Stephen, is the framework for linux-next merge tests OK with this tag? > can you confirm that the > -next bits of the rdma tree are covered fine? linux-next fetches the "for-next" tag for that tree. -- Cheers,

[PATCH libibcm] cmpost.c: Handle ibv_get_device_list returning no IB devices in init()

Also, print message when init fails Signed-off-by: Hal Rosenstock --- diff --git a/examples/cmpost.c b/examples/cmpost.c index 1b0edf8..f7833f5 100644 --- a/examples/cmpost.c +++ b/examples/cmpost.c @@ -447,6 +447,8 @@ static int init(void) test.disconnects_left =

[PATCH 2/4] RDMA/libocrdma: set vlan present bit for UD

This patch tells f/w about the presence of VLAN tag in the AH being supplied to the QP. Signed-off-by: Devesh Sharma --- src/ocrdma_abi.h | 7 --- src/ocrdma_main.h | 7 +++ src/ocrdma_verbs.c | 8 ++-- 3 files changed, 17 insertions(+), 5

[PATCH 4/4] RDMA/libocrdma: update libocrdma version string

version string updated from 1.0.5 to 1.0.6 Signed-off-by: Devesh Sharma --- configure.in | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/configure.in b/configure.in index 140c07b..653bc43 100644 --- a/configure.in +++ b/configure.in @@ -1,11

[PATCH 1/4] RDMA/libocrdma:sync qp-state with hw state

From: Padmanabh Ratnakar This patch sync up the QP state with the underlying h/w QP state and reports the same to user application. Signed-off-by: Padmanabh Ratnakar Signed-off-by: Devesh Sharma

[PATCH 3/4] RDMA/libocrdma: Prevent CQ-Doorbell floods

Changing CQ-Doorbell(DB) logic to prevent DB floods, it is supposed to be pressed only if any hw CQE is polled. If cq-arm was requested previously then don't bother about number of hw CQEs polled and arm the CQ. Signed-off-by: Devesh Sharma --- src/ocrdma_verbs.c |