[PATCH v1 1/3] Add support for extended query device capabilities

From: Eli Cohen Add the verb ibv_query_device_ex which is extensible and allows following commits to add new features to define additional properties. Cc: Moshe Lazer Signed-off-by: Eli Cohen Signed-off-by: Haggai Eran

[PATCH v1 0/3] libibverbs: On-demand paging support

This series adds userspace support for on-demand paging. The first patch adds support for the new extended query device verb. Patch 2 adds the capability and interface bits related to on-demand paging, and patch 3 adds example code to the rc_pingpong program to use on-demand paging. Changes from

[PATCH v1 3/3] libibverbs/examples: Support odp in rc_pingpong

From: Majd Dibbiny Signed-off-by: Majd Dibbiny Signed-off-by: Haggai Eran --- examples/rc_pingpong.c | 31 +-- 1 file changed, 29 insertions(+), 2 deletions(-) diff --git a/examples/rc_pingpong.c

[PATCH v1 2/3] Add on-demand paging support

On-demand paging feature allows registering memory regions without pinning their pages. Unfortunately the feature doesn't work together will all transports and all operations. This patch adds the ability to report on-demand paging capabilities through the ibv_query_device_ex. The patch also add

Re: [PATCH] staging/hfi1: replace indent spaces with tabs

On 08/21/2015 03:26 PM, Jeff Becker wrote: > Running checkpatch.pl on mad.c produces several > "ERROR: code indent should use tabs where possible" messages. > This patch fixes these. > > Signed-off-by: Jeff Becker Thanks, applied. > --- > drivers/staging/hfi1/mad.c

Re: [PATCH] Kconfig: add temporary PCI dependency

On 08/18/2015 10:15 AM, Mike Marciniszyn wrote: > The move from infiniband to staging requires a temporary > PCI dependency to fix 0-day build issues. The > drivers/infiniband/hw/Kconfig gratuitously added it for all drivers. This was no longer needed after I created drivers/staging/rdma and

Re: [PATCH] IB/hfi1: Add PSM2 user space header to header_install

On 09/02/2015 06:46 PM, ira.we...@intel.com wrote: > From: Ira Weiny > > When the hfi1 driver was added a user space header file (hfi1_user.h) was > added > to be shared between PSM2 and the driver. However, the file was not added to > the header install. Add it now. > >

Re: shrink struct ib_send_wr V3

On 08/31/2015 08:24 PM, Doug Ledford wrote: > On 08/31/2015 12:11 PM, Christoph Hellwig wrote: >> On Sun, Aug 30, 2015 at 06:31:35PM +0300, Sagi Grimberg wrote: - patch 2 now explicitly replaces the weird overloading in the mlx5 driver with an explicit embedding of struct

Re: [PATCH] IB/hfi1: Add CSRs for CONFIG_SDMA_VERBOSITY

On 09/02/2015 10:43 AM, Mike Marciniszyn wrote: > From: Jubin John > > 3 CSRs needed by the CONFIG_SDMA_VERBOSITY code were removed during > the CSR clean up. Adding these CSRs back to resolve 0-day build failure: >

[PATCH V2 2/2] IB/core: Move SM class defines from ib_mad.h to ib_smi.h

From: Ira Weiny When the hfi1 driver was added these definitions were moved from the qib driver to ib_mad.h to be used by both qib and hfi1. They should have been moved to ib_smi.h instead. Fixes: d4ab347005fb ("IB/core: Add core header changes needed for OPA")

Re: [PATCH] IB/mlx5: avoid destroying a NULL mr in reg_user_mr error flow

On 09/01/2015 04:06 AM, Sagi Grimberg wrote: > On 9/1/2015 9:56 AM, Haggai Eran wrote: >> The mlx5_ib_reg_user_mr() function will attempt to call clean_mr() in >> its error flow even though there is never a case where the error flow >> occurs with a valid MR pointer to destroy. >> >> Remove the

Re: [PATCH] infiniband:cxgb4:Fix if statement check in the function pick_local_ip6adddrs

On 08/26/2015 11:00 PM, Nicholas Krause wrote: > This fixes a if statement checking the return value of the function > get_lladdr for success in the function pick_local_ip6addrs to instead > of directly checking the return value of this call check the opposite > as get_lladdr returns zero for

Re: [PATCH v1] mlx5: Fix incorrect wc pkey_index assignment for GSI messages

On 09/02/2015 03:23 PM, Sagi Grimberg wrote: > Since patch series "Demux IB CM requests in the rdma_cm module" the > P_Key index is taken from the work completion rather than the message > itself. > > The HCA provides us with the message P_Key. In order to provide the > P_Key index, we need to

Re: [patch] IB/core: missing curly braces in ib_find_gid()

On 08/18/2015 05:22 AM, Dan Carpenter wrote: > Smatch says that, based on the indenting, we should probably add curly > braces here. > > Fixes: 230145ff8124 ('IB/core: Add RoCE GID table management') > Signed-off-by: Dan Carpenter Thanks, applied. > diff --git

Re: [patch] IB/core: off by one in error handling

On 08/18/2015 05:23 AM, Dan Carpenter wrote: > This is a zero offset array. The current code could try to free random > memory and crash. Also it leaks the first element. > > Fixes: 230145ff8124 ('IB/core: Add RoCE GID table management') > Signed-off-by: Dan Carpenter

Re: [PATCH 1/2] IB/ipoib: Clean up send-only multicast joins

On Fri, 21 Aug 2015, Jason Gunthorpe wrote: > Even though we don't expect the group to be created by the SM we > sill need to provide all the parameters to force the SM to validate > they are correct. Just ran into this issue with Redhat 7.1. Earlier code base. Same problem. qkey etc not set.

Re: [PATCH 2/2] IB/core: Move SM class defines from ib_mad.h to ib_smi.h

On 9/2/2015 6:45 PM, ira.we...@intel.com wrote: > From: Ira Weiny > > When the hfi1 driver was added these definitions were moved from the qib > driver > to ib_mad.h to be used by both qib and hfi1. They should have been moved to > ib_smi.h instead. > > Fixes:

Re: [PATCH] MAINTAINERS: Add maintainer section for hfi1

On 08/18/2015 10:06 AM, Mike Marciniszyn wrote: > Signed-off-by: Mike Marciniszyn This was squashed into the rest of the hfi1 driver patchset. > --- > 0 files changed > > diff --git a/MAINTAINERS b/MAINTAINERS > index b3c1a56..45953e9 100644 > --- a/MAINTAINERS >

Re: [PATCH 1/2] IB/core: Remove unnecessary defines from ib_mad.h

On 9/2/2015 6:45 PM, ira.we...@intel.com wrote: > From: Ira Weiny > > Remove the unused IB_NOTICE_REPRESS_* defines. > > When the hfi1 driver was added these definitions were moved from the qib > driver > to ib_mad.h. They should have been removed instead. > > Fixes:

Re: [PATCH] IB/cma: Fix net_dev reference leak with failed requests

On 08/27/2015 08:55 AM, Haggai Eran wrote: > When no matching listening ID is found for a given request, the net_dev > that was used to find the request isn't released. > > Fixes: 20c36836ecad ("IB/cma: Use found net_dev for passive connections") > Signed-off-by: Haggai Eran

Re: [PATCH] IB/srp: Fix possible use-after-free

On 08/12/2015 02:31 AM, Sagi Grimberg wrote: > > Looks better, I'll resubmit. For some reason I don't have the email for the v1 of this patchset in my mail. It must have gotten accidentally deleted. In any case, v1 was applied. -- Doug Ledford GPG KeyID:

Re: [PATCH] IB/ipoib: CSUM support in connected mode

On 07/30/2015 10:03 PM, Bart Van Assche wrote: > On 07/30/15 13:09, Yuval Shaia wrote: >> On Thu, Jul 30, 2015 at 09:38:54AM -0700, Bart Van Assche wrote: >>> On 07/30/2015 04:46 AM, Yuval Shaia wrote: struct ipoib_cm_data { __be32 qpn; /* High byte MUST be ignored on receive */

Re: [PATCH 1/2] IB/ipoib: Clean up send-only multicast joins

On Thu, Sep 03, 2015 at 05:17:31PM -0400, Doug Ledford wrote: > On 08/27/2015 07:33 PM, Jason Gunthorpe wrote: > > On Wed, Aug 26, 2015 at 12:43:15PM -0400, Doug Ledford wrote: > > > >> That still takes us back to the fact that the locking changes are > >> unneeded. I'm not opposed to them, but

RE: [GIT PULL] pull request v2: linux-firmware: Add Intel OPA hfi1 firmware

> > On 09/03/2015 04:26 PM, Kyle McMartin wrote: > > On Wed, Sep 02, 2015 at 10:15:15PM +, Weiny, Ira wrote: > >>> > >>> On 08/24/2015 11:28 AM, ira.weiny wrote: > git://github.com/weiny2/linux-firmware.git master-hfi1-firmware-v2 > >>> > >>> Should this go through me or though the

Re: [PATCH 1/2] IB/ipoib: Clean up send-only multicast joins

On 09/03/2015 05:23 PM, Jason Gunthorpe wrote: > On Thu, Sep 03, 2015 at 05:17:31PM -0400, Doug Ledford wrote: >> On 08/27/2015 07:33 PM, Jason Gunthorpe wrote: >>> On Wed, Aug 26, 2015 at 12:43:15PM -0400, Doug Ledford wrote: >>> That still takes us back to the fact that the locking changes

Re: [PATCH V2 2/2] IB/core: Move SM class defines from ib_mad.h to ib_smi.h

On 09/03/2015 02:16 PM, ira.we...@intel.com wrote: > From: Ira Weiny > > When the hfi1 driver was added these definitions were moved from the qib > driver > to ib_mad.h to be used by both qib and hfi1. They should have been moved to > ib_smi.h instead. > > Fixes:

Re: [PATCH] RDMA/cma: fix IPv6 address resolution

On 08/13/2015 03:19 PM, Spencer Baugh wrote: > Resolving a link-local IPv6 address with an unspecified source address > was broken by commit 5462eddd7a, which prevented the IPv6 stack from > learning the scope id of the link-local IPv6 address, causing random > failures as the IP stack chose a

Re: [PATCH 1/2] IB/ipoib: Clean up send-only multicast joins

On 08/27/2015 07:33 PM, Jason Gunthorpe wrote: > On Wed, Aug 26, 2015 at 12:43:15PM -0400, Doug Ledford wrote: > >> That still takes us back to the fact that the locking changes are >> unneeded. I'm not opposed to them, but as you mentioned in your first >> email, they should go with the changes

Re: [PATCH v2] xprtrdma: take HCA driver refcount at client

On 07/30/2015 07:00 AM, Devesh Sharma wrote: > Thanks Chuck Lever for the valuable feedback and suggestions. > > This is a rework of the following patch sent almost a year back: > http://www.mail-archive.com/linux-rdma%40vger.kernel.org/msg20730.html > > In presence of active mount if someone

Re: [PATCH v2] xprtrdma: take HCA driver refcount at client

On 09/03/2015 04:24 PM, Anna Schumaker wrote: > Hi Doug, > > On 09/03/2015 04:11 PM, Doug Ledford wrote: >> On 07/30/2015 07:00 AM, Devesh Sharma wrote: >>> Thanks Chuck Lever for the valuable feedback and suggestions. >>> >>> This is a rework of the following patch sent almost a year back: >>>

Re: [PATCH v2] xprtrdma: take HCA driver refcount at client

Hi Doug, On 09/03/2015 04:11 PM, Doug Ledford wrote: > On 07/30/2015 07:00 AM, Devesh Sharma wrote: >> Thanks Chuck Lever for the valuable feedback and suggestions. >> >> This is a rework of the following patch sent almost a year back: >>

Re: [PATCH for-next 0/2] IB/{core,mlx4_ib}: RX/TX checksum offload

On 9/2/2015 5:32 PM, Christoph Lameter wrote: On Wed, 5 Aug 2015, Amir Vadai wrote: This will be used by a revised version of the IP checksum patches [1], that will be sent later on. Ok when can we get the full set for testing? Seems that the libibverbs and libmlx4 portions are missing? not

Re: [PATCH 2/3] Add on-demand paging support

On 02/09/2015 22:17, Sagi Grimberg wrote: > On 8/27/2015 6:22 PM, Haggai Eran wrote: >> On-demand paging feature allows registering memory regions without >> pinning >> their pages. Unfortunately the feature doesn't work together will all >> transports and all operations. This patch adds the

Re: [PATCH 1/2] IB/core: Remove unnecessary defines from ib_mad.h

On 09/02/2015 06:45 PM, ira.we...@intel.com wrote: > From: Ira Weiny > > Remove the unused IB_NOTICE_REPRESS_* defines. > > When the hfi1 driver was added these definitions were moved from the qib > driver > to ib_mad.h. They should have been removed instead. > > Fixes:

Re: [GIT PULL] pull request v2: linux-firmware: Add Intel OPA hfi1 firmware

On Wed, Sep 02, 2015 at 10:15:15PM +, Weiny, Ira wrote: > > > > On 08/24/2015 11:28 AM, ira.weiny wrote: > > > git://github.com/weiny2/linux-firmware.git master-hfi1-firmware-v2 > > > > Should this go through me or though the linux-firmware tree? > > I don't know. My apologizes for being

Re: [GIT PULL] pull request v2: linux-firmware: Add Intel OPA hfi1 firmware

On Thu, Sep 03, 2015 at 04:27:52PM -0400, Doug Ledford wrote: > On 09/03/2015 04:26 PM, Kyle McMartin wrote: > > On Wed, Sep 02, 2015 at 10:15:15PM +, Weiny, Ira wrote: > >>> > >>> On 08/24/2015 11:28 AM, ira.weiny wrote: > git://github.com/weiny2/linux-firmware.git

Re: [PATCH 2/2] IB/ipoib: Suppress warning for send only join failures

On 08/21/2015 07:34 PM, Jason Gunthorpe wrote: > We expect send only joins to fail, it just means there are no listeners > for the group. The correct thing to do is silently drop the packet > at source. > > Eg avahi will full join 224.0.0.251 which causes a send only IGMP packet > to 224.0.0.22,

Re: [GIT PULL] pull request v2: linux-firmware: Add Intel OPA hfi1 firmware

On 09/02/2015 06:15 PM, Weiny, Ira wrote: >> >> On 08/24/2015 11:28 AM, ira.weiny wrote: >>> git://github.com/weiny2/linux-firmware.git master-hfi1-firmware-v2 >> >> Should this go through me or though the linux-firmware tree? > > I don't know. My apologizes for being ignorant in this case. >