[v1 0/2] Checksum offload capability report

[v1 0/2] Checksum offload capability report

[wbd2905-Re5JQEeQqe8AvxtiuMwx3w]

From: Bodong Wang <bodong-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

This series adds kernel support for checksum offload cap report. The first patch
adds reporting for RAW and RC QPs. Patch 2 sets the capability according to
hardware.

Changes from v1:
  * The cap is reported through existing device_cap_flags. Only new enum members
    are added rather than to use an extra structure. IB_DEVICE_UD_IP_CSUM is
    already defined there.
  * Note: although there is no link layer info indicated here, normally UD and
    RC QPs are only available through IB, RAW QP is only available over
    Ethernet.

Bodong Wang (2):
  IB/core: Add support of checksum capability reporting for RC and RAW
  IB/mlx4: Report checksum offload cap for RAW QP when query device

 drivers/infiniband/hw/mlx4/main.c | 2 ++
 include/rdma/ib_verbs.h           | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[v1 1/2] IB/core: Add support of checksum capability reporting for RC and RAW

[wbd2905-Re5JQEeQqe8AvxtiuMwx3w]

From: Bodong Wang <bodong-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Two enum members IB_DEVICE_RC_IP_CSUM and IB_DEVICE_RAW_IP_CSUM are
added to ib_device_cap_flags. Device should set these two flags if they support
insertion of UDP and TCP checksum on outgoing IPv4 messages and can verify the
validity of checksum for incoming IPv4 messages, for RC IPoIB and RAW over
Ethernet respectively. They are similar to IB_DEVICE_UD_IP_CSUM.

Signed-off-by: Bodong Wang <bodong-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 include/rdma/ib_verbs.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b0f898e..091894a 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -130,6 +130,8 @@ enum ib_device_cap_flags {
 	IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22),
 	IB_DEVICE_MEM_WINDOW_TYPE_2A	= (1<<23),
 	IB_DEVICE_MEM_WINDOW_TYPE_2B	= (1<<24),
+	IB_DEVICE_RC_IP_CSUM		= (1<<25),
+	IB_DEVICE_RAW_IP_CSUM		= (1<<26),
 	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29),
 	IB_DEVICE_SIGNATURE_HANDOVER	= (1<<30),
 	IB_DEVICE_ON_DEMAND_PAGING	= (1<<31),
@@ -868,7 +870,6 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
 };
 
-
 /*
  * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
  * callback to destroy the passed in QP.
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[v1 2/2] IB/mlx4: Report checksum offload cap for RAW QP when query device

[wbd2905-Re5JQEeQqe8AvxtiuMwx3w]

From: Bodong Wang <bodong-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Signed-off-by: Bodong Wang <bodong-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/hw/mlx4/main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8be6db8..9e18392 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -217,6 +217,8 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 	}
 
+	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
+
 	props->vendor_id	   = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
 		0xffffff;
 	props->vendor_part_id	   = dev->dev->persist->pdev->device;
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [v1 0/2] Checksum offload capability report

[Doug Ledford]

[-- Attachment #1: Type: text/plain, Size: 1207 bytes --]

On 09/22/2015 04:18 PM, wbd2905-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org wrote:
> From: Bodong Wang <bodong-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> 
> This series adds kernel support for checksum offload cap report. The first patch
> adds reporting for RAW and RC QPs. Patch 2 sets the capability according to
> hardware.
> 
> Changes from v1:
>   * The cap is reported through existing device_cap_flags. Only new enum members
>     are added rather than to use an extra structure. IB_DEVICE_UD_IP_CSUM is
>     already defined there.
>   * Note: although there is no link layer info indicated here, normally UD and
>     RC QPs are only available through IB, RAW QP is only available over
>     Ethernet.
> 
> Bodong Wang (2):
>   IB/core: Add support of checksum capability reporting for RC and RAW
>   IB/mlx4: Report checksum offload cap for RAW QP when query device
> 
>  drivers/infiniband/hw/mlx4/main.c | 2 ++
>  include/rdma/ib_verbs.h           | 3 ++-
>  2 files changed, 4 insertions(+), 1 deletion(-)
> 

Thanks.  I'm happy with this.  Picked up for next.

-- 
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
              GPG KeyID: 0E572FDD



[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]