linux.git/include/uapi/rdma, branch arm64-uaccess

RDMA/efa: Support QP with unsolicited write w/ imm. receive

2024-05-08T08:18:26+00:00

Add a new EFA flags attribute for QP creation, and support unsolicited
write with immediate flag. QPs created with this flag set will not
consume receive work requests for incoming RDMA write with immediate.
Expose device capability bit for this feature support.

Reviewed-by: Daniel Kranzdorf 
Reviewed-by: Firas Jahjah 
Signed-off-by: Michael Margolin 
Link: https://lore.kernel.org/r/20240506151829.6475-1-mrgolin@amazon.com
Signed-off-by: Leon Romanovsky

RDMA/mana_ib: implement uapi for creation of rnic cq

2024-05-05T12:27:23+00:00

Enable users to create RNIC CQs using a corresponding flag.
With the previous request size, an ethernet CQ is created.
As a response, return ID of the created CQ.

Signed-off-by: Konstantin Taranov 
Link: https://lore.kernel.org/r/1714137160-5222-6-git-send-email-kotaranov@linux.microsoft.com
Reviewed-by: Long Li 
Signed-off-by: Leon Romanovsky

RDMA/core: Add an option to display driver-specific QPs in the rdmatool

2024-04-30T08:19:29+00:00

Utilize the -dd flag (driver-specific details) in the rdmatool
to view driver-specific QPs which are not exposed yet.

Add the netlink attribute to mark request to convey driver details and
use it to return QP subtype as a string.

$ rdma resource show qp link ibp8s0f1
link ibp8s0f1/1 lqpn 360 type UD state RTS sq-psn 0 comm [mlx5_ib]
link ibp8s0f1/1 lqpn 0 type SMI state RTS sq-psn 0 comm [ib_core]
link ibp8s0f1/1 lqpn 1 type GSI state RTS sq-psn 0 comm [ib_core]

$ rdma resource show qp link ibp8s0f1 -dd
link ibp8s0f1/1 lqpn 360 type UD state RTS sq-psn 0 comm [mlx5_ib]
link ibp8s0f1/1 lqpn 465 type DRIVER subtype REG_UMR state RTS sq-psn 0 comm [mlx5_ib]
link ibp8s0f1/1 lqpn 0 type SMI state RTS sq-psn 0 comm [ib_core]
link ibp8s0f1/1 lqpn 1 type GSI state RTS sq-psn 0 comm [ib_core]

$ rdma resource show
0: ibp8s0f0: pd 3 cq 4 qp 3 cm_id 0 mr 0 ctx 0 srq 2
1: ibp8s0f1: pd 3 cq 4 qp 3 cm_id 0 mr 0 ctx 0 srq 2

$ rdma resource show -dd
0: ibp8s0f0: pd 3 cq 4 qp 4 cm_id 0 mr 0 ctx 0 srq 2
1: ibp8s0f1: pd 3 cq 4 qp 4 cm_id 0 mr 0 ctx 0 srq 2

Signed-off-by: Chiara Meiohas 
Link: https://lore.kernel.org/r/2607bb3ddec3cae3443c2ea19e9f700825d20a98.1713268997.git.leon@kernel.org
Signed-off-by: Leon Romanovsky

RDMA/hns: Support DSCP

2024-04-09T07:27:41+00:00

Add support for DSCP configuration. For DSCP, get dscp-prio mapping
via hns3 nic driver api .get_dscp_prio() and fill the SL (in WQE for
UD or in QPC for RC) with the priority value. The prio-tc mapping is
configured to HW by hns3 nic driver. HW will select a corresponding
TC according to SL and the prio-tc mapping.

Signed-off-by: Junxian Huang 
Link: https://lore.kernel.org/r/20240315093551.1650088-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky

RDMA/hns: Support userspace configuring congestion control algorithm with QP granularity

2024-03-03T13:01:33+00:00

Currently, congestion control algorithm is statically configured in
FW, and all QPs use the same algorithm(except UD which has a fixed
configuration of DCQCN). This is not flexible enough.

Support userspace configuring congestion control algorithm with QP
granularity while creating QPs. If the algorithm is not specified in
userspace, use the default one.

Signed-off-by: Junxian Huang 
Link: https://lore.kernel.org/r/20240301104845.1141083-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky

RDMA/efa: Add EFA query MR support

2024-01-07T10:02:27+00:00

Add EFA driver uapi definitions and register a new query MR method that
currently returns the physical interconnects the device is using to
reach the MR. Update admin definitions and efa-abi accordingly.

Reviewed-by: Anas Mousa 
Reviewed-by: Firas Jahjah 
Signed-off-by: Michael Margolin 
Link: https://lore.kernel.org/r/20240104095155.10676-1-mrgolin@amazon.com
Signed-off-by: Leon Romanovsky

RDMA/bnxt_re: Share a page to expose per CQ info with userspace

2023-12-17T13:35:58+00:00

Gen P7 adapters needs to share a toggle bits information received
in kernel driver with the user space. User space needs this
info during the request notify call back to arm the CQ.

User space application can get this page using the
UAPI routines. Library will mmap this page and get the
toggle bits to be used in the next ARM Doorbell.

Uses a hash list to map the CQ structure from the CQ ID.
CQ structure is retrieved from the hash list while the
library calls the UAPI routine to get the toggle page
mapping. Currently the full page is mapped per CQ. This
can be optimized to enable multiple CQs from the same
application share the same page and different offsets
in the page.

Signed-off-by: Selvin Xavier 
Link: https://lore.kernel.org/r/1702535484-26844-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky

RDMA/bnxt_re: Add UAPI to share a page with user space

2023-12-17T13:35:58+00:00

Gen P7 adapters require to share a toggle value for CQ
and SRQ. This is received by the driver as part of
interrupt notifications and needs to be shared with the
user space. Add a new UAPI infrastructure to get the
shared page for CQ and SRQ.

Signed-off-by: Selvin Xavier 
Link: https://lore.kernel.org/r/1702535484-26844-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky

Expose c0 and SW encap ICM for RDMA

2023-12-12T07:04:59+00:00

These two series from Mark and Shun extend RDMA mlx5 API.

Mark's series provides c0 register used to match egress
traffic sent by local device.

Shun's series adds new type for ICM area.

Link: https://lore.kernel.org/all/cover.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky

RDMA/mlx5: Expose register c0 for RDMA device

2023-12-12T07:04:07+00:00

This patch introduces improvements for matching egress traffic sent by the
local device. When applicable, all egress traffic from the local vport is
now tagged with the provided value. This enhancement is particularly useful
for FDB steering purposes.

The primary focus of this update is facilitating the transmission of
traffic from the hypervisor to a VF. To achieve this, one must initiate an
SQ on the hypervisor and subsequently create a rule in the FDB that matches
on the eswitch manager vport and the SQN of the aforementioned SQ.

Obtaining the SQN can be had from SQ opened, and the eswitch manager vport
match can be substituted with the register c0 value exposed by this patch.

Signed-off-by: Mark Bloch 
Reviewed-by: Michael Guralnik 
Link: https://lore.kernel.org/r/aa4120a91c98ff1c44f1213388c744d4cb0324d6.1701871118.git.leon@kernel.org
Signed-off-by: Leon Romanovsky