linux-toradex.git/include/rdma, branch v6.6-rc3

RDMA Remove unused function declarations

2023-08-13T07:32:35+00:00

Commit c2261dd76b54 ("RDMA/device: Add ib_device_set_netdev() as an alternative to get_netdev")
declared but never implemented ib_device_netdev(), remove it.
Commit 922a8e9fb2e0 ("RDMA: iWARP Connection Manager.") declared but never implemented
iw_cm_unbind_qp() and iw_cm_get_qp().

Signed-off-by: Yue Haibing 
Link: https://lore.kernel.org/r/20230809142718.42316-1-yuehaibing@huawei.com
Signed-off-by: Leon Romanovsky

rdma: fix INFINIBAND_USER_ACCESS dependency

2023-07-03T23:55:04+00:00

After a change to the bnxt_re driver, it fails to link when
CONFIG_INFINIBAND_USER_ACCESS is disabled:

  aarch64-linux-ld: drivers/infiniband/hw/bnxt_re/ib_verbs.o: in function `bnxt_re_handler_BNXT_RE_METHOD_ALLOC_PAGE':
  ib_verbs.c:(.text+0xd64): undefined reference to `ib_uverbs_get_ucontext_file'
  aarch64-linux-ld: drivers/infiniband/hw/bnxt_re/ib_verbs.o:(.rodata+0x168): undefined reference to `uverbs_idr_class'
  aarch64-linux-ld: drivers/infiniband/hw/bnxt_re/ib_verbs.o:(.rodata+0x1a8): undefined reference to `uverbs_destroy_def_handler'

The problem is that the 'bnxt_re_uapi_defs' structure is built
unconditionally and references a couple of functions that are never
really called in this configuration but instead require other functions
that are left out.

Adding an #ifdef around the new code, or a Kconfig dependency would
address this problem, but adding the compile-time check inside of the
UAPI_DEF_CHAIN_OBJ_TREE_NAMED() macro seems best because that also
addresses the problem in other drivers that may run into the same
dependency.

Fixes: 360da60d6c6ed ("RDMA/bnxt_re: Enable low latency push")
Signed-off-by: Arnd Bergmann 
Acked-by: Leon Romanovsky 
Signed-off-by: Linus Torvalds

RDMA/cma: Always set static rate to 0 for RoCE

2023-06-11T08:26:02+00:00

Set static rate to 0 as it should be discovered by path query and
has no meaning for RoCE.
This also avoid of using the rtnl lock and ethtool API, which is
a bottleneck when try to setup many rdma-cm connections at the same
time, especially with multiple processes.

Fixes: 3c86aa70bf67 ("RDMA/cm: Add RDMA CM support for IBoE devices")
Signed-off-by: Mark Zhang 
Link: https://lore.kernel.org/r/f72a4f8b667b803aee9fa794069f61afb5839ce4.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky

RDMA: Add ib_virt_dma_to_page()

2023-04-16T08:08:07+00:00

Make it clearer what is going on by adding a function to go back from the
"virtual" dma_addr to a kva and another to a struct page. This is used in the
ib_uses_virt_dma() style drivers (siw, rxe, hfi, qib).

Call them instead of a naked casting and  virt_to_page() when working with dma_addr
values encoded by the various ib_map functions.

This also fixes the virt_to_page() casting problem Linus Walleij has been
chasing.

Cc: Linus Walleij 
Signed-off-by: Jason Gunthorpe 
Link: https://lore.kernel.org/r/0-v2-05ea785520ed+10-ib_virt_page_jgg@nvidia.com
Signed-off-by: Leon Romanovsky

RDMA/umem: Remove unused 'work' member from struct ib_umem

2023-02-12T18:25:25+00:00

It is not used now.

Fixes: b95df5e3e459 ("drivers/IB,core: reduce scope of mmap_sem")
Signed-off-by: Jason Gunthorpe 
Link: https://lore.kernel.org/r/0-v1-22a2667fa089+a3-umem_work_jgg@nvidia.com
Reviewed-by: Devesh Sharma 
Signed-off-by: Leon Romanovsky

RDMA/restrack: Correct spelling

2023-02-07T09:25:10+00:00

Fix spelling errors.

Signed-off-by: Deming Wang 
Link: https://lore.kernel.org/r/20230206085725.1507-1-wangdeming@inspur.com
Signed-off-by: Leon Romanovsky

RDMA/mlx: Calling qp event handler in workqueue context

2023-01-15T10:23:10+00:00

Move the call of qp event handler from atomic to workqueue context,
so that the handler is able to block. This is needed by following
patches.

Signed-off-by: Mark Zhang 
Reviewed-by: Patrisious Haddad 
Link: https://lore.kernel.org/r/0cd17b8331e445f03942f4bb28d447f24ac5669d.1672821186.git.leonro@nvidia.com
Signed-off-by: Leon Romanovsky

RDMA/cma: Refactor the inbound/outbound path records process flow

2023-01-10T08:49:50+00:00

Refactors based on comments [1] of the multiple path records support
patchset:
- Return failure if not able to set inbound/outbound PRs;
- Simplify the flow when receiving the PRs from netlink channel: When
  a good PR response is received, unpack it and call the path_query
  callback directly. This saves two memory allocations;
- Define RDMA_PRIMARY_PATH_MAX_REC_NUM in a proper place.

[1] https://lore.kernel.org/linux-rdma/Yyxp9E9pJtUids2o@nvidia.com/

Signed-off-by: Mark Zhang 
Reviewed-by: Bart Van Assche  #srp
Link: https://lore.kernel.org/r/7610025d57342b8b6da0f19516c9612f9c3fdc37.1672819376.git.leonro@nvidia.com
Signed-off-by: Leon Romanovsky

RDMA: Extend RDMA kernel verbs ABI to support flush

2022-12-09T23:36:01+00:00

This commit extends the RDMA kernel verbs ABI to support the flush
operation defined in IBA A19.4.1. These changes are
backward compatible with the existing RDMA kernel verbs ABI.

It makes device/HCA support new FLUSH attributes/capabilities, and it
also makes memory region support new FLUSH access flags.

Users can use ibv_reg_mr(3) to register flush access flags. Only the
access flags also supported by device's capabilities can be registered
successfully.

Once registered successfully, it means the MR is flushable. Similarly,
A flushable MR should also have one or both of GLOBAL_VISIBILITY and
PERSISTENT attributes/capabilities like device/HCA.

Link: https://lore.kernel.org/r/20221206130201.30986-3-lizhijian@fujitsu.com
Reviewed-by: Zhu Yanjun 
Signed-off-by: Li Zhijian 
Signed-off-by: Jason Gunthorpe

RDMA: Extend RDMA kernel ABI to support atomic write

2022-12-01T23:51:09+00:00

1) Define new atomic write request/completion in kernel.
2) Define new atomic write capability in kernel.
3) Define new atomic write opcode for RC service in packet.

Link: https://lore.kernel.org/r/1669905432-14-3-git-send-email-yangx.jy@fujitsu.com
Signed-off-by: Xiao Yang 
Signed-off-by: Jason Gunthorpe