]> git.ipfire.org Git - thirdparty/kernel/stable.git/commit
RDMA/bnxt_re: Check cqe flags to know imm_data vs inv_irkey
authorKashyap Desai <kashyap.desai@broadcom.com>
Mon, 28 Oct 2024 10:06:54 +0000 (03:06 -0700)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Thu, 5 Dec 2024 12:53:36 +0000 (13:53 +0100)
commitee31de294ec86a2ddd1d15fd957fb98cb9c18764
treec2df16cec9cb4f9d70b2b7e3f7e4b0e515d6db85
parente4f26fae6075f136616d12a369b0ef7f0cf16436
RDMA/bnxt_re: Check cqe flags to know imm_data vs inv_irkey

[ Upstream commit 808ca6de989c598bc5af1ae0ad971a66077efac0 ]

Invalidate rkey is cpu endian and immediate data is in big endian format.
Both immediate data and invalidate the remote key returned by
HW is in little endian format.

While handling the commit in fixes tag, the difference between
immediate data and invalidate rkey endianness was not considered.

Without changes of this patch, Kernel ULP was failing while processing
inv_rkey.

dmesg log snippet -
nvme nvme0: Bogus remote invalidation for rkey 0x2000019Fix in this patch

Do endianness conversion based on completion queue entry flag.
Also, the HW completions are already converted to host endianness in
bnxt_qplib_cq_process_res_rc and bnxt_qplib_cq_process_res_ud and there
is no need to convert it again in bnxt_re_poll_cq. Modified the union to
hold the correct data type.

Fixes: 95b087f87b78 ("bnxt_re: Fix imm_data endianness")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1730110014-20755-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drivers/infiniband/hw/bnxt_re/ib_verbs.c
drivers/infiniband/hw/bnxt_re/qplib_fp.h