From: "lizhijian@fujitsu.com" <lizhijian@fujitsu.com>
To: "Daisuke Matsuda (Fujitsu)" <matsuda-daisuke@fujitsu.com>,
"leonro@nvidia.com" <leonro@nvidia.com>,
"jgg@nvidia.com" <jgg@nvidia.com>,
"zyjzyj2000@gmail.com" <zyjzyj2000@gmail.com>,
"linux-rdma@vger.kernel.org" <linux-rdma@vger.kernel.org>
Subject: Re: [PATCH] RDMA/rxe: Implement packet length validation on responder
Date: Sat, 5 Nov 2022 09:37:19 +0000 [thread overview]
Message-ID: <09db5954-a1e2-e164-edf2-319cb51bb7cd@fujitsu.com> (raw)
In-Reply-To: <20221028090438.2685345-1-matsuda-daisuke@fujitsu.com>
On 28/10/2022 17:04, Daisuke Matsuda wrote:
> The function check_length() is supposed to check the length of inbound
> packets on responder, but it actually has been a stub since the driver was
> born. Let it check the payload length and the DMA length.
>
> Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
> ---
> FOR REVIEWERS
> I referred to IB Specification Vol 1-Revision-1.5 to create this patch.
> Please see 9.7.4.1.6 (page.330).
>
> drivers/infiniband/sw/rxe/rxe_resp.c | 36 ++++++++++++++++++++++------
> 1 file changed, 29 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
> index ed5a09e86417..62e3a8195072 100644
> --- a/drivers/infiniband/sw/rxe/rxe_resp.c
> +++ b/drivers/infiniband/sw/rxe/rxe_resp.c
> @@ -390,16 +390,38 @@ static enum resp_states check_resource(struct rxe_qp *qp,
> static enum resp_states check_length(struct rxe_qp *qp,
> struct rxe_pkt_info *pkt)
> {
> - switch (qp_type(qp)) {
> - case IB_QPT_RC:
> - return RESPST_CHK_RKEY;
> + int mtu = qp->mtu;
> + u32 payload = payload_size(pkt);
> + u32 dmalen = reth_len(pkt);
>
> - case IB_QPT_UC:
> - return RESPST_CHK_RKEY;
> + /* RoCEv2 packets do not have LRH.
> + * Let's skip checking it.
> + */
>
> - default:
> - return RESPST_CHK_RKEY;
> + if ((pkt->opcode & RXE_START_MASK) &&
> + (pkt->opcode & RXE_END_MASK)) {
> + /* "only" packets */
> + if (payload > mtu)
> + return RESPST_ERR_LENGTH;
> +
> + } else if ((pkt->opcode & RXE_START_MASK) ||
> + (pkt->opcode & RXE_MIDDLE_MASK)) {
> + /* "first" or "middle" packets */
> + if (payload != mtu)
> + return RESPST_ERR_LENGTH;
> +
> + } else if (pkt->opcode & RXE_END_MASK) {
> + /* "last" packets */
> + if ((pkt->paylen == 0) || (pkt->paylen > mtu))
As per IBA spec, i didn't see any difference about the 'packet payload
length' from others,
so May I know why here you are using 'pkt->paylen' instead of payload ?
Thanks
Zhijian
> + return RESPST_ERR_LENGTH;
> + }
> +
> + if (pkt->opcode & (RXE_WRITE_MASK | RXE_READ_MASK)) {
> + if (dmalen > (1 << 31))
> + return RESPST_ERR_LENGTH;
> }
> +
> + return RESPST_CHK_RKEY;
> }
>
> static enum resp_states check_rkey(struct rxe_qp *qp,
next prev parent reply other threads:[~2022-11-05 9:38 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-28 9:04 [PATCH] RDMA/rxe: Implement packet length validation on responder Daisuke Matsuda
2022-11-05 9:37 ` lizhijian [this message]
2022-11-07 2:08 ` Daisuke Matsuda (Fujitsu)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=09db5954-a1e2-e164-edf2-319cb51bb7cd@fujitsu.com \
--to=lizhijian@fujitsu.com \
--cc=jgg@nvidia.com \
--cc=leonro@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=matsuda-daisuke@fujitsu.com \
--cc=zyjzyj2000@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox