From: Zhu Yanjun <zyjzyj2000@gmail.com>
To: Bob Pearson <rpearsonhpe@gmail.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>,
RDMA mailing list <linux-rdma@vger.kernel.org>
Subject: Re: [PATCH v2 1/9] RDMA/rxe: Move ICRC checking to a subroutine
Date: Tue, 13 Jul 2021 15:27:37 +0800 [thread overview]
Message-ID: <CAD=hENfY2PwNF71QFkR981CA8z7WFR65a2qxkeP61r0Zbaq+GQ@mail.gmail.com> (raw)
In-Reply-To: <20210707040040.15434-2-rpearsonhpe@gmail.com>
On Wed, Jul 7, 2021 at 12:01 PM Bob Pearson <rpearsonhpe@gmail.com> wrote:
>
> Move the code in rxe_recv() that checks the ICRC on incoming packets to a
> subroutine rxe_check_icrc() and move that to rxe_icrc.c.
In this commit, a new function rxe_icrc_check is created with the
original source code.
Reviewed-by: Zhu Yanjun <zyjzyj2000@gmail.com>
Zhu Yanjun
>
> Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
> ---
> drivers/infiniband/sw/rxe/rxe_icrc.c | 38 ++++++++++++++++++++++++++++
> drivers/infiniband/sw/rxe/rxe_loc.h | 2 ++
> drivers/infiniband/sw/rxe/rxe_recv.c | 23 ++---------------
> 3 files changed, 42 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_icrc.c b/drivers/infiniband/sw/rxe/rxe_icrc.c
> index 66b2aad54bb7..d067841214be 100644
> --- a/drivers/infiniband/sw/rxe/rxe_icrc.c
> +++ b/drivers/infiniband/sw/rxe/rxe_icrc.c
> @@ -67,3 +67,41 @@ u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb)
> rxe_opcode[pkt->opcode].length - RXE_BTH_BYTES);
> return crc;
> }
> +
> +/**
> + * rxe_icrc_check() - Compute ICRC for a packet and compare to the ICRC
> + * delivered in the packet.
> + * @skb: packet buffer
> + * @pkt: packet info
> + *
> + * Return: 0 if the values match else an error
> + */
> +int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt)
> +{
> + __be32 *icrcp;
> + u32 pkt_icrc;
> + u32 icrc;
> +
> + icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE);
> + pkt_icrc = be32_to_cpu(*icrcp);
> +
> + icrc = rxe_icrc_hdr(pkt, skb);
> + icrc = rxe_crc32(pkt->rxe, icrc, (u8 *)payload_addr(pkt),
> + payload_size(pkt) + bth_pad(pkt));
> + icrc = (__force u32)cpu_to_be32(~icrc);
> +
> + if (unlikely(icrc != pkt_icrc)) {
> + if (skb->protocol == htons(ETH_P_IPV6))
> + pr_warn_ratelimited("bad ICRC from %pI6c\n",
> + &ipv6_hdr(skb)->saddr);
> + else if (skb->protocol == htons(ETH_P_IP))
> + pr_warn_ratelimited("bad ICRC from %pI4\n",
> + &ip_hdr(skb)->saddr);
> + else
> + pr_warn_ratelimited("bad ICRC from unknown\n");
> +
> + return -EINVAL;
> + }
> +
> + return 0;
> +}
> diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
> index 1ddb20855dee..015777e31ec9 100644
> --- a/drivers/infiniband/sw/rxe/rxe_loc.h
> +++ b/drivers/infiniband/sw/rxe/rxe_loc.h
> @@ -193,7 +193,9 @@ int rxe_completer(void *arg);
> int rxe_requester(void *arg);
> int rxe_responder(void *arg);
>
> +/* rxe_icrc.c */
> u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb);
> +int rxe_icrc_check(struct sk_buff *skb, struct rxe_pkt_info *pkt);
>
> void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb);
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
> index 7a49e27da23a..6a6cc1fa90e4 100644
> --- a/drivers/infiniband/sw/rxe/rxe_recv.c
> +++ b/drivers/infiniband/sw/rxe/rxe_recv.c
> @@ -361,8 +361,6 @@ void rxe_rcv(struct sk_buff *skb)
> int err;
> struct rxe_pkt_info *pkt = SKB_TO_PKT(skb);
> struct rxe_dev *rxe = pkt->rxe;
> - __be32 *icrcp;
> - u32 calc_icrc, pack_icrc;
>
> if (unlikely(skb->len < RXE_BTH_BYTES))
> goto drop;
> @@ -384,26 +382,9 @@ void rxe_rcv(struct sk_buff *skb)
> if (unlikely(err))
> goto drop;
>
> - /* Verify ICRC */
> - icrcp = (__be32 *)(pkt->hdr + pkt->paylen - RXE_ICRC_SIZE);
> - pack_icrc = be32_to_cpu(*icrcp);
> -
> - calc_icrc = rxe_icrc_hdr(pkt, skb);
> - calc_icrc = rxe_crc32(rxe, calc_icrc, (u8 *)payload_addr(pkt),
> - payload_size(pkt) + bth_pad(pkt));
> - calc_icrc = (__force u32)cpu_to_be32(~calc_icrc);
> - if (unlikely(calc_icrc != pack_icrc)) {
> - if (skb->protocol == htons(ETH_P_IPV6))
> - pr_warn_ratelimited("bad ICRC from %pI6c\n",
> - &ipv6_hdr(skb)->saddr);
> - else if (skb->protocol == htons(ETH_P_IP))
> - pr_warn_ratelimited("bad ICRC from %pI4\n",
> - &ip_hdr(skb)->saddr);
> - else
> - pr_warn_ratelimited("bad ICRC from unknown\n");
> -
> + err = rxe_icrc_check(skb, pkt);
> + if (unlikely(err))
> goto drop;
> - }
>
> rxe_counter_inc(rxe, RXE_CNT_RCVD_PKTS);
>
> --
> 2.30.2
>
next prev parent reply other threads:[~2021-07-13 7:27 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-07 4:00 [PATCH for-next v2 0/9] ICRC cleanup Bob Pearson
2021-07-07 4:00 ` [PATCH v2 1/9] RDMA/rxe: Move ICRC checking to a subroutine Bob Pearson
2021-07-13 7:27 ` Zhu Yanjun [this message]
2021-07-16 15:55 ` Jason Gunthorpe
2021-07-07 4:00 ` [PATCH v2 2/9] RDMA/rxe: Move rxe_xmit_packet " Bob Pearson
2021-07-14 3:24 ` Zhu Yanjun
2021-07-07 4:00 ` [PATCH v2 3/9] RDMA/rxe: Fixup rxe_send and rxe_loopback Bob Pearson
2021-07-07 4:00 ` [PATCH v2 4/9] RDMA/rxe: Move ICRC generation to a subroutine Bob Pearson
2021-07-16 15:57 ` Jason Gunthorpe
2021-07-16 16:08 ` Bob Pearson
2021-07-16 16:29 ` Jason Gunthorpe
2021-07-16 16:38 ` Pearson, Robert B
2021-07-07 4:00 ` [PATCH v2 5/9] RDMA/rxe: Move rxe_crc32 " Bob Pearson
2021-07-07 4:00 ` [PATCH v2 6/9] RDMA/rxe: Fixup rxe_icrc_hdr Bob Pearson
2021-07-07 4:00 ` [PATCH v2 7/9] RDMA/rxe: Move crc32 init code to rxe_icrc.c Bob Pearson
2021-07-07 4:00 ` [PATCH v2 8/9] RDMA/rxe: Add kernel-doc comments " Bob Pearson
2021-07-07 4:00 ` [PATCH v2 9/9] RDMA/rxe: Fix types in rxe_icrc.c Bob Pearson
2021-07-16 16:06 ` Jason Gunthorpe
2021-07-08 7:36 ` [PATCH for-next v2 0/9] ICRC cleanup Zhu Yanjun
2021-07-16 17:38 ` Jason Gunthorpe
2021-07-19 8:42 ` Zhu Yanjun
2021-07-19 15:53 ` Olga Kornievskaia
2021-07-19 17:10 ` Jason Gunthorpe
2021-07-19 21:26 ` Bob Pearson
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='CAD=hENfY2PwNF71QFkR981CA8z7WFR65a2qxkeP61r0Zbaq+GQ@mail.gmail.com' \
--to=zyjzyj2000@gmail.com \
--cc=jgg@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=rpearsonhpe@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;
as well as URLs for NNTP newsgroup(s).