Re: [PATCH] RDMA/rtrs-clt: Validate peer-supplied IO completion msg_id

From: Jinpu Wang

Date: Tue Sep 29 2026 - 00:03:29 EST


On Wed, Sep 23, 2026 at 12:52 PM Quanye Yang via B4 Relay
<devnull+quanyeyang.proton.me@xxxxxxxxxx> wrote:
>
> From: Quanye Yang <quanyeyang@xxxxxxxxx>
>
> process_io_rsp() indexes clt_path->reqs[] with the 19-bit msg_id
> taken from a WRITE_WITH_IMM immediate. That value is chosen by the
> peer. The only check was WARN_ON(msg_id >= queue_depth), which still
> lets a completion run after free_path_reqs() has set reqs to NULL,
> or against a slot whose FRWR is already gone. Either path
> dereferences req->mr and can GPF; KASAN reports a null-ptr-deref at
> offsetof(struct rtrs_clt_io_req, mr).
>
> Treat a missing reqs array, an out-of-range msg_id, or a req
> without an MR as a protocol error and recover the connection.
>
> Reported-by: Farhad Alemi <farhad.alemi@xxxxxxxxxxxx>
> Link: https://lore.kernel.org/r/CA+0ovCiJZz6O8LzsS9Dq1-JE1OE1L_OTA6Mr-WratpUE6jczHw@xxxxxxxxxxxxxx
> Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality")
> Signed-off-by: Quanye Yang <quanyeyang@xxxxxxxxx>
lgtm, thx!
Reviewed-by: Jack Wang <jinpu.wang@xxxxxxxxxxxxxxx>
> ---
> drivers/infiniband/ulp/rtrs/rtrs-clt.c | 21 ++++++++++++++++-----
> 1 file changed, 16 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
> index eac38b57b00d..f8d3c6f37e3e 100644
> --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
> +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
> @@ -489,18 +489,22 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con,
> imm, flags, wr, NULL);
> }
>
> -static void process_io_rsp(struct rtrs_clt_path *clt_path, u32 msg_id,
> +static bool process_io_rsp(struct rtrs_clt_path *clt_path, u32 msg_id,
> s16 errno, bool w_inval)
> {
> struct rtrs_clt_io_req *req;
>
> - if (WARN_ON(msg_id >= clt_path->queue_depth))
> - return;
> + if (!clt_path->reqs || msg_id >= clt_path->queue_depth)
> + return false;
>
> req = &clt_path->reqs[msg_id];
> + if (!req->mr)
> + return false;
> +
> /* Drop need_inv if server responded with send with invalidation */
> req->mr->need_inval &= !w_inval;
> complete_rdma_req(req, errno, true, false);
> + return true;
> }
>
> static void rtrs_clt_recv_done(struct rtrs_clt_con *con, struct ib_wc *wc)
> @@ -562,7 +566,8 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
> if (WARN_ON(buf_id != msg_id))
> goto out;
> clt_path->rbufs[buf_id].rkey = le32_to_cpu(msg->rkey);
> - process_io_rsp(clt_path, msg_id, err, w_inval);
> + if (!process_io_rsp(clt_path, msg_id, err, w_inval))
> + goto out;
> }
> ib_dma_sync_single_for_device(clt_path->s.dev->ib_dev, iu->dma_addr,
> iu->size, DMA_FROM_DEVICE);
> @@ -634,7 +639,13 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
> w_inval = (imm_type == RTRS_IO_RSP_W_INV_IMM);
> rtrs_from_io_rsp_imm(imm_payload, &msg_id, &err);
>
> - process_io_rsp(clt_path, msg_id, err, w_inval);
> + if (!process_io_rsp(clt_path, msg_id, err, w_inval)) {
> + rtrs_err(clt_path->clt,
> + "Invalid IO rsp: msg_id %u queue_depth %zu\n",
> + msg_id, clt_path->queue_depth);
> + rtrs_rdma_error_recovery(con);
> + return;
> + }
> } else if (imm_type == RTRS_HB_MSG_IMM) {
> WARN_ON(con->c.cid);
> rtrs_send_hb_ack(&clt_path->s);
>
> ---
> base-commit: 93f51579e7df248780214094418f205253383cc5
> change-id: 20260923-rtrs-warning-inrtrs-clt-rdma-done-3a72d73550b1
>
> Best regards,
> --
> Quanye Yang <quanyeyang@xxxxxxxxx>
>
>