linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: bugzilla-daemon@bugzilla.kernel.org
To: linux-rdma@vger.kernel.org
Subject: [Bug 212991] New: A possible divide by zero in calc_sq_size
Date: Sat, 08 May 2021 10:41:37 +0000	[thread overview]
Message-ID: <bug-212991-11804@https.bugzilla.kernel.org/> (raw)

https://bugzilla.kernel.org/show_bug.cgi?id=212991

            Bug ID: 212991
           Summary: A possible divide by zero in calc_sq_size
           Product: Drivers
           Version: 2.5
    Kernel Version: 5.12.2
          Hardware: All
                OS: Linux
              Tree: Mainline
            Status: NEW
          Severity: normal
          Priority: P1
         Component: Infiniband/RDMA
          Assignee: drivers_infiniband-rdma@kernel-bugs.osdl.org
          Reporter: yguoaz@gmail.com
        Regression: No

In the file drivers/infiniband/hw/mlx5/qp.c, the function calc_sq_size has the
following code(link to code location:
https://github.com/torvalds/linux/blob/master/drivers/infiniband/hw/mlx5/qp.c#L510):

static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
                        struct mlx5_ib_qp *qp) {
   ...
   wqe_size = calc_send_wqe(attr);
   ...
   qp->sq.max_post = wq_size / wqe_size;
}


static int calc_send_wqe(struct ib_qp_init_attr *attr)
{
        int inl_size = 0;
        int size;

        size = sq_overhead(attr);
        if (size < 0)
                return size;

        if (attr->cap.max_inline_data) {
                inl_size = size + sizeof(struct mlx5_wqe_inline_seg) +
                        attr->cap.max_inline_data;
        }

        size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg);
        if (attr->create_flags & IB_QP_CREATE_INTEGRITY_EN &&
            ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) <
MLX5_SIG_WQE_SIZE)
                return MLX5_SIG_WQE_SIZE;
        else
                return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
}

The function calc_send_wqe may return 0 (when attr->qp_type == IB_QPT_XRC_TGT
&& attr->cap.max_send_sge == 0), leading to a possible divide by zero problem.

-- 
You may reply to this email to add a comment.

You are receiving this mail because:
You are watching the assignee of the bug.

                 reply	other threads:[~2021-05-08 10:41 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=bug-212991-11804@https.bugzilla.kernel.org/ \
    --to=bugzilla-daemon@bugzilla.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    /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).