get_srq_wqe() reads wqe->dma.num_sge from the shared receive queue
buffer, which is mapped into userspace. It validates num_sge against
max_sge, but then re-reads the same field to calculate the memcpy
size. A concurrent userspace thread can modify num_sge between
validation and use, causing a heap buffer overflow when copying the
WQE into qp->resp.srq_wqe.
Read num_sge into a local variable and use it for both the bounds
check and the size calculation.
Fixes: 8700e3e7c485 ("Soft RoCE driver")
Link: https://patch.msgid.link/r/20260518215040.1598586-2-tristan@talencesecurity.com
Signed-off-by: Tristan Madani <tristan@talencesecurity.com>
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
struct rxe_recv_wqe *wqe;
struct ib_event ev;
unsigned int count;
+ unsigned int num_sge;
size_t size;
unsigned long flags;
}
/* don't trust user space data */
- if (unlikely(wqe->dma.num_sge > srq->rq.max_sge)) {
+ num_sge = wqe->dma.num_sge;
+ if (unlikely(num_sge > srq->rq.max_sge)) {
spin_unlock_irqrestore(&srq->rq.consumer_lock, flags);
rxe_dbg_qp(qp, "invalid num_sge in SRQ entry\n");
return RESPST_ERR_MALFORMED_WQE;
}
- size = sizeof(*wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge);
+ size = sizeof(*wqe) + num_sge * sizeof(struct rxe_sge);
memcpy(&qp->resp.srq_wqe, wqe, size);
qp->resp.wqe = &qp->resp.srq_wqe.wqe;