The rxe send queue is mapped into userspace via mmap. The requester processes Work Queue Entries (WQEs) directly from this shared buffer without first copying them to kernel memory. Userspace can modify WQE fields (num_sge, sge_offset, SGE entries) between kernel reads, leading to inconsistent state in copy_data(). This is the send-path counterpart to the receive-path fixes: - commit 22b8fbded65b8 ("RDMA/rxe: Fix TOCTOU heap overflow in get_srq_wqe") - commit d6ab440240a04 ("RDMA/rxe: Copy WQE to local buffer in non-SRQ receive path") Fix by copying the send WQE to a kernel-private buffer in req_next_wqe() before processing. The copy uses the full queue element data size (max of max_sge SGEs and max_inline bytes) so that both SGE entries and inline data are always captured. After copying, reject out-of-range opcodes and oversized atomic write residuals by setting mask to 0 so that next_opcode() transitions the QP to error state through the normal error path. This covers all valid opcodes up to IB_WR_REG_MR while preventing OOB access in both the wr_opcode_mask() lookup table and finish_packet() for atomic writes. The local copy is reused across multi-packet sends to preserve DMA progress state (cur_sge, sge_offset, resid). Field updates including DMA progress are written back to the shared queue using WRITE_ONCE() for individual fields and smp_store_release() for state transitions, so the completer and userspace observe consistent values without the tearing risk of bulk memcpy(). DMA progress writeback ensures retries can resume from the correct offset. The copy is invalidated when the WQE index advances (last packet sent, error, local ops, UD oversized), when a retry resets WQE state, on QP reset, or when the QP enters error state for flush. Fixes: 8700e3e7c485 ("Soft RoCE driver") Cc: stable@vger.kernel.org Signed-off-by: Tristan Madani --- Changes since v7: - Reject atomic write WQEs with oversized dma.resid to prevent OOB read in finish_packet() (sashiko finding). Changes since v6: - Fixed all sashiko review findings (2 Critical + 9 High). - FORTIFY_SOURCE: memcpy into enclosing struct, not inner member. - Copy size: max(max_sge * sizeof(ib_sge), max_inline). - Opcode bound: IB_WR_REG_MR (was IB_WR_ATOMIC_WRITE). - Removed silent num_sge clamp, use mask=0 for invalid opcodes. - DMA progress writeback (resid, cur_sge, sge_offset). - Addressed Zhu Yanjun review feedback. Changes since v5: - Added opcode bounds check and num_sge clamp after copy. Changes since v4: - Resent from the correct sender address. Changes since v3: - Copy full queue element (max_sge SGEs) instead of per-WQE size. - Invalidate on QP reset, ERR flush, RESET state check. Changes since v2: - WRITE_ONCE/smp_store_release for field writeback. Changes since v1: - Split into per-path patches. Cache across multi-packet ops. --- drivers/infiniband/sw/rxe/rxe_qp.c | 1 + drivers/infiniband/sw/rxe/rxe_req.c | 71 +++++++++++++++++++++++++-- drivers/infiniband/sw/rxe/rxe_verbs.h | 6 +++ 3 files changed, 73 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 311f285d78a6b..77606c4a039b1 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -581,6 +581,7 @@ static void rxe_qp_reset(struct rxe_qp *qp) qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; qp->req.noack_pkts = 0; + qp->req.send_wqe_valid = false; qp->resp.msn = 0; qp->resp.opcode = -1; qp->resp.drop_msg = 0; diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 24f5c044363f7..d5a0c46eb8a25 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -161,6 +161,26 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) spin_unlock_irqrestore(&qp->state_lock, flags); } +static void rxe_req_writeback_wqe(struct rxe_qp *qp) +{ + struct rxe_send_wqe *shared = qp->req.shared_wqe; + struct rxe_send_wqe *local = &qp->req.send_wqe.wqe; + + if (!qp->req.send_wqe_valid || !shared) + return; + + WRITE_ONCE(shared->status, local->status); + WRITE_ONCE(shared->first_psn, local->first_psn); + WRITE_ONCE(shared->last_psn, local->last_psn); + WRITE_ONCE(shared->mask, local->mask); + WRITE_ONCE(shared->has_rd_atomic, local->has_rd_atomic); + WRITE_ONCE(shared->dma.resid, local->dma.resid); + WRITE_ONCE(shared->dma.cur_sge, local->dma.cur_sge); + WRITE_ONCE(shared->dma.sge_offset, local->dma.sge_offset); + /* State must be last so the completer sees prior updates */ + smp_store_release(&shared->state, local->state); +} + static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) { struct rxe_queue *q = qp->sq.queue; @@ -193,7 +213,35 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) } spin_unlock_irqrestore(&qp->state_lock, flags); - wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); + /* Reuse the existing kernel-private copy if still valid */ + if (qp->req.send_wqe_valid && qp->req.shared_wqe == wqe) + return &qp->req.send_wqe.wqe; + + /* Copy WQE from userspace-mapped shared queue to kernel-private + * buffer. Copy size matches the queue element data area. + */ + memcpy(&qp->req.send_wqe, wqe, sizeof(*wqe) + + max_t(int, qp->sq.max_sge * sizeof(struct ib_sge), + qp->sq.max_inline)); + qp->req.shared_wqe = wqe; + qp->req.send_wqe_valid = true; + + wqe = &qp->req.send_wqe.wqe; + + /* Prevent OOB in wr_opcode_mask() for corrupted opcodes. + * Mask 0 causes next_opcode() to fail, moving QP to error state. + */ + if (unlikely(wqe->wr.opcode > IB_WR_REG_MR)) + wqe->mask = 0; + else + wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); + + /* Atomic writes carry exactly sizeof(u64) payload. + * Reject oversized resid to prevent OOB read in finish_packet(). + */ + if (unlikely((wqe->mask & RXE_ATOMIC_WRITE_MASK) && + wqe->dma.resid > sizeof(u64))) + wqe->mask = 0; return wqe; } @@ -582,9 +630,13 @@ static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { qp->req.opcode = pkt->opcode; - if (pkt->mask & RXE_END_MASK) + rxe_req_writeback_wqe(qp); + + if (pkt->mask & RXE_END_MASK) { qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); + qp->req.send_wqe_valid = false; + } qp->need_req_skb = 0; @@ -634,7 +686,9 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe) wqe->state = wqe_state_done; wqe->status = IB_WC_SUCCESS; + rxe_req_writeback_wqe(qp); qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); + qp->req.send_wqe_valid = false; return 0; } @@ -666,6 +720,7 @@ int rxe_requester(struct rxe_qp *qp) wqe = __req_next_wqe(qp); spin_unlock_irqrestore(&qp->state_lock, flags); if (wqe) { + qp->req.send_wqe_valid = false; wqe->status = IB_WC_WR_FLUSH_ERR; goto err; } else { @@ -681,6 +736,7 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wait_psn = 0; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; + qp->req.send_wqe_valid = false; spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } @@ -695,6 +751,7 @@ int rxe_requester(struct rxe_qp *qp) if (unlikely(qp->req.need_retry && !qp->req.wait_for_rnr_timer)) { req_retry(qp); qp->req.need_retry = 0; + qp->req.send_wqe_valid = false; } wqe = req_next_wqe(qp); @@ -772,10 +829,12 @@ int rxe_requester(struct rxe_qp *qp) wqe->last_psn = qp->req.psn; qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK; qp->req.opcode = IB_OPCODE_UD_SEND_ONLY; - qp->req.wqe_index = queue_next_index(qp->sq.queue, - qp->req.wqe_index); wqe->state = wqe_state_done; wqe->status = IB_WC_SUCCESS; + rxe_req_writeback_wqe(qp); + qp->req.wqe_index = queue_next_index(qp->sq.queue, + qp->req.wqe_index); + qp->req.send_wqe_valid = false; goto done; } payload = mtu; @@ -839,8 +898,10 @@ int rxe_requester(struct rxe_qp *qp) goto out; err: /* update wqe_index for each wqe completion */ - qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); wqe->state = wqe_state_error; + rxe_req_writeback_wqe(qp); + qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); + qp->req.send_wqe_valid = false; rxe_qp_error(qp); exit: ret = -EAGAIN; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 0f5ffd94643f9..a22dfc6e5ae3c 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -114,6 +114,12 @@ struct rxe_req_info { int wait_for_rnr_timer; int noack_pkts; int again; + struct rxe_send_wqe *shared_wqe; + bool send_wqe_valid; + struct { + struct rxe_send_wqe wqe; + struct ib_sge sge[RXE_MAX_SGE]; + } send_wqe; }; struct rxe_comp_info { -- 2.47.3 The completer reads send WQEs from the same userspace-mapped shared queue as the requester. Even after the requester copies the WQE to a kernel-private buffer (previous patch), the completer still reads directly from shared memory, leaving it exposed to the same TOCTOU races. Fix by copying the WQE in get_wqe() to a completer-private buffer using the full queue element data size. The local copy is reused when the same WQE is being processed with unchanged state, which preserves DMA progress across multi-packet RDMA READ responses. A fresh copy is taken when the state changes or a new WQE appears. After copying, reject invalid opcodes (above IB_WR_REG_MR), out-of- bounds num_sge, and invalid cur_sge by transitioning the QP to error state through COMPST_ERROR. This prevents OOB SGE walks in copy_data() from corrupted DMA indices. The state read from the shared queue is preserved via smp_load_acquire() and restored after the memcpy to prevent a concurrent userspace write from overwriting it with a stale value. DMA progress (resid, cur_sge, sge_offset) is written back alongside completion status and rd_atomic state on completion and before retry invalidation, ensuring retries can resume from the correct offset rather than restarting from zero. The cache is invalidated on QP reset, when a completion advances to the next WQE, on error retry, and on RNR retry to ensure fresh state after the requester retransmits. Fixes: 8700e3e7c485 ("Soft RoCE driver") Cc: stable@vger.kernel.org Signed-off-by: Tristan Madani --- Changes since v7: - Write back DMA progress before invalidating completer cache on error retry, so req_retry() resumes multi-packet reads from the correct offset (sashiko finding). - Invalidate completer cache in COMPST_RNR_RETRY to prevent stale PSN comparison after RNR timer fires (sashiko finding). Changes since v6: - Fixed all sashiko review findings (2 Critical + 9 High). - FORTIFY_SOURCE: memcpy into enclosing struct, not inner member. - Copy size: max(max_sge * sizeof(ib_sge), max_inline). - Opcode bound: IB_WR_REG_MR (was IB_WR_ATOMIC_WRITE). - Validate num_sge + cur_sge, preserve smp_load_acquire state. - DMA progress writeback (resid, cur_sge, sge_offset). - *wqe_p = NULL for posted state, invalidate on retry. - Addressed Zhu Yanjun review feedback. Changes since v5: - Added opcode bounds check and num_sge clamp after copy. Changes since v4: - Resent from the correct sender address. Changes since v3: - Copy full queue element (max_sge SGEs) instead of per-WQE size. - Invalidate on QP reset, ERR flush, RESET state check. Changes since v2: - WRITE_ONCE/smp_store_release for field writeback. Changes since v1: - Split into per-path patches. Cache across multi-packet ops. drivers/infiniband/sw/rxe/rxe_comp.c | 75 ++++++++++++++++++++++++++- drivers/infiniband/sw/rxe/rxe_qp.c | 1 + drivers/infiniband/sw/rxe/rxe_verbs.h | 6 +++ 3 files changed, 80 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 1390e861bd1d7..b8bc710dc75e9 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -137,22 +137,87 @@ void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) rxe_sched_task(&qp->send_task); } +/* Write back completer WQE fields to shared memory */ +static void rxe_comp_writeback_wqe(struct rxe_qp *qp) +{ + struct rxe_send_wqe *shared = qp->comp.shared_wqe; + struct rxe_send_wqe *local = &qp->comp.comp_wqe.wqe; + + if (!qp->comp.comp_wqe_valid || !shared) + return; + + WRITE_ONCE(shared->status, local->status); + WRITE_ONCE(shared->has_rd_atomic, local->has_rd_atomic); + WRITE_ONCE(shared->dma.resid, local->dma.resid); + WRITE_ONCE(shared->dma.cur_sge, local->dma.cur_sge); + WRITE_ONCE(shared->dma.sge_offset, local->dma.sge_offset); +} + static inline enum comp_state get_wqe(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct rxe_send_wqe **wqe_p) { struct rxe_send_wqe *wqe; + u32 state; /* we come here whether or not we found a response packet to see if * there are any posted WQEs */ wqe = queue_head(qp->sq.queue, QUEUE_TYPE_FROM_CLIENT); - *wqe_p = wqe; /* no WQE or requester has not started it yet */ - if (!wqe || wqe->state == wqe_state_posted) + if (!wqe) { + *wqe_p = NULL; return pkt ? COMPST_DONE : COMPST_EXIT; + } + + /* Pairs with smp_store_release() in rxe_req_writeback_wqe() */ + state = smp_load_acquire(&wqe->state); + if (state == wqe_state_posted) { + *wqe_p = NULL; + return pkt ? COMPST_DONE : COMPST_EXIT; + } + + /* Reuse existing local copy if still processing same WQE + * with unchanged state (preserves DMA progress for multi-packet ops) + */ + if (qp->comp.comp_wqe_valid && qp->comp.shared_wqe == wqe && + qp->comp.comp_wqe.wqe.state == state) { + wqe = &qp->comp.comp_wqe.wqe; + *wqe_p = wqe; + goto check_state; + } + + /* Copy shared WQE to kernel-private buffer. + * Copy size matches the queue element data area. + */ + qp->comp.shared_wqe = wqe; + memcpy(&qp->comp.comp_wqe, wqe, + sizeof(*wqe) + max_t(int, + qp->sq.max_sge * sizeof(struct ib_sge), + qp->sq.max_inline)); + qp->comp.comp_wqe_valid = true; + + /* Preserve the state we observed via smp_load_acquire() + * since memcpy may have overwritten it with a stale read. + */ + qp->comp.comp_wqe.wqe.state = state; + + /* Reject corrupted opcode or SGE indices, error the QP */ + if (unlikely(qp->comp.comp_wqe.wqe.wr.opcode > IB_WR_REG_MR) || + qp->comp.comp_wqe.wqe.dma.num_sge > qp->sq.max_sge || + (qp->comp.comp_wqe.wqe.dma.resid && + qp->comp.comp_wqe.wqe.dma.cur_sge >= qp->sq.max_sge)) { + qp->comp.comp_wqe.wqe.status = IB_WC_LOC_QP_OP_ERR; + wqe = &qp->comp.comp_wqe.wqe; + *wqe_p = wqe; + return COMPST_ERROR; + } + + wqe = &qp->comp.comp_wqe.wqe; + *wqe_p = wqe; +check_state: /* WQE does not require an ack */ if (wqe->state == wqe_state_done) return COMPST_COMP_WQE; @@ -454,6 +519,8 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) if (post) make_send_cqe(qp, wqe, &cqe); + rxe_comp_writeback_wqe(qp); + qp->comp.comp_wqe_valid = false; queue_advance_consumer(qp->sq.queue, QUEUE_TYPE_FROM_CLIENT); if (post) @@ -788,6 +855,8 @@ int rxe_completer(struct rxe_qp *qp) RXE_CNT_COMP_RETRY); qp->req.need_retry = 1; qp->comp.started_retry = 1; + rxe_comp_writeback_wqe(qp); + qp->comp.comp_wqe_valid = false; qp->req.again = 1; } goto done; @@ -809,6 +878,8 @@ int rxe_completer(struct rxe_qp *qp) * rnr timer has fired */ qp->req.wait_for_rnr_timer = 1; + rxe_comp_writeback_wqe(qp); + qp->comp.comp_wqe_valid = false; rxe_dbg_qp(qp, "set rnr nak timer\n"); // TODO who protects from destroy_qp?? mod_timer(&qp->rnr_nak_timer, diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 77606c4a039b1..450254a131017 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -582,6 +582,7 @@ static void rxe_qp_reset(struct rxe_qp *qp) qp->req.wait_for_rnr_timer = 0; qp->req.noack_pkts = 0; qp->req.send_wqe_valid = false; + qp->comp.comp_wqe_valid = false; qp->resp.msn = 0; qp->resp.opcode = -1; qp->resp.drop_msg = 0; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index a22dfc6e5ae3c..6205dbc29dff6 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -130,6 +130,12 @@ struct rxe_comp_info { int started_retry; u32 retry_cnt; u32 rnr_retry; + struct rxe_send_wqe *shared_wqe; + bool comp_wqe_valid; + struct { + struct rxe_send_wqe wqe; + struct ib_sge sge[RXE_MAX_SGE]; + } comp_wqe; }; /* responder states */ -- 2.47.3