Netdev List
 help / color / mirror / Atom feed
From: Yishai Hadas <yishaih@nvidia.com>
To: <jgg@ziepe.ca>, <leon@kernel.org>
Cc: <linux-rdma@vger.kernel.org>, <netdev@vger.kernel.org>,
	<saeedm@nvidia.com>, <tariqt@nvidia.com>, <mbloch@nvidia.com>,
	<kuba@kernel.org>, <pabeni@redhat.com>, <edumazet@kernel.org>,
	<davem@davemloft.net>, <andrew+netdev@lunn.ch>,
	<dtatulea@nvidia.com>, <moshe@nvidia.com>, <yishaih@nvidia.com>,
	<maorg@nvidia.com>
Subject: [PATCH V2 rdma-next 11/21] RDMA/mlx5: Add shadow FIFO infrastructure for UMR completions
Date: Tue, 17 Nov 2026 19:09:04 +0200	[thread overview]
Message-ID: <20261117170914.27410-12-yishaih@nvidia.com> (raw)
In-Reply-To: <20261117170914.27410-1-yishaih@nvidia.com>

The UMR CQ is polled by the generic path, which finds the completed
request by indexing qp->sq.wrid[] with the CQE wqe_counter. A hostile
NIC can forge it to complete a request other than the one that really
completed, or one that is not pending at all.

The UMR QP signals every WR, and its send queue completes in posting
order. In adversarial mode, keep a FIFO of the posted UMR contexts, so
a follow-up patch can check each CQE against the oldest pending
request instead of trusting it. Each context also records the
SQ producer counter it was posted at, as its address alone doesn't
identify the post: it is usually on the stack and reused across posts.

Nothing consumes the FIFO yet.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h | 10 +++++++
 drivers/infiniband/hw/mlx5/umr.c     | 42 +++++++++++++++++++++++-----
 drivers/infiniband/hw/mlx5/umr.h     |  6 ++++
 3 files changed, 51 insertions(+), 7 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 5b81d7596bea..08d2a37a5f3b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -756,6 +756,12 @@ enum {
 	MLX5_UMR_STATE_ERR,
 };
 
+#define MLX5_UMR_MAX_WR 128
+static_assert((MLX5_UMR_MAX_WR & (MLX5_UMR_MAX_WR - 1)) == 0,
+	      "MLX5_UMR_MAX_WR must be a power of two for FIFO index masking");
+
+struct mlx5r_umr_context;
+
 struct umr_common {
 	struct ib_pd	*pd;
 	struct ib_cq	*cq;
@@ -769,6 +775,10 @@ struct umr_common {
 	unsigned int state;
 	/* Protects from repeat UMR QP creation */
 	struct mutex init_lock;
+	/* Posted UMR contexts in posting order, adversarial_mode only */
+	struct mlx5r_umr_context **pending;
+	u32 pending_head;
+	u32 pending_tail;
 };
 
 struct mlx5_ib_port_resources {
diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index 4a3fa79eba3a..bd180cb7f211 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -98,9 +98,7 @@ static int umr_check_mkey_mask(struct mlx5_ib_dev *dev, u64 mask)
 	return 0;
 }
 
-enum {
-	MAX_UMR_WR = 128,
-};
+#define MAX_UMR_WR MLX5_UMR_MAX_WR
 
 static int mlx5r_umr_qp_rst2rts(struct mlx5_ib_dev *dev, struct ib_qp *qp)
 {
@@ -181,6 +179,16 @@ int mlx5r_umr_resource_init(struct mlx5_ib_dev *dev)
 	if (ret)
 		goto destroy_qp;
 
+	if (dev->ib_dev.adversarial_mode) {
+		dev->umrc.pending = kcalloc(MAX_UMR_WR,
+					    sizeof(*dev->umrc.pending),
+					    GFP_KERNEL);
+		if (!dev->umrc.pending) {
+			ret = -ENOMEM;
+			goto destroy_qp;
+		}
+	}
+
 	dev->umrc.cq = cq;
 
 	sema_init(&dev->umrc.sem, MAX_UMR_WR);
@@ -208,6 +216,7 @@ void mlx5r_umr_resource_cleanup(struct mlx5_ib_dev *dev)
 	/* After device init, UMR cp/qp are not unset during the lifetime. */
 	ib_destroy_qp(dev->umrc.qp);
 	ib_free_cq(dev->umrc.cq);
+	kfree(dev->umrc.pending);
 }
 
 int mlx5r_umr_init(struct mlx5_ib_dev *dev)
@@ -236,7 +245,8 @@ void mlx5r_umr_cleanup(struct mlx5_ib_dev *dev)
 }
 
 
-static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
+static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey,
+			       struct mlx5r_umr_context *ctx,
 			       struct mlx5r_umr_wqe *wqe, bool with_data)
 {
 	unsigned int wqe_size =
@@ -245,6 +255,7 @@ static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
 				    sizeof(struct mlx5_wqe_data_seg);
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_core_dev *mdev = dev->mdev;
+	struct umr_common *umrc = &dev->umrc;
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
 	struct mlx5_wqe_ctrl_seg *ctrl;
 	union {
@@ -267,13 +278,30 @@ static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
 		goto out;
 
 	qp->sq.wr_data[idx] = MLX5_IB_WR_UMR;
+	if (dev->ib_dev.adversarial_mode) {
+		/* mlx5r_finish_wqe() advances cur_post, so record it first */
+		ctx->wqe_ctr = qp->sq.cur_post;
+	}
 
 	mlx5r_memcpy_send_wqe(&qp->sq, &cur_edge, &seg, &size, wqe, wqe_size);
 
-	id.ib_cqe = cqe;
+	id.ib_cqe = &ctx->cqe;
 	mlx5r_finish_wqe(qp, ctrl, seg, size, cur_edge, idx, id.wr_id, 0,
 			 MLX5_FENCE_MODE_INITIATOR_SMALL, MLX5_OPCODE_UMR);
 
+	/*
+	 * Push to the shadow FIFO before the doorbell, so the entry exists
+	 * before a CQE for it can arrive. A hostile NIC can post a CQE before
+	 * the doorbell, so the UMR CQ poller, on another CPU, can't rely on
+	 * the doorbell to see ctx->wqe_ctr and ctx->cqe.done with the entry.
+	 * Publish it with a release, which pairs with the poller's acquire.
+	 */
+	if (dev->ib_dev.adversarial_mode) {
+		smp_store_release(&umrc->pending[umrc->pending_tail & (MAX_UMR_WR - 1)],
+				  ctx);
+		umrc->pending_tail++;
+	}
+
 	mlx5r_ring_db(qp, 1, ctrl);
 
 out:
@@ -303,7 +331,7 @@ static int mlx5r_umr_recover(struct mlx5_ib_dev *dev, u32 mkey,
 	 * This will ensure that all the previous WRs got a completion before
 	 * we set the QP state to RESET.
 	 */
-	err = mlx5r_umr_post_send(umrc->qp, mkey, &umr_context->cqe, wqe,
+	err = mlx5r_umr_post_send(umrc->qp, mkey, umr_context, wqe,
 				  with_data);
 	if (err) {
 		mlx5_ib_warn(dev, "UMR recovery post send failed, err %d\n", err);
@@ -380,7 +408,7 @@ static int mlx5r_umr_post_send_wait(struct mlx5_ib_dev *dev, u32 mkey,
 			continue;
 		}
 
-		err = mlx5r_umr_post_send(umrc->qp, mkey, &umr_context.cqe, wqe,
+		err = mlx5r_umr_post_send(umrc->qp, mkey, &umr_context, wqe,
 					  with_data);
 		mutex_unlock(&umrc->lock);
 		if (err) {
diff --git a/drivers/infiniband/hw/mlx5/umr.h b/drivers/infiniband/hw/mlx5/umr.h
index bda7123781a9..0b245eec521f 100644
--- a/drivers/infiniband/hw/mlx5/umr.h
+++ b/drivers/infiniband/hw/mlx5/umr.h
@@ -84,6 +84,12 @@ struct mlx5r_umr_context {
 	struct ib_cqe cqe;
 	enum ib_wc_status status;
 	struct completion done;
+	/*
+	 * SQ producer counter the WQE was posted at, matched against the CQE
+	 * wqe_counter in adversarial_mode. Unlike the context address, which
+	 * is reused across posts, or the ring slot, it identifies the WQE.
+	 */
+	u16 wqe_ctr;
 };
 
 struct mlx5r_umr_wqe {
-- 
2.18.1


  parent reply	other threads:[~2026-11-17 17:11 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-17 17:08 [PATCH V2 rdma-next 00/21] mlx5: Adversarial mode for confidential computing guests Yishai Hadas
2026-11-17 17:08 ` [PATCH V2 rdma-next 01/21] net/mlx5: Add mlx5_trigger_health_work_force() Yishai Hadas
2026-11-17 17:08 ` [PATCH V2 rdma-next 02/21] net/mlx5: Derive adversarial mode from CC guest memory encryption Yishai Hadas
2026-11-17 17:08 ` [PATCH V2 rdma-next 03/21] net/mlx5: Add capability filtering in adversarial mode Yishai Hadas
2026-11-17 17:08 ` [PATCH V2 rdma-next 04/21] net/mlx5: Catch too low max number of EQs Yishai Hadas
2026-11-17 17:08 ` [PATCH V2 rdma-next 05/21] net/mlx5: Add macros for reading log-based caps Yishai Hadas
2026-11-17 17:08 ` [PATCH V2 rdma-next 06/21] RDMA/mlx5: Reject QP transport types not enabled by FW capability Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 07/21] RDMA/mlx5: Require IB_QPT_DRIVER for the DC vendor QP types Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 08/21] RDMA/core: Suppress kverbs_provider for adversarial_mode devices Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 09/21] RDMA/mlx5: Set ib_device::adversarial_mode from mlx5_core Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 10/21] RDMA/mlx5: Remove duplicate mlx5_ib_umr_context struct Yishai Hadas
2026-11-17 17:09 ` Yishai Hadas [this message]
2026-11-17 17:09 ` [PATCH V2 rdma-next 12/21] RDMA/mlx5: Verify UMR CQ polling against a hostile NIC Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 13/21] RDMA/mlx5: Keep the UMR QP failed once a forged CQE is detected Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 14/21] RDMA/core: Set the CQ comp_handler after its poll context is set up Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 15/21] RDMA/mlx5: Ignore completion events for a kernel CQ that is not ready Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 16/21] RDMA/mlx5: Validate EQE port and GSI port before indexing devr.ports[] Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 17/21] RDMA/mlx5: Validate firmware RQ/SQ state before sqrq_trans[] lookup Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 18/21] RDMA/mlx5: Clamp log_max_cq_sz shift in CQ size checks Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 19/21] RDMA/mlx5: Clamp log_max_* shifts in QP and WQ limit checks Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 20/21] RDMA/mlx5: Clamp log_max_* shifts in query_device and ucontext paths Yishai Hadas
2026-11-17 17:09 ` [PATCH V2 rdma-next 21/21] RDMA/core: Report and enforce adversarial mode via GET_CONTEXT Yishai Hadas

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=20261117170914.27410-12-yishaih@nvidia.com \
    --to=yishaih@nvidia.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=dtatulea@nvidia.com \
    --cc=edumazet@kernel.org \
    --cc=jgg@ziepe.ca \
    --cc=kuba@kernel.org \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=maorg@nvidia.com \
    --cc=mbloch@nvidia.com \
    --cc=moshe@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeedm@nvidia.com \
    --cc=tariqt@nvidia.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