net/mlx5e: kTLS, Cancel RX async resync request in error flows

When device loses track of TLS records, it attempts to resync by
monitoring records and requests an asynchronous resynchronization
from software for this TLS connection.

The TLS module handles such device RX resync requests by logging record
headers and comparing them with the record tcp_sn when provided by the
device. It also increments rcd_delta to track how far the current
record tcp_sn is from the tcp_sn of the original resync request.
If the device later responds with a matching tcp_sn, the TLS module
approves the tcp_sn for resync.

However, the device response may be delayed or never arrive,
particularly due to traffic-related issues such as packet drops or
reordering. In such cases, the TLS module remains unaware that resync
will not complete, and continues performing unnecessary work by logging
headers and incrementing rcd_delta, which can eventually exceed the
threshold and trigger a WARN(). For example, this was observed when the
device got out of tracking, causing
mlx5e_ktls_handle_get_psv_completion() to fail and ultimately leading
to the rcd_delta warning.

To address this, call tls_offload_rx_resync_async_request_cancel()
to cancel the resync request and stop resync tracking in such error
cases. Also, increment the tls_resync_req_skip counter to track these
cancellations.

Fixes: 0419d8c9d8f8 ("net/mlx5e: kTLS, Add kTLS RX resync support")
Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1761508983-937977-4-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 5fbc922695858e87ccf1980874816ae02fac0cdf..da2d1eb52c131aa4a91ea883b44615e1a050277d 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -320,7 +320,6 @@ err_dma_unmap:
 err_free:
        kfree(buf);
 err_out:
-       priv_rx->rq_stats->tls_resync_req_skip++;
        return err;
 }
 
@@ -339,14 +338,19 @@ static void resync_handle_work(struct work_struct *work)
 
        if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) {
                mlx5e_ktls_priv_rx_put(priv_rx);
+               priv_rx->rq_stats->tls_resync_req_skip++;
+               tls_offload_rx_resync_async_request_cancel(&resync->core);
                return;
        }
 
        c = resync->priv->channels.c[priv_rx->rxq];
        sq = &c->async_icosq;
 
-       if (resync_post_get_progress_params(sq, priv_rx))
+       if (resync_post_get_progress_params(sq, priv_rx)) {
+               priv_rx->rq_stats->tls_resync_req_skip++;
+               tls_offload_rx_resync_async_request_cancel(&resync->core);
                mlx5e_ktls_priv_rx_put(priv_rx);
+       }
 }
 
 static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync,
@@ -425,6 +429,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 {
        struct mlx5e_ktls_rx_resync_buf *buf = wi->tls_get_params.buf;
        struct mlx5e_ktls_offload_context_rx *priv_rx;
+       struct tls_offload_resync_async *async_resync;
        struct tls_offload_context_rx *rx_ctx;
        u8 tracker_state, auth_state, *ctx;
        struct device *dev;
@@ -433,8 +438,12 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
        priv_rx = buf->priv_rx;
        dev = mlx5_core_dma_dev(sq->channel->mdev);
        rx_ctx = tls_offload_ctx_rx(tls_get_ctx(priv_rx->sk));
-       if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags)))
+       async_resync = rx_ctx->resync_async;
+       if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) {
+               priv_rx->rq_stats->tls_resync_req_skip++;
+               tls_offload_rx_resync_async_request_cancel(async_resync);
                goto out;
+       }
 
        dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE,
                                DMA_FROM_DEVICE);
@@ -445,11 +454,12 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
        if (tracker_state != MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING ||
            auth_state != MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD) {
                priv_rx->rq_stats->tls_resync_req_skip++;
+               tls_offload_rx_resync_async_request_cancel(async_resync);
                goto out;
        }
 
        hw_seq = MLX5_GET(tls_progress_params, ctx, hw_resync_tcp_sn);
-       tls_offload_rx_resync_async_request_end(rx_ctx->resync_async,
+       tls_offload_rx_resync_async_request_end(async_resync,
                                                cpu_to_be32(hw_seq));
        priv_rx->rq_stats->tls_resync_req_end++;
 out:
@@ -475,8 +485,10 @@ static bool resync_queue_get_psv(struct sock *sk)
 
        resync = &priv_rx->resync;
        mlx5e_ktls_priv_rx_get(priv_rx);
-       if (unlikely(!queue_work(resync->priv->tls->rx_wq, &resync->work)))
+       if (unlikely(!queue_work(resync->priv->tls->rx_wq, &resync->work))) {
                mlx5e_ktls_priv_rx_put(priv_rx);
+               return false;
+       }
 
        return true;
 }
@@ -561,6 +573,18 @@ void mlx5e_ktls_rx_resync(struct net_device *netdev, struct sock *sk,
        resync_handle_seq_match(priv_rx, c);
 }
 
+void
+mlx5e_ktls_rx_resync_async_request_cancel(struct mlx5e_icosq_wqe_info *wi)
+{
+       struct mlx5e_ktls_offload_context_rx *priv_rx;
+       struct mlx5e_ktls_rx_resync_buf *buf;
+
+       buf = wi->tls_get_params.buf;
+       priv_rx = buf->priv_rx;
+       priv_rx->rq_stats->tls_resync_req_skip++;
+       tls_offload_rx_resync_async_request_cancel(&priv_rx->resync.core);
+}
+
 /* End of resync section */
 
 void mlx5e_ktls_handle_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb,

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
index f87b65c560ea68ef764139d1039286c1a350efa1..cb08799769ee19d8437a289f0cf6841b52ce0883 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h
@@ -29,6 +29,10 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi,
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
                                           struct mlx5e_tx_wqe_info *wi,
                                           u32 *dma_fifo_cc);
+
+void
+mlx5e_ktls_rx_resync_async_request_cancel(struct mlx5e_icosq_wqe_info *wi);
+
 static inline bool
 mlx5e_ktls_tx_try_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
                                          struct mlx5e_tx_wqe_info *wi,

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1c79adc51a0416e73884745cd0312e54b1be6ecb..26621a2972ec2babf877ac033e97303d8606fd79 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1036,6 +1036,10 @@ int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
                                netdev_WARN_ONCE(cq->netdev,
                                                 "Bad OP in ICOSQ CQE: 0x%x\n",
                                                 get_cqe_opcode(cqe));
+#ifdef CONFIG_MLX5_EN_TLS
+                               if (wi->wqe_type == MLX5E_ICOSQ_WQE_GET_PSV_TLS)
+                                       mlx5e_ktls_rx_resync_async_request_cancel(wi);
+#endif
                                mlx5e_dump_error_cqe(&sq->cq, sq->sqn,
                                                     (struct mlx5_err_cqe *)cqe);
                                mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);