[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20260204-psp-v1-7-5f034e2dfa36@gmail.com>
Date: Wed, 04 Feb 2026 07:20:11 -0800
From: Daniel Zahka <daniel.zahka@...il.com>
To: "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, Simon Horman <horms@...nel.org>,
Donald Hunter <donald.hunter@...il.com>, Boris Pismenny <borisp@...dia.com>,
Saeed Mahameed <saeedm@...dia.com>, Leon Romanovsky <leon@...nel.org>,
Tariq Toukan <tariqt@...dia.com>, Mark Bloch <mbloch@...dia.com>,
Andrew Lunn <andrew+netdev@...n.ch>, Shuah Khan <shuah@...nel.org>,
Willem de Bruijn <willemdebruijn.kernel@...il.com>
Cc: netdev@...r.kernel.org, linux-kselftest@...r.kernel.org,
Daniel Zahka <daniel.zahka@...il.com>
Subject: [PATCH net-next 7/9] mlx5: psp: implement deferred tx key deletion
Implement the deferred tx key deletion api. In the case of mlx5,
mlx5e_psp_tx_grace_begin() records the number of wqes retired on each
tx queue, and then mlx5e_psp_tx_grace_end() returns 0 only if
all tx queues have advanced a full ring cycle past the point where
they were snapshotted.
Signed-off-by: Daniel Zahka <daniel.zahka@...il.com>
---
.../net/ethernet/mellanox/mlx5/core/en_accel/psp.c | 101 +++++++++++++++++++--
.../net/ethernet/mellanox/mlx5/core/en_accel/psp.h | 7 ++
drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 1 +
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 1 +
4 files changed, 104 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
index 9a74438ce10a..30f1dbc3fa9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c
@@ -1059,13 +1059,102 @@ mlx5e_psp_get_stats(struct psp_dev *psd, struct psp_dev_stats *stats)
stats->tx_error = atomic_read(&priv->psp->tx_drop);
}
+static int mlx5e_psp_tx_grace_begin(struct psp_dev *psd)
+{
+ struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+ struct mlx5e_psp_tx_snapshot *snap;
+ int num_channels, num_tc, num_sqs;
+ int idx = 0, rc = 0;
+ int i, tc;
+
+ mutex_lock(&priv->state_lock);
+
+ num_channels = priv->channels.num;
+ num_tc = mlx5e_get_dcb_num_tc(&priv->channels.params);
+ num_sqs = num_channels * num_tc;
+
+ snap = kzalloc(struct_size(snap, wqes, num_sqs), GFP_KERNEL);
+ if (!snap) {
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+
+ snap->num_channels = num_channels;
+ snap->num_tc = num_tc;
+
+ for (i = 0; i < priv->channels.num; i++) {
+ struct mlx5e_channel *c = priv->channels.c[i];
+
+ for (tc = 0; tc < c->num_tc; tc++)
+ snap->wqes[idx++] = READ_ONCE(c->sq[tc].stats->wqes);
+ }
+
+ priv->psp->tx_snapshot = snap;
+
+out_unlock:
+ mutex_unlock(&priv->state_lock);
+ return rc;
+}
+
+static int mlx5e_psp_tx_grace_end(struct psp_dev *psd)
+{
+ struct mlx5e_priv *priv = netdev_priv(psd->main_netdev);
+ struct mlx5e_psp_tx_snapshot *snap;
+ int num_channels, num_tc;
+ int idx = 0, rc = 0;
+ int i, tc;
+
+ mutex_lock(&priv->state_lock);
+
+ snap = priv->psp->tx_snapshot;
+ num_channels = priv->channels.num;
+ num_tc = mlx5e_get_dcb_num_tc(&priv->channels.params);
+
+ /* If channels were reconfigured, tell core to restart grace period */
+ if (snap->num_channels != num_channels || snap->num_tc != num_tc) {
+ kfree(snap);
+ priv->psp->tx_snapshot = NULL;
+ rc = -ESTALE;
+ goto out_unlock;
+ }
+
+ for (i = 0; i < priv->channels.num; i++) {
+ struct mlx5e_channel *c = priv->channels.c[i];
+
+ for (tc = 0; tc < c->num_tc; tc++) {
+ struct mlx5e_txqsq *sq = &c->sq[tc];
+ u32 ring_size = mlx5_wq_cyc_get_size(&sq->wq);
+ u64 current_wqes = READ_ONCE(sq->stats->wqes);
+ u64 snapshot_wqes = snap->wqes[idx++];
+
+ /* If the ring has cycled, any key_id handles in tx
+ * descriptors must have been consumed by hw and
+ * cleaned by sw.
+ */
+ if ((s64)(current_wqes - snapshot_wqes) < ring_size) {
+ rc = -EAGAIN;
+ goto out_unlock;
+ }
+ }
+ }
+
+ kfree(snap);
+ priv->psp->tx_snapshot = NULL;
+
+out_unlock:
+ mutex_unlock(&priv->state_lock);
+ return rc;
+}
+
static struct psp_dev_ops mlx5_psp_ops = {
- .set_config = mlx5e_psp_set_config,
- .rx_spi_alloc = mlx5e_psp_rx_spi_alloc,
- .tx_key_add = mlx5e_psp_assoc_add,
- .tx_key_del = mlx5e_psp_assoc_del,
- .key_rotate = mlx5e_psp_key_rotate,
- .get_stats = mlx5e_psp_get_stats,
+ .set_config = mlx5e_psp_set_config,
+ .rx_spi_alloc = mlx5e_psp_rx_spi_alloc,
+ .tx_key_add = mlx5e_psp_assoc_add,
+ .tx_key_del = mlx5e_psp_assoc_del,
+ .key_rotate = mlx5e_psp_key_rotate,
+ .tx_grace_begin = mlx5e_psp_tx_grace_begin,
+ .tx_grace_end = mlx5e_psp_tx_grace_end,
+ .get_stats = mlx5e_psp_get_stats,
};
void mlx5e_psp_unregister(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
index 6b62fef0d9a7..29800050a331 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h
@@ -22,10 +22,17 @@ struct mlx5e_psp_stats {
u64 psp_tx_bytes_drop;
};
+struct mlx5e_psp_tx_snapshot {
+ int num_channels;
+ int num_tc;
+ u64 wqes[];
+};
+
struct mlx5e_psp {
struct psp_dev *psp;
struct psp_dev_caps caps;
struct mlx5e_psp_fs *fs;
+ struct mlx5e_psp_tx_snapshot *tx_snapshot;
atomic_t tx_key_cnt;
atomic_t tx_drop;
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 09f155acb461..5173a0d3f01a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -445,6 +445,7 @@ struct mlx5e_sq_stats {
u64 cqes ____cacheline_aligned_in_smp;
u64 wake;
u64 cqe_err;
+ u64 wqes;
};
struct mlx5e_xdpsq_stats {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index a01ee656a1e7..412ebc160056 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -883,6 +883,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
wmb();
sq->dma_fifo_cc = dma_fifo_cc;
+ stats->wqes += (u16)(sqcc - sq->cc);
sq->cc = sqcc;
netdev_tx_completed_queue(sq->txq, npkts, nbytes);
--
2.47.3
Powered by blists - more mailing lists