Message-ID: <20250625135210.2975231-17-daniel.zahka@gmail.com>
Date: Wed, 25 Jun 2025 06:52:06 -0700
From: Daniel Zahka <daniel.zahka@...il.com>
To: Donald Hunter <donald.hunter@...il.com>,
	Jakub Kicinski <kuba@...nel.org>,
	"David S. Miller" <davem@...emloft.net>,
	Eric Dumazet <edumazet@...gle.com>,
	Paolo Abeni <pabeni@...hat.com>,
	Simon Horman <horms@...nel.org>,
	Jonathan Corbet <corbet@....net>,
	Andrew Lunn <andrew+netdev@...n.ch>
Cc: Saeed Mahameed <saeedm@...dia.com>,
	Leon Romanovsky <leon@...nel.org>,
	Tariq Toukan <tariqt@...dia.com>,
	Boris Pismenny <borisp@...dia.com>,
	Kuniyuki Iwashima <kuniyu@...gle.com>,
	Willem de Bruijn <willemb@...gle.com>,
	David Ahern <dsahern@...nel.org>,
	Neal Cardwell <ncardwell@...gle.com>,
	Patrisious Haddad <phaddad@...dia.com>,
	Raed Salem <raeds@...dia.com>,
	Jianbo Liu <jianbol@...dia.com>,
	Dragos Tatulea <dtatulea@...dia.com>,
	Rahul Rameshbabu <rrameshbabu@...dia.com>,
	Stanislav Fomichev <sdf@...ichev.me>,
	Toke Høiland-Jørgensen <toke@...hat.com>,
	Alexander Lobakin <aleksander.lobakin@...el.com>,
	Jacob Keller <jacob.e.keller@...el.com>,
	netdev@...r.kernel.org
Subject: [PATCH v2 16/17] net/mlx5e: Add Rx data path offload

From: Raed Salem <raeds@...dia.com>

On receive flow inspect received packets for PSP offload indication using
the cqe, for PSP offloaded packets set SKB PSP metadata i.e spi, header
length and key generation number to stack for further processing.

Signed-off-by: Raed Salem <raeds@...dia.com>
Signed-off-by: Rahul Rameshbabu <rrameshbabu@...dia.com>
Signed-off-by: Daniel Zahka <daniel.zahka@...il.com>
---

Notes:
    v2:
    - fill out new pse::dev_id field in psp_rcv()
    v1:
    - https://lore.kernel.org/netdev/20240510030435.120935-15-kuba@kernel.org/

 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h  |  2 +-
 .../mellanox/mlx5/core/en_accel/psp_rxtx.c    | 81 +++++++++++++++++++
 .../mellanox/mlx5/core/en_accel/psp_rxtx.h    | 29 +++++++
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 50 +++++++++---
 4 files changed, 149 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 3cc640669247..45b0d19e735c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -40,7 +40,7 @@
 #include "en/txrx.h"
 
 /* Bit31: IPsec marker, Bit30: reserved, Bit29-24: IPsec syndrome, Bit23-0: IPsec obj id */
-#define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
+#define MLX5_IPSEC_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3) == 0x2)
 #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0))
 #define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
index 7ed59546db4e..86f21ac1ef63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c
@@ -15,6 +15,12 @@
 #include "en_accel/psp.h"
 #include "lib/psp_defs.h"
 
+enum {
+	MLX5E_PSP_OFFLOAD_RX_SYNDROME_DECRYPTED,
+	MLX5E_PSP_OFFLOAD_RX_SYNDROME_AUTH_FAILED,
+	MLX5E_PSP_OFFLOAD_RX_SYNDROME_BAD_TRAILER,
+};
+
 static void mlx5e_psp_set_swp(struct sk_buff *skb,
 			      struct mlx5e_accel_tx_psp_state *psp_st,
 			      struct mlx5_wqe_eth_seg *eseg)
@@ -114,6 +120,81 @@ static bool mlx5e_psp_set_state(struct mlx5e_priv *priv,
 	return ret;
 }
 
+void mlx5e_psp_csum_complete(struct net_device *netdev, struct sk_buff *skb)
+{
+	pskb_trim(skb, skb->len - PSP_TRL_SIZE);
+}
+
+/* Receive handler for PSP packets.
+ *
+ * Presently it accepts only already-authenticated packets and does not
+ * support optional fields, such as virtualization cookies.
+ */
+static int psp_rcv(struct sk_buff *skb, u16 dev_id)
+{
+	const struct psphdr *psph;
+	int depth = 0, end_depth;
+	struct psp_skb_ext *pse;
+	struct ipv6hdr *ipv6h;
+	struct ethhdr *eth;
+	__be16 proto;
+	u32 spi;
+
+	eth = (struct ethhdr *)(skb->data);
+	proto = __vlan_get_protocol(skb, eth->h_proto, &depth);
+	if (proto != htons(ETH_P_IPV6))
+		return -EINVAL;
+
+	ipv6h = (struct ipv6hdr *)(skb->data + depth);
+	depth += sizeof(*ipv6h);
+	end_depth = depth + sizeof(struct udphdr) + sizeof(struct psphdr);
+
+	if (unlikely(end_depth > skb_headlen(skb)))
+		return -EINVAL;
+
+	pse = skb_ext_add(skb, SKB_EXT_PSP);
+	if (!pse)
+		return -EINVAL;
+
+	psph = (const struct psphdr *)(skb->data + depth + sizeof(struct udphdr));
+	pse->spi = psph->spi;
+	pse->dev_id = dev_id;
+	spi = ntohl(psph->spi);
+	pse->generation = 0;
+	pse->version = FIELD_GET(PSPHDR_VERFL_VERSION, psph->verfl);
+
+	ipv6h->nexthdr = psph->nexthdr;
+	ipv6h->payload_len =
+		htons(ntohs(ipv6h->payload_len) - PSP_ENCAP_HLEN - PSP_TRL_SIZE);
+
+	memmove(skb->data + PSP_ENCAP_HLEN, skb->data, depth);
+	skb_pull(skb, PSP_ENCAP_HLEN);
+
+	return 0;
+}
+
+bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+				     struct mlx5_cqe64 *cqe)
+{
+	u32 psp_meta_data = be32_to_cpu(cqe->ft_metadata);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	u16 dev_id = priv->psp->psp->id;
+
+	/* TBD: report errors as SW counters to ethtool, any further handling ? */
+	if (MLX5_PSP_METADATA_SYNDROM(psp_meta_data) != MLX5E_PSP_OFFLOAD_RX_SYNDROME_DECRYPTED)
+		goto drop;
+
+	if (psp_rcv(skb, dev_id))
+		goto drop;
+
+	skb->decrypted = 1;
+	return false;
+
+drop:
+	kfree_skb(skb);
+	return true;
+}
+
 void mlx5e_psp_tx_build_eseg(struct mlx5e_priv *priv, struct sk_buff *skb,
 			     struct mlx5e_accel_tx_psp_state *psp_st,
 			     struct mlx5_wqe_eth_seg *eseg)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
index 521b2c3620e6..e3cf34bafc24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.h
@@ -10,6 +10,11 @@
 #include "en.h"
 #include "en/txrx.h"
 
+/* Bit30: PSP marker, Bit29-23: PSP syndrome, Bit22-0: PSP obj id */
+#define MLX5_PSP_METADATA_MARKER(metadata)  ((((metadata) >> 30) & 0x3) == 0x3)
+#define MLX5_PSP_METADATA_SYNDROM(metadata) (((metadata) >> 23) & GENMASK(6, 0))
+#define MLX5_PSP_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(22, 0))
+
 struct mlx5e_accel_tx_psp_state {
 	u32 tailen;
 	u32 keyid;
@@ -75,6 +80,16 @@ static inline unsigned int mlx5e_psp_tx_ids_len(struct mlx5e_accel_tx_psp_state
 {
 	return psp_st->tailen;
 }
+
+static inline bool mlx5e_psp_is_rx_flow(struct mlx5_cqe64 *cqe)
+{
+	return MLX5_PSP_METADATA_MARKER(be32_to_cpu(cqe->ft_metadata));
+}
+
+bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+				     struct mlx5_cqe64 *cqe);
+
+void mlx5e_psp_csum_complete(struct net_device *netdev, struct sk_buff *skb);
 #else
 static inline bool mlx5e_psp_is_offload_state(struct mlx5e_accel_tx_psp_state *psp_state)
 {
@@ -92,5 +107,19 @@ static inline bool mlx5e_psp_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struc
 {
 	return false;
 }
+
+static inline bool mlx5e_psp_is_rx_flow(struct mlx5_cqe64 *cqe)
+{
+	return false;
+}
+
+static inline bool mlx5e_psp_offload_handle_rx_skb(struct net_device *netdev,
+						   struct sk_buff *skb,
+						   struct mlx5_cqe64 *cqe)
+{
+	return false;
+}
+
+static inline void mlx5e_psp_csum_complete(struct net_device *netdev, struct sk_buff *skb) { }
 #endif /* CONFIG_MLX5_EN_PSP */
 #endif /* __MLX5E_PSP_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 2bb32082bfcc..4456971eba8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -51,6 +51,7 @@
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec.h"
 #include "en_accel/macsec.h"
+#include "en_accel/psp_rxtx.h"
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ktls_txrx.h"
 #include "en/xdp.h"
@@ -1518,6 +1519,12 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
 
+		if (unlikely(mlx5e_psp_is_rx_flow(cqe))) {
+			/* TBD: PSP csum complete corrections for now chose csum_unnecessary path */
+			mlx5e_psp_csum_complete(netdev, skb);
+			goto csum_unnecessary;
+		}
+
 		if (test_bit(MLX5E_RQ_STATE_CSUM_FULL, &rq->state))
 			return; /* CQE csum covers all received bytes */
 
@@ -1546,7 +1553,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 
 #define MLX5E_CE_BIT_MASK 0x80
 
-static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
+static inline bool mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 				      u32 cqe_bcnt,
 				      struct mlx5e_rq *rq,
 				      struct sk_buff *skb)
@@ -1560,6 +1567,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	if (unlikely(get_cqe_tls_offload(cqe)))
 		mlx5e_ktls_handle_rx_skb(rq, skb, cqe, &cqe_bcnt);
 
+	if (unlikely(mlx5e_psp_is_rx_flow(cqe))) {
+		if (mlx5e_psp_offload_handle_rx_skb(netdev, skb, cqe))
+			return true;
+	}
+
 	if (unlikely(mlx5_ipsec_is_rx_flow(cqe)))
 		mlx5e_ipsec_offload_handle_rx_skb(netdev, skb,
 						  be32_to_cpu(cqe->ft_metadata));
@@ -1603,9 +1615,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 
 	if (unlikely(mlx5e_skb_is_multicast(skb)))
 		stats->mcast_packets++;
+
+	return false;
 }
 
-static void mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
+static bool mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct mlx5_cqe64 *cqe,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
@@ -1615,16 +1629,20 @@ static void mlx5e_shampo_complete_rx_cqe(struct mlx5e_rq *rq,
 	stats->packets++;
 	stats->bytes += cqe_bcnt;
 	if (NAPI_GRO_CB(skb)->count != 1)
-		return;
-	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
+		return false;
+
+	if (mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb))
+		return true;
+
 	skb_reset_network_header(skb);
 	if (!skb_flow_dissect_flow_keys(skb, &rq->hw_gro_data->fk, 0)) {
 		napi_gro_receive(rq->cq.napi, skb);
 		rq->hw_gro_data->skb = NULL;
 	}
+	return false;
 }
 
-static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
+static inline bool mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 					 struct mlx5_cqe64 *cqe,
 					 u32 cqe_bcnt,
 					 struct sk_buff *skb)
@@ -1633,7 +1651,7 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	stats->packets++;
 	stats->bytes += cqe_bcnt;
-	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
+	return mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
 }
 
 static inline
@@ -1850,7 +1868,8 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto wq_cyc_pop;
 	}
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto wq_cyc_pop;
 
 	if (mlx5e_cqe_regb_chain(cqe))
 		if (!mlx5e_tc_update_skb_nic(cqe, skb)) {
@@ -1897,7 +1916,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		goto wq_cyc_pop;
 	}
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto wq_cyc_pop;
 
 	if (rep->vlan && skb_vlan_tag_present(skb))
 		skb_vlan_pop(skb);
@@ -1946,7 +1966,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64
 	if (!skb)
 		goto mpwrq_cqe_out;
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto mpwrq_cqe_out;
 
 	mlx5e_rep_tc_receive(cqe, rq, skb);
 
@@ -2383,7 +2404,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 		stats->hds_nosplit_bytes += data_bcnt;
 	}
 
-	mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
+	if (mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb)) {
+		*skb = NULL;
+		goto free_hd_entry;
+	}
 	if (flush && rq->hw_gro_data->skb)
 		mlx5e_shampo_flush_skb(rq, cqe, match);
 free_hd_entry:
@@ -2441,7 +2465,8 @@ static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cq
 	if (!skb)
 		goto mpwrq_cqe_out;
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto mpwrq_cqe_out;
 
 	if (mlx5e_cqe_regb_chain(cqe))
 		if (!mlx5e_tc_update_skb_nic(cqe, skb)) {
@@ -2774,7 +2799,8 @@ static void mlx5e_trap_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe
 	if (!skb)
 		goto wq_cyc_pop;
 
-	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	if (mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb))
+		goto wq_cyc_pop;
 	skb_push(skb, ETH_HLEN);
 
 	mlx5_devlink_trap_report(rq->mdev, trap_id, skb,
-- 
2.47.1

Powered by blists - more mailing lists