From 1762f132d54200ffa008e86f9f6c96ab4ee3fb71 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:16 +0300
Subject: net/mlx5e: Support IPsec packet offload for RX in switchdev mode

As decryption must be done first, add new prio for IPsec offload in
FDB, and put it just lower than BYPASS prio and higher than TC prio.
Three levels are added for RX. The first one is for ip xfrm policy. SA
table is created in the second level for ip xfrm state. The status
table is created in the last to check the decryption result. If
success, packets continue with the next process, or dropped otherwise.
For now, the set of reg c1 is removed for swtichdev mode, and the
datapath process will be added in the next patch.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/c91063554cf643fb50b99cf093e8a9bf11729de5.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/mlx5/fs.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2cb404c7ea13..6b1fa94f69c8 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -109,6 +109,7 @@ enum mlx5_flow_namespace_type {
 
 enum {
 	FDB_BYPASS_PATH,
+	FDB_CRYPTO_INGRESS,
 	FDB_TC_OFFLOAD,
 	FDB_FT_OFFLOAD,
 	FDB_TC_MISS,
-- 
cgit v1.2.3


From 91bafc638ed4128eaca074fe7e88a5444db14325 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:17 +0300
Subject: net/mlx5e: Handle IPsec offload for RX datapath in switchdev mode

Reuse tun opts bits in reg c1, to pass IPsec obj id to datapath.
As this is only for RX SA and there are only 11 bits, xarray is used
to map IPsec obj id to an index, which is between 1 and 0x7ff, and
replace obj id to write to reg c1.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/43d60fbcc9cd672a97d7e2a2f7fe6a3d9e9a776d.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/rep/tc.c    | 17 +++++-
 .../ethernet/mellanox/mlx5/core/en_accel/ipsec.h   |  2 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         |  7 +++
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c       | 22 +++++++
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.h       |  2 +
 .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 69 ++++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h | 20 +++++++
 include/linux/mlx5/eswitch.h                       |  3 +
 8 files changed, 139 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
index b5c773ffc763..b12fe3c5a258 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c
@@ -715,9 +715,20 @@ void mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
 	uplink_priv = &uplink_rpriv->uplink_priv;
 	ct_priv = uplink_priv->ct_priv;
 
-	if (!mlx5_ipsec_is_rx_flow(cqe) &&
-	    !mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv, zone_restore_id, tunnel_id,
-				 &tc_priv))
+#ifdef CONFIG_MLX5_EN_IPSEC
+	if (!(tunnel_id >> ESW_TUN_OPTS_BITS)) {
+		u32 mapped_id;
+		u32 metadata;
+
+		mapped_id = tunnel_id & ESW_IPSEC_RX_MAPPED_ID_MASK;
+		if (mapped_id &&
+		    !mlx5_esw_ipsec_rx_make_metadata(priv, mapped_id, &metadata))
+			mlx5e_ipsec_offload_handle_rx_skb(priv->netdev, skb, metadata);
+	}
+#endif
+
+	if (!mlx5e_tc_update_skb(cqe, skb, mapping_ctx, reg_c0, ct_priv,
+				 zone_restore_id, tunnel_id, &tc_priv))
 		goto free_skb;
 
 forward:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 578af9d7aef3..168b9600bde3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -210,6 +210,7 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
 	u8 allow_tunnel_mode : 1;
+	struct xarray ipsec_obj_id_map;
 };
 
 struct mlx5e_ipsec {
@@ -256,6 +257,7 @@ struct mlx5e_ipsec_sa_entry {
 	struct mlx5e_ipsec_work *work;
 	struct mlx5e_ipsec_dwork *dwork;
 	struct mlx5e_ipsec_limits limits;
+	u32 rx_mapped_id;
 };
 
 struct mlx5_accel_pol_xfrm_attrs {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 2db16e49abc1..84322e85cd23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1153,6 +1153,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		err = setup_modify_header(ipsec, attrs->type,
 					  sa_entry->ipsec_obj_id | BIT(31),
 					  XFRM_DEV_OFFLOAD_IN, &flow_act);
+	else
+		err = mlx5_esw_ipsec_rx_setup_modify_header(sa_entry, &flow_act);
+
 	if (err)
 		goto err_mod_header;
 
@@ -1641,6 +1644,7 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	}
 
 	mlx5_modify_header_dealloc(mdev, ipsec_rule->modify_hdr);
+	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
 	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
 }
 
@@ -1693,6 +1697,8 @@ void mlx5e_accel_ipsec_fs_cleanup(struct mlx5e_ipsec *ipsec)
 	kfree(ipsec->rx_ipv6);
 
 	if (ipsec->is_uplink_rep) {
+		xa_destroy(&ipsec->rx_esw->ipsec_obj_id_map);
+
 		mutex_destroy(&ipsec->tx_esw->ft.mutex);
 		WARN_ON(ipsec->tx_esw->ft.refcnt);
 		kfree(ipsec->tx_esw);
@@ -1753,6 +1759,7 @@ int mlx5e_accel_ipsec_fs_init(struct mlx5e_ipsec *ipsec)
 		mutex_init(&ipsec->tx_esw->ft.mutex);
 		mutex_init(&ipsec->rx_esw->ft.mutex);
 		ipsec->tx_esw->ns = ns_esw;
+		xa_init_flags(&ipsec->rx_esw->ipsec_obj_id_map, XA_FLAGS_ALLOC1);
 	} else if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ROCE) {
 		ipsec->roce = mlx5_ipsec_fs_roce_init(mdev);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 8d6379ac4574..c00fe0d5ea11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -37,6 +37,7 @@
 #include "ipsec.h"
 #include "ipsec_rxtx.h"
 #include "en.h"
+#include "esw/ipsec_fs.h"
 
 enum {
 	MLX5E_IPSEC_TX_SYNDROME_OFFLOAD = 0x8,
@@ -355,3 +356,24 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome);
 	}
 }
+
+int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	u32 ipsec_obj_id;
+	int err;
+
+	if (!ipsec || !ipsec->is_uplink_rep)
+		return -EINVAL;
+
+	err = mlx5_esw_ipsec_rx_ipsec_obj_id_search(priv, id, &ipsec_obj_id);
+	if (err) {
+		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_sadb_miss);
+		return err;
+	}
+
+	*metadata = MLX5_IPSEC_METADATA_CREATE(ipsec_obj_id,
+					       MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED);
+
+	return 0;
+}
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 436e9a8a32d3..9ee014a8ad24 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
@@ -43,6 +43,7 @@
 #define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
 #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0))
 #define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
+#define MLX5_IPSEC_METADATA_CREATE(id, syndrome) ((id) | ((syndrome) << 24))
 
 struct mlx5e_accel_tx_ipsec_state {
 	struct xfrm_offload *xo;
@@ -67,6 +68,7 @@ void mlx5e_ipsec_handle_tx_wqe(struct mlx5e_tx_wqe *wqe,
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
 				       u32 ipsec_meta_data);
+int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata);
 static inline unsigned int mlx5e_ipsec_tx_ids_len(struct mlx5e_accel_tx_ipsec_state *ipsec_st)
 {
 	return ipsec_st->tailen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 7df7a8b0a6a0..0675587c1a79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -182,3 +182,72 @@ int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 
 	return 0;
 }
+
+int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_act *flow_act)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_modify_hdr *modify_hdr;
+	u32 mapped_id;
+	int err;
+
+	err = xa_alloc_bh(&ipsec->rx_esw->ipsec_obj_id_map, &mapped_id,
+			  xa_mk_value(sa_entry->ipsec_obj_id),
+			  XA_LIMIT(1, ESW_IPSEC_RX_MAPPED_ID_MASK), 0);
+	if (err)
+		return err;
+
+	/* reuse tunnel bits for ipsec,
+	 * tun_id is always 0 and tun_opts is mapped to ipsec_obj_id.
+	 */
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field,
+		 MLX5_ACTION_IN_FIELD_METADATA_REG_C_1);
+	MLX5_SET(set_action_in, action, offset, ESW_ZONE_ID_BITS);
+	MLX5_SET(set_action_in, action, length,
+		 ESW_TUN_ID_BITS + ESW_TUN_OPTS_BITS);
+	MLX5_SET(set_action_in, action, data, mapped_id);
+
+	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB,
+					      1, action);
+	if (IS_ERR(modify_hdr)) {
+		err = PTR_ERR(modify_hdr);
+		goto err_header_alloc;
+	}
+
+	sa_entry->rx_mapped_id = mapped_id;
+	flow_act->modify_hdr = modify_hdr;
+	flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+	return 0;
+
+err_header_alloc:
+	xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map, mapped_id);
+	return err;
+}
+
+void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+
+	if (sa_entry->rx_mapped_id)
+		xa_erase_bh(&ipsec->rx_esw->ipsec_obj_id_map,
+			    sa_entry->rx_mapped_id);
+}
+
+int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+					  u32 *ipsec_obj_id)
+{
+	struct mlx5e_ipsec *ipsec = priv->ipsec;
+	void *val;
+
+	val = xa_load(&ipsec->rx_esw->ipsec_obj_id_map, id);
+	if (!val)
+		return -ENOENT;
+
+	*ipsec_obj_id = xa_to_value(val);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 1d6104648d32..44df34032d1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -5,6 +5,7 @@
 #define __MLX5_ESW_IPSEC_FS_H__
 
 struct mlx5e_ipsec;
+struct mlx5e_ipsec_sa_entry;
 
 #ifdef CONFIG_MLX5_ESWITCH
 void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
@@ -16,6 +17,11 @@ void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx_create_attr *attr);
 int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 					   struct mlx5_flow_destination *dest);
+int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_act *flow_act);
+void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry);
+int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+					  u32 *ipsec_obj_id);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}
@@ -35,5 +41,19 @@ static inline int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ips
 {
 	return -EINVAL;
 }
+
+static inline int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
+							struct mlx5_flow_act *flow_act)
+{
+	return -EINVAL;
+}
+
+static inline void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry) {}
+
+static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
+							u32 *ipsec_obj_id)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index e2701ed0200e..950d2431a53c 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -144,6 +144,9 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
 		ESW_TUN_OPTS_OFFSET + 1)
 
+/* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */
+#define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
+
 u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
 struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw);
-- 
cgit v1.2.3


From c6c2bf5db4ea14b316af1fd03cc6c5c61f751f79 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:19 +0300
Subject: net/mlx5e: Support IPsec packet offload for TX in switchdev mode

The IPsec encryption is done at the last, so add new prio for IPsec
offload in FDB, and put it just lower than the slow path prio and
higher than the per-vport prio.
Three levels are added for TX. The first one is for ip xfrm policy.
The sa table is created in the second level for ip xfrm state. The
status table is created at the last to count the number of packets
encrypted.
The rules, which forward packets to uplink, are changed to forward
them to IPsec TX tables first. These rules are restored after those
tables are destroyed, which is done immediately when there is no
reference to them, just as what does in legacy mode. The support for
slow path is added here, by refreshing uplink's channels. But, the
handling for TC fast path, which is more complicated, will be added
later. Besides, reg c4 is used instead to match reqid.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/cfd0e6ffaf0b8c55ebaa9fb0649b7c504b6b8ec6.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 70 +++++++++++++++++++---
 .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c | 16 +++++
 .../net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h |  5 ++
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  1 +
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 11 ++++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  |  6 ++
 include/linux/mlx5/fs.h                            |  1 +
 7 files changed, 101 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 6d4d2b824b75..36704c9fce33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -10,6 +10,7 @@
 #include "lib/ipsec_fs_roce.h"
 #include "lib/fs_chains.h"
 #include "esw/ipsec_fs.h"
+#include "en_rep.h"
 
 #define NUM_IPSEC_FTE BIT(15)
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
@@ -23,6 +24,7 @@ struct mlx5e_ipsec_fc {
 struct mlx5e_ipsec_tx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
 	struct mlx5e_ipsec_rule status;
 	struct mlx5_flow_namespace *ns;
 	struct mlx5e_ipsec_fc *fc;
@@ -550,7 +552,7 @@ err_rule:
 }
 
 /* IPsec TX flow steering */
-static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
+static void tx_destroy(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		       struct mlx5_ipsec_fs *roce)
 {
 	mlx5_ipsec_fs_roce_tx_destroy(roce);
@@ -562,9 +564,13 @@ static void tx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec_tx *tx,
 		mlx5_destroy_flow_table(tx->ft.pol);
 	}
 
+	if (tx == ipsec->tx_esw) {
+		mlx5_del_flow_rules(tx->sa.rule);
+		mlx5_destroy_flow_group(tx->sa.group);
+	}
 	mlx5_destroy_flow_table(tx->ft.sa);
 	if (tx->allow_tunnel_mode)
-		mlx5_eswitch_unblock_encap(mdev);
+		mlx5_eswitch_unblock_encap(ipsec->mdev);
 	mlx5_del_flow_rules(tx->status.rule);
 	mlx5_destroy_flow_table(tx->ft.status);
 }
@@ -573,6 +579,11 @@ static void ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				     struct mlx5e_ipsec_tx *tx,
 				     struct mlx5e_ipsec_tx_create_attr *attr)
 {
+	if (tx == ipsec->tx_esw) {
+		mlx5_esw_ipsec_tx_create_attr_set(ipsec, attr);
+		return;
+	}
+
 	attr->prio = 0;
 	attr->pol_level = 0;
 	attr->sa_level = 1;
@@ -611,6 +622,15 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	}
 	tx->ft.sa = ft;
 
+	if (tx == ipsec->tx_esw) {
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+		dest.vport.num = MLX5_VPORT_UPLINK;
+		err = ipsec_miss_create(mdev, tx->ft.sa, &tx->sa, &dest);
+		if (err)
+			goto err_sa_miss;
+		memset(&dest, 0, sizeof(dest));
+	}
+
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
 		tx->chains = ipsec_chains_create(
 			mdev, tx->ft.sa, attr.chains_ns, attr.prio, attr.pol_level,
@@ -652,6 +672,11 @@ err_roce:
 		mlx5_destroy_flow_table(tx->ft.pol);
 	}
 err_pol_ft:
+	if (tx == ipsec->tx_esw) {
+		mlx5_del_flow_rules(tx->sa.rule);
+		mlx5_destroy_flow_group(tx->sa.group);
+	}
+err_sa_miss:
 	mlx5_destroy_flow_table(tx->ft.sa);
 err_sa_ft:
 	if (tx->allow_tunnel_mode)
@@ -662,6 +687,25 @@ err_status_rule:
 	return err;
 }
 
+static void ipsec_esw_tx_ft_policy_set(struct mlx5_core_dev *mdev,
+				       struct mlx5_flow_table *ft)
+{
+#ifdef CONFIG_MLX5_ESWITCH
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	struct mlx5e_rep_priv *uplink_rpriv;
+	struct mlx5e_priv *priv;
+
+	esw->offloads.ft_ipsec_tx_pol = ft;
+	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	priv = netdev_priv(uplink_rpriv->netdev);
+	if (!priv->channels.num)
+		return;
+
+	mlx5e_rep_deactivate_channels(priv);
+	mlx5e_rep_activate_channels(priv);
+#endif
+}
+
 static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		  struct mlx5e_ipsec_tx *tx)
 {
@@ -674,6 +718,9 @@ static int tx_get(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
+	if (tx == ipsec->tx_esw)
+		ipsec_esw_tx_ft_policy_set(mdev, tx->ft.pol);
+
 skip:
 	tx->ft.refcnt++;
 	return 0;
@@ -684,7 +731,10 @@ static void tx_put(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx)
 	if (--tx->ft.refcnt)
 		return;
 
-	tx_destroy(ipsec->mdev, tx, ipsec->roce);
+	if (tx == ipsec->tx_esw)
+		ipsec_esw_tx_ft_policy_set(ipsec->mdev, NULL);
+
+	tx_destroy(ipsec, tx, ipsec->roce);
 }
 
 static struct mlx5_flow_table *tx_ft_get_policy(struct mlx5_core_dev *mdev,
@@ -842,15 +892,15 @@ static void setup_fte_reg_a(struct mlx5_flow_spec *spec)
 		 misc_parameters_2.metadata_reg_a, MLX5_ETH_WQE_FT_META_IPSEC);
 }
 
-static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid)
+static void setup_fte_reg_c4(struct mlx5_flow_spec *spec, u32 reqid)
 {
 	/* Pass policy check before choosing this SA */
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
 
-	MLX5_SET(fte_match_param, spec->match_criteria,
-		 misc_parameters_2.metadata_reg_c_0, reqid);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_0, reqid);
+		 misc_parameters_2.metadata_reg_c_4, reqid);
 }
 
 static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec)
@@ -902,7 +952,7 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		MLX5_SET(set_action_in, action, field,
-			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+			 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
 		break;
 	default:
 		return -EINVAL;
@@ -1268,7 +1318,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		break;
 	case XFRM_DEV_OFFLOAD_PACKET:
 		if (attrs->reqid)
-			setup_fte_reg_c0(spec, attrs->reqid);
+			setup_fte_reg_c4(spec, attrs->reqid);
 		err = setup_pkt_reformat(ipsec, attrs, &flow_act);
 		if (err)
 			goto err_pkt_reformat;
@@ -1379,6 +1429,8 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
+	if (tx == ipsec->tx_esw && tx->chains)
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[dstn].ft = tx->ft.sa;
 	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dstn++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 0675587c1a79..e60cd3dc1b13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -12,6 +12,12 @@ enum {
 	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
 };
 
+enum {
+	MLX5_ESW_IPSEC_TX_POL_FT_LEVEL,
+	MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL,
+	MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL,
+};
+
 static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					     struct mlx5e_ipsec_rx *rx)
 {
@@ -251,3 +257,13 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 
 	return 0;
 }
+
+void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_tx_create_attr *attr)
+{
+	attr->prio = FDB_CRYPTO_EGRESS;
+	attr->pol_level = MLX5_ESW_IPSEC_TX_POL_FT_LEVEL;
+	attr->sa_level = MLX5_ESW_IPSEC_TX_ESP_FT_LEVEL;
+	attr->cnt_level = MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL;
+	attr->chains_ns = MLX5_FLOW_NAMESPACE_FDB;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index 44df34032d1e..275684f99ed3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -22,6 +22,8 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry);
 int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 					  u32 *ipsec_obj_id);
+void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_tx_create_attr *attr);
 #else
 static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 						    struct mlx5e_ipsec_rx *rx) {}
@@ -55,5 +57,8 @@ static inline int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv,
 {
 	return -EINVAL;
 }
+
+static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
+						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 2944c9207487..c7b5faae20a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -254,6 +254,7 @@ struct mlx5_esw_offload {
 	struct mlx5_flow_group *vport_rx_group;
 	struct mlx5_flow_group *vport_rx_drop_group;
 	struct mlx5_flow_handle *vport_rx_drop_rule;
+	struct mlx5_flow_table *ft_ipsec_tx_pol;
 	struct xarray vport_reps;
 	struct list_head peer_flows[MLX5_MAX_PORTS];
 	struct mutex peer_mutex;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f83667b4339e..dc22a7f959e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -884,6 +884,17 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
+	if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) {
+		dest.ft = on_esw->offloads.ft_ipsec_tx_pol;
+		flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	} else {
+		dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+		dest.vport.num = rep->vport;
+		dest.vport.vhca_id = MLX5_CAP_GEN(rep->esw->dev, vhca_id);
+		dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+	}
+
 	if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) &&
 	    rep->vport == MLX5_VPORT_UPLINK)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8ae1854d6b73..830ff8480fe1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3015,6 +3015,12 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		goto out_err;
 	}
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_CRYPTO_EGRESS, 3);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	/* We put this priority last, knowing that nothing will get here
 	 * unless explicitly forwarded to. This is possible because the
 	 * slow path tables have catch all rules and nothing gets passed
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 6b1fa94f69c8..c302ec34255b 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -115,6 +115,7 @@ enum {
 	FDB_TC_MISS,
 	FDB_BR_OFFLOAD,
 	FDB_SLOW_PATH,
+	FDB_CRYPTO_EGRESS,
 	FDB_PER_VPORT,
 };
 
-- 
cgit v1.2.3


From c8e350e62fc51f3fda28f166fc402f4fb539f528 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 31 Jul 2023 14:28:24 +0300
Subject: net/mlx5e: Make TC and IPsec offloads mutually exclusive on a netdev

For IPsec packet offload mode, the order of TC offload and IPsec
offload on the same netdevice is not aligned with the order in the
non-offload software. For example, for RX, the software performs TC
first and then IPsec transformation, but the implementation for
offload does that in the opposite way.

To resolve the difference for now, either IPsec offload or TC offload,
not both, is allowed for a specific interface.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/8e2e5e3b0984d785066e8663aaf97b3ba1bb873f.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 84 ++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 47 ++++++++++++
 include/linux/mlx5/driver.h                        |  2 +
 3 files changed, 129 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index f635b5f6e886..9a5b67344277 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1717,12 +1717,68 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	}
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
+static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int err = 0;
+
+	if (esw)
+		down_write(&esw->mode_lock);
+
+	if (mdev->num_block_ipsec) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	mdev->num_block_tc++;
+
+unlock:
+	if (esw)
+		up_write(&esw->mode_lock);
+
+	return err;
+}
+#else
+static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev)
+{
+	if (mdev->num_block_ipsec)
+		return -EBUSY;
+
+	mdev->num_block_tc++;
+	return 0;
+}
+#endif
+
+static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev)
+{
+	mdev->num_block_tc++;
+}
+
 int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
+	int err;
+
+	if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET) {
+		err = mlx5e_ipsec_block_tc_offload(sa_entry->ipsec->mdev);
+		if (err)
+			return err;
+	}
+
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
-		return tx_add_rule(sa_entry);
+		err = tx_add_rule(sa_entry);
+	else
+		err = rx_add_rule(sa_entry);
+
+	if (err)
+		goto err_out;
+
+	return 0;
 
-	return rx_add_rule(sa_entry);
+err_out:
+	if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET)
+		mlx5e_ipsec_unblock_tc_offload(sa_entry->ipsec->mdev);
+	return err;
 }
 
 void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
@@ -1735,6 +1791,9 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	if (ipsec_rule->pkt_reformat)
 		mlx5_packet_reformat_dealloc(mdev, ipsec_rule->pkt_reformat);
 
+	if (sa_entry->attrs.type == XFRM_DEV_OFFLOAD_PACKET)
+		mlx5e_ipsec_unblock_tc_offload(mdev);
+
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT) {
 		tx_ft_put(sa_entry->ipsec, sa_entry->attrs.type);
 		return;
@@ -1747,10 +1806,25 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 {
+	int err;
+
+	err = mlx5e_ipsec_block_tc_offload(pol_entry->ipsec->mdev);
+	if (err)
+		return err;
+
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
-		return tx_add_policy(pol_entry);
+		err = tx_add_policy(pol_entry);
+	else
+		err = rx_add_policy(pol_entry);
+
+	if (err)
+		goto err_out;
+
+	return 0;
 
-	return rx_add_policy(pol_entry);
+err_out:
+	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
+	return err;
 }
 
 void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
@@ -1760,6 +1834,8 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 
 	mlx5_del_flow_rules(ipsec_rule->rule);
 
+	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
+
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
 		rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family,
 				 pol_entry->attrs.prio, pol_entry->attrs.type);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dfd282319753..7d2a029e0932 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4606,6 +4606,46 @@ static bool is_flow_rule_duplicate_allowed(struct net_device *dev,
 	return netif_is_lag_port(dev) && rpriv && rpriv->rep->vport != MLX5_VPORT_UPLINK;
 }
 
+/* As IPsec and TC order is not aligned between software and hardware-offload,
+ * either IPsec offload or TC offload, not both, is allowed for a specific interface.
+ */
+static bool is_tc_ipsec_order_check_needed(struct net_device *filter, struct mlx5e_priv *priv)
+{
+	if (!IS_ENABLED(CONFIG_MLX5_EN_IPSEC))
+		return false;
+
+	if (filter != priv->netdev)
+		return false;
+
+	if (mlx5e_eswitch_vf_rep(priv->netdev))
+		return false;
+
+	return true;
+}
+
+static int mlx5e_tc_block_ipsec_offload(struct net_device *filter, struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (!is_tc_ipsec_order_check_needed(filter, priv))
+		return 0;
+
+	if (mdev->num_block_tc)
+		return -EBUSY;
+
+	mdev->num_block_ipsec++;
+
+	return 0;
+}
+
+static void mlx5e_tc_unblock_ipsec_offload(struct net_device *filter, struct mlx5e_priv *priv)
+{
+	if (!is_tc_ipsec_order_check_needed(filter, priv))
+		return;
+
+	priv->mdev->num_block_ipsec--;
+}
+
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct flow_cls_offload *f, unsigned long flags)
 {
@@ -4618,6 +4658,10 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	if (!mlx5_esw_hold(priv->mdev))
 		return -EBUSY;
 
+	err = mlx5e_tc_block_ipsec_offload(dev, priv);
+	if (err)
+		goto esw_release;
+
 	mlx5_esw_get(priv->mdev);
 
 	rcu_read_lock();
@@ -4663,7 +4707,9 @@ rcu_unlock:
 err_free:
 	mlx5e_flow_put(priv, flow);
 out:
+	mlx5e_tc_unblock_ipsec_offload(dev, priv);
 	mlx5_esw_put(priv->mdev);
+esw_release:
 	mlx5_esw_release(priv->mdev);
 	return err;
 }
@@ -4704,6 +4750,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	trace_mlx5e_delete_flower(f);
 	mlx5e_flow_put(priv, flow);
 
+	mlx5e_tc_unblock_ipsec_offload(dev, priv);
 	mlx5_esw_put(priv->mdev);
 	return 0;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f21703fb75fd..fa70c25423b2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -806,6 +806,8 @@ struct mlx5_core_dev {
 	u32                      vsc_addr;
 	struct mlx5_hv_vhca	*hv_vhca;
 	struct mlx5_thermal	*thermal;
+	u64			num_block_tc;
+	u64			num_block_ipsec;
 };
 
 struct mlx5_db {
-- 
cgit v1.2.3