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 <[email protected]>
Signed-off-by: Leon Romanovsky <[email protected]>
Link: https://lore.kernel.org/r/c91063554cf643fb50b99cf093e8a9bf11729de5.1690802064.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <[email protected]>

Author: Jianbo Liu

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -75,6 +75,10 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/acl/helper.o \
 				      esw/acl/egress_lgcy.o esw/acl/egress_ofld.o \
 				      esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o
 
+ifneq ($(CONFIG_MLX5_EN_IPSEC),)
+	mlx5_core-$(CONFIG_MLX5_ESWITCH)   += esw/ipsec_fs.o
+endif
+
 mlx5_core-$(CONFIG_MLX5_BRIDGE)    += esw/bridge.o esw/bridge_mcast.o esw/bridge_debugfs.o \
 				      en/rep/bridge.o
 

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h

@@ -143,7 +143,7 @@ struct mlx5e_ipsec_sw_stats {
 	atomic64_t ipsec_tx_drop_trailer;
 };
 
-struct mlx5e_ipsec_rx;
+struct mlx5e_ipsec_fc;
 struct mlx5e_ipsec_tx;
 
 struct mlx5e_ipsec_work {
@@ -180,6 +180,38 @@ struct mlx5e_ipsec_rx_create_attr {
 	enum mlx5_flow_namespace_type chains_ns;
 };
 
+struct mlx5e_ipsec_ft {
+	struct mutex mutex; /* Protect changes to this struct */
+	struct mlx5_flow_table *pol;
+	struct mlx5_flow_table *sa;
+	struct mlx5_flow_table *status;
+	u32 refcnt;
+};
+
+struct mlx5e_ipsec_rule {
+	struct mlx5_flow_handle *rule;
+	struct mlx5_modify_hdr *modify_hdr;
+	struct mlx5_pkt_reformat *pkt_reformat;
+	struct mlx5_fc *fc;
+};
+
+struct mlx5e_ipsec_miss {
+	struct mlx5_flow_group *group;
+	struct mlx5_flow_handle *rule;
+};
+
+struct mlx5e_ipsec_rx {
+	struct mlx5e_ipsec_ft ft;
+	struct mlx5e_ipsec_miss pol;
+	struct mlx5e_ipsec_miss sa;
+	struct mlx5e_ipsec_rule status;
+	struct mlx5e_ipsec_miss status_drop;
+	struct mlx5_fc *status_drop_cnt;
+	struct mlx5e_ipsec_fc *fc;
+	struct mlx5_fs_chains *chains;
+	u8 allow_tunnel_mode : 1;
+};
+
 struct mlx5e_ipsec {
 	struct mlx5_core_dev *mdev;
 	struct xarray sadb;
@@ -205,13 +237,6 @@ struct mlx5e_ipsec_esn_state {
 	u8 overlap: 1;
 };
 
-struct mlx5e_ipsec_rule {
-	struct mlx5_flow_handle *rule;
-	struct mlx5_modify_hdr *modify_hdr;
-	struct mlx5_pkt_reformat *pkt_reformat;
-	struct mlx5_fc *fc;
-};
-
 struct mlx5e_ipsec_limits {
 	u64 round;
 	u8 soft_limit_hit : 1;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c

@@ -9,6 +9,7 @@
 #include "fs_core.h"
 #include "lib/ipsec_fs_roce.h"
 #include "lib/fs_chains.h"
+#include "esw/ipsec_fs.h"
 
 #define NUM_IPSEC_FTE BIT(15)
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
@@ -19,29 +20,6 @@ struct mlx5e_ipsec_fc {
 	struct mlx5_fc *drop;
 };
 
-struct mlx5e_ipsec_ft {
-	struct mutex mutex; /* Protect changes to this struct */
-	struct mlx5_flow_table *pol;
-	struct mlx5_flow_table *sa;
-	struct mlx5_flow_table *status;
-	u32 refcnt;
-};
-
-struct mlx5e_ipsec_miss {
-	struct mlx5_flow_group *group;
-	struct mlx5_flow_handle *rule;
-};
-
-struct mlx5e_ipsec_rx {
-	struct mlx5e_ipsec_ft ft;
-	struct mlx5e_ipsec_miss pol;
-	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_fc *fc;
-	struct mlx5_fs_chains *chains;
-	u8 allow_tunnel_mode : 1;
-};
-
 struct mlx5e_ipsec_tx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
@@ -259,9 +237,9 @@ static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family)
 static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		       struct mlx5e_ipsec_rx *rx, u32 family)
 {
-
 	/* disconnect */
-	ipsec_rx_ft_disconnect(ipsec, family);
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_disconnect(ipsec, family);
 
 	if (rx->chains) {
 		ipsec_chains_destroy(rx->chains);
@@ -276,8 +254,12 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_destroy_flow_table(rx->ft.sa);
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
+	if (rx == ipsec->rx_esw) {
+		mlx5_esw_ipsec_rx_status_destroy(ipsec, rx);
+	} else {
+		mlx5_del_flow_rules(rx->status.rule);
+		mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
+	}
 	mlx5_destroy_flow_table(rx->ft.status);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family);
@@ -288,6 +270,13 @@ static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				     u32 family,
 				     struct mlx5e_ipsec_rx_create_attr *attr)
 {
+	if (rx == ipsec->rx_esw) {
+		/* For packet offload in switchdev mode, RX & TX use FDB namespace */
+		attr->ns = ipsec->tx_esw->ns;
+		mlx5_esw_ipsec_rx_create_attr_set(ipsec, attr);
+		return;
+	}
+
 	attr->ns = mlx5e_fs_get_ns(ipsec->fs, false);
 	attr->ttc = mlx5e_fs_get_ttc(ipsec->fs, false);
 	attr->family = family;
@@ -306,6 +295,9 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 	struct mlx5_flow_table *ft;
 	int err;
 
+	if (rx == ipsec->rx_esw)
+		return mlx5_esw_ipsec_rx_status_pass_dest_get(ipsec, dest);
+
 	*dest = mlx5_ttc_get_default_dest(attr->ttc, family2tt(attr->family));
 	err = mlx5_ipsec_fs_roce_rx_create(ipsec->mdev, ipsec->roce, attr->ns, dest,
 					   attr->family, MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
@@ -357,7 +349,10 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter_id = mlx5_fc_id(rx->fc->cnt);
-	err = ipsec_status_rule(mdev, rx, dest);
+	if (rx == ipsec->rx_esw)
+		err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest);
+	else
+		err = ipsec_status_rule(mdev, rx, dest);
 	if (err)
 		goto err_add;
 
@@ -406,7 +401,8 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 
 connect:
 	/* connect */
-	ipsec_rx_ft_connect(ipsec, rx, &attr);
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_connect(ipsec, rx, &attr);
 	return 0;
 
 err_pol_miss:
@@ -864,18 +860,22 @@ static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upsp
 	}
 }
 
-static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec, u8 dir)
+static enum mlx5_flow_namespace_type ipsec_fs_get_ns(struct mlx5e_ipsec *ipsec,
+						     int type, u8 dir)
 {
+	if (ipsec->is_uplink_rep && type == XFRM_DEV_OFFLOAD_PACKET)
+		return MLX5_FLOW_NAMESPACE_FDB;
+
 	if (dir == XFRM_DEV_OFFLOAD_IN)
 		return MLX5_FLOW_NAMESPACE_KERNEL;
 
 	return MLX5_FLOW_NAMESPACE_EGRESS;
 }
 
-static int setup_modify_header(struct mlx5e_ipsec *ipsec, u32 val, u8 dir,
+static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8 dir,
 			       struct mlx5_flow_act *flow_act)
 {
-	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, dir);
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, type, dir);
 	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_modify_hdr *modify_hdr;
@@ -1085,7 +1085,8 @@ static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 			      struct mlx5_accel_esp_xfrm_attrs *attrs,
 			      struct mlx5_flow_act *flow_act)
 {
-	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->dir);
+	enum mlx5_flow_namespace_type ns_type = ipsec_fs_get_ns(ipsec, attrs->type,
+								attrs->dir);
 	struct mlx5_pkt_reformat_params reformat_params = {};
 	struct mlx5_core_dev *mdev = ipsec->mdev;
 	struct mlx5_pkt_reformat *pkt_reformat;
@@ -1127,7 +1128,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_flow_spec *spec;
 	struct mlx5e_ipsec_rx *rx;
 	struct mlx5_fc *counter;
-	int err;
+	int err = 0;
 
 	rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type);
 	if (IS_ERR(rx))
@@ -1148,8 +1149,10 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
 
-	err = setup_modify_header(ipsec, sa_entry->ipsec_obj_id | BIT(31),
-				  XFRM_DEV_OFFLOAD_IN, &flow_act);
+	if (rx != ipsec->rx_esw)
+		err = setup_modify_header(ipsec, attrs->type,
+					  sa_entry->ipsec_obj_id | BIT(31),
+					  XFRM_DEV_OFFLOAD_IN, &flow_act);
 	if (err)
 		goto err_mod_header;
 
@@ -1340,7 +1343,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		if (!attrs->reqid)
 			break;
 
-		err = setup_modify_header(ipsec, attrs->reqid,
+		err = setup_modify_header(ipsec, attrs->type, attrs->reqid,
 					  XFRM_DEV_OFFLOAD_OUT, &flow_act);
 		if (err)
 			goto err_mod_header;
@@ -1388,6 +1391,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 {
 	struct mlx5_accel_pol_xfrm_attrs *attrs = &pol_entry->attrs;
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_pol2dev(pol_entry);
+	struct mlx5e_ipsec *ipsec = pol_entry->ipsec;
 	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
@@ -1433,6 +1437,8 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
+	if (rx == ipsec->rx_esw && rx->chains)
+		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[dstn].ft = rx->ft.sa;
 	dstn++;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c

@@ -45,8 +45,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
 			caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
-		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
-		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level))
+		if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+		     MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+		    MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
 			caps |= MLX5_IPSEC_CAP_PRIO;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,