net/mlx5: E-Switch, Indirect table infrastructure

Indirect table infrastructure is used to allow fully processing VF tunnel
traffic in hardware. Kernel software model uses two TC rules for such
traffic: UL rep to tunnel device, then tunnel VF rep to destination VF rep.
To implement such pipeline driver needs to program the hardware after
matching on UL rule to overwrite source vport from UL to tunnel VF and
recirculate the packet to the root table to allow matching on the rule
installed on tunnel VF. For this indirect table matches all encapsulated
traffic by tunnel parameters and all other IP traffic is sent to tunnel VF
by the miss rule.

Indirect table API overview:

- mlx5_esw_indir_table_{init|destroy}() - init and destroy opaque indirect
table object.

- mlx5_esw_indir_table_get() - get or create new table according to vport
id and IP version. Table has following pre-created groups: recirculation
group with match on ethertype and VNI (rules that match encapsulated
packets are installed to this group) and forward group with default/miss
rule that forwards to vport of tunnel endpoint VF (rule for regular
non-encapsulated packets).

- mlx5_esw_indir_table_put() - decrease reference to the indirect table and
matching rule (for encapsulated traffic).

- mlx5_esw_indir_table_needed() - check that in_port is an uplink port and
out_port is VF on the same eswitch, verify that the rule is for IP traffic
and source port rewrite functionality can be used.

- mlx5_esw_indir_table_decap_vport() - function returns decap vport of
flow attribute.
Co-developed-by: Dmytro Linkin <dlinkin@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

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

@@ -40,6 +40,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += lag_mp.o lib/geneve.o lib/port_tun.o \
 					en_rep.o en/rep/bond.o en/mod_hdr.o
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
 					en/mapping.o lib/fs_chains.o en/tc_tun.o \
+					esw/indir_table.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
 					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o

drivers/net/ethernet/mellanox/mlx5/core/en_tc.h

@@ -76,6 +76,7 @@ struct mlx5_flow_attr {
 	struct mlx5_flow_table *dest_ft;
 	u8 inner_match_level;
 	u8 outer_match_level;
+	u8 ip_version;
 	u32 flags;
 	union {
 		struct mlx5_esw_flow_attr esw_attr[0];
@@ -83,6 +84,19 @@ struct mlx5_flow_attr {
 	};
 };
 
+struct mlx5_rx_tun_attr {
+	u16 decap_vport;
+	union {
+		__be32 v4;
+		struct in6_addr v6;
+	} src_ip; /* Valid if decap_vport is not zero */
+	union {
+		__be32 v4;
+		struct in6_addr v6;
+	} dst_ip; /* Valid if decap_vport is not zero */
+	u32 vni;
+};
+
 #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16
 #define MLX5E_TC_TABLE_CHAIN_TAG_MASK GENMASK(MLX5E_TC_TABLE_CHAIN_TAG_BITS - 1, 0)
 

drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021 Mellanox Technologies. */
+
+#ifndef __MLX5_ESW_FT_H__
+#define __MLX5_ESW_FT_H__
+
+#ifdef CONFIG_MLX5_CLS_ACT
+
+struct mlx5_esw_indir_table *
+mlx5_esw_indir_table_init(void);
+void
+mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir);
+
+struct mlx5_flow_table *mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
+						 struct mlx5_flow_attr *attr,
+						 struct mlx5_flow_spec *spec,
+						 u16 vport, bool decap);
+void mlx5_esw_indir_table_put(struct mlx5_eswitch *esw,
+			      struct mlx5_flow_attr *attr,
+			      u16 vport, bool decap);
+
+bool
+mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw,
+			    struct mlx5_flow_attr *attr,
+			    u16 vport_num,
+			    struct mlx5_core_dev *dest_mdev);
+
+u16
+mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr);
+
+#else
+/* indir API stubs */
+struct mlx5_esw_indir_table *
+mlx5_esw_indir_table_init(void)
+{
+	return NULL;
+}
+
+void
+mlx5_esw_indir_table_destroy(struct mlx5_esw_indir_table *indir)
+{
+}
+
+static inline struct mlx5_flow_table *
+mlx5_esw_indir_table_get(struct mlx5_eswitch *esw,
+			 struct mlx5_flow_attr *attr,
+			 struct mlx5_flow_spec *spec,
+			 u16 vport, bool decap)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void
+mlx5_esw_indir_table_put(struct mlx5_eswitch *esw,
+			 struct mlx5_flow_attr *attr,
+			 u16 vport, bool decap)
+{
+}
+
+bool
+mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw,
+			    struct mlx5_flow_attr *attr,
+			    u16 vport_num,
+			    struct mlx5_core_dev *dest_mdev)
+{
+	return false;
+}
+
+static inline u16
+mlx5_esw_indir_table_decap_vport(struct mlx5_flow_attr *attr)
+{
+	return 0;
+}
+#endif
+
+#endif /* __MLX5_ESW_FT_H__ */

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -161,6 +161,8 @@ struct mlx5_vport {
 	struct devlink_port *dl_port;
 };
 
+struct mlx5_esw_indir_table;
+
 struct mlx5_eswitch_fdb {
 	union {
 		struct legacy_fdb {
@@ -191,6 +193,8 @@ struct mlx5_eswitch_fdb {
 				struct mutex lock;
 			} vports;
 
+			struct mlx5_esw_indir_table *indir;
+
 		} offloads;
 	};
 	u32 flags;
@@ -418,6 +422,7 @@ struct mlx5_esw_flow_attr {
 		struct mlx5_core_dev *mdev;
 		struct mlx5_termtbl_handle *termtbl;
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
+	struct mlx5_rx_tun_attr *rx_tun_attr;
 	struct mlx5_pkt_reformat *decap_pkt_reformat;
 };
 

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -38,6 +38,7 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "esw/indir_table.h"
 #include "esw/acl/ofld.h"
 #include "rdma.h"
 #include "en.h"
@@ -2342,12 +2343,20 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 
 static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 {
+	struct mlx5_esw_indir_table *indir;
 	int err;
 
 	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.vports.lock);
 	hash_init(esw->fdb_table.offloads.vports.table);
 
+	indir = mlx5_esw_indir_table_init();
+	if (IS_ERR(indir)) {
+		err = PTR_ERR(indir);
+		goto create_indir_err;
+	}
+	esw->fdb_table.offloads.indir = indir;
+
 	err = esw_create_uplink_offloads_acl_tables(esw);
 	if (err)
 		goto create_acl_err;
@@ -2379,6 +2388,8 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 create_offloads_err:
 	esw_destroy_uplink_offloads_acl_tables(esw);
 create_acl_err:
+	mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir);
+create_indir_err:
 	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 	return err;
 }
@@ -2390,6 +2401,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 	esw_destroy_restore_table(esw);
 	esw_destroy_offloads_table(esw);
 	esw_destroy_uplink_offloads_acl_tables(esw);
+	mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir);
 	mutex_destroy(&esw->fdb_table.offloads.vports.lock);
 }