Merge branch 'mlx5-next' into wip/leon-for-next

Mark Bloch Says:
================
Expose steering anchor

Expose a steering anchor per priority to allow users to re-inject
packets back into default NIC pipeline for additional processing.

MLX5_IB_METHOD_STEERING_ANCHOR_CREATE returns a flow table ID which
a user can use to re-inject packets at a specific priority.

A FTE (flow table entry) can be created and the flow table ID
used as a destination.

When a packet is taken into a RDMA-controlled steering domain (like
software steering) there may be a need to insert the packet back into
the default NIC pipeline. This exposes a flow table ID to the user that can
be used as a destination in a flow table entry.

With this new method priorities that are exposed to users via
MLX5_IB_METHOD_FLOW_MATCHER_CREATE can be reached from a non-zero UID.

As user-created flow tables (via RDMA DEVX) are created with a non-zero UID
thus it's impossible to point to a NIC core flow table (core driver flow tables
are created with UID value of zero) from userspace.
Create flow tables that are exposed to users with the shared UID, this
allows users to point to default NIC flow tables.

Steering loops are prevented at FW level as FW enforces that no flow
table at level X can point to a table at level lower than X.

================

Link: https://lore.kernel.org/all/20220703205407.110890-1-saeed@kernel.orgSigned-off-by: Leon Romanovsky <leon@kernel.org>

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

@@ -50,10 +50,12 @@ static int mlx5_cmd_stub_update_root_ft(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_stub_create_flow_table(struct mlx5_flow_root_namespace *ns,
 					   struct mlx5_flow_table *ft,
-					   unsigned int size,
+					   struct mlx5_flow_table_attr *ft_attr,
 					   struct mlx5_flow_table *next_ft)
 {
-	ft->max_fte = size ? roundup_pow_of_two(size) : 1;
+	int max_fte = ft_attr->max_fte;
+
+	ft->max_fte = max_fte ? roundup_pow_of_two(max_fte) : 1;
 
 	return 0;
 }
@@ -258,7 +260,7 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
-				      unsigned int size,
+				      struct mlx5_flow_table_attr *ft_attr,
 				      struct mlx5_flow_table *next_ft)
 {
 	int en_encap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
@@ -267,17 +269,19 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {};
 	struct mlx5_core_dev *dev = ns->dev;
+	unsigned int size;
 	int err;
 
-	if (size != POOL_NEXT_SIZE)
-		size = roundup_pow_of_two(size);
-	size = mlx5_ft_pool_get_avail_sz(dev, ft->type, size);
+	if (ft_attr->max_fte != POOL_NEXT_SIZE)
+		size = roundup_pow_of_two(ft_attr->max_fte);
+	size = mlx5_ft_pool_get_avail_sz(dev, ft->type, ft_attr->max_fte);
 	if (!size)
 		return -ENOSPC;
 
 	MLX5_SET(create_flow_table_in, in, opcode,
 		 MLX5_CMD_OP_CREATE_FLOW_TABLE);
 
+	MLX5_SET(create_flow_table_in, in, uid, ft_attr->uid);
 	MLX5_SET(create_flow_table_in, in, table_type, ft->type);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level);
 	MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, size ? ilog2(size) : 0);

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

@@ -38,7 +38,7 @@
 struct mlx5_flow_cmds {
 	int (*create_flow_table)(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_table *ft,
-				 unsigned int size,
+				 struct mlx5_flow_table_attr *ft_attr,
 				 struct mlx5_flow_table *next_ft);
 	int (*destroy_flow_table)(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft);

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

@@ -1155,7 +1155,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 			      find_next_chained_ft(fs_prio);
 	ft->def_miss_action = ns->def_miss_action;
 	ft->ns = ns;
-	err = root->cmds->create_flow_table(root, ft, ft_attr->max_fte, next_ft);
+	err = root->cmds->create_flow_table(root, ft, ft_attr, next_ft);
 	if (err)
 		goto free_ft;
 
@@ -1195,6 +1195,12 @@ struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns,
 }
 EXPORT_SYMBOL(mlx5_create_flow_table);
 
+u32 mlx5_flow_table_id(struct mlx5_flow_table *ft)
+{
+	return ft->id;
+}
+EXPORT_SYMBOL(mlx5_flow_table_id);
+
 struct mlx5_flow_table *
 mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns,
 			     struct mlx5_flow_table_attr *ft_attr, u16 vport)

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c

@@ -439,6 +439,7 @@ int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
 	MLX5_SET(create_flow_table_in, in, table_type, attr->table_type);
+	MLX5_SET(create_flow_table_in, in, uid, attr->uid);
 
 	ft_mdev = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
 	MLX5_SET(flow_table_context, ft_mdev, termination_table, attr->term_tbl);

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c

@@ -214,7 +214,7 @@ static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl)
 					     tbl->table_type);
 }
 
-static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
+static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl, u16 uid)
 {
 	bool en_encap = !!(tbl->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT);
 	bool en_decap = !!(tbl->flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
@@ -236,6 +236,7 @@ static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
 	ft_attr.sw_owner = true;
 	ft_attr.decap_en = en_decap;
 	ft_attr.reformat_en = en_encap;
+	ft_attr.uid = uid;
 
 	ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev, &ft_attr,
 					   NULL, &tbl->table_id);
@@ -243,7 +244,8 @@ static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
 	return ret;
 }
 
-struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level, u32 flags)
+struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level,
+					 u32 flags, u16 uid)
 {
 	struct mlx5dr_table *tbl;
 	int ret;
@@ -263,7 +265,7 @@ struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level, u
 	if (ret)
 		goto free_tbl;
 
-	ret = dr_table_create_sw_owned_tbl(tbl);
+	ret = dr_table_create_sw_owned_tbl(tbl, uid);
 	if (ret)
 		goto uninit_tbl;
 

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h

@@ -1200,6 +1200,7 @@ struct mlx5dr_cmd_query_flow_table_details {
 
 struct mlx5dr_cmd_create_flow_table_attr {
 	u32 table_type;
+	u16 uid;
 	u64 icm_addr_rx;
 	u64 icm_addr_tx;
 	u8 level;

drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c

@@ -62,7 +62,7 @@ static int set_miss_action(struct mlx5_flow_root_namespace *ns,
 
 static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 					 struct mlx5_flow_table *ft,
-					 unsigned int size,
+					 struct mlx5_flow_table_attr *ft_attr,
 					 struct mlx5_flow_table *next_ft)
 {
 	struct mlx5dr_table *tbl;
@@ -71,7 +71,7 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 
 	if (mlx5_dr_is_fw_table(ft->flags))
 		return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
-								    size,
+								    ft_attr,
 								    next_ft);
 	flags = ft->flags;
 	/* turn off encap/decap if not supported for sw-str by fw */
@@ -79,7 +79,8 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 		flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				      MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags);
+	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags,
+				  ft_attr->uid);
 	if (!tbl) {
 		mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
 		return -EINVAL;

drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h

@@ -51,7 +51,8 @@ void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn);
 
 struct mlx5dr_table *
-mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags);
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags,
+		    u16 uid);
 
 struct mlx5dr_table *
 mlx5dr_table_get_from_fs_ft(struct mlx5_flow_table *ft);

include/linux/mlx5/fs.h

@@ -178,6 +178,7 @@ struct mlx5_flow_table_attr {
 	int max_fte;
 	u32 level;
 	u32 flags;
+	u16 uid;
 	struct mlx5_flow_table *next_ft;
 
 	struct {
@@ -315,4 +316,5 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
 void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
 				  struct mlx5_pkt_reformat *reformat);
 
+u32 mlx5_flow_table_id(struct mlx5_flow_table *ft);
 #endif

include/linux/mlx5/mlx5_ifc.h

@@ -1371,7 +1371,9 @@ enum {
 };
 
 struct mlx5_ifc_cmd_hca_cap_bits {
-	u8         reserved_at_0[0x1f];
+	u8         reserved_at_0[0x10];
+	u8         shared_object_to_user_object_allowed[0x1];
+	u8         reserved_at_13[0xe];
 	u8         vhca_resource_manager[0x1];
 
 	u8         hca_cap_2[0x1];
@@ -8507,7 +8509,7 @@ struct mlx5_ifc_create_flow_table_out_bits {
 
 struct mlx5_ifc_create_flow_table_in_bits {
 	u8         opcode[0x10];
-	u8         reserved_at_10[0x10];
+	u8         uid[0x10];
 
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];