Merge branch 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Saeed Mahameed says:

====================
mlx5-next 2022-22-02

The following PR includes updates to mlx5-next branch:

Headlines:
==========

1) Jakub cleans up unused static inline functions

2) I did some low level firmware command interface return status changes to
provide the caller with full visibility on the error/status returned by
the Firmware.

3) Use the new command interface in RDMA DEVX usecases to avoid flooding
dmesg with some "expected" user error prone use cases.

4) Moshe also uses the new command interface to grab the specific error
code from MFRL register command to provide the exact error reason for
why SW reset couldn't perform internally in FW.

5) From Mark Bloch: Lag, drop packets in hardware when possible

In active-backup mode the inactive interface's packets are dropped by the
bond device. In switchdev where TC rules are offloaded to the FDB
this can lead to packets being hit in the FDB where without offload
they would have been dropped before reaching TC rules in the kernel.

Create a drop rule to make sure packets on inactive ports are dropped
before reaching the FDB.

Listen on NETDEV_CHANGEUPPER / NETDEV_CHANGEINFODATA events and record
the inactive state and offload accordingly.

* 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5: Add clarification on sync reset failure
  net/mlx5: Add reset_state field to MFRL register
  RDMA/mlx5: Use new command interface API
  net/mlx5: cmdif, Refactor error handling and reporting of async commands
  net/mlx5: Use mlx5_cmd_do() in core create_{cq,dct}
  net/mlx5: cmdif, Add new api for command execution
  net/mlx5: cmdif, cmd_check refactoring
  net/mlx5: cmdif, Return value improvements
  net/mlx5: Lag, offload active-backup drops to hardware
  net/mlx5: Lag, record inactive state of bond device
  net/mlx5: Lag, don't use magic numbers for ports
  net/mlx5: Lag, use local variable already defined to access E-Switch
  net/mlx5: E-switch, add drop rule support to ingress ACL
  net/mlx5: E-switch, remove special uplink ingress ACL handling
  net/mlx5: E-Switch, reserve and use same uplink metadata across ports
  net/mlx5: Add ability to insert to specific flow group
  mlx5: remove unused static inlines
====================

Link: https://lore.kernel.org/r/20220223233930.319301-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 26 insertions, 67 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 27e58ea13f63..35cf4cb3098e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2379,60 +2379,6 @@ void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
 		mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
 }
 
-static int esw_set_uplink_slave_ingress_root(struct mlx5_core_dev *master,
-					     struct mlx5_core_dev *slave)
-{
-	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {};
-	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
-	struct mlx5_eswitch *esw;
-	struct mlx5_flow_root_namespace *root;
-	struct mlx5_flow_namespace *ns;
-	struct mlx5_vport *vport;
-	int err;
-
-	MLX5_SET(set_flow_table_root_in, in, opcode,
-		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
-	MLX5_SET(set_flow_table_root_in, in, table_type, FS_FT_ESW_INGRESS_ACL);
-	MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
-	MLX5_SET(set_flow_table_root_in, in, vport_number, MLX5_VPORT_UPLINK);
-
-	if (master) {
-		esw = master->priv.eswitch;
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
-		MLX5_SET(set_flow_table_root_in, in, table_of_other_vport, 1);
-		MLX5_SET(set_flow_table_root_in, in, table_vport_number,
-			 MLX5_VPORT_UPLINK);
-
-		ns = mlx5_get_flow_vport_acl_namespace(master,
-						       MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-						       vport->index);
-		root = find_root(&ns->node);
-		mutex_lock(&root->chain_lock);
-
-		MLX5_SET(set_flow_table_root_in, in,
-			 table_eswitch_owner_vhca_id_valid, 1);
-		MLX5_SET(set_flow_table_root_in, in,
-			 table_eswitch_owner_vhca_id,
-			 MLX5_CAP_GEN(master, vhca_id));
-		MLX5_SET(set_flow_table_root_in, in, table_id,
-			 root->root_ft->id);
-	} else {
-		esw = slave->priv.eswitch;
-		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
-		ns = mlx5_get_flow_vport_acl_namespace(slave,
-						       MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-						       vport->index);
-		root = find_root(&ns->node);
-		mutex_lock(&root->chain_lock);
-		MLX5_SET(set_flow_table_root_in, in, table_id, root->root_ft->id);
-	}
-
-	err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
-	mutex_unlock(&root->chain_lock);
-
-	return err;
-}
-
 static int esw_set_slave_root_fdb(struct mlx5_core_dev *master,
 				  struct mlx5_core_dev *slave)
 {
@@ -2614,15 +2560,10 @@ int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
 {
 	int err;
 
-	err = esw_set_uplink_slave_ingress_root(master_esw->dev,
-						slave_esw->dev);
-	if (err)
-		return -EINVAL;
-
 	err = esw_set_slave_root_fdb(master_esw->dev,
 				     slave_esw->dev);
 	if (err)
-		goto err_fdb;
+		return err;
 
 	err = esw_set_master_egress_rule(master_esw->dev,
 					 slave_esw->dev);
@@ -2634,9 +2575,6 @@ int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
 err_acl:
 	esw_set_slave_root_fdb(NULL, slave_esw->dev);
 
-err_fdb:
-	esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev);
-
 	return err;
 }
 
@@ -2645,7 +2583,6 @@ void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
 {
 	esw_unset_master_egress_rule(master_esw->dev);
 	esw_set_slave_root_fdb(NULL, slave_esw->dev);
-	esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev);
 }
 
 #define ESW_OFFLOADS_DEVCOM_PAIR	(0)
@@ -2842,6 +2779,19 @@ bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 	return true;
 }
 
+#define MLX5_ESW_METADATA_RSVD_UPLINK 1
+
+/* Share the same metadata for uplink's. This is fine because:
+ * (a) In shared FDB mode (LAG) both uplink's are treated the
+ *     same and tagged with the same metadata.
+ * (b) In non shared FDB mode, packets from physical port0
+ *     cannot hit eswitch of PF1 and vice versa.
+ */
+static u32 mlx5_esw_match_metadata_reserved(struct mlx5_eswitch *esw)
+{
+	return MLX5_ESW_METADATA_RSVD_UPLINK;
+}
+
 u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
 {
 	u32 vport_end_ida = (1 << ESW_VPORT_BITS) - 1;
@@ -2856,8 +2806,10 @@ u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
 		return 0;
 
 	/* Metadata is 4 bits of PFNUM and 12 bits of unique id */
-	/* Use only non-zero vport_id (1-4095) for all PF's */
-	id = ida_alloc_range(&esw->offloads.vport_metadata_ida, 1, vport_end_ida, GFP_KERNEL);
+	/* Use only non-zero vport_id (2-4095) for all PF's */
+	id = ida_alloc_range(&esw->offloads.vport_metadata_ida,
+			     MLX5_ESW_METADATA_RSVD_UPLINK + 1,
+			     vport_end_ida, GFP_KERNEL);
 	if (id < 0)
 		return 0;
 	id = (pf_num << ESW_VPORT_BITS) | id;
@@ -2875,7 +2827,11 @@ void mlx5_esw_match_metadata_free(struct mlx5_eswitch *esw, u32 metadata)
 static int esw_offloads_vport_metadata_setup(struct mlx5_eswitch *esw,
 					     struct mlx5_vport *vport)
 {
-	vport->default_metadata = mlx5_esw_match_metadata_alloc(esw);
+	if (vport->vport == MLX5_VPORT_UPLINK)
+		vport->default_metadata = mlx5_esw_match_metadata_reserved(esw);
+	else
+		vport->default_metadata = mlx5_esw_match_metadata_alloc(esw);
+
 	vport->metadata = vport->default_metadata;
 	return vport->metadata ? 0 : -ENOSPC;
 }
@@ -2886,6 +2842,9 @@ static void esw_offloads_vport_metadata_cleanup(struct mlx5_eswitch *esw,
 	if (!vport->default_metadata)
 		return;
 
+	if (vport->vport == MLX5_VPORT_UPLINK)
+		return;
+
 	WARN_ON(vport->metadata != vport->default_metadata);
 	mlx5_esw_match_metadata_free(esw, vport->default_metadata);
 }