Merge tag 'mlx5-updates-2019-02-15' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
Support Mellanox BlueField SmartNIC (mlx5-updates-2019-02-15)

Bodong Wang says,

BlueField device is a multi-core ARM processor in a highly integrated
system on chip coupled with the ConnectX interconnect controller.
BlueField device can be presented in one out of two modes:

- SEPARATED_HOST: ARM processors as a separated and orthogonal host
  like any other external host in the multi-host virtualization model.
- EMBEDDED_CPU: ARM processors as Embedded CPU (EC) and part of the
  external hosts virtualization model.

While existing driver already supports the device on separated_host
mode, this patch series focus on the functionalities of embedded_cpu
mode.

On embedded_cpu mode, BlueField device exposes regular network
controller PCI function in the BlueField host(e.g, x86). However, a
separate PCI function called Embedded CPU Physical Function(ECPF) is
also added to the ARM host side, where standard Linux distributions is
able to run on the ARM cores. Depends on the NV configuration from
firmware, ECPF can be the e-switch manager and firmware pages supplier.
If ECPF is configured as e-switch manager and page supplier, it will
take over the responsibilities from the PF on BlueField host includes:
- Owns, controls and manages all e-switch parts, and takes e-switch
  traffic by default. It also should perform ENABLE_HCA for the host
  PF just like a PF does for its VFs.
- Provides and manages the ICM host memory required for the HCA to
  store various contexts for itself, the PF and VFs belong the
  e-switch it manages.

The PF on BlueField host side is still responsible for:
- Control its own permanent MAC.
- PCI and SRIOV configurations and perform ENABLE_HCA for its VFs.

The ECPF can also retrieve information about the external host it
controls, like host identifier, PCI BDF and number of virtual functions.
As these parameters may be changed dynamically, an event will be triggered
to the driver on ECPF side.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/infiniband/hw/mlx5/cmd.c

@@ -345,3 +345,40 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id,
 				       counter_set_id);
 	return err;
 }
+
+int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
+		     u16 opmod, u8 port)
+{
+	int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out);
+	int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in);
+	int err = -ENOMEM;
+	void *data;
+	void *resp;
+	u32 *out;
+	u32 *in;
+
+	in = kzalloc(inlen, GFP_KERNEL);
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!in || !out)
+		goto out;
+
+	MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC);
+	MLX5_SET(mad_ifc_in, in, op_mod, opmod);
+	MLX5_SET(mad_ifc_in, in, port, port);
+
+	data = MLX5_ADDR_OF(mad_ifc_in, in, mad);
+	memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad));
+
+	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
+	if (err)
+		goto out;
+
+	resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet);
+	memcpy(outb, resp,
+	       MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet));
+
+out:
+	kfree(out);
+	kfree(in);
+	return err;
+}

drivers/infiniband/hw/mlx5/cmd.h

@@ -63,4 +63,6 @@ int mlx5_cmd_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn, u16 uid);
 int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid);
 int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id,
 			     u16 uid);
+int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
+		     u16 opmod, u8 port);
 #endif /* MLX5_IB_CMD_H */

drivers/infiniband/hw/mlx5/ib_rep.c

@@ -3,10 +3,11 @@
  * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
  */
 
+#include <linux/mlx5/vport.h>
 #include "ib_rep.h"
 #include "srq.h"
 
-static const struct mlx5_ib_profile rep_profile = {
+static const struct mlx5_ib_profile vf_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
 		     mlx5_ib_stage_init_init,
 		     mlx5_ib_stage_init_cleanup),
@@ -45,31 +46,17 @@ static const struct mlx5_ib_profile rep_profile = {
 		     NULL),
 };
 
-static int
-mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5_ib_dev *ibdev;
-
-	ibdev = mlx5_ib_rep_to_dev(rep);
-	if (!__mlx5_ib_add(ibdev, ibdev->profile))
-		return -EINVAL;
-	return 0;
-}
-
-static void
-mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5_ib_dev *ibdev;
-
-	ibdev = mlx5_ib_rep_to_dev(rep);
-	__mlx5_ib_remove(ibdev, ibdev->profile, MLX5_IB_STAGE_MAX);
-}
-
 static int
 mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
+	const struct mlx5_ib_profile *profile;
 	struct mlx5_ib_dev *ibdev;
 
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		profile = &uplink_rep_profile;
+	else
+		profile = &vf_rep_profile;
+
 	ibdev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*ibdev));
 	if (!ibdev)
 		return -ENOMEM;
@@ -78,7 +65,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	ibdev->mdev = dev;
 	ibdev->num_ports = max(MLX5_CAP_GEN(dev, num_ports),
 			       MLX5_CAP_GEN(dev, num_vhca_ports));
-	if (!__mlx5_ib_add(ibdev, &rep_profile))
+	if (!__mlx5_ib_add(ibdev, profile))
 		return -EINVAL;
 
 	rep->rep_if[REP_IB].priv = ibdev;
@@ -105,53 +92,23 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return mlx5_ib_rep_to_dev(rep);
 }
 
-static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev);
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep_if rep_if = {};
-
-		rep_if.load = mlx5_ib_vport_rep_load;
-		rep_if.unload = mlx5_ib_vport_rep_unload;
-		rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
-		mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_IB);
-	}
-}
-
-static void mlx5_ib_rep_unregister_vf_vports(struct mlx5_ib_dev *dev)
+void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev);
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_IB);
-}
-
-void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 	struct mlx5_eswitch_rep_if rep_if = {};
 
-	rep_if.load = mlx5_ib_nic_rep_load;
-	rep_if.unload = mlx5_ib_nic_rep_unload;
+	rep_if.load = mlx5_ib_vport_rep_load;
+	rep_if.unload = mlx5_ib_vport_rep_unload;
 	rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
-	rep_if.priv = dev;
-
-	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_IB);
 
-	mlx5_ib_rep_register_vf_vports(dev);
+	mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_IB);
 }
 
-void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev)
+void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
 
-	mlx5_ib_rep_unregister_vf_vports(dev); /* VFs vports */
-	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_IB); /* UPLINK PF*/
+	mlx5_eswitch_unregister_vport_reps(esw, REP_IB);
 }
 
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw)

drivers/infiniband/hw/mlx5/ib_rep.h

@@ -10,14 +10,16 @@
 #include "mlx5_ib.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
+extern const struct mlx5_ib_profile uplink_rep_profile;
+
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
 					  int vport_index);
 struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw);
 struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw,
 					   int vport_index);
-void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev);
-void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev);
+void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev);
+void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev);
 int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 			      struct mlx5_ib_sq *sq);
 struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
@@ -48,8 +50,8 @@ struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw,
 	return NULL;
 }
 
-static inline void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) {}
-static inline void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) {}
+static inline void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) {}
 static inline int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 					    struct mlx5_ib_sq *sq)
 {

drivers/infiniband/hw/mlx5/mad.c

@@ -36,6 +36,7 @@
 #include <rdma/ib_smi.h>
 #include <rdma/ib_pma.h>
 #include "mlx5_ib.h"
+#include "cmd.h"
 
 enum {
 	MLX5_IB_VENDOR_CLASS1 = 0x9,
@@ -51,9 +52,10 @@ static bool can_do_mad_ifc(struct mlx5_ib_dev *dev, u8 port_num,
 	return dev->mdev->port_caps[port_num - 1].has_smi;
 }
 
-int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
-		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
-		 const void *in_mad, void *response_mad)
+static int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey,
+			int ignore_bkey, u8 port, const struct ib_wc *in_wc,
+			const struct ib_grh *in_grh, const void *in_mad,
+			void *response_mad)
 {
 	u8 op_modifier = 0;
 
@@ -68,7 +70,8 @@ int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
 	if (ignore_bkey || !in_wc)
 		op_modifier |= 0x2;
 
-	return mlx5_core_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier, port);
+	return mlx5_cmd_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier,
+				port);
 }
 
 static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,