Commit ebd0d30c authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

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

Saeed Mahameed says:

====================
pull-request: mlx5-next 2020-08-9

This pulls mlx5-next branch which includes patches already reviewed on
net-next and rdma mailing lists.

1) mlx5 single E-Switch FDB for lag

2) IB/mlx5: Rename is_apu_thread_cq function to is_apu_cq

3) Add DCS caps & fields support

[1] https://patchwork.kernel.org/project/netdevbpf/cover/20210803231959.26513-1-saeed@kernel.org/

[2] https://patchwork.kernel.org/project/netdevbpf/patch/0e3364dab7e0e4eea5423878b01aa42470be8d36.1626609184.git.leonro@nvidia.com/

[3] https://patchwork.kernel.org/project/netdevbpf/patch/55e1d69bef1fbfa5cf195c0bfcbe35c8019de35e.1624258894.git.leonro@nvidia.com/

* 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5: Lag, Create shared FDB when in switchdev mode
  net/mlx5: E-Switch, add logic to enable shared FDB
  net/mlx5: Lag, move lag destruction to a workqueue
  net/mlx5: Lag, properly lock eswitch if needed
  net/mlx5: Add send to vport rules on paired device
  net/mlx5: E-Switch, Add event callback for representors
  net/mlx5e: Use shared mappings for restoring from metadata
  net/mlx5e: Add an option to create a shared mapping
  net/mlx5: E-Switch, set flow source for send to uplink rule
  RDMA/mlx5: Add shared FDB support
  {net, RDMA}/mlx5: Extend send to vport rules
  RDMA/mlx5: Fill port info based on the relevant eswitch
  net/mlx5: Lag, add initial logic for shared FDB
  net/mlx5: Return mdev from eswitch
  IB/mlx5: Rename is_apu_thread_cq function to is_apu_cq
  net/mlx5: Add DCS caps & fields support
====================

Link: https://lore.kernel.org/r/20210809202522.316930-1-saeed@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents d1a4e0a9 598fe77d

drivers/infiniband/hw/mlx5/cq.c

+1 −1
Original line number Diff line number Diff line
@@ -997,7 +997,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, 
				  MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD));

	MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries));

	MLX5_SET(cqc, cqc, uar_page, index);

	MLX5_SET(cqc, cqc, c_eqn, eqn);

	MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn);

	MLX5_SET64(cqc, cqc, dbr_addr, cq->db.dma);

	if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN)

		MLX5_SET(cqc, cqc, oi, 1);

drivers/infiniband/hw/mlx5/devx.c

+3 −4
Original line number Diff line number Diff line
@@ -1437,11 +1437,10 @@ static void devx_cq_comp(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe) 
	rcu_read_unlock();

}



static bool is_apu_thread_cq(struct mlx5_ib_dev *dev, const void *in)

static bool is_apu_cq(struct mlx5_ib_dev *dev, const void *in)

{

	if (!MLX5_CAP_GEN(dev->mdev, apu) ||

	    !MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context),

		      apu_thread_cq))

	    !MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), apu_cq))

		return false;



	return true;
@@ -1501,7 +1500,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( 
		err = mlx5_core_create_dct(dev, &obj->core_dct, cmd_in,

					   cmd_in_len, cmd_out, cmd_out_len);

	} else if (opcode == MLX5_CMD_OP_CREATE_CQ &&

		   !is_apu_thread_cq(dev, cmd_in)) {

		   !is_apu_cq(dev, cmd_in)) {

		obj->flags |= DEVX_OBJ_FLAGS_CQ;

		obj->core_cq.comp = devx_cq_comp;

		err = mlx5_core_create_cq(dev->mdev, &obj->core_cq,

drivers/infiniband/hw/mlx5/ib_rep.c

+70 −7
Original line number Diff line number Diff line
@@ -8,13 +8,15 @@ 
#include "srq.h"



static int

mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)

mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev,

		      struct mlx5_eswitch_rep *rep,

		      int vport_index)

{

	struct mlx5_ib_dev *ibdev;

	int vport_index;



	ibdev = mlx5_eswitch_uplink_get_proto_dev(dev->priv.eswitch, REP_IB);

	vport_index = rep->vport_index;

	if (!ibdev)

		return -EINVAL;



	ibdev->port[vport_index].rep = rep;

	rep->rep_data[REP_IB].priv = ibdev;
@@ -26,19 +28,39 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) 
	return 0;

}



static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev);



static int

mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)

{

	u32 num_ports = mlx5_eswitch_get_total_vports(dev);

	const struct mlx5_ib_profile *profile;

	struct mlx5_core_dev *peer_dev;

	struct mlx5_ib_dev *ibdev;

	u32 peer_num_ports;

	int vport_index;

	int ret;



	vport_index = rep->vport_index;



	if (mlx5_lag_is_shared_fdb(dev)) {

		peer_dev = mlx5_lag_get_peer_mdev(dev);

		peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev);

		if (mlx5_lag_is_master(dev)) {

			/* Only 1 ib port is the representor for both uplinks */

			num_ports += peer_num_ports - 1;

		} else {

			if (rep->vport == MLX5_VPORT_UPLINK)

				return 0;

			vport_index += peer_num_ports;

			dev = peer_dev;

		}

	}



	if (rep->vport == MLX5_VPORT_UPLINK)

		profile = &raw_eth_profile;

	else

		return mlx5_ib_set_vport_rep(dev, rep);

		return mlx5_ib_set_vport_rep(dev, rep, vport_index);



	ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev);

	if (!ibdev)
@@ -64,6 +86,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) 
		goto fail_add;



	rep->rep_data[REP_IB].priv = ibdev;

	if (mlx5_lag_is_shared_fdb(dev))

		mlx5_ib_register_peer_vport_reps(dev);



	return 0;
@@ -82,19 +106,46 @@ static void *mlx5_ib_rep_to_dev(struct mlx5_eswitch_rep *rep) 
static void

mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)

{

	struct mlx5_core_dev *mdev = mlx5_eswitch_get_core_dev(rep->esw);

	struct mlx5_ib_dev *dev = mlx5_ib_rep_to_dev(rep);

	int vport_index = rep->vport_index;

	struct mlx5_ib_port *port;



	port = &dev->port[rep->vport_index];

	if (WARN_ON(!mdev))

		return;



	if (mlx5_lag_is_shared_fdb(mdev) &&

	    !mlx5_lag_is_master(mdev)) {

		struct mlx5_core_dev *peer_mdev;



		if (rep->vport == MLX5_VPORT_UPLINK)

			return;

		peer_mdev = mlx5_lag_get_peer_mdev(mdev);

		vport_index += mlx5_eswitch_get_total_vports(peer_mdev);

	}



	if (!dev)

		return;



	port = &dev->port[vport_index];

	write_lock(&port->roce.netdev_lock);

	port->roce.netdev = NULL;

	write_unlock(&port->roce.netdev_lock);

	rep->rep_data[REP_IB].priv = NULL;

	port->rep = NULL;



	if (rep->vport == MLX5_VPORT_UPLINK)

	if (rep->vport == MLX5_VPORT_UPLINK) {

		struct mlx5_core_dev *peer_mdev;

		struct mlx5_eswitch *esw;



		if (mlx5_lag_is_shared_fdb(mdev)) {

			peer_mdev = mlx5_lag_get_peer_mdev(mdev);

			esw = peer_mdev->priv.eswitch;

			mlx5_eswitch_unregister_vport_reps(esw, REP_IB);

		}

		__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);

	}

}



static const struct mlx5_eswitch_rep_ops rep_ops = {

	.load = mlx5_ib_vport_rep_load,
@@ -102,6 +153,18 @@ static const struct mlx5_eswitch_rep_ops rep_ops = { 
	.get_proto_dev = mlx5_ib_rep_to_dev,

};



static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev)

{

	struct mlx5_core_dev *peer_mdev = mlx5_lag_get_peer_mdev(mdev);

	struct mlx5_eswitch *esw;



	if (!peer_mdev)

		return;



	esw = peer_mdev->priv.eswitch;

	mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);

}



struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,

					  u16 vport_num)

{
@@ -123,7 +186,7 @@ struct mlx5_flow_handle *create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, 


	rep = dev->port[port - 1].rep;



	return mlx5_eswitch_add_send_to_vport_rule(esw, rep, sq->base.mqp.qpn);

	return mlx5_eswitch_add_send_to_vport_rule(esw, esw, rep, sq->base.mqp.qpn);

}



static int mlx5r_rep_probe(struct auxiliary_device *adev,

drivers/infiniband/hw/mlx5/main.c

+26 −18
Original line number Diff line number Diff line
@@ -126,6 +126,7 @@ static int get_port_state(struct ib_device *ibdev, 


static struct mlx5_roce *mlx5_get_rep_roce(struct mlx5_ib_dev *dev,

					   struct net_device *ndev,

					   struct net_device *upper,

					   u32 *port_num)

{

	struct net_device *rep_ndev;
@@ -137,6 +138,14 @@ static struct mlx5_roce *mlx5_get_rep_roce(struct mlx5_ib_dev *dev, 
		if (!port->rep)

			continue;



		if (upper == ndev && port->rep->vport == MLX5_VPORT_UPLINK) {

			*port_num = i + 1;

			return &port->roce;

		}



		if (upper && port->rep->vport == MLX5_VPORT_UPLINK)

			continue;



		read_lock(&port->roce.netdev_lock);

		rep_ndev = mlx5_ib_get_rep_netdev(port->rep->esw,

						  port->rep->vport);
@@ -196,11 +205,12 @@ static int mlx5_netdev_event(struct notifier_block *this, 
		}



		if (ibdev->is_rep)

			roce = mlx5_get_rep_roce(ibdev, ndev, &port_num);

			roce = mlx5_get_rep_roce(ibdev, ndev, upper, &port_num);

		if (!roce)

			return NOTIFY_DONE;

		if ((upper == ndev || (!upper && ndev == roce->netdev))

		    && ibdev->ib_active) {

		if ((upper == ndev ||

		     ((!upper || ibdev->is_rep) && ndev == roce->netdev)) &&

		    ibdev->ib_active) {

			struct ib_event ibev = { };

			enum ib_port_state port_state;
@@ -3012,7 +3022,7 @@ static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev) 
	struct mlx5_flow_table *ft;

	int err;



	if (!ns || !mlx5_lag_is_roce(mdev))

	if (!ns || !mlx5_lag_is_active(mdev))

		return 0;



	err = mlx5_cmd_create_vport_lag(mdev);
@@ -3074,9 +3084,11 @@ static int mlx5_enable_eth(struct mlx5_ib_dev *dev) 
{

	int err;



	if (!dev->is_rep && dev->profile != &raw_eth_profile) {

		err = mlx5_nic_vport_enable_roce(dev->mdev);

		if (err)

			return err;

	}



	err = mlx5_eth_lag_init(dev);

	if (err)
@@ -3085,6 +3097,7 @@ static int mlx5_enable_eth(struct mlx5_ib_dev *dev) 
	return 0;



err_disable_roce:

	if (!dev->is_rep && dev->profile != &raw_eth_profile)

		mlx5_nic_vport_disable_roce(dev->mdev);



	return err;
@@ -3093,6 +3106,7 @@ static int mlx5_enable_eth(struct mlx5_ib_dev *dev) 
static void mlx5_disable_eth(struct mlx5_ib_dev *dev)

{

	mlx5_eth_lag_cleanup(dev);

	if (!dev->is_rep && dev->profile != &raw_eth_profile)

		mlx5_nic_vport_disable_roce(dev->mdev);

}
@@ -3950,12 +3964,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev) 


		/* Register only for native ports */

		err = mlx5_add_netdev_notifier(dev, port_num);

		if (err || dev->is_rep || !mlx5_is_roce_init_enabled(mdev))

			/*

			 * We don't enable ETH interface for

			 * 1. IB representors

			 * 2. User disabled ROCE through devlink interface

			 */

		if (err)

			return err;



		err = mlx5_enable_eth(dev);
@@ -3980,7 +3989,6 @@ static void mlx5_ib_roce_cleanup(struct mlx5_ib_dev *dev) 
	ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap);



	if (ll == IB_LINK_LAYER_ETHERNET) {

		if (!dev->is_rep)

		mlx5_disable_eth(dev);



		port_num = mlx5_core_native_port_num(dev->mdev) - 1;
@@ -4037,7 +4045,7 @@ static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev) 
{

	const char *name;



	if (!mlx5_lag_is_roce(dev->mdev))

	if (!mlx5_lag_is_active(dev->mdev))

		name = "mlx5_%d";

	else

		name = "mlx5_bond_%d";

drivers/infiniband/hw/mlx5/std_types.c

+7 −3
Original line number Diff line number Diff line
@@ -114,14 +114,18 @@ static int fill_vport_vhca_id(struct mlx5_core_dev *mdev, u16 vport, 
static int fill_switchdev_info(struct mlx5_ib_dev *dev, u32 port_num,

			       struct mlx5_ib_uapi_query_port *info)

{

	struct mlx5_core_dev *mdev = dev->mdev;

	struct mlx5_eswitch_rep *rep;

	struct mlx5_core_dev *mdev;

	int err;



	rep = dev->port[port_num - 1].rep;

	if (!rep)

		return -EOPNOTSUPP;



	mdev = mlx5_eswitch_get_core_dev(rep->esw);

	if (!mdev)

		return -EINVAL;



	info->vport = rep->vport;

	info->flags |= MLX5_IB_UAPI_QUERY_PORT_VPORT;
@@ -138,9 +142,9 @@ static int fill_switchdev_info(struct mlx5_ib_dev *dev, u32 port_num, 
	if (err)

		return err;



	if (mlx5_eswitch_vport_match_metadata_enabled(mdev->priv.eswitch)) {

	if (mlx5_eswitch_vport_match_metadata_enabled(rep->esw)) {

		info->reg_c0.value = mlx5_eswitch_get_vport_metadata_for_match(

			mdev->priv.eswitch, rep->vport);

			rep->esw, rep->vport);

		info->reg_c0.mask = mlx5_eswitch_get_vport_metadata_mask();

		info->flags |= MLX5_IB_UAPI_QUERY_PORT_VPORT_REG_C0;

	}