net/mlx5: SD, Implement devcom communication and primary election

Use devcom to communicate between the different devices. Add a new
devcom component type for this.

Each device registers itself to the devcom component <SD, group ID>.
Once all devices of a component are registered, the component becomes
ready, and a primary device is elected.

In principle, any of the devices can act as a primary, they are all
capable, and a random election would've worked. However, we aim to
achieve predictability and consistency, hence each group always choses
the same device, with the lowest PCI BUS number, as primary.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

2 files changed, 121 insertions, 2 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index ec32b686f586..d58032dd0df7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -10,6 +10,7 @@ enum mlx5_devcom_component {
 	MLX5_DEVCOM_ESW_OFFLOADS,
 	MLX5_DEVCOM_MPV,
 	MLX5_DEVCOM_HCA_PORTS,
+	MLX5_DEVCOM_SD_GROUP,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index 9d8b1bb0c0a6..19e674dd1af7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -14,6 +14,16 @@
 struct mlx5_sd {
 	u32 group_id;
 	u8 host_buses;
+	struct mlx5_devcom_comp_dev *devcom;
+	bool primary;
+	union {
+		struct { /* primary */
+			struct mlx5_core_dev *secondaries[MLX5_SD_MAX_GROUP_SZ - 1];
+		};
+		struct { /* secondary */
+			struct mlx5_core_dev *primary_dev;
+		};
+	};
 };
 
 static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev)
@@ -26,13 +36,29 @@ static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev)
 	return sd->host_buses;
 }
 
+static struct mlx5_core_dev *mlx5_sd_get_primary(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sd *sd = mlx5_get_sd(dev);
+
+	if (!sd)
+		return dev;
+
+	return sd->primary ? dev : sd->primary_dev;
+}
+
 struct mlx5_core_dev *
 mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx)
 {
+	struct mlx5_sd *sd;
+
 	if (idx == 0)
 		return primary;
 
-	return NULL;
+	if (idx >= mlx5_sd_get_host_buses(primary))
+		return NULL;
+
+	sd = mlx5_get_sd(primary);
+	return sd->secondaries[idx - 1];
 }
 
 int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix)
@@ -136,15 +162,93 @@ static void sd_cleanup(struct mlx5_core_dev *dev)
 	kfree(sd);
 }
 
+static int sd_register(struct mlx5_core_dev *dev)
+{
+	struct mlx5_devcom_comp_dev *devcom, *pos;
+	struct mlx5_core_dev *peer, *primary;
+	struct mlx5_sd *sd, *primary_sd;
+	int err, i;
+
+	sd = mlx5_get_sd(dev);
+	devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP,
+						sd->group_id, NULL, dev);
+	if (!devcom)
+		return -ENOMEM;
+
+	sd->devcom = devcom;
+
+	if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses)
+		return 0;
+
+	mlx5_devcom_comp_lock(devcom);
+	mlx5_devcom_comp_set_ready(devcom, true);
+	mlx5_devcom_comp_unlock(devcom);
+
+	if (!mlx5_devcom_for_each_peer_begin(devcom)) {
+		err = -ENODEV;
+		goto err_devcom_unreg;
+	}
+
+	primary = dev;
+	mlx5_devcom_for_each_peer_entry(devcom, peer, pos)
+		if (peer->pdev->bus->number < primary->pdev->bus->number)
+			primary = peer;
+
+	primary_sd = mlx5_get_sd(primary);
+	primary_sd->primary = true;
+	i = 0;
+	/* loop the secondaries */
+	mlx5_devcom_for_each_peer_entry(primary_sd->devcom, peer, pos) {
+		struct mlx5_sd *peer_sd = mlx5_get_sd(peer);
+
+		primary_sd->secondaries[i++] = peer;
+		peer_sd->primary = false;
+		peer_sd->primary_dev = primary;
+	}
+
+	mlx5_devcom_for_each_peer_end(devcom);
+	return 0;
+
+err_devcom_unreg:
+	mlx5_devcom_comp_lock(sd->devcom);
+	mlx5_devcom_comp_set_ready(sd->devcom, false);
+	mlx5_devcom_comp_unlock(sd->devcom);
+	mlx5_devcom_unregister_component(sd->devcom);
+	return err;
+}
+
+static void sd_unregister(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sd *sd = mlx5_get_sd(dev);
+
+	mlx5_devcom_comp_lock(sd->devcom);
+	mlx5_devcom_comp_set_ready(sd->devcom, false);
+	mlx5_devcom_comp_unlock(sd->devcom);
+	mlx5_devcom_unregister_component(sd->devcom);
+}
+
 int mlx5_sd_init(struct mlx5_core_dev *dev)
 {
+	struct mlx5_sd *sd = mlx5_get_sd(dev);
 	int err;
 
 	err = sd_init(dev);
 	if (err)
 		return err;
 
+	sd = mlx5_get_sd(dev);
+	if (!sd)
+		return 0;
+
+	err = sd_register(dev);
+	if (err)
+		goto err_sd_cleanup;
+
 	return 0;
+
+err_sd_cleanup:
+	sd_cleanup(dev);
+	return err;
 }
 
 void mlx5_sd_cleanup(struct mlx5_core_dev *dev)
@@ -154,6 +258,7 @@ void mlx5_sd_cleanup(struct mlx5_core_dev *dev)
 	if (!sd)
 		return;
 
+	sd_unregister(dev);
 	sd_cleanup(dev);
 }
 
@@ -161,5 +266,18 @@ struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev,
 					  struct auxiliary_device *adev,
 					  int idx)
 {
-	return adev;
+	struct mlx5_sd *sd = mlx5_get_sd(dev);
+	struct mlx5_core_dev *primary;
+
+	if (!sd)
+		return adev;
+
+	if (!mlx5_devcom_comp_is_ready(sd->devcom))
+		return NULL;
+
+	primary = mlx5_sd_get_primary(dev);
+	if (dev == primary)
+		return adev;
+
+	return &primary->priv.adev[idx]->adev;
 }