From: Shay Drory <shayd@nvidia.com>

mlx5_sd_init() / mlx5_sd_cleanup() may run from multiple PFs in the same
Socket-Direct group. This can cause the SD bring-up/tear-down sequence
to be executed more than once or interleaved across PFs.

Protect SD init/cleanup with mlx5_devcom_comp_lock() and track the SD
group state on the primary device. Skip init if the primary is already
UP, and skip cleanup unless the primary is UP.

Fixes: 381978d28317 ("net/mlx5e: Create single netdev per SD group")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/lib/sd.c  | 28 +++++++++++++++++--
 1 file changed, 25 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index 4c80b9d25283..374f27b78fbe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -18,6 +18,7 @@ struct mlx5_sd {
 	u8 host_buses;
 	struct mlx5_devcom_comp_dev *devcom;
 	struct dentry *dfs;
+	u8 state;
 	bool primary;
 	union {
 		struct { /* primary */
@@ -31,6 +32,11 @@ struct mlx5_sd {
 	};
 };
 
+enum mlx5_sd_state {
+	MLX5_SD_STATE_DOWN = 0,
+	MLX5_SD_STATE_UP,
+};
+
 static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sd *sd = mlx5_get_sd(dev);
@@ -441,12 +447,16 @@ int mlx5_sd_init(struct mlx5_core_dev *dev)
 	if (err)
 		goto err_sd_cleanup;
 
+	mlx5_devcom_comp_lock(sd->devcom);
 	if (!mlx5_devcom_comp_is_ready(sd->devcom))
-		return 0;
+		goto out;
 
 	primary = mlx5_sd_get_primary(dev);
 	primary_sd = mlx5_get_sd(primary);
 
+	if (primary_sd->state == MLX5_SD_STATE_UP)
+		goto out;
+
 	for (i = 0; i < ACCESS_KEY_LEN; i++)
 		alias_key[i] = get_random_u8();
 
@@ -479,6 +489,9 @@ int mlx5_sd_init(struct mlx5_core_dev *dev)
 		sd->group_id, mlx5_devcom_comp_get_size(sd->devcom));
 	sd_print_group(primary);
 
+	primary_sd->state = MLX5_SD_STATE_UP;
+out:
+	mlx5_devcom_comp_unlock(sd->devcom);
 	return 0;
 
 err_unset_secondaries:
@@ -489,6 +502,8 @@ int mlx5_sd_init(struct mlx5_core_dev *dev)
 	debugfs_remove_recursive(primary_sd->dfs);
 	primary_sd->dfs = NULL;
 err_sd_unregister:
+	primary_sd->state = MLX5_SD_STATE_DOWN;
+	mlx5_devcom_comp_unlock(sd->devcom);
 	sd_unregister(dev);
 err_sd_cleanup:
 	sd_cleanup(dev);
@@ -505,11 +520,16 @@ void mlx5_sd_cleanup(struct mlx5_core_dev *dev)
 	if (!sd)
 		return;
 
+	mlx5_devcom_comp_lock(sd->devcom);
 	if (!mlx5_devcom_comp_is_ready(sd->devcom))
-		goto out;
+		goto out_unlock;
 
 	primary = mlx5_sd_get_primary(dev);
 	primary_sd = mlx5_get_sd(primary);
+
+	if (primary_sd->state != MLX5_SD_STATE_UP)
+		goto out_unlock;
+
 	mlx5_sd_for_each_secondary(i, primary, pos)
 		sd_cmd_unset_secondary(pos);
 	sd_cmd_unset_primary(primary);
@@ -517,7 +537,9 @@ void mlx5_sd_cleanup(struct mlx5_core_dev *dev)
 	primary_sd->dfs = NULL;
 
 	sd_info(primary, "group id %#x, uncombined\n", sd->group_id);
-out:
+	primary_sd->state = MLX5_SD_STATE_DOWN;
+out_unlock:
+	mlx5_devcom_comp_unlock(sd->devcom);
 	sd_unregister(dev);
 	sd_cleanup(dev);
 }
-- 
2.44.0