net/mlx5: Fix race for multiple RoCE enable

[ Upstream commit 734dc065 ]

There are two potential problems with the existing implementation.

1. Enable and disable can race after the atomic operations.
2. If a command fails the refcount is left in an inconsistent state.

Introduce a lock and perform error checking.

Fixes: a6f7d2af ("net/mlx5: Add support for multiple RoCE enable")
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/net/ethernet/mellanox/mlx5/core/vport.c

@@ -36,6 +36,9 @@
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
 
+/* Mutex to hold while enabling or disabling RoCE */
+static DEFINE_MUTEX(mlx5_roce_en_lock);
+
 static int _mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod,
 				   u16 vport, u32 *out, int outlen)
 {
@@ -998,17 +1001,35 @@ static int mlx5_nic_vport_update_roce_state(struct mlx5_core_dev *mdev,
 
 int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev)
 {
-	if (atomic_inc_return(&mdev->roce.roce_en) != 1)
-		return 0;
-	return mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_ENABLED);
+	int err = 0;
+
+	mutex_lock(&mlx5_roce_en_lock);
+	if (!mdev->roce.roce_en)
+		err = mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_ENABLED);
+
+	if (!err)
+		mdev->roce.roce_en++;
+	mutex_unlock(&mlx5_roce_en_lock);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_nic_vport_enable_roce);
 
 int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev)
 {
-	if (atomic_dec_return(&mdev->roce.roce_en) != 0)
-		return 0;
-	return mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_DISABLED);
+	int err = 0;
+
+	mutex_lock(&mlx5_roce_en_lock);
+	if (mdev->roce.roce_en) {
+		mdev->roce.roce_en--;
+		if (mdev->roce.roce_en == 0)
+			err = mlx5_nic_vport_update_roce_state(mdev, MLX5_VPORT_ROCE_DISABLED);
+
+		if (err)
+			mdev->roce.roce_en++;
+	}
+	mutex_unlock(&mlx5_roce_en_lock);
+	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_nic_vport_disable_roce);
 

include/linux/mlx5/driver.h

@@ -794,7 +794,7 @@ struct mlx5_core_dev {
 	struct mlx5e_resources  mlx5e_res;
 	struct {
 		struct mlx5_rsvd_gids	reserved_gids;
-		atomic_t                roce_en;
+		u32			roce_en;
 	} roce;
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;