[PATCH AUTOSEL for 4.14 60/97] net/mlx5: Fix race for multiple RoCE enable

[Sasha Levin <Alexander.Levin@xxxxxxxxxxxxx>]

From: Daniel Jurgens <danielj@xxxxxxxxxxxx>

[ Upstream commit 734dc065fc41f6143ff88225aa5d335cb1e0f6aa ]

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: a6f7d2aff623 ("net/mlx5: Add support for multiple RoCE enable")
Signed-off-by: Daniel Jurgens <danielj@xxxxxxxxxxxx>
Reviewed-by: Parav Pandit <parav@xxxxxxxxxxxx>
Signed-off-by: Leon Romanovsky <leon@xxxxxxxxxx>
Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 33 ++++++++++++++++++++-----
 include/linux/mlx5/driver.h                     |  2 +-
 2 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index a1296a62497d..71153c0f1605 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/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);
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 8f9fc6e5539a..bb6e3afe9dcb 100644
--- a/include/linux/mlx5/driver.h
+++ b/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;
-- 
2.14.1