[PATCH V5 mlx5-next 13/13] vfio/mlx5: Use its own PCI reset_done error handler

[Yishai Hadas <yishaih@xxxxxxxxxx>]

Register its own handler for pci_error_handlers.reset_done and update
state accordingly.

Signed-off-by: Yishai Hadas <yishaih@xxxxxxxxxx>
Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxx>
---
 drivers/vfio/pci/mlx5/main.c | 56 ++++++++++++++++++++++++++++++++++--
 1 file changed, 54 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 467dee08ad77..a94cb9cdb82e 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -55,8 +55,11 @@ struct mlx5vf_pci_migration_info {
 struct mlx5vf_pci_core_device {
 	struct vfio_pci_core_device core_device;
 	u8 migrate_cap:1;
+	u8 deferred_reset:1;
 	/* protect migration state */
 	struct mutex state_mutex;
+	/* protect the reset_done flow */
+	spinlock_t reset_lock;
 	struct mlx5vf_pci_migration_info vmig;
 };
 
@@ -473,6 +476,49 @@ mlx5vf_pci_migration_data_rw(struct mlx5vf_pci_core_device *mvdev,
 	return count;
 }
 
+/*
+ * This function is called in all state_mutex unlock cases to
+ * handle a 'deferred_reset' if exists.
+ */
+static void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
+{
+again:
+	spin_lock(&mvdev->reset_lock);
+	if (mvdev->deferred_reset) {
+		mvdev->deferred_reset = false;
+		spin_unlock(&mvdev->reset_lock);
+		mlx5vf_reset_mig_state(mvdev);
+		mvdev->vmig.vfio_dev_state = VFIO_DEVICE_STATE_RUNNING;
+		goto again;
+	}
+	mutex_unlock(&mvdev->state_mutex);
+	spin_unlock(&mvdev->reset_lock);
+}
+
+static void mlx5vf_pci_aer_reset_done(struct pci_dev *pdev)
+{
+	struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
+
+	if (!mvdev->migrate_cap)
+		return;
+
+	/*
+	 * As the higher VFIO layers are holding locks across reset and using
+	 * those same locks with the mm_lock we need to prevent ABBA deadlock
+	 * with the state_mutex and mm_lock.
+	 * In case the state_mutex was taken already we defer the cleanup work
+	 * to the unlock flow of the other running context.
+	 */
+	spin_lock(&mvdev->reset_lock);
+	mvdev->deferred_reset = true;
+	if (!mutex_trylock(&mvdev->state_mutex)) {
+		spin_unlock(&mvdev->reset_lock);
+		return;
+	}
+	spin_unlock(&mvdev->reset_lock);
+	mlx5vf_state_mutex_unlock(mvdev);
+}
+
 static ssize_t mlx5vf_pci_mig_rw(struct vfio_pci_core_device *vdev,
 				 char __user *buf, size_t count, loff_t *ppos,
 				 bool iswrite)
@@ -541,7 +587,7 @@ static ssize_t mlx5vf_pci_mig_rw(struct vfio_pci_core_device *vdev,
 	}
 
 end:
-	mutex_unlock(&mvdev->state_mutex);
+	mlx5vf_state_mutex_unlock(mvdev);
 	return ret;
 }
 
@@ -636,6 +682,7 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
 			if (MLX5_CAP_GEN(mdev, migration)) {
 				mvdev->migrate_cap = 1;
 				mutex_init(&mvdev->state_mutex);
+				spin_lock_init(&mvdev->reset_lock);
 			}
 			mlx5_vf_put_core_dev(mdev);
 		}
@@ -670,12 +717,17 @@ static const struct pci_device_id mlx5vf_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, mlx5vf_pci_table);
 
+const struct pci_error_handlers mlx5vf_err_handlers = {
+	.reset_done = mlx5vf_pci_aer_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
 static struct pci_driver mlx5vf_pci_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = mlx5vf_pci_table,
 	.probe = mlx5vf_pci_probe,
 	.remove = mlx5vf_pci_remove,
-	.err_handler = &vfio_pci_core_err_handlers,
+	.err_handler = &mlx5vf_err_handlers,
 };
 
 static void __exit mlx5vf_pci_cleanup(void)
-- 
2.18.1