vfio/mlx5: Use its own PCI reset_done error handler

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

Link: https://lore.kernel.org/all/20220224142024.147653-16-yishaih@nvidia.com
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>

1 files changed, 55 insertions, 2 deletions

diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index ae1e40f7b290..282a9d4bf776 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -29,9 +29,12 @@ struct mlx5vf_pci_core_device {
 	struct vfio_pci_core_device core_device;
 	u16 vhca_id;
 	u8 migrate_cap:1;
+	u8 deferred_reset:1;
 	/* protect migration state */
 	struct mutex state_mutex;
 	enum vfio_device_mig_state mig_state;
+	/* protect the reset_done flow */
+	spinlock_t reset_lock;
 	struct mlx5_vf_migration_file *resuming_migf;
 	struct mlx5_vf_migration_file *saving_migf;
 };
@@ -437,6 +440,25 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	return ERR_PTR(-EINVAL);
 }
 
+/*
+ * 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);
+		mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+		mlx5vf_disable_fds(mvdev);
+		goto again;
+	}
+	mutex_unlock(&mvdev->state_mutex);
+	spin_unlock(&mvdev->reset_lock);
+}
+
 static struct file *
 mlx5vf_pci_set_device_state(struct vfio_device *vdev,
 			    enum vfio_device_mig_state new_state)
@@ -465,7 +487,7 @@ mlx5vf_pci_set_device_state(struct vfio_device *vdev,
 			break;
 		}
 	}
-	mutex_unlock(&mvdev->state_mutex);
+	mlx5vf_state_mutex_unlock(mvdev);
 	return res;
 }
 
@@ -477,10 +499,34 @@ static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
 
 	mutex_lock(&mvdev->state_mutex);
 	*curr_state = mvdev->mig_state;
-	mutex_unlock(&mvdev->state_mutex);
+	mlx5vf_state_mutex_unlock(mvdev);
 	return 0;
 }
 
+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 int mlx5vf_pci_open_device(struct vfio_device *core_vdev)
 {
 	struct mlx5vf_pci_core_device *mvdev = container_of(
@@ -562,6 +608,7 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
 					VFIO_MIGRATION_STOP_COPY |
 					VFIO_MIGRATION_P2P;
 				mutex_init(&mvdev->state_mutex);
+				spin_lock_init(&mvdev->reset_lock);
 			}
 			mlx5_vf_put_core_dev(mdev);
 		}
@@ -596,11 +643,17 @@ static const struct pci_device_id mlx5vf_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, mlx5vf_pci_table);
 
+static 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 = &mlx5vf_err_handlers,
 };
 
 static void __exit mlx5vf_pci_cleanup(void)