[RFC PATCH v2 09/16] vfio/pci: Add PCI error recovery state

[Shameer Kolothum <skolothumtho@nvidia.com>]

Add recovery flags, a sequence number, a saved PCI_COMMAND value and an
eventfd for recovery notifications. Initialize the per-open state at
open and clear it at close.

Track the host transaction separately from the userspace session. The
host-active flag survives close so a later patch can reject reopen until
the outstanding recovery completes.

Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com>
---
 include/linux/vfio_pci_core.h    | 19 ++++++++++++++++++-
 drivers/vfio/pci/vfio_pci_core.c | 11 +++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 1dc9630dc740..61d21c3f8089 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -96,6 +96,11 @@ static inline int vfio_pci_core_get_dmabuf_phys(
 }
 #endif
 
+#define VFIO_PCI_RECOVERY_IN_PROGRESS	BIT(0)
+#define VFIO_PCI_RECOVERY_FROZEN	BIT(1)
+#define VFIO_PCI_RECOVERY_RESET		BIT(2)
+#define VFIO_PCI_RECOVERY_FAILED	BIT(3)
+
 struct vfio_pci_core_device {
 	struct vfio_device	vdev;
 	struct pci_dev		*pdev;
@@ -143,6 +148,7 @@ struct vfio_pci_core_device {
 	int			ioeventfds_nr;
 	struct vfio_pci_eventfd __rcu *err_trigger;
 	struct vfio_pci_eventfd __rcu *req_trigger;
+	struct vfio_pci_eventfd __rcu *pci_recovery_trigger;
 	struct eventfd_ctx	*pm_wake_eventfd_ctx;
 	struct list_head	dummy_resources_list;
 	struct mutex		ioeventfds_lock;
@@ -168,7 +174,18 @@ struct vfio_pci_core_device {
 	bool			access_blocked;
 	/* Set after open completes, cleared before close tears down state. */
 	bool			device_open;
-	struct mutex		access_lock;	/* gate flag writers */
+	struct mutex		access_lock;	/* gate and recovery state writers */
+	u32			pci_recovery_flags;
+	u64			pci_recovery_sequence;
+	/* Saved PCI_COMMAND, valid when pci_recovery_command_valid is set. */
+	u16			pci_recovery_command;
+	bool			pci_recovery_enabled;
+	bool			pci_recovery_command_valid;
+	/*
+	 * Host recovery in progress, protected by access_lock. Unlike the
+	 * per-open recovery flags, this is preserved across close.
+	 */
+	bool			pci_recovery_host_active;
 	struct list_head	dmabufs;
 };
 
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 92497224f471..667c5813f6c7 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -845,8 +845,11 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev)
 
 	if (vdev->pci_recovery_supported) {
 		scoped_guard(mutex, &vdev->access_lock) {
+			WRITE_ONCE(vdev->pci_recovery_enabled, false);
+			vdev->pci_recovery_command_valid = false;
 			WRITE_ONCE(vdev->access_blocked, false);
 			WRITE_ONCE(vdev->device_open, false);
+			WRITE_ONCE(vdev->pci_recovery_flags, 0);
 		}
 	}
 
@@ -866,6 +869,10 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev)
 	mutex_lock(&vdev->igate);
 	vfio_pci_eventfd_replace_locked(vdev, &vdev->err_trigger, NULL);
 	vfio_pci_eventfd_replace_locked(vdev, &vdev->req_trigger, NULL);
+	if (vdev->pci_recovery_supported)
+		vfio_pci_eventfd_replace_locked(vdev,
+						&vdev->pci_recovery_trigger,
+						NULL);
 	mutex_unlock(&vdev->igate);
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_close_device);
@@ -885,6 +892,10 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev)
 
 	if (vdev->pci_recovery_supported) {
 		guard(mutex)(&vdev->access_lock);
+		WRITE_ONCE(vdev->pci_recovery_flags, 0);
+		vdev->pci_recovery_sequence = 0;
+		vdev->pci_recovery_command_valid = false;
+		WRITE_ONCE(vdev->pci_recovery_enabled, false);
 		WRITE_ONCE(vdev->access_blocked, false);
 		WRITE_ONCE(vdev->device_open, true);
 	}
-- 
2.43.0