[PATCH] vfio: add pci resume error handler

[Cao jin <caoj.fnst@cn.fujitsu.com>]

From: Chen Fan <chen.fan.fnst@cn.fujitsu.com>

when the device encounters a falal error, the host aer driver may
do secondary bus reset to recovery the devices under the bus, and
for guest driver also do the same way to recovery the device under
the virtual bus. in order to avoid guest and host do the bus reset
simultaneously, we sould introduce a resume handler to notify userspace
that the host bus reset has finished.

Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
---
 drivers/vfio/pci/vfio_pci.c         | 28 +++++++++++++++++++++++++++-
 drivers/vfio/pci/vfio_pci_intrs.c   | 18 ++++++++++++++++++
 drivers/vfio/pci/vfio_pci_private.h |  1 +
 include/uapi/linux/vfio.h           |  1 +
 4 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 712a849..398d8b8 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -328,7 +328,8 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
 
 			return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
 		}
-	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX) {
+	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX ||
+		   irq_type == VFIO_PCI_RESUME_IRQ_INDEX) {
 		if (pci_is_pcie(vdev->pdev))
 			return 1;
 	} else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) {
@@ -696,6 +697,7 @@ static long vfio_pci_ioctl(void *device_data,
 		case VFIO_PCI_REQ_IRQ_INDEX:
 			break;
 		case VFIO_PCI_ERR_IRQ_INDEX:
+		case VFIO_PCI_RESUME_IRQ_INDEX:
 			if (pci_is_pcie(vdev->pdev))
 				break;
 		/* pass thru to return error */
@@ -1199,8 +1201,32 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
+static void vfio_pci_aer_resume(struct pci_dev *pdev)
+{
+	struct vfio_pci_device *vdev;
+	struct vfio_device *device;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (device == NULL)
+		return;
+
+	vdev = vfio_device_data(device);
+	if (vdev == NULL) {
+		vfio_device_put(device);
+		return;
+	}
+
+	mutex_lock(&vdev->igate);
+	if (vdev->resume_trigger)
+		eventfd_signal(vdev->resume_trigger, 1);
+
+	mutex_unlock(&vdev->igate);
+	vfio_device_put(device);
+}
+
 static const struct pci_error_handlers vfio_err_handlers = {
 	.error_detected = vfio_pci_aer_err_detected,
+	.resume         = vfio_pci_aer_resume,
 };
 
 static struct pci_driver vfio_pci_driver = {
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index e9ea3fe..6d3e396 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -617,6 +617,16 @@ static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
 	return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data);
 }
 
+static int vfio_pci_set_resume_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	if (index != VFIO_PCI_RESUME_IRQ_INDEX)
+		return -EINVAL;
+
+	return vfio_pci_set_ctx_trigger_single(&vdev->resume_trigger, flags, data);
+}
+
 static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev,
 				    unsigned index, unsigned start,
 				    unsigned count, uint32_t flags, void *data)
@@ -676,6 +686,14 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
 			break;
 		}
 		break;
+	case VFIO_PCI_RESUME_IRQ_INDEX:
+		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
+		case VFIO_IRQ_SET_ACTION_TRIGGER:
+			if (pci_is_pcie(vdev->pdev))
+				func = vfio_pci_set_resume_trigger;
+			break;
+		}
+		break;
 	}
 
 	if (!func)
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 8a7d546..129d43d 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -87,6 +87,7 @@ struct vfio_pci_device {
 	int			refcnt;
 	struct eventfd_ctx	*err_trigger;
 	struct eventfd_ctx	*req_trigger;
+	struct eventfd_ctx	*resume_trigger;
 };
 
 #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 255a211..34ab138 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -433,6 +433,7 @@ enum {
 	VFIO_PCI_MSIX_IRQ_INDEX,
 	VFIO_PCI_ERR_IRQ_INDEX,
 	VFIO_PCI_REQ_IRQ_INDEX,
+	VFIO_PCI_RESUME_IRQ_INDEX,
 	VFIO_PCI_NUM_IRQS
 };
 
-- 
1.9.3