[PATCH v4] vfio error recovery: kernel support

[Cao jin]

From: "Michael S. Tsirkin" <mst@xxxxxxxxxx>

0. What happens now (PCIE AER only)
   Fatal errors cause a link reset.
   Non fatal errors don't.
   All errors stop the VM eventually, but not immediately
   because it's detected and reported asynchronously.
   Interrupts are forwarded as usual.
   Correctable errors are not reported to guest at all.
   Note: PPC EEH is different. This focuses on AER.

1. Correctable errors
   There is no need to report these to guest. So let's not.

2. Fatal errors
   It's not easy to handle them gracefully since link reset
   is needed. As a first step, let's use the existing mechanism
   in that case.

2. Non-fatal errors
   Here we could make progress by reporting them to guest
   and have guest handle them.

   Issues:
   a. this behaviour should only be enabled with new userspace,
      old userspace should work without changes.

      Suggestion: One way to address this would be to add a new eventfd
      non_fatal_err_trigger. If not set, invoke err_trigger.

   b. drivers are supposed to stop MMIO when error is reported,
      if vm keeps going, we will keep doing MMIO/config.

      Suggestion 1: ignore this. vm stop happens much later when
      userspace runs anyway, so we are not making things much worse.

      Suggestion 2: try to stop MMIO/config, resume on resume call

      Patch below implements Suggestion 1.

      Note that although this is really against the documentation, which
      states error_detected() is the point at which the driver should quiesce
      the device and not touch it further (until diagnostic poking at
      mmio_enabled or full access at resume callback).

      Fixing this won't be easy. However, this is not a regression.

      Also note this does nothing about interrupts, documentation
      suggests returning IRQ_NONE until reset.
      Again, not a regression.

   c. PF driver might detect that function is completely broken,
      if vm keeps going, we will keep doing MMIO/config.

      Suggestion 1: ignore this. vm stop happens much later when
      userspace runs anyway, so we are not making things much worse.

      Suggestion 2: detect this and invoke err_trigger to stop VM.

      Patch below implements Suggestion 2.

Signed-off-by: Cao jin <caoj.fnst@xxxxxxxxxxxxxx>
---
Inherit from MST's v3.
v4 changelog:
1. Tiny modification on commit message.
2. Remove unrelated virtio code.
3. VFIO_DEVICE_SET_IRQS process for VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX

 drivers/vfio/pci/vfio_pci.c         | 38 +++++++++++++++++++++++++++++++++++--
 drivers/vfio/pci/vfio_pci_intrs.c   | 19 +++++++++++++++++++
 drivers/vfio/pci/vfio_pci_private.h |  1 +
 include/uapi/linux/vfio.h           |  1 +
 4 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 324c52e..3551cc9 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -441,7 +441,8 @@ 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_NON_FATAL_ERR_IRQ_INDEX) {
 		if (pci_is_pcie(vdev->pdev))
 			return 1;
 	} else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) {
@@ -796,6 +797,7 @@ static long vfio_pci_ioctl(void *device_data,
 		case VFIO_PCI_REQ_IRQ_INDEX:
 			break;
 		case VFIO_PCI_ERR_IRQ_INDEX:
+		case VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX:
 			if (pci_is_pcie(vdev->pdev))
 				break;
 		/* pass thru to return error */
@@ -1282,7 +1284,9 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
 
 	mutex_lock(&vdev->igate);
 
-	if (vdev->err_trigger)
+	if (state == pci_channel_io_normal && vdev->non_fatal_err_trigger)
+		eventfd_signal(vdev->non_fatal_err_trigger, 1);
+	else if (vdev->err_trigger)
 		eventfd_signal(vdev->err_trigger, 1);
 
 	mutex_unlock(&vdev->igate);
@@ -1292,8 +1296,38 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
 	return PCI_ERS_RESULT_CAN_RECOVER;
 }
 
+static pci_ers_result_t vfio_pci_aer_slot_reset(struct pci_dev *pdev)
+{
+	struct vfio_pci_device *vdev;
+	struct vfio_device *device;
+	static pci_ers_result_t err = PCI_ERS_RESULT_NONE;
+
+	device = vfio_device_get_from_dev(&pdev->dev);
+	if (!device)
+		goto err_dev;
+
+	vdev = vfio_device_data(device);
+	if (!vdev)
+		goto err_data;
+
+	mutex_lock(&vdev->igate);
+
+	if (vdev->err_trigger)
+		eventfd_signal(vdev->err_trigger, 1);
+
+	mutex_unlock(&vdev->igate);
+
+	err = PCI_ERS_RESULT_RECOVERED;
+
+err_data:
+	vfio_device_put(device);
+err_dev:
+	return err;
+}
+
 static const struct pci_error_handlers vfio_err_handlers = {
 	.error_detected = vfio_pci_aer_err_detected,
+	.slot_reset = vfio_pci_aer_slot_reset,
 };
 
 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 1c46045..270d568 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -611,6 +611,17 @@ static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
 					       count, flags, data);
 }
 
+static int vfio_pci_set_non_fatal_err_trigger(struct vfio_pci_device *vdev,
+				    unsigned index, unsigned start,
+				    unsigned count, uint32_t flags, void *data)
+{
+	if (index != VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX || start != 0 || count > 1)
+		return -EINVAL;
+
+	return vfio_pci_set_ctx_trigger_single(&vdev->non_fatal_err_trigger,
+					       count, 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)
@@ -664,6 +675,14 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
 			break;
 		}
 		break;
+	case VFIO_PCI_NON_FATAL_ERR_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_non_fatal_err_trigger;
+			break;
+		}
+		break;
 	case VFIO_PCI_REQ_IRQ_INDEX:
 		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
 		case VFIO_IRQ_SET_ACTION_TRIGGER:
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index f561ac1..d30f8a3 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -93,6 +93,7 @@ struct vfio_pci_device {
 	struct pci_saved_state	*pci_saved_state;
 	int			refcnt;
 	struct eventfd_ctx	*err_trigger;
+	struct eventfd_ctx	*non_fatal_err_trigger;
 	struct eventfd_ctx	*req_trigger;
 	struct list_head	dummy_resources_list;
 };
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 519eff3..affa973 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -443,6 +443,7 @@ enum {
 	VFIO_PCI_MSIX_IRQ_INDEX,
 	VFIO_PCI_ERR_IRQ_INDEX,
 	VFIO_PCI_REQ_IRQ_INDEX,
+	VFIO_PCI_NON_FATAL_ERR_IRQ_INDEX,
 	VFIO_PCI_NUM_IRQS
 };
 
-- 
1.8.3.1