[Qemu-devel] [PATCH v2 2/3] VFIO-AER: Vfio-pci driver changes for supporting AER

[Pandarathil, Vijaymohan R]

        - New VFIO_SET_IRQ ioctl option to pass the eventfd that is signalled 
when
          an error occurs in the vfio_pci_device

        - Register pci_error_handler for the vfio_pci driver

        - When the device encounters an error, the error handler registered by
          the vfio_pci driver gets invoked by the AER infrastructure

        - In the error handler, signal the eventfd registered for the device.

        - This results in the qemu eventfd handler getting invoked and
          appropriate action taken for the guest.

Signed-off-by: Vijay Mohan Pandarathil <address@hidden>
---
 drivers/vfio/pci/vfio_pci.c         | 44 ++++++++++++++++++++++++++++++++++++-
 drivers/vfio/pci/vfio_pci_intrs.c   | 32 +++++++++++++++++++++++++++
 drivers/vfio/pci/vfio_pci_private.h |  1 +
 include/uapi/linux/vfio.h           |  3 +++
 4 files changed, 79 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b28e66c..ff2a078 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -196,7 +196,9 @@ 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)
+               if (pci_is_pcie(vdev->pdev))
+                       return 1;
 
        return 0;
 }
@@ -223,9 +225,18 @@ static long vfio_pci_ioctl(void *device_data,
                if (vdev->reset_works)
                        info.flags |= VFIO_DEVICE_FLAGS_RESET;
 
+               if (pci_is_pcie(vdev->pdev)) {
+                       info.flags |= VFIO_DEVICE_FLAGS_PCI_AER;
+                       info.flags |= VFIO_DEVICE_FLAGS_PCI_AER_NOTIFY;
+               }
+
                info.num_regions = VFIO_PCI_NUM_REGIONS;
                info.num_irqs = VFIO_PCI_NUM_IRQS;
 
+               /* Expose only implemented IRQs */
+               if (!(info.flags & VFIO_DEVICE_FLAGS_PCI_AER_NOTIFY))
+                       info.num_irqs--;
+
                return copy_to_user((void __user *)arg, &info, minsz);
 
        } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) {
@@ -302,6 +313,10 @@ static long vfio_pci_ioctl(void *device_data,
                if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS)
                        return -EINVAL;
 
+               if ((info.index == VFIO_PCI_ERR_IRQ_INDEX) &&
+                    !pci_is_pcie(vdev->pdev))
+                       return -EINVAL;
+
                info.flags = VFIO_IRQ_INFO_EVENTFD;
 
                info.count = vfio_pci_get_irq_count(vdev, info.index);
@@ -538,11 +553,38 @@ static void vfio_pci_remove(struct pci_dev *pdev)
        kfree(vdev);
 }
 
+static pci_ers_result_t vfio_err_detected(struct pci_dev *pdev,
+                               pci_channel_state_t state)
+{
+       struct vfio_pci_device *vpdev;
+       void *vdev;
+
+       vdev = vfio_device_get_from_dev(&pdev->dev);
+       if (vdev == NULL)
+               return PCI_ERS_RESULT_DISCONNECT;
+
+       vpdev = vfio_device_data(vdev);
+       if (vpdev == NULL)
+               return PCI_ERS_RESULT_DISCONNECT;
+
+       if (vpdev->err_trigger)
+               eventfd_signal(vpdev->err_trigger, 1);
+
+       vfio_device_put_vdev(vdev);
+
+       return PCI_ERS_RESULT_CAN_RECOVER;
+}
+
+static const struct pci_error_handlers vfio_err_handlers = {
+       .error_detected = vfio_err_detected,
+};
+
 static struct pci_driver vfio_pci_driver = {
        .name           = "vfio-pci",
        .id_table       = NULL, /* only dynamic ids */
        .probe          = vfio_pci_probe,
        .remove         = vfio_pci_remove,
+       .err_handler    = &vfio_err_handlers,
 };
 
 static void __exit vfio_pci_cleanup(void)
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c 
b/drivers/vfio/pci/vfio_pci_intrs.c
index 3639371..f003e08 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -745,6 +745,31 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_device 
*vdev,
        return 0;
 }
 
+static int vfio_pci_set_err_eventfd(struct vfio_pci_device *vdev,
+                                   unsigned index, unsigned start,
+                                   unsigned count, uint32_t flags, void *data)
+{
+       if ((index == VFIO_PCI_ERR_IRQ_INDEX) &&
+           (flags & VFIO_IRQ_SET_DATA_EVENTFD)   &&
+           pci_is_pcie(vdev->pdev)) {
+
+               int32_t fd = *(int32_t *)data;
+
+               if (fd == -1) {
+                       if (vdev->err_trigger)
+                               eventfd_ctx_put(vdev->err_trigger);
+                       vdev->err_trigger = NULL;
+                       return 0;
+               } else if (fd >= 0) {
+                       vdev->err_trigger = eventfd_ctx_fdget(fd);
+                       if (IS_ERR(vdev->err_trigger))
+                               return PTR_ERR(vdev->err_trigger);
+                       return 0;
+               } else
+                       return -EINVAL;
+       }
+       return -EINVAL;
+}
 int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
                            unsigned index, unsigned start, unsigned count,
                            void *data)
@@ -779,6 +804,13 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, 
uint32_t flags,
                        break;
                }
                break;
+       case VFIO_PCI_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_err_eventfd;
+                       break;
+               }
        }
 
        if (!func)
diff --git a/drivers/vfio/pci/vfio_pci_private.h 
b/drivers/vfio/pci/vfio_pci_private.h
index 611827c..daee62f 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -55,6 +55,7 @@ struct vfio_pci_device {
        bool                    bardirty;
        struct pci_saved_state  *pci_saved_state;
        atomic_t                refcnt;
+       struct eventfd_ctx      *err_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 4758d1b..e81eb4d 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -147,6 +147,8 @@ struct vfio_device_info {
        __u32   flags;
 #define VFIO_DEVICE_FLAGS_RESET        (1 << 0)        /* Device supports 
reset */
 #define VFIO_DEVICE_FLAGS_PCI  (1 << 1)        /* vfio-pci device */
+#define VFIO_DEVICE_FLAGS_PCI_AER      (1 << 2) /* AER capable */
+#define VFIO_DEVICE_FLAGS_PCI_AER_NOTIFY (1 << 3) /* Supports aer notify */
        __u32   num_regions;    /* Max region index + 1 */
        __u32   num_irqs;       /* Max IRQ index + 1 */
 };
@@ -310,6 +312,7 @@ enum {
        VFIO_PCI_INTX_IRQ_INDEX,
        VFIO_PCI_MSI_IRQ_INDEX,
        VFIO_PCI_MSIX_IRQ_INDEX,
+       VFIO_PCI_ERR_IRQ_INDEX,
        VFIO_PCI_NUM_IRQS
 };
 
-- 
1.7.11.3