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

when the vfio device encounters an uncorrectable error in host,
the vfio_pci driver will signal the eventfd registered by this
vfio device, the results in the qemu eventfd handler getting
invoked.

this patch is to pass the error to guest and have the guest driver
recover from the error.

Signed-off-by: Chen Fan <chen.fan.f...@cn.fujitsu.com>
---
 hw/vfio/pci.c | 45 +++++++++++++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 90df393..c593876 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2523,18 +2523,51 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
 static void vfio_err_notifier_handler(void *opaque)
 {
     VFIOPCIDevice *vdev = opaque;
+    PCIDevice *dev = &vdev->pdev;
+    PCIEAERMsg msg = {
+        .severity = 0,
+        .source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn,
+    };
 
     if (!event_notifier_test_and_clear(&vdev->err_notifier)) {
         return;
     }
 
     /*
-     * TBD. Retrieve the error details and decide what action
-     * needs to be taken. One of the actions could be to pass
-     * the error to the guest and have the guest driver recover
-     * from the error. This requires that PCIe capabilities be
-     * exposed to the guest. For now, we just terminate the
-     * guest to contain the error.
+     * in case the real hardware configration has been changed,
+     * here we should recheck the bus reset capability.
+     */
+    if ((vdev->features & VFIO_FEATURE_ENABLE_AER) &&
+        vfio_check_host_bus_reset(vdev)) {
+        goto stop;
+    }
+    /*
+     * we should read the error details from the real hardware
+     * configuration spaces, here we only need to do is signaling
+     * to guest an uncorrectable error has occurred.
+     */
+    if ((vdev->features & VFIO_FEATURE_ENABLE_AER) &&
+        dev->exp.aer_cap) {
+        uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+        uint32_t uncor_status;
+        bool isfatal;
+
+        uncor_status = vfio_pci_read_config(dev,
+                           dev->exp.aer_cap + PCI_ERR_UNCOR_STATUS, 4);
+
+        isfatal = uncor_status & pci_get_long(aer_cap + PCI_ERR_UNCOR_SEVER);
+
+        msg.severity = isfatal ? PCI_ERR_ROOT_CMD_FATAL_EN :
+                                 PCI_ERR_ROOT_CMD_NONFATAL_EN;
+
+        pcie_aer_msg(dev, &msg);
+        return;
+    }
+
+stop:
+    /*
+     * If the aer capability is not exposed to the guest. we just
+     * terminate the guest to contain the error.
      */
 
     error_report("%s(%04x:%02x:%02x.%x) Unrecoverable error detected.  "
-- 
1.9.3


Reply via email to