[Qemu-devel] [PATCH v9 09/11] vfio-pci: pass the aer error to guest

[Zhou Jie]

From: Chen Fan <address@hidden>

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

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

Signed-off-by: Chen Fan <address@hidden>
---
 hw/vfio/pci.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 54 insertions(+), 6 deletions(-)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 0521652..0e42786 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2627,18 +2627,66 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
 static void vfio_err_notifier_handler(void *opaque)
 {
     VFIOPCIDevice *vdev = opaque;
+    PCIDevice *dev = &vdev->pdev;
+    Error *local_err = NULL;
+    PCIEAERMsg msg = {
+        .severity = 0,
+        .source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn,
+    };
 
     if (!event_notifier_test_and_clear(&vdev->err_notifier)) {
         return;
     }
 
+
+    if (!(vdev->features & VFIO_FEATURE_ENABLE_AER)) {
+        goto stop;
+    }
+
+    /*
+     * in case the real hardware configuration has been changed,
+     * here we should recheck the bus reset capability.
+     */
+    vfio_check_hot_bus_reset(vdev, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        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 (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);
+
+        /*
+         * if the error is not emitted by this device, we can
+         * just ignore it.
+         */
+        if (!(uncor_status & ~0UL)) {
+            return;
+        }
+
+        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:
     /*
-     * 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.
+     * If the aer capability is not exposed to the guest. we just
+     * terminate the guest to contain the error.
      */
 
     error_report("%s(%s) Unrecoverable error detected. Please collect any data 
possible and then kill the guest", __func__, vdev->vbasedev.name);
-- 
1.8.3.1