[Qemu-devel] [PATCH v10 09/10] vfio-pci: pass the aer error to guest

[Cao jin]

From: Chen Fan <address@hidden>

When physical device has uncorrectable error hanppened, the vfio_pci
driver will signal the corresponding QEMU's vfio-pci device via the eventfd
registered by this device, then, the qemu error eventfd handler will be
invoked in event loop.

Construct and pass the aer message to root port, root port will trigger an
interrupt to signal guest, then, the guest driver will do the recovery.

Signed-off-by: Chen Fan <address@hidden>
Signed-off-by: Dou Liyang <address@hidden>
Signed-off-by: Cao jin <address@hidden>
---
 hw/vfio/pci.c | 52 +++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 45 insertions(+), 7 deletions(-)

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index d9236ed..8bdd889 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2716,18 +2716,56 @@ static void vfio_put_device(VFIOPCIDevice *vdev)
 static void vfio_err_notifier_handler(void *opaque)
 {
     VFIOPCIDevice *vdev = opaque;
+    PCIDevice *dev = &vdev->pdev;
+    Error *err = NULL;
+    PCIEAERMsg msg = {
+        .severity = 0,
+        .source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn,
+    };
+    int len;
+    uint64_t uncor_status;
+
+    /* Read the uncorrectable error status from vfio-pci driver via the 
eventfd */
+    len = read(vdev->err_notifier.rfd, &uncor_status, sizeof(uncor_status));
+    if (len != sizeof(uncor_status)) {
+        error_report("vfio-pci: uncor error status reading returns"
+                     " invalid number of bytes: %d", len);
+        return;
+    }
+
+    if (!(vdev->features & VFIO_FEATURE_ENABLE_AER)) {
+        goto stop;
+    }
+
+    /*
+     * In case the actual hardware configuration has been changed,
+     * should re-check the bus reset capability here.
+     */
+    vfio_check_hot_bus_reset(vdev, &err);
+    if (err) {
+        error_report_err(err);
+        goto stop;
+    }
+
+    /* Complete the aer msg and send it to root port */
+    if (dev->exp.aer_cap) {
+        uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+        bool isfatal = uncor_status &
+                       pci_get_long(aer_cap + PCI_ERR_UNCOR_SEVER);
 
-    if (!event_notifier_test_and_clear(&vdev->err_notifier)) {
+        msg.severity = isfatal ? PCI_ERR_ROOT_CMD_FATAL_EN :
+                                 PCI_ERR_ROOT_CMD_NONFATAL_EN;
+ 
+        error_report("vfio-pci device %d sending AER to root port. uncor"
+                     " status = 0x%"PRIx64, dev->devfn, uncor_status);
+        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