hw/pci-host: save/restore pci host config register

The pci host config register is used to save PCI address for
read/write config data. If guest writes a value to config register,
and then QEMU pauses the vcpu to migrate, after the migration, the guest
will continue to write pci config data, and the write data will be ignored
because of new qemu process losing the config register state.

To trigger the bug:
1. guest is booting in seabios.
2. guest enables the SMRAM in seabios:piix4_apmc_smm_setup, and then
   expects to disable the SMRAM by pci_config_writeb.
3. after guest writes the pci host config register, QEMU pauses vcpu
   to finish migration.
4. guest write of config data(0x0A) fails to disable the SMRAM because
   the config register state is lost.
5. guest continues to boot and crashes in ipxe option ROM due to SMRAM
   in enabled state.

Example Reproducer:

step 1. Make modifications to seabios and qemu for increase reproduction
efficiency, write 0xf0 to 0x402 port notify qemu to stop vcpu after
0x0cf8 port wrote i440 configure register. qemu stop vcpu when catch
0x402 port wrote 0xf0.

seabios:/src/hw/pci.c
@@ -52,6 +52,11 @@ void pci_config_writeb(u16 bdf, u32 addr, u8 val)
         writeb(mmconfig_addr(bdf, addr), val);
     } else {
         outl(ioconfig_cmd(bdf, addr), PORT_PCI_CMD);
+       if (bdf == 0 && addr == 0x72 && val == 0xa) {
+            dprintf(1, "stop vcpu\n");
+            outb(0xf0, 0x402); // notify qemu to stop vcpu
+            dprintf(1, "resume vcpu\n");
+        }
         outb(val, PORT_PCI_DATA + (addr & 3));
     }
 }

qemu:hw/char/debugcon.c
@@ -60,6 +61,9 @@ static void debugcon_ioport_write(void *opaque, hwaddr addr, uint64_t val,
     printf(" [debugcon: write addr=0x%04" HWADDR_PRIx " val=0x%02" PRIx64 "]\n", addr, val);
 #endif

+    if (ch == 0xf0) {
+        vm_stop(RUN_STATE_PAUSED);
+    }
     /* XXX this blocks entire thread. Rewrite to use
      * qemu_chr_fe_write and background I/O callbacks */
     qemu_chr_fe_write_all(&s->chr, &ch, 1);

step 2. start vm1 by the following command line, and then vm stopped.
$ qemu-system-x86_64 -machine pc-i440fx-5.0,accel=kvm\
 -netdev tap,ifname=tap-test,id=hostnet0,vhost=on,downscript=no,script=no\
 -device virtio-net-pci,netdev=hostnet0,id=net0,bus=pci.0,addr=0x13,bootindex=3\
 -device cirrus-vga,id=video0,vgamem_mb=16,bus=pci.0,addr=0x2\
 -chardev file,id=seabios,path=/var/log/test.seabios,append=on\
 -device isa-debugcon,iobase=0x402,chardev=seabios\
 -monitor stdio

step 3. start vm2 to accept vm1 state.
$ qemu-system-x86_64 -machine pc-i440fx-5.0,accel=kvm\
 -netdev tap,ifname=tap-test1,id=hostnet0,vhost=on,downscript=no,script=no\
 -device virtio-net-pci,netdev=hostnet0,id=net0,bus=pci.0,addr=0x13,bootindex=3\
 -device cirrus-vga,id=video0,vgamem_mb=16,bus=pci.0,addr=0x2\
 -chardev file,id=seabios,path=/var/log/test.seabios,append=on\
 -device isa-debugcon,iobase=0x402,chardev=seabios\
 -monitor stdio \
 -incoming tcp:127.0.0.1:8000

step 4. execute the following qmp command in vm1 to migrate.
(qemu) migrate tcp:127.0.0.1:8000

step 5. execute the following qmp command in vm2 to resume vcpu.
(qemu) cont
Before this patch, we get KVM "emulation failure" error on vm2.
This patch fixes it.

Cc: qemu-stable@nongnu.org
Signed-off-by: Hogan Wang <hogan.wang@huawei.com>
Message-Id: <20200727084621.3279-1-hogan.wang@huawei.com>
Reported-by: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

hw/core/machine.c

@@ -29,6 +29,7 @@
 #include "migration/vmstate.h"
 
 GlobalProperty hw_compat_5_0[] = {
+    { "pci-host-bridge", "x-config-reg-migration-enabled", "off" },
     { "virtio-balloon-device", "page-poison", "false" },
     { "vmport", "x-read-set-eax", "off" },
     { "vmport", "x-signal-unsupported-cmd", "off" },

hw/i386/pc.c

@@ -97,7 +97,8 @@
 #include "fw_cfg.h"
 #include "trace.h"
 
-GlobalProperty pc_compat_5_0[] = {};
+GlobalProperty pc_compat_5_0[] = {
+};
 const size_t pc_compat_5_0_len = G_N_ELEMENTS(pc_compat_5_0);
 
 GlobalProperty pc_compat_4_2[] = {

hw/pci/pci_host.c

@@ -22,8 +22,10 @@
 #include "hw/pci/pci.h"
 #include "hw/pci/pci_bridge.h"
 #include "hw/pci/pci_host.h"
+#include "hw/qdev-properties.h"
 #include "qemu/module.h"
 #include "hw/pci/pci_bus.h"
+#include "migration/vmstate.h"
 #include "trace.h"
 
 /* debug PCI */
@@ -200,12 +202,43 @@ const MemoryRegionOps pci_host_data_be_ops = {
     .endianness = DEVICE_BIG_ENDIAN,
 };
 
+static bool pci_host_needed(void *opaque)
+{
+    PCIHostState *s = opaque;
+    return s->mig_enabled;
+}
+
+const VMStateDescription vmstate_pcihost = {
+    .name = "PCIHost",
+    .needed = pci_host_needed,
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(config_reg, PCIHostState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static Property pci_host_properties_common[] = {
+    DEFINE_PROP_BOOL("x-config-reg-migration-enabled", PCIHostState,
+                     mig_enabled, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void pci_host_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    device_class_set_props(dc, pci_host_properties_common);
+    dc->vmsd = &vmstate_pcihost;
+}
+
 static const TypeInfo pci_host_type_info = {
     .name = TYPE_PCI_HOST_BRIDGE,
     .parent = TYPE_SYS_BUS_DEVICE,
     .abstract = true,
     .class_size = sizeof(PCIHostBridgeClass),
     .instance_size = sizeof(PCIHostState),
+    .class_init = pci_host_class_init,
 };
 
 static void pci_host_register_types(void)

include/hw/pci/pci_host.h

@@ -45,6 +45,7 @@ struct PCIHostState {
     MemoryRegion data_mem;
     MemoryRegion mmcfg;
     uint32_t config_reg;
+    bool mig_enabled;
     PCIBus *bus;
 
     QLIST_ENTRY(PCIHostState) next;