Re: [PATCH v5] hw/pci-host: save/restore pci host config register for old ones

[Dr. David Alan Gilbert]

* Michael S. Tsirkin (mst@redhat.com) wrote:
> On Tue, Jul 28, 2020 at 11:27:09AM +0800, Hogan Wang wrote:
> > The i440fx and q35 machines integrate i440FX or MCH PCI device by default.
> > Refer to i440FX and ICH9-LPC spcifications, there are some reserved
> > configuration registers can used to save/restore PCIHostState.config_reg.
> > It's nasty but friendly to old ones.
> > 
> > Reproducer steps:
> > 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.
> > 
> > Signed-off-by: Hogan Wang <hogan.wang@huawei.com>
> > ---
> >  hw/pci-host/i440fx.c | 46 ++++++++++++++++++++++++++++++++++++++++++++
> >  hw/pci-host/q35.c    | 44 ++++++++++++++++++++++++++++++++++++++++++
> >  2 files changed, 90 insertions(+)
> > 
> > diff --git a/hw/pci-host/i440fx.c b/hw/pci-host/i440fx.c
> > index 8ed2417f0c..419e27c21a 100644
> > --- a/hw/pci-host/i440fx.c
> > +++ b/hw/pci-host/i440fx.c
> > @@ -64,6 +64,14 @@ typedef struct I440FXState {
> >   */
> >  #define I440FX_COREBOOT_RAM_SIZE 0x57
> >  
> > +/* Older I440FX machines (5.0 and older) do not support i440FX-pcihost 
> > state
> > + * migration, use some reserved INTEL 82441 configuration registers to
> > + * save/restore i440FX-pcihost config register. Refer to [INTEL 440FX 
> > PCISET
> > + * 82441FX PCI AND MEMORY CONTROLLER (PMC) AND 82442FX DATA BUS ACCELERATOR
> > + * (DBX) Table 1. PMC Configuration Space]
> > + */
> > +#define I440FX_PCI_HOST_CONFIG_REG 0x94
> > +
> >  static void i440fx_update_memory_mappings(PCII440FXState *d)
> >  {
> >      int i;
> > @@ -98,15 +106,53 @@ static void i440fx_write_config(PCIDevice *dev,
> >  static int i440fx_post_load(void *opaque, int version_id)
> >  {
> >      PCII440FXState *d = opaque;
> > +    PCIDevice *dev;
> > +    PCIHostState *s = OBJECT_CHECK(PCIHostState,
> > +                                   object_resolve_path("/machine/i440fx", 
> > NULL),
> > +                                   TYPE_PCI_HOST_BRIDGE);
> >  
> >      i440fx_update_memory_mappings(d);
> > +
> > +    if (!s->mig_enabled) {
> 
> Thinking more about it, I think we should rename mig_enabled to
> config_reg_mig_enabled or something like this.

Agreed.

Dave

> 
> > +        dev = PCI_DEVICE(d);
> > +        s->config_reg = 
> > pci_get_long(&dev->config[I440FX_PCI_HOST_CONFIG_REG]);
> > +        pci_set_long(&dev->config[I440FX_PCI_HOST_CONFIG_REG], 0);
> > +    }
> > +    return 0;
> > +}
> > +
> > +static int i440fx_pre_save(void *opaque)
> > +{
> > +    PCIDevice *dev = opaque;
> > +    PCIHostState *s = OBJECT_CHECK(PCIHostState,
> > +                                   object_resolve_path("/machine/i440fx", 
> > NULL),
> > +                                   TYPE_PCI_HOST_BRIDGE);
> > +    if (!s->mig_enabled) {
> > +        pci_set_long(&dev->config[I440FX_PCI_HOST_CONFIG_REG],
> > +                     s->config_reg);
> > +    }
> > +    return 0;
> > +}
> > +
> > +static int i440fx_post_save(void *opaque)
> > +{
> > +    PCIDevice *dev = opaque;
> > +    PCIHostState *s = OBJECT_CHECK(PCIHostState,
> > +                                   object_resolve_path("/machine/i440fx", 
> > NULL),
> > +                                   TYPE_PCI_HOST_BRIDGE);
> > +    if (!s->mig_enabled) {
> > +        pci_set_long(&dev->config[I440FX_PCI_HOST_CONFIG_REG], 0);
> > +    }
> >      return 0;
> >  }
> >  
> > +
> 
> Extra empty line.
> 
> 
> >  static const VMStateDescription vmstate_i440fx = {
> >      .name = "I440FX",
> >      .version_id = 3,
> >      .minimum_version_id = 3,
> > +    .pre_save = i440fx_pre_save,
> > +    .post_save = i440fx_post_save,
> >      .post_load = i440fx_post_load,
> >      .fields = (VMStateField[]) {
> >          VMSTATE_PCI_DEVICE(parent_obj, PCII440FXState),
> > diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
> > index b67cb9c29f..d87f892945 100644
> > --- a/hw/pci-host/q35.c
> > +++ b/hw/pci-host/q35.c
> > @@ -43,6 +43,14 @@
> >  
> >  #define Q35_PCI_HOST_HOLE64_SIZE_DEFAULT (1ULL << 35)
> >  
> > +/* Older Q35 machines (5.0 and older) do not support q35-pcihost state
> > + * migration, use some reserved INTEL MCH configuration registers to
> > + * save/restore q35-pcihost config register. Refer to [Intel 3 Series
> > + * Chipset Family Datasheet Table 5-1. DRAM Controller Register Address
> > + * Map (D0:F0)]
> > + */
> > +#define Q35_PCI_HOST_CONFIG_REG 0x70
> > +
> >  static void q35_host_realize(DeviceState *dev, Error **errp)
> >  {
> >      PCIHostState *pci = PCI_HOST_BRIDGE(dev);
> > @@ -513,14 +521,50 @@ static void mch_update(MCHPCIState *mch)
> >  static int mch_post_load(void *opaque, int version_id)
> >  {
> >      MCHPCIState *mch = opaque;
> > +    PCIDevice *dev;
> > +    PCIHostState *s = OBJECT_CHECK(PCIHostState,
> > +                                   object_resolve_path("/machine/q35", 
> > NULL),
> > +                                   TYPE_PCI_HOST_BRIDGE);
> >      mch_update(mch);
> > +    if (!s->mig_enabled) {
> > +        dev = PCI_DEVICE(mch);
> > +        s->config_reg = 
> > pci_get_long(&dev->config[Q35_PCI_HOST_CONFIG_REG]);
> > +        pci_set_long(&dev->config[Q35_PCI_HOST_CONFIG_REG], 0);
> > +    }
> > +    return 0;
> > +}
> > +
> > +static int mch_pre_save(void *opaque)
> > +{
> > +    PCIDevice *dev = opaque;
> > +    PCIHostState *s = OBJECT_CHECK(PCIHostState,
> > +                                   object_resolve_path("/machine/q35", 
> > NULL),
> > +                                   TYPE_PCI_HOST_BRIDGE);
> > +    if (!s->mig_enabled) {
> > +        pci_set_long(&dev->config[Q35_PCI_HOST_CONFIG_REG], s->config_reg);
> > +    }
> >      return 0;
> >  }
> >  
> > +static int mch_post_save(void *opaque)
> > +{
> > +    PCIDevice *dev = opaque;
> > +    PCIHostState *s = OBJECT_CHECK(PCIHostState,
> > +                                   object_resolve_path("/machine/q35", 
> > NULL),
> > +                                   TYPE_PCI_HOST_BRIDGE);
> > +    if (!s->mig_enabled) {
> > +        pci_set_long(&dev->config[Q35_PCI_HOST_CONFIG_REG], 0);
> > +    }
> > +    return 0;
> > +}
> > +
> > +
> >  static const VMStateDescription vmstate_mch = {
> >      .name = "mch",
> >      .version_id = 1,
> >      .minimum_version_id = 1,
> > +    .pre_save = mch_pre_save,
> > +    .post_save = mch_post_save,
> >      .post_load = mch_post_load,
> >      .fields = (VMStateField[]) {
> >          VMSTATE_PCI_DEVICE(parent_obj, MCHPCIState),
> > -- 
> > 2.27.0
> > 
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK