Re: [Qemu-devel] [RFC 5/5] vifo: introduce new VFIO ioctl VFIO_DEVICE_PCI_GET_DIRTY_BITMAP

[Alex Williamson]

On Tue, 27 Jun 2017 08:56:01 +0000
"Zhang, Yulei" <address@hidden> wrote:

> > -----Original Message-----
> > From: Qemu-devel [mailto:qemu-devel-
> > address@hidden On Behalf Of Alex Williamson
> > Sent: Tuesday, June 27, 2017 4:19 AM
> > To: Zhang, Yulei <address@hidden>
> > Cc: Tian, Kevin <address@hidden>; address@hidden;
> > address@hidden; address@hidden; Zheng, Xiao
> > <address@hidden>; Wang, Zhi A <address@hidden>
> > Subject: Re: [Qemu-devel] [RFC 5/5] vifo: introduce new VFIO ioctl
> > VFIO_DEVICE_PCI_GET_DIRTY_BITMAP
> > 
> > On Tue,  4 Apr 2017 18:28:04 +0800
> > Yulei Zhang <address@hidden> wrote:
> >   
> > > New VFIO ioctl VFIO_DEVICE_PCI_GET_DIRTY_BITMAP is used to sync the
> > > pci device dirty pages during the migration.  
> > 
> > If this needs to exist, it needs a lot more documentation.  Why is this
> > a PCI specific device ioctl?  Couldn't any vfio device need this?
> >  
> > > Signed-off-by: Yulei Zhang <address@hidden>
> > > ---
> > >  hw/vfio/pci.c              | 32 ++++++++++++++++++++++++++++++++
> > >  hw/vfio/pci.h              |  2 ++
> > >  linux-headers/linux/vfio.h | 14 ++++++++++++++
> > >  3 files changed, 48 insertions(+)
> > >
> > > diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
> > > index 833cd90..64c851f 100644
> > > --- a/hw/vfio/pci.c
> > > +++ b/hw/vfio/pci.c
> > > @@ -32,6 +32,7 @@
> > >  #include "pci.h"
> > >  #include "trace.h"
> > >  #include "qapi/error.h"
> > > +#include "exec/ram_addr.h"
> > >
> > >  #define MSIX_CAP_LENGTH 12
> > >
> > > @@ -39,6 +40,7 @@ static void vfio_disable_interrupts(VFIOPCIDevice  
> > *vdev);  
> > >  static void vfio_mmap_set_enabled(VFIOPCIDevice *vdev, bool enabled);
> > >  static VMStateDescription vfio_pci_vmstate;
> > >  static void vfio_vm_change_state_handler(void *pv, int running, RunState 
> > >  
> > state);  
> > > +static void vfio_log_sync(MemoryListener *listener,  
> > MemoryRegionSection *section);  
> > >
> > >  /*
> > >   * Disabling BAR mmaping can be slow, but toggling it around INTx can
> > > @@ -2869,6 +2871,11 @@ static void vfio_realize(PCIDevice *pdev, Error  
> > **errp)  
> > >      vfio_setup_resetfn_quirk(vdev);
> > >      qemu_add_vm_change_state_handler(vfio_vm_change_state_handler,  
> > vdev);  
> > >
> > > +    vdev->vfio_memory_listener = (MemoryListener) {
> > > +     .log_sync = vfio_log_sync,
> > > +    };
> > > +    memory_listener_register(&vdev->vfio_memory_listener,  
> > &address_space_memory);  
> > > +
> > >      return;
> > >
> > >  out_teardown:
> > > @@ -2964,6 +2971,7 @@ static void vfio_vm_change_state_handler(void  
> > *pv, int running, RunState state)  
> > >      if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_PCI_STATUS_SET, 
> > > vfio_status))  
> > {  
> > >          error_report("vfio: Failed to %s device\n", running ? "start" : 
> > > "stop");
> > >      }
> > > +    vdev->device_stop = running ? false : true;
> > >      g_free(vfio_status);
> > >  }
> > >
> > > @@ -3079,6 +3087,30 @@ static int vfio_device_get(QEMUFile *f, void *pv,  
> > size_t size, VMStateField *fie  
> > >      return 0;
> > >  }
> > >
> > > +static void vfio_log_sync(MemoryListener *listener,  
> > MemoryRegionSection *section)  
> > > +{
> > > +    VFIOPCIDevice *vdev = container_of(listener, struct VFIOPCIDevice,  
> > vfio_memory_listener);  
> > > +
> > > +    if (vdev->device_stop) {
> > > +        struct vfio_pci_get_dirty_bitmap *d;
> > > +        ram_addr_t size = int128_get64(section->size);
> > > +        unsigned long page_nr = size >> TARGET_PAGE_BITS;
> > > +        unsigned long bitmap_size = (BITS_TO_LONGS(page_nr) + 1) *  
> > sizeof(unsigned long);  
> > > +        d = g_malloc0(sizeof(*d) + bitmap_size);
> > > +        d->start_addr = section->offset_within_address_space;
> > > +        d->page_nr = page_nr;
> > > +
> > > +        if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_PCI_GET_DIRTY_BITMAP, 
> > > d))  
> > {  
> > > +            error_report("vfio: Failed to fetch dirty pages for 
> > > migration\n");
> > > +            goto exit;
> > > +        }
> > > +        cpu_physical_memory_set_dirty_lebitmap((unsigned long*)&d-
> > >dirty_bitmap, d->start_addr, d->page_nr);
> > > +
> > > +exit:
> > > +        g_free(d);
> > > +    }
> > > +}
> > > +
> > >  static void vfio_instance_init(Object *obj)
> > >  {
> > >      PCIDevice *pci_dev = PCI_DEVICE(obj);
> > > diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
> > > index bd98618..984391d 100644
> > > --- a/hw/vfio/pci.h
> > > +++ b/hw/vfio/pci.h
> > > @@ -144,6 +144,8 @@ typedef struct VFIOPCIDevice {
> > >      bool no_kvm_intx;
> > >      bool no_kvm_msi;
> > >      bool no_kvm_msix;
> > > +    bool device_stop;
> > > +    MemoryListener vfio_memory_listener;
> > >  } VFIOPCIDevice;
> > >
> > >  uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);
> > > diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
> > > index fa17848..aa73ee1 100644
> > > --- a/linux-headers/linux/vfio.h
> > > +++ b/linux-headers/linux/vfio.h
> > > @@ -502,6 +502,20 @@ struct vfio_pci_status_set{
> > >
> > >  #define VFIO_DEVICE_PCI_STATUS_SET       _IO(VFIO_TYPE, VFIO_BASE + 14)
> > >
> > > +/**
> > > + * VFIO_DEVICE_PCI_GET_DIRTY_BITMAP - _IOW(VFIO_TYPE, VFIO_BASE +  
> > 15,  
> > > + *                                   struct vfio_pci_get_dirty_bitmap)
> > > + *
> > > + * Return: 0 on success, -errno on failure.
> > > + */
> > > +struct vfio_pci_get_dirty_bitmap{
> > > + __u64          start_addr;
> > > + __u64          page_nr;
> > > + __u8           dirty_bitmap[];
> > > +};
> > > +
> > > +#define VFIO_DEVICE_PCI_GET_DIRTY_BITMAP _IO(VFIO_TYPE, VFIO_BASE  
> > + 15)  
> > > +  
> > 
> > Dirty since when?  Since the last time we asked?  Since the device was
> > stopped?  Why is anything dirtied after the device is stopped?  Is this
> > any pages the device has ever touched?  Thanks,
> > 
> > Alex  
> Dirty since the device start operation and before it was stopped. We track
> down all the guest pages that device was using before it was stopped, and
> leverage this dirty bitmap for page sync during migration.

I don't understand how this is useful or efficient.  This implies that
the device is always tracking dirtied pages even when we don't care
about migration.  Don't we want to enable dirty logging at some point
and track dirty pages since then?  Otherwise we can just assume the
device dirties all pages and get rid of this ioctl.  Thanks,

Alex