[v27,05/17] vfio: Add VM state change handler to know state of VM

Commit Message

Kirti Wankhede Oct. 22, 2020, 11:11 a.m. UTC

VM state change handler is called on change in VM's state. Based on
VM state, VFIO device state should be changed.
Added read/write helper functions for migration region.
Added function to set device_state.

Signed-off-by: Kirti Wankhede <[e-mail]>
Reviewed-by: Neo Jia <[e-mail]>
Reviewed-by: Dr. David Alan Gilbert <[e-mail]>
---
 hw/vfio/migration.c           | 158 ++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/trace-events          |   2 +
 include/hw/vfio/vfio-common.h |   4 ++
 3 files changed, 164 insertions(+)

Comments

Alex Williamson Oct. 22, 2020, 4:35 p.m. UTC | #1

On Thu, 22 Oct 2020 16:41:55 +0530
Kirti Wankhede <[e-mail]> wrote:

> VM state change handler is called on change in VM's state. Based on
> VM state, VFIO device state should be changed.
> Added read/write helper functions for migration region.
> Added function to set device_state.
> 
> Signed-off-by: Kirti Wankhede <[e-mail]>
> Reviewed-by: Neo Jia <[e-mail]>
> Reviewed-by: Dr. David Alan Gilbert <[e-mail]>
> ---
>  hw/vfio/migration.c           | 158 ++++++++++++++++++++++++++++++++++++++++++
>  hw/vfio/trace-events          |   2 +
>  include/hw/vfio/vfio-common.h |   4 ++
>  3 files changed, 164 insertions(+)
> 
> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> index 5f74a3ad1d72..34f39c7e2e28 100644
> --- a/hw/vfio/migration.c
> +++ b/hw/vfio/migration.c
> @@ -10,6 +10,7 @@
>  #include "qemu/osdep.h"
>  #include <linux/vfio.h>
>  
> +#include "sysemu/runstate.h"
>  #include "hw/vfio/vfio-common.h"
>  #include "cpu.h"
>  #include "migration/migration.h"
> @@ -22,6 +23,157 @@
>  #include "exec/ram_addr.h"
>  #include "pci.h"
>  #include "trace.h"
> +#include "hw/hw.h"
> +
> +static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
> +                                  off_t off, bool iswrite)
> +{
> +    int ret;
> +
> +    ret = iswrite ? pwrite(vbasedev->fd, val, count, off) :
> +                    pread(vbasedev->fd, val, count, off);
> +    if (ret < count) {
> +        error_report("vfio_mig_%s %d byte %s: failed at offset 0x%lx, err: %s",
> +                     iswrite ? "write" : "read", count,
> +                     vbasedev->name, off, strerror(errno));
> +        return (ret < 0) ? ret : -EINVAL;
> +    }
> +    return 0;
> +}
> +
> +static int vfio_mig_rw(VFIODevice *vbasedev, __u8 *buf, size_t count,
> +                       off_t off, bool iswrite)
> +{
> +    int ret, done = 0;
> +    __u8 *tbuf = buf;
> +
> +    while (count) {
> +        int bytes = 0;
> +
> +        if (count >= 8 && !(off % 8)) {
> +            bytes = 8;
> +        } else if (count >= 4 && !(off % 4)) {
> +            bytes = 4;
> +        } else if (count >= 2 && !(off % 2)) {
> +            bytes = 2;
> +        } else {
> +            bytes = 1;
> +        }
> +
> +        ret = vfio_mig_access(vbasedev, tbuf, bytes, off, iswrite);
> +        if (ret) {
> +            return ret;
> +        }
> +
> +        count -= bytes;
> +        done += bytes;
> +        off += bytes;
> +        tbuf += bytes;
> +    }
> +    return done;
> +}
> +
> +#define vfio_mig_read(f, v, c, o)       vfio_mig_rw(f, (__u8 *)v, c, o, false)
> +#define vfio_mig_write(f, v, c, o)      vfio_mig_rw(f, (__u8 *)v, c, o, true)
> +
> +#define VFIO_MIG_STRUCT_OFFSET(f)       \
> +                                 offsetof(struct vfio_device_migration_info, f)
> +/*
> + * Change the device_state register for device @vbasedev. Bits set in @mask
> + * are preserved, bits set in @value are set, and bits not set in either @mask
> + * or @value are cleared in device_state. If the register cannot be accessed,
> + * the resulting state would be invalid, or the device enters an error state,
> + * an error is returned.
> + */
> +
> +static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t mask,
> +                                    uint32_t value)
> +{
> +    VFIOMigration *migration = vbasedev->migration;
> +    VFIORegion *region = &migration->region;
> +    off_t dev_state_off = region->fd_offset +
> +                          VFIO_MIG_STRUCT_OFFSET(device_state);
> +    uint32_t device_state;
> +    int ret;
> +
> +    ret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
> +                        dev_state_off);
> +    if (ret < 0) {
> +        return ret;
> +    }
> +
> +    device_state = (device_state & mask) | value;
> +
> +    if (!VFIO_DEVICE_STATE_VALID(device_state)) {
> +        return -EINVAL;
> +    }
> +
> +    ret = vfio_mig_write(vbasedev, &device_state, sizeof(device_state),
> +                         dev_state_off);
> +    if (ret < 0) {
> +        int rret;
> +
> +        rret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
> +                             dev_state_off);
> +
> +        if ((rret < 0) || (VFIO_DEVICE_STATE_IS_ERROR(device_state))) {
> +            hw_error("%s: Device in error state 0x%x", vbasedev->name,
> +                     device_state);
> +            return rret ? rret : -EIO;
> +        }
> +        return ret;
> +    }
> +
> +    migration->device_state = device_state;
> +    trace_vfio_migration_set_state(vbasedev->name, device_state);
> +    return 0;
> +}
> +
> +static void vfio_vmstate_change(void *opaque, int running, RunState state)
> +{
> +    VFIODevice *vbasedev = opaque;
> +    VFIOMigration *migration = vbasedev->migration;
> +    uint32_t value, mask;
> +    int ret;
> +
> +    if ((vbasedev->migration->vm_running == running)) {
> +        return;
> +    }
> +
> +    if (running) {
> +        /*
> +         * Here device state can have one of _SAVING, _RESUMING or _STOP bit.
> +         * Transition from _SAVING to _RUNNING can happen if there is migration
> +         * failure, in that case clear _SAVING bit.
> +         * Transition from _RESUMING to _RUNNING occurs during resuming
> +         * phase, in that case clear _RESUMING bit.
> +         * In both the above cases, set _RUNNING bit.
> +         */
> +        mask = ~VFIO_DEVICE_STATE_MASK;
> +        value = VFIO_DEVICE_STATE_RUNNING;
> +    } else {
> +        /*
> +         * Here device state could be either _RUNNING or _SAVING|_RUNNING. Reset
> +         * _RUNNING bit
> +         */
> +        mask = ~VFIO_DEVICE_STATE_RUNNING;
> +        value = 0;
> +    }
> +
> +    ret = vfio_migration_set_state(vbasedev, mask, value);
> +    if (ret) {
> +        /*
> +         * Migration should be aborted in this case, but vm_state_notify()
> +         * currently does not support reporting failures.
> +         */
> +        error_report("%s: Failed to set device state 0x%x", vbasedev->name,
> +                     (migration->device_state & mask) | value);
> +        qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
> +    }
> +    vbasedev->migration->vm_running = running;
> +    trace_vfio_vmstate_change(vbasedev->name, running, RunState_str(state),
> +            (migration->device_state & mask) | value);
> +}
>  
>  static void vfio_migration_region_exit(VFIODevice *vbasedev)
>  {
> @@ -71,6 +223,8 @@ static int vfio_migration_init(VFIODevice *vbasedev,
>      }
>  
>      vbasedev->migration = migration;
> +    migration->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
> +                                                          vbasedev);
>      return 0;
>  
>  err:
> @@ -118,6 +272,10 @@ add_blocker:
>  
>  void vfio_migration_finalize(VFIODevice *vbasedev)
>  {
> +    if (vbasedev->migration->vm_state) {
> +        qemu_del_vm_change_state_handler(vbasedev->migration->vm_state);
> +    }


This looks like a segfault, vfio_migration_teardown() is eventually
called unconditionally.  The next patch modifies this function further,
but never checks that vbasedev->migration is non-NULL.  Thanks,

Alex


> +
>      if (vbasedev->migration_blocker) {
>          migrate_del_blocker(vbasedev->migration_blocker);
>          error_free(vbasedev->migration_blocker);
> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> index 9ced5ec6277c..41de81f12f60 100644
> --- a/hw/vfio/trace-events
> +++ b/hw/vfio/trace-events
> @@ -148,3 +148,5 @@ vfio_display_edid_write_error(void) ""
>  
>  # migration.c
>  vfio_migration_probe(const char *name, uint32_t index) " (%s) Region %d"
> +vfio_migration_set_state(const char *name, uint32_t state) " (%s) state %d"
> +vfio_vmstate_change(const char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d"
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index 8275c4c68f45..9a571f1fb552 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -29,6 +29,7 @@
>  #ifdef CONFIG_LINUX
>  #include <linux/vfio.h>
>  #endif
> +#include "sysemu/sysemu.h"
>  
>  #define VFIO_MSG_PREFIX "vfio %s: "
>  
> @@ -58,7 +59,10 @@ typedef struct VFIORegion {
>  } VFIORegion;
>  
>  typedef struct VFIOMigration {
> +    VMChangeStateEntry *vm_state;
>      VFIORegion region;
> +    uint32_t device_state;
> +    int vm_running;
>  } VFIOMigration;
>  
>  typedef struct VFIOAddressSpace {

Kirti Wankhede Oct. 22, 2020, 5:41 p.m. UTC | #2

On 10/22/2020 10:05 PM, Alex Williamson wrote:
> On Thu, 22 Oct 2020 16:41:55 +0530
> Kirti Wankhede <[e-mail]> wrote:
> 
>> VM state change handler is called on change in VM's state. Based on
>> VM state, VFIO device state should be changed.
>> Added read/write helper functions for migration region.
>> Added function to set device_state.
>>
>> Signed-off-by: Kirti Wankhede <[e-mail]>
>> Reviewed-by: Neo Jia <[e-mail]>
>> Reviewed-by: Dr. David Alan Gilbert <[e-mail]>
>> ---
>>   hw/vfio/migration.c           | 158 ++++++++++++++++++++++++++++++++++++++++++
>>   hw/vfio/trace-events          |   2 +
>>   include/hw/vfio/vfio-common.h |   4 ++
>>   3 files changed, 164 insertions(+)
>>
>> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
>> index 5f74a3ad1d72..34f39c7e2e28 100644
>> --- a/hw/vfio/migration.c
>> +++ b/hw/vfio/migration.c
>> @@ -10,6 +10,7 @@
>>   #include "qemu/osdep.h"
>>   #include <linux/vfio.h>
>>   
>> +#include "sysemu/runstate.h"
>>   #include "hw/vfio/vfio-common.h"
>>   #include "cpu.h"
>>   #include "migration/migration.h"
>> @@ -22,6 +23,157 @@
>>   #include "exec/ram_addr.h"
>>   #include "pci.h"
>>   #include "trace.h"
>> +#include "hw/hw.h"
>> +
>> +static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
>> +                                  off_t off, bool iswrite)
>> +{
>> +    int ret;
>> +
>> +    ret = iswrite ? pwrite(vbasedev->fd, val, count, off) :
>> +                    pread(vbasedev->fd, val, count, off);
>> +    if (ret < count) {
>> +        error_report("vfio_mig_%s %d byte %s: failed at offset 0x%lx, err: %s",
>> +                     iswrite ? "write" : "read", count,
>> +                     vbasedev->name, off, strerror(errno));
>> +        return (ret < 0) ? ret : -EINVAL;
>> +    }
>> +    return 0;
>> +}
>> +
>> +static int vfio_mig_rw(VFIODevice *vbasedev, __u8 *buf, size_t count,
>> +                       off_t off, bool iswrite)
>> +{
>> +    int ret, done = 0;
>> +    __u8 *tbuf = buf;
>> +
>> +    while (count) {
>> +        int bytes = 0;
>> +
>> +        if (count >= 8 && !(off % 8)) {
>> +            bytes = 8;
>> +        } else if (count >= 4 && !(off % 4)) {
>> +            bytes = 4;
>> +        } else if (count >= 2 && !(off % 2)) {
>> +            bytes = 2;
>> +        } else {
>> +            bytes = 1;
>> +        }
>> +
>> +        ret = vfio_mig_access(vbasedev, tbuf, bytes, off, iswrite);
>> +        if (ret) {
>> +            return ret;
>> +        }
>> +
>> +        count -= bytes;
>> +        done += bytes;
>> +        off += bytes;
>> +        tbuf += bytes;
>> +    }
>> +    return done;
>> +}
>> +
>> +#define vfio_mig_read(f, v, c, o)       vfio_mig_rw(f, (__u8 *)v, c, o, false)
>> +#define vfio_mig_write(f, v, c, o)      vfio_mig_rw(f, (__u8 *)v, c, o, true)
>> +
>> +#define VFIO_MIG_STRUCT_OFFSET(f)       \
>> +                                 offsetof(struct vfio_device_migration_info, f)
>> +/*
>> + * Change the device_state register for device @vbasedev. Bits set in @mask
>> + * are preserved, bits set in @value are set, and bits not set in either @mask
>> + * or @value are cleared in device_state. If the register cannot be accessed,
>> + * the resulting state would be invalid, or the device enters an error state,
>> + * an error is returned.
>> + */
>> +
>> +static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t mask,
>> +                                    uint32_t value)
>> +{
>> +    VFIOMigration *migration = vbasedev->migration;
>> +    VFIORegion *region = &migration->region;
>> +    off_t dev_state_off = region->fd_offset +
>> +                          VFIO_MIG_STRUCT_OFFSET(device_state);
>> +    uint32_t device_state;
>> +    int ret;
>> +
>> +    ret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
>> +                        dev_state_off);
>> +    if (ret < 0) {
>> +        return ret;
>> +    }
>> +
>> +    device_state = (device_state & mask) | value;
>> +
>> +    if (!VFIO_DEVICE_STATE_VALID(device_state)) {
>> +        return -EINVAL;
>> +    }
>> +
>> +    ret = vfio_mig_write(vbasedev, &device_state, sizeof(device_state),
>> +                         dev_state_off);
>> +    if (ret < 0) {
>> +        int rret;
>> +
>> +        rret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
>> +                             dev_state_off);
>> +
>> +        if ((rret < 0) || (VFIO_DEVICE_STATE_IS_ERROR(device_state))) {
>> +            hw_error("%s: Device in error state 0x%x", vbasedev->name,
>> +                     device_state);
>> +            return rret ? rret : -EIO;
>> +        }
>> +        return ret;
>> +    }
>> +
>> +    migration->device_state = device_state;
>> +    trace_vfio_migration_set_state(vbasedev->name, device_state);
>> +    return 0;
>> +}
>> +
>> +static void vfio_vmstate_change(void *opaque, int running, RunState state)
>> +{
>> +    VFIODevice *vbasedev = opaque;
>> +    VFIOMigration *migration = vbasedev->migration;
>> +    uint32_t value, mask;
>> +    int ret;
>> +
>> +    if ((vbasedev->migration->vm_running == running)) {
>> +        return;
>> +    }
>> +
>> +    if (running) {
>> +        /*
>> +         * Here device state can have one of _SAVING, _RESUMING or _STOP bit.
>> +         * Transition from _SAVING to _RUNNING can happen if there is migration
>> +         * failure, in that case clear _SAVING bit.
>> +         * Transition from _RESUMING to _RUNNING occurs during resuming
>> +         * phase, in that case clear _RESUMING bit.
>> +         * In both the above cases, set _RUNNING bit.
>> +         */
>> +        mask = ~VFIO_DEVICE_STATE_MASK;
>> +        value = VFIO_DEVICE_STATE_RUNNING;
>> +    } else {
>> +        /*
>> +         * Here device state could be either _RUNNING or _SAVING|_RUNNING. Reset
>> +         * _RUNNING bit
>> +         */
>> +        mask = ~VFIO_DEVICE_STATE_RUNNING;
>> +        value = 0;
>> +    }
>> +
>> +    ret = vfio_migration_set_state(vbasedev, mask, value);
>> +    if (ret) {
>> +        /*
>> +         * Migration should be aborted in this case, but vm_state_notify()
>> +         * currently does not support reporting failures.
>> +         */
>> +        error_report("%s: Failed to set device state 0x%x", vbasedev->name,
>> +                     (migration->device_state & mask) | value);
>> +        qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
>> +    }
>> +    vbasedev->migration->vm_running = running;
>> +    trace_vfio_vmstate_change(vbasedev->name, running, RunState_str(state),
>> +            (migration->device_state & mask) | value);
>> +}
>>   
>>   static void vfio_migration_region_exit(VFIODevice *vbasedev)
>>   {
>> @@ -71,6 +223,8 @@ static int vfio_migration_init(VFIODevice *vbasedev,
>>       }
>>   
>>       vbasedev->migration = migration;
>> +    migration->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
>> +                                                          vbasedev);
>>       return 0;
>>   
>>   err:
>> @@ -118,6 +272,10 @@ add_blocker:
>>   
>>   void vfio_migration_finalize(VFIODevice *vbasedev)
>>   {
>> +    if (vbasedev->migration->vm_state) {
>> +        qemu_del_vm_change_state_handler(vbasedev->migration->vm_state);
>> +    }
> 
> 
> This looks like a segfault, vfio_migration_teardown() is eventually
> called unconditionally.  The next patch modifies this function further,
> but never checks that vbasedev->migration is non-NULL.  Thanks,
> 

Yup.
Updated patch 4, 5 and 6. So now vfio_migration_finalize() looks like:

void vfio_migration_finalize(VFIODevice *vbasedev)
{
     VFIOMigration *migration = vbasedev->migration;

     if (migration) {
         if (migration->migration_state.notify) {
 
remove_migration_state_change_notifier(&migration->migration_state);
         }

         if (migration->vm_state) {
             qemu_del_vm_change_state_handler(migration->vm_state);
         }

         vfio_migration_region_exit(vbasedev);
         g_free(vbasedev->migration);
         vbasedev->migration = NULL;
     }

     if (vbasedev->migration_blocker) {
         migrate_del_blocker(vbasedev->migration_blocker);
         error_free(vbasedev->migration_blocker);
         vbasedev->migration_blocker = NULL;
     }
}

Thanks,
Kirti

> Alex
> 
> 
>> +
>>       if (vbasedev->migration_blocker) {
>>           migrate_del_blocker(vbasedev->migration_blocker);
>>           error_free(vbasedev->migration_blocker);
>> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
>> index 9ced5ec6277c..41de81f12f60 100644
>> --- a/hw/vfio/trace-events
>> +++ b/hw/vfio/trace-events
>> @@ -148,3 +148,5 @@ vfio_display_edid_write_error(void) ""
>>   
>>   # migration.c
>>   vfio_migration_probe(const char *name, uint32_t index) " (%s) Region %d"
>> +vfio_migration_set_state(const char *name, uint32_t state) " (%s) state %d"
>> +vfio_vmstate_change(const char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d"
>> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
>> index 8275c4c68f45..9a571f1fb552 100644
>> --- a/include/hw/vfio/vfio-common.h
>> +++ b/include/hw/vfio/vfio-common.h
>> @@ -29,6 +29,7 @@
>>   #ifdef CONFIG_LINUX
>>   #include <linux/vfio.h>
>>   #endif
>> +#include "sysemu/sysemu.h"
>>   
>>   #define VFIO_MSG_PREFIX "vfio %s: "
>>   
>> @@ -58,7 +59,10 @@ typedef struct VFIORegion {
>>   } VFIORegion;
>>   
>>   typedef struct VFIOMigration {
>> +    VMChangeStateEntry *vm_state;
>>       VFIORegion region;
>> +    uint32_t device_state;
>> +    int vm_running;
>>   } VFIOMigration;
>>   
>>   typedef struct VFIOAddressSpace {
>

Alex Williamson Oct. 22, 2020, 6:29 p.m. UTC | #3

On Thu, 22 Oct 2020 23:11:39 +0530
Kirti Wankhede <[e-mail]> wrote:

> On 10/22/2020 10:05 PM, Alex Williamson wrote:
> > On Thu, 22 Oct 2020 16:41:55 +0530
> > Kirti Wankhede <[e-mail]> wrote:
> >   
> >> VM state change handler is called on change in VM's state. Based on
> >> VM state, VFIO device state should be changed.
> >> Added read/write helper functions for migration region.
> >> Added function to set device_state.
> >>
> >> Signed-off-by: Kirti Wankhede <[e-mail]>
> >> Reviewed-by: Neo Jia <[e-mail]>
> >> Reviewed-by: Dr. David Alan Gilbert <[e-mail]>
> >> ---
> >>   hw/vfio/migration.c           | 158 ++++++++++++++++++++++++++++++++++++++++++
> >>   hw/vfio/trace-events          |   2 +
> >>   include/hw/vfio/vfio-common.h |   4 ++
> >>   3 files changed, 164 insertions(+)
> >>
> >> diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
> >> index 5f74a3ad1d72..34f39c7e2e28 100644
> >> --- a/hw/vfio/migration.c
> >> +++ b/hw/vfio/migration.c
> >> @@ -10,6 +10,7 @@
> >>   #include "qemu/osdep.h"
> >>   #include <linux/vfio.h>
> >>   
> >> +#include "sysemu/runstate.h"
> >>   #include "hw/vfio/vfio-common.h"
> >>   #include "cpu.h"
> >>   #include "migration/migration.h"
> >> @@ -22,6 +23,157 @@
> >>   #include "exec/ram_addr.h"
> >>   #include "pci.h"
> >>   #include "trace.h"
> >> +#include "hw/hw.h"
> >> +
> >> +static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
> >> +                                  off_t off, bool iswrite)
> >> +{
> >> +    int ret;
> >> +
> >> +    ret = iswrite ? pwrite(vbasedev->fd, val, count, off) :
> >> +                    pread(vbasedev->fd, val, count, off);
> >> +    if (ret < count) {
> >> +        error_report("vfio_mig_%s %d byte %s: failed at offset 0x%lx, err: %s",
> >> +                     iswrite ? "write" : "read", count,
> >> +                     vbasedev->name, off, strerror(errno));
> >> +        return (ret < 0) ? ret : -EINVAL;
> >> +    }
> >> +    return 0;
> >> +}
> >> +
> >> +static int vfio_mig_rw(VFIODevice *vbasedev, __u8 *buf, size_t count,
> >> +                       off_t off, bool iswrite)
> >> +{
> >> +    int ret, done = 0;
> >> +    __u8 *tbuf = buf;
> >> +
> >> +    while (count) {
> >> +        int bytes = 0;
> >> +
> >> +        if (count >= 8 && !(off % 8)) {
> >> +            bytes = 8;
> >> +        } else if (count >= 4 && !(off % 4)) {
> >> +            bytes = 4;
> >> +        } else if (count >= 2 && !(off % 2)) {
> >> +            bytes = 2;
> >> +        } else {
> >> +            bytes = 1;
> >> +        }
> >> +
> >> +        ret = vfio_mig_access(vbasedev, tbuf, bytes, off, iswrite);
> >> +        if (ret) {
> >> +            return ret;
> >> +        }
> >> +
> >> +        count -= bytes;
> >> +        done += bytes;
> >> +        off += bytes;
> >> +        tbuf += bytes;
> >> +    }
> >> +    return done;
> >> +}
> >> +
> >> +#define vfio_mig_read(f, v, c, o)       vfio_mig_rw(f, (__u8 *)v, c, o, false)
> >> +#define vfio_mig_write(f, v, c, o)      vfio_mig_rw(f, (__u8 *)v, c, o, true)
> >> +
> >> +#define VFIO_MIG_STRUCT_OFFSET(f)       \
> >> +                                 offsetof(struct vfio_device_migration_info, f)
> >> +/*
> >> + * Change the device_state register for device @vbasedev. Bits set in @mask
> >> + * are preserved, bits set in @value are set, and bits not set in either @mask
> >> + * or @value are cleared in device_state. If the register cannot be accessed,
> >> + * the resulting state would be invalid, or the device enters an error state,
> >> + * an error is returned.
> >> + */
> >> +
> >> +static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t mask,
> >> +                                    uint32_t value)
> >> +{
> >> +    VFIOMigration *migration = vbasedev->migration;
> >> +    VFIORegion *region = &migration->region;
> >> +    off_t dev_state_off = region->fd_offset +
> >> +                          VFIO_MIG_STRUCT_OFFSET(device_state);
> >> +    uint32_t device_state;
> >> +    int ret;
> >> +
> >> +    ret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
> >> +                        dev_state_off);
> >> +    if (ret < 0) {
> >> +        return ret;
> >> +    }
> >> +
> >> +    device_state = (device_state & mask) | value;
> >> +
> >> +    if (!VFIO_DEVICE_STATE_VALID(device_state)) {
> >> +        return -EINVAL;
> >> +    }
> >> +
> >> +    ret = vfio_mig_write(vbasedev, &device_state, sizeof(device_state),
> >> +                         dev_state_off);
> >> +    if (ret < 0) {
> >> +        int rret;
> >> +
> >> +        rret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
> >> +                             dev_state_off);
> >> +
> >> +        if ((rret < 0) || (VFIO_DEVICE_STATE_IS_ERROR(device_state))) {
> >> +            hw_error("%s: Device in error state 0x%x", vbasedev->name,
> >> +                     device_state);
> >> +            return rret ? rret : -EIO;
> >> +        }
> >> +        return ret;
> >> +    }
> >> +
> >> +    migration->device_state = device_state;
> >> +    trace_vfio_migration_set_state(vbasedev->name, device_state);
> >> +    return 0;
> >> +}
> >> +
> >> +static void vfio_vmstate_change(void *opaque, int running, RunState state)
> >> +{
> >> +    VFIODevice *vbasedev = opaque;
> >> +    VFIOMigration *migration = vbasedev->migration;
> >> +    uint32_t value, mask;
> >> +    int ret;
> >> +
> >> +    if ((vbasedev->migration->vm_running == running)) {
> >> +        return;
> >> +    }
> >> +
> >> +    if (running) {
> >> +        /*
> >> +         * Here device state can have one of _SAVING, _RESUMING or _STOP bit.
> >> +         * Transition from _SAVING to _RUNNING can happen if there is migration
> >> +         * failure, in that case clear _SAVING bit.
> >> +         * Transition from _RESUMING to _RUNNING occurs during resuming
> >> +         * phase, in that case clear _RESUMING bit.
> >> +         * In both the above cases, set _RUNNING bit.
> >> +         */
> >> +        mask = ~VFIO_DEVICE_STATE_MASK;
> >> +        value = VFIO_DEVICE_STATE_RUNNING;
> >> +    } else {
> >> +        /*
> >> +         * Here device state could be either _RUNNING or _SAVING|_RUNNING. Reset
> >> +         * _RUNNING bit
> >> +         */
> >> +        mask = ~VFIO_DEVICE_STATE_RUNNING;
> >> +        value = 0;
> >> +    }
> >> +
> >> +    ret = vfio_migration_set_state(vbasedev, mask, value);
> >> +    if (ret) {
> >> +        /*
> >> +         * Migration should be aborted in this case, but vm_state_notify()
> >> +         * currently does not support reporting failures.
> >> +         */
> >> +        error_report("%s: Failed to set device state 0x%x", vbasedev->name,
> >> +                     (migration->device_state & mask) | value);
> >> +        qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
> >> +    }
> >> +    vbasedev->migration->vm_running = running;
> >> +    trace_vfio_vmstate_change(vbasedev->name, running, RunState_str(state),
> >> +            (migration->device_state & mask) | value);
> >> +}
> >>   
> >>   static void vfio_migration_region_exit(VFIODevice *vbasedev)
> >>   {
> >> @@ -71,6 +223,8 @@ static int vfio_migration_init(VFIODevice *vbasedev,
> >>       }
> >>   
> >>       vbasedev->migration = migration;
> >> +    migration->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
> >> +                                                          vbasedev);
> >>       return 0;
> >>   
> >>   err:
> >> @@ -118,6 +272,10 @@ add_blocker:
> >>   
> >>   void vfio_migration_finalize(VFIODevice *vbasedev)
> >>   {
> >> +    if (vbasedev->migration->vm_state) {
> >> +        qemu_del_vm_change_state_handler(vbasedev->migration->vm_state);
> >> +    }  
> > 
> > 
> > This looks like a segfault, vfio_migration_teardown() is eventually
> > called unconditionally.  The next patch modifies this function further,
> > but never checks that vbasedev->migration is non-NULL.  Thanks,
> >   
> 
> Yup.
> Updated patch 4, 5 and 6. So now vfio_migration_finalize() looks like:
> 
> void vfio_migration_finalize(VFIODevice *vbasedev)
> {
>      VFIOMigration *migration = vbasedev->migration;
> 
>      if (migration) {
>          if (migration->migration_state.notify) {
>  
> remove_migration_state_change_notifier(&migration->migration_state);
>          }
> 
>          if (migration->vm_state) {
>              qemu_del_vm_change_state_handler(migration->vm_state);
>          }

We should be able to remove these based only on migration being
non-NULL, their setup cannot fail once we've setup the migration
pointer.  Thanks,

Alex

> 
>          vfio_migration_region_exit(vbasedev);
>          g_free(vbasedev->migration);
>          vbasedev->migration = NULL;
>      }
> 
>      if (vbasedev->migration_blocker) {
>          migrate_del_blocker(vbasedev->migration_blocker);
>          error_free(vbasedev->migration_blocker);
>          vbasedev->migration_blocker = NULL;
>      }
> }
> 
> Thanks,
> Kirti
> 
> > Alex
> > 
> >   
> >> +
> >>       if (vbasedev->migration_blocker) {
> >>           migrate_del_blocker(vbasedev->migration_blocker);
> >>           error_free(vbasedev->migration_blocker);
> >> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
> >> index 9ced5ec6277c..41de81f12f60 100644
> >> --- a/hw/vfio/trace-events
> >> +++ b/hw/vfio/trace-events
> >> @@ -148,3 +148,5 @@ vfio_display_edid_write_error(void) ""
> >>   
> >>   # migration.c
> >>   vfio_migration_probe(const char *name, uint32_t index) " (%s) Region %d"
> >> +vfio_migration_set_state(const char *name, uint32_t state) " (%s) state %d"
> >> +vfio_vmstate_change(const char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d"
> >> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> >> index 8275c4c68f45..9a571f1fb552 100644
> >> --- a/include/hw/vfio/vfio-common.h
> >> +++ b/include/hw/vfio/vfio-common.h
> >> @@ -29,6 +29,7 @@
> >>   #ifdef CONFIG_LINUX
> >>   #include <linux/vfio.h>
> >>   #endif
> >> +#include "sysemu/sysemu.h"
> >>   
> >>   #define VFIO_MSG_PREFIX "vfio %s: "
> >>   
> >> @@ -58,7 +59,10 @@ typedef struct VFIORegion {
> >>   } VFIORegion;
> >>   
> >>   typedef struct VFIOMigration {
> >> +    VMChangeStateEntry *vm_state;
> >>       VFIORegion region;
> >> +    uint32_t device_state;
> >> +    int vm_running;
> >>   } VFIOMigration;
> >>   
> >>   typedef struct VFIOAddressSpace {  
> >   
>

Patch

diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 5f74a3ad1d72..34f39c7e2e28 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -10,6 +10,7 @@ 
 #include "qemu/osdep.h"
 #include <linux/vfio.h>
 
+#include "sysemu/runstate.h"
 #include "hw/vfio/vfio-common.h"
 #include "cpu.h"
 #include "migration/migration.h"
@@ -22,6 +23,157 @@ 
 #include "exec/ram_addr.h"
 #include "pci.h"
 #include "trace.h"
+#include "hw/hw.h"
+
+static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
+                                  off_t off, bool iswrite)
+{
+    int ret;
+
+    ret = iswrite ? pwrite(vbasedev->fd, val, count, off) :
+                    pread(vbasedev->fd, val, count, off);
+    if (ret < count) {
+        error_report("vfio_mig_%s %d byte %s: failed at offset 0x%lx, err: %s",
+                     iswrite ? "write" : "read", count,
+                     vbasedev->name, off, strerror(errno));
+        return (ret < 0) ? ret : -EINVAL;
+    }
+    return 0;
+}
+
+static int vfio_mig_rw(VFIODevice *vbasedev, __u8 *buf, size_t count,
+                       off_t off, bool iswrite)
+{
+    int ret, done = 0;
+    __u8 *tbuf = buf;
+
+    while (count) {
+        int bytes = 0;
+
+        if (count >= 8 && !(off % 8)) {
+            bytes = 8;
+        } else if (count >= 4 && !(off % 4)) {
+            bytes = 4;
+        } else if (count >= 2 && !(off % 2)) {
+            bytes = 2;
+        } else {
+            bytes = 1;
+        }
+
+        ret = vfio_mig_access(vbasedev, tbuf, bytes, off, iswrite);
+        if (ret) {
+            return ret;
+        }
+
+        count -= bytes;
+        done += bytes;
+        off += bytes;
+        tbuf += bytes;
+    }
+    return done;
+}
+
+#define vfio_mig_read(f, v, c, o)       vfio_mig_rw(f, (__u8 *)v, c, o, false)
+#define vfio_mig_write(f, v, c, o)      vfio_mig_rw(f, (__u8 *)v, c, o, true)
+
+#define VFIO_MIG_STRUCT_OFFSET(f)       \
+                                 offsetof(struct vfio_device_migration_info, f)
+/*
+ * Change the device_state register for device @vbasedev. Bits set in @mask
+ * are preserved, bits set in @value are set, and bits not set in either @mask
+ * or @value are cleared in device_state. If the register cannot be accessed,
+ * the resulting state would be invalid, or the device enters an error state,
+ * an error is returned.
+ */
+
+static int vfio_migration_set_state(VFIODevice *vbasedev, uint32_t mask,
+                                    uint32_t value)
+{
+    VFIOMigration *migration = vbasedev->migration;
+    VFIORegion *region = &migration->region;
+    off_t dev_state_off = region->fd_offset +
+                          VFIO_MIG_STRUCT_OFFSET(device_state);
+    uint32_t device_state;
+    int ret;
+
+    ret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
+                        dev_state_off);
+    if (ret < 0) {
+        return ret;
+    }
+
+    device_state = (device_state & mask) | value;
+
+    if (!VFIO_DEVICE_STATE_VALID(device_state)) {
+        return -EINVAL;
+    }
+
+    ret = vfio_mig_write(vbasedev, &device_state, sizeof(device_state),
+                         dev_state_off);
+    if (ret < 0) {
+        int rret;
+
+        rret = vfio_mig_read(vbasedev, &device_state, sizeof(device_state),
+                             dev_state_off);
+
+        if ((rret < 0) || (VFIO_DEVICE_STATE_IS_ERROR(device_state))) {
+            hw_error("%s: Device in error state 0x%x", vbasedev->name,
+                     device_state);
+            return rret ? rret : -EIO;
+        }
+        return ret;
+    }
+
+    migration->device_state = device_state;
+    trace_vfio_migration_set_state(vbasedev->name, device_state);
+    return 0;
+}
+
+static void vfio_vmstate_change(void *opaque, int running, RunState state)
+{
+    VFIODevice *vbasedev = opaque;
+    VFIOMigration *migration = vbasedev->migration;
+    uint32_t value, mask;
+    int ret;
+
+    if ((vbasedev->migration->vm_running == running)) {
+        return;
+    }
+
+    if (running) {
+        /*
+         * Here device state can have one of _SAVING, _RESUMING or _STOP bit.
+         * Transition from _SAVING to _RUNNING can happen if there is migration
+         * failure, in that case clear _SAVING bit.
+         * Transition from _RESUMING to _RUNNING occurs during resuming
+         * phase, in that case clear _RESUMING bit.
+         * In both the above cases, set _RUNNING bit.
+         */
+        mask = ~VFIO_DEVICE_STATE_MASK;
+        value = VFIO_DEVICE_STATE_RUNNING;
+    } else {
+        /*
+         * Here device state could be either _RUNNING or _SAVING|_RUNNING. Reset
+         * _RUNNING bit
+         */
+        mask = ~VFIO_DEVICE_STATE_RUNNING;
+        value = 0;
+    }
+
+    ret = vfio_migration_set_state(vbasedev, mask, value);
+    if (ret) {
+        /*
+         * Migration should be aborted in this case, but vm_state_notify()
+         * currently does not support reporting failures.
+         */
+        error_report("%s: Failed to set device state 0x%x", vbasedev->name,
+                     (migration->device_state & mask) | value);
+        qemu_file_set_error(migrate_get_current()->to_dst_file, ret);
+    }
+    vbasedev->migration->vm_running = running;
+    trace_vfio_vmstate_change(vbasedev->name, running, RunState_str(state),
+            (migration->device_state & mask) | value);
+}
 
 static void vfio_migration_region_exit(VFIODevice *vbasedev)
 {
@@ -71,6 +223,8 @@  static int vfio_migration_init(VFIODevice *vbasedev,
     }
 
     vbasedev->migration = migration;
+    migration->vm_state = qemu_add_vm_change_state_handler(vfio_vmstate_change,
+                                                          vbasedev);
     return 0;
 
 err:
@@ -118,6 +272,10 @@  add_blocker:
 
 void vfio_migration_finalize(VFIODevice *vbasedev)
 {
+    if (vbasedev->migration->vm_state) {
+        qemu_del_vm_change_state_handler(vbasedev->migration->vm_state);
+    }
+
     if (vbasedev->migration_blocker) {
         migrate_del_blocker(vbasedev->migration_blocker);
         error_free(vbasedev->migration_blocker);
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 9ced5ec6277c..41de81f12f60 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -148,3 +148,5 @@  vfio_display_edid_write_error(void) ""
 
 # migration.c
 vfio_migration_probe(const char *name, uint32_t index) " (%s) Region %d"
+vfio_migration_set_state(const char *name, uint32_t state) " (%s) state %d"
+vfio_vmstate_change(const char *name, int running, const char *reason, uint32_t dev_state) " (%s) running %d reason %s device state %d"
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 8275c4c68f45..9a571f1fb552 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -29,6 +29,7 @@ 
 #ifdef CONFIG_LINUX
 #include <linux/vfio.h>
 #endif
+#include "sysemu/sysemu.h"
 
 #define VFIO_MSG_PREFIX "vfio %s: "
 
@@ -58,7 +59,10 @@  typedef struct VFIORegion {
 } VFIORegion;
 
 typedef struct VFIOMigration {
+    VMChangeStateEntry *vm_state;
     VFIORegion region;
+    uint32_t device_state;
+    int vm_running;
 } VFIOMigration;
 
 typedef struct VFIOAddressSpace {