diff mbox series

[v9,Kernel,3/5] vfio iommu: Add ioctl defination to unmap IOVA and return dirty bitmap

Message ID 1573578220-7530-4-git-send-email-kwankhede@nvidia.com (mailing list archive)
State New, archived
Headers show
Series Add KABIs to support migration for VFIO devices | expand

Commit Message

Kirti Wankhede Nov. 12, 2019, 5:03 p.m. UTC
With vIOMMU, during pre-copy phase of migration, while CPUs are still
running, IO virtual address unmap can happen while device still keeping
reference of guest pfns. Those pages should be reported as dirty before
unmap, so that VFIO user space application can copy content of those pages
from source to destination.

IOCTL defination added here add bitmap pointer, size and flag. If flag
VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set and bitmap memory is allocated
and bitmap_size of set, then ioctl will create bitmap of pinned pages and
then unmap those.

Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
---
 include/uapi/linux/vfio.h | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

Comments

Alex Williamson Nov. 12, 2019, 10:30 p.m. UTC | #1
On Tue, 12 Nov 2019 22:33:38 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> With vIOMMU, during pre-copy phase of migration, while CPUs are still
> running, IO virtual address unmap can happen while device still keeping
> reference of guest pfns. Those pages should be reported as dirty before
> unmap, so that VFIO user space application can copy content of those pages
> from source to destination.
> 
> IOCTL defination added here add bitmap pointer, size and flag. If flag

definition, adds

> VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set and bitmap memory is allocated
> and bitmap_size of set, then ioctl will create bitmap of pinned pages and

s/of/is/

> then unmap those.
> 
> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> Reviewed-by: Neo Jia <cjia@nvidia.com>
> ---
>  include/uapi/linux/vfio.h | 33 +++++++++++++++++++++++++++++++++
>  1 file changed, 33 insertions(+)
> 
> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> index 6fd3822aa610..72fd297baf52 100644
> --- a/include/uapi/linux/vfio.h
> +++ b/include/uapi/linux/vfio.h
> @@ -925,6 +925,39 @@ struct vfio_iommu_type1_dirty_bitmap {
>  
>  #define VFIO_IOMMU_GET_DIRTY_BITMAP             _IO(VFIO_TYPE, VFIO_BASE + 17)
>  
> +/**
> + * VFIO_IOMMU_UNMAP_DMA_GET_BITMAP - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
> + *				      struct vfio_iommu_type1_dma_unmap_bitmap)
> + *
> + * Unmap IO virtual addresses using the provided struct
> + * vfio_iommu_type1_dma_unmap_bitmap.  Caller sets argsz.
> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
> + * before unmapping IO virtual addresses. If this flag is not set, only IO
> + * virtual address are unmapped without creating pinned pages bitmap, that
> + * is, behave same as VFIO_IOMMU_UNMAP_DMA ioctl.
> + * User should allocate memory to get bitmap and should set size of allocated
> + * memory in bitmap_size field. One bit in bitmap is used to represent per page
> + * consecutively starting from iova offset. Bit set indicates page at that
> + * offset from iova is dirty.
> + * The actual unmapped size is returned in the size field and bitmap of pages
> + * in the range of unmapped size is returned in bitmap if flag
> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set.
> + *
> + * No guarantee is made to the user that arbitrary unmaps of iova or size
> + * different from those used in the original mapping call will succeed.
> + */
> +struct vfio_iommu_type1_dma_unmap_bitmap {
> +	__u32        argsz;
> +	__u32        flags;
> +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
> +	__u64        iova;                        /* IO virtual address */
> +	__u64        size;                        /* Size of mapping (bytes) */
> +	__u64        bitmap_size;                 /* in bytes */
> +	void __user *bitmap;                      /* one bit per page */
> +};
> +
> +#define VFIO_IOMMU_UNMAP_DMA_GET_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 18)
> +

Why not extend VFIO_IOMMU_UNMAP_DMA to support this rather than add an
ioctl that duplicates the functionality and extends it??  Otherwise
same comments as previous, in fact it's too bad we can't use this ioctl
for both, but a DONT_UNMAP flag on the UNMAP_DMA ioctl seems a bit
absurd.

I suspect we also want a flags bit in VFIO_IOMMU_GET_INFO to indicate
these capabilities are supported.

Maybe for both ioctls we also want to define it as the user's
responsibility to zero the bitmap, requiring the kernel to only set
bits as necessary.  Thanks,

Alex

>  /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>  
>  /*
Kirti Wankhede Nov. 13, 2019, 7:52 p.m. UTC | #2
On 11/13/2019 4:00 AM, Alex Williamson wrote:
> On Tue, 12 Nov 2019 22:33:38 +0530
> Kirti Wankhede <kwankhede@nvidia.com> wrote:
> 
>> With vIOMMU, during pre-copy phase of migration, while CPUs are still
>> running, IO virtual address unmap can happen while device still keeping
>> reference of guest pfns. Those pages should be reported as dirty before
>> unmap, so that VFIO user space application can copy content of those pages
>> from source to destination.
>>
>> IOCTL defination added here add bitmap pointer, size and flag. If flag
> 
> definition, adds
> 
>> VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set and bitmap memory is allocated
>> and bitmap_size of set, then ioctl will create bitmap of pinned pages and
> 
> s/of/is/
> 
>> then unmap those.
>>
>> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
>> Reviewed-by: Neo Jia <cjia@nvidia.com>
>> ---
>>   include/uapi/linux/vfio.h | 33 +++++++++++++++++++++++++++++++++
>>   1 file changed, 33 insertions(+)
>>
>> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
>> index 6fd3822aa610..72fd297baf52 100644
>> --- a/include/uapi/linux/vfio.h
>> +++ b/include/uapi/linux/vfio.h
>> @@ -925,6 +925,39 @@ struct vfio_iommu_type1_dirty_bitmap {
>>   
>>   #define VFIO_IOMMU_GET_DIRTY_BITMAP             _IO(VFIO_TYPE, VFIO_BASE + 17)
>>   
>> +/**
>> + * VFIO_IOMMU_UNMAP_DMA_GET_BITMAP - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
>> + *				      struct vfio_iommu_type1_dma_unmap_bitmap)
>> + *
>> + * Unmap IO virtual addresses using the provided struct
>> + * vfio_iommu_type1_dma_unmap_bitmap.  Caller sets argsz.
>> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
>> + * before unmapping IO virtual addresses. If this flag is not set, only IO
>> + * virtual address are unmapped without creating pinned pages bitmap, that
>> + * is, behave same as VFIO_IOMMU_UNMAP_DMA ioctl.
>> + * User should allocate memory to get bitmap and should set size of allocated
>> + * memory in bitmap_size field. One bit in bitmap is used to represent per page
>> + * consecutively starting from iova offset. Bit set indicates page at that
>> + * offset from iova is dirty.
>> + * The actual unmapped size is returned in the size field and bitmap of pages
>> + * in the range of unmapped size is returned in bitmap if flag
>> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set.
>> + *
>> + * No guarantee is made to the user that arbitrary unmaps of iova or size
>> + * different from those used in the original mapping call will succeed.
>> + */
>> +struct vfio_iommu_type1_dma_unmap_bitmap {
>> +	__u32        argsz;
>> +	__u32        flags;
>> +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
>> +	__u64        iova;                        /* IO virtual address */
>> +	__u64        size;                        /* Size of mapping (bytes) */
>> +	__u64        bitmap_size;                 /* in bytes */
>> +	void __user *bitmap;                      /* one bit per page */
>> +};
>> +
>> +#define VFIO_IOMMU_UNMAP_DMA_GET_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 18)
>> +
> 
> Why not extend VFIO_IOMMU_UNMAP_DMA to support this rather than add an
> ioctl that duplicates the functionality and extends it?? 

We do want old userspace applications to work with new kernel and 
vice-versa, right?

If I try to change existing VFIO_IOMMU_UNMAP_DMA ioctl structure, say if 
add 'bitmap_size' and 'bitmap' after 'size', with below code in old 
kernel, old kernel & new userspace will work.

         minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);

         if (copy_from_user(&unmap, (void __user *)arg, minsz))
                 return -EFAULT;

         if (unmap.argsz < minsz || unmap.flags)
                 return -EINVAL;


With new kernel it would change to:
         minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, bitmap);

         if (copy_from_user(&unmap, (void __user *)arg, minsz))
                 return -EFAULT;

         if (unmap.argsz < minsz || unmap.flags)
                 return -EINVAL;

Then old userspace app will fail because unmap.argsz < minsz and might 
be copy_from_user would cause seg fault because userspace sdk doesn't 
contain new member variables.
We can't change the sequence to keep 'size' as last member, because then 
new userspace app on old kernel will interpret it wrong.

> Otherwise
> same comments as previous, in fact it's too bad we can't use this ioctl
> for both, but a DONT_UNMAP flag on the UNMAP_DMA ioctl seems a bit
> absurd.
> 
> I suspect we also want a flags bit in VFIO_IOMMU_GET_INFO to indicate
> these capabilities are supported.
> 

Ok. I'll add that.

> Maybe for both ioctls we also want to define it as the user's
> responsibility to zero the bitmap, requiring the kernel to only set
> bits as necessary. 

Ok. Updating comment.

Thanks,
Kirti

> Thanks,
> 
> Alex
> 
>>   /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>>   
>>   /*
>
Alex Williamson Nov. 13, 2019, 8:22 p.m. UTC | #3
On Thu, 14 Nov 2019 01:22:39 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> On 11/13/2019 4:00 AM, Alex Williamson wrote:
> > On Tue, 12 Nov 2019 22:33:38 +0530
> > Kirti Wankhede <kwankhede@nvidia.com> wrote:
> >   
> >> With vIOMMU, during pre-copy phase of migration, while CPUs are still
> >> running, IO virtual address unmap can happen while device still keeping
> >> reference of guest pfns. Those pages should be reported as dirty before
> >> unmap, so that VFIO user space application can copy content of those pages
> >> from source to destination.
> >>
> >> IOCTL defination added here add bitmap pointer, size and flag. If flag  
> > 
> > definition, adds
> >   
> >> VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set and bitmap memory is allocated
> >> and bitmap_size of set, then ioctl will create bitmap of pinned pages and  
> > 
> > s/of/is/
> >   
> >> then unmap those.
> >>
> >> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> >> Reviewed-by: Neo Jia <cjia@nvidia.com>
> >> ---
> >>   include/uapi/linux/vfio.h | 33 +++++++++++++++++++++++++++++++++
> >>   1 file changed, 33 insertions(+)
> >>
> >> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> >> index 6fd3822aa610..72fd297baf52 100644
> >> --- a/include/uapi/linux/vfio.h
> >> +++ b/include/uapi/linux/vfio.h
> >> @@ -925,6 +925,39 @@ struct vfio_iommu_type1_dirty_bitmap {
> >>   
> >>   #define VFIO_IOMMU_GET_DIRTY_BITMAP             _IO(VFIO_TYPE, VFIO_BASE + 17)
> >>   
> >> +/**
> >> + * VFIO_IOMMU_UNMAP_DMA_GET_BITMAP - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
> >> + *				      struct vfio_iommu_type1_dma_unmap_bitmap)
> >> + *
> >> + * Unmap IO virtual addresses using the provided struct
> >> + * vfio_iommu_type1_dma_unmap_bitmap.  Caller sets argsz.
> >> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
> >> + * before unmapping IO virtual addresses. If this flag is not set, only IO
> >> + * virtual address are unmapped without creating pinned pages bitmap, that
> >> + * is, behave same as VFIO_IOMMU_UNMAP_DMA ioctl.
> >> + * User should allocate memory to get bitmap and should set size of allocated
> >> + * memory in bitmap_size field. One bit in bitmap is used to represent per page
> >> + * consecutively starting from iova offset. Bit set indicates page at that
> >> + * offset from iova is dirty.
> >> + * The actual unmapped size is returned in the size field and bitmap of pages
> >> + * in the range of unmapped size is returned in bitmap if flag
> >> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set.
> >> + *
> >> + * No guarantee is made to the user that arbitrary unmaps of iova or size
> >> + * different from those used in the original mapping call will succeed.
> >> + */
> >> +struct vfio_iommu_type1_dma_unmap_bitmap {
> >> +	__u32        argsz;
> >> +	__u32        flags;
> >> +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
> >> +	__u64        iova;                        /* IO virtual address */
> >> +	__u64        size;                        /* Size of mapping (bytes) */
> >> +	__u64        bitmap_size;                 /* in bytes */
> >> +	void __user *bitmap;                      /* one bit per page */
> >> +};
> >> +
> >> +#define VFIO_IOMMU_UNMAP_DMA_GET_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 18)
> >> +  
> > 
> > Why not extend VFIO_IOMMU_UNMAP_DMA to support this rather than add an
> > ioctl that duplicates the functionality and extends it??   
> 
> We do want old userspace applications to work with new kernel and 
> vice-versa, right?
> 
> If I try to change existing VFIO_IOMMU_UNMAP_DMA ioctl structure, say if 
> add 'bitmap_size' and 'bitmap' after 'size', with below code in old 
> kernel, old kernel & new userspace will work.
> 
>          minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
> 
>          if (copy_from_user(&unmap, (void __user *)arg, minsz))
>                  return -EFAULT;
> 
>          if (unmap.argsz < minsz || unmap.flags)
>                  return -EINVAL;
> 
> 
> With new kernel it would change to:
>          minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, bitmap);

No, the minimum structure size still ends at size, we interpret flags
and argsz to learn if the user understands those fields and optionally
include them.  Therefore old userspace on new kernel continues to work.

>          if (copy_from_user(&unmap, (void __user *)arg, minsz))
>                  return -EFAULT;
> 
>          if (unmap.argsz < minsz || unmap.flags)
>                  return -EINVAL;
> 
> Then old userspace app will fail because unmap.argsz < minsz and might 
> be copy_from_user would cause seg fault because userspace sdk doesn't 
> contain new member variables.
> We can't change the sequence to keep 'size' as last member, because then 
> new userspace app on old kernel will interpret it wrong.

If we have new userspace on old kernel, that userspace needs to be able
to learn that this feature exists (new flag in the
vfio_iommu_type1_info struct as suggested below) and only make use of it
when available.  This is why the old kernel checks argsz against minsz.
So long as the user passes something at least minsz in size, we have
compatibility.  The old kernel doesn't understand the GET_DIRTY_BITMAP
flag and will return an error if the user attempts to use it.  Thanks,

Alex
 
> > Otherwise
> > same comments as previous, in fact it's too bad we can't use this ioctl
> > for both, but a DONT_UNMAP flag on the UNMAP_DMA ioctl seems a bit
> > absurd.
> > 
> > I suspect we also want a flags bit in VFIO_IOMMU_GET_INFO to indicate
> > these capabilities are supported.
> >   
> 
> Ok. I'll add that.
> 
> > Maybe for both ioctls we also want to define it as the user's
> > responsibility to zero the bitmap, requiring the kernel to only set
> > bits as necessary.   
> 
> Ok. Updating comment.
> 
> Thanks,
> Kirti
> 
> > Thanks,
> > 
> > Alex
> >   
> >>   /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
> >>   
> >>   /*  
> >   
>
Kirti Wankhede Nov. 14, 2019, 6:56 p.m. UTC | #4
On 11/14/2019 1:52 AM, Alex Williamson wrote:
> On Thu, 14 Nov 2019 01:22:39 +0530
> Kirti Wankhede <kwankhede@nvidia.com> wrote:
> 
>> On 11/13/2019 4:00 AM, Alex Williamson wrote:
>>> On Tue, 12 Nov 2019 22:33:38 +0530
>>> Kirti Wankhede <kwankhede@nvidia.com> wrote:
>>>    
>>>> With vIOMMU, during pre-copy phase of migration, while CPUs are still
>>>> running, IO virtual address unmap can happen while device still keeping
>>>> reference of guest pfns. Those pages should be reported as dirty before
>>>> unmap, so that VFIO user space application can copy content of those pages
>>>> from source to destination.
>>>>
>>>> IOCTL defination added here add bitmap pointer, size and flag. If flag
>>>
>>> definition, adds
>>>    
>>>> VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set and bitmap memory is allocated
>>>> and bitmap_size of set, then ioctl will create bitmap of pinned pages and
>>>
>>> s/of/is/
>>>    
>>>> then unmap those.
>>>>
>>>> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
>>>> Reviewed-by: Neo Jia <cjia@nvidia.com>
>>>> ---
>>>>    include/uapi/linux/vfio.h | 33 +++++++++++++++++++++++++++++++++
>>>>    1 file changed, 33 insertions(+)
>>>>
>>>> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
>>>> index 6fd3822aa610..72fd297baf52 100644
>>>> --- a/include/uapi/linux/vfio.h
>>>> +++ b/include/uapi/linux/vfio.h
>>>> @@ -925,6 +925,39 @@ struct vfio_iommu_type1_dirty_bitmap {
>>>>    
>>>>    #define VFIO_IOMMU_GET_DIRTY_BITMAP             _IO(VFIO_TYPE, VFIO_BASE + 17)
>>>>    
>>>> +/**
>>>> + * VFIO_IOMMU_UNMAP_DMA_GET_BITMAP - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
>>>> + *				      struct vfio_iommu_type1_dma_unmap_bitmap)
>>>> + *
>>>> + * Unmap IO virtual addresses using the provided struct
>>>> + * vfio_iommu_type1_dma_unmap_bitmap.  Caller sets argsz.
>>>> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
>>>> + * before unmapping IO virtual addresses. If this flag is not set, only IO
>>>> + * virtual address are unmapped without creating pinned pages bitmap, that
>>>> + * is, behave same as VFIO_IOMMU_UNMAP_DMA ioctl.
>>>> + * User should allocate memory to get bitmap and should set size of allocated
>>>> + * memory in bitmap_size field. One bit in bitmap is used to represent per page
>>>> + * consecutively starting from iova offset. Bit set indicates page at that
>>>> + * offset from iova is dirty.
>>>> + * The actual unmapped size is returned in the size field and bitmap of pages
>>>> + * in the range of unmapped size is returned in bitmap if flag
>>>> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set.
>>>> + *
>>>> + * No guarantee is made to the user that arbitrary unmaps of iova or size
>>>> + * different from those used in the original mapping call will succeed.
>>>> + */
>>>> +struct vfio_iommu_type1_dma_unmap_bitmap {
>>>> +	__u32        argsz;
>>>> +	__u32        flags;
>>>> +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
>>>> +	__u64        iova;                        /* IO virtual address */
>>>> +	__u64        size;                        /* Size of mapping (bytes) */
>>>> +	__u64        bitmap_size;                 /* in bytes */
>>>> +	void __user *bitmap;                      /* one bit per page */
>>>> +};
>>>> +
>>>> +#define VFIO_IOMMU_UNMAP_DMA_GET_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 18)
>>>> +
>>>
>>> Why not extend VFIO_IOMMU_UNMAP_DMA to support this rather than add an
>>> ioctl that duplicates the functionality and extends it??
>>
>> We do want old userspace applications to work with new kernel and
>> vice-versa, right?
>>
>> If I try to change existing VFIO_IOMMU_UNMAP_DMA ioctl structure, say if
>> add 'bitmap_size' and 'bitmap' after 'size', with below code in old
>> kernel, old kernel & new userspace will work.
>>
>>           minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
>>
>>           if (copy_from_user(&unmap, (void __user *)arg, minsz))
>>                   return -EFAULT;
>>
>>           if (unmap.argsz < minsz || unmap.flags)
>>                   return -EINVAL;
>>
>>
>> With new kernel it would change to:
>>           minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, bitmap);
> 
> No, the minimum structure size still ends at size, we interpret flags
> and argsz to learn if the user understands those fields and optionally
> include them.  Therefore old userspace on new kernel continues to work.
> 
>>           if (copy_from_user(&unmap, (void __user *)arg, minsz))
>>                   return -EFAULT;
>>
>>           if (unmap.argsz < minsz || unmap.flags)
>>                   return -EINVAL;
>>
>> Then old userspace app will fail because unmap.argsz < minsz and might
>> be copy_from_user would cause seg fault because userspace sdk doesn't
>> contain new member variables.
>> We can't change the sequence to keep 'size' as last member, because then
>> new userspace app on old kernel will interpret it wrong.
> 
> If we have new userspace on old kernel, that userspace needs to be able
> to learn that this feature exists (new flag in the
> vfio_iommu_type1_info struct as suggested below) and only make use of it
> when available.  This is why the old kernel checks argsz against minsz.
> So long as the user passes something at least minsz in size, we have
> compatibility.  The old kernel doesn't understand the GET_DIRTY_BITMAP
> flag and will return an error if the user attempts to use it.  Thanks,
> 

Ok. So then VFIO_IOMMU_UNMAP_DMA_GET_BITMAP ioctl is not needed. I'll do 
the change. Again bitmap will be created considering smallest page size 
of iova_pgsizes

But VFIO_IOMMU_GET_DIRTY_BITMAP ioctl will still required, right?

Thanks,
Kirti

> Alex
>   
>>> Otherwise
>>> same comments as previous, in fact it's too bad we can't use this ioctl
>>> for both, but a DONT_UNMAP flag on the UNMAP_DMA ioctl seems a bit
>>> absurd.
>>>
>>> I suspect we also want a flags bit in VFIO_IOMMU_GET_INFO to indicate
>>> these capabilities are supported.
>>>    
>>
>> Ok. I'll add that.
>>
>>> Maybe for both ioctls we also want to define it as the user's
>>> responsibility to zero the bitmap, requiring the kernel to only set
>>> bits as necessary.
>>
>> Ok. Updating comment.
>>
>> Thanks,
>> Kirti
>>
>>> Thanks,
>>>
>>> Alex
>>>    
>>>>    /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
>>>>    
>>>>    /*
>>>    
>>
>
Alex Williamson Nov. 14, 2019, 9:08 p.m. UTC | #5
On Fri, 15 Nov 2019 00:26:26 +0530
Kirti Wankhede <kwankhede@nvidia.com> wrote:

> On 11/14/2019 1:52 AM, Alex Williamson wrote:
> > On Thu, 14 Nov 2019 01:22:39 +0530
> > Kirti Wankhede <kwankhede@nvidia.com> wrote:
> >   
> >> On 11/13/2019 4:00 AM, Alex Williamson wrote:  
> >>> On Tue, 12 Nov 2019 22:33:38 +0530
> >>> Kirti Wankhede <kwankhede@nvidia.com> wrote:
> >>>      
> >>>> With vIOMMU, during pre-copy phase of migration, while CPUs are still
> >>>> running, IO virtual address unmap can happen while device still keeping
> >>>> reference of guest pfns. Those pages should be reported as dirty before
> >>>> unmap, so that VFIO user space application can copy content of those pages
> >>>> from source to destination.
> >>>>
> >>>> IOCTL defination added here add bitmap pointer, size and flag. If flag  
> >>>
> >>> definition, adds
> >>>      
> >>>> VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set and bitmap memory is allocated
> >>>> and bitmap_size of set, then ioctl will create bitmap of pinned pages and  
> >>>
> >>> s/of/is/
> >>>      
> >>>> then unmap those.
> >>>>
> >>>> Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
> >>>> Reviewed-by: Neo Jia <cjia@nvidia.com>
> >>>> ---
> >>>>    include/uapi/linux/vfio.h | 33 +++++++++++++++++++++++++++++++++
> >>>>    1 file changed, 33 insertions(+)
> >>>>
> >>>> diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
> >>>> index 6fd3822aa610..72fd297baf52 100644
> >>>> --- a/include/uapi/linux/vfio.h
> >>>> +++ b/include/uapi/linux/vfio.h
> >>>> @@ -925,6 +925,39 @@ struct vfio_iommu_type1_dirty_bitmap {
> >>>>    
> >>>>    #define VFIO_IOMMU_GET_DIRTY_BITMAP             _IO(VFIO_TYPE, VFIO_BASE + 17)
> >>>>    
> >>>> +/**
> >>>> + * VFIO_IOMMU_UNMAP_DMA_GET_BITMAP - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
> >>>> + *				      struct vfio_iommu_type1_dma_unmap_bitmap)
> >>>> + *
> >>>> + * Unmap IO virtual addresses using the provided struct
> >>>> + * vfio_iommu_type1_dma_unmap_bitmap.  Caller sets argsz.
> >>>> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
> >>>> + * before unmapping IO virtual addresses. If this flag is not set, only IO
> >>>> + * virtual address are unmapped without creating pinned pages bitmap, that
> >>>> + * is, behave same as VFIO_IOMMU_UNMAP_DMA ioctl.
> >>>> + * User should allocate memory to get bitmap and should set size of allocated
> >>>> + * memory in bitmap_size field. One bit in bitmap is used to represent per page
> >>>> + * consecutively starting from iova offset. Bit set indicates page at that
> >>>> + * offset from iova is dirty.
> >>>> + * The actual unmapped size is returned in the size field and bitmap of pages
> >>>> + * in the range of unmapped size is returned in bitmap if flag
> >>>> + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set.
> >>>> + *
> >>>> + * No guarantee is made to the user that arbitrary unmaps of iova or size
> >>>> + * different from those used in the original mapping call will succeed.
> >>>> + */
> >>>> +struct vfio_iommu_type1_dma_unmap_bitmap {
> >>>> +	__u32        argsz;
> >>>> +	__u32        flags;
> >>>> +#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
> >>>> +	__u64        iova;                        /* IO virtual address */
> >>>> +	__u64        size;                        /* Size of mapping (bytes) */
> >>>> +	__u64        bitmap_size;                 /* in bytes */
> >>>> +	void __user *bitmap;                      /* one bit per page */
> >>>> +};
> >>>> +
> >>>> +#define VFIO_IOMMU_UNMAP_DMA_GET_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 18)
> >>>> +  
> >>>
> >>> Why not extend VFIO_IOMMU_UNMAP_DMA to support this rather than add an
> >>> ioctl that duplicates the functionality and extends it??  
> >>
> >> We do want old userspace applications to work with new kernel and
> >> vice-versa, right?
> >>
> >> If I try to change existing VFIO_IOMMU_UNMAP_DMA ioctl structure, say if
> >> add 'bitmap_size' and 'bitmap' after 'size', with below code in old
> >> kernel, old kernel & new userspace will work.
> >>
> >>           minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
> >>
> >>           if (copy_from_user(&unmap, (void __user *)arg, minsz))
> >>                   return -EFAULT;
> >>
> >>           if (unmap.argsz < minsz || unmap.flags)
> >>                   return -EINVAL;
> >>
> >>
> >> With new kernel it would change to:
> >>           minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, bitmap);  
> > 
> > No, the minimum structure size still ends at size, we interpret flags
> > and argsz to learn if the user understands those fields and optionally
> > include them.  Therefore old userspace on new kernel continues to work.
> >   
> >>           if (copy_from_user(&unmap, (void __user *)arg, minsz))
> >>                   return -EFAULT;
> >>
> >>           if (unmap.argsz < minsz || unmap.flags)
> >>                   return -EINVAL;
> >>
> >> Then old userspace app will fail because unmap.argsz < minsz and might
> >> be copy_from_user would cause seg fault because userspace sdk doesn't
> >> contain new member variables.
> >> We can't change the sequence to keep 'size' as last member, because then
> >> new userspace app on old kernel will interpret it wrong.  
> > 
> > If we have new userspace on old kernel, that userspace needs to be able
> > to learn that this feature exists (new flag in the
> > vfio_iommu_type1_info struct as suggested below) and only make use of it
> > when available.  This is why the old kernel checks argsz against minsz.
> > So long as the user passes something at least minsz in size, we have
> > compatibility.  The old kernel doesn't understand the GET_DIRTY_BITMAP
> > flag and will return an error if the user attempts to use it.  Thanks,
> >   
> 
> Ok. So then VFIO_IOMMU_UNMAP_DMA_GET_BITMAP ioctl is not needed. I'll do 
> the change. Again bitmap will be created considering smallest page size 
> of iova_pgsizes
> 
> But VFIO_IOMMU_GET_DIRTY_BITMAP ioctl will still required, right?

Yes, I'm not willing to suggest a flag on an unmap ioctl that
eliminates the unmap just so we can re-use it for retrieving a dirty
page bitmap.  That'd be ugly.  Thanks,

Alex
diff mbox series

Patch

diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 6fd3822aa610..72fd297baf52 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -925,6 +925,39 @@  struct vfio_iommu_type1_dirty_bitmap {
 
 #define VFIO_IOMMU_GET_DIRTY_BITMAP             _IO(VFIO_TYPE, VFIO_BASE + 17)
 
+/**
+ * VFIO_IOMMU_UNMAP_DMA_GET_BITMAP - _IOWR(VFIO_TYPE, VFIO_BASE + 18,
+ *				      struct vfio_iommu_type1_dma_unmap_bitmap)
+ *
+ * Unmap IO virtual addresses using the provided struct
+ * vfio_iommu_type1_dma_unmap_bitmap.  Caller sets argsz.
+ * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP should be set to get dirty bitmap
+ * before unmapping IO virtual addresses. If this flag is not set, only IO
+ * virtual address are unmapped without creating pinned pages bitmap, that
+ * is, behave same as VFIO_IOMMU_UNMAP_DMA ioctl.
+ * User should allocate memory to get bitmap and should set size of allocated
+ * memory in bitmap_size field. One bit in bitmap is used to represent per page
+ * consecutively starting from iova offset. Bit set indicates page at that
+ * offset from iova is dirty.
+ * The actual unmapped size is returned in the size field and bitmap of pages
+ * in the range of unmapped size is returned in bitmap if flag
+ * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is set.
+ *
+ * No guarantee is made to the user that arbitrary unmaps of iova or size
+ * different from those used in the original mapping call will succeed.
+ */
+struct vfio_iommu_type1_dma_unmap_bitmap {
+	__u32        argsz;
+	__u32        flags;
+#define VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP (1 << 0)
+	__u64        iova;                        /* IO virtual address */
+	__u64        size;                        /* Size of mapping (bytes) */
+	__u64        bitmap_size;                 /* in bytes */
+	void __user *bitmap;                      /* one bit per page */
+};
+
+#define VFIO_IOMMU_UNMAP_DMA_GET_BITMAP _IO(VFIO_TYPE, VFIO_BASE + 18)
+
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*