[v2,3/9] KVM: x86: Introduce KVM_GET_PAGE_ENC_BITMAP ioctl

Commit Message

Kalra, Ashish Dec. 1, 2020, 12:47 a.m. UTC

From: Brijesh Singh <[e-mail]>

The ioctl can be used to retrieve page encryption bitmap for a given
gfn range.

Return the correct bitmap as per the number of pages being requested
by the user. Ensure that we only copy bmap->num_pages bytes in the
userspace buffer, if bmap->num_pages is not byte aligned we read
the trailing bits from the userspace and copy those bits as is.

Cc: Thomas Gleixner <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: "H. Peter Anvin" <[e-mail]>
Cc: Paolo Bonzini <[e-mail]>
Cc: "Radim Krčmář" <[e-mail]>
Cc: Joerg Roedel <[e-mail]>
Cc: Borislav Petkov <[e-mail]>
Cc: Tom Lendacky <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Reviewed-by: Venu Busireddy <[e-mail]>
Signed-off-by: Brijesh Singh <[e-mail]>
Signed-off-by: Ashish Kalra <[e-mail]>
---
 Documentation/virt/kvm/api.rst  | 27 +++++++++++++
 arch/x86/include/asm/kvm_host.h |  2 +
 arch/x86/kvm/svm/sev.c          | 70 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  1 +
 arch/x86/kvm/svm/svm.h          |  1 +
 arch/x86/kvm/x86.c              | 12 ++++++
 include/uapi/linux/kvm.h        | 12 ++++++
 7 files changed, 125 insertions(+)

Comments

Dov Murik Dec. 6, 2020, 11:02 a.m. UTC | #1

On 01/12/2020 2:47, Ashish Kalra wrote:
> From: Brijesh Singh <[e-mail]>
> 
> The ioctl can be used to retrieve page encryption bitmap for a given
> gfn range.
> 
> Return the correct bitmap as per the number of pages being requested
> by the user. Ensure that we only copy bmap->num_pages bytes in the
> userspace buffer, if bmap->num_pages is not byte aligned we read
> the trailing bits from the userspace and copy those bits as is.

I think you meant to say "Ensure that we only copy bmap->num_pages 
*bits* in the userspace buffer".  But maybe I'm missed something.


> 
> Cc: Thomas Gleixner <[e-mail]>
> Cc: Ingo Molnar <[e-mail]>
> Cc: "H. Peter Anvin" <[e-mail]>
> Cc: Paolo Bonzini <[e-mail]>
> Cc: "Radim Krčmář" <[e-mail]>
> Cc: Joerg Roedel <[e-mail]>
> Cc: Borislav Petkov <[e-mail]>
> Cc: Tom Lendacky <[e-mail]>
> Cc: [e-mail]
> Cc: [e-mail]
> Cc: [e-mail]
> Reviewed-by: Venu Busireddy <[e-mail]>
> Signed-off-by: Brijesh Singh <[e-mail]>
> Signed-off-by: Ashish Kalra <[e-mail]>
> ---
>   Documentation/virt/kvm/api.rst  | 27 +++++++++++++
>   arch/x86/include/asm/kvm_host.h |  2 +
>   arch/x86/kvm/svm/sev.c          | 70 +++++++++++++++++++++++++++++++++
>   arch/x86/kvm/svm/svm.c          |  1 +
>   arch/x86/kvm/svm/svm.h          |  1 +
>   arch/x86/kvm/x86.c              | 12 ++++++
>   include/uapi/linux/kvm.h        | 12 ++++++
>   7 files changed, 125 insertions(+)
> 
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index 70254eaa5229..ae410f4332ab 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -4671,6 +4671,33 @@ This ioctl resets VCPU registers and control structures according to
>   the clear cpu reset definition in the POP. However, the cpu is not put
>   into ESA mode. This reset is a superset of the initial reset.
> 
> +4.125 KVM_GET_PAGE_ENC_BITMAP (vm ioctl)
> +---------------------------------------
> +
> +:Capability: basic
> +:Architectures: x86
> +:Type: vm ioctl
> +:Parameters: struct kvm_page_enc_bitmap (in/out)
> +:Returns: 0 on success, -1 on error
> +
> +/* for KVM_GET_PAGE_ENC_BITMAP */
> +struct kvm_page_enc_bitmap {
> +	__u64 start_gfn;
> +	__u64 num_pages;
> +	union {
> +		void __user *enc_bitmap; /* one bit per page */
> +		__u64 padding2;
> +	};
> +};
> +
> +The encrypted VMs have the concept of private and shared pages. The private
> +pages are encrypted with the guest-specific key, while the shared pages may
> +be encrypted with the hypervisor key. The KVM_GET_PAGE_ENC_BITMAP can
> +be used to get the bitmap indicating whether the guest page is private
> +or shared. The bitmap can be used during the guest migration. If the page
> +is private then the userspace need to use SEV migration commands to transmit
> +the page.
> +
> 
>   4.125 KVM_S390_PV_COMMAND
>   -------------------------
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index d035dc983a7a..8c2e40199ecb 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1284,6 +1284,8 @@ struct kvm_x86_ops {
>   	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
>   	int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa,
>   				  unsigned long sz, unsigned long mode);
> +	int (*get_page_enc_bitmap)(struct kvm *kvm,
> +				struct kvm_page_enc_bitmap *bmap);
>   };
> 
>   struct kvm_x86_nested_ops {
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index 6b8bc1297f9c..a6586dd29767 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -1014,6 +1014,76 @@ int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
>   	return 0;
>   }
> 
> +int svm_get_page_enc_bitmap(struct kvm *kvm,
> +				   struct kvm_page_enc_bitmap *bmap)
> +{
> +	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
> +	unsigned long gfn_start, gfn_end;
> +	unsigned long sz, i, sz_bytes;
> +	unsigned long *bitmap;
> +	int ret, n;
> +
> +	if (!sev_guest(kvm))
> +		return -ENOTTY;
> +
> +	gfn_start = bmap->start_gfn;
> +	gfn_end = gfn_start + bmap->num_pages;
> +
> +	sz = ALIGN(bmap->num_pages, BITS_PER_LONG) / BITS_PER_BYTE;
> +	bitmap = kmalloc(sz, GFP_KERNEL);

Maybe use bitmap_alloc which accepts size in bits (and corresponding 
bitmap_free)?


> +	if (!bitmap)
> +		return -ENOMEM;
> +
> +	/* by default all pages are marked encrypted */
> +	memset(bitmap, 0xff, sz);

Maybe use bitmap_fill to clarify the intent?


> +
> +	mutex_lock(&kvm->lock);
> +	if (sev->page_enc_bmap) {
> +		i = gfn_start;
> +		for_each_clear_bit_from(i, sev->page_enc_bmap,
> +				      min(sev->page_enc_bmap_size, gfn_end))
> +			clear_bit(i - gfn_start, bitmap);
> +	}
> +	mutex_unlock(&kvm->lock);
> +
> +	ret = -EFAULT;
> +
> +	n = bmap->num_pages % BITS_PER_BYTE;
> +	sz_bytes = ALIGN(bmap->num_pages, BITS_PER_BYTE) / BITS_PER_BYTE;

Maybe clearer:

	sz_bytes = BITS_TO_BYTES(bmap->num_pages);



> +
> +	/*
> +	 * Return the correct bitmap as per the number of pages being
> +	 * requested by the user. Ensure that we only copy bmap->num_pages
> +	 * bytes in the userspace buffer, if bmap->num_pages is not byte
> +	 * aligned we read the trailing bits from the userspace and copy
> +	 * those bits as is.
> +	 */

(see my comment on the commit message above.)


> +
> +	if (n) {
> +		unsigned char *bitmap_kernel = (unsigned char *)bitmap;
> +		unsigned char bitmap_user;
> +		unsigned long offset, mask;
> +
> +		offset = bmap->num_pages / BITS_PER_BYTE;
> +		if (copy_from_user(&bitmap_user, bmap->enc_bitmap + offset,
> +				sizeof(unsigned char)))
> +			goto out;
> +
> +		mask = GENMASK(n - 1, 0);
> +		bitmap_user &= ~mask;
> +		bitmap_kernel[offset] &= mask;
> +		bitmap_kernel[offset] |= bitmap_user;
> +	}
> +
> +	if (copy_to_user(bmap->enc_bitmap, bitmap, sz_bytes))
> +		goto out;
> +
> +	ret = 0;
> +out:
> +	kfree(bitmap);
> +	return ret;
> +}
> +
>   int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
>   {
>   	struct kvm_sev_cmd sev_cmd;
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 7122ea5f7c47..bff89cab3ed0 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -4314,6 +4314,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
>   	.msr_filter_changed = svm_msr_filter_changed,
> 
>   	.page_enc_status_hc = svm_page_enc_status_hc,
> +	.get_page_enc_bitmap = svm_get_page_enc_bitmap,
>   };
> 
>   static struct kvm_x86_init_ops svm_init_ops __initdata = {
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index 0103a23ca174..4ce73f1034b9 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -413,6 +413,7 @@ int nested_svm_exit_special(struct vcpu_svm *svm);
>   void sync_nested_vmcb_control(struct vcpu_svm *svm);
>   int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
>                              unsigned long npages, unsigned long enc);
> +int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
> 
>   extern struct kvm_x86_nested_ops svm_nested_ops;
> 
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 3afc78f18f69..d3cb95a4dd55 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -5695,6 +5695,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
>   	case KVM_X86_SET_MSR_FILTER:
>   		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
>   		break;
> +	case KVM_GET_PAGE_ENC_BITMAP: {
> +		struct kvm_page_enc_bitmap bitmap;
> +
> +		r = -EFAULT;
> +		if (copy_from_user(&bitmap, argp, sizeof(bitmap)))
> +			goto out;
> +
> +		r = -ENOTTY;
> +		if (kvm_x86_ops.get_page_enc_bitmap)
> +			r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap);
> +		break;
> +	}
>   	default:
>   		r = -ENOTTY;
>   	}
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 886802b8ffba..d0b9171bdb03 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -532,6 +532,16 @@ struct kvm_dirty_log {
>   	};
>   };
> 
> +/* for KVM_GET_PAGE_ENC_BITMAP */
> +struct kvm_page_enc_bitmap {
> +	__u64 start_gfn;
> +	__u64 num_pages;
> +	union {
> +		void __user *enc_bitmap; /* one bit per page */
> +		__u64 padding2;
> +	};
> +};
> +
>   /* for KVM_CLEAR_DIRTY_LOG */
>   struct kvm_clear_dirty_log {
>   	__u32 slot;
> @@ -1563,6 +1573,8 @@ struct kvm_pv_cmd {
>   /* Available with KVM_CAP_DIRTY_LOG_RING */
>   #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
> 
> +#define KVM_GET_PAGE_ENC_BITMAP	_IOW(KVMIO, 0xc6, struct kvm_page_enc_bitmap)

I see that kvm/next already defines ioctls numbered 0xc6 and 0xc7. 
Wouldn't these new ioctls (KVM_GET_PAGE_ENC_BITMAP, 
KVM_SET_PAGE_ENC_BITMAP) collide?


> +
>   /* Secure Encrypted Virtualization command */
>   enum sev_cmd_id {
>   	/* Guest initialization commands */
> 

-Dov

Kalra, Ashish Dec. 7, 2020, 10 p.m. UTC | #2

Hello Dov,

On Sun, Dec 06, 2020 at 01:02:47PM +0200, Dov Murik wrote:
> 
> 
> On 01/12/2020 2:47, Ashish Kalra wrote:
> > From: Brijesh Singh <[e-mail]>
> > 
> > The ioctl can be used to retrieve page encryption bitmap for a given
> > gfn range.
> > 
> > Return the correct bitmap as per the number of pages being requested
> > by the user. Ensure that we only copy bmap->num_pages bytes in the
> > userspace buffer, if bmap->num_pages is not byte aligned we read
> > the trailing bits from the userspace and copy those bits as is.
> 
> I think you meant to say "Ensure that we only copy bmap->num_pages *bits* in
> the userspace buffer".  But maybe I'm missed something.
>

Yes, that is correct. It should read bmap->num_pages *bits* instead of
*bytes*, i will fix the comments.

> 
> > 
> > Cc: Thomas Gleixner <[e-mail]>
> > Cc: Ingo Molnar <[e-mail]>
> > Cc: "H. Peter Anvin" <[e-mail]>
> > Cc: Paolo Bonzini <[e-mail]>
> > Cc: "Radim Krčmář" <[e-mail]>
> > Cc: Joerg Roedel <[e-mail]>
> > Cc: Borislav Petkov <[e-mail]>
> > Cc: Tom Lendacky <[e-mail]>
> > Cc: [e-mail]
> > Cc: [e-mail]
> > Cc: [e-mail]
> > Reviewed-by: Venu Busireddy <[e-mail]>
> > Signed-off-by: Brijesh Singh <[e-mail]>
> > Signed-off-by: Ashish Kalra <[e-mail]>
> > ---
> >   Documentation/virt/kvm/api.rst  | 27 +++++++++++++
> >   arch/x86/include/asm/kvm_host.h |  2 +
> >   arch/x86/kvm/svm/sev.c          | 70 +++++++++++++++++++++++++++++++++
> >   arch/x86/kvm/svm/svm.c          |  1 +
> >   arch/x86/kvm/svm/svm.h          |  1 +
> >   arch/x86/kvm/x86.c              | 12 ++++++
> >   include/uapi/linux/kvm.h        | 12 ++++++
> >   7 files changed, 125 insertions(+)
> > 
> > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> > index 70254eaa5229..ae410f4332ab 100644
> > --- a/Documentation/virt/kvm/api.rst
> > +++ b/Documentation/virt/kvm/api.rst
> > @@ -4671,6 +4671,33 @@ This ioctl resets VCPU registers and control structures according to
> >   the clear cpu reset definition in the POP. However, the cpu is not put
> >   into ESA mode. This reset is a superset of the initial reset.
> > 
> > +4.125 KVM_GET_PAGE_ENC_BITMAP (vm ioctl)
> > +---------------------------------------
> > +
> > +:Capability: basic
> > +:Architectures: x86
> > +:Type: vm ioctl
> > +:Parameters: struct kvm_page_enc_bitmap (in/out)
> > +:Returns: 0 on success, -1 on error
> > +
> > +/* for KVM_GET_PAGE_ENC_BITMAP */
> > +struct kvm_page_enc_bitmap {
> > +	__u64 start_gfn;
> > +	__u64 num_pages;
> > +	union {
> > +		void __user *enc_bitmap; /* one bit per page */
> > +		__u64 padding2;
> > +	};
> > +};
> > +
> > +The encrypted VMs have the concept of private and shared pages. The private
> > +pages are encrypted with the guest-specific key, while the shared pages may
> > +be encrypted with the hypervisor key. The KVM_GET_PAGE_ENC_BITMAP can
> > +be used to get the bitmap indicating whether the guest page is private
> > +or shared. The bitmap can be used during the guest migration. If the page
> > +is private then the userspace need to use SEV migration commands to transmit
> > +the page.
> > +
> > 
> >   4.125 KVM_S390_PV_COMMAND
> >   -------------------------
> > diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> > index d035dc983a7a..8c2e40199ecb 100644
> > --- a/arch/x86/include/asm/kvm_host.h
> > +++ b/arch/x86/include/asm/kvm_host.h
> > @@ -1284,6 +1284,8 @@ struct kvm_x86_ops {
> >   	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
> >   	int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa,
> >   				  unsigned long sz, unsigned long mode);
> > +	int (*get_page_enc_bitmap)(struct kvm *kvm,
> > +				struct kvm_page_enc_bitmap *bmap);
> >   };
> > 
> >   struct kvm_x86_nested_ops {
> > diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> > index 6b8bc1297f9c..a6586dd29767 100644
> > --- a/arch/x86/kvm/svm/sev.c
> > +++ b/arch/x86/kvm/svm/sev.c
> > @@ -1014,6 +1014,76 @@ int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
> >   	return 0;
> >   }
> > 
> > +int svm_get_page_enc_bitmap(struct kvm *kvm,
> > +				   struct kvm_page_enc_bitmap *bmap)
> > +{
> > +	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
> > +	unsigned long gfn_start, gfn_end;
> > +	unsigned long sz, i, sz_bytes;
> > +	unsigned long *bitmap;
> > +	int ret, n;
> > +
> > +	if (!sev_guest(kvm))
> > +		return -ENOTTY;
> > +
> > +	gfn_start = bmap->start_gfn;
> > +	gfn_end = gfn_start + bmap->num_pages;
> > +
> > +	sz = ALIGN(bmap->num_pages, BITS_PER_LONG) / BITS_PER_BYTE;
> > +	bitmap = kmalloc(sz, GFP_KERNEL);
> 
> Maybe use bitmap_alloc which accepts size in bits (and corresponding
> bitmap_free)?
>

I will look at this. 

> 
> > +	if (!bitmap)
> > +		return -ENOMEM;
> > +
> > +	/* by default all pages are marked encrypted */
> > +	memset(bitmap, 0xff, sz);
> 
> Maybe use bitmap_fill to clarify the intent?
>

Again, i will look at this. 
> 
> > +
> > +	mutex_lock(&kvm->lock);
> > +	if (sev->page_enc_bmap) {
> > +		i = gfn_start;
> > +		for_each_clear_bit_from(i, sev->page_enc_bmap,
> > +				      min(sev->page_enc_bmap_size, gfn_end))
> > +			clear_bit(i - gfn_start, bitmap);
> > +	}
> > +	mutex_unlock(&kvm->lock);
> > +
> > +	ret = -EFAULT;
> > +
> > +	n = bmap->num_pages % BITS_PER_BYTE;
> > +	sz_bytes = ALIGN(bmap->num_pages, BITS_PER_BYTE) / BITS_PER_BYTE;
> 
> Maybe clearer:
> 
> 	sz_bytes = BITS_TO_BYTES(bmap->num_pages);
> 
> 
> 
> > +
> > +	/*
> > +	 * Return the correct bitmap as per the number of pages being
> > +	 * requested by the user. Ensure that we only copy bmap->num_pages
> > +	 * bytes in the userspace buffer, if bmap->num_pages is not byte
> > +	 * aligned we read the trailing bits from the userspace and copy
> > +	 * those bits as is.
> > +	 */
> 
> (see my comment on the commit message above.)
> 
Yes, as i mentioned above, this need to be bmap->num pages *bits* and 
not *bytes*. 

> 
> > +
> > +	if (n) {
> > +		unsigned char *bitmap_kernel = (unsigned char *)bitmap;
> > +		unsigned char bitmap_user;
> > +		unsigned long offset, mask;
> > +
> > +		offset = bmap->num_pages / BITS_PER_BYTE;
> > +		if (copy_from_user(&bitmap_user, bmap->enc_bitmap + offset,
> > +				sizeof(unsigned char)))
> > +			goto out;
> > +
> > +		mask = GENMASK(n - 1, 0);
> > +		bitmap_user &= ~mask;
> > +		bitmap_kernel[offset] &= mask;
> > +		bitmap_kernel[offset] |= bitmap_user;
> > +	}
> > +
> > +	if (copy_to_user(bmap->enc_bitmap, bitmap, sz_bytes))
> > +		goto out;
> > +
> > +	ret = 0;
> > +out:
> > +	kfree(bitmap);
> > +	return ret;
> > +}
> > +
> >   int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
> >   {
> >   	struct kvm_sev_cmd sev_cmd;
> > diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> > index 7122ea5f7c47..bff89cab3ed0 100644
> > --- a/arch/x86/kvm/svm/svm.c
> > +++ b/arch/x86/kvm/svm/svm.c
> > @@ -4314,6 +4314,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
> >   	.msr_filter_changed = svm_msr_filter_changed,
> > 
> >   	.page_enc_status_hc = svm_page_enc_status_hc,
> > +	.get_page_enc_bitmap = svm_get_page_enc_bitmap,
> >   };
> > 
> >   static struct kvm_x86_init_ops svm_init_ops __initdata = {
> > diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> > index 0103a23ca174..4ce73f1034b9 100644
> > --- a/arch/x86/kvm/svm/svm.h
> > +++ b/arch/x86/kvm/svm/svm.h
> > @@ -413,6 +413,7 @@ int nested_svm_exit_special(struct vcpu_svm *svm);
> >   void sync_nested_vmcb_control(struct vcpu_svm *svm);
> >   int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
> >                              unsigned long npages, unsigned long enc);
> > +int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
> > 
> >   extern struct kvm_x86_nested_ops svm_nested_ops;
> > 
> > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> > index 3afc78f18f69..d3cb95a4dd55 100644
> > --- a/arch/x86/kvm/x86.c
> > +++ b/arch/x86/kvm/x86.c
> > @@ -5695,6 +5695,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
> >   	case KVM_X86_SET_MSR_FILTER:
> >   		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
> >   		break;
> > +	case KVM_GET_PAGE_ENC_BITMAP: {
> > +		struct kvm_page_enc_bitmap bitmap;
> > +
> > +		r = -EFAULT;
> > +		if (copy_from_user(&bitmap, argp, sizeof(bitmap)))
> > +			goto out;
> > +
> > +		r = -ENOTTY;
> > +		if (kvm_x86_ops.get_page_enc_bitmap)
> > +			r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap);
> > +		break;
> > +	}
> >   	default:
> >   		r = -ENOTTY;
> >   	}
> > diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> > index 886802b8ffba..d0b9171bdb03 100644
> > --- a/include/uapi/linux/kvm.h
> > +++ b/include/uapi/linux/kvm.h
> > @@ -532,6 +532,16 @@ struct kvm_dirty_log {
> >   	};
> >   };
> > 
> > +/* for KVM_GET_PAGE_ENC_BITMAP */
> > +struct kvm_page_enc_bitmap {
> > +	__u64 start_gfn;
> > +	__u64 num_pages;
> > +	union {
> > +		void __user *enc_bitmap; /* one bit per page */
> > +		__u64 padding2;
> > +	};
> > +};
> > +
> >   /* for KVM_CLEAR_DIRTY_LOG */
> >   struct kvm_clear_dirty_log {
> >   	__u32 slot;
> > @@ -1563,6 +1573,8 @@ struct kvm_pv_cmd {
> >   /* Available with KVM_CAP_DIRTY_LOG_RING */
> >   #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
> > 
> > +#define KVM_GET_PAGE_ENC_BITMAP	_IOW(KVMIO, 0xc6, struct kvm_page_enc_bitmap)
> 
> I see that kvm/next already defines ioctls numbered 0xc6 and 0xc7. Wouldn't
> these new ioctls (KVM_GET_PAGE_ENC_BITMAP, KVM_SET_PAGE_ENC_BITMAP) collide?
>

Yes, but they will be fixed for the next version of the patch-set i am
going to post. 

Thanks for your feedback.
Ashish

> 
> > +
> >   /* Secure Encrypted Virtualization command */
> >   enum sev_cmd_id {
> >   	/* Guest initialization commands */
> > 
> 
> -Dov

Patch

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 70254eaa5229..ae410f4332ab 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4671,6 +4671,33 @@  This ioctl resets VCPU registers and control structures according to
 the clear cpu reset definition in the POP. However, the cpu is not put
 into ESA mode. This reset is a superset of the initial reset.
 
+4.125 KVM_GET_PAGE_ENC_BITMAP (vm ioctl)
+---------------------------------------
+
+:Capability: basic
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_page_enc_bitmap (in/out)
+:Returns: 0 on success, -1 on error
+
+/* for KVM_GET_PAGE_ENC_BITMAP */
+struct kvm_page_enc_bitmap {
+	__u64 start_gfn;
+	__u64 num_pages;
+	union {
+		void __user *enc_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
+The encrypted VMs have the concept of private and shared pages. The private
+pages are encrypted with the guest-specific key, while the shared pages may
+be encrypted with the hypervisor key. The KVM_GET_PAGE_ENC_BITMAP can
+be used to get the bitmap indicating whether the guest page is private
+or shared. The bitmap can be used during the guest migration. If the page
+is private then the userspace need to use SEV migration commands to transmit
+the page.
+
 
 4.125 KVM_S390_PV_COMMAND
 -------------------------
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d035dc983a7a..8c2e40199ecb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1284,6 +1284,8 @@  struct kvm_x86_ops {
 	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
 	int (*page_enc_status_hc)(struct kvm *kvm, unsigned long gpa,
 				  unsigned long sz, unsigned long mode);
+	int (*get_page_enc_bitmap)(struct kvm *kvm,
+				struct kvm_page_enc_bitmap *bmap);
 };
 
 struct kvm_x86_nested_ops {
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6b8bc1297f9c..a6586dd29767 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1014,6 +1014,76 @@  int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
 	return 0;
 }
 
+int svm_get_page_enc_bitmap(struct kvm *kvm,
+				   struct kvm_page_enc_bitmap *bmap)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	unsigned long gfn_start, gfn_end;
+	unsigned long sz, i, sz_bytes;
+	unsigned long *bitmap;
+	int ret, n;
+
+	if (!sev_guest(kvm))
+		return -ENOTTY;
+
+	gfn_start = bmap->start_gfn;
+	gfn_end = gfn_start + bmap->num_pages;
+
+	sz = ALIGN(bmap->num_pages, BITS_PER_LONG) / BITS_PER_BYTE;
+	bitmap = kmalloc(sz, GFP_KERNEL);
+	if (!bitmap)
+		return -ENOMEM;
+
+	/* by default all pages are marked encrypted */
+	memset(bitmap, 0xff, sz);
+
+	mutex_lock(&kvm->lock);
+	if (sev->page_enc_bmap) {
+		i = gfn_start;
+		for_each_clear_bit_from(i, sev->page_enc_bmap,
+				      min(sev->page_enc_bmap_size, gfn_end))
+			clear_bit(i - gfn_start, bitmap);
+	}
+	mutex_unlock(&kvm->lock);
+
+	ret = -EFAULT;
+
+	n = bmap->num_pages % BITS_PER_BYTE;
+	sz_bytes = ALIGN(bmap->num_pages, BITS_PER_BYTE) / BITS_PER_BYTE;
+
+	/*
+	 * Return the correct bitmap as per the number of pages being
+	 * requested by the user. Ensure that we only copy bmap->num_pages
+	 * bytes in the userspace buffer, if bmap->num_pages is not byte
+	 * aligned we read the trailing bits from the userspace and copy
+	 * those bits as is.
+	 */
+
+	if (n) {
+		unsigned char *bitmap_kernel = (unsigned char *)bitmap;
+		unsigned char bitmap_user;
+		unsigned long offset, mask;
+
+		offset = bmap->num_pages / BITS_PER_BYTE;
+		if (copy_from_user(&bitmap_user, bmap->enc_bitmap + offset,
+				sizeof(unsigned char)))
+			goto out;
+
+		mask = GENMASK(n - 1, 0);
+		bitmap_user &= ~mask;
+		bitmap_kernel[offset] &= mask;
+		bitmap_kernel[offset] |= bitmap_user;
+	}
+
+	if (copy_to_user(bmap->enc_bitmap, bitmap, sz_bytes))
+		goto out;
+
+	ret = 0;
+out:
+	kfree(bitmap);
+	return ret;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7122ea5f7c47..bff89cab3ed0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4314,6 +4314,7 @@  static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.msr_filter_changed = svm_msr_filter_changed,
 
 	.page_enc_status_hc = svm_page_enc_status_hc,
+	.get_page_enc_bitmap = svm_get_page_enc_bitmap,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 0103a23ca174..4ce73f1034b9 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -413,6 +413,7 @@  int nested_svm_exit_special(struct vcpu_svm *svm);
 void sync_nested_vmcb_control(struct vcpu_svm *svm);
 int svm_page_enc_status_hc(struct kvm *kvm, unsigned long gpa,
                            unsigned long npages, unsigned long enc);
+int svm_get_page_enc_bitmap(struct kvm *kvm, struct kvm_page_enc_bitmap *bmap);
 
 extern struct kvm_x86_nested_ops svm_nested_ops;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3afc78f18f69..d3cb95a4dd55 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5695,6 +5695,18 @@  long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_X86_SET_MSR_FILTER:
 		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
 		break;
+	case KVM_GET_PAGE_ENC_BITMAP: {
+		struct kvm_page_enc_bitmap bitmap;
+
+		r = -EFAULT;
+		if (copy_from_user(&bitmap, argp, sizeof(bitmap)))
+			goto out;
+
+		r = -ENOTTY;
+		if (kvm_x86_ops.get_page_enc_bitmap)
+			r = kvm_x86_ops.get_page_enc_bitmap(kvm, &bitmap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 886802b8ffba..d0b9171bdb03 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -532,6 +532,16 @@  struct kvm_dirty_log {
 	};
 };
 
+/* for KVM_GET_PAGE_ENC_BITMAP */
+struct kvm_page_enc_bitmap {
+	__u64 start_gfn;
+	__u64 num_pages;
+	union {
+		void __user *enc_bitmap; /* one bit per page */
+		__u64 padding2;
+	};
+};
+
 /* for KVM_CLEAR_DIRTY_LOG */
 struct kvm_clear_dirty_log {
 	__u32 slot;
@@ -1563,6 +1573,8 @@  struct kvm_pv_cmd {
 /* Available with KVM_CAP_DIRTY_LOG_RING */
 #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
 
+#define KVM_GET_PAGE_ENC_BITMAP	_IOW(KVMIO, 0xc6, struct kvm_page_enc_bitmap)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */