Re: [PATCH v8 23/46] KVM: TDX: Make source page optional for KVM_TDX_INIT_MEM_REGION

[Yan Zhao <yan.y.zhao@intel.com>]

On Thu, Jun 18, 2026 at 05:32:00PM -0700, Ackerley Tng via B4 Relay wrote:
> From: Ackerley Tng <ackerleytng@google.com>
> 
> Update tdx_gmem_post_populate() to handle cases where a source page is
> not explicitly provided. Instead of returning -EOPNOTSUPP when src_page
> is NULL, default to using the page associated with the destination PFN.
> 
> This change allows for in-place memory conversion where the data is
> already present in the target PFN, ensuring the TDX module has a valid
> source page reference for the TDH.MEM.PAGE.ADD operation.
> 
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> ---
>  Documentation/virt/kvm/x86/intel-tdx.rst |  4 ++++
>  arch/x86/kvm/vmx/tdx.c                   | 11 ++++++++---
>  2 files changed, 12 insertions(+), 3 deletions(-)
> 
> diff --git a/Documentation/virt/kvm/x86/intel-tdx.rst b/Documentation/virt/kvm/x86/intel-tdx.rst
> index 6a222e9d09541..74357fe87f9ec 100644
> --- a/Documentation/virt/kvm/x86/intel-tdx.rst
> +++ b/Documentation/virt/kvm/x86/intel-tdx.rst
> @@ -158,6 +158,10 @@ KVM_TDX_INIT_MEM_REGION
>  Initialize @nr_pages TDX guest private memory starting from @gpa with userspace
>  provided data from @source_addr. @source_addr must be PAGE_SIZE-aligned.
>  
> +If guest_memfd in-place conversion is enabled, pass NULL for @source_addr to
> +initialize the memory region using memory contents already populated in
> +guest_memfd memory.
> +
>  Note, before calling this sub command, memory attribute of the range
>  [gpa, gpa + nr_pages] needs to be private.  Userspace can use
>  KVM_SET_MEMORY_ATTRIBUTES to set the attribute.
> diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
> index ffe9d0db58c59..56d10333c61a7 100644
> --- a/arch/x86/kvm/vmx/tdx.c
> +++ b/arch/x86/kvm/vmx/tdx.c
> @@ -3198,8 +3198,12 @@ static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
>  	if (KVM_BUG_ON(kvm_tdx->page_add_src, kvm))
>  		return -EIO;
>  
> -	if (!src_page)
> -		return -EOPNOTSUPP;
> +	if (!src_page) {
> +		if (!gmem_in_place_conversion)
When userspace turns on gmem_in_place_conversion while creating guest_memfd
without the MMAP flag, the absence of src_page should still be treated as an
error.

Additionally, to properly enable in-place copying for the TDX initial memory
region, userspace must not only specify source_addr to NULL, but also follow
a specific sequence (where steps 1/2/3/7 are required only for in-place copy):
1. create guest_memfd with MMAP flag
2. mmap the guest_memfd.
3. convert the initial memory range to shared.
4. copy initial content to the source page.
5. convert the initial memory range to private
6. invoke ioctl KVM_TDX_INIT_MEM_REGION.
7. do not unmap the source backend.

So, would it be reasonable to introduce a dedicated flag that allows userspace
to explicitly opt into the in-place copy functionality? e.g.,

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 1585ec804066..d047a6efc728 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -1043,6 +1043,9 @@ struct kvm_tdx_init_vm {
 };

 #define KVM_TDX_MEASURE_MEMORY_REGION   _BITULL(0)
+#define KVM_TDX_IN_PLACE_COPY_INITIAL_MEMORY_REGION _BITULL(1)
+#define KVM_TDX_INIT_MEM_VALID_FLAGS (KVM_TDX_MEASURE_MEMORY_REGION | \
+                                     KVM_TDX_IN_PLACE_COPY_INITIAL_MEMORY_REGION)

 struct kvm_tdx_init_mem_region {
        __u64 source_addr;
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 56d10333c61a..6072b38ceb37 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -3190,6 +3190,7 @@ static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
                                  struct page *src_page, void *_arg)
 {
        struct tdx_gmem_post_populate_arg *arg = _arg;
+       bool in_place_copy = arg->flags & KVM_TDX_IN_PLACE_COPY_INITIAL_MEMORY_REGION;
        struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
        u64 err, entry, level_state;
        gpa_t gpa = gfn_to_gpa(gfn);
@@ -3199,7 +3200,7 @@ static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
                return -EIO;

        if (!src_page) {
-               if (!gmem_in_place_conversion)
+               if (!in_place_copy)
                        return -EOPNOTSUPP;

                src_page = pfn_to_page(pfn);
@@ -3245,7 +3246,7 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c
        if (kvm_tdx->state == TD_STATE_RUNNABLE)
                return -EINVAL;

-       if (cmd->flags & ~KVM_TDX_MEASURE_MEMORY_REGION)
+       if (cmd->flags & ~KVM_TDX_INIT_MEM_VALID_FLAGS)
                return -EINVAL;

> +			return -EOPNOTSUPP;
> +
> +		src_page = pfn_to_page(pfn);
> +	}
>  
>  	kvm_tdx->page_add_src = src_page;
>  	ret = kvm_tdp_mmu_map_private_pfn(arg->vcpu, gfn, pfn);
> @@ -3278,7 +3282,8 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c
>  			break;
>  		}
>  
> -		region.source_addr += PAGE_SIZE;
> +		if (region.source_addr)
> +			region.source_addr += PAGE_SIZE;
>  		region.gpa += PAGE_SIZE;
>  		region.nr_pages--;
>  
> 
> -- 
> 2.55.0.rc0.738.g0c8ab3ebcc-goog
> 
>