Re: [RFC PATCH v2 21/23] KVM: TDX: Preallocate PAMT pages to be used in split path

[Binbin Wu <binbin.wu@linux.intel.com>]

On 8/7/2025 5:46 PM, Yan Zhao wrote:
> From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
>
> Preallocate a page to be used in the split_external_spt() path.

Not just "a" page.

>
> Kernel needs one PAMT page pair for external_spt and one that provided
> directly to the TDH.MEM.PAGE.DEMOTE SEAMCALL.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Co-developed-by: Yan Zhao <yan.y.zhao@intel.com>
> Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
> ---
> RFC v2:
> - Pulled from
>    git://git.kernel.org/pub/scm/linux/kernel/git/kas/linux.git tdx/dpamt-huge.
> - Implemented the flow of topup pamt_page_cache in
>    tdp_mmu_split_huge_pages_root() (Yan)
> ---
>   arch/x86/include/asm/kvm_host.h |  2 ++
>   arch/x86/kvm/mmu/mmu.c          |  1 +
>   arch/x86/kvm/mmu/tdp_mmu.c      | 51 +++++++++++++++++++++++++++++++++
>   3 files changed, 54 insertions(+)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 6b6c46c27390..508b133df903 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1591,6 +1591,8 @@ struct kvm_arch {
>   #define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1)
>   	struct kvm_mmu_memory_cache split_desc_cache;
>   
> +	struct kvm_mmu_memory_cache pamt_page_cache;
> +
>   	gfn_t gfn_direct_bits;
>   
>   	/*
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index f23d8fc59323..e581cee37f64 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -6848,6 +6848,7 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm)
>   	kvm_mmu_free_memory_cache(&kvm->arch.split_desc_cache);
>   	kvm_mmu_free_memory_cache(&kvm->arch.split_page_header_cache);
>   	kvm_mmu_free_memory_cache(&kvm->arch.split_shadow_page_cache);
> +	kvm_mmu_free_memory_cache(&kvm->arch.pamt_page_cache);
>   }
>   
>   void kvm_mmu_uninit_vm(struct kvm *kvm)
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index eb758aaa4374..064c4e823658 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -1584,6 +1584,27 @@ static bool iter_cross_boundary(struct tdp_iter *iter, gfn_t start, gfn_t end)
>   		 (iter->gfn + KVM_PAGES_PER_HPAGE(iter->level)) <= end);
>   }
>   
> +static bool need_topup_mirror_caches(struct kvm *kvm)
> +{
> +	int nr = tdx_nr_pamt_pages() * 2;
> +
> +	return kvm_mmu_memory_cache_nr_free_objects(&kvm->arch.pamt_page_cache) < nr;
> +}
> +
> +static int topup_mirror_caches(struct kvm *kvm)
> +{
> +	int r, nr;
> +
> +	/* One for external_spt, one for TDH.MEM.PAGE.DEMOTE */

The comment is a bit confusing.
IIUC, external_spt is also for TDH.MEM.PAGE.DEMOTE.
and it's "one pair" for PAMT pages.

> +	nr = tdx_nr_pamt_pages() * 2;
> +
> +	r = kvm_mmu_topup_memory_cache(&kvm->arch.pamt_page_cache, nr);
> +	if (r)
> +		return r;
> +
> +	return 0;

This could be simplified:
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 064c4e823658..35d052aa408c 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1593,16 +1593,12 @@ static bool need_topup_mirror_caches(struct kvm *kvm)

  static int topup_mirror_caches(struct kvm *kvm)
  {
-       int r, nr;
+       int nr;

         /* One for external_spt, one for TDH.MEM.PAGE.DEMOTE */
         nr = tdx_nr_pamt_pages() * 2;

-       r = kvm_mmu_topup_memory_cache(&kvm->arch.pamt_page_cache, nr);
-       if (r)
-               return r;
-
-       return 0;
+       return kvm_mmu_topup_memory_cache(&kvm->arch.pamt_page_cache, nr);
  }

> +}
> +
>   static int tdp_mmu_split_huge_pages_root(struct kvm *kvm,
>   					 struct kvm_mmu_page *root,
>   					 gfn_t start, gfn_t end,
> @@ -1656,6 +1677,36 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm,
>   			continue;
>   		}
>   
> +		if (is_mirror_sp(root) && need_topup_mirror_caches(kvm)) {
> +			int r;
> +
> +			rcu_read_unlock();
> +
> +			if (shared)
> +				read_unlock(&kvm->mmu_lock);
> +			else
> +				write_unlock(&kvm->mmu_lock);
> +
> +			r = topup_mirror_caches(kvm);
> +
> +			if (shared)
> +				read_lock(&kvm->mmu_lock);
> +			else
> +				write_lock(&kvm->mmu_lock);
> +
> +			if (r) {
> +				trace_kvm_mmu_split_huge_page(iter.gfn,
> +							      iter.old_spte,
> +							      iter.level, r);
> +				return r;
> +			}
> +
> +			rcu_read_lock();
> +
> +			iter.yielded = true;
> +			continue;
> +		}
> +
>   		tdp_mmu_init_child_sp(sp, &iter);
>   
>   		if (tdp_mmu_split_huge_page(kvm, &iter, sp, shared))