Re: [PATCH v12 21/29] KVM: SEV: Implement gmem hook for initializing private pages

[Paolo Bonzini <pbonzini@redhat.com>]

On 3/29/24 23:58, Michael Roth wrote:
> This will handle the RMP table updates needed to put a page into a
> private state before mapping it into an SEV-SNP guest.
> 
> Signed-off-by: Michael Roth <michael.roth@amd.com>
> ---
>   arch/x86/kvm/Kconfig   |  1 +
>   arch/x86/kvm/svm/sev.c | 98 ++++++++++++++++++++++++++++++++++++++++++
>   arch/x86/kvm/svm/svm.c |  2 +
>   arch/x86/kvm/svm/svm.h |  5 +++
>   arch/x86/kvm/x86.c     |  5 +++
>   virt/kvm/guest_memfd.c |  4 +-
>   6 files changed, 113 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> index d0bb0e7a4e80..286b40d0b07c 100644
> --- a/arch/x86/kvm/Kconfig
> +++ b/arch/x86/kvm/Kconfig
> @@ -124,6 +124,7 @@ config KVM_AMD_SEV
>   	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
>   	select ARCH_HAS_CC_PLATFORM
>   	select KVM_GENERIC_PRIVATE_MEM
> +	select HAVE_KVM_GMEM_PREPARE
>   	help
>   	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
>   	  with Encrypted State (SEV-ES) on AMD processors.
> diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
> index 9ea13c2de668..e1f8be1df219 100644
> --- a/arch/x86/kvm/svm/sev.c
> +++ b/arch/x86/kvm/svm/sev.c
> @@ -4282,3 +4282,101 @@ void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
>   out:
>   	put_page(pfn_to_page(pfn));
>   }
> +
> +static bool is_pfn_range_shared(kvm_pfn_t start, kvm_pfn_t end)
> +{
> +	kvm_pfn_t pfn = start;
> +
> +	while (pfn < end) {
> +		int ret, rmp_level;
> +		bool assigned;
> +
> +		ret = snp_lookup_rmpentry(pfn, &assigned, &rmp_level);
> +		if (ret) {
> +			pr_warn_ratelimited("SEV: Failed to retrieve RMP entry: PFN 0x%llx GFN start 0x%llx GFN end 0x%llx RMP level %d error %d\n",
> +					    pfn, start, end, rmp_level, ret);
> +			return false;
> +		}
> +
> +		if (assigned) {
> +			pr_debug("%s: overlap detected, PFN 0x%llx start 0x%llx end 0x%llx RMP level %d\n",
> +				 __func__, pfn, start, end, rmp_level);
> +			return false;
> +		}
> +
> +		pfn++;
> +	}
> +
> +	return true;
> +}
> +
> +static u8 max_level_for_order(int order)
> +{
> +	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> +		return PG_LEVEL_2M;
> +
> +	return PG_LEVEL_4K;
> +}
> +
> +static bool is_large_rmp_possible(struct kvm *kvm, kvm_pfn_t pfn, int order)
> +{
> +	kvm_pfn_t pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
> +
> +	/*
> +	 * If this is a large folio, and the entire 2M range containing the
> +	 * PFN is currently shared, then the entire 2M-aligned range can be
> +	 * set to private via a single 2M RMP entry.
> +	 */
> +	if (max_level_for_order(order) > PG_LEVEL_4K &&
> +	    is_pfn_range_shared(pfn_aligned, pfn_aligned + PTRS_PER_PMD))
> +		return true;
> +
> +	return false;
> +}
> +
> +int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
> +{
> +	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
> +	kvm_pfn_t pfn_aligned;
> +	gfn_t gfn_aligned;
> +	int level, rc;
> +	bool assigned;
> +
> +	if (!sev_snp_guest(kvm))
> +		return 0;
> +
> +	rc = snp_lookup_rmpentry(pfn, &assigned, &level);
> +	if (rc) {
> +		pr_err_ratelimited("SEV: Failed to look up RMP entry: GFN %llx PFN %llx error %d\n",
> +				   gfn, pfn, rc);
> +		return -ENOENT;
> +	}
> +
> +	if (assigned) {
> +		pr_debug("%s: already assigned: gfn %llx pfn %llx max_order %d level %d\n",
> +			 __func__, gfn, pfn, max_order, level);
> +		return 0;
> +	}
> +
> +	if (is_large_rmp_possible(kvm, pfn, max_order)) {
> +		level = PG_LEVEL_2M;
> +		pfn_aligned = ALIGN_DOWN(pfn, PTRS_PER_PMD);
> +		gfn_aligned = ALIGN_DOWN(gfn, PTRS_PER_PMD);
> +	} else {
> +		level = PG_LEVEL_4K;
> +		pfn_aligned = pfn;
> +		gfn_aligned = gfn;
> +	}
> +
> +	rc = rmp_make_private(pfn_aligned, gfn_to_gpa(gfn_aligned), level, sev->asid, false);
> +	if (rc) {
> +		pr_err_ratelimited("SEV: Failed to update RMP entry: GFN %llx PFN %llx level %d error %d\n",
> +				   gfn, pfn, level, rc);
> +		return -EINVAL;
> +	}
> +
> +	pr_debug("%s: updated: gfn %llx pfn %llx pfn_aligned %llx max_order %d level %d\n",
> +		 __func__, gfn, pfn, pfn_aligned, max_order, level);
> +
> +	return 0;
> +}
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index a895d3f07cb8..c099154e326a 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -5078,6 +5078,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
>   	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
>   	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
>   	.alloc_apic_backing_page = svm_alloc_apic_backing_page,
> +
> +	.gmem_prepare = sev_gmem_prepare,
>   };
>   
>   /*
> diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
> index 0cdcd0759fe0..53618cfc2b89 100644
> --- a/arch/x86/kvm/svm/svm.h
> +++ b/arch/x86/kvm/svm/svm.h
> @@ -730,6 +730,7 @@ extern unsigned int max_sev_asid;
>   void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code);
>   void sev_vcpu_unblocking(struct kvm_vcpu *vcpu);
>   void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
> +int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
>   #else
>   static inline struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) {
>   	return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
> @@ -746,6 +747,10 @@ static inline int sev_dev_get_attr(u64 attr, u64 *val) { return -ENXIO; }
>   static inline void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code) {}
>   static inline void sev_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
>   static inline void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu) {}
> +static inline int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order)
> +{
> +	return 0;
> +}
>   
>   #endif
>   
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 617c38656757..d05922684005 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -13615,6 +13615,11 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
>   EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
>   
>   #ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
> +bool kvm_arch_gmem_prepare_needed(struct kvm *kvm)
> +{
> +	return kvm->arch.vm_type == KVM_X86_SNP_VM;
> +}
> +
>   int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
>   {
>   	return static_call(kvm_x86_gmem_prepare)(kvm, pfn, gfn, max_order);
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index 3e3c4b7fff3b..11952254ae48 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -46,8 +46,8 @@ static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct fol
>   		gfn = slot->base_gfn + index - slot->gmem.pgoff;
>   		rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, compound_order(compound_head(page)));
>   		if (rc) {
> -			pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx, error %d.\n",
> -					    index, rc);
> +			pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n",
> +					    index, gfn, pfn, rc);
>   			return rc;
>   		}
>   	}

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>

Paolo