KVM: guest_memfd: Add hook for invalidating memory

In some cases, like with SEV-SNP, guest memory needs to be updated in a
platform-specific manner before it can be safely freed back to the host.
Wire up arch-defined hooks to the .free_folio kvm_gmem_aops callback to
allow for special handling of this sort when freeing memory in response
to FALLOC_FL_PUNCH_HOLE operations and when releasing the inode, and go
ahead and define an arch-specific hook for x86 since it will be needed
for handling memory used for SEV-SNP guests.
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-Id: <20231230172351.574091-6-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm-x86-ops.h

@@ -140,6 +140,7 @@ KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 KVM_X86_OP_OPTIONAL(get_untagged_addr)
 KVM_X86_OP_OPTIONAL(alloc_apic_backing_page)
 KVM_X86_OP_OPTIONAL_RET0(gmem_prepare)
+KVM_X86_OP_OPTIONAL(gmem_invalidate)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL

arch/x86/include/asm/kvm_host.h

@@ -1813,6 +1813,7 @@ struct kvm_x86_ops {
 	gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
 	void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu);
 	int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
+	void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end);
 };
 
 struct kvm_x86_nested_ops {

arch/x86/kvm/x86.c

@@ -13605,6 +13605,13 @@ int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_ord
 }
 #endif
 
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
+{
+	static_call_cond(kvm_x86_gmem_invalidate)(start, end);
+}
+#endif
+
 int kvm_spec_ctrl_test_value(u64 value)
 {
 	/*

include/linux/kvm_host.h

@@ -2475,4 +2475,8 @@ typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
 long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
 		       kvm_gmem_populate_cb post_populate, void *opaque);
 
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+#endif
+
 #endif

virt/kvm/Kconfig

@@ -113,3 +113,7 @@ config KVM_GENERIC_PRIVATE_MEM
 config HAVE_KVM_GMEM_PREPARE
        bool
        depends on KVM_PRIVATE_MEM
+
+config HAVE_KVM_GMEM_INVALIDATE
+       bool
+       depends on KVM_PRIVATE_MEM

virt/kvm/guest_memfd.c

@@ -343,10 +343,24 @@ static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *fol
 	return MF_DELAYED;
 }
 
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+static void kvm_gmem_free_folio(struct folio *folio)
+{
+	struct page *page = folio_page(folio, 0);
+	kvm_pfn_t pfn = page_to_pfn(page);
+	int order = folio_order(folio);
+
+	kvm_arch_gmem_invalidate(pfn, pfn + (1ul << order));
+}
+#endif
+
 static const struct address_space_operations kvm_gmem_aops = {
 	.dirty_folio = noop_dirty_folio,
 	.migrate_folio	= kvm_gmem_migrate_folio,
 	.error_remove_folio = kvm_gmem_error_folio,
+#ifdef CONFIG_HAVE_KVM_GMEM_INVALIDATE
+	.free_folio = kvm_gmem_free_folio,
+#endif
 };
 
 static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,