Merge branch 'kvm-coco-hooks' into HEAD

Common patches for the target-independent functionality and hooks
that are needed by SEV-SNP and TDX.

Author: bonzini

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

@@ -139,6 +139,9 @@ KVM_X86_OP(vcpu_deliver_sipi_vector)
 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_RET0(private_max_mapping_level)
+KVM_X86_OP_OPTIONAL(gmem_invalidate)
 
 #undef KVM_X86_OP
 #undef KVM_X86_OP_OPTIONAL

arch/x86/include/asm/kvm_host.h

@@ -1812,6 +1812,9 @@ 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);
+	int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn);
 };
 
 struct kvm_x86_nested_ops {

arch/x86/kvm/mmu/mmu.c

@@ -4280,6 +4280,25 @@ static inline u8 kvm_max_level_for_order(int order)
 	return PG_LEVEL_4K;
 }
 
+static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn,
+					u8 max_level, int gmem_order)
+{
+	u8 req_max_level;
+
+	if (max_level == PG_LEVEL_4K)
+		return PG_LEVEL_4K;
+
+	max_level = min(kvm_max_level_for_order(gmem_order), max_level);
+	if (max_level == PG_LEVEL_4K)
+		return PG_LEVEL_4K;
+
+	req_max_level = static_call(kvm_x86_private_max_mapping_level)(kvm, pfn);
+	if (req_max_level)
+		max_level = min(max_level, req_max_level);
+
+	return req_max_level;
+}
+
 static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 				   struct kvm_page_fault *fault)
 {
@@ -4297,9 +4316,9 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
 		return r;
 	}
 
-	fault->max_level = min(kvm_max_level_for_order(max_order),
-			       fault->max_level);
 	fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY);
+	fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn,
+							 fault->max_level, max_order);
 
 	return RET_PF_CONTINUE;
 }

arch/x86/kvm/x86.c

@@ -13599,6 +13599,19 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+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);
+}
+#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

@@ -2441,4 +2441,40 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_PRIVATE_MEM */
 
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
+bool kvm_arch_gmem_prepare_needed(struct kvm *kvm);
+#endif
+
+/**
+ * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
+ *
+ * @kvm: KVM instance
+ * @gfn: starting GFN to be populated
+ * @src: userspace-provided buffer containing data to copy into GFN range
+ *       (passed to @post_populate, and incremented on each iteration
+ *       if not NULL)
+ * @npages: number of pages to copy from userspace-buffer
+ * @post_populate: callback to issue for each gmem page that backs the GPA
+ *                 range
+ * @opaque: opaque data to pass to @post_populate callback
+ *
+ * This is primarily intended for cases where a gmem-backed GPA range needs
+ * to be initialized with userspace-provided data prior to being mapped into
+ * the guest as a private page. This should be called with the slots->lock
+ * held so that caller-enforced invariants regarding the expected memory
+ * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES.
+ *
+ * Returns the number of pages that were populated.
+ */
+typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+				    void __user *src, int order, void *opaque);
+
+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

include/linux/pagemap.h

@@ -207,6 +207,7 @@ enum mapping_flags {
 	AS_STABLE_WRITES,	/* must wait for writeback before modifying
 				   folio contents */
 	AS_UNMOVABLE,		/* The mapping cannot be moved, ever */
+	AS_INACCESSIBLE,	/* Do not attempt direct R/W access to the mapping */
 };
 
 /**

mm/truncate.c

@@ -233,7 +233,8 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
 	 * doing a complex calculation here, and then doing the zeroing
 	 * anyway if the page split fails.
 	 */
-	folio_zero_range(folio, offset, length);
+	if (!(folio->mapping->flags & AS_INACCESSIBLE))
+		folio_zero_range(folio, offset, length);
 
 	if (folio_has_private(folio))
 		folio_invalidate(folio, offset, length);

virt/kvm/Kconfig

@@ -109,3 +109,11 @@ config KVM_GENERIC_PRIVATE_MEM
        select KVM_GENERIC_MEMORY_ATTRIBUTES
        select KVM_PRIVATE_MEM
        bool
+
+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

@@ -13,14 +13,50 @@ struct kvm_gmem {
 	struct list_head entry;
 };
 
-static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
+static int kvm_gmem_prepare_folio(struct inode *inode, pgoff_t index, struct folio *folio)
+{
+#ifdef CONFIG_HAVE_KVM_GMEM_PREPARE
+	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
+	struct kvm_gmem *gmem;
+
+	list_for_each_entry(gmem, gmem_list, entry) {
+		struct kvm_memory_slot *slot;
+		struct kvm *kvm = gmem->kvm;
+		struct page *page;
+		kvm_pfn_t pfn;
+		gfn_t gfn;
+		int rc;
+
+		if (!kvm_arch_gmem_prepare_needed(kvm))
+			continue;
+
+		slot = xa_load(&gmem->bindings, index);
+		if (!slot)
+			continue;
+
+		page = folio_file_page(folio, index);
+		pfn = page_to_pfn(page);
+		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);
+			return rc;
+		}
+	}
+
+#endif
+	return 0;
+}
+
+static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index, bool prepare)
 {
 	struct folio *folio;
 
 	/* TODO: Support huge pages. */
 	folio = filemap_grab_folio(inode->i_mapping, index);
-	if (IS_ERR_OR_NULL(folio))
-		return NULL;
+	if (IS_ERR(folio))
+		return folio;
 
 	/*
 	 * Use the up-to-date flag to track whether or not the memory has been
@@ -41,6 +77,15 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
 		folio_mark_uptodate(folio);
 	}
 
+	if (prepare) {
+		int r =	kvm_gmem_prepare_folio(inode, index, folio);
+		if (r < 0) {
+			folio_unlock(folio);
+			folio_put(folio);
+			return ERR_PTR(r);
+		}
+	}
+
 	/*
 	 * Ignore accessed, referenced, and dirty flags.  The memory is
 	 * unevictable and there is no storage to write back to.
@@ -145,9 +190,9 @@ static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
 			break;
 		}
 
-		folio = kvm_gmem_get_folio(inode, index);
-		if (!folio) {
-			r = -ENOMEM;
+		folio = kvm_gmem_get_folio(inode, index, true);
+		if (IS_ERR(folio)) {
+			r = PTR_ERR(folio);
 			break;
 		}
 
@@ -298,10 +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,
@@ -357,6 +416,7 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 	inode->i_private = (void *)(unsigned long)flags;
 	inode->i_op = &kvm_gmem_iops;
 	inode->i_mapping->a_ops = &kvm_gmem_aops;
+	inode->i_mapping->flags |= AS_INACCESSIBLE;
 	inode->i_mode |= S_IFREG;
 	inode->i_size = size;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
@@ -482,32 +542,29 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot)
 	fput(file);
 }
 
-int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
-		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+static int __kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot,
+		       gfn_t gfn, kvm_pfn_t *pfn, int *max_order, bool prepare)
 {
 	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
-	struct kvm_gmem *gmem;
+	struct kvm_gmem *gmem = file->private_data;
 	struct folio *folio;
 	struct page *page;
-	struct file *file;
 	int r;
 
-	file = kvm_gmem_get_file(slot);
-	if (!file)
+	if (file != slot->gmem.file) {
+		WARN_ON_ONCE(slot->gmem.file);
 		return -EFAULT;
+	}
 
 	gmem = file->private_data;
-
-	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
-		r = -EIO;
-		goto out_fput;
+	if (xa_load(&gmem->bindings, index) != slot) {
+		WARN_ON_ONCE(xa_load(&gmem->bindings, index));
+		return -EIO;
 	}
 
-	folio = kvm_gmem_get_folio(file_inode(file), index);
-	if (!folio) {
-		r = -ENOMEM;
-		goto out_fput;
-	}
+	folio = kvm_gmem_get_folio(file_inode(file), index, prepare);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
 	if (folio_test_hwpoison(folio)) {
 		r = -EHWPOISON;
@@ -524,9 +581,73 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
 
 out_unlock:
 	folio_unlock(folio);
-out_fput:
-	fput(file);
 
 	return r;
 }
+
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
+{
+	struct file *file = kvm_gmem_get_file(slot);
+	int r;
+
+	if (!file)
+		return -EFAULT;
+
+	r = __kvm_gmem_get_pfn(file, slot, gfn, pfn, max_order, true);
+	fput(file);
+	return r;
+}
 EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);
+
+long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages,
+		       kvm_gmem_populate_cb post_populate, void *opaque)
+{
+	struct file *file;
+	struct kvm_memory_slot *slot;
+	void __user *p;
+
+	int ret = 0, max_order;
+	long i;
+
+	lockdep_assert_held(&kvm->slots_lock);
+	if (npages < 0)
+		return -EINVAL;
+
+	slot = gfn_to_memslot(kvm, start_gfn);
+	if (!kvm_slot_can_be_private(slot))
+		return -EINVAL;
+
+	file = kvm_gmem_get_file(slot);
+	if (!file)
+		return -EFAULT;
+
+	filemap_invalidate_lock(file->f_mapping);
+
+	npages = min_t(ulong, slot->npages - (start_gfn - slot->base_gfn), npages);
+	for (i = 0; i < npages; i += (1 << max_order)) {
+		gfn_t gfn = start_gfn + i;
+		kvm_pfn_t pfn;
+
+		ret = __kvm_gmem_get_pfn(file, slot, gfn, &pfn, &max_order, false);
+		if (ret)
+			break;
+
+		if (!IS_ALIGNED(gfn, (1 << max_order)) ||
+		    (npages - i) < (1 << max_order))
+			max_order = 0;
+
+		p = src ? src + i * PAGE_SIZE : NULL;
+		ret = post_populate(kvm, gfn, pfn, p, max_order, opaque);
+
+		put_page(pfn_to_page(pfn));
+		if (ret)
+			break;
+	}
+
+	filemap_invalidate_unlock(file->f_mapping);
+
+	fput(file);
+	return ret && !i ? ret : i;
+}
+EXPORT_SYMBOL_GPL(kvm_gmem_populate);