[RFC PATCH v4 08/14] KVM: guest_memfd: Add guest_memfd support to kvm_(read|/write)_guest_page()

[Fuad Tabba <tabba@google.com>]

Make kvm_(read|/write)_guest_page() capable of accessing guest
memory for slots that don't have a userspace address, but only if
the memory is mappable, which also indicates that it is
accessible by the host.

Signed-off-by: Fuad Tabba <tabba@google.com>
---
 virt/kvm/kvm_main.c | 133 +++++++++++++++++++++++++++++++++++++-------
 1 file changed, 114 insertions(+), 19 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fffff01cebe7..53692feb6213 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3184,23 +3184,110 @@ int kvm_gmem_clear_mappable(struct kvm *kvm, gfn_t start, gfn_t end)
 	return r;
 }
 
+static int __kvm_read_guest_memfd_page(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, void *data, int offset,
+				       int len)
+{
+	struct page *page;
+	u64 pfn;
+	int r;
+
+	/*
+	 * Holds the folio lock until after checking whether it can be faulted
+	 * in, to avoid races with paths that change a folio's mappability.
+	 */
+	r = kvm_gmem_get_pfn_locked(kvm, slot, gfn, &pfn, &page, NULL);
+	if (r)
+		return r;
+
+	if (!kvm_gmem_is_mappable(kvm, gfn, gfn + 1)) {
+		r = -EPERM;
+		goto unlock;
+	}
+	memcpy(data, page_address(page) + offset, len);
+unlock:
+	unlock_page(page);
+	if (r)
+		put_page(page);
+	else
+		kvm_release_page_clean(page);
+
+	return r;
+}
+
+static int __kvm_write_guest_memfd_page(struct kvm *kvm,
+					struct kvm_memory_slot *slot,
+					gfn_t gfn, const void *data,
+					int offset, int len)
+{
+	struct page *page;
+	u64 pfn;
+	int r;
+
+	/*
+	 * Holds the folio lock until after checking whether it can be faulted
+	 * in, to avoid races with paths that change a folio's mappability.
+	 */
+	r = kvm_gmem_get_pfn_locked(kvm, slot, gfn, &pfn, &page, NULL);
+	if (r)
+		return r;
+
+	if (!kvm_gmem_is_mappable(kvm, gfn, gfn + 1)) {
+		r = -EPERM;
+		goto unlock;
+	}
+	memcpy(page_address(page) + offset, data, len);
+unlock:
+	unlock_page(page);
+	if (r)
+		put_page(page);
+	else
+		kvm_release_page_dirty(page);
+
+	return r;
+}
+#else
+static int __kvm_read_guest_memfd_page(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn, void *data, int offset,
+				       int len)
+{
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
+
+static int __kvm_write_guest_memfd_page(struct kvm *kvm,
+					struct kvm_memory_slot *slot,
+					gfn_t gfn, const void *data,
+					int offset, int len)
+{
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
 #endif /* CONFIG_KVM_GMEM_MAPPABLE */
 
 /* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */
-static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn,
-				 void *data, int offset, int len)
+
+static int __kvm_read_guest_page(struct kvm *kvm, struct kvm_memory_slot *slot,
+				 gfn_t gfn, void *data, int offset, int len)
 {
-	int r;
 	unsigned long addr;
 
 	if (WARN_ON_ONCE(offset + len > PAGE_SIZE))
 		return -EFAULT;
 
+	if (IS_ENABLED(CONFIG_KVM_GMEM_MAPPABLE) &&
+	    kvm_slot_can_be_private(slot) &&
+	    !slot->userspace_addr) {
+		return __kvm_read_guest_memfd_page(kvm, slot, gfn, data,
+						   offset, len);
+	}
+
 	addr = gfn_to_hva_memslot_prot(slot, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = __copy_from_user(data, (void __user *)addr + offset, len);
-	if (r)
+	if (__copy_from_user(data, (void __user *)addr + offset, len))
 		return -EFAULT;
 	return 0;
 }
@@ -3210,7 +3297,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 
-	return __kvm_read_guest_page(slot, gfn, data, offset, len);
+	return __kvm_read_guest_page(kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_page);
 
@@ -3219,7 +3306,7 @@ int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data,
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	return __kvm_read_guest_page(slot, gfn, data, offset, len);
+	return __kvm_read_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page);
 
@@ -3296,22 +3383,30 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
 
 /* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */
 static int __kvm_write_guest_page(struct kvm *kvm,
-				  struct kvm_memory_slot *memslot, gfn_t gfn,
-			          const void *data, int offset, int len)
+				  struct kvm_memory_slot *slot, gfn_t gfn,
+				  const void *data, int offset, int len)
 {
-	int r;
-	unsigned long addr;
-
 	if (WARN_ON_ONCE(offset + len > PAGE_SIZE))
 		return -EFAULT;
 
-	addr = gfn_to_hva_memslot(memslot, gfn);
-	if (kvm_is_error_hva(addr))
-		return -EFAULT;
-	r = __copy_to_user((void __user *)addr + offset, data, len);
-	if (r)
-		return -EFAULT;
-	mark_page_dirty_in_slot(kvm, memslot, gfn);
+	if (IS_ENABLED(CONFIG_KVM_GMEM_MAPPABLE) &&
+	    kvm_slot_can_be_private(slot) &&
+	    !slot->userspace_addr) {
+		int r = __kvm_write_guest_memfd_page(kvm, slot, gfn, data,
+						     offset, len);
+
+		if (r)
+			return r;
+	} else {
+		unsigned long addr = gfn_to_hva_memslot(slot, gfn);
+
+		if (kvm_is_error_hva(addr))
+			return -EFAULT;
+		if (__copy_to_user((void __user *)addr + offset, data, len))
+			return -EFAULT;
+	}
+
+	mark_page_dirty_in_slot(kvm, slot, gfn);
 	return 0;
 }
 
-- 
2.47.1.613.gc27f4b7a9f-goog