KVM: Introduce KVM_SET_USER_MEMORY_REGION2

Introduce a "version 2" of KVM_SET_USER_MEMORY_REGION so that additional
information can be supplied without setting userspace up to fail.  The
padding in the new kvm_userspace_memory_region2 structure will be used to
pass a file descriptor in addition to the userspace_addr, i.e. allow
userspace to point at a file descriptor and map memory into a guest that
is NOT mapped into host userspace.

Alternatively, KVM could simply add "struct kvm_userspace_memory_region2"
without a new ioctl(), but as Paolo pointed out, adding a new ioctl()
makes detection of bad flags a bit more robust, e.g. if the new fd field
is guarded only by a flag and not a new ioctl(), then a userspace bug
(setting a "bad" flag) would generate out-of-bounds access instead of an
-EINVAL error.

Cc: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com>
Message-Id: <20231027182217.3615211-9-seanjc@google.com>
Acked-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -6192,6 +6192,28 @@ to know what fields can be changed for the system register described by
 ``op0, op1, crn, crm, op2``. KVM rejects ID register values that describe a
 superset of the features supported by the system.
 
+4.140 KVM_SET_USER_MEMORY_REGION2
+---------------------------------
+
+:Capability: KVM_CAP_USER_MEMORY2
+:Architectures: all
+:Type: vm ioctl
+:Parameters: struct kvm_userspace_memory_region2 (in)
+:Returns: 0 on success, -1 on error
+
+::
+
+  struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size; /* bytes */
+	__u64 userspace_addr; /* start of the userspace allocated memory */
+	__u64 pad[16];
+  };
+
+See KVM_SET_USER_MEMORY_REGION.
+
 5. The kvm_run structure
 ========================
 

arch/x86/kvm/x86.c

@@ -12576,7 +12576,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 	}
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		struct kvm_userspace_memory_region m;
+		struct kvm_userspace_memory_region2 m;
 
 		m.slot = id | (i << 16);
 		m.flags = 0;

include/linux/kvm_host.h

@@ -1146,9 +1146,9 @@ enum kvm_mr_change {
 };
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+			  const struct kvm_userspace_memory_region2 *mem);
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+			    const struct kvm_userspace_memory_region2 *mem);
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,

include/uapi/linux/kvm.h

@@ -95,6 +95,16 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
+/* for KVM_SET_USER_MEMORY_REGION2 */
+struct kvm_userspace_memory_region2 {
+	__u32 slot;
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 userspace_addr;
+	__u64 pad[16];
+};
+
 /*
  * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for
  * userspace, other bits are reserved for kvm internal use which are defined
@@ -1201,6 +1211,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
 #define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
 #define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230
+#define KVM_CAP_USER_MEMORY2 231
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1483,6 +1494,8 @@ struct kvm_vfio_spapr_tce {
 					struct kvm_userspace_memory_region)
 #define KVM_SET_TSS_ADDR          _IO(KVMIO,   0x47)
 #define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO,  0x48, __u64)
+#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \
+					 struct kvm_userspace_memory_region2)
 
 /* enable ucontrol for s390 */
 struct kvm_s390_ucas_mapping {

virt/kvm/kvm_main.c

@@ -1580,7 +1580,15 @@ static void kvm_replace_memslot(struct kvm *kvm,
 	}
 }
 
-static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
+/*
+ * Flags that do not access any of the extra space of struct
+ * kvm_userspace_memory_region2.  KVM_SET_USER_MEMORY_REGION_V1_FLAGS
+ * only allows these.
+ */
+#define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \
+	(KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY)
+
+static int check_memory_region_flags(const struct kvm_userspace_memory_region2 *mem)
 {
 	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
 
@@ -1982,7 +1990,7 @@ static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id,
  * Must be called holding kvm->slots_lock for write.
  */
 int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem)
+			    const struct kvm_userspace_memory_region2 *mem)
 {
 	struct kvm_memory_slot *old, *new;
 	struct kvm_memslots *slots;
@@ -2086,7 +2094,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem)
+			  const struct kvm_userspace_memory_region2 *mem)
 {
 	int r;
 
@@ -2098,7 +2106,7 @@ int kvm_set_memory_region(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 
 static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
-					  struct kvm_userspace_memory_region *mem)
+					  struct kvm_userspace_memory_region2 *mem)
 {
 	if ((u16)mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
@@ -4568,6 +4576,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 {
 	switch (arg) {
 	case KVM_CAP_USER_MEMORY:
+	case KVM_CAP_USER_MEMORY2:
 	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
 	case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
 	case KVM_CAP_INTERNAL_ERROR_DATA:
@@ -4823,6 +4832,14 @@ static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
 	return fd;
 }
 
+#define SANITY_CHECK_MEM_REGION_FIELD(field)					\
+do {										\
+	BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) !=		\
+		     offsetof(struct kvm_userspace_memory_region2, field));	\
+	BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) !=		\
+		     sizeof_field(struct kvm_userspace_memory_region2, field));	\
+} while (0)
+
 static long kvm_vm_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4845,15 +4862,39 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap);
 		break;
 	}
+	case KVM_SET_USER_MEMORY_REGION2:
 	case KVM_SET_USER_MEMORY_REGION: {
-		struct kvm_userspace_memory_region kvm_userspace_mem;
+		struct kvm_userspace_memory_region2 mem;
+		unsigned long size;
+
+		if (ioctl == KVM_SET_USER_MEMORY_REGION) {
+			/*
+			 * Fields beyond struct kvm_userspace_memory_region shouldn't be
+			 * accessed, but avoid leaking kernel memory in case of a bug.
+			 */
+			memset(&mem, 0, sizeof(mem));
+			size = sizeof(struct kvm_userspace_memory_region);
+		} else {
+			size = sizeof(struct kvm_userspace_memory_region2);
+		}
+
+		/* Ensure the common parts of the two structs are identical. */
+		SANITY_CHECK_MEM_REGION_FIELD(slot);
+		SANITY_CHECK_MEM_REGION_FIELD(flags);
+		SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr);
+		SANITY_CHECK_MEM_REGION_FIELD(memory_size);
+		SANITY_CHECK_MEM_REGION_FIELD(userspace_addr);
 
 		r = -EFAULT;
-		if (copy_from_user(&kvm_userspace_mem, argp,
-						sizeof(kvm_userspace_mem)))
+		if (copy_from_user(&mem, argp, size))
+			goto out;
+
+		r = -EINVAL;
+		if (ioctl == KVM_SET_USER_MEMORY_REGION &&
+		    (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem);
+		r = kvm_vm_ioctl_set_memory_region(kvm, &mem);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {