Merge branch 'Dynptr Verifier Adjustments'

Daniel Rosenberg says:

====================
These patches relax a few verifier requirements around dynptrs.
Patches 1-3 are unchanged from v2, apart from rebasing
Patch 4 is the same as in v1, see
https://lore.kernel.org/bpf/CA+PiJmST4WUH061KaxJ4kRL=fqy3X6+Wgb2E2rrLT5OYjUzxfQ@mail.gmail.com/
Patch 5 adds a test for the change in Patch 4
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Documentation/bpf/kfuncs.rst

@@ -100,7 +100,7 @@ Hence, whenever a constant scalar argument is accepted by a kfunc which is not a
 size parameter, and the value of the constant matters for program safety, __k
 suffix should be used.
 
-2.2.2 __uninit Annotation
+2.2.3 __uninit Annotation
 -------------------------
 
 This annotation is used to indicate that the argument will be treated as
@@ -117,6 +117,27 @@ Here, the dynptr will be treated as an uninitialized dynptr. Without this
 annotation, the verifier will reject the program if the dynptr passed in is
 not initialized.
 
+2.2.4 __opt Annotation
+-------------------------
+
+This annotation is used to indicate that the buffer associated with an __sz or __szk
+argument may be null. If the function is passed a nullptr in place of the buffer,
+the verifier will not check that length is appropriate for the buffer. The kfunc is
+responsible for checking if this buffer is null before using it.
+
+An example is given below::
+
+        __bpf_kfunc void *bpf_dynptr_slice(..., void *buffer__opt, u32 buffer__szk)
+        {
+        ...
+        }
+
+Here, the buffer may be null. If buffer is not null, it at least of size buffer_szk.
+Either way, the returned buffer is either NULL, or of size buffer_szk. Without this
+annotation, the verifier will reject the program if a null pointer is passed in with
+a nonzero size.
+
+
 .. _BPF_kfunc_nodef:
 
 2.3 Using an existing kernel function

include/linux/skbuff.h

@@ -4033,7 +4033,7 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len,
 	if (likely(hlen - offset >= len))
 		return (void *)data + offset;
 
-	if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0))
+	if (!skb || !buffer || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0))
 		return NULL;
 
 	return buffer;

kernel/bpf/helpers.c

@@ -2190,13 +2190,15 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
  * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data.
  * @ptr: The dynptr whose data slice to retrieve
  * @offset: Offset into the dynptr
- * @buffer: User-provided buffer to copy contents into
- * @buffer__szk: Size (in bytes) of the buffer. This is the length of the
- *		 requested slice. This must be a constant.
+ * @buffer__opt: User-provided buffer to copy contents into.  May be NULL
+ * @buffer__szk: Size (in bytes) of the buffer if present. This is the
+ *               length of the requested slice. This must be a constant.
  *
  * For non-skb and non-xdp type dynptrs, there is no difference between
  * bpf_dynptr_slice and bpf_dynptr_data.
  *
+ *  If buffer__opt is NULL, the call will fail if buffer_opt was needed.
+ *
  * If the intention is to write to the data slice, please use
  * bpf_dynptr_slice_rdwr.
  *
@@ -2213,7 +2215,7 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
  * direct pointer)
  */
 __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset,
-				   void *buffer, u32 buffer__szk)
+				   void *buffer__opt, u32 buffer__szk)
 {
 	enum bpf_dynptr_type type;
 	u32 len = buffer__szk;
@@ -2233,15 +2235,17 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
 	case BPF_DYNPTR_TYPE_RINGBUF:
 		return ptr->data + ptr->offset + offset;
 	case BPF_DYNPTR_TYPE_SKB:
-		return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer);
+		return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt);
 	case BPF_DYNPTR_TYPE_XDP:
 	{
 		void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len);
 		if (xdp_ptr)
 			return xdp_ptr;
 
-		bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer, len, false);
-		return buffer;
+		if (!buffer__opt)
+			return NULL;
+		bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false);
+		return buffer__opt;
 	}
 	default:
 		WARN_ONCE(true, "unknown dynptr type %d\n", type);
@@ -2253,13 +2257,15 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
  * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data.
  * @ptr: The dynptr whose data slice to retrieve
  * @offset: Offset into the dynptr
- * @buffer: User-provided buffer to copy contents into
- * @buffer__szk: Size (in bytes) of the buffer. This is the length of the
- *		 requested slice. This must be a constant.
+ * @buffer__opt: User-provided buffer to copy contents into. May be NULL
+ * @buffer__szk: Size (in bytes) of the buffer if present. This is the
+ *               length of the requested slice. This must be a constant.
  *
  * For non-skb and non-xdp type dynptrs, there is no difference between
  * bpf_dynptr_slice and bpf_dynptr_data.
  *
+ * If buffer__opt is NULL, the call will fail if buffer_opt was needed.
+ *
  * The returned pointer is writable and may point to either directly the dynptr
  * data at the requested offset or to the buffer if unable to obtain a direct
  * data pointer to (example: the requested slice is to the paged area of an skb
@@ -2290,7 +2296,7 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset
  * direct pointer)
  */
 __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset,
-					void *buffer, u32 buffer__szk)
+					void *buffer__opt, u32 buffer__szk)
 {
 	if (!ptr->data || __bpf_dynptr_is_rdonly(ptr))
 		return NULL;
@@ -2317,7 +2323,7 @@ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 o
 	 * will be copied out into the buffer and the user will need to call
 	 * bpf_dynptr_write() to commit changes.
 	 */
-	return bpf_dynptr_slice(ptr, offset, buffer, buffer__szk);
+	return bpf_dynptr_slice(ptr, offset, buffer__opt, buffer__szk);
 }
 
 __bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 end)

kernel/bpf/verifier.c

@@ -7495,12 +7495,16 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
 	 * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
 	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
 	 *
+	 * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type.
+	 *
 	 * Therefore we fold these flags depending on the arg_type before comparison.
 	 */
 	if (arg_type & MEM_RDONLY)
 		type &= ~MEM_RDONLY;
 	if (arg_type & PTR_MAYBE_NULL)
 		type &= ~PTR_MAYBE_NULL;
+	if (base_type(arg_type) == ARG_PTR_TO_MEM)
+		type &= ~DYNPTR_TYPE_FLAG_MASK;
 
 	if (meta->func_id == BPF_FUNC_kptr_xchg && type & MEM_ALLOC)
 		type &= ~MEM_ALLOC;
@@ -9743,6 +9747,11 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf,
 	return __kfunc_param_match_suffix(btf, arg, "__szk");
 }
 
+static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg)
+{
+	return __kfunc_param_match_suffix(btf, arg, "__opt");
+}
+
 static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg)
 {
 	return __kfunc_param_match_suffix(btf, arg, "__k");
@@ -10830,13 +10839,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			break;
 		case KF_ARG_PTR_TO_MEM_SIZE:
 		{
+			struct bpf_reg_state *buff_reg = &regs[regno];
+			const struct btf_param *buff_arg = &args[i];
 			struct bpf_reg_state *size_reg = &regs[regno + 1];
 			const struct btf_param *size_arg = &args[i + 1];
 
-			ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
-			if (ret < 0) {
-				verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
-				return ret;
+			if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) {
+				ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
+				if (ret < 0) {
+					verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
+					return ret;
+				}
 			}
 
 			if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) {

tools/testing/selftests/bpf/prog_tests/dynptr.c

@@ -26,6 +26,8 @@ static struct {
 	{"test_dynptr_is_null", SETUP_SYSCALL_SLEEP},
 	{"test_dynptr_is_rdonly", SETUP_SKB_PROG},
 	{"test_dynptr_clone", SETUP_SKB_PROG},
+	{"test_dynptr_skb_no_buff", SETUP_SKB_PROG},
+	{"test_dynptr_skb_strcmp", SETUP_SKB_PROG},
 };
 
 static void verify_success(const char *prog_name, enum test_setup_type setup_type)

tools/testing/selftests/bpf/progs/dynptr_fail.c

@@ -1665,3 +1665,23 @@ int clone_xdp_packet_data(struct xdp_md *xdp)
 
 	return 0;
 }
+
+/* Buffers that are provided must be sufficiently long */
+SEC("?cgroup_skb/egress")
+__failure __msg("memory, len pair leads to invalid memory access")
+int test_dynptr_skb_small_buff(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	char buffer[8] = {};
+	__u64 *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This may return NULL. SKB may require a buffer */
+	data = bpf_dynptr_slice(&ptr, 0, buffer, 9);
+
+	return !!data;
+}

tools/testing/selftests/bpf/progs/dynptr_success.c

@@ -505,3 +505,41 @@ int test_dynptr_clone(struct __sk_buff *skb)
 
 	return 0;
 }
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_skb_no_buff(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	__u64 *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This may return NULL. SKB may require a buffer */
+	data = bpf_dynptr_slice(&ptr, 0, NULL, 1);
+
+	return !!data;
+}
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_skb_strcmp(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	char *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This may return NULL. SKB may require a buffer */
+	data = bpf_dynptr_slice(&ptr, 0, NULL, 10);
+	if (data) {
+		bpf_strncmp(data, 10, "foo");
+		return 1;
+	}
+
+	return 1;
+}