bpf: Add bpf_loop helper

This patch adds the kernel-side and API changes for a new helper
function, bpf_loop:

long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx,
u64 flags);

where long (*callback_fn)(u32 index, void *ctx);

bpf_loop invokes the "callback_fn" **nr_loops** times or until the
callback_fn returns 1. The callback_fn can only return 0 or 1, and
this is enforced by the verifier. The callback_fn index is zero-indexed.

A few things to please note:
~ The "u64 flags" parameter is currently unused but is included in
case a future use case for it arises.
~ In the kernel-side implementation of bpf_loop (kernel/bpf/bpf_iter.c),
bpf_callback_t is used as the callback function cast.
~ A program can have nested bpf_loop calls but the program must
still adhere to the verifier constraint of its stack depth (the stack depth
cannot exceed MAX_BPF_STACK))
~ Recursive callback_fns do not pass the verifier, due to the call stack
for these being too deep.
~ The next patch will include the tests and benchmark

Signed-off-by: Joanne Koong <[e-mail]>
Signed-off-by: Alexei Starovoitov <[e-mail]>
Acked-by: Andrii Nakryiko <[e-mail]>
Link: https://lore.kernel.org/bpf/[e-mail]

include/linux/bpf.h

···
 extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
 extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto;
 extern const struct bpf_func_proto bpf_find_vma_proto;
+extern const struct bpf_func_proto bpf_loop_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);

include/uapi/linux/bpf.h

···
  *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
  *		**-EBUSY** if failed to try lock mmap_lock.
  *		**-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		For **nr_loops**, call **callback_fn** function
+ *		with **callback_ctx** as the context parameter.
+ *		The **callback_fn** should be a static function and
+ *		the **callback_ctx** should be a pointer to the stack.
+ *		The **flags** is used to control certain aspects of the helper.
+ *		Currently, the **flags** must be 0. Currently, nr_loops is
+ *		limited to 1 << 23 (~8 million) loops.
+ *
+ *		long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ *		where **index** is the current index in the loop. The index
+ *		is zero-indexed.
+ *
+ *		If **callback_fn** returns 0, the helper will continue to the next
+ *		loop. If return value is 1, the helper will skip the rest of
+ *		the loops and return. Other return values are not used now,
+ *		and will be rejected by the verifier.
+ *
+ *	Return
+ *		The number of loops performed, **-EINVAL** for invalid **flags**,
+ *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
···
 	FN(skc_to_unix_sock),		\
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
+	FN(loop),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

kernel/bpf/bpf_iter.c

···
 	.arg3_type	= ARG_PTR_TO_STACK_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
 };
+
+/* maximum number of loops */
+#define MAX_LOOPS	BIT(23)
+
+BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx,
+	   u64, flags)
+{
+	bpf_callback_t callback = (bpf_callback_t)callback_fn;
+	u64 ret;
+	u32 i;
+
+	if (flags)
+		return -EINVAL;
+	if (nr_loops > MAX_LOOPS)
+		return -E2BIG;
+
+	for (i = 0; i < nr_loops; i++) {
+		ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0);
+		/* return value: 0 - continue, 1 - stop and return */
+		if (ret)
+			return i + 1;
+	}
+
+	return i;
+}
+
+const struct bpf_func_proto bpf_loop_proto = {
+	.func		= bpf_loop,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type	= ARG_PTR_TO_FUNC,
+	.arg3_type	= ARG_PTR_TO_STACK_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+};

kernel/bpf/helpers.c

···
 		return &bpf_ringbuf_query_proto;
 	case BPF_FUNC_for_each_map_elem:
 		return &bpf_for_each_map_elem_proto;
+	case BPF_FUNC_loop:
+		return &bpf_loop_proto;
 	default:
 		break;
 	}

kernel/bpf/verifier.c

···
 	return 0;
 }
 
+static int set_loop_callback_state(struct bpf_verifier_env *env,
+				   struct bpf_func_state *caller,
+				   struct bpf_func_state *callee,
+				   int insn_idx)
+{
+	/* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx,
+	 *	    u64 flags);
+	 * callback_fn(u32 index, void *callback_ctx);
+	 */
+	callee->regs[BPF_REG_1].type = SCALAR_VALUE;
+	callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3];
+
+	/* unused */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_3]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
+
+	callee->in_callback_fn = true;
+	return 0;
+}
+
 static int set_timer_callback_state(struct bpf_verifier_env *env,
 				    struct bpf_func_state *caller,
 				    struct bpf_func_state *callee,
···
 			return err;
 	}
 
-	if (func_id == BPF_FUNC_tail_call) {
-		err = check_reference_leak(env);
-		if (err) {
-			verbose(env, "tail_call would lead to reference leak\n");
-			return err;
-		}
-	} else if (is_release_function(func_id)) {
+	if (is_release_function(func_id)) {
 		err = release_reference(env, meta.ref_obj_id);
 		if (err) {
 			verbose(env, "func %s#%d reference has not been acquired before\n",
···
 
 	regs = cur_regs(env);
 
-	/* check that flags argument in get_local_storage(map, flags) is 0,
-	 * this is required because get_local_storage() can't return an error.
-	 */
-	if (func_id == BPF_FUNC_get_local_storage &&
-	    !register_is_null(&regs[BPF_REG_2])) {
-		verbose(env, "get_local_storage() doesn't support non-zero flags\n");
-		return -EINVAL;
-	}
-
-	if (func_id == BPF_FUNC_for_each_map_elem) {
+	switch (func_id) {
+	case BPF_FUNC_tail_call:
+		err = check_reference_leak(env);
+		if (err) {
+			verbose(env, "tail_call would lead to reference leak\n");
+			return err;
+		}
+		break;
+	case BPF_FUNC_get_local_storage:
+		/* check that flags argument in get_local_storage(map, flags) is 0,
+		 * this is required because get_local_storage() can't return an error.
+		 */
+		if (!register_is_null(&regs[BPF_REG_2])) {
+			verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+			return -EINVAL;
+		}
+		break;
+	case BPF_FUNC_for_each_map_elem:
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_map_elem_callback_state);
-		if (err < 0)
-			return -EINVAL;
-	}
-
-	if (func_id == BPF_FUNC_timer_set_callback) {
+		break;
+	case BPF_FUNC_timer_set_callback:
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_timer_callback_state);
-		if (err < 0)
-			return -EINVAL;
-	}
-
-	if (func_id == BPF_FUNC_find_vma) {
+		break;
+	case BPF_FUNC_find_vma:
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_find_vma_callback_state);
-		if (err < 0)
-			return -EINVAL;
+		break;
+	case BPF_FUNC_snprintf:
+		err = check_bpf_snprintf_call(env, regs);
+		break;
+	case BPF_FUNC_loop:
+		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
+					set_loop_callback_state);
+		break;
 	}
 
-	if (func_id == BPF_FUNC_snprintf) {
-		err = check_bpf_snprintf_call(env, regs);
-		if (err < 0)
-			return err;
-	}
+	if (err)
+		return err;
 
 	/* reset caller saved regs */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {

tools/include/uapi/linux/bpf.h

···
  *		**-ENOENT** if *task->mm* is NULL, or no vma contains *addr*.
  *		**-EBUSY** if failed to try lock mmap_lock.
  *		**-EINVAL** for invalid **flags**.
+ *
+ * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags)
+ *	Description
+ *		For **nr_loops**, call **callback_fn** function
+ *		with **callback_ctx** as the context parameter.
+ *		The **callback_fn** should be a static function and
+ *		the **callback_ctx** should be a pointer to the stack.
+ *		The **flags** is used to control certain aspects of the helper.
+ *		Currently, the **flags** must be 0. Currently, nr_loops is
+ *		limited to 1 << 23 (~8 million) loops.
+ *
+ *		long (\*callback_fn)(u32 index, void \*ctx);
+ *
+ *		where **index** is the current index in the loop. The index
+ *		is zero-indexed.
+ *
+ *		If **callback_fn** returns 0, the helper will continue to the next
+ *		loop. If return value is 1, the helper will skip the rest of
+ *		the loops and return. Other return values are not used now,
+ *		and will be rejected by the verifier.
+ *
+ *	Return
+ *		The number of loops performed, **-EINVAL** for invalid **flags**,
+ *		**-E2BIG** if **nr_loops** exceeds the maximum number of loops.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
···
 	FN(skc_to_unix_sock),		\
 	FN(kallsyms_lookup_name),	\
 	FN(find_vma),			\
+	FN(loop),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper