bpf: Introduce css_task open-coded iterator kfuncs

This patch adds kfuncs bpf_iter_css_task_{new,next,destroy} which allow
creation and manipulation of struct bpf_iter_css_task in open-coded
iterator style. These kfuncs actually wrapps css_task_iter_{start,next,
end}. BPF programs can use these kfuncs through bpf_for_each macro for
iteration of all tasks under a css.

css_task_iter_*() would try to get the global spin-lock *css_set_lock*, so
the bpf side has to be careful in where it allows to use this iter.
Currently we only allow it in bpf_lsm and bpf iter-s.

Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20231018061746.111364-3-zhouchuyi@bytedance.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/helpers.c

@@ -2560,6 +2560,9 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
 BTF_ID_FLAGS(func, bpf_dynptr_adjust)
 BTF_ID_FLAGS(func, bpf_dynptr_is_null)
 BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)

kernel/bpf/task_iter.c

@@ -894,6 +894,64 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
 
 __diag_pop();
 
+struct bpf_iter_css_task {
+	__u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_task_kern {
+	struct css_task_iter *css_it;
+} __attribute__((aligned(8)));
+
+__diag_push();
+__diag_ignore_all("-Wmissing-prototypes",
+		  "Global functions as their definitions will be in vmlinux BTF");
+
+__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+		struct cgroup_subsys_state *css, unsigned int flags)
+{
+	struct bpf_iter_css_task_kern *kit = (void *)it;
+
+	BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task));
+	BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) !=
+					__alignof__(struct bpf_iter_css_task));
+	kit->css_it = NULL;
+	switch (flags) {
+	case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED:
+	case CSS_TASK_ITER_PROCS:
+	case 0:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter));
+	if (!kit->css_it)
+		return -ENOMEM;
+	css_task_iter_start(css, flags, kit->css_it);
+	return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it)
+{
+	struct bpf_iter_css_task_kern *kit = (void *)it;
+
+	if (!kit->css_it)
+		return NULL;
+	return css_task_iter_next(kit->css_it);
+}
+
+__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
+{
+	struct bpf_iter_css_task_kern *kit = (void *)it;
+
+	if (!kit->css_it)
+		return;
+	css_task_iter_end(kit->css_it);
+	bpf_mem_free(&bpf_global_ma, kit->css_it);
+}
+
+__diag_pop();
+
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 
 static void do_mmap_read_unlock(struct irq_work *entry)

kernel/bpf/verifier.c

@@ -10472,6 +10472,7 @@ enum special_kfunc_type {
 	KF_bpf_percpu_obj_new_impl,
 	KF_bpf_percpu_obj_drop_impl,
 	KF_bpf_throw,
+	KF_bpf_iter_css_task_new,
 };
 
 BTF_SET_START(special_kfunc_set)
@@ -10495,6 +10496,7 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+BTF_ID(func, bpf_iter_css_task_new)
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -10520,6 +10522,7 @@ BTF_ID(func, bpf_dynptr_clone)
 BTF_ID(func, bpf_percpu_obj_new_impl)
 BTF_ID(func, bpf_percpu_obj_drop_impl)
 BTF_ID(func, bpf_throw)
+BTF_ID(func, bpf_iter_css_task_new)
 
 static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -11050,6 +11053,20 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
 						  &meta->arg_rbtree_root.field);
 }
 
+static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
+{
+	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+
+	switch (prog_type) {
+	case BPF_PROG_TYPE_LSM:
+		return true;
+	case BPF_TRACE_ITER:
+		return env->prog->aux->sleepable;
+	default:
+		return false;
+	}
+}
+
 static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta,
 			    int insn_idx)
 {
@@ -11300,6 +11317,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			break;
 		}
 		case KF_ARG_PTR_TO_ITER:
+			if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
+				if (!check_css_task_iter_allowlist(env)) {
+					verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n");
+					return -EINVAL;
+				}
+			}
 			ret = process_iter_arg(env, regno, insn_idx, meta);
 			if (ret < 0)
 				return ret;

tools/testing/selftests/bpf/bpf_experimental.h

@@ -458,4 +458,12 @@ extern void bpf_throw(u64 cookie) __ksym;
 		__bpf_assert_op(LHS, <=, END, value, false);		\
 	})
 
+struct bpf_iter_css_task;
+struct cgroup_subsys_state;
+extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+		struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym;
+extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym;
+extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym;
+
+
 #endif