Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:2 as permitted sender) client-ip=2620:137:e000::3:2;
From:   Chuyi Zhou <zhouchuyi@bytedance.com>
To:     bpf@vger.kernel.org
Cc:     ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
        martin.lau@kernel.org, tj@kernel.org, linux-kernel@vger.kernel.org,
        Chuyi Zhou <zhouchuyi@bytedance.com>
Subject: [PATCH bpf-next v4 2/8] bpf: Introduce css_task open-coded iterator kfuncs
Date:   Sat,  7 Oct 2023 20:45:16 +0800
Message-Id: <20231007124522.34834-3-zhouchuyi@bytedance.com>
In-Reply-To: <20231007124522.34834-1-zhouchuyi@bytedance.com>
References: <20231007124522.34834-1-zhouchuyi@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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>
---
 kernel/bpf/helpers.c                          |  3 ++
 kernel/bpf/task_iter.c                        | 53 +++++++++++++++++++
 kernel/bpf/verifier.c                         | 23 ++++++++
 .../testing/selftests/bpf/bpf_experimental.h  |  8 +++
 4 files changed, 87 insertions(+)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index dd1c69ee3375..8699cabb52b2 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2549,6 +2549,9 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL)
 BTF_ID_FLAGS(func, bpf_iter_num_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)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 7473068ed313..2cfcb4dd8a37 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/fdtable.h>
 #include <linux/filter.h>
+#include <linux/bpf_mem_alloc.h>
 #include <linux/btf_ids.h>
 #include "mmap_unlock_work.h"
 
@@ -803,6 +804,58 @@ const struct bpf_func_proto bpf_find_vma_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
+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)));
+
+__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);
+}
+
 DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
 
 static void do_mmap_read_unlock(struct irq_work *entry)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index eed7350e15f4..528d375c17ee 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10450,6 +10450,7 @@ 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)
@@ -10473,6 +10474,7 @@ 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)
@@ -10498,6 +10500,7 @@ 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)
 {
@@ -11028,6 +11031,20 @@ 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)
 {
@@ -11278,6 +11295,12 @@ 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;
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 9aa29564bd74..8b53537e0f27 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -450,4 +450,12 @@ 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
-- 
2.20.1