Hello, Alexei.
在 2023/9/6 04:09, Alexei Starovoitov 写道:
On Sun, Aug 27, 2023 at 12:21 AM Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx> wrote:
This patch adds kfuncs bpf_iter_process_{new,next,destroy} which allow
creation and manipulation of struct bpf_iter_process in open-coded iterator
style. BPF programs can use these kfuncs or through bpf_for_each macro to
iterate all processes in the system.
Signed-off-by: Chuyi Zhou <zhouchuyi@xxxxxxxxxxxxx>
---
include/uapi/linux/bpf.h | 4 ++++
kernel/bpf/helpers.c | 3 +++
kernel/bpf/task_iter.c | 31 +++++++++++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 4 ++++
tools/lib/bpf/bpf_helpers.h | 5 +++++
5 files changed, 47 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2a6e9b99564b..cfbd527e3733 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7199,4 +7199,8 @@ struct bpf_iter_css_task {
__u64 __opaque[1];
} __attribute__((aligned(8)));
+struct bpf_iter_process {
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index cf113ad24837..81a2005edc26 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -2458,6 +2458,9 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW)
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_iter_process_new, KF_ITER_NEW)
+BTF_ID_FLAGS(func, bpf_iter_process_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_process_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 b1bdba40b684..a6717a76c1e0 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -862,6 +862,37 @@ __bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
kfree(kit->css_it);
}
+struct bpf_iter_process_kern {
+ struct task_struct *tsk;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc int bpf_iter_process_new(struct bpf_iter_process *it)
+{
+ struct bpf_iter_process_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_process_kern) != sizeof(struct bpf_iter_process));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_process_kern) !=
+ __alignof__(struct bpf_iter_process));
+
+ rcu_read_lock();
+ kit->tsk = &init_task;
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_process_next(struct bpf_iter_process *it)
+{
+ struct bpf_iter_process_kern *kit = (void *)it;
+
+ kit->tsk = next_task(kit->tsk);
+
+ return kit->tsk == &init_task ? NULL : kit->tsk;
+}
+
+__bpf_kfunc void bpf_iter_process_destroy(struct bpf_iter_process *it)
+{
+ rcu_read_unlock();
+}
This iter can be used in all ctx-s which is nice, but let's
make the verifier enforce rcu_read_lock/unlock done by bpf prog
instead of doing in the ctor/dtor of iter, since
in sleepable progs the verifier won't recognize that body is RCU CS.
We'd need to teach the verifier to allow bpf_iter_process_new()
inside in_rcu_cs() and make sure there is no rcu_read_unlock
while BPF_ITER_STATE_ACTIVE.
bpf_iter_process_destroy() would become a nop.
Thanks for your review!
I think bpf_iter_process_{new, next, destroy} should be protected by
bpf_rcu_read_lock/unlock explicitly whether the prog is sleepable or
not, right? I'm not very familiar with the BPF verifier, but I believe
there is still a risk in directly calling these kfuns even if
in_rcu_cs() is true.
Maby what we actually need here is to enforce BPF verifier to check
env->cur_state->active_rcu_lock is true when we want to call these kfuncs.
Thanks.
