On 11/14/22 10:50 PM, Martin KaFai Lau wrote:
On 11/11/22 8:58 AM, Yonghong Song wrote:
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
new file mode 100644
index 000000000000..c11b4f8f9a9d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -0,0 +1,355 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_CGRP_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, long);
+} map_a SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, long);
+} map_b SEC(".maps");
+
+__u32 user_data, key_serial, target_pid = 0;
+__u64 flags, result = 0;
+
+struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+void bpf_key_put(struct bpf_key *key) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int cgrp_succ(void *ctx)
+{
+ struct task_struct *task;
+ struct css_set *cgroups;
+ struct cgroup *dfl_cgrp;
+ long init_val = 2;
+ long *ptr;
+
+ task = bpf_get_current_task_btf();
+ if (task->pid != target_pid)
+ return 0;
+
+ bpf_rcu_read_lock();
+ cgroups = task->cgroups;
+ dfl_cgrp = cgroups->dfl_cgrp;
+ bpf_rcu_read_unlock();
Outside of the rcu section, "cgroups" could have been gone. Is it
possible that "dfl_cgrp" could be gone together with "cgroups"?
In this particular case, looks like the best is indeed
to get a reference for dfl_cgrp before doing bpf_rcu_read_unlock.
But to decide whether a particular non-rcu pointer needs
reference or not needs kernel internal knowledge for
that particular context.
So right now, the approach is to take the approach
for generic ptr_to_btf_id approach. That is, the
non-rcu pointer after rcu pointer tracing is 'trusted'.
The user can always increase bpf_rcu_read_lock() region
by himself to cover the case if the non-rcu pointer
is untrusted.
+ ptr = bpf_cgrp_storage_get(&map_a, dfl_cgrp, &init_val,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!ptr)
+ return 0;
+ ptr = bpf_cgrp_storage_get(&map_a, dfl_cgrp, 0, 0);
+ if (!ptr)
+ return 0;
+ result = *ptr;
+ return 0;
+}
+
[ ... ]
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int miss_unlock(void *ctx)
+{
+ struct task_struct *task;
+ struct css_set *cgroups;
+ struct cgroup *dfl_cgrp;
+
+ /* missing bpf_rcu_read_unlock() */
+ bpf_rcu_read_lock();
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
One of the bpf_rcu_read_lock() needs to be removed. Otherwise, I think
the verifier will error on the nested rcu read lock first instead of
testing the missing unlock case here.
Thanks, will do.
+ cgroups = task->cgroups;
+ bpf_rcu_read_unlock();
+ dfl_cgrp = cgroups->dfl_cgrp;
+ (void)bpf_cgrp_storage_get(&map_a, dfl_cgrp, 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ return 0;
+}
