bpf: Add KF_PERFMON kfunc flag

Tracing related BPF helpers e.g. under bpf_base_func_proto() are gated
behind CAP_PERFMON. However, the same is currently not true for kfuncs
and they are accessible via plain CAP_BPF. Add a new KF_PERFMON flag
which can be used such that check_kfunc_call() ensures env->allow_ptr_leaks
is permitted. This follows similar pattern to existing KF_DESTRUCTIVE flag.

The rejection returns -EPERM to match the other CAP_PERFMON gates in the
verifier, that is, check_ptr_to_btf_access() and check_ptr_to_map_access(),
which report the very same policy to user space.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20260910213510.49358-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 25 insertions, 0 deletions

diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst
index 85f73e0bbd0f..6691fe8a32c3 100644
--- a/Documentation/bpf/kfuncs.rst
+++ b/Documentation/bpf/kfuncs.rst
@@ -486,6 +486,16 @@ Example usage in BPF program:
 	/* note that the last argument is omitted */
         bpf_task_work_schedule_signal(task, &work->tw, &arrmap, task_work_callback);
 
+2.5.10 KF_PERFMON flag
+----------------------
+
+The KF_PERFMON flag is used for kfuncs that can expose kernel memory or kernel
+addresses to the BPF program, for example by reading through a pointer that the
+verifier does not check. Calling such a kfunc requires CAP_PERFMON, or
+CAP_SYS_ADMIN, in the same way that the equivalent BPF helpers are gated in
+bpf_base_func_proto(). A program loaded with CAP_BPF alone is rejected at load
+time.
+
 2.6 Registering the kfuncs
 --------------------------
 
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 89d5a5c4f117..7c62ea17b116 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -80,6 +80,7 @@
 #define KF_ARENA_ARG2   (1 << 15) /* kfunc takes an arena pointer as its second argument */
 #define KF_IMPLICIT_ARGS (1 << 16) /* kfunc has implicit arguments supplied by the verifier */
 #define KF_SPINLOCK_SAFE (1 << 17) /* kfunc is allowed inside bpf_spin_lock-ed region */
+#define KF_PERFMON      (1 << 18) /* kfunc requires CAP_PERFMON */
 
 /*
  * Tag marking a kernel function as a kfunc. This is meant to minimize the
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 72a3f5998dd2..939e535a3442 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11356,6 +11356,11 @@ static bool is_kfunc_destructive(struct bpf_call_arg_meta *meta)
 	return meta->kfunc_flags & KF_DESTRUCTIVE;
 }
 
+static bool is_kfunc_perfmon(struct bpf_call_arg_meta *meta)
+{
+	return meta->kfunc_flags & KF_PERFMON;
+}
+
 static bool is_kfunc_rcu(struct bpf_call_arg_meta *meta)
 {
 	return meta->kfunc_flags & KF_RCU;
@@ -13834,6 +13839,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		return -EACCES;
 	}
 
+	if (is_kfunc_perfmon(&meta) && !env->allow_ptr_leaks) {
+		verbose(env, "%s is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
+			func_name);
+		operation = bpf_diag_fmt(env, "kfunc %s", func_name);
+		bpf_diag_policy(env, insn_idx, operation, "the kfunc requires CAP_PERFMON",
+				"Load the program with CAP_PERFMON, or avoid the kfunc.");
+		return -EPERM;
+	}
+
 	sleepable = bpf_is_kfunc_sleepable(&meta);
 	if (sleepable && !in_sleepable(env)) {
 		verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name);