sched_ext: Deny SCX kfuncs to non-SCX struct_ops programs

scx_kfunc_context_filter() currently allows non-SCX struct_ops programs (e.g. tcp_congestion_ops) to call SCX unlocked kfuncs. This is wrong for two reasons: - It is semantically incorrect: a TCP congestion control program has no business calling SCX kfuncs such as scx_bpf_kick_cpu(). - With CONFIG_EXT_SUB_SCHED=y, kfuncs like scx_bpf_kick_cpu() call scx_prog_sched(aux), which invokes bpf_prog_get_assoc_struct_ops(aux) and casts the result to struct sched_ext_ops * before reading ops->priv. For a non-SCX struct_ops program the returned pointer is the kdata of that struct_ops type, which is far smaller than sched_ext_ops, making the read an out-of-bounds access (confirmed with KASAN). Extend the filter to cover scx_kfunc_set_any and scx_kfunc_set_idle as well, and deny all SCX kfuncs for any struct_ops program that is not the SCX struct_ops. This addresses both issues: the semantic contract is enforced at the verifier level, and the runtime out-of-bounds access becomes unreachable.

Cheng-Yang Chou committed 6 months ago

Commit 2d2b0261 parent 87019cb3 files · +20 −14Browse files

Showing the changes to kernel (3 of 3 files). Show all

Unified · Split

3 files

kernel/sched/ext.c +18 −14
kernel/sched/ext_idle.c +1 −0
kernel/sched/ext_idle.h +1 −0

kernel/sched/ext.c+18−14

 static const struct btf_kfunc_id_set scx_kfunc_set_any = {
 	.owner			= THIS_MODULE,
 	.set			= &scx_kfunc_ids_any,
+	.filter			= scx_kfunc_context_filter,
 };
 /*
 };
 /*
- * Verifier-time filter for context-sensitive SCX kfuncs. Registered via the
+ * Verifier-time filter for SCX kfuncs. Registered via the .filter field on
- * .filter field on each per-group btf_kfunc_id_set. The BPF core invokes this
+ * each per-group btf_kfunc_id_set. The BPF core invokes this for every kfunc
- * for every kfunc call in the registered hook (BPF_PROG_TYPE_STRUCT_OPS or
+ * call in the registered hook (BPF_PROG_TYPE_STRUCT_OPS or
  * BPF_PROG_TYPE_SYSCALL), regardless of which set originally introduced the
- * kfunc - so the filter must short-circuit on kfuncs it doesn't govern (e.g.
+ * kfunc - so the filter must short-circuit on kfuncs it doesn't govern by
- * scx_kfunc_ids_any) by falling through to "allow" when none of the
+ * falling through to "allow" when none of the SCX sets contain the kfunc.
- * context-sensitive sets contain the kfunc.
  */
 int scx_kfunc_context_filter(const struct bpf_prog *prog, u32 kfunc_id)
 {
 	bool in_enqueue = btf_id_set8_contains(&scx_kfunc_ids_enqueue_dispatch, kfunc_id);
 	bool in_dispatch = btf_id_set8_contains(&scx_kfunc_ids_dispatch, kfunc_id);
 	bool in_cpu_release = btf_id_set8_contains(&scx_kfunc_ids_cpu_release, kfunc_id);
+	bool in_idle = btf_id_set8_contains(&scx_kfunc_ids_idle, kfunc_id);
+	bool in_any = btf_id_set8_contains(&scx_kfunc_ids_any, kfunc_id);
 	u32 moff, flags;
-	/* Not a context-sensitive kfunc (e.g. from scx_kfunc_ids_any) - allow. */
+	/* Not an SCX kfunc - allow. */
-	if (!(in_unlocked || in_select_cpu || in_enqueue || in_dispatch || in_cpu_release))
+	if (!(in_unlocked || in_select_cpu || in_enqueue || in_dispatch ||
+	      in_cpu_release || in_idle || in_any))
 		return 0;
 	/* SYSCALL progs (e.g. BPF test_run()) may call unlocked and select_cpu kfuncs. */
 	if (prog->type == BPF_PROG_TYPE_SYSCALL)
-		return (in_unlocked || in_select_cpu) ? 0 : -EACCES;
+		return (in_unlocked || in_select_cpu || in_idle || in_any) ? 0 : -EACCES;
 	if (prog->type != BPF_PROG_TYPE_STRUCT_OPS)
-		return -EACCES;
+		return (in_any || in_idle) ? 0 : -EACCES;
 	/*
 	 * add_subprog_and_kfunc() collects all kfunc calls, including dead code
 		return 0;
 	/*
-	 * Non-SCX struct_ops: only unlocked kfuncs are safe. The other
+	 * Non-SCX struct_ops: SCX kfuncs are not permitted.
-	 * context-sensitive kfuncs assume the rq lock is held by the SCX
-	 * dispatch path, which doesn't apply to other struct_ops users.
 	 */
 	if (prog->aux->st_ops != &bpf_sched_ext_ops)
-		return in_unlocked ? 0 : -EACCES;
+		return -EACCES;
 	/* SCX struct_ops: check the per-op allow list. */
+	if (in_any || in_idle)
+		return 0;
 	moff = prog->aux->attach_st_ops_member_off;
 	flags = scx_kf_allow_flags[SCX_MOFF_IDX(moff)];

kernel/sched/ext_idle.c+1−0

@@ -1467,6 +1467,7 @@ BTF_KFUNCS_END(scx_kfunc_ids_idle) · 1466 unmodified lines
1467	static const struct btf_kfunc_id_set scx_kfunc_set_idle = {	1467	static const struct btf_kfunc_id_set scx_kfunc_set_idle = {
1468	.owner = THIS_MODULE,	1468	.owner = THIS_MODULE,
1469	.set = &scx_kfunc_ids_idle,	1469	.set = &scx_kfunc_ids_idle,
		1470	.filter = scx_kfunc_context_filter,
1470	};	1471	};
1471		1472
1472	/*	1473	/*

kernel/sched/ext_idle.h+1−0

@@ -12,6 +12,7 @@ · 11 unmodified lines
12		12
13	struct sched_ext_ops;	13	struct sched_ext_ops;
14		14
		15	extern struct btf_id_set8 scx_kfunc_ids_idle;
15	extern struct btf_id_set8 scx_kfunc_ids_select_cpu;	16	extern struct btf_id_set8 scx_kfunc_ids_select_cpu;
16		17
17	void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops);	18	void scx_idle_update_selcpu_topology(struct sched_ext_ops *ops);