[bpf-next,v10,6/7] bpf: Support private stack for struct_ops progs

Commit Message

Yonghong Song Nov. 7, 2024, 2:42 a.m. UTC

For struct_ops progs, whether a particular prog uses private stack
depends on prog->aux->priv_stack_requested setting before actual
insn-level verification for that prog. One particular implementation
is to piggyback on struct_ops->check_member(). The next patch has
an example for this. The struct_ops->check_member() sets
prog->aux->priv_stack_requested to be true which enables private stack
usage.

The struct_ops prog follows the same rule as kprobe/tracing progs after
function bpf_enable_priv_stack(). For example, even a struct_ops prog
requests private stack, it could still use normal kernel stack if
the stack size is small (< 64 bytes).

The prog->aux->priv_stack_requested is also used for recursion checking
for struct_ops progs. Similar to tracing progs, nested same cpu same
prog run will be skipped. A field (recursion_detected()) is added to
bpf_prog_aux structure. If bpf_prog->aux->recursion_detected
is implemented by the struct_ops subsystem and nested same cpu/prog
happens, the function will be triggered to report an error, collect
related info, etc.

Signed-off-by: Yonghong Song <[e-mail]>
---
 include/linux/bpf.h          | 1 +
 include/linux/bpf_verifier.h | 1 +
 kernel/bpf/trampoline.c      | 4 ++++
 kernel/bpf/verifier.c        | 6 ++++++
 4 files changed, 12 insertions(+)

Comments

Tejun Heo Nov. 7, 2024, 7:20 p.m. UTC | #1

On Wed, Nov 06, 2024 at 06:42:09PM -0800, Yonghong Song wrote:
> For struct_ops progs, whether a particular prog uses private stack
> depends on prog->aux->priv_stack_requested setting before actual
> insn-level verification for that prog. One particular implementation
> is to piggyback on struct_ops->check_member(). The next patch has
> an example for this. The struct_ops->check_member() sets
> prog->aux->priv_stack_requested to be true which enables private stack
> usage.
> 
> The struct_ops prog follows the same rule as kprobe/tracing progs after
> function bpf_enable_priv_stack(). For example, even a struct_ops prog
> requests private stack, it could still use normal kernel stack if
> the stack size is small (< 64 bytes).
> 
> The prog->aux->priv_stack_requested is also used for recursion checking
> for struct_ops progs. Similar to tracing progs, nested same cpu same
> prog run will be skipped. A field (recursion_detected()) is added to
> bpf_prog_aux structure. If bpf_prog->aux->recursion_detected
> is implemented by the struct_ops subsystem and nested same cpu/prog
> happens, the function will be triggered to report an error, collect
> related info, etc.
> 
> Signed-off-by: Yonghong Song <[e-mail]>

From user's POV, this looks great:

 Acked-by: Tejun Heo <[e-mail]>

Thanks.

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 644ad35b88ec..938e9c4fa9b1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1528,6 +1528,7 @@  struct bpf_prog_aux {
 	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
 	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
 	struct bpf_arena *arena;
+	void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 456fd2265345..6c1a173c30e6 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -895,6 +895,7 @@  static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
 	case BPF_PROG_TYPE_TRACING:
 		return prog->expected_attach_type != BPF_TRACE_ITER;
 	case BPF_PROG_TYPE_STRUCT_OPS:
+		return prog->aux->priv_stack_requested;
 	case BPF_PROG_TYPE_LSM:
 		return false;
 	default:
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 9f36c049f4c2..a8d188b31da5 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -899,6 +899,8 @@  static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram
 
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
+		if (prog->aux->recursion_detected)
+			prog->aux->recursion_detected(prog);
 		return 0;
 	}
 	return bpf_prog_start_time();
@@ -975,6 +977,8 @@  u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
 		bpf_prog_inc_misses_counter(prog);
+		if (prog->aux->recursion_detected)
+			prog->aux->recursion_detected(prog);
 		return 0;
 	}
 	return bpf_prog_start_time();
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 09bb9dc939d6..d0e5038a844a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6279,6 +6279,7 @@  static int check_max_stack_depth(struct bpf_verifier_env *env)
 		}
 	}
 
+	env->prog->aux->priv_stack_requested = false;
 	if (si[0].priv_stack_mode == PRIV_STACK_ADAPTIVE)
 		env->prog->aux->priv_stack_requested = true;
 
@@ -21986,6 +21987,11 @@  static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 		}
 	}
 
+	if (prog->aux->priv_stack_requested && !bpf_jit_supports_private_stack()) {
+		verbose(env, "Private stack not supported by jit\n");
+		return -EACCES;
+	}
+
 	/* btf_ctx_access() used this to provide argument type info */
 	prog->aux->ctx_arg_info =
 		st_ops_desc->arg_info[member_idx].info;