bpf: Support private stack for struct_ops progs

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).

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.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20241112163933.2224962-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: Yonghong Song

include/linux/bpf.h

@@ -1525,9 +1525,11 @@ struct bpf_prog_aux {
 	bool exception_boundary;
 	bool is_extended; /* true if extended by freplace program */
 	bool jits_use_priv_stack;
+	bool priv_stack_requested;
 	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 */

include/linux/bpf_verifier.h

@@ -879,6 +879,7 @@ 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->jits_use_priv_stack;
 	case BPF_PROG_TYPE_LSM:
 		return false;
 	default:

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();

kernel/bpf/verifier.c

@@ -6110,7 +6110,7 @@ static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog)
 	case BPF_PROG_TYPE_TRACING:
 	case BPF_PROG_TYPE_LSM:
 	case BPF_PROG_TYPE_STRUCT_OPS:
-		if (bpf_prog_check_recur(prog))
+		if (prog->aux->priv_stack_requested || bpf_prog_check_recur(prog))
 			return PRIV_STACK_ADAPTIVE;
 		fallthrough;
 	default:
@@ -22053,6 +22053,11 @@ 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;