Merge branch 'Enable struct_ops programs to be sleepable'

David Vernet says:

====================

This is part 4 of https://lore.kernel.org/bpf/20230123232228.646563-1-void@manifault.com/

Part 3: https://lore.kernel.org/all/20230125050359.339273-1-void@manifault.com/
Part 2: https://lore.kernel.org/all/20230124160802.1122124-1-void@manifault.com/

Changelog:
----------
v3 -> v4:
- Fix accidental typo in name of dummy_st_ops introduced in v2, moving
  it back to dummy_st_ops from dummy_st_ops_success. Should fix s390x
  testruns.

v2 -> v3:
- Don't call a KF_SLEEPABLE kfunc from the dummy_st_ops testsuite, and
  remove the newly added bpf_kfunc_call_test_sleepable() test kfunc
  (Martin).
- Include vmlinux.h from progs/dummy_st_ops_success.c (previously
  progs/dummy_st_ops.c) rather than manually defining
  struct bpf_dummy_ops_state and struct bpf_dummy_ops.
  (Martin).
- Fix a typo added to prog_tests/dummy_st_ops.c in a previous version:
  s/trace_dummy_st_ops_success__open/trace_dummy_st_ops__open.

v1 -> v2:
- Add support for specifying sleepable struct_ops programs with
  struct_ops.s in libbpf (Alexei).
- Move failure test case into new dummy_st_ops_fail.c prog file.
- Update test_dummy_sleepable() to use struct_ops.s instead of manually
  setting prog flags. Also remove open_load_skel() helper which is no
  longer needed.
- Fix verifier tests to expect new sleepable prog failure message.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -1422,7 +1422,8 @@ struct bpf_struct_ops {
 	const struct bpf_verifier_ops *verifier_ops;
 	int (*init)(struct btf *btf);
 	int (*check_member)(const struct btf_type *t,
-			    const struct btf_member *member);
+			    const struct btf_member *member,
+			    const struct bpf_prog *prog);
 	int (*init_member)(const struct btf_type *t,
 			   const struct btf_member *member,
 			   void *kdata, const void *udata);
@@ -1473,6 +1474,7 @@ struct bpf_dummy_ops {
 	int (*test_1)(struct bpf_dummy_ops_state *cb);
 	int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2,
 		      char a3, unsigned long a4);
+	int (*test_sleepable)(struct bpf_dummy_ops_state *cb);
 };
 
 int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,

kernel/bpf/verifier.c

@@ -16792,7 +16792,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
 	}
 
 	if (st_ops->check_member) {
-		int err = st_ops->check_member(t, member);
+		int err = st_ops->check_member(t, member, prog);
 
 		if (err) {
 			verbose(env, "attach to unsupported member %s of struct %s\n",
@@ -17114,7 +17114,8 @@ static bool can_be_sleepable(struct bpf_prog *prog)
 		}
 	}
 	return prog->type == BPF_PROG_TYPE_LSM ||
-	       prog->type == BPF_PROG_TYPE_KPROBE; /* only for uprobes */
+	       prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ ||
+	       prog->type == BPF_PROG_TYPE_STRUCT_OPS;
 }
 
 static int check_attach_btf_id(struct bpf_verifier_env *env)
@@ -17136,7 +17137,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 	}
 
 	if (prog->aux->sleepable && !can_be_sleepable(prog)) {
-		verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter and uprobe programs can be sleepable\n");
+		verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n");
 		return -EINVAL;
 	}
 

net/bpf/bpf_dummy_struct_ops.c

@@ -154,6 +154,23 @@ static bool bpf_dummy_ops_is_valid_access(int off, int size,
 	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
 }
 
+static int bpf_dummy_ops_check_member(const struct btf_type *t,
+				      const struct btf_member *member,
+				      const struct bpf_prog *prog)
+{
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+	switch (moff) {
+	case offsetof(struct bpf_dummy_ops, test_sleepable):
+		break;
+	default:
+		if (prog->aux->sleepable)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log,
 					   const struct bpf_reg_state *reg,
 					   int off, int size, enum bpf_access_type atype,
@@ -208,6 +225,7 @@ static void bpf_dummy_unreg(void *kdata)
 struct bpf_struct_ops bpf_bpf_dummy_ops = {
 	.verifier_ops = &bpf_dummy_verifier_ops,
 	.init = bpf_dummy_init,
+	.check_member = bpf_dummy_ops_check_member,
 	.init_member = bpf_dummy_init_member,
 	.reg = bpf_dummy_reg,
 	.unreg = bpf_dummy_unreg,

net/ipv4/bpf_tcp_ca.c

@@ -248,7 +248,8 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t,
 }
 
 static int bpf_tcp_ca_check_member(const struct btf_type *t,
-				   const struct btf_member *member)
+				   const struct btf_member *member,
+				   const struct bpf_prog *prog)
 {
 	if (is_unsupported(__btf_member_bit_offset(t, member) / 8))
 		return -ENOTSUPP;

tools/lib/bpf/libbpf.c

@@ -8605,6 +8605,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE),
 	SEC_DEF("cgroup/dev",		CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT),
 	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
+	SEC_DEF("struct_ops.s+",	STRUCT_OPS, 0, SEC_SLEEPABLE),
 	SEC_DEF("sk_lookup",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
 };
 

tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c

@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
 #include <test_progs.h>
-#include "dummy_st_ops.skel.h"
+#include "dummy_st_ops_success.skel.h"
+#include "dummy_st_ops_fail.skel.h"
 #include "trace_dummy_st_ops.skel.h"
 
 /* Need to keep consistent with definition in include/linux/bpf.h */
@@ -11,17 +12,17 @@ struct bpf_dummy_ops_state {
 
 static void test_dummy_st_ops_attach(void)
 {
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	struct bpf_link *link;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(skel->maps.dummy_1);
 	ASSERT_EQ(libbpf_get_error(link), -EOPNOTSUPP, "dummy_st_ops_attach");
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 }
 
 static void test_dummy_init_ret_value(void)
@@ -31,10 +32,10 @@ static void test_dummy_init_ret_value(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -43,7 +44,7 @@ static void test_dummy_init_ret_value(void)
 	ASSERT_OK(err, "test_run");
 	ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret");
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 }
 
 static void test_dummy_init_ptr_arg(void)
@@ -58,10 +59,10 @@ static void test_dummy_init_ptr_arg(void)
 		.ctx_size_in = sizeof(args),
 	);
 	struct trace_dummy_st_ops *trace_skel;
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -91,7 +92,7 @@ static void test_dummy_init_ptr_arg(void)
 	ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val");
 
 done:
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 	trace_dummy_st_ops__destroy(trace_skel);
 }
 
@@ -102,12 +103,12 @@ static void test_dummy_multiple_args(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 	size_t i;
 	char name[8];
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -119,7 +120,28 @@ static void test_dummy_multiple_args(void)
 		ASSERT_EQ(skel->bss->test_2_args[i], args[i], name);
 	}
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
+}
+
+static void test_dummy_sleepable(void)
+{
+	__u64 args[1] = {0};
+	LIBBPF_OPTS(bpf_test_run_opts, attr,
+		.ctx_in = args,
+		.ctx_size_in = sizeof(args),
+	);
+	struct dummy_st_ops_success *skel;
+	int fd, err;
+
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_sleepable);
+	err = bpf_prog_test_run_opts(fd, &attr);
+	ASSERT_OK(err, "test_run");
+
+	dummy_st_ops_success__destroy(skel);
 }
 
 void test_dummy_st_ops(void)
@@ -132,4 +154,8 @@ void test_dummy_st_ops(void)
 		test_dummy_init_ptr_arg();
 	if (test__start_subtest("dummy_multiple_args"))
 		test_dummy_multiple_args();
+	if (test__start_subtest("dummy_sleepable"))
+		test_dummy_sleepable();
+
+	RUN_TESTS(dummy_st_ops_fail);
 }

tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c

@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops.s/test_2")
+__failure __msg("attach to unsupported member test_2 of struct bpf_dummy_ops")
+int BPF_PROG(test_unsupported_field_sleepable,
+	     struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
+	     char a3, unsigned long a4)
+{
+	/* Tries to mark an unsleepable field in struct bpf_dummy_ops as sleepable. */
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = NULL,
+	.test_2 = (void *)test_unsupported_field_sleepable,
+	.test_sleepable = (void *)NULL,
+};

tools/testing/selftests/bpf/progs/dummy_st_ops_success.c

@@ -1,19 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct bpf_dummy_ops_state {
-	int val;
-} __attribute__((preserve_access_index));
-
-struct bpf_dummy_ops {
-	int (*test_1)(struct bpf_dummy_ops_state *state);
-	int (*test_2)(struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
-		      char a3, unsigned long a4);
-};
-
 char _license[] SEC("license") = "GPL";
 
 SEC("struct_ops/test_1")
@@ -43,8 +33,15 @@ int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a
 	return 0;
 }
 
+SEC("struct_ops.s/test_sleepable")
+int BPF_PROG(test_sleepable, struct bpf_dummy_ops_state *state)
+{
+	return 0;
+}
+
 SEC(".struct_ops")
 struct bpf_dummy_ops dummy_1 = {
 	.test_1 = (void *)test_1,
 	.test_2 = (void *)test_2,
+	.test_sleepable = (void *)test_sleepable,
 };

tools/testing/selftests/bpf/verifier/sleepable.c

@@ -85,7 +85,7 @@
 	.expected_attach_type = BPF_TRACE_RAW_TP,
 	.kfunc = "sched_switch",
 	.result = REJECT,
-	.errstr = "Only fentry/fexit/fmod_ret, lsm, iter and uprobe programs can be sleepable",
+	.errstr = "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable",
 	.flags = BPF_F_SLEEPABLE,
 	.runs = -1,
 },