Merge branch 'Allow attaching to bare tracepoints'

Qais Yousef says:

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

Changes in v3:
* Fix not returning error value correctly in
trigger_module_test_write() (Yonghong)
* Add Yonghong acked-by to patch 1.

Changes in v2:
* Fix compilation error. (Andrii)
* Make the new test use write() instead of read() (Andrii)

Add some missing glue logic to teach bpf about bare tracepoints - tracepoints
without any trace event associated with them.

Bare tracepoints are declare with DECLARE_TRACE(). Full tracepoints are declare
with TRACE_EVENT().

BPF can attach to these tracepoints as RAW_TRACEPOINT() only as there're no
events in tracefs created with them.
====================

Signed-off-by: Alexei Starovoitov <[e-mail]>

Documentation/bpf/bpf_design_QA.rst

···
 kernel internals are subject to change and can break with newer kernels
 such that the program needs to be adapted accordingly.
 
+Q: Are tracepoints part of the stable ABI?
+------------------------------------------
+A: NO. Tracepoints are tied to internal implementation details hence they are
+subject to change and can break with newer kernels. BPF programs need to change
+accordingly when this happens.
+
 Q: How much stack space a BPF program uses?
 -------------------------------------------
 A: Currently all program types are limited to 512 bytes of stack

include/trace/bpf_probe.h

···
 /* tracepoints with more than 12 arguments will hit build error */
 #define CAST_TO_U64(...) CONCATENATE(__CAST, COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__)
 
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+#define __BPF_DECLARE_TRACE(call, proto, args)				\
 static notrace void							\
 __bpf_trace_##call(void *__data, proto)					\
 {									\
 	struct bpf_prog *prog = __data;					\
 	CONCATENATE(bpf_trace_run, COUNT_ARGS(args))(prog, CAST_TO_U64(args));	\
 }
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+	__BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args))
 
 /*
  * This part is compiled out, it is only here as a build time check
···
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(call, proto, args)				\
+	__BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args))		\
+	__DEFINE_EVENT(call, call, PARAMS(proto), PARAMS(args), 0)
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h

···
 		  __entry->pid, __entry->comm, __entry->off, __entry->len)
 );
 
+/* A bare tracepoint with no event associated with it */
+DECLARE_TRACE(bpf_testmod_test_write_bare,
+	TP_PROTO(struct task_struct *task, struct bpf_testmod_test_write_ctx *ctx),
+	TP_ARGS(task, ctx)
+);
+
 #endif /* _BPF_TESTMOD_EVENTS_H */
 
 #undef TRACE_INCLUDE_PATH

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c

···
 EXPORT_SYMBOL(bpf_testmod_test_read);
 ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO);
 
+noinline ssize_t
+bpf_testmod_test_write(struct file *file, struct kobject *kobj,
+		      struct bin_attribute *bin_attr,
+		      char *buf, loff_t off, size_t len)
+{
+	struct bpf_testmod_test_write_ctx ctx = {
+		.buf = buf,
+		.off = off,
+		.len = len,
+	};
+
+	trace_bpf_testmod_test_write_bare(current, &ctx);
+
+	return -EIO; /* always fail */
+}
+EXPORT_SYMBOL(bpf_testmod_test_write);
+ALLOW_ERROR_INJECTION(bpf_testmod_test_write, ERRNO);
+
 static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
-	.attr = { .name = "bpf_testmod", .mode = 0444, },
+	.attr = { .name = "bpf_testmod", .mode = 0666, },
 	.read = bpf_testmod_test_read,
+	.write = bpf_testmod_test_write,
 };
 
 static int bpf_testmod_init(void)

tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h

···
 	size_t len;
 };
 
+struct bpf_testmod_test_write_ctx {
+	char *buf;
+	loff_t off;
+	size_t len;
+};
+
 #endif /* _BPF_TESTMOD_H */

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

···
 	return 0;
 }
 
+static int trigger_module_test_write(int write_sz)
+{
+	int fd, err;
+	char *buf = malloc(write_sz);
+
+	if (!buf)
+		return -ENOMEM;
+
+	memset(buf, 'a', write_sz);
+	buf[write_sz-1] = '\0';
+
+	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
+	err = -errno;
+	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) {
+		free(buf);
+		return err;
+	}
+
+	write(fd, buf, write_sz);
+	close(fd);
+	free(buf);
+	return 0;
+}
+
 void test_module_attach(void)
 {
 	const int READ_SZ = 456;
+	const int WRITE_SZ = 457;
 	struct test_module_attach* skel;
 	struct test_module_attach__bss *bss;
 	int err;
···
 
 	/* trigger tracepoint */
 	ASSERT_OK(trigger_module_test_read(READ_SZ), "trigger_read");
+	ASSERT_OK(trigger_module_test_write(WRITE_SZ), "trigger_write");
 
 	ASSERT_EQ(bss->raw_tp_read_sz, READ_SZ, "raw_tp");
+	ASSERT_EQ(bss->raw_tp_bare_write_sz, WRITE_SZ, "raw_tp_bare");
 	ASSERT_EQ(bss->tp_btf_read_sz, READ_SZ, "tp_btf");
 	ASSERT_EQ(bss->fentry_read_sz, READ_SZ, "fentry");
 	ASSERT_EQ(bss->fentry_manual_read_sz, READ_SZ, "fentry_manual");

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

···
 	return 0;
 }
 
+__u32 raw_tp_bare_write_sz = 0;
+
+SEC("raw_tp/bpf_testmod_test_write_bare")
+int BPF_PROG(handle_raw_tp_bare,
+	     struct task_struct *task, struct bpf_testmod_test_write_ctx *write_ctx)
+{
+	raw_tp_bare_write_sz = BPF_CORE_READ(write_ctx, len);
+	return 0;
+}
+
 __u32 tp_btf_read_sz = 0;
 
 SEC("tp_btf/bpf_testmod_test_read")