Merge branch 'add support for writable bare tracepoint'

Hou Tao says:

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

From: Hou Tao <houtao1@huawei.com>

Hi,

The patchset series supports writable context for bare tracepoint.

The main idea comes from patchset "writable contexts for bpf raw
tracepoints" [1], but it only supports normal tracepoint with
associated trace event under tracefs. Now we have one use case
in which we add bare tracepoint in VFS layer, and update
file::f_mode for specific files. The reason using bare tracepoint
is that it doesn't form a ABI and we can change it freely. So
add support for it in BPF.

Comments are always welcome.

[1]: https://lore.kernel.org/lkml/20190426184951.21812-1-mmullins@fb.com

Change log:
v5:
 * rebased on bpf-next
 * patch 1: add Acked-by tag
 * patch 2: handle invalid section name, make prefixes array being const

v4: https://www.spinics.net/lists/bpf/msg47021.html
 * rebased on bpf-next
 * update patch 2 to add support for writable raw tracepoint attachment
   in attach_raw_tp().
 * update patch 3 to add Acked-by tag

v3: https://www.spinics.net/lists/bpf/msg46824.html
  * use raw_tp.w instead of raw_tp_writable as section
    name of writable tp
  * use ASSERT_XXX() instead of CHECK()
  * define a common macro for "/sys/kernel/bpf_testmod"

v2: https://www.spinics.net/lists/bpf/msg46356.html
  * rebase on bpf-next tree
  * address comments from Yonghong Song
  * rename bpf_testmode_test_writable_ctx::ret as early_ret to reflect
    its purpose better.

v1: https://www.spinics.net/lists/bpf/msg46221.html
====================
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

include/trace/bpf_probe.h

@@ -93,8 +93,7 @@ __section("__bpf_raw_tp_map") = {					\
 
 #define FIRST(x, ...) x
 
-#undef DEFINE_EVENT_WRITABLE
-#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size)	\
+#define __CHECK_WRITABLE_BUF_SIZE(call, proto, args, size)		\
 static inline void bpf_test_buffer_##call(void)				\
 {									\
 	/* BUILD_BUG_ON() is ignored if the code is completely eliminated, but \
@@ -103,8 +102,12 @@ static inline void bpf_test_buffer_##call(void)				\
 	 */								\
 	FIRST(proto);							\
 	(void)BUILD_BUG_ON_ZERO(size != sizeof(*FIRST(args)));		\
-}									\
-__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size)
+}
+
+#undef DEFINE_EVENT_WRITABLE
+#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size) \
+	__CHECK_WRITABLE_BUF_SIZE(call, PARAMS(proto), PARAMS(args), size) \
+	__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size)
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
@@ -119,9 +122,17 @@ __DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size)
 	__BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args))		\
 	__DEFINE_EVENT(call, call, PARAMS(proto), PARAMS(args), 0)
 
+#undef DECLARE_TRACE_WRITABLE
+#define DECLARE_TRACE_WRITABLE(call, proto, args, size) \
+	__CHECK_WRITABLE_BUF_SIZE(call, PARAMS(proto), PARAMS(args), size) \
+	__BPF_DECLARE_TRACE(call, PARAMS(proto), PARAMS(args)) \
+	__DEFINE_EVENT(call, call, PARAMS(proto), PARAMS(args), size)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#undef DECLARE_TRACE_WRITABLE
 #undef DEFINE_EVENT_WRITABLE
+#undef __CHECK_WRITABLE_BUF_SIZE
 #undef __DEFINE_EVENT
 #undef FIRST
 

tools/lib/bpf/libbpf.c

@@ -8077,6 +8077,8 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("tp/",			TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("raw_tracepoint/",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
 	SEC_DEF("raw_tp/",		RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tracepoint.w/",	RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tp.w/",		RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp),
 	SEC_DEF("tp_btf/",		TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace),
 	SEC_DEF("fentry/",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace),
 	SEC_DEF("fmod_ret/",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace),
@@ -9846,12 +9848,26 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 
 static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie)
 {
-	const char *tp_name;
+	static const char *const prefixes[] = {
+		"raw_tp/",
+		"raw_tracepoint/",
+		"raw_tp.w/",
+		"raw_tracepoint.w/",
+	};
+	size_t i;
+	const char *tp_name = NULL;
 
-	if (str_has_pfx(prog->sec_name, "raw_tp/"))
-		tp_name = prog->sec_name + sizeof("raw_tp/") - 1;
-	else
-		tp_name = prog->sec_name + sizeof("raw_tracepoint/") - 1;
+	for (i = 0; i < ARRAY_SIZE(prefixes); i++) {
+		if (str_has_pfx(prog->sec_name, prefixes[i])) {
+			tp_name = prog->sec_name + strlen(prefixes[i]);
+			break;
+		}
+	}
+	if (!tp_name) {
+		pr_warn("prog '%s': invalid section name '%s'\n",
+			prog->name, prog->sec_name);
+		return libbpf_err_ptr(-EINVAL);
+	}
 
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }

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

@@ -34,6 +34,21 @@ DECLARE_TRACE(bpf_testmod_test_write_bare,
 	TP_ARGS(task, ctx)
 );
 
+#undef BPF_TESTMOD_DECLARE_TRACE
+#ifdef DECLARE_TRACE_WRITABLE
+#define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \
+	DECLARE_TRACE_WRITABLE(call, PARAMS(proto), PARAMS(args), size)
+#else
+#define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \
+	DECLARE_TRACE(call, PARAMS(proto), PARAMS(args))
+#endif
+
+BPF_TESTMOD_DECLARE_TRACE(bpf_testmod_test_writable_bare,
+	TP_PROTO(struct bpf_testmod_test_writable_ctx *ctx),
+	TP_ARGS(ctx),
+	sizeof(struct bpf_testmod_test_writable_ctx)
+);
+
 #endif /* _BPF_TESTMOD_EVENTS_H */
 
 #undef TRACE_INCLUDE_PATH

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

@@ -50,6 +50,16 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	if (bpf_testmod_loop_test(101) > 100)
 		trace_bpf_testmod_test_read(current, &ctx);
 
+	/* Magic number to enable writable tp */
+	if (len == 64) {
+		struct bpf_testmod_test_writable_ctx writable = {
+			.val = 1024,
+		};
+		trace_bpf_testmod_test_writable_bare(&writable);
+		if (writable.early_ret)
+			return snprintf(buf, len, "%d\n", writable.val);
+	}
+
 	return -EIO; /* always fail */
 }
 EXPORT_SYMBOL(bpf_testmod_test_read);

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

@@ -17,4 +17,9 @@ struct bpf_testmod_test_write_ctx {
 	size_t len;
 };
 
+struct bpf_testmod_test_writable_ctx {
+	bool early_ret;
+	int val;
+};
+
 #endif /* _BPF_TESTMOD_H */

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

@@ -2,10 +2,36 @@
 /* Copyright (c) 2020 Facebook */
 
 #include <test_progs.h>
+#include <stdbool.h>
 #include "test_module_attach.skel.h"
 
 static int duration;
 
+static int trigger_module_test_writable(int *val)
+{
+	int fd, err;
+	char buf[65];
+	ssize_t rd;
+
+	fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmode_file_open"))
+		return err;
+
+	rd = read(fd, buf, sizeof(buf) - 1);
+	err = -errno;
+	if (!ASSERT_GT(rd, 0, "testmod_file_rd_val")) {
+		close(fd);
+		return err;
+	}
+
+	buf[rd] = '\0';
+	*val = strtol(buf, NULL, 0);
+	close(fd);
+
+	return 0;
+}
+
 static int delete_module(const char *name, int flags)
 {
 	return syscall(__NR_delete_module, name, flags);
@@ -19,6 +45,7 @@ void test_module_attach(void)
 	struct test_module_attach__bss *bss;
 	struct bpf_link *link;
 	int err;
+	int writable_val = 0;
 
 	skel = test_module_attach__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -51,6 +78,14 @@ void test_module_attach(void)
 	ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
 	ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
 
+	bss->raw_tp_writable_bare_early_ret = true;
+	bss->raw_tp_writable_bare_out_val = 0xf1f2f3f4;
+	ASSERT_OK(trigger_module_test_writable(&writable_val),
+		  "trigger_writable");
+	ASSERT_EQ(bss->raw_tp_writable_bare_in_val, 1024, "writable_test_in");
+	ASSERT_EQ(bss->raw_tp_writable_bare_out_val, writable_val,
+		  "writable_test_out");
+
 	test_module_attach__detach(skel);
 
 	/* attach fentry/fexit and make sure it get's module reference */

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

@@ -27,6 +27,20 @@ int BPF_PROG(handle_raw_tp_bare,
 	return 0;
 }
 
+int raw_tp_writable_bare_in_val = 0;
+int raw_tp_writable_bare_early_ret = 0;
+int raw_tp_writable_bare_out_val = 0;
+
+SEC("raw_tp.w/bpf_testmod_test_writable_bare")
+int BPF_PROG(handle_raw_tp_writable_bare,
+	     struct bpf_testmod_test_writable_ctx *writable)
+{
+	raw_tp_writable_bare_in_val = writable->val;
+	writable->early_ret = raw_tp_writable_bare_early_ret;
+	writable->val = raw_tp_writable_bare_out_val;
+	return 0;
+}
+
 __u32 tp_btf_read_sz = 0;
 
 SEC("tp_btf/bpf_testmod_test_read")

tools/testing/selftests/bpf/test_progs.c

@@ -747,7 +747,7 @@ int trigger_module_test_read(int read_sz)
 {
 	int fd, err;
 
-	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+	fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY);
 	err = -errno;
 	if (!ASSERT_GE(fd, 0, "testmod_file_open"))
 		return err;
@@ -769,7 +769,7 @@ int trigger_module_test_write(int write_sz)
 	memset(buf, 'a', write_sz);
 	buf[write_sz-1] = '\0';
 
-	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
+	fd = open(BPF_TESTMOD_TEST_FILE, O_WRONLY);
 	err = -errno;
 	if (!ASSERT_GE(fd, 0, "testmod_file_open")) {
 		free(buf);

tools/testing/selftests/bpf/test_progs.h

@@ -301,3 +301,5 @@ int trigger_module_test_write(int write_sz);
 #else
 #define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
 #endif
+
+#define BPF_TESTMOD_TEST_FILE "/sys/kernel/bpf_testmod"