Merge tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - User events are finally ready!

   After lots of collaboration between various parties, we finally
   locked down on a stable interface for user events that can also work
   with user space only tracing.

   This is implemented by telling the kernel (or user space library, but
   that part is user space only and not part of this patch set), where
   the variable is that the application uses to know if something is
   listening to the trace.

   There's also an interface to tell the kernel about these events,
   which will show up in the /sys/kernel/tracing/events/user_events/
   directory, where it can be enabled.

   When it's enabled, the kernel will update the variable, to tell the
   application to start writing to the kernel.

   See https://lwn.net/Articles/927595/

 - Cleaned up the direct trampolines code to simplify arm64 addition of
   direct trampolines.

   Direct trampolines use the ftrace interface but instead of jumping to
   the ftrace trampoline, applications (mostly BPF) can register their
   own trampoline for performance reasons.

 - Some updates to the fprobe infrastructure. fprobes are more efficient
   than kprobes, as it does not need to save all the registers that
   kprobes on ftrace do. More work needs to be done before the fprobes
   will be exposed as dynamic events.

 - More updates to references to the obsolete path of
   /sys/kernel/debug/tracing for the new /sys/kernel/tracing path.

 - Add a seq_buf_do_printk() helper to seq_bufs, to print a large buffer
   line by line instead of all at once.

   There are users in production kernels that have a large data dump
   that originally used printk() directly, but the data dump was larger
   than what printk() allowed as a single print.

   Using seq_buf() to do the printing fixes that.

 - Add /sys/kernel/tracing/touched_functions that shows all functions
   that was every traced by ftrace or a direct trampoline. This is used
   for debugging issues where a traced function could have caused a
   crash by a bpf program or live patching.

 - Add a "fields" option that is similar to "raw" but outputs the fields
   of the events. It's easier to read by humans.

 - Some minor fixes and clean ups.

* tag 'trace-v6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (41 commits)
  ring-buffer: Sync IRQ works before buffer destruction
  tracing: Add missing spaces in trace_print_hex_seq()
  ring-buffer: Ensure proper resetting of atomic variables in ring_buffer_reset_online_cpus
  recordmcount: Fix memory leaks in the uwrite function
  tracing/user_events: Limit max fault-in attempts
  tracing/user_events: Prevent same address and bit per process
  tracing/user_events: Ensure bit is cleared on unregister
  tracing/user_events: Ensure write index cannot be negative
  seq_buf: Add seq_buf_do_printk() helper
  tracing: Fix print_fields() for __dyn_loc/__rel_loc
  tracing/user_events: Set event filter_type from type
  ring-buffer: Clearly check null ptr returned by rb_set_head_page()
  tracing: Unbreak user events
  tracing/user_events: Use print_format_fields() for trace output
  tracing/user_events: Align structs with tabs for readability
  tracing/user_events: Limit global user_event count
  tracing/user_events: Charge event allocs to cgroups
  tracing/user_events: Update documentation for ABI
  tracing/user_events: Use write ABI in example
  tracing/user_events: Add ABI self-test
  ...

2 files changed, 135 insertions, 2 deletions

diff --git a/lib/seq_buf.c b/lib/seq_buf.c
index 0a68f7aa85d6..45c450f423fa 100644
--- a/lib/seq_buf.c
+++ b/lib/seq_buf.c
@@ -93,6 +93,38 @@ int seq_buf_printf(struct seq_buf *s, const char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(seq_buf_printf);
 
+/**
+ * seq_buf_do_printk - printk seq_buf line by line
+ * @s: seq_buf descriptor
+ * @lvl: printk level
+ *
+ * printk()-s a multi-line sequential buffer line by line. The function
+ * makes sure that the buffer in @s is nul terminated and safe to read
+ * as a string.
+ */
+void seq_buf_do_printk(struct seq_buf *s, const char *lvl)
+{
+	const char *start, *lf;
+
+	if (s->size == 0 || s->len == 0)
+		return;
+
+	seq_buf_terminate(s);
+
+	start = s->buffer;
+	while ((lf = strchr(start, '\n'))) {
+		int len = lf - start + 1;
+
+		printk("%s%.*s", lvl, len, start);
+		start = ++lf;
+	}
+
+	/* No trailing LF */
+	if (start < s->buffer + s->len)
+		printk("%s%s\n", lvl, start);
+}
+EXPORT_SYMBOL_GPL(seq_buf_do_printk);
+
 #ifdef CONFIG_BINARY_PRINTF
 /**
  * seq_buf_bprintf - Write the printf string from binary arguments
diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c
index fd6153800e56..079435a2e26c 100644
--- a/lib/test_fprobe.c
+++ b/lib/test_fprobe.c
@@ -17,8 +17,11 @@ static u32 rand1, entry_val, exit_val;
 /* Use indirect calls to avoid inlining the target functions */
 static u32 (*target)(u32 value);
 static u32 (*target2)(u32 value);
+static u32 (*target_nest)(u32 value, u32 (*nest)(u32));
 static unsigned long target_ip;
 static unsigned long target2_ip;
+static unsigned long target_nest_ip;
+static int entry_return_value;
 
 static noinline u32 fprobe_selftest_target(u32 value)
 {
@@ -30,16 +33,31 @@ static noinline u32 fprobe_selftest_target2(u32 value)
 	return (value / div_factor) + 1;
 }
 
-static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs)
+static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32))
+{
+	return nest(value + 2);
+}
+
+static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip,
+				     struct pt_regs *regs, void *data)
 {
 	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	/* This can be called on the fprobe_selftest_target and the fprobe_selftest_target2 */
 	if (ip != target_ip)
 		KUNIT_EXPECT_EQ(current_test, ip, target2_ip);
 	entry_val = (rand1 / div_factor);
+	if (fp->entry_data_size) {
+		KUNIT_EXPECT_NOT_NULL(current_test, data);
+		if (data)
+			*(u32 *)data = entry_val;
+	} else
+		KUNIT_EXPECT_NULL(current_test, data);
+
+	return entry_return_value;
 }
 
-static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs)
+static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip,
+				    struct pt_regs *regs, void *data)
 {
 	unsigned long ret = regs_return_value(regs);
 
@@ -51,6 +69,26 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, struct
 		KUNIT_EXPECT_EQ(current_test, ret, (rand1 / div_factor));
 	KUNIT_EXPECT_EQ(current_test, entry_val, (rand1 / div_factor));
 	exit_val = entry_val + div_factor;
+	if (fp->entry_data_size) {
+		KUNIT_EXPECT_NOT_NULL(current_test, data);
+		if (data)
+			KUNIT_EXPECT_EQ(current_test, *(u32 *)data, entry_val);
+	} else
+		KUNIT_EXPECT_NULL(current_test, data);
+}
+
+static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip,
+				     struct pt_regs *regs, void *data)
+{
+	KUNIT_EXPECT_FALSE(current_test, preemptible());
+	return 0;
+}
+
+static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip,
+				    struct pt_regs *regs, void *data)
+{
+	KUNIT_EXPECT_FALSE(current_test, preemptible());
+	KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip);
 }
 
 /* Test entry only (no rethook) */
@@ -132,6 +170,64 @@ static void test_fprobe_syms(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp));
 }
 
+/* Test private entry_data */
+static void test_fprobe_data(struct kunit *test)
+{
+	struct fprobe fp = {
+		.entry_handler = fp_entry_handler,
+		.exit_handler = fp_exit_handler,
+		.entry_data_size = sizeof(u32),
+	};
+
+	current_test = test;
+	KUNIT_EXPECT_EQ(test, 0, register_fprobe(&fp, "fprobe_selftest_target", NULL));
+
+	target(rand1);
+
+	KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp));
+}
+
+/* Test nr_maxactive */
+static void test_fprobe_nest(struct kunit *test)
+{
+	static const char *syms[] = {"fprobe_selftest_target", "fprobe_selftest_nest_target"};
+	struct fprobe fp = {
+		.entry_handler = nest_entry_handler,
+		.exit_handler = nest_exit_handler,
+		.nr_maxactive = 1,
+	};
+
+	current_test = test;
+	KUNIT_EXPECT_EQ(test, 0, register_fprobe_syms(&fp, syms, 2));
+
+	target_nest(rand1, target);
+	KUNIT_EXPECT_EQ(test, 1, fp.nmissed);
+
+	KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp));
+}
+
+static void test_fprobe_skip(struct kunit *test)
+{
+	struct fprobe fp = {
+		.entry_handler = fp_entry_handler,
+		.exit_handler = fp_exit_handler,
+	};
+
+	current_test = test;
+	KUNIT_EXPECT_EQ(test, 0, register_fprobe(&fp, "fprobe_selftest_target", NULL));
+
+	entry_return_value = 1;
+	entry_val = 0;
+	exit_val = 0;
+	target(rand1);
+	KUNIT_EXPECT_NE(test, 0, entry_val);
+	KUNIT_EXPECT_EQ(test, 0, exit_val);
+	KUNIT_EXPECT_EQ(test, 0, fp.nmissed);
+	entry_return_value = 0;
+
+	KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp));
+}
+
 static unsigned long get_ftrace_location(void *func)
 {
 	unsigned long size, addr = (unsigned long)func;
@@ -147,8 +243,10 @@ static int fprobe_test_init(struct kunit *test)
 	rand1 = get_random_u32_above(div_factor);
 	target = fprobe_selftest_target;
 	target2 = fprobe_selftest_target2;
+	target_nest = fprobe_selftest_nest_target;
 	target_ip = get_ftrace_location(target);
 	target2_ip = get_ftrace_location(target2);
+	target_nest_ip = get_ftrace_location(target_nest);
 
 	return 0;
 }
@@ -157,6 +255,9 @@ static struct kunit_case fprobe_testcases[] = {
 	KUNIT_CASE(test_fprobe_entry),
 	KUNIT_CASE(test_fprobe),
 	KUNIT_CASE(test_fprobe_syms),
+	KUNIT_CASE(test_fprobe_data),
+	KUNIT_CASE(test_fprobe_nest),
+	KUNIT_CASE(test_fprobe_skip),
 	{}
 };