Merge tag 'trace-v5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:

 - New user_events interface. User space can register an event with the
   kernel describing the format of the event. Then it will receive a
   byte in a page mapping that it can check against. A privileged task
   can then enable that event like any other event, which will change
   the mapped byte to true, telling the user space application to start
   writing the event to the tracing buffer.

 - Add new "ftrace_boot_snapshot" kernel command line parameter. When
   set, the tracing buffer will be saved in the snapshot buffer at boot
   up when the kernel hands things over to user space. This will keep
   the traces that happened at boot up available even if user space boot
   up has tracing as well.

 - Have TRACE_EVENT_ENUM() also update trace event field type
   descriptions. Thus if a static array defines its size with an enum,
   the user space trace event parsers can still know how to parse that
   array.

 - Add new TRACE_CUSTOM_EVENT() macro. This acts the same as the
   TRACE_EVENT() macro, but will attach to an existing tracepoint. This
   will make one tracepoint be able to trace different content and not
   be stuck at only what the original TRACE_EVENT() macro exports.

 - Fixes to tracing error logging.

 - Better saving of cmdlines to PIDs when tracing (use the wakeup events
   for mapping).

* tag 'trace-v5.18' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (30 commits)
  tracing: Have type enum modifications copy the strings
  user_events: Add trace event call as root for low permission cases
  tracing/user_events: Use alloc_pages instead of kzalloc() for register pages
  tracing: Add snapshot at end of kernel boot up
  tracing: Have TRACE_DEFINE_ENUM affect trace event types as well
  tracing: Fix strncpy warning in trace_events_synth.c
  user_events: Prevent dyn_event delete racing with ioctl add/delete
  tracing: Add TRACE_CUSTOM_EVENT() macro
  tracing: Move the defines to create TRACE_EVENTS into their own files
  tracing: Add sample code for custom trace events
  tracing: Allow custom events to be added to the tracefs directory
  tracing: Fix last_cmd_set() string management in histogram code
  user_events: Fix potential uninitialized pointer while parsing field
  tracing: Fix allocation of last_cmd in last_cmd_set()
  user_events: Add documentation file
  user_events: Add sample code for typical usage
  user_events: Add self-test for validator boundaries
  user_events: Add self-test for perf_event integration
  user_events: Add self-test for dynamic_events integration
  user_events: Add self-test for ftrace integration
  ...

7 files changed, 262 insertions, 1 deletions

diff --git a/samples/Kconfig b/samples/Kconfig
index 22cc921ae291..10e021c72282 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -14,7 +14,13 @@ config SAMPLE_TRACE_EVENTS
 	tristate "Build trace_events examples -- loadable modules only"
 	depends on EVENT_TRACING && m
 	help
-	  This build trace event example modules.
+	  This builds the trace event example module.
+
+config SAMPLE_TRACE_CUSTOM_EVENTS
+	tristate "Build custom trace event example -- loadable modules only"
+	depends on EVENT_TRACING && m
+	help
+	  This builds the custom trace event example module.
 
 config SAMPLE_TRACE_PRINTK
         tristate "Build trace_printk module - tests various trace_printk formats"
diff --git a/samples/Makefile b/samples/Makefile
index 1ae4de99c983..448343e8faeb 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_SAMPLE_RPMSG_CLIENT)	+= rpmsg/
 subdir-$(CONFIG_SAMPLE_SECCOMP)		+= seccomp
 subdir-$(CONFIG_SAMPLE_TIMER)		+= timers
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS)	+= trace_events/
+obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_events/
 obj-$(CONFIG_SAMPLE_TRACE_PRINTK)	+= trace_printk/
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT)	+= ftrace/
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace/
diff --git a/samples/trace_events/Makefile b/samples/trace_events/Makefile
index b78344e7bbed..b3808bb4cf8b 100644
--- a/samples/trace_events/Makefile
+++ b/samples/trace_events/Makefile
@@ -11,5 +11,7 @@
 # Here trace-events-sample.c does the CREATE_TRACE_POINTS.
 #
 CFLAGS_trace-events-sample.o := -I$(src)
+CFLAGS_trace_custom_sched.o := -I$(src)
 
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS) += trace-events-sample.o
+obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_custom_sched.o
diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c
new file mode 100644
index 000000000000..b99d9ab7db85
--- /dev/null
+++ b/samples/trace_events/trace_custom_sched.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * event tracer
+ *
+ * Copyright (C) 2022 Google Inc, Steven Rostedt <rostedt@goodmis.org>
+ */
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/trace_events.h>
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+
+/*
+ * Must include the event header that the custom event will attach to,
+ * from the C file, and not in the custom header file.
+ */
+#include <trace/events/sched.h>
+
+/* Declare CREATE_CUSTOM_TRACE_EVENTS before including custom header */
+#define CREATE_CUSTOM_TRACE_EVENTS
+
+#include "trace_custom_sched.h"
+
+/*
+ * As the trace events are not exported to modules, the use of
+ * for_each_kernel_tracepoint() is needed to find the trace event
+ * to attach to. The fct() function below, is a callback that
+ * will be called for every event.
+ *
+ * Helper functions are created by the TRACE_CUSTOM_EVENT() macro
+ * update the event. Those are of the form:
+ *
+ *    trace_custom_event_<event>_update()
+ *
+ * Where <event> is the event to attach.
+ */
+static void fct(struct tracepoint *tp, void *priv)
+{
+	trace_custom_event_sched_switch_update(tp);
+	trace_custom_event_sched_waking_update(tp);
+}
+
+static int __init trace_sched_init(void)
+{
+	for_each_kernel_tracepoint(fct, NULL);
+	return 0;
+}
+
+static void __exit trace_sched_exit(void)
+{
+}
+
+module_init(trace_sched_init);
+module_exit(trace_sched_exit);
+
+MODULE_AUTHOR("Steven Rostedt");
+MODULE_DESCRIPTION("Custom scheduling events");
+MODULE_LICENSE("GPL");
diff --git a/samples/trace_events/trace_custom_sched.h b/samples/trace_events/trace_custom_sched.h
new file mode 100644
index 000000000000..9fdd8e7c2a45
--- /dev/null
+++ b/samples/trace_events/trace_custom_sched.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Like the headers that use TRACE_EVENT(), the TRACE_CUSTOM_EVENT()
+ * needs a header that allows for multiple inclusions.
+ *
+ * Test for a unique name (here we have _TRACE_CUSTOM_SCHED_H),
+ * also allowing to continue if TRACE_CUSTOM_MULTI_READ is defined.
+ */
+#if !defined(_TRACE_CUSTOM_SCHED_H) || defined(TRACE_CUSTOM_MULTI_READ)
+#define _TRACE_CUSTOM_SCHED_H
+
+/* Include linux/trace_events.h for initial defines of TRACE_CUSTOM_EVENT() */
+#include <linux/trace_events.h>
+
+/*
+ * TRACE_CUSTOM_EVENT() is just like TRACE_EVENT(). The first parameter
+ * is the event name of an existing event where the TRACE_EVENT has been included
+ * in the C file before including this file.
+ */
+TRACE_CUSTOM_EVENT(sched_switch,
+
+	/*
+	 * The TP_PROTO() and TP_ARGS must match the trace event
+	 * that the custom event is using.
+	 */
+	TP_PROTO(bool preempt,
+		 unsigned int prev_state,
+		 struct task_struct *prev,
+		 struct task_struct *next),
+
+	TP_ARGS(preempt, prev_state, prev, next),
+
+	/*
+	 * The next fields are where the customization happens.
+	 * The TP_STRUCT__entry() defines what will be recorded
+	 * in the ring buffer when the custom event triggers.
+	 *
+	 * The rest is just like the TRACE_EVENT() macro except that
+	 * it uses the custom entry.
+	 */
+	TP_STRUCT__entry(
+		__field(	unsigned short,		prev_prio	)
+		__field(	unsigned short,		next_prio	)
+		__field(	pid_t,	next_pid			)
+	),
+
+	TP_fast_assign(
+		__entry->prev_prio	= prev->prio;
+		__entry->next_pid	= next->pid;
+		__entry->next_prio	= next->prio;
+	),
+
+	TP_printk("prev_prio=%d next_pid=%d next_prio=%d",
+		  __entry->prev_prio, __entry->next_pid, __entry->next_prio)
+)
+
+
+TRACE_CUSTOM_EVENT(sched_waking,
+
+	TP_PROTO(struct task_struct *p),
+
+	TP_ARGS(p),
+
+	TP_STRUCT__entry(
+		__field(	pid_t,			pid	)
+		__field(	unsigned short,		prio	)
+	),
+
+	TP_fast_assign(
+		__entry->pid	= p->pid;
+		__entry->prio	= p->prio;
+	),
+
+	TP_printk("pid=%d prio=%d", __entry->pid, __entry->prio)
+)
+#endif
+/*
+ * Just like the headers that create TRACE_EVENTs, the below must
+ * be outside the protection of the above #if block.
+ */
+
+/*
+ * It is required that the Makefile includes:
+ *    CFLAGS_<c_file>.o := -I$(src)
+ */
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+
+/*
+ * It is requred that the TRACE_INCLUDE_FILE be the same
+ * as this file without the ".h".
+ */
+#define TRACE_INCLUDE_FILE trace_custom_sched
+#include <trace/define_custom_trace.h>
diff --git a/samples/user_events/Makefile b/samples/user_events/Makefile
new file mode 100644
index 000000000000..7252b589db57
--- /dev/null
+++ b/samples/user_events/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wl,-no-as-needed -Wall -I../../usr/include
+
+example: example.o
+example.o: example.c
diff --git a/samples/user_events/example.c b/samples/user_events/example.c
new file mode 100644
index 000000000000..4f5778e441c0
--- /dev/null
+++ b/samples/user_events/example.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Beau Belgrave <beaub@linux.microsoft.com>
+ */
+
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/user_events.h>
+
+/* Assumes debugfs is mounted */
+const char *data_file = "/sys/kernel/debug/tracing/user_events_data";
+const char *status_file = "/sys/kernel/debug/tracing/user_events_status";
+
+static int event_status(char **status)
+{
+	int fd = open(status_file, O_RDONLY);
+
+	*status = mmap(NULL, sysconf(_SC_PAGESIZE), PROT_READ,
+		       MAP_SHARED, fd, 0);
+
+	close(fd);
+
+	if (*status == MAP_FAILED)
+		return -1;
+
+	return 0;
+}
+
+static int event_reg(int fd, const char *command, int *status, int *write)
+{
+	struct user_reg reg = {0};
+
+	reg.size = sizeof(reg);
+	reg.name_args = (__u64)command;
+
+	if (ioctl(fd, DIAG_IOCSREG, &reg) == -1)
+		return -1;
+
+	*status = reg.status_index;
+	*write = reg.write_index;
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	int data_fd, status, write;
+	char *status_page;
+	struct iovec io[2];
+	__u32 count = 0;
+
+	if (event_status(&status_page) == -1)
+		return errno;
+
+	data_fd = open(data_file, O_RDWR);
+
+	if (event_reg(data_fd, "test u32 count", &status, &write) == -1)
+		return errno;
+
+	/* Setup iovec */
+	io[0].iov_base = &write;
+	io[0].iov_len = sizeof(write);
+	io[1].iov_base = &count;
+	io[1].iov_len = sizeof(count);
+
+ask:
+	printf("Press enter to check status...\n");
+	getchar();
+
+	/* Check if anyone is listening */
+	if (status_page[status]) {
+		/* Yep, trace out our data */
+		writev(data_fd, (const struct iovec *)io, 2);
+
+		/* Increase the count */
+		count++;
+
+		printf("Something was attached, wrote data\n");
+	}
+
+	goto ask;
+
+	return 0;
+}