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
  ...

kernel/trace/Kconfig

@@ -737,6 +737,20 @@ config SYNTH_EVENTS
 
 	  If in doubt, say N.
 
+config USER_EVENTS
+	bool "User trace events"
+	select TRACING
+	select DYNAMIC_EVENTS
+	help
+	  User trace events are user-defined trace events that
+	  can be used like an existing kernel trace event.  User trace
+	  events are generated by writing to a tracefs file.  User
+	  processes can determine if their tracing events should be
+	  generated by memory mapping a tracefs file and checking for
+	  an associated byte being non-zero.
+
+	  If in doubt, say N.
+
 config HIST_TRIGGERS
 	bool "Histogram triggers"
 	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG

kernel/trace/Makefile

@@ -82,6 +82,7 @@ obj-$(CONFIG_PROBE_EVENTS) += trace_eprobe.o
 obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o
 obj-$(CONFIG_SYNTH_EVENTS) += trace_events_synth.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
+obj-$(CONFIG_USER_EVENTS) += trace_events_user.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += error_report-traces.o

kernel/trace/ftrace.c

@@ -7096,6 +7096,8 @@ void __init ftrace_free_init_mem(void)
 	void *start = (void *)(&__init_begin);
 	void *end = (void *)(&__init_end);
 
+	ftrace_boot_snapshot();
+
 	ftrace_free_mem(NULL, start, end);
 }
 

kernel/trace/trace.c

@@ -185,6 +185,7 @@ static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
 static char *default_bootup_tracer;
 
 static bool allocate_snapshot;
+static bool snapshot_at_boot;
 
 static int __init set_cmdline_ftrace(char *str)
 {
@@ -230,6 +231,15 @@ static int __init boot_alloc_snapshot(char *str)
 __setup("alloc_snapshot", boot_alloc_snapshot);
 
 
+static int __init boot_snapshot(char *str)
+{
+	snapshot_at_boot = true;
+	boot_alloc_snapshot(str);
+	return 1;
+}
+__setup("ftrace_boot_snapshot", boot_snapshot);
+
+
 static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
 
 static int __init set_trace_boot_options(char *str)
@@ -7725,7 +7735,7 @@ const struct file_operations trace_min_max_fops = {
 struct err_info {
 	const char	**errs;	/* ptr to loc-specific array of err strings */
 	u8		type;	/* index into errs -> specific err string */
-	u8		pos;	/* MAX_FILTER_STR_VAL = 256 */
+	u16		pos;	/* caret position */
 	u64		ts;
 };
 
@@ -7733,26 +7743,52 @@ struct tracing_log_err {
 	struct list_head	list;
 	struct err_info		info;
 	char			loc[TRACING_LOG_LOC_MAX]; /* err location */
-	char			cmd[MAX_FILTER_STR_VAL]; /* what caused err */
+	char			*cmd;                     /* what caused err */
 };
 
 static DEFINE_MUTEX(tracing_err_log_lock);
 
-static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr)
+static struct tracing_log_err *alloc_tracing_log_err(int len)
+{
+	struct tracing_log_err *err;
+
+	err = kzalloc(sizeof(*err), GFP_KERNEL);
+	if (!err)
+		return ERR_PTR(-ENOMEM);
+
+	err->cmd = kzalloc(len, GFP_KERNEL);
+	if (!err->cmd) {
+		kfree(err);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return err;
+}
+
+static void free_tracing_log_err(struct tracing_log_err *err)
+{
+	kfree(err->cmd);
+	kfree(err);
+}
+
+static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr,
+						   int len)
 {
 	struct tracing_log_err *err;
 
 	if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) {
-		err = kzalloc(sizeof(*err), GFP_KERNEL);
-		if (!err)
-			err = ERR_PTR(-ENOMEM);
-		else
+		err = alloc_tracing_log_err(len);
+		if (PTR_ERR(err) != -ENOMEM)
 			tr->n_err_log_entries++;
 
 		return err;
 	}
 
 	err = list_first_entry(&tr->err_log, struct tracing_log_err, list);
+	kfree(err->cmd);
+	err->cmd = kzalloc(len, GFP_KERNEL);
+	if (!err->cmd)
+		return ERR_PTR(-ENOMEM);
 	list_del(&err->list);
 
 	return err;
@@ -7813,22 +7849,25 @@ unsigned int err_pos(char *cmd, const char *str)
  */
 void tracing_log_err(struct trace_array *tr,
 		     const char *loc, const char *cmd,
-		     const char **errs, u8 type, u8 pos)
+		     const char **errs, u8 type, u16 pos)
 {
 	struct tracing_log_err *err;
+	int len = 0;
 
 	if (!tr)
 		tr = &global_trace;
 
+	len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1;
+
 	mutex_lock(&tracing_err_log_lock);
-	err = get_tracing_log_err(tr);
+	err = get_tracing_log_err(tr, len);
 	if (PTR_ERR(err) == -ENOMEM) {
 		mutex_unlock(&tracing_err_log_lock);
 		return;
 	}
 
 	snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc);
-	snprintf(err->cmd, MAX_FILTER_STR_VAL,"\n" CMD_PREFIX "%s\n", cmd);
+	snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd);
 
 	err->info.errs = errs;
 	err->info.type = type;
@@ -7846,7 +7885,7 @@ static void clear_tracing_err_log(struct trace_array *tr)
 	mutex_lock(&tracing_err_log_lock);
 	list_for_each_entry_safe(err, next, &tr->err_log, list) {
 		list_del(&err->list);
-		kfree(err);
+		free_tracing_log_err(err);
 	}
 
 	tr->n_err_log_entries = 0;
@@ -7874,9 +7913,9 @@ static void tracing_err_log_seq_stop(struct seq_file *m, void *v)
 	mutex_unlock(&tracing_err_log_lock);
 }
 
-static void tracing_err_log_show_pos(struct seq_file *m, u8 pos)
+static void tracing_err_log_show_pos(struct seq_file *m, u16 pos)
 {
-	u8 i;
+	u16 i;
 
 	for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++)
 		seq_putc(m, ' ');
@@ -10122,6 +10161,14 @@ out:
 	return ret;
 }
 
+void __init ftrace_boot_snapshot(void)
+{
+	if (snapshot_at_boot) {
+		tracing_snapshot();
+		internal_trace_puts("** Boot snapshot taken **\n");
+	}
+}
+
 void __init early_trace_init(void)
 {
 	if (tracepoint_printk) {

kernel/trace/trace.h

@@ -1877,7 +1877,7 @@ extern ssize_t trace_parse_run_command(struct file *file,
 extern unsigned int err_pos(char *cmd, const char *str);
 extern void tracing_log_err(struct trace_array *tr,
 			    const char *loc, const char *cmd,
-			    const char **errs, u8 type, u8 pos);
+			    const char **errs, u8 type, u16 pos);
 
 /*
  * Normal trace_printk() and friends allocates special buffers

kernel/trace/trace_events.c

@@ -40,6 +40,14 @@ static LIST_HEAD(ftrace_generic_fields);
 static LIST_HEAD(ftrace_common_fields);
 static bool eventdir_initialized;
 
+static LIST_HEAD(module_strings);
+
+struct module_string {
+	struct list_head	next;
+	struct module		*module;
+	char			*str;
+};
+
 #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
 
 static struct kmem_cache *field_cachep;
@@ -2643,6 +2651,76 @@ static void update_event_printk(struct trace_event_call *call,
 	}
 }
 
+static void add_str_to_module(struct module *module, char *str)
+{
+	struct module_string *modstr;
+
+	modstr = kmalloc(sizeof(*modstr), GFP_KERNEL);
+
+	/*
+	 * If we failed to allocate memory here, then we'll just
+	 * let the str memory leak when the module is removed.
+	 * If this fails to allocate, there's worse problems than
+	 * a leaked string on module removal.
+	 */
+	if (WARN_ON_ONCE(!modstr))
+		return;
+
+	modstr->module = module;
+	modstr->str = str;
+
+	list_add(&modstr->next, &module_strings);
+}
+
+static void update_event_fields(struct trace_event_call *call,
+				struct trace_eval_map *map)
+{
+	struct ftrace_event_field *field;
+	struct list_head *head;
+	char *ptr;
+	char *str;
+	int len = strlen(map->eval_string);
+
+	/* Dynamic events should never have field maps */
+	if (WARN_ON_ONCE(call->flags & TRACE_EVENT_FL_DYNAMIC))
+		return;
+
+	head = trace_get_fields(call);
+	list_for_each_entry(field, head, link) {
+		ptr = strchr(field->type, '[');
+		if (!ptr)
+			continue;
+		ptr++;
+
+		if (!isalpha(*ptr) && *ptr != '_')
+			continue;
+
+		if (strncmp(map->eval_string, ptr, len) != 0)
+			continue;
+
+		str = kstrdup(field->type, GFP_KERNEL);
+		if (WARN_ON_ONCE(!str))
+			return;
+		ptr = str + (ptr - field->type);
+		ptr = eval_replace(ptr, map, len);
+		/* enum/sizeof string smaller than value */
+		if (WARN_ON_ONCE(!ptr)) {
+			kfree(str);
+			continue;
+		}
+
+		/*
+		 * If the event is part of a module, then we need to free the string
+		 * when the module is removed. Otherwise, it will stay allocated
+		 * until a reboot.
+		 */
+		if (call->module)
+			add_str_to_module(call->module, str);
+
+		field->type = str;
+	}
+}
+
 void trace_event_eval_update(struct trace_eval_map **map, int len)
 {
 	struct trace_event_call *call, *p;
@@ -2678,6 +2756,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 					first = false;
 				}
 				update_event_printk(call, map[i]);
+				update_event_fields(call, map[i]);
 			}
 		}
 	}
@@ -2768,6 +2847,7 @@ int trace_add_event_call(struct trace_event_call *call)
 	mutex_unlock(&trace_types_lock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(trace_add_event_call);
 
 /*
  * Must be called under locking of trace_types_lock, event_mutex and
@@ -2829,6 +2909,7 @@ int trace_remove_event_call(struct trace_event_call *call)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(trace_remove_event_call);
 
 #define for_each_event(event, start, end)			\
 	for (event = start;					\
@@ -2863,6 +2944,7 @@ static void trace_module_add_events(struct module *mod)
 static void trace_module_remove_events(struct module *mod)
 {
 	struct trace_event_call *call, *p;
+	struct module_string *modstr, *m;
 
 	down_write(&trace_event_sem);
 	list_for_each_entry_safe(call, p, &ftrace_events, list) {
@@ -2871,6 +2953,14 @@ static void trace_module_remove_events(struct module *mod)
 		if (call->module == mod)
 			__trace_remove_event_call(call);
 	}
+	/* Check for any strings allocade for this module */
+	list_for_each_entry_safe(modstr, m, &module_strings, next) {
+		if (modstr->module != mod)
+			continue;
+		list_del(&modstr->next);
+		kfree(modstr->str);
+		kfree(modstr);
+	}
 	up_write(&trace_event_sem);
 
 	/*

kernel/trace/trace_events_hist.c

@@ -727,11 +727,16 @@ static struct track_data *track_data_alloc(unsigned int key_len,
 	return data;
 }
 
-static char last_cmd[MAX_FILTER_STR_VAL];
+#define HIST_PREFIX "hist:"
+
+static char *last_cmd;
 static char last_cmd_loc[MAX_FILTER_STR_VAL];
 
 static int errpos(char *str)
 {
+	if (!str || !last_cmd)
+		return 0;
+
 	return err_pos(last_cmd, str);
 }
 
@@ -739,12 +744,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 {
 	const char *system = NULL, *name = NULL;
 	struct trace_event_call *call;
+	int len;
 
 	if (!str)
 		return;
 
-	strcpy(last_cmd, "hist:");
-	strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:"));
+	/* sizeof() contains the nul byte */
+	len = sizeof(HIST_PREFIX) + strlen(str);
+	kfree(last_cmd);
+	last_cmd = kzalloc(len, GFP_KERNEL);
+	if (!last_cmd)
+		return;
+
+	strcpy(last_cmd, HIST_PREFIX);
+	/* Again, sizeof() contains the nul byte */
+	len -= sizeof(HIST_PREFIX);
+	strncat(last_cmd, str, len);
 
 	if (file) {
 		call = file->event_call;
@@ -757,18 +772,22 @@ static void last_cmd_set(struct trace_event_file *file, char *str)
 	}
 
 	if (system)
-		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, "hist:%s:%s", system, name);
+		snprintf(last_cmd_loc, MAX_FILTER_STR_VAL, HIST_PREFIX "%s:%s", system, name);
 }
 
-static void hist_err(struct trace_array *tr, u8 err_type, u8 err_pos)
+static void hist_err(struct trace_array *tr, u8 err_type, u16 err_pos)
 {
+	if (!last_cmd)
+		return;
+
 	tracing_log_err(tr, last_cmd_loc, last_cmd, err_text,
 			err_type, err_pos);
 }
 
 static void hist_err_clear(void)
 {
-	last_cmd[0] = '\0';
+	if (last_cmd)
+		last_cmd[0] = '\0';
 	last_cmd_loc[0] = '\0';
 }
 
@@ -5610,7 +5629,7 @@ static int event_hist_trigger_print(struct seq_file *m,
 	bool have_var = false;
 	unsigned int i;
 
-	seq_puts(m, "hist:");
+	seq_puts(m, HIST_PREFIX);
 
 	if (data->name)
 		seq_printf(m, "%s:", data->name);

kernel/trace/trace_events_synth.c

@@ -42,10 +42,13 @@ enum { ERRORS };
 
 static const char *err_text[] = { ERRORS };
 
-static char last_cmd[MAX_FILTER_STR_VAL];
+static char *last_cmd;
 
 static int errpos(const char *str)
 {
+	if (!str || !last_cmd)
+		return 0;
+
 	return err_pos(last_cmd, str);
 }
 
@@ -54,11 +57,16 @@ static void last_cmd_set(const char *str)
 	if (!str)
 		return;
 
-	strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1);
+	kfree(last_cmd);
+
+	last_cmd = kstrdup(str, GFP_KERNEL);
 }
 
-static void synth_err(u8 err_type, u8 err_pos)
+static void synth_err(u8 err_type, u16 err_pos)
 {
+	if (!last_cmd)
+		return;
+
 	tracing_log_err(NULL, "synthetic_events", last_cmd, err_text,
 			err_type, err_pos);
 }

kernel/trace/trace_sched_switch.c

@@ -45,7 +45,7 @@ probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 
 	if (!flags)
 		return;
-	tracing_record_taskinfo(current, flags);
+	tracing_record_taskinfo_sched_switch(current, wakee, flags);
 }
 
 static int tracing_sched_register(void)