Merge branch 'trace/for-next-rtla' into trace/for-next

Documentation/tools/rtla/common_hist_options.rst

@@ -2,7 +2,7 @@
 
         Set the histogram bucket size (default *1*).
 
-**-e**, **--entries** *N*
+**-E**, **--entries** *N*
 
         Set the number of entries of the histogram (default 256).
 

Documentation/tools/rtla/common_options.rst

@@ -14,6 +14,25 @@
 
         Save the stopped trace to [*file|osnoise_trace.txt*].
 
+**-e**, **--event** *sys:event*
+
+        Enable an event in the trace (**-t**) session. The argument can be a specific event, e.g., **-e** *sched:sched_switch*, or all events of a system group, e.g., **-e** *sched*. Multiple **-e** are allowed. It is only active when **-t** or **-a** are set.
+
+**--filter** *<filter>*
+
+        Filter the previous **-e** *sys:event* event with *<filter>*. For further information about event filtering see https://www.kernel.org/doc/html/latest/trace/events.html#event-filtering.
+
+**--trigger** *<trigger>*
+        Enable a trace event trigger to the previous **-e** *sys:event*.
+        If the *hist:* trigger is activated, the output histogram will be automatically saved to a file named *system_event_hist.txt*.
+        For example, the command:
+
+        rtla <command> <mode> -t -e osnoise:irq_noise --trigger="hist:key=desc,duration/1000:sort=desc,duration/1000:vals=hitcount"
+
+        Will automatically save the content of the histogram associated to *osnoise:irq_noise* event in *osnoise_irq_noise_hist.txt*.
+
+        For further information about event trigger see https://www.kernel.org/doc/html/latest/trace/events.html#event-triggers.
+
 **-P**, **--priority** *o:prio|r:prio|f:prio|d:runtime:period*
 
         Set scheduling parameters to the osnoise tracer threads, the format to set the priority are:

Documentation/tools/rtla/common_osnoise_description.rst

@@ -1,7 +1,7 @@
 The **rtla osnoise** tool is an interface for the *osnoise* tracer. The
 *osnoise* tracer dispatches a kernel thread per-cpu. These threads read the
 time in a loop while with preemption, softirq and IRQs enabled, thus
-allowing all the sources of operating systme noise during its execution.
+allowing all the sources of operating system noise during its execution.
 The *osnoise*'s tracer threads take note of the delta between each time
 read, along with an interference counter of all sources of interference.
 At the end of each period, the *osnoise* tracer displays a summary of

Documentation/tools/rtla/common_osnoise_options.rst

@@ -1,3 +1,8 @@
+**-a**, **--auto** *us*
+
+        Set the automatic trace mode. This mode sets some commonly used options
+        while debugging the system. It is equivalent to use **-s** *us* **-T 1 -t**.
+
 **-p**, **--period** *us*
 
         Set the *osnoise* tracer period in microseconds.
@@ -15,3 +20,8 @@
 
         Stop the trace if the total sample is higher than the argument in microseconds.
         If **-T** is set, it will also save the trace to the output.
+
+**-T**, **--threshold** *us*
+
+        Specify the minimum delta between two time reads to be considered noise.
+        The default threshold is *5 us*.

Documentation/tools/rtla/common_timerlat_options.rst

@@ -1,3 +1,10 @@
+**-a**, **--auto** *us*
+
+        Set the automatic trace mode. This mode sets some commonly used options
+        while debugging the system. It is equivalent to use **-T** *us* **-s** *us*
+        **-t**. By default, *timerlat* tracer uses FIFO:95 for *timerlat* threads,
+        thus equilavent to **-P** *f:95*.
+
 **-p**, **--period** *us*
 
         Set the *timerlat* tracer period in microseconds.
@@ -14,3 +21,8 @@
 
         Save the stack trace at the *IRQ* if a *Thread* latency is higher than the
         argument in us.
+
+**--dma-latency** *us*
+        Set the /dev/cpu_dma_latency to *us*, aiming to bound exit from idle latencies.
+        *cyclictest* sets this value to *0* by default, use **--dma-latency** *0* to have
+        similar results.

Documentation/tools/rtla/rtla-osnoise-hist.rst

@@ -36,7 +36,7 @@ default). The reason for reducing the runtime is to avoid starving the
 **rtla** tool. The tool is also set to run for *one minute*. The output
 histogram is set to group outputs in buckets of *10us* and *25* entries::
 
-  [root@f34 ~/]# rtla osnoise hist -P F:1 -c 0-11 -r 900000 -d 1M -b 10 -e 25
+  [root@f34 ~/]# rtla osnoise hist -P F:1 -c 0-11 -r 900000 -d 1M -b 10 -E 25
   # RTLA osnoise histogram
   # Time unit is microseconds (us)
   # Duration:   0 00:01:00

fs/tracefs/inode.c

@@ -264,7 +264,6 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 			if (!gid_valid(gid))
 				return -EINVAL;
 			opts->gid = gid;
-			set_gid(tracefs_mount->mnt_root, gid);
 			break;
 		case Opt_mode:
 			if (match_octal(&args[0], &option))
@@ -291,7 +290,9 @@ static int tracefs_apply_options(struct super_block *sb)
 	inode->i_mode |= opts->mode;
 
 	inode->i_uid = opts->uid;
-	inode->i_gid = opts->gid;
+
+	/* Set all the group ids to the mount option */
+	set_gid(sb->s_root, opts->gid);
 
 	return 0;
 }

include/linux/trace_events.h

@@ -706,6 +706,8 @@ event_triggers_post_call(struct trace_event_file *file,
 
 bool trace_event_ignore_this_pid(struct trace_event_file *trace_file);
 
+bool __trace_trigger_soft_disabled(struct trace_event_file *file);
+
 /**
  * trace_trigger_soft_disabled - do triggers and test if soft disabled
  * @file: The file pointer of the event to test
@@ -715,20 +717,20 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file);
  * triggers that require testing the fields, it will return true,
  * otherwise false.
  */
-static inline bool
+static __always_inline bool
 trace_trigger_soft_disabled(struct trace_event_file *file)
 {
 	unsigned long eflags = file->flags;
 
-	if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) {
-		if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
-			event_triggers_call(file, NULL, NULL, NULL);
-		if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
-			return true;
-		if (eflags & EVENT_FILE_FL_PID_FILTER)
-			return trace_event_ignore_this_pid(file);
-	}
-	return false;
+	if (likely(!(eflags & (EVENT_FILE_FL_TRIGGER_MODE |
+			       EVENT_FILE_FL_SOFT_DISABLED |
+			       EVENT_FILE_FL_PID_FILTER))))
+		return false;
+
+	if (likely(eflags & EVENT_FILE_FL_TRIGGER_COND))
+		return false;
+
+	return __trace_trigger_soft_disabled(file);
 }
 
 #ifdef CONFIG_BPF_EVENTS

kernel/trace/ftrace.c

@@ -7193,7 +7193,6 @@ static int __init ftrace_nodyn_init(void)
 core_initcall(ftrace_nodyn_init);
 
 static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; }
-static inline void ftrace_startup_enable(int command) { }
 static inline void ftrace_startup_all(int command) { }
 
 # define ftrace_startup_sysctl()	do { } while (0)
@@ -7793,7 +7792,7 @@ int ftrace_is_dead(void)
 
 /**
  * register_ftrace_function - register a function for profiling
- * @ops - ops structure that holds the function for profiling.
+ * @ops:	ops structure that holds the function for profiling.
  *
  * Register a function to be called by all functions in the
  * kernel.
@@ -7820,7 +7819,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_function);
 
 /**
  * unregister_ftrace_function - unregister a function for profiling.
- * @ops - ops structure that holds the function to unregister
+ * @ops:	ops structure that holds the function to unregister
  *
  * Unregister a function that was added to be called by ftrace profiling.
  */

kernel/trace/trace.c

@@ -245,7 +245,7 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata;
 static int __init set_trace_boot_options(char *str)
 {
 	strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE);
-	return 0;
+	return 1;
 }
 __setup("trace_options=", set_trace_boot_options);
 
@@ -256,7 +256,7 @@ static int __init set_trace_boot_clock(char *str)
 {
 	strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE);
 	trace_boot_clock = trace_boot_clock_buf;
-	return 0;
+	return 1;
 }
 __setup("trace_clock=", set_trace_boot_clock);
 
@@ -1484,10 +1484,12 @@ static int __init set_buf_size(char *str)
 	if (!str)
 		return 0;
 	buf_size = memparse(str, &str);
-	/* nr_entries can not be zero */
-	if (buf_size == 0)
-		return 0;
-	trace_buf_size = buf_size;
+	/*
+	 * nr_entries can not be zero and the startup
+	 * tests require some buffer space. Therefore
+	 * ensure we have at least 4096 bytes of buffer.
+	 */
+	trace_buf_size = max(4096UL, buf_size);
 	return 1;
 }
 __setup("trace_buf_size=", set_buf_size);

kernel/trace/trace.h

@@ -136,7 +136,6 @@ struct kprobe_trace_entry_head {
 
 struct eprobe_trace_entry_head {
 	struct trace_entry	ent;
-	unsigned int		type;
 };
 
 struct kretprobe_trace_entry_head {

kernel/trace/trace_eprobe.c

@@ -242,16 +242,13 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i)
 
 static int eprobe_event_define_fields(struct trace_event_call *event_call)
 {
-	int ret;
 	struct eprobe_trace_entry_head field;
 	struct trace_probe *tp;
 
 	tp = trace_probe_primary_from_call(event_call);
 	if (WARN_ON_ONCE(!tp))
 		return -ENOENT;
 
-	DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0);
-
 	return traceprobe_define_arg_fields(event_call, sizeof(field), tp);
 }
 
@@ -270,23 +267,28 @@ print_eprobe_event(struct trace_iterator *iter, int flags,
 	struct trace_event_call *pevent;
 	struct trace_event *probed_event;
 	struct trace_seq *s = &iter->seq;
+	struct trace_eprobe *ep;
 	struct trace_probe *tp;
+	unsigned int type;
 
 	field = (struct eprobe_trace_entry_head *)iter->ent;
 	tp = trace_probe_primary_from_call(
 		container_of(event, struct trace_event_call, event));
 	if (WARN_ON_ONCE(!tp))
 		goto out;
 
+	ep = container_of(tp, struct trace_eprobe, tp);
+	type = ep->event->event.type;
+
 	trace_seq_printf(s, "%s: (", trace_probe_name(tp));
 
-	probed_event = ftrace_find_event(field->type);
+	probed_event = ftrace_find_event(type);
 	if (probed_event) {
 		pevent = container_of(probed_event, struct trace_event_call, event);
 		trace_seq_printf(s, "%s.%s", pevent->class->system,
 				 trace_event_name(pevent));
 	} else {
-		trace_seq_printf(s, "%u", field->type);
+		trace_seq_printf(s, "%u", type);
 	}
 
 	trace_seq_putc(s, ')');
@@ -498,10 +500,6 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
 		return;
 
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
-	if (edata->ep->event)
-		entry->type = edata->ep->event->event.type;
-	else
-		entry->type = 0;
 	store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);

kernel/trace/trace_events_hist.c

@@ -2308,9 +2308,9 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
 			/*
 			 * For backward compatibility, if field_name
 			 * was "cpu", then we treat this the same as
-			 * common_cpu.
+			 * common_cpu. This also works for "CPU".
 			 */
-			if (strcmp(field_name, "cpu") == 0) {
+			if (field && field->filter_type == FILTER_CPU) {
 				*flags |= HIST_FIELD_FL_CPU;
 			} else {
 				hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
@@ -4851,7 +4851,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data)
 
 			if (hist_field->flags & HIST_FIELD_FL_STACKTRACE)
 				cmp_fn = tracing_map_cmp_none;
-			else if (!field)
+			else if (!field || hist_field->flags & HIST_FIELD_FL_CPU)
 				cmp_fn = tracing_map_cmp_num(hist_field->size,
 							     hist_field->is_signed);
 			else if (is_string_field(field))