Merge tag 'trace-v5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "New tracing features:

   - The ring buffer is no longer disabled when reading the trace file.

     The trace_pipe file was made to be used for live tracing and
     reading as it acted like the normal producer/consumer. As the trace
     file would not consume the data, the easy way of handling it was to
     just disable writes to the ring buffer.

     This came to a surprise to the BPF folks who complained about lost
     events due to reading. This is no longer an issue. If someone wants
     to keep the old disabling there's a new option "pause-on-trace"
     that can be set.

   - New set_ftrace_notrace_pid file. PIDs in this file will not be
     traced by the function tracer.

     Similar to set_ftrace_pid, which makes the function tracer only
     trace those tasks with PIDs in the file, the set_ftrace_notrace_pid
     does the reverse.

   - New set_event_notrace_pid file. PIDs in this file will cause events
     not to be traced if triggered by a task with a matching PID.

     Similar to the set_event_pid file but will not be traced. Note,
     sched_waking and sched_switch events may still be traced if one of
     the tasks referenced by those events contains a PID that is allowed
     to be traced.

  Tracing related features:

   - New bootconfig option, that is attached to the initrd file.

     If bootconfig is on the command line, then the initrd file is
     searched looking for a bootconfig appended at the end.

   - New GPU tracepoint infrastructure to help the gfx drivers to get
     off debugfs (acked by Greg Kroah-Hartman)

  And other minor updates and fixes"

* tag 'trace-v5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (27 commits)
  tracing: Do not allocate buffer in trace_find_next_entry() in atomic
  tracing: Add documentation on set_ftrace_notrace_pid and set_event_notrace_pid
  selftests/ftrace: Add test to test new set_event_notrace_pid file
  selftests/ftrace: Add test to test new set_ftrace_notrace_pid file
  tracing: Create set_event_notrace_pid to not trace tasks
  ftrace: Create set_ftrace_notrace_pid to not trace tasks
  ftrace: Make function trace pid filtering a bit more exact
  ftrace/kprobe: Show the maxactive number on kprobe_events
  tracing: Have the document reflect that the trace file keeps tracing enabled
  ring-buffer/tracing: Have iterator acknowledge dropped events
  tracing: Do not disable tracing when reading the trace file
  ring-buffer: Do not disable recording when there is an iterator
  ring-buffer: Make resize disable per cpu buffer instead of total buffer
  ring-buffer: Optimize rb_iter_head_event()
  ring-buffer: Do not die if rb_iter_peek() fails more than thrice
  ring-buffer: Have rb_iter_head_event() handle concurrent writer
  ring-buffer: Add page_stamp to iterator for synchronization
  ring-buffer: Rename ring_buffer_read() to read_buffer_iter_advance()
  ring-buffer: Have ring_buffer_empty() not depend on tracing stopped
  tracing: Save off entry when peeking at next entry
  ...

1 files changed, 93 insertions, 17 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6b11e4e2150c..8d2b98812625 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -386,16 +386,22 @@ trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
  * Returns false if @task should be traced.
  */
 bool
-trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
+trace_ignore_this_task(struct trace_pid_list *filtered_pids,
+		       struct trace_pid_list *filtered_no_pids,
+		       struct task_struct *task)
 {
 	/*
-	 * Return false, because if filtered_pids does not exist,
-	 * all pids are good to trace.
+	 * If filterd_no_pids is not empty, and the task's pid is listed
+	 * in filtered_no_pids, then return true.
+	 * Otherwise, if filtered_pids is empty, that means we can
+	 * trace all tasks. If it has content, then only trace pids
+	 * within filtered_pids.
 	 */
-	if (!filtered_pids)
-		return false;
 
-	return !trace_find_filtered_pid(filtered_pids, task->pid);
+	return (filtered_pids &&
+		!trace_find_filtered_pid(filtered_pids, task->pid)) ||
+		(filtered_no_pids &&
+		 trace_find_filtered_pid(filtered_no_pids, task->pid));
 }
 
 /**
@@ -3378,7 +3384,7 @@ static void trace_iterator_increment(struct trace_iterator *iter)
 
 	iter->idx++;
 	if (buf_iter)
-		ring_buffer_read(buf_iter, NULL);
+		ring_buffer_iter_advance(buf_iter);
 }
 
 static struct trace_entry *
@@ -3388,11 +3394,15 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu);
 
-	if (buf_iter)
+	if (buf_iter) {
 		event = ring_buffer_iter_peek(buf_iter, ts);
-	else
+		if (lost_events)
+			*lost_events = ring_buffer_iter_dropped(buf_iter) ?
+				(unsigned long)-1 : 0;
+	} else {
 		event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts,
 					 lost_events);
+	}
 
 	if (event) {
 		iter->ent_size = ring_buffer_event_length(event);
@@ -3462,11 +3472,51 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
 	return next;
 }
 
+#define STATIC_TEMP_BUF_SIZE	128
+static char static_temp_buf[STATIC_TEMP_BUF_SIZE];
+
 /* Find the next real entry, without updating the iterator itself */
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts)
 {
-	return __find_next_entry(iter, ent_cpu, NULL, ent_ts);
+	/* __find_next_entry will reset ent_size */
+	int ent_size = iter->ent_size;
+	struct trace_entry *entry;
+
+	/*
+	 * If called from ftrace_dump(), then the iter->temp buffer
+	 * will be the static_temp_buf and not created from kmalloc.
+	 * If the entry size is greater than the buffer, we can
+	 * not save it. Just return NULL in that case. This is only
+	 * used to add markers when two consecutive events' time
+	 * stamps have a large delta. See trace_print_lat_context()
+	 */
+	if (iter->temp == static_temp_buf &&
+	    STATIC_TEMP_BUF_SIZE < ent_size)
+		return NULL;
+
+	/*
+	 * The __find_next_entry() may call peek_next_entry(), which may
+	 * call ring_buffer_peek() that may make the contents of iter->ent
+	 * undefined. Need to copy iter->ent now.
+	 */
+	if (iter->ent && iter->ent != iter->temp) {
+		if ((!iter->temp || iter->temp_size < iter->ent_size) &&
+		    !WARN_ON_ONCE(iter->temp == static_temp_buf)) {
+			kfree(iter->temp);
+			iter->temp = kmalloc(iter->ent_size, GFP_KERNEL);
+			if (!iter->temp)
+				return NULL;
+		}
+		memcpy(iter->temp, iter->ent, iter->ent_size);
+		iter->temp_size = iter->ent_size;
+		iter->ent = iter->temp;
+	}
+	entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts);
+	/* Put back the original ent_size */
+	iter->ent_size = ent_size;
+
+	return entry;
 }
 
 /* Find the next real entry, and increment the iterator to the next entry */
@@ -3538,7 +3588,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 		if (ts >= iter->array_buffer->time_start)
 			break;
 		entries++;
-		ring_buffer_read(buf_iter, NULL);
+		ring_buffer_iter_advance(buf_iter);
 	}
 
 	per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries;
@@ -3981,8 +4031,12 @@ enum print_line_t print_trace_line(struct trace_iterator *iter)
 	enum print_line_t ret;
 
 	if (iter->lost_events) {
-		trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
-				 iter->cpu, iter->lost_events);
+		if (iter->lost_events == (unsigned long)-1)
+			trace_seq_printf(&iter->seq, "CPU:%d [LOST EVENTS]\n",
+					 iter->cpu);
+		else
+			trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n",
+					 iter->cpu, iter->lost_events);
 		if (trace_seq_has_overflowed(&iter->seq))
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
@@ -4198,6 +4252,18 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 		goto release;
 
 	/*
+	 * trace_find_next_entry() may need to save off iter->ent.
+	 * It will place it into the iter->temp buffer. As most
+	 * events are less than 128, allocate a buffer of that size.
+	 * If one is greater, then trace_find_next_entry() will
+	 * allocate a new buffer to adjust for the bigger iter->ent.
+	 * It's not critical if it fails to get allocated here.
+	 */
+	iter->temp = kmalloc(128, GFP_KERNEL);
+	if (iter->temp)
+		iter->temp_size = 128;
+
+	/*
 	 * We make a copy of the current tracer to avoid concurrent
 	 * changes on it while we are reading.
 	 */
@@ -4237,8 +4303,11 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (trace_clocks[tr->clock_id].in_ns)
 		iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
 
-	/* stop the trace while dumping if we are not opening "snapshot" */
-	if (!iter->snapshot)
+	/*
+	 * If pause-on-trace is enabled, then stop the trace while
+	 * dumping, unless this is the "snapshot" file
+	 */
+	if (!iter->snapshot && (tr->trace_flags & TRACE_ITER_PAUSE_ON_TRACE))
 		tracing_stop_tr(tr);
 
 	if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
@@ -4269,6 +4338,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
+	kfree(iter->temp);
 	kfree(iter->buffer_iter);
 release:
 	seq_release_private(inode, file);
@@ -4334,7 +4404,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 	if (iter->trace && iter->trace->close)
 		iter->trace->close(iter);
 
-	if (!iter->snapshot)
+	if (!iter->snapshot && tr->stop_count)
 		/* reenable tracing if it was previously enabled */
 		tracing_start_tr(tr);
 
@@ -4344,6 +4414,7 @@ static int tracing_release(struct inode *inode, struct file *file)
 
 	mutex_destroy(&iter->mutex);
 	free_cpumask_var(iter->started);
+	kfree(iter->temp);
 	kfree(iter->trace);
 	kfree(iter->buffer_iter);
 	seq_release_private(inode, file);
@@ -4964,6 +5035,8 @@ static const char readme_msg[] =
 #ifdef CONFIG_FUNCTION_TRACER
 	"  set_ftrace_pid\t- Write pid(s) to only function trace those pids\n"
 	"\t\t    (function)\n"
+	"  set_ftrace_notrace_pid\t- Write pid(s) to not function trace those pids\n"
+	"\t\t    (function)\n"
 #endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	"  set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
@@ -9146,6 +9219,9 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
+	/* Can not use kmalloc for iter.temp */
+	iter.temp = static_temp_buf;
+	iter.temp_size = STATIC_TEMP_BUF_SIZE;
 
 	for_each_tracing_cpu(cpu) {
 		atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
@@ -9334,7 +9410,7 @@ __init static int tracer_alloc_buffers(void)
 		goto out_free_buffer_mask;
 
 	/* Only allocate trace_printk buffers if a trace_printk exists */
-	if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
+	if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt)
 		/* Must be called before global_trace.buffer is allocated */
 		trace_printk_init_buffers();