Merge tag 'trace-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "New:

   - The Real Time Linux Analysis (RTLA) tool is added to the tools
     directory.

   - Can safely filter on user space pointers with: field.ustring ~
     "match-string"

   - eprobes can now be filtered like any other event.

   - trace_marker(_raw) now uses stream_open() to allow multiple threads
     to safely write to it. Note, this could possibly break existing
     user space, but we will not know until we hear about it, and then
     can revert the change if need be.

   - New field in events to display when bottom halfs are disabled.

   - Sorting of the ftrace functions are now done at compile time
     instead of at bootup.

  Infrastructure changes to support future efforts:

   - Added __rel_loc type for trace events. Similar to __data_loc but
     the offset to the dynamic data is based off of the location of the
     descriptor and not the beginning of the event. Needed for user
     defined events.

   - Some simplification of event trigger code.

   - Make synthetic events process its callback better to not hinder
     other event callbacks that are registered. Needed for user defined
     events.

  And other small fixes and cleanups"

* tag 'trace-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (50 commits)
  tracing: Add ustring operation to filtering string pointers
  rtla: Add rtla timerlat hist documentation
  rtla: Add rtla timerlat top documentation
  rtla: Add rtla timerlat documentation
  rtla: Add rtla osnoise hist documentation
  rtla: Add rtla osnoise top documentation
  rtla: Add rtla osnoise man page
  rtla: Add Documentation
  rtla/timerlat: Add timerlat hist mode
  rtla: Add timerlat tool and timelart top mode
  rtla/osnoise: Add the hist mode
  rtla/osnoise: Add osnoise top mode
  rtla: Add osnoise tool
  rtla: Helper functions for rtla
  rtla: Real-Time Linux Analysis tool
  tracing/osnoise: Properly unhook events if start_per_cpu_kthreads() fails
  tracing: Remove duplicate warnings when calling trace_create_file()
  tracing/kprobes: 'nmissed' not showed correctly for kretprobe
  tracing: Add test for user space strings when filtering on string pointers
  tracing: Have syscall trace events use trace_event_buffer_lock_reserve()
  ...

1 files changed, 47 insertions, 41 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 78ea542ce3bc..a569a0cb81ee 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -980,6 +980,8 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev
 		ring_buffer_write(buffer, event->array[0], &event->array[1]);
 		/* Release the temp buffer */
 		this_cpu_dec(trace_buffered_event_cnt);
+		/* ring_buffer_unlock_commit() enables preemption */
+		preempt_enable_notrace();
 	} else
 		ring_buffer_unlock_commit(buffer, event);
 }
@@ -2601,6 +2603,8 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status)
 		trace_flags |= TRACE_FLAG_HARDIRQ;
 	if (in_serving_softirq())
 		trace_flags |= TRACE_FLAG_SOFTIRQ;
+	if (softirq_count() >> (SOFTIRQ_SHIFT + 1))
+		trace_flags |= TRACE_FLAG_BH_OFF;
 
 	if (tif_need_resched())
 		trace_flags |= TRACE_FLAG_NEED_RESCHED;
@@ -2745,8 +2749,8 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 	*current_rb = tr->array_buffer.buffer;
 
 	if (!tr->no_filter_buffering_ref &&
-	    (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
-	    (entry = this_cpu_read(trace_buffered_event))) {
+	    (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) {
+		preempt_disable_notrace();
 		/*
 		 * Filtering is on, so try to use the per cpu buffer first.
 		 * This buffer will simulate a ring_buffer_event,
@@ -2764,33 +2768,38 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb,
 		 * is still quicker than no copy on match, but having
 		 * to discard out of the ring buffer on a failed match.
 		 */
-		int max_len = PAGE_SIZE - struct_size(entry, array, 1);
+		if ((entry = __this_cpu_read(trace_buffered_event))) {
+			int max_len = PAGE_SIZE - struct_size(entry, array, 1);
 
-		val = this_cpu_inc_return(trace_buffered_event_cnt);
+			val = this_cpu_inc_return(trace_buffered_event_cnt);
 
-		/*
-		 * Preemption is disabled, but interrupts and NMIs
-		 * can still come in now. If that happens after
-		 * the above increment, then it will have to go
-		 * back to the old method of allocating the event
-		 * on the ring buffer, and if the filter fails, it
-		 * will have to call ring_buffer_discard_commit()
-		 * to remove it.
-		 *
-		 * Need to also check the unlikely case that the
-		 * length is bigger than the temp buffer size.
-		 * If that happens, then the reserve is pretty much
-		 * guaranteed to fail, as the ring buffer currently
-		 * only allows events less than a page. But that may
-		 * change in the future, so let the ring buffer reserve
-		 * handle the failure in that case.
-		 */
-		if (val == 1 && likely(len <= max_len)) {
-			trace_event_setup(entry, type, trace_ctx);
-			entry->array[0] = len;
-			return entry;
+			/*
+			 * Preemption is disabled, but interrupts and NMIs
+			 * can still come in now. If that happens after
+			 * the above increment, then it will have to go
+			 * back to the old method of allocating the event
+			 * on the ring buffer, and if the filter fails, it
+			 * will have to call ring_buffer_discard_commit()
+			 * to remove it.
+			 *
+			 * Need to also check the unlikely case that the
+			 * length is bigger than the temp buffer size.
+			 * If that happens, then the reserve is pretty much
+			 * guaranteed to fail, as the ring buffer currently
+			 * only allows events less than a page. But that may
+			 * change in the future, so let the ring buffer reserve
+			 * handle the failure in that case.
+			 */
+			if (val == 1 && likely(len <= max_len)) {
+				trace_event_setup(entry, type, trace_ctx);
+				entry->array[0] = len;
+				/* Return with preemption disabled */
+				return entry;
+			}
+			this_cpu_dec(trace_buffered_event_cnt);
 		}
-		this_cpu_dec(trace_buffered_event_cnt);
+		/* __trace_buffer_lock_reserve() disables preemption */
+		preempt_enable_notrace();
 	}
 
 	entry = __trace_buffer_lock_reserve(*current_rb, type, len,
@@ -4183,7 +4192,7 @@ unsigned long trace_total_entries(struct trace_array *tr)
 static void print_lat_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#                    _------=> CPU#            \n"
-		    "#                   / _-----=> irqs-off        \n"
+		    "#                   / _-----=> irqs-off/BH-disabled\n"
 		    "#                  | / _----=> need-resched    \n"
 		    "#                  || / _---=> hardirq/softirq \n"
 		    "#                  ||| / _--=> preempt-depth   \n"
@@ -4224,7 +4233,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#                            %.*s  _-----=> irqs-off\n", prec, space);
+	seq_printf(m, "#                            %.*s  _-----=> irqs-off/BH-disabled\n", prec, space);
 	seq_printf(m, "#                            %.*s / _----=> need-resched\n", prec, space);
 	seq_printf(m, "#                            %.*s| / _---=> hardirq/softirq\n", prec, space);
 	seq_printf(m, "#                            %.*s|| / _--=> preempt-depth\n", prec, space);
@@ -4834,6 +4843,12 @@ int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int tracing_mark_open(struct inode *inode, struct file *filp)
+{
+	stream_open(inode, filp);
+	return tracing_open_generic_tr(inode, filp);
+}
+
 static int tracing_release(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
@@ -5635,7 +5650,7 @@ static const char readme_msg[] =
 	"\t        - a numeric literal: e.g. ms_per_sec=1000,\n"
 	"\t        - an arithmetic expression: e.g. time_secs=current_timestamp/1000\n"
 	"\n"
-	"\t    hist trigger aritmethic expressions support addition(+), subtraction(-),\n"
+	"\t    hist trigger arithmetic expressions support addition(+), subtraction(-),\n"
 	"\t    multiplication(*) and division(/) operators. An operand can be either a\n"
 	"\t    variable reference, field or numeric literal.\n"
 	"\n"
@@ -6718,10 +6733,9 @@ waitagain:
 		cnt = PAGE_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
-	memset_startat(iter, 0, seq);
+	trace_iterator_reset(iter);
 	cpumask_clear(iter->started);
 	trace_seq_init(&iter->seq);
-	iter->pos = -1;
 
 	trace_event_read_lock();
 	trace_access_lock(iter->cpu_file);
@@ -7110,9 +7124,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (tt)
 		event_triggers_post_call(tr->trace_marker_file, tt);
 
-	if (written > 0)
-		*fpos += written;
-
 	return written;
 }
 
@@ -7171,9 +7182,6 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,
 
 	__buffer_unlock_commit(buffer, event);
 
-	if (written > 0)
-		*fpos += written;
-
 	return written;
 }
 
@@ -7573,16 +7581,14 @@ static const struct file_operations tracing_free_buffer_fops = {
 };
 
 static const struct file_operations tracing_mark_fops = {
-	.open		= tracing_open_generic_tr,
+	.open		= tracing_mark_open,
 	.write		= tracing_mark_write,
-	.llseek		= generic_file_llseek,
 	.release	= tracing_release_generic_tr,
 };
 
 static const struct file_operations tracing_mark_raw_fops = {
-	.open		= tracing_open_generic_tr,
+	.open		= tracing_mark_open,
 	.write		= tracing_mark_raw_write,
-	.llseek		= generic_file_llseek,
 	.release	= tracing_release_generic_tr,
 };