Merge tag 'trace-v6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Fix trace histogram sort function cmp_entries_dup()

   The sort function cmp_entries_dup() returns either 1 or 0, and not -1
   if parameter "a" is less than "b" by memcmp().

 - Fix archs that call trace_hardirqs_off() without RCU watching

   Both x86 and arm64 no longer call any tracepoints with RCU not
   watching. It was assumed that it was safe to get rid of
   trace_*_rcuidle() version of the tracepoint calls. This was needed to
   get rid of the SRCU protection and be able to implement features like
   faultable traceponits and add rust tracepoints.

   Unfortunately, there were a few architectures that still relied on
   that logic. There's only one file that has tracepoints that are
   called without RCU watching. Add macro logic around the tracepoints
   for architectures that do not have CONFIG_ARCH_WANTS_NO_INSTR defined
   will check if the code is in the idle path (the only place RCU isn't
   watching), and enable RCU around calling the tracepoint, but only do
   it if the tracepoint is enabled.

* tag 'trace-v6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Fix archs that still call tracepoints without RCU watching
  tracing: Fix cmp_entries_dup() to respect sort() comparison rules

2 files changed, 38 insertions, 11 deletions

diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 5c03633316a6..0c42b15c3800 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -10,11 +10,42 @@
 #include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/kprobes.h>
+#include <linux/hardirq.h>
 #include "trace.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/preemptirq.h>
 
+/*
+ * Use regular trace points on architectures that implement noinstr
+ * tooling: these calls will only happen with RCU enabled, which can
+ * use a regular tracepoint.
+ *
+ * On older architectures, RCU may not be watching in idle. In that
+ * case, wake up RCU to watch while calling the tracepoint. These
+ * aren't NMI-safe - so exclude NMI contexts:
+ */
+#ifdef CONFIG_ARCH_WANTS_NO_INSTR
+#define trace(point, args)	trace_##point(args)
+#else
+#define trace(point, args)					\
+	do {							\
+		if (trace_##point##_enabled()) {		\
+			bool exit_rcu = false;			\
+			if (in_nmi())				\
+				break;				\
+			if (!IS_ENABLED(CONFIG_TINY_RCU) &&	\
+			    is_idle_task(current)) {		\
+				ct_irq_enter();			\
+				exit_rcu = true;		\
+			}					\
+			trace_##point(args);			\
+			if (exit_rcu)				\
+				ct_irq_exit();			\
+		}						\
+	} while (0)
+#endif
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 /* Per-cpu variable to prevent redundant calls when IRQs already off */
 static DEFINE_PER_CPU(int, tracing_irq_cpu);
@@ -28,7 +59,7 @@ static DEFINE_PER_CPU(int, tracing_irq_cpu);
 void trace_hardirqs_on_prepare(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
-		trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_enable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
@@ -39,7 +70,7 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
-		trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_enable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
@@ -61,7 +92,7 @@ void trace_hardirqs_off_finish(void)
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
-		trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_disable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 	}
 
 }
@@ -75,7 +106,7 @@ void trace_hardirqs_off(void)
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
-		trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_disable, TP_ARGS(CALLER_ADDR0, CALLER_ADDR1));
 	}
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
@@ -86,13 +117,13 @@ NOKPROBE_SYMBOL(trace_hardirqs_off);
 
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-	trace_preempt_enable(a0, a1);
+	trace(preempt_enable, TP_ARGS(a0, a1));
 	tracer_preempt_on(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-	trace_preempt_disable(a0, a1);
+	trace(preempt_disable, TP_ARGS(a0, a1));
 	tracer_preempt_off(a0, a1);
 }
 #endif
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 3a56e7c8aa4f..1921ade45be3 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -845,15 +845,11 @@ int tracing_map_init(struct tracing_map *map)
 static int cmp_entries_dup(const void *A, const void *B)
 {
 	const struct tracing_map_sort_entry *a, *b;
-	int ret = 0;
 
 	a = *(const struct tracing_map_sort_entry **)A;
 	b = *(const struct tracing_map_sort_entry **)B;
 
-	if (memcmp(a->key, b->key, a->elt->map->key_size))
-		ret = 1;
-
-	return ret;
+	return memcmp(a->key, b->key, a->elt->map->key_size);
 }
 
 static int cmp_entries_sum(const void *A, const void *B)