---

yaml
---
r: 140697
b: refs/heads/master
c: 78d904b
h: refs/heads/master
i:
  140695: 331df11
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 1830b52d0de8c60c4f5dfbac134aa8f69d815801
+refs/heads/master: 78d904b46a72fcf15ea6a39672bbef92953876b5

trunk/arch/x86/Kconfig

@@ -34,6 +34,7 @@ config X86
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE || FUNCTION_GRAPH_TRACER
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 	select HAVE_ARCH_TRACEHOOK

trunk/arch/x86/kernel/ftrace.c

@@ -113,7 +113,7 @@ static void ftrace_mod_code(void)
 					     MCOUNT_INSN_SIZE);
 }
 
-void ftrace_nmi_enter(void)
+void arch_ftrace_nmi_enter(void)
 {
 	atomic_inc(&in_nmi);
 	/* Must have in_nmi seen before reading write flag */
@@ -124,7 +124,7 @@ void ftrace_nmi_enter(void)
 	}
 }
 
-void ftrace_nmi_exit(void)
+void arch_ftrace_nmi_exit(void)
 {
 	/* Finish all executions before clearing in_nmi */
 	smp_wmb();
@@ -376,12 +376,12 @@ int ftrace_disable_ftrace_graph_caller(void)
  */
 static atomic_t in_nmi;
 
-void ftrace_nmi_enter(void)
+void arch_ftrace_nmi_enter(void)
 {
 	atomic_inc(&in_nmi);
 }
 
-void ftrace_nmi_exit(void)
+void arch_ftrace_nmi_exit(void)
 {
 	atomic_dec(&in_nmi);
 }

trunk/include/linux/ftrace_irq.h

@@ -2,7 +2,15 @@
 #define _LINUX_FTRACE_IRQ_H
 
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
+#ifdef CONFIG_FTRACE_NMI_ENTER
+extern void arch_ftrace_nmi_enter(void);
+extern void arch_ftrace_nmi_exit(void);
+#else
+static inline void arch_ftrace_nmi_enter(void) { }
+static inline void arch_ftrace_nmi_exit(void) { }
+#endif
+
+#ifdef CONFIG_RING_BUFFER
 extern void ftrace_nmi_enter(void);
 extern void ftrace_nmi_exit(void);
 #else

trunk/kernel/trace/Kconfig

@@ -9,6 +9,9 @@ config USER_STACKTRACE_SUPPORT
 config NOP_TRACER
 	bool
 
+config HAVE_FTRACE_NMI_ENTER
+	bool
+
 config HAVE_FUNCTION_TRACER
 	bool
 
@@ -37,6 +40,11 @@ config TRACER_MAX_TRACE
 config RING_BUFFER
 	bool
 
+config FTRACE_NMI_ENTER
+       bool
+       depends on HAVE_FTRACE_NMI_ENTER
+       default y
+
 config TRACING
 	bool
 	select DEBUG_FS

trunk/kernel/trace/ring_buffer.c

@@ -4,6 +4,7 @@
  * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
  */
 #include <linux/ring_buffer.h>
+#include <linux/ftrace_irq.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
@@ -18,6 +19,35 @@
 
 #include "trace.h"
 
+/*
+ * Since the write to the buffer is still not fully lockless,
+ * we must be careful with NMIs. The locks in the writers
+ * are taken when a write crosses to a new page. The locks
+ * protect against races with the readers (this will soon
+ * be fixed with a lockless solution).
+ *
+ * Because we can not protect against NMIs, and we want to
+ * keep traces reentrant, we need to manage what happens
+ * when we are in an NMI.
+ */
+static DEFINE_PER_CPU(int, rb_in_nmi);
+
+void ftrace_nmi_enter(void)
+{
+	__get_cpu_var(rb_in_nmi)++;
+	/* call arch specific handler too */
+	arch_ftrace_nmi_enter();
+}
+
+void ftrace_nmi_exit(void)
+{
+	arch_ftrace_nmi_exit();
+	__get_cpu_var(rb_in_nmi)--;
+	/* NMIs are not recursive */
+	WARN_ON_ONCE(__get_cpu_var(rb_in_nmi));
+}
+
+
 /*
  * A fast way to enable or disable all ring buffers is to
  * call tracing_on or tracing_off. Turning off the ring buffers
@@ -982,6 +1012,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	struct ring_buffer *buffer = cpu_buffer->buffer;
 	struct ring_buffer_event *event;
 	unsigned long flags;
+	bool lock_taken = false;
 
 	commit_page = cpu_buffer->commit_page;
 	/* we just need to protect against interrupts */
@@ -995,7 +1026,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		struct buffer_page *next_page = tail_page;
 
 		local_irq_save(flags);
-		__raw_spin_lock(&cpu_buffer->lock);
+		/*
+		 * NMIs can happen after we take the lock.
+		 * If we are in an NMI, only take the lock
+		 * if it is not already taken. Otherwise
+		 * simply fail.
+		 */
+		if (unlikely(__get_cpu_var(rb_in_nmi))) {
+			if (!__raw_spin_trylock(&cpu_buffer->lock))
+				goto out_unlock;
+		} else
+			__raw_spin_lock(&cpu_buffer->lock);
+
+		lock_taken = true;
 
 		rb_inc_page(cpu_buffer, &next_page);
 
@@ -1097,7 +1140,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (tail <= BUF_PAGE_SIZE)
 		local_set(&tail_page->write, tail);
 
-	__raw_spin_unlock(&cpu_buffer->lock);
+	if (likely(lock_taken))
+		__raw_spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 	return NULL;
 }