[PATCH -rt 8/8] stop critical timing in idle.

[Daniel Walker <dwalker@mvista.com>]

[-- Attachment #1: fix-idle-latency-tracing.patch --]
[-- Type: text/plain, Size: 1656 bytes --]

without this the idle routine still gets traced.. This is done already
for ACPI idle , but it should also be done for other idle routines.

Signed-off-by: Daniel Walker <dwalker@mvista.com>
 
---
 arch/i386/kernel/process.c   |    9 +++++++++
 arch/x86_64/kernel/process.c |   10 ++++++++++
 2 files changed, 19 insertions(+)

Index: linux-2.6.22/arch/i386/kernel/process.c
===================================================================
--- linux-2.6.22.orig/arch/i386/kernel/process.c
+++ linux-2.6.22/arch/i386/kernel/process.c
@@ -197,8 +197,17 @@ void cpu_idle(void)
 			if (cpu_is_offline(cpu))
 				play_dead();
 
+			/*
+			 * We have irqs disabled here, so stop latency tracing
+			 * at this point and restart it after we return:
+			 */
+			stop_critical_timing();
+
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
 			idle();
+
+ 			touch_critical_timing();
+
 		}
 		local_irq_disable();
 		trace_preempt_exit_idle();
Index: linux-2.6.22/arch/x86_64/kernel/process.c
===================================================================
--- linux-2.6.22.orig/arch/x86_64/kernel/process.c
+++ linux-2.6.22/arch/x86_64/kernel/process.c
@@ -223,8 +223,18 @@ void cpu_idle (void)
 			 * Otherwise, idle callbacks can misfire.
 			 */
 			local_irq_disable();
+
+			/*
+			 * We have irqs disabled here, so stop latency tracing
+			 * at this point and restart it after we return:
+			 */
+			stop_critical_timing();
+
 			enter_idle();
 			idle();
+
+			touch_critical_timing();
+
 			/* In many cases the interrupt that ended idle
 			   has already called exit_idle. But some idle
 			   loops can be woken up without interrupt. */

--