ftrace: trace preempt off critical timings

Add preempt off timings. A lot of kernel core code is taken from the RT patch
latency trace that was written by Ingo Molnar.

This adds "preemptoff" and "preemptirqsoff" to /debugfs/tracing/available_tracers

Now instead of just tracing irqs off, preemption off can be selected
to be recorded.

When this is selected, it shares the same files as irqs off timings.
One can either trace preemption off, irqs off, or one or the other off.

By echoing "preemptoff" into /debugfs/tracing/current_tracer, recording
of preempt off only is performed. "irqsoff" will only record the time
irqs are disabled, but "preemptirqsoff" will take the total time irqs
or preemption are disabled. Runtime switching of these options is now
supported by simpling echoing in the appropriate trace name into
/debugfs/tracing/current_tracer.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 23 insertions, 1 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 73e600852365..328494e28df2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -70,6 +70,7 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
+#include <linux/ftrace.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -4365,26 +4366,44 @@ void scheduler_tick(void)
 #endif
 }
 
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+                                defined(CONFIG_PREEMPT_TRACER))
+
+static inline unsigned long get_parent_ip(unsigned long addr)
+{
+        if (in_lock_functions(addr)) {
+                addr = CALLER_ADDR2;
+                if (in_lock_functions(addr))
+                        addr = CALLER_ADDR3;
+        }
+        return addr;
+}
 
 void __kprobes add_preempt_count(int val)
 {
+#ifdef CONFIG_DEBUG_PREEMPT
         /*
          * Underflow?
          */
         if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
                 return;
+#endif
         preempt_count() += val;
+#ifdef CONFIG_DEBUG_PREEMPT
         /*
          * Spinlock count overflowing soon?
          */
         DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
                                 PREEMPT_MASK - 10);
+#endif
+        if (preempt_count() == val)
+                trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 EXPORT_SYMBOL(add_preempt_count);
 
 void __kprobes sub_preempt_count(int val)
 {
+#ifdef CONFIG_DEBUG_PREEMPT
         /*
          * Underflow?
          */
@@ -4396,7 +4415,10 @@ void __kprobes sub_preempt_count(int val)
         if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
                         !(preempt_count() & PREEMPT_MASK)))
                 return;
+#endif
 
+        if (preempt_count() == val)
+                trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
         preempt_count() -= val;
 }
 EXPORT_SYMBOL(sub_preempt_count);