ftrace: trace irq disabled critical timings

This patch adds latency tracing for critical timings
(how long interrupts are disabled for).

 "irqsoff" is added to /debugfs/tracing/available_tracers

Note:
  tracing_max_latency
    also holds the max latency for irqsoff (in usecs).
   (default to large number so one must start latency tracing)

  tracing_thresh
    threshold (in usecs) to always print out if irqs off
    is detected to be longer than stated here.
    If irq_thresh is non-zero, then max_irq_latency
    is ignored.

Here's an example of a trace with ftrace_enabled = 0

=======
preemption latency trace v1.1.5 on 2.6.24-rc7
Signed-off-by: Ingo Molnar <mingo@elte.hu>
--------------------------------------------------------------------
 latency: 100 us, #3/3, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2)
    -----------------
    | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0)
    -----------------
 => started at: _spin_lock_irqsave+0x2a/0xb7
 => ended at:   _spin_unlock_irqrestore+0x32/0x5f

                 _------=> CPU#
                / _-----=> irqs-off
               | / _----=> need-resched
               || / _---=> hardirq/softirq
               ||| / _--=> preempt-depth
               |||| /
               |||||     delay
   cmd     pid ||||| time  |   caller
      \   /    |||||   \   |   /
 swapper-0     1d.s3    0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000])
 swapper-0     1d.s3  100us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000])
 swapper-0     1d.s3  100us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f)

vim:ft=help
=======

And this is a trace with ftrace_enabled == 1

=======
preemption latency trace v1.1.5 on 2.6.24-rc7
--------------------------------------------------------------------
 latency: 102 us, #12/12, CPU#1 | (M:rt VP:0, KP:0, SP:0 HP:0 #P:2)
    -----------------
    | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0)
    -----------------
 => started at: _spin_lock_irqsave+0x2a/0xb7
 => ended at:   _spin_unlock_irqrestore+0x32/0x5f

                 _------=> CPU#
                / _-----=> irqs-off
               | / _----=> need-resched
               || / _---=> hardirq/softirq
               ||| / _--=> preempt-depth
               |||| /
               |||||     delay
   cmd     pid ||||| time  |   caller
      \   /    |||||   \   |   /
 swapper-0     1dNs3    0us+: _spin_lock_irqsave+0x2a/0xb7 (e1000_update_stats+0x47/0x64c [e1000])
 swapper-0     1dNs3   46us : e1000_read_phy_reg+0x16/0x225 [e1000] (e1000_update_stats+0x5e2/0x64c [e1000])
 swapper-0     1dNs3   46us : e1000_swfw_sync_acquire+0x10/0x99 [e1000] (e1000_read_phy_reg+0x49/0x225 [e1000])
 swapper-0     1dNs3   46us : e1000_get_hw_eeprom_semaphore+0x12/0xa6 [e1000] (e1000_swfw_sync_acquire+0x36/0x99 [e1000])
 swapper-0     1dNs3   47us : __const_udelay+0x9/0x47 (e1000_read_phy_reg+0x116/0x225 [e1000])
 swapper-0     1dNs3   47us+: __delay+0x9/0x50 (__const_udelay+0x45/0x47)
 swapper-0     1dNs3   97us : preempt_schedule+0xc/0x84 (__delay+0x4e/0x50)
 swapper-0     1dNs3   98us : e1000_swfw_sync_release+0xc/0x55 [e1000] (e1000_read_phy_reg+0x211/0x225 [e1000])
 swapper-0     1dNs3   99us+: e1000_put_hw_eeprom_semaphore+0x9/0x35 [e1000] (e1000_swfw_sync_release+0x50/0x55 [e1000])
 swapper-0     1dNs3  101us : _spin_unlock_irqrestore+0xe/0x5f (e1000_update_stats+0x641/0x64c [e1000])
 swapper-0     1dNs3  102us : _spin_unlock_irqrestore+0x32/0x5f (e1000_update_stats+0x641/0x64c [e1000])
 swapper-0     1dNs3  102us : trace_hardirqs_on_caller+0x75/0x89 (_spin_unlock_irqrestore+0x32/0x5f)

vim:ft=help
=======

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

6 files changed, 443 insertions, 5 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 19908b26cf80..d66d676dc362 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -909,7 +909,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
         rt_mutex_init_task(p);
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_LOCKDEP)
         DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
         DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
 #endif
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 81a4e4a3f087..e21924365ea3 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -39,6 +39,7 @@
 #include <linux/irqflags.h>
 #include <linux/utsname.h>
 #include <linux/hash.h>
+#include <linux/ftrace.h>
 
 #include <asm/sections.h>
 
@@ -982,7 +983,7 @@ check_noncircular(struct lock_class *source, unsigned int depth)
         return 1;
 }
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 /*
  * Forwards and backwards subgraph searching, for the purposes of
  * proving that two subgraphs can be connected by a new dependency
@@ -1680,7 +1681,7 @@ valid_state(struct task_struct *curr, struct held_lock *this,
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
                      enum lock_usage_bit new_bit);
 
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 
 /*
  * print irq inversion bug:
@@ -2013,11 +2014,13 @@ void early_boot_irqs_on(void)
 /*
  * Hardirqs will be enabled:
  */
-void trace_hardirqs_on(void)
+void notrace trace_hardirqs_on_caller(unsigned long a0)
 {
         struct task_struct *curr = current;
         unsigned long ip;
 
+        time_hardirqs_on(CALLER_ADDR0, a0);
+
         if (unlikely(!debug_locks || current->lockdep_recursion))
                 return;
 
@@ -2055,16 +2058,23 @@ void trace_hardirqs_on(void)
         curr->hardirq_enable_event = ++curr->irq_events;
         debug_atomic_inc(&hardirqs_on_events);
 }
+EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
+void notrace trace_hardirqs_on(void)
+{
+        trace_hardirqs_on_caller(CALLER_ADDR0);
+}
 EXPORT_SYMBOL(trace_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
  */
-void trace_hardirqs_off(void)
+void notrace trace_hardirqs_off_caller(unsigned long a0)
 {
         struct task_struct *curr = current;
 
+        time_hardirqs_off(CALLER_ADDR0, a0);
+
         if (unlikely(!debug_locks || current->lockdep_recursion))
                 return;
 
@@ -2082,7 +2092,12 @@ void trace_hardirqs_off(void)
         } else
                 debug_atomic_inc(&redundant_hardirqs_off);
 }
+EXPORT_SYMBOL(trace_hardirqs_off_caller);
 
+void notrace trace_hardirqs_off(void)
+{
+        trace_hardirqs_off_caller(CALLER_ADDR0);
+}
 EXPORT_SYMBOL(trace_hardirqs_off);
 
 /*
diff --git a/kernel/printk.c b/kernel/printk.c
index 8fb01c32aa3b..ae7d5b9e535d 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -1041,7 +1041,9 @@ void release_console_sem(void)
                 _log_end = log_end;
                 con_start = log_end;            /* Flush */
                 spin_unlock(&logbuf_lock);
+                stop_critical_timings();        /* don't trace print latency */
                 call_console_drivers(_con_start, _log_end);
+                start_critical_timings();
                 local_irq_restore(flags);
         }
         console_locked = 0;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 892ecc94a82b..896df1cf6adc 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -26,6 +26,24 @@ config FTRACE
           (the bootup default), then the overhead of the instructions is very
           small and not measurable even in micro-benchmarks.
 
+config IRQSOFF_TRACER
+        bool "Interrupts-off Latency Tracer"
+        default n
+        depends on TRACE_IRQFLAGS_SUPPORT
+        depends on GENERIC_TIME
+        select TRACE_IRQFLAGS
+        select TRACING
+        select TRACER_MAX_TRACE
+        help
+          This option measures the time spent in irqs-off critical
+          sections, with microsecond accuracy.
+
+          The default measurement method is a maximum search, which is
+          disabled by default and can be runtime (re-)started
+          via:
+
+              echo 0 > /debugfs/tracing/tracing_max_latency
+
 config SCHED_TRACER
         bool "Scheduling Latency Tracer"
         depends on DEBUG_KERNEL
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 5508cdb19aea..46be8647fb65 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_FTRACE) += libftrace.o
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_FTRACE) += trace_functions.o
+obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
new file mode 100644
index 000000000000..a9131b0cf1a5
--- /dev/null
+++ b/kernel/trace/trace_irqsoff.c
@@ -0,0 +1,402 @@
+/*
+ * trace irqs off criticall timings
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
+ *