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>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e2319f3..dd349c9 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -165,7 +165,10 @@
*/
local_irq_disable();
enter_idle();
+ /* Don't trace irqs off for idle */
+ stop_critical_timings();
idle();
+ start_critical_timings();
/* In many cases the interrupt that ended idle
has already called exit_idle. But some idle
loops can be woken up without interrupt. */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 76f60f5..84aa288 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -5,6 +5,7 @@
obj-$(CONFIG_SMP) := msr-on-cpu.o
lib-y := delay_$(BITS).o
+lib-y += thunk_$(BITS).o
lib-y += usercopy_$(BITS).o getuser_$(BITS).o putuser_$(BITS).o
lib-y += memcpy_$(BITS).o
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
new file mode 100644
index 0000000..650b11e
--- /dev/null
+++ b/arch/x86/lib/thunk_32.S
@@ -0,0 +1,47 @@
+/*
+ * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
+ * Copyright 2008 by Steven Rostedt, Red Hat, Inc
+ * (inspired by Andi Kleen's thunk_64.S)
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+
+ #include <linux/linkage.h>
+
+#define ARCH_TRACE_IRQS_ON \
+ pushl %eax; \
+ pushl %ecx; \
+ pushl %edx; \
+ call trace_hardirqs_on; \
+ popl %edx; \
+ popl %ecx; \
+ popl %eax;
+
+#define ARCH_TRACE_IRQS_OFF \
+ pushl %eax; \
+ pushl %ecx; \
+ pushl %edx; \
+ call trace_hardirqs_off; \
+ popl %edx; \
+ popl %ecx; \
+ popl %eax;
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* put return address in eax (arg1) */
+ .macro thunk_ra name,func
+ .globl \name
+\name:
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+ /* Place EIP in the arg1 */
+ movl 3*4(%esp), %eax
+ call \func
+ popl %edx
+ popl %ecx
+ popl %eax
+ ret
+ .endm
+
+ thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
+ thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#endif
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index e009251..bf9a7d5 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -2,6 +2,7 @@
* Save registers before calling assembly functions. This avoids
* disturbance of register allocation in some inline assembly constructs.
* Copyright 2001,2002 by Andi Kleen, SuSE Labs.
+ * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
* Subject to the GNU public license, v.2. No warranty of any kind.
*/
@@ -42,8 +43,22 @@
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
- thunk trace_hardirqs_on_thunk,trace_hardirqs_on
- thunk trace_hardirqs_off_thunk,trace_hardirqs_off
+ /* put return address in rdi (arg1) */
+ .macro thunk_ra name,func
+ .globl \name
+\name:
+ CFI_STARTPROC
+ SAVE_ARGS
+ /* SAVE_ARGS pushs 9 elements */
+ /* the next element would be the rip */
+ movq 9*8(%rsp), %rdi
+ call \func
+ jmp restore
+ CFI_ENDPROC
+ .endm
+
+ thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
+ thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC