[PATCH -v6 00/13] ftrace for MIPS

[PATCH -v6 00/13] ftrace for MIPS

[Wu Zhangjin]

This -v6 revision incorporates the feedbacks of -v5 revision from Frederic
Weisbecker, the most important changes include:

1. tracing: add IRQENTRY_EXIT section for MIPS

Tag the mips irq entry functions with "__irq_entry".

2. "notrace" relative patches

To avoid hanging on mips_timecounter_read() when using function graph tracer,
we need not to trace the subroutines called by mips_timecounter_read(). for the
mips specific subroutines, we use __notrac_funcgraph to tag them.

For the common timecounter_read_* functions, we add a new __arch_notrace
flag/macro to include/linux/ftrace.h for the arch specific requirement, and use
it to tag them. and then we define the macro in arch/mips/include/asm/ftrace.h
to make it take effect for MIPS.

All of the latest update have been pushed into:

git://dev.lemote.com/rt4ls.git  linux-mips/dev/ftrace-upstream

Thanks & Regards,
	Wu Zhangjin

Wu Zhangjin (13):
  tracing: convert trace_clock_local() as weak function
  tracing: add mips_timecounter_read() for MIPS
  tracing: add MIPS specific trace_clock_local()
  tracing: add static function tracer support for MIPS
  tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST for MIPS
  tracing: add an endian argument to scripts/recordmcount.pl
  tracing: add dynamic function tracer support for MIPS
  tracing: add IRQENTRY_EXIT section for MIPS
  tracing: Add __arch_notrace for arch specific requirement
  tracing: not trace the timecounter_read* in kernel/time/clocksource.c
  tracing: not trace mips_timecounter_read() for MIPS
  tracing: add function graph tracer support for MIPS
  tracing: add dynamic function graph tracer for MIPS

 arch/mips/Kconfig              |    5 +
 arch/mips/Makefile             |    4 +
 arch/mips/include/asm/ftrace.h |   42 +++++++++-
 arch/mips/include/asm/irq.h    |   29 +------
 arch/mips/include/asm/time.h   |   19 ++++
 arch/mips/kernel/Makefile      |    9 ++
 arch/mips/kernel/csrc-r4k.c    |   42 +++++++++
 arch/mips/kernel/ftrace.c      |  190 ++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/irq.c         |   34 +++++++
 arch/mips/kernel/mcount.S      |  177 +++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mips_ksyms.c  |    5 +
 arch/mips/kernel/smp.c         |    3 +-
 arch/mips/kernel/smtc.c        |   21 +++--
 arch/mips/kernel/time.c        |    2 +
 arch/mips/kernel/trace_clock.c |   33 +++++++
 arch/mips/kernel/vmlinux.lds.S |    1 +
 arch/mips/sgi-ip22/ip22-int.c  |    3 +-
 arch/mips/sgi-ip22/ip22-time.c |    3 +-
 include/linux/ftrace.h         |   19 ++++
 kernel/time/clocksource.c      |    5 +-
 kernel/trace/trace_clock.c     |    2 +-
 scripts/Makefile.build         |    1 +
 scripts/recordmcount.pl        |   44 +++++++++-
 23 files changed, 649 insertions(+), 44 deletions(-)
 create mode 100644 arch/mips/kernel/ftrace.c
 create mode 100644 arch/mips/kernel/mcount.S
 create mode 100644 arch/mips/kernel/trace_clock.c

[PATCH -v6 01/13] tracing: convert trace_clock_local() as weak function

[Wu Zhangjin]

trace_clock_local() is based on the arch-specific sched_clock(), in X86,
it is tsc(64bit) based, which can give very high precision(about 1ns
with 1GHz). but in MIPS, the sched_clock() is jiffies based, which can
give only 10ms precison with 1000 HZ. which is not enough for tracing,
especially for Real Time system.

so, we need to implement a MIPS specific sched_clock() to get higher
precision. There is a tsc like clock counter register in MIPS, whose
frequency is half of the processor, so, if the cpu frequency is 800MHz,
the time precision reaches 2.5ns, which is very good for tracing, even
for Real Time system.

but 'Cause it is only 32bit long, which will rollover quickly, so, such
a sched_clock() will bring with extra load, which is not good for the
whole system. so, we only need to implement a arch-specific
trace_clock_local() for tracing. as a preparation, we convert it as a
weak function.

The MIPS specific trace_clock_local() is coming in the next two patches.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 kernel/trace/trace_clock.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 20c5f92..06b8cd2 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -26,7 +26,7 @@
  * Useful for tracing that does not cross to other CPUs nor
  * does it go through idle events.
  */
-u64 notrace trace_clock_local(void)
+u64 __weak notrace trace_clock_local(void)
 {
 	unsigned long flags;
 	u64 clock;
-- 
1.6.2.1

[PATCH -v6 02/13] tracing: add mips_timecounter_read() for MIPS

[Wu Zhangjin]

This patch add a new function: mips_timecounter_read() to get high
precision timestamp without extra lock.

It is based on the clock counter register and the
timecounter/cyclecounter abstraction layer of kernel.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/include/asm/time.h |   19 +++++++++++++++++++
 arch/mips/kernel/csrc-r4k.c  |   41 +++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/time.c      |    2 ++
 3 files changed, 62 insertions(+), 0 deletions(-)

diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
index df6a430..b8af7fa 100644
--- a/arch/mips/include/asm/time.h
+++ b/arch/mips/include/asm/time.h
@@ -73,8 +73,18 @@ static inline int mips_clockevent_init(void)
  */
 #ifdef CONFIG_CSRC_R4K_LIB
 extern int init_r4k_clocksource(void);
+extern int init_r4k_timecounter(void);
+extern u64 r4k_timecounter_read(void);
 #endif
 
+static inline u64 mips_timecounter_read(void)
+{
+#ifdef CONFIG_CSRC_R4K
+	return r4k_timecounter_read();
+#else
+	return sched_clock();
+#endif
+}
 static inline int init_mips_clocksource(void)
 {
 #ifdef CONFIG_CSRC_R4K
@@ -84,6 +94,15 @@ static inline int init_mips_clocksource(void)
 #endif
 }
 
+static inline int init_mips_timecounter(void)
+{
+#ifdef CONFIG_CSRC_R4K
+	return init_r4k_timecounter();
+#else
+	return 0;
+#endif
+}
+
 extern void clocksource_set_clock(struct clocksource *cs, unsigned int clock);
 extern void clockevent_set_clock(struct clock_event_device *cd,
 		unsigned int clock);
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index e95a3cd..4e7705f 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -7,6 +7,7 @@
  */
 #include <linux/clocksource.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 
 #include <asm/time.h>
 
@@ -36,3 +37,43 @@ int __init init_r4k_clocksource(void)
 
 	return 0;
 }
+
+static struct timecounter r4k_tc = {
+	.cc = NULL,
+};
+
+static cycle_t r4k_cc_read(const struct cyclecounter *cc)
+{
+	return read_c0_count();
+}
+
+static struct cyclecounter r4k_cc = {
+	.read = r4k_cc_read,
+	.mask = CLOCKSOURCE_MASK(32),
+	.shift = 32,
+};
+
+int __init init_r4k_timecounter(void)
+{
+	if (!cpu_has_counter || !mips_hpt_frequency)
+		return -ENXIO;
+
+	r4k_cc.mult = div_sc((unsigned long)mips_hpt_frequency, NSEC_PER_SEC,
+			32);
+
+	timecounter_init(&r4k_tc, &r4k_cc, sched_clock());
+
+	return 0;
+}
+
+u64 r4k_timecounter_read(void)
+{
+	u64 clock;
+
+	if (r4k_tc.cc != NULL)
+		clock = timecounter_read(&r4k_tc);
+	else
+		clock = sched_clock();
+
+	return clock;
+}
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index 1f467d5..e38cca1 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -156,4 +156,6 @@ void __init time_init(void)
 
 	if (!mips_clockevent_init() || !cpu_has_mfc0_count_bug())
 		init_mips_clocksource();
+	if (!cpu_has_mfc0_count_bug())
+		init_mips_timecounter();
 }
-- 
1.6.2.1

[PATCH -v6 03/13] tracing: add MIPS specific trace_clock_local()

[Wu Zhangjin]

This patch add the mips_timecounter_read() based high precision version
of trace_clock_local().

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/kernel/Makefile      |    6 ++++++
 arch/mips/kernel/trace_clock.c |   33 +++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 0 deletions(-)
 create mode 100644 arch/mips/kernel/trace_clock.c

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 8e26e9c..f228868 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -8,6 +8,10 @@ obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 		   ptrace.o reset.o setup.o signal.o syscall.o \
 		   time.o topology.o traps.o unaligned.o watch.o
 
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_trace_clock.o = -pg
+endif
+
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K_LIB)	+= cevt-r4k.o
 obj-$(CONFIG_MIPS_MT_SMTC)	+= cevt-smtc.o
@@ -24,6 +28,8 @@ obj-$(CONFIG_SYNC_R4K)		+= sync-r4k.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
+obj-$(CONFIG_FTRACE)		+= trace_clock.o
+
 obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS32)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS64)	+= r4k_fpu.o r4k_switch.o
diff --git a/arch/mips/kernel/trace_clock.c b/arch/mips/kernel/trace_clock.c
new file mode 100644
index 0000000..0fe85ea
--- /dev/null
+++ b/arch/mips/kernel/trace_clock.c
@@ -0,0 +1,33 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive for
+ * more details.
+ *
+ * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ */
+
+#include <linux/clocksource.h>
+#include <linux/sched.h>
+
+#include <asm/time.h>
+
+/*
+ * trace_clock_local(): the simplest and least coherent tracing clock.
+ *
+ * Useful for tracing that does not cross to other CPUs nor
+ * does it go through idle events.
+ */
+u64 trace_clock_local(void)
+{
+	unsigned long flags;
+	u64 clock;
+
+	raw_local_irq_save(flags);
+
+	clock = mips_timecounter_read();
+
+	raw_local_irq_restore(flags);
+
+	return clock;
+}
-- 
1.6.2.1

[PATCH -v6 04/13] tracing: add static function tracer support for MIPS

[Wu Zhangjin]

If -pg of gcc is enabled with CONFIG_FUNCTION_TRACER=y. a calling to
_mcount will be inserted into each kernel function. so, there is a
possibility to trace the kernel functions in _mcount.

This patch add the MIPS specific _mcount support for static function
tracing. by deafult, ftrace_trace_function is initialized as
ftrace_stub(an empty function), so, the default _mcount will introduce
very little overhead. after enabling ftrace in user-space, it will jump
to a real tracing function and do static function tracing for us.

And to support module tracing, we need to enable -mlong-calls for the
long call from modules space to kernel space. -mlong-calls load the
address of _mcount to a register and then jump to it, so, the address is
allowed to be 32bit long, but without -mlong-calls, for the instruction
"jal _mcount" only left 26bit for the address of _mcount, which is not
enough for jumping from the module space to kernel space.

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/Kconfig              |    1 +
 arch/mips/Makefile             |    4 ++
 arch/mips/include/asm/ftrace.h |   25 +++++++++++-
 arch/mips/kernel/Makefile      |    2 +
 arch/mips/kernel/mcount.S      |   89 ++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mips_ksyms.c  |    5 ++
 6 files changed, 125 insertions(+), 1 deletions(-)
 create mode 100644 arch/mips/kernel/mcount.S

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 03bd56a..6b33e88 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -4,6 +4,7 @@ config MIPS
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_ARCH_KGDB
+	select HAVE_FUNCTION_TRACER
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB if !LEMOTE_FULOONG2E
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 77f5021..041deca 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -48,7 +48,11 @@ ifneq ($(SUBARCH),$(ARCH))
   endif
 endif
 
+ifndef CONFIG_FUNCTION_TRACER
 cflags-y := -ffunction-sections
+else
+cflags-y := -mlong-calls
+endif
 cflags-y += $(call cc-option, -mno-check-zero-division)
 
 ifdef CONFIG_32BIT
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index 40a8c17..5f8ebcf 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -1 +1,24 @@
-/* empty */
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive for
+ * more details.
+ *
+ * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ */
+
+#ifndef _ASM_MIPS_FTRACE_H
+#define _ASM_MIPS_FTRACE_H
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+#define MCOUNT_ADDR ((unsigned long)(_mcount))
+#define MCOUNT_INSN_SIZE 4		/* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void _mcount(void);
+#define mcount _mcount
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FUNCTION_TRACER */
+#endif /* _ASM_MIPS_FTRACE_H */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index f228868..38e704a 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -10,6 +10,7 @@ obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_trace_clock.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
@@ -29,6 +30,7 @@ obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
 obj-$(CONFIG_FTRACE)		+= trace_clock.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
 
 obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS32)	+= r4k_fpu.o r4k_switch.o
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
new file mode 100644
index 0000000..0c39bc8
--- /dev/null
+++ b/arch/mips/kernel/mcount.S
@@ -0,0 +1,89 @@
+/*
+ * MIPS specific _mcount support
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive for
+ * more details.
+ *
+ * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ */
+
+#include <asm/regdef.h>
+#include <asm/stackframe.h>
+#include <asm/ftrace.h>
+
+	.text
+	.set noreorder
+	.set noat
+
+	.macro MCOUNT_SAVE_REGS
+	PTR_SUBU	sp, PT_SIZE
+	PTR_S	ra, PT_R31(sp)
+	PTR_S	AT, PT_R1(sp)
+	PTR_S	a0, PT_R4(sp)
+	PTR_S	a1, PT_R5(sp)
+	PTR_S	a2, PT_R6(sp)
+	PTR_S	a3, PT_R7(sp)
+#ifdef CONFIG_64BIT
+	PTR_S	a4, PT_R8(sp)
+	PTR_S	a5, PT_R9(sp)
+	PTR_S	a6, PT_R10(sp)
+	PTR_S	a7, PT_R11(sp)
+#endif
+	.endm
+
+	.macro MCOUNT_RESTORE_REGS
+	PTR_L	ra, PT_R31(sp)
+	PTR_L	AT, PT_R1(sp)
+	PTR_L	a0, PT_R4(sp)
+	PTR_L	a1, PT_R5(sp)
+	PTR_L	a2, PT_R6(sp)
+	PTR_L	a3, PT_R7(sp)
+#ifdef CONFIG_64BIT
+	PTR_L	a4, PT_R8(sp)
+	PTR_L	a5, PT_R9(sp)
+	PTR_L	a6, PT_R10(sp)
+	PTR_L	a7, PT_R11(sp)
+#endif
+	PTR_ADDIU	sp, PT_SIZE
+.endm
+
+	.macro MCOUNT_SET_ARGS
+	move	a0, ra		/* arg1: next ip, selfaddr */
+	move	a1, AT		/* arg2: the caller's next ip, parent */
+	PTR_SUBU a0, MCOUNT_INSN_SIZE
+	.endm
+
+	.macro RETURN_BACK
+#ifdef CONFIG_32BIT
+	PTR_ADDIU	sp, 8
+#endif
+	jr ra
+	move ra, AT
+	.endm
+
+NESTED(_mcount, PT_SIZE, ra)
+	PTR_LA	t0, ftrace_stub
+	PTR_L	t1, ftrace_trace_function /* Prepare t1 for (1) */
+	bne	t0, t1, static_trace
+	nop
+
+	j	ftrace_stub
+	nop
+
+static_trace:
+	MCOUNT_SAVE_REGS
+
+	MCOUNT_SET_ARGS			/* call *ftrace_trace_function */
+	jalr	t1			/* (1) */
+	nop
+
+	MCOUNT_RESTORE_REGS
+	.globl ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+	END(_mcount)
+
+	.set at
+	.set reorder
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 225755d..1d04807 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -13,6 +13,7 @@
 #include <asm/checksum.h>
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
+#include <asm/ftrace.h>
 
 extern void *__bzero(void *__s, size_t __count);
 extern long __strncpy_from_user_nocheck_asm(char *__to,
@@ -51,3 +52,7 @@ EXPORT_SYMBOL(csum_partial_copy_nocheck);
 EXPORT_SYMBOL(__csum_partial_copy_user);
 
 EXPORT_SYMBOL(invalid_pte_table);
+#ifdef CONFIG_FUNCTION_TRACER
+/* _mcount is defined in arch/mips/kernel/mcount.S */
+EXPORT_SYMBOL(_mcount);
+#endif
-- 
1.6.2.1

[PATCH -v6 05/13] tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST for MIPS

[Wu Zhangjin]

There is an exisiting common ftrace_test_stop_func() in
kernel/trace/ftrace.c, which is used to check the global variable
ftrace_trace_stop to determine whether stop the function tracing.

This patch implepment the MIPS specific one to speedup the procedure.

Thanks goes to Zhang Le for Cleaning it up.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/Kconfig         |    1 +
 arch/mips/kernel/mcount.S |    4 ++++
 2 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 6b33e88..a9bd992 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -5,6 +5,7 @@ config MIPS
 	select HAVE_OPROFILE
 	select HAVE_ARCH_KGDB
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB if !LEMOTE_FULOONG2E
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 0c39bc8..5dfaca8 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -64,6 +64,10 @@
 	.endm
 
 NESTED(_mcount, PT_SIZE, ra)
+	lw	t0, function_trace_stop
+	bnez	t0, ftrace_stub
+	nop
+
 	PTR_LA	t0, ftrace_stub
 	PTR_L	t1, ftrace_trace_function /* Prepare t1 for (1) */
 	bne	t0, t1, static_trace
-- 
1.6.2.1

[PATCH -v6 06/13] tracing: add an endian argument to scripts/recordmcount.pl

[Wu Zhangjin]

MIPS and some other architectures need this argument to handle
big/little endian respectively.

Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 scripts/Makefile.build  |    1 +
 scripts/recordmcount.pl |    6 +++---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 341b589..0b94d2f 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -207,6 +207,7 @@ endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
 cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
+	"$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \
 	"$(if $(CONFIG_64BIT),64,32)" \
 	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index bfb8b2c..465fe5e 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -99,13 +99,13 @@ $P =~ s@.*/@@g;
 
 my $V = '0.1';
 
-if ($#ARGV < 7) {
-	print "usage: $P arch bits objdump objcopy cc ld nm rm mv is_module inputfile\n";
+if ($#ARGV < 8) {
+	print "usage: $P arch endian bits objdump objcopy cc ld nm rm mv is_module inputfile\n";
 	print "version: $V\n";
 	exit(1);
 }
 
-my ($arch, $bits, $objdump, $objcopy, $cc,
+my ($arch, $endian, $bits, $objdump, $objcopy, $cc,
     $ld, $nm, $rm, $mv, $is_module, $inputfile) = @ARGV;
 
 # This file refers to mcount and shouldn't be ftraced, so lets' ignore it
-- 
1.6.2.1

[PATCH -v6 07/13] tracing: add dynamic function tracer support for MIPS

[Wu Zhangjin]

With dynamic function tracer, by default, _mcount is defined as an
"empty" function, it just return without any more action, just like the
static function tracer does. When enabling it in user-space, it will
jump to a real tracing function(ftrace_caller), and do some real job for
us.

Differ from the static function tracer, dynamic function tracer provides
two functions ftrace_make_call()/ftrace_make_nop() to enable/disable the
tracing of some indicated kernel functions(set_ftrace_filter).

In the -v4 version, the implementation of this support is basically the same as
X86 version does: _mcount is implemented as an empty function and ftrace_caller
is implemented as a real tracing function respectively.

But in this version, to support module tracing with the help of
-mlong-calls. the stuff becomes a little more complex, let's have a look
at the new calling to _mcount with -mlong-calls(result of "objdump -hdr
vmlinux").

	c:	3c030000 	lui	v1,0x0
			c: R_MIPS_HI16	_mcount
			c: R_MIPS_NONE	*ABS*
			c: R_MIPS_NONE	*ABS*
	10:	64630000 	daddiu	v1,v1,0
			10: R_MIPS_LO16	_mcount
			10: R_MIPS_NONE	*ABS*
			10: R_MIPS_NONE	*ABS*
	14:	03e0082d 	move	at,ra
	18:	0060f809 	jalr	v1

and the old version without -mlong-calls looks like this:

	108:   03e0082d        move    at,ra
	10c:   0c000000        jal     0 <fpcsr_pending>
                        10c: R_MIPS_26  _mcount
                        10c: R_MIPS_NONE        *ABS*
                        10c: R_MIPS_NONE        *ABS*
	110:   00020021        nop

In the old version, there is only one "_mcount" string for every kernel
function, so, we just need to match this one in mcount_regex of
scripts/recordmcount.pl, but in the new version, we need to choose one
of the two to match. Herein, I choose the first one with "R_MIPS_HI16
_mcount".

and In the old verion, without module tracing support, we just need to replace
"jal _mcount" by "jal ftrace_caller" to do real tracing, and filter the tracing
of some kernel functions via replacing it by a nop instruction.

but as we have described before, the instruction "jal ftrace_caller" only left
32bit length for the address of ftrace_caller, it will fail when calling from
the module space. so, herein, we must replace something else.

the basic idea is loading the address of ftrace_caller to v1 via changing these
two instructions:

	lui	v1,0x0
	addiu	v1,v1,0

If we want to enable the tracing, we need to replace the above instructions to:

	lui	v1, HI_16BIT_ftrace_caller
	addiu	v1, v1, LOW_16BIT_ftrace_caller

If we want to stop the tracing of the indicated kernel functions, we
just need to replace the "jalr v1" to a nop instruction. but we need to
replace two instructions and encode the above two instructions
oursevles.

Is there a simpler solution, Yes! Here it is, in this version, we put _mcount
and ftrace_caller together, which means the address of _mcount and
ftrace_caller is the same:

_mcount:
ftrace_caller:
	j	ftrace_stub
	nop

	...(do real tracing here)...

ftrace_stub:
	jr	ra
	move	ra, at

By default, the kernel functions call _mcount, and then jump to ftrace_stub and
return. and when we want to do real tracing, we just need to remove that "j
ftrace_stub", and it will run through the two "nop" instructions and then do
the real tracing job.

what about filtering job? we just need to switching the "jalr v1" and "nop"
instruction.

In linux-mips64, there will be some local symbols, whose name are
prefixed by $L, which need to be filtered. thanks goes to Steven for
writing the mips64-specific function_regex.

In a conclusion, with RISC, things becomes easier with such a "stupid"
trick, RISC is something like K.I.S.S, and also, there are lots of
"simple" tricks in the whole ftrace support, thanks goes to Steven and
the other folks for providing such a wonderful tracing framework!

Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 arch/mips/Kconfig              |    2 +
 arch/mips/include/asm/ftrace.h |   12 ++++++
 arch/mips/kernel/Makefile      |    3 +-
 arch/mips/kernel/ftrace.c      |   76 ++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mcount.S      |   29 +++++++++++++++
 scripts/recordmcount.pl        |   38 ++++++++++++++++++++
 6 files changed, 159 insertions(+), 1 deletions(-)
 create mode 100644 arch/mips/kernel/ftrace.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a9bd992..147fbbc 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -6,6 +6,8 @@ config MIPS
 	select HAVE_ARCH_KGDB
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_FTRACE_MCOUNT_RECORD
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB if !LEMOTE_FULOONG2E
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index 5f8ebcf..d5771e8 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -19,6 +19,18 @@
 extern void _mcount(void);
 #define mcount _mcount
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* 12 is the offset of "jalr v1" from the first loading instruction
+	 * "lui v1, HI_16BIT", please get more information from
+	 * scripts/recordmcount.pl */
+	return addr + 12;
+}
+
+struct dyn_arch_ftrace {
+};
+#endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 #endif /* _ASM_MIPS_FTRACE_H */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 38e704a..3cda3ab 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -10,6 +10,7 @@ obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_trace_clock.o = -pg
+CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
@@ -30,7 +31,7 @@ obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
 obj-$(CONFIG_FTRACE)		+= trace_clock.o
-obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
 
 obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS32)	+= r4k_fpu.o r4k_switch.o
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
new file mode 100644
index 0000000..0be30cf
--- /dev/null
+++ b/arch/mips/kernel/ftrace.c
@@ -0,0 +1,76 @@
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ *
+ * Thanks goes to Steven Rostedt for writing the original x86 version.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/init.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#define JAL 0x0c000000		/* jump & link: ip --> ra, jump to target */
+#define ADDR_MASK 0x03ffffff	/*  op_code|addr : 31...26|25 ....0 */
+
+#ifdef CONFIG_CPU_LOONGSON2F
+static unsigned int ftrace_nop = 0x00020021;
+#else
+static unsigned int ftrace_nop = 0x00000000;
+#endif
+
+static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
+{
+	*(unsigned int *)ip = new_code;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	return ftrace_modify_code(rec->ip, ftrace_nop);
+}
+
+static int modified;	/* initialized as 0 by default */
+#define JALR_V1 0x0060f809
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	/* We just need to remove the "j ftrace_stub" at the fist time! */
+	if (modified == 0) {
+		modified = 1;
+		ftrace_modify_code(addr, ftrace_nop);
+	}
+	return ftrace_modify_code(rec->ip, JALR_V1);
+}
+
+#define FTRACE_CALL_IP ((unsigned long)(&ftrace_call))
+#define jump_insn_encode(op_code, addr) \
+	((unsigned int)((op_code) | (((addr) >> 2) & ADDR_MASK)))
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned int new;
+
+	new = jump_insn_encode(JAL, (unsigned long)func);
+
+	return ftrace_modify_code(FTRACE_CALL_IP, new);
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	/* The return code is retured via data */
+	*(unsigned long *)data = 0;
+
+	return 0;
+}
+#endif				/* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 5dfaca8..389be7b 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -63,6 +63,33 @@
 	move ra, AT
 	.endm
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+NESTED(ftrace_caller, PT_SIZE, ra)
+	.globl _mcount
+_mcount:
+	j	ftrace_stub
+	nop
+	lw	t0, function_trace_stop
+	bnez	t0, ftrace_stub
+	nop
+
+	MCOUNT_SAVE_REGS
+
+	MCOUNT_SET_ARGS
+	.globl ftrace_call
+ftrace_call:
+	nop	/* a placeholder for the call to a real tracing function */
+	nop	/* Do not touch me, I'm in the dealy slot of "jal func" */
+
+	MCOUNT_RESTORE_REGS
+	.globl ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+	END(ftrace_caller)
+
+#else	/* ! CONFIG_DYNAMIC_FTRACE */
+
 NESTED(_mcount, PT_SIZE, ra)
 	lw	t0, function_trace_stop
 	bnez	t0, ftrace_stub
@@ -89,5 +116,7 @@ ftrace_stub:
 	RETURN_BACK
 	END(_mcount)
 
+#endif	/* ! CONFIG_DYNAMIC_FTRACE */
+
 	.set at
 	.set reorder
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 465fe5e..d83c0c1 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -246,6 +246,44 @@ if ($arch eq "x86_64") {
     $ld .= " -m elf64_sparc";
     $cc .= " -m64";
     $objcopy .= " -O elf64-sparc";
+
+} elsif ($arch eq "mips") {
+    # To enable module support, we need to enable the -mlong-calls option
+    # of gcc for MIPS, after using this option, we can not get the real
+    # offset of the calling to _mcount, but the offset of the first loading
+    # instruction or the second one, here we get the first one, and then,
+    # we plus it with 12 in arch/mips/kernel/asm/ftrace.h.
+    #
+    #       c:	3c030000 	lui	v1,0x0
+    #			c: R_MIPS_HI16	_mcount
+    #			c: R_MIPS_NONE	*ABS*
+    #			c: R_MIPS_NONE	*ABS*
+    #      10:	64630000 	daddiu	v1,v1,0
+    #			10: R_MIPS_LO16	_mcount
+    #			10: R_MIPS_NONE	*ABS*
+    #			10: R_MIPS_NONE	*ABS*
+    #      14:	03e0082d 	move	at,ra
+    #      18:	0060f809 	jalr	v1
+    $mcount_regex = "^\\s*([0-9a-fA-F]+): R_MIPS_HI16\\s+_mcount\$";
+    $objdump .= " -Melf-trad".$endian."mips ";
+
+    if ($endian eq "big") {
+	    $endian = " -EB ";
+	    $ld .= " -melf".$bits."btsmip";
+    } else {
+	    $endian = " -EL ";
+	    $ld .= " -melf".$bits."ltsmip";
+    }
+
+    $cc .= " -mno-abicalls -fno-pic -mabi=" . $bits . $endian;
+    $ld .= $endian;
+
+    if ($bits == 64) {
+	    $function_regex =
+		"^([0-9a-fA-F]+)\\s+<(.|[^\$]L.*?|\$[^L].*?|[^\$][^L].*?)>:";
+	    $type = ".dword";
+    }
+
 } else {
     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 }
-- 
1.6.2.1

[PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Wu Zhangjin]

This patch add a new section for MIPS to record the block of the hardirq
handling for function graph tracer(print_graph_irq) via adding the
__irq_entry annotation to the the entrypoints of the hardirqs(the block
with irq_enter()...irq_exit()).

Thanks goes to Steven & Frederic Weisbecker for their feedbacks.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/include/asm/irq.h    |   29 ++---------------------------
 arch/mips/kernel/irq.c         |   34 ++++++++++++++++++++++++++++++++++
 arch/mips/kernel/smp.c         |    3 ++-
 arch/mips/kernel/smtc.c        |   21 ++++++++++++++-------
 arch/mips/kernel/vmlinux.lds.S |    1 +
 arch/mips/sgi-ip22/ip22-int.c  |    3 ++-
 arch/mips/sgi-ip22/ip22-time.c |    3 ++-
 7 files changed, 57 insertions(+), 37 deletions(-)

diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 09b08d0..6cdd8c2 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -113,36 +113,11 @@ do {									\
 
 #endif
 
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- *
- * Ideally there should be away to get this into kernel/irq/handle.c to
- * avoid the overhead of a call for just a tiny function ...
- */
-#define do_IRQ(irq)							\
-do {									\
-	irq_enter();							\
-	__DO_IRQ_SMTC_HOOK(irq);					\
-	generic_handle_irq(irq);					\
-	irq_exit();							\
-} while (0)
+extern unsigned int do_IRQ(unsigned int irq);
 
 #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-/*
- * To avoid inefficient and in some cases pathological re-checking of
- * IRQ affinity, we have this variant that skips the affinity check.
- */
-
 
-#define do_IRQ_no_affinity(irq)						\
-do {									\
-	irq_enter();							\
-	__NO_AFFINITY_IRQ_SMTC_HOOK(irq);				\
-	generic_handle_irq(irq);					\
-	irq_exit();							\
-} while (0)
+extern unsigned int do_IRQ_no_affinity(unsigned int irq);
 
 #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
 
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 7b845ba..c10ea8f 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/kgdb.h>
+#include <linux/ftrace.h>
 
 #include <asm/atomic.h>
 #include <asm/system.h>
@@ -150,3 +151,36 @@ void __init init_IRQ(void)
 		kgdb_early_setup = 1;
 #endif
 }
+
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+unsigned int __irq_entry do_IRQ(unsigned int irq)
+{
+	irq_enter();
+	__DO_IRQ_SMTC_HOOK(irq);
+	generic_handle_irq(irq);
+	irq_exit();
+
+	return 1;
+}
+
+#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
+/*
+ * To avoid inefficient and in some cases pathological re-checking of
+ * IRQ affinity, we have this variant that skips the affinity check.
+ */
+
+unsigned int __irq_entry do_IRQ_no_affinity(unsigned int irq)
+{
+	irq_enter();
+	__NO_AFFINITY_IRQ_SMTC_HOOK(irq);
+	generic_handle_irq(irq);
+	irq_exit();
+
+	return 1;
+}
+
+#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index e72e684..6cdca19 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -32,6 +32,7 @@
 #include <linux/cpumask.h>
 #include <linux/cpu.h>
 #include <linux/err.h>
+#include <linux/ftrace.h>
 
 #include <asm/atomic.h>
 #include <asm/cpu.h>
@@ -130,7 +131,7 @@ asmlinkage __cpuinit void start_secondary(void)
 /*
  * Call into both interrupt handlers, as we share the IPI for them
  */
-void smp_call_function_interrupt(void)
+void __irq_entry smp_call_function_interrupt(void)
 {
 	irq_enter();
 	generic_smp_call_function_single_interrupt();
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 24630fd..75034a8 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
+#include <linux/ftrace.h>
 
 #include <asm/cpu.h>
 #include <asm/processor.h>
@@ -939,23 +940,29 @@ static void ipi_call_interrupt(void)
 
 DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 
-void ipi_decode(struct smtc_ipi *pipi)
+static void __irq_entry smtc_clock_tick_interrupt(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *cd;
+	int irq = MIPS_CPU_IRQ_BASE + 1;
+
+	irq_enter();
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+	cd = &per_cpu(mips_clockevent_device, cpu);
+	cd->event_handler(cd);
+	irq_exit();
+}
+
+void ipi_decode(struct smtc_ipi *pipi)
+{
 	void *arg_copy = pipi->arg;
 	int type_copy = pipi->type;
-	int irq = MIPS_CPU_IRQ_BASE + 1;
 
 	smtc_ipi_nq(&freeIPIq, pipi);
 
 	switch (type_copy) {
 	case SMTC_CLOCK_TICK:
-		irq_enter();
-		kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
-		cd = &per_cpu(mips_clockevent_device, cpu);
-		cd->event_handler(cd);
-		irq_exit();
+		smtc_clock_tick_interrupt();
 		break;
 
 	case LINUX_SMP_IPI:
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 162b299..f25df73 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -46,6 +46,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		IRQENTRY_TEXT
 		*(.text.*)
 		*(.fixup)
 		*(.gnu.warning)
diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
index 0ecd5fe..383f11d 100644
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
+#include <linux/ftrace.h>
 
 #include <asm/irq_cpu.h>
 #include <asm/sgi/hpc3.h>
@@ -150,7 +151,7 @@ static void indy_local1_irqdispatch(void)
 
 extern void ip22_be_interrupt(int irq);
 
-static void indy_buserror_irq(void)
+static void __irq_entry indy_buserror_irq(void)
 {
 	int irq = SGI_BUSERR_IRQ;
 
diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
index c8f7d23..603fc91 100644
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/time.h>
+#include <linux/ftrace.h>
 
 #include <asm/cpu.h>
 #include <asm/mipsregs.h>
@@ -115,7 +116,7 @@ __init void plat_time_init(void)
 }
 
 /* Generic SGI handler for (spurious) 8254 interrupts */
-void indy_8254timer_irq(void)
+void __irq_entry indy_8254timer_irq(void)
 {
 	int irq = SGI_8254_0_IRQ;
 	ULONG cnt;
-- 
1.6.2.1

[PATCH -v6 09/13] tracing: Add __arch_notrace for arch specific requirement

[Wu Zhangjin]

Some arch need to not trace the common functions, but the other archs do
not need it, so, we add a new __arch_notrace to solve this problem, if
your arch need it, define it in your arch specific ftrace.h, otherwise,
ignore it! and if you just need to enable it with function graph tracer,
wrap it with "#ifdef CONFIG_FUNCTION_GRAPH_TRACER ... #endif".

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 include/linux/ftrace.h |   19 +++++++++++++++++++
 1 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 0b4f97d..b3bd349 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -511,4 +511,23 @@ static inline void trace_hw_branch_oops(void) {}
 
 #endif /* CONFIG_HW_BRANCH_TRACER */
 
+/* Arch Specific notrace
+ *
+ * If your arch need it, define it in the arch specific ftrace.h
+ *
+ *	#define __arch_notrace
+ *
+ * If only need it with function graph tracer, wrap it.
+ *
+ *	#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ *	#define __arch_notrace
+ *	#endif
+ */
+#ifndef __arch_notrace
+#define __arch_notrace
+#else
+#undef __arch_notrace
+#define __arch_notrace	notrace
+#endif
+
 #endif /* _LINUX_FTRACE_H */
-- 
1.6.2.1

[PATCH -v6 10/13] tracing: not trace the timecounter_read* in kernel/time/clocksource.c

[Wu Zhangjin]

Some platforms(i.e. MIPS) need these two functions to get the precise
timestamp, we use __arch_notrace(added in the last patch) to annotate
it. By default, __arch_notrace is empty, so, this patch have no
influence to the original functions, but if you really not need to trace
them, just add the following line into the arch specific ftrace.h:

	#define __arch_notrace

If only want to enable it for function graph tracer, add these lines
instead.

	#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	#define __arch_notrace
	#endif

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 kernel/time/clocksource.c |    5 +++--
 1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 5e18c6a..91acdf7 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -30,6 +30,7 @@
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
 #include <linux/tick.h>
 #include <linux/kthread.h>
+#include <linux/ftrace.h>
 
 void timecounter_init(struct timecounter *tc,
 		      const struct cyclecounter *cc,
@@ -52,7 +53,7 @@ EXPORT_SYMBOL(timecounter_init);
  * The first call to this function for a new time counter initializes
  * the time tracking and returns an undefined result.
  */
-static u64 timecounter_read_delta(struct timecounter *tc)
+static u64 __arch_notrace timecounter_read_delta(struct timecounter *tc)
 {
 	cycle_t cycle_now, cycle_delta;
 	u64 ns_offset;
@@ -72,7 +73,7 @@ static u64 timecounter_read_delta(struct timecounter *tc)
 	return ns_offset;
 }
 
-u64 timecounter_read(struct timecounter *tc)
+u64 __arch_notrace timecounter_read(struct timecounter *tc)
 {
 	u64 nsec;
 
-- 
1.6.2.1

[PATCH -v6 11/13] tracing: not trace mips_timecounter_read() for MIPS

[Wu Zhangjin]

We use mips_timecounter_read() to get the timestamp in MIPS, so, it's
better to not trace it and it's subroutines, otherwise, it will goto
recursion(hang) when using function graph tracer. we use the
__notrace_funcgraph annotation to indicate them not to be traced.

And there are two common functions called by mips_timecounter_read(), we
define the __arch_notrace macro to ensure they are not to be traced.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/include/asm/ftrace.h |    5 +++++
 arch/mips/kernel/csrc-r4k.c    |    5 +++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index d5771e8..452b996 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -31,6 +31,11 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 struct dyn_arch_ftrace {
 };
 #endif /*  CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#define __arch_notrace
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 #endif /* _ASM_MIPS_FTRACE_H */
diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index 4e7705f..0c1bf80 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -8,6 +8,7 @@
 #include <linux/clocksource.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/ftrace.h>
 
 #include <asm/time.h>
 
@@ -42,7 +43,7 @@ static struct timecounter r4k_tc = {
 	.cc = NULL,
 };
 
-static cycle_t r4k_cc_read(const struct cyclecounter *cc)
+static cycle_t __notrace_funcgraph r4k_cc_read(const struct cyclecounter *cc)
 {
 	return read_c0_count();
 }
@@ -66,7 +67,7 @@ int __init init_r4k_timecounter(void)
 	return 0;
 }
 
-u64 r4k_timecounter_read(void)
+u64 __notrace_funcgraph r4k_timecounter_read(void)
 {
 	u64 clock;
 
-- 
1.6.2.1

[PATCH -v6 12/13] tracing: add function graph tracer support for MIPS

[Wu Zhangjin]

The implementation of function graph tracer for MIPS is a little
different from X86.

in MIPS, gcc(with -pg) only transfer the caller's return address(at) and
the _mcount's return address(ra) to us.

move at, ra
jal _mcount

if the function is a leaf, it will no save the return address(ra):

ffffffff80101298 <au1k_wait>:
ffffffff80101298:       67bdfff0        daddiu  sp,sp,-16
ffffffff8010129c:       ffbe0008        sd      s8,8(sp)
ffffffff801012a0:       03a0f02d        move    s8,sp
ffffffff801012a4:       03e0082d        move    at,ra
ffffffff801012a8:       0c042930        jal     ffffffff8010a4c0 <_mcount>
ffffffff801012ac:       00020021        nop

so, we can hijack it directly in _mcount, but if the function is non-leaf, the
return address is saved in the stack.

ffffffff80133030 <copy_process>:
ffffffff80133030:       67bdff50        daddiu  sp,sp,-176
ffffffff80133034:       ffbe00a0        sd      s8,160(sp)
ffffffff80133038:       03a0f02d        move    s8,sp
ffffffff8013303c:       ffbf00a8        sd      ra,168(sp)
ffffffff80133040:       ffb70098        sd      s7,152(sp)
ffffffff80133044:       ffb60090        sd      s6,144(sp)
ffffffff80133048:       ffb50088        sd      s5,136(sp)
ffffffff8013304c:       ffb40080        sd      s4,128(sp)
ffffffff80133050:       ffb30078        sd      s3,120(sp)
ffffffff80133054:       ffb20070        sd      s2,112(sp)
ffffffff80133058:       ffb10068        sd      s1,104(sp)
ffffffff8013305c:       ffb00060        sd      s0,96(sp)
ffffffff80133060:       03e0082d        move    at,ra
ffffffff80133064:       0c042930        jal     ffffffff8010a4c0 <_mcount>
ffffffff80133068:       00020021        nop

but we can not get the exact stack address(which saved ra) directly in
_mcount, we need to search the content of at register in the stack space
or search the "s{d,w} ra, offset(sp)" instruction in the text. 'Cause we
can not prove there is only a match in the stack space, so, we search
the text instead.

as we can see, if the first instruction above "move at, ra" is "move
s8(fp), sp"(only available with -fno-omit-frame-pointer which is enabled
by CONFIG_FRAME_POINTER), it is a leaf function, so we hijack the at
register directly via putting &return_to_handler into it, otherwise, we
search the "s{d,w} ra, offset(sp)" instruction to get the stack offset,
and then the stack address. we use the above copy_process() as an
example, we at last find "ffbf00a8", 0xa8 is the stack offset, we plus
it with s8(fp), that is the stack address, we hijack the content via
writing the &return_to_handler in.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/Kconfig         |    1 +
 arch/mips/kernel/ftrace.c |   93 +++++++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mcount.S |   47 ++++++++++++++++++++++-
 3 files changed, 140 insertions(+), 1 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 147fbbc..de690fd 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -8,6 +8,7 @@ config MIPS
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_GRAPH_TRACER
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB if !LEMOTE_FULOONG2E
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 0be30cf..4cf11f5 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -13,6 +13,8 @@
 #include <linux/ftrace.h>
 
 #include <asm/cacheflush.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
@@ -74,3 +76,94 @@ int __init ftrace_dyn_arch_init(void *data)
 	return 0;
 }
 #endif				/* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#define S_RA    (0x2fbf << 16)	/* 32bit: afbf, 64bit: ffbf */
+#define MOV_FP_SP       0x03a0f021	/* 32bit: 0x03a0f021, 64bit: 0x03a0f02d */
+#define STACK_OFFSET_MASK	0xfff	/* stack offset range: 0 ~ PT_SIZE(304) */
+
+unsigned long ftrace_get_parent_addr(unsigned long self_addr,
+				     unsigned long parent,
+				     unsigned long parent_addr,
+				     unsigned long fp)
+{
+	unsigned long sp, ip, ra;
+	unsigned int code;
+
+	/* move to the instruction "move ra, at" */
+	ip = self_addr - 8;
+
+	/* search the text until finding the "move s8, sp" instruction or
+	 * "s{d,w} ra, offset(sp)" instruction */
+	do {
+		ip -= 4;
+
+		/* get the code at "ip" */
+		code = *(unsigned int *)ip;
+
+		/* If we hit the "move s8(fp), sp" instruction before finding
+		 * where the ra is stored, then this is a leaf function and it
+		 * does not store the ra on the stack. */
+		if ((code & MOV_FP_SP) == MOV_FP_SP)
+			return parent_addr;
+	} while (((code & S_RA) != S_RA));
+
+	sp = fp + (code & STACK_OFFSET_MASK);
+	ra = *(unsigned long *)sp;
+
+	if (ra == parent)
+		return sp;
+
+	ftrace_graph_stop();
+	WARN_ON(1);
+	return parent_addr;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long fp)
+{
+	unsigned long old;
+	struct ftrace_graph_ent trace;
+	unsigned long return_hooker = (unsigned long)
+	    &return_to_handler;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/* "parent" is the stack address saved the return address of the caller
+	 * of _mcount, for a leaf function not save the return address in the
+	 * stack address, so, we "emulate" one in _mcount's stack space, and
+	 * hijack it directly, but for a non-leaf function, it will save the
+	 * return address to the its stack space, so, we can not hijack the
+	 * "parent" directly, but need to find the real stack address,
+	 * ftrace_get_parent_addr() does it!
+	 */
+
+	old = *parent;
+
+	parent = (unsigned long *)ftrace_get_parent_addr(self_addr, old,
+							 (unsigned long)parent,
+							 fp);
+
+	*parent = return_hooker;
+
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth, fp) ==
+	    -EBUSY) {
+		*parent = old;
+		return;
+	}
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		*parent = old;
+	}
+}
+#endif				/* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 389be7b..a9ba888 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -99,7 +99,15 @@ NESTED(_mcount, PT_SIZE, ra)
 	PTR_L	t1, ftrace_trace_function /* Prepare t1 for (1) */
 	bne	t0, t1, static_trace
 	nop
-
+#ifdef	CONFIG_FUNCTION_GRAPH_TRACER
+	PTR_L	t2, ftrace_graph_return
+	bne	t0, t2, ftrace_graph_caller
+	nop
+	PTR_LA	t0, ftrace_graph_entry_stub
+	PTR_L	t2, ftrace_graph_entry
+	bne	t0, t2, ftrace_graph_caller
+	nop
+#endif
 	j	ftrace_stub
 	nop
 
@@ -118,5 +126,42 @@ ftrace_stub:
 
 #endif	/* ! CONFIG_DYNAMIC_FTRACE */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+NESTED(ftrace_graph_caller, PT_SIZE, ra)
+	MCOUNT_SAVE_REGS
+
+	PTR_LA	a0, PT_R1(sp)	/* arg1: &AT -> a0 */
+	move	a1, ra		/* arg2: next ip, selfaddr */
+	PTR_SUBU a1, MCOUNT_INSN_SIZE
+	move	a2, fp		/* arg3: frame pointer */
+	jal	prepare_ftrace_return
+	nop
+
+	MCOUNT_RESTORE_REGS
+	RETURN_BACK
+	END(ftrace_graph_caller)
+
+	.align	2
+	.globl	return_to_handler
+return_to_handler:
+	PTR_SUBU	sp, PT_SIZE
+	PTR_S	v0, PT_R2(sp)
+	PTR_S	v1, PT_R3(sp)
+
+	jal	ftrace_return_to_handler
+	nop
+
+	/* restore the real parent address: v0 -> ra */
+	move	ra, v0
+
+	PTR_L	v0, PT_R2(sp)
+	PTR_L	v1, PT_R3(sp)
+	PTR_ADDIU	sp, PT_SIZE
+
+	jr	ra
+	nop
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 	.set at
 	.set reorder
-- 
1.6.2.1

[PATCH -v6 13/13] tracing: add dynamic function graph tracer for MIPS

[Wu Zhangjin]

This patch make function graph tracer work with dynamic function tracer.

To share the source code of dynamic function tracer(MCOUNT_SAVE_REGS),
and avoid restoring the whole saved registers, we need to restore the ra
register from the stack.

Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
---
 arch/mips/kernel/ftrace.c |   21 +++++++++++++++++++++
 arch/mips/kernel/mcount.S |   14 ++++++++++++--
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 4cf11f5..1c02e65 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -79,6 +79,27 @@ int __init ftrace_dyn_arch_init(void *data)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+extern void ftrace_graph_call(void);
+#define JMP	0x08000000	/* jump to target directly */
+#define CALL_FTRACE_GRAPH_CALLER \
+	jump_insn_encode(JMP, (unsigned long)(&ftrace_graph_caller))
+#define FTRACE_GRAPH_CALL_IP	((unsigned long)(&ftrace_graph_call))
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP,
+				  CALL_FTRACE_GRAPH_CALLER);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	return ftrace_modify_code(FTRACE_GRAPH_CALL_IP, ftrace_nop);
+}
+
+#endif				/* !CONFIG_DYNAMIC_FTRACE */
+
 #define S_RA    (0x2fbf << 16)	/* 32bit: afbf, 64bit: ffbf */
 #define MOV_FP_SP       0x03a0f021	/* 32bit: 0x03a0f021, 64bit: 0x03a0f02d */
 #define STACK_OFFSET_MASK	0xfff	/* stack offset range: 0 ~ PT_SIZE(304) */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index a9ba888..260719d 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -82,6 +82,13 @@ ftrace_call:
 	nop	/* a placeholder for the call to a real tracing function */
 	nop	/* Do not touch me, I'm in the dealy slot of "jal func" */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.globl ftrace_graph_call
+ftrace_graph_call:
+	nop
+	nop
+#endif
+
 	MCOUNT_RESTORE_REGS
 	.globl ftrace_stub
 ftrace_stub:
@@ -129,10 +136,13 @@ ftrace_stub:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 NESTED(ftrace_graph_caller, PT_SIZE, ra)
+#ifdef CONFIG_DYNAMIC_FTRACE
+	PTR_L	a1, PT_R31(sp)	/* load the original ra from the stack */
+#else
 	MCOUNT_SAVE_REGS
-
-	PTR_LA	a0, PT_R1(sp)	/* arg1: &AT -> a0 */
 	move	a1, ra		/* arg2: next ip, selfaddr */
+#endif
+	PTR_LA	a0, PT_R1(sp)	/* arg1: &AT -> a0 */
 	PTR_SUBU a1, MCOUNT_INSN_SIZE
 	move	a2, fp		/* arg3: frame pointer */
 	jal	prepare_ftrace_return
-- 
1.6.2.1

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Frederic Weisbecker]

On Mon, Oct 26, 2009 at 11:13:25PM +0800, Wu Zhangjin wrote:
> This patch add a new section for MIPS to record the block of the hardirq
> handling for function graph tracer(print_graph_irq) via adding the
> __irq_entry annotation to the the entrypoints of the hardirqs(the block
> with irq_enter()...irq_exit()).
> 
> Thanks goes to Steven & Frederic Weisbecker for their feedbacks.
> 
> Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> +
> +/*
> + * do_IRQ handles all normal device IRQ's (the special
> + * SMP cross-CPU interrupts have their own specific
> + * handlers).
> + */
> +unsigned int __irq_entry do_IRQ(unsigned int irq)
> +{
> +	irq_enter();
> +	__DO_IRQ_SMTC_HOOK(irq);
> +	generic_handle_irq(irq);
> +	irq_exit();
> +
> +	return 1;
> +}



Nano-neat:

Why is it returning a value, it doesn't seem needed (the macro
version didn't)?

Anyway, that looks good to me. I hope the changes from macro
to function calls will be ack by the MIPS maintainers.

Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Wu Zhangjin]

Hi,

On Mon, 2009-11-09 at 03:26 +0100, Frederic Weisbecker wrote:
> On Mon, Oct 26, 2009 at 11:13:25PM +0800, Wu Zhangjin wrote:
> > This patch add a new section for MIPS to record the block of the hardirq
> > handling for function graph tracer(print_graph_irq) via adding the
> > __irq_entry annotation to the the entrypoints of the hardirqs(the block
> > with irq_enter()...irq_exit()).
> > 
> > Thanks goes to Steven & Frederic Weisbecker for their feedbacks.
> > 
> > Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> > +
> > +/*
> > + * do_IRQ handles all normal device IRQ's (the special
> > + * SMP cross-CPU interrupts have their own specific
> > + * handlers).
> > + */
> > +unsigned int __irq_entry do_IRQ(unsigned int irq)
> > +{
> > +	irq_enter();
> > +	__DO_IRQ_SMTC_HOOK(irq);
> > +	generic_handle_irq(irq);
> > +	irq_exit();
> > +
> > +	return 1;
> > +}
> 
> 
> 
> Nano-neat:
> 
> Why is it returning a value, it doesn't seem needed (the macro
> version didn't)?
> 

Will remove it later. 

> Anyway, that looks good to me. I hope the changes from macro
> to function calls will be ack by the MIPS maintainers.
> 

Hope Ralf give some feedbacks about it ;)

> Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
> 

Thanks!

BTW: 

Who should I resend this patchset to? you or Steven? If this patchset
are okay, I will rebase it on the latest tracing/core branch of -tip and
send the latest version out, and hope you can apply it, otherwise, I
need to rebase it to the future mainline versions again and again ;) and
at least, I have tested all of them and their combinations on YeeLoong
netbook, they work well. of course, more testing report from the other
MIPS developers are welcome ;)

Regards,
	Wu Zhangjin

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Wu Zhangjin]

Hi,

On Mon, 2009-11-09 at 03:26 +0100, Frederic Weisbecker wrote:
> On Mon, Oct 26, 2009 at 11:13:25PM +0800, Wu Zhangjin wrote:
> > This patch add a new section for MIPS to record the block of the hardirq
> > handling for function graph tracer(print_graph_irq) via adding the
> > __irq_entry annotation to the the entrypoints of the hardirqs(the block
> > with irq_enter()...irq_exit()).
> > 
> > Thanks goes to Steven & Frederic Weisbecker for their feedbacks.
> > 
> > Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> > +
> > +/*
> > + * do_IRQ handles all normal device IRQ's (the special
> > + * SMP cross-CPU interrupts have their own specific
> > + * handlers).
> > + */
> > +unsigned int __irq_entry do_IRQ(unsigned int irq)
> > +{
> > +	irq_enter();
> > +	__DO_IRQ_SMTC_HOOK(irq);
> > +	generic_handle_irq(irq);
> > +	irq_exit();
> > +
> > +	return 1;
> > +}
> 
> 
> 
> Nano-neat:
> 
> Why is it returning a value, it doesn't seem needed (the macro
> version didn't)?
> 

Will remove it later. 

> Anyway, that looks good to me. I hope the changes from macro
> to function calls will be ack by the MIPS maintainers.
> 

Hope Ralf give some feedbacks about it ;)

> Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
> 

Thanks!

BTW: 

Who should I resend this patchset to? you or Steven? If this patchset
are okay, I will rebase it on the latest tracing/core branch of -tip and
send the latest version out, and hope you can apply it, otherwise, I
need to rebase it to the future mainline versions again and again ;) and
at least, I have tested all of them and their combinations on YeeLoong
netbook, they work well. of course, more testing report from the other
MIPS developers are welcome ;)

Regards,
	Wu Zhangjin

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Frederic Weisbecker]

On Mon, Nov 09, 2009 at 11:31:08AM +0800, Wu Zhangjin wrote:
> Who should I resend this patchset to? you or Steven? If this patchset
> are okay, I will rebase it on the latest tracing/core branch of -tip and
> send the latest version out, and hope you can apply it, otherwise, I
> need to rebase it to the future mainline versions again and again ;) and
> at least, I have tested all of them and their combinations on YeeLoong
> netbook, they work well. of course, more testing report from the other
> MIPS developers are welcome ;)
> 
> Regards,
> 	Wu Zhangjin


You can keep the current Cc list so that we are all uptodate with the
latest state. I don't think you need to rebase against latest tracing/core
as there doesn't seem to be conflicatble changes inside added lately.
The person who is likely to apply it is Steven as he can test it :)

Thanks.

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Steven Rostedt]

On Mon, 2009-11-09 at 11:31 +0800, Wu Zhangjin wrote:
> Hi,

> BTW: 
> 
> Who should I resend this patchset to? you or Steven? If this patchset
> are okay, I will rebase it on the latest tracing/core branch of -tip and
> send the latest version out, and hope you can apply it, otherwise, I
> need to rebase it to the future mainline versions again and again ;) and
> at least, I have tested all of them and their combinations on YeeLoong
> netbook, they work well. of course, more testing report from the other
> MIPS developers are welcome ;)

Just Cc Frederic, Ingo and myself. We'll figure out who will pull it in.
I'll probably do it since I have the MIPS box to do the testing.

Note, I'm currently in NYC at a conference and will not be pulling in
anything till Wednesday when I get back.

Any changes to MIPS arch must have an Acked-by: the MIPS maintainer
(Ralf?) before anything can be pulled in.

Thanks!

-- Steve

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Steven Rostedt]

On Mon, 2009-11-09 at 11:31 +0800, Wu Zhangjin wrote:

> Who should I resend this patchset to? you or Steven? If this patchset
> are okay, I will rebase it on the latest tracing/core branch of -tip and
> send the latest version out, and hope you can apply it, otherwise, I
> need to rebase it to the future mainline versions again and again ;) and
> at least, I have tested all of them and their combinations on YeeLoong
> netbook, they work well. of course, more testing report from the other
> MIPS developers are welcome ;)

Oh, and yes, just base it with tracing/core. We should be able to handle
the conflicts then.

Thanks,

-- Steve

Re: [PATCH -v6 08/13] tracing: add IRQENTRY_EXIT section for MIPS

[Wu Zhangjin]

Hi Ralf,

This one is also MIPS relative, also need your feedback ;)

Thanks & Regards,
	Wu Zhangjin

On Mon, 2009-10-26 at 23:13 +0800, Wu Zhangjin wrote:
> This patch add a new section for MIPS to record the block of the hardirq
> handling for function graph tracer(print_graph_irq) via adding the
> __irq_entry annotation to the the entrypoints of the hardirqs(the block
> with irq_enter()...irq_exit()).
> 
> Thanks goes to Steven & Frederic Weisbecker for their feedbacks.
> 
> Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> ---
>  arch/mips/include/asm/irq.h    |   29 ++---------------------------
>  arch/mips/kernel/irq.c         |   34 ++++++++++++++++++++++++++++++++++
>  arch/mips/kernel/smp.c         |    3 ++-
>  arch/mips/kernel/smtc.c        |   21 ++++++++++++++-------
>  arch/mips/kernel/vmlinux.lds.S |    1 +
>  arch/mips/sgi-ip22/ip22-int.c  |    3 ++-
>  arch/mips/sgi-ip22/ip22-time.c |    3 ++-
>  7 files changed, 57 insertions(+), 37 deletions(-)
> 
> diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
> index 09b08d0..6cdd8c2 100644
> --- a/arch/mips/include/asm/irq.h
> +++ b/arch/mips/include/asm/irq.h
> @@ -113,36 +113,11 @@ do {									\
>  
>  #endif
>  
> -/*
> - * do_IRQ handles all normal device IRQ's (the special
> - * SMP cross-CPU interrupts have their own specific
> - * handlers).
> - *
> - * Ideally there should be away to get this into kernel/irq/handle.c to
> - * avoid the overhead of a call for just a tiny function ...
> - */
> -#define do_IRQ(irq)							\
> -do {									\
> -	irq_enter();							\
> -	__DO_IRQ_SMTC_HOOK(irq);					\
> -	generic_handle_irq(irq);					\
> -	irq_exit();							\
> -} while (0)
> +extern unsigned int do_IRQ(unsigned int irq);
>  
>  #ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
> -/*
> - * To avoid inefficient and in some cases pathological re-checking of
> - * IRQ affinity, we have this variant that skips the affinity check.
> - */
> -
>  
> -#define do_IRQ_no_affinity(irq)						\
> -do {									\
> -	irq_enter();							\
> -	__NO_AFFINITY_IRQ_SMTC_HOOK(irq);				\
> -	generic_handle_irq(irq);					\
> -	irq_exit();							\
> -} while (0)
> +extern unsigned int do_IRQ_no_affinity(unsigned int irq);
>  
>  #endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
>  
> diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
> index 7b845ba..c10ea8f 100644
> --- a/arch/mips/kernel/irq.c
> +++ b/arch/mips/kernel/irq.c
> @@ -22,6 +22,7 @@
>  #include <linux/seq_file.h>
>  #include <linux/kallsyms.h>
>  #include <linux/kgdb.h>
> +#include <linux/ftrace.h>
>  
>  #include <asm/atomic.h>
>  #include <asm/system.h>
> @@ -150,3 +151,36 @@ void __init init_IRQ(void)
>  		kgdb_early_setup = 1;
>  #endif
>  }
> +
> +/*
> + * do_IRQ handles all normal device IRQ's (the special
> + * SMP cross-CPU interrupts have their own specific
> + * handlers).
> + */
> +unsigned int __irq_entry do_IRQ(unsigned int irq)
> +{
> +	irq_enter();
> +	__DO_IRQ_SMTC_HOOK(irq);
> +	generic_handle_irq(irq);
> +	irq_exit();
> +
> +	return 1;
> +}
> +
> +#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
> +/*
> + * To avoid inefficient and in some cases pathological re-checking of
> + * IRQ affinity, we have this variant that skips the affinity check.
> + */
> +
> +unsigned int __irq_entry do_IRQ_no_affinity(unsigned int irq)
> +{
> +	irq_enter();
> +	__NO_AFFINITY_IRQ_SMTC_HOOK(irq);
> +	generic_handle_irq(irq);
> +	irq_exit();
> +
> +	return 1;
> +}
> +
> +#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
> diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
> index e72e684..6cdca19 100644
> --- a/arch/mips/kernel/smp.c
> +++ b/arch/mips/kernel/smp.c
> @@ -32,6 +32,7 @@
>  #include <linux/cpumask.h>
>  #include <linux/cpu.h>
>  #include <linux/err.h>
> +#include <linux/ftrace.h>
>  
>  #include <asm/atomic.h>
>  #include <asm/cpu.h>
> @@ -130,7 +131,7 @@ asmlinkage __cpuinit void start_secondary(void)
>  /*
>   * Call into both interrupt handlers, as we share the IPI for them
>   */
> -void smp_call_function_interrupt(void)
> +void __irq_entry smp_call_function_interrupt(void)
>  {
>  	irq_enter();
>  	generic_smp_call_function_single_interrupt();
> diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
> index 24630fd..75034a8 100644
> --- a/arch/mips/kernel/smtc.c
> +++ b/arch/mips/kernel/smtc.c
> @@ -25,6 +25,7 @@
>  #include <linux/interrupt.h>
>  #include <linux/kernel_stat.h>
>  #include <linux/module.h>
> +#include <linux/ftrace.h>
>  
>  #include <asm/cpu.h>
>  #include <asm/processor.h>
> @@ -939,23 +940,29 @@ static void ipi_call_interrupt(void)
>  
>  DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
>  
> -void ipi_decode(struct smtc_ipi *pipi)
> +static void __irq_entry smtc_clock_tick_interrupt(void)
>  {
>  	unsigned int cpu = smp_processor_id();
>  	struct clock_event_device *cd;
> +	int irq = MIPS_CPU_IRQ_BASE + 1;
> +
> +	irq_enter();
> +	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
> +	cd = &per_cpu(mips_clockevent_device, cpu);
> +	cd->event_handler(cd);
> +	irq_exit();
> +}
> +
> +void ipi_decode(struct smtc_ipi *pipi)
> +{
>  	void *arg_copy = pipi->arg;
>  	int type_copy = pipi->type;
> -	int irq = MIPS_CPU_IRQ_BASE + 1;
>  
>  	smtc_ipi_nq(&freeIPIq, pipi);
>  
>  	switch (type_copy) {
>  	case SMTC_CLOCK_TICK:
> -		irq_enter();
> -		kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
> -		cd = &per_cpu(mips_clockevent_device, cpu);
> -		cd->event_handler(cd);
> -		irq_exit();
> +		smtc_clock_tick_interrupt();
>  		break;
>  
>  	case LINUX_SMP_IPI:
> diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
> index 162b299..f25df73 100644
> --- a/arch/mips/kernel/vmlinux.lds.S
> +++ b/arch/mips/kernel/vmlinux.lds.S
> @@ -46,6 +46,7 @@ SECTIONS
>  		SCHED_TEXT
>  		LOCK_TEXT
>  		KPROBES_TEXT
> +		IRQENTRY_TEXT
>  		*(.text.*)
>  		*(.fixup)
>  		*(.gnu.warning)
> diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
> index 0ecd5fe..383f11d 100644
> --- a/arch/mips/sgi-ip22/ip22-int.c
> +++ b/arch/mips/sgi-ip22/ip22-int.c
> @@ -13,6 +13,7 @@
>  #include <linux/init.h>
>  #include <linux/kernel_stat.h>
>  #include <linux/interrupt.h>
> +#include <linux/ftrace.h>
>  
>  #include <asm/irq_cpu.h>
>  #include <asm/sgi/hpc3.h>
> @@ -150,7 +151,7 @@ static void indy_local1_irqdispatch(void)
>  
>  extern void ip22_be_interrupt(int irq);
>  
> -static void indy_buserror_irq(void)
> +static void __irq_entry indy_buserror_irq(void)
>  {
>  	int irq = SGI_BUSERR_IRQ;
>  
> diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
> index c8f7d23..603fc91 100644
> --- a/arch/mips/sgi-ip22/ip22-time.c
> +++ b/arch/mips/sgi-ip22/ip22-time.c
> @@ -16,6 +16,7 @@
>  #include <linux/interrupt.h>
>  #include <linux/kernel_stat.h>
>  #include <linux/time.h>
> +#include <linux/ftrace.h>
>  
>  #include <asm/cpu.h>
>  #include <asm/mipsregs.h>
> @@ -115,7 +116,7 @@ __init void plat_time_init(void)
>  }
>  
>  /* Generic SGI handler for (spurious) 8254 interrupts */
> -void indy_8254timer_irq(void)
> +void __irq_entry indy_8254timer_irq(void)
>  {
>  	int irq = SGI_8254_0_IRQ;
>  	ULONG cnt;

Re: [PATCH -v6 07/13] tracing: add dynamic function tracer support for MIPS

[Steven Rostedt]

On Mon, 2009-10-26 at 23:13 +0800, Wu Zhangjin wrote:
> With dynamic function tracer, by default, _mcount is defined as an
> "empty" function, it just return without any more action, just like the
> static function tracer does. When enabling it in user-space, it will
> jump to a real tracing function(ftrace_caller), and do some real job for
> us.
> 
> Differ from the static function tracer, dynamic function tracer provides
> two functions ftrace_make_call()/ftrace_make_nop() to enable/disable the
> tracing of some indicated kernel functions(set_ftrace_filter).
> 
> In the -v4 version, the implementation of this support is basically the same as
> X86 version does: _mcount is implemented as an empty function and ftrace_caller
> is implemented as a real tracing function respectively.
> 
> But in this version, to support module tracing with the help of
> -mlong-calls. the stuff becomes a little more complex, let's have a look
> at the new calling to _mcount with -mlong-calls(result of "objdump -hdr
> vmlinux").
> 

Note in cases where the call to mcount is more that one instruction, it
may be better to add a jump over everything.

> 	c:	3c030000 	lui	v1,0x0

				b	1f


> 			c: R_MIPS_HI16	_mcount
> 			c: R_MIPS_NONE	*ABS*
> 			c: R_MIPS_NONE	*ABS*
> 	10:	64630000 	daddiu	v1,v1,0
> 			10: R_MIPS_LO16	_mcount
> 			10: R_MIPS_NONE	*ABS*
> 			10: R_MIPS_NONE	*ABS*
> 	14:	03e0082d 	move	at,ra
> 	18:	0060f809 	jalr	v1

1:

Yes, it will still execute in the delay slot daddiu. Not sure if this is
better than two adds and a nop. I'll have to play with it.

> 
> and the old version without -mlong-calls looks like this:
> 
> 	108:   03e0082d        move    at,ra
> 	10c:   0c000000        jal     0 <fpcsr_pending>
>                         10c: R_MIPS_26  _mcount
>                         10c: R_MIPS_NONE        *ABS*
>                         10c: R_MIPS_NONE        *ABS*
> 	110:   00020021        nop
> 
> In the old version, there is only one "_mcount" string for every kernel
> function, so, we just need to match this one in mcount_regex of
> scripts/recordmcount.pl, but in the new version, we need to choose one
> of the two to match. Herein, I choose the first one with "R_MIPS_HI16
> _mcount".
> 
> and In the old verion, without module tracing support, we just need to replace
> "jal _mcount" by "jal ftrace_caller" to do real tracing, and filter the tracing
> of some kernel functions via replacing it by a nop instruction.
> 
> but as we have described before, the instruction "jal ftrace_caller" only left
> 32bit length for the address of ftrace_caller, it will fail when calling from
> the module space. so, herein, we must replace something else.
> 
> the basic idea is loading the address of ftrace_caller to v1 via changing these
> two instructions:
> 
> 	lui	v1,0x0
> 	addiu	v1,v1,0
> 
> If we want to enable the tracing, we need to replace the above instructions to:
> 
> 	lui	v1, HI_16BIT_ftrace_caller
> 	addiu	v1, v1, LOW_16BIT_ftrace_caller
> 
> If we want to stop the tracing of the indicated kernel functions, we
> just need to replace the "jalr v1" to a nop instruction. but we need to
> replace two instructions and encode the above two instructions
> oursevles.
> 
> Is there a simpler solution, Yes! Here it is, in this version, we put _mcount
> and ftrace_caller together, which means the address of _mcount and
> ftrace_caller is the same:
> 
> _mcount:
> ftrace_caller:
> 	j	ftrace_stub
> 	nop
> 
> 	...(do real tracing here)...
> 
> ftrace_stub:
> 	jr	ra
> 	move	ra, at
> 
> By default, the kernel functions call _mcount, and then jump to ftrace_stub and
> return. and when we want to do real tracing, we just need to remove that "j
> ftrace_stub", and it will run through the two "nop" instructions and then do
> the real tracing job.

The problem with this is that all .init functions always call _mcount
and we never nop it. Since the initial nop is done at boot up with only
one CPU running, it is safe to modify all locations with the jump to
something other than _mcount and not to worry about it later.


> 
> what about filtering job? we just need to switching the "jalr v1" and "nop"
> instruction.
> 
> In linux-mips64, there will be some local symbols, whose name are
> prefixed by $L, which need to be filtered. thanks goes to Steven for
> writing the mips64-specific function_regex.
> 
> In a conclusion, with RISC, things becomes easier with such a "stupid"
> trick, RISC is something like K.I.S.S, and also, there are lots of
> "simple" tricks in the whole ftrace support, thanks goes to Steven and
> the other folks for providing such a wonderful tracing framework!
> 
> Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
> ---
>  arch/mips/Kconfig              |    2 +
>  arch/mips/include/asm/ftrace.h |   12 ++++++
>  arch/mips/kernel/Makefile      |    3 +-
>  arch/mips/kernel/ftrace.c      |   76 ++++++++++++++++++++++++++++++++++++++++
>  arch/mips/kernel/mcount.S      |   29 +++++++++++++++
>  scripts/recordmcount.pl        |   38 ++++++++++++++++++++
>  6 files changed, 159 insertions(+), 1 deletions(-)
>  create mode 100644 arch/mips/kernel/ftrace.c
> 
> diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
> index a9bd992..147fbbc 100644
> --- a/arch/mips/Kconfig
> +++ b/arch/mips/Kconfig
> @@ -6,6 +6,8 @@ config MIPS
>  	select HAVE_ARCH_KGDB
>  	select HAVE_FUNCTION_TRACER
>  	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
> +	select HAVE_DYNAMIC_FTRACE
> +	select HAVE_FTRACE_MCOUNT_RECORD
>  	# Horrible source of confusion.  Die, die, die ...
>  	select EMBEDDED
>  	select RTC_LIB if !LEMOTE_FULOONG2E
> diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
> index 5f8ebcf..d5771e8 100644
> --- a/arch/mips/include/asm/ftrace.h
> +++ b/arch/mips/include/asm/ftrace.h
> @@ -19,6 +19,18 @@
>  extern void _mcount(void);
>  #define mcount _mcount
>  
> +#ifdef CONFIG_DYNAMIC_FTRACE
> +static inline unsigned long ftrace_call_adjust(unsigned long addr)
> +{
> +	/* 12 is the offset of "jalr v1" from the first loading instruction
> +	 * "lui v1, HI_16BIT", please get more information from
> +	 * scripts/recordmcount.pl */
> +	return addr + 12;
> +}
> +
> +struct dyn_arch_ftrace {
> +};
> +#endif /*  CONFIG_DYNAMIC_FTRACE */
>  #endif /* __ASSEMBLY__ */
>  #endif /* CONFIG_FUNCTION_TRACER */
>  #endif /* _ASM_MIPS_FTRACE_H */
> diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
> index 38e704a..3cda3ab 100644
> --- a/arch/mips/kernel/Makefile
> +++ b/arch/mips/kernel/Makefile
> @@ -10,6 +10,7 @@ obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
>  
>  ifdef CONFIG_FUNCTION_TRACER
>  CFLAGS_REMOVE_trace_clock.o = -pg
> +CFLAGS_REMOVE_ftrace.o = -pg
>  CFLAGS_REMOVE_early_printk.o = -pg
>  endif
>  
> @@ -30,7 +31,7 @@ obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
>  obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
>  
>  obj-$(CONFIG_FTRACE)		+= trace_clock.o
> -obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
> +obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o ftrace.o
>  
>  obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
>  obj-$(CONFIG_CPU_MIPS32)	+= r4k_fpu.o r4k_switch.o
> diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
> new file mode 100644
> index 0000000..0be30cf
> --- /dev/null
> +++ b/arch/mips/kernel/ftrace.c
> @@ -0,0 +1,76 @@
> +/*
> + * Code for replacing ftrace calls with jumps.
> + *
> + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
> + * Copyright (C) 2009 DSLab, Lanzhou University, China
> + * Author: Wu Zhangjin <wuzj@lemote.com>
> + *
> + * Thanks goes to Steven Rostedt for writing the original x86 version.
> + */
> +
> +#include <linux/uaccess.h>
> +#include <linux/init.h>
> +#include <linux/ftrace.h>
> +
> +#include <asm/cacheflush.h>
> +
> +#ifdef CONFIG_DYNAMIC_FTRACE
> +
> +#define JAL 0x0c000000		/* jump & link: ip --> ra, jump to target */
> +#define ADDR_MASK 0x03ffffff	/*  op_code|addr : 31...26|25 ....0 */
> +
> +#ifdef CONFIG_CPU_LOONGSON2F
> +static unsigned int ftrace_nop = 0x00020021;
> +#else
> +static unsigned int ftrace_nop = 0x00000000;
> +#endif
> +
> +static int ftrace_modify_code(unsigned long ip, unsigned int new_code)
> +{
> +	*(unsigned int *)ip = new_code;
> +
> +	flush_icache_range(ip, ip + 8);
> +
> +	return 0;
> +}
> +
> +int ftrace_make_nop(struct module *mod,
> +		    struct dyn_ftrace *rec, unsigned long addr)
> +{
> +	return ftrace_modify_code(rec->ip, ftrace_nop);
> +}
> +
> +static int modified;	/* initialized as 0 by default */
> +#define JALR_V1 0x0060f809
> +
> +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
> +{
> +	/* We just need to remove the "j ftrace_stub" at the fist time! */
> +	if (modified == 0) {
> +		modified = 1;
> +		ftrace_modify_code(addr, ftrace_nop);
> +	}
> +	return ftrace_modify_code(rec->ip, JALR_V1);
> +}
> +
> +#define FTRACE_CALL_IP ((unsigned long)(&ftrace_call))
> +#define jump_insn_encode(op_code, addr) \
> +	((unsigned int)((op_code) | (((addr) >> 2) & ADDR_MASK)))
> +
> +int ftrace_update_ftrace_func(ftrace_func_t func)
> +{
> +	unsigned int new;
> +
> +	new = jump_insn_encode(JAL, (unsigned long)func);
> +
> +	return ftrace_modify_code(FTRACE_CALL_IP, new);
> +}
> +
> +int __init ftrace_dyn_arch_init(void *data)
> +{
> +	/* The return code is retured via data */
> +	*(unsigned long *)data = 0;
> +
> +	return 0;
> +}
> +#endif				/* CONFIG_DYNAMIC_FTRACE */
> diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
> index 5dfaca8..389be7b 100644
> --- a/arch/mips/kernel/mcount.S
> +++ b/arch/mips/kernel/mcount.S
> @@ -63,6 +63,33 @@
>  	move ra, AT
>  	.endm
>  
> +#ifdef CONFIG_DYNAMIC_FTRACE
> +
> +NESTED(ftrace_caller, PT_SIZE, ra)
> +	.globl _mcount
> +_mcount:
> +	j	ftrace_stub
> +	nop
> +	lw	t0, function_trace_stop
> +	bnez	t0, ftrace_stub
> +	nop
> +
> +	MCOUNT_SAVE_REGS
> +
> +	MCOUNT_SET_ARGS
> +	.globl ftrace_call
> +ftrace_call:
> +	nop	/* a placeholder for the call to a real tracing function */
> +	nop	/* Do not touch me, I'm in the dealy slot of "jal func" */

Indent the second nop ;-)

> +
> +	MCOUNT_RESTORE_REGS
> +	.globl ftrace_stub
> +ftrace_stub:
> +	RETURN_BACK
> +	END(ftrace_caller)
> +
> +#else	/* ! CONFIG_DYNAMIC_FTRACE */
> +
>  NESTED(_mcount, PT_SIZE, ra)
>  	lw	t0, function_trace_stop
>  	bnez	t0, ftrace_stub
> @@ -89,5 +116,7 @@ ftrace_stub:
>  	RETURN_BACK
>  	END(_mcount)
>  
> +#endif	/* ! CONFIG_DYNAMIC_FTRACE */
> +
>  	.set at
>  	.set reorder
> diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
> index 465fe5e..d83c0c1 100755
> --- a/scripts/recordmcount.pl
> +++ b/scripts/recordmcount.pl
> @@ -246,6 +246,44 @@ if ($arch eq "x86_64") {
>      $ld .= " -m elf64_sparc";
>      $cc .= " -m64";
>      $objcopy .= " -O elf64-sparc";
> +
> +} elsif ($arch eq "mips") {
> +    # To enable module support, we need to enable the -mlong-calls option
> +    # of gcc for MIPS, after using this option, we can not get the real
> +    # offset of the calling to _mcount, but the offset of the first loading
> +    # instruction or the second one, here we get the first one, and then,
> +    # we plus it with 12 in arch/mips/kernel/asm/ftrace.h.
> +    #
> +    #       c:	3c030000 	lui	v1,0x0
> +    #			c: R_MIPS_HI16	_mcount
> +    #			c: R_MIPS_NONE	*ABS*
> +    #			c: R_MIPS_NONE	*ABS*
> +    #      10:	64630000 	daddiu	v1,v1,0
> +    #			10: R_MIPS_LO16	_mcount
> +    #			10: R_MIPS_NONE	*ABS*
> +    #			10: R_MIPS_NONE	*ABS*
> +    #      14:	03e0082d 	move	at,ra
> +    #      18:	0060f809 	jalr	v1
> +    $mcount_regex = "^\\s*([0-9a-fA-F]+): R_MIPS_HI16\\s+_mcount\$";
> +    $objdump .= " -Melf-trad".$endian."mips ";
> +
> +    if ($endian eq "big") {
> +	    $endian = " -EB ";
> +	    $ld .= " -melf".$bits."btsmip";
> +    } else {
> +	    $endian = " -EL ";
> +	    $ld .= " -melf".$bits."ltsmip";
> +    }
> +
> +    $cc .= " -mno-abicalls -fno-pic -mabi=" . $bits . $endian;
> +    $ld .= $endian;
> +
> +    if ($bits == 64) {
> +	    $function_regex =
> +		"^([0-9a-fA-F]+)\\s+<(.|[^\$]L.*?|\$[^L].*?|[^\$][^L].*?)>:";
> +	    $type = ".dword";
> +    }
> +
>  } else {
>      die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
>  }

So if I convert mips to do what ppc does, we can remove the long jump
thing, right?

-- Steve

Re: [PATCH -v6 07/13] tracing: add dynamic function tracer support for MIPS

[Wu Zhangjin]

Hi,

[...]
> > +
> > +NESTED(ftrace_caller, PT_SIZE, ra)
> > +	.globl _mcount
> > +_mcount:
> > +	j	ftrace_stub
> > +	nop
> > +	lw	t0, function_trace_stop
> > +	bnez	t0, ftrace_stub
> > +	nop
> > +
> > +	MCOUNT_SAVE_REGS
> > +
> > +	MCOUNT_SET_ARGS
> > +	.globl ftrace_call
> > +ftrace_call:
> > +	nop	/* a placeholder for the call to a real tracing function */
> > +	nop	/* Do not touch me, I'm in the dealy slot of "jal func" */
> 
> Indent the second nop ;-)
> 

Yup, later in -v7.

> > +    $mcount_regex = "^\\s*([0-9a-fA-F]+): R_MIPS_HI16\\s+_mcount\$";
> > +    $objdump .= " -Melf-trad".$endian."mips ";
> > +
> > +    if ($endian eq "big") {
> > +	    $endian = " -EB ";
> > +	    $ld .= " -melf".$bits."btsmip";
> > +    } else {
> > +	    $endian = " -EL ";
> > +	    $ld .= " -melf".$bits."ltsmip";
> > +    }
> > +
> > +    $cc .= " -mno-abicalls -fno-pic -mabi=" . $bits . $endian;
> > +    $ld .= $endian;
> > +
> > +    if ($bits == 64) {
> > +	    $function_regex =
> > +		"^([0-9a-fA-F]+)\\s+<(.|[^\$]L.*?|\$[^L].*?|[^\$][^L].*?)>:";
> > +	    $type = ".dword";
> > +    }
> > +
> >  } else {
> >      die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
> >  }
> 
> So if I convert mips to do what ppc does, we can remove the long jump
> thing, right?
> 

If remove the long jump, we at least to change the $mcount_regex in
scripts/recordmcount.pl, the addr + 12 in arch/mips/include/asm/ftrace.h
and the _mcount & ftrace_caller in mcount.S and the ftrace_make_nop &
ftrace_make_call in arch/mips/kernel/ftrace.c back to the -v4 version.

I think this method of supporting module is not that BAD, no obvious
overhead added except the "lui...addiu..." and two more "nop"
instructions. and it's very understandable, so, just use this version?

Regards,
	Wu Zhangjin

Re: [PATCH -v6 07/13] tracing: add dynamic function tracer support for MIPS

[Steven Rostedt]

On Tue, 2009-10-27 at 00:35 +0800, Wu Zhangjin wrote:

> If remove the long jump, we at least to change the $mcount_regex in
> scripts/recordmcount.pl, the addr + 12 in arch/mips/include/asm/ftrace.h
> and the _mcount & ftrace_caller in mcount.S and the ftrace_make_nop &
> ftrace_make_call in arch/mips/kernel/ftrace.c back to the -v4 version.
> 
> I think this method of supporting module is not that BAD, no obvious
> overhead added except the "lui...addiu..." and two more "nop"
> instructions. and it's very understandable, so, just use this version?

You don't nop the lui and addiu do you? If you do you will crash the
machine.

As for overhead, you might want to test that out.

-- Steve

Re: [PATCH -v6 07/13] tracing: add dynamic function tracer support for MIPS

[Wu Zhangjin]

On Mon, 2009-10-26 at 12:45 -0400, Steven Rostedt wrote:
> On Tue, 2009-10-27 at 00:35 +0800, Wu Zhangjin wrote:
> 
> > If remove the long jump, we at least to change the $mcount_regex in
> > scripts/recordmcount.pl, the addr + 12 in arch/mips/include/asm/ftrace.h
> > and the _mcount & ftrace_caller in mcount.S and the ftrace_make_nop &
> > ftrace_make_call in arch/mips/kernel/ftrace.c back to the -v4 version.
> > 
> > I think this method of supporting module is not that BAD, no obvious
> > overhead added except the "lui...addiu..." and two more "nop"
> > instructions. and it's very understandable, so, just use this version?
> 
> You don't nop the lui and addiu do you? If you do you will crash the
> machine.

Not test it yet, Seems what you have mentioned in another thread:

b  1f
....
1:

is a good idea, it will only left one "lui" and one "b 1f" instruction
there.

(I'm sleepy now, the time is Tue Oct 27 01:34:51 CST 2009 in China, See
you~~)

Regards,
	Wu Zhangjin

Re: [PATCH -v6 05/13] tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST for MIPS

[Sergei Shtylyov]

Hello.

Wu Zhangjin wrote:

> There is an exisiting common ftrace_test_stop_func() in
> kernel/trace/ftrace.c, which is used to check the global variable
> ftrace_trace_stop to determine whether stop the function tracing.

> This patch implepment the MIPS specific one to speedup the procedure.

> Thanks goes to Zhang Le for Cleaning it up.

> Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>

[...]

> diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
> index 0c39bc8..5dfaca8 100644
> --- a/arch/mips/kernel/mcount.S
> +++ b/arch/mips/kernel/mcount.S
> @@ -64,6 +64,10 @@
>  	.endm
>  
>  NESTED(_mcount, PT_SIZE, ra)
> +	lw	t0, function_trace_stop
> +	bnez	t0, ftrace_stub
> +	nop

1) unless .set noreorder is specified in this file, explicit nop is not needed;

2) delay slot instruction is usually denoted by adding extra space on its 
left, like this:

	bnez	t0, ftrace_stub
	 nop

WBR, Sergei

Re: [PATCH -v6 05/13] tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST for MIPS

[Steven Rostedt]

On Mon, 2009-10-26 at 18:41 +0300, Sergei Shtylyov wrote:
> Hello.
> 
> Wu Zhangjin wrote:
> 
> > There is an exisiting common ftrace_test_stop_func() in
> > kernel/trace/ftrace.c, which is used to check the global variable
> > ftrace_trace_stop to determine whether stop the function tracing.
> 
> > This patch implepment the MIPS specific one to speedup the procedure.
> 
> > Thanks goes to Zhang Le for Cleaning it up.
> 
> > Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> 
> [...]
> 
> > diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
> > index 0c39bc8..5dfaca8 100644
> > --- a/arch/mips/kernel/mcount.S
> > +++ b/arch/mips/kernel/mcount.S
> > @@ -64,6 +64,10 @@
> >  	.endm
> >  
> >  NESTED(_mcount, PT_SIZE, ra)
> > +	lw	t0, function_trace_stop
> > +	bnez	t0, ftrace_stub
> > +	nop
> 
> 1) unless .set noreorder is specified in this file, explicit nop is not needed;

>From patch 4:

+++ b/arch/mips/kernel/mcount.S
@@ -0,0 +1,89 @@
+/*
+ * MIPS specific _mcount support
+ *
+ * This file is subject to the terms and conditions of the GNU General
Public
+ * License.  See the file "COPYING" in the main directory of this
archive for
+ * more details.
+ *
+ * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ */
+
+#include <asm/regdef.h>
+#include <asm/stackframe.h>
+#include <asm/ftrace.h>
+
+       .text
+       .set noreorder
+       .set noat

-- Steve

> 
> 2) delay slot instruction is usually denoted by adding extra space on its 
> left, like this:
> 
> 	bnez	t0, ftrace_stub
> 	 nop

Re: [PATCH -v6 05/13] tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST for MIPS

[Steven Rostedt]

On Mon, 2009-10-26 at 18:41 +0300, Sergei Shtylyov wrote:
> Hello.
> 
> Wu Zhangjin wrote:
> 
> > There is an exisiting common ftrace_test_stop_func() in
> > kernel/trace/ftrace.c, which is used to check the global variable
> > ftrace_trace_stop to determine whether stop the function tracing.
> 
> > This patch implepment the MIPS specific one to speedup the procedure.
> 
> > Thanks goes to Zhang Le for Cleaning it up.
> 
> > Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> 
> [...]
> 
> > diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
> > index 0c39bc8..5dfaca8 100644
> > --- a/arch/mips/kernel/mcount.S
> > +++ b/arch/mips/kernel/mcount.S
> > @@ -64,6 +64,10 @@
> >  	.endm
> >  
> >  NESTED(_mcount, PT_SIZE, ra)
> > +	lw	t0, function_trace_stop
> > +	bnez	t0, ftrace_stub
> > +	nop
> 
> 1) unless .set noreorder is specified in this file, explicit nop is not needed;

From patch 4:

+++ b/arch/mips/kernel/mcount.S
@@ -0,0 +1,89 @@
+/*
+ * MIPS specific _mcount support
+ *
+ * This file is subject to the terms and conditions of the GNU General
Public
+ * License.  See the file "COPYING" in the main directory of this
archive for
+ * more details.
+ *
+ * Copyright (C) 2009 Lemote Inc. & DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ */
+
+#include <asm/regdef.h>
+#include <asm/stackframe.h>
+#include <asm/ftrace.h>
+
+       .text
+       .set noreorder
+       .set noat

-- Steve

> 
> 2) delay slot instruction is usually denoted by adding extra space on its 
> left, like this:
> 
> 	bnez	t0, ftrace_stub
> 	 nop

Re: [PATCH -v6 05/13] tracing: enable HAVE_FUNCTION_TRACE_MCOUNT_TEST for MIPS

[Wu Zhangjin]

On Mon, 2009-10-26 at 18:41 +0300, Sergei Shtylyov wrote:
> Hello.
> 
> Wu Zhangjin wrote:
> 
> > There is an exisiting common ftrace_test_stop_func() in
> > kernel/trace/ftrace.c, which is used to check the global variable
> > ftrace_trace_stop to determine whether stop the function tracing.
> 
> > This patch implepment the MIPS specific one to speedup the procedure.
> 
> > Thanks goes to Zhang Le for Cleaning it up.
> 
> > Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> 
> [...]
> 
> > diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
> > index 0c39bc8..5dfaca8 100644
> > --- a/arch/mips/kernel/mcount.S
> > +++ b/arch/mips/kernel/mcount.S
> > @@ -64,6 +64,10 @@
> >  	.endm
> >  
> >  NESTED(_mcount, PT_SIZE, ra)
> > +	lw	t0, function_trace_stop
> > +	bnez	t0, ftrace_stub
> > +	nop
> 
> 1) unless .set noreorder is specified in this file, explicit nop is not needed;
> 
> 2) delay slot instruction is usually denoted by adding extra space on its 
> left, like this:
> 
> 	bnez	t0, ftrace_stub
> 	 nop
> 

Okay, Will add an extra space for them later, thanks!

Regards,
	Wu Zhangjin

Re: [PATCH -v6 02/13] tracing: add mips_timecounter_read() for MIPS

[Wu Zhangjin]

Hi Ralf, 

Could you please give some feedback on this patch?

Really looking forward to your feedback and then resend this patchset
out ;)

Thanks & Regards,
	Wu Zhangjin

On Mon, 2009-10-26 at 23:13 +0800, Wu Zhangjin wrote:
> This patch add a new function: mips_timecounter_read() to get high
> precision timestamp without extra lock.
> 
> It is based on the clock counter register and the
> timecounter/cyclecounter abstraction layer of kernel.
> 
> Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> ---
>  arch/mips/include/asm/time.h |   19 +++++++++++++++++++
>  arch/mips/kernel/csrc-r4k.c  |   41 +++++++++++++++++++++++++++++++++++++++++
>  arch/mips/kernel/time.c      |    2 ++
>  3 files changed, 62 insertions(+), 0 deletions(-)
> 
> diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
> index df6a430..b8af7fa 100644
> --- a/arch/mips/include/asm/time.h
> +++ b/arch/mips/include/asm/time.h
> @@ -73,8 +73,18 @@ static inline int mips_clockevent_init(void)
>   */
>  #ifdef CONFIG_CSRC_R4K_LIB
>  extern int init_r4k_clocksource(void);
> +extern int init_r4k_timecounter(void);
> +extern u64 r4k_timecounter_read(void);
>  #endif
>  
> +static inline u64 mips_timecounter_read(void)
> +{
> +#ifdef CONFIG_CSRC_R4K
> +	return r4k_timecounter_read();
> +#else
> +	return sched_clock();
> +#endif
> +}
>  static inline int init_mips_clocksource(void)
>  {
>  #ifdef CONFIG_CSRC_R4K
> @@ -84,6 +94,15 @@ static inline int init_mips_clocksource(void)
>  #endif
>  }
>  
> +static inline int init_mips_timecounter(void)
> +{
> +#ifdef CONFIG_CSRC_R4K
> +	return init_r4k_timecounter();
> +#else
> +	return 0;
> +#endif
> +}
> +
>  extern void clocksource_set_clock(struct clocksource *cs, unsigned int clock);
>  extern void clockevent_set_clock(struct clock_event_device *cd,
>  		unsigned int clock);
> diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
> index e95a3cd..4e7705f 100644
> --- a/arch/mips/kernel/csrc-r4k.c
> +++ b/arch/mips/kernel/csrc-r4k.c
> @@ -7,6 +7,7 @@
>   */
>  #include <linux/clocksource.h>
>  #include <linux/init.h>
> +#include <linux/sched.h>
>  
>  #include <asm/time.h>
>  
> @@ -36,3 +37,43 @@ int __init init_r4k_clocksource(void)
>  
>  	return 0;
>  }
> +
> +static struct timecounter r4k_tc = {
> +	.cc = NULL,
> +};
> +
> +static cycle_t r4k_cc_read(const struct cyclecounter *cc)
> +{
> +	return read_c0_count();
> +}
> +
> +static struct cyclecounter r4k_cc = {
> +	.read = r4k_cc_read,
> +	.mask = CLOCKSOURCE_MASK(32),
> +	.shift = 32,
> +};
> +
> +int __init init_r4k_timecounter(void)
> +{
> +	if (!cpu_has_counter || !mips_hpt_frequency)
> +		return -ENXIO;
> +
> +	r4k_cc.mult = div_sc((unsigned long)mips_hpt_frequency, NSEC_PER_SEC,
> +			32);
> +
> +	timecounter_init(&r4k_tc, &r4k_cc, sched_clock());
> +
> +	return 0;
> +}
> +
> +u64 r4k_timecounter_read(void)
> +{
> +	u64 clock;
> +
> +	if (r4k_tc.cc != NULL)
> +		clock = timecounter_read(&r4k_tc);
> +	else
> +		clock = sched_clock();
> +
> +	return clock;
> +}
> diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
> index 1f467d5..e38cca1 100644
> --- a/arch/mips/kernel/time.c
> +++ b/arch/mips/kernel/time.c
> @@ -156,4 +156,6 @@ void __init time_init(void)
>  
>  	if (!mips_clockevent_init() || !cpu_has_mfc0_count_bug())
>  		init_mips_clocksource();
> +	if (!cpu_has_mfc0_count_bug())
> +		init_mips_timecounter();
>  }

Re: [PATCH -v6 02/13] tracing: add mips_timecounter_read() for MIPS

[Wu Zhangjin]

Hi Ralf, 

Could you please give some feedback on this patch?

Really looking forward to your feedback and then resend this patchset
out ;)

Thanks & Regards,
	Wu Zhangjin

On Mon, 2009-10-26 at 23:13 +0800, Wu Zhangjin wrote:
> This patch add a new function: mips_timecounter_read() to get high
> precision timestamp without extra lock.
> 
> It is based on the clock counter register and the
> timecounter/cyclecounter abstraction layer of kernel.
> 
> Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>
> ---
>  arch/mips/include/asm/time.h |   19 +++++++++++++++++++
>  arch/mips/kernel/csrc-r4k.c  |   41 +++++++++++++++++++++++++++++++++++++++++
>  arch/mips/kernel/time.c      |    2 ++
>  3 files changed, 62 insertions(+), 0 deletions(-)
> 
> diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
> index df6a430..b8af7fa 100644
> --- a/arch/mips/include/asm/time.h
> +++ b/arch/mips/include/asm/time.h
> @@ -73,8 +73,18 @@ static inline int mips_clockevent_init(void)
>   */
>  #ifdef CONFIG_CSRC_R4K_LIB
>  extern int init_r4k_clocksource(void);
> +extern int init_r4k_timecounter(void);
> +extern u64 r4k_timecounter_read(void);
>  #endif
>  
> +static inline u64 mips_timecounter_read(void)
> +{
> +#ifdef CONFIG_CSRC_R4K
> +	return r4k_timecounter_read();
> +#else
> +	return sched_clock();
> +#endif
> +}
>  static inline int init_mips_clocksource(void)
>  {
>  #ifdef CONFIG_CSRC_R4K
> @@ -84,6 +94,15 @@ static inline int init_mips_clocksource(void)
>  #endif
>  }
>  
> +static inline int init_mips_timecounter(void)
> +{
> +#ifdef CONFIG_CSRC_R4K
> +	return init_r4k_timecounter();
> +#else
> +	return 0;
> +#endif
> +}
> +
>  extern void clocksource_set_clock(struct clocksource *cs, unsigned int clock);
>  extern void clockevent_set_clock(struct clock_event_device *cd,
>  		unsigned int clock);
> diff --git a/arch/mips/kernel/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
> index e95a3cd..4e7705f 100644
> --- a/arch/mips/kernel/csrc-r4k.c
> +++ b/arch/mips/kernel/csrc-r4k.c
> @@ -7,6 +7,7 @@
>   */
>  #include <linux/clocksource.h>
>  #include <linux/init.h>
> +#include <linux/sched.h>
>  
>  #include <asm/time.h>
>  
> @@ -36,3 +37,43 @@ int __init init_r4k_clocksource(void)
>  
>  	return 0;
>  }
> +
> +static struct timecounter r4k_tc = {
> +	.cc = NULL,
> +};
> +
> +static cycle_t r4k_cc_read(const struct cyclecounter *cc)
> +{
> +	return read_c0_count();
> +}
> +
> +static struct cyclecounter r4k_cc = {
> +	.read = r4k_cc_read,
> +	.mask = CLOCKSOURCE_MASK(32),
> +	.shift = 32,
> +};
> +
> +int __init init_r4k_timecounter(void)
> +{
> +	if (!cpu_has_counter || !mips_hpt_frequency)
> +		return -ENXIO;
> +
> +	r4k_cc.mult = div_sc((unsigned long)mips_hpt_frequency, NSEC_PER_SEC,
> +			32);
> +
> +	timecounter_init(&r4k_tc, &r4k_cc, sched_clock());
> +
> +	return 0;
> +}
> +
> +u64 r4k_timecounter_read(void)
> +{
> +	u64 clock;
> +
> +	if (r4k_tc.cc != NULL)
> +		clock = timecounter_read(&r4k_tc);
> +	else
> +		clock = sched_clock();
> +
> +	return clock;
> +}
> diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
> index 1f467d5..e38cca1 100644
> --- a/arch/mips/kernel/time.c
> +++ b/arch/mips/kernel/time.c
> @@ -156,4 +156,6 @@ void __init time_init(void)
>  
>  	if (!mips_clockevent_init() || !cpu_has_mfc0_count_bug())
>  		init_mips_clocksource();
> +	if (!cpu_has_mfc0_count_bug())
> +		init_mips_timecounter();
>  }

Re: [PATCH -v6 01/13] tracing: convert trace_clock_local() as weak function

[Frederic Weisbecker]

On Mon, Oct 26, 2009 at 11:13:18PM +0800, Wu Zhangjin wrote:
> trace_clock_local() is based on the arch-specific sched_clock(), in X86,
> it is tsc(64bit) based, which can give very high precision(about 1ns
> with 1GHz). but in MIPS, the sched_clock() is jiffies based, which can
> give only 10ms precison with 1000 HZ. which is not enough for tracing,
> especially for Real Time system.
> 
> so, we need to implement a MIPS specific sched_clock() to get higher
> precision. There is a tsc like clock counter register in MIPS, whose
> frequency is half of the processor, so, if the cpu frequency is 800MHz,
> the time precision reaches 2.5ns, which is very good for tracing, even
> for Real Time system.
> 
> but 'Cause it is only 32bit long, which will rollover quickly, so, such
> a sched_clock() will bring with extra load, which is not good for the
> whole system. so, we only need to implement a arch-specific
> trace_clock_local() for tracing. as a preparation, we convert it as a
> weak function.
> 
> The MIPS specific trace_clock_local() is coming in the next two patches.
> 
> Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com>


Yep, if trace_clock_local() had to be a strict alias
to sched_clock(), we would have simply used sched_clock().

If an arch need to implement it another way, then yeah making
it weak is a good thing.

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>