[PATCH v3] mips-specific ftrace support

[PATCH v3] mips-specific ftrace support

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

ftrace is a mcount based kernel tracing tool/framework, which is originally
from RT_PREEMPT(http://rt.wiki.kernel.org).

ftrace is short for function tracer, this is its original name, but now, it
becomes a kernel tracing framework, lots of kernel tracers are built on it,
such as irqoff tracer, wakeup tracer and so forth.  these tracers are
arch-independent(?), but some of them are arch-dependent, such as the original
ftrace: function tracer, and dynamic function tracer, function graph tracer,
and also, system call tracer.

here is the mips porting of these four arch-dependent tracers, it will enable
the following new kernel config options in linux-mips system.

kernel hacking --->
           Tracers -->
                [*] Kernel Function Tracer
                [*]   Kernel Function Graph Tracer
                ...
                [*] Trace syscalls
                                ...
                [*] enable/disable ftrace tracepoints dynamically

in reality, because the timestamp getting function are arch-dependent, lots of
the tracers are arch-dependent. the arch-dependent part is that: sched_clock().
the original sched_clock() in mips is jiffes based, only give 10ms precision in
1000HZ, which is not enough for ftrace. to get high-precise timestamp, we must
implement a new native_sched_clock() via reading the MIPS clock counter, but
since it is only 32bit long, so, overflow should be handled carefully.

this -v3 patch series is based on the -v2 patch series and incorporates the
feedback from Steven Rostedt and Thomas Gleixner.

!!NOTE!!

this -v3 not support modules yet, really hope this can be fixed in -v4 patch.

read the following document, and play with it:
        Documentation/trace/ftrace.txt

Wu Zhangjin (7):
  mips static function tracer support
  add an endian argument to scripts/recordmcount.pl
  mips dynamic function tracer support
  filter local function prefixed by $L
  mips function graph tracer support
  mips specific clock function to get precise timestamp
  mips specific system call tracer

 arch/mips/Kconfig                   |    7 +
 arch/mips/Makefile                  |    2 +
 arch/mips/include/asm/ftrace.h      |   35 ++++-
 arch/mips/include/asm/ptrace.h      |    2 +
 arch/mips/include/asm/reg.h         |    5 +
 arch/mips/include/asm/syscall.h     |   84 +++++++++
 arch/mips/include/asm/thread_info.h |    5 +-
 arch/mips/kernel/Makefile           |   12 ++
 arch/mips/kernel/csrc-r4k.c         |    2 +-
 arch/mips/kernel/entry.S            |    2 +-
 arch/mips/kernel/ftrace.c           |  344 +++++++++++++++++++++++++++++++++++
 arch/mips/kernel/ftrace_clock.c     |   71 +++++++
 arch/mips/kernel/mcount.S           |  184 +++++++++++++++++++
 arch/mips/kernel/mips_ksyms.c       |    5 +
 arch/mips/kernel/ptrace.c           |   14 ++-
 arch/mips/kernel/scall64-o32.S      |    2 +-
 arch/mips/kernel/vmlinux.lds.S      |    1 +
 kernel/trace/trace_clock.c          |    2 +-
 scripts/Makefile.build              |    1 +
 scripts/recordmcount.pl             |   30 +++-
 20 files changed, 799 insertions(+), 11 deletions(-)
 create mode 100644 arch/mips/include/asm/syscall.h
 create mode 100644 arch/mips/kernel/ftrace.c
 create mode 100644 arch/mips/kernel/ftrace_clock.c
 create mode 100644 arch/mips/kernel/mcount.S

[PATCH v3] mips static function tracer support

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

if -pg of gcc is enabled. a calling to _mcount will be inserted to each
kernel function. so, there is a possibility to trace the functions in
_mcount.

here is the implementation of mips specific _mcount for static function
tracer.

-ffunction-sections option not works with -pg, so disable it if enables
FUNCTION_TRACER.

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 arch/mips/Kconfig              |    2 +
 arch/mips/Makefile             |    2 +
 arch/mips/include/asm/ftrace.h |   25 ++++++++++-
 arch/mips/kernel/Makefile      |    7 +++
 arch/mips/kernel/mcount.S      |   98 ++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mips_ksyms.c  |    5 ++
 6 files changed, 138 insertions(+), 1 deletions(-)
 create mode 100644 arch/mips/kernel/mcount.S

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 25f3b0a..2e2fdbe 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -4,6 +4,8 @@ config MIPS
 	select HAVE_IDE
 	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
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index c4cae9e..f86fb15 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -48,7 +48,9 @@ ifneq ($(SUBARCH),$(ARCH))
   endif
 endif
 
+ifndef CONFIG_FUNCTION_TRACER
 cflags-y := -ffunction-sections
+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 e961221..559a820 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -8,6 +8,11 @@ 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
+# Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_early_printk.o = -pg
+endif
+
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K_LIB)	+= cevt-r4k.o
 obj-$(CONFIG_MIPS_MT_SMTC)	+= cevt-smtc.o
@@ -24,6 +29,8 @@ obj-$(CONFIG_SYNC_R4K)		+= sync-r4k.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
+
 obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS32)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_MIPS64)	+= 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..268724e
--- /dev/null
+++ b/arch/mips/kernel/mcount.S
@@ -0,0 +1,98 @@
+/*
+ * the mips-specific _mcount implementation
+ *
+ * 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>
+ */
+
+#include <asm/regdef.h>
+#include <asm/stackframe.h>
+#include <asm/ftrace.h>
+
+	.text
+	.set noreorder
+	.set noat
+
+	/* since there is a "addiu sp,sp,-8" before "jal _mcount" in 32bit */
+	.macro RESTORE_SP_FOR_32BIT
+#ifdef CONFIG_32BIT
+	PTR_ADDIU	sp, 8
+#endif
+	.endm
+
+	.macro MCOUNT_SAVE_REGS
+	PTR_SUBU	sp, PT_SIZE
+	PTR_S	ra, PT_R31(sp)
+	PTR_S	$1, 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	$1, 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, $1		/* arg2: the caller's next ip, parent */
+	PTR_SUBU a0, MCOUNT_INSN_SIZE
+	.endm
+
+	.macro RETURN_BACK
+	jr ra
+	move ra, $1
+	.endm
+
+NESTED(_mcount, PT_SIZE, ra)
+	RESTORE_SP_FOR_32BIT
+	PTR_L	t0, function_trace_stop
+	bnez	t0, ftrace_stub
+	nop
+
+	PTR_LA	t0, ftrace_stub
+	PTR_L	t1, ftrace_trace_function /* please don't use t1 later, safe? */
+	bne	t0, t1, static_trace
+	nop
+
+	j	ftrace_stub
+	nop
+
+static_trace:
+	MCOUNT_SAVE_REGS
+
+	MCOUNT_SET_ARGS			/* call *ftrace_trace_function */
+	jalr	t1
+	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
-- 
1.6.0.4

[PATCH v3] add an endian argument to scripts/recordmcount.pl

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

mips architecture need this argument to handle big/little endian
differently.

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
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 5c4b7a4..548d575 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -207,6 +207,7 @@ endif
 
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
 cmd_record_mcount = 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 0fae7da..f1e3e9c 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -100,13 +100,13 @@ $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
-- 
1.6.0.4

[PATCH v3] mips dynamic function tracer support

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

dynamic function tracer need to replace "nop" to "jumps & links" and
something reversely.

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 arch/mips/Kconfig              |    3 +
 arch/mips/include/asm/ftrace.h |   10 ++
 arch/mips/kernel/Makefile      |    2 +
 arch/mips/kernel/ftrace.c      |  207 ++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mcount.S      |   31 ++++++
 scripts/recordmcount.pl        |   20 ++++
 6 files changed, 273 insertions(+), 0 deletions(-)
 create mode 100644 arch/mips/kernel/ftrace.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2e2fdbe..0857239 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -6,6 +6,9 @@ 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
+	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index 5f8ebcf..b4970c9 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -19,6 +19,16 @@
 extern void _mcount(void);
 #define mcount _mcount
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+/* reloction of mcount call site is the same as the address */
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
+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 559a820..8dabcc6 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
 # Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
@@ -30,6 +31,7 @@ obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= 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..ad490cc
--- /dev/null
+++ b/arch/mips/kernel/ftrace.c
@@ -0,0 +1,207 @@
+/*
+ * 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/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/ftrace.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/asm.h>
+#include <asm/unistd.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 */
+
+static unsigned int ftrace_nop = 0x00000000;
+
+static unsigned char *ftrace_call_replace(unsigned long op_code,
+					  unsigned long addr)
+{
+    static unsigned int op;
+
+    op = op_code | ((addr >> 2) & ADDR_MASK);
+
+    return (unsigned char *) &op;
+}
+
+static atomic_t nmi_running = ATOMIC_INIT(0);
+static int mod_code_status;	/* holds return value of text write */
+static int mod_code_write;	/* set when NMI should do the write */
+static void *mod_code_ip;	/* holds the IP to write to */
+static void *mod_code_newcode;	/* holds the text to write to the IP */
+
+static unsigned nmi_wait_count;
+static atomic_t nmi_update_count = ATOMIC_INIT(0);
+
+int ftrace_arch_read_dyn_info(char *buf, int size)
+{
+    int r;
+
+    r = snprintf(buf, size, "%u %u",
+		 nmi_wait_count, atomic_read(&nmi_update_count));
+    return r;
+}
+
+static void ftrace_mod_code(void)
+{
+    /*
+     * Yes, more than one CPU process can be writing to mod_code_status.
+     *    (and the code itself)
+     * But if one were to fail, then they all should, and if one were
+     * to succeed, then they all should.
+     */
+    mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+					 MCOUNT_INSN_SIZE);
+
+    /* if we fail, then kill any new writers */
+    if (mod_code_status)
+		mod_code_write = 0;
+}
+
+void ftrace_nmi_enter(void)
+{
+    atomic_inc(&nmi_running);
+    /* Must have nmi_running seen before reading write flag */
+    smp_mb();
+    if (mod_code_write) {
+		ftrace_mod_code();
+		atomic_inc(&nmi_update_count);
+    }
+}
+
+void ftrace_nmi_exit(void)
+{
+    /* Finish all executions before clearing nmi_running */
+    smp_wmb();
+    atomic_dec(&nmi_running);
+}
+
+static void wait_for_nmi(void)
+{
+    int waited = 0;
+
+    while (atomic_read(&nmi_running)) {
+		waited = 1;
+		cpu_relax();
+    }
+
+    if (waited)
+		nmi_wait_count++;
+}
+
+static int do_ftrace_mod_code(unsigned long ip, void *new_code)
+{
+    mod_code_ip = (void *) ip;
+    mod_code_newcode = new_code;
+
+    /* The buffers need to be visible before we let NMIs write them */
+    smp_wmb();
+
+    mod_code_write = 1;
+
+    /* Make sure write bit is visible before we wait on NMIs */
+    smp_mb();
+
+    wait_for_nmi();
+
+    /* Make sure all running NMIs have finished before we write the code */
+    smp_mb();
+
+    ftrace_mod_code();
+
+    /* Make sure the write happens before clearing the bit */
+    smp_wmb();
+
+    mod_code_write = 0;
+
+    /* make sure NMIs see the cleared bit */
+    smp_mb();
+
+    wait_for_nmi();
+
+    return mod_code_status;
+}
+
+static unsigned char *ftrace_nop_replace(void)
+{
+    return (unsigned char *) &ftrace_nop;
+}
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned char *old_code,
+		   unsigned char *new_code)
+{
+    unsigned char replaced[MCOUNT_INSN_SIZE];
+
+    /* read the text we want to modify */
+    if (probe_kernel_read(replaced, (void *) ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+    /* Make sure it is what we expect it to be */
+    if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+    /* replace the text with the new text */
+    if (do_ftrace_mod_code(ip, new_code))
+		return -EPERM;
+
+    return 0;
+}
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+    unsigned char *new, *old;
+
+    old = ftrace_call_replace(JAL, addr);
+    new = ftrace_nop_replace();
+
+    return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+    unsigned char *new, *old;
+
+    old = ftrace_nop_replace();
+    new = ftrace_call_replace(JAL, addr);
+
+    return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+    unsigned long ip = (unsigned long) (&ftrace_call);
+    unsigned char old[MCOUNT_INSN_SIZE], *new;
+    int ret;
+
+    memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
+    new = ftrace_call_replace(JAL, (unsigned long) func);
+    ret = ftrace_modify_code(ip, old, new);
+
+    return ret;
+}
+
+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 268724e..723ace2 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -67,6 +67,35 @@
 	move ra, $1
 	.endm
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+LEAF(_mcount)
+	RESTORE_SP_FOR_32BIT
+	RETURN_BACK
+	END(_mcount)
+
+NESTED(ftrace_caller, PT_SIZE, ra)
+	RESTORE_SP_FOR_32BIT
+	lw	t0, function_trace_stop
+	bnez	t0, ftrace_stub
+	nop
+
+	MCOUNT_SAVE_REGS
+
+	MCOUNT_SET_ARGS
+	.globl ftrace_call
+ftrace_call:
+	jal	ftrace_stub
+	nop
+
+	MCOUNT_RESTORE_REGS
+	.globl ftrace_stub
+ftrace_stub:
+	RETURN_BACK
+	END(ftrace_caller)
+
+#else	/* ! CONFIG_DYNAMIC_FTRACE */
+
 NESTED(_mcount, PT_SIZE, ra)
 	RESTORE_SP_FOR_32BIT
 	PTR_L	t0, function_trace_stop
@@ -94,5 +123,7 @@ 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 f1e3e9c..533d3bf 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -213,6 +213,26 @@ if ($arch eq "x86_64") {
     if ($is_module eq "0") {
         $cc .= " -mconstant-gp";
     }
+
+} elsif ($arch eq "mips") {
+	$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\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) {
+		$type = ".dword";
+    }
+
 } else {
     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 }
-- 
1.6.0.4

[PATCH v3] filter local function prefixed by $L

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

this patch fixed the warning as following:

mipsel-linux-gnu-objcopy: 'fs/proc/.tmp_gl_devices.o': No such file
mipsel-linux-gnu-ld: fs/proc/.tmp_gl_devices.o: No such file: No such
file or directory
rm: cannot remove `fs/proc/.tmp_gl_devices.o': No such file or directory
rm: cannot remove `fs/proc/.tmp_mx_devices.o': No such file or directory

the real reason of above warning is that the $Lxx local functions will
be treated as global symbols, so, should be filtered.

Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 scripts/recordmcount.pl |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 533d3bf..542cb04 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -343,6 +343,10 @@ sub update_funcs
 	if (!$use_locals) {
 	    return;
 	}
+	# filter $LXXX tags
+	if ("$ref_func" =~ m/\$L/) {
+		return;
+	}
 	$convert{$ref_func} = 1;
     }
 
-- 
1.6.0.4

Re: [PATCH v3] filter local function prefixed by $L

[David Daney]

Wu Zhangjin wrote:
> From: Wu Zhangjin <wuzj@lemote.com>
> 
> this patch fixed the warning as following:
> 
> mipsel-linux-gnu-objcopy: 'fs/proc/.tmp_gl_devices.o': No such file
> mipsel-linux-gnu-ld: fs/proc/.tmp_gl_devices.o: No such file: No such
> file or directory
> rm: cannot remove `fs/proc/.tmp_gl_devices.o': No such file or directory
> rm: cannot remove `fs/proc/.tmp_mx_devices.o': No such file or directory
> 
> the real reason of above warning is that the $Lxx local functions will
> be treated as global symbols, so, should be filtered.
> 
> Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
> ---
>  scripts/recordmcount.pl |    4 ++++
>  1 files changed, 4 insertions(+), 0 deletions(-)
> 
> diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
> index 533d3bf..542cb04 100755
> --- a/scripts/recordmcount.pl
> +++ b/scripts/recordmcount.pl
> @@ -343,6 +343,10 @@ sub update_funcs
>  	if (!$use_locals) {
>  	    return;
>  	}
> +	# filter $LXXX tags
> +	if ("$ref_func" =~ m/\$L/) {
> +		return;
> +	}

Certainly this is true for mips.  I doubt it is for all architectures 
targed by Linux.

David Daney

Re: [PATCH v3] filter local function prefixed by $L

[Steven Rostedt]

On Mon, 15 Jun 2009, David Daney wrote:

> Wu Zhangjin wrote:
> > From: Wu Zhangjin <wuzj@lemote.com>
> > 
> > this patch fixed the warning as following:
> > 
> > mipsel-linux-gnu-objcopy: 'fs/proc/.tmp_gl_devices.o': No such file
> > mipsel-linux-gnu-ld: fs/proc/.tmp_gl_devices.o: No such file: No such
> > file or directory
> > rm: cannot remove `fs/proc/.tmp_gl_devices.o': No such file or directory
> > rm: cannot remove `fs/proc/.tmp_mx_devices.o': No such file or directory
> > 
> > the real reason of above warning is that the $Lxx local functions will
> > be treated as global symbols, so, should be filtered.
> > 
> > Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
> > ---
> >  scripts/recordmcount.pl |    4 ++++
> >  1 files changed, 4 insertions(+), 0 deletions(-)
> > 
> > diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
> > index 533d3bf..542cb04 100755
> > --- a/scripts/recordmcount.pl
> > +++ b/scripts/recordmcount.pl
> > @@ -343,6 +343,10 @@ sub update_funcs
> >  	if (!$use_locals) {
> >  	    return;
> >  	}
> > +	# filter $LXXX tags
> > +	if ("$ref_func" =~ m/\$L/) {
> > +		return;
> > +	}
> 
> Certainly this is true for mips.  I doubt it is for all architectures targed
> by Linux.

Yes, that should probably go into a mips only change. Unless you can 
reproduce it on all other archs, or at least x86.

You could also do this in the function_regex variable.

 "^([0-9a-fA-F]+)\\s+<(.|[^\$]L.*?|\$[^L].*?|[^\$][^L].*?)>:"

There may even be a better way, but I'm not in the mood to look it up ;-)

-- Steve

Re: [PATCH v3] filter local function prefixed by $L

[Wu Zhangjin]

On Mon, 2009-06-15 at 12:30 -0400, Steven Rostedt wrote:
> On Mon, 15 Jun 2009, David Daney wrote:
> 
> > Wu Zhangjin wrote:
> > > From: Wu Zhangjin <wuzj@lemote.com>
> > > 
> > > this patch fixed the warning as following:
> > > 
> > > mipsel-linux-gnu-objcopy: 'fs/proc/.tmp_gl_devices.o': No such file
> > > mipsel-linux-gnu-ld: fs/proc/.tmp_gl_devices.o: No such file: No such
> > > file or directory
> > > rm: cannot remove `fs/proc/.tmp_gl_devices.o': No such file or directory
> > > rm: cannot remove `fs/proc/.tmp_mx_devices.o': No such file or directory
> > > 
> > > the real reason of above warning is that the $Lxx local functions will
> > > be treated as global symbols, so, should be filtered.
> > > 
> > > Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
> > > ---
> > >  scripts/recordmcount.pl |    4 ++++
> > >  1 files changed, 4 insertions(+), 0 deletions(-)
> > > 
> > > diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
> > > index 533d3bf..542cb04 100755
> > > --- a/scripts/recordmcount.pl
> > > +++ b/scripts/recordmcount.pl
> > > @@ -343,6 +343,10 @@ sub update_funcs
> > >  	if (!$use_locals) {
> > >  	    return;
> > >  	}
> > > +	# filter $LXXX tags
> > > +	if ("$ref_func" =~ m/\$L/) {
> > > +		return;
> > > +	}
> > 
> > Certainly this is true for mips.  I doubt it is for all architectures targed
> > by Linux.
> 

have tried to use function_regex instead, but for I'm poor in playing
with regular expression of perl. at last, i use something easier like
above. and I _guess_ this problem maybe exist in some other platforms,
so just put it there.

> Yes, that should probably go into a mips only change. Unless you can 
> reproduce it on all other archs, or at least x86.
> 
> You could also do this in the function_regex variable.
> 
>  "^([0-9a-fA-F]+)\\s+<(.|[^\$]L.*?|\$[^L].*?|[^\$][^L].*?)>:"
> 

works well, and this seems mips64-specific, so, I moved this specific
function_regex to "if ($bits == 64) { ... }".

> There may even be a better way, but I'm not in the mood to look it up ;-)

seems not that easy to understand :-)

-- Wu Zhangjin

[PATCH v3] mips function graph tracer support

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

this works something like -finstrument-functions does, instead of using

                void __cyg_profile_func_enter (void *this_fn,
                                                  void *call_site);
                   void __cyg_profile_func_exit  (void *this_fn,
                                                  void *call_site);

-pg use _mcount, so some tricks are adoptive by the author of orignal function
graph tracer:

	the _mcount function will call prepare_function_return to save the
	parent_ip, ip and calltime in a tracing array, if success, the
	address of a hooker function &return_to_handler will be substitued
	to the parent_ip, so, after return from _mcount it will call the
	&return_to_handler, not back to the parent_ip, but calling
	ftrace_return_to_handler to remember the rettime, and return the
	parent_ip to let &return_to_handler go back to the real parent.

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 arch/mips/Kconfig              |    1 +
 arch/mips/kernel/ftrace.c      |   66 ++++++++++++++++++++++++++++++++++++++++
 arch/mips/kernel/mcount.S      |   61 +++++++++++++++++++++++++++++++++++--
 arch/mips/kernel/vmlinux.lds.S |    1 +
 4 files changed, 126 insertions(+), 3 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 0857239..5ac9f45 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -9,6 +9,7 @@ config MIPS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
+	select HAVE_FUNCTION_GRAPH_TRACER
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index ad490cc..65d4d56 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -205,3 +205,69 @@ int __init ftrace_dyn_arch_init(void *data)
     return 0;
 }
 #endif				/* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+#define JMP	0x08000000			/* jump to target directly */
+extern void ftrace_graph_call(void);
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+    unsigned long ip = (unsigned long) (&ftrace_graph_call);
+    unsigned char old[MCOUNT_INSN_SIZE], *new;
+    int ret;
+
+	/* j ftrace_stub */
+    memcpy(old, (unsigned long *) ip, MCOUNT_INSN_SIZE);
+    new = ftrace_call_replace(JMP, (unsigned long) ftrace_graph_caller);
+
+    ret = ftrace_modify_code(ip, old, new);
+
+    return ret;
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+    unsigned long ip = (unsigned long) (&ftrace_graph_call);
+    unsigned char old[MCOUNT_INSN_SIZE], *new;
+    int ret;
+
+	/* j ftrace_graph_caller */
+    memcpy(old, (unsigned long *) ip, MCOUNT_INSN_SIZE);
+    new = ftrace_call_replace(JMP, (unsigned long) ftrace_stub);
+
+    ret = ftrace_modify_code(ip, old, new);
+
+    return ret;
+}
+
+#endif				/* !CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+
+unsigned long prepare_ftrace_return(unsigned long ip,
+				    unsigned long parent_ip)
+{
+    struct ftrace_graph_ent trace;
+
+    /* Nmi's are currently unsupported */
+    if (unlikely(in_nmi()) ||
+		unlikely(atomic_read(&current->tracing_graph_pause)) ||
+		(ftrace_push_return_trace(parent_ip, ip, &trace.depth) == -EBUSY))
+		return parent_ip;
+
+	trace.func = ip;
+
+	/* Only trace if the calling function expects to */
+	if (ftrace_graph_entry(&trace))
+		return (unsigned long) &return_to_handler;
+
+	current->curr_ret_stack--;
+	return parent_ip;
+}
+#endif				/* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 723ace2..559f9bd 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -27,7 +27,6 @@
 	.macro MCOUNT_SAVE_REGS
 	PTR_SUBU	sp, PT_SIZE
 	PTR_S	ra, PT_R31(sp)
-	PTR_S	$1, PT_R1(sp)
 	PTR_S	a0, PT_R4(sp)
 	PTR_S	a1, PT_R5(sp)
 	PTR_S	a2, PT_R6(sp)
@@ -42,7 +41,6 @@
 
 	.macro MCOUNT_RESTORE_REGS
 	PTR_L	ra, PT_R31(sp)
-	PTR_L	$1, PT_R1(sp)
 	PTR_L	a0, PT_R4(sp)
 	PTR_L	a1, PT_R5(sp)
 	PTR_L	a2, PT_R6(sp)
@@ -81,6 +79,7 @@ NESTED(ftrace_caller, PT_SIZE, ra)
 	nop
 
 	MCOUNT_SAVE_REGS
+	PTR_S	$1, PT_R1(sp)
 
 	MCOUNT_SET_ARGS
 	.globl ftrace_call
@@ -88,7 +87,16 @@ ftrace_call:
 	jal	ftrace_stub
 	nop
 
+	PTR_L	$1, PT_R1(sp)
 	MCOUNT_RESTORE_REGS
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.globl ftrace_graph_call
+ftrace_graph_call:
+	j	ftrace_stub
+	nop
+#endif
+
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK
@@ -106,17 +114,27 @@ NESTED(_mcount, PT_SIZE, ra)
 	PTR_L	t1, ftrace_trace_function /* please don't use t1 later, safe? */
 	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
 
 static_trace:
 	MCOUNT_SAVE_REGS
+	PTR_S	$1, PT_R1(sp)
 
 	MCOUNT_SET_ARGS			/* call *ftrace_trace_function */
 	jalr	t1
 	nop
 
+	PTR_L	$1, PT_R1(sp)
 	MCOUNT_RESTORE_REGS
 	.globl ftrace_stub
 ftrace_stub:
@@ -125,5 +143,42 @@ ftrace_stub:
 
 #endif	/* ! CONFIG_DYNAMIC_FTRACE */
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+NESTED(ftrace_graph_caller, PT_SIZE, ra)
+	MCOUNT_SAVE_REGS
+	PTR_S	v0, PT_R2(sp)
+
+	MCOUNT_SET_ARGS
+	jal	prepare_ftrace_return
+	nop
+
+	/* overwrite the parent as &return_to_handler: v0 -> $1(at) */
+	move	$1,	v0
+
+	PTR_L	v0, PT_R2(sp)
+	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)
+
+	jal	ftrace_return_to_handler
+	nop
+
+	/* restore the real parent address: v0 -> ra */
+	move	ra, v0
+
+	PTR_L	v0, PT_R2(sp)
+	PTR_ADDIU	sp, PT_SIZE
+
+	jr	ra
+
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 	.set at
 	.set reorder
diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S
index 58738c8..67435e5 100644
--- a/arch/mips/kernel/vmlinux.lds.S
+++ b/arch/mips/kernel/vmlinux.lds.S
@@ -36,6 +36,7 @@ SECTIONS
 		SCHED_TEXT
 		LOCK_TEXT
 		KPROBES_TEXT
+		IRQENTRY_TEXT
 		*(.text.*)
 		*(.fixup)
 		*(.gnu.warning)
-- 
1.6.0.4

[PATCH v3] mips specific clock function to get precise timestamp

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

by default, trace_clock_local calling sched_clock(jiffies-based) to get
timestamp, in x86, there is a tsc(64bit) based sched_clock, but in mips,
the 'tsc'(clock counter) is only 32bit long, which will easily rollover,
and there is no existing high precise sched_clock in mips, we need to
get one ourselves.

to avoid invading the whole linux-mips, i do not want to implement a
tsc-based native_sched_clock instead of sched_clock like x86 does.
because, there is a need to handling rollover of the only 32-bit long
'tsc' of mips, which will need extra overhead. in reality, i have tried
to do it, but made the kernel hangs when booting, I'm not sure why it
not work.

so, I just implement a native_sched_clock in arch/mips/kernel/ftrace.c,
but not override the original sched_clock(). to get high precise
timestamp, we implement a native_trace_clock_local, which will not call
original sched_clock again, but native_sched_clock().

and what about the trace_clock and trace_clock_global function, should
we also implement a mips-secific one? I'm not sure.

Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 arch/mips/kernel/Makefile       |    2 +
 arch/mips/kernel/csrc-r4k.c     |    2 +-
 arch/mips/kernel/ftrace_clock.c |   71 +++++++++++++++++++++++++++++++++++++++
 kernel/trace/trace_clock.c      |    2 +-
 4 files changed, 75 insertions(+), 2 deletions(-)
 create mode 100644 arch/mips/kernel/ftrace_clock.c

diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 8dabcc6..44ec7e0 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -11,6 +11,7 @@ obj-y		+= cpu-probe.o branch.o entry.o genex.o irq.o process.o \
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_ftrace_clock.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
@@ -32,6 +33,7 @@ obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o
+obj-$(CONFIG_NOP_TRACER)	+= ftrace_clock.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/csrc-r4k.c b/arch/mips/kernel/csrc-r4k.c
index e95a3cd..3da1c7a 100644
--- a/arch/mips/kernel/csrc-r4k.c
+++ b/arch/mips/kernel/csrc-r4k.c
@@ -10,7 +10,7 @@
 
 #include <asm/time.h>
 
-static cycle_t c0_hpt_read(struct clocksource *cs)
+static cycle_t notrace c0_hpt_read(struct clocksource *cs)
 {
 	return read_c0_count();
 }
diff --git a/arch/mips/kernel/ftrace_clock.c b/arch/mips/kernel/ftrace_clock.c
new file mode 100644
index 0000000..8ad896e
--- /dev/null
+++ b/arch/mips/kernel/ftrace_clock.c
@@ -0,0 +1,71 @@
+/*
+ * 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>
+ */
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/jiffies.h>
+#include <linux/clocksource.h>
+
+/*
+ * mips-specific high precise sched_clock() implementation,
+ *
+ * currently, this is only needed in ftrace, so not override the original
+ * sched_clock().
+ */
+
+unsigned long long native_sched_clock(void)
+{
+	u64 current_cycles;
+	static unsigned long old_jiffies;
+	static u64 time, old_cycles;
+
+	preempt_disable_notrace();
+    /* update timestamp to avoid missing the timer interrupt */
+	if (time_before(jiffies, old_jiffies)) {
+		old_jiffies = jiffies;
+		time = sched_clock();
+		old_cycles = clock->cycle_last;
+	}
+	current_cycles = clock->read(clock);
+
+	time = (time + cyc2ns(clock, (current_cycles - old_cycles)
+				& clock->mask));
+
+	old_cycles = current_cycles;
+	preempt_enable_no_resched_notrace();
+
+	return time;
+}
+
+/*
+ * native_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 native_trace_clock_local(void)
+{
+	unsigned long flags;
+	u64 clock;
+
+	/*
+	 * herein, we use the above native_sched_clock() to get high precise
+	 * timestamp, because the original sched_clock in mips is jiffies based,
+	 * which not have enough precision.
+	 */
+	raw_local_irq_save(flags);
+	clock = native_sched_clock();
+	raw_local_irq_restore(flags);
+
+	return clock;
+}
+
+u64 trace_clock_local(void)
+		__attribute__((alias("native_trace_clock_local")));
+
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index b588fd8..78c98c8 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 __attribute__((weak)) notrace trace_clock_local(void)
 {
 	unsigned long flags;
 	u64 clock;
-- 
1.6.0.4

[PATCH v3] mips specific system call tracer

[Wu Zhangjin]

From: Wu Zhangjin <wuzj@lemote.com>

FIXME: there are several different sys_call_entry in mips64, but
currently, i only use the the one in arch/mips/kernel/scall64-o32.S
so,if people not use o32 standard, it will not compiled normally.

the system call tracing demo in a debian system on
qemu-system-mipsel/malta:

debian-mips-malta:~# mount -t debugfs nodev /debug
debian-mips-malta:~# echo 20000 > /debug/tracing/buffer_size_kb
debian-mips-malta:~# cat /debug/tracing/available_tracers
syscall nop
debian-mips-malta:~# echo syscall > /debug/tracing/current_tracer
debian-mips-malta:~# echo 1 > /debug/tracing/tracing_enabled
debian-mips-malta:~# sleep 1
debian-mips-malta:~# echo 0 > /debug/tracing/tracing_enabled
debian-mips-malta:~# cat /debug/tracing/trace | head -20
           <...>-533   [000]    60.458291: sys_write(fd: 1, buf: 4fc408, count: 8)
           <...>-533   [000]    64.325614: sys_getrlimit(resource: 3, rlim: 530020)
           <...>-533   [000]    64.327089: sys_read(fd: 2, buf: 4fc008, count: 6)
           <...>-533   [000]    64.969663: sys_exit(error_code: 2)
           <...>-533   [000]    65.608794: sys_exit(error_code: 2)
           <...>-533   [000]    66.231796: sys_read(fd: 2, buf: 4fc008, count: 6)
           <...>-533   [000]    66.913687: sys_open(filename: 1, flags: 0, mode: a)
           <...>-533   [000]    66.914617: sys_exit(error_code: 1)
           <...>-533   [000]    70.797507: sys_exit(error_code: 503be8)
           <...>-536   [000]    70.833108: sys_exit(error_code: 2aac6cfc)
           <...>-536   [000]    70.833897: sys_exit(error_code: 2aac6540)
           <...>-536   [000]    70.835711: sys_exit(error_code: 2aac6cfc)
           <...>-536   [000]    70.840609: sys_lchown(filename: 3, user: 7fb08b38, group: 20)
           <...>-533   [000]    71.877785: sys_open(filename: ffffffff, flags: 7fcf08c8, mode: b)
           <...>-533   [000]    75.531122: sys_open(filename: 1, flags: 0, mode: a)

Signed-off-by: Wu Zhangjin <wuzj@lemote.com>
---
 arch/mips/Kconfig                   |    1 +
 arch/mips/include/asm/ptrace.h      |    2 +
 arch/mips/include/asm/reg.h         |    5 ++
 arch/mips/include/asm/syscall.h     |   84 +++++++++++++++++++++++++++++++++++
 arch/mips/include/asm/thread_info.h |    5 ++-
 arch/mips/kernel/Makefile           |    1 +
 arch/mips/kernel/entry.S            |    2 +-
 arch/mips/kernel/ftrace.c           |   71 +++++++++++++++++++++++++++++
 arch/mips/kernel/ptrace.c           |   14 +++++-
 arch/mips/kernel/scall64-o32.S      |    2 +-
 10 files changed, 182 insertions(+), 5 deletions(-)
 create mode 100644 arch/mips/include/asm/syscall.h

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 5ac9f45..a4a5af5 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -10,6 +10,7 @@ config MIPS
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FTRACE_SYSCALLS
 	# Horrible source of confusion.  Die, die, die ...
 	select EMBEDDED
 	select RTC_LIB
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index ce47118..32e5b62 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -45,6 +45,8 @@ struct pt_regs {
 	unsigned long cp0_badvaddr;
 	unsigned long cp0_cause;
 	unsigned long cp0_epc;
+	/* Used for restarting system calls */
+	unsigned long orig_v0;
 #ifdef CONFIG_MIPS_MT_SMTC
 	unsigned long cp0_tcstatus;
 #endif /* CONFIG_MIPS_MT_SMTC */
diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h
index 634b55d..93d66bc 100644
--- a/arch/mips/include/asm/reg.h
+++ b/arch/mips/include/asm/reg.h
@@ -65,6 +65,8 @@
 #define EF_CP0_CAUSE		43
 #define EF_UNUSED0		44
 
+#define EF_ORIG_V0		45
+
 #define EF_SIZE			180
 
 #endif
@@ -121,6 +123,9 @@
 #define EF_CP0_STATUS		36
 #define EF_CP0_CAUSE		37
 
+
+#define EF_ORIG_V0			38
+
 #define EF_SIZE			304	/* size in bytes */
 
 #endif /* CONFIG_64BIT */
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
new file mode 100644
index 0000000..b785098
--- /dev/null
+++ b/arch/mips/include/asm/syscall.h
@@ -0,0 +1,84 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2009 DSLab, Lanzhou University, China
+ * Author: Wu Zhangjin <wuzj@lemote.com>
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H	1
+
+#include <linux/sched.h>
+
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	/*        syscall   Exc-Code: 0 1000 00     v0 */
+	return ((regs->cp0_cause&0xff) == 0x20)  ? regs->regs[2] : -1L;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->regs[2] = regs->orig_v0;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return regs->regs[2] ? -regs->regs[2] : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->regs[2];
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	if (error)
+		regs->regs[2] = -error;
+	else
+		regs->regs[2] = val;
+}
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+#ifdef CONFIG_32BIT
+	/* fixme: only 4 argument register available in mip32, so, how to handle
+	 * others?
+	 */
+	BUG_ON(i + n > 4);
+#else
+	BUG_ON(i + n > 6);
+#endif
+	memcpy(args, &regs->regs[4 + i], n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+#ifdef CONFIG_32BIT
+	BUG_ON(i + n > 4);
+#else
+	BUG_ON(i + n > 6);
+#endif
+	memcpy(&regs->regs[4 + i], args, n * sizeof(args[0]));
+}
+
+#endif	/* _ASM_SYSCALL_H */
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 143a481..1d55dc0 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -128,6 +128,7 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define TIF_32BIT_ADDR		23	/* 32-bit address space (o32/n32) */
 #define TIF_FPUBOUND		24	/* thread bound to FPU-full CPU set */
 #define TIF_LOAD_WATCH		25	/* If set, load watch registers */
+#define TIF_SYSCALL_FTRACE	27	/* for ftrace syscall instrumentation */
 #define TIF_SYSCALL_TRACE	31	/* syscall trace active */
 
 #ifdef CONFIG_MIPS32_O32
@@ -151,11 +152,13 @@ register struct thread_info *__current_thread_info __asm__("$28");
 #define _TIF_32BIT_ADDR		(1<<TIF_32BIT_ADDR)
 #define _TIF_FPUBOUND		(1<<TIF_FPUBOUND)
 #define _TIF_LOAD_WATCH		(1<<TIF_LOAD_WATCH)
+#define _TIF_SYSCALL_FTRACE	(1<<TIF_SYSCALL_FTRACE)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK		(0x0000ffef & ~_TIF_SECCOMP)
 /* work to do on any return to u-space */
-#define _TIF_ALLWORK_MASK	(0x8000ffff & ~_TIF_SECCOMP)
+#define _TIF_ALLWORK_MASK	\
+	((0x8000ffff & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE)
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 44ec7e0..1114c85 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_MODULES)		+= mips_ksyms.o module.o
 
 obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o
+obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_NOP_TRACER)	+= ftrace_clock.o
 
 obj-$(CONFIG_CPU_LOONGSON2)	+= r4k_fpu.o r4k_switch.o
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index ffa3310..786e4ef 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -167,7 +167,7 @@ work_notifysig:				# deal with pending signals and
 FEXPORT(syscall_exit_work_partial)
 	SAVE_STATIC
 syscall_exit_work:
-	li	t0, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+	li	t0, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SYSCALL_FTRACE
 	and	t0, a2			# a2 is preloaded with TI_FLAGS
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let do_syscall_trace()
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 65d4d56..c83b586 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -22,6 +22,8 @@
 #include <asm/asm.h>
 #include <asm/unistd.h>
 
+#include <trace/syscall.h>
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #define JAL 0x0c000000	/* jump & link: ip --> ra, jump to target */
@@ -271,3 +273,72 @@ unsigned long prepare_ftrace_return(unsigned long ip,
 	return parent_ip;
 }
 #endif				/* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_FTRACE_SYSCALLS
+
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+/* fixme: in mips64, there are different entries of sys_call_table when using
+ * different standards, in loongson2f based machines: Fuloong & Yeeloong, the
+ * system use o32 standard, so here, we only use the sys_call_table in
+ * arch/mips/kernel/scall64-o32.S */
+
+extern unsigned long *sys_call_table;
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		if (start->name && !strcmp(start->name, str))
+			return start;
+	}
+	return NULL;
+}
+
+struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= __NR_Linux_syscalls || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+void arch_init_ftrace_syscalls(void)
+{
+	int i;
+	struct syscall_metadata *meta;
+	unsigned long **psys_syscall_table = &sys_call_table;
+	static atomic_t refs;
+
+	if (atomic_inc_return(&refs) != 1)
+		goto end;
+
+	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+					__NR_Linux_syscalls, GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return;
+	}
+
+	for (i = 0; i < __NR_Linux_syscalls; i++) {
+		meta = find_syscall_meta(psys_syscall_table[i]);
+		syscalls_metadata[i] = meta;
+	}
+	return;
+
+	/* Paranoid: avoid overflow */
+end:
+	atomic_dec(&refs);
+}
+#endif	/* CONFIG_FTRACE_SYSCALLS */
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 054861c..fa762dc 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -25,6 +25,7 @@
 #include <linux/security.h>
 #include <linux/audit.h>
 #include <linux/seccomp.h>
+#include <linux/ftrace.h>
 
 #include <asm/byteorder.h>
 #include <asm/cpu.h>
@@ -39,6 +40,7 @@
 #include <asm/bootinfo.h>
 #include <asm/reg.h>
 
+#include <trace/syscall.h>
 /*
  * Called by kernel/ptrace.c when detaching..
  *
@@ -60,7 +62,7 @@ int ptrace_getregs(struct task_struct *child, __s64 __user *data)
 	struct pt_regs *regs;
 	int i;
 
-	if (!access_ok(VERIFY_WRITE, data, 38 * 8))
+	if (!access_ok(VERIFY_WRITE, data, 39 * 8))
 		return -EIO;
 
 	regs = task_pt_regs(child);
@@ -73,6 +75,7 @@ int ptrace_getregs(struct task_struct *child, __s64 __user *data)
 	__put_user((long)regs->cp0_badvaddr, data + EF_CP0_BADVADDR - EF_R0);
 	__put_user((long)regs->cp0_status, data + EF_CP0_STATUS - EF_R0);
 	__put_user((long)regs->cp0_cause, data + EF_CP0_CAUSE - EF_R0);
+	__put_user((long)regs->orig_v0, data + EF_ORIG_V0 - EF_R0);
 
 	return 0;
 }
@@ -87,7 +90,7 @@ int ptrace_setregs(struct task_struct *child, __s64 __user *data)
 	struct pt_regs *regs;
 	int i;
 
-	if (!access_ok(VERIFY_READ, data, 38 * 8))
+	if (!access_ok(VERIFY_READ, data, 39 * 8))
 		return -EIO;
 
 	regs = task_pt_regs(child);
@@ -97,6 +100,7 @@ int ptrace_setregs(struct task_struct *child, __s64 __user *data)
 	__get_user(regs->lo, data + EF_LO - EF_R0);
 	__get_user(regs->hi, data + EF_HI - EF_R0);
 	__get_user(regs->cp0_epc, data + EF_CP0_EPC - EF_R0);
+	__get_user(regs->orig_v0, data + EF_ORIG_V0 - EF_R0);
 
 	/* badvaddr, status, and cause may not be written.  */
 
@@ -575,6 +579,9 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
 	if (!(current->ptrace & PT_PTRACED))
 		goto out;
 
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_exit(regs);
+
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
 		goto out;
 
@@ -594,6 +601,9 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit)
 	}
 
 out:
+	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+		ftrace_syscall_enter(regs);
+
 	if (unlikely(current->audit_context) && !entryexit)
 		audit_syscall_entry(audit_arch(), regs->regs[0],
 				    regs->regs[4], regs->regs[5],
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index a5598b2..dd1f13a 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -202,7 +202,7 @@ einval:	li	v0, -ENOSYS
 
 	.align	3
 	.type	sys_call_table,@object
-sys_call_table:
+EXPORT(sys_call_table)
 	PTR	sys32_syscall			/* 4000 */
 	PTR	sys_exit
 	PTR	sys_fork
-- 
1.6.0.4