Ganapatrao,

On 02/26/2014 12:38 AM, Kulkarni, Ganapatrao wrote:

________________________________________
From: AKASHI Takahiro <takahiro.aka...@linaro.org>
Sent: Tuesday, February 25, 2014 2:53 PM
To: rost...@goodmis.org; fweis...@gmail.com; mi...@redhat.com; 
catalin.mari...@arm.com; will.dea...@arm.com; tim.b...@sonymobile.com
Cc: Kulkarni, Ganapatrao; dsax...@linaro.org; ar...@arndb.de; 
linux-arm-ker...@lists.infradead.org; linaro-ker...@lists.linaro.org; 
linux-kernel@vger.kernel.org; AKASHI Takahiro
Subject: [PATCH v4 1/7] arm64: Add ftrace support

This patch implements arm64 specific part to support function tracers,
such as function (CONFIG_FUNCTION_TRACER), function_graph
(CONFIG_FUNCTION_GRAPH_TRACER) and function profiler
(CONFIG_FUNCTION_PROFILER).

With 'function' tracer, all the functions in the kernel are traced with
timestamps in ${sysfs}/tracing/trace. If function_graph tracer is
specified, call graph is generated.

The kernel must be compiled with -pg option so that _mcount() is inserted
at the beginning of functions. This function is called on every function's
entry as long as tracing is enabled.
In addition, function_graph tracer also needs to be able to probe function's
exit. ftrace_graph_caller() & return_to_handler do this by faking link
register's value to intercept function's return path.

More details on architecture specific requirements are described in
Documentation/trace/ftrace-design.txt.

Signed-off-by: AKASHI Takahiro <takahiro.aka...@linaro.org>
---
  arch/arm64/Kconfig               |    2 +
  arch/arm64/include/asm/ftrace.h  |   23 +++++
  arch/arm64/kernel/Makefile       |    4 +
  arch/arm64/kernel/arm64ksyms.c   |    4 +
  arch/arm64/kernel/entry-ftrace.S |  173 ++++++++++++++++++++++++++++++++++++++
  arch/arm64/kernel/ftrace.c       |   64 ++++++++++++++
  6 files changed, 270 insertions(+)
  create mode 100644 arch/arm64/include/asm/ftrace.h
  create mode 100644 arch/arm64/kernel/entry-ftrace.S
  create mode 100644 arch/arm64/kernel/ftrace.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 27bbcfc..5783641 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -33,6 +33,8 @@ config ARM64
         select HAVE_DMA_ATTRS
         select HAVE_DMA_CONTIGUOUS
         select HAVE_EFFICIENT_UNALIGNED_ACCESS
+       select HAVE_FUNCTION_TRACER
+       select HAVE_FUNCTION_GRAPH_TRACER
         select HAVE_GENERIC_DMA_COHERENT
         select HAVE_HW_BREAKPOINT if PERF_EVENTS
         select HAVE_MEMBLOCK
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
new file mode 100644
index 0000000..58ea595
--- /dev/null
+++ b/arch/arm64/include/asm/ftrace.h
@@ -0,0 +1,23 @@
+/*
+ * arch/arm64/include/asm/ftrace.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.aka...@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_FTRACE_H
+#define __ASM_FTRACE_H
+
+#include <asm/insn.h>
+
+#define MCOUNT_ADDR            ((unsigned long)_mcount)
+#define MCOUNT_INSN_SIZE       AARCH64_INSN_SIZE
+
+#ifndef __ASSEMBLY__
+extern void _mcount(unsigned long);
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_FTRACE_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2d4554b..ac67fd0 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -5,6 +5,9 @@
  CPPFLAGS_vmlinux.lds   := -DTEXT_OFFSET=$(TEXT_OFFSET)
  AFLAGS_head.o          := -DTEXT_OFFSET=$(TEXT_OFFSET)

+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+
  # Object file lists.
  arm64-obj-y            := cputable.o debug-monitors.o entry.o irq.o fpsimd.o  
 \
                            entry-fpsimd.o process.o ptrace.o setup.o signal.o  
 \
@@ -13,6 +16,7 @@ arm64-obj-y           := cputable.o debug-monitors.o entry.o 
irq.o fpsimd.o   \

  arm64-obj-$(CONFIG_COMPAT)             += sys32.o kuser32.o signal32.o        
 \
                                            sys_compat.o
+arm64-obj-$(CONFIG_FUNCTION_TRACER)    += ftrace.o entry-ftrace.o
  arm64-obj-$(CONFIG_MODULES)            += arm64ksyms.o module.o
  arm64-obj-$(CONFIG_SMP)                        += smp.o smp_spin_table.o
  arm64-obj-$(CONFIG_HW_PERF_EVENTS)     += perf_event.o
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 338b568..7f0512f 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -56,3 +56,7 @@ EXPORT_SYMBOL(clear_bit);
  EXPORT_SYMBOL(test_and_clear_bit);
  EXPORT_SYMBOL(change_bit);
  EXPORT_SYMBOL(test_and_change_bit);
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
new file mode 100644
index 0000000..2e8162e
--- /dev/null
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -0,0 +1,173 @@
+/*
+ * arch/arm64/kernel/entry-ftrace.S
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.aka...@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+/*
+ * Gcc with -pg will put the following code in the beginning of each function:
+ *      mov x0, x30
+ *      bl _mcount
+ *     [function's body ...]
+ * "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic
+ * ftrace is enabled.
+ *
+ * Please note that x0 as an argument will not be used here because we can
+ * get lr(x30) of instrumented function at any time by winding up call stack
+ * as long as the kernel is compiled without -fomit-frame-pointer.
+ * (or CONFIG_FRAME_POINTER, this is forced on arm64)
+ *
+ * stack layout after mcount_enter:
+ *
+ *   0 ---------------------------------------- sp of _mcount()
+ *      x29: fp of instrumented function       fp is not winded
+ *     --------------------
+ *      x30: lr of _mcount() (= instrumented function's pc)
+ * +16 ---------------------------------------- sp of instrumented function
+ *
+ *     ....
+ *
+ * +xx ---------------------------------------- fp of instrumented function
+ *      x29: fp of parent
+ *     --------------------
+ *      x30: lr of instrumented function (= parent's pc)
+ *     --------------------
+ *      xxx
+ */
+
can stack layout be more readable as below?
>
Stack layout of _mcount after mcount_enter

        |------------------| sp + 16   <= frame pointer of _mcount.
        |                       |
        |       x30          | <=  lr of _mcount (instrumented func's pc)
        |                       |
        |------------------| sp + 8
        |                       |
        |       x29          | <= value of x29 is sp of instrumented function.

not sp, but fp.
Anyway pls check with my new patch v5.

Thanks,
-Takahiro AKASHI

        |                       |
        |------------------| sp   <= stack pointer of _mcount


Stack layout of instrumented function.
                 .
                 .
                 .
                 .
        |------------------| sp + 16
        |                      |
        |       x30         | <=  lr of instrumented function (= parent's pc)
        |                      |
        |------------------| sp + 8
        |                      |
        |       x29         | <= sp of parent.
        |                      |
        |------------------| sp  <= this address is stored at sp of _mcount


+       .macro mcount_enter
+       stp     x29, x30, [sp, #-16]!
+       .endm
+
+       .macro mcount_exit
+       ldp     x29, x30, [sp], #16
+       ret
+       .endm
+
+       .macro mcount_adjust_addr rd, rn
+       sub     \rd, \rn, #AARCH64_INSN_SIZE
+       .endm
+
+       /* for instrumented function's parent */
+       .macro mcount_get_parent_fp reg
+       ldr     \reg, [sp]
+       ldr     \reg, [\reg]
+       .endm
+
+       /* for instrumented function */
+       .macro mcount_get_pc0 reg
+       mcount_adjust_addr      \reg, x30
+       .endm
+
+       .macro mcount_get_pc reg
+       ldr     \reg, [sp, #8]
+       mcount_adjust_addr      \reg, \reg
+       .endm
+
+       .macro mcount_get_lr reg
+       ldr     \reg, [sp]
+       ldr     \reg, [\reg, #8]
+       mcount_adjust_addr      \reg, \reg
+       .endm
+
+       .macro mcount_get_saved_lr_addr reg
+       ldr     \reg, [sp]
+       add     \reg, \reg, #8
+       .endm
+
+/*
+ * void _mcount(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function makes calls, if enabled, to:
+ *     - tracer function to probe instrumented function's entry,
+ *     - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(_mcount)
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+       ldr     x0, =ftrace_trace_stop
+       ldr     x0, [x0]                // if ftrace_trace_stop
+       ret                             //   return;
+#endif
+       mcount_enter
+
+       ldr     x0, =ftrace_trace_function
+       ldr     x2, [x0]
+       adr     x0, ftrace_stub
+       cmp     x0, x2                  // if (ftrace_trace_function
+       b.eq    skip_ftrace_call        //     != ftrace_stub) {
+
+       mcount_get_pc   x0              //       function's pc
+       mcount_get_lr   x1              //       function's lr (= parent's pc)
+       blr     x2                      //   (*ftrace_trace_function)(pc, lr);
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+skip_ftrace_call:                      //   return;
+       mcount_exit                     // }
+#else
+       mcount_exit                     //   return;
+                                       // }
+skip_ftrace_call:
+       ldr     x1, =ftrace_graph_return
+       ldr     x2, [x1]                //   if ((ftrace_graph_return
+       cmp     x0, x2                  //        != ftrace_stub)
+       b.ne    ftrace_graph_caller
+
+       ldr     x1, =ftrace_graph_entry //     || (ftrace_graph_entry
+       ldr     x2, [x1]                //        != ftrace_graph_entry_stub))
+       ldr     x0, =ftrace_graph_entry_stub
+       cmp     x0, x2
+       b.ne    ftrace_graph_caller     //     ftrace_graph_caller();
+
+       mcount_exit
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+ENDPROC(_mcount)
+
+ENTRY(ftrace_stub)
+       ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * void ftrace_graph_caller(void)
+ *
+ * Called from _mcount() or ftrace_caller() when function_graph tracer is
+ * selected.
+ * This function w/ prepare_ftrace_return() fakes link register's value on
+ * the call stack in order to intercept instrumented function's return path
+ * and run return_to_handler() later on its exit.
+ */
+ENTRY(ftrace_graph_caller)
+       mcount_get_saved_lr_addr  x0    //     pointer to function's saved lr
+       mcount_get_pc             x1    //     function's pc
+       mcount_get_parent_fp      x2    //     parent's fp
+       bl      prepare_ftrace_return   // prepare_ftrace_return(&lr, pc, fp)
+
+       mcount_exit
+ENDPROC(ftrace_graph_caller)
+
+/*
+ * void return_to_handler(void)
+ *
+ * Run ftrace_return_to_handler() before going back to parent.
+ * @fp is checked against the value passed by ftrace_graph_caller()
+ * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ */
+       .global return_to_handler
+return_to_handler:
+       str     x0, [sp, #-16]!
+       mov     x0, x29                 //     parent's fp
+       bl      ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
+       mov     x30, x0                 // restore the original return address
+       ldr     x0, [sp], #16
+       ret
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
new file mode 100644
index 0000000..a559ab8
--- /dev/null
+++ b/arch/arm64/kernel/ftrace.c
@@ -0,0 +1,64 @@
+/*
+ * arch/arm64/kernel/ftrace.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.aka...@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ftrace.h>
+#include <linux/swab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * function_graph tracer expects ftrace_return_to_handler() to be called
+ * on the way back to parent. For this purpose, this function is called
+ * in _mcount() or ftrace_caller() to replace return address (*parent) on
+ * the call stack to return_to_handler.
+ *
+ * Note that @frame_pointer is used only for sanity check later.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+                          unsigned long frame_pointer)
+{
+       unsigned long return_hooker = (unsigned long)&return_to_handler;
+       unsigned long old;
+       struct ftrace_graph_ent trace;
+       int err;
+
+       if (unlikely(atomic_read(&current->tracing_graph_pause)))
+               return;
+
+       /*
+        * Note:
+        * No protection against faulting at *parent, which may be seen
+        * on other archs. It's unlikely on AArch64.
+        */
+       old = *parent;
+       *parent = return_hooker;
+
+       trace.func = self_addr;
+       trace.depth = current->curr_ret_stack + 1;
+
+       /* Only trace if the calling function expects to */
+       if (!ftrace_graph_entry(&trace)) {
+               *parent = old;
+               return;
+       }
+
+       err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+                                      frame_pointer);
+       if (err == -EBUSY) {
+               *parent = old;
+               return;
+       }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
--
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to