kernel_optimize_test/arch/mips/kernel/mcount.S

158 lines
3.0 KiB
ArmAsm
Raw Normal View History

/*
* 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
#ifdef CONFIG_64BIT
PTR_ADDIU sp, PT_SIZE
#else
PTR_ADDIU sp, (PT_SIZE + 8)
#endif
.endm
.macro RETURN_BACK
jr ra
move ra, AT
.endm
MIPS: Tracing: Add dynamic function tracer support With dynamic function tracer, by default, _mcount is defined as an "empty" function, it returns directly without any more action . When enabling it in user-space, it will jump to a real tracing function(ftrace_caller), and do the 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 in arch/mips/Makefile: MODFLAGS += -mlong-calls. The stuff becomes a little more complex. We need to cope with two different type of calling to _mcount. For the kernel part, the calling to _mcount(result of "objdump -hdr vmlinux"). is 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 For the module with -mlong-calls, it looks like this: 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 In the kernel 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 module 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 kernel 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 do this: lui v1, hi_16bit_of_mcount <--> b 1f (0x10000004) addiu v1, v1, low_16bit_of_mcount move at, ra jalr v1 nop 1f: (rec->ip + 12) 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 <wuzhangjin@gmail.com> Cc: Nicholas Mc Guire <der.herr@hofr.at> Cc: zhangfx@lemote.com Cc: Wu Zhangjin <wuzhangjin@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/675/ Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2009-11-20 20:34:32 +08:00
#ifdef CONFIG_DYNAMIC_FTRACE
NESTED(ftrace_caller, PT_SIZE, ra)
.globl _mcount
_mcount:
b ftrace_stub
nop
lw t0, function_trace_stop
bnez t0, ftrace_stub
nop
MCOUNT_SAVE_REGS
move a0, ra /* arg1: next ip, selfaddr */
.globl ftrace_call
ftrace_call:
nop /* a placeholder for the call to a real tracing function */
move a1, AT /* arg2: the caller's next ip, parent */
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
nop
PTR_LA t0, ftrace_stub
PTR_L t1, ftrace_trace_function /* Prepare t1 for (1) */
bne t0, t1, static_trace
nop
MIPS: Tracing: Add function graph tracer support for MIPS 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. For the kernel part without -mlong-calls: move at, ra jal _mcount For the module part with -mlong-calls: lui v1, hi16bit_of_mcount addiu v1, v1, low16bit_of_mcount move at, ra jal _mcount Without -mlong-calls, if the function is a leaf, it will not 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 not a store instruction, there should be 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. If with -mlong-calls, since there are two more instructions above "move at, ra", so, we can move the pointer to the position above "lui v1, hi16bit_of_mcount". Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Nicholas Mc Guire <der.herr@hofr.at> Cc: zhangfx@lemote.com Cc: Wu Zhangjin <wuzhangjin@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/677/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2009-11-20 20:34:34 +08:00
#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
b ftrace_stub
nop
static_trace:
MCOUNT_SAVE_REGS
move a0, ra /* arg1: next ip, selfaddr */
jalr t1 /* (1) call *ftrace_trace_function */
move a1, AT /* arg2: the caller's next ip, parent */
MCOUNT_RESTORE_REGS
.globl ftrace_stub
ftrace_stub:
RETURN_BACK
END(_mcount)
MIPS: Tracing: Add dynamic function tracer support With dynamic function tracer, by default, _mcount is defined as an "empty" function, it returns directly without any more action . When enabling it in user-space, it will jump to a real tracing function(ftrace_caller), and do the 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 in arch/mips/Makefile: MODFLAGS += -mlong-calls. The stuff becomes a little more complex. We need to cope with two different type of calling to _mcount. For the kernel part, the calling to _mcount(result of "objdump -hdr vmlinux"). is 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 For the module with -mlong-calls, it looks like this: 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 In the kernel 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 module 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 kernel 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 do this: lui v1, hi_16bit_of_mcount <--> b 1f (0x10000004) addiu v1, v1, low_16bit_of_mcount move at, ra jalr v1 nop 1f: (rec->ip + 12) 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 <wuzhangjin@gmail.com> Cc: Nicholas Mc Guire <der.herr@hofr.at> Cc: zhangfx@lemote.com Cc: Wu Zhangjin <wuzhangjin@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/675/ Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2009-11-20 20:34:32 +08:00
#endif /* ! CONFIG_DYNAMIC_FTRACE */
MIPS: Tracing: Add function graph tracer support for MIPS 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. For the kernel part without -mlong-calls: move at, ra jal _mcount For the module part with -mlong-calls: lui v1, hi16bit_of_mcount addiu v1, v1, low16bit_of_mcount move at, ra jal _mcount Without -mlong-calls, if the function is a leaf, it will not 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 not a store instruction, there should be 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. If with -mlong-calls, since there are two more instructions above "move at, ra", so, we can move the pointer to the position above "lui v1, hi16bit_of_mcount". Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Nicholas Mc Guire <der.herr@hofr.at> Cc: zhangfx@lemote.com Cc: Wu Zhangjin <wuzhangjin@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/677/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2009-11-20 20:34:34 +08:00
#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 */
jal prepare_ftrace_return
move a2, fp /* arg3: frame pointer */
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
PTR_S v1, PT_R3(sp)
/* restore the real parent address: v0 -> ra */
move ra, v0
PTR_L v0, PT_R2(sp)
PTR_L v1, PT_R3(sp)
jr ra
PTR_ADDIU sp, PT_SIZE
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
.set at
.set reorder