mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-29 23:24:11 +08:00
9eff26ea48
This implements a powerpc version of perf_arch_fetch_caller_regs
to get correct call-graphs.
It's implemented in assembly because that way we can be sure there isn't
a stack frame for perf_arch_fetch_caller_regs. If it was in C, gcc might
or might not create a stack frame for it, which would affect the number
of levels we have to skip.
With this, we see results from perf record -e lock:lock_acquire like
this:
# Samples: 24878
#
# Overhead Command Shared Object Symbol
# ........ .............. ................. ......
#
14.99% perf [kernel.kallsyms] [k] ._raw_spin_lock
|
--- ._raw_spin_lock
|
|--25.00%-- .alloc_fd
| (nil)
| |
| |--50.00%-- .anon_inode_getfd
| | .sys_perf_event_open
| | syscall_exit
| | syscall
| | create_counter
| | __cmd_record
| | run_builtin
| | main
| | 0xfd2e704
| | 0xfd2e8c0
| | (nil)
... etc.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: anton@samba.org
Cc: linuxppc-dev@ozlabs.org
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20100318050513.GA6575@drongo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
158 lines
3.2 KiB
ArmAsm
158 lines
3.2 KiB
ArmAsm
/*
|
|
* This file contains miscellaneous low-level functions.
|
|
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
|
|
*
|
|
* Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
|
|
* and Paul Mackerras.
|
|
*
|
|
* Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
|
|
* PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
|
|
*
|
|
* setjmp/longjmp code by Paul Mackerras.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
#include <asm/ppc_asm.h>
|
|
#include <asm/unistd.h>
|
|
#include <asm/asm-compat.h>
|
|
#include <asm/asm-offsets.h>
|
|
|
|
.text
|
|
|
|
/*
|
|
* Returns (address we are running at) - (address we were linked at)
|
|
* for use before the text and data are mapped to KERNELBASE.
|
|
*/
|
|
|
|
_GLOBAL(reloc_offset)
|
|
mflr r0
|
|
bl 1f
|
|
1: mflr r3
|
|
PPC_LL r4,(2f-1b)(r3)
|
|
subf r3,r4,r3
|
|
mtlr r0
|
|
blr
|
|
|
|
.align 3
|
|
2: PPC_LONG 1b
|
|
|
|
/*
|
|
* add_reloc_offset(x) returns x + reloc_offset().
|
|
*/
|
|
_GLOBAL(add_reloc_offset)
|
|
mflr r0
|
|
bl 1f
|
|
1: mflr r5
|
|
PPC_LL r4,(2f-1b)(r5)
|
|
subf r5,r4,r5
|
|
add r3,r3,r5
|
|
mtlr r0
|
|
blr
|
|
|
|
.align 3
|
|
2: PPC_LONG 1b
|
|
|
|
_GLOBAL(kernel_execve)
|
|
li r0,__NR_execve
|
|
sc
|
|
bnslr
|
|
neg r3,r3
|
|
blr
|
|
|
|
_GLOBAL(setjmp)
|
|
mflr r0
|
|
PPC_STL r0,0(r3)
|
|
PPC_STL r1,SZL(r3)
|
|
PPC_STL r2,2*SZL(r3)
|
|
mfcr r0
|
|
PPC_STL r0,3*SZL(r3)
|
|
PPC_STL r13,4*SZL(r3)
|
|
PPC_STL r14,5*SZL(r3)
|
|
PPC_STL r15,6*SZL(r3)
|
|
PPC_STL r16,7*SZL(r3)
|
|
PPC_STL r17,8*SZL(r3)
|
|
PPC_STL r18,9*SZL(r3)
|
|
PPC_STL r19,10*SZL(r3)
|
|
PPC_STL r20,11*SZL(r3)
|
|
PPC_STL r21,12*SZL(r3)
|
|
PPC_STL r22,13*SZL(r3)
|
|
PPC_STL r23,14*SZL(r3)
|
|
PPC_STL r24,15*SZL(r3)
|
|
PPC_STL r25,16*SZL(r3)
|
|
PPC_STL r26,17*SZL(r3)
|
|
PPC_STL r27,18*SZL(r3)
|
|
PPC_STL r28,19*SZL(r3)
|
|
PPC_STL r29,20*SZL(r3)
|
|
PPC_STL r30,21*SZL(r3)
|
|
PPC_STL r31,22*SZL(r3)
|
|
li r3,0
|
|
blr
|
|
|
|
_GLOBAL(longjmp)
|
|
PPC_LCMPI r4,0
|
|
bne 1f
|
|
li r4,1
|
|
1: PPC_LL r13,4*SZL(r3)
|
|
PPC_LL r14,5*SZL(r3)
|
|
PPC_LL r15,6*SZL(r3)
|
|
PPC_LL r16,7*SZL(r3)
|
|
PPC_LL r17,8*SZL(r3)
|
|
PPC_LL r18,9*SZL(r3)
|
|
PPC_LL r19,10*SZL(r3)
|
|
PPC_LL r20,11*SZL(r3)
|
|
PPC_LL r21,12*SZL(r3)
|
|
PPC_LL r22,13*SZL(r3)
|
|
PPC_LL r23,14*SZL(r3)
|
|
PPC_LL r24,15*SZL(r3)
|
|
PPC_LL r25,16*SZL(r3)
|
|
PPC_LL r26,17*SZL(r3)
|
|
PPC_LL r27,18*SZL(r3)
|
|
PPC_LL r28,19*SZL(r3)
|
|
PPC_LL r29,20*SZL(r3)
|
|
PPC_LL r30,21*SZL(r3)
|
|
PPC_LL r31,22*SZL(r3)
|
|
PPC_LL r0,3*SZL(r3)
|
|
mtcrf 0x38,r0
|
|
PPC_LL r0,0(r3)
|
|
PPC_LL r1,SZL(r3)
|
|
PPC_LL r2,2*SZL(r3)
|
|
mtlr r0
|
|
mr r3,r4
|
|
blr
|
|
|
|
_GLOBAL(__setup_cpu_power7)
|
|
_GLOBAL(__restore_cpu_power7)
|
|
/* place holder */
|
|
blr
|
|
|
|
#ifdef CONFIG_EVENT_TRACING
|
|
/*
|
|
* Get a minimal set of registers for our caller's nth caller.
|
|
* r3 = regs pointer, r5 = n.
|
|
*
|
|
* We only get R1 (stack pointer), NIP (next instruction pointer)
|
|
* and LR (link register). These are all we can get in the
|
|
* general case without doing complicated stack unwinding, but
|
|
* fortunately they are enough to do a stack backtrace, which
|
|
* is all we need them for.
|
|
*/
|
|
_GLOBAL(perf_arch_fetch_caller_regs)
|
|
mr r6,r1
|
|
cmpwi r5,0
|
|
mflr r4
|
|
ble 2f
|
|
mtctr r5
|
|
1: PPC_LL r6,0(r6)
|
|
bdnz 1b
|
|
PPC_LL r4,PPC_LR_STKOFF(r6)
|
|
2: PPC_LL r7,0(r6)
|
|
PPC_LL r7,PPC_LR_STKOFF(r7)
|
|
PPC_STL r6,GPR1-STACK_FRAME_OVERHEAD(r3)
|
|
PPC_STL r4,_NIP-STACK_FRAME_OVERHEAD(r3)
|
|
PPC_STL r7,_LINK-STACK_FRAME_OVERHEAD(r3)
|
|
blr
|
|
#endif /* CONFIG_EVENT_TRACING */
|