d15d356887
Currently perf callchain doesn't work well with ORC unwinder
when sampling from trace point. We'll get useless in kernel callchain
like this:
perf 6429 [000] 22.498450: kmem:mm_page_alloc: page=0x176a17 pfn=1534487 order=0 migratetype=0 gfp_flags=GFP_KERNEL
ffffffffbe23e32e __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux)
7efdf7f7d3e8 __poll+0x18 (/usr/lib64/libc-2.28.so)
5651468729c1 [unknown] (/usr/bin/perf)
5651467ee82a main+0x69a (/usr/bin/perf)
7efdf7eaf413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so)
5541f689495641d7 [unknown] ([unknown])
The root cause is that, for trace point events, it doesn't provide a
real snapshot of the hardware registers. Instead perf tries to get
required caller's registers and compose a fake register snapshot
which suppose to contain enough information for start a unwinding.
However without CONFIG_FRAME_POINTER, if failed to get caller's BP as the
frame pointer, so current frame pointer is returned instead. We get
a invalid register combination which confuse the unwinder, and end the
stacktrace early.
So in such case just don't try dump BP, and let the unwinder start
directly when the register is not a real snapshot. Use SP
as the skip mark, unwinder will skip all the frames until it meet
the frame of the trace point caller.
Tested with frame pointer unwinder and ORC unwinder, this makes perf
callchain get the full kernel space stacktrace again like this:
perf 6503 [000] 1567.570191: kmem:mm_page_alloc: page=0x16c904 pfn=1493252 order=0 migratetype=0 gfp_flags=GFP_KERNEL
ffffffffb523e2ae __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb52383bd __get_free_pages+0xd (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb52fd28a __pollwait+0x8a (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb521426f perf_poll+0x2f (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb52fe3e2 do_sys_poll+0x252 (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb52ff027 __x64_sys_poll+0x37 (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb500418b do_syscall_64+0x5b (/lib/modules/5.1.0-rc3+/build/vmlinux)
ffffffffb5a0008c entry_SYSCALL_64_after_hwframe+0x44 (/lib/modules/5.1.0-rc3+/build/vmlinux)
7f71e92d03e8 __poll+0x18 (/usr/lib64/libc-2.28.so)
55a22960d9c1 [unknown] (/usr/bin/perf)
55a22958982a main+0x69a (/usr/bin/perf)
7f71e9202413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so)
5541f689495641d7 [unknown] ([unknown])
Co-developed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Kairui Song <kasong@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190422162652.15483-1-kasong@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
104 lines
2.4 KiB
C
104 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
|
|
*/
|
|
|
|
#ifndef _ASM_X86_STACKTRACE_H
|
|
#define _ASM_X86_STACKTRACE_H
|
|
|
|
#include <linux/uaccess.h>
|
|
#include <linux/ptrace.h>
|
|
#include <asm/switch_to.h>
|
|
|
|
enum stack_type {
|
|
STACK_TYPE_UNKNOWN,
|
|
STACK_TYPE_TASK,
|
|
STACK_TYPE_IRQ,
|
|
STACK_TYPE_SOFTIRQ,
|
|
STACK_TYPE_ENTRY,
|
|
STACK_TYPE_EXCEPTION,
|
|
STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
|
|
};
|
|
|
|
struct stack_info {
|
|
enum stack_type type;
|
|
unsigned long *begin, *end, *next_sp;
|
|
};
|
|
|
|
bool in_task_stack(unsigned long *stack, struct task_struct *task,
|
|
struct stack_info *info);
|
|
|
|
bool in_entry_stack(unsigned long *stack, struct stack_info *info);
|
|
|
|
int get_stack_info(unsigned long *stack, struct task_struct *task,
|
|
struct stack_info *info, unsigned long *visit_mask);
|
|
|
|
const char *stack_type_name(enum stack_type type);
|
|
|
|
static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
|
|
{
|
|
void *begin = info->begin;
|
|
void *end = info->end;
|
|
|
|
return (info->type != STACK_TYPE_UNKNOWN &&
|
|
addr >= begin && addr < end &&
|
|
addr + len > begin && addr + len <= end);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_32
|
|
#define STACKSLOTS_PER_LINE 8
|
|
#else
|
|
#define STACKSLOTS_PER_LINE 4
|
|
#endif
|
|
|
|
#ifdef CONFIG_FRAME_POINTER
|
|
static inline unsigned long *
|
|
get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
if (regs)
|
|
return (unsigned long *)regs->bp;
|
|
|
|
if (task == current)
|
|
return __builtin_frame_address(0);
|
|
|
|
return &((struct inactive_task_frame *)task->thread.sp)->bp;
|
|
}
|
|
#else
|
|
static inline unsigned long *
|
|
get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif /* CONFIG_FRAME_POINTER */
|
|
|
|
static inline unsigned long *
|
|
get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
if (regs)
|
|
return (unsigned long *)kernel_stack_pointer(regs);
|
|
|
|
if (task == current)
|
|
return __builtin_frame_address(0);
|
|
|
|
return (unsigned long *)task->thread.sp;
|
|
}
|
|
|
|
void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
|
|
unsigned long *stack, char *log_lvl);
|
|
|
|
/* The form of the top of the frame on the stack */
|
|
struct stack_frame {
|
|
struct stack_frame *next_frame;
|
|
unsigned long return_address;
|
|
};
|
|
|
|
struct stack_frame_ia32 {
|
|
u32 next_frame;
|
|
u32 return_address;
|
|
};
|
|
|
|
void show_opcodes(struct pt_regs *regs, const char *loglvl);
|
|
void show_ip(struct pt_regs *regs, const char *loglvl);
|
|
#endif /* _ASM_X86_STACKTRACE_H */
|