c5dfd78eb7
The default remains 127, which is good for most cases, and not even hit most of the time, but then for some cases, as reported by Brendan, 1024+ deep frames are appearing on the radar for things like groovy, ruby. And in some workloads putting a _lower_ cap on this may make sense. One that is per event still needs to be put in place tho. The new file is: # cat /proc/sys/kernel/perf_event_max_stack 127 Chaging it: # echo 256 > /proc/sys/kernel/perf_event_max_stack # cat /proc/sys/kernel/perf_event_max_stack 256 But as soon as there is some event using callchains we get: # echo 512 > /proc/sys/kernel/perf_event_max_stack -bash: echo: write error: Device or resource busy # Because we only allocate the callchain percpu data structures when there is a user, which allows for changing the max easily, its just a matter of having no callchain users at that point. Reported-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Milian Wolff <milian.wolff@kdab.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Wang Nan <wangnan0@huawei.com> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/20160426002928.GB16708@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
70 lines
1.8 KiB
C
70 lines
1.8 KiB
C
/*
|
|
* Linux performance counter support for MIPS.
|
|
*
|
|
* Copyright (C) 2010 MIPS Technologies, Inc.
|
|
* Author: Deng-Cheng Zhu
|
|
*
|
|
* This code is based on the implementation for ARM, which is in turn
|
|
* based on the sparc64 perf event code and the x86 code. Performance
|
|
* counter access is based on the MIPS Oprofile code. And the callchain
|
|
* support references the code of MIPS stacktrace.c.
|
|
*
|
|
* 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/perf_event.h>
|
|
|
|
#include <asm/stacktrace.h>
|
|
|
|
/* Callchain handling code. */
|
|
|
|
/*
|
|
* Leave userspace callchain empty for now. When we find a way to trace
|
|
* the user stack callchains, we will add it here.
|
|
*/
|
|
|
|
static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
|
|
unsigned long reg29)
|
|
{
|
|
unsigned long *sp = (unsigned long *)reg29;
|
|
unsigned long addr;
|
|
|
|
while (!kstack_end(sp)) {
|
|
addr = *sp++;
|
|
if (__kernel_text_address(addr)) {
|
|
perf_callchain_store(entry, addr);
|
|
if (entry->nr >= sysctl_perf_event_max_stack)
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
void perf_callchain_kernel(struct perf_callchain_entry *entry,
|
|
struct pt_regs *regs)
|
|
{
|
|
unsigned long sp = regs->regs[29];
|
|
#ifdef CONFIG_KALLSYMS
|
|
unsigned long ra = regs->regs[31];
|
|
unsigned long pc = regs->cp0_epc;
|
|
|
|
if (raw_show_trace || !__kernel_text_address(pc)) {
|
|
unsigned long stack_page =
|
|
(unsigned long)task_stack_page(current);
|
|
if (stack_page && sp >= stack_page &&
|
|
sp <= stack_page + THREAD_SIZE - 32)
|
|
save_raw_perf_callchain(entry, sp);
|
|
return;
|
|
}
|
|
do {
|
|
perf_callchain_store(entry, pc);
|
|
if (entry->nr >= sysctl_perf_event_max_stack)
|
|
break;
|
|
pc = unwind_stack(current, &sp, pc, &ra);
|
|
} while (pc);
|
|
#else
|
|
save_raw_perf_callchain(entry, sp);
|
|
#endif
|
|
}
|