linux/arch/sh/kernel/perf_callchain.c
Anton Blanchard 339ce1a4dc perf: Fix inconsistency between IP and callchain sampling
When running perf across all cpus with backtracing (-a -g), sometimes we
get samples without associated backtraces:

    23.44%         init  [kernel]                     [k] restore
    11.46%         init                       eeba0c  [k] 0x00000000eeba0c
     6.77%      swapper  [kernel]                     [k] .perf_ctx_adjust_freq
     5.73%         init  [kernel]                     [k] .__trace_hcall_entry
     4.69%         perf  libc-2.9.so                  [.] 0x0000000006bb8c
                       |
                       |--11.11%-- 0xfffa941bbbc

It turns out the backtrace code has a check for the idle task and the IP
sampling does not. This creates problems when profiling an interrupt
heavy workload (in my case 10Gbit ethernet) since we get no backtraces
for interrupts received while idle (ie most of the workload).

Right now x86 and sh check that current is not NULL, which should never
happen so remove that too.

Idle task's exclusion must be performed from the core code, on top
of perf_event_attr:exclude_idle.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mundt <lethal@linux-sh.org>
LKML-Reference: <20100118054707.GT12666@kryten>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2010-01-28 14:31:20 +01:00

95 lines
2 KiB
C

/*
* Performance event callchain support - SuperH architecture code
*
* Copyright (C) 2009 Paul Mundt
*
* 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.
*/
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/perf_event.h>
#include <linux/percpu.h>
#include <asm/unwinder.h>
#include <asm/ptrace.h>
static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
{
if (entry->nr < PERF_MAX_STACK_DEPTH)
entry->ip[entry->nr++] = ip;
}
static void callchain_warning(void *data, char *msg)
{
}
static void
callchain_warning_symbol(void *data, char *msg, unsigned long symbol)
{
}
static int callchain_stack(void *data, char *name)
{
return 0;
}
static void callchain_address(void *data, unsigned long addr, int reliable)
{
struct perf_callchain_entry *entry = data;
if (reliable)
callchain_store(entry, addr);
}
static const struct stacktrace_ops callchain_ops = {
.warning = callchain_warning,
.warning_symbol = callchain_warning_symbol,
.stack = callchain_stack,
.address = callchain_address,
};
static void
perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
callchain_store(entry, PERF_CONTEXT_KERNEL);
callchain_store(entry, regs->pc);
unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
}
static void
perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
int is_user;
if (!regs)
return;
is_user = user_mode(regs);
if (is_user && current->state != TASK_RUNNING)
return;
/*
* Only the kernel side is implemented for now.
*/
if (!is_user)
perf_callchain_kernel(regs, entry);
}
/*
* No need for separate IRQ and NMI entries.
*/
static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
{
struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
entry->nr = 0;
perf_do_callchain(regs, entry);
return entry;
}