linux_dsm_epyc7002/kernel/trace/trace_sched_switch.c
Tom Zanussi f306cc82a9 tracing: Update event filters for multibuffer
The trace event filters are still tied to event calls rather than
event files, which means you don't get what you'd expect when using
filters in the multibuffer case:

Before:

  # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 8192
  # mkdir /sys/kernel/debug/tracing/instances/test1
  # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 2048
  # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  bytes_alloc > 2048

Setting the filter in tracing/instances/test1/events shouldn't affect
the same event in tracing/events as it does above.

After:

  # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 8192
  # mkdir /sys/kernel/debug/tracing/instances/test1
  # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter
  bytes_alloc > 8192
  # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter
  bytes_alloc > 2048

We'd like to just move the filter directly from ftrace_event_call to
ftrace_event_file, but there are a couple cases that don't yet have
multibuffer support and therefore have to continue using the current
event_call-based filters.  For those cases, a new USE_CALL_FILTER bit
is added to the event_call flags, whose main purpose is to keep the
old behavior for those cases until they can be updated with
multibuffer support; at that point, the USE_CALL_FILTER flag (and the
new associated call_filter_check_discard() function) can go away.

The multibuffer support also made filter_current_check_discard()
redundant, so this change removes that function as well and replaces
it with filter_check_discard() (or call_filter_check_discard() as
appropriate).

Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com

Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-11-05 16:50:20 -05:00

248 lines
5.8 KiB
C

/*
* trace context switch
*
* Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <trace/events/sched.h>
#include "trace.h"
static struct trace_array *ctx_trace;
static int __read_mostly tracer_enabled;
static int sched_ref;
static DEFINE_MUTEX(sched_register_mutex);
static int sched_stopped;
void
tracing_sched_switch_trace(struct trace_array *tr,
struct task_struct *prev,
struct task_struct *next,
unsigned long flags, int pc)
{
struct ftrace_event_call *call = &event_context_switch;
struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->prev_pid = prev->pid;
entry->prev_prio = prev->prio;
entry->prev_state = prev->state;
entry->next_pid = next->pid;
entry->next_prio = next->prio;
entry->next_state = next->state;
entry->next_cpu = task_cpu(next);
if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, flags, pc);
}
static void
probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
unsigned long flags;
int cpu;
int pc;
if (unlikely(!sched_ref))
return;
tracing_record_cmdline(prev);
tracing_record_cmdline(next);
if (!tracer_enabled || sched_stopped)
return;
pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu);
if (likely(!atomic_read(&data->disabled)))
tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc);
local_irq_restore(flags);
}
void
tracing_sched_wakeup_trace(struct trace_array *tr,
struct task_struct *wakee,
struct task_struct *curr,
unsigned long flags, int pc)
{
struct ftrace_event_call *call = &event_wakeup;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
struct ring_buffer *buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->prev_pid = curr->pid;
entry->prev_prio = curr->prio;
entry->prev_state = curr->state;
entry->next_pid = wakee->pid;
entry->next_prio = wakee->prio;
entry->next_state = wakee->state;
entry->next_cpu = task_cpu(wakee);
if (!call_filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, flags, pc);
}
static void
probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
{
struct trace_array_cpu *data;
unsigned long flags;
int cpu, pc;
if (unlikely(!sched_ref))
return;
tracing_record_cmdline(current);
if (!tracer_enabled || sched_stopped)
return;
pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(ctx_trace->trace_buffer.data, cpu);
if (likely(!atomic_read(&data->disabled)))
tracing_sched_wakeup_trace(ctx_trace, wakee, current,
flags, pc);
local_irq_restore(flags);
}
static int tracing_sched_register(void)
{
int ret;
ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return ret;
}
ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
ret = register_trace_sched_switch(probe_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
goto fail_deprobe_wake_new;
}
return ret;
fail_deprobe_wake_new:
unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
fail_deprobe:
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
return ret;
}
static void tracing_sched_unregister(void)
{
unregister_trace_sched_switch(probe_sched_switch, NULL);
unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
}
static void tracing_start_sched_switch(void)
{
mutex_lock(&sched_register_mutex);
if (!(sched_ref++))
tracing_sched_register();
mutex_unlock(&sched_register_mutex);
}
static void tracing_stop_sched_switch(void)
{
mutex_lock(&sched_register_mutex);
if (!(--sched_ref))
tracing_sched_unregister();
mutex_unlock(&sched_register_mutex);
}
void tracing_start_cmdline_record(void)
{
tracing_start_sched_switch();
}
void tracing_stop_cmdline_record(void)
{
tracing_stop_sched_switch();
}
/**
* tracing_start_sched_switch_record - start tracing context switches
*
* Turns on context switch tracing for a tracer.
*/
void tracing_start_sched_switch_record(void)
{
if (unlikely(!ctx_trace)) {
WARN_ON(1);
return;
}
tracing_start_sched_switch();
mutex_lock(&sched_register_mutex);
tracer_enabled++;
mutex_unlock(&sched_register_mutex);
}
/**
* tracing_stop_sched_switch_record - start tracing context switches
*
* Turns off context switch tracing for a tracer.
*/
void tracing_stop_sched_switch_record(void)
{
mutex_lock(&sched_register_mutex);
tracer_enabled--;
WARN_ON(tracer_enabled < 0);
mutex_unlock(&sched_register_mutex);
tracing_stop_sched_switch();
}
/**
* tracing_sched_switch_assign_trace - assign a trace array for ctx switch
* @tr: trace array pointer to assign
*
* Some tracers might want to record the context switches in their
* trace. This function lets those tracers assign the trace array
* to use.
*/
void tracing_sched_switch_assign_trace(struct trace_array *tr)
{
ctx_trace = tr;
}