mirror of
https://github.com/team-infusion-developers/android_kernel_samsung_msm8976.git
synced 2024-11-01 10:33:27 +00:00
eb1e79611c
The trace event buffer used by perf to record raw sample events is typed as an array of char and may then not be aligned to 8 by alloc_percpu(). But we need it to be aligned to 8 in sparc64 because we cast this buffer into a random structure type built by the TRACE_EVENT() macro to store the traces. So if a random 64 bits field is accessed inside, it may be not under an expected good alignment. Use an array of long instead to force the appropriate alignment, and perform a compile time check to ensure the size in byte of the buffer is a multiple of sizeof(long) so that its actual size doesn't get shrinked under us. This fixes unaligned accesses reported while using perf lock in sparc 64. Suggested-by: David Miller <davem@davemloft.net> Suggested-by: Tejun Heo <htejun@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: David Miller <davem@davemloft.net> Cc: Steven Rostedt <rostedt@goodmis.org>
175 lines
3.7 KiB
C
175 lines
3.7 KiB
C
/*
|
|
* trace event based perf event profiling/tracing
|
|
*
|
|
* Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
|
|
* Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/kprobes.h>
|
|
#include "trace.h"
|
|
|
|
DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
|
|
EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
|
|
|
|
EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
|
|
|
|
static char *perf_trace_buf;
|
|
static char *perf_trace_buf_nmi;
|
|
|
|
/*
|
|
* Force it to be aligned to unsigned long to avoid misaligned accesses
|
|
* suprises
|
|
*/
|
|
typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
|
|
perf_trace_t;
|
|
|
|
/* Count the events in use (per event id, not per instance) */
|
|
static int total_ref_count;
|
|
|
|
static int perf_trace_event_enable(struct ftrace_event_call *event)
|
|
{
|
|
char *buf;
|
|
int ret = -ENOMEM;
|
|
|
|
if (event->perf_refcount++ > 0)
|
|
return 0;
|
|
|
|
if (!total_ref_count) {
|
|
buf = (char *)alloc_percpu(perf_trace_t);
|
|
if (!buf)
|
|
goto fail_buf;
|
|
|
|
rcu_assign_pointer(perf_trace_buf, buf);
|
|
|
|
buf = (char *)alloc_percpu(perf_trace_t);
|
|
if (!buf)
|
|
goto fail_buf_nmi;
|
|
|
|
rcu_assign_pointer(perf_trace_buf_nmi, buf);
|
|
}
|
|
|
|
ret = event->perf_event_enable(event);
|
|
if (!ret) {
|
|
total_ref_count++;
|
|
return 0;
|
|
}
|
|
|
|
fail_buf_nmi:
|
|
if (!total_ref_count) {
|
|
free_percpu(perf_trace_buf_nmi);
|
|
free_percpu(perf_trace_buf);
|
|
perf_trace_buf_nmi = NULL;
|
|
perf_trace_buf = NULL;
|
|
}
|
|
fail_buf:
|
|
event->perf_refcount--;
|
|
|
|
return ret;
|
|
}
|
|
|
|
int perf_trace_enable(int event_id)
|
|
{
|
|
struct ftrace_event_call *event;
|
|
int ret = -EINVAL;
|
|
|
|
mutex_lock(&event_mutex);
|
|
list_for_each_entry(event, &ftrace_events, list) {
|
|
if (event->id == event_id && event->perf_event_enable &&
|
|
try_module_get(event->mod)) {
|
|
ret = perf_trace_event_enable(event);
|
|
break;
|
|
}
|
|
}
|
|
mutex_unlock(&event_mutex);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void perf_trace_event_disable(struct ftrace_event_call *event)
|
|
{
|
|
char *buf, *nmi_buf;
|
|
|
|
if (--event->perf_refcount > 0)
|
|
return;
|
|
|
|
event->perf_event_disable(event);
|
|
|
|
if (!--total_ref_count) {
|
|
buf = perf_trace_buf;
|
|
rcu_assign_pointer(perf_trace_buf, NULL);
|
|
|
|
nmi_buf = perf_trace_buf_nmi;
|
|
rcu_assign_pointer(perf_trace_buf_nmi, NULL);
|
|
|
|
/*
|
|
* Ensure every events in profiling have finished before
|
|
* releasing the buffers
|
|
*/
|
|
synchronize_sched();
|
|
|
|
free_percpu(buf);
|
|
free_percpu(nmi_buf);
|
|
}
|
|
}
|
|
|
|
void perf_trace_disable(int event_id)
|
|
{
|
|
struct ftrace_event_call *event;
|
|
|
|
mutex_lock(&event_mutex);
|
|
list_for_each_entry(event, &ftrace_events, list) {
|
|
if (event->id == event_id) {
|
|
perf_trace_event_disable(event);
|
|
module_put(event->mod);
|
|
break;
|
|
}
|
|
}
|
|
mutex_unlock(&event_mutex);
|
|
}
|
|
|
|
__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
|
|
int *rctxp, unsigned long *irq_flags)
|
|
{
|
|
struct trace_entry *entry;
|
|
char *trace_buf, *raw_data;
|
|
int pc, cpu;
|
|
|
|
BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
|
|
|
|
pc = preempt_count();
|
|
|
|
/* Protect the per cpu buffer, begin the rcu read side */
|
|
local_irq_save(*irq_flags);
|
|
|
|
*rctxp = perf_swevent_get_recursion_context();
|
|
if (*rctxp < 0)
|
|
goto err_recursion;
|
|
|
|
cpu = smp_processor_id();
|
|
|
|
if (in_nmi())
|
|
trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
|
|
else
|
|
trace_buf = rcu_dereference_sched(perf_trace_buf);
|
|
|
|
if (!trace_buf)
|
|
goto err;
|
|
|
|
raw_data = per_cpu_ptr(trace_buf, cpu);
|
|
|
|
/* zero the dead bytes from align to not leak stack to user */
|
|
memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
|
|
|
|
entry = (struct trace_entry *)raw_data;
|
|
tracing_generic_entry_update(entry, *irq_flags, pc);
|
|
entry->type = type;
|
|
|
|
return raw_data;
|
|
err:
|
|
perf_swevent_put_recursion_context(*rctxp);
|
|
err_recursion:
|
|
local_irq_restore(*irq_flags);
|
|
return NULL;
|
|
}
|
|
EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
|