summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2010-03-03 07:16:16 +0100
committerFrederic Weisbecker <fweisbec@gmail.com>2010-03-10 14:40:38 +0100
commitc530665c31c0140b74ca7689e7f836177796e5bd (patch)
treeac9ebb98aca58fdf84cc18958a94393a9a7bbdf3 /include
parent5331d7b84613b8325362dde53dc2bff2fb87d351 (diff)
downloadop-kernel-dev-c530665c31c0140b74ca7689e7f836177796e5bd.zip
op-kernel-dev-c530665c31c0140b74ca7689e7f836177796e5bd.tar.gz
perf: Take a hot regs snapshot for trace events
We are taking a wrong regs snapshot when a trace event triggers. Either we use get_irq_regs(), which gives us the interrupted registers if we are in an interrupt, or we use task_pt_regs() which gives us the state before we entered the kernel, assuming we are lucky enough to be no kernel thread, in which case task_pt_regs() returns the initial set of regs when the kernel thread was started. What we want is different. We need a hot snapshot of the regs, so that we can get the instruction pointer to record in the sample, the frame pointer for the callchain, and some other things. Let's use the new perf_fetch_caller_regs() for that. Comparison with perf record -e lock: -R -a -f -g Before: perf [kernel] [k] __do_softirq | --- __do_softirq | |--55.16%-- __open | --44.84%-- __write_nocancel After: perf [kernel] [k] perf_tp_event | --- perf_tp_event | |--41.07%-- lock_acquire | | | |--39.36%-- _raw_spin_lock | | | | | |--7.81%-- hrtimer_interrupt | | | smp_apic_timer_interrupt | | | apic_timer_interrupt The old case was producing unreliable callchains. Now having right frame and instruction pointers, we have the trace we want. Also syscalls and kprobe events already have the right regs, let's use them instead of wasting a retrieval. v2: Follow the rename perf_save_regs() -> perf_fetch_caller_regs() Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Archs <linux-arch@vger.kernel.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/ftrace_event.h7
-rw-r--r--include/trace/ftrace.h6
2 files changed, 10 insertions, 3 deletions
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6b7c444..ac424f1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -187,6 +187,9 @@ do { \
#ifdef CONFIG_PERF_EVENTS
struct perf_event;
+
+DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+
extern int ftrace_profile_enable(int event_id);
extern void ftrace_profile_disable(int event_id);
extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
@@ -198,11 +201,11 @@ ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
static inline void
ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
- u64 count, unsigned long irq_flags)
+ u64 count, unsigned long irq_flags, struct pt_regs *regs)
{
struct trace_entry *entry = raw_data;
- perf_tp_event(entry->type, addr, count, raw_data, size);
+ perf_tp_event(entry->type, addr, count, raw_data, size, regs);
perf_swevent_put_recursion_context(rctx);
local_irq_restore(irq_flags);
}
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 0804cd5..f31bb8b 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -764,6 +764,7 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \
struct ftrace_raw_##call *entry; \
u64 __addr = 0, __count = 1; \
unsigned long irq_flags; \
+ struct pt_regs *__regs; \
int __entry_size; \
int __data_size; \
int rctx; \
@@ -784,8 +785,11 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call, \
\
{ assign; } \
\
+ __regs = &__get_cpu_var(perf_trace_regs); \
+ perf_fetch_caller_regs(__regs, 2); \
+ \
ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr, \
- __count, irq_flags); \
+ __count, irq_flags, __regs); \
}
#undef DEFINE_EVENT
OpenPOWER on IntegriCloud