Set a default event->overflow_handler in perf_event_alloc() so don't
need to check event->overflow_handler in __perf_event_overflow().
Following commits can give a different default overflow_handler.

Initial idea comes from Peter at [1]

Since default value of event->overflow_handler is not null, existing
'if (!overflow_handler)' need to be changed.
is_default_overflow_handler() is introduced for this.

No extra performance introduced into hot path because in the original
code we still need reading this handler from memory. A conditional branch
is avoided so actually we remove some instructions.

[1] 
http://lkml.kernel.org/r/20130708121557.ga17...@twins.programming.kicks-ass.net

Signed-off-by: Wang Nan <wangn...@huawei.com>
Cc: He Kuang <heku...@huawei.com>
Cc: Alexei Starovoitov <a...@kernel.org>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Brendan Gregg <brendan.d.gr...@gmail.com>
Cc: Jiri Olsa <jo...@kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu...@hitachi.com>
Cc: Namhyung Kim <namhy...@kernel.org>
Cc: Peter Zijlstra <pet...@infradead.org>
Cc: Zefan Li <lize...@huawei.com>
Cc: pi3or...@163.com
---
 arch/arm/kernel/hw_breakpoint.c   |  4 ++--
 arch/arm64/kernel/hw_breakpoint.c |  4 ++--
 include/linux/perf_event.h        |  6 ++++++
 kernel/events/core.c              | 14 ++++++++------
 4 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 6284779..b8df458 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -631,7 +631,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
        info->address &= ~alignment_mask;
        info->ctrl.len <<= offset;
 
-       if (!bp->overflow_handler) {
+       if (is_default_overflow_handler(bp)) {
                /*
                 * Mismatch breakpoints are required for single-stepping
                 * breakpoints.
@@ -754,7 +754,7 @@ static void watchpoint_handler(unsigned long addr, unsigned 
int fsr,
                 * mismatch breakpoint so we can single-step over the
                 * watchpoint trigger.
                 */
-               if (!wp->overflow_handler)
+               if (is_default_overflow_handler(wp))
                        enable_single_step(wp, instruction_pointer(regs));
 
 unlock:
diff --git a/arch/arm64/kernel/hw_breakpoint.c 
b/arch/arm64/kernel/hw_breakpoint.c
index b45c95d..4ef5373 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -616,7 +616,7 @@ static int breakpoint_handler(unsigned long unused, 
unsigned int esr,
                perf_bp_event(bp, regs);
 
                /* Do we need to handle the stepping? */
-               if (!bp->overflow_handler)
+               if (is_default_overflow_handler(bp))
                        step = 1;
 unlock:
                rcu_read_unlock();
@@ -712,7 +712,7 @@ static int watchpoint_handler(unsigned long addr, unsigned 
int esr,
                perf_bp_event(wp, regs);
 
                /* Do we need to handle the stepping? */
-               if (!wp->overflow_handler)
+               if (is_default_overflow_handler(wp))
                        step = 1;
 
 unlock:
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 15588d4..4065ca2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -838,6 +838,12 @@ extern void perf_event_output(struct perf_event *event,
                                struct perf_sample_data *data,
                                struct pt_regs *regs);
 
+static inline bool
+is_default_overflow_handler(struct perf_event *event)
+{
+       return (event->overflow_handler == perf_event_output);
+}
+
 extern void
 perf_event_header__init_id(struct perf_event_header *header,
                           struct perf_sample_data *data,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cb47da3..3bd4b2b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6502,10 +6502,7 @@ static int __perf_event_overflow(struct perf_event 
*event,
                irq_work_queue(&event->pending);
        }
 
-       if (event->overflow_handler)
-               event->overflow_handler(event, data, regs);
-       else
-               perf_event_output(event, data, regs);
+       event->overflow_handler(event, data, regs);
 
        if (*perf_event_fasync(event) && event->pending_kill) {
                event->pending_wakeup = 1;
@@ -8017,8 +8014,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
                context = parent_event->overflow_handler_context;
        }
 
-       event->overflow_handler = overflow_handler;
-       event->overflow_handler_context = context;
+       if (overflow_handler) {
+               event->overflow_handler = overflow_handler;
+               event->overflow_handler_context = context;
+       } else {
+               event->overflow_handler = perf_event_output;
+               event->overflow_handler_context = NULL;
+       }
 
        perf_event__state_init(event);
 
-- 
1.8.3.4

Reply via email to