Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752175AbcCGDwH (ORCPT ); Sun, 6 Mar 2016 22:52:07 -0500 Received: from szxga02-in.huawei.com ([119.145.14.65]:20546 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752063AbcCGDvu (ORCPT ); Sun, 6 Mar 2016 22:51:50 -0500 From: Wang Nan To: , CC: , Wang Nan , He Kuang , Alexei Starovoitov , "Arnaldo Carvalho de Melo" , Brendan Gregg , "Jiri Olsa" , Masami Hiramatsu , Namhyung Kim , Zefan Li , Subject: [RESEND PATCH 5/5] perf core: Reduce perf event output overhead by new overflow handler Date: Mon, 7 Mar 2016 03:50:19 +0000 Message-ID: <1457322619-170254-6-git-send-email-wangnan0@huawei.com> X-Mailer: git-send-email 1.8.3.4 In-Reply-To: <1457322619-170254-1-git-send-email-wangnan0@huawei.com> References: <1457322619-170254-1-git-send-email-wangnan0@huawei.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.107.193.248] X-CFilter-Loop: Reflected X-Mirapoint-Virus-RAPID-Raw: score=unknown(0), refid=str=0001.0A090203.56DCFA8E.0020,ss=1,re=0.000,recu=0.000,reip=0.000,cl=1,cld=1,fgs=0, ip=0.0.0.0, so=2013-06-18 04:22:30, dmn=2013-03-21 17:37:32 X-Mirapoint-Loop-Id: cdcde80297ed78bdfc2e073f969c602e Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5432 Lines: 161 By creating onward and backward specific overflow handlers and setting them according to event's backward setting, normal sampling events don't need checking backward setting of an event any more. This is the last patch of backward writing patchset. After this patch, there's no extra overhead introduced to the fast path of sampling output. Signed-off-by: Wang Nan Cc: He Kuang Cc: Alexei Starovoitov Cc: Arnaldo Carvalho de Melo Cc: Brendan Gregg Cc: Ingo Molnar Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama@163.com --- include/linux/perf_event.h | 17 +++++++++++++++-- kernel/events/core.c | 41 ++++++++++++++++++++++++++++++++++++----- kernel/events/ring_buffer.c | 12 ++++++++++++ 3 files changed, 63 insertions(+), 7 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 88e2b47..bbe913f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -829,9 +829,15 @@ extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); +extern void perf_event_output_onward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); +extern void perf_event_output_backward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs); extern void perf_event_output(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs); + struct perf_sample_data *data, + struct pt_regs *regs); extern void perf_event_header__init_id(struct perf_event_header *header, @@ -1038,6 +1044,13 @@ static inline bool is_write_backward(struct perf_event *event) extern int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size); +extern int perf_output_begin_onward(struct perf_output_handle *handle, + struct perf_event *event, + unsigned int size); +extern int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_event *event, + unsigned int size); + extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); diff --git a/kernel/events/core.c b/kernel/events/core.c index 513b556..969c43e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5606,9 +5606,13 @@ void perf_prepare_sample(struct perf_event_header *header, } } -void perf_event_output(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) +static void __always_inline +__perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs, + int (*output_begin)(struct perf_output_handle *, + struct perf_event *, + unsigned int)) { struct perf_output_handle handle; struct perf_event_header header; @@ -5618,7 +5622,7 @@ void perf_event_output(struct perf_event *event, perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size)) + if (output_begin(&handle, event, header.size)) goto exit; perf_output_sample(&handle, &header, data, event); @@ -5629,6 +5633,30 @@ exit: rcu_read_unlock(); } +void +perf_event_output_onward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + __perf_event_output(event, data, regs, perf_output_begin_onward); +} + +void +perf_event_output_backward(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + __perf_event_output(event, data, regs, perf_output_begin_backward); +} + +void +perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + __perf_event_output(event, data, regs, perf_output_begin); +} + /* * read event_id */ @@ -7963,8 +7991,11 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (overflow_handler) { event->overflow_handler = overflow_handler; event->overflow_handler_context = context; + } else if (is_write_backward(event)){ + event->overflow_handler = perf_event_output_backward; + event->overflow_handler_context = NULL; } else { - event->overflow_handler = perf_event_output; + event->overflow_handler = perf_event_output_onward; event->overflow_handler_context = NULL; } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 80b1fa7..7e30e012 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -230,6 +230,18 @@ out: return -ENOSPC; } +int perf_output_begin_onward(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + return __perf_output_begin(handle, event, size, false); +} + +int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + return __perf_output_begin(handle, event, size, true); +} + int perf_output_begin(struct perf_output_handle *handle, struct perf_event *event, unsigned int size) { -- 1.8.3.4